control: Read/write interface to control SMT. Possible
values:
- "on" SMT is enabled
- "off" SMT is disabled
- "forceoff" SMT is force disabled. Cannot be changed.
- "notsupported" SMT is not supported by the CPU
+ "on" SMT is enabled
+ "off" SMT is disabled
+ "forceoff" SMT is force disabled. Cannot be changed.
+ "notsupported" SMT is not supported by the CPU
+ "notimplemented" SMT runtime toggling is not
+ implemented for the architecture
If control status is "forceoff" or "notsupported" writes
are rejected.
of the level of loading on the system.
</p><p>RCU updaters wait for normal grace periods by registering
-RCU callbacks, either directly via <tt>call_rcu()</tt> and
-friends (namely <tt>call_rcu_bh()</tt> and <tt>call_rcu_sched()</tt>),
+RCU callbacks, either directly via <tt>call_rcu()</tt>
or indirectly via <tt>synchronize_rcu()</tt> and friends.
RCU callbacks are represented by <tt>rcu_head</tt> structures,
which are queued on <tt>rcu_data</tt> structures while they are
RCU-preempt Expedited Grace Periods</a></h2>
<p>
+<tt>CONFIG_PREEMPT=y</tt> kernels implement RCU-preempt.
The overall flow of the handling of a given CPU by an RCU-preempt
expedited grace period is shown in the following diagram:
RCU-sched Expedited Grace Periods</a></h2>
<p>
+<tt>CONFIG_PREEMPT=n</tt> kernels implement RCU-sched.
The overall flow of the handling of a given CPU by an RCU-sched
expedited grace period is shown in the following diagram:
<p>
As with RCU-preempt, RCU-sched's
-<tt>synchronize_sched_expedited()</tt> ignores offline and
+<tt>synchronize_rcu_expedited()</tt> ignores offline and
idle CPUs, again because they are in remotely detectable
quiescent states.
However, because the
period is guaranteed to see the effects of all accesses following the end
of that grace period that are within RCU read-side critical sections.
-<p>This guarantee is particularly pervasive for <tt>synchronize_sched()</tt>,
-for which RCU-sched read-side critical sections include any region
+<p>Note well that RCU-sched read-side critical sections include any region
of code for which preemption is disabled.
Given that each individual machine instruction can be thought of as
an extremely small region of preemption-disabled code, one can think of
-<tt>synchronize_sched()</tt> as <tt>smp_mb()</tt> on steroids.
+<tt>synchronize_rcu()</tt> as <tt>smp_mb()</tt> on steroids.
<p>RCU updaters use this guarantee by splitting their updates into
two phases, one of which is executed before the grace period and
up any data structures used by the old NMI handler until execution
of it completes on all other CPUs.
-One way to accomplish this is via synchronize_sched(), perhaps as
+One way to accomplish this is via synchronize_rcu(), perhaps as
follows:
unset_nmi_callback();
- synchronize_sched();
+ synchronize_rcu();
kfree(my_nmi_data);
-This works because synchronize_sched() blocks until all CPUs complete
-any preemption-disabled segments of code that they were executing.
-Since NMI handlers disable preemption, synchronize_sched() is guaranteed
+This works because (as of v4.20) synchronize_rcu() blocks until all
+CPUs complete any preemption-disabled segments of code that they were
+executing.
+Since NMI handlers disable preemption, synchronize_rcu() is guaranteed
not to return until all ongoing NMI handlers exit. It is therefore safe
-to free up the handler's data as soon as synchronize_sched() returns.
+to free up the handler's data as soon as synchronize_rcu() returns.
Important note: for this to work, the architecture in question must
invoke nmi_enter() and nmi_exit() on NMI entry and exit, respectively.
infrastructure -must- respect grace periods, and -must- invoke callbacks
from a known environment in which no locks are held.
-It -is- safe for synchronize_sched() and synchronize_rcu_bh() to return
-immediately on an UP system. It is also safe for synchronize_rcu()
-to return immediately on UP systems, except when running preemptable
-RCU.
+Note that it -is- safe for synchronize_rcu() to return immediately on
+UP systems, including !PREEMPT SMP builds running on UP systems.
Quick Quiz #3: Why can't synchronize_rcu() return immediately on
UP systems running preemptable RCU?
when publicizing a pointer to a structure that can
be traversed by an RCU read-side critical section.
-5. If call_rcu(), or a related primitive such as call_rcu_bh(),
- call_rcu_sched(), or call_srcu() is used, the callback function
- will be called from softirq context. In particular, it cannot
- block.
+5. If call_rcu() or call_srcu() is used, the callback function will
+ be called from softirq context. In particular, it cannot block.
-6. Since synchronize_rcu() can block, it cannot be called from
- any sort of irq context. The same rule applies for
- synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(),
- synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(),
- synchronize_sched_expedite(), and synchronize_srcu_expedited().
+6. Since synchronize_rcu() can block, it cannot be called
+ from any sort of irq context. The same rule applies
+ for synchronize_srcu(), synchronize_rcu_expedited(), and
+ synchronize_srcu_expedited().
The expedited forms of these primitives have the same semantics
as the non-expedited forms, but expediting is both expensive and
of the system, especially to real-time workloads running on
the rest of the system.
-7. If the updater uses call_rcu() or synchronize_rcu(), then the
- corresponding readers must use rcu_read_lock() and
- rcu_read_unlock(). If the updater uses call_rcu_bh() or
- synchronize_rcu_bh(), then the corresponding readers must
- use rcu_read_lock_bh() and rcu_read_unlock_bh(). If the
- updater uses call_rcu_sched() or synchronize_sched(), then
- the corresponding readers must disable preemption, possibly
- by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
- If the updater uses synchronize_srcu() or call_srcu(), then
- the corresponding readers must use srcu_read_lock() and
+7. As of v4.20, a given kernel implements only one RCU flavor,
+ which is RCU-sched for PREEMPT=n and RCU-preempt for PREEMPT=y.
+ If the updater uses call_rcu() or synchronize_rcu(),
+ then the corresponding readers my use rcu_read_lock() and
+ rcu_read_unlock(), rcu_read_lock_bh() and rcu_read_unlock_bh(),
+ or any pair of primitives that disables and re-enables preemption,
+ for example, rcu_read_lock_sched() and rcu_read_unlock_sched().
+ If the updater uses synchronize_srcu() or call_srcu(),
+ then the corresponding readers must use srcu_read_lock() and
srcu_read_unlock(), and with the same srcu_struct. The rules for
the expedited primitives are the same as for their non-expedited
counterparts. Mixing things up will result in confusion and
- broken kernels.
+ broken kernels, and has even resulted in an exploitable security
+ issue.
One exception to this rule: rcu_read_lock() and rcu_read_unlock()
may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
d. Periodically invoke synchronize_rcu(), permitting a limited
number of updates per grace period.
- The same cautions apply to call_rcu_bh(), call_rcu_sched(),
- call_srcu(), and kfree_rcu().
+ The same cautions apply to call_srcu() and kfree_rcu().
Note that although these primitives do take action to avoid memory
exhaustion when any given CPU has too many callbacks, a determined
11. Any lock acquired by an RCU callback must be acquired elsewhere
with softirq disabled, e.g., via spin_lock_irqsave(),
- spin_lock_bh(), etc. Failing to disable irq on a given
+ spin_lock_bh(), etc. Failing to disable softirq on a given
acquisition of that lock will result in deadlock as soon as
the RCU softirq handler happens to run your RCU callback while
interrupting that acquisition's critical section.
must use whatever locking or other synchronization is required
to safely access and/or modify that data structure.
- RCU callbacks are -usually- executed on the same CPU that executed
- the corresponding call_rcu(), call_rcu_bh(), or call_rcu_sched(),
- but are by -no- means guaranteed to be. For example, if a given
- CPU goes offline while having an RCU callback pending, then that
- RCU callback will execute on some surviving CPU. (If this was
- not the case, a self-spawning RCU callback would prevent the
- victim CPU from ever going offline.)
+ Do not assume that RCU callbacks will be executed on the same
+ CPU that executed the corresponding call_rcu() or call_srcu().
+ For example, if a given CPU goes offline while having an RCU
+ callback pending, then that RCU callback will execute on some
+ surviving CPU. (If this was not the case, a self-spawning RCU
+ callback would prevent the victim CPU from ever going offline.)
+ Furthermore, CPUs designated by rcu_nocbs= might well -always-
+ have their RCU callbacks executed on some other CPUs, in fact,
+ for some real-time workloads, this is the whole point of using
+ the rcu_nocbs= kernel boot parameter.
13. Unlike other forms of RCU, it -is- permissible to block in an
SRCU read-side critical section (demarked by srcu_read_lock()
SRCU's expedited primitive (synchronize_srcu_expedited())
never sends IPIs to other CPUs, so it is easier on
- real-time workloads than is synchronize_rcu_expedited(),
- synchronize_rcu_bh_expedited() or synchronize_sched_expedited().
+ real-time workloads than is synchronize_rcu_expedited().
- Note that rcu_dereference() and rcu_assign_pointer() relate to
- SRCU just as they do to other forms of RCU.
+ Note that rcu_assign_pointer() relates to SRCU just as it does to
+ other forms of RCU, but instead of rcu_dereference() you should
+ use srcu_dereference() in order to avoid lockdep splats.
14. The whole point of call_rcu(), synchronize_rcu(), and friends
is to wait until all pre-existing readers have finished before
read-side critical sections. It is the responsibility of the
RCU update-side primitives to deal with this.
+ For SRCU readers, you can use smp_mb__after_srcu_read_unlock()
+ immediately after an srcu_read_unlock() to get a full barrier.
+
16. Use CONFIG_PROVE_LOCKING, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and the
__rcu sparse checks to validate your RCU code. These can help
find problems as follows:
These debugging aids can help you find problems that are
otherwise extremely difficult to spot.
-17. If you register a callback using call_rcu(), call_rcu_bh(),
- call_rcu_sched(), or call_srcu(), and pass in a function defined
- within a loadable module, then it in necessary to wait for
- all pending callbacks to be invoked after the last invocation
- and before unloading that module. Note that it is absolutely
- -not- sufficient to wait for a grace period! The current (say)
- synchronize_rcu() implementation waits only for all previous
- callbacks registered on the CPU that synchronize_rcu() is running
- on, but it is -not- guaranteed to wait for callbacks registered
- on other CPUs.
+17. If you register a callback using call_rcu() or call_srcu(), and
+ pass in a function defined within a loadable module, then it in
+ necessary to wait for all pending callbacks to be invoked after
+ the last invocation and before unloading that module. Note that
+ it is absolutely -not- sufficient to wait for a grace period!
+ The current (say) synchronize_rcu() implementation is -not-
+ guaranteed to wait for callbacks registered on other CPUs.
+ Or even on the current CPU if that CPU recently went offline
+ and came back online.
You instead need to use one of the barrier functions:
o call_rcu() -> rcu_barrier()
- o call_rcu_bh() -> rcu_barrier()
- o call_rcu_sched() -> rcu_barrier()
o call_srcu() -> srcu_barrier()
However, these barrier functions are absolutely -not- guaranteed
o How can I see where RCU is currently used in the Linux kernel?
Search for "rcu_read_lock", "rcu_read_unlock", "call_rcu",
- "rcu_read_lock_bh", "rcu_read_unlock_bh", "call_rcu_bh",
- "srcu_read_lock", "srcu_read_unlock", "synchronize_rcu",
- "synchronize_net", "synchronize_srcu", and the other RCU
- primitives. Or grab one of the cscope databases from:
+ "rcu_read_lock_bh", "rcu_read_unlock_bh", "srcu_read_lock",
+ "srcu_read_unlock", "synchronize_rcu", "synchronize_net",
+ "synchronize_srcu", and the other RCU primitives. Or grab one
+ of the cscope databases from:
http://www.rdrop.com/users/paulmck/RCU/linuxusage/rculocktab.html
In short, rcu_dereference() is -not- optional when you are going to
dereference the resulting pointer.
+
+
+WHICH MEMBER OF THE rcu_dereference() FAMILY SHOULD YOU USE?
+
+First, please avoid using rcu_dereference_raw() and also please avoid
+using rcu_dereference_check() and rcu_dereference_protected() with a
+second argument with a constant value of 1 (or true, for that matter).
+With that caution out of the way, here is some guidance for which
+member of the rcu_dereference() to use in various situations:
+
+1. If the access needs to be within an RCU read-side critical
+ section, use rcu_dereference(). With the new consolidated
+ RCU flavors, an RCU read-side critical section is entered
+ using rcu_read_lock(), anything that disables bottom halves,
+ anything that disables interrupts, or anything that disables
+ preemption.
+
+2. If the access might be within an RCU read-side critical section
+ on the one hand, or protected by (say) my_lock on the other,
+ use rcu_dereference_check(), for example:
+
+ p1 = rcu_dereference_check(p->rcu_protected_pointer,
+ lockdep_is_held(&my_lock));
+
+
+3. If the access might be within an RCU read-side critical section
+ on the one hand, or protected by either my_lock or your_lock on
+ the other, again use rcu_dereference_check(), for example:
+
+ p1 = rcu_dereference_check(p->rcu_protected_pointer,
+ lockdep_is_held(&my_lock) ||
+ lockdep_is_held(&your_lock));
+
+4. If the access is on the update side, so that it is always protected
+ by my_lock, use rcu_dereference_protected():
+
+ p1 = rcu_dereference_protected(p->rcu_protected_pointer,
+ lockdep_is_held(&my_lock));
+
+ This can be extended to handle multiple locks as in #3 above,
+ and both can be extended to check other conditions as well.
+
+5. If the protection is supplied by the caller, and is thus unknown
+ to this code, that is the rare case when rcu_dereference_raw()
+ is appropriate. In addition, rcu_dereference_raw() might be
+ appropriate when the lockdep expression would be excessively
+ complex, except that a better approach in that case might be to
+ take a long hard look at your synchronization design. Still,
+ there are data-locking cases where any one of a very large number
+ of locks or reference counters suffices to protect the pointer,
+ so rcu_dereference_raw() does have its place.
+
+ However, its place is probably quite a bit smaller than one
+ might expect given the number of uses in the current kernel.
+ Ditto for its synonym, rcu_dereference_check( ... , 1), and
+ its close relative, rcu_dereference_protected(... , 1).
+
+
+SPARSE CHECKING OF RCU-PROTECTED POINTERS
+
+The sparse static-analysis tool checks for direct access to RCU-protected
+pointers, which can result in "interesting" bugs due to compiler
+optimizations involving invented loads and perhaps also load tearing.
+For example, suppose someone mistakenly does something like this:
+
+ p = q->rcu_protected_pointer;
+ do_something_with(p->a);
+ do_something_else_with(p->b);
+
+If register pressure is high, the compiler might optimize "p" out
+of existence, transforming the code to something like this:
+
+ do_something_with(q->rcu_protected_pointer->a);
+ do_something_else_with(q->rcu_protected_pointer->b);
+
+This could fatally disappoint your code if q->rcu_protected_pointer
+changed in the meantime. Nor is this a theoretical problem: Exactly
+this sort of bug cost Paul E. McKenney (and several of his innocent
+colleagues) a three-day weekend back in the early 1990s.
+
+Load tearing could of course result in dereferencing a mashup of a pair
+of pointers, which also might fatally disappoint your code.
+
+These problems could have been avoided simply by making the code instead
+read as follows:
+
+ p = rcu_dereference(q->rcu_protected_pointer);
+ do_something_with(p->a);
+ do_something_else_with(p->b);
+
+Unfortunately, these sorts of bugs can be extremely hard to spot during
+review. This is where the sparse tool comes into play, along with the
+"__rcu" marker. If you mark a pointer declaration, whether in a structure
+or as a formal parameter, with "__rcu", which tells sparse to complain if
+this pointer is accessed directly. It will also cause sparse to complain
+if a pointer not marked with "__rcu" is accessed using rcu_dereference()
+and friends. For example, ->rcu_protected_pointer might be declared as
+follows:
+
+ struct foo __rcu *rcu_protected_pointer;
+
+Use of "__rcu" is opt-in. If you choose not to use it, then you should
+ignore the sparse warnings.
2. Execute rcu_barrier().
3. Allow the module to be unloaded.
-There are also rcu_barrier_bh(), rcu_barrier_sched(), and srcu_barrier()
-functions for the other flavors of RCU, and you of course must match
-the flavor of rcu_barrier() with that of call_rcu(). If your module
-uses multiple flavors of call_rcu(), then it must also use multiple
+There is also an srcu_barrier() function for SRCU, and you of course
+must match the flavor of rcu_barrier() with that of call_rcu(). If your
+module uses multiple flavors of call_rcu(), then it must also use multiple
flavors of rcu_barrier() when unloading that module. For example, if
-it uses call_rcu_bh(), call_srcu() on srcu_struct_1, and call_srcu() on
+it uses call_rcu(), call_srcu() on srcu_struct_1, and call_srcu() on
srcu_struct_2(), then the following three lines of code will be required
when unloading:
- 1 rcu_barrier_bh();
+ 1 rcu_barrier();
2 srcu_barrier(&srcu_struct_1);
3 srcu_barrier(&srcu_struct_2);
the timers, and only then invoke rcu_barrier() to wait for any remaining
RCU callbacks to complete.
-Of course, if you module uses call_rcu_bh(), you will need to invoke
-rcu_barrier_bh() before unloading. Similarly, if your module uses
-call_rcu_sched(), you will need to invoke rcu_barrier_sched() before
-unloading. If your module uses call_rcu(), call_rcu_bh(), -and-
-call_rcu_sched(), then you will need to invoke each of rcu_barrier(),
-rcu_barrier_bh(), and rcu_barrier_sched().
+Of course, if you module uses call_rcu(), you will need to invoke
+rcu_barrier() before unloading. Similarly, if your module uses
+call_srcu(), you will need to invoke srcu_barrier() before unloading,
+and on the same srcu_struct structure. If your module uses call_rcu()
+-and- call_srcu(), then you will need to invoke rcu_barrier() -and-
+srcu_barrier().
Implementing rcu_barrier()
ensures that all the calls to rcu_barrier_func() will have completed
before on_each_cpu() returns. Line 9 then waits for the completion.
-This code was rewritten in 2008 to support rcu_barrier_bh() and
-rcu_barrier_sched() in addition to the original rcu_barrier().
+This code was rewritten in 2008 and several times thereafter, but this
+still gives the general idea.
The rcu_barrier_func() runs on each CPU, where it invokes call_rcu()
to post an RCU callback, as follows:
rcu_assign_pointer()
- +--------+
+ +--------+
+---------------------->| reader |---------+
| +--------+ |
| | |
| | | rcu_read_lock()
| | | rcu_read_unlock()
| rcu_dereference() | |
- +---------+ | |
- | updater |<---------------------+ |
- +---------+ V
+ +---------+ | |
+ | updater |<----------------+ |
+ +---------+ V
| +-----------+
+----------------------------------->| reclaimer |
- +-----------+
+ +-----------+
Defer:
synchronize_rcu() & call_rcu()
in the "bleeding edge" mini2440 support kernel at
http://repo.or.cz/w/linux-2.6/mini2440.git
+ mitigations=
+ [X86,PPC,S390] Control optional mitigations for CPU
+ vulnerabilities. This is a set of curated,
+ arch-independent options, each of which is an
+ aggregation of existing arch-specific options.
+
+ off
+ Disable all optional CPU mitigations. This
+ improves system performance, but it may also
+ expose users to several CPU vulnerabilities.
+ Equivalent to: nopti [X86,PPC]
+ nospectre_v1 [PPC]
+ nobp=0 [S390]
+ nospectre_v2 [X86,PPC,S390]
+ spectre_v2_user=off [X86]
+ spec_store_bypass_disable=off [X86,PPC]
+ l1tf=off [X86]
+
+ auto (default)
+ Mitigate all CPU vulnerabilities, but leave SMT
+ enabled, even if it's vulnerable. This is for
+ users who don't want to be surprised by SMT
+ getting disabled across kernel upgrades, or who
+ have other ways of avoiding SMT-based attacks.
+ Equivalent to: (default behavior)
+
+ auto,nosmt
+ Mitigate all CPU vulnerabilities, disabling SMT
+ if needed. This is for users who always want to
+ be fully mitigated, even if it means losing SMT.
+ Equivalent to: l1tf=flush,nosmt [X86]
+
mminit_loglevel=
[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
parameter allows control of the logging verbosity for
see CONFIG_RAS_CEC help text.
rcu_nocbs= [KNL]
- The argument is a cpu list, as described above.
+ The argument is a cpu list, as described above,
+ except that the string "all" can be used to
+ specify every CPU on the system.
In kernels built with CONFIG_RCU_NOCB_CPU=y, set
the specified list of CPUs to be no-callback CPUs.
smp_mb__{before,after}_atomic()
+TYPES (signed vs unsigned)
+-----
+
+While atomic_t, atomic_long_t and atomic64_t use int, long and s64
+respectively (for hysterical raisins), the kernel uses -fno-strict-overflow
+(which implies -fwrapv) and defines signed overflow to behave like
+2s-complement.
+
+Therefore, an explicitly unsigned variant of the atomic ops is strictly
+unnecessary and we can simply cast, there is no UB.
+
+There was a bug in UBSAN prior to GCC-8 that would generate UB warnings for
+signed types.
+
+With this we also conform to the C/C++ _Atomic behaviour and things like
+P1236R1.
+
SEMANTICS
---------
translations for software managed TLB configurations.
The sparc64 port currently does this.
-6) ``void tlb_migrate_finish(struct mm_struct *mm)``
-
- This interface is called at the end of an explicit
- process migration. This interface provides a hook
- to allow a platform to update TLB or context-specific
- information for the address space.
-
- The ia64 sn2 platform is one example of a platform
- that uses this interface.
-
Next, we have the cache flushing interfaces. In general, when Linux
is changing an existing virtual-->physical mapping to a new value,
the sequence will be in one of the following forms::
Optional properties:
- phy-handle: See ethernet.txt file in the same directory.
If absent, davinci_emac driver defaults to 100/FULL.
+- nvmem-cells: phandle, reference to an nvmem node for the MAC address
+- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used
- ti,davinci-rmii-en: 1 byte, 1 means use RMII
- ti,davinci-no-bd-ram: boolean, does EMAC have BD RAM?
the boot program; should be used in cases where the MAC address assigned to
the device by the boot program is different from the "local-mac-address"
property;
-- nvmem-cells: phandle, reference to an nvmem node for the MAC address;
-- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used;
- max-speed: number, specifies maximum speed in Mbit/s supported by the device;
- max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than
the maximum frame size (there's contradiction in the Devicetree
Specification).
- phy-mode: string, operation mode of the PHY interface. This is now a de-facto
standard property; supported values are:
- * "internal"
+ * "internal" (Internal means there is not a standard bus between the MAC and
+ the PHY, something proprietary is being used to embed the PHY in the MAC.)
* "mii"
* "gmii"
* "sgmii"
Optional elements: 'tsu_clk'
- clocks: Phandles to input clocks.
+Optional properties:
+- nvmem-cells: phandle, reference to an nvmem node for the MAC address
+- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used
+
Optional properties for PHY child node:
- reset-gpios : Should specify the gpio for phy reset
- magic-packet : If present, indicates that the hardware supports waking
then the interface is considered to be idle, and the kernel may
autosuspend the device.
-Drivers need not be concerned about balancing changes to the usage
-counter; the USB core will undo any remaining "get"s when a driver
-is unbound from its interface. As a corollary, drivers must not call
-any of the ``usb_autopm_*`` functions after their ``disconnect``
-routine has returned.
+Drivers must be careful to balance their overall changes to the usage
+counter. Unbalanced "get"s will remain in effect when a driver is
+unbound from its interface, preventing the device from going into
+runtime suspend should the interface be bound to a driver again. On
+the other hand, drivers are allowed to achieve this balance by calling
+the ``usb_autopm_*`` functions even after their ``disconnect`` routine
+has returned -- say from within a work-queue routine -- provided they
+retain an active reference to the interface (via ``usb_get_intf`` and
+``usb_put_intf``).
Drivers using the async routines are responsible for their own
synchronization and mutual exclusion.
^^^^^^^^^^^^
The Kprobe-optimizer doesn't insert the jump instruction immediately;
-rather, it calls synchronize_sched() for safety first, because it's
+rather, it calls synchronize_rcu() for safety first, because it's
possible for a CPU to be interrupted in the middle of executing the
-optimized region [3]_. As you know, synchronize_sched() can ensure
-that all interruptions that were active when synchronize_sched()
+optimized region [3]_. As you know, synchronize_rcu() can ensure
+that all interruptions that were active when synchronize_rcu()
was called are done, but only if CONFIG_PREEMPT=n. So, this version
of kprobe optimization supports only kernels with CONFIG_PREEMPT=n [4]_.
- .. row 78
- - ``KEY_SCREEN``
+ - ``KEY_ASPECT_RATIO``
- Select screen aspect ratio
- .. row 79
- - ``KEY_ZOOM``
+ - ``KEY_FULL_SCREEN``
- Put device into zoom/full screen mode
CONFIG_DECNET_ROUTER (to be able to add/delete routes)
CONFIG_NETFILTER (will be required for the DECnet routing daemon)
- CONFIG_DECNET_ROUTE_FWMARK is optional
-
Don't turn on SIOCGIFCONF support for DECnet unless you are really sure
that you need it, in general you won't and it can cause ifconfig to
malfunction.
minimum RTT when it is moved to a longer path (e.g., due to traffic
engineering). A longer window makes the filter more resistant to RTT
inflations such as transient congestion. The unit is seconds.
+ Possible values: 0 - 86400 (1 day)
Default: 300
tcp_moderate_rcvbuf - BOOLEAN
Default value is 0.
xfrm4_gc_thresh - INTEGER
+ (Obsolete since linux-4.14)
The threshold at which we will start garbage collecting for IPv4
destination cache entries. At twice this value the system will
refuse new allocations.
Default: 0
xfrm6_gc_thresh - INTEGER
+ (Obsolete since linux-4.14)
The threshold at which we will start garbage collecting for IPv6
destination cache entries. At twice this value the system will
refuse new allocations.
will reply and ask what should be done.
Q: I made changes to only a few patches in a patch series should I resend only those changed?
---------------------------------------------------------------------------------------------
+---------------------------------------------------------------------------------------------
A: No, please resend the entire patch series and make sure you do number your
patches such that it is clear this is the latest and greatest set of patches
that can be applied.
(*) Check call still alive.
- u32 rxrpc_kernel_check_life(struct socket *sock,
- struct rxrpc_call *call);
+ bool rxrpc_kernel_check_life(struct socket *sock,
+ struct rxrpc_call *call,
+ u32 *_life);
void rxrpc_kernel_probe_life(struct socket *sock,
struct rxrpc_call *call);
- The first function returns a number that is updated when ACKs are received
- from the peer (notably including PING RESPONSE ACKs which we can elicit by
- sending PING ACKs to see if the call still exists on the server). The
- caller should compare the numbers of two calls to see if the call is still
- alive after waiting for a suitable interval.
+ The first function passes back in *_life a number that is updated when
+ ACKs are received from the peer (notably including PING RESPONSE ACKs
+ which we can elicit by sending PING ACKs to see if the call still exists
+ on the server). The caller should compare the numbers of two calls to see
+ if the call is still alive after waiting for a suitable interval. It also
+ returns true as long as the call hasn't yet reached the completed state.
This allows the caller to work out if the server is still contactable and
if the call is still alive on the server while waiting for the server to
increase the success rate of future high-order allocations such as SLUB
allocations, THP and hugetlbfs pages.
-To make it sensible with respect to the watermark_scale_factor parameter,
-the unit is in fractions of 10,000. The default value of 15,000 means
-that up to 150% of the high watermark will be reclaimed in the event of
-a pageblock being mixed due to fragmentation. The level of reclaim is
-determined by the number of fragmentation events that occurred in the
-recent past. If this value is smaller than a pageblock then a pageblocks
-worth of pages will be reclaimed (e.g. 2MB on 64-bit x86). A boost factor
-of 0 will disable the feature.
+To make it sensible with respect to the watermark_scale_factor
+parameter, the unit is in fractions of 10,000. The default value of
+15,000 on !DISCONTIGMEM configurations means that up to 150% of the high
+watermark will be reclaimed in the event of a pageblock being mixed due
+to fragmentation. The level of reclaim is determined by the number of
+fragmentation events that occurred in the recent past. If this value is
+smaller than a pageblock then a pageblocks worth of pages will be reclaimed
+(e.g. 2MB on 64-bit x86). A boost factor of 0 will disable the feature.
=============================================================
이 타입의 오퍼레이션은 단방향의 투과성 배리어처럼 동작합니다. ACQUIRE
오퍼레이션 뒤의 모든 메모리 오퍼레이션들이 ACQUIRE 오퍼레이션 후에
일어난 것으로 시스템의 나머지 컴포넌트들에 보이게 될 것이 보장됩니다.
- LOCK 오퍼레이션과 smp_load_acquire(), smp_cond_acquire() 오퍼레이션도
- ACQUIRE 오퍼레이션에 포함됩니다. smp_cond_acquire() 오퍼레이션은 컨트롤
- 의존성과 smp_rmb() 를 사용해서 ACQUIRE 의 의미적 요구사항(semantic)을
- 충족시킵니다.
+ LOCK 오퍼레이션과 smp_load_acquire(), smp_cond_load_acquire() 오퍼레이션도
+ ACQUIRE 오퍼레이션에 포함됩니다.
ACQUIRE 오퍼레이션 앞의 메모리 오퍼레이션들은 ACQUIRE 오퍼레이션 완료 후에
수행된 것처럼 보일 수 있습니다.
event_indicated = 1;
wake_up_process(event_daemon);
-wake_up() 류에 의해 쓰기 메모리 배리어가 내포됩니다. 만약 그것들이 뭔가를
-깨운다면요. 이 배리어는 태스크 상태가 지워지기 전에 수행되므로, 이벤트를
-알리기 위한 STORE 와 태스크 상태를 TASK_RUNNING 으로 설정하는 STORE 사이에
-위치하게 됩니다.
+wake_up() 이 무언가를 깨우게 되면, 이 함수는 범용 메모리 배리어를 수행합니다.
+이 함수가 아무것도 깨우지 않는다면 메모리 배리어는 수행될 수도, 수행되지 않을
+수도 있습니다; 이 경우에 메모리 배리어를 수행할 거라 오해해선 안됩니다. 이
+배리어는 태스크 상태가 접근되기 전에 수행되는데, 자세히 말하면 이 이벤트를
+알리기 위한 STORE 와 TASK_RUNNING 으로 상태를 쓰는 STORE 사이에 수행됩니다:
- CPU 1 CPU 2
+ CPU 1 (Sleeper) CPU 2 (Waker)
=============================== ===============================
set_current_state(); STORE event_indicated
smp_store_mb(); wake_up();
- STORE current->state <쓰기 배리어>
- <범용 배리어> STORE current->state
- LOAD event_indicated
+ STORE current->state ...
+ <범용 배리어> <범용 배리어>
+ LOAD event_indicated if ((LOAD task->state) & TASK_NORMAL)
+ STORE task->state
-한번더 말합니다만, 이 쓰기 메모리 배리어는 이 코드가 정말로 뭔가를 깨울 때에만
-실행됩니다. 이걸 설명하기 위해, X 와 Y 는 모두 0 으로 초기화 되어 있다는 가정
-하에 아래의 이벤트 시퀀스를 생각해 봅시다:
+여기서 "task" 는 깨어나지는 쓰레드이고 CPU 1 의 "current" 와 같습니다.
+
+반복하지만, wake_up() 이 무언가를 정말 깨운다면 범용 메모리 배리어가 수행될
+것이 보장되지만, 그렇지 않다면 그런 보장이 없습니다. 이걸 이해하기 위해, X 와
+Y 는 모두 0 으로 초기화 되어 있다는 가정 하에 아래의 이벤트 시퀀스를 생각해
+봅시다:
CPU 1 CPU 2
=============================== ===============================
- X = 1; STORE event_indicated
+ X = 1; Y = 1;
smp_mb(); wake_up();
- Y = 1; wait_event(wq, Y == 1);
- wake_up(); load from Y sees 1, no memory barrier
- load from X might see 0
+ LOAD Y LOAD X
+
+정말로 깨우기가 행해졌다면, 두 로드 중 (최소한) 하나는 1 을 보게 됩니다.
+반면에, 실제 깨우기가 행해지지 않았다면, 두 로드 모두 0을 볼 수도 있습니다.
-위 예제에서의 경우와 달리 깨우기가 정말로 행해졌다면, CPU 2 의 X 로드는 1 을
-본다고 보장될 수 있을 겁니다.
+wake_up_process() 는 항상 범용 메모리 배리어를 수행합니다. 이 배리어 역시
+태스크 상태가 접근되기 전에 수행됩니다. 특히, 앞의 예제 코드에서 wake_up() 이
+wake_up_process() 로 대체된다면 두 로드 중 하나는 1을 볼 것이 보장됩니다.
사용 가능한 깨우기류 함수들로 다음과 같은 것들이 있습니다:
wake_up_poll();
wake_up_process();
+메모리 순서규칙 관점에서, 이 함수들은 모두 wake_up() 과 같거나 보다 강한 순서
+보장을 제공합니다.
[!] 잠재우는 코드와 깨우는 코드에 내포되는 메모리 배리어들은 깨우기 전에
이루어진 스토어를 잠재우는 코드가 set_current_state() 를 호출한 후에 행하는
4.8 KVM_GET_DIRTY_LOG (vm ioctl)
Capability: basic
-Architectures: x86
+Architectures: all
Type: vm ioctl
Parameters: struct kvm_dirty_log (in/out)
Returns: 0 on success, -1 on error
4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl)
Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
-Architectures: x86
+Architectures: x86, arm, arm64, mips
Type: vm ioctl
Parameters: struct kvm_dirty_log (in)
Returns: 0 on success, -1 on error
the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap
field. Bit 0 of the bitmap corresponds to page "first_page" in the
memory slot, and num_pages is the size in bits of the input bitmap.
-Both first_page and num_pages must be a multiple of 64. For each bit
-that is set in the input bitmap, the corresponding page is marked "clean"
+first_page must be a multiple of 64; num_pages must also be a multiple of
+64 unless first_page + num_pages is the size of the memory slot. For each
+bit that is set in the input bitmap, the corresponding page is marked "clean"
in KVM's dirty bitmap, and dirty tracking is re-enabled for that page
(for example via write-protection, or by clearing the dirty bit in
a page table entry).
7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
-Architectures: all
+Architectures: x86, arm, arm64, mips
Parameters: args[0] whether feature should be enabled or not
With this capability enabled, KVM_GET_DIRTY_LOG will not automatically
BROADCOM BMIPS MIPS ARCHITECTURE
M: Kevin Cernekee <cernekee@gmail.com>
M: Florian Fainelli <f.fainelli@gmail.com>
+L: bcm-kernel-feedback-list@broadcom.com
L: linux-mips@vger.kernel.org
T: git git://github.com/broadcom/stblinux.git
S: Maintained
F: drivers/media/radio/radio-gemtek*
GENERIC GPIO I2C DRIVER
-M: Haavard Skinnemoen <hskinnemoen@gmail.com>
+M: Wolfram Sang <wsa+renesas@sang-engineering.com>
S: Supported
F: drivers/i2c/busses/i2c-gpio.c
F: include/linux/platform_data/i2c-gpio.h
F: Documentation/driver-api/i3c
F: drivers/i3c/
F: include/linux/i3c/
-F: include/dt-bindings/i3c/
I3C DRIVER FOR SYNOPSYS DESIGNWARE
M: Vitor Soares <vitor.soares@synopsys.com>
LED SUBSYSTEM
M: Jacek Anaszewski <jacek.anaszewski@gmail.com>
M: Pavel Machek <pavel@ucw.cz>
+R: Dan Murphy <dmurphy@ti.com>
L: linux-leds@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git
S: Maintained
L: linux-kernel@vger.kernel.org
L: linux-arch@vger.kernel.org
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
F: tools/memory-model/
F: Documentation/atomic_bitops.txt
F: Documentation/atomic_t.txt
F: include/linux/rwlock*.h
F: include/linux/mutex*.h
F: include/linux/rwsem*.h
-F: arch/*/include/asm/rwsem.h
F: include/linux/seqlock.h
F: lib/locking*.[ch]
F: kernel/locking/
F: Documentation/devicetree/bindings/mfd/atmel-usart.txt
MICROCHIP KSZ SERIES ETHERNET SWITCH DRIVER
-M: Woojung Huh <Woojung.Huh@microchip.com>
+M: Woojung Huh <woojung.huh@microchip.com>
M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
L: netdev@vger.kernel.org
S: Maintained
F: arch/*/include/asm/perf_event.h
F: arch/*/kernel/perf_callchain.c
F: arch/*/events/*
+F: arch/*/events/*/*
F: tools/perf/
PERSONALITY HANDLING
R: Steven Rostedt <rostedt@goodmis.org>
R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
R: Lai Jiangshan <jiangshanlai@gmail.com>
-L: linux-kernel@vger.kernel.org
+L: rcu@vger.kernel.org
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
F: tools/testing/selftests/rcutorture
RDC R-321X SoC
R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
R: Lai Jiangshan <jiangshanlai@gmail.com>
R: Joel Fernandes <joel@joelfernandes.org>
-L: linux-kernel@vger.kernel.org
+L: rcu@vger.kernel.org
W: http://www.rdrop.com/users/paulmck/RCU/
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
F: Documentation/RCU/
X: Documentation/RCU/torture.txt
F: include/linux/rcu*
M: Josh Triplett <josh@joshtriplett.org>
R: Steven Rostedt <rostedt@goodmis.org>
R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
-L: linux-kernel@vger.kernel.org
+L: rcu@vger.kernel.org
W: http://www.rdrop.com/users/paulmck/RCU/
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
F: include/linux/srcu*.h
F: kernel/rcu/srcu*.c
M: Josh Triplett <josh@joshtriplett.org>
L: linux-kernel@vger.kernel.org
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
F: Documentation/RCU/torture.txt
F: kernel/torture.c
F: kernel/rcu/rcutorture.c
VERSION = 5
PATCHLEVEL = 1
SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION =
NAME = Shy Crocodile
# *DOCUMENTATION*
KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation)
KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow)
KBUILD_CFLAGS += $(call cc-disable-warning, int-in-bool-context)
+KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
KBUILD_CFLAGS += -Os
KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
-KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
# Quiet clang warning: comparison of unsigned expression < 0 is always false
KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
config HAVE_RCU_TABLE_FREE
bool
-config HAVE_RCU_TABLE_INVALIDATE
+config HAVE_RCU_TABLE_NO_INVALIDATE
+ bool
+
+config HAVE_MMU_GATHER_PAGE_SIZE
+ bool
+
+config HAVE_MMU_GATHER_NO_GATHER
bool
config ARCH_HAVE_NMI_SAFE_CMPXCHG
config ARCH_USE_MEMREMAP_PROT
bool
+config LOCK_EVENT_COUNTS
+ bool "Locking event counts collection"
+ depends on DEBUG_FS
+ ---help---
+ Enable light-weight counting of various locking related events
+ in the system with minimal performance impact. This reduces
+ the chance of application behavior change because of timing
+ differences. The counts are reported via debugfs.
+
source "kernel/gcov/Kconfig"
source "scripts/gcc-plugins/Kconfig"
select ODD_RT_SIGACTION
select OLD_SIGSUSPEND
select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
+ select MMU_GATHER_NO_RANGE
help
The Alpha is a 64-bit general-purpose processor designed and
marketed by the Digital Equipment Corporation of blessed memory,
bool
default y
-config RWSEM_GENERIC_SPINLOCK
- bool
-
-config RWSEM_XCHGADD_ALGORITHM
- bool
- default y
-
config ARCH_HAS_ILOG2_U32
bool
default n
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ALPHA_RWSEM_H
-#define _ALPHA_RWSEM_H
-
-/*
- * Written by Ivan Kokshaysky <ink@jurassic.park.msu.ru>, 2001.
- * Based on asm-alpha/semaphore.h and asm-i386/rwsem.h
- */
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-
-#include <linux/compiler.h>
-
-#define RWSEM_UNLOCKED_VALUE 0x0000000000000000L
-#define RWSEM_ACTIVE_BIAS 0x0000000000000001L
-#define RWSEM_ACTIVE_MASK 0x00000000ffffffffL
-#define RWSEM_WAITING_BIAS (-0x0000000100000000L)
-#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-static inline int ___down_read(struct rw_semaphore *sem)
-{
- long oldcount;
-#ifndef CONFIG_SMP
- oldcount = sem->count.counter;
- sem->count.counter += RWSEM_ACTIVE_READ_BIAS;
-#else
- long temp;
- __asm__ __volatile__(
- "1: ldq_l %0,%1\n"
- " addq %0,%3,%2\n"
- " stq_c %2,%1\n"
- " beq %2,2f\n"
- " mb\n"
- ".subsection 2\n"
- "2: br 1b\n"
- ".previous"
- :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
- :"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory");
-#endif
- return (oldcount < 0);
-}
-
-static inline void __down_read(struct rw_semaphore *sem)
-{
- if (unlikely(___down_read(sem)))
- rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
- if (unlikely(___down_read(sem)))
- if (IS_ERR(rwsem_down_read_failed_killable(sem)))
- return -EINTR;
-
- return 0;
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
- long old, new, res;
-
- res = atomic_long_read(&sem->count);
- do {
- new = res + RWSEM_ACTIVE_READ_BIAS;
- if (new <= 0)
- break;
- old = res;
- res = atomic_long_cmpxchg(&sem->count, old, new);
- } while (res != old);
- return res >= 0 ? 1 : 0;
-}
-
-static inline long ___down_write(struct rw_semaphore *sem)
-{
- long oldcount;
-#ifndef CONFIG_SMP
- oldcount = sem->count.counter;
- sem->count.counter += RWSEM_ACTIVE_WRITE_BIAS;
-#else
- long temp;
- __asm__ __volatile__(
- "1: ldq_l %0,%1\n"
- " addq %0,%3,%2\n"
- " stq_c %2,%1\n"
- " beq %2,2f\n"
- " mb\n"
- ".subsection 2\n"
- "2: br 1b\n"
- ".previous"
- :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
- :"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory");
-#endif
- return oldcount;
-}
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
- if (unlikely(___down_write(sem)))
- rwsem_down_write_failed(sem);
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
- if (unlikely(___down_write(sem))) {
- if (IS_ERR(rwsem_down_write_failed_killable(sem)))
- return -EINTR;
- }
-
- return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
- long ret = atomic_long_cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
- RWSEM_ACTIVE_WRITE_BIAS);
- if (ret == RWSEM_UNLOCKED_VALUE)
- return 1;
- return 0;
-}
-
-static inline void __up_read(struct rw_semaphore *sem)
-{
- long oldcount;
-#ifndef CONFIG_SMP
- oldcount = sem->count.counter;
- sem->count.counter -= RWSEM_ACTIVE_READ_BIAS;
-#else
- long temp;
- __asm__ __volatile__(
- " mb\n"
- "1: ldq_l %0,%1\n"
- " subq %0,%3,%2\n"
- " stq_c %2,%1\n"
- " beq %2,2f\n"
- ".subsection 2\n"
- "2: br 1b\n"
- ".previous"
- :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
- :"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory");
-#endif
- if (unlikely(oldcount < 0))
- if ((int)oldcount - RWSEM_ACTIVE_READ_BIAS == 0)
- rwsem_wake(sem);
-}
-
-static inline void __up_write(struct rw_semaphore *sem)
-{
- long count;
-#ifndef CONFIG_SMP
- sem->count.counter -= RWSEM_ACTIVE_WRITE_BIAS;
- count = sem->count.counter;
-#else
- long temp;
- __asm__ __volatile__(
- " mb\n"
- "1: ldq_l %0,%1\n"
- " subq %0,%3,%2\n"
- " stq_c %2,%1\n"
- " beq %2,2f\n"
- " subq %0,%3,%0\n"
- ".subsection 2\n"
- "2: br 1b\n"
- ".previous"
- :"=&r" (count), "=m" (sem->count), "=&r" (temp)
- :"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory");
-#endif
- if (unlikely(count))
- if ((int)count == 0)
- rwsem_wake(sem);
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
- long oldcount;
-#ifndef CONFIG_SMP
- oldcount = sem->count.counter;
- sem->count.counter -= RWSEM_WAITING_BIAS;
-#else
- long temp;
- __asm__ __volatile__(
- "1: ldq_l %0,%1\n"
- " addq %0,%3,%2\n"
- " stq_c %2,%1\n"
- " beq %2,2f\n"
- " mb\n"
- ".subsection 2\n"
- "2: br 1b\n"
- ".previous"
- :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
- :"Ir" (-RWSEM_WAITING_BIAS), "m" (sem->count) : "memory");
-#endif
- if (unlikely(oldcount < 0))
- rwsem_downgrade_wake(sem);
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ALPHA_RWSEM_H */
#ifndef _ALPHA_TLB_H
#define _ALPHA_TLB_H
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, addr) do { } while (0)
-
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
#include <asm-generic/tlb.h>
#define __pte_free_tlb(tlb, pte, address) pte_free((tlb)->mm, pte)
532 common getppid sys_getppid
# all other architectures have common numbers for new syscall, alpha
# is the exception.
+534 common pidfd_send_signal sys_pidfd_send_signal
+535 common io_uring_setup sys_io_uring_setup
+536 common io_uring_enter sys_io_uring_enter
+537 common io_uring_register sys_io_uring_register
config GENERIC_CSUM
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
config ARCH_DISCONTIGMEM_ENABLE
def_bool n
model = "snps,hsdk";
compatible = "snps,hsdk";
- #address-cells = <1>;
- #size-cells = <1>;
+ #address-cells = <2>;
+ #size-cells = <2>;
chosen {
bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
#size-cells = <1>;
interrupt-parent = <&idu_intc>;
- ranges = <0x00000000 0xf0000000 0x10000000>;
+ ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
cgu_rst: reset-controller@8a0 {
compatible = "snps,hsdk-reset";
};
memory@80000000 {
- #address-cells = <1>;
- #size-cells = <1>;
+ #address-cells = <2>;
+ #size-cells = <2>;
device_type = "memory";
- reg = <0x80000000 0x40000000>; /* 1 GiB */
+ reg = <0x0 0x80000000 0x0 0x40000000>; /* 1 GB lowmem */
+ /* 0x1 0x00000000 0x0 0x40000000>; 1 GB highmem */
};
};
#ifndef _ASM_ARC_TLB_H
#define _ASM_ARC_TLB_H
-#define tlb_flush(tlb) \
-do { \
- if (tlb->fullmm) \
- flush_tlb_mm((tlb)->mm); \
-} while (0)
-
-/*
- * This pair is called at time of munmap/exit to flush cache and TLB entries
- * for mappings being torn down.
- * 1) cache-flush part -implemented via tlb_start_vma( ) for VIPT aliasing D$
- * 2) tlb-flush part - implemted via tlb_end_vma( ) flushes the TLB range
- *
- * Note, read http://lkml.org/lkml/2004/1/15/6
- */
-#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
-#define tlb_start_vma(tlb, vma)
-#else
-#define tlb_start_vma(tlb, vma) \
-do { \
- if (!tlb->fullmm) \
- flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-} while(0)
-#endif
-
-#define tlb_end_vma(tlb, vma) \
-do { \
- if (!tlb->fullmm) \
- flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, ptep, address)
-
#include <linux/pagemap.h>
#include <asm-generic/tlb.h>
#else
-.macro PREALLOC_INSTR
+.macro PREALLOC_INSTR reg, off
.endm
-.macro PREFETCHW_INSTR
+.macro PREFETCHW_INSTR reg, off
.endm
#endif
}
READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
- if (cbcr.c)
+ if (cbcr.c) {
ioc_exists = 1;
- else
+
+ /*
+ * As for today we don't support both IOC and ZONE_HIGHMEM enabled
+ * simultaneously. This happens because as of today IOC aperture covers
+ * only ZONE_NORMAL (low mem) and any dma transactions outside this
+ * region won't be HW coherent.
+ * If we want to use both IOC and ZONE_HIGHMEM we can use
+ * bounce_buffer to handle dma transactions to HIGHMEM.
+ * Also it is possible to modify dma_direct cache ops or increase IOC
+ * aperture size if we are planning to use HIGHMEM without PAE.
+ */
+ if (IS_ENABLED(CONFIG_HIGHMEM) || is_pae40_enabled())
+ ioc_enable = 0;
+ } else {
ioc_enable = 0;
+ }
/* HS 2.0 didn't have AUX_VOL */
if (cpuinfo_arc700[cpu].core.family > 0x51) {
if (!ioc_enable)
return;
- /*
- * As for today we don't support both IOC and ZONE_HIGHMEM enabled
- * simultaneously. This happens because as of today IOC aperture covers
- * only ZONE_NORMAL (low mem) and any dma transactions outside this
- * region won't be HW coherent.
- * If we want to use both IOC and ZONE_HIGHMEM we can use
- * bounce_buffer to handle dma transactions to HIGHMEM.
- * Also it is possible to modify dma_direct cache ops or increase IOC
- * aperture size if we are planning to use HIGHMEM without PAE.
- */
- if (IS_ENABLED(CONFIG_HIGHMEM))
- panic("IOC and HIGHMEM can't be used simultaneously");
-
/* Flush + invalidate + disable L1 dcache */
__dc_disable();
select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
select HAVE_EXIT_THREAD
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
- select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL
+ select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
bool
default !CPU_V7M
-config RWSEM_XCHGADD_ALGORITHM
- bool
- default y
-
config ARCH_HAS_ILOG2_U32
bool
choice
prompt "Choose kernel unwinder"
- default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER
- default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER
+ default UNWINDER_ARM if AEABI
+ default UNWINDER_FRAME_POINTER if !AEABI
help
This determines which method will be used for unwinding kernel stack
traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
config UNWINDER_ARM
bool "ARM EABI stack unwinder"
- depends on AEABI
+ depends on AEABI && !FUNCTION_GRAPH_TRACER
select ARM_UNWIND
help
This option enables stack unwinding support in the kernel
@ Preserve return value of efi_entry() in r4
mov r4, r0
- bl cache_clean_flush
+
+ @ our cache maintenance code relies on CP15 barrier instructions
+ @ but since we arrived here with the MMU and caches configured
+ @ by UEFI, we must check that the CP15BEN bit is set in SCTLR.
+ @ Note that this bit is RAO/WI on v6 and earlier, so the ISB in
+ @ the enable path will be executed on v7+ only.
+ mrc p15, 0, r1, c1, c0, 0 @ read SCTLR
+ tst r1, #(1 << 5) @ CP15BEN bit set?
+ bne 0f
+ orr r1, r1, #(1 << 5) @ CP15 barrier instructions
+ mcr p15, 0, r1, c1, c0, 0 @ write SCTLR
+ ARM( .inst 0xf57ff06f @ v7+ isb )
+ THUMB( isb )
+
+0: bl cache_clean_flush
bl cache_off
@ Set parameters for booting zImage according to boot protocol
generic-y += msi.h
generic-y += parport.h
generic-y += preempt.h
-generic-y += rwsem.h
generic-y += seccomp.h
generic-y += segment.h
generic-y += serial.h
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
-#define MMU_GATHER_BUNDLE 8
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
static inline void __tlb_remove_table(void *_table)
{
free_page_and_swap_cache((struct page *)_table);
}
-struct mmu_table_batch {
- struct rcu_head rcu;
- unsigned int nr;
- void *tables[0];
-};
-
-#define MAX_TABLE_BATCH \
- ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-#define tlb_remove_entry(tlb, entry) tlb_remove_table(tlb, entry)
-#else
-#define tlb_remove_entry(tlb, entry) tlb_remove_page(tlb, entry)
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
-
-/*
- * TLB handling. This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
- struct mm_struct *mm;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
- struct mmu_table_batch *batch;
- unsigned int need_flush;
-#endif
- unsigned int fullmm;
- struct vm_area_struct *vma;
- unsigned long start, end;
- unsigned long range_start;
- unsigned long range_end;
- unsigned int nr;
- unsigned int max;
- struct page **pages;
- struct page *local[MMU_GATHER_BUNDLE];
-};
-
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-/*
- * This is unnecessarily complex. There's three ways the TLB shootdown
- * code is used:
- * 1. Unmapping a range of vmas. See zap_page_range(), unmap_region().
- * tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- * tlb->vma will be non-NULL.
- * 2. Unmapping all vmas. See exit_mmap().
- * tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- * tlb->vma will be non-NULL. Additionally, page tables will be freed.
- * 3. Unmapping argument pages. See shift_arg_pages().
- * tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- * tlb->vma will be NULL.
- */
-static inline void tlb_flush(struct mmu_gather *tlb)
-{
- if (tlb->fullmm || !tlb->vma)
- flush_tlb_mm(tlb->mm);
- else if (tlb->range_end > 0) {
- flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
- tlb->range_start = TASK_SIZE;
- tlb->range_end = 0;
- }
-}
-
-static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
-{
- if (!tlb->fullmm) {
- if (addr < tlb->range_start)
- tlb->range_start = addr;
- if (addr + PAGE_SIZE > tlb->range_end)
- tlb->range_end = addr + PAGE_SIZE;
- }
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
- unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
- if (addr) {
- tlb->pages = (void *)addr;
- tlb->max = PAGE_SIZE / sizeof(struct page *);
- }
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
- tlb_flush(tlb);
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
- tlb_table_flush(tlb);
-#endif
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
- free_pages_and_swap_cache(tlb->pages, tlb->nr);
- tlb->nr = 0;
- if (tlb->pages == tlb->local)
- __tlb_alloc_page(tlb);
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
- tlb_flush_mmu_tlbonly(tlb);
- tlb_flush_mmu_free(tlb);
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- tlb->mm = mm;
- tlb->fullmm = !(start | (end+1));
- tlb->start = start;
- tlb->end = end;
- tlb->vma = NULL;
- tlb->max = ARRAY_SIZE(tlb->local);
- tlb->pages = tlb->local;
- tlb->nr = 0;
- __tlb_alloc_page(tlb);
+#include <asm-generic/tlb.h>
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
- tlb->batch = NULL;
+#ifndef CONFIG_HAVE_RCU_TABLE_FREE
+#define tlb_remove_table(tlb, entry) tlb_remove_page(tlb, entry)
#endif
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end, bool force)
-{
- if (force) {
- tlb->range_start = start;
- tlb->range_end = end;
- }
-
- tlb_flush_mmu(tlb);
-
- /* keep the page table cache within bounds */
- check_pgt_cache();
-
- if (tlb->pages != tlb->local)
- free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Memorize the range for the TLB flush.
- */
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
-{
- tlb_add_flush(tlb, addr);
-}
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
- tlb_remove_tlb_entry(tlb, ptep, address)
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush. When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
- if (!tlb->fullmm) {
- flush_cache_range(vma, vma->vm_start, vma->vm_end);
- tlb->vma = vma;
- tlb->range_start = TASK_SIZE;
- tlb->range_end = 0;
- }
-}
static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
- if (!tlb->fullmm)
- tlb_flush(tlb);
-}
-
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- tlb->pages[tlb->nr++] = page;
- VM_WARN_ON(tlb->nr > tlb->max);
- if (tlb->nr == tlb->max)
- return true;
- return false;
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- if (__tlb_remove_page(tlb, page))
- tlb_flush_mmu(tlb);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
-{
- return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
-{
- return tlb_remove_page(tlb, page);
-}
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
- unsigned long addr)
+__pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr)
{
pgtable_page_dtor(pte);
-#ifdef CONFIG_ARM_LPAE
- tlb_add_flush(tlb, addr);
-#else
+#ifndef CONFIG_ARM_LPAE
/*
* With the classic ARM MMU, a pte page has two corresponding pmd
* entries, each covering 1MB.
*/
- addr &= PMD_MASK;
- tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
- tlb_add_flush(tlb, addr + SZ_1M);
+ addr = (addr & PMD_MASK) + SZ_1M;
+ __tlb_adjust_range(tlb, addr - PAGE_SIZE, 2 * PAGE_SIZE);
#endif
- tlb_remove_entry(tlb, pte);
-}
-
-static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
- unsigned long addr)
-{
-#ifdef CONFIG_ARM_LPAE
- tlb_add_flush(tlb, addr);
- tlb_remove_entry(tlb, virt_to_page(pmdp));
-#endif
+ tlb_remove_table(tlb, pte);
}
static inline void
-tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
-{
- tlb_add_flush(tlb, addr);
-}
-
-#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
-#define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm) do { } while (0)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
- unsigned int page_size)
+__pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
{
-}
-
-static inline void tlb_flush_remove_tables(struct mm_struct *mm)
-{
-}
+#ifdef CONFIG_ARM_LPAE
+ struct page *page = virt_to_page(pmdp);
-static inline void tlb_flush_remove_tables_local(void *arg)
-{
+ tlb_remove_table(tlb, page);
+#endif
}
#endif /* CONFIG_MMU */
*/
.text
__after_proc_init:
-#ifdef CONFIG_ARM_MPU
M_CLASS(movw r12, #:lower16:BASEADDR_V7M_SCB)
M_CLASS(movt r12, #:upper16:BASEADDR_V7M_SCB)
+#ifdef CONFIG_ARM_MPU
M_CLASS(ldr r3, [r12, 0x50])
AR_CLASS(mrc p15, 0, r3, c0, c1, 4) @ Read ID_MMFR0
and r3, r3, #(MMFR0_PMSA) @ PMSA field
int ret;
/*
- * Increment event counter and perform fixup for the pre-signal
- * frame.
+ * Perform fixup for the pre-signal frame.
*/
rseq_signal_deliver(ksig, regs);
* running on another CPU? For now, ignore it as we
* can't guarantee we won't explode.
*/
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
return;
#else
frame.fp = thread_saved_fp(tsk);
}
walk_stackframe(&frame, save_trace, &data);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
frame.pc = regs->ARM_pc;
walk_stackframe(&frame, save_trace, &data);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RCU_TABLE_FREE
- select HAVE_RCU_TABLE_INVALIDATE
select HAVE_RSEQ
select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
config TRACE_IRQFLAGS_SUPPORT
def_bool y
-config RWSEM_XCHGADD_ALGORITHM
- def_bool y
-
config GENERIC_BUG
def_bool y
depends on BUG
generic-y += msi.h
generic-y += qrwlock.h
generic-y += qspinlock.h
-generic-y += rwsem.h
generic-y += segment.h
generic-y += serial.h
generic-y += set_memory.h
static inline int
arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
{
- int oldval, ret, tmp;
+ int oldval = 0, ret, tmp;
u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
pagefault_disable();
free_page_and_swap_cache((struct page *)_table);
}
+#define tlb_flush tlb_flush
static void tlb_flush(struct mmu_gather *tlb);
#include <asm-generic/tlb.h>
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 424
+#define __NR_compat_syscalls 428
#endif
#define __ARCH_WANT_SYS_CLONE
__SYSCALL(__NR_futex_time64, sys_futex)
#define __NR_sched_rr_get_interval_time64 423
__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
/*
* Please add new compat syscalls above this comment and update
* to be revisited if support for multiple ftrace entry points
* is added in the future, but for now, the pr_err() below
* deals with a theoretical issue only.
+ *
+ * Note that PLTs are place relative, and plt_entries_equal()
+ * checks whether they point to the same target. Here, we need
+ * to check if the actual opcodes are in fact identical,
+ * regardless of the offset in memory so use memcmp() instead.
*/
trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
- if (!plt_entries_equal(mod->arch.ftrace_trampoline,
- &trampoline)) {
+ if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
+ sizeof(trampoline))) {
if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
return -EINVAL;
#endif
walk_stackframe(current, &frame, save_trace, &data);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace_regs);
#endif
walk_stackframe(tsk, &frame, save_trace, &data);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
put_task_stack(tsk);
}
* Otherwise, this is a no-op
*/
u64 base = phys_initrd_start & PAGE_MASK;
- u64 size = PAGE_ALIGN(phys_initrd_size);
+ u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;
/*
* We can only add back the initrd memory if we don't end up
select GENERIC_CLOCKEVENTS
select MODULES_USE_ELF_RELA
select ARCH_NO_COHERENT_DMA_MMAP
+ select MMU_GATHER_NO_RANGE if MMU
config MMU
def_bool n
config FPU
def_bool n
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
config GENERIC_CALIBRATE_DELAY
def_bool y
#ifndef _ASM_C6X_TLB_H
#define _ASM_C6X_TLB_H
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
#include <asm-generic/tlb.h>
#endif /* _ASM_C6X_TLB_H */
config MMU
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
config STACKTRACE_SUPPORT
def_bool y
config CPU_BIG_ENDIAN
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
config GENERIC_HWEIGHT
def_bool y
#ifndef __H8300_TLB_H__
#define __H8300_TLB_H__
-#define tlb_flush(tlb) do { } while (0)
-
#include <asm-generic/tlb.h>
#endif
config GENERIC_IRQ_PROBE
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- def_bool n
-
-config RWSEM_XCHGADD_ALGORITHM
- def_bool y
-
config GENERIC_HWEIGHT
def_bool y
generic-y += pci.h
generic-y += percpu.h
generic-y += preempt.h
-generic-y += rwsem.h
generic-y += sections.h
generic-y += segment.h
generic-y += serial.h
#include <linux/pagemap.h>
#include <asm/tlbflush.h>
-/*
- * We don't need any special per-pte or per-vma handling...
- */
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-
-/*
- * .. because we flush the whole mm when it fills up
- */
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
#include <asm-generic/tlb.h>
#endif
config GENERIC_LOCKBREAK
def_bool n
-config RWSEM_XCHGADD_ALGORITHM
- bool
- default y
-
config HUGETLB_PAGE_SIZE_VARIABLE
bool
depends on HUGETLB_PAGE
typedef void ia64_mv_send_ipi_t (int, int, int, int);
typedef void ia64_mv_timer_interrupt_t (int, void *);
typedef void ia64_mv_global_tlb_purge_t (struct mm_struct *, unsigned long, unsigned long, unsigned long);
-typedef void ia64_mv_tlb_migrate_finish_t (struct mm_struct *);
typedef u8 ia64_mv_irq_to_vector (int);
typedef unsigned int ia64_mv_local_vector_to_irq (u8);
typedef char *ia64_mv_pci_get_legacy_mem_t (struct pci_bus *);
{
}
-static inline void
-machvec_noop_mm (struct mm_struct *mm)
-{
-}
-
static inline void
machvec_noop_task (struct task_struct *task)
{
extern void machvec_setup (char **);
extern void machvec_timer_interrupt (int, void *);
-extern void machvec_tlb_migrate_finish (struct mm_struct *);
# if defined (CONFIG_IA64_HP_SIM)
# include <asm/machvec_hpsim.h>
# define platform_send_ipi ia64_mv.send_ipi
# define platform_timer_interrupt ia64_mv.timer_interrupt
# define platform_global_tlb_purge ia64_mv.global_tlb_purge
-# define platform_tlb_migrate_finish ia64_mv.tlb_migrate_finish
# define platform_dma_init ia64_mv.dma_init
# define platform_dma_get_ops ia64_mv.dma_get_ops
# define platform_irq_to_vector ia64_mv.irq_to_vector
ia64_mv_send_ipi_t *send_ipi;
ia64_mv_timer_interrupt_t *timer_interrupt;
ia64_mv_global_tlb_purge_t *global_tlb_purge;
- ia64_mv_tlb_migrate_finish_t *tlb_migrate_finish;
ia64_mv_dma_init *dma_init;
ia64_mv_dma_get_ops *dma_get_ops;
ia64_mv_irq_to_vector *irq_to_vector;
platform_send_ipi, \
platform_timer_interrupt, \
platform_global_tlb_purge, \
- platform_tlb_migrate_finish, \
platform_dma_init, \
platform_dma_get_ops, \
platform_irq_to_vector, \
#ifndef platform_global_tlb_purge
# define platform_global_tlb_purge ia64_global_tlb_purge /* default to architected version */
#endif
-#ifndef platform_tlb_migrate_finish
-# define platform_tlb_migrate_finish machvec_noop_mm
-#endif
#ifndef platform_kernel_launch_event
# define platform_kernel_launch_event machvec_noop
#endif
extern ia64_mv_send_ipi_t sn2_send_IPI;
extern ia64_mv_timer_interrupt_t sn_timer_interrupt;
extern ia64_mv_global_tlb_purge_t sn2_global_tlb_purge;
-extern ia64_mv_tlb_migrate_finish_t sn_tlb_migrate_finish;
extern ia64_mv_irq_to_vector sn_irq_to_vector;
extern ia64_mv_local_vector_to_irq sn_local_vector_to_irq;
extern ia64_mv_pci_get_legacy_mem_t sn_pci_get_legacy_mem;
#define platform_send_ipi sn2_send_IPI
#define platform_timer_interrupt sn_timer_interrupt
#define platform_global_tlb_purge sn2_global_tlb_purge
-#define platform_tlb_migrate_finish sn_tlb_migrate_finish
#define platform_pci_fixup sn_pci_fixup
#define platform_inb __sn_inb
#define platform_inw __sn_inw
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * R/W semaphores for ia64
- *
- * Copyright (C) 2003 Ken Chen <kenneth.w.chen@intel.com>
- * Copyright (C) 2003 Asit Mallick <asit.k.mallick@intel.com>
- * Copyright (C) 2005 Christoph Lameter <cl@linux.com>
- *
- * Based on asm-i386/rwsem.h and other architecture implementation.
- *
- * The MSW of the count is the negated number of active writers and
- * waiting lockers, and the LSW is the total number of active locks.
- *
- * The lock count is initialized to 0 (no active and no waiting lockers).
- *
- * When a writer subtracts WRITE_BIAS, it'll get 0xffffffff00000001 for
- * the case of an uncontended lock. Readers increment by 1 and see a positive
- * value when uncontended, negative if there are writers (and maybe) readers
- * waiting (in which case it goes to sleep).
- */
-
-#ifndef _ASM_IA64_RWSEM_H
-#define _ASM_IA64_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
-#endif
-
-#include <asm/intrinsics.h>
-
-#define RWSEM_UNLOCKED_VALUE __IA64_UL_CONST(0x0000000000000000)
-#define RWSEM_ACTIVE_BIAS (1L)
-#define RWSEM_ACTIVE_MASK (0xffffffffL)
-#define RWSEM_WAITING_BIAS (-0x100000000L)
-#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline int
-___down_read (struct rw_semaphore *sem)
-{
- long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1);
-
- return (result < 0);
-}
-
-static inline void
-__down_read (struct rw_semaphore *sem)
-{
- if (___down_read(sem))
- rwsem_down_read_failed(sem);
-}
-
-static inline int
-__down_read_killable (struct rw_semaphore *sem)
-{
- if (___down_read(sem))
- if (IS_ERR(rwsem_down_read_failed_killable(sem)))
- return -EINTR;
-
- return 0;
-}
-
-/*
- * lock for writing
- */
-static inline long
-___down_write (struct rw_semaphore *sem)
-{
- long old, new;
-
- do {
- old = atomic_long_read(&sem->count);
- new = old + RWSEM_ACTIVE_WRITE_BIAS;
- } while (atomic_long_cmpxchg_acquire(&sem->count, old, new) != old);
-
- return old;
-}
-
-static inline void
-__down_write (struct rw_semaphore *sem)
-{
- if (___down_write(sem))
- rwsem_down_write_failed(sem);
-}
-
-static inline int
-__down_write_killable (struct rw_semaphore *sem)
-{
- if (___down_write(sem)) {
- if (IS_ERR(rwsem_down_write_failed_killable(sem)))
- return -EINTR;
- }
-
- return 0;
-}
-
-/*
- * unlock after reading
- */
-static inline void
-__up_read (struct rw_semaphore *sem)
-{
- long result = ia64_fetchadd8_rel((unsigned long *)&sem->count.counter, -1);
-
- if (result < 0 && (--result & RWSEM_ACTIVE_MASK) == 0)
- rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void
-__up_write (struct rw_semaphore *sem)
-{
- long old, new;
-
- do {
- old = atomic_long_read(&sem->count);
- new = old - RWSEM_ACTIVE_WRITE_BIAS;
- } while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
-
- if (new < 0 && (new & RWSEM_ACTIVE_MASK) == 0)
- rwsem_wake(sem);
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline int
-__down_read_trylock (struct rw_semaphore *sem)
-{
- long tmp;
- while ((tmp = atomic_long_read(&sem->count)) >= 0) {
- if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp+1)) {
- return 1;
- }
- }
- return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline int
-__down_write_trylock (struct rw_semaphore *sem)
-{
- long tmp = atomic_long_cmpxchg_acquire(&sem->count,
- RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS);
- return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void
-__downgrade_write (struct rw_semaphore *sem)
-{
- long old, new;
-
- do {
- old = atomic_long_read(&sem->count);
- new = old - RWSEM_WAITING_BIAS;
- } while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
-
- if (old < 0)
- rwsem_downgrade_wake(sem);
-}
-
-#endif /* _ASM_IA64_RWSEM_H */
#include <asm/tlbflush.h>
#include <asm/machvec.h>
-/*
- * If we can't allocate a page to make a big batch of page pointers
- * to work on, then just handle a few from the on-stack structure.
- */
-#define IA64_GATHER_BUNDLE 8
-
-struct mmu_gather {
- struct mm_struct *mm;
- unsigned int nr;
- unsigned int max;
- unsigned char fullmm; /* non-zero means full mm flush */
- unsigned char need_flush; /* really unmapped some PTEs? */
- unsigned long start, end;
- unsigned long start_addr;
- unsigned long end_addr;
- struct page **pages;
- struct page *local[IA64_GATHER_BUNDLE];
-};
-
-struct ia64_tr_entry {
- u64 ifa;
- u64 itir;
- u64 pte;
- u64 rr;
-}; /*Record for tr entry!*/
-
-extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
-extern void ia64_ptr_entry(u64 target_mask, int slot);
-
-extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
-
-/*
- region register macros
-*/
-#define RR_TO_VE(val) (((val) >> 0) & 0x0000000000000001)
-#define RR_VE(val) (((val) & 0x0000000000000001) << 0)
-#define RR_VE_MASK 0x0000000000000001L
-#define RR_VE_SHIFT 0
-#define RR_TO_PS(val) (((val) >> 2) & 0x000000000000003f)
-#define RR_PS(val) (((val) & 0x000000000000003f) << 2)
-#define RR_PS_MASK 0x00000000000000fcL
-#define RR_PS_SHIFT 2
-#define RR_RID_MASK 0x00000000ffffff00L
-#define RR_TO_RID(val) ((val >> 8) & 0xffffff)
-
-static inline void
-ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
- tlb->need_flush = 0;
-
- if (tlb->fullmm) {
- /*
- * Tearing down the entire address space. This happens both as a result
- * of exit() and execve(). The latter case necessitates the call to
- * flush_tlb_mm() here.
- */
- flush_tlb_mm(tlb->mm);
- } else if (unlikely (end - start >= 1024*1024*1024*1024UL
- || REGION_NUMBER(start) != REGION_NUMBER(end - 1)))
- {
- /*
- * If we flush more than a tera-byte or across regions, we're probably
- * better off just flushing the entire TLB(s). This should be very rare
- * and is not worth optimizing for.
- */
- flush_tlb_all();
- } else {
- /*
- * flush_tlb_range() takes a vma instead of a mm pointer because
- * some architectures want the vm_flags for ITLB/DTLB flush.
- */
- struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
-
- /* flush the address range from the tlb: */
- flush_tlb_range(&vma, start, end);
- /* now flush the virt. page-table area mapping the address range: */
- flush_tlb_range(&vma, ia64_thash(start), ia64_thash(end));
- }
-
-}
-
-static inline void
-ia64_tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
- unsigned long i;
- unsigned int nr;
-
- /* lastly, release the freed pages */
- nr = tlb->nr;
-
- tlb->nr = 0;
- tlb->start_addr = ~0UL;
- for (i = 0; i < nr; ++i)
- free_page_and_swap_cache(tlb->pages[i]);
-}
-
-/*
- * Flush the TLB for address range START to END and, if not in fast mode, release the
- * freed pages that where gathered up to this point.
- */
-static inline void
-ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
- if (!tlb->need_flush)
- return;
- ia64_tlb_flush_mmu_tlbonly(tlb, start, end);
- ia64_tlb_flush_mmu_free(tlb);
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
- unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
- if (addr) {
- tlb->pages = (void *)addr;
- tlb->max = PAGE_SIZE / sizeof(void *);
- }
-}
-
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- tlb->mm = mm;
- tlb->max = ARRAY_SIZE(tlb->local);
- tlb->pages = tlb->local;
- tlb->nr = 0;
- tlb->fullmm = !(start | (end+1));
- tlb->start = start;
- tlb->end = end;
- tlb->start_addr = ~0UL;
-}
-
-/*
- * Called at the end of the shootdown operation to free up any resources that were
- * collected.
- */
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end, bool force)
-{
- if (force)
- tlb->need_flush = 1;
- /*
- * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
- * tlb->end_addr.
- */
- ia64_tlb_flush_mmu(tlb, start, end);
-
- /* keep the page table cache within bounds */
- check_pgt_cache();
-
- if (tlb->pages != tlb->local)
- free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Logically, this routine frees PAGE. On MP machines, the actual freeing of the page
- * must be delayed until after the TLB has been flushed (see comments at the beginning of
- * this file).
- */
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- tlb->need_flush = 1;
-
- if (!tlb->nr && tlb->pages == tlb->local)
- __tlb_alloc_page(tlb);
-
- tlb->pages[tlb->nr++] = page;
- VM_WARN_ON(tlb->nr > tlb->max);
- if (tlb->nr == tlb->max)
- return true;
- return false;
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
- ia64_tlb_flush_mmu_tlbonly(tlb, tlb->start_addr, tlb->end_addr);
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
- ia64_tlb_flush_mmu_free(tlb);
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
- ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- if (__tlb_remove_page(tlb, page))
- tlb_flush_mmu(tlb);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
-{
- return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
-{
- return tlb_remove_page(tlb, page);
-}
-
-/*
- * Remove TLB entry for PTE mapped at virtual address ADDRESS. This is called for any
- * PTE, not just those pointing to (normal) physical memory.
- */
-static inline void
-__tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
-{
- if (tlb->start_addr == ~0UL)
- tlb->start_addr = address;
- tlb->end_addr = address + PAGE_SIZE;
-}
-
-#define tlb_migrate_finish(mm) platform_tlb_migrate_finish(mm)
-
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-
-#define tlb_remove_tlb_entry(tlb, ptep, addr) \
-do { \
- tlb->need_flush = 1; \
- __tlb_remove_tlb_entry(tlb, ptep, addr); \
-} while (0)
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
- tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
- unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, address) \
-do { \
- tlb->need_flush = 1; \
- __pte_free_tlb(tlb, ptep, address); \
-} while (0)
-
-#define pmd_free_tlb(tlb, ptep, address) \
-do { \
- tlb->need_flush = 1; \
- __pmd_free_tlb(tlb, ptep, address); \
-} while (0)
-
-#define pud_free_tlb(tlb, pudp, address) \
-do { \
- tlb->need_flush = 1; \
- __pud_free_tlb(tlb, pudp, address); \
-} while (0)
+#include <asm-generic/tlb.h>
#endif /* _ASM_IA64_TLB_H */
#include <asm/mmu_context.h>
#include <asm/page.h>
+struct ia64_tr_entry {
+ u64 ifa;
+ u64 itir;
+ u64 pte;
+ u64 rr;
+}; /*Record for tr entry!*/
+
+extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
+extern void ia64_ptr_entry(u64 target_mask, int slot);
+extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
+
+/*
+ region register macros
+*/
+#define RR_TO_VE(val) (((val) >> 0) & 0x0000000000000001)
+#define RR_VE(val) (((val) & 0x0000000000000001) << 0)
+#define RR_VE_MASK 0x0000000000000001L
+#define RR_VE_SHIFT 0
+#define RR_TO_PS(val) (((val) >> 2) & 0x000000000000003f)
+#define RR_PS(val) (((val) & 0x000000000000003f) << 2)
+#define RR_PS_MASK 0x00000000000000fcL
+#define RR_PS_SHIFT 2
+#define RR_RID_MASK 0x00000000ffffff00L
+#define RR_TO_RID(val) ((val >> 8) & 0xffffff)
+
/*
* Now for some TLB flushing routines. This is the kind of stuff that
* can be very expensive, so try to avoid them whenever possible.
static int __init run_dmi_scan(void)
{
- dmi_scan_machine();
- dmi_memdev_walk();
- dmi_set_dump_stack_arch_desc();
+ dmi_setup();
return 0;
}
core_initcall(run_dmi_scan);
332 common pkey_free sys_pkey_free
333 common rseq sys_rseq
# 334 through 423 are reserved to sync up with other architectures
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
ia64_srlz_i(); /* srlz.i implies srlz.d */
}
-void
-flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
+static void
+__flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
preempt_enable();
ia64_srlz_i(); /* srlz.i implies srlz.d */
}
+
+void flush_tlb_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ if (unlikely(end - start >= 1024*1024*1024*1024UL
+ || REGION_NUMBER(start) != REGION_NUMBER(end - 1))) {
+ /*
+ * If we flush more than a tera-byte or across regions, we're
+ * probably better off just flushing the entire TLB(s). This
+ * should be very rare and is not worth optimizing for.
+ */
+ flush_tlb_all();
+ } else {
+ /* flush the address range from the tlb */
+ __flush_tlb_range(vma, start, end);
+ /* flush the virt. page-table area mapping the addr range */
+ __flush_tlb_range(vma, ia64_thash(start), ia64_thash(end));
+ }
+}
EXPORT_SYMBOL(flush_tlb_range);
void ia64_tlb_init(void)
cpu_relax();
}
-void sn_tlb_migrate_finish(struct mm_struct *mm)
-{
- /* flush_tlb_mm is inefficient if more than 1 users of mm */
- if (mm == current->mm && mm && atomic_read(&mm->mm_users) == 1)
- flush_tlb_mm(mm);
-}
-
static void
sn2_ipi_flush_all_tlb(struct mm_struct *mm)
{
select OLD_SIGSUSPEND3
select OLD_SIGACTION
select ARCH_DISCARD_MEMBLOCK
+ select MMU_GATHER_NO_RANGE if MMU
config CPU_BIG_ENDIAN
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- bool
- default y
-
-config RWSEM_XCHGADD_ALGORITHM
- bool
-
config ARCH_HAS_ILOG2_U32
bool
#ifndef _M68K_TLB_H
#define _M68K_TLB_H
-/*
- * m68k doesn't need any special per-pte or
- * per-vma handling..
- */
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-
-/*
- * .. because we flush the whole mm when it
- * fills up.
- */
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
#include <asm-generic/tlb.h>
#endif /* _M68K_TLB_H */
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
select TRACING_SUPPORT
select VIRT_TO_BUS
select CPU_NO_EFFICIENT_FFS
+ select MMU_GATHER_NO_RANGE if MMU
# Endianness selection
choice
endchoice
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
config ZONE_DMA
def_bool y
-config RWSEM_XCHGADD_ALGORITHM
- bool
-
config ARCH_HAS_ILOG2_U32
def_bool n
#ifndef _ASM_MICROBLAZE_TLB_H
#define _ASM_MICROBLAZE_TLB_H
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
#include <linux/pagemap.h>
-
-#ifdef CONFIG_MMU
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0)
-#endif
-
#include <asm-generic/tlb.h>
#endif /* _ASM_MICROBLAZE_TLB_H */
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
endmenu
-config RWSEM_GENERIC_SPINLOCK
- bool
- default y
-
-config RWSEM_XCHGADD_ALGORITHM
- bool
-
config GENERIC_HWEIGHT
bool
default y
return ath79_sys_type;
}
-int get_c0_perfcount_int(void)
-{
- return ATH79_MISC_IRQ(5);
-}
-EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
-
unsigned int get_c0_compare_int(void)
{
return CP0_LEGACY_COMPARE_IRQ;
#include <asm/cpu-features.h>
#include <asm/mipsregs.h>
-/*
- * MIPS doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for area to be unmapped.
- */
-#define tlb_start_vma(tlb, vma) \
- do { \
- if (!tlb->fullmm) \
- flush_cache_range(vma, vma->vm_start, vma->vm_end); \
- } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-
-/*
- * .. because we flush the whole mm when it fills up.
- */
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
#define _UNIQUE_ENTRYHI(base, idx) \
(((base) + ((idx) << (PAGE_SHIFT + 1))) | \
(cpu_has_tlbinv ? MIPS_ENTRYHI_EHINV : 0))
subu t1, v0, __NR_O32_Linux
move a1, v0
bnez t1, 1f /* __NR_syscall at offset 0 */
- lw a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
+ ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
.set pop
1: jal syscall_trace_enter
421 n32 rt_sigtimedwait_time64 compat_sys_rt_sigtimedwait_time64
422 n32 futex_time64 sys_futex
423 n32 sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 n32 pidfd_send_signal sys_pidfd_send_signal
+425 n32 io_uring_setup sys_io_uring_setup
+426 n32 io_uring_enter sys_io_uring_enter
+427 n32 io_uring_register sys_io_uring_register
327 n64 rseq sys_rseq
328 n64 io_pgetevents sys_io_pgetevents
# 329 through 423 are reserved to sync up with other architectures
+424 n64 pidfd_send_signal sys_pidfd_send_signal
+425 n64 io_uring_setup sys_io_uring_setup
+426 n64 io_uring_enter sys_io_uring_enter
+427 n64 io_uring_register sys_io_uring_register
421 o32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 o32 futex_time64 sys_futex sys_futex
423 o32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 o32 pidfd_send_signal sys_pidfd_send_signal
+425 o32 io_uring_setup sys_io_uring_setup
+426 o32 io_uring_enter sys_io_uring_enter
+427 o32 io_uring_register sys_io_uring_register
* separate frame pointer, so BPF_REG_10 relative accesses are
* adjusted to be $sp relative.
*/
-int ebpf_to_mips_reg(struct jit_ctx *ctx, const struct bpf_insn *insn,
- enum which_ebpf_reg w)
+static int ebpf_to_mips_reg(struct jit_ctx *ctx,
+ const struct bpf_insn *insn,
+ enum which_ebpf_reg w)
{
int ebpf_reg = (w == src_reg || w == src_reg_no_fp) ?
insn->src_reg : insn->dst_reg;
def_bool y
depends on PREEMPT
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
config TRACE_IRQFLAGS_SUPPORT
def_bool y
#ifndef __ASMNDS32_TLB_H
#define __ASMNDS32_TLB_H
-#define tlb_start_vma(tlb,vma) \
- do { \
- if (!tlb->fullmm) \
- flush_cache_range(vma, vma->vm_start, vma->vm_end); \
- } while (0)
-
-#define tlb_end_vma(tlb,vma) \
- do { \
- if(!tlb->fullmm) \
- flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
- } while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, addr) do { } while (0)
-
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
#include <asm-generic/tlb.h>
#define __pte_free_tlb(tlb, pte, addr) pte_free((tlb)->mm, pte)
void update_mmu_cache(struct vm_area_struct *vma,
unsigned long address, pte_t * pte);
-void tlb_migrate_finish(struct mm_struct *mm);
#endif
select USB_ARCH_HAS_HCD if USB_SUPPORT
select CPU_NO_EFFICIENT_FFS
select ARCH_DISCARD_MEMBLOCK
+ select MMU_GATHER_NO_RANGE if MMU
config GENERIC_CSUM
def_bool y
config FPU
def_bool n
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
config TRACE_IRQFLAGS_SUPPORT
def_bool n
#ifndef _ASM_NIOS2_TLB_H
#define _ASM_NIOS2_TLB_H
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
extern void set_mmu_pid(unsigned long pid);
/*
- * NiosII doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for the area to be unmapped.
+ * NIOS32 does have flush_tlb_range(), but it lacks a limit and fallback to
+ * full mm invalidation. So use flush_tlb_mm() for everything.
*/
-#define tlb_start_vma(tlb, vma) \
- do { \
- if (!tlb->fullmm) \
- flush_cache_range(vma, vma->vm_start, vma->vm_end); \
- } while (0)
-
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
#include <linux/pagemap.h>
#include <asm-generic/tlb.h>
select OMPIC if SMP
select ARCH_WANT_FRAME_POINTERS
select GENERIC_IRQ_MULTI_HANDLER
+ select MMU_GATHER_NO_RANGE if MMU
config CPU_BIG_ENDIAN
def_bool y
config MMU
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
- def_bool n
-
config GENERIC_HWEIGHT
def_bool y
#define __ASM_OPENRISC_TLB_H__
/*
- * or32 doesn't need any special per-pte or
- * per-vma handling..
+ * OpenRISC doesn't have an efficient flush_tlb_range() so use flush_tlb_mm()
+ * for everything.
*/
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
#include <linux/pagemap.h>
#include <asm-generic/tlb.h>
default y
depends on SMP && PREEMPT
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
- bool
-
config ARCH_HAS_ILOG2_U32
bool
default n
#ifndef _PARISC_TLB_H
#define _PARISC_TLB_H
-#define tlb_flush(tlb) \
-do { if ((tlb)->fullmm) \
- flush_tlb_mm((tlb)->mm);\
-} while (0)
-
-#define tlb_start_vma(tlb, vma) \
-do { if (!(tlb)->fullmm) \
- flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define tlb_end_vma(tlb, vma) \
-do { if (!(tlb)->fullmm) \
- flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) \
- do { } while (0)
-
#include <asm-generic/tlb.h>
#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd)
}
}
-
/*
* Save stack-backtrace addresses into a stack_trace buffer.
*/
void save_stack_trace(struct stack_trace *trace)
{
dump_trace(current, trace);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace);
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
dump_trace(tsk, trace);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 sys_futex sys_futex
423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
bool
default y
-config RWSEM_GENERIC_SPINLOCK
- bool
-
-config RWSEM_XCHGADD_ALGORITHM
- bool
- default y
-
config GENERIC_LOCKBREAK
bool
default y
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
select HAVE_RCU_TABLE_FREE if SMP
+ select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE
+ select HAVE_MMU_GATHER_PAGE_SIZE
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RELIABLE_STACKTRACE if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
select HAVE_SYSCALL_TRACEPOINTS
(PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \
|| 44x || 40x
+config ARCH_SUSPEND_NONZERO_CPU
+ def_bool y
+ depends on PPC_POWERNV || PPC_PSERIES
+
config PPC_DCR_NATIVE
bool
CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=m
CONFIG_PROC_KCORE=y
+CONFIG_HUGETLBFS=y
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_NETWORK_FILESYSTEMS is not set
CONFIG_NLS=y
generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += preempt.h
-generic-y += rwsem.h
generic-y += vtime.h
generic-y += msi.h
#define tlb_start_vma(tlb, vma) do { } while (0)
#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry __tlb_remove_tlb_entry
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
+#define tlb_flush tlb_flush
extern void tlb_flush(struct mmu_gather *tlb);
/* Get the generic bits... */
#endif
}
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
- unsigned int page_size)
-{
- if (!tlb->page_size)
- tlb->page_size = page_size;
- else if (tlb->page_size != page_size) {
- if (!tlb->fullmm)
- tlb_flush_mmu(tlb);
- /*
- * update the page size after flush for the new
- * mmu_gather.
- */
- tlb->page_size = page_size;
- }
-}
-
#ifdef CONFIG_SMP
static inline int mm_is_core_local(struct mm_struct *mm)
{
enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR);
- if (!no_nospec)
+ if (!no_nospec && !cpu_mitigations_off())
enable_barrier_nospec(enable);
}
early_param("nospectre_v2", handle_nospectre_v2);
void setup_spectre_v2(void)
{
- if (no_spectrev2)
+ if (no_spectrev2 || cpu_mitigations_off())
do_btb_flush_fixups();
else
btb_flush_enabled = true;
stf_enabled_flush_types = type;
- if (!no_stf_barrier)
+ if (!no_stf_barrier && !cpu_mitigations_off())
stf_barrier_enable(enable);
}
enabled_flush_types = types;
- if (!no_rfi_flush)
+ if (!no_rfi_flush && !cpu_mitigations_off())
rfi_flush_enable(enable);
}
421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 sys_futex sys_futex
423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
if (ret != H_SUCCESS)
return ret;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+
ret = kvmppc_tce_validate(stt, tce);
if (ret != H_SUCCESS)
- return ret;
+ goto unlock_exit;
dir = iommu_tce_direction(tce);
- idx = srcu_read_lock(&vcpu->kvm->srcu);
-
if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
ret = H_PARAMETER;
goto unlock_exit;
vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
- mtspr(SPRN_PSSCR, host_psscr);
+ /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
+ mtspr(SPRN_PSSCR, host_psscr |
+ (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
mtspr(SPRN_HFSCR, host_hfscr);
mtspr(SPRN_CIABR, host_ciabr);
mtspr(SPRN_DAWR, host_dawr);
unsigned long entries, unsigned long dev_hpa,
struct mm_iommu_table_group_mem_t **pmem)
{
- struct mm_iommu_table_group_mem_t *mem;
- long i, ret, locked_entries = 0;
+ struct mm_iommu_table_group_mem_t *mem, *mem2;
+ long i, ret, locked_entries = 0, pinned = 0;
unsigned int pageshift;
-
- mutex_lock(&mem_list_mutex);
-
- list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
- next) {
- /* Overlap? */
- if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
- (ua < (mem->ua +
- (mem->entries << PAGE_SHIFT)))) {
- ret = -EINVAL;
- goto unlock_exit;
- }
-
- }
+ unsigned long entry, chunk;
if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
ret = mm_iommu_adjust_locked_vm(mm, entries, true);
if (ret)
- goto unlock_exit;
+ return ret;
locked_entries = entries;
}
}
down_read(&mm->mmap_sem);
- ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+ chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) /
+ sizeof(struct vm_area_struct *);
+ chunk = min(chunk, entries);
+ for (entry = 0; entry < entries; entry += chunk) {
+ unsigned long n = min(entries - entry, chunk);
+
+ ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n,
+ FOLL_WRITE, mem->hpages + entry, NULL);
+ if (ret == n) {
+ pinned += n;
+ continue;
+ }
+ if (ret > 0)
+ pinned += ret;
+ break;
+ }
up_read(&mm->mmap_sem);
- if (ret != entries) {
- /* free the reference taken */
- for (i = 0; i < ret; i++)
- put_page(mem->hpages[i]);
-
- vfree(mem->hpas);
- kfree(mem);
- ret = -EFAULT;
- goto unlock_exit;
+ if (pinned != entries) {
+ if (!ret)
+ ret = -EFAULT;
+ goto free_exit;
}
pageshift = PAGE_SHIFT;
}
good_exit:
- ret = 0;
atomic64_set(&mem->mapped, 1);
mem->used = 1;
mem->ua = ua;
mem->entries = entries;
- *pmem = mem;
- list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
+ mutex_lock(&mem_list_mutex);
-unlock_exit:
- if (locked_entries && ret)
- mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+ list_for_each_entry_rcu(mem2, &mm->context.iommu_group_mem_list, next) {
+ /* Overlap? */
+ if ((mem2->ua < (ua + (entries << PAGE_SHIFT))) &&
+ (ua < (mem2->ua +
+ (mem2->entries << PAGE_SHIFT)))) {
+ ret = -EINVAL;
+ mutex_unlock(&mem_list_mutex);
+ goto free_exit;
+ }
+ }
+
+ list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
mutex_unlock(&mem_list_mutex);
+ *pmem = mem;
+
+ return 0;
+
+free_exit:
+ /* free the reference taken */
+ for (i = 0; i < pinned; i++)
+ put_page(mem->hpages[i]);
+
+ vfree(mem->hpas);
+ kfree(mem);
+
+unlock_exit:
+ mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+
return ret;
}
long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
{
long ret = 0;
- unsigned long entries, dev_hpa;
+ unsigned long unlock_entries = 0;
mutex_lock(&mem_list_mutex);
goto unlock_exit;
}
+ if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+ unlock_entries = mem->entries;
+
/* @mapped became 0 so now mappings are disabled, release the region */
- entries = mem->entries;
- dev_hpa = mem->dev_hpa;
mm_iommu_release(mem);
- if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
- mm_iommu_adjust_locked_vm(mm, entries, false);
-
unlock_exit:
mutex_unlock(&mem_list_mutex);
+ mm_iommu_adjust_locked_vm(mm, unlock_entries, false);
+
return ret;
}
EXPORT_SYMBOL_GPL(mm_iommu_put);
return -1;
}
+/*
+ * This function calculates the size of the larger block usable to map the
+ * beginning of an area based on the start address and size of that area:
+ * - max block size is 8M on 601 and 256 on other 6xx.
+ * - base address must be aligned to the block size. So the maximum block size
+ * is identified by the lowest bit set to 1 in the base address (for instance
+ * if base is 0x16000000, max size is 0x02000000).
+ * - block size has to be a power of two. This is calculated by finding the
+ * highest bit set to 1.
+ */
static unsigned int block_size(unsigned long base, unsigned long top)
{
unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20;
- unsigned int base_shift = (fls(base) - 1) & 31;
+ unsigned int base_shift = (ffs(base) - 1) & 31;
unsigned int block_shift = (fls(top - base) - 1) & 31;
return min3(max_size, 1U << base_shift, 1U << block_shift);
unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
- int done;
+ unsigned long done;
unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
if (__map_without_bats) {
return __mmu_mapin_ram(base, top);
done = __mmu_mapin_ram(base, border);
- if (done != border - base)
+ if (done != border)
return done;
- return done + __mmu_mapin_ram(border, top);
+ return __mmu_mapin_ram(border, top);
}
void mmu_mark_initmem_nx(void)
config PPC_RADIX_MMU
bool "Radix MMU Support"
- depends on PPC_BOOK3S_64
+ depends on PPC_BOOK3S_64 && HUGETLB_PAGE
select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
default y
help
config TRACE_IRQFLAGS_SUPPORT
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
config GENERIC_BUG
def_bool y
depends on BUG
--- /dev/null
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_ARCH_RV32I=y
+CONFIG_SMP=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
+CONFIG_HVC_RISCV_SBI=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_UAS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_SIFIVE_PLIC=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_RCU_TRACE is not set
static void tlb_flush(struct mmu_gather *tlb);
+#define tlb_flush tlb_flush
#include <asm-generic/tlb.h>
static inline void tlb_flush(struct mmu_gather *tlb)
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
walk_stackframe(tsk, NULL, save_trace, trace);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
*/
memblock_reserve(reg->base, vmlinux_end - reg->base);
mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
+
+ /*
+ * Remove memblock from the end of usable area to the
+ * end of region
+ */
+ if (reg->base + mem_size < end)
+ memblock_remove(reg->base + mem_size,
+ end - reg->base - mem_size);
}
}
BUG_ON(mem_size == 0);
config STACKTRACE_SUPPORT
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- bool
-
-config RWSEM_XCHGADD_ALGORITHM
- def_bool y
-
config ARCH_HAS_ILOG2_U32
def_bool n
select HAVE_PERF_USER_STACK_DUMP
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_MEMBLOCK_PHYS_MAP
+ select HAVE_MMU_GATHER_NO_GATHER
select HAVE_MOD_ARCH_SPECIFIC
select HAVE_NOP_MCOUNT
select HAVE_OPROFILE
select HAVE_PCI
select HAVE_PERF_EVENTS
+ select HAVE_RCU_TABLE_FREE
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RSEQ
select HAVE_SYSCALL_TRACEPOINTS
{
unsigned long offset = ALIGN(mem_safe_offset(), sizeof(u64));
- if (IS_ENABLED(BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
INITRD_START < offset + ENTRIES_EXTENDED_MAX)
offset = ALIGN(INITRD_START + INITRD_SIZE, sizeof(u64));
generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
-generic-y += rwsem.h
generic-y += trace_clock.h
generic-y += unaligned.h
generic-y += word-at-a-time.h
* Pages used for the page tables is a different story. FIXME: more
*/
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/processor.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-
-struct mmu_gather {
- struct mm_struct *mm;
- struct mmu_table_batch *batch;
- unsigned int fullmm;
- unsigned long start, end;
-};
-
-struct mmu_table_batch {
- struct rcu_head rcu;
- unsigned int nr;
- void *tables[0];
-};
-
-#define MAX_TABLE_BATCH \
- ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- tlb->mm = mm;
- tlb->start = start;
- tlb->end = end;
- tlb->fullmm = !(start | (end+1));
- tlb->batch = NULL;
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
- __tlb_flush_mm_lazy(tlb->mm);
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
- tlb_table_flush(tlb);
-}
-
+void __tlb_remove_table(void *_table);
+static inline void tlb_flush(struct mmu_gather *tlb);
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size);
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
- tlb_flush_mmu_tlbonly(tlb);
- tlb_flush_mmu_free(tlb);
-}
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#define tlb_end_vma(tlb, vma) do { } while (0)
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end, bool force)
-{
- if (force) {
- tlb->start = start;
- tlb->end = end;
- }
+#define tlb_flush tlb_flush
+#define pte_free_tlb pte_free_tlb
+#define pmd_free_tlb pmd_free_tlb
+#define p4d_free_tlb p4d_free_tlb
+#define pud_free_tlb pud_free_tlb
- tlb_flush_mmu(tlb);
-}
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm-generic/tlb.h>
/*
* Release the page cache reference for a pte removed by
* tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
* has already been freed, so just do free_page_and_swap_cache.
*/
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- free_page_and_swap_cache(page);
- return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- free_page_and_swap_cache(page);
-}
-
static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size)
{
- return __tlb_remove_page(tlb, page);
+ free_page_and_swap_cache(page);
+ return false;
}
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
+static inline void tlb_flush(struct mmu_gather *tlb)
{
- return tlb_remove_page(tlb, page);
+ __tlb_flush_mm_lazy(tlb->mm);
}
/*
* page table from the tlb.
*/
static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
- unsigned long address)
+ unsigned long address)
{
+ __tlb_adjust_range(tlb, address, PAGE_SIZE);
+ tlb->mm->context.flush_mm = 1;
+ tlb->freed_tables = 1;
+ tlb->cleared_ptes = 1;
+ /*
+ * page_table_free_rcu takes care of the allocation bit masks
+ * of the 2K table fragments in the 4K page table page,
+ * then calls tlb_remove_table.
+ */
page_table_free_rcu(tlb, (unsigned long *) pte, address);
}
if (mm_pmd_folded(tlb->mm))
return;
pgtable_pmd_page_dtor(virt_to_page(pmd));
+ __tlb_adjust_range(tlb, address, PAGE_SIZE);
+ tlb->mm->context.flush_mm = 1;
+ tlb->freed_tables = 1;
+ tlb->cleared_puds = 1;
tlb_remove_table(tlb, pmd);
}
{
if (mm_p4d_folded(tlb->mm))
return;
+ __tlb_adjust_range(tlb, address, PAGE_SIZE);
+ tlb->mm->context.flush_mm = 1;
+ tlb->freed_tables = 1;
+ tlb->cleared_p4ds = 1;
tlb_remove_table(tlb, p4d);
}
{
if (mm_pud_folded(tlb->mm))
return;
+ tlb->mm->context.flush_mm = 1;
+ tlb->freed_tables = 1;
+ tlb->cleared_puds = 1;
tlb_remove_table(tlb, pud);
}
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define tlb_remove_tlb_entry(tlb, ptep, addr) do { } while (0)
-#define tlb_remove_pmd_tlb_entry(tlb, pmdp, addr) do { } while (0)
-#define tlb_migrate_finish(mm) do { } while (0)
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
- tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
- unsigned int page_size)
-{
-}
#endif /* _S390_TLB_H */
if (flags & KERNEL_FPC)
/* Save floating point control */
- asm volatile("stfpc %0" : "=m" (state->fpc));
+ asm volatile("stfpc %0" : "=Q" (state->fpc));
if (!MACHINE_HAS_VX) {
if (flags & KERNEL_VXR_V0V7) {
// SPDX-License-Identifier: GPL-2.0
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/cpu.h>
#include <asm/nospec-branch.h>
static int __init nobp_setup_early(char *str)
void __init nospec_auto_detect(void)
{
- if (test_facility(156)) {
+ if (test_facility(156) || cpu_mitigations_off()) {
/*
* The machine supports etokens.
* Disable expolines and disable nobp.
sp = current_stack_pointer();
dump_trace(save_address, trace, NULL, sp);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace);
if (tsk == current)
sp = current_stack_pointer();
dump_trace(save_address_nosched, trace, tsk, sp);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
sp = kernel_stack_pointer(regs);
dump_trace(save_address, trace, NULL, sp);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace_regs);
421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 - sys_futex
423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register sys_io_uring_register
{
u64 timer;
- asm volatile("stpt %0" : "=m" (timer));
+ asm volatile("stpt %0" : "=Q" (timer));
return timer;
}
asm volatile(
" stpt %0\n" /* Store current cpu timer value */
" spt %1" /* Set new value imm. afterwards */
- : "=m" (timer) : "m" (expires));
+ : "=Q" (timer) : "Q" (expires));
S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer;
S390_lowcore.last_update_timer = expires;
}
#else
" stck %1" /* Store current tod clock value */
#endif
- : "=m" (S390_lowcore.last_update_timer),
- "=m" (S390_lowcore.last_update_clock));
+ : "=Q" (S390_lowcore.last_update_timer),
+ "=Q" (S390_lowcore.last_update_clock));
clock = S390_lowcore.last_update_clock - clock;
timer -= S390_lowcore.last_update_timer;
tlb_remove_table(tlb, table);
}
-static void __tlb_remove_table(void *_table)
+void __tlb_remove_table(void *_table)
{
unsigned int mask = (unsigned long) _table & 3;
void *table = (void *)((unsigned long) _table ^ mask);
}
}
-static void tlb_remove_table_smp_sync(void *arg)
-{
- /* Simply deliver the interrupt */
-}
-
-static void tlb_remove_table_one(void *table)
-{
- /*
- * This isn't an RCU grace period and hence the page-tables cannot be
- * assumed to be actually RCU-freed.
- *
- * It is however sufficient for software page-table walkers that rely
- * on IRQ disabling. See the comment near struct mmu_table_batch.
- */
- smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
- __tlb_remove_table(table);
-}
-
-static void tlb_remove_table_rcu(struct rcu_head *head)
-{
- struct mmu_table_batch *batch;
- int i;
-
- batch = container_of(head, struct mmu_table_batch, rcu);
-
- for (i = 0; i < batch->nr; i++)
- __tlb_remove_table(batch->tables[i]);
-
- free_page((unsigned long)batch);
-}
-
-void tlb_table_flush(struct mmu_gather *tlb)
-{
- struct mmu_table_batch **batch = &tlb->batch;
-
- if (*batch) {
- call_rcu(&(*batch)->rcu, tlb_remove_table_rcu);
- *batch = NULL;
- }
-}
-
-void tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
- struct mmu_table_batch **batch = &tlb->batch;
-
- tlb->mm->context.flush_mm = 1;
- if (*batch == NULL) {
- *batch = (struct mmu_table_batch *)
- __get_free_page(GFP_NOWAIT | __GFP_NOWARN);
- if (*batch == NULL) {
- __tlb_flush_mm_lazy(tlb->mm);
- tlb_remove_table_one(table);
- return;
- }
- (*batch)->nr = 0;
- }
- (*batch)->tables[(*batch)->nr++] = table;
- if ((*batch)->nr == MAX_TABLE_BATCH)
- tlb_flush_mmu(tlb);
-}
-
/*
* Base infrastructure required to generate basic asces, region, segment,
* and page tables that do not make use of enhanced features like EDAT1.
default "arch/sh/configs/shx3_defconfig" if SUPERH32
default "arch/sh/configs/cayman_defconfig" if SUPERH64
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
- bool
-
config GENERIC_BUG
def_bool y
depends on BUG && SUPERH32
generic-y += parport.h
generic-y += percpu.h
generic-y += preempt.h
-generic-y += rwsem.h
generic-y += serial.h
generic-y += sizes.h
generic-y += trace_clock.h
tlb_remove_page((tlb), (pte)); \
} while (0)
+#if CONFIG_PGTABLE_LEVELS > 2
+#define __pmd_free_tlb(tlb, pmdp, addr) \
+do { \
+ struct page *page = virt_to_page(pmdp); \
+ pgtable_pmd_page_dtor(page); \
+ tlb_remove_page((tlb), page); \
+} while (0);
+#endif
+
static inline void check_pgt_cache(void)
{
quicklist_trim(QUICK_PT, NULL, 25, 16);
#ifdef CONFIG_MMU
#include <linux/swap.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
-/*
- * TLB handling. This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
- struct mm_struct *mm;
- unsigned int fullmm;
- unsigned long start, end;
-};
-
-static inline void init_tlb_gather(struct mmu_gather *tlb)
-{
- tlb->start = TASK_SIZE;
- tlb->end = 0;
-
- if (tlb->fullmm) {
- tlb->start = 0;
- tlb->end = TASK_SIZE;
- }
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- tlb->mm = mm;
- tlb->start = start;
- tlb->end = end;
- tlb->fullmm = !(start | (end+1));
-
- init_tlb_gather(tlb);
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end, bool force)
-{
- if (tlb->fullmm || force)
- flush_tlb_mm(tlb->mm);
-
- /* keep the page table cache within bounds */
- check_pgt_cache();
-}
-
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
-{
- if (tlb->start > address)
- tlb->start = address;
- if (tlb->end < address + PAGE_SIZE)
- tlb->end = address + PAGE_SIZE;
-}
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
- tlb_remove_tlb_entry(tlb, ptep, address)
-
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush. When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
- if (!tlb->fullmm)
- flush_cache_range(vma, vma->vm_start, vma->vm_end);
-}
-
-static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
- if (!tlb->fullmm && tlb->end) {
- flush_tlb_range(vma, tlb->start, tlb->end);
- init_tlb_gather(tlb);
- }
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-}
-
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- free_page_and_swap_cache(page);
- return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- __tlb_remove_page(tlb, page);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
-{
- return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
-{
- return tlb_remove_page(tlb, page);
-}
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
- unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, addr) pte_free((tlb)->mm, ptep)
-#define pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, pmdp)
-#define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm) do { } while (0)
+#include <asm-generic/tlb.h>
#if defined(CONFIG_CPU_SH4) || defined(CONFIG_SUPERH64)
extern void tlb_wire_entry(struct vm_area_struct *, unsigned long, pte_t);
#else /* CONFIG_MMU */
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0)
-#define tlb_flush(tlb) do { } while (0)
-
#include <asm-generic/tlb.h>
#endif /* CONFIG_MMU */
unsigned long *sp = (unsigned long *)current_stack_pointer;
unwind_stack(current, NULL, sp, &save_stack_ops, trace);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace);
unsigned long *sp = (unsigned long *)tsk->thread.sp;
unwind_stack(current, NULL, sp, &save_stack_ops_nosched, trace);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
select HAVE_KRETPROBES
select HAVE_KPROBES
select HAVE_RCU_TABLE_FREE if SMP
+ select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_DYNAMIC_FTRACE
source "kernel/Kconfig.hz"
-config RWSEM_GENERIC_SPINLOCK
- bool
- default y if SPARC32
-
-config RWSEM_XCHGADD_ALGORITHM
- bool
- default y if SPARC64
-
config GENERIC_HWEIGHT
bool
default y
generic-y += module.h
generic-y += msi.h
generic-y += preempt.h
-generic-y += rwsem.h
generic-y += serial.h
generic-y += trace_clock.h
generic-y += word-at-a-time.h
#ifndef _SPARC_TLB_H
#define _SPARC_TLB_H
-#define tlb_start_vma(tlb, vma) \
-do { \
- flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define tlb_end_vma(tlb, vma) \
-do { \
- flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) \
- do { } while (0)
-
-#define tlb_flush(tlb) \
-do { \
- flush_tlb_mm((tlb)->mm); \
-} while (0)
-
#include <asm-generic/tlb.h>
#endif /* _SPARC_TLB_H */
421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 sys_futex sys_futex
423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
#ifndef __UM_TLB_H
#define __UM_TLB_H
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/percpu.h>
-#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
-
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-/* struct mmu_gather is an opaque type used by the mm code for passing around
- * any data needed by arch specific code for tlb_remove_page.
- */
-struct mmu_gather {
- struct mm_struct *mm;
- unsigned int need_flush; /* Really unmapped some ptes? */
- unsigned long start;
- unsigned long end;
- unsigned int fullmm; /* non-zero means full mm flush */
-};
-
-static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
- unsigned long address)
-{
- if (tlb->start > address)
- tlb->start = address;
- if (tlb->end < address + PAGE_SIZE)
- tlb->end = address + PAGE_SIZE;
-}
-
-static inline void init_tlb_gather(struct mmu_gather *tlb)
-{
- tlb->need_flush = 0;
-
- tlb->start = TASK_SIZE;
- tlb->end = 0;
-
- if (tlb->fullmm) {
- tlb->start = 0;
- tlb->end = TASK_SIZE;
- }
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- tlb->mm = mm;
- tlb->start = start;
- tlb->end = end;
- tlb->fullmm = !(start | (end+1));
-
- init_tlb_gather(tlb);
-}
-
-extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
- unsigned long end);
-
-static inline void
-tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
- flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
-}
-
-static inline void
-tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
- init_tlb_gather(tlb);
-}
-
-static inline void
-tlb_flush_mmu(struct mmu_gather *tlb)
-{
- if (!tlb->need_flush)
- return;
-
- tlb_flush_mmu_tlbonly(tlb);
- tlb_flush_mmu_free(tlb);
-}
-
-/* arch_tlb_finish_mmu
- * Called at the end of the shootdown operation to free up any resources
- * that were required.
- */
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end, bool force)
-{
- if (force) {
- tlb->start = start;
- tlb->end = end;
- tlb->need_flush = 1;
- }
- tlb_flush_mmu(tlb);
-
- /* keep the page table cache within bounds */
- check_pgt_cache();
-}
-
-/* tlb_remove_page
- * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)),
- * while handling the additional races in SMP caused by other CPUs
- * caching valid mappings in their TLBs.
- */
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- tlb->need_flush = 1;
- free_page_and_swap_cache(page);
- return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
- __tlb_remove_page(tlb, page);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
-{
- return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
- struct page *page, int page_size)
-{
- return tlb_remove_page(tlb, page);
-}
-
-/**
- * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
- *
- * Record the fact that pte's were really umapped in ->need_flush, so we can
- * later optimise away the tlb invalidate. This helps when userspace is
- * unmapping already-unmapped pages, which happens quite a lot.
- */
-#define tlb_remove_tlb_entry(tlb, ptep, address) \
- do { \
- tlb->need_flush = 1; \
- __tlb_remove_tlb_entry(tlb, ptep, address); \
- } while (0)
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
- tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
- unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
-
-#define pud_free_tlb(tlb, pudp, addr) __pud_free_tlb(tlb, pudp, addr)
-
-#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
-
-#define tlb_migrate_finish(mm) do {} while (0)
+#include <asm-generic/cacheflush.h>
+#include <asm-generic/tlb.h>
#endif
static void __save_stack_trace(struct task_struct *tsk, struct stack_trace *trace)
{
dump_trace(tsk, &dump_ops, trace);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
void save_stack_trace(struct stack_trace *trace)
select GENERIC_IOMAP
select MODULES_USE_ELF_REL
select NEED_DMA_MAP_STATE
+ select MMU_GATHER_NO_RANGE if MMU
help
UniCore-32 is 32-bit Instruction Set Architecture,
including a series of low-power-consumption RISC chip
config LOCKDEP_SUPPORT
def_bool y
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
- bool
-
config ARCH_HAS_ILOG2_U32
bool
#ifndef __UNICORE_TLB_H__
#define __UNICORE_TLB_H__
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+/*
+ * unicore32 lacks an efficient flush_tlb_range(), use flush_tlb_mm().
+ */
#define __pte_free_tlb(tlb, pte, addr) \
do { \
}
walk_stackframe(&frame, save_trace, &data);
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
void save_stack_trace(struct stack_trace *trace)
select MODULES_USE_ELF_RELA
select NEED_DMA_MAP_STATE
select SWIOTLB
- select X86_DEV_DMA_OPS
select ARCH_HAS_SYSCALL_WRAPPER
#
select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
+ select ARCH_STACKWALK
select ARCH_SUPPORTS_ACPI
select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
select HAVE_RCU_TABLE_FREE if PARAVIRT
- select HAVE_RCU_TABLE_INVALIDATE if HAVE_RCU_TABLE_FREE
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
select HAVE_FUNCTION_ARG_ACCESS_API
def_bool y
depends on ISA_DMA_API
-config RWSEM_XCHGADD_ALGORITHM
- def_bool y
-
config GENERIC_CALIBRATE_DELAY
def_bool y
bool "STA2X11 Companion Chip Support"
depends on X86_32_NON_STANDARD && PCI
select ARCH_HAS_PHYS_TO_DMA
- select X86_DEV_DMA_OPS
- select X86_DMA_REMAP
select SWIOTLB
select MFD_STA2X11
select GPIOLIB
If you are unsure how to answer this question, answer Y.
-config QUEUED_LOCK_STAT
- bool "Paravirt queued spinlock statistics"
- depends on PARAVIRT_SPINLOCKS && DEBUG_FS
- ---help---
- Enable the collection of statistical data on the slowpath
- behavior of paravirtualized queued spinlocks and report
- them on debugfs.
-
source "arch/x86/xen/Kconfig"
config KVM_GUEST
depends on DEBUG_FS
---help---
Expose statistics about the Change Page Attribute mechanims, which
- helps to determine the effectivness of preserving large and huge
+ helps to determine the effectiveness of preserving large and huge
page mappings when mapping protections are changed.
config ARCH_HAS_MEM_ENCRYPT
config X86_DEV_DMA_OPS
bool
- depends on X86_64 || STA2X11
-
-config X86_DMA_REMAP
- bool
- depends on STA2X11
config HAVE_GENERIC_GUP
def_bool y
export BITS
ifdef CONFIG_X86_NEED_RELOCS
- LDFLAGS_vmlinux := --emit-relocs
+ LDFLAGS_vmlinux := --emit-relocs --discard-none
endif
#
boot_params->hdr.loadflags &= ~KASLR_FLAG;
/* Save RSDP address for later use. */
- boot_params->acpi_rsdp_addr = get_rsdp_addr();
+ /* boot_params->acpi_rsdp_addr = get_rsdp_addr(); */
sanitize_boot_params(boot_params);
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
CONFIG_SMP=y
CONFIG_X86_GENERIC=y
CONFIG_HPET_TIMER=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
CONFIG_SMP=y
CONFIG_CALGARY_IOMMU=y
CONFIG_NR_CPUS=64
vpaddq t2,t1,t1
vmovq t1x,d4
+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
+ # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
+ # amount. Careful: we must not assume the carry bits 'd0 >> 26',
+ # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
+ # integers. It's true in a single-block implementation, but not here.
+
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
paddq t2,t1
movq t1,d4
+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
+ # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
+ # amount. Careful: we must not assume the carry bits 'd0 >> 26',
+ # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
+ # integers. It's true in a single-block implementation, but not here.
+
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
pushl %ebx
pushl %edi
pushl %esi
+ pushfl
/* switch stack */
movl %esp, TASK_threadsp(%eax)
#endif
/* restore callee-saved registers */
+ popfl
popl %esi
popl %edi
popl %ebx
#ifdef CONFIG_PREEMPT
ENTRY(resume_kernel)
DISABLE_INTERRUPTS(CLBR_ANY)
-.Lneed_resched:
cmpl $0, PER_CPU_VAR(__preempt_count)
jnz restore_all_kernel
testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
jz restore_all_kernel
call preempt_schedule_irq
- jmp .Lneed_resched
+ jmp restore_all_kernel
END(resume_kernel)
#endif
/* Check if we need preemption */
btl $9, EFLAGS(%rsp) /* were interrupts off? */
jnc 1f
-0: cmpl $0, PER_CPU_VAR(__preempt_count)
+ cmpl $0, PER_CPU_VAR(__preempt_count)
jnz 1f
call preempt_schedule_irq
- jmp 0b
1:
#endif
/*
targets += vdsox32.lds $(vobjx32s-y)
$(obj)/%.so: OBJCOPYFLAGS := -S
-$(obj)/%.so: $(obj)/%.so.dbg
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
$(call if_changed,objcopy)
$(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
extern time_t __vdso_time(time_t *t);
#ifdef CONFIG_PARAVIRT_CLOCK
-extern u8 pvclock_page
+extern u8 pvclock_page[PAGE_SIZE]
__attribute__((visibility("hidden")));
#endif
#ifdef CONFIG_HYPERV_TSCPAGE
-extern u8 hvclock_page
+extern u8 hvclock_page[PAGE_SIZE]
__attribute__((visibility("hidden")));
#endif
static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
void *stripped_addr, size_t stripped_len,
- FILE *outfile, const char *name)
+ FILE *outfile, const char *image_name)
{
int found_load = 0;
unsigned long load_size = -1; /* Work around bogus warning */
int k;
ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
GET_LE(&symtab_hdr->sh_entsize) * i;
- const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) +
- GET_LE(&sym->st_name);
+ const char *sym_name = raw_addr +
+ GET_LE(&strtab_hdr->sh_offset) +
+ GET_LE(&sym->st_name);
for (k = 0; k < NSYMS; k++) {
- if (!strcmp(name, required_syms[k].name)) {
+ if (!strcmp(sym_name, required_syms[k].name)) {
if (syms[k]) {
fail("duplicate symbol %s\n",
required_syms[k].name);
if (syms[sym_vvar_start] % 4096)
fail("vvar_begin must be a multiple of 4096\n");
- if (!name) {
+ if (!image_name) {
fwrite(stripped_addr, stripped_len, 1, outfile);
return;
}
}
fprintf(outfile, "\n};\n\n");
- fprintf(outfile, "const struct vdso_image %s = {\n", name);
+ fprintf(outfile, "const struct vdso_image %s = {\n", image_name);
fprintf(outfile, "\t.data = raw_data,\n");
fprintf(outfile, "\t.size = %lu,\n", mapping_size);
if (alt_sec) {
},
};
+static __initconst const u64 amd_hw_cache_event_ids_f17h
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */
+ [C(RESULT_MISS)] = 0xc860, /* L2$ access from DC Miss */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches */
+ [C(RESULT_MISS)] = 0x0081, /* Instruction cache misses */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */
+ [C(RESULT_MISS)] = 0xf045, /* L2 DTLB misses (PT walks) */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */
+ [C(RESULT_MISS)] = 0xff85, /* L1 ITLB misses, L2 misses */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+[C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr. */
+ [C(RESULT_MISS)] = 0x00c3, /* Retired Mispredicted BI */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+[C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+};
+
/*
- * AMD Performance Monitor K7 and later.
+ * AMD Performance Monitor K7 and later, up to and including Family 16h:
*/
static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
- [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
- [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */
+};
+
+/*
+ * AMD Performance Monitor Family 17h and later:
+ */
+static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287,
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187,
};
static u64 amd_pmu_event_map(int hw_event)
{
+ if (boot_cpu_data.x86 >= 0x17)
+ return amd_f17h_perfmon_event_map[hw_event];
+
return amd_perfmon_event_map[hw_event];
}
x86_pmu.amd_nb_constraints = 0;
}
- /* Events are common for all AMDs */
- memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
+ if (boot_cpu_data.x86 >= 0x17)
+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids));
+ else
+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids));
return 0;
}
return -EINVAL;
}
+ /* sample_regs_user never support XMM registers */
+ if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
+ return -EINVAL;
+ /*
+ * Besides the general purpose registers, XMM registers may
+ * be collected in PEBS on some platforms, e.g. Icelake
+ */
+ if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
+ if (x86_pmu.pebs_no_xmm_regs)
+ return -EINVAL;
+
+ if (!event->attr.precise_ip)
+ return -EINVAL;
+ }
+
return x86_setup_perfctr(event);
}
return event->pmu == &pmu;
}
+struct pmu *x86_get_pmu(void)
+{
+ return &pmu;
+}
/*
* Event scheduler state:
*
struct event_constraint *c;
unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
struct perf_event *e;
- int i, wmin, wmax, unsched = 0;
+ int n0, i, wmin, wmax, unsched = 0;
struct hw_perf_event *hwc;
bitmap_zero(used_mask, X86_PMC_IDX_MAX);
+ /*
+ * Compute the number of events already present; see x86_pmu_add(),
+ * validate_group() and x86_pmu_commit_txn(). For the former two
+ * cpuc->n_events hasn't been updated yet, while for the latter
+ * cpuc->n_txn contains the number of events added in the current
+ * transaction.
+ */
+ n0 = cpuc->n_events;
+ if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
+ n0 -= cpuc->n_txn;
+
if (x86_pmu.start_scheduling)
x86_pmu.start_scheduling(cpuc);
for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
- cpuc->event_constraint[i] = NULL;
- c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
- cpuc->event_constraint[i] = c;
+ c = cpuc->event_constraint[i];
+
+ /*
+ * Previously scheduled events should have a cached constraint,
+ * while new events should not have one.
+ */
+ WARN_ON_ONCE((c && i >= n0) || (!c && i < n0));
+
+ /*
+ * Request constraints for new events; or for those events that
+ * have a dynamic constraint -- for those the constraint can
+ * change due to external factors (sibling state, allow_tfa).
+ */
+ if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) {
+ c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
+ cpuc->event_constraint[i] = c;
+ }
wmin = min(wmin, c->weight);
wmax = max(wmax, c->weight);
if (!unsched && assign) {
for (i = 0; i < n; i++) {
e = cpuc->event_list[i];
- e->hw.flags |= PERF_X86_EVENT_COMMITTED;
if (x86_pmu.commit_scheduling)
x86_pmu.commit_scheduling(cpuc, i, assign[i]);
}
} else {
- for (i = 0; i < n; i++) {
+ for (i = n0; i < n; i++) {
e = cpuc->event_list[i];
- /*
- * do not put_constraint() on comitted events,
- * because they are good to go
- */
- if ((e->hw.flags & PERF_X86_EVENT_COMMITTED))
- continue;
/*
* release events that failed scheduling
*/
if (x86_pmu.put_event_constraints)
x86_pmu.put_event_constraints(cpuc, e);
+
+ cpuc->event_constraint[i] = NULL;
}
}
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int i;
- /*
- * event is descheduled
- */
- event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
-
/*
* If we're called during a txn, we only need to undo x86_pmu.add.
* The events never got scheduled and ->cancel_txn will truncate
cpuc->event_list[i-1] = cpuc->event_list[i];
cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
}
+ cpuc->event_constraint[i-1] = NULL;
--cpuc->n_events;
perf_event_update_userpage(event);
if (IS_ERR(fake_cpuc))
return PTR_ERR(fake_cpuc);
- c = x86_pmu.get_event_constraints(fake_cpuc, -1, event);
+ c = x86_pmu.get_event_constraints(fake_cpuc, 0, event);
if (!c || !c->weight)
ret = -EINVAL;
if (n < 0)
goto out;
- fake_cpuc->n_events = n;
-
+ fake_cpuc->n_events = 0;
ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
out:
cyc2ns_read_end();
}
+/*
+ * Determine whether the regs were taken from an irq/exception handler rather
+ * than from perf_arch_fetch_caller_regs().
+ */
+static bool perf_hw_regs(struct pt_regs *regs)
+{
+ return regs->flags & X86_EFLAGS_FIXED;
+}
+
void
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
return;
}
- if (perf_callchain_store(entry, regs->ip))
- return;
+ if (perf_hw_regs(regs)) {
+ if (perf_callchain_store(entry, regs->ip))
+ return;
+ unwind_start(&state, current, regs, NULL);
+ } else {
+ unwind_start(&state, current, NULL, (void *)regs->sp);
+ }
- for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
- unwind_next_frame(&state)) {
+ for (; !unwind_done(&state); unwind_next_frame(&state)) {
addr = unwind_get_return_address(&state);
if (!addr || perf_callchain_store(entry, addr))
return;
EVENT_EXTRA_END
};
+static struct event_constraint intel_icl_event_constraints[] = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
+ INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */
+ INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.STALLS_MEM_ANY */
+ INTEL_EVENT_CONSTRAINT(0xa3, 0xf), /* CYCLE_ACTIVITY.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
+ EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+ EVENT_EXTRA_END
+};
+
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
},
};
+#define TNT_LOCAL_DRAM BIT_ULL(26)
+#define TNT_DEMAND_READ GLM_DEMAND_DATA_RD
+#define TNT_DEMAND_WRITE GLM_DEMAND_RFO
+#define TNT_LLC_ACCESS GLM_ANY_RESPONSE
+#define TNT_SNP_ANY (SNB_SNP_NOT_NEEDED|SNB_SNP_MISS| \
+ SNB_NO_FWD|SNB_SNP_FWD|SNB_HITM)
+#define TNT_LLC_MISS (TNT_SNP_ANY|SNB_NON_DRAM|TNT_LOCAL_DRAM)
+
+static __initconst const u64 tnt_hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = TNT_DEMAND_READ|
+ TNT_LLC_ACCESS,
+ [C(RESULT_MISS)] = TNT_DEMAND_READ|
+ TNT_LLC_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = TNT_DEMAND_WRITE|
+ TNT_LLC_ACCESS,
+ [C(RESULT_MISS)] = TNT_DEMAND_WRITE|
+ TNT_LLC_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0x0,
+ [C(RESULT_MISS)] = 0x0,
+ },
+ },
+};
+
+static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
+ /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1),
+ EVENT_EXTRA_END
+};
+
#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */
#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */
#define KNL_MCDRAM_LOCAL BIT_ULL(21)
/*
* We're going to use PMC3, make sure TFA is set before we touch it.
*/
- if (cntr == 3 && !cpuc->is_fake)
+ if (cntr == 3)
intel_set_tfa(cpuc, true);
}
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
cpuc->intel_cp_status &= ~(1ull << hwc->idx);
- if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_disable(event);
-
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc);
return;
}
x86_pmu_disable_event(event);
+
+ /*
+ * Needs to be called after x86_pmu_disable_event,
+ * so we don't trigger the event without PEBS bit set.
+ */
+ if (unlikely(event->attr.precise_ip))
+ intel_pmu_pebs_disable(event);
}
static void intel_pmu_del_event(struct perf_event *event)
bits <<= (idx * 4);
mask = 0xfULL << (idx * 4);
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) {
+ bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ }
+
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
ctrl_val |= bits;
if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
struct intel_excl_states *xlo;
int tid = cpuc->excl_thread_id;
- int is_excl, i;
+ int is_excl, i, w;
/*
* validating a group does not require
* SHARED : sibling counter measuring non-exclusive event
* UNUSED : sibling counter unused
*/
+ w = c->weight;
for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
/*
* exclusive event in sibling counter
* our corresponding counter cannot be used
* regardless of our event
*/
- if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+ if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) {
__clear_bit(i, c->idxmsk);
+ w--;
+ continue;
+ }
/*
* if measuring an exclusive event, sibling
* measuring non-exclusive, then counter cannot
* be used
*/
- if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+ if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) {
__clear_bit(i, c->idxmsk);
+ w--;
+ continue;
+ }
}
- /*
- * recompute actual bit weight for scheduling algorithm
- */
- c->weight = hweight64(c->idxmsk64);
-
/*
* if we return an empty mask, then switch
* back to static empty constraint to avoid
* the cost of freeing later on
*/
- if (c->weight == 0)
+ if (!w)
c = &emptyconstraint;
+ c->weight = w;
+
return c;
}
intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
{
- struct event_constraint *c1 = NULL;
- struct event_constraint *c2;
+ struct event_constraint *c1, *c2;
- if (idx >= 0) /* fake does < 0 */
- c1 = cpuc->event_constraint[idx];
+ c1 = cpuc->event_constraint[idx];
/*
* first time only
* - dynamic constraint: handled by intel_get_excl_constraints()
*/
c2 = __intel_get_event_constraints(cpuc, idx, event);
- if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) {
+ if (c1) {
+ WARN_ON_ONCE(!(c1->flags & PERF_X86_EVENT_DYNAMIC));
bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX);
c1->weight = c2->weight;
c2 = c1;
flags &= ~PERF_SAMPLE_TIME;
if (!event->attr.exclude_kernel)
flags &= ~PERF_SAMPLE_REGS_USER;
- if (event->attr.sample_regs_user & ~PEBS_REGS)
+ if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
return flags;
}
static struct event_constraint counter2_constraint =
EVENT_CONSTRAINT(0, 0x4, 0);
+static struct event_constraint fixed0_constraint =
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0);
+
+static struct event_constraint fixed0_counter0_constraint =
+ INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL);
+
static struct event_constraint *
hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
return c;
}
+static struct event_constraint *
+icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ /*
+ * Fixed counter 0 has less skid.
+ * Force instruction:ppp in Fixed counter 0
+ */
+ if ((event->attr.precise_ip == 3) &&
+ constraint_match(&fixed0_constraint, event->hw.config))
+ return &fixed0_constraint;
+
+ return hsw_get_event_constraints(cpuc, idx, event);
+}
+
static struct event_constraint *
glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
return c;
}
+static struct event_constraint *
+tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ struct event_constraint *c;
+
+ /*
+ * :ppp means to do reduced skid PEBS,
+ * which is available on PMC0 and fixed counter 0.
+ */
+ if (event->attr.precise_ip == 3) {
+ /* Force instruction:ppp on PMC0 and Fixed counter 0 */
+ if (constraint_match(&fixed0_constraint, event->hw.config))
+ return &fixed0_counter0_constraint;
+
+ return &counter0_constraint;
+ }
+
+ c = intel_get_event_constraints(cpuc, idx, event);
+
+ return c;
+}
+
static bool allow_tsx_force_abort = true;
static struct event_constraint *
/*
* Without TFA we must not use PMC3.
*/
- if (!allow_tsx_force_abort && test_bit(3, c->idxmsk) && idx >= 0) {
+ if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) {
c = dyn_constraint(cpuc, c, idx);
c->idxmsk64 &= ~(1ULL << 3);
c->weight--;
int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
{
+ cpuc->pebs_record_size = x86_pmu.pebs_record_size;
+
if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
cpuc->shared_regs = allocate_shared_regs(cpu);
if (!cpuc->shared_regs)
NULL
};
+EVENT_ATTR_STR(tx-capacity-read, tx_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-capacity-read, el_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2");
+
+static struct attribute *icl_events_attrs[] = {
+ EVENT_PTR(mem_ld_hsw),
+ EVENT_PTR(mem_st_hsw),
+ NULL,
+};
+
+static struct attribute *icl_tsx_events_attrs[] = {
+ EVENT_PTR(tx_start),
+ EVENT_PTR(tx_abort),
+ EVENT_PTR(tx_commit),
+ EVENT_PTR(tx_capacity_read),
+ EVENT_PTR(tx_capacity_write),
+ EVENT_PTR(tx_conflict),
+ EVENT_PTR(el_start),
+ EVENT_PTR(el_abort),
+ EVENT_PTR(el_commit),
+ EVENT_PTR(el_capacity_read),
+ EVENT_PTR(el_capacity_write),
+ EVENT_PTR(el_conflict),
+ EVENT_PTR(cycles_t),
+ EVENT_PTR(cycles_ct),
+ NULL,
+};
+
+static __init struct attribute **get_icl_events_attrs(void)
+{
+ return boot_cpu_has(X86_FEATURE_RTM) ?
+ merge_attr(icl_events_attrs, icl_tsx_events_attrs) :
+ icl_events_attrs;
+}
+
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
char *buf)
return count;
}
+static void update_tfa_sched(void *ignored)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ /*
+ * check if PMC3 is used
+ * and if so force schedule out for all event types all contexts
+ */
+ if (test_bit(3, cpuc->active_mask))
+ perf_pmu_resched(x86_get_pmu());
+}
+
+static ssize_t show_sysctl_tfa(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, 40, "%d\n", allow_tsx_force_abort);
+}
+
+static ssize_t set_sysctl_tfa(struct device *cdev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ bool val;
+ ssize_t ret;
+
+ ret = kstrtobool(buf, &val);
+ if (ret)
+ return ret;
+
+ /* no change */
+ if (val == allow_tsx_force_abort)
+ return count;
+
+ allow_tsx_force_abort = val;
+
+ get_online_cpus();
+ on_each_cpu(update_tfa_sched, NULL, 1);
+ put_online_cpus();
+
+ return count;
+}
+
+
static DEVICE_ATTR_RW(freeze_on_smi);
static ssize_t branches_show(struct device *cdev,
NULL
};
-static DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort);
+static DEVICE_ATTR(allow_tsx_force_abort, 0644,
+ show_sysctl_tfa,
+ set_sysctl_tfa);
static struct attribute *intel_pmu_attrs[] = {
&dev_attr_freeze_on_smi.attr,
name = "goldmont_plus";
break;
+ case INTEL_FAM6_ATOM_TREMONT_X:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
+ hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+ intel_pmu_lbr_init_skl();
+
+ x86_pmu.event_constraints = intel_slm_event_constraints;
+ x86_pmu.extra_regs = intel_tnt_extra_regs;
+ /*
+ * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+ * for precise cycles.
+ */
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.lbr_pt_coexist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.get_event_constraints = tnt_get_event_constraints;
+ extra_attr = slm_format_attr;
+ pr_cont("Tremont events, ");
+ name = "Tremont";
+ break;
+
case INTEL_FAM6_WESTMERE:
case INTEL_FAM6_WESTMERE_EP:
case INTEL_FAM6_WESTMERE_EX:
x86_pmu.get_event_constraints = tfa_get_event_constraints;
x86_pmu.enable_all = intel_tfa_pmu_enable_all;
x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
- intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr;
+ intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr;
}
pr_cont("Skylake events, ");
name = "skylake";
break;
+ case INTEL_FAM6_ICELAKE_MOBILE:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+ hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+ intel_pmu_lbr_init_skl();
+
+ x86_pmu.event_constraints = intel_icl_event_constraints;
+ x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_icl_extra_regs;
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+ x86_pmu.hw_config = hsw_hw_config;
+ x86_pmu.get_event_constraints = icl_get_event_constraints;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ hsw_format_attr : nhm_format_attr;
+ extra_attr = merge_attr(extra_attr, skl_format_attr);
+ x86_pmu.cpu_events = get_icl_events_attrs();
+ x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
+ x86_pmu.lbr_pt_coexist = true;
+ intel_pmu_pebs_data_source_skl(false);
+ pr_cont("Icelake events, ");
+ name = "icelake";
+ break;
+
default:
switch (x86_pmu.version) {
case 1:
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
- * Available model: HSW ULT,GLM,CNL
+ * Available model: HSW ULT,KBL,GLM,CNL
* Scope: Package (physical package)
*
*/
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, hswult_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+
+ X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_icl_pebs_event_constraints[] = {
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */
+
+ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
+
+ /*
+ * Everything else is handled by PMU_FL_PEBS_ALL, because we
+ * need the full constraints from the main table.
+ */
+
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *c;
if (x86_pmu.pebs_constraints) {
for_each_event_constraint(c, x86_pmu.pebs_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
if (cpuc->n_pebs == cpuc->n_large_pebs) {
threshold = ds->pebs_absolute_maximum -
- reserved * x86_pmu.pebs_record_size;
+ reserved * cpuc->pebs_record_size;
} else {
- threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+ threshold = ds->pebs_buffer_base + cpuc->pebs_record_size;
}
ds->pebs_interrupt_threshold = threshold;
}
+static void adaptive_pebs_record_size_update(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ u64 pebs_data_cfg = cpuc->pebs_data_cfg;
+ int sz = sizeof(struct pebs_basic);
+
+ if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+ sz += sizeof(struct pebs_meminfo);
+ if (pebs_data_cfg & PEBS_DATACFG_GP)
+ sz += sizeof(struct pebs_gprs);
+ if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+ sz += sizeof(struct pebs_xmm);
+ if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+ sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+
+ cpuc->pebs_record_size = sz;
+}
+
+#define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \
+ PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
+ PERF_SAMPLE_TRANSACTION)
+
+static u64 pebs_update_adaptive_cfg(struct perf_event *event)
+{
+ struct perf_event_attr *attr = &event->attr;
+ u64 sample_type = attr->sample_type;
+ u64 pebs_data_cfg = 0;
+ bool gprs, tsx_weight;
+
+ if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
+ attr->precise_ip > 1)
+ return pebs_data_cfg;
+
+ if (sample_type & PERF_PEBS_MEMINFO_TYPE)
+ pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+
+ /*
+ * We need GPRs when:
+ * + user requested them
+ * + precise_ip < 2 for the non event IP
+ * + For RTM TSX weight we need GPRs for the abort code.
+ */
+ gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_GP_REGS);
+
+ tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+ ((attr->config & INTEL_ARCH_EVENT_MASK) ==
+ x86_pmu.rtm_abort_event);
+
+ if (gprs || (attr->precise_ip < 2) || tsx_weight)
+ pebs_data_cfg |= PEBS_DATACFG_GP;
+
+ if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_XMM_REGS))
+ pebs_data_cfg |= PEBS_DATACFG_XMMS;
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ /*
+ * For now always log all LBRs. Could configure this
+ * later.
+ */
+ pebs_data_cfg |= PEBS_DATACFG_LBRS |
+ ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
+ }
+
+ return pebs_data_cfg;
+}
+
static void
-pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
+ struct perf_event *event, bool add)
{
+ struct pmu *pmu = event->ctx->pmu;
/*
* Make sure we get updated with the first PEBS
* event. It will trigger also during removal, but
update = true;
}
+ /*
+ * The PEBS record doesn't shrink on pmu::del(). Doing so would require
+ * iterating all remaining PEBS events to reconstruct the config.
+ */
+ if (x86_pmu.intel_cap.pebs_baseline && add) {
+ u64 pebs_data_cfg;
+
+ /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
+ if (cpuc->n_pebs == 1) {
+ cpuc->pebs_data_cfg = 0;
+ cpuc->pebs_record_size = sizeof(struct pebs_basic);
+ }
+
+ pebs_data_cfg = pebs_update_adaptive_cfg(event);
+
+ /* Update pebs_record_size if new event requires more data. */
+ if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
+ cpuc->pebs_data_cfg |= pebs_data_cfg;
+ adaptive_pebs_record_size_update();
+ update = true;
+ }
+ }
+
if (update)
pebs_update_threshold(cpuc);
}
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs++;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, true);
}
void intel_pmu_pebs_enable(struct perf_event *event)
cpuc->pebs_enabled |= 1ULL << hwc->idx;
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ hwc->config |= ICL_EVENTSEL_ADAPTIVE;
+ if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+ wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
+ cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+ }
+ }
+
/*
* Use auto-reload if possible to save a MSR write in the PMI.
* This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs--;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, false);
}
void intel_pmu_pebs_disable(struct perf_event *event)
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
+ (x86_pmu.version < 5))
cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled &= ~(1ULL << 63);
return 0;
}
-static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_weight(u64 tsx_tuning)
{
- if (pebs->tsx_tuning) {
- union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+ if (tsx_tuning) {
+ union hsw_tsx_tuning tsx = { .value = tsx_tuning };
return tsx.cycles_last_block;
}
return 0;
}
-static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
{
- u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+ u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
/* For RTM XABORTs also log the abort code from AX */
- if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
- txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ if ((txn & PERF_TXN_TRANSACTION) && (ax & 1))
+ txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
return txn;
}
-static void setup_pebs_sample_data(struct perf_event *event,
- struct pt_regs *iregs, void *__pebs,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+static inline u64 get_pebs_status(void *n)
{
+ if (x86_pmu.intel_cap.pebs_format < 4)
+ return ((struct pebs_record_nhm *)n)->status;
+ return ((struct pebs_basic *)n)->applicable_counters;
+}
+
#define PERF_X86_EVENT_PEBS_HSW_PREC \
(PERF_X86_EVENT_PEBS_ST_HSW | \
PERF_X86_EVENT_PEBS_LD_HSW | \
PERF_X86_EVENT_PEBS_NA_HSW)
+
+static u64 get_data_src(struct perf_event *event, u64 aux)
+{
+ u64 val = PERF_MEM_NA;
+ int fl = event->hw.flags;
+ bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+
+ if (fl & PERF_X86_EVENT_PEBS_LDLAT)
+ val = load_latency_data(aux);
+ else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+ val = precise_datala_hsw(event, aux);
+ else if (fst)
+ val = precise_store_data(aux);
+ return val;
+}
+
+static void setup_pebs_fixed_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
/*
* We cast to the biggest pebs_record but are careful not to
* unconditionally access the 'extra' entries.
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_record_skl *pebs = __pebs;
u64 sample_type;
- int fll, fst, dsrc;
- int fl = event->hw.flags;
+ int fll;
if (pebs == NULL)
return;
sample_type = event->attr.sample_type;
- dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
-
- fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
- fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+ fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
perf_sample_data_init(data, 0, event->hw.last_period);
/*
* data.data_src encodes the data source
*/
- if (dsrc) {
- u64 val = PERF_MEM_NA;
- if (fll)
- val = load_latency_data(pebs->dse);
- else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
- val = precise_datala_hsw(event, pebs->dse);
- else if (fst)
- val = precise_store_data(pebs->dse);
- data->data_src.val = val;
- }
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, pebs->dse);
/*
* We must however always use iregs for the unwinder to stay sane; the
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
- data->weight = intel_hsw_weight(pebs);
+ data->weight = intel_get_tsx_weight(pebs->tsx_tuning);
if (sample_type & PERF_SAMPLE_TRANSACTION)
- data->txn = intel_hsw_transaction(pebs);
+ data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
+ pebs->ax);
}
/*
data->br_stack = &cpuc->lbr_stack;
}
+static void adaptive_pebs_save_regs(struct pt_regs *regs,
+ struct pebs_gprs *gprs)
+{
+ regs->ax = gprs->ax;
+ regs->bx = gprs->bx;
+ regs->cx = gprs->cx;
+ regs->dx = gprs->dx;
+ regs->si = gprs->si;
+ regs->di = gprs->di;
+ regs->bp = gprs->bp;
+ regs->sp = gprs->sp;
+#ifndef CONFIG_X86_32
+ regs->r8 = gprs->r8;
+ regs->r9 = gprs->r9;
+ regs->r10 = gprs->r10;
+ regs->r11 = gprs->r11;
+ regs->r12 = gprs->r12;
+ regs->r13 = gprs->r13;
+ regs->r14 = gprs->r14;
+ regs->r15 = gprs->r15;
+#endif
+}
+
+/*
+ * With adaptive PEBS the layout depends on what fields are configured.
+ */
+
+static void setup_pebs_adaptive_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct pebs_basic *basic = __pebs;
+ void *next_record = basic + 1;
+ u64 sample_type;
+ u64 format_size;
+ struct pebs_meminfo *meminfo = NULL;
+ struct pebs_gprs *gprs = NULL;
+ struct x86_perf_regs *perf_regs;
+
+ if (basic == NULL)
+ return;
+
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ perf_regs->xmm_regs = NULL;
+
+ sample_type = event->attr.sample_type;
+ format_size = basic->format_size;
+ perf_sample_data_init(data, 0, event->hw.last_period);
+ data->period = event->hw.last_period;
+
+ if (event->attr.use_clockid == 0)
+ data->time = native_sched_clock_from_tsc(basic->tsc);
+
+ /*
+ * We must however always use iregs for the unwinder to stay sane; the
+ * record BP,SP,IP can point into thin air when the record is from a
+ * previous PMI context or an (I)RET happened between the record and
+ * PMI.
+ */
+ if (sample_type & PERF_SAMPLE_CALLCHAIN)
+ data->callchain = perf_callchain(event, iregs);
+
+ *regs = *iregs;
+ /* The ip in basic is EventingIP */
+ set_linear_ip(regs, basic->ip);
+ regs->flags = PERF_EFLAGS_EXACT;
+
+ /*
+ * The record for MEMINFO is in front of GP
+ * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
+ * Save the pointer here but process later.
+ */
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ meminfo = next_record;
+ next_record = meminfo + 1;
+ }
+
+ if (format_size & PEBS_DATACFG_GP) {
+ gprs = next_record;
+ next_record = gprs + 1;
+
+ if (event->attr.precise_ip < 2) {
+ set_linear_ip(regs, gprs->ip);
+ regs->flags &= ~PERF_EFLAGS_EXACT;
+ }
+
+ if (sample_type & PERF_SAMPLE_REGS_INTR)
+ adaptive_pebs_save_regs(regs, gprs);
+ }
+
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ if (sample_type & PERF_SAMPLE_WEIGHT)
+ data->weight = meminfo->latency ?:
+ intel_get_tsx_weight(meminfo->tsx_tuning);
+
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, meminfo->aux);
+
+ if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+ data->addr = meminfo->address;
+
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
+ gprs ? gprs->ax : 0);
+ }
+
+ if (format_size & PEBS_DATACFG_XMMS) {
+ struct pebs_xmm *xmm = next_record;
+
+ next_record = xmm + 1;
+ perf_regs->xmm_regs = xmm->xmm;
+ }
+
+ if (format_size & PEBS_DATACFG_LBRS) {
+ struct pebs_lbr *lbr = next_record;
+ int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+ & 0xff) + 1;
+ next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+
+ if (has_branch_stack(event)) {
+ intel_pmu_store_pebs_lbrs(lbr);
+ data->br_stack = &cpuc->lbr_stack;
+ }
+ }
+
+ WARN_ONCE(next_record != __pebs + (format_size >> 48),
+ "PEBS record size %llu, expected %llu, config %llx\n",
+ format_size >> 48,
+ (u64)(next_record - __pebs),
+ basic->format_size);
+}
+
static inline void *
get_next_pebs_record_by_bit(void *base, void *top, int bit)
{
if (base == NULL)
return NULL;
- for (at = base; at < top; at += x86_pmu.pebs_record_size) {
- struct pebs_record_nhm *p = at;
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ unsigned long status = get_pebs_status(at);
- if (test_bit(bit, (unsigned long *)&p->status)) {
+ if (test_bit(bit, (unsigned long *)&status)) {
/* PEBS v3 has accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3)
return at;
- if (p->status == (1 << bit))
+ if (status == (1 << bit))
return at;
/* clear non-PEBS bit and re-check */
- pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status = status & cpuc->pebs_enabled;
pebs_status &= PEBS_COUNTER_MASK;
if (pebs_status == (1 << bit))
return at;
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs,
void *base, void *top,
- int bit, int count)
+ int bit, int count,
+ void (*setup_sample)(struct perf_event *,
+ struct pt_regs *,
+ void *,
+ struct perf_sample_data *,
+ struct pt_regs *))
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
struct perf_sample_data data;
- struct pt_regs regs;
+ struct x86_perf_regs perf_regs;
+ struct pt_regs *regs = &perf_regs.regs;
void *at = get_next_pebs_record_by_bit(base, top, bit);
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
return;
while (count > 1) {
- setup_pebs_sample_data(event, iregs, at, &data, ®s);
- perf_event_output(event, &data, ®s);
- at += x86_pmu.pebs_record_size;
+ setup_sample(event, iregs, at, &data, regs);
+ perf_event_output(event, &data, regs);
+ at += cpuc->pebs_record_size;
at = get_next_pebs_record_by_bit(at, top, bit);
count--;
}
- setup_pebs_sample_data(event, iregs, at, &data, ®s);
+ setup_sample(event, iregs, at, &data, regs);
/*
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, &data, ®s)) {
+ if (perf_event_overflow(event, &data, regs)) {
x86_pmu_stop(event, 0);
return;
}
return;
}
- __intel_pmu_pebs_event(event, iregs, at, top, 0, n);
+ __intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+ setup_pebs_fixed_sample_data);
+}
+
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+{
+ struct perf_event *event;
+ int bit;
+
+ /*
+ * The drain_pebs() could be called twice in a short period
+ * for auto-reload event in pmu::read(). There are no
+ * overflows have happened in between.
+ * It needs to call intel_pmu_save_and_restart_reload() to
+ * update the event->count for this case.
+ */
+ for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+ event = cpuc->events[bit];
+ if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+ intel_pmu_save_and_restart_reload(event, 0);
+ }
}
static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
}
if (unlikely(base >= top)) {
- /*
- * The drain_pebs() could be called twice in a short period
- * for auto-reload event in pmu::read(). There are no
- * overflows have happened in between.
- * It needs to call intel_pmu_save_and_restart_reload() to
- * update the event->count for this case.
- */
- for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
- size) {
- event = cpuc->events[bit];
- if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
- intel_pmu_save_and_restart_reload(event, 0);
- }
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
return;
}
/* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&pebs_status,
- size)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
counts[bit]++;
continue;
* If collision happened, the record will be dropped.
*/
if (p->status != (1ULL << bit)) {
- for_each_set_bit(i, (unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events)
+ for_each_set_bit(i, (unsigned long *)&pebs_status, size)
error[i]++;
continue;
}
counts[bit]++;
}
- for (bit = 0; bit < size; bit++) {
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
if ((counts[bit] == 0) && (error[bit] == 0))
continue;
if (counts[bit]) {
__intel_pmu_pebs_event(event, iregs, base,
- top, bit, counts[bit]);
+ top, bit, counts[bit],
+ setup_pebs_fixed_sample_data);
}
}
}
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+{
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct perf_event *event;
+ void *base, *at, *top;
+ int bit, size;
+ u64 mask;
+
+ if (!x86_pmu.pebs_active)
+ return;
+
+ base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_basic *)(unsigned long)ds->pebs_index;
+
+ ds->pebs_index = ds->pebs_buffer_base;
+
+ mask = ((1ULL << x86_pmu.max_pebs_events) - 1) |
+ (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
+ size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+
+ if (unlikely(base >= top)) {
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
+ return;
+ }
+
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ u64 pebs_status;
+
+ pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+ pebs_status &= mask;
+
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+ counts[bit]++;
+ }
+
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
+ if (counts[bit] == 0)
+ continue;
+
+ event = cpuc->events[bit];
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
+
+ __intel_pmu_pebs_event(event, iregs, base,
+ top, bit, counts[bit],
+ setup_pebs_adaptive_sample_data);
+ }
+}
+
/*
* BTS, PEBS probe and setup
*/
x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
- if (x86_pmu.version <= 4)
+ if (x86_pmu.version <= 4) {
x86_pmu.pebs_no_isolation = 1;
+ x86_pmu.pebs_no_xmm_regs = 1;
+ }
if (x86_pmu.pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
+ char *pebs_qual = "";
int format = x86_pmu.intel_cap.pebs_format;
+ if (format < 4)
+ x86_pmu.intel_cap.pebs_baseline = 0;
+
switch (format) {
case 0:
pr_cont("PEBS fmt0%c, ", pebs_type);
x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
break;
+ case 4:
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
+ x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ x86_pmu.large_pebs_flags |=
+ PERF_SAMPLE_BRANCH_STACK |
+ PERF_SAMPLE_TIME;
+ x86_pmu.flags |= PMU_FL_PEBS_ALL;
+ pebs_qual = "-baseline";
+ } else {
+ /* Only basic record supported */
+ x86_pmu.pebs_no_xmm_regs = 1;
+ x86_pmu.large_pebs_flags &=
+ ~(PERF_SAMPLE_ADDR |
+ PERF_SAMPLE_TIME |
+ PERF_SAMPLE_DATA_SRC |
+ PERF_SAMPLE_TRANSACTION |
+ PERF_SAMPLE_REGS_USER |
+ PERF_SAMPLE_REGS_INTR);
+ }
+ pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+ break;
+
default:
pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
* be 'new'. Conversely, a new event can get installed through the
* context switch path for the first time.
*/
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users++;
perf_sched_cb_inc(event->ctx->pmu);
if (!cpuc->lbr_users++ && !event->total_time_running)
intel_pmu_lbr_reset();
task_ctx->lbr_callstack_users--;
}
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users--;
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
+ WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
perf_sched_cb_dec(event->ctx->pmu);
}
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- if (!cpuc->lbr_users)
+ /*
+ * Don't read when all LBRs users are using adaptive PEBS.
+ *
+ * This could be smarter and actually check the event,
+ * but this simple approach seems to work for now.
+ */
+ if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
return;
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
}
}
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int i;
+
+ cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+ for (i = 0; i < x86_pmu.lbr_nr; i++) {
+ u64 info = lbr->lbr[i].info;
+ struct perf_branch_entry *e = &cpuc->lbr_entries[i];
+
+ e->from = lbr->lbr[i].from;
+ e->to = lbr->lbr[i].to;
+ e->mispred = !!(info & LBR_INFO_MISPRED);
+ e->predicted = !(info & LBR_INFO_MISPRED);
+ e->in_tx = !!(info & LBR_INFO_IN_TX);
+ e->abort = !!(info & LBR_INFO_ABORT);
+ e->cycles = info & LBR_INFO_CYCLES;
+ e->reserved = 0;
+ }
+ intel_pmu_lbr_filter(cpuc);
+}
+
/*
* Map interface branch filters onto LBR filters
*/
}
if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
- pt_pmu.pmu.capabilities =
- PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
+ pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
pt_pmu.pmu.attr_groups = pt_attr_groups;
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
+
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init),
{},
};
.pci_init = skx_uncore_pci_init,
};
+static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
+ .cpu_init = icl_uncore_cpu_init,
+ .pci_init = skl_uncore_pci_init,
+};
+
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
{},
};
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
void skl_uncore_cpu_init(void);
+void icl_uncore_cpu_init(void);
int snb_pci2phy_map_init(int devid);
/* uncore_snbep.c */
#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33
#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca
#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32
+#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02
+#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
#define SKL_UNC_PERF_GLOBAL_CTL 0xe01
#define SKL_UNC_GLOBAL_CTL_CORE_ALL ((1 << 5) - 1)
+/* ICL Cbo register */
+#define ICL_UNC_CBO_CONFIG 0x396
+#define ICL_UNC_NUM_CBO_MASK 0xf
+#define ICL_UNC_CBO_0_PER_CTR0 0x702
+#define ICL_UNC_CBO_MSR_OFFSET 0x8
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
snb_uncore_arb.ops = &skl_uncore_msr_ops;
}
+static struct intel_uncore_type icl_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .perf_ctr_bits = 44,
+ .perf_ctr = ICL_UNC_CBO_0_PER_CTR0,
+ .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0,
+ .event_mask = SNB_UNC_RAW_EVENT_MASK,
+ .msr_offset = ICL_UNC_CBO_MSR_OFFSET,
+ .ops = &skl_uncore_msr_ops,
+ .format_group = &snb_uncore_format_group,
+};
+
+static struct uncore_event_desc icl_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute *icl_uncore_clock_formats_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group icl_uncore_clock_format_group = {
+ .name = "format",
+ .attrs = icl_uncore_clock_formats_attr,
+};
+
+static struct intel_uncore_type icl_uncore_clockbox = {
+ .name = "clock",
+ .num_counters = 1,
+ .num_boxes = 1,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNB_UNC_FIXED_CTR,
+ .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL,
+ .single_fixed = 1,
+ .event_mask = SNB_UNC_CTL_EV_SEL_MASK,
+ .format_group = &icl_uncore_clock_format_group,
+ .ops = &skl_uncore_msr_ops,
+ .event_descs = icl_uncore_events,
+};
+
+static struct intel_uncore_type *icl_msr_uncores[] = {
+ &icl_uncore_cbox,
+ &snb_uncore_arb,
+ &icl_uncore_clockbox,
+ NULL,
+};
+
+static int icl_get_cbox_num(void)
+{
+ u64 num_boxes;
+
+ rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes);
+
+ return num_boxes & ICL_UNC_NUM_CBO_MASK;
+}
+
+void icl_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = icl_msr_uncores;
+ icl_uncore_cbox.num_boxes = icl_get_cbox_num();
+ snb_uncore_arb.ops = &skl_uncore_msr_ops;
+}
+
enum {
SNB_PCI_UNCORE_IMC,
};
{ /* end: all zeroes */ },
};
+static const struct pci_device_id icl_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
static struct pci_driver snb_uncore_pci_driver = {
.name = "snb_uncore",
.id_table = snb_uncore_pci_ids,
.id_table = skl_uncore_pci_ids,
};
+static struct pci_driver icl_uncore_pci_driver = {
+ .name = "icl_uncore",
+ .id_table = icl_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */
IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */
IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */
+ IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
+ IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
{ /* end marker */ }
};
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_KABYLAKE_DESKTOP:
+ case INTEL_FAM6_ICELAKE_MOBILE:
if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
return true;
break;
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
u64 idxmsk64;
};
- u64 code;
- u64 cmask;
- int weight;
- int overlap;
- int flags;
+ u64 code;
+ u64 cmask;
+ int weight;
+ int overlap;
+ int flags;
+ unsigned int size;
};
+
+static inline bool constraint_match(struct event_constraint *c, u64 ecode)
+{
+ return ((ecode & c->cmask) - c->code) <= (u64)c->size;
+}
+
/*
* struct hw_perf_event.flags flags
*/
#define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */
#define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */
#define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */
-#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */
-#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */
-#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */
-#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */
-#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */
-#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */
-#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */
-#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */
-
+#define PERF_X86_EVENT_PEBS_LD_HSW 0x0008 /* haswell style datala, load */
+#define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */
+#define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */
+#define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */
+#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */
+#define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */
struct amd_nb {
int nb_id; /* NorthBridge id */
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
PERF_SAMPLE_PERIOD)
-#define PEBS_REGS \
- (PERF_REG_X86_AX | \
- PERF_REG_X86_BX | \
- PERF_REG_X86_CX | \
- PERF_REG_X86_DX | \
- PERF_REG_X86_DI | \
- PERF_REG_X86_SI | \
- PERF_REG_X86_SP | \
- PERF_REG_X86_BP | \
- PERF_REG_X86_IP | \
- PERF_REG_X86_FLAGS | \
- PERF_REG_X86_R8 | \
- PERF_REG_X86_R9 | \
- PERF_REG_X86_R10 | \
- PERF_REG_X86_R11 | \
- PERF_REG_X86_R12 | \
- PERF_REG_X86_R13 | \
- PERF_REG_X86_R14 | \
- PERF_REG_X86_R15)
+#define PEBS_GP_REGS \
+ ((1ULL << PERF_REG_X86_AX) | \
+ (1ULL << PERF_REG_X86_BX) | \
+ (1ULL << PERF_REG_X86_CX) | \
+ (1ULL << PERF_REG_X86_DX) | \
+ (1ULL << PERF_REG_X86_DI) | \
+ (1ULL << PERF_REG_X86_SI) | \
+ (1ULL << PERF_REG_X86_SP) | \
+ (1ULL << PERF_REG_X86_BP) | \
+ (1ULL << PERF_REG_X86_IP) | \
+ (1ULL << PERF_REG_X86_FLAGS) | \
+ (1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
+
+#define PEBS_XMM_REGS \
+ ((1ULL << PERF_REG_X86_XMM0) | \
+ (1ULL << PERF_REG_X86_XMM1) | \
+ (1ULL << PERF_REG_X86_XMM2) | \
+ (1ULL << PERF_REG_X86_XMM3) | \
+ (1ULL << PERF_REG_X86_XMM4) | \
+ (1ULL << PERF_REG_X86_XMM5) | \
+ (1ULL << PERF_REG_X86_XMM6) | \
+ (1ULL << PERF_REG_X86_XMM7) | \
+ (1ULL << PERF_REG_X86_XMM8) | \
+ (1ULL << PERF_REG_X86_XMM9) | \
+ (1ULL << PERF_REG_X86_XMM10) | \
+ (1ULL << PERF_REG_X86_XMM11) | \
+ (1ULL << PERF_REG_X86_XMM12) | \
+ (1ULL << PERF_REG_X86_XMM13) | \
+ (1ULL << PERF_REG_X86_XMM14) | \
+ (1ULL << PERF_REG_X86_XMM15))
/*
* Per register state.
int n_pebs;
int n_large_pebs;
+ /* Current super set of events hardware configuration */
+ u64 pebs_data_cfg;
+ u64 active_pebs_data_cfg;
+ int pebs_record_size;
+
/*
* Intel LBR bits
*/
int lbr_users;
+ int lbr_pebs_users;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
void *kfree_on_online[X86_PERF_KFREE_MAX];
};
-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \
{ .idxmsk64 = (n) }, \
.code = (c), \
+ .size = (e) - (c), \
.cmask = (m), \
.weight = (w), \
.overlap = (o), \
.flags = f, \
}
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
+ __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
+
#define EVENT_CONSTRAINT(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
+/*
+ * The constraint_match() function only works for 'simple' event codes
+ * and not for extended (AMD64_EVENTSEL_EVENT) events codes.
+ */
+#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
+ __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
+
#define INTEL_EXCLEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
0, PERF_X86_EVENT_EXCL)
#define INTEL_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
+/*
+ * Constraint on a range of Event codes
+ */
+#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
+
/*
* Constraint on the Event code + UMask + fixed-mask
*
#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
/* Check only flags, but allow all event/umask */
#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \
EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
+ __EVENT_CONSTRAINT_RANGE(code, end, n, \
+ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
* values > 32bit.
*/
u64 full_width_write:1;
+ u64 pebs_baseline:1;
};
u64 capabilities;
};
pebs_broken :1,
pebs_prec_dist :1,
pebs_no_tlb :1,
- pebs_no_isolation :1;
+ pebs_no_isolation :1,
+ pebs_no_xmm_regs :1;
int pebs_record_size;
int pebs_buffer_size;
+ int max_pebs_events;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
- int max_pebs_events;
unsigned long large_pebs_flags;
+ u64 rtm_abort_event;
/*
* Intel LBR
.event_str_ht = ht, \
}
+struct pmu *x86_get_pmu(void);
extern struct x86_pmu x86_pmu __read_mostly;
static inline bool x86_pmu_has_lbr_callstack(void)
extern struct event_constraint intel_skl_pebs_event_constraints[];
+extern struct event_constraint intel_icl_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_add(struct perf_event *event);
void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
} while (0)
#define RELOAD_SEG(seg) { \
- unsigned int pre = GET_SEG(seg); \
+ unsigned int pre = (seg) | 3; \
unsigned int cur = get_user_seg(seg); \
- pre |= 3; \
if (pre != cur) \
set_user_seg(seg, pre); \
}
struct sigcontext_32 __user *sc)
{
unsigned int tmpflags, err = 0;
+ u16 gs, fs, es, ds;
void __user *buf;
u32 tmp;
current->restart_block.fn = do_no_restart_syscall;
get_user_try {
- /*
- * Reload fs and gs if they have changed in the signal
- * handler. This does not handle long fs/gs base changes in
- * the handler, but does not clobber them at least in the
- * normal case.
- */
- RELOAD_SEG(gs);
- RELOAD_SEG(fs);
- RELOAD_SEG(ds);
- RELOAD_SEG(es);
+ gs = GET_SEG(gs);
+ fs = GET_SEG(fs);
+ ds = GET_SEG(ds);
+ es = GET_SEG(es);
COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
COPY(dx); COPY(cx); COPY(ip); COPY(ax);
buf = compat_ptr(tmp);
} get_user_catch(err);
+ /*
+ * Reload fs and gs if they have changed in the signal
+ * handler. This does not handle long fs/gs base changes in
+ * the handler, but does not clobber them at least in the
+ * normal case.
+ */
+ RELOAD_SEG(gs);
+ RELOAD_SEG(fs);
+ RELOAD_SEG(ds);
+ RELOAD_SEG(es);
+
err |= fpu__restore_sig(buf, 1);
force_iret();
.endm
#endif
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+.macro ANNOTATE_IGNORE_ALTERNATIVE
+ .Lannotate_\@:
+ .pushsection .discard.ignore_alts
+ .long .Lannotate_\@ - .
+ .popsection
+.endm
+
/*
* Issue one struct alt_instr descriptor entry (need to put it into
* the section .altinstructions, see below). This entry contains
#define LOCK_PREFIX ""
#endif
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+#define ANNOTATE_IGNORE_ALTERNATIVE \
+ "999:\n\t" \
+ ".pushsection .discard.ignore_alts\n\t" \
+ ".long 999b - .\n\t" \
+ ".popsection\n\t"
+
struct alt_instr {
s32 instr_offset; /* original instruction */
s32 repl_offset; /* offset to replacement instruction */
_ASM_PTR (entry); \
.popsection
-.macro ALIGN_DESTINATION
- /* check for bad alignment of destination */
- movl %edi,%ecx
- andl $7,%ecx
- jz 102f /* already aligned */
- subl $8,%ecx
- negl %ecx
- subl %ecx,%edx
-100: movb (%rsi),%al
-101: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 100b
-102:
- .section .fixup,"ax"
-103: addl %ecx,%edx /* ecx is zerorest also */
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE_UA(100b, 103b)
- _ASM_EXTABLE_UA(101b, 103b)
- .endm
-
#else
# define _EXPAND_EXTABLE_HANDLE(x) #x
# define _ASM_EXTABLE_HANDLE(from, to, handler) \
#else
/*
- * Static testing of CPU features. Used the same as boot_cpu_has().
- * These will statically patch the target code for additional
- * performance.
+ * Static testing of CPU features. Used the same as boot_cpu_has(). It
+ * statically patches the target code for additional performance. Use
+ * static_cpu_has() only in fast paths, where every cycle counts. Which
+ * means that the boot_cpu_has() variant is already fast enough for the
+ * majority of cases and you should stick to using it as it is generally
+ * only two instructions: a RIP-relative MOV and a TEST.
*/
-static __always_inline __pure bool _static_cpu_has(u16 bit)
+static __always_inline bool _static_cpu_has(u16 bit)
{
asm_volatile_goto("1: jmp 6f\n"
"2:\n"
WARN_ON(system_state != SYSTEM_BOOTING);
- if (static_cpu_has(X86_FEATURE_XSAVES))
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
else
XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
WARN_ON(system_state != SYSTEM_BOOTING);
- if (static_cpu_has(X86_FEATURE_XSAVES))
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
else
XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
* - switch_fpu_finish() restores the new state as
* necessary.
*/
-static inline void
-switch_fpu_prepare(struct fpu *old_fpu, int cpu)
+static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
{
if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
if (!copy_fpregs_to_fpstate(old_fpu))
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS 8
-#define MAX_FIXED_PEBS_EVENTS 3
+#define MAX_FIXED_PEBS_EVENTS 4
/*
* A debug store configuration.
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
- int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase);
+ int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt,
+ const char *smstate);
+ void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt);
};
}
#define KVM_PERMILLE_MMU_PAGES 20
-#define KVM_MIN_ALLOC_MMU_PAGES 64
+#define KVM_MIN_ALLOC_MMU_PAGES 64UL
#define KVM_MMU_HASH_SHIFT 12
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
#define KVM_MIN_FREE_MMU_PAGES 5
unsigned int valid:1;
unsigned int execonly:1;
unsigned int cr0_pg:1;
+ unsigned int cr4_pae:1;
unsigned int cr4_pse:1;
unsigned int cr4_pke:1;
unsigned int cr4_smap:1;
};
struct kvm_arch {
- unsigned int n_used_mmu_pages;
- unsigned int n_requested_mmu_pages;
- unsigned int n_max_mmu_pages;
+ unsigned long n_used_mmu_pages;
+ unsigned long n_requested_mmu_pages;
+ unsigned long n_max_mmu_pages;
unsigned int indirect_shadow_pages;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
/*
int (*smi_allowed)(struct kvm_vcpu *vcpu);
int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
- int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
+ int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
int (*enable_smi_window)(struct kvm_vcpu *vcpu);
int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
gfn_t gfn_offset, unsigned long mask);
void kvm_mmu_zap_all(struct kvm *kvm);
void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
bool pdptrs_changed(struct kvm_vcpu *vcpu);
#define put_smstate(type, buf, offset, val) \
*(type *)((buf) + (offset) - 0x7e00) = val
+#define GET_SMSTATE(type, buf, offset) \
+ (*(type *)((buf) + (offset) - 0x7e00))
+
#endif /* _ASM_X86_KVM_HOST_H */
#define LBR_INFO_CYCLES 0xffff
#define MSR_IA32_PEBS_ENABLE 0x000003f1
+#define MSR_PEBS_DATA_CFG 0x000003f2
#define MSR_IA32_DS_AREA 0x00000600
#define MSR_IA32_PERF_CAPABILITIES 0x00000345
#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
#include <asm/cpufeatures.h>
#include <asm/msr-index.h>
+/*
+ * This should be used immediately before a retpoline alternative. It tells
+ * objtool where the retpolines are so that it can make sense of the control
+ * flow by just reading the original instruction(s) and ignoring the
+ * alternatives.
+ */
+#define ANNOTATE_NOSPEC_ALTERNATIVE \
+ ANNOTATE_IGNORE_ALTERNATIVE
+
/*
* Fill the CPU return stack buffer.
*
#ifdef __ASSEMBLY__
-/*
- * This should be used immediately before a retpoline alternative. It tells
- * objtool where the retpolines are so that it can make sense of the control
- * flow by just reading the original instruction(s) and ignoring the
- * alternatives.
- */
-.macro ANNOTATE_NOSPEC_ALTERNATIVE
- .Lannotate_\@:
- .pushsection .discard.nospec
- .long .Lannotate_\@ - .
- .popsection
-.endm
-
/*
* This should be used immediately before an indirect jump/call. It tells
* objtool the subsequent indirect jump/call is vouched safe for retpoline
#else /* __ASSEMBLY__ */
-#define ANNOTATE_NOSPEC_ALTERNATIVE \
- "999:\n\t" \
- ".pushsection .discard.nospec\n\t" \
- ".long 999b - .\n\t" \
- ".popsection\n\t"
-
#define ANNOTATE_RETPOLINE_SAFE \
"999:\n\t" \
".pushsection .discard.retpoline_safe\n\t" \
*/
#define INTEL_PMC_MAX_GENERIC 32
-#define INTEL_PMC_MAX_FIXED 3
+#define INTEL_PMC_MAX_FIXED 4
#define INTEL_PMC_IDX_FIXED 32
#define X86_PMC_IDX_MAX 64
#define HSW_IN_TX (1ULL << 32)
#define HSW_IN_TX_CHECKPOINTED (1ULL << 33)
+#define ICL_EVENTSEL_ADAPTIVE (1ULL << 34)
+#define ICL_FIXED_0_ADAPTIVE (1ULL << 32)
#define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36)
#define AMD64_EVENTSEL_GUESTONLY (1ULL << 40)
#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6
#define ARCH_PERFMON_EVENTS_COUNT 7
+#define PEBS_DATACFG_MEMINFO BIT_ULL(0)
+#define PEBS_DATACFG_GP BIT_ULL(1)
+#define PEBS_DATACFG_XMMS BIT_ULL(2)
+#define PEBS_DATACFG_LBRS BIT_ULL(3)
+#define PEBS_DATACFG_LBR_SHIFT 24
+
/*
* Intel "Architectural Performance Monitoring" CPUID
* detection/enumeration details:
#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58)
#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55)
+/*
+ * Adaptive PEBS v4
+ */
+
+struct pebs_basic {
+ u64 format_size;
+ u64 ip;
+ u64 applicable_counters;
+ u64 tsc;
+};
+
+struct pebs_meminfo {
+ u64 address;
+ u64 aux;
+ u64 latency;
+ u64 tsx_tuning;
+};
+
+struct pebs_gprs {
+ u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di;
+ u64 r8, r9, r10, r11, r12, r13, r14, r15;
+};
+
+struct pebs_xmm {
+ u64 xmm[16*2]; /* two entries for each register */
+};
+
+struct pebs_lbr_entry {
+ u64 from, to, info;
+};
+
+struct pebs_lbr {
+ struct pebs_lbr_entry lbr[0]; /* Variable length */
+};
+
/*
* IBS cpuid feature detection
*/
#define PERF_EFLAGS_VM (1UL << 5)
struct pt_regs;
+struct x86_perf_regs {
+ struct pt_regs regs;
+ u64 *xmm_regs;
+};
+
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
extern unsigned long perf_misc_flags(struct pt_regs *regs);
#define perf_misc_flags(regs) perf_misc_flags(regs)
*/
#define perf_arch_fetch_caller_regs(regs, __ip) { \
(regs)->ip = (__ip); \
- (regs)->bp = caller_frame_pointer(); \
+ (regs)->sp = (unsigned long)__builtin_frame_address(0); \
(regs)->cs = __KERNEL_CS; \
regs->flags = 0; \
- asm volatile( \
- _ASM_MOV "%%"_ASM_SP ", %0\n" \
- : "=m" ((regs)->sp) \
- :: "memory" \
- ); \
}
struct perf_guest_switch_msr {
*/
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
__visible;
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page))
extern spinlock_t pgd_lock;
extern struct list_head pgd_list;
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
- *
- * Written by David Howells (dhowells@redhat.com).
- *
- * Derived from asm-x86/semaphore.h
- *
- *
- * The MSW of the count is the negated number of active writers and waiting
- * lockers, and the LSW is the total number of active locks
- *
- * The lock count is initialized to 0 (no active and no waiting lockers).
- *
- * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
- * uncontended lock. This can be determined because XADD returns the old value.
- * Readers increment by 1 and see a positive value when uncontended, negative
- * if there are writers (and maybe) readers waiting (in which case it goes to
- * sleep).
- *
- * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
- * be extended to 65534 by manually checking the whole MSW rather than relying
- * on the S flag.
- *
- * The value of ACTIVE_BIAS supports up to 65535 active processes.
- *
- * This should be totally fair - if anything is waiting, a process that wants a
- * lock will go to the back of the queue. When the currently active lock is
- * released, if there's a writer at the front of the queue, then that and only
- * that will be woken up; if there's a bunch of consecutive readers at the
- * front, then they'll all be woken up, but no other readers will be.
- */
-
-#ifndef _ASM_X86_RWSEM_H
-#define _ASM_X86_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-#include <asm/asm.h>
-
-/*
- * The bias values and the counter type limits the number of
- * potential readers/writers to 32767 for 32 bits and 2147483647
- * for 64 bits.
- */
-
-#ifdef CONFIG_X86_64
-# define RWSEM_ACTIVE_MASK 0xffffffffL
-#else
-# define RWSEM_ACTIVE_MASK 0x0000ffffL
-#endif
-
-#define RWSEM_UNLOCKED_VALUE 0x00000000L
-#define RWSEM_ACTIVE_BIAS 0x00000001L
-#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1)
-#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-#define ____down_read(sem, slow_path) \
-({ \
- struct rw_semaphore* ret; \
- asm volatile("# beginning down_read\n\t" \
- LOCK_PREFIX _ASM_INC "(%[sem])\n\t" \
- /* adds 0x00000001 */ \
- " jns 1f\n" \
- " call " slow_path "\n" \
- "1:\n\t" \
- "# ending down_read\n\t" \
- : "+m" (sem->count), "=a" (ret), \
- ASM_CALL_CONSTRAINT \
- : [sem] "a" (sem) \
- : "memory", "cc"); \
- ret; \
-})
-
-static inline void __down_read(struct rw_semaphore *sem)
-{
- ____down_read(sem, "call_rwsem_down_read_failed");
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
- if (IS_ERR(____down_read(sem, "call_rwsem_down_read_failed_killable")))
- return -EINTR;
- return 0;
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline bool __down_read_trylock(struct rw_semaphore *sem)
-{
- long result, tmp;
- asm volatile("# beginning __down_read_trylock\n\t"
- " mov %[count],%[result]\n\t"
- "1:\n\t"
- " mov %[result],%[tmp]\n\t"
- " add %[inc],%[tmp]\n\t"
- " jle 2f\n\t"
- LOCK_PREFIX " cmpxchg %[tmp],%[count]\n\t"
- " jnz 1b\n\t"
- "2:\n\t"
- "# ending __down_read_trylock\n\t"
- : [count] "+m" (sem->count), [result] "=&a" (result),
- [tmp] "=&r" (tmp)
- : [inc] "i" (RWSEM_ACTIVE_READ_BIAS)
- : "memory", "cc");
- return result >= 0;
-}
-
-/*
- * lock for writing
- */
-#define ____down_write(sem, slow_path) \
-({ \
- long tmp; \
- struct rw_semaphore* ret; \
- \
- asm volatile("# beginning down_write\n\t" \
- LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" \
- /* adds 0xffff0001, returns the old value */ \
- " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
- /* was the active mask 0 before? */\
- " jz 1f\n" \
- " call " slow_path "\n" \
- "1:\n" \
- "# ending down_write" \
- : "+m" (sem->count), [tmp] "=d" (tmp), \
- "=a" (ret), ASM_CALL_CONSTRAINT \
- : [sem] "a" (sem), "[tmp]" (RWSEM_ACTIVE_WRITE_BIAS) \
- : "memory", "cc"); \
- ret; \
-})
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
- ____down_write(sem, "call_rwsem_down_write_failed");
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
- if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable")))
- return -EINTR;
-
- return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline bool __down_write_trylock(struct rw_semaphore *sem)
-{
- bool result;
- long tmp0, tmp1;
- asm volatile("# beginning __down_write_trylock\n\t"
- " mov %[count],%[tmp0]\n\t"
- "1:\n\t"
- " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t"
- /* was the active mask 0 before? */
- " jnz 2f\n\t"
- " mov %[tmp0],%[tmp1]\n\t"
- " add %[inc],%[tmp1]\n\t"
- LOCK_PREFIX " cmpxchg %[tmp1],%[count]\n\t"
- " jnz 1b\n\t"
- "2:\n\t"
- CC_SET(e)
- "# ending __down_write_trylock\n\t"
- : [count] "+m" (sem->count), [tmp0] "=&a" (tmp0),
- [tmp1] "=&r" (tmp1), CC_OUT(e) (result)
- : [inc] "er" (RWSEM_ACTIVE_WRITE_BIAS)
- : "memory");
- return result;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
- long tmp;
- asm volatile("# beginning __up_read\n\t"
- LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t"
- /* subtracts 1, returns the old value */
- " jns 1f\n\t"
- " call call_rwsem_wake\n" /* expects old value in %edx */
- "1:\n"
- "# ending __up_read\n"
- : "+m" (sem->count), [tmp] "=d" (tmp)
- : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_READ_BIAS)
- : "memory", "cc");
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
- long tmp;
- asm volatile("# beginning __up_write\n\t"
- LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t"
- /* subtracts 0xffff0001, returns the old value */
- " jns 1f\n\t"
- " call call_rwsem_wake\n" /* expects old value in %edx */
- "1:\n\t"
- "# ending __up_write\n"
- : "+m" (sem->count), [tmp] "=d" (tmp)
- : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_WRITE_BIAS)
- : "memory", "cc");
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
- asm volatile("# beginning __downgrade_write\n\t"
- LOCK_PREFIX _ASM_ADD "%[inc],(%[sem])\n\t"
- /*
- * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386)
- * 0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64)
- */
- " jns 1f\n\t"
- " call call_rwsem_downgrade_wake\n"
- "1:\n\t"
- "# ending __downgrade_write\n"
- : "+m" (sem->count)
- : [sem] "a" (sem), [inc] "er" (-RWSEM_WAITING_BIAS)
- : "memory", "cc");
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_X86_RWSEM_H */
#ifndef _ASM_X86_SMAP_H
#define _ASM_X86_SMAP_H
-#include <linux/stringify.h>
#include <asm/nops.h>
#include <asm/cpufeatures.h>
/* "Raw" instruction opcodes */
-#define __ASM_CLAC .byte 0x0f,0x01,0xca
-#define __ASM_STAC .byte 0x0f,0x01,0xcb
+#define __ASM_CLAC ".byte 0x0f,0x01,0xca"
+#define __ASM_STAC ".byte 0x0f,0x01,0xcb"
#ifdef __ASSEMBLY__
#ifdef CONFIG_X86_SMAP
#define ASM_CLAC \
- ALTERNATIVE "", __stringify(__ASM_CLAC), X86_FEATURE_SMAP
+ ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP
#define ASM_STAC \
- ALTERNATIVE "", __stringify(__ASM_STAC), X86_FEATURE_SMAP
+ ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP
#else /* CONFIG_X86_SMAP */
static __always_inline void clac(void)
{
/* Note: a barrier is implicit in alternative() */
- alternative("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP);
+ alternative("", __ASM_CLAC, X86_FEATURE_SMAP);
}
static __always_inline void stac(void)
{
/* Note: a barrier is implicit in alternative() */
- alternative("", __stringify(__ASM_STAC), X86_FEATURE_SMAP);
+ alternative("", __ASM_STAC, X86_FEATURE_SMAP);
+}
+
+static __always_inline unsigned long smap_save(void)
+{
+ unsigned long flags;
+
+ asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC,
+ X86_FEATURE_SMAP)
+ : "=rm" (flags) : : "memory", "cc");
+
+ return flags;
+}
+
+static __always_inline void smap_restore(unsigned long flags)
+{
+ asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP)
+ : : "g" (flags) : "memory", "cc");
}
/* These macros can be used in asm() statements */
#define ASM_CLAC \
- ALTERNATIVE("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP)
+ ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP)
#define ASM_STAC \
- ALTERNATIVE("", __stringify(__ASM_STAC), X86_FEATURE_SMAP)
+ ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP)
#else /* CONFIG_X86_SMAP */
static inline void clac(void) { }
static inline void stac(void) { }
+static inline unsigned long smap_save(void) { return 0; }
+static inline void smap_restore(unsigned long flags) { }
+
#define ASM_CLAC
#define ASM_STAC
u32 return_address;
};
-static inline unsigned long caller_frame_pointer(void)
-{
- struct stack_frame *frame;
-
- frame = __builtin_frame_address(0);
-
-#ifdef CONFIG_FRAME_POINTER
- frame = frame->next_frame;
-#endif
-
- return (unsigned long)frame;
-}
-
void show_opcodes(struct pt_regs *regs, const char *loglvl);
void show_ip(struct pt_regs *regs, const char *loglvl);
#endif /* _ASM_X86_STACKTRACE_H */
unsigned long r13;
unsigned long r12;
#else
+ unsigned long flags;
unsigned long si;
unsigned long di;
#endif
* bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
*/
+#include <asm/rmwcc.h>
+
#define ADDR (*(volatile long *)addr)
/**
*/
static inline void sync_set_bit(long nr, volatile unsigned long *addr)
{
- asm volatile("lock; bts %1,%0"
+ asm volatile("lock; " __ASM_SIZE(bts) " %1,%0"
: "+m" (ADDR)
: "Ir" (nr)
: "memory");
*/
static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
{
- asm volatile("lock; btr %1,%0"
+ asm volatile("lock; " __ASM_SIZE(btr) " %1,%0"
: "+m" (ADDR)
: "Ir" (nr)
: "memory");
*/
static inline void sync_change_bit(long nr, volatile unsigned long *addr)
{
- asm volatile("lock; btc %1,%0"
+ asm volatile("lock; " __ASM_SIZE(btc) " %1,%0"
: "+m" (ADDR)
: "Ir" (nr)
: "memory");
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
+static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
{
- unsigned char oldbit;
-
- asm volatile("lock; bts %2,%1\n\tsetc %0"
- : "=qm" (oldbit), "+m" (ADDR)
- : "Ir" (nr) : "memory");
- return oldbit;
+ return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(bts), *addr, c, "Ir", nr);
}
/**
*/
static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
{
- unsigned char oldbit;
-
- asm volatile("lock; btr %2,%1\n\tsetc %0"
- : "=qm" (oldbit), "+m" (ADDR)
- : "Ir" (nr) : "memory");
- return oldbit;
+ return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btr), *addr, c, "Ir", nr);
}
/**
*/
static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
{
- unsigned char oldbit;
-
- asm volatile("lock; btc %2,%1\n\tsetc %0"
- : "=qm" (oldbit), "+m" (ADDR)
- : "Ir" (nr) : "memory");
- return oldbit;
+ return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btc), *addr, c, "Ir", nr);
}
#define sync_test_bit(nr, addr) test_bit(nr, addr)
#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+#define tlb_flush tlb_flush
static inline void tlb_flush(struct mmu_gather *tlb);
#include <asm-generic/tlb.h>
*/
struct mm_struct *loaded_mm;
-#define LOADED_MM_SWITCHING ((struct mm_struct *)1)
+#define LOADED_MM_SWITCHING ((struct mm_struct *)1UL)
/* Last user mm for optimizing IBPB */
union {
({ \
__label__ __pu_label; \
int __pu_err = -EFAULT; \
- __typeof__(*(ptr)) __pu_val; \
- __pu_val = x; \
+ __typeof__(*(ptr)) __pu_val = (x); \
+ __typeof__(ptr) __pu_ptr = (ptr); \
+ __typeof__(size) __pu_size = (size); \
__uaccess_begin(); \
- __put_user_size(__pu_val, (ptr), (size), __pu_label); \
+ __put_user_size(__pu_val, __pu_ptr, __pu_size, __pu_label); \
__pu_err = 0; \
__pu_label: \
__uaccess_end(); \
#define __user_atomic_cmpxchg_inatomic(uval, ptr, old, new, size) \
({ \
int __ret = 0; \
- __typeof__(ptr) __uval = (uval); \
__typeof__(*(ptr)) __old = (old); \
__typeof__(*(ptr)) __new = (new); \
__uaccess_begin_nospec(); \
__cmpxchg_wrong_size(); \
} \
__uaccess_end(); \
- *__uval = __old; \
+ *(uval) = __old; \
__ret; \
})
* checking before using them, but you have to surround them with the
* user_access_begin/end() pair.
*/
-static __must_check inline bool user_access_begin(const void __user *ptr, size_t len)
+static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len)
{
if (unlikely(!access_ok(ptr,len)))
return 0;
#define user_access_begin(a,b) user_access_begin(a,b)
#define user_access_end() __uaccess_end()
+#define user_access_save() smap_save()
+#define user_access_restore(x) smap_restore(x)
+
#define unsafe_put_user(x, ptr, label) \
__put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label)
return __copy_user_flushcache(dst, src, size);
}
-unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len);
-
unsigned long
mcsafe_handle_tail(char *to, char *from, unsigned len);
return (long)__res;
}
+static __always_inline void __xen_stac(void)
+{
+ /*
+ * Suppress objtool seeing the STAC/CLAC and getting confused about it
+ * calling random code with AC=1.
+ */
+ asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
+ ASM_STAC ::: "memory", "flags");
+}
+
+static __always_inline void __xen_clac(void)
+{
+ asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
+ ASM_CLAC ::: "memory", "flags");
+}
+
static inline long
privcmd_call(unsigned int call,
unsigned long a1, unsigned long a2,
{
long res;
- stac();
+ __xen_stac();
res = xen_single_call(call, a1, a2, a3, a4, a5);
- clac();
+ __xen_clac();
return res;
}
domid_t dom, unsigned int nr_bufs, struct xen_dm_op_buf *bufs)
{
int ret;
- stac();
+ __xen_stac();
ret = _hypercall3(int, dm_op, dom, nr_bufs, bufs);
- clac();
+ __xen_clac();
return ret;
}
#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
PERF_REG_X86_R13,
PERF_REG_X86_R14,
PERF_REG_X86_R15,
-
+ /* These are the limits for the GPRs. */
PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+
+ /* These all need two bits set because they are 128bit */
+ PERF_REG_X86_XMM0 = 32,
+ PERF_REG_X86_XMM1 = 34,
+ PERF_REG_X86_XMM2 = 36,
+ PERF_REG_X86_XMM3 = 38,
+ PERF_REG_X86_XMM4 = 40,
+ PERF_REG_X86_XMM5 = 42,
+ PERF_REG_X86_XMM6 = 44,
+ PERF_REG_X86_XMM7 = 46,
+ PERF_REG_X86_XMM8 = 48,
+ PERF_REG_X86_XMM9 = 50,
+ PERF_REG_X86_XMM10 = 52,
+ PERF_REG_X86_XMM11 = 54,
+ PERF_REG_X86_XMM12 = 56,
+ PERF_REG_X86_XMM13 = 58,
+ PERF_REG_X86_XMM14 = 60,
+ PERF_REG_X86_XMM15 = 62,
+
+ /* These include both GPRs and XMMX registers */
+ PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
};
#endif /* _ASM_X86_PERF_REGS_H */
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
+#define VMX_ABORT_VMCS_CORRUPTED 3
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
if (c->x86_vendor == X86_VENDOR_INTEL &&
(c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f)))
flags->bm_control = 0;
+ /*
+ * For all recent Centaur CPUs, the ucode will make sure that each
+ * core can keep cache coherence with each other while entering C3
+ * type state. So, set bm_check to 1 to indicate that the kernel
+ * doesn't need to execute a cache flush operation (WBINVD) when
+ * entering C3 type state.
+ */
+ if (c->x86_vendor == X86_VENDOR_CENTAUR) {
+ if (c->x86 > 6 || (c->x86 == 6 && c->x86_model == 0x0f &&
+ c->x86_stepping >= 0x0e))
+ flags->bm_check = 1;
+ }
}
EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
return 0;
}
+static int __init lapic_init_clockevent(void)
+{
+ if (!lapic_timer_frequency)
+ return -1;
+
+ /* Calculate the scaled math multiplication factor */
+ lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+ TICK_NSEC, lapic_clockevent.shift);
+ lapic_clockevent.max_delta_ns =
+ clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
+ lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
+ lapic_clockevent.min_delta_ns =
+ clockevent_delta2ns(0xF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ticks = 0xF;
+
+ return 0;
+}
+
static int __init calibrate_APIC_clock(void)
{
struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
long delta, deltatsc;
int pm_referenced = 0;
- /**
- * check if lapic timer has already been calibrated by platform
- * specific routine, such as tsc calibration code. if so, we just fill
+ if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+ return 0;
+
+ /*
+ * Check if lapic timer has already been calibrated by platform
+ * specific routine, such as tsc calibration code. If so just fill
* in the clockevent structure and return.
*/
-
- if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
- return 0;
- } else if (lapic_timer_frequency) {
+ if (!lapic_init_clockevent()) {
apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
- lapic_timer_frequency);
- lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
- TICK_NSEC, lapic_clockevent.shift);
- lapic_clockevent.max_delta_ns =
- clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
- lapic_clockevent.max_delta_ticks = 0x7FFFFF;
- lapic_clockevent.min_delta_ns =
- clockevent_delta2ns(0xF, &lapic_clockevent);
- lapic_clockevent.min_delta_ticks = 0xF;
+ lapic_timer_frequency);
+ /*
+ * Direct calibration methods must have an always running
+ * local APIC timer, no need for broadcast timer.
+ */
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
return 0;
}
pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
&delta, &deltatsc);
- /* Calculate the scaled math multiplication factor */
- lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
- lapic_clockevent.shift);
- lapic_clockevent.max_delta_ns =
- clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
- lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
- lapic_clockevent.min_delta_ns =
- clockevent_delta2ns(0xF, &lapic_clockevent);
- lapic_clockevent.min_delta_ticks = 0xF;
-
lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+ lapic_init_clockevent();
apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
this_cpu_write(cpu_llc_id, node);
/* Account for nodes per socket in multi-core-module processors */
- if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
+ if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
rdmsrl(MSR_FAM10H_NODE_ID, val);
nodes = ((val >> 3) & 7) + 1;
}
* performance at the same time..
*/
+#ifdef CONFIG_X86_32
extern __visible void vide(void);
-__asm__(".globl vide\n"
+__asm__(".text\n"
+ ".globl vide\n"
".type vide, @function\n"
".align 4\n"
"vide: ret\n");
+#endif
static void init_amd_k5(struct cpuinfo_x86 *c)
{
if (!cpu_khz)
return 0;
- if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
if (!cpu_khz)
return;
- if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return;
for_each_online_cpu(cpu)
if (!cpu_khz)
return 0;
- if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
const char *option;
enum spectre_v2_user_cmd cmd;
bool secure;
-} v2_user_options[] __initdata = {
+} v2_user_options[] __initconst = {
{ "auto", SPECTRE_V2_USER_CMD_AUTO, false },
{ "off", SPECTRE_V2_USER_CMD_NONE, false },
{ "on", SPECTRE_V2_USER_CMD_FORCE, true },
const char *option;
enum spectre_v2_mitigation_cmd cmd;
bool secure;
-} mitigation_options[] __initdata = {
+} mitigation_options[] __initconst = {
{ "off", SPECTRE_V2_CMD_NONE, false },
{ "on", SPECTRE_V2_CMD_FORCE, true },
{ "retpoline", SPECTRE_V2_CMD_RETPOLINE, false },
char arg[20];
int ret, i;
- if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+ if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") ||
+ cpu_mitigations_off())
return SPECTRE_V2_CMD_NONE;
ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
static const struct {
const char *option;
enum ssb_mitigation_cmd cmd;
-} ssb_mitigation_options[] __initdata = {
+} ssb_mitigation_options[] __initconst = {
{ "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */
{ "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */
{ "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */
char arg[20];
int ret, i;
- if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+ if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") ||
+ cpu_mitigations_off()) {
return SPEC_STORE_BYPASS_CMD_NONE;
} else {
ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
if (!boot_cpu_has_bug(X86_BUG_L1TF))
return;
+ if (cpu_mitigations_off())
+ l1tf_mitigation = L1TF_MITIGATION_OFF;
+ else if (cpu_mitigations_auto_nosmt())
+ l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+
override_cache_bits(&boot_cpu_data);
switch (l1tf_mitigation) {
unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
struct desc_struct d = { };
- if (static_cpu_has(X86_FEATURE_RDTSCP))
+ if (boot_cpu_has(X86_FEATURE_RDTSCP))
write_rdtscp_aux(cpudata);
/* Store CPU and node number in limit. */
#include "cpu.h"
+#define APICID_SOCKET_ID_BIT 6
+
/*
* nodes_per_socket: Stores the number of nodes per socket.
* Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8]
if (!err)
c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+ /* Socket ID is ApicId[6] for these processors. */
+ c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
+
cacheinfo_hygon_init_llc_id(c, cpu, node_id);
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;
if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE)
return;
- pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
- pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
+ pr_info_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
+ pr_info_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
}
* only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for
* Fam10h and later BKDGs.
*/
- if (static_cpu_has(X86_FEATURE_AMD_DCM) &&
+ if (boot_cpu_has(X86_FEATURE_AMD_DCM) &&
b == 4 &&
boot_cpu_data.x86 < 0x17) {
toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu));
"fpu_exception\t: %s\n"
"cpuid level\t: %d\n"
"wp\t\t: yes\n",
- static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
- static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
- static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
- static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
- static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+ boot_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
+ boot_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
+ boot_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
+ boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+ boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
c->cpuid_level);
}
#else
if (cpumask_empty(cpu_mask) || mba_sc)
goto done;
cpu = get_cpu();
- /* Update CBM on this cpu if it's in cpu_mask. */
+ /* Update resource control msr on this CPU if it's in cpu_mask. */
if (cpumask_test_cpu(cpu, cpu_mask))
rdt_ctrl_update(&msr_param);
- /* Update CBM on other cpus. */
+ /* Update resource control msr on other CPUs. */
smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
put_cpu();
bitmap_clear(val, zero_bit, cbm_len - zero_bit);
}
-/**
- * rdtgroup_init_alloc - Initialize the new RDT group's allocations
- *
- * A new RDT group is being created on an allocation capable (CAT)
- * supporting system. Set this group up to start off with all usable
- * allocations. That is, all shareable and unused bits.
+/*
+ * Initialize cache resources per RDT domain
*
- * All-zero CBM is invalid. If there are no more shareable bits available
- * on any domain then the entire allocation will fail.
+ * Set the RDT domain up to start off with all usable allocations. That is,
+ * all shareable and unused bits. All-zero CBM is invalid.
*/
-static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r,
+ u32 closid)
{
struct rdt_resource *r_cdp = NULL;
struct rdt_domain *d_cdp = NULL;
u32 used_b = 0, unused_b = 0;
- u32 closid = rdtgrp->closid;
- struct rdt_resource *r;
unsigned long tmp_cbm;
enum rdtgrp_mode mode;
- struct rdt_domain *d;
u32 peer_ctl, *ctrl;
- int i, ret;
+ int i;
- for_each_alloc_enabled_rdt_resource(r) {
- /*
- * Only initialize default allocations for CBM cache
- * resources
- */
- if (r->rid == RDT_RESOURCE_MBA)
- continue;
- list_for_each_entry(d, &r->domains, list) {
- rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
- d->have_new_ctrl = false;
- d->new_ctrl = r->cache.shareable_bits;
- used_b = r->cache.shareable_bits;
- ctrl = d->ctrl_val;
- for (i = 0; i < closids_supported(); i++, ctrl++) {
- if (closid_allocated(i) && i != closid) {
- mode = rdtgroup_mode_by_closid(i);
- if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
- break;
- /*
- * If CDP is active include peer
- * domain's usage to ensure there
- * is no overlap with an exclusive
- * group.
- */
- if (d_cdp)
- peer_ctl = d_cdp->ctrl_val[i];
- else
- peer_ctl = 0;
- used_b |= *ctrl | peer_ctl;
- if (mode == RDT_MODE_SHAREABLE)
- d->new_ctrl |= *ctrl | peer_ctl;
- }
- }
- if (d->plr && d->plr->cbm > 0)
- used_b |= d->plr->cbm;
- unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
- unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
- d->new_ctrl |= unused_b;
- /*
- * Force the initial CBM to be valid, user can
- * modify the CBM based on system availability.
- */
- cbm_ensure_valid(&d->new_ctrl, r);
+ rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
+ d->have_new_ctrl = false;
+ d->new_ctrl = r->cache.shareable_bits;
+ used_b = r->cache.shareable_bits;
+ ctrl = d->ctrl_val;
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
+ if (closid_allocated(i) && i != closid) {
+ mode = rdtgroup_mode_by_closid(i);
+ if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+ break;
/*
- * Assign the u32 CBM to an unsigned long to ensure
- * that bitmap_weight() does not access out-of-bound
- * memory.
+ * If CDP is active include peer domain's
+ * usage to ensure there is no overlap
+ * with an exclusive group.
*/
- tmp_cbm = d->new_ctrl;
- if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
- r->cache.min_cbm_bits) {
- rdt_last_cmd_printf("No space on %s:%d\n",
- r->name, d->id);
- return -ENOSPC;
- }
- d->have_new_ctrl = true;
+ if (d_cdp)
+ peer_ctl = d_cdp->ctrl_val[i];
+ else
+ peer_ctl = 0;
+ used_b |= *ctrl | peer_ctl;
+ if (mode == RDT_MODE_SHAREABLE)
+ d->new_ctrl |= *ctrl | peer_ctl;
}
}
+ if (d->plr && d->plr->cbm > 0)
+ used_b |= d->plr->cbm;
+ unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+ unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+ d->new_ctrl |= unused_b;
+ /*
+ * Force the initial CBM to be valid, user can
+ * modify the CBM based on system availability.
+ */
+ cbm_ensure_valid(&d->new_ctrl, r);
+ /*
+ * Assign the u32 CBM to an unsigned long to ensure that
+ * bitmap_weight() does not access out-of-bound memory.
+ */
+ tmp_cbm = d->new_ctrl;
+ if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
+ rdt_last_cmd_printf("No space on %s:%d\n", r->name, d->id);
+ return -ENOSPC;
+ }
+ d->have_new_ctrl = true;
+
+ return 0;
+}
+
+/*
+ * Initialize cache resources with default values.
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations.
+ *
+ * If there are no more shareable bits available on any domain then
+ * the entire allocation will fail.
+ */
+static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid)
+{
+ struct rdt_domain *d;
+ int ret;
+
+ list_for_each_entry(d, &r->domains, list) {
+ ret = __init_one_rdt_domain(d, r, closid);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+/* Initialize MBA resource with default values. */
+static void rdtgroup_init_mba(struct rdt_resource *r)
+{
+ struct rdt_domain *d;
+
+ list_for_each_entry(d, &r->domains, list) {
+ d->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
+ d->have_new_ctrl = true;
+ }
+}
+
+/* Initialize the RDT group's allocations. */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+ struct rdt_resource *r;
+ int ret;
for_each_alloc_enabled_rdt_resource(r) {
- /*
- * Only initialize default allocations for CBM cache
- * resources
- */
- if (r->rid == RDT_RESOURCE_MBA)
- continue;
+ if (r->rid == RDT_RESOURCE_MBA) {
+ rdtgroup_init_mba(r);
+ } else {
+ ret = rdtgroup_init_cat(r, rdtgrp->closid);
+ if (ret < 0)
+ return ret;
+ }
+
ret = update_domains(r, rdtgrp->closid);
if (ret < 0) {
rdt_last_cmd_puts("Failed to initialize allocations\n");
return ret;
}
- rdtgrp->mode = RDT_MODE_SHAREABLE;
+
}
+ rdtgrp->mode = RDT_MODE_SHAREABLE;
+
return 0;
}
* another range split. So add extra two slots here.
*/
nr_ranges += 2;
- cmem = vzalloc(sizeof(struct crash_mem) +
- sizeof(struct crash_mem_range) * nr_ranges);
+ cmem = vzalloc(struct_size(cmem, ranges, nr_ranges));
if (!cmem)
return NULL;
unsigned long *sara = stack_addr(regs);
ri->ret_addr = (kprobe_opcode_t *) *sara;
+ ri->fp = sara;
/* Replace the return addr with trampoline addr */
*sara = (unsigned long) &kretprobe_trampoline;
* calls trampoline_handler() runs, which calls the kretprobe's handler.
*/
asm(
+ ".text\n"
".global kretprobe_trampoline\n"
".type kretprobe_trampoline, @function\n"
"kretprobe_trampoline:\n"
NOKPROBE_SYMBOL(kretprobe_trampoline);
STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
+static struct kprobe kretprobe_kprobe = {
+ .addr = (void *)kretprobe_trampoline,
+};
+
/*
* Called from kretprobe_trampoline
*/
static __used void *trampoline_handler(struct pt_regs *regs)
{
+ struct kprobe_ctlblk *kcb;
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
kprobe_opcode_t *correct_ret_addr = NULL;
+ void *frame_pointer;
+ bool skipped = false;
+
+ preempt_disable();
+
+ /*
+ * Set a dummy kprobe for avoiding kretprobe recursion.
+ * Since kretprobe never run in kprobe handler, kprobe must not
+ * be running at this point.
+ */
+ kcb = get_kprobe_ctlblk();
+ __this_cpu_write(current_kprobe, &kretprobe_kprobe);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
/* fixup registers */
#ifdef CONFIG_X86_64
regs->cs = __KERNEL_CS;
+ /* On x86-64, we use pt_regs->sp for return address holder. */
+ frame_pointer = ®s->sp;
#else
regs->cs = __KERNEL_CS | get_kernel_rpl();
regs->gs = 0;
+ /* On x86-32, we use pt_regs->flags for return address holder. */
+ frame_pointer = ®s->flags;
#endif
regs->ip = trampoline_address;
regs->orig_ax = ~0UL;
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
+ /*
+ * Return probes must be pushed on this hash list correct
+ * order (same as return order) so that it can be poped
+ * correctly. However, if we find it is pushed it incorrect
+ * order, this means we find a function which should not be
+ * probed, because the wrong order entry is pushed on the
+ * path of processing other kretprobe itself.
+ */
+ if (ri->fp != frame_pointer) {
+ if (!skipped)
+ pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+ skipped = true;
+ continue;
+ }
orig_ret_address = (unsigned long)ri->ret_addr;
+ if (skipped)
+ pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+ ri->rp->kp.addr);
if (orig_ret_address != trampoline_address)
/*
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
+ if (ri->fp != frame_pointer)
+ continue;
orig_ret_address = (unsigned long)ri->ret_addr;
if (ri->rp && ri->rp->handler) {
__this_cpu_write(current_kprobe, &ri->rp->kp);
- get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
- __this_cpu_write(current_kprobe, NULL);
+ __this_cpu_write(current_kprobe, &kretprobe_kprobe);
}
recycle_rp_inst(ri, &empty_rp);
kretprobe_hash_unlock(current, &flags);
+ __this_cpu_write(current_kprobe, NULL);
+ preempt_enable();
+
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
* tables.
*/
WARN_ON(!had_kernel_mapping);
- if (static_cpu_has(X86_FEATURE_PTI))
+ if (boot_cpu_has(X86_FEATURE_PTI))
WARN_ON(!had_user_mapping);
} else {
/*
* Sync the pgd to the usermode tables.
*/
WARN_ON(had_kernel_mapping);
- if (static_cpu_has(X86_FEATURE_PTI))
+ if (boot_cpu_has(X86_FEATURE_PTI))
WARN_ON(had_user_mapping);
}
}
k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
- if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+ if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
set_pmd(u_pmd, *k_pmd);
}
{
pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
- if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+ if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
set_pgd(kernel_to_user_pgdp(pgd), *pgd);
}
spinlock_t *ptl;
int i, nr_pages;
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return 0;
/*
return;
/* LDT map/unmap is only required for PTI */
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return;
nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
unsigned long start = LDT_BASE_ADDR;
unsigned long end = LDT_END_ADDR;
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return;
tlb_gather_mmu(&tlb, mm, start, end);
void __init native_pv_lock_init(void)
{
- if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
static_branch_disable(&virt_spin_lock_key);
}
u64 perf_reg_value(struct pt_regs *regs, int idx)
{
+ struct x86_perf_regs *perf_regs;
+
+ if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ if (!perf_regs->xmm_regs)
+ return 0;
+ return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
+ }
+
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
return 0;
return regs_get_register(regs, pt_regs_offset[idx]);
}
-#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
-
#ifdef CONFIG_X86_32
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
+
int perf_reg_validate(u64 mask)
{
- if (!mask || mask & REG_RESERVED)
+ if (!mask || (mask & REG_NOSUPPORT))
return -EINVAL;
return 0;
int perf_reg_validate(u64 mask)
{
- if (!mask || mask & REG_RESERVED)
- return -EINVAL;
-
- if (mask & REG_NOSUPPORT)
+ if (!mask || (mask & REG_NOSUPPORT))
return -EINVAL;
return 0;
static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled)
{
- if (!static_cpu_has(X86_FEATURE_CPUID_FAULT))
+ if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT))
return -ENODEV;
if (cpuid_enabled)
u64 msr = x86_spec_ctrl_base;
bool updmsr = false;
+ lockdep_assert_irqs_disabled();
+
/*
* If TIF_SSBD is different, select the proper mitigation
* method. Note that if SSBD mitigation is disabled or permanentely
void speculation_ctrl_update(unsigned long tif)
{
+ unsigned long flags;
+
/* Forced update. Make sure all relevant TIF flags are different */
- preempt_disable();
+ local_irq_save(flags);
__speculation_ctrl_update(~tif, tif);
- preempt_enable();
+ local_irq_restore(flags);
}
/* Called from seccomp/prctl update */
if (c->x86_vendor != X86_VENDOR_INTEL)
return 0;
- if (!cpu_has(c, X86_FEATURE_MWAIT) || static_cpu_has_bug(X86_BUG_MONITOR))
+ if (!cpu_has(c, X86_FEATURE_MWAIT) || boot_cpu_has_bug(X86_BUG_MONITOR))
return 0;
return 1;
struct task_struct *tsk;
int err;
+ /*
+ * For a new task use the RESET flags value since there is no before.
+ * All the status flags are zero; DF and all the system flags must also
+ * be 0, specifically IF must be 0 because we context switch to the new
+ * task with interrupts disabled.
+ */
+ frame->flags = X86_EFLAGS_FIXED;
frame->bp = 0;
frame->ret_addr = (unsigned long) ret_from_fork;
p->thread.sp = (unsigned long) fork_frame;
childregs = task_pt_regs(p);
fork_frame = container_of(childregs, struct fork_frame, regs);
frame = &fork_frame->frame;
+
frame->bp = 0;
frame->ret_addr = (unsigned long) ret_from_fork;
p->thread.sp = (unsigned long) fork_frame;
return 0;
}
+/*
+ * Some machines don't handle the default ACPI reboot method and
+ * require the EFI reboot method:
+ */
+static int __init set_efi_reboot(const struct dmi_system_id *d)
+{
+ if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) {
+ reboot_type = BOOT_EFI;
+ pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident);
+ }
+ return 0;
+}
+
void __noreturn machine_real_restart(unsigned int type)
{
local_irq_disable();
write_cr3(real_mode_header->trampoline_pgd);
/* Exiting long mode will fail if CR4.PCIDE is set. */
- if (static_cpu_has(X86_FEATURE_PCID))
+ if (boot_cpu_has(X86_FEATURE_PCID))
cr4_clear_bits(X86_CR4_PCIDE);
#endif
DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
},
},
+ { /* Handle reboot issue on Acer TravelMate X514-51T */
+ .callback = set_efi_reboot,
+ .ident = "Acer TravelMate X514-51T",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"),
+ },
+ },
/* Apple */
{ /* Handle problems with rebooting on Apple MacBook5 */
if (efi_enabled(EFI_BOOT))
efi_init();
- dmi_scan_machine();
- dmi_memdev_walk();
- dmi_set_dump_stack_arch_desc();
+ dmi_setup();
/*
* VMware detection requires dmi to be available, so this
- * needs to be done after dmi_scan_machine(), for the boot CPU.
+ * needs to be done after dmi_setup(), for the boot CPU.
*/
init_hypervisor_platform();
COPY_SEG_CPL3(cs);
COPY_SEG_CPL3(ss);
-#ifdef CONFIG_X86_64
- /*
- * Fix up SS if needed for the benefit of old DOSEMU and
- * CRIU.
- */
- if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) &&
- user_64bit_mode(regs)))
- force_valid_ss(regs);
-#endif
-
get_user_ex(tmpflags, &sc->flags);
regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
regs->orig_ax = -1; /* disable syscall checks */
buf = (void __user *)buf_val;
} get_user_catch(err);
+#ifdef CONFIG_X86_64
+ /*
+ * Fix up SS if needed for the benefit of old DOSEMU and
+ * CRIU.
+ */
+ if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs)))
+ force_valid_ss(regs);
+#endif
+
err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32));
force_iret();
{
struct rt_sigframe __user *frame;
void __user *fp = NULL;
+ unsigned long uc_flags;
int err = 0;
frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
return -EFAULT;
}
+ uc_flags = frame_uc_flags(regs);
+
put_user_try {
/* Create the ucontext. */
- put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+ put_user_ex(uc_flags, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
save_altstack_ex(&frame->uc.uc_stack, regs->sp);
{
#ifdef CONFIG_X86_X32_ABI
struct rt_sigframe_x32 __user *frame;
+ unsigned long uc_flags;
void __user *restorer;
int err = 0;
void __user *fpstate = NULL;
return -EFAULT;
}
+ uc_flags = frame_uc_flags(regs);
+
put_user_try {
/* Create the ucontext. */
- put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+ put_user_ex(uc_flags, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
put_user_ex(0, &frame->uc.uc__pad0);
sigset_t *set = sigmask_to_save();
compat_sigset_t *cset = (compat_sigset_t *) set;
- /*
- * Increment event counter and perform fixup for the pre-signal
- * frame.
- */
+ /* Perform fixup for the pre-signal frame. */
rseq_signal_deliver(ksig, regs);
/* Set up the stack frame */
#include <asm/stacktrace.h>
#include <asm/unwind.h>
-static int save_stack_address(struct stack_trace *trace, unsigned long addr,
- bool nosched)
-{
- if (nosched && in_sched_functions(addr))
- return 0;
-
- if (trace->skip > 0) {
- trace->skip--;
- return 0;
- }
-
- if (trace->nr_entries >= trace->max_entries)
- return -1;
-
- trace->entries[trace->nr_entries++] = addr;
- return 0;
-}
-
-static void noinline __save_stack_trace(struct stack_trace *trace,
- struct task_struct *task, struct pt_regs *regs,
- bool nosched)
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+ struct task_struct *task, struct pt_regs *regs)
{
struct unwind_state state;
unsigned long addr;
- if (regs)
- save_stack_address(trace, regs->ip, nosched);
+ if (regs && !consume_entry(cookie, regs->ip, false))
+ return;
for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
addr = unwind_get_return_address(&state);
- if (!addr || save_stack_address(trace, addr, nosched))
+ if (!addr || !consume_entry(cookie, addr, false))
break;
}
-
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
/*
- * Save stack-backtrace addresses into a stack_trace buffer.
+ * This function returns an error if it detects any unreliable features of the
+ * stack. Otherwise it guarantees that the stack trace is reliable.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
*/
-void save_stack_trace(struct stack_trace *trace)
-{
- trace->skip++;
- __save_stack_trace(trace, current, NULL, false);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace);
-
-void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
-{
- __save_stack_trace(trace, current, regs, false);
-}
-
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
-{
- if (!try_get_task_stack(tsk))
- return;
-
- if (tsk == current)
- trace->skip++;
- __save_stack_trace(trace, tsk, NULL, true);
-
- put_task_stack(tsk);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
-
-#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
-
-static int __always_inline
-__save_stack_trace_reliable(struct stack_trace *trace,
- struct task_struct *task)
+int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
+ void *cookie, struct task_struct *task)
{
struct unwind_state state;
struct pt_regs *regs;
if (regs) {
/* Success path for user tasks */
if (user_mode(regs))
- goto success;
+ return 0;
/*
* Kernel mode registers on the stack indicate an
if (!addr)
return -EINVAL;
- if (save_stack_address(trace, addr, false))
+ if (!consume_entry(cookie, addr, false))
return -EINVAL;
}
if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
return -EINVAL;
-success:
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
-
return 0;
}
-/*
- * This function returns an error if it detects any unreliable features of the
- * stack. Otherwise it guarantees that the stack trace is reliable.
- *
- * If the task is not 'current', the caller *must* ensure the task is inactive.
- */
-int save_stack_trace_tsk_reliable(struct task_struct *tsk,
- struct stack_trace *trace)
-{
- int ret;
-
- /*
- * If the task doesn't have a stack (e.g., a zombie), the stack is
- * "reliably" empty.
- */
- if (!try_get_task_stack(tsk))
- return 0;
-
- ret = __save_stack_trace_reliable(trace, tsk);
-
- put_task_stack(tsk);
-
- return ret;
-}
-#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
-
/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
struct stack_frame_user {
return ret;
}
-static inline void __save_stack_trace_user(struct stack_trace *trace)
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+ const struct pt_regs *regs)
{
- const struct pt_regs *regs = task_pt_regs(current);
const void __user *fp = (const void __user *)regs->bp;
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = regs->ip;
+ if (!consume_entry(cookie, regs->ip, false))
+ return;
- while (trace->nr_entries < trace->max_entries) {
+ while (1) {
struct stack_frame_user frame;
frame.next_fp = NULL;
if ((unsigned long)fp < regs->sp)
break;
if (frame.ret_addr) {
- trace->entries[trace->nr_entries++] =
- frame.ret_addr;
+ if (!consume_entry(cookie, frame.ret_addr, false))
+ return;
}
if (fp == frame.next_fp)
break;
}
}
-void save_stack_trace_user(struct stack_trace *trace)
-{
- /*
- * Trace user stack if we are not a kernel thread
- */
- if (current->mm) {
- __save_stack_trace_user(trace);
- }
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
-}
preempt_disable();
tsk->thread.sp0 += 16;
- if (static_cpu_has(X86_FEATURE_SEP)) {
+ if (boot_cpu_has(X86_FEATURE_SEP)) {
tsk->thread.sysenter_cs = 0;
refresh_sysenter_cs(&tsk->thread);
}
.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
__bss_start = .;
*(.bss..page_aligned)
- *(.bss)
+ *(BSS_MAIN)
BSS_DECRYPTED
. = ALIGN(PAGE_SIZE);
__bss_stop = .;
static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
{
+#ifdef CONFIG_X86_64
u32 eax, ebx, ecx, edx;
eax = 0x80000001;
ecx = 0;
ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
return edx & bit(X86_FEATURE_LM);
+#else
+ return false;
+#endif
}
-#define GET_SMSTATE(type, smbase, offset) \
- ({ \
- type __val; \
- int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \
- sizeof(__val)); \
- if (r != X86EMUL_CONTINUE) \
- return X86EMUL_UNHANDLEABLE; \
- __val; \
- })
-
static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
{
desc->g = (flags >> 23) & 1;
desc->type = (flags >> 8) & 15;
}
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
u16 selector;
- selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+ selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
if (n < 3)
offset = 0x7f84 + n * 12;
else
offset = 0x7f2c + (n - 3) * 12;
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
return X86EMUL_CONTINUE;
}
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+#ifdef CONFIG_X86_64
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
offset = 0x7e00 + n * 16;
- selector = GET_SMSTATE(u16, smbase, offset);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- base3 = GET_SMSTATE(u32, smbase, offset + 12);
+ selector = GET_SMSTATE(u16, smstate, offset);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ base3 = GET_SMSTATE(u32, smstate, offset + 12);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
return X86EMUL_CONTINUE;
}
+#endif
static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
u64 cr0, u64 cr3, u64 cr4)
return X86EMUL_CONTINUE;
}
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
u32 val, cr0, cr3, cr4;
int i;
- cr0 = GET_SMSTATE(u32, smbase, 0x7ffc);
- cr3 = GET_SMSTATE(u32, smbase, 0x7ff8);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
- ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0);
+ cr0 = GET_SMSTATE(u32, smstate, 0x7ffc);
+ cr3 = GET_SMSTATE(u32, smstate, 0x7ff8);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
for (i = 0; i < 8; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+ *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
- val = GET_SMSTATE(u32, smbase, 0x7fcc);
+ val = GET_SMSTATE(u32, smstate, 0x7fcc);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7fc8);
+ val = GET_SMSTATE(u32, smstate, 0x7fc8);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- selector = GET_SMSTATE(u32, smbase, 0x7fc4);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc4);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
- selector = GET_SMSTATE(u32, smbase, 0x7fc0);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc0);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f74);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f70);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f74);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f70);
ctxt->ops->set_gdt(ctxt, &dt);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f58);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f54);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f58);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f54);
ctxt->ops->set_idt(ctxt, &dt);
for (i = 0; i < 6; i++) {
- int r = rsm_load_seg_32(ctxt, smbase, i);
+ int r = rsm_load_seg_32(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
- cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+ cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
}
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
int i, r;
for (i = 0; i < 16; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+ *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
- ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
- val = GET_SMSTATE(u32, smbase, 0x7f68);
+ val = GET_SMSTATE(u32, smstate, 0x7f68);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7f60);
+ val = GET_SMSTATE(u32, smstate, 0x7f60);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- cr0 = GET_SMSTATE(u64, smbase, 0x7f58);
- cr3 = GET_SMSTATE(u64, smbase, 0x7f50);
- cr4 = GET_SMSTATE(u64, smbase, 0x7f48);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
- val = GET_SMSTATE(u64, smbase, 0x7ed0);
+ cr0 = GET_SMSTATE(u64, smstate, 0x7f58);
+ cr3 = GET_SMSTATE(u64, smstate, 0x7f50);
+ cr4 = GET_SMSTATE(u64, smstate, 0x7f48);
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
+ val = GET_SMSTATE(u64, smstate, 0x7ed0);
ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
- selector = GET_SMSTATE(u32, smbase, 0x7e90);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98));
- base3 = GET_SMSTATE(u32, smbase, 0x7e9c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e90);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e9c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e84);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e88);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e84);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e88);
ctxt->ops->set_idt(ctxt, &dt);
- selector = GET_SMSTATE(u32, smbase, 0x7e70);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78));
- base3 = GET_SMSTATE(u32, smbase, 0x7e7c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e70);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e7c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e64);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e68);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e64);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e68);
ctxt->ops->set_gdt(ctxt, &dt);
r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
return r;
for (i = 0; i < 6; i++) {
- r = rsm_load_seg_64(ctxt, smbase, i);
+ r = rsm_load_seg_64(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
return X86EMUL_CONTINUE;
}
+#endif
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
unsigned long cr0, cr4, efer;
+ char buf[512];
u64 smbase;
int ret;
if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
return emulate_ud(ctxt);
+ smbase = ctxt->ops->get_smbase(ctxt);
+
+ ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+ if (ret != X86EMUL_CONTINUE)
+ return X86EMUL_UNHANDLEABLE;
+
+ if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+ ctxt->ops->set_nmi_mask(ctxt, false);
+
+ ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+ ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
+
/*
* Get back to real mode, to prepare a safe state in which to load
* CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU
* supports long mode.
*/
- cr4 = ctxt->ops->get_cr(ctxt, 4);
if (emulator_has_longmode(ctxt)) {
struct desc_struct cs_desc;
/* Zero CR4.PCIDE before CR0.PG. */
- if (cr4 & X86_CR4_PCIDE) {
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PCIDE)
ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
- cr4 &= ~X86_CR4_PCIDE;
- }
/* A 32-bit code segment is required to clear EFER.LMA. */
memset(&cs_desc, 0, sizeof(cs_desc));
if (cr0 & X86_CR0_PE)
ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
- /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */
- if (cr4 & X86_CR4_PAE)
- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
-
- /* And finally go back to 32-bit mode. */
- efer = 0;
- ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ if (emulator_has_longmode(ctxt)) {
+ /* Clear CR4.PAE before clearing EFER.LME. */
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PAE)
+ ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
- smbase = ctxt->ops->get_smbase(ctxt);
+ /* And finally go back to 32-bit mode. */
+ efer = 0;
+ ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ }
/*
* Give pre_leave_smm() a chance to make ISA-specific changes to the
* vCPU state (e.g. enter guest mode) before loading state from the SMM
* state-save area.
*/
- if (ctxt->ops->pre_leave_smm(ctxt, smbase))
+ if (ctxt->ops->pre_leave_smm(ctxt, buf))
return X86EMUL_UNHANDLEABLE;
+#ifdef CONFIG_X86_64
if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+ ret = rsm_load_state_64(ctxt, buf);
else
- ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+#endif
+ ret = rsm_load_state_32(ctxt, buf);
if (ret != X86EMUL_CONTINUE) {
/* FIXME: should triple fault */
return X86EMUL_UNHANDLEABLE;
}
- if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
- ctxt->ops->set_nmi_mask(ctxt, false);
+ ctxt->ops->post_leave_smm(ctxt);
- ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
- ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
return X86EMUL_CONTINUE;
}
valid_bank_mask = BIT_ULL(0);
sparse_banks[0] = flush.processor_mask;
- all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
+
+ /*
+ * Work around possible WS2012 bug: it sends hypercalls
+ * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear,
+ * while also expecting us to flush something and crashing if
+ * we don't. Let's treat processor_mask == 0 same as
+ * HV_FLUSH_ALL_PROCESSORS.
+ */
+ all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) ||
+ flush.processor_mask == 0;
} else {
if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex,
sizeof(flush_ex))))
#define APIC_BROADCAST 0xFF
#define X2APIC_BROADCAST 0xFFFFFFFFul
-static bool lapic_timer_advance_adjust_done = false;
#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
/* step-by-step approximation to mitigate fluctuation */
#define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
if (offset <= max_apic_id) {
u8 cluster_size = min(max_apic_id - offset + 1, 16U);
+ offset = array_index_nospec(offset, map->max_apic_id + 1);
*cluster = &map->phys_map[offset];
*mask = dest_id & (0xffff >> (16 - cluster_size));
} else {
if (irq->dest_id > map->max_apic_id) {
*bitmap = 0;
} else {
- *dst = &map->phys_map[irq->dest_id];
+ u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1);
+ *dst = &map->phys_map[dest_id];
*bitmap = 1;
}
return true;
return false;
}
+static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles)
+{
+ u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns;
+
+ /*
+ * If the guest TSC is running at a different ratio than the host, then
+ * convert the delay to nanoseconds to achieve an accurate delay. Note
+ * that __delay() uses delay_tsc whenever the hardware has TSC, thus
+ * always for VMX enabled hardware.
+ */
+ if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) {
+ __delay(min(guest_cycles,
+ nsec_to_cycles(vcpu, timer_advance_ns)));
+ } else {
+ u64 delay_ns = guest_cycles * 1000000ULL;
+ do_div(delay_ns, vcpu->arch.virtual_tsc_khz);
+ ndelay(min_t(u32, delay_ns, timer_advance_ns));
+ }
+}
+
void wait_lapic_expire(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
+ u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns;
u64 guest_tsc, tsc_deadline, ns;
- if (!lapic_in_kernel(vcpu))
- return;
-
if (apic->lapic_timer.expired_tscdeadline == 0)
return;
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
- /* __delay is delay_tsc whenever the hardware has TSC, thus always. */
if (guest_tsc < tsc_deadline)
- __delay(min(tsc_deadline - guest_tsc,
- nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+ __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
- if (!lapic_timer_advance_adjust_done) {
+ if (!apic->lapic_timer.timer_advance_adjust_done) {
/* too early */
if (guest_tsc < tsc_deadline) {
ns = (tsc_deadline - guest_tsc) * 1000000ULL;
do_div(ns, vcpu->arch.virtual_tsc_khz);
- lapic_timer_advance_ns -= min((unsigned int)ns,
- lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ timer_advance_ns -= min((u32)ns,
+ timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
} else {
/* too late */
ns = (guest_tsc - tsc_deadline) * 1000000ULL;
do_div(ns, vcpu->arch.virtual_tsc_khz);
- lapic_timer_advance_ns += min((unsigned int)ns,
- lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ timer_advance_ns += min((u32)ns,
+ timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
}
if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
- lapic_timer_advance_adjust_done = true;
+ apic->lapic_timer.timer_advance_adjust_done = true;
+ if (unlikely(timer_advance_ns > 5000)) {
+ timer_advance_ns = 0;
+ apic->lapic_timer.timer_advance_adjust_done = true;
+ }
+ apic->lapic_timer.timer_advance_ns = timer_advance_ns;
}
}
static void start_sw_tscdeadline(struct kvm_lapic *apic)
{
- u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
+ struct kvm_timer *ktimer = &apic->lapic_timer;
+ u64 guest_tsc, tscdeadline = ktimer->tscdeadline;
u64 ns = 0;
ktime_t expire;
struct kvm_vcpu *vcpu = apic->vcpu;
now = ktime_get();
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
- if (likely(tscdeadline > guest_tsc)) {
- ns = (tscdeadline - guest_tsc) * 1000000ULL;
- do_div(ns, this_tsc_khz);
+
+ ns = (tscdeadline - guest_tsc) * 1000000ULL;
+ do_div(ns, this_tsc_khz);
+
+ if (likely(tscdeadline > guest_tsc) &&
+ likely(ns > apic->lapic_timer.timer_advance_ns)) {
expire = ktime_add_ns(now, ns);
- expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
- hrtimer_start(&apic->lapic_timer.timer,
- expire, HRTIMER_MODE_ABS_PINNED);
+ expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
+ hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_PINNED);
} else
apic_timer_expired(apic);
return HRTIMER_NORESTART;
}
-int kvm_create_lapic(struct kvm_vcpu *vcpu)
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
{
struct kvm_lapic *apic;
hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
HRTIMER_MODE_ABS_PINNED);
apic->lapic_timer.timer.function = apic_timer_fn;
+ if (timer_advance_ns == -1) {
+ apic->lapic_timer.timer_advance_ns = 1000;
+ apic->lapic_timer.timer_advance_adjust_done = false;
+ } else {
+ apic->lapic_timer.timer_advance_ns = timer_advance_ns;
+ apic->lapic_timer.timer_advance_adjust_done = true;
+ }
+
/*
* APIC is created enabled. This will prevent kvm_lapic_set_base from
u32 timer_mode_mask;
u64 tscdeadline;
u64 expired_tscdeadline;
+ u32 timer_advance_ns;
atomic_t pending; /* accumulated triggered timers */
bool hv_timer_in_use;
+ bool timer_advance_adjust_done;
};
struct kvm_lapic {
struct dest_map;
-int kvm_create_lapic(struct kvm_vcpu *vcpu);
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
void kvm_free_lapic(struct kvm_vcpu *vcpu);
int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
* aggregate version in order to make the slab shrinker
* faster
*/
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
{
kvm->arch.n_used_mmu_pages += nr;
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
struct list_head *invalid_list,
bool remote_flush)
{
- if (!remote_flush && !list_empty(invalid_list))
+ if (!remote_flush && list_empty(invalid_list))
return false;
if (!list_empty(invalid_list))
* Changing the number of mmu pages allocated to the vm
* Note: if goal_nr_mmu_pages is too small, you will get dead lock
*/
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
{
LIST_HEAD(invalid_list);
union kvm_mmu_extended_role ext = {0};
ext.cr0_pg = !!is_paging(vcpu);
+ ext.cr4_pae = !!is_pae(vcpu);
ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
ext.cr4_pse = !!is_pse(vcpu);
/*
* Calculate mmu pages needed for kvm.
*/
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
{
- unsigned int nr_mmu_pages;
- unsigned int nr_pages = 0;
+ unsigned long nr_mmu_pages;
+ unsigned long nr_pages = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int i;
}
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
- nr_mmu_pages = max(nr_mmu_pages,
- (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+ nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
return nr_mmu_pages;
}
int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
u64 fault_address, char *insn, int insn_len);
-static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
{
if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
return kvm->arch.n_max_mmu_pages -
int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
{
bool fast_mode = idx & (1u << 31);
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct kvm_pmc *pmc;
u64 ctr_val;
+ if (!pmu->version)
+ return 1;
+
if (is_vmware_backdoor_pmc(idx))
return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
};
#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31
#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31)
#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL)
static int db_interception(struct vcpu_svm *svm)
{
struct kvm_run *kvm_run = svm->vcpu.run;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
if (!(svm->vcpu.guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
if (svm->nmi_singlestep) {
disable_nmi_singlestep(svm);
+ /* Make sure we check for pending NMIs upon entry */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
}
if (svm->vcpu.guest_debug &
kvm_lapic_reg_write(apic, APIC_ICR, icrl);
break;
case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
+ int i;
+ struct kvm_vcpu *vcpu;
+ struct kvm *kvm = svm->vcpu.kvm;
struct kvm_lapic *apic = svm->vcpu.arch.apic;
/*
- * Update ICR high and low, then emulate sending IPI,
- * which is handled when writing APIC_ICR.
+ * At this point, we expect that the AVIC HW has already
+ * set the appropriate IRR bits on the valid target
+ * vcpus. So, we just need to kick the appropriate vcpu.
*/
- kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
- kvm_lapic_reg_write(apic, APIC_ICR, icrl);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ bool m = kvm_apic_match_dest(vcpu, apic,
+ icrl & KVM_APIC_SHORT_MASK,
+ GET_APIC_DEST_FIELD(icrh),
+ icrl & KVM_APIC_DEST_MASK);
+
+ if (m && !avic_vcpu_is_running(vcpu))
+ kvm_vcpu_wake_up(vcpu);
+ }
break;
}
case AVIC_IPI_FAILURE_INVALID_TARGET:
u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
if (entry)
- WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK);
+ clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
}
static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
svm->vmcb->save.cr2 = vcpu->arch.cr2;
clgi();
+ kvm_load_guest_xcr0(vcpu);
/*
* If this vCPU has touched SPEC_CTRL, restore the guest's value if
if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
kvm_before_interrupt(&svm->vcpu);
+ kvm_put_guest_xcr0(vcpu);
stgi();
/* Any pending NMI will happen here */
return 0;
}
-static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *nested_vmcb;
struct page *page;
- struct {
- u64 guest;
- u64 vmcb;
- } svm_state_save;
- int ret;
+ u64 guest;
+ u64 vmcb;
- ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save,
- sizeof(svm_state_save));
- if (ret)
- return ret;
+ guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+ vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
- if (svm_state_save.guest) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
- nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page);
- if (nested_vmcb)
- enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page);
- else
- ret = 1;
- vcpu->arch.hflags |= HF_SMM_MASK;
+ if (guest) {
+ nested_vmcb = nested_svm_map(svm, vmcb, &page);
+ if (!nested_vmcb)
+ return 1;
+ enter_svm_guest_mode(svm, vmcb, nested_vmcb, page);
}
- return ret;
+ return 0;
}
static int enable_smi_window(struct kvm_vcpu *vcpu)
);
TRACE_EVENT(kvm_apic_accept_irq,
- TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+ TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec),
TP_ARGS(apicid, dm, tm, vec),
TP_STRUCT__entry(
__field( __u32, apicid )
__field( __u16, dm )
- __field( __u8, tm )
+ __field( __u16, tm )
__field( __u8, vec )
),
/*
* If translation failed, VM entry will fail because
* prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
- * Failing the vm entry is _not_ what the processor
- * does but it's basically the only possibility we
- * have. We could still enter the guest if CR8 load
- * exits are enabled, CR8 store exits are enabled, and
- * virtualize APIC access is disabled; in this case
- * the processor would never use the TPR shadow and we
- * could simply clear the bit from the execution
- * control. But such a configuration is useless, so
- * let's keep the code simple.
*/
if (!is_error_page(page)) {
vmx->nested.virtual_apic_page = page;
hpa = page_to_phys(vmx->nested.virtual_apic_page);
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
+ } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
+ nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
+ !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ /*
+ * The processor will never use the TPR shadow, simply
+ * clear the bit from the execution control. Such a
+ * configuration is useless, but it happens in tests.
+ * For any other configuration, failing the vm entry is
+ * _not_ what the processor does but it's basically the
+ * only possibility we have.
+ */
+ vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_TPR_SHADOW);
+ } else {
+ printk("bad virtual-APIC page address\n");
+ dump_vmcs();
}
}
vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
nested_ept_uninit_mmu_context(vcpu);
- vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
- __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+ /*
+ * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3
+ * points to shadow pages! Fortunately we only get here after a WARN_ON
+ * if EPT is disabled, so a VMabort is perfectly fine.
+ */
+ if (enable_ept) {
+ vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+ } else {
+ nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED);
+ }
/*
* Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
return ret;
/* Empty 'VMXON' state is permitted */
- if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
+ if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
return 0;
if (kvm_state->vmx.vmcs_pa != -1ull) {
vmcs12->vmcs_link_pointer != -1ull) {
struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
- if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12))
+ if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12))
return -EINVAL;
if (copy_from_user(shadow_vmcs12,
{
int i;
+ /*
+ * Without EPT it is not possible to restore L1's CR3 and PDPTR on
+ * VMfail, because they are not available in vmcs01. Just always
+ * use hardware checks.
+ */
+ if (!enable_ept)
+ nested_early_check = 1;
+
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
if (enable_shadow_vmcs) {
#include <asm/asm.h>
#include <asm/bitsperlong.h>
#include <asm/kvm_vcpu_regs.h>
+#include <asm/nospec-branch.h>
#define WORD_SIZE (BITS_PER_LONG / 8)
* referred to by VMCS.HOST_RIP.
*/
ENTRY(vmx_vmexit)
+#ifdef CONFIG_RETPOLINE
+ ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE
+ /* Preserve guest's RAX, it's used to stuff the RSB. */
+ push %_ASM_AX
+
+ /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+
+ pop %_ASM_AX
+.Lvmexit_skip_rsb:
+#endif
ret
ENDPROC(vmx_vmexit)
vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
}
-static void dump_vmcs(void)
+void dump_vmcs(void)
{
u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
+ kvm_load_guest_xcr0(vcpu);
+
if (static_cpu_has(X86_FEATURE_PKU) &&
kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
vcpu->arch.pkru != vmx->host_pkru)
x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
- /* Eliminate branch target predictions from guest mode */
- vmexit_fill_RSB();
-
/* All fields are clean at this point */
if (static_branch_unlikely(&enable_evmcs))
current_evmcs->hv_clean_fields |=
__write_pkru(vmx->host_pkru);
}
+ kvm_put_guest_xcr0(vcpu);
+
vmx->nested.nested_run_pending = 0;
vmx->idt_vectoring_info = 0;
}
}
+static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *entry;
+ union cpuid10_eax eax;
+
+ entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+ if (!entry)
+ return false;
+
+ eax.full = entry->eax;
+ return (eax.split.version_id > 0);
+}
+
+static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool pmu_enabled = guest_cpuid_has_pmu(vcpu);
+
+ if (pmu_enabled)
+ vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING;
+ else
+ vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING;
+}
+
static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
if (nested_vmx_allowed(vcpu)) {
nested_vmx_cr_fixed1_bits_update(vcpu);
nested_vmx_entry_exit_ctls_update(vcpu);
+ nested_vmx_procbased_ctls_update(vcpu);
}
if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
{
struct vcpu_vmx *vmx;
u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
+ struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer;
if (kvm_mwait_in_guest(vcpu->kvm))
return -EOPNOTSUPP;
tscl = rdtsc();
guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
- lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);
+ lapic_timer_advance_cycles = nsec_to_cycles(vcpu,
+ ktimer->timer_advance_ns);
if (delta_tsc > lapic_timer_advance_cycles)
delta_tsc -= lapic_timer_advance_cycles;
return 0;
}
-static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
}
if (vmx->nested.smm.guest_mode) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
ret = nested_vmx_enter_non_root_mode(vcpu, false);
- vcpu->arch.hflags |= HF_SMM_MASK;
if (ret)
return ret;
vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
}
+void dump_vmcs(void);
+
#endif /* __KVM_X86_VMX_H */
static u32 __read_mostly tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
-/* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 1000;
+/*
+ * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables
+ * adaptive tuning starting from default advancment of 1000ns. '0' disables
+ * advancement entirely. Any other value is used as-is and disables adaptive
+ * tuning, i.e. allows priveleged userspace to set an exact advancement time.
+ */
+static int __read_mostly lapic_timer_advance_ns = -1;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
-EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
static bool __read_mostly vector_hashing = true;
module_param(vector_hashing, bool, S_IRUGO);
}
EXPORT_SYMBOL_GPL(kvm_lmsw);
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
!vcpu->guest_xcr0_loaded) {
vcpu->guest_xcr0_loaded = 1;
}
}
+EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (vcpu->guest_xcr0_loaded) {
if (vcpu->arch.xcr0 != host_xcr0)
vcpu->guest_xcr0_loaded = 0;
}
}
+EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
break;
case KVM_CAP_NESTED_STATE:
r = kvm_x86_ops->get_nested_state ?
- kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0;
+ kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
break;
default:
break;
memset(&events->reserved, 0, sizeof(events->reserved));
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu);
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
- u32 hflags = vcpu->arch.hflags;
- if (events->smi.smm)
- hflags |= HF_SMM_MASK;
- else
- hflags &= ~HF_SMM_MASK;
- kvm_set_hflags(vcpu, hflags);
+ if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
+ if (events->smi.smm)
+ vcpu->arch.hflags |= HF_SMM_MASK;
+ else
+ vcpu->arch.hflags &= ~HF_SMM_MASK;
+ kvm_smm_changed(vcpu);
+ }
vcpu->arch.smi_pending = events->smi.pending;
}
static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
- u32 kvm_nr_mmu_pages)
+ unsigned long kvm_nr_mmu_pages)
{
if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
return -EINVAL;
return 0;
}
-static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
{
return kvm->arch.n_max_mmu_pages;
}
static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
{
- kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+ emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
}
-static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
- return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase);
+ return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate);
+}
+
+static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt)
+{
+ kvm_smm_changed(emul_to_vcpu(ctxt));
}
static const struct x86_emulate_ops emulate_ops = {
.get_hflags = emulator_get_hflags,
.set_hflags = emulator_set_hflags,
.pre_leave_smm = emulator_pre_leave_smm,
+ .post_leave_smm = emulator_post_leave_smm,
};
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
kvm_mmu_reset_context(vcpu);
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
-{
- unsigned changed = vcpu->arch.hflags ^ emul_flags;
-
- vcpu->arch.hflags = emul_flags;
-
- if (changed & HF_SMM_MASK)
- kvm_smm_changed(vcpu);
-}
-
static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
unsigned long *db)
{
}
EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
+static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.pio.count = 0;
+ return 1;
+}
+
static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
{
vcpu->arch.pio.count = 0;
unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
size, port, &val, 1);
+ if (ret)
+ return ret;
- if (!ret) {
+ /*
+ * Workaround userspace that relies on old KVM behavior of %rip being
+ * incremented prior to exiting to userspace to handle "OUT 0x7e".
+ */
+ if (port == 0x7e &&
+ kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
+ vcpu->arch.complete_userspace_io =
+ complete_fast_pio_out_port_0x7e;
+ kvm_skip_emulated_instruction(vcpu);
+ } else {
vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
vcpu->arch.complete_userspace_io = complete_fast_pio_out;
}
- return ret;
+ return 0;
}
static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
}
+#ifdef CONFIG_X86_64
static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
{
-#ifdef CONFIG_X86_64
struct desc_ptr dt;
struct kvm_segment seg;
unsigned long val;
for (i = 0; i < 6; i++)
enter_smm_save_seg_64(vcpu, buf, i);
-#else
- WARN_ON_ONCE(1);
-#endif
}
+#endif
static void enter_smm(struct kvm_vcpu *vcpu)
{
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
memset(buf, 0, 512);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
enter_smm_save_state_64(vcpu, buf);
else
+#endif
enter_smm_save_state_32(vcpu, buf);
/*
kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
kvm_x86_ops->set_efer(vcpu, 0);
+#endif
kvm_update_cpuid(vcpu);
kvm_mmu_reset_context(vcpu);
goto cancel_injection;
}
- kvm_load_guest_xcr0(vcpu);
-
if (req_immediate_exit) {
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_x86_ops->request_immediate_exit(vcpu);
}
trace_kvm_entry(vcpu->vcpu_id);
- if (lapic_timer_advance_ns)
+ if (lapic_in_kernel(vcpu) &&
+ vcpu->arch.apic->lapic_timer.timer_advance_ns)
wait_lapic_expire(vcpu);
guest_enter_irqoff();
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
- kvm_put_guest_xcr0(vcpu);
-
kvm_before_interrupt(vcpu);
kvm_x86_ops->handle_external_intr(vcpu);
kvm_after_interrupt(vcpu);
if (irqchip_in_kernel(vcpu->kvm)) {
vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
- r = kvm_create_lapic(vcpu);
+ r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
if (r < 0)
goto fail_mmu_destroy;
} else
extern unsigned int min_timer_period_us;
-extern unsigned int lapic_timer_advance_ns;
-
extern bool enable_vmware_backdoor;
extern struct static_key kvm_no_apic_vcpu;
__this_cpu_write(current_vcpu, NULL);
}
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
#endif
# Produces uninteresting flaky coverage.
KCOV_INSTRUMENT_delay.o := n
+# Early boot use of cmdline; don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KCOV_INSTRUMENT_cmdline.o := n
+KASAN_SANITIZE_cmdline.o := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_cmdline.o = -pg
+endif
+
+CFLAGS_cmdline.o := $(call cc-option, -fno-stack-protector)
+endif
+
inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
quiet_cmd_inat_tables = GEN $@
lib-y := delay.o misc.o cmdline.o cpu.o
lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
-lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
#include <asm/smap.h>
#include <asm/export.h>
+.macro ALIGN_DESTINATION
+ /* check for bad alignment of destination */
+ movl %edi,%ecx
+ andl $7,%ecx
+ jz 102f /* already aligned */
+ subl $8,%ecx
+ negl %ecx
+ subl %ecx,%edx
+100: movb (%rsi),%al
+101: movb %al,(%rdi)
+ incq %rsi
+ incq %rdi
+ decl %ecx
+ jnz 100b
+102:
+ .section .fixup,"ax"
+103: addl %ecx,%edx /* ecx is zerorest also */
+ jmp copy_user_handle_tail
+ .previous
+
+ _ASM_EXTABLE_UA(100b, 103b)
+ _ASM_EXTABLE_UA(101b, 103b)
+ .endm
+
/*
* copy_user_generic_unrolled - memory copy with exception handling.
* This version is for CPUs like P4 that don't have efficient micro
ENDPROC(copy_user_enhanced_fast_string)
EXPORT_SYMBOL(copy_user_enhanced_fast_string)
+/*
+ * Try to copy last bytes and clear the rest if needed.
+ * Since protection fault in copy_from/to_user is not a normal situation,
+ * it is not necessary to optimize tail handling.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * eax uncopied bytes or 0 if successful.
+ */
+ALIGN;
+copy_user_handle_tail:
+ movl %edx,%ecx
+1: rep movsb
+2: mov %ecx,%eax
+ ASM_CLAC
+ ret
+
+ _ASM_EXTABLE_UA(1b, 2b)
+ENDPROC(copy_user_handle_tail)
+
/*
* copy_user_nocache - Uncached memory copy with exception handling
* This will force destination out of cache for more performance.
asmlinkage void just_return_func(void);
asm(
+ ".text\n"
".type just_return_func, @function\n"
".globl just_return_func\n"
"just_return_func:\n"
/* Copy successful. Return zero */
.L_done_memcpy_trap:
xorl %eax, %eax
+.L_done:
ret
ENDPROC(__memcpy_mcsafe)
EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
addl %edx, %ecx
.E_trailing_bytes:
mov %ecx, %eax
- ret
+ jmp .L_done
/*
* For write fault handling, given the destination is unaligned,
+++ /dev/null
-/*
- * x86 semaphore implementation.
- *
- * (C) Copyright 1999 Linus Torvalds
- *
- * Portions Copyright 1999 Red Hat, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org>
- */
-
-#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
-
-#define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg)
-#define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l)
-
-#ifdef CONFIG_X86_32
-
-/*
- * The semaphore operations have a special calling sequence that
- * allow us to do a simpler in-line version of them. These routines
- * need to convert that sequence back into the C sequence when
- * there is contention on the semaphore.
- *
- * %eax contains the semaphore pointer on entry. Save the C-clobbered
- * registers (%eax, %edx and %ecx) except %eax which is either a return
- * value or just gets clobbered. Same is true for %edx so make sure GCC
- * reloads it after the slow path, by making it hold a temporary, for
- * example see ____down_write().
- */
-
-#define save_common_regs \
- pushl %ecx
-
-#define restore_common_regs \
- popl %ecx
-
- /* Avoid uglifying the argument copying x86-64 needs to do. */
- .macro movq src, dst
- .endm
-
-#else
-
-/*
- * x86-64 rwsem wrappers
- *
- * This interfaces the inline asm code to the slow-path
- * C routines. We need to save the call-clobbered regs
- * that the asm does not mark as clobbered, and move the
- * argument from %rax to %rdi.
- *
- * NOTE! We don't need to save %rax, because the functions
- * will always return the semaphore pointer in %rax (which
- * is also the input argument to these helpers)
- *
- * The following can clobber %rdx because the asm clobbers it:
- * call_rwsem_down_write_failed
- * call_rwsem_wake
- * but %rdi, %rsi, %rcx, %r8-r11 always need saving.
- */
-
-#define save_common_regs \
- pushq %rdi; \
- pushq %rsi; \
- pushq %rcx; \
- pushq %r8; \
- pushq %r9; \
- pushq %r10; \
- pushq %r11
-
-#define restore_common_regs \
- popq %r11; \
- popq %r10; \
- popq %r9; \
- popq %r8; \
- popq %rcx; \
- popq %rsi; \
- popq %rdi
-
-#endif
-
-/* Fix up special calling conventions */
-ENTRY(call_rwsem_down_read_failed)
- FRAME_BEGIN
- save_common_regs
- __ASM_SIZE(push,) %__ASM_REG(dx)
- movq %rax,%rdi
- call rwsem_down_read_failed
- __ASM_SIZE(pop,) %__ASM_REG(dx)
- restore_common_regs
- FRAME_END
- ret
-ENDPROC(call_rwsem_down_read_failed)
-
-ENTRY(call_rwsem_down_read_failed_killable)
- FRAME_BEGIN
- save_common_regs
- __ASM_SIZE(push,) %__ASM_REG(dx)
- movq %rax,%rdi
- call rwsem_down_read_failed_killable
- __ASM_SIZE(pop,) %__ASM_REG(dx)
- restore_common_regs
- FRAME_END
- ret
-ENDPROC(call_rwsem_down_read_failed_killable)
-
-ENTRY(call_rwsem_down_write_failed)
- FRAME_BEGIN
- save_common_regs
- movq %rax,%rdi
- call rwsem_down_write_failed
- restore_common_regs
- FRAME_END
- ret
-ENDPROC(call_rwsem_down_write_failed)
-
-ENTRY(call_rwsem_down_write_failed_killable)
- FRAME_BEGIN
- save_common_regs
- movq %rax,%rdi
- call rwsem_down_write_failed_killable
- restore_common_regs
- FRAME_END
- ret
-ENDPROC(call_rwsem_down_write_failed_killable)
-
-ENTRY(call_rwsem_wake)
- FRAME_BEGIN
- /* do nothing if still outstanding active readers */
- __ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
- jnz 1f
- save_common_regs
- movq %rax,%rdi
- call rwsem_wake
- restore_common_regs
-1: FRAME_END
- ret
-ENDPROC(call_rwsem_wake)
-
-ENTRY(call_rwsem_downgrade_wake)
- FRAME_BEGIN
- save_common_regs
- __ASM_SIZE(push,) %__ASM_REG(dx)
- movq %rax,%rdi
- call rwsem_downgrade_wake
- __ASM_SIZE(pop,) %__ASM_REG(dx)
- restore_common_regs
- FRAME_END
- ret
-ENDPROC(call_rwsem_downgrade_wake)
}
EXPORT_SYMBOL(clear_user);
-/*
- * Try to copy last bytes and clear the rest if needed.
- * Since protection fault in copy_from/to_user is not a normal situation,
- * it is not necessary to optimize tail handling.
- */
-__visible unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len)
-{
- for (; len; --len, to++) {
- char c;
-
- if (__get_user_nocheck(c, from++, sizeof(char)))
- break;
- if (__put_user_nocheck(c, to, sizeof(char)))
- break;
- }
- clac();
- return len;
-}
-
/*
* Similar to copy_user_handle_tail, probe for the write fault point,
* but reuse __memcpy_mcsafe in case a new read error is encountered.
#endif
/* Account the WX pages */
st->wx_pages += npages;
- WARN_ONCE(1, "x86/mm: Found insecure W+X mapping at address %pS\n",
+ WARN_ONCE(__supported_pte_mask & _PAGE_NX,
+ "x86/mm: Found insecure W+X mapping at address %pS\n",
(void *)st->start_address);
}
void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
{
#ifdef CONFIG_PAGE_TABLE_ISOLATION
- if (user && static_cpu_has(X86_FEATURE_PTI))
+ if (user && boot_cpu_has(X86_FEATURE_PTI))
pgd = kernel_to_user_pgdp(pgd);
#endif
ptdump_walk_pgd_level_core(m, pgd, false, false);
pgd_t *pgd = INIT_PGD;
if (!(__supported_pte_mask & _PAGE_NX) ||
- !static_cpu_has(X86_FEATURE_PTI))
+ !boot_cpu_has(X86_FEATURE_PTI))
return;
pr_info("x86/mm: Checking user space page tables\n");
#include <linux/memblock.h>
#include <linux/swapfile.h>
#include <linux/swapops.h>
+#include <linux/kmemleak.h>
#include <asm/set_memory.h>
#include <asm/e820/api.h>
if (debug_pagealloc_enabled()) {
pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n",
begin, end - 1);
+ /*
+ * Inform kmemleak about the hole in the memory since the
+ * corresponding pages will be unmapped.
+ */
+ kmemleak_free_part((void *)begin, end - begin);
set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
} else {
/*
pte = early_ioremap_pte(addr);
/* Sanitize 'prot' against any unsupported bits: */
- pgprot_val(flags) &= __default_kernel_pte_mask;
+ pgprot_val(flags) &= __supported_pte_mask;
if (pgprot_val(flags))
set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
if (!kaslr_memory_enabled())
return;
- kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT);
+ kaslr_regions[0].size_tb = 1 << (MAX_PHYSMEM_BITS - TB_SHIFT);
kaslr_regions[1].size_tb = VMALLOC_SIZE_TB;
/*
* when PTI is enabled. We need them to map the per-process LDT into the
* user-space page-table.
*/
-#define PREALLOCATED_USER_PMDS (static_cpu_has(X86_FEATURE_PTI) ? \
+#define PREALLOCATED_USER_PMDS (boot_cpu_has(X86_FEATURE_PTI) ? \
KERNEL_PGD_PTRS : 0)
#define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS
#ifdef CONFIG_PAGE_TABLE_ISOLATION
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return;
pgdp = kernel_to_user_pgdp(pgdp);
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/uaccess.h>
+#include <linux/cpu.h>
#include <asm/cpufeature.h>
#include <asm/hypervisor.h>
}
}
- if (cmdline_find_option_bool(boot_command_line, "nopti")) {
+ if (cmdline_find_option_bool(boot_command_line, "nopti") ||
+ cpu_mitigations_off()) {
pti_mode = PTI_FORCE_OFF;
pti_print_if_insecure("disabled on command line.");
return;
*/
void __init pti_init(void)
{
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return;
pr_info("enabled\n");
{
int cpu;
- struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = {
+ struct flush_tlb_info info = {
.mm = mm,
.stride_shift = stride_shift,
.freed_tables = freed_tables,
*/
static int __init init_per_cpu(int nuvhubs, int base_part_pnode)
{
- unsigned char *uvhub_mask;
struct uvhub_desc *uvhub_descs;
+ unsigned char *uvhub_mask = NULL;
if (is_uv3_hub() || is_uv2_hub() || is_uv1_hub())
timeout_us = calculate_destination_timeout();
uvhub_descs = kcalloc(nuvhubs, sizeof(struct uvhub_desc), GFP_KERNEL);
+ if (!uvhub_descs)
+ goto fail;
+
uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL);
+ if (!uvhub_mask)
+ goto fail;
if (get_cpu_topology(base_part_pnode, uvhub_descs, uvhub_mask))
goto fail;
#define Elf_Shdr ElfW(Shdr)
#define Elf_Sym ElfW(Sym)
-static Elf_Ehdr ehdr;
+static Elf_Ehdr ehdr;
+static unsigned long shnum;
+static unsigned int shstrndx;
struct relocs {
uint32_t *offset;
{
const char *sec_strtab;
const char *name;
- sec_strtab = secs[ehdr.e_shstrndx].strtab;
+ sec_strtab = secs[shstrndx].strtab;
name = "<noname>";
- if (shndx < ehdr.e_shnum) {
+ if (shndx < shnum) {
name = sec_strtab + secs[shndx].shdr.sh_name;
}
else if (shndx == SHN_ABS) {
static Elf_Sym *sym_lookup(const char *symname)
{
int i;
- for (i = 0; i < ehdr.e_shnum; i++) {
+ for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
long nsyms;
char *strtab;
ehdr.e_shnum = elf_half_to_cpu(ehdr.e_shnum);
ehdr.e_shstrndx = elf_half_to_cpu(ehdr.e_shstrndx);
- if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN)) {
+ shnum = ehdr.e_shnum;
+ shstrndx = ehdr.e_shstrndx;
+
+ if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN))
die("Unsupported ELF header type\n");
- }
- if (ehdr.e_machine != ELF_MACHINE) {
+ if (ehdr.e_machine != ELF_MACHINE)
die("Not for %s\n", ELF_MACHINE_NAME);
- }
- if (ehdr.e_version != EV_CURRENT) {
+ if (ehdr.e_version != EV_CURRENT)
die("Unknown ELF version\n");
- }
- if (ehdr.e_ehsize != sizeof(Elf_Ehdr)) {
+ if (ehdr.e_ehsize != sizeof(Elf_Ehdr))
die("Bad Elf header size\n");
- }
- if (ehdr.e_phentsize != sizeof(Elf_Phdr)) {
+ if (ehdr.e_phentsize != sizeof(Elf_Phdr))
die("Bad program header entry\n");
- }
- if (ehdr.e_shentsize != sizeof(Elf_Shdr)) {
+ if (ehdr.e_shentsize != sizeof(Elf_Shdr))
die("Bad section header entry\n");
+
+
+ if (shnum == SHN_UNDEF || shstrndx == SHN_XINDEX) {
+ Elf_Shdr shdr;
+
+ if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0)
+ die("Seek to %d failed: %s\n", ehdr.e_shoff, strerror(errno));
+
+ if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
+ die("Cannot read initial ELF section header: %s\n", strerror(errno));
+
+ if (shnum == SHN_UNDEF)
+ shnum = elf_xword_to_cpu(shdr.sh_size);
+
+ if (shstrndx == SHN_XINDEX)
+ shstrndx = elf_word_to_cpu(shdr.sh_link);
}
- if (ehdr.e_shstrndx >= ehdr.e_shnum) {
+
+ if (shstrndx >= shnum)
die("String table index out of bounds\n");
- }
}
static void read_shdrs(FILE *fp)
int i;
Elf_Shdr shdr;
- secs = calloc(ehdr.e_shnum, sizeof(struct section));
+ secs = calloc(shnum, sizeof(struct section));
if (!secs) {
die("Unable to allocate %d section headers\n",
- ehdr.e_shnum);
+ shnum);
}
if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) {
die("Seek to %d failed: %s\n",
ehdr.e_shoff, strerror(errno));
}
- for (i = 0; i < ehdr.e_shnum; i++) {
+ for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
die("Cannot read ELF section headers %d/%d: %s\n",
- i, ehdr.e_shnum, strerror(errno));
+ i, shnum, strerror(errno));
sec->shdr.sh_name = elf_word_to_cpu(shdr.sh_name);
sec->shdr.sh_type = elf_word_to_cpu(shdr.sh_type);
sec->shdr.sh_flags = elf_xword_to_cpu(shdr.sh_flags);
sec->shdr.sh_info = elf_word_to_cpu(shdr.sh_info);
sec->shdr.sh_addralign = elf_xword_to_cpu(shdr.sh_addralign);
sec->shdr.sh_entsize = elf_xword_to_cpu(shdr.sh_entsize);
- if (sec->shdr.sh_link < ehdr.e_shnum)
+ if (sec->shdr.sh_link < shnum)
sec->link = &secs[sec->shdr.sh_link];
}
static void read_strtabs(FILE *fp)
{
int i;
- for (i = 0; i < ehdr.e_shnum; i++) {
+ for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
if (sec->shdr.sh_type != SHT_STRTAB) {
continue;
static void read_symtabs(FILE *fp)
{
int i,j;
- for (i = 0; i < ehdr.e_shnum; i++) {
+ for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
if (sec->shdr.sh_type != SHT_SYMTAB) {
continue;
static void read_relocs(FILE *fp)
{
int i,j;
- for (i = 0; i < ehdr.e_shnum; i++) {
+ for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
if (sec->shdr.sh_type != SHT_REL_TYPE) {
continue;
printf("Absolute symbols\n");
printf(" Num: Value Size Type Bind Visibility Name\n");
- for (i = 0; i < ehdr.e_shnum; i++) {
+ for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
char *sym_strtab;
int j;
else
format = "%08"PRIx32" %08"PRIx32" %10s %08"PRIx32" %s\n";
- for (i = 0; i < ehdr.e_shnum; i++) {
+ for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
struct section *sec_applies, *sec_symtab;
char *sym_strtab;
{
int i;
/* Walk through the relocations */
- for (i = 0; i < ehdr.e_shnum; i++) {
+ for (i = 0; i < shnum; i++) {
char *sym_strtab;
Elf_Sym *sh_symtab;
struct section *sec_applies, *sec_symtab;
static void percpu_init(void)
{
int i;
- for (i = 0; i < ehdr.e_shnum; i++) {
+ for (i = 0; i < shnum; i++) {
ElfW(Sym) *sym;
if (strcmp(sec_name(i), ".data..percpu"))
continue;
default "arch/um/configs/i386_defconfig" if X86_32
default "arch/um/configs/x86_64_defconfig" if X86_64
-config RWSEM_XCHGADD_ALGORITHM
- def_bool 64BIT
-
-config RWSEM_GENERIC_SPINLOCK
- def_bool !RWSEM_XCHGADD_ALGORITHM
-
config 3_LEVEL_PGTABLES
bool "Three-level pagetables" if !64BIT
default 64BIT
obj-$(CONFIG_ELF_CORE) += elfcore.o
subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
-subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o
else
obj-y += syscalls_64.o vdso/
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \
- ../lib/rwsem.o
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o
endif
-Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv
GCOV_PROFILE := n
#
with reasonable minimum requirements. The Xtensa Linux project has
a home page at <http://www.linux-xtensa.org/>.
-config RWSEM_XCHGADD_ALGORITHM
- def_bool y
-
config GENERIC_HWEIGHT
def_bool y
generic-y += preempt.h
generic-y += qrwlock.h
generic-y += qspinlock.h
-generic-y += rwsem.h
generic-y += sections.h
generic-y += socket.h
generic-y += topology.h
#include <asm/cache.h>
#include <asm/page.h>
-#if (DCACHE_WAY_SIZE <= PAGE_SIZE)
-
-/* Note, read http://lkml.org/lkml/2004/1/15/6 */
-
-# define tlb_start_vma(tlb,vma) do { } while (0)
-# define tlb_end_vma(tlb,vma) do { } while (0)
-
-#else
-
-# define tlb_start_vma(tlb, vma) \
- do { \
- if (!tlb->fullmm) \
- flush_cache_range(vma, vma->vm_start, vma->vm_end); \
- } while(0)
-
-# define tlb_end_vma(tlb, vma) \
- do { \
- if (!tlb->fullmm) \
- flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
- } while(0)
-
-#endif
-
-#define __tlb_remove_tlb_entry(tlb,pte,addr) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
#include <asm-generic/tlb.h>
#define __pte_free_tlb(tlb, pte, address) pte_free((tlb)->mm, pte)
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
return min_shallow;
}
-static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
{
struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
struct blk_mq_tags *tags = hctx->sched_tags;
min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
+}
+
+static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+{
+ bfq_depth_updated(hctx);
return 0;
}
.requests_merged = bfq_requests_merged,
.request_merged = bfq_request_merged,
.has_work = bfq_has_work,
+ .depth_updated = bfq_depth_updated,
.init_hctx = bfq_init_hctx,
.init_sched = bfq_init_queue,
.exit_sched = bfq_exit_queue,
}
if (ret)
break;
+ if (q->elevator && q->elevator->type->ops.depth_updated)
+ q->elevator->type->ops.depth_updated(hctx);
}
if (!ret)
{
struct skcipher_request *req = areq->data;
- if (!err)
+ if (!err) {
+ struct rctx *rctx = skcipher_request_ctx(req);
+
+ rctx->subreq.base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
err = xor_tweak_post(req);
+ }
skcipher_request_complete(req, err);
}
.psize = 80,
.digest = "\x13\x00\x00\x00\x00\x00\x00\x00"
"\x00\x00\x00\x00\x00\x00\x00\x00",
- },
+ }, { /* Regression test for overflow in AVX2 implementation */
+ .plaintext = "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff\xff\xff\xff\xff"
+ "\xff\xff\xff\xff",
+ .psize = 300,
+ .digest = "\xfb\x5e\x96\xd8\x61\xd5\xc7\xc8"
+ "\x78\xe5\x87\xcc\x2d\x5a\x22\xe1",
+ }
};
/* NHPoly1305 test vectors from https://github.com/google/adiantum */
{
struct skcipher_request *req = areq->data;
- if (!err)
+ if (!err) {
+ struct rctx *rctx = skcipher_request_ctx(req);
+
+ rctx->subreq.base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
err = xor_tweak_post(req);
+ }
skcipher_request_complete(req, err);
}
ACPI_FUNCTION_TRACE(ev_enable_gpe);
- /* Clear the GPE status */
- status = acpi_hw_clear_gpe(gpe_event_info);
- if (ACPI_FAILURE(status))
- return_ACPI_STATUS(status);
-
/* Enable the requested GPE */
+
status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE);
return_ACPI_STATUS(status);
}
goto out;
}
+ dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name,
+ cmd_name, out_obj->buffer.length);
+ print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
+ out_obj->buffer.pointer,
+ min_t(u32, 128, out_obj->buffer.length), true);
+
if (call_pkg) {
call_pkg->nd_fw_size = out_obj->buffer.length;
memcpy(call_pkg->nd_payload + call_pkg->nd_size_in,
return 0;
}
- dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name,
- cmd_name, out_obj->buffer.length);
- print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
- out_obj->buffer.pointer,
- min_t(u32, 128, out_obj->buffer.length), true);
-
for (i = 0, offset = 0; i < desc->out_num; i++) {
u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf,
(u32 *) out_obj->buffer.pointer,
if (!test_bit(cmd, &nfit_mem->dsm_mask))
return -ENOTTY;
- if (old_data)
- memcpy(nd_cmd.cmd.old_pass, old_data->data,
- sizeof(nd_cmd.cmd.old_pass));
+ memcpy(nd_cmd.cmd.old_pass, old_data->data,
+ sizeof(nd_cmd.cmd.old_pass));
memcpy(nd_cmd.cmd.new_pass, new_data->data,
sizeof(nd_cmd.cmd.new_pass));
rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
/* flush all cache before we erase DIMM */
nvdimm_invalidate_cache();
- if (nkey)
- memcpy(nd_cmd.cmd.passphrase, nkey->data,
- sizeof(nd_cmd.cmd.passphrase));
+ memcpy(nd_cmd.cmd.passphrase, nkey->data,
+ sizeof(nd_cmd.cmd.passphrase));
rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
if (rc < 0)
return rc;
}
if (status & ISR_TBRQ_W) {
- fs_dprintk (FS_DEBUG_IRQ, "Data tramsitted!\n");
+ fs_dprintk (FS_DEBUG_IRQ, "Data transmitted!\n");
process_txdone_queue (dev, &dev->tx_relq);
}
ret = lock_device_hotplug_sysfs();
if (ret)
- goto out;
+ return ret;
nid = memory_add_physaddr_to_nid(phys_addr);
ret = __add_memory(nid, phys_addr,
struct zram *zram;
unsigned long entry;
struct bio *bio;
+ struct bio_vec bvec;
};
#if PAGE_SIZE != 4096
static void zram_sync_read(struct work_struct *work)
{
- struct bio_vec bvec;
struct zram_work *zw = container_of(work, struct zram_work, work);
struct zram *zram = zw->zram;
unsigned long entry = zw->entry;
struct bio *bio = zw->bio;
- read_from_bdev_async(zram, &bvec, entry, bio);
+ read_from_bdev_async(zram, &zw->bvec, entry, bio);
}
/*
{
struct zram_work work;
+ work.bvec = *bvec;
work.zram = zram;
work.entry = entry;
work.bio = bio;
return;
}
- memset(&p, 0, sizeof(p));
p.addr = base_addr;
p.space = space;
p.regspacing = offset;
/* Does this interface receive IPMI events? */
bool gets_events;
+
+ /* Free must run in process context for RCU cleanup. */
+ struct work_struct remove_work;
};
static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index)
return rv;
}
+static void free_user_work(struct work_struct *work)
+{
+ struct ipmi_user *user = container_of(work, struct ipmi_user,
+ remove_work);
+
+ cleanup_srcu_struct(&user->release_barrier);
+ kfree(user);
+}
+
int ipmi_create_user(unsigned int if_num,
const struct ipmi_user_hndl *handler,
void *handler_data,
goto out_kfree;
found:
+ INIT_WORK(&new_user->remove_work, free_user_work);
+
rv = init_srcu_struct(&new_user->release_barrier);
if (rv)
goto out_kfree;
static void free_user(struct kref *ref)
{
struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
- cleanup_srcu_struct(&user->release_barrier);
- kfree(user);
+
+ /* SRCU cleanup must happen in task context. */
+ schedule_work(&user->remove_work);
}
static void _ipmi_destroy_user(struct ipmi_user *user)
char *str;
char *si_type[SI_MAX_PARMS];
+ memset(si_type, 0, sizeof(si_type));
+
/* Parse out the si_type string into its components. */
str = si_type_str;
if (*str != '\0') {
if (con_id)
best_possible += 1;
+ lockdep_assert_held(&clocks_mutex);
+
list_for_each_entry(p, &clocks, node) {
match = 0;
if (p->dev_id) {
struct clk_lookup *cl;
int rval;
+ mutex_lock(&clocks_mutex);
cl = clk_find(dev_id, con_id);
+ mutex_unlock(&clocks_mutex);
+
WARN_ON(!cl);
rval = devres_release(dev, devm_clkdev_release,
devm_clk_match_clkdev, cl);
unsigned long parent_rate)
{
struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
- u32 n_mask, k_mask, m_mask, p_mask;
+ u32 n_mask = 0, k_mask = 0, m_mask = 0, p_mask = 0;
struct _ccu_nkmp _nkmp;
unsigned long flags;
u32 reg;
ccu_nkmp_find_best(parent_rate, rate, &_nkmp);
- n_mask = GENMASK(nkmp->n.width + nkmp->n.shift - 1, nkmp->n.shift);
- k_mask = GENMASK(nkmp->k.width + nkmp->k.shift - 1, nkmp->k.shift);
- m_mask = GENMASK(nkmp->m.width + nkmp->m.shift - 1, nkmp->m.shift);
- p_mask = GENMASK(nkmp->p.width + nkmp->p.shift - 1, nkmp->p.shift);
+ /*
+ * If width is 0, GENMASK() macro may not generate expected mask (0)
+ * as it falls under undefined behaviour by C standard due to shifts
+ * which are equal or greater than width of left operand. This can
+ * be easily avoided by explicitly checking if width is 0.
+ */
+ if (nkmp->n.width)
+ n_mask = GENMASK(nkmp->n.width + nkmp->n.shift - 1,
+ nkmp->n.shift);
+ if (nkmp->k.width)
+ k_mask = GENMASK(nkmp->k.width + nkmp->k.shift - 1,
+ nkmp->k.shift);
+ if (nkmp->m.width)
+ m_mask = GENMASK(nkmp->m.width + nkmp->m.shift - 1,
+ nkmp->m.shift);
+ if (nkmp->p.width)
+ p_mask = GENMASK(nkmp->p.width + nkmp->p.shift - 1,
+ nkmp->p.shift);
spin_lock_irqsave(nkmp->common.lock, flags);
config NPCM7XX_TIMER
bool "NPCM7xx timer driver" if COMPILE_TEST
depends on HAS_IOMEM
+ select TIMER_OF
select CLKSRC_MMIO
help
Enable 24-bit TIMER0 and TIMER1 counters in the NPCM7xx architecture,
* published by the Free Software Foundation.
*/
-#define pr_fmt(fmt) "arm_arch_timer: " fmt
+#define pr_fmt(fmt) "arch_timer: " fmt
#include <linux/init.h>
#include <linux/kernel.h>
#include <clocksource/arm_arch_timer.h>
-#undef pr_fmt
-#define pr_fmt(fmt) "arch_timer: " fmt
-
#define CNTTIDR 0x08
#define CNTTIDR_VIRT(n) (BIT(1) << ((n) * 4))
TIMER_OF_DECLARE(ox810se_rps,
"oxsemi,ox810se-rps-timer", oxnas_rps_timer_init);
TIMER_OF_DECLARE(ox820_rps,
- "oxsemi,ox820se-rps-timer", oxnas_rps_timer_init);
+ "oxsemi,ox820-rps-timer", oxnas_rps_timer_init);
return 0;
}
-/* Optimized set_load which removes costly spin wait in timer_start */
-static int omap_dm_timer_set_load_start(struct omap_dm_timer *timer,
- int autoreload, unsigned int load)
-{
- u32 l;
-
- if (unlikely(!timer))
- return -EINVAL;
-
- omap_dm_timer_enable(timer);
-
- l = omap_dm_timer_read_reg(timer, OMAP_TIMER_CTRL_REG);
- if (autoreload) {
- l |= OMAP_TIMER_CTRL_AR;
- omap_dm_timer_write_reg(timer, OMAP_TIMER_LOAD_REG, load);
- } else {
- l &= ~OMAP_TIMER_CTRL_AR;
- }
- l |= OMAP_TIMER_CTRL_ST;
-
- __omap_dm_timer_load_start(timer, l, load, timer->posted);
-
- /* Save the context */
- timer->context.tclr = l;
- timer->context.tldr = load;
- timer->context.tcrr = load;
- return 0;
-}
static int omap_dm_timer_set_match(struct omap_dm_timer *timer, int enable,
unsigned int match)
{
d = bcm2835_dma_create_cb_chain(chan, direction, false,
info, extra,
frames, src, dst, 0, 0,
- GFP_KERNEL);
+ GFP_NOWAIT);
if (!d)
return NULL;
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
mtk_dma_set(pc, MTK_CQDMA_DST2, cvd->dest >> MTK_CQDMA_ADDR2_SHFIT);
#else
- mtk_dma_set(pc, MTK_CQDMA_SRC2, 0);
+ mtk_dma_set(pc, MTK_CQDMA_DST2, 0);
#endif
/* setup the length */
enum dma_status status;
unsigned int residue = 0;
unsigned int dptr = 0;
+ unsigned int chcrb;
+ unsigned int tcrb;
+ unsigned int i;
if (!desc)
return 0;
return 0;
}
+ /*
+ * We need to read two registers.
+ * Make sure the control register does not skip to next chunk
+ * while reading the counter.
+ * Trying it 3 times should be enough: Initial read, retry, retry
+ * for the paranoid.
+ */
+ for (i = 0; i < 3; i++) {
+ chcrb = rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+ RCAR_DMACHCRB_DPTR_MASK;
+ tcrb = rcar_dmac_chan_read(chan, RCAR_DMATCRB);
+ /* Still the same? */
+ if (chcrb == (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+ RCAR_DMACHCRB_DPTR_MASK))
+ break;
+ }
+ WARN_ONCE(i >= 3, "residue might be not continuous!");
+
/*
* In descriptor mode the descriptor running pointer is not maintained
* by the interrupt handler, find the running descriptor from the
* mode just use the running descriptor pointer.
*/
if (desc->hwdescs.use) {
- dptr = (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
- RCAR_DMACHCRB_DPTR_MASK) >> RCAR_DMACHCRB_DPTR_SHIFT;
+ dptr = chcrb >> RCAR_DMACHCRB_DPTR_SHIFT;
if (dptr == 0)
dptr = desc->nchunks;
dptr--;
}
/* Add the residue for the current chunk. */
- residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
+ residue += tcrb << desc->xfer_shift;
return residue;
}
enum dma_status status;
unsigned long flags;
unsigned int residue;
+ bool cyclic;
status = dma_cookie_status(chan, cookie, txstate);
if (status == DMA_COMPLETE || !txstate)
spin_lock_irqsave(&rchan->lock, flags);
residue = rcar_dmac_chan_get_residue(rchan, cookie);
+ cyclic = rchan->desc.running ? rchan->desc.running->cyclic : false;
spin_unlock_irqrestore(&rchan->lock, flags);
/* if there's no residue, the cookie is complete */
- if (!residue)
+ if (!residue && !cyclic)
return DMA_COMPLETE;
dma_set_residue(txstate, residue);
config EXTCON_PTN5150
tristate "NXP PTN5150 CC LOGIC USB EXTCON support"
- depends on I2C && GPIOLIB || COMPILE_TEST
+ depends on I2C && (GPIOLIB || COMPILE_TEST)
select REGMAP_I2C
help
Say Y here to enable support for USB peripheral and USB host
nr++;
}
-void __init dmi_memdev_walk(void)
+static void __init dmi_memdev_walk(void)
{
- if (!dmi_available)
- return;
-
if (dmi_walk_early(count_mem_devices) == 0 && dmi_memdev_nr) {
dmi_memdev = dmi_alloc(sizeof(*dmi_memdev) * dmi_memdev_nr);
if (dmi_memdev)
return 1;
}
-void __init dmi_scan_machine(void)
+static void __init dmi_scan_machine(void)
{
char __iomem *p, *q;
char buf[32];
subsys_initcall(dmi_init);
/**
- * dmi_set_dump_stack_arch_desc - set arch description for dump_stack()
+ * dmi_setup - scan and setup DMI system information
*
- * Invoke dump_stack_set_arch_desc() with DMI system information so that
- * DMI identifiers are printed out on task dumps. Arch boot code should
- * call this function after dmi_scan_machine() if it wants to print out DMI
- * identifiers on task dumps.
+ * Scan the DMI system information. This setups DMI identifiers
+ * (dmi_system_id) for printing it out on task dumps and prepares
+ * DIMM entry information (dmi_memdev_info) from the SMBIOS table
+ * for using this when reporting memory errors.
*/
-void __init dmi_set_dump_stack_arch_desc(void)
+void __init dmi_setup(void)
{
+ dmi_scan_machine();
+ if (!dmi_available)
+ return;
+
+ dmi_memdev_walk();
dump_stack_set_arch_desc("%s", dmi_ids_string);
}
* returns non zero or we hit the end. Callback function is called for
* each successful match. Returns the number of matches.
*
- * dmi_scan_machine must be called before this function is called.
+ * dmi_setup must be called before this function is called.
*/
int dmi_check_system(const struct dmi_system_id *list)
{
* Walk the blacklist table until the first match is found. Return the
* pointer to the matching entry or NULL if there's no match.
*
- * dmi_scan_machine must be called before this function is called.
+ * dmi_setup must be called before this function is called.
*/
const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list)
{
static int __init arm_dmi_init(void)
{
/*
- * On arm64/ARM, DMI depends on UEFI, and dmi_scan_machine() needs to
+ * On arm64/ARM, DMI depends on UEFI, and dmi_setup() needs to
* be called early because dmi_id_init(), which is an arch_initcall
* itself, depends on dmi_scan_machine() having been called already.
*/
- dmi_scan_machine();
- if (dmi_available)
- dmi_set_dump_stack_arch_desc();
+ dmi_setup();
return 0;
}
core_initcall(arm_dmi_init);
extra-$(CONFIG_EFI_ARMSTUB) := $(lib-y)
lib-$(CONFIG_EFI_ARMSTUB) := $(patsubst %.o,%.stub.o,$(lib-y))
-STUBCOPY_RM-y := -R *ksymtab* -R *kcrctab*
STUBCOPY_FLAGS-$(CONFIG_ARM64) += --prefix-alloc-sections=.init \
--prefix-symbols=__efistub_
STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS
# this time, use objcopy and leave all sections in place.
#
quiet_cmd_stubcopy = STUBCPY $@
- cmd_stubcopy = if $(STRIP) --strip-debug $(STUBCOPY_RM-y) -o $@ $<; \
- then if $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y); \
- then (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \
- rm -f $@; /bin/false); \
- else $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; fi \
- else /bin/false; fi
+ cmd_stubcopy = \
+ $(STRIP) --strip-debug -o $@ $<; \
+ if $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y); then \
+ echo "$@: absolute symbol references not allowed in the EFI stub" >&2; \
+ /bin/false; \
+ fi; \
+ $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@
#
# ARM discards the .data section because it disallows r/w data in the
irq_set_handler_locked(data, handle_edge_irq);
break;
case IRQ_TYPE_EDGE_BOTH:
+ sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1);
irq_set_handler_locked(data, handle_edge_irq);
break;
status = gpiochip_add_irqchip(chip, lock_key, request_key);
if (status)
- goto err_remove_chip;
+ goto err_free_gpiochip_mask;
status = of_gpiochip_add(chip);
if (status)
status = gpiochip_init_valid_mask(chip);
if (status)
- goto err_remove_chip;
+ goto err_remove_of_chip;
for (i = 0; i < chip->ngpio; i++) {
struct gpio_desc *desc = &gdev->descs[i];
if (gpiolib_initialized) {
status = gpiochip_setup_dev(gdev);
if (status)
- goto err_remove_chip;
+ goto err_remove_acpi_chip;
}
return 0;
-err_remove_chip:
+err_remove_acpi_chip:
acpi_gpiochip_remove(chip);
+err_remove_of_chip:
gpiochip_free_hogs(chip);
of_gpiochip_remove(chip);
+err_remove_chip:
+ gpiochip_irqchip_remove(chip);
+err_free_gpiochip_mask:
gpiochip_free_valid_mask(chip);
err_remove_irqchip_mask:
gpiochip_irqchip_free_valid_mask(chip);
/* No need to recover an evicted BO */
if (shadow->tbo.mem.mem_type != TTM_PL_TT ||
+ shadow->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET ||
shadow->parent->tbo.mem.mem_type != TTM_PL_VRAM)
continue;
tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
}
+ WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL3, tmp);
tmp = mmVM_L2_CNTL4_DEFAULT;
tmp = REG_SET_FIELD(tmp, VM_L2_CNTL4, VMC_TAP_PDE_REQUEST_PHYSICAL, 0);
return UPDATE_TYPE_FULL;
}
+ if (u->surface->force_full_update) {
+ update_flags->bits.full_update = 1;
+ return UPDATE_TYPE_FULL;
+ }
+
type = get_plane_info_update_type(u);
elevate_update_type(&overall_type, type);
}
dc_resource_state_copy_construct(state, context);
+
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
+ struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+
+ if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state)
+ new_pipe->plane_state->force_full_update = true;
+ }
}
dc->current_state = context;
dc_release_state(old);
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+ if (pipe_ctx->plane_state && pipe_ctx->stream == stream)
+ pipe_ctx->plane_state->force_full_update = false;
+ }
}
/*let's use current_state to update watermark etc*/
if (update_type >= UPDATE_TYPE_FULL)
struct dc_plane_status status;
struct dc_context *ctx;
+ /* HACK: Workaround for forcing full reprogramming under some conditions */
+ bool force_full_update;
+
/* private to dc_surface.c */
enum dc_irq_source irq_source;
struct kref refcount;
1,
0);
}
+
+ REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
+
+ REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
+ 10, aux110->timeout_period/10);
+
/* set the delay and the number of bytes to write */
/* The length include
}
}
- REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
- REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
- 10, aux110->timeout_period/10);
REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
}
* at most within ~240usec. That means,
* increasing this timeout will not affect normal operation,
* and we'll timeout after
- * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 1600usec.
+ * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 2400usec.
* This timeout is especially important for
- * resume from S3 and CTS.
+ * converters, resume from S3, and CTS.
*/
- SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 4
+ SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 6
};
struct dce_aux {
if (hdmi->version < 0x200a)
return false;
+ /* Disable if no DDC bus */
+ if (!hdmi->ddc)
+ return false;
+
/* Disable if SCDC is not supported, or if an HF-VSDB block is absent */
if (!display->hdmi.scdc.supported ||
!display->hdmi.scdc.scrambling.supported)
* Source Devices compliant shall set the
* Source Version = 1.
*/
- drm_scdc_readb(&hdmi->i2c->adap, SCDC_SINK_VERSION,
+ drm_scdc_readb(hdmi->ddc, SCDC_SINK_VERSION,
&bytes);
- drm_scdc_writeb(&hdmi->i2c->adap, SCDC_SOURCE_VERSION,
+ drm_scdc_writeb(hdmi->ddc, SCDC_SOURCE_VERSION,
min_t(u8, bytes, SCDC_MIN_SOURCE_VERSION));
/* Enabled Scrambling in the Sink */
- drm_scdc_set_scrambling(&hdmi->i2c->adap, 1);
+ drm_scdc_set_scrambling(hdmi->ddc, 1);
/*
* To activate the scrambler feature, you must ensure
hdmi_writeb(hdmi, 0, HDMI_FC_SCRAMBLER_CTRL);
hdmi_writeb(hdmi, (u8)~HDMI_MC_SWRSTZ_TMDSSWRST_REQ,
HDMI_MC_SWRSTZ);
- drm_scdc_set_scrambling(&hdmi->i2c->adap, 0);
+ drm_scdc_set_scrambling(hdmi->ddc, 0);
}
}
* iteration for others.
* The Amlogic Meson GX SoCs (v2.01a) have been identified as needing
* the workaround with a single iteration.
+ * The Rockchip RK3288 SoC (v2.00a) and RK3328/RK3399 SoCs (v2.11a) have
+ * been identified as needing the workaround with a single iteration.
*/
switch (hdmi->version) {
break;
case 0x131a:
case 0x132a:
+ case 0x200a:
case 0x201a:
+ case 0x211a:
case 0x212a:
count = 1;
break;
static noinline void save_stack(struct drm_mm_node *node)
{
unsigned long entries[STACKDEPTH];
- struct stack_trace trace = {
- .entries = entries,
- .max_entries = STACKDEPTH,
- .skip = 1
- };
+ unsigned int n;
- save_stack_trace(&trace);
- if (trace.nr_entries != 0 &&
- trace.entries[trace.nr_entries-1] == ULONG_MAX)
- trace.nr_entries--;
+ n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
/* May be called under spinlock, so avoid sleeping */
- node->stack = depot_save_stack(&trace, GFP_NOWAIT);
+ node->stack = stack_depot_save(entries, n, GFP_NOWAIT);
}
static void show_leaks(struct drm_mm *mm)
{
struct drm_mm_node *node;
- unsigned long entries[STACKDEPTH];
+ unsigned long *entries;
+ unsigned int nr_entries;
char *buf;
buf = kmalloc(BUFSZ, GFP_KERNEL);
return;
list_for_each_entry(node, drm_mm_nodes(mm), node_list) {
- struct stack_trace trace = {
- .entries = entries,
- .max_entries = STACKDEPTH
- };
-
if (!node->stack) {
DRM_ERROR("node [%08llx + %08llx]: unknown owner\n",
node->start, node->size);
continue;
}
- depot_fetch_stack(node->stack, &trace);
- snprint_stack_trace(buf, BUFSZ, &trace, 0);
+ nr_entries = stack_depot_fetch(node->stack, &entries);
+ stack_trace_snprint(buf, BUFSZ, entries, nr_entries, 0);
DRM_ERROR("node [%08llx + %08llx]: inserted at\n%s",
node->start, node->size, buf);
}
len)) {
end_user:
user_access_end();
+end:
kvfree(relocs);
err = -EFAULT;
goto err;
* relocations were valid.
*/
if (!user_access_begin(urelocs, size))
- goto end_user;
+ goto end;
for (copied = 0; copied < nreloc; copied++)
unsafe_put_user(-1,
* when we did the "copy_from_user()" above.
*/
if (!user_access_begin(user_exec_list, count * sizeof(*user_exec_list)))
- goto end_user;
+ goto end;
for (i = 0; i < args->buffer_count; i++) {
if (!(exec2_list[i].offset & UPDATE))
}
end_user:
user_access_end();
+end:;
}
args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
static void vma_print_allocator(struct i915_vma *vma, const char *reason)
{
- unsigned long entries[12];
- struct stack_trace trace = {
- .entries = entries,
- .max_entries = ARRAY_SIZE(entries),
- };
+ unsigned long *entries;
+ unsigned int nr_entries;
char buf[512];
if (!vma->node.stack) {
return;
}
- depot_fetch_stack(vma->node.stack, &trace);
- snprint_stack_trace(buf, sizeof(buf), &trace, 0);
+ nr_entries = stack_depot_fetch(vma->node.stack, &entries);
+ stack_trace_snprint(buf, sizeof(buf), entries, nr_entries, 0);
DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n",
vma->node.start, vma->node.size, reason, buf);
}
ret = intel_hdmi_compute_config(encoder, pipe_config, conn_state);
else
ret = intel_dp_compute_config(encoder, pipe_config, conn_state);
+ if (ret)
+ return ret;
- if (IS_GEN9_LP(dev_priv) && ret)
+ if (IS_GEN9_LP(dev_priv))
pipe_config->lane_lat_optim_mask =
bxt_ddi_phy_calc_lane_lat_optim_mask(pipe_config->lane_count);
intel_ddi_compute_min_voltage_level(dev_priv, pipe_config);
- return ret;
+ return 0;
}
int pipe_bpp;
int ret;
+ pipe_config->fec_enable = !intel_dp_is_edp(intel_dp) &&
+ intel_dp_supports_fec(intel_dp, pipe_config);
+
if (!intel_dp_supports_dsc(intel_dp, pipe_config))
return -EINVAL;
if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
return -EINVAL;
- pipe_config->fec_enable = !intel_dp_is_edp(intel_dp) &&
- intel_dp_supports_fec(intel_dp, pipe_config);
-
ret = intel_dp_compute_link_config(encoder, pipe_config, conn_state);
if (ret < 0)
return ret;
bool *enabled, int width, int height)
{
struct drm_i915_private *dev_priv = to_i915(fb_helper->dev);
+ unsigned long conn_configured, conn_seq, mask;
unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG);
- unsigned long conn_configured, conn_seq;
int i, j;
bool *save_enabled;
bool fallback = true, ret = true;
drm_modeset_backoff(&ctx);
memcpy(save_enabled, enabled, count);
- conn_seq = GENMASK(count - 1, 0);
+ mask = GENMASK(count - 1, 0);
conn_configured = 0;
retry:
+ conn_seq = conn_configured;
for (i = 0; i < count; i++) {
struct drm_fb_helper_connector *fb_conn;
struct drm_connector *connector;
if (conn_configured & BIT(i))
continue;
- /* First pass, only consider tiled connectors */
- if (conn_seq == GENMASK(count - 1, 0) && !connector->has_tile)
+ if (conn_seq == 0 && !connector->has_tile)
continue;
if (connector->status == connector_status_connected)
conn_configured |= BIT(i);
}
- if (conn_configured != conn_seq) { /* repeat until no more are found */
- conn_seq = conn_configured;
+ if ((conn_configured & mask) != mask && conn_configured != conn_seq)
goto retry;
- }
/*
* If the BIOS didn't enable everything it could, fall back to have the
static noinline depot_stack_handle_t __save_depot_stack(void)
{
unsigned long entries[STACKDEPTH];
- struct stack_trace trace = {
- .entries = entries,
- .max_entries = ARRAY_SIZE(entries),
- .skip = 1,
- };
+ unsigned int n;
- save_stack_trace(&trace);
- if (trace.nr_entries &&
- trace.entries[trace.nr_entries - 1] == ULONG_MAX)
- trace.nr_entries--;
-
- return depot_save_stack(&trace, GFP_NOWAIT | __GFP_NOWARN);
+ n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
+ return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN);
}
static void __print_depot_stack(depot_stack_handle_t stack,
char *buf, int sz, int indent)
{
- unsigned long entries[STACKDEPTH];
- struct stack_trace trace = {
- .entries = entries,
- .max_entries = ARRAY_SIZE(entries),
- };
+ unsigned long *entries;
+ unsigned int nr_entries;
- depot_fetch_stack(stack, &trace);
- snprint_stack_trace(buf, sz, &trace, indent);
+ nr_entries = stack_depot_fetch(stack, &entries);
+ stack_trace_snprint(buf, sz, entries, nr_entries, indent);
}
static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
if (disable_partial)
ipu_plane_disable(ipu_crtc->plane[1], true);
if (disable_full)
- ipu_plane_disable(ipu_crtc->plane[0], false);
+ ipu_plane_disable(ipu_crtc->plane[0], true);
}
static void ipu_crtc_atomic_disable(struct drm_crtc *crtc,
#if defined(CONFIG_DEBUG_FS)
.debugfs_init = qxl_debugfs_init,
#endif
+ .prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+ .prime_fd_to_handle = drm_gem_prime_fd_to_handle,
.gem_prime_export = drm_gem_prime_export,
.gem_prime_import = drm_gem_prime_import,
.gem_prime_pin = qxl_gem_prime_pin,
.gem_prime_unpin = qxl_gem_prime_unpin,
+ .gem_prime_get_sg_table = qxl_gem_prime_get_sg_table,
+ .gem_prime_import_sg_table = qxl_gem_prime_import_sg_table,
.gem_prime_vmap = qxl_gem_prime_vmap,
.gem_prime_vunmap = qxl_gem_prime_vunmap,
.gem_prime_mmap = qxl_gem_prime_mmap,
qxl_bo_unpin(bo);
}
+struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+struct drm_gem_object *qxl_gem_prime_import_sg_table(
+ struct drm_device *dev, struct dma_buf_attachment *attach,
+ struct sg_table *table)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
void *qxl_gem_prime_vmap(struct drm_gem_object *obj)
{
struct qxl_bo *bo = gem_to_qxl_bo(obj);
EXPORT_SYMBOL(drm_sched_increase_karma);
/**
- * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
+ * drm_sched_stop - stop the scheduler
*
* @sched: scheduler instance
- * @bad: bad scheduler job
*
*/
void drm_sched_stop(struct drm_gpu_scheduler *sched)
#include <linux/of_reserved_mem.h>
#include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
#include <drm/drm_fb_cma_helper.h>
#include <drm/drm_fb_helper.h>
#include <drm/drm_gem_cma_helper.h>
ret = -ENOMEM;
goto free_drm;
}
+
+ dev_set_drvdata(dev, drm);
drm->dev_private = drv;
INIT_LIST_HEAD(&drv->frontend_list);
INIT_LIST_HEAD(&drv->engine_list);
drm_dev_unregister(drm);
drm_kms_helper_poll_fini(drm);
+ drm_atomic_helper_shutdown(drm);
drm_mode_config_cleanup(drm);
+
+ component_unbind_all(dev, NULL);
of_reserved_mem_device_release(dev);
+
drm_dev_put(drm);
}
static int sun4i_drv_remove(struct platform_device *pdev)
{
+ component_master_del(&pdev->dev, &sun4i_drv_master_ops);
+
return 0;
}
hdmi->dvi = !tegra_output_is_hdmi(output);
if (!hdmi->dvi) {
- err = tegra_hdmi_setup_audio(hdmi);
- if (err < 0)
- hdmi->dvi = true;
+ /*
+ * Make sure that the audio format has been configured before
+ * enabling audio, otherwise we may try to divide by zero.
+ */
+ if (hdmi->format.sample_rate > 0) {
+ err = tegra_hdmi_setup_audio(hdmi);
+ if (err < 0)
+ hdmi->dvi = true;
+ }
}
if (hdmi->config->has_hda)
* ttm_global_mutex - protecting the global BO state
*/
DEFINE_MUTEX(ttm_global_mutex);
-struct ttm_bo_global ttm_bo_glob = {
- .use_count = 0
-};
+unsigned ttm_bo_glob_use_count;
+struct ttm_bo_global ttm_bo_glob;
static struct attribute ttm_bo_count = {
.name = "bo_count",
reservation_object_add_shared_fence(bo->resv, fence);
ret = reservation_object_reserve_shared(bo->resv, 1);
- if (unlikely(ret))
+ if (unlikely(ret)) {
+ dma_fence_put(fence);
return ret;
+ }
dma_fence_put(bo->moving);
bo->moving = fence;
struct ttm_bo_global *glob = &ttm_bo_glob;
mutex_lock(&ttm_global_mutex);
- if (--glob->use_count > 0)
+ if (--ttm_bo_glob_use_count > 0)
goto out;
kobject_del(&glob->kobj);
kobject_put(&glob->kobj);
ttm_mem_global_release(&ttm_mem_glob);
+ memset(glob, 0, sizeof(*glob));
out:
mutex_unlock(&ttm_global_mutex);
}
unsigned i;
mutex_lock(&ttm_global_mutex);
- if (++glob->use_count > 1)
+ if (++ttm_bo_glob_use_count > 1)
goto out;
ret = ttm_mem_global_init(&ttm_mem_glob);
void ttm_mem_global_release(struct ttm_mem_global *glob)
{
- unsigned int i;
struct ttm_mem_zone *zone;
+ unsigned int i;
/* let the page allocator first stop the shrink work. */
ttm_page_alloc_fini();
zone = glob->zones[i];
kobject_del(&zone->kobj);
kobject_put(&zone->kobj);
- }
+ }
kobject_del(&glob->kobj);
kobject_put(&glob->kobj);
+ memset(glob, 0, sizeof(*glob));
}
static void ttm_check_swapping(struct ttm_mem_global *glob)
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- if (!(flags & TTM_PAGE_FLAG_DMA32)) {
- for (j = 0; j < HPAGE_PMD_NR; ++j)
- if (p++ != pages[i + j])
+ if (!(flags & TTM_PAGE_FLAG_DMA32) &&
+ (npages - i) >= HPAGE_PMD_NR) {
+ for (j = 1; j < HPAGE_PMD_NR; ++j)
+ if (++p != pages[i + j])
break;
if (j == HPAGE_PMD_NR)
unsigned max_size, n2free;
spin_lock_irqsave(&huge->lock, irq_flags);
- while (i < npages) {
+ while ((npages - i) >= HPAGE_PMD_NR) {
struct page *p = pages[i];
unsigned j;
if (!p)
break;
- for (j = 0; j < HPAGE_PMD_NR; ++j)
- if (p++ != pages[i + j])
+ for (j = 1; j < HPAGE_PMD_NR; ++j)
+ if (++p != pages[i + j])
break;
if (j != HPAGE_PMD_NR)
vc4_crtc_reset(struct drm_crtc *crtc)
{
if (crtc->state)
- __drm_atomic_helper_crtc_destroy_state(crtc->state);
+ vc4_crtc_destroy_state(crtc, crtc->state);
crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL);
if (crtc->state)
#if defined(CONFIG_DEBUG_FS)
.debugfs_init = virtio_gpu_debugfs_init,
#endif
+ .prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+ .prime_fd_to_handle = drm_gem_prime_fd_to_handle,
.gem_prime_export = drm_gem_prime_export,
.gem_prime_import = drm_gem_prime_import,
.gem_prime_pin = virtgpu_gem_prime_pin,
.gem_prime_unpin = virtgpu_gem_prime_unpin,
+ .gem_prime_get_sg_table = virtgpu_gem_prime_get_sg_table,
+ .gem_prime_import_sg_table = virtgpu_gem_prime_import_sg_table,
.gem_prime_vmap = virtgpu_gem_prime_vmap,
.gem_prime_vunmap = virtgpu_gem_prime_vunmap,
.gem_prime_mmap = virtgpu_gem_prime_mmap,
/* virtgpu_prime.c */
int virtgpu_gem_prime_pin(struct drm_gem_object *obj);
void virtgpu_gem_prime_unpin(struct drm_gem_object *obj);
+struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj);
+struct drm_gem_object *virtgpu_gem_prime_import_sg_table(
+ struct drm_device *dev, struct dma_buf_attachment *attach,
+ struct sg_table *sgt);
void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj);
void virtgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
int virtgpu_gem_prime_mmap(struct drm_gem_object *obj,
WARN_ONCE(1, "not implemented");
}
+struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
+{
+ return ERR_PTR(-ENODEV);
+}
+
+struct drm_gem_object *virtgpu_gem_prime_import_sg_table(
+ struct drm_device *dev, struct dma_buf_attachment *attach,
+ struct sg_table *table)
+{
+ return ERR_PTR(-ENODEV);
+}
+
void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj)
{
struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj);
dev_priv->initial_height = height;
}
-/**
- * vmw_assume_iommu - Figure out whether coherent dma-remapping might be
- * taking place.
- * @dev: Pointer to the struct drm_device.
- *
- * Return: true if iommu present, false otherwise.
- */
-static bool vmw_assume_iommu(struct drm_device *dev)
-{
- const struct dma_map_ops *ops = get_dma_ops(dev->dev);
-
- return !dma_is_direct(ops) && ops &&
- ops->map_page != dma_direct_map_page;
-}
-
/**
* vmw_dma_select_mode - Determine how DMA mappings should be set up for this
* system.
*
* @dev_priv: Pointer to a struct vmw_private
*
- * This functions tries to determine the IOMMU setup and what actions
- * need to be taken by the driver to make system pages visible to the
- * device.
+ * This functions tries to determine what actions need to be taken by the
+ * driver to make system pages visible to the device.
* If this function decides that DMA is not possible, it returns -EINVAL.
* The driver may then try to disable features of the device that require
* DMA.
static const char *names[vmw_dma_map_max] = {
[vmw_dma_phys] = "Using physical TTM page addresses.",
[vmw_dma_alloc_coherent] = "Using coherent TTM pages.",
- [vmw_dma_map_populate] = "Keeping DMA mappings.",
+ [vmw_dma_map_populate] = "Caching DMA mappings.",
[vmw_dma_map_bind] = "Giving up DMA mappings early."};
if (vmw_force_coherent)
dev_priv->map_mode = vmw_dma_alloc_coherent;
- else if (vmw_assume_iommu(dev_priv->dev))
- dev_priv->map_mode = vmw_dma_map_populate;
- else if (!vmw_force_iommu)
- dev_priv->map_mode = vmw_dma_phys;
- else if (IS_ENABLED(CONFIG_SWIOTLB) && swiotlb_nr_tbl())
- dev_priv->map_mode = vmw_dma_alloc_coherent;
+ else if (vmw_restrict_iommu)
+ dev_priv->map_mode = vmw_dma_map_bind;
else
dev_priv->map_mode = vmw_dma_map_populate;
- if (dev_priv->map_mode == vmw_dma_map_populate && vmw_restrict_iommu)
- dev_priv->map_mode = vmw_dma_map_bind;
-
/* No TTM coherent page pool? FIXME: Ask TTM instead! */
if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) &&
(dev_priv->map_mode == vmw_dma_alloc_coherent))
static void host1x_channel_set_streamid(struct host1x_channel *channel)
{
-#if IS_ENABLED(CONFIG_IOMMU_API) && HOST1X_HW >= 6
+#if HOST1X_HW >= 6
+ u32 sid = 0x7f;
+#ifdef CONFIG_IOMMU_API
struct iommu_fwspec *spec = dev_iommu_fwspec_get(channel->dev->parent);
- u32 sid = spec ? spec->ids[0] & 0xffff : 0x7f;
+ if (spec)
+ sid = spec->ids[0] & 0xffff;
+#endif
host1x_ch_writel(channel, sid, HOST1X_CHANNEL_SMMU_STREAMID);
#endif
ipu_dp_csc_init(flow, flow->foreground.in_cs, flow->out_cs,
DP_COM_CONF_CSC_DEF_BOTH);
} else {
- if (flow->foreground.in_cs == flow->out_cs)
+ if (flow->foreground.in_cs == IPUV3_COLORSPACE_UNKNOWN ||
+ flow->foreground.in_cs == flow->out_cs)
/*
* foreground identical to output, apply color
* conversion on background
struct ipu_dp_priv *priv = flow->priv;
u32 reg, csc;
+ dp->in_cs = IPUV3_COLORSPACE_UNKNOWN;
+
if (!dp->foreground)
return;
reg = readl(flow->base + DP_COM_CONF);
csc = reg & DP_COM_CONF_CSC_DEF_MASK;
- if (csc == DP_COM_CONF_CSC_DEF_FG)
- reg &= ~DP_COM_CONF_CSC_DEF_MASK;
+ reg &= ~DP_COM_CONF_CSC_DEF_MASK;
+ if (csc == DP_COM_CONF_CSC_DEF_BOTH || csc == DP_COM_CONF_CSC_DEF_BG)
+ reg |= DP_COM_CONF_CSC_DEF_BG;
reg &= ~DP_COM_CONF_FG_EN;
writel(reg, flow->base + DP_COM_CONF);
mutex_init(&priv->mutex);
for (i = 0; i < IPUV3_NUM_FLOWS; i++) {
+ priv->flow[i].background.in_cs = IPUV3_COLORSPACE_UNKNOWN;
+ priv->flow[i].foreground.in_cs = IPUV3_COLORSPACE_UNKNOWN;
priv->flow[i].foreground.foreground = true;
priv->flow[i].base = priv->base + ipu_dp_flow_base[i];
priv->flow[i].priv = priv;
break;
}
+ if ((usage->hid & 0xf0) == 0xb0) { /* SC - Display */
+ switch (usage->hid & 0xf) {
+ case 0x05: map_key_clear(KEY_SWITCHVIDEOMODE); break;
+ default: goto ignore;
+ }
+ break;
+ }
+
/*
* Some lazy vendors declare 255 usages for System Control,
* leading to the creation of ABS_X|Y axis and too many others.
case 0x06a: map_key_clear(KEY_GREEN); break;
case 0x06b: map_key_clear(KEY_BLUE); break;
case 0x06c: map_key_clear(KEY_YELLOW); break;
- case 0x06d: map_key_clear(KEY_ZOOM); break;
+ case 0x06d: map_key_clear(KEY_ASPECT_RATIO); break;
case 0x06f: map_key_clear(KEY_BRIGHTNESSUP); break;
case 0x070: map_key_clear(KEY_BRIGHTNESSDOWN); break;
case 0x074: map_key_clear(KEY_BRIGHTNESS_MAX); break;
case 0x075: map_key_clear(KEY_BRIGHTNESS_AUTO); break;
+ case 0x079: map_key_clear(KEY_KBDILLUMUP); break;
+ case 0x07a: map_key_clear(KEY_KBDILLUMDOWN); break;
+ case 0x07c: map_key_clear(KEY_KBDILLUMTOGGLE); break;
+
case 0x082: map_key_clear(KEY_VIDEO_NEXT); break;
case 0x083: map_key_clear(KEY_LAST); break;
case 0x084: map_key_clear(KEY_ENTER); break;
case 0x22d: map_key_clear(KEY_ZOOMIN); break;
case 0x22e: map_key_clear(KEY_ZOOMOUT); break;
case 0x22f: map_key_clear(KEY_ZOOMRESET); break;
+ case 0x232: map_key_clear(KEY_FULL_SCREEN); break;
case 0x233: map_key_clear(KEY_SCROLLUP); break;
case 0x234: map_key_clear(KEY_SCROLLDOWN); break;
case 0x238: /* AC Pan */
case 0x2cb: map_key_clear(KEY_KBDINPUTASSIST_ACCEPT); break;
case 0x2cc: map_key_clear(KEY_KBDINPUTASSIST_CANCEL); break;
+ case 0x29f: map_key_clear(KEY_SCALE); break;
+
default: map_key_clear(KEY_UNKNOWN);
}
break;
pm_runtime_get_sync(dev->dev);
- if (dev->suspended) {
- dev_err(dev->dev, "Error %s call while suspended\n", __func__);
+ if (dev_WARN_ONCE(dev->dev, dev->suspended, "Transfer while suspended\n")) {
ret = -ESHUTDOWN;
goto done_nolock;
}
unsigned long action, void *data)
{
struct clk_notifier_data *ndata = data;
- struct imx_i2c_struct *i2c_imx = container_of(&ndata->clk,
+ struct imx_i2c_struct *i2c_imx = container_of(nb,
struct imx_i2c_struct,
- clk);
+ clk_change_nb);
if (action & POST_RATE_CHANGE)
i2c_imx_set_clk(i2c_imx, ndata->new_rate);
i2c->adapter = synquacer_i2c_ops;
i2c_set_adapdata(&i2c->adapter, i2c);
i2c->adapter.dev.parent = &pdev->dev;
+ i2c->adapter.dev.of_node = pdev->dev.of_node;
+ ACPI_COMPANION_SET(&i2c->adapter.dev, ACPI_COMPANION(&pdev->dev));
i2c->adapter.nr = pdev->id;
init_completion(&i2c->completion);
int i2c_generic_scl_recovery(struct i2c_adapter *adap)
{
struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
- int i = 0, scl = 1, ret;
+ int i = 0, scl = 1, ret = 0;
if (bri->prepare_recovery)
bri->prepare_recovery(adap);
if (client->flags & I2C_CLIENT_HOST_NOTIFY) {
dev_dbg(dev, "Using Host Notify IRQ\n");
+ /* Keep adapter active when Host Notify is required */
+ pm_runtime_get_sync(&client->adapter->dev);
irq = i2c_smbus_host_notify_to_irq(client);
} else if (dev->of_node) {
irq = of_irq_get_byname(dev->of_node, "irq");
device_init_wakeup(&client->dev, false);
client->irq = client->init_irq;
+ if (client->flags & I2C_CLIENT_HOST_NOTIFY)
+ pm_runtime_put(&client->adapter->dev);
return status;
}
{
struct i3c_dev_boardinfo *boardinfo;
struct device *dev = &master->dev;
- struct i3c_device_info info = { };
enum i3c_addr_slot_status addrstatus;
u32 init_dyn_addr = 0;
boardinfo->pid = ((u64)reg[1] << 32) | reg[2];
- if ((info.pid & GENMASK_ULL(63, 48)) ||
- I3C_PID_RND_LOWER_32BITS(info.pid))
+ if ((boardinfo->pid & GENMASK_ULL(63, 48)) ||
+ I3C_PID_RND_LOWER_32BITS(boardinfo->pid))
return -EINVAL;
boardinfo->init_dyn_addr = init_dyn_addr;
static void dw_i3c_master_disable(struct dw_i3c_master *master)
{
- writel(readl(master->regs + DEVICE_CTRL) & DEV_CTRL_ENABLE,
+ writel(readl(master->regs + DEVICE_CTRL) & ~DEV_CTRL_ENABLE,
master->regs + DEVICE_CTRL);
}
mutex_lock(&data->mutex);
ret = kxcjk1013_set_mode(data, OPERATION);
+ if (ret == 0)
+ ret = kxcjk1013_set_range(data, data->range);
mutex_unlock(&data->mutex);
return ret;
if (sigma_delta->info->has_registers) {
data[0] = reg << sigma_delta->info->addr_shift;
data[0] |= sigma_delta->info->read_mask;
+ data[0] |= sigma_delta->comm;
spi_message_add_tail(&t[0], &m);
}
spi_message_add_tail(&t[1], &m);
ret = wait_event_interruptible_timeout(st->wq_data_avail,
st->done,
msecs_to_jiffies(1000));
- if (ret == 0)
- ret = -ETIMEDOUT;
- if (ret < 0) {
- mutex_unlock(&st->lock);
- return ret;
- }
-
- *val = st->last_value;
+ /* Disable interrupts, regardless if adc conversion was
+ * successful or not
+ */
at91_adc_writel(st, AT91_ADC_CHDR,
AT91_ADC_CH(chan->channel));
at91_adc_writel(st, AT91_ADC_IDR, BIT(chan->channel));
- st->last_value = 0;
- st->done = false;
+ if (ret > 0) {
+ /* a valid conversion took place */
+ *val = st->last_value;
+ st->last_value = 0;
+ st->done = false;
+ ret = IIO_VAL_INT;
+ } else if (ret == 0) {
+ /* conversion timeout */
+ dev_err(&idev->dev, "ADC Channel %d timeout.\n",
+ chan->channel);
+ ret = -ETIMEDOUT;
+ }
+
mutex_unlock(&st->lock);
- return IIO_VAL_INT;
+ return ret;
case IIO_CHAN_INFO_SCALE:
*val = st->vref_mv;
err_free_irq:
free_irq(xadc->irq, indio_dev);
+ cancel_delayed_work_sync(&xadc->zynq_unmask_work);
err_clk_disable_unprepare:
clk_disable_unprepare(xadc->clk);
err_free_samplerate_trigger:
iio_triggered_buffer_cleanup(indio_dev);
}
free_irq(xadc->irq, indio_dev);
+ cancel_delayed_work_sync(&xadc->zynq_unmask_work);
clk_disable_unprepare(xadc->clk);
- cancel_delayed_work(&xadc->zynq_unmask_work);
kfree(xadc->data);
kfree(indio_dev->channels);
config PMS7003
tristate "Plantower PMS7003 particulate matter sensor"
depends on SERIAL_DEV_BUS
+ select IIO_TRIGGERED_BUFFER
help
Say Y here to build support for the Plantower PMS7003 particulate
matter sensor.
To compile this driver as a module, choose M here: the module will
be called pms7003.
+config SENSIRION_SGP30
+ tristate "Sensirion SGPxx gas sensors"
+ depends on I2C
+ select CRC8
+ help
+ Say Y here to build I2C interface support for the following
+ Sensirion SGP gas sensors:
+ * SGP30 gas sensor
+ * SGPC3 low power gas sensor
+
+ To compile this driver as module, choose M here: the
+ module will be called sgp30.
+
config SPS30
tristate "SPS30 particulate matter sensor"
depends on I2C
#ifndef BME680_H_
#define BME680_H_
-#define BME680_REG_CHIP_I2C_ID 0xD0
-#define BME680_REG_CHIP_SPI_ID 0x50
+#define BME680_REG_CHIP_ID 0xD0
#define BME680_CHIP_ID_VAL 0x61
-#define BME680_REG_SOFT_RESET_I2C 0xE0
-#define BME680_REG_SOFT_RESET_SPI 0x60
+#define BME680_REG_SOFT_RESET 0xE0
#define BME680_CMD_SOFTRESET 0xB6
#define BME680_REG_STATUS 0x73
#define BME680_SPI_MEM_PAGE_BIT BIT(4)
s32 t_fine;
};
+static const struct regmap_range bme680_volatile_ranges[] = {
+ regmap_reg_range(BME680_REG_MEAS_STAT_0, BME680_REG_GAS_R_LSB),
+ regmap_reg_range(BME680_REG_STATUS, BME680_REG_STATUS),
+ regmap_reg_range(BME680_T2_LSB_REG, BME680_GH3_REG),
+};
+
+static const struct regmap_access_table bme680_volatile_table = {
+ .yes_ranges = bme680_volatile_ranges,
+ .n_yes_ranges = ARRAY_SIZE(bme680_volatile_ranges),
+};
+
const struct regmap_config bme680_regmap_config = {
.reg_bits = 8,
.val_bits = 8,
+ .max_register = 0xef,
+ .volatile_table = &bme680_volatile_table,
+ .cache_type = REGCACHE_RBTREE,
};
EXPORT_SYMBOL(bme680_regmap_config);
s64 var1, var2, var3;
s16 calc_temp;
+ /* If the calibration is invalid, attempt to reload it */
+ if (!calib->par_t2)
+ bme680_read_calib(data, calib);
+
var1 = (adc_temp >> 3) - (calib->par_t1 << 1);
var2 = (var1 * calib->par_t2) >> 11;
var3 = ((var1 >> 1) * (var1 >> 1)) >> 12;
return ret;
}
-static int bme680_read_temp(struct bme680_data *data,
- int *val, int *val2)
+static int bme680_read_temp(struct bme680_data *data, int *val)
{
struct device *dev = regmap_get_device(data->regmap);
int ret;
* compensate_press/compensate_humid to get compensated
* pressure/humidity readings.
*/
- if (val && val2) {
- *val = comp_temp;
- *val2 = 100;
- return IIO_VAL_FRACTIONAL;
+ if (val) {
+ *val = comp_temp * 10; /* Centidegrees to millidegrees */
+ return IIO_VAL_INT;
}
return ret;
s32 adc_press;
/* Read and compensate temperature to get a reading of t_fine */
- ret = bme680_read_temp(data, NULL, NULL);
+ ret = bme680_read_temp(data, NULL);
if (ret < 0)
return ret;
u32 comp_humidity;
/* Read and compensate temperature to get a reading of t_fine */
- ret = bme680_read_temp(data, NULL, NULL);
+ ret = bme680_read_temp(data, NULL);
if (ret < 0)
return ret;
case IIO_CHAN_INFO_PROCESSED:
switch (chan->type) {
case IIO_TEMP:
- return bme680_read_temp(data, val, val2);
+ return bme680_read_temp(data, val);
case IIO_PRESSURE:
return bme680_read_press(data, val, val2);
case IIO_HUMIDITYRELATIVE:
{
struct iio_dev *indio_dev;
struct bme680_data *data;
+ unsigned int val;
int ret;
+ ret = regmap_write(regmap, BME680_REG_SOFT_RESET,
+ BME680_CMD_SOFTRESET);
+ if (ret < 0) {
+ dev_err(dev, "Failed to reset chip\n");
+ return ret;
+ }
+
+ ret = regmap_read(regmap, BME680_REG_CHIP_ID, &val);
+ if (ret < 0) {
+ dev_err(dev, "Error reading chip ID\n");
+ return ret;
+ }
+
+ if (val != BME680_CHIP_ID_VAL) {
+ dev_err(dev, "Wrong chip ID, got %x expected %x\n",
+ val, BME680_CHIP_ID_VAL);
+ return -ENODEV;
+ }
+
indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
if (!indio_dev)
return -ENOMEM;
{
struct regmap *regmap;
const char *name = NULL;
- unsigned int val;
- int ret;
regmap = devm_regmap_init_i2c(client, &bme680_regmap_config);
if (IS_ERR(regmap)) {
return PTR_ERR(regmap);
}
- ret = regmap_write(regmap, BME680_REG_SOFT_RESET_I2C,
- BME680_CMD_SOFTRESET);
- if (ret < 0) {
- dev_err(&client->dev, "Failed to reset chip\n");
- return ret;
- }
-
- ret = regmap_read(regmap, BME680_REG_CHIP_I2C_ID, &val);
- if (ret < 0) {
- dev_err(&client->dev, "Error reading I2C chip ID\n");
- return ret;
- }
-
- if (val != BME680_CHIP_ID_VAL) {
- dev_err(&client->dev, "Wrong chip ID, got %x expected %x\n",
- val, BME680_CHIP_ID_VAL);
- return -ENODEV;
- }
-
if (id)
name = id->name;
#include "bme680.h"
+struct bme680_spi_bus_context {
+ struct spi_device *spi;
+ u8 current_page;
+};
+
+/*
+ * In SPI mode there are only 7 address bits, a "page" register determines
+ * which part of the 8-bit range is active. This function looks at the address
+ * and writes the page selection bit if needed
+ */
+static int bme680_regmap_spi_select_page(
+ struct bme680_spi_bus_context *ctx, u8 reg)
+{
+ struct spi_device *spi = ctx->spi;
+ int ret;
+ u8 buf[2];
+ u8 page = (reg & 0x80) ? 0 : 1; /* Page "1" is low range */
+
+ if (page == ctx->current_page)
+ return 0;
+
+ /*
+ * Data sheet claims we're only allowed to change bit 4, so we must do
+ * a read-modify-write on each and every page select
+ */
+ buf[0] = BME680_REG_STATUS;
+ ret = spi_write_then_read(spi, buf, 1, buf + 1, 1);
+ if (ret < 0) {
+ dev_err(&spi->dev, "failed to set page %u\n", page);
+ return ret;
+ }
+
+ buf[0] = BME680_REG_STATUS;
+ if (page)
+ buf[1] |= BME680_SPI_MEM_PAGE_BIT;
+ else
+ buf[1] &= ~BME680_SPI_MEM_PAGE_BIT;
+
+ ret = spi_write(spi, buf, 2);
+ if (ret < 0) {
+ dev_err(&spi->dev, "failed to set page %u\n", page);
+ return ret;
+ }
+
+ ctx->current_page = page;
+
+ return 0;
+}
+
static int bme680_regmap_spi_write(void *context, const void *data,
size_t count)
{
- struct spi_device *spi = context;
+ struct bme680_spi_bus_context *ctx = context;
+ struct spi_device *spi = ctx->spi;
+ int ret;
u8 buf[2];
memcpy(buf, data, 2);
+
+ ret = bme680_regmap_spi_select_page(ctx, buf[0]);
+ if (ret)
+ return ret;
+
/*
* The SPI register address (= full register address without bit 7)
* and the write command (bit7 = RW = '0')
*/
buf[0] &= ~0x80;
- return spi_write_then_read(spi, buf, 2, NULL, 0);
+ return spi_write(spi, buf, 2);
}
static int bme680_regmap_spi_read(void *context, const void *reg,
size_t reg_size, void *val, size_t val_size)
{
- struct spi_device *spi = context;
+ struct bme680_spi_bus_context *ctx = context;
+ struct spi_device *spi = ctx->spi;
+ int ret;
+ u8 addr = *(const u8 *)reg;
+
+ ret = bme680_regmap_spi_select_page(ctx, addr);
+ if (ret)
+ return ret;
- return spi_write_then_read(spi, reg, reg_size, val, val_size);
+ addr |= 0x80; /* bit7 = RW = '1' */
+
+ return spi_write_then_read(spi, &addr, 1, val, val_size);
}
static struct regmap_bus bme680_regmap_bus = {
static int bme680_spi_probe(struct spi_device *spi)
{
const struct spi_device_id *id = spi_get_device_id(spi);
+ struct bme680_spi_bus_context *bus_context;
struct regmap *regmap;
- unsigned int val;
int ret;
spi->bits_per_word = 8;
return ret;
}
+ bus_context = devm_kzalloc(&spi->dev, sizeof(*bus_context), GFP_KERNEL);
+ if (!bus_context)
+ return -ENOMEM;
+
+ bus_context->spi = spi;
+ bus_context->current_page = 0xff; /* Undefined on warm boot */
+
regmap = devm_regmap_init(&spi->dev, &bme680_regmap_bus,
- &spi->dev, &bme680_regmap_config);
+ bus_context, &bme680_regmap_config);
if (IS_ERR(regmap)) {
dev_err(&spi->dev, "Failed to register spi regmap %d\n",
(int)PTR_ERR(regmap));
return PTR_ERR(regmap);
}
- ret = regmap_write(regmap, BME680_REG_SOFT_RESET_SPI,
- BME680_CMD_SOFTRESET);
- if (ret < 0) {
- dev_err(&spi->dev, "Failed to reset chip\n");
- return ret;
- }
-
- /* after power-on reset, Page 0(0x80-0xFF) of spi_mem_page is active */
- ret = regmap_read(regmap, BME680_REG_CHIP_SPI_ID, &val);
- if (ret < 0) {
- dev_err(&spi->dev, "Error reading SPI chip ID\n");
- return ret;
- }
-
- if (val != BME680_CHIP_ID_VAL) {
- dev_err(&spi->dev, "Wrong chip ID, got %x expected %x\n",
- val, BME680_CHIP_ID_VAL);
- return -ENODEV;
- }
- /*
- * select Page 1 of spi_mem_page to enable access to
- * to registers from address 0x00 to 0x7F.
- */
- ret = regmap_write_bits(regmap, BME680_REG_STATUS,
- BME680_SPI_MEM_PAGE_BIT,
- BME680_SPI_MEM_PAGE_1_VAL);
- if (ret < 0) {
- dev_err(&spi->dev, "failed to set page 1 of spi_mem_page\n");
- return ret;
- }
-
return bme680_core_probe(&spi->dev, regmap, id->name);
}
* Do not use IIO_DEGREE_TO_RAD to avoid precision
* loss. Round to the nearest integer.
*/
- *val = div_s64(val64 * 314159 + 9000000ULL, 1000);
- *val2 = 18000 << (CROS_EC_SENSOR_BITS - 1);
- ret = IIO_VAL_FRACTIONAL;
+ *val = 0;
+ *val2 = div_s64(val64 * 3141592653ULL,
+ 180 << (CROS_EC_SENSOR_BITS - 1));
+ ret = IIO_VAL_INT_PLUS_NANO;
break;
case MOTIONSENSE_TYPE_MAG:
/*
inoutbuf[0] = 0x60; /* write EEPROM */
inoutbuf[0] |= data->ref_mode << 3;
+ inoutbuf[0] |= data->powerdown ? ((data->powerdown_mode + 1) << 1) : 0;
inoutbuf[1] = data->dac_value >> 4;
inoutbuf[2] = (data->dac_value & 0xf) << 4;
case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
return bmg160_get_filter(data, val);
case IIO_CHAN_INFO_SCALE:
- *val = 0;
switch (chan->type) {
case IIO_TEMP:
- *val2 = 500000;
- return IIO_VAL_INT_PLUS_MICRO;
+ *val = 500;
+ return IIO_VAL_INT;
case IIO_ANGL_VEL:
{
int i;
for (i = 0; i < ARRAY_SIZE(bmg160_scale_table); ++i) {
if (bmg160_scale_table[i].dps_range ==
data->dps_range) {
+ *val = 0;
*val2 = bmg160_scale_table[i].scale;
return IIO_VAL_INT_PLUS_MICRO;
}
#include "mpu3050.h"
-#define MPU3050_CHIP_ID 0x69
+#define MPU3050_CHIP_ID 0x68
+#define MPU3050_CHIP_ID_MASK 0x7E
/*
* Register map: anything suffixed *_H is a big-endian high byte and always
goto err_power_down;
}
- if (val != MPU3050_CHIP_ID) {
- dev_err(dev, "unsupported chip id %02x\n", (u8)val);
+ if ((val & MPU3050_CHIP_ID_MASK) != MPU3050_CHIP_ID) {
+ dev_err(dev, "unsupported chip id %02x\n",
+ (u8)(val & MPU3050_CHIP_ID_MASK));
ret = -ENODEV;
goto err_power_down;
}
const unsigned long *mask;
unsigned long *trialmask;
- trialmask = kmalloc_array(BITS_TO_LONGS(indio_dev->masklength),
- sizeof(*trialmask),
- GFP_KERNEL);
+ trialmask = kcalloc(BITS_TO_LONGS(indio_dev->masklength),
+ sizeof(*trialmask), GFP_KERNEL);
if (trialmask == NULL)
return -ENOMEM;
if (!indio_dev->masklength) {
**/
void iio_device_unregister(struct iio_dev *indio_dev)
{
- mutex_lock(&indio_dev->info_exist_lock);
-
cdev_device_del(&indio_dev->chrdev, &indio_dev->dev);
+ mutex_lock(&indio_dev->info_exist_lock);
+
iio_device_unregister_debugfs(indio_dev);
iio_disable_all_buffers(indio_dev);
struct mutex umap_lock;
struct list_head umaps;
+ struct page *disassociate_page;
struct idr idr;
/* spinlock protects write access to idr */
kref_put(&file->async_file->ref,
ib_uverbs_release_async_event_file);
put_device(&file->device->dev);
+
+ if (file->disassociate_page)
+ __free_pages(file->disassociate_page, 0);
kfree(file);
}
kfree(priv);
}
+/*
+ * Once the zap_vma_ptes has been called touches to the VMA will come here and
+ * we return a dummy writable zero page for all the pfns.
+ */
+static vm_fault_t rdma_umap_fault(struct vm_fault *vmf)
+{
+ struct ib_uverbs_file *ufile = vmf->vma->vm_file->private_data;
+ struct rdma_umap_priv *priv = vmf->vma->vm_private_data;
+ vm_fault_t ret = 0;
+
+ if (!priv)
+ return VM_FAULT_SIGBUS;
+
+ /* Read only pages can just use the system zero page. */
+ if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) {
+ vmf->page = ZERO_PAGE(vmf->address);
+ get_page(vmf->page);
+ return 0;
+ }
+
+ mutex_lock(&ufile->umap_lock);
+ if (!ufile->disassociate_page)
+ ufile->disassociate_page =
+ alloc_pages(vmf->gfp_mask | __GFP_ZERO, 0);
+
+ if (ufile->disassociate_page) {
+ /*
+ * This VMA is forced to always be shared so this doesn't have
+ * to worry about COW.
+ */
+ vmf->page = ufile->disassociate_page;
+ get_page(vmf->page);
+ } else {
+ ret = VM_FAULT_SIGBUS;
+ }
+ mutex_unlock(&ufile->umap_lock);
+
+ return ret;
+}
+
static const struct vm_operations_struct rdma_umap_ops = {
.open = rdma_umap_open,
.close = rdma_umap_close,
+ .fault = rdma_umap_fault,
};
static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext,
struct ib_uverbs_file *ufile = ucontext->ufile;
struct rdma_umap_priv *priv;
+ if (!(vma->vm_flags & VM_SHARED))
+ return ERR_PTR(-EINVAL);
+
if (vma->vm_end - vma->vm_start != size)
return ERR_PTR(-EINVAL);
* at a time to get the lock ordering right. Typically there
* will only be one mm, so no big deal.
*/
- down_write(&mm->mmap_sem);
+ down_read(&mm->mmap_sem);
+ if (!mmget_still_valid(mm))
+ goto skip_mm;
mutex_lock(&ufile->umap_lock);
list_for_each_entry_safe (priv, next_priv, &ufile->umaps,
list) {
zap_vma_ptes(vma, vma->vm_start,
vma->vm_end - vma->vm_start);
- vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
}
mutex_unlock(&ufile->umap_lock);
- up_write(&mm->mmap_sem);
+ skip_mm:
+ up_read(&mm->mmap_sem);
mmput(mm);
}
}
static int hns_roce_qp_has_sq(struct ib_qp_init_attr *attr)
{
- if (attr->qp_type == IB_QPT_XRC_TGT)
+ if (attr->qp_type == IB_QPT_XRC_TGT || !attr->cap.max_send_wr)
return 0;
return 1;
if (MLX5_CAP_GEN(mdev, qp_packet_based))
resp.flags |=
MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE;
+
+ resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT;
}
if (field_avail(typeof(resp), sw_parsing_caps,
if (vma->vm_flags & VM_WRITE)
return -EPERM;
+ vma->vm_flags &= ~VM_MAYWRITE;
if (!dev->mdev->clock_info_page)
return -EOPNOTSUPP;
if (vma->vm_flags & VM_WRITE)
return -EPERM;
+ vma->vm_flags &= ~VM_MAYWRITE;
/* Don't expose to user-space information it shouldn't have */
if (PAGE_SIZE > 4096)
return -EOPNOTSUPP;
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
pfn = (dev->mdev->iseg_base +
offsetof(struct mlx5_init_seg, internal_timer_h)) >>
PAGE_SHIFT;
- if (io_remap_pfn_range(vma, vma->vm_start, pfn,
- PAGE_SIZE, vma->vm_page_prot))
- return -EAGAIN;
- break;
+ return rdma_user_mmap_io(&context->ibucontext, vma, pfn,
+ PAGE_SIZE,
+ pgprot_noncached(vma->vm_page_prot));
case MLX5_IB_MMAP_CLOCK_INFO:
return mlx5_ib_mmap_clock_info_page(dev, vma, context);
rcqe_sz = mlx5_ib_get_cqe_size(init_attr->recv_cq);
- if (rcqe_sz == 128) {
- MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE);
+ if (init_attr->qp_type == MLX5_IB_QPT_DCT) {
+ if (rcqe_sz == 128)
+ MLX5_SET(dctc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE);
+
return;
}
- if (init_attr->qp_type != MLX5_IB_QPT_DCT)
- MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA32_CQE);
+ MLX5_SET(qpc, qpc, cs_res,
+ rcqe_sz == 128 ? MLX5_RES_SCAT_DATA64_CQE :
+ MLX5_RES_SCAT_DATA32_CQE);
}
static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev,
if (unlikely(mapped_segs == mr->mr.max_segs))
return -ENOMEM;
- if (mr->mr.length == 0) {
- mr->mr.user_base = addr;
- mr->mr.iova = addr;
- }
-
m = mapped_segs / RVT_SEGSZ;
n = mapped_segs % RVT_SEGSZ;
mr->mr.map[m]->segs[n].vaddr = (void *)addr;
* @sg_nents: number of entries in sg
* @sg_offset: offset in bytes into sg
*
+ * Overwrite rvt_mr length with mr length calculated by ib_sg_to_pages.
+ *
* Return: number of sg elements mapped to the memory region
*/
int rvt_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
int sg_nents, unsigned int *sg_offset)
{
struct rvt_mr *mr = to_imr(ibmr);
+ int ret;
mr->mr.length = 0;
mr->mr.page_shift = PAGE_SHIFT;
- return ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset,
- rvt_set_page);
+ ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rvt_set_page);
+ mr->mr.user_base = ibmr->iova;
+ mr->mr.iova = ibmr->iova;
+ mr->mr.offset = ibmr->iova - (u64)mr->mr.map[0]->segs[0].vaddr;
+ mr->mr.length = (size_t)ibmr->length;
+ return ret;
}
/**
ibmr->rkey = key;
mr->mr.lkey = key;
mr->mr.access_flags = access;
+ mr->mr.iova = ibmr->iova;
atomic_set(&mr->mr.lkey_invalid, 0);
return 0;
config KEYBOARD_SNVS_PWRKEY
tristate "IMX SNVS Power Key Driver"
- depends on SOC_IMX6SX || SOC_IMX7D
+ depends on ARCH_MXC || COMPILE_TEST
depends on OF
help
This is the snvs powerkey driver for the Freescale i.MX application
return error;
}
+ pdata->input = input;
+ platform_set_drvdata(pdev, pdata);
+
error = devm_request_irq(&pdev->dev, pdata->irq,
imx_snvs_pwrkey_interrupt,
0, pdev->name, pdev);
return error;
}
- pdata->input = input;
- platform_set_drvdata(pdev, pdata);
-
device_init_wakeup(&pdev->dev, pdata->wakeup);
return 0;
{ "ELAN0600", 0 },
{ "ELAN0601", 0 },
{ "ELAN0602", 0 },
+ { "ELAN0603", 0 },
+ { "ELAN0604", 0 },
{ "ELAN0605", 0 },
+ { "ELAN0606", 0 },
+ { "ELAN0607", 0 },
{ "ELAN0608", 0 },
{ "ELAN0609", 0 },
{ "ELAN060B", 0 },
{ "ELAN060C", 0 },
+ { "ELAN060F", 0 },
+ { "ELAN0610", 0 },
{ "ELAN0611", 0 },
{ "ELAN0612", 0 },
+ { "ELAN0615", 0 },
+ { "ELAN0616", 0 },
{ "ELAN0617", 0 },
{ "ELAN0618", 0 },
+ { "ELAN0619", 0 },
+ { "ELAN061A", 0 },
+ { "ELAN061B", 0 },
{ "ELAN061C", 0 },
{ "ELAN061D", 0 },
{ "ELAN061E", 0 },
+ { "ELAN061F", 0 },
{ "ELAN0620", 0 },
{ "ELAN0621", 0 },
{ "ELAN0622", 0 },
+ { "ELAN0623", 0 },
+ { "ELAN0624", 0 },
+ { "ELAN0625", 0 },
+ { "ELAN0626", 0 },
+ { "ELAN0627", 0 },
+ { "ELAN0628", 0 },
+ { "ELAN0629", 0 },
+ { "ELAN062A", 0 },
+ { "ELAN062B", 0 },
+ { "ELAN062C", 0 },
+ { "ELAN062D", 0 },
+ { "ELAN0631", 0 },
+ { "ELAN0632", 0 },
{ "ELAN1000", 0 },
{ }
};
error = rmi_register_function(fn);
if (error)
- goto err_put_fn;
+ return error;
if (pdt->function_number == 0x01)
data->f01_container = fn;
list_add_tail(&fn->node, &data->function_list);
return RMI_SCAN_CONTINUE;
-
-err_put_fn:
- put_device(&fn->dev);
- return error;
}
void rmi_enable_irq(struct rmi_device *rmi_dev, bool clear_wake)
}
rc = f11_write_control_regs(fn, &f11->sens_query,
- &f11->dev_controls, fn->fd.query_base_addr);
+ &f11->dev_controls, fn->fd.control_base_addr);
if (rc)
dev_warn(&fn->dev, "Failed to write control registers\n");
#define AR71XX_RESET_REG_MISC_INT_ENABLE 4
#define ATH79_MISC_IRQ_COUNT 32
+#define ATH79_MISC_PERF_IRQ 5
+
+static int ath79_perfcount_irq;
+
+int get_c0_perfcount_int(void)
+{
+ return ath79_perfcount_irq;
+}
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
static void ath79_misc_irq_handler(struct irq_desc *desc)
{
{
void __iomem *base = domain->host_data;
+ ath79_perfcount_irq = irq_create_mapping(domain, ATH79_MISC_PERF_IRQ);
+
/* Disable and clear all interrupts */
__raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_ENABLE);
__raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS);
struct sock *sk = sock->sk;
int err = 0;
- if (!maddr || maddr->family != AF_ISDN)
+ if (addr_len < sizeof(struct sockaddr_mISDN))
return -EINVAL;
- if (addr_len < sizeof(struct sockaddr_mISDN))
+ if (!maddr || maddr->family != AF_ISDN)
return -EINVAL;
lock_sock(sk);
void (*end_io)(struct dm_buffer *, blk_status_t);
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
#define MAX_STACK 10
- struct stack_trace stack_trace;
+ unsigned int stack_len;
unsigned long stack_entries[MAX_STACK];
#endif
};
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
static void buffer_record_stack(struct dm_buffer *b)
{
- b->stack_trace.nr_entries = 0;
- b->stack_trace.max_entries = MAX_STACK;
- b->stack_trace.entries = b->stack_entries;
- b->stack_trace.skip = 2;
- save_stack_trace(&b->stack_trace);
+ b->stack_len = stack_trace_save(b->stack_entries, MAX_STACK, 2);
}
#endif
adjust_total_allocated(b->data_mode, (long)c->block_size);
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
- memset(&b->stack_trace, 0, sizeof(b->stack_trace));
+ b->stack_len = 0;
#endif
return b;
}
DMERR("leaked buffer %llx, hold count %u, list %d",
(unsigned long long)b->block, b->hold_count, i);
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
- print_stack_trace(&b->stack_trace, 1);
- b->hold_count = 0; /* mark unclaimed to avoid BUG_ON below */
+ stack_trace_print(b->stack_entries, b->stack_len, 1);
+ /* mark unclaimed to avoid BUG_ON below */
+ b->hold_count = 0;
#endif
}
#define MAX_HOLDERS 4
#define MAX_STACK 10
-typedef unsigned long stack_entries[MAX_STACK];
+struct stack_store {
+ unsigned int nr_entries;
+ unsigned long entries[MAX_STACK];
+};
struct block_lock {
spinlock_t lock;
struct task_struct *holders[MAX_HOLDERS];
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
- struct stack_trace traces[MAX_HOLDERS];
- stack_entries entries[MAX_HOLDERS];
+ struct stack_store traces[MAX_HOLDERS];
#endif
};
{
unsigned h = __find_holder(lock, NULL);
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
- struct stack_trace *t;
+ struct stack_store *t;
#endif
get_task_struct(task);
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
t = lock->traces + h;
- t->nr_entries = 0;
- t->max_entries = MAX_STACK;
- t->entries = lock->entries[h];
- t->skip = 2;
- save_stack_trace(t);
+ t->nr_entries = stack_trace_save(t->entries, MAX_STACK, 2);
#endif
}
DMERR("recursive lock detected in metadata");
#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
DMERR("previously held here:");
- print_stack_trace(lock->traces + i, 4);
+ stack_trace_print(lock->traces[i].entries,
+ lock->traces[i].nr_entries, 4);
DMERR("subsequent acquisition attempted here:");
dump_stack();
struct fastrpc_session_ctx *sess;
struct device *dev = &pdev->dev;
int i, sessions = 0;
+ int rc;
cctx = dev_get_drvdata(dev->parent);
if (!cctx)
}
cctx->sesscount++;
spin_unlock(&cctx->lock);
- dma_set_mask(dev, DMA_BIT_MASK(32));
+ rc = dma_set_mask(dev, DMA_BIT_MASK(32));
+ if (rc) {
+ dev_err(dev, "32-bit DMA enable failed\n");
+ return rc;
+ }
return 0;
}
/*
* Workaround for H2 #HW-23 bug
- * Set DMA max outstanding read requests to 240 on DMA CH 1. Set it
- * to 16 on KMD DMA
- * We need to limit only these DMAs because the user can only read
+ * Set DMA max outstanding read requests to 240 on DMA CH 1.
+ * This limitation is still large enough to not affect Gen4 bandwidth.
+ * We need to only limit that DMA channel because the user can only read
* from Host using DMA CH 1
*/
- WREG32(mmDMA_CH_0_CFG0, 0x0fff0010);
WREG32(mmDMA_CH_1_CFG0, 0x0fff00F0);
goya->hw_cap_initialized |= HW_CAP_GOLDEN;
* WA for HW-23.
* We can't allow user to read from Host using QMANs other than 1.
*/
- if (parser->hw_queue_id > GOYA_QUEUE_ID_DMA_1 &&
+ if (parser->hw_queue_id != GOYA_QUEUE_ID_DMA_1 &&
hl_mem_area_inside_range(le64_to_cpu(user_dma_pkt->src_addr),
le32_to_cpu(user_dma_pkt->tsize),
hdev->asic_prop.va_space_host_start_address,
config INTEL_MIC_BUS
tristate "Intel MIC Bus Driver"
- depends on 64BIT && PCI && X86 && X86_DEV_DMA_OPS
+ depends on 64BIT && PCI && X86
help
This option is selected by any driver which registers a
device or driver on the MIC Bus, such as CONFIG_INTEL_MIC_HOST,
config SCIF_BUS
tristate "SCIF Bus Driver"
- depends on 64BIT && PCI && X86 && X86_DEV_DMA_OPS
+ depends on 64BIT && PCI && X86
help
This option is selected by any driver which registers a
device or driver on the SCIF Bus, such as CONFIG_INTEL_MIC_HOST
struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
u32 ndcr_generic;
- if (chip == nfc->selected_chip && die_nr == marvell_nand->selected_die)
- return;
-
- writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
- writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
-
/*
* Reset the NDCR register to a clean state for this particular chip,
* also clear ND_RUN bit.
/* Also reset the interrupt status register */
marvell_nfc_clear_int(nfc, NDCR_ALL_INT);
+ if (chip == nfc->selected_chip && die_nr == marvell_nand->selected_die)
+ return;
+
+ writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
+ writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
+
nfc->selected_chip = chip;
marvell_nand->selected_die = die_nr;
}
return NOTIFY_DONE;
if (event_dev->flags & IFF_MASTER) {
+ int ret;
+
netdev_dbg(event_dev, "IFF_MASTER\n");
- return bond_master_netdev_event(event, event_dev);
+ ret = bond_master_netdev_event(event, event_dev);
+ if (ret != NOTIFY_DONE)
+ return ret;
}
if (event_dev->flags & IFF_SLAVE) {
fs->m_ext.data[1]))
return -EINVAL;
+ if (fs->location != RX_CLS_LOC_ANY && fs->location >= CFP_NUM_RULES)
+ return -EINVAL;
+
if (fs->location != RX_CLS_LOC_ANY &&
test_bit(fs->location, priv->cfp.used))
return -EBUSY;
struct cfp_rule *rule;
int ret;
+ if (loc >= CFP_NUM_RULES)
+ return -EINVAL;
+
/* Refuse deleting unused rules, and those that are not unique since
* that could leave IPv6 rules with one of the chained rule in the
* table.
adapter->soft_stats.scc += smb->tx_1_col;
adapter->soft_stats.mcc += smb->tx_2_col;
adapter->soft_stats.latecol += smb->tx_late_col;
- adapter->soft_stats.tx_underun += smb->tx_underrun;
+ adapter->soft_stats.tx_underrun += smb->tx_underrun;
adapter->soft_stats.tx_trunc += smb->tx_trunc;
adapter->soft_stats.tx_pause += smb->tx_pause;
{"tx_deferred_ok", ATL1_STAT(soft_stats.deffer)},
{"tx_single_coll_ok", ATL1_STAT(soft_stats.scc)},
{"tx_multi_coll_ok", ATL1_STAT(soft_stats.mcc)},
- {"tx_underun", ATL1_STAT(soft_stats.tx_underun)},
+ {"tx_underrun", ATL1_STAT(soft_stats.tx_underrun)},
{"tx_trunc", ATL1_STAT(soft_stats.tx_trunc)},
{"tx_pause", ATL1_STAT(soft_stats.tx_pause)},
{"rx_pause", ATL1_STAT(soft_stats.rx_pause)},
u64 scc; /* packets TX after a single collision */
u64 mcc; /* packets TX after multiple collisions */
u64 latecol; /* TX packets w/ late collisions */
- u64 tx_underun; /* TX packets aborted due to TX FIFO underrun
+ u64 tx_underrun; /* TX packets aborted due to TX FIFO underrun
* or TRD FIFO underrun */
u64 tx_trunc; /* TX packets truncated due to size > MTU */
u64 rx_pause; /* num Pause packets received. */
netdev->stats.tx_aborted_errors++;
if (txs->late_col)
netdev->stats.tx_window_errors++;
- if (txs->underun)
+ if (txs->underrun)
netdev->stats.tx_fifo_errors++;
} while (1);
unsigned multi_col:1;
unsigned late_col:1;
unsigned abort_col:1;
- unsigned underun:1; /* current packet is aborted
+ unsigned underrun:1; /* current packet is aborted
* due to txram underrun */
unsigned:3; /* reserved */
unsigned update:1; /* always 1'b1 in tx_status_buf */
bnx2x_sample_bulletin(bp);
if (bp->shadow_bulletin.content.valid_bitmap & 1 << VLAN_VALID) {
- BNX2X_ERR("Hypervisor will dicline the request, avoiding\n");
+ BNX2X_ERR("Hypervisor will decline the request, avoiding\n");
rc = -EINVAL;
goto out;
}
netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
bnxt_sched_reset(bp, rxr);
}
- goto next_rx;
+ goto next_rx_no_len;
}
len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
rc = 1;
next_rx:
- rxr->rx_prod = NEXT_RX(prod);
- rxr->rx_next_cons = NEXT_RX(cons);
-
cpr->rx_packets += 1;
cpr->rx_bytes += len;
+next_rx_no_len:
+ rxr->rx_prod = NEXT_RX(prod);
+ rxr->rx_next_cons = NEXT_RX(cons);
+
next_rx_no_prod_no_len:
*raw_cons = tmp_raw_cons;
for (i = 0; i < bp->tx_nr_rings; i++) {
struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
- u32 cmpl_ring_id;
- cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+ u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
+
hwrm_ring_free_send_msg(bp, ring,
RING_FREE_REQ_RING_TYPE_TX,
close_path ? cmpl_ring_id :
struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
struct bnxt_ring_struct *ring = &rxr->rx_ring_struct;
u32 grp_idx = rxr->bnapi->index;
- u32 cmpl_ring_id;
- cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+ u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
hwrm_ring_free_send_msg(bp, ring,
RING_FREE_REQ_RING_TYPE_RX,
close_path ? cmpl_ring_id :
struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct;
u32 grp_idx = rxr->bnapi->index;
- u32 cmpl_ring_id;
- cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+ u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
hwrm_ring_free_send_msg(bp, ring, type,
close_path ? cmpl_ring_id :
INVALID_HW_RING_ID);
req->num_tx_rings = cpu_to_le16(tx_rings);
if (BNXT_NEW_RM(bp)) {
enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
+ enables |= stats ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
if (bp->flags & BNXT_FLAG_CHIP_P5) {
enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0;
enables |= tx_rings + ring_grps ?
- FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
- FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+ FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
enables |= rx_rings ?
FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
} else {
enables |= cp_rings ?
- FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
- FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+ FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
enables |= ring_grps ?
FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS |
FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS |
FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
+ enables |= stats ? FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
if (bp->flags & BNXT_FLAG_CHIP_P5) {
enables |= tx_rings + ring_grps ?
- FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
- FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+ FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
} else {
enables |= cp_rings ?
- FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
- FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+ FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
enables |= ring_grps ?
FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0;
}
struct hwrm_queue_pri2cos_qcfg_input req2 = {0};
struct hwrm_port_qstats_ext_input req = {0};
struct bnxt_pf_info *pf = &bp->pf;
+ u32 tx_stat_size;
int rc;
if (!(bp->flags & BNXT_FLAG_PORT_STATS_EXT))
req.port_id = cpu_to_le16(pf->port_id);
req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext));
req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_ext_map);
- req.tx_stat_size = cpu_to_le16(sizeof(struct tx_port_stats_ext));
+ tx_stat_size = bp->hw_tx_port_stats_ext ?
+ sizeof(*bp->hw_tx_port_stats_ext) : 0;
+ req.tx_stat_size = cpu_to_le16(tx_stat_size);
req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_ext_map);
mutex_lock(&bp->hwrm_cmd_lock);
rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
if (!rc) {
bp->fw_rx_stats_ext_size = le16_to_cpu(resp->rx_stat_size) / 8;
- bp->fw_tx_stats_ext_size = le16_to_cpu(resp->tx_stat_size) / 8;
+ bp->fw_tx_stats_ext_size = tx_stat_size ?
+ le16_to_cpu(resp->tx_stat_size) / 8 : 0;
} else {
bp->fw_rx_stats_ext_size = 0;
bp->fw_tx_stats_ext_size = 0;
skip_uc:
rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+ if (rc && vnic->mc_list_count) {
+ netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n",
+ rc);
+ vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+ vnic->mc_list_count = 0;
+ rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+ }
if (rc)
- netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n",
+ netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %d\n",
rc);
return rc;
bnxt_clear_int_mode(bp);
init_err_pci_clean:
+ bnxt_free_hwrm_short_cmd_req(bp);
bnxt_free_hwrm_resources(bp);
bnxt_free_ctx_mem(bp);
kfree(bp->ctx);
#define DRV_NAME "nicvf"
#define DRV_VERSION "1.0"
+/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs
+ * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed
+ * this value, keeping headroom for the 14 byte Ethernet header and two
+ * VLAN tags (for QinQ)
+ */
+#define MAX_XDP_MTU (1530 - ETH_HLEN - VLAN_HLEN * 2)
+
/* Supported devices */
static const struct pci_device_id nicvf_id_table[] = {
{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
struct nicvf *nic = netdev_priv(netdev);
int orig_mtu = netdev->mtu;
+ /* For now just support only the usual MTU sized frames,
+ * plus some headroom for VLAN, QinQ.
+ */
+ if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) {
+ netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+ netdev->mtu);
+ return -EINVAL;
+ }
+
netdev->mtu = new_mtu;
if (!netif_running(netdev))
bool bpf_attached = false;
int ret = 0;
- /* For now just support only the usual MTU sized frames */
- if (prog && (dev->mtu > 1500)) {
+ /* For now just support only the usual MTU sized frames,
+ * plus some headroom for VLAN, QinQ.
+ */
+ if (prog && dev->mtu > MAX_XDP_MTU) {
netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
dev->mtu);
return -EOPNOTSUPP;
int ret;
if (enable) {
- ret = clk_prepare_enable(fep->clk_ahb);
- if (ret)
- return ret;
-
ret = clk_prepare_enable(fep->clk_enet_out);
if (ret)
- goto failed_clk_enet_out;
+ return ret;
if (fep->clk_ptp) {
mutex_lock(&fep->ptp_clk_mutex);
phy_reset_after_clk_enable(ndev->phydev);
} else {
- clk_disable_unprepare(fep->clk_ahb);
clk_disable_unprepare(fep->clk_enet_out);
if (fep->clk_ptp) {
mutex_lock(&fep->ptp_clk_mutex);
failed_clk_ptp:
if (fep->clk_enet_out)
clk_disable_unprepare(fep->clk_enet_out);
-failed_clk_enet_out:
- clk_disable_unprepare(fep->clk_ahb);
return ret;
}
ret = clk_prepare_enable(fep->clk_ipg);
if (ret)
goto failed_clk_ipg;
+ ret = clk_prepare_enable(fep->clk_ahb);
+ if (ret)
+ goto failed_clk_ahb;
fep->reg_phy = devm_regulator_get_optional(&pdev->dev, "phy");
if (!IS_ERR(fep->reg_phy)) {
pm_runtime_put(&pdev->dev);
pm_runtime_disable(&pdev->dev);
failed_regulator:
+ clk_disable_unprepare(fep->clk_ahb);
+failed_clk_ahb:
+ clk_disable_unprepare(fep->clk_ipg);
failed_clk_ipg:
fec_enet_clk_enable(ndev, false);
failed_clk:
struct net_device *ndev = dev_get_drvdata(dev);
struct fec_enet_private *fep = netdev_priv(ndev);
+ clk_disable_unprepare(fep->clk_ahb);
clk_disable_unprepare(fep->clk_ipg);
return 0;
{
struct net_device *ndev = dev_get_drvdata(dev);
struct fec_enet_private *fep = netdev_priv(ndev);
+ int ret;
- return clk_prepare_enable(fep->clk_ipg);
+ ret = clk_prepare_enable(fep->clk_ahb);
+ if (ret)
+ return ret;
+ ret = clk_prepare_enable(fep->clk_ipg);
+ if (ret)
+ goto failed_clk_ipg;
+
+ return 0;
+
+failed_clk_ipg:
+ clk_disable_unprepare(fep->clk_ahb);
+ return ret;
}
static const struct dev_pm_ops fec_pm_ops = {
{
struct device *dev = &adapter->vdev->dev;
struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
+ netdev_features_t old_hw_features = 0;
union ibmvnic_crq crq;
int i;
adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
adapter->ip_offload_ctrl.large_rx_ipv6 = 0;
- adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO;
+ if (adapter->state != VNIC_PROBING) {
+ old_hw_features = adapter->netdev->hw_features;
+ adapter->netdev->hw_features = 0;
+ }
+
+ adapter->netdev->hw_features = NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO;
if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
- adapter->netdev->features |= NETIF_F_IP_CSUM;
+ adapter->netdev->hw_features |= NETIF_F_IP_CSUM;
if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum)
- adapter->netdev->features |= NETIF_F_IPV6_CSUM;
+ adapter->netdev->hw_features |= NETIF_F_IPV6_CSUM;
if ((adapter->netdev->features &
(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
- adapter->netdev->features |= NETIF_F_RXCSUM;
+ adapter->netdev->hw_features |= NETIF_F_RXCSUM;
if (buf->large_tx_ipv4)
- adapter->netdev->features |= NETIF_F_TSO;
+ adapter->netdev->hw_features |= NETIF_F_TSO;
if (buf->large_tx_ipv6)
- adapter->netdev->features |= NETIF_F_TSO6;
+ adapter->netdev->hw_features |= NETIF_F_TSO6;
- adapter->netdev->hw_features |= adapter->netdev->features;
+ if (adapter->state == VNIC_PROBING) {
+ adapter->netdev->features |= adapter->netdev->hw_features;
+ } else if (old_hw_features != adapter->netdev->hw_features) {
+ netdev_features_t tmp = 0;
+
+ /* disable features no longer supported */
+ adapter->netdev->features &= adapter->netdev->hw_features;
+ /* turn on features now supported if previously enabled */
+ tmp = (old_hw_features ^ adapter->netdev->hw_features) &
+ adapter->netdev->hw_features;
+ adapter->netdev->features |=
+ tmp & adapter->netdev->wanted_features;
+ }
memset(&crq, 0, sizeof(crq));
crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
* switching channels
*/
typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
struct mlx5e_channels *new_chs,
mlx5e_fp_hw_modify hw_modify);
static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
{
- int err;
+ int err = 0;
rtnl_lock();
mutex_lock(&priv->state_lock);
- mlx5e_close_locked(priv->netdev);
- err = mlx5e_open_locked(priv->netdev);
+
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+ goto out;
+
+ err = mlx5e_safe_reopen_channels(priv);
+
+out:
mutex_unlock(&priv->state_lock);
rtnl_unlock();
return -EOPNOTSUPP;
}
+ if (!(mlx5e_eswitch_rep(*out_dev) &&
+ mlx5e_is_uplink_rep(netdev_priv(*out_dev))))
+ return -EOPNOTSUPP;
+
return 0;
}
#include <linux/bpf_trace.h>
#include "en/xdp.h"
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params)
+{
+ int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM;
+
+ /* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)).
+ * The condition checked in mlx5e_rx_is_linear_skb is:
+ * SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE (1)
+ * (Note that hw_mtu == sw_mtu + hard_mtu.)
+ * What is returned from this function is:
+ * max_mtu = PAGE_SIZE - S - hr - hard_mtu (2)
+ * After assigning sw_mtu := max_mtu, the left side of (1) turns to
+ * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE,
+ * because both PAGE_SIZE and S are already aligned. Any number greater
+ * than max_mtu would make the left side of (1) greater than PAGE_SIZE,
+ * so max_mtu is the maximum MTU allowed.
+ */
+
+ return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr));
+}
+
static inline bool
mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
struct xdp_buff *xdp)
mlx5e_xdpi_fifo_pop(xdpi_fifo);
if (is_redirect) {
- xdp_return_frame(xdpi.xdpf);
dma_unmap_single(sq->pdev, xdpi.dma_addr,
xdpi.xdpf->len, DMA_TO_DEVICE);
+ xdp_return_frame(xdpi.xdpf);
} else {
/* Recycle RX page */
mlx5e_page_release(rq, &xdpi.di, true);
mlx5e_xdpi_fifo_pop(xdpi_fifo);
if (is_redirect) {
- xdp_return_frame(xdpi.xdpf);
dma_unmap_single(sq->pdev, xdpi.dma_addr,
xdpi.xdpf->len, DMA_TO_DEVICE);
+ xdp_return_frame(xdpi.xdpf);
} else {
/* Recycle RX page */
mlx5e_page_release(rq, &xdpi.di, false);
#include "en.h"
-#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
- MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
#define MLX5E_XDP_TX_EMPTY_DS_COUNT \
(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
#define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params);
bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
void *va, u16 *rx_headroom, u32 *len);
bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq);
break;
case MLX5_MODULE_ID_SFP:
modinfo->type = ETH_MODULE_SFF_8472;
- modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+ modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH;
break;
default:
netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n",
struct mlx5e_channel *c;
int i;
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state) ||
+ priv->channels.params.xdp_prog)
return 0;
for (i = 0; i < channels->num; i++) {
if (params->rx_dim_enabled)
__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
- if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE))
+ /* We disable csum_complete when XDP is enabled since
+ * XDP programs might manipulate packets which will render
+ * skb->checksum incorrect.
+ */
+ if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
return 0;
return 0;
}
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
+{
+ struct mlx5e_channels new_channels = {};
+
+ new_channels.params = priv->channels.params;
+ return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+}
+
void mlx5e_timestamp_init(struct mlx5e_priv *priv)
{
priv->tstamp.tx_type = HWTSTAMP_TX_OFF;
if (params->xdp_prog &&
!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
- new_mtu, MLX5E_XDP_MAX_MTU);
+ new_mtu, mlx5e_xdp_max_mtu(params));
err = -EINVAL;
goto out;
}
if (!report_failed)
goto unlock;
- mlx5e_close_locked(priv->netdev);
- err = mlx5e_open_locked(priv->netdev);
+ err = mlx5e_safe_reopen_channels(priv);
if (err)
netdev_err(priv->netdev,
- "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+ "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n",
err);
unlock:
if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
- new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+ new_channels.params.sw_mtu,
+ mlx5e_xdp_max_mtu(&new_channels.params));
return -EINVAL;
}
{
enum mlx5e_traffic_types tt;
- rss_params->hfunc = ETH_RSS_HASH_XOR;
+ rss_params->hfunc = ETH_RSS_HASH_TOP;
netdev_rss_key_fill(rss_params->toeplitz_hash_key,
sizeof(rss_params->toeplitz_hash_key));
mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
{
*proto = ((struct ethhdr *)skb->data)->h_proto;
*proto = __vlan_get_protocol(skb, *proto, network_depth);
- return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6));
+
+ if (*proto == htons(ETH_P_IP))
+ return pskb_may_pull(skb, *network_depth + sizeof(struct iphdr));
+
+ if (*proto == htons(ETH_P_IPV6))
+ return pskb_may_pull(skb, *network_depth + sizeof(struct ipv6hdr));
+
+ return false;
}
static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
rq->stats->ecn_mark += !!rc;
}
-static u32 mlx5e_get_fcs(const struct sk_buff *skb)
-{
- const void *fcs_bytes;
- u32 _fcs_bytes;
-
- fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
- ETH_FCS_LEN, &_fcs_bytes);
-
- return __get_unaligned_cpu32(fcs_bytes);
-}
-
static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
{
void *ip_p = skb->data + network_depth;
#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+#define MAX_PADDING 8
+
+static void
+tail_padding_csum_slow(struct sk_buff *skb, int offset, int len,
+ struct mlx5e_rq_stats *stats)
+{
+ stats->csum_complete_tail_slow++;
+ skb->csum = csum_block_add(skb->csum,
+ skb_checksum(skb, offset, len, 0),
+ offset);
+}
+
+static void
+tail_padding_csum(struct sk_buff *skb, int offset,
+ struct mlx5e_rq_stats *stats)
+{
+ u8 tail_padding[MAX_PADDING];
+ int len = skb->len - offset;
+ void *tail;
+
+ if (unlikely(len > MAX_PADDING)) {
+ tail_padding_csum_slow(skb, offset, len, stats);
+ return;
+ }
+
+ tail = skb_header_pointer(skb, offset, len, tail_padding);
+ if (unlikely(!tail)) {
+ tail_padding_csum_slow(skb, offset, len, stats);
+ return;
+ }
+
+ stats->csum_complete_tail++;
+ skb->csum = csum_block_add(skb->csum, csum_partial(tail, len, 0), offset);
+}
+
+static void
+mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto,
+ struct mlx5e_rq_stats *stats)
+{
+ struct ipv6hdr *ip6;
+ struct iphdr *ip4;
+ int pkt_len;
+
+ switch (proto) {
+ case htons(ETH_P_IP):
+ ip4 = (struct iphdr *)(skb->data + network_depth);
+ pkt_len = network_depth + ntohs(ip4->tot_len);
+ break;
+ case htons(ETH_P_IPV6):
+ ip6 = (struct ipv6hdr *)(skb->data + network_depth);
+ pkt_len = network_depth + sizeof(*ip6) + ntohs(ip6->payload_len);
+ break;
+ default:
+ return;
+ }
+
+ if (likely(pkt_len >= skb->len))
+ return;
+
+ tail_padding_csum(skb, pkt_len, stats);
+}
+
static inline void mlx5e_handle_csum(struct net_device *netdev,
struct mlx5_cqe64 *cqe,
struct mlx5e_rq *rq,
return;
}
- if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)))
+ /* True when explicitly set via priv flag, or XDP prog is loaded */
+ if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))
goto csum_unnecessary;
/* CQE csum doesn't cover padding octets in short ethernet
skb->csum = csum_partial(skb->data + ETH_HLEN,
network_depth - ETH_HLEN,
skb->csum);
- if (unlikely(netdev->features & NETIF_F_RXFCS))
- skb->csum = csum_block_add(skb->csum,
- (__force __wsum)mlx5e_get_fcs(skb),
- skb->len - ETH_FCS_LEN);
+
+ mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
stats->csum_complete++;
return;
}
csum_unnecessary:
if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
- ((cqe->hds_ip_ext & CQE_L4_OK) ||
- (get_cqe_l4_hdr_type(cqe) == CQE_L4_HDR_TYPE_NONE)))) {
+ (cqe->hds_ip_ext & CQE_L4_OK))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
if (cqe_is_tunneled(cqe)) {
skb->csum_level = 1;
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail_slow) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
s->rx_csum_none += rq_stats->csum_none;
s->rx_csum_complete += rq_stats->csum_complete;
+ s->rx_csum_complete_tail += rq_stats->csum_complete_tail;
+ s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow;
s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
s->rx_xdp_drop += rq_stats->xdp_drop;
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail_slow) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
u64 rx_csum_unnecessary;
u64 rx_csum_none;
u64 rx_csum_complete;
+ u64 rx_csum_complete_tail;
+ u64 rx_csum_complete_tail_slow;
u64 rx_csum_unnecessary_inner;
u64 rx_xdp_drop;
u64 rx_xdp_redirect;
u64 packets;
u64 bytes;
u64 csum_complete;
+ u64 csum_complete_tail;
+ u64 csum_complete_tail_slow;
u64 csum_unnecessary;
u64 csum_unnecessary_inner;
u64 csum_none;
return ret;
}
-static void mlx5_fpga_tls_release_swid(struct idr *idr,
- spinlock_t *idr_spinlock, u32 swid)
+static void *mlx5_fpga_tls_release_swid(struct idr *idr,
+ spinlock_t *idr_spinlock, u32 swid)
{
unsigned long flags;
+ void *ptr;
spin_lock_irqsave(idr_spinlock, flags);
- idr_remove(idr, swid);
+ ptr = idr_remove(idr, swid);
spin_unlock_irqrestore(idr_spinlock, flags);
+ return ptr;
}
static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
kfree(buf);
}
-struct mlx5_teardown_stream_context {
- struct mlx5_fpga_tls_command_context cmd;
- u32 swid;
-};
-
static void
mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
struct mlx5_fpga_device *fdev,
struct mlx5_fpga_tls_command_context *cmd,
struct mlx5_fpga_dma_buf *resp)
{
- struct mlx5_teardown_stream_context *ctx =
- container_of(cmd, struct mlx5_teardown_stream_context, cmd);
-
if (resp) {
u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
mlx5_fpga_err(fdev,
"Teardown stream failed with syndrome = %d",
syndrome);
- else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
- mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
- &fdev->tls->tx_idr_spinlock,
- ctx->swid);
- else
- mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
- &fdev->tls->rx_idr_spinlock,
- ctx->swid);
}
mlx5_fpga_tls_put_command_ctx(cmd);
}
void *cmd;
int ret;
- rcu_read_lock();
- flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
- rcu_read_unlock();
-
- if (!flow) {
- WARN_ONCE(1, "Received NULL pointer for handle\n");
- return -EINVAL;
- }
-
buf = kzalloc(size, GFP_ATOMIC);
if (!buf)
return -ENOMEM;
cmd = (buf + 1);
+ rcu_read_lock();
+ flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+ if (unlikely(!flow)) {
+ rcu_read_unlock();
+ WARN_ONCE(1, "Received NULL pointer for handle\n");
+ kfree(buf);
+ return -EINVAL;
+ }
mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+ rcu_read_unlock();
MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
void *flow, u32 swid, gfp_t flags)
{
- struct mlx5_teardown_stream_context *ctx;
+ struct mlx5_fpga_tls_command_context *ctx;
struct mlx5_fpga_dma_buf *buf;
void *cmd;
if (!ctx)
return;
- buf = &ctx->cmd.buf;
+ buf = &ctx->buf;
cmd = (ctx + 1);
MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
MLX5_SET(tls_cmd, cmd, swid, swid);
buf->sg[0].data = cmd;
buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
- ctx->swid = swid;
- mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+ mlx5_fpga_tls_cmd_send(mdev->fpga, ctx,
mlx5_fpga_tls_teardown_completion);
}
struct mlx5_fpga_tls *tls = mdev->fpga->tls;
void *flow;
- rcu_read_lock();
if (direction_sx)
- flow = idr_find(&tls->tx_idr, swid);
+ flow = mlx5_fpga_tls_release_swid(&tls->tx_idr,
+ &tls->tx_idr_spinlock,
+ swid);
else
- flow = idr_find(&tls->rx_idr, swid);
-
- rcu_read_unlock();
+ flow = mlx5_fpga_tls_release_swid(&tls->rx_idr,
+ &tls->rx_idr_spinlock,
+ swid);
if (!flow) {
mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
return;
}
+ synchronize_rcu(); /* before kfree(flow) */
mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
}
size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
i2c_addr = MLX5_I2C_ADDR_LOW;
- if (offset >= MLX5_EEPROM_PAGE_LENGTH) {
- i2c_addr = MLX5_I2C_ADDR_HIGH;
- offset -= MLX5_EEPROM_PAGE_LENGTH;
- }
MLX5_SET(mcia_reg, in, l, 0);
MLX5_SET(mcia_reg, in, module, module_num);
if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
return 0;
- emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_MEM_RECLAIM, 0);
+ emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0);
if (!emad_wq)
return -ENOMEM;
mlxsw_core->emad_wq = emad_wq;
{
int err;
- mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0);
+ mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0);
if (!mlxsw_wq)
return -ENOMEM;
- mlxsw_owq = alloc_ordered_workqueue("%s_ordered", WQ_MEM_RECLAIM,
+ mlxsw_owq = alloc_ordered_workqueue("%s_ordered", 0,
mlxsw_core_driver_name);
if (!mlxsw_owq) {
err = -ENOMEM;
#define MLXSW_PCI_SW_RESET 0xF0010
#define MLXSW_PCI_SW_RESET_RST_BIT BIT(0)
-#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 13000
+#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 20000
#define MLXSW_PCI_SW_RESET_WAIT_MSECS 100
#define MLXSW_PCI_FW_READY 0xA1844
#define MLXSW_PCI_FW_READY_MASK 0xFFFF
if (err)
return err;
+ mlxsw_sp_port->link.autoneg = autoneg;
+
if (!netif_running(dev))
return 0;
- mlxsw_sp_port->link.autoneg = autoneg;
-
mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
MLXSW_REG_QEEC_HIERARCY_TC,
i + 8, i,
- false, 0);
+ true, 100);
if (err)
return err;
}
{MLXSW_REG_SBXX_DIR_EGRESS, 1},
{MLXSW_REG_SBXX_DIR_EGRESS, 2},
{MLXSW_REG_SBXX_DIR_EGRESS, 3},
+ {MLXSW_REG_SBXX_DIR_EGRESS, 15},
};
#define MLXSW_SP_SB_ING_TC_COUNT 8
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+ MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI),
};
static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
MLXSW_SP_SB_CM(0, 7, 4),
MLXSW_SP_SB_CM(0, 7, 4),
MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
- MLXSW_SP_SB_CM(0, 7, 4),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+ MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
MLXSW_SP_SB_CM(1, 0xff, 4),
};
MLXSW_SP_SB_PM(0, 0),
MLXSW_SP_SB_PM(0, 0),
MLXSW_SP_SB_PM(0, 0),
+ MLXSW_SP_SB_PM(10000, 90000),
};
static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
/* A RIF is not created for macvlan netdevs. Their MAC is used to
* populate the FDB
*/
- if (netif_is_macvlan(dev))
+ if (netif_is_macvlan(dev) || netif_is_l3_master(dev))
return 0;
for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
u16 fid_index;
int err = 0;
- if (switchdev_trans_ph_prepare(trans))
+ if (switchdev_trans_ph_commit(trans))
return 0;
bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
struct netdev_hw_addr *hw_addr)
{
struct ocelot *ocelot = port->ocelot;
- struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_KERNEL);
+ struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_ATOMIC);
if (!ha)
return -ENOMEM;
ETH_GSTRING_LEN);
}
-static void ocelot_check_stats(struct work_struct *work)
+static void ocelot_update_stats(struct ocelot *ocelot)
{
- struct delayed_work *del_work = to_delayed_work(work);
- struct ocelot *ocelot = container_of(del_work, struct ocelot, stats_work);
int i, j;
mutex_lock(&ocelot->stats_lock);
}
}
- cancel_delayed_work(&ocelot->stats_work);
+ mutex_unlock(&ocelot->stats_lock);
+}
+
+static void ocelot_check_stats_work(struct work_struct *work)
+{
+ struct delayed_work *del_work = to_delayed_work(work);
+ struct ocelot *ocelot = container_of(del_work, struct ocelot,
+ stats_work);
+
+ ocelot_update_stats(ocelot);
+
queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
OCELOT_STATS_CHECK_DELAY);
-
- mutex_unlock(&ocelot->stats_lock);
}
static void ocelot_get_ethtool_stats(struct net_device *dev,
int i;
/* check and update now */
- ocelot_check_stats(&ocelot->stats_work.work);
+ ocelot_update_stats(ocelot);
/* Copy all counters */
for (i = 0; i < ocelot->num_stats; i++)
ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
ANA_CPUQ_8021_CFG, i);
- INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats);
+ INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
OCELOT_STATS_CHECK_DELAY);
return 0;
dma_object->addr))) {
vxge_os_dma_free(devh->pdev, memblock,
&dma_object->acc_handle);
+ memblock = NULL;
goto exit;
}
}
if (knode->sel->off || knode->sel->offshift || knode->sel->offmask ||
knode->sel->offoff || knode->fshift) {
- NL_SET_ERR_MSG_MOD(extack, "variable offseting not supported");
+ NL_SET_ERR_MSG_MOD(extack, "variable offsetting not supported");
return false;
}
if (knode->sel->hoff || knode->sel->hmask) {
k = &knode->sel->keys[0];
if (k->offmask) {
- NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offseting not supported");
+ NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offsetting not supported");
return false;
}
if (k->off) {
u8 num_pf_rls;
};
+#define QED_OVERFLOW_BIT 1
+
struct qed_db_recovery_info {
struct list_head list;
/* Lock to protect the doorbell recovery mechanism list */
spinlock_t lock;
+ bool dorq_attn;
u32 db_recovery_counter;
+ unsigned long overflow;
};
struct storm_stats {
/* doorbell recovery mechanism */
void qed_db_recovery_dp(struct qed_hwfn *p_hwfn);
-void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
- enum qed_db_rec_exec db_exec);
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn);
bool qed_edpm_enabled(struct qed_hwfn *p_hwfn);
/* Other Linux specific common definitions */
/* Doorbell address sanity (address within doorbell bar range) */
static bool qed_db_rec_sanity(struct qed_dev *cdev,
- void __iomem *db_addr, void *db_data)
+ void __iomem *db_addr,
+ enum qed_db_rec_width db_width,
+ void *db_data)
{
+ u32 width = (db_width == DB_REC_WIDTH_32B) ? 32 : 64;
+
/* Make sure doorbell address is within the doorbell bar */
if (db_addr < cdev->doorbells ||
- (u8 __iomem *)db_addr >
+ (u8 __iomem *)db_addr + width >
(u8 __iomem *)cdev->doorbells + cdev->db_size) {
WARN(true,
"Illegal doorbell address: %p. Legal range for doorbell addresses is [%p..%p]\n",
}
/* Sanitize doorbell address */
- if (!qed_db_rec_sanity(cdev, db_addr, db_data))
+ if (!qed_db_rec_sanity(cdev, db_addr, db_width, db_data))
return -EINVAL;
/* Obtain hwfn from doorbell address */
return 0;
}
- /* Sanitize doorbell address */
- if (!qed_db_rec_sanity(cdev, db_addr, db_data))
- return -EINVAL;
-
/* Obtain hwfn from doorbell address */
p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr);
/* Ring the doorbell of a single doorbell recovery entry */
static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
- struct qed_db_recovery_entry *db_entry,
- enum qed_db_rec_exec db_exec)
-{
- if (db_exec != DB_REC_ONCE) {
- /* Print according to width */
- if (db_entry->db_width == DB_REC_WIDTH_32B) {
- DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
- "%s doorbell address %p data %x\n",
- db_exec == DB_REC_DRY_RUN ?
- "would have rung" : "ringing",
- db_entry->db_addr,
- *(u32 *)db_entry->db_data);
- } else {
- DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
- "%s doorbell address %p data %llx\n",
- db_exec == DB_REC_DRY_RUN ?
- "would have rung" : "ringing",
- db_entry->db_addr,
- *(u64 *)(db_entry->db_data));
- }
+ struct qed_db_recovery_entry *db_entry)
+{
+ /* Print according to width */
+ if (db_entry->db_width == DB_REC_WIDTH_32B) {
+ DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+ "ringing doorbell address %p data %x\n",
+ db_entry->db_addr,
+ *(u32 *)db_entry->db_data);
+ } else {
+ DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+ "ringing doorbell address %p data %llx\n",
+ db_entry->db_addr,
+ *(u64 *)(db_entry->db_data));
}
/* Sanity */
if (!qed_db_rec_sanity(p_hwfn->cdev, db_entry->db_addr,
- db_entry->db_data))
+ db_entry->db_width, db_entry->db_data))
return;
/* Flush the write combined buffer. Since there are multiple doorbelling
wmb();
/* Ring the doorbell */
- if (db_exec == DB_REC_REAL_DEAL || db_exec == DB_REC_ONCE) {
- if (db_entry->db_width == DB_REC_WIDTH_32B)
- DIRECT_REG_WR(db_entry->db_addr,
- *(u32 *)(db_entry->db_data));
- else
- DIRECT_REG_WR64(db_entry->db_addr,
- *(u64 *)(db_entry->db_data));
- }
+ if (db_entry->db_width == DB_REC_WIDTH_32B)
+ DIRECT_REG_WR(db_entry->db_addr,
+ *(u32 *)(db_entry->db_data));
+ else
+ DIRECT_REG_WR64(db_entry->db_addr,
+ *(u64 *)(db_entry->db_data));
/* Flush the write combined buffer. Next doorbell may come from a
* different entity to the same address...
}
/* Traverse the doorbell recovery entry list and ring all the doorbells */
-void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
- enum qed_db_rec_exec db_exec)
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn)
{
struct qed_db_recovery_entry *db_entry = NULL;
- if (db_exec != DB_REC_ONCE) {
- DP_NOTICE(p_hwfn,
- "Executing doorbell recovery. Counter was %d\n",
- p_hwfn->db_recovery_info.db_recovery_counter);
+ DP_NOTICE(p_hwfn, "Executing doorbell recovery. Counter was %d\n",
+ p_hwfn->db_recovery_info.db_recovery_counter);
- /* Track amount of times recovery was executed */
- p_hwfn->db_recovery_info.db_recovery_counter++;
- }
+ /* Track amount of times recovery was executed */
+ p_hwfn->db_recovery_info.db_recovery_counter++;
/* Protect the list */
spin_lock_bh(&p_hwfn->db_recovery_info.lock);
list_for_each_entry(db_entry,
- &p_hwfn->db_recovery_info.list, list_entry) {
- qed_db_recovery_ring(p_hwfn, db_entry, db_exec);
- if (db_exec == DB_REC_ONCE)
- break;
- }
-
+ &p_hwfn->db_recovery_info.list, list_entry)
+ qed_db_recovery_ring(p_hwfn, db_entry);
spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
}
u32 count = QED_DB_REC_COUNT;
u32 usage = 1;
+ /* Flush any pending (e)dpms as they may never arrive */
+ qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
+
/* wait for usage to zero or count to run out. This is necessary since
* EDPM doorbell transactions can take multiple 64b cycles, and as such
* can "split" over the pci. Possibly, the doorbell drop can happen with
int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
- u32 overflow;
+ u32 attn_ovfl, cur_ovfl;
int rc;
- overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
- DP_NOTICE(p_hwfn, "PF Overflow sticky 0x%x\n", overflow);
- if (!overflow) {
- qed_db_recovery_execute(p_hwfn, DB_REC_ONCE);
+ attn_ovfl = test_and_clear_bit(QED_OVERFLOW_BIT,
+ &p_hwfn->db_recovery_info.overflow);
+ cur_ovfl = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+ if (!cur_ovfl && !attn_ovfl)
return 0;
- }
- if (qed_edpm_enabled(p_hwfn)) {
+ DP_NOTICE(p_hwfn, "PF Overflow sticky: attn %u current %u\n",
+ attn_ovfl, cur_ovfl);
+
+ if (cur_ovfl && !p_hwfn->db_bar_no_edpm) {
rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
if (rc)
return rc;
}
- /* Flush any pending (e)dpm as they may never arrive */
- qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
-
/* Release overflow sticky indication (stop silently dropping everything) */
qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
/* Repeat all last doorbells (doorbell drop recovery) */
- qed_db_recovery_execute(p_hwfn, DB_REC_REAL_DEAL);
+ qed_db_recovery_execute(p_hwfn);
return 0;
}
-static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+static void qed_dorq_attn_overflow(struct qed_hwfn *p_hwfn)
{
- u32 int_sts, first_drop_reason, details, address, all_drops_reason;
struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
+ u32 overflow;
int rc;
- int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
- DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+ overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+ if (!overflow)
+ goto out;
+
+ /* Run PF doorbell recovery in next periodic handler */
+ set_bit(QED_OVERFLOW_BIT, &p_hwfn->db_recovery_info.overflow);
+
+ if (!p_hwfn->db_bar_no_edpm) {
+ rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
+ if (rc)
+ goto out;
+ }
+
+ qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
+out:
+ /* Schedule the handler even if overflow was not detected */
+ qed_periodic_db_rec_start(p_hwfn);
+}
+
+static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn)
+{
+ u32 int_sts, first_drop_reason, details, address, all_drops_reason;
+ struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
/* int_sts may be zero since all PFs were interrupted for doorbell
* overflow but another one already handled it. Can abort here. If
* This PF also requires overflow recovery we will be interrupted again.
* The masked almost full indication may also be set. Ignoring.
*/
+ int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL))
return 0;
+ DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+
/* check if db_drop or overflow happened */
if (int_sts & (DORQ_REG_INT_STS_DB_DROP |
DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR)) {
GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4,
first_drop_reason, all_drops_reason);
- rc = qed_db_rec_handler(p_hwfn, p_ptt);
- qed_periodic_db_rec_start(p_hwfn);
- if (rc)
- return rc;
-
/* Clear the doorbell drop details and prepare for next drop */
qed_wr(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS_REL, 0);
return -EINVAL;
}
+static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+{
+ p_hwfn->db_recovery_info.dorq_attn = true;
+ qed_dorq_attn_overflow(p_hwfn);
+
+ return qed_dorq_attn_int_sts(p_hwfn);
+}
+
+static void qed_dorq_attn_handler(struct qed_hwfn *p_hwfn)
+{
+ if (p_hwfn->db_recovery_info.dorq_attn)
+ goto out;
+
+ /* Call DORQ callback if the attention was missed */
+ qed_dorq_attn_cb(p_hwfn);
+out:
+ p_hwfn->db_recovery_info.dorq_attn = false;
+}
+
/* Instead of major changes to the data-structure, we have a some 'special'
* identifiers for sources that changed meaning between adapters.
*/
}
}
+ /* Handle missed DORQ attention */
+ qed_dorq_attn_handler(p_hwfn);
+
/* Clear IGU indication for the deasserted bits */
DIRECT_REG_WR((u8 __iomem *)p_hwfn->regview +
GTT_BAR0_MAP_REG_IGU_CMD +
/**
* @brief - Doorbell Recovery handler.
- * Run DB_REAL_DEAL doorbell recovery in case of PF overflow
- * (and flush DORQ if needed), otherwise run DB_REC_ONCE.
+ * Run doorbell recovery in case of PF overflow (and flush DORQ if
+ * needed).
*
* @param p_hwfn
* @param p_ptt
}
}
-#define QED_PERIODIC_DB_REC_COUNT 100
+#define QED_PERIODIC_DB_REC_COUNT 10
#define QED_PERIODIC_DB_REC_INTERVAL_MS 100
#define QED_PERIODIC_DB_REC_INTERVAL \
msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS)
p_vfdev->eth_fp_hsi_minor = ETH_HSI_VER_NO_PKT_LEN_TUNN;
} else {
DP_INFO(p_hwfn,
- "VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's faspath HSI %02x.%02x\n",
+ "VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's fastpath HSI %02x.%02x\n",
vf->abs_vf_id,
req->vfdev_info.eth_fp_hsi_major,
req->vfdev_info.eth_fp_hsi_minor,
ptp->clock = ptp_clock_register(&ptp->clock_info, &edev->pdev->dev);
if (IS_ERR(ptp->clock)) {
- rc = -EINVAL;
DP_ERR(edev, "PTP clock registration failed\n");
+ qede_ptp_disable(edev);
+ rc = -EINVAL;
goto err2;
}
return 0;
-err2:
- qede_ptp_disable(edev);
- ptp->clock = NULL;
err1:
kfree(ptp);
+err2:
edev->ptp = NULL;
return rc;
}
static void *netsec_alloc_rx_data(struct netsec_priv *priv,
- dma_addr_t *dma_handle, u16 *desc_len)
+ dma_addr_t *dma_handle, u16 *desc_len,
+ bool napi)
{
size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
size_t payload_len = NETSEC_RX_BUF_SZ;
total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD);
- buf = napi_alloc_frag(total_len);
+ buf = napi ? napi_alloc_frag(total_len) : netdev_alloc_frag(total_len);
if (!buf)
return NULL;
/* allocate a fresh buffer and map it to the hardware.
* This will eventually replace the old buffer in the hardware
*/
- buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len);
+ buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len,
+ true);
if (unlikely(!buf_addr))
break;
void *buf;
u16 len;
- buf = netsec_alloc_rx_data(priv, &dma_handle, &len);
+ buf = netsec_alloc_rx_data(priv, &dma_handle, &len,
+ false);
if (!buf) {
netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
goto err_out;
*/
dwmac->irq_pwr_wakeup = platform_get_irq_byname(pdev,
"stm32_pwr_wakeup");
+ if (dwmac->irq_pwr_wakeup == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+
if (!dwmac->clk_eth_ck && dwmac->irq_pwr_wakeup >= 0) {
err = device_init_wakeup(&pdev->dev, true);
if (err) {
p->des0 |= cpu_to_le32(RDES0_OWN);
bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1);
- p->des1 |= cpu_to_le32(bfsize & RDES1_BUFFER1_SIZE_MASK);
+ p->des1 |= cpu_to_le32(bfsize1 & RDES1_BUFFER1_SIZE_MASK);
if (mode == STMMAC_CHAIN_MODE)
ndesc_rx_set_on_chain(p, end);
u32 chan;
int ret;
- stmmac_check_ether_addr(priv);
-
if (priv->hw->pcs != STMMAC_PCS_RGMII &&
priv->hw->pcs != STMMAC_PCS_TBI &&
priv->hw->pcs != STMMAC_PCS_RTBI) {
if (ret)
goto error_hw_init;
+ stmmac_check_ether_addr(priv);
+
/* Configure real RX and TX queues */
netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use);
netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use);
},
.driver_data = (void *)&galileo_stmmac_dmi_data,
},
+ /*
+ * There are 2 types of SIMATIC IOT2000: IOT2020 and IOT2040.
+ * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which
+ * has only one pci network device while other asset tags are
+ * for IOT2040 which has two.
+ */
{
.matches = {
DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
{
.matches = {
DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
- DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG,
- "6ES7647-0AA00-1YA2"),
},
.driver_data = (void *)&iot2040_stmmac_dmi_data,
},
dev_dbg(printdev(lp), "no slotted operation\n");
ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1,
DAR_PHY_CTRL1_SLOTTED, 0x0);
+ if (ret < 0)
+ return ret;
/* enable irq */
enable_irq(lp->spi->irq);
/* Unmask SEQ interrupt */
ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL2,
DAR_PHY_CTRL2_SEQMSK, 0x0);
+ if (ret < 0)
+ return ret;
/* Start the RX sequence */
dev_dbg(printdev(lp), "start the RX sequence\n");
ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1,
DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_RX);
+ if (ret < 0)
+ return ret;
return 0;
}
static void marvell_get_strings(struct phy_device *phydev, u8 *data)
{
+ int count = marvell_get_sset_count(phydev);
int i;
- for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) {
+ for (i = 0; i < count; i++) {
strlcpy(data + i * ETH_GSTRING_LEN,
marvell_hw_stats[i].string, ETH_GSTRING_LEN);
}
static void marvell_get_stats(struct phy_device *phydev,
struct ethtool_stats *stats, u64 *data)
{
+ int count = marvell_get_sset_count(phydev);
int i;
- for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++)
+ for (i = 0; i < count; i++)
data[i] = marvell_get_stat(phydev, i);
}
};
MODULE_DEVICE_TABLE(spi, ks8995_id);
+static const struct of_device_id ks8895_spi_of_match[] = {
+ { .compatible = "micrel,ks8995" },
+ { .compatible = "micrel,ksz8864" },
+ { .compatible = "micrel,ksz8795" },
+ { },
+ };
+MODULE_DEVICE_TABLE(of, ks8895_spi_of_match);
+
static inline u8 get_chip_id(u8 val)
{
return (val >> ID1_CHIPID_S) & ID1_CHIPID_M;
static struct spi_driver ks8995_driver = {
.driver = {
.name = "spi-ks8995",
+ .of_match_table = of_match_ptr(ks8895_spi_of_match),
},
.probe = ks8995_probe,
.remove = ks8995_remove,
void
slhc_free(struct slcompress *comp)
{
- if ( comp == NULLSLCOMPR )
+ if ( IS_ERR_OR_NULL(comp) )
return;
if ( comp->tstate != NULLSLSTATE )
return -EINVAL;
}
+ if (netdev_has_upper_dev(dev, port_dev)) {
+ NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface");
+ netdev_err(dev, "Device %s is already an upper device of the team interface\n",
+ portname);
+ return -EBUSY;
+ }
+
if (port_dev->features & NETIF_F_VLAN_CHALLENGED &&
vlan_uses_dev(dev)) {
NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up");
goto err_option_port_add;
}
+ /* set promiscuity level to new slave */
+ if (dev->flags & IFF_PROMISC) {
+ err = dev_set_promiscuity(port_dev, 1);
+ if (err)
+ goto err_set_slave_promisc;
+ }
+
+ /* set allmulti level to new slave */
+ if (dev->flags & IFF_ALLMULTI) {
+ err = dev_set_allmulti(port_dev, 1);
+ if (err) {
+ if (dev->flags & IFF_PROMISC)
+ dev_set_promiscuity(port_dev, -1);
+ goto err_set_slave_promisc;
+ }
+ }
+
netif_addr_lock_bh(dev);
dev_uc_sync_multiple(port_dev, dev);
dev_mc_sync_multiple(port_dev, dev);
return 0;
+err_set_slave_promisc:
+ __team_option_inst_del_port(team, port);
+
err_option_port_add:
team_upper_dev_unlink(team, port);
team_port_disable(team, port);
list_del_rcu(&port->list);
+
+ if (dev->flags & IFF_PROMISC)
+ dev_set_promiscuity(port_dev, -1);
+ if (dev->flags & IFF_ALLMULTI)
+ dev_set_allmulti(port_dev, -1);
+
team_upper_dev_unlink(team, port);
netdev_rx_handler_unregister(port_dev);
team_port_disable_netpoll(port);
{QMI_FIXED_INTF(0x0846, 0x68d3, 8)}, /* Netgear Aircard 779S */
{QMI_FIXED_INTF(0x12d1, 0x140c, 1)}, /* Huawei E173 */
{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)}, /* Huawei E1820 */
+ {QMI_FIXED_INTF(0x1435, 0x0918, 3)}, /* Wistron NeWeb D16Q1 */
+ {QMI_FIXED_INTF(0x1435, 0x0918, 4)}, /* Wistron NeWeb D16Q1 */
+ {QMI_FIXED_INTF(0x1435, 0x0918, 5)}, /* Wistron NeWeb D16Q1 */
+ {QMI_FIXED_INTF(0x1435, 0x3185, 4)}, /* Wistron NeWeb M18Q5 */
+ {QMI_FIXED_INTF(0x1435, 0xd111, 4)}, /* M9615A DM11-1 D51QC */
{QMI_FIXED_INTF(0x1435, 0xd181, 3)}, /* Wistron NeWeb D18Q1 */
{QMI_FIXED_INTF(0x1435, 0xd181, 4)}, /* Wistron NeWeb D18Q1 */
{QMI_FIXED_INTF(0x1435, 0xd181, 5)}, /* Wistron NeWeb D18Q1 */
+ {QMI_FIXED_INTF(0x1435, 0xd182, 4)}, /* Wistron NeWeb D18 */
+ {QMI_FIXED_INTF(0x1435, 0xd182, 5)}, /* Wistron NeWeb D18 */
{QMI_FIXED_INTF(0x1435, 0xd191, 4)}, /* Wistron NeWeb D19Q1 */
{QMI_QUIRK_SET_DTR(0x1508, 0x1001, 4)}, /* Fibocom NL668 series */
{QMI_FIXED_INTF(0x16d8, 0x6003, 0)}, /* CMOTech 6003 */
{QMI_FIXED_INTF(0x19d2, 0x0265, 4)}, /* ONDA MT8205 4G LTE */
{QMI_FIXED_INTF(0x19d2, 0x0284, 4)}, /* ZTE MF880 */
{QMI_FIXED_INTF(0x19d2, 0x0326, 4)}, /* ZTE MF821D */
+ {QMI_FIXED_INTF(0x19d2, 0x0396, 3)}, /* ZTE ZM8620 */
{QMI_FIXED_INTF(0x19d2, 0x0412, 4)}, /* Telewell TW-LTE 4G */
{QMI_FIXED_INTF(0x19d2, 0x1008, 4)}, /* ZTE (Vodafone) K3570-Z */
{QMI_FIXED_INTF(0x19d2, 0x1010, 4)}, /* ZTE (Vodafone) K3571-Z */
{QMI_FIXED_INTF(0x19d2, 0x1425, 2)},
{QMI_FIXED_INTF(0x19d2, 0x1426, 2)}, /* ZTE MF91 */
{QMI_FIXED_INTF(0x19d2, 0x1428, 2)}, /* Telewell TW-LTE 4G v2 */
+ {QMI_FIXED_INTF(0x19d2, 0x1432, 3)}, /* ZTE ME3620 */
{QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */
+ {QMI_FIXED_INTF(0x2001, 0x7e16, 3)}, /* D-Link DWM-221 */
{QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */
{QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */
{QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */
.ndo_init = vrf_dev_init,
.ndo_uninit = vrf_dev_uninit,
.ndo_start_xmit = vrf_xmit,
+ .ndo_set_mac_address = eth_mac_addr,
.ndo_get_stats64 = vrf_get_stats64,
.ndo_add_slave = vrf_add_slave,
.ndo_del_slave = vrf_del_slave,
/* default to no qdisc; user can add if desired */
dev->priv_flags |= IFF_NO_QUEUE;
dev->priv_flags |= IFF_NO_RX_HANDLER;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
/* VRF devices do not care about MTU, but if the MTU is set
* too low then the ipv4 and ipv6 protocols are disabled
struct ath10k_ce_crash_data ce_data;
u32 addr, id;
- lockdep_assert_held(&ar->data_lock);
+ lockdep_assert_held(&ar->dump_mutex);
ath10k_err(ar, "Copy Engine register dump:\n");
goto err_free_wq;
mutex_init(&ar->conf_mutex);
+ mutex_init(&ar->dump_mutex);
spin_lock_init(&ar->data_lock);
INIT_LIST_HEAD(&ar->peers);
/* prevents concurrent FW reconfiguration */
struct mutex conf_mutex;
+ /* protects coredump data */
+ struct mutex dump_mutex;
+
/* protects shared structure data */
spinlock_t data_lock;
{
struct ath10k_fw_crash_data *crash_data = ar->coredump.fw_crash_data;
- lockdep_assert_held(&ar->data_lock);
+ lockdep_assert_held(&ar->dump_mutex);
if (ath10k_coredump_mask == 0)
/* coredump disabled */
if (!buf)
return NULL;
- spin_lock_bh(&ar->data_lock);
+ mutex_lock(&ar->dump_mutex);
dump_data = (struct ath10k_dump_file_data *)(buf);
strlcpy(dump_data->df_magic, "ATH10K-FW-DUMP",
sofar += sizeof(*dump_tlv) + crash_data->ramdump_buf_len;
}
- spin_unlock_bh(&ar->data_lock);
+ mutex_unlock(&ar->dump_mutex);
return dump_data;
}
num_msdus++;
num_bytes += ret;
}
- ieee80211_return_txq(hw, txq);
+ ieee80211_return_txq(hw, txq, false);
ieee80211_txq_schedule_end(hw, txq->ac);
record->num_msdus = cpu_to_le16(num_msdus);
if (ret < 0)
break;
}
- ieee80211_return_txq(hw, txq);
+ ieee80211_return_txq(hw, txq, false);
ath10k_htt_tx_txq_update(hw, txq);
if (ret == -EBUSY)
break;
if (ret < 0)
break;
}
- ieee80211_return_txq(hw, txq);
+ ieee80211_return_txq(hw, txq, false);
ath10k_htt_tx_txq_update(hw, txq);
out:
ieee80211_txq_schedule_end(hw, ac);
}
if (changed & BSS_CHANGED_MCAST_RATE &&
- !WARN_ON(ath10k_mac_vif_chan(arvif->vif, &def))) {
+ !ath10k_mac_vif_chan(arvif->vif, &def)) {
band = def.chan->band;
rateidx = vif->bss_conf.mcast_rate[band] - 1;
}
if (changed & BSS_CHANGED_BASIC_RATES) {
- if (WARN_ON(ath10k_mac_vif_chan(vif, &def))) {
+ if (ath10k_mac_vif_chan(vif, &def)) {
mutex_unlock(&ar->conf_mutex);
return;
}
__le32 reg_dump_values[REG_DUMP_COUNT_QCA988X] = {};
int i, ret;
- lockdep_assert_held(&ar->data_lock);
+ lockdep_assert_held(&ar->dump_mutex);
ret = ath10k_pci_diag_read_hi(ar, ®_dump_values[0],
hi_failure_state,
int ret, i;
u8 *buf;
- lockdep_assert_held(&ar->data_lock);
+ lockdep_assert_held(&ar->dump_mutex);
if (!crash_data)
return;
}
}
-static void ath10k_pci_fw_crashed_dump(struct ath10k *ar)
+static void ath10k_pci_fw_dump_work(struct work_struct *work)
{
+ struct ath10k_pci *ar_pci = container_of(work, struct ath10k_pci,
+ dump_work);
struct ath10k_fw_crash_data *crash_data;
+ struct ath10k *ar = ar_pci->ar;
char guid[UUID_STRING_LEN + 1];
- spin_lock_bh(&ar->data_lock);
+ mutex_lock(&ar->dump_mutex);
+ spin_lock_bh(&ar->data_lock);
ar->stats.fw_crash_counter++;
+ spin_unlock_bh(&ar->data_lock);
crash_data = ath10k_coredump_new(ar);
ath10k_ce_dump_registers(ar, crash_data);
ath10k_pci_dump_memory(ar, crash_data);
- spin_unlock_bh(&ar->data_lock);
+ mutex_unlock(&ar->dump_mutex);
queue_work(ar->workqueue, &ar->restart_work);
}
+static void ath10k_pci_fw_crashed_dump(struct ath10k *ar)
+{
+ struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+
+ queue_work(ar->workqueue, &ar_pci->dump_work);
+}
+
void ath10k_pci_hif_send_complete_check(struct ath10k *ar, u8 pipe,
int force)
{
spin_lock_init(&ar_pci->ps_lock);
mutex_init(&ar_pci->ce_diag_mutex);
+ INIT_WORK(&ar_pci->dump_work, ath10k_pci_fw_dump_work);
+
timer_setup(&ar_pci->rx_post_retry, ath10k_pci_rx_replenish_retry, 0);
if (QCA_REV_6174(ar) || QCA_REV_9377(ar))
/* For protecting ce_diag */
struct mutex ce_diag_mutex;
+ struct work_struct dump_work;
+
struct ath10k_ce ce;
struct timer_list rx_post_retry;
goto out;
while ((queue = ieee80211_next_txq(hw, txq->mac80211_qnum))) {
+ bool force;
+
tid = (struct ath_atx_tid *)queue->drv_priv;
ret = ath_tx_sched_aggr(sc, txq, tid);
ath_dbg(common, QUEUE, "ath_tx_sched_aggr returned %d\n", ret);
- ieee80211_return_txq(hw, queue);
+ force = !skb_queue_empty(&tid->retry_q);
+ ieee80211_return_txq(hw, queue, force);
}
out:
#define IWL_22000_HR_A0_FW_PRE "iwlwifi-QuQnj-a0-hr-a0-"
#define IWL_22000_SU_Z0_FW_PRE "iwlwifi-su-z0-"
#define IWL_QU_B_JF_B_FW_PRE "iwlwifi-Qu-b0-jf-b0-"
+#define IWL_QUZ_A_HR_B_FW_PRE "iwlwifi-QuZ-a0-hr-b0-"
#define IWL_QNJ_B_JF_B_FW_PRE "iwlwifi-QuQnj-b0-jf-b0-"
#define IWL_CC_A_FW_PRE "iwlwifi-cc-a0-"
#define IWL_22000_SO_A_JF_B_FW_PRE "iwlwifi-so-a0-jf-b0-"
IWL_22000_HR_A0_FW_PRE __stringify(api) ".ucode"
#define IWL_22000_SU_Z0_MODULE_FIRMWARE(api) \
IWL_22000_SU_Z0_FW_PRE __stringify(api) ".ucode"
-#define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \
- IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode"
+#define IWL_QUZ_A_HR_B_MODULE_FIRMWARE(api) \
+ IWL_QUZ_A_HR_B_FW_PRE __stringify(api) ".ucode"
#define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \
IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode"
#define IWL_QNJ_B_JF_B_MODULE_FIRMWARE(api) \
#define IWL_DEVICE_AX210 \
IWL_DEVICE_AX200_COMMON, \
.device_family = IWL_DEVICE_FAMILY_AX210, \
- .base_params = &iwl_22000_base_params, \
+ .base_params = &iwl_22560_base_params, \
.csr = &iwl_csr_v1, \
.min_txq_size = 128
.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
};
-const struct iwl_cfg iwl22260_2ax_cfg = {
- .name = "Intel(R) Wireless-AX 22260",
+const struct iwl_cfg iwl_ax101_cfg_quz_hr = {
+ .name = "Intel(R) Wi-Fi 6 AX101",
+ .fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE,
+ IWL_DEVICE_22500,
+ /*
+ * This device doesn't support receiving BlockAck with a large bitmap
+ * so we need to restrict the size of transmitted aggregation to the
+ * HT size; mac80211 would otherwise pick the HE max (256) by default.
+ */
+ .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
+};
+
+const struct iwl_cfg iwl_ax200_cfg_cc = {
+ .name = "Intel(R) Wi-Fi 6 AX200 160MHz",
.fw_name_pre = IWL_CC_A_FW_PRE,
IWL_DEVICE_22500,
/*
};
const struct iwl_cfg killer1650x_2ax_cfg = {
- .name = "Killer(R) Wireless-AX 1650x Wireless Network Adapter (200NGW)",
+ .name = "Killer(R) Wi-Fi 6 AX1650x 160MHz Wireless Network Adapter (200NGW)",
.fw_name_pre = IWL_CC_A_FW_PRE,
IWL_DEVICE_22500,
/*
};
const struct iwl_cfg killer1650w_2ax_cfg = {
- .name = "Killer(R) Wireless-AX 1650w Wireless Network Adapter (200D2W)",
+ .name = "Killer(R) Wi-Fi 6 AX1650w 160MHz Wireless Network Adapter (200D2W)",
.fw_name_pre = IWL_CC_A_FW_PRE,
IWL_DEVICE_22500,
/*
};
const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0 = {
- .name = "Killer(R) Wireless-AX 1650i Wireless Network Adapter (22560NGW)",
+ .name = "Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201NGW)",
.fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE,
IWL_DEVICE_22500,
/*
};
const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0 = {
- .name = "Killer(R) Wireless-AX 1650s Wireless Network Adapter (22560D2W)",
+ .name = "Killer(R) Wi-Fi 6 AX1650s 160MHz Wireless Network Adapter (201D2W)",
.fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE,
IWL_DEVICE_22500,
/*
MODULE_FIRMWARE(IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_22000_SU_Z0_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_QU_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_QUZ_A_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_QNJ_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_CC_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
MODULE_FIRMWARE(IWL_22000_SO_A_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
/******************************************************************************
*
* Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2 of the GNU General Public License as
.ht_params = &iwl5000_ht_params,
.led_mode = IWL_LED_BLINK,
.internal_wimax_coex = true,
+ .csr = &iwl_csr_v1,
};
#define IWL_DEVICE_5150 \
if (!range) {
IWL_ERR(fwrt, "Failed to fill region header: id=%d, type=%d\n",
le32_to_cpu(reg->region_id), type);
+ memset(*data, 0, le32_to_cpu((*data)->len));
return;
}
if (range_size < 0) {
IWL_ERR(fwrt, "Failed to dump region: id=%d, type=%d\n",
le32_to_cpu(reg->region_id), type);
+ memset(*data, 0, le32_to_cpu((*data)->len));
return;
}
range = range + range_size;
trigger = fwrt->dump.active_trigs[id].trig;
- size = sizeof(*dump_file);
- size += iwl_fw_ini_get_trigger_len(fwrt, trigger);
-
+ size = iwl_fw_ini_get_trigger_len(fwrt, trigger);
if (!size)
return NULL;
+ size += sizeof(*dump_file);
+
dump_file = vzalloc(size);
if (!dump_file)
return NULL;
iwl_dump_error_desc->len = 0;
ret = iwl_fw_dbg_collect_desc(fwrt, iwl_dump_error_desc, false, 0);
- if (ret) {
+ if (ret)
kfree(iwl_dump_error_desc);
- } else {
- set_bit(STATUS_FW_WAIT_DUMP, &fwrt->trans->status);
-
- /* trigger nmi to halt the fw */
- iwl_force_nmi(fwrt->trans);
- }
+ else
+ iwl_trans_sync_nmi(fwrt->trans);
return ret;
}
void iwl_fwrt_stop_device(struct iwl_fw_runtime *fwrt)
{
- /* if the wait event timeout elapses instead of wake up then
- * the driver did not receive NMI interrupt and can not assume the FW
- * is halted
- */
- int ret = wait_event_timeout(fwrt->trans->fw_halt_waitq,
- !test_bit(STATUS_FW_WAIT_DUMP,
- &fwrt->trans->status),
- msecs_to_jiffies(2000));
- if (!ret) {
- /* failed to receive NMI interrupt, assuming the FW is stuck */
- set_bit(STATUS_FW_ERROR, &fwrt->trans->status);
-
- clear_bit(STATUS_FW_WAIT_DUMP, &fwrt->trans->status);
- }
-
- /* Assuming the op mode mutex is held at this point */
iwl_fw_dbg_collect_sync(fwrt);
iwl_trans_stop_device(fwrt->trans);
} u;
};
-#define IWL_UCODE_INI_TLV_GROUP BIT(24)
+#define IWL_UCODE_INI_TLV_GROUP 0x1000000
/*
* new TLV uCode file layout
IWL_UCODE_TLV_UMAC_DEBUG_ADDRS = 54,
IWL_UCODE_TLV_LMAC_DEBUG_ADDRS = 55,
IWL_UCODE_TLV_FW_RECOVERY_INFO = 57,
- IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION = IWL_UCODE_INI_TLV_GROUP | 0x1,
- IWL_UCODE_TLV_TYPE_HCMD = IWL_UCODE_INI_TLV_GROUP | 0x2,
- IWL_UCODE_TLV_TYPE_REGIONS = IWL_UCODE_INI_TLV_GROUP | 0x3,
- IWL_UCODE_TLV_TYPE_TRIGGERS = IWL_UCODE_INI_TLV_GROUP | 0x4,
- IWL_UCODE_TLV_TYPE_DEBUG_FLOW = IWL_UCODE_INI_TLV_GROUP | 0x5,
+
+ IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION = IWL_UCODE_INI_TLV_GROUP + 0x1,
+ IWL_UCODE_TLV_DEBUG_BASE = IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION,
+ IWL_UCODE_TLV_TYPE_HCMD = IWL_UCODE_INI_TLV_GROUP + 0x2,
+ IWL_UCODE_TLV_TYPE_REGIONS = IWL_UCODE_INI_TLV_GROUP + 0x3,
+ IWL_UCODE_TLV_TYPE_TRIGGERS = IWL_UCODE_INI_TLV_GROUP + 0x4,
+ IWL_UCODE_TLV_TYPE_DEBUG_FLOW = IWL_UCODE_INI_TLV_GROUP + 0x5,
+ IWL_UCODE_TLV_DEBUG_MAX = IWL_UCODE_TLV_TYPE_DEBUG_FLOW,
/* TLVs 0x1000-0x2000 are for internal driver usage */
IWL_UCODE_TLV_FW_DBG_DUMP_LST = 0x1000,
fwrt->ops_ctx = ops_ctx;
INIT_DELAYED_WORK(&fwrt->dump.wk, iwl_fw_error_dump_wk);
iwl_fwrt_dbgfs_register(fwrt, dbgfs_dir);
- init_waitqueue_head(&fwrt->trans->fw_halt_waitq);
}
IWL_EXPORT_SYMBOL(iwl_fw_runtime_init);
extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb;
extern const struct iwl_cfg iwl22000_2ac_cfg_jf;
extern const struct iwl_cfg iwl_ax101_cfg_qu_hr;
+extern const struct iwl_cfg iwl_ax101_cfg_quz_hr;
extern const struct iwl_cfg iwl22000_2ax_cfg_hr;
-extern const struct iwl_cfg iwl22260_2ax_cfg;
+extern const struct iwl_cfg iwl_ax200_cfg_cc;
extern const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0;
extern const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0;
extern const struct iwl_cfg killer1650x_2ax_cfg;
#define CSR_HW_REV_TYPE_NONE (0x00001F0)
#define CSR_HW_REV_TYPE_QNJ (0x0000360)
#define CSR_HW_REV_TYPE_QNJ_B0 (0x0000364)
+#define CSR_HW_REV_TYPE_QUZ (0x0000354)
#define CSR_HW_REV_TYPE_HR_CDB (0x0000340)
#define CSR_HW_REV_TYPE_SO (0x0000370)
#define CSR_HW_REV_TYPE_TY (0x0000420)
len -= ALIGN(tlv_len, 4);
data += sizeof(*tlv) + ALIGN(tlv_len, 4);
- if (!(tlv_type & IWL_UCODE_INI_TLV_GROUP))
+ if (tlv_type < IWL_UCODE_TLV_DEBUG_BASE ||
+ tlv_type > IWL_UCODE_TLV_DEBUG_MAX)
continue;
hdr = (void *)&tlv->data[0];
* are sent
* @STATUS_TRANS_IDLE: the trans is idle - general commands are not to be sent
* @STATUS_TRANS_DEAD: trans is dead - avoid any read/write operation
- * @STATUS_FW_WAIT_DUMP: if set, wait until cleared before collecting dump
*/
enum iwl_trans_status {
STATUS_SYNC_HCMD_ACTIVE,
STATUS_TRANS_GOING_IDLE,
STATUS_TRANS_IDLE,
STATUS_TRANS_DEAD,
- STATUS_FW_WAIT_DUMP,
};
static inline int
struct iwl_trans_dump_data *(*dump_data)(struct iwl_trans *trans,
u32 dump_mask);
void (*debugfs_cleanup)(struct iwl_trans *trans);
+ void (*sync_nmi)(struct iwl_trans *trans);
};
/**
u32 lmac_error_event_table[2];
u32 umac_error_event_table;
unsigned int error_event_table_tlv_status;
- wait_queue_head_t fw_halt_waitq;
/* pointer to trans specific struct */
/*Ensure that this pointer will always be aligned to sizeof pointer */
/* prevent double restarts due to the same erroneous FW */
if (!test_and_set_bit(STATUS_FW_ERROR, &trans->status))
iwl_op_mode_nic_error(trans->op_mode);
+}
- if (test_and_clear_bit(STATUS_FW_WAIT_DUMP, &trans->status))
- wake_up(&trans->fw_halt_waitq);
-
+static inline void iwl_trans_sync_nmi(struct iwl_trans *trans)
+{
+ if (trans->ops->sync_nmi)
+ trans->ops->sync_nmi(trans);
}
/*****************************************************
return;
mvmvif->dbgfs_dir = debugfs_create_dir("iwlmvm", dbgfs_dir);
-
- if (!mvmvif->dbgfs_dir) {
+ if (IS_ERR_OR_NULL(mvmvif->dbgfs_dir)) {
IWL_ERR(mvm, "Failed to create debugfs directory under %pd\n",
dbgfs_dir);
return;
ret = iwl_mvm_load_rt_fw(mvm);
if (ret) {
IWL_ERR(mvm, "Failed to start RT ucode: %d\n", ret);
- iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER);
+ if (ret != -ERFKILL)
+ iwl_fw_dbg_error_collect(&mvm->fwrt,
+ FW_DBG_TRIGGER_DRIVER);
goto error;
}
iwl_mvm_mac_ctxt_remove(mvm, vif);
- kfree(mvmvif->ap_wep_key);
- mvmvif->ap_wep_key = NULL;
-
mutex_unlock(&mvm->mutex);
}
ret = iwl_mvm_update_sta(mvm, vif, sta);
} else if (old_state == IEEE80211_STA_ASSOC &&
new_state == IEEE80211_STA_AUTHORIZED) {
- /* if wep is used, need to set the key for the station now */
- if (vif->type == NL80211_IFTYPE_AP && mvmvif->ap_wep_key) {
- mvm_sta->wep_key =
- kmemdup(mvmvif->ap_wep_key,
- sizeof(*mvmvif->ap_wep_key) +
- mvmvif->ap_wep_key->keylen,
- GFP_KERNEL);
- if (!mvm_sta->wep_key) {
- ret = -ENOMEM;
- goto out_unlock;
- }
-
- ret = iwl_mvm_set_sta_key(mvm, vif, sta,
- mvm_sta->wep_key,
- STA_KEY_IDX_INVALID);
- } else {
- ret = 0;
- }
+ ret = 0;
/* we don't support TDLS during DCM */
if (iwl_mvm_phy_ctx_count(mvm) > 1)
NL80211_TDLS_DISABLE_LINK);
}
- /* Remove STA key if this is an AP using WEP */
- if (vif->type == NL80211_IFTYPE_AP && mvmvif->ap_wep_key) {
- int rm_ret = iwl_mvm_remove_sta_key(mvm, vif, sta,
- mvm_sta->wep_key);
-
- if (!ret)
- ret = rm_ret;
- kfree(mvm_sta->wep_key);
- mvm_sta->wep_key = NULL;
- }
-
if (unlikely(ret &&
test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED,
&mvm->status)))
struct ieee80211_sta *sta, u32 changed)
{
struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+ struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+
+ if (changed & (IEEE80211_RC_BW_CHANGED |
+ IEEE80211_RC_SUPP_RATES_CHANGED |
+ IEEE80211_RC_NSS_CHANGED))
+ iwl_mvm_rs_rate_init(mvm, sta, mvmvif->phy_ctxt->channel->band,
+ true);
if (vif->type == NL80211_IFTYPE_STATION &&
changed & IEEE80211_RC_NSS_CHANGED)
break;
case WLAN_CIPHER_SUITE_WEP40:
case WLAN_CIPHER_SUITE_WEP104:
- if (vif->type == NL80211_IFTYPE_AP) {
- struct iwl_mvm_vif *mvmvif =
- iwl_mvm_vif_from_mac80211(vif);
-
- mvmvif->ap_wep_key = kmemdup(key,
- sizeof(*key) + key->keylen,
- GFP_KERNEL);
- if (!mvmvif->ap_wep_key)
- return -ENOMEM;
- }
-
- if (vif->type != NL80211_IFTYPE_STATION)
- return 0;
- break;
+ if (vif->type == NL80211_IFTYPE_STATION)
+ break;
+ if (iwl_mvm_has_new_tx_api(mvm))
+ return -EOPNOTSUPP;
+ /* support HW crypto on TX */
+ return 0;
default:
/* currently FW supports only one optional cipher scheme */
if (hw->n_cipher_schemes &&
ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, key_offset);
if (ret) {
IWL_WARN(mvm, "set key failed\n");
+ key->hw_key_idx = STA_KEY_IDX_INVALID;
/*
* can't add key for RX, but we don't need it
- * in the device for TX so still return 0
+ * in the device for TX so still return 0,
+ * unless we have new TX API where we cannot
+ * put key material into the TX_CMD
*/
- key->hw_key_idx = STA_KEY_IDX_INVALID;
- ret = 0;
+ if (iwl_mvm_has_new_tx_api(mvm))
+ ret = -EOPNOTSUPP;
+ else
+ ret = 0;
}
break;
netdev_features_t features;
struct iwl_probe_resp_data __rcu *probe_resp_data;
- struct ieee80211_key_conf *ap_wep_key;
};
static inline struct iwl_mvm_vif *
mutex_lock(&mvm->mutex);
iwl_mvm_ref(mvm, IWL_MVM_REF_INIT_UCODE);
err = iwl_run_init_mvm_ucode(mvm, true);
- if (err)
+ if (err && err != -ERFKILL)
iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER);
if (!iwlmvm_mod_params.init_dbg || !err)
iwl_mvm_stop_device(mvm);
}
/* iwl_mvm_create_skb Adds the rxb to a new skb */
-static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr,
- u16 len, u8 crypt_len,
- struct iwl_rx_cmd_buffer *rxb)
+static int iwl_mvm_create_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
+ struct ieee80211_hdr *hdr, u16 len, u8 crypt_len,
+ struct iwl_rx_cmd_buffer *rxb)
{
struct iwl_rx_packet *pkt = rxb_addr(rxb);
struct iwl_rx_mpdu_desc *desc = (void *)pkt->data;
* present before copying packet data.
*/
hdrlen += crypt_len;
+
+ if (WARN_ONCE(headlen < hdrlen,
+ "invalid packet lengths (hdrlen=%d, len=%d, crypt_len=%d)\n",
+ hdrlen, len, crypt_len)) {
+ /*
+ * We warn and trace because we want to be able to see
+ * it in trace-cmd as well.
+ */
+ IWL_DEBUG_RX(mvm,
+ "invalid packet lengths (hdrlen=%d, len=%d, crypt_len=%d)\n",
+ hdrlen, len, crypt_len);
+ return -EINVAL;
+ }
+
skb_put_data(skb, hdr, hdrlen);
skb_put_data(skb, (u8 *)hdr + hdrlen + pad_len, headlen - hdrlen);
skb_add_rx_frag(skb, 0, rxb_steal_page(rxb), offset,
fraglen, rxb->truesize);
}
+
+ return 0;
}
static void iwl_mvm_add_rtap_sniffer_config(struct iwl_mvm *mvm,
rx_status->boottime_ns = ktime_get_boot_ns();
}
- iwl_mvm_create_skb(skb, hdr, len, crypt_len, rxb);
+ if (iwl_mvm_create_skb(mvm, skb, hdr, len, crypt_len, rxb)) {
+ kfree_skb(skb);
+ goto out;
+ }
+
if (!iwl_mvm_reorder(mvm, napi, queue, sta, skb, desc))
iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue,
sta, csi);
* Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
iwl_mvm_sta_alloc_queue(mvm, txq->sta, txq->ac, tid);
list_del_init(&mvmtxq->list);
+ local_bh_disable();
iwl_mvm_mac_itxq_xmit(mvm->hw, txq);
+ local_bh_enable();
}
mutex_unlock(&mvm->mutex);
iwl_mvm_enable_txq(mvm, NULL, mvmvif->cab_queue, 0, &cfg,
timeout);
- if (mvmvif->ap_wep_key) {
- u8 key_offset = iwl_mvm_set_fw_key_idx(mvm);
-
- __set_bit(key_offset, mvm->fw_key_table);
-
- if (key_offset == STA_KEY_IDX_INVALID)
- return -ENOSPC;
-
- ret = iwl_mvm_send_sta_key(mvm, mvmvif->mcast_sta.sta_id,
- mvmvif->ap_wep_key, true, 0, NULL, 0,
- key_offset, 0);
- if (ret)
- return ret;
- }
-
return 0;
}
iwl_mvm_disable_txq(mvm, NULL, mvmvif->cab_queue, 0, 0);
- if (mvmvif->ap_wep_key) {
- int i;
-
- if (!__test_and_clear_bit(mvmvif->ap_wep_key->hw_key_idx,
- mvm->fw_key_table)) {
- IWL_ERR(mvm, "offset %d not used in fw key table.\n",
- mvmvif->ap_wep_key->hw_key_idx);
- return -ENOENT;
- }
-
- /* track which key was deleted last */
- for (i = 0; i < STA_KEY_MAX_NUM; i++) {
- if (mvm->fw_key_deleted[i] < U8_MAX)
- mvm->fw_key_deleted[i]++;
- }
- mvm->fw_key_deleted[mvmvif->ap_wep_key->hw_key_idx] = 0;
- ret = __iwl_mvm_remove_sta_key(mvm, mvmvif->mcast_sta.sta_id,
- mvmvif->ap_wep_key, true);
- if (ret)
- return ret;
- }
-
ret = iwl_mvm_rm_sta_common(mvm, mvmvif->mcast_sta.sta_id);
if (ret)
IWL_WARN(mvm, "Failed sending remove station\n");
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
* Copyright(c) 2015 - 2016 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
* Copyright(c) 2015 - 2016 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* the BA window. To be used for UAPSD only.
* @ptk_pn: per-queue PTK PN data structures
* @dup_data: per queue duplicate packet detection data
- * @wep_key: used in AP mode. Is a duplicate of the WEP key.
* @deferred_traffic_tid_map: indication bitmap of deferred traffic per-TID
* @tx_ant: the index of the antenna to use for data tx to this station. Only
* used during connection establishment (e.g. for the 4 way handshake
struct iwl_mvm_key_pn __rcu *ptk_pn[4];
struct iwl_mvm_rxq_dup_data *dup_data;
- struct ieee80211_key_conf *wep_key;
-
u8 reserved_queue;
/* Temporary, until the new TLC will control the Tx protection */
{IWL_PCI_DEVICE(0xA0F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)},
{IWL_PCI_DEVICE(0xA0F0, 0x4070, iwl_ax101_cfg_qu_hr)},
- {IWL_PCI_DEVICE(0x2723, 0x0080, iwl22260_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x0084, iwl22260_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x0088, iwl22260_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x008C, iwl22260_2ax_cfg)},
+ {IWL_PCI_DEVICE(0x2723, 0x0080, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x0084, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x0088, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x008C, iwl_ax200_cfg_cc)},
{IWL_PCI_DEVICE(0x2723, 0x1653, killer1650w_2ax_cfg)},
{IWL_PCI_DEVICE(0x2723, 0x1654, killer1650x_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x4080, iwl22260_2ax_cfg)},
- {IWL_PCI_DEVICE(0x2723, 0x4088, iwl22260_2ax_cfg)},
+ {IWL_PCI_DEVICE(0x2723, 0x2080, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x4080, iwl_ax200_cfg_cc)},
+ {IWL_PCI_DEVICE(0x2723, 0x4088, iwl_ax200_cfg_cc)},
{IWL_PCI_DEVICE(0x1a56, 0x1653, killer1650w_2ax_cfg)},
{IWL_PCI_DEVICE(0x1a56, 0x1654, killer1650x_2ax_cfg)},
void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state);
void iwl_trans_pcie_dump_regs(struct iwl_trans *trans);
-void iwl_trans_sync_nmi(struct iwl_trans *trans);
+void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans);
#ifdef CONFIG_IWLWIFI_DEBUGFS
int iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans);
.unref = iwl_trans_pcie_unref, \
.dump_data = iwl_trans_pcie_dump_data, \
.d3_suspend = iwl_trans_pcie_d3_suspend, \
- .d3_resume = iwl_trans_pcie_d3_resume
+ .d3_resume = iwl_trans_pcie_d3_resume, \
+ .sync_nmi = iwl_trans_pcie_sync_nmi
#ifdef CONFIG_PM_SLEEP
#define IWL_TRANS_PM_OPS \
}
} else if (cfg == &iwl_ax101_cfg_qu_hr) {
if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
+ CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) &&
+ trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0) {
+ trans->cfg = &iwl22000_2ax_cfg_qnj_hr_b0;
+ } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) {
trans->cfg = &iwl_ax101_cfg_qu_hr;
} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
}
} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) &&
- (trans->cfg != &iwl22260_2ax_cfg ||
+ (trans->cfg != &iwl_ax200_cfg_cc ||
trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0)) {
u32 hw_status;
return ERR_PTR(ret);
}
-void iwl_trans_sync_nmi(struct iwl_trans *trans)
+void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans)
{
+ struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
unsigned long timeout = jiffies + IWL_TRANS_NMI_TIMEOUT;
+ u32 inta_addr, sw_err_bit;
+
+ if (trans_pcie->msix_enabled) {
+ inta_addr = CSR_MSIX_HW_INT_CAUSES_AD;
+ sw_err_bit = MSIX_HW_INT_CAUSES_REG_SW_ERR;
+ } else {
+ inta_addr = CSR_INT;
+ sw_err_bit = CSR_INT_BIT_SW_ERR;
+ }
iwl_disable_interrupts(trans);
iwl_force_nmi(trans);
while (time_after(timeout, jiffies)) {
- u32 inta_hw = iwl_read32(trans,
- CSR_MSIX_HW_INT_CAUSES_AD);
+ u32 inta_hw = iwl_read32(trans, inta_addr);
/* Error detected by uCode */
- if (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR) {
+ if (inta_hw & sw_err_bit) {
/* Clear causes register */
- iwl_write32(trans, CSR_MSIX_HW_INT_CAUSES_AD,
- inta_hw &
- MSIX_HW_INT_CAUSES_REG_SW_ERR);
+ iwl_write32(trans, inta_addr, inta_hw & sw_err_bit);
break;
}
cmd_str);
ret = -ETIMEDOUT;
- iwl_trans_sync_nmi(trans);
+ iwl_trans_pcie_sync_nmi(trans);
goto cancel;
}
iwl_get_cmd_string(trans, cmd->id));
ret = -ETIMEDOUT;
- iwl_trans_sync_nmi(trans);
+ iwl_trans_pcie_sync_nmi(trans);
goto cancel;
}
unsigned int rx_filter;
bool started, idle, scanning;
struct mutex mutex;
- struct tasklet_hrtimer beacon_timer;
+ struct hrtimer beacon_timer;
enum ps_mode {
PS_DISABLED, PS_ENABLED, PS_AUTO_POLL, PS_MANUAL_POLL
} ps;
{
struct mac80211_hwsim_data *data = hw->priv;
data->started = false;
- tasklet_hrtimer_cancel(&data->beacon_timer);
+ hrtimer_cancel(&data->beacon_timer);
wiphy_dbg(hw->wiphy, "%s\n", __func__);
}
mac80211_hwsim_beacon(struct hrtimer *timer)
{
struct mac80211_hwsim_data *data =
- container_of(timer, struct mac80211_hwsim_data,
- beacon_timer.timer);
+ container_of(timer, struct mac80211_hwsim_data, beacon_timer);
struct ieee80211_hw *hw = data->hw;
u64 bcn_int = data->beacon_int;
- ktime_t next_bcn;
if (!data->started)
- goto out;
+ return HRTIMER_NORESTART;
ieee80211_iterate_active_interfaces_atomic(
hw, IEEE80211_IFACE_ITER_NORMAL,
bcn_int -= data->bcn_delta;
data->bcn_delta = 0;
}
-
- next_bcn = ktime_add(hrtimer_get_expires(timer),
- ns_to_ktime(bcn_int * 1000));
- tasklet_hrtimer_start(&data->beacon_timer, next_bcn, HRTIMER_MODE_ABS);
-out:
- return HRTIMER_NORESTART;
+ hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer),
+ ns_to_ktime(bcn_int * NSEC_PER_USEC));
+ return HRTIMER_RESTART;
}
static const char * const hwsim_chanwidths[] = {
mutex_unlock(&data->mutex);
if (!data->started || !data->beacon_int)
- tasklet_hrtimer_cancel(&data->beacon_timer);
- else if (!hrtimer_is_queued(&data->beacon_timer.timer)) {
+ hrtimer_cancel(&data->beacon_timer);
+ else if (!hrtimer_is_queued(&data->beacon_timer)) {
u64 tsf = mac80211_hwsim_get_tsf(hw, NULL);
u32 bcn_int = data->beacon_int;
u64 until_tbtt = bcn_int - do_div(tsf, bcn_int);
- tasklet_hrtimer_start(&data->beacon_timer,
- ns_to_ktime(until_tbtt * 1000),
- HRTIMER_MODE_REL);
+ hrtimer_start(&data->beacon_timer,
+ ns_to_ktime(until_tbtt * NSEC_PER_USEC),
+ HRTIMER_MODE_REL_SOFT);
}
return 0;
info->enable_beacon, info->beacon_int);
vp->bcn_en = info->enable_beacon;
if (data->started &&
- !hrtimer_is_queued(&data->beacon_timer.timer) &&
+ !hrtimer_is_queued(&data->beacon_timer) &&
info->enable_beacon) {
u64 tsf, until_tbtt;
u32 bcn_int;
tsf = mac80211_hwsim_get_tsf(hw, vif);
bcn_int = data->beacon_int;
until_tbtt = bcn_int - do_div(tsf, bcn_int);
- tasklet_hrtimer_start(&data->beacon_timer,
- ns_to_ktime(until_tbtt * 1000),
- HRTIMER_MODE_REL);
+
+ hrtimer_start(&data->beacon_timer,
+ ns_to_ktime(until_tbtt * NSEC_PER_USEC),
+ HRTIMER_MODE_REL_SOFT);
} else if (!info->enable_beacon) {
unsigned int count = 0;
ieee80211_iterate_active_interfaces_atomic(
wiphy_dbg(hw->wiphy, " beaconing vifs remaining: %u",
count);
if (count == 0) {
- tasklet_hrtimer_cancel(&data->beacon_timer);
+ hrtimer_cancel(&data->beacon_timer);
data->beacon_int = 0;
}
}
enum nl80211_band band;
const struct ieee80211_ops *ops = &mac80211_hwsim_ops;
struct net *net;
- int idx;
+ int idx, i;
int n_limits = 0;
if (WARN_ON(param->channels > 1 && !param->use_chanctx))
goto failed_hw;
}
+ data->if_combination.max_interfaces = 0;
+ for (i = 0; i < n_limits; i++)
+ data->if_combination.max_interfaces +=
+ data->if_limits[i].max;
+
data->if_combination.n_limits = n_limits;
- data->if_combination.max_interfaces = 2048;
data->if_combination.limits = data->if_limits;
- hw->wiphy->iface_combinations = &data->if_combination;
- hw->wiphy->n_iface_combinations = 1;
+ /*
+ * If we actually were asked to support combinations,
+ * advertise them - if there's only a single thing like
+ * only IBSS then don't advertise it as combinations.
+ */
+ if (data->if_combination.max_interfaces > 1) {
+ hw->wiphy->iface_combinations = &data->if_combination;
+ hw->wiphy->n_iface_combinations = 1;
+ }
if (param->ciphers) {
memcpy(data->ciphers, param->ciphers,
wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
- tasklet_hrtimer_init(&data->beacon_timer,
- mac80211_hwsim_beacon,
- CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_init(&data->beacon_timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS_SOFT);
+ data->beacon_timer.function = mac80211_hwsim_beacon;
err = ieee80211_register_hw(hw);
if (err < 0) {
adapter = card->adapter;
- if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
+ if (!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
mwifiex_dbg(adapter, WARN,
"device already resumed\n");
return 0;
bus_ops->rmw = mt7603_rmw;
dev->mt76.bus = bus_ops;
+ spin_lock_init(&dev->ps_lock);
+
INIT_DELAYED_WORK(&dev->mac_work, mt7603_mac_work);
tasklet_init(&dev->pre_tbtt_tasklet, mt7603_pre_tbtt_tasklet,
(unsigned long)dev);
MT_BA_CONTROL_1_RESET));
}
-void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn,
+void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid,
int ba_size)
{
u32 addr = mt7603_wtbl2_addr(wcid);
mt76_clear(dev, addr + (15 * 4), tid_mask);
return;
}
- mt76_poll(dev, MT_WTBL_UPDATE, MT_WTBL_UPDATE_BUSY, 0, 5000);
-
- mt7603_mac_stop(dev);
- switch (tid) {
- case 0:
- mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID0_SN, ssn);
- break;
- case 1:
- mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID1_SN, ssn);
- break;
- case 2:
- mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID2_SN_LO,
- ssn);
- mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID2_SN_HI,
- ssn >> 8);
- break;
- case 3:
- mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID3_SN, ssn);
- break;
- case 4:
- mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID4_SN, ssn);
- break;
- case 5:
- mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID5_SN_LO,
- ssn);
- mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID5_SN_HI,
- ssn >> 4);
- break;
- case 6:
- mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID6_SN, ssn);
- break;
- case 7:
- mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID7_SN, ssn);
- break;
- }
- mt7603_wtbl_update(dev, wcid, MT_WTBL_UPDATE_WTBL2);
- mt7603_mac_start(dev);
for (i = 7; i > 0; i--) {
if (ba_size >= MT_AGG_SIZE_LIMIT(i))
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
struct ieee80211_tx_rate *rate = &info->control.rates[0];
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+ struct ieee80211_bar *bar = (struct ieee80211_bar *)skb->data;
struct ieee80211_vif *vif = info->control.vif;
struct mt7603_vif *mvif;
int wlan_idx;
int tx_count = 8;
u8 frame_type, frame_subtype;
u16 fc = le16_to_cpu(hdr->frame_control);
+ u16 seqno = 0;
u8 vif_idx = 0;
u32 val;
u8 bw;
tx_count = 0x1f;
val = FIELD_PREP(MT_TXD3_REM_TX_COUNT, tx_count) |
- FIELD_PREP(MT_TXD3_SEQ, le16_to_cpu(hdr->seq_ctrl));
+ MT_TXD3_SN_VALID;
+
+ if (ieee80211_is_data_qos(hdr->frame_control))
+ seqno = le16_to_cpu(hdr->seq_ctrl);
+ else if (ieee80211_is_back_req(hdr->frame_control))
+ seqno = le16_to_cpu(bar->start_seq_num);
+ else
+ val &= ~MT_TXD3_SN_VALID;
+
+ val |= FIELD_PREP(MT_TXD3_SEQ, seqno >> 4);
+
txwi[3] = cpu_to_le32(val);
if (key) {
struct mt7603_sta *msta = (struct mt7603_sta *)sta->drv_priv;
struct sk_buff_head list;
- mt76_stop_tx_queues(&dev->mt76, sta, false);
+ mt76_stop_tx_queues(&dev->mt76, sta, true);
mt7603_wtbl_set_ps(dev, msta, ps);
if (ps)
return;
case IEEE80211_AMPDU_TX_OPERATIONAL:
mtxq->aggr = true;
mtxq->send_bar = false;
- mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, ba_size);
+ mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, ba_size);
break;
case IEEE80211_AMPDU_TX_STOP_FLUSH:
case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
mtxq->aggr = false;
ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
- mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, -1);
+ mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, -1);
break;
case IEEE80211_AMPDU_TX_START:
mtxq->agg_ssn = *ssn << 4;
break;
case IEEE80211_AMPDU_TX_STOP_CONT:
mtxq->aggr = false;
- mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, -1);
+ mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, -1);
ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
break;
}
int mt7603_mac_fill_rx(struct mt7603_dev *dev, struct sk_buff *skb);
void mt7603_mac_add_txs(struct mt7603_dev *dev, void *data);
void mt7603_mac_rx_ba_reset(struct mt7603_dev *dev, void *addr, u8 tid);
-void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn,
+void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid,
int ba_size);
void mt7603_pse_client_reset(struct mt7603_dev *dev);
return;
rcu_read_lock();
- mt76_tx_status_lock(mdev, &list);
if (stat->wcid < ARRAY_SIZE(dev->mt76.wcid))
wcid = rcu_dereference(dev->mt76.wcid[stat->wcid]);
drv_priv);
}
+ mt76_tx_status_lock(mdev, &list);
+
if (wcid) {
if (stat->pktid >= MT_PACKET_ID_FIRST)
status.skb = mt76_tx_status_skb_get(mdev, wcid,
if (*update == 0 && stat_val == stat_cache &&
stat->wcid == msta->status.wcid && msta->n_frames < 32) {
msta->n_frames++;
- goto out;
+ mt76_tx_status_unlock(mdev, &list);
+ rcu_read_unlock();
+ return;
}
mt76x02_mac_fill_tx_status(dev, status.info, &msta->status,
if (status.skb)
mt76_tx_status_skb_done(mdev, status.skb, &list);
- else
- ieee80211_tx_status_ext(mt76_hw(dev), &status);
-
-out:
mt76_tx_status_unlock(mdev, &list);
+
+ if (!status.skb)
+ ieee80211_tx_status_ext(mt76_hw(dev), &status);
rcu_read_unlock();
}
CONFIG_CHANNEL_HT40,
CONFIG_POWERSAVING,
CONFIG_HT_DISABLED,
- CONFIG_QOS_DISABLED,
CONFIG_MONITORING,
/*
rt2x00dev->intf_associated--;
rt2x00leds_led_assoc(rt2x00dev, !!rt2x00dev->intf_associated);
-
- clear_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags);
}
- /*
- * Check for access point which do not support 802.11e . We have to
- * generate data frames sequence number in S/W for such AP, because
- * of H/W bug.
- */
- if (changes & BSS_CHANGED_QOS && !bss_conf->qos)
- set_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags);
-
/*
* When the erp information has changed, we should perform
* additional configuration steps. For all other changes we are done.
if (!rt2x00_has_cap_flag(rt2x00dev, REQUIRE_SW_SEQNO)) {
/*
* rt2800 has a H/W (or F/W) bug, device incorrectly increase
- * seqno on retransmited data (non-QOS) frames. To workaround
- * the problem let's generate seqno in software if QOS is
- * disabled.
+ * seqno on retransmitted data (non-QOS) and management frames.
+ * To workaround the problem let's generate seqno in software.
+ * Except for beacons which are transmitted periodically by H/W
+ * hence hardware has to assign seqno for them.
*/
- if (test_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags))
- __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
- else
+ if (ieee80211_is_beacon(hdr->frame_control)) {
+ __set_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
/* H/W will generate sequence number */
return;
+ }
+
+ __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
}
/*
};
MODULE_DEVICE_TABLE(spi, st95hf_id);
+static const struct of_device_id st95hf_spi_of_match[] = {
+ { .compatible = "st,st95hf" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, st95hf_spi_of_match);
+
static int st95hf_probe(struct spi_device *nfc_spi_dev)
{
int ret;
.driver = {
.name = "st95hf",
.owner = THIS_MODULE,
+ .of_match_table = of_match_ptr(st95hf_spi_of_match),
},
.id_table = st95hf_id,
.probe = st95hf_probe,
return NULL;
nd_btt->id = ida_simple_get(&nd_region->btt_ida, 0, 0, GFP_KERNEL);
- if (nd_btt->id < 0) {
- kfree(nd_btt);
- return NULL;
- }
+ if (nd_btt->id < 0)
+ goto out_nd_btt;
nd_btt->lbasize = lbasize;
- if (uuid)
+ if (uuid) {
uuid = kmemdup(uuid, 16, GFP_KERNEL);
+ if (!uuid)
+ goto out_put_id;
+ }
nd_btt->uuid = uuid;
dev = &nd_btt->dev;
dev_set_name(dev, "btt%d.%d", nd_region->id, nd_btt->id);
return NULL;
}
return dev;
+
+out_put_id:
+ ida_simple_remove(&nd_region->btt_ida, nd_btt->id);
+
+out_nd_btt:
+ kfree(nd_btt);
+ return NULL;
}
struct device *nd_btt_create(struct nd_region *nd_region)
if (!nsblk->uuid)
goto blk_err;
memcpy(name, nd_label->name, NSLABEL_NAME_LEN);
- if (name[0])
+ if (name[0]) {
nsblk->alt_name = kmemdup(name, NSLABEL_NAME_LEN,
GFP_KERNEL);
+ if (!nsblk->alt_name)
+ goto blk_err;
+ }
res = nsblk_add_resource(nd_region, ndd, nsblk,
__le64_to_cpu(nd_label->dpa));
if (!res)
while (len) {
mem = kmap_atomic(page);
- chunk = min_t(unsigned int, len, PAGE_SIZE);
+ chunk = min_t(unsigned int, len, PAGE_SIZE - off);
memcpy_flushcache(pmem_addr, mem + off, chunk);
kunmap_atomic(mem);
len -= chunk;
off = 0;
page++;
- pmem_addr += PAGE_SIZE;
+ pmem_addr += chunk;
}
}
while (len) {
mem = kmap_atomic(page);
- chunk = min_t(unsigned int, len, PAGE_SIZE);
+ chunk = min_t(unsigned int, len, PAGE_SIZE - off);
rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
kunmap_atomic(mem);
if (rem)
len -= chunk;
off = 0;
page++;
- pmem_addr += PAGE_SIZE;
+ pmem_addr += chunk;
}
return BLK_STS_OK;
}
module_param(key_revalidate, bool, 0444);
MODULE_PARM_DESC(key_revalidate, "Require key validation at init.");
+static const char zero_key[NVDIMM_PASSPHRASE_LEN];
+
static void *key_data(struct key *key)
{
struct encrypted_key_payload *epayload = dereference_key_locked(key);
return key;
}
+static const void *nvdimm_get_key_payload(struct nvdimm *nvdimm,
+ struct key **key)
+{
+ *key = nvdimm_request_key(nvdimm);
+ if (!*key)
+ return zero_key;
+
+ return key_data(*key);
+}
+
static struct key *nvdimm_lookup_user_key(struct nvdimm *nvdimm,
key_serial_t id, int subclass)
{
return key;
}
-static struct key *nvdimm_key_revalidate(struct nvdimm *nvdimm)
+static const void *nvdimm_get_user_key_payload(struct nvdimm *nvdimm,
+ key_serial_t id, int subclass, struct key **key)
+{
+ *key = NULL;
+ if (id == 0) {
+ if (subclass == NVDIMM_BASE_KEY)
+ return zero_key;
+ else
+ return NULL;
+ }
+
+ *key = nvdimm_lookup_user_key(nvdimm, id, subclass);
+ if (!*key)
+ return NULL;
+
+ return key_data(*key);
+}
+
+
+static int nvdimm_key_revalidate(struct nvdimm *nvdimm)
{
struct key *key;
int rc;
+ const void *data;
if (!nvdimm->sec.ops->change_key)
- return NULL;
+ return -EOPNOTSUPP;
- key = nvdimm_request_key(nvdimm);
- if (!key)
- return NULL;
+ data = nvdimm_get_key_payload(nvdimm, &key);
/*
* Send the same key to the hardware as new and old key to
* verify that the key is good.
*/
- rc = nvdimm->sec.ops->change_key(nvdimm, key_data(key),
- key_data(key), NVDIMM_USER);
+ rc = nvdimm->sec.ops->change_key(nvdimm, data, data, NVDIMM_USER);
if (rc < 0) {
nvdimm_put_key(key);
- key = NULL;
+ return rc;
}
- return key;
+
+ nvdimm_put_key(key);
+ nvdimm->sec.state = nvdimm_security_state(nvdimm, NVDIMM_USER);
+ return 0;
}
static int __nvdimm_security_unlock(struct nvdimm *nvdimm)
{
struct device *dev = &nvdimm->dev;
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
- struct key *key = NULL;
+ struct key *key;
+ const void *data;
int rc;
/* The bus lock should be held at the top level of the call stack */
if (!key_revalidate)
return 0;
- key = nvdimm_key_revalidate(nvdimm);
- if (!key)
- return nvdimm_security_freeze(nvdimm);
+ return nvdimm_key_revalidate(nvdimm);
} else
- key = nvdimm_request_key(nvdimm);
+ data = nvdimm_get_key_payload(nvdimm, &key);
- if (!key)
- return -ENOKEY;
-
- rc = nvdimm->sec.ops->unlock(nvdimm, key_data(key));
+ rc = nvdimm->sec.ops->unlock(nvdimm, data);
dev_dbg(dev, "key: %d unlock: %s\n", key_serial(key),
rc == 0 ? "success" : "fail");
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
struct key *key;
int rc;
+ const void *data;
/* The bus lock should be held at the top level of the call stack */
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
return -EBUSY;
}
- key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
- if (!key)
+ data = nvdimm_get_user_key_payload(nvdimm, keyid,
+ NVDIMM_BASE_KEY, &key);
+ if (!data)
return -ENOKEY;
- rc = nvdimm->sec.ops->disable(nvdimm, key_data(key));
+ rc = nvdimm->sec.ops->disable(nvdimm, data);
dev_dbg(dev, "key: %d disable: %s\n", key_serial(key),
rc == 0 ? "success" : "fail");
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
struct key *key, *newkey;
int rc;
+ const void *data, *newdata;
/* The bus lock should be held at the top level of the call stack */
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
return -EIO;
}
- if (keyid == 0)
- key = NULL;
- else {
- key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
- if (!key)
- return -ENOKEY;
- }
+ data = nvdimm_get_user_key_payload(nvdimm, keyid,
+ NVDIMM_BASE_KEY, &key);
+ if (!data)
+ return -ENOKEY;
- newkey = nvdimm_lookup_user_key(nvdimm, new_keyid, NVDIMM_NEW_KEY);
- if (!newkey) {
+ newdata = nvdimm_get_user_key_payload(nvdimm, new_keyid,
+ NVDIMM_NEW_KEY, &newkey);
+ if (!newdata) {
nvdimm_put_key(key);
return -ENOKEY;
}
- rc = nvdimm->sec.ops->change_key(nvdimm, key ? key_data(key) : NULL,
- key_data(newkey), pass_type);
+ rc = nvdimm->sec.ops->change_key(nvdimm, data, newdata, pass_type);
dev_dbg(dev, "key: %d %d update%s: %s\n",
key_serial(key), key_serial(newkey),
pass_type == NVDIMM_MASTER ? "(master)" : "(user)",
{
struct device *dev = &nvdimm->dev;
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
- struct key *key;
+ struct key *key = NULL;
int rc;
+ const void *data;
/* The bus lock should be held at the top level of the call stack */
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
return -EOPNOTSUPP;
}
- key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
- if (!key)
+ data = nvdimm_get_user_key_payload(nvdimm, keyid,
+ NVDIMM_BASE_KEY, &key);
+ if (!data)
return -ENOKEY;
- rc = nvdimm->sec.ops->erase(nvdimm, key_data(key), pass_type);
+ rc = nvdimm->sec.ops->erase(nvdimm, data, pass_type);
dev_dbg(dev, "key: %d erase%s: %s\n", key_serial(key),
pass_type == NVDIMM_MASTER ? "(master)" : "(user)",
rc == 0 ? "success" : "fail");
{
struct device *dev = &nvdimm->dev;
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
- struct key *key;
+ struct key *key = NULL;
int rc;
+ const void *data;
/* The bus lock should be held at the top level of the call stack */
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
return -EBUSY;
}
- if (keyid == 0)
- key = NULL;
- else {
- key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
- if (!key)
- return -ENOKEY;
- }
+ data = nvdimm_get_user_key_payload(nvdimm, keyid,
+ NVDIMM_BASE_KEY, &key);
+ if (!data)
+ return -ENOKEY;
- rc = nvdimm->sec.ops->overwrite(nvdimm, key ? key_data(key) : NULL);
+ rc = nvdimm->sec.ops->overwrite(nvdimm, data);
dev_dbg(dev, "key: %d overwrite submission: %s\n", key_serial(key),
rc == 0 ? "success" : "fail");
nvme_mpath_remove_disk(head);
ida_simple_remove(&head->subsys->ns_ida, head->instance);
list_del_init(&head->entry);
- cleanup_srcu_struct_quiesced(&head->srcu);
+ cleanup_srcu_struct(&head->srcu);
nvme_put_subsystem(head->subsys);
kfree(head);
}
*/
#include <linux/etherdevice.h>
#include <linux/kernel.h>
-#include <linux/nvmem-consumer.h>
#include <linux/of_net.h>
#include <linux/phy.h>
#include <linux/export.h>
config VMD
depends on PCI_MSI && X86_64 && SRCU
+ select X86_DEV_DMA_OPS
tristate "Intel Volume Management Device Driver"
---help---
Adds support for the Intel Volume Management Device (VMD). VMD is a
struct irq_domain *irq_domain;
struct pci_bus *bus;
-#ifdef CONFIG_X86_DEV_DMA_OPS
struct dma_map_ops dma_ops;
struct dma_domain dma_domain;
-#endif
};
static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
.chip = &vmd_msi_controller,
};
-#ifdef CONFIG_X86_DEV_DMA_OPS
/*
* VMD replaces the requester ID with its own. DMA mappings for devices in a
* VMD domain need to be mapped for the VMD, not the device requiring
add_dma_domain(domain);
}
#undef ASSIGN_VMD_DMA_OPS
-#else
-static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {}
-static void vmd_setup_dma_ops(struct vmd_dev *vmd) {}
-#endif
static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus,
unsigned int devfn, int reg, int len)
} else if (!strncmp(str, "pcie_scan_all", 13)) {
pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
} else if (!strncmp(str, "disable_acs_redir=", 18)) {
- disable_acs_redir_param =
- kstrdup(str + 18, GFP_KERNEL);
+ disable_acs_redir_param = str + 18;
} else {
printk(KERN_ERR "PCI: Unknown option `%s'\n",
str);
return 0;
}
early_param("pci", pci_setup);
+
+/*
+ * 'disable_acs_redir_param' is initialized in pci_setup(), above, to point
+ * to data in the __initdata section which will be freed after the init
+ * sequence is complete. We can't allocate memory in pci_setup() because some
+ * architectures do not have any memory allocation service available during
+ * an early_param() call. So we allocate memory and copy the variable here
+ * before the init section is freed.
+ */
+static int __init pci_realloc_setup_params(void)
+{
+ disable_acs_redir_param = kstrdup(disable_acs_redir_param, GFP_KERNEL);
+
+ return 0;
+}
+pure_initcall(pci_realloc_setup_params);
This is only useful if you have devices that support PTM, but it
is safe to enable even if you don't.
+
+config PCIE_BW
+ bool "PCI Express Bandwidth Change Notification"
+ depends on PCIEPORTBUS
+ help
+ This enables PCI Express Bandwidth Change Notification. If
+ you know link width or rate changes occur only to correct
+ unreliable links, you may answer Y.
# Makefile for PCI Express features and port driver
pcieportdrv-y := portdrv_core.o portdrv_pci.o err.o
-pcieportdrv-y += bw_notification.o
obj-$(CONFIG_PCIEPORTBUS) += pcieportdrv.o
obj-$(CONFIG_PCIE_PME) += pme.o
obj-$(CONFIG_PCIE_DPC) += dpc.o
obj-$(CONFIG_PCIE_PTM) += ptm.o
+obj-$(CONFIG_PCIE_BW) += bw_notification.o
static inline int pcie_dpc_init(void) { return 0; }
#endif
+#ifdef CONFIG_PCIE_BW
int pcie_bandwidth_notification_init(void);
+#else
+static inline int pcie_bandwidth_notification_init(void) { return 0; }
+#endif
/* Port Type */
#define PCIE_ANY_PORT (~0)
* 7.8.2, 7.10.10, 7.31.2.
*/
- if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP)) {
+ if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP |
+ PCIE_PORT_SERVICE_BWNOTIF)) {
pcie_capability_read_word(dev, PCI_EXP_FLAGS, ®16);
*pme = (reg16 & PCI_EXP_FLAGS_IRQ) >> 9;
nvec = *pme + 1;
int avg_current;
u32 cc_lsb;
+ if (!divider)
+ return 0;
+
sample &= 0xffffff; /* 24-bits, unsigned */
offset &= 0x7ff; /* 10-bits, signed */
-// SPDX-License-Identifier: GPL
+// SPDX-License-Identifier: GPL-2.0
/*
* Power supply driver for the goldfish emulator
*
char *prop_buf;
char *attrname;
- dev_dbg(dev, "uevent\n");
-
if (!psy || !psy->desc) {
dev_dbg(dev, "No power supply yet\n");
return ret;
}
- dev_dbg(dev, "POWER_SUPPLY_NAME=%s\n", psy->desc->name);
-
ret = add_uevent_var(env, "POWER_SUPPLY_NAME=%s", psy->desc->name);
if (ret)
return ret;
goto out;
}
- dev_dbg(dev, "prop %s=%s\n", attrname, prop_buf);
-
ret = add_uevent_var(env, "POWER_SUPPLY_%s=%s", attrname, prop_buf);
kfree(attrname);
if (ret)
blk_per_trk = recs_per_track(&private->rdc_data, 0, block->bp_block);
raw:
- block->blocks = (private->real_cyl *
+ block->blocks = ((unsigned long) private->real_cyl *
private->rdc_data.trk_per_cyl *
blk_per_trk);
dev_info(&device->cdev->dev,
- "DASD with %d KB/block, %d KB total size, %d KB/track, "
+ "DASD with %u KB/block, %lu KB total size, %u KB/track, "
"%s\n", (block->bp_block >> 10),
- ((private->real_cyl *
+ (((unsigned long) private->real_cyl *
private->rdc_data.trk_per_cyl *
blk_per_trk * (block->bp_block >> 9)) >> 1),
((blk_per_trk * block->bp_block) >> 10),
(void (*)(unsigned long)) con3270_read_tasklet,
(unsigned long) condev->read);
- raw3270_add_view(&condev->view, &con3270_fn, 1);
+ raw3270_add_view(&condev->view, &con3270_fn, 1, RAW3270_VIEW_LOCK_IRQ);
INIT_LIST_HEAD(&condev->freemem);
for (i = 0; i < CON3270_STRING_PAGES; i++) {
init_waitqueue_head(&fp->wait);
fp->fs_pid = get_pid(task_pid(current));
- rc = raw3270_add_view(&fp->view, &fs3270_fn, minor);
+ rc = raw3270_add_view(&fp->view, &fs3270_fn, minor,
+ RAW3270_VIEW_LOCK_BH);
if (rc) {
fs3270_free_view(&fp->view);
goto out;
* Add view to device with minor "minor".
*/
int
-raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor)
+raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor, int subclass)
{
unsigned long flags;
struct raw3270 *rp;
view->cols = rp->cols;
view->ascebc = rp->ascebc;
spin_lock_init(&view->lock);
+ lockdep_set_subclass(&view->lock, subclass);
list_add(&view->list, &rp->view_list);
rc = 0;
spin_unlock_irqrestore(get_ccwdev_lock(rp->cdev), flags);
struct raw3270_view {
struct list_head list;
spinlock_t lock;
+#define RAW3270_VIEW_LOCK_IRQ 0
+#define RAW3270_VIEW_LOCK_BH 1
atomic_t ref_count;
struct raw3270 *dev;
struct raw3270_fn *fn;
unsigned char *ascebc; /* ascii -> ebcdic table */
};
-int raw3270_add_view(struct raw3270_view *, struct raw3270_fn *, int);
+int raw3270_add_view(struct raw3270_view *, struct raw3270_fn *, int, int);
int raw3270_activate_view(struct raw3270_view *);
void raw3270_del_view(struct raw3270_view *);
void raw3270_deactivate_view(struct raw3270_view *);
return PTR_ERR(tp);
rc = raw3270_add_view(&tp->view, &tty3270_fn,
- tty->index + RAW3270_FIRSTMINOR);
+ tty->index + RAW3270_FIRSTMINOR,
+ RAW3270_VIEW_LOCK_BH);
if (rc) {
tty3270_free_view(tp);
return rc;
__ap_flush_queue(aq);
/* set REMOVE state to prevent new messages are queued in */
aq->state = AP_STATE_REMOVE;
- del_timer_sync(&aq->timeout);
spin_unlock_bh(&aq->lock);
+ del_timer_sync(&aq->timeout);
}
void ap_queue_remove(struct ap_queue *aq)
static void __init pkey_debug_init(void)
{
- debug_info = debug_register("pkey", 1, 1, 4 * sizeof(long));
+ /* 5 arguments per dbf entry (including the format string ptr) */
+ debug_info = debug_register("pkey", 1, 1, 5 * sizeof(long));
debug_register_view(debug_info, &debug_sprintf_view);
debug_set_level(debug_info, 3);
}
if (priv->channel[direction] == NULL) {
if (direction == CTCM_WRITE)
channel_free(priv->channel[CTCM_READ]);
+ result = -ENODEV;
goto out_dev;
}
priv->channel[direction]->netdev = dev;
ahc = ahc_alloc(&aic7xxx_driver_template, name);
if (ahc == NULL)
return (ENOMEM);
+ ahc->dev = dev;
error = aic7770_config(ahc, aic7770_ident_table + edev->id.driver_data,
eisaBase);
if (error != 0) {
* Platform specific device information.
*/
ahc_dev_softc_t dev_softc;
+ struct device *dev;
/*
* Bus specific device information.
ahc_dmamem_alloc(struct ahc_softc *ahc, bus_dma_tag_t dmat, void** vaddr,
int flags, bus_dmamap_t *mapp)
{
- *vaddr = pci_alloc_consistent(ahc->dev_softc,
- dmat->maxsize, mapp);
+ /* XXX: check if we really need the GFP_ATOMIC and unwind this mess! */
+ *vaddr = dma_alloc_coherent(ahc->dev, dmat->maxsize, mapp, GFP_ATOMIC);
if (*vaddr == NULL)
return ENOMEM;
return 0;
ahc_dmamem_free(struct ahc_softc *ahc, bus_dma_tag_t dmat,
void* vaddr, bus_dmamap_t map)
{
- pci_free_consistent(ahc->dev_softc, dmat->maxsize,
- vaddr, map);
+ dma_free_coherent(ahc->dev, dmat->maxsize, vaddr, map);
}
int
host->transportt = ahc_linux_transport_template;
- retval = scsi_add_host(host,
- (ahc->dev_softc ? &ahc->dev_softc->dev : NULL));
+ retval = scsi_add_host(host, ahc->dev);
if (retval) {
printk(KERN_WARNING "aic7xxx: scsi_add_host failed\n");
scsi_host_put(host);
}
}
ahc->dev_softc = pci;
+ ahc->dev = &pci->dev;
error = ahc_pci_config(ahc, entry);
if (error != 0) {
ahc_free(ahc);
FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n",
fc_rport_state(rdata));
- rdata->flags &= ~FC_RP_STARTED;
fc_rport_enter_delete(rdata, RPORT_EV_STOP);
mutex_unlock(&rdata->rp_mutex);
kref_put(&rdata->kref, fc_rport_destroy);
ret = BLK_STS_DEV_RESOURCE;
break;
default:
+ if (unlikely(!scsi_device_online(sdev)))
+ scsi_req(req)->result = DID_NO_CONNECT << 16;
+ else
+ scsi_req(req)->result = DID_ERROR << 16;
/*
- * Make sure to release all allocated ressources when
+ * Make sure to release all allocated resources when
* we hit an error, as we will never see this command
* again.
*/
size = usb_endpoint_maxp(devpriv->ep_tx);
devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL);
- if (!devpriv->usb_tx_buf) {
- kfree(devpriv->usb_rx_buf);
+ if (!devpriv->usb_tx_buf)
return -ENOMEM;
- }
return 0;
}
if (!devpriv)
return -ENOMEM;
+ mutex_init(&devpriv->mut);
+ usb_set_intfdata(intf, devpriv);
+
ret = ni6501_find_endpoints(dev);
if (ret)
return ret;
if (ret)
return ret;
- mutex_init(&devpriv->mut);
- usb_set_intfdata(intf, devpriv);
-
ret = comedi_alloc_subdevices(dev, 2);
if (ret)
return ret;
size = usb_endpoint_maxp(devpriv->ep_tx);
devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL);
- if (!devpriv->usb_tx_buf) {
- kfree(devpriv->usb_rx_buf);
+ if (!devpriv->usb_tx_buf)
return -ENOMEM;
- }
return 0;
}
devpriv->model = board->model;
+ sema_init(&devpriv->limit_sem, 8);
+
ret = vmk80xx_find_usb_endpoints(dev);
if (ret)
return ret;
if (ret)
return ret;
- sema_init(&devpriv->limit_sem, 8);
-
usb_set_intfdata(intf, devpriv);
if (devpriv->model == VMK8055_MODEL)
*last_block = current_block;
/* shift in advance in case of it followed by too many gaps */
- if (unlikely(bio->bi_vcnt >= bio->bi_max_vecs)) {
+ if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
/* err should reassign to 0 after submitting */
err = 0;
goto submit_bio_out;
#define AD7192_CH_AIN3 BIT(6) /* AIN3 - AINCOM */
#define AD7192_CH_AIN4 BIT(7) /* AIN4 - AINCOM */
-#define AD7193_CH_AIN1P_AIN2M 0x000 /* AIN1(+) - AIN2(-) */
-#define AD7193_CH_AIN3P_AIN4M 0x001 /* AIN3(+) - AIN4(-) */
-#define AD7193_CH_AIN5P_AIN6M 0x002 /* AIN5(+) - AIN6(-) */
-#define AD7193_CH_AIN7P_AIN8M 0x004 /* AIN7(+) - AIN8(-) */
+#define AD7193_CH_AIN1P_AIN2M 0x001 /* AIN1(+) - AIN2(-) */
+#define AD7193_CH_AIN3P_AIN4M 0x002 /* AIN3(+) - AIN4(-) */
+#define AD7193_CH_AIN5P_AIN6M 0x004 /* AIN5(+) - AIN6(-) */
+#define AD7193_CH_AIN7P_AIN8M 0x008 /* AIN7(+) - AIN8(-) */
#define AD7193_CH_TEMP 0x100 /* Temp senseor */
#define AD7193_CH_AIN2P_AIN2M 0x200 /* AIN2(+) - AIN2(-) */
#define AD7193_CH_AIN1 0x401 /* AIN1 - AINCOM */
static IIO_DEV_ATTR_IPEAK(0644,
ade7854_read_32bit,
ade7854_write_32bit,
- ADE7854_VPEAK);
+ ADE7854_IPEAK);
static IIO_DEV_ATTR_APHCAL(0644,
ade7854_read_16bit,
ade7854_write_16bit,
INIT_LIST_HEAD(&iface->p->channel_list);
iface->p->dev_id = id;
- snprintf(iface->p->name, STRING_SIZE, "mdev%d", id);
+ strcpy(iface->p->name, iface->description);
iface->dev.init_name = iface->p->name;
iface->dev.bus = &mc.bus;
iface->dev.parent = &mc.dev;
module_param_array(pc104_4, ulong, NULL, 0);
MODULE_PARM_DESC(pc104_4, "set interface types for ISA(PC104) board #4 (e.g. pc104_4=232,232,485,485,...");
-static int rp_init(void);
+static int __init rp_init(void);
static void rp_cleanup_module(void);
module_init(rp_init);
#endif
return ret;
+#ifdef CONFIG_SERIAL_SC16IS7XX_SPI
err_spi:
+#endif
#ifdef CONFIG_SERIAL_SC16IS7XX_I2C
i2c_del_driver(&sc16is7xx_i2c_uart_driver);
-#endif
err_i2c:
+#endif
uart_unregister_driver(&sc16is7xx_uart);
return ret;
}
* center of the last stop bit in sampling clocks.
*/
int last_stop = bits * 2 - 1;
- int deviation = min_err * srr * last_stop / 2 / baud;
+ int deviation = DIV_ROUND_CLOSEST(min_err * last_stop *
+ (int)(srr + 1),
+ 2 * (int)baud);
if (abs(deviation) >= 2) {
/* At least two sampling clocks off at the
* last stop bit; we can increase the error
* margin by shifting the sampling point.
*/
- int shift = min(-8, max(7, deviation / 2));
+ int shift = clamp(deviation / 2, -8, 7);
hssrr |= (shift << HSCIF_SRHP_SHIFT) &
HSCIF_SRHP_MASK;
return;
}
scr_memsetw(start, vc->vc_video_erase_char, 2 * count);
- update_region(vc, (unsigned long) start, count);
+ if (con_should_update(vc))
+ do_update_region(vc, (unsigned long) start, count);
vc->vc_need_wrap = 0;
}
pm_runtime_disable(dev);
pm_runtime_set_suspended(dev);
- /* Undo any residual pm_autopm_get_interface_* calls */
- for (r = atomic_read(&intf->pm_usage_cnt); r > 0; --r)
- usb_autopm_put_interface_no_suspend(intf);
- atomic_set(&intf->pm_usage_cnt, 0);
-
if (!error)
usb_autosuspend_device(udev);
int status;
usb_mark_last_busy(udev);
- atomic_dec(&intf->pm_usage_cnt);
status = pm_runtime_put_sync(&intf->dev);
dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
__func__, atomic_read(&intf->dev.power.usage_count),
int status;
usb_mark_last_busy(udev);
- atomic_dec(&intf->pm_usage_cnt);
status = pm_runtime_put(&intf->dev);
dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
__func__, atomic_read(&intf->dev.power.usage_count),
struct usb_device *udev = interface_to_usbdev(intf);
usb_mark_last_busy(udev);
- atomic_dec(&intf->pm_usage_cnt);
pm_runtime_put_noidle(&intf->dev);
}
EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend);
status = pm_runtime_get_sync(&intf->dev);
if (status < 0)
pm_runtime_put_sync(&intf->dev);
- else
- atomic_inc(&intf->pm_usage_cnt);
dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
__func__, atomic_read(&intf->dev.power.usage_count),
status);
status = pm_runtime_get(&intf->dev);
if (status < 0 && status != -EINPROGRESS)
pm_runtime_put_noidle(&intf->dev);
- else
- atomic_inc(&intf->pm_usage_cnt);
dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
__func__, atomic_read(&intf->dev.power.usage_count),
status);
struct usb_device *udev = interface_to_usbdev(intf);
usb_mark_last_busy(udev);
- atomic_inc(&intf->pm_usage_cnt);
pm_runtime_get_noresume(&intf->dev);
}
EXPORT_SYMBOL_GPL(usb_autopm_get_interface_no_resume);
if (dev->state == USB_STATE_SUSPENDED)
return -EHOSTUNREACH;
- if (size <= 0 || !buf || !index)
+ if (size <= 0 || !buf)
return -EINVAL;
buf[0] = 0;
+ if (index <= 0 || index >= 256)
+ return -EINVAL;
tbuf = kmalloc(256, GFP_NOIO);
if (!tbuf)
return -ENOMEM;
struct dummy_hcd *dum_hcd = gadget_to_dummy_hcd(g);
struct dummy *dum = dum_hcd->dum;
- if (driver->max_speed == USB_SPEED_UNKNOWN)
+ switch (g->speed) {
+ /* All the speeds we support */
+ case USB_SPEED_LOW:
+ case USB_SPEED_FULL:
+ case USB_SPEED_HIGH:
+ case USB_SPEED_SUPER:
+ break;
+ default:
+ dev_err(dummy_dev(dum_hcd), "Unsupported driver max speed %d\n",
+ driver->max_speed);
return -EINVAL;
+ }
/*
* SLAVE side init ... the layer above hardware, which
/* Bus speed is 500000 bytes/ms, so use a little less */
total = 490000;
break;
- default:
+ default: /* Can't happen */
dev_err(dummy_dev(dum_hcd), "bogus device speed\n");
- return;
+ total = 0;
+ break;
}
/* FIXME if HZ != 1000 this will probably misbehave ... */
/* Used up this frame's bandwidth? */
if (total <= 0)
- break;
+ continue;
/* find the gadget's ep for this request (if configured) */
address = usb_pipeendpoint (urb->pipe);
usb_deregister_dev(interface, &yurex_class);
/* prevent more I/O from starting */
+ usb_poison_urb(dev->urb);
mutex_lock(&dev->io_mutex);
dev->interface = NULL;
mutex_unlock(&dev->io_mutex);
break;
case RTS51X_STAT_IDLE:
case RTS51X_STAT_SS:
- usb_stor_dbg(us, "RTS51X_STAT_SS, intf->pm_usage_cnt:%d, power.usage:%d\n",
- atomic_read(&us->pusb_intf->pm_usage_cnt),
+ usb_stor_dbg(us, "RTS51X_STAT_SS, power.usage:%d\n",
atomic_read(&us->pusb_intf->dev.power.usage_count));
- if (atomic_read(&us->pusb_intf->pm_usage_cnt) > 0) {
+ if (atomic_read(&us->pusb_intf->dev.power.usage_count) > 0) {
usb_stor_dbg(us, "Ready to enter SS state\n");
rts51x_set_stat(chip, RTS51X_STAT_SS);
/* ignore mass storage interface's children */
pm_suspend_ignore_children(&us->pusb_intf->dev, true);
usb_autopm_put_interface_async(us->pusb_intf);
- usb_stor_dbg(us, "RTS51X_STAT_SS 01, intf->pm_usage_cnt:%d, power.usage:%d\n",
- atomic_read(&us->pusb_intf->pm_usage_cnt),
+ usb_stor_dbg(us, "RTS51X_STAT_SS 01, power.usage:%d\n",
atomic_read(&us->pusb_intf->dev.power.usage_count));
}
break;
int ret;
if (working_scsi(srb)) {
- usb_stor_dbg(us, "working scsi, intf->pm_usage_cnt:%d, power.usage:%d\n",
- atomic_read(&us->pusb_intf->pm_usage_cnt),
+ usb_stor_dbg(us, "working scsi, power.usage:%d\n",
atomic_read(&us->pusb_intf->dev.power.usage_count));
- if (atomic_read(&us->pusb_intf->pm_usage_cnt) <= 0) {
+ if (atomic_read(&us->pusb_intf->dev.power.usage_count) <= 0) {
ret = usb_autopm_get_interface(us->pusb_intf);
usb_stor_dbg(us, "working scsi, ret=%d\n", ret);
}
}
if (usb_endpoint_xfer_isoc(epd)) {
- /* validate packet size and number of packets */
- unsigned int maxp, packets, bytes;
-
- maxp = usb_endpoint_maxp(epd);
- maxp *= usb_endpoint_maxp_mult(epd);
- bytes = pdu->u.cmd_submit.transfer_buffer_length;
- packets = DIV_ROUND_UP(bytes, maxp);
-
+ /* validate number of packets */
if (pdu->u.cmd_submit.number_of_packets < 0 ||
- pdu->u.cmd_submit.number_of_packets > packets) {
+ pdu->u.cmd_submit.number_of_packets >
+ USBIP_MAX_ISO_PACKETS) {
dev_err(&sdev->udev->dev,
"CMD_SUBMIT: isoc invalid num packets %d\n",
pdu->u.cmd_submit.number_of_packets);
#define USBIP_DIR_OUT 0x00
#define USBIP_DIR_IN 0x01
+/*
+ * Arbitrary limit for the maximum number of isochronous packets in an URB,
+ * compare for example the uhci_submit_isochronous function in
+ * drivers/usb/host/uhci-q.c
+ */
+#define USBIP_MAX_ISO_PACKETS 1024
+
/**
* struct usbip_header_basic - data pertinent to every request
* @command: the usbip request type
u64 start, u64 size, u64 end,
u64 userspace_addr, int perm)
{
- struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC);
+ struct vhost_umem_node *tmp, *node;
+ if (!size)
+ return -EFAULT;
+
+ node = kmalloc(sizeof(*node), GFP_ATOMIC);
if (!node)
return -ENOMEM;
info->apertures->ranges[0].base = efifb_fix.smem_start;
info->apertures->ranges[0].size = size_remap;
- if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
+ if (efi_enabled(EFI_BOOT) &&
+ !efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
if ((efifb_fix.smem_start + efifb_fix.smem_len) >
(md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) {
pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n",
/* alternative 3, 1ms interrupt (greatly speeds search), 64 byte bulk */
alt = 3;
err = usb_set_interface(dev->udev,
- intf->altsetting[alt].desc.bInterfaceNumber, alt);
+ intf->cur_altsetting->desc.bInterfaceNumber, alt);
if (err) {
dev_err(&dev->udev->dev, "Failed to set alternative setting %d "
"for %d interface: err=%d.\n", alt,
- intf->altsetting[alt].desc.bInterfaceNumber, err);
+ intf->cur_altsetting->desc.bInterfaceNumber, err);
goto err_out_clear;
}
- iface_desc = &intf->altsetting[alt];
+ iface_desc = intf->cur_altsetting;
if (iface_desc->desc.bNumEndpoints != NUM_EP-1) {
pr_info("Num endpoints=%d. It is not DS9490R.\n",
iface_desc->desc.bNumEndpoints);
*/
void afs_init_callback_state(struct afs_server *server)
{
- if (!test_and_clear_bit(AFS_SERVER_FL_NEW, &server->flags))
- server->cb_s_break++;
+ server->cb_s_break++;
}
/*
static int afs_deliver_yfs_cb_callback(struct afs_call *);
#define CM_NAME(name) \
- const char afs_SRXCB##name##_name[] __tracepoint_string = \
+ char afs_SRXCB##name##_name[] __tracepoint_string = \
"CB." #name
/*
set_nlink(inode, 2);
inode->i_uid = GLOBAL_ROOT_UID;
inode->i_gid = GLOBAL_ROOT_GID;
- inode->i_ctime.tv_sec = get_seconds();
- inode->i_ctime.tv_nsec = 0;
- inode->i_atime = inode->i_mtime = inode->i_ctime;
+ inode->i_ctime = inode->i_atime = inode->i_mtime = current_time(inode);
inode->i_blocks = 0;
inode_set_iversion_raw(inode, 0);
inode->i_generation = 0;
time64_t put_time; /* Time at which last put */
time64_t update_at; /* Time at which to next update the record */
unsigned long flags;
-#define AFS_SERVER_FL_NEW 0 /* New server, don't inc cb_s_break */
#define AFS_SERVER_FL_NOT_READY 1 /* The record is not ready for use */
#define AFS_SERVER_FL_NOT_FOUND 2 /* VL server says no such server */
#define AFS_SERVER_FL_VL_FAIL 3 /* Failed to access VL server */
static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
{
- return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break;
+ return vnode->cb_break + vnode->cb_v_break;
}
static inline bool afs_cb_is_broken(unsigned int cb_break,
const struct afs_cb_interest *cbi)
{
return !cbi || cb_break != (vnode->cb_break +
- cbi->server->cb_s_break +
vnode->volume->cb_v_break);
}
case -ENODATA:
case -EBADMSG:
case -EMSGSIZE:
- default:
abort_code = RXGEN_CC_UNMARSHAL;
if (state != AFS_CALL_CL_AWAIT_REPLY)
abort_code = RXGEN_SS_UNMARSHAL;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
abort_code, ret, "KUM");
goto local_abort;
+ default:
+ abort_code = RX_USER_ABORT;
+ rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+ abort_code, ret, "KER");
+ goto local_abort;
}
}
bool stalled = false;
u64 rtt;
u32 life, last_life;
+ bool rxrpc_complete = false;
DECLARE_WAITQUEUE(myself, current);
rtt2 = 2;
timeout = rtt2;
- last_life = rxrpc_kernel_check_life(call->net->socket, call->rxcall);
+ rxrpc_kernel_check_life(call->net->socket, call->rxcall, &last_life);
add_wait_queue(&call->waitq, &myself);
for (;;) {
if (afs_check_call_state(call, AFS_CALL_COMPLETE))
break;
- life = rxrpc_kernel_check_life(call->net->socket, call->rxcall);
+ if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall, &life)) {
+ /* rxrpc terminated the call. */
+ rxrpc_complete = true;
+ break;
+ }
+
if (timeout == 0 &&
life == last_life && signal_pending(current)) {
if (stalled)
remove_wait_queue(&call->waitq, &myself);
__set_current_state(TASK_RUNNING);
- /* Kill off the call if it's still live. */
if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) {
- _debug("call interrupted");
- if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- RX_USER_ABORT, -EINTR, "KWI"))
- afs_set_call_complete(call, -EINTR, 0);
+ if (rxrpc_complete) {
+ afs_set_call_complete(call, call->error, call->abort_code);
+ } else {
+ /* Kill off the call if it's still live. */
+ _debug("call interrupted");
+ if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+ RX_USER_ABORT, -EINTR, "KWI"))
+ afs_set_call_complete(call, -EINTR, 0);
+ }
}
spin_lock_bh(&call->state_lock);
RCU_INIT_POINTER(server->addresses, alist);
server->addr_version = alist->version;
server->uuid = *uuid;
- server->flags = (1UL << AFS_SERVER_FL_NEW);
server->update_at = ktime_get_real_seconds() + afs_server_update_delay;
rwlock_init(&server->fs_lock);
INIT_HLIST_HEAD(&server->cb_volumes);
first = page->index + 1;
lock_page(page);
generic_error_remove_page(mapping, page);
+ unlock_page(page);
}
__pagevec_release(&pv);
bio_for_each_segment_all(bvec, &bio, i, iter_all) {
if (should_dirty && !PageCompound(bvec->bv_page))
set_page_dirty_lock(bvec->bv_page);
- put_page(bvec->bv_page);
+ if (!bio_flagged(&bio, BIO_NO_PAGE_REF))
+ put_page(bvec->bv_page);
}
if (unlikely(bio.bi_status))
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
+#include <linux/sched/mm.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
unsigned long this_sum_bytes = 0;
int i;
u64 offset;
+ unsigned nofs_flag;
+
+ nofs_flag = memalloc_nofs_save();
+ sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
+ GFP_KERNEL);
+ memalloc_nofs_restore(nofs_flag);
- sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
- GFP_NOFS);
if (!sums)
return BLK_STS_RESOURCE;
bytes_left = bio->bi_iter.bi_size - total_bytes;
- sums = kzalloc(btrfs_ordered_sum_size(fs_info, bytes_left),
- GFP_NOFS);
+ nofs_flag = memalloc_nofs_save();
+ sums = kvzalloc(btrfs_ordered_sum_size(fs_info,
+ bytes_left), GFP_KERNEL);
+ memalloc_nofs_restore(nofs_flag);
BUG_ON(!sums); /* -ENOMEM */
sums->len = bytes_left;
ordered = btrfs_lookup_ordered_extent(inode,
u64 extent_start = 0;
u64 extent_end = 0;
u64 objectid = btrfs_ino(inode);
- u8 extent_type;
+ int extent_type = -1;
struct btrfs_path *path = NULL;
struct btrfs_root *root = inode->root;
struct btrfs_file_extent_item *item;
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
+#include <linux/sched/mm.h>
#include "ctree.h"
#include "transaction.h"
#include "btrfs_inode.h"
cur = entry->list.next;
sum = list_entry(cur, struct btrfs_ordered_sum, list);
list_del(&sum->list);
- kfree(sum);
+ kvfree(sum);
}
kmem_cache_free(btrfs_ordered_extent_cache, entry);
}
#ifdef CONFIG_STACKTRACE
static void __save_stack_trace(struct ref_action *ra)
{
- struct stack_trace stack_trace;
-
- stack_trace.max_entries = MAX_TRACE;
- stack_trace.nr_entries = 0;
- stack_trace.entries = ra->trace;
- stack_trace.skip = 2;
- save_stack_trace(&stack_trace);
- ra->trace_len = stack_trace.nr_entries;
+ ra->trace_len = stack_trace_save(ra->trace, MAX_TRACE, 2);
}
static void __print_stack_trace(struct btrfs_fs_info *fs_info,
struct ref_action *ra)
{
- struct stack_trace trace;
-
if (ra->trace_len == 0) {
btrfs_err(fs_info, " ref-verify: no stacktrace");
return;
}
- trace.nr_entries = ra->trace_len;
- trace.entries = ra->trace;
- print_stack_trace(&trace, 2);
+ stack_trace_print(ra->trace, ra->trace_len, 2);
}
#else
static void inline __save_stack_trace(struct ref_action *ra)
unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
{
struct ceph_inode_info *dci = ceph_inode(dir);
+ unsigned hash;
switch (dci->i_dir_layout.dl_dir_hash) {
case 0: /* for backward compat */
return dn->d_name.hash;
default:
- return ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
+ spin_lock(&dn->d_lock);
+ hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
dn->d_name.name, dn->d_name.len);
+ spin_unlock(&dn->d_lock);
+ return hash;
}
}
return 0;
}
+static int d_name_cmp(struct dentry *dentry, const char *name, size_t len)
+{
+ int ret;
+
+ /* take d_lock to ensure dentry->d_name stability */
+ spin_lock(&dentry->d_lock);
+ ret = dentry->d_name.len - len;
+ if (!ret)
+ ret = memcmp(dentry->d_name.name, name, len);
+ spin_unlock(&dentry->d_lock);
+ return ret;
+}
+
/*
* Incorporate results into the local cache. This is either just
* one inode, or a directory, dentry, and possibly linked-to inode (e.g.,
err = splice_dentry(&req->r_dentry, in);
if (err < 0)
goto done;
- } else if (rinfo->head->is_dentry) {
+ } else if (rinfo->head->is_dentry &&
+ !d_name_cmp(req->r_dentry, rinfo->dname, rinfo->dname_len)) {
struct ceph_vino *ptvino = NULL;
if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) ||
list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove);
ci->i_prealloc_cap_flush = NULL;
}
+
+ if (drop &&
+ ci->i_wrbuffer_ref_head == 0 &&
+ ci->i_wr_ref == 0 &&
+ ci->i_dirty_caps == 0 &&
+ ci->i_flushing_caps == 0) {
+ ceph_put_snap_context(ci->i_head_snapc);
+ ci->i_head_snapc = NULL;
+ }
}
spin_unlock(&ci->i_ceph_lock);
while (!list_empty(&to_remove)) {
return path;
}
+/* Duplicate the dentry->d_name.name safely */
+static int clone_dentry_name(struct dentry *dentry, const char **ppath,
+ int *ppathlen)
+{
+ u32 len;
+ char *name;
+
+retry:
+ len = READ_ONCE(dentry->d_name.len);
+ name = kmalloc(len + 1, GFP_NOFS);
+ if (!name)
+ return -ENOMEM;
+
+ spin_lock(&dentry->d_lock);
+ if (dentry->d_name.len != len) {
+ spin_unlock(&dentry->d_lock);
+ kfree(name);
+ goto retry;
+ }
+ memcpy(name, dentry->d_name.name, len);
+ spin_unlock(&dentry->d_lock);
+
+ name[len] = '\0';
+ *ppath = name;
+ *ppathlen = len;
+ return 0;
+}
+
static int build_dentry_path(struct dentry *dentry, struct inode *dir,
const char **ppath, int *ppathlen, u64 *pino,
- int *pfreepath)
+ bool *pfreepath, bool parent_locked)
{
+ int ret;
char *path;
rcu_read_lock();
if (dir && ceph_snap(dir) == CEPH_NOSNAP) {
*pino = ceph_ino(dir);
rcu_read_unlock();
- *ppath = dentry->d_name.name;
- *ppathlen = dentry->d_name.len;
+ if (parent_locked) {
+ *ppath = dentry->d_name.name;
+ *ppathlen = dentry->d_name.len;
+ } else {
+ ret = clone_dentry_name(dentry, ppath, ppathlen);
+ if (ret)
+ return ret;
+ *pfreepath = true;
+ }
return 0;
}
rcu_read_unlock();
if (IS_ERR(path))
return PTR_ERR(path);
*ppath = path;
- *pfreepath = 1;
+ *pfreepath = true;
return 0;
}
static int build_inode_path(struct inode *inode,
const char **ppath, int *ppathlen, u64 *pino,
- int *pfreepath)
+ bool *pfreepath)
{
struct dentry *dentry;
char *path;
if (IS_ERR(path))
return PTR_ERR(path);
*ppath = path;
- *pfreepath = 1;
+ *pfreepath = true;
return 0;
}
static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
struct inode *rdiri, const char *rpath,
u64 rino, const char **ppath, int *pathlen,
- u64 *ino, int *freepath)
+ u64 *ino, bool *freepath, bool parent_locked)
{
int r = 0;
ceph_snap(rinode));
} else if (rdentry) {
r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino,
- freepath);
+ freepath, parent_locked);
dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen,
*ppath);
} else if (rpath || rino) {
const char *path2 = NULL;
u64 ino1 = 0, ino2 = 0;
int pathlen1 = 0, pathlen2 = 0;
- int freepath1 = 0, freepath2 = 0;
+ bool freepath1 = false, freepath2 = false;
int len;
u16 releases;
void *p, *end;
ret = set_request_path_attr(req->r_inode, req->r_dentry,
req->r_parent, req->r_path1, req->r_ino1.ino,
- &path1, &pathlen1, &ino1, &freepath1);
+ &path1, &pathlen1, &ino1, &freepath1,
+ test_bit(CEPH_MDS_R_PARENT_LOCKED,
+ &req->r_req_flags));
if (ret < 0) {
msg = ERR_PTR(ret);
goto out;
}
+ /* If r_old_dentry is set, then assume that its parent is locked */
ret = set_request_path_attr(NULL, req->r_old_dentry,
req->r_old_dentry_dir,
req->r_path2, req->r_ino2.ino,
- &path2, &pathlen2, &ino2, &freepath2);
+ &path2, &pathlen2, &ino2, &freepath2, true);
if (ret < 0) {
msg = ERR_PTR(ret);
goto out_free1;
old_snapc = NULL;
update_snapc:
- if (ci->i_head_snapc) {
+ if (ci->i_wrbuffer_ref_head == 0 &&
+ ci->i_wr_ref == 0 &&
+ ci->i_dirty_caps == 0 &&
+ ci->i_flushing_caps == 0) {
+ ci->i_head_snapc = NULL;
+ } else {
ci->i_head_snapc = ceph_get_snap_context(new_snapc);
dout(" new snapc is %p\n", new_snapc);
}
}
struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file);
+void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr);
void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
#define CIFS_CACHE_READ_FLG 1
#endif /* CONFIG_CIFS_ACL */
void cifs_oplock_break(struct work_struct *work);
+void cifs_queue_oplock_break(struct cifsFileInfo *cfile);
extern const struct slow_work_ops cifs_oplock_break_ops;
extern struct workqueue_struct *cifsiod_wq;
return cifs_file;
}
-/*
- * Release a reference on the file private data. This may involve closing
- * the filehandle out on the server. Must be called without holding
- * tcon->open_file_lock and cifs_file->file_info_lock.
+/**
+ * cifsFileInfo_put - release a reference of file priv data
+ *
+ * Always potentially wait for oplock handler. See _cifsFileInfo_put().
*/
void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
+{
+ _cifsFileInfo_put(cifs_file, true);
+}
+
+/**
+ * _cifsFileInfo_put - release a reference of file priv data
+ *
+ * This may involve closing the filehandle @cifs_file out on the
+ * server. Must be called without holding tcon->open_file_lock and
+ * cifs_file->file_info_lock.
+ *
+ * If @wait_for_oplock_handler is true and we are releasing the last
+ * reference, wait for any running oplock break handler of the file
+ * and cancel any pending one. If calling this function from the
+ * oplock break handler, you need to pass false.
+ *
+ */
+void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
{
struct inode *inode = d_inode(cifs_file->dentry);
struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
spin_unlock(&tcon->open_file_lock);
- oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break);
+ oplock_break_cancelled = wait_oplock_handler ?
+ cancel_work_sync(&cifs_file->oplock_break) : false;
if (!tcon->need_reconnect && !cifs_file->invalidHandle) {
struct TCP_Server_Info *server = tcon->ses->server;
struct cifs_tcon *tcon;
struct cifs_sb_info *cifs_sb;
struct dentry *dentry = ctx->cfile->dentry;
- unsigned int i;
int rc;
tcon = tlink_tcon(ctx->cfile->tlink);
kref_put(&wdata->refcount, cifs_uncached_writedata_release);
}
- if (!ctx->direct_io)
- for (i = 0; i < ctx->npages; i++)
- put_page(ctx->bv[i].bv_page);
-
cifs_stats_bytes_written(tcon, ctx->total_len);
set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags);
struct iov_iter *to = &ctx->iter;
struct cifs_sb_info *cifs_sb;
struct cifs_tcon *tcon;
- unsigned int i;
int rc;
tcon = tlink_tcon(ctx->cfile->tlink);
kref_put(&rdata->refcount, cifs_uncached_readdata_release);
}
- if (!ctx->direct_io) {
- for (i = 0; i < ctx->npages; i++) {
- if (ctx->should_dirty)
- set_page_dirty(ctx->bv[i].bv_page);
- put_page(ctx->bv[i].bv_page);
- }
-
+ if (!ctx->direct_io)
ctx->total_len = ctx->len - iov_iter_count(to);
- }
/* mask nodata case */
if (rc == -ENODATA)
cinode);
cifs_dbg(FYI, "Oplock release rc = %d\n", rc);
}
+ _cifsFileInfo_put(cfile, false /* do not wait for ourself */);
cifs_done_oplock_break(cinode);
}
if (rc == 0 || rc != -EBUSY)
goto do_rename_exit;
+ /* Don't fall back to using SMB on SMB 2+ mount */
+ if (server->vals->protocol_id != 0)
+ goto do_rename_exit;
+
/* open-file renames don't work across directories */
if (to_dentry->d_parent != from_dentry->d_parent)
goto do_rename_exit;
CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
&pCifsInode->flags);
- queue_work(cifsoplockd_wq,
- &netfile->oplock_break);
+ cifs_queue_oplock_break(netfile);
netfile->oplock_break_cancelled = false;
spin_unlock(&tcon->open_file_lock);
spin_unlock(&cinode->writers_lock);
}
+/**
+ * cifs_queue_oplock_break - queue the oplock break handler for cfile
+ *
+ * This function is called from the demultiplex thread when it
+ * receives an oplock break for @cfile.
+ *
+ * Assumes the tcon->open_file_lock is held.
+ * Assumes cfile->file_info_lock is NOT held.
+ */
+void cifs_queue_oplock_break(struct cifsFileInfo *cfile)
+{
+ /*
+ * Bump the handle refcount now while we hold the
+ * open_file_lock to enforce the validity of it for the oplock
+ * break handler. The matching put is done at the end of the
+ * handler.
+ */
+ cifsFileInfo_get(cfile);
+
+ queue_work(cifsoplockd_wq, &cfile->oplock_break);
+}
+
void cifs_done_oplock_break(struct cifsInodeInfo *cinode)
{
clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags);
{
struct cifs_aio_ctx *ctx;
+ /*
+ * Must use kzalloc to initialize ctx->bv to NULL and ctx->direct_io
+ * to false so that we know when we have to unreference pages within
+ * cifs_aio_ctx_release()
+ */
ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL);
if (!ctx)
return NULL;
struct cifs_aio_ctx, refcount);
cifsFileInfo_put(ctx->cfile);
- kvfree(ctx->bv);
+
+ /*
+ * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly
+ * which means that iov_iter_get_pages() was a success and thus that
+ * we have taken reference on pages.
+ */
+ if (ctx->bv) {
+ unsigned i;
+
+ for (i = 0; i < ctx->npages; i++) {
+ if (ctx->should_dirty)
+ set_page_dirty(ctx->bv[i].bv_page);
+ put_page(ctx->bv[i].bv_page);
+ }
+ kvfree(ctx->bv);
+ }
+
kfree(ctx);
}
clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
&cinode->flags);
- queue_work(cifsoplockd_wq, &cfile->oplock_break);
+ cifs_queue_oplock_break(cfile);
kfree(lw);
return true;
}
CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
&cinode->flags);
spin_unlock(&cfile->file_info_lock);
- queue_work(cifsoplockd_wq,
- &cfile->oplock_break);
+
+ cifs_queue_oplock_break(cfile);
spin_unlock(&tcon->open_file_lock);
spin_unlock(&cifs_tcp_ses_lock);
rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov,
&resp_buftype);
+ if (!rc)
+ SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
if (!rc || !err_iov.iov_base) {
rc = -ENOENT;
goto free_path;
} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
/* ops set to 3.0 by default for default so update */
ses->server->ops = &smb21_operations;
- } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID))
+ ses->server->vals = &smb21_values;
+ } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
ses->server->ops = &smb311_operations;
+ ses->server->vals = &smb311_values;
+ }
} else if (le16_to_cpu(rsp->DialectRevision) !=
ses->server->vals->protocol_id) {
/* if requested single dialect ensure returned dialect matched */
rqst.rq_nvec = 1;
rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
- cifs_small_buf_release(req);
-
rsp = (struct smb2_read_rsp *)rsp_iov.iov_base;
if (rc) {
io_parms->tcon->tid, ses->Suid,
io_parms->offset, 0);
free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+ cifs_small_buf_release(req);
return rc == -ENODATA ? 0 : rc;
} else
trace_smb3_read_done(xid, req->PersistentFileId,
io_parms->tcon->tid, ses->Suid,
io_parms->offset, io_parms->length);
+ cifs_small_buf_release(req);
+
*nbytes = le32_to_cpu(rsp->DataLength);
if ((*nbytes > CIFS_MAX_MSGSIZE) ||
(*nbytes > io_parms->length)) {
rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst,
&resp_buftype, flags, &rsp_iov);
- cifs_small_buf_release(req);
rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
if (rc) {
io_parms->offset, *nbytes);
}
+ cifs_small_buf_release(req);
free_rsp_buf(resp_buftype, rsp);
return rc;
}
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
+#include <asm/pgalloc.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
unsigned long pmd_addr = vmf->address & PMD_MASK;
+ struct vm_area_struct *vma = vmf->vma;
struct inode *inode = mapping->host;
+ pgtable_t pgtable = NULL;
struct page *zero_page;
spinlock_t *ptl;
pmd_t pmd_entry;
*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
DAX_PMD | DAX_ZERO_PAGE, false);
+ if (arch_needs_pgtable_deposit()) {
+ pgtable = pte_alloc_one(vma->vm_mm);
+ if (!pgtable)
+ return VM_FAULT_OOM;
+ }
+
ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
if (!pmd_none(*(vmf->pmd))) {
spin_unlock(ptl);
goto fallback;
}
+ if (pgtable) {
+ pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
+ mm_inc_nr_ptes(vma->vm_mm);
+ }
pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
pmd_entry = pmd_mkhuge(pmd_entry);
set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
return VM_FAULT_NOPAGE;
fallback:
+ if (pgtable)
+ pte_free(vma->vm_mm, pgtable);
trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry);
return VM_FAULT_FALLBACK;
}
int kill;
int error = 0;
- /* Fast path for nothing security related */
- if (IS_NOSEC(inode))
+ /*
+ * Fast path for nothing security related.
+ * As well for non-regular files, e.g. blkdev inodes.
+ * For example, blkdev_write_iter() might get here
+ * trying to remove privs which it is not allowed to.
+ */
+ if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
return 0;
kill = dentry_needs_remove_privs(dentry);
* supporting fast/efficient IO.
*
* A note on the read/write ordering memory barriers that are matched between
- * the application and kernel side. When the application reads the CQ ring
- * tail, it must use an appropriate smp_rmb() to order with the smp_wmb()
- * the kernel uses after writing the tail. Failure to do so could cause a
- * delay in when the application notices that completion events available.
- * This isn't a fatal condition. Likewise, the application must use an
- * appropriate smp_wmb() both before writing the SQ tail, and after writing
- * the SQ tail. The first one orders the sqe writes with the tail write, and
- * the latter is paired with the smp_rmb() the kernel will issue before
- * reading the SQ tail on submission.
+ * the application and kernel side.
+ *
+ * After the application reads the CQ ring tail, it must use an
+ * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
+ * before writing the tail (using smp_load_acquire to read the tail will
+ * do). It also needs a smp_mb() before updating CQ head (ordering the
+ * entry load(s) with the head store), pairing with an implicit barrier
+ * through a control-dependency in io_get_cqring (smp_store_release to
+ * store head will do). Failure to do so could lead to reading invalid
+ * CQ entries.
+ *
+ * Likewise, the application must use an appropriate smp_wmb() before
+ * writing the SQ tail (ordering SQ entry stores with the tail store),
+ * which pairs with smp_load_acquire in io_get_sqring (smp_store_release
+ * to store the tail will do). And it needs a barrier ordering the SQ
+ * head load before writing new SQ entries (smp_load_acquire to read
+ * head will do).
+ *
+ * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application
+ * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after*
+ * updating the SQ tail; a full memory barrier smp_mb() is needed
+ * between.
*
* Also see the examples in the liburing library:
*
u32 tail ____cacheline_aligned_in_smp;
};
+/*
+ * This data is shared with the application through the mmap at offset
+ * IORING_OFF_SQ_RING.
+ *
+ * The offsets to the member fields are published through struct
+ * io_sqring_offsets when calling io_uring_setup.
+ */
struct io_sq_ring {
+ /*
+ * Head and tail offsets into the ring; the offsets need to be
+ * masked to get valid indices.
+ *
+ * The kernel controls head and the application controls tail.
+ */
struct io_uring r;
+ /*
+ * Bitmask to apply to head and tail offsets (constant, equals
+ * ring_entries - 1)
+ */
u32 ring_mask;
+ /* Ring size (constant, power of 2) */
u32 ring_entries;
+ /*
+ * Number of invalid entries dropped by the kernel due to
+ * invalid index stored in array
+ *
+ * Written by the kernel, shouldn't be modified by the
+ * application (i.e. get number of "new events" by comparing to
+ * cached value).
+ *
+ * After a new SQ head value was read by the application this
+ * counter includes all submissions that were dropped reaching
+ * the new SQ head (and possibly more).
+ */
u32 dropped;
+ /*
+ * Runtime flags
+ *
+ * Written by the kernel, shouldn't be modified by the
+ * application.
+ *
+ * The application needs a full memory barrier before checking
+ * for IORING_SQ_NEED_WAKEUP after updating the sq tail.
+ */
u32 flags;
+ /*
+ * Ring buffer of indices into array of io_uring_sqe, which is
+ * mmapped by the application using the IORING_OFF_SQES offset.
+ *
+ * This indirection could e.g. be used to assign fixed
+ * io_uring_sqe entries to operations and only submit them to
+ * the queue when needed.
+ *
+ * The kernel modifies neither the indices array nor the entries
+ * array.
+ */
u32 array[];
};
+/*
+ * This data is shared with the application through the mmap at offset
+ * IORING_OFF_CQ_RING.
+ *
+ * The offsets to the member fields are published through struct
+ * io_cqring_offsets when calling io_uring_setup.
+ */
struct io_cq_ring {
+ /*
+ * Head and tail offsets into the ring; the offsets need to be
+ * masked to get valid indices.
+ *
+ * The application controls head and the kernel tail.
+ */
struct io_uring r;
+ /*
+ * Bitmask to apply to head and tail offsets (constant, equals
+ * ring_entries - 1)
+ */
u32 ring_mask;
+ /* Ring size (constant, power of 2) */
u32 ring_entries;
+ /*
+ * Number of completion events lost because the queue was full;
+ * this should be avoided by the application by making sure
+ * there are not more requests pending thatn there is space in
+ * the completion queue.
+ *
+ * Written by the kernel, shouldn't be modified by the
+ * application (i.e. get number of "new events" by comparing to
+ * cached value).
+ *
+ * As completion events come in out of order this counter is not
+ * ordered with any other data.
+ */
u32 overflow;
+ /*
+ * Ring buffer of completion events.
+ *
+ * The kernel writes completion events fresh every time they are
+ * produced, so the application is allowed to modify pending
+ * entries.
+ */
struct io_uring_cqe cqes[];
};
struct list_head list;
unsigned int flags;
refcount_t refs;
-#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */
+#define REQ_F_NOWAIT 1 /* must not punt to workers */
#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */
#define REQ_F_FIXED_FILE 4 /* ctx owns file */
#define REQ_F_SEQ_PREV 8 /* sequential with previous */
/* order cqe stores with ring update */
smp_store_release(&ring->r.tail, ctx->cached_cq_tail);
- /*
- * Write sider barrier of tail update, app has read side. See
- * comment at the top of this file.
- */
- smp_wmb();
-
if (wq_has_sleeper(&ctx->cq_wait)) {
wake_up_interruptible(&ctx->cq_wait);
kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
unsigned tail;
tail = ctx->cached_cq_tail;
- /* See comment at the top of the file */
- smp_rmb();
- if (tail + 1 == READ_ONCE(ring->r.head))
+ /*
+ * writes to the cq entry need to come after reading head; the
+ * control dependency is enough as we're using WRITE_ONCE to
+ * fill the cq entry
+ */
+ if (tail - READ_ONCE(ring->r.head) == ring->ring_entries)
return NULL;
ctx->cached_cq_tail++;
list_add_tail(&req->list, &ctx->poll_list);
}
-static void io_file_put(struct io_submit_state *state, struct file *file)
+static void io_file_put(struct io_submit_state *state)
{
- if (!state) {
- fput(file);
- } else if (state->file) {
+ if (state->file) {
int diff = state->has_refs - state->used_refs;
if (diff)
state->ios_left--;
return state->file;
}
- io_file_put(state, NULL);
+ io_file_put(state);
}
state->file = fget_many(fd, state->ios_left);
if (!state->file)
}
static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
- bool force_nonblock, struct io_submit_state *state)
+ bool force_nonblock)
{
const struct io_uring_sqe *sqe = s->sqe;
struct io_ring_ctx *ctx = req->ctx;
ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
if (unlikely(ret))
return ret;
- if (force_nonblock) {
+
+ /* don't allow async punt if RWF_NOWAIT was requested */
+ if (kiocb->ki_flags & IOCB_NOWAIT)
+ req->flags |= REQ_F_NOWAIT;
+
+ if (force_nonblock)
kiocb->ki_flags |= IOCB_NOWAIT;
- req->flags |= REQ_F_FORCE_NONBLOCK;
- }
+
if (ctx->flags & IORING_SETUP_IOPOLL) {
if (!(kiocb->ki_flags & IOCB_DIRECT) ||
!kiocb->ki_filp->f_op->iopoll)
}
static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
- bool force_nonblock, struct io_submit_state *state)
+ bool force_nonblock)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *kiocb = &req->rw;
size_t iov_count;
int ret;
- ret = io_prep_rw(req, s, force_nonblock, state);
+ ret = io_prep_rw(req, s, force_nonblock);
if (ret)
return ret;
file = kiocb->ki_filp;
}
static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
- bool force_nonblock, struct io_submit_state *state)
+ bool force_nonblock)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *kiocb = &req->rw;
size_t iov_count;
int ret;
- ret = io_prep_rw(req, s, force_nonblock, state);
+ ret = io_prep_rw(req, s, force_nonblock);
if (ret)
return ret;
}
static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- const struct sqe_submit *s, bool force_nonblock,
- struct io_submit_state *state)
+ const struct sqe_submit *s, bool force_nonblock)
{
int ret, opcode;
case IORING_OP_READV:
if (unlikely(s->sqe->buf_index))
return -EINVAL;
- ret = io_read(req, s, force_nonblock, state);
+ ret = io_read(req, s, force_nonblock);
break;
case IORING_OP_WRITEV:
if (unlikely(s->sqe->buf_index))
return -EINVAL;
- ret = io_write(req, s, force_nonblock, state);
+ ret = io_write(req, s, force_nonblock);
break;
case IORING_OP_READ_FIXED:
- ret = io_read(req, s, force_nonblock, state);
+ ret = io_read(req, s, force_nonblock);
break;
case IORING_OP_WRITE_FIXED:
- ret = io_write(req, s, force_nonblock, state);
+ ret = io_write(req, s, force_nonblock);
break;
case IORING_OP_FSYNC:
ret = io_fsync(req, s->sqe, force_nonblock);
struct sqe_submit *s = &req->submit;
const struct io_uring_sqe *sqe = s->sqe;
- /* Ensure we clear previously set forced non-block flag */
- req->flags &= ~REQ_F_FORCE_NONBLOCK;
+ /* Ensure we clear previously set non-block flag */
req->rw.ki_flags &= ~IOCB_NOWAIT;
ret = 0;
s->has_user = cur_mm != NULL;
s->needs_lock = true;
do {
- ret = __io_submit_sqe(ctx, req, s, false, NULL);
+ ret = __io_submit_sqe(ctx, req, s, false);
/*
* We can get EAGAIN for polled IO even though
* we're forcing a sync submission from here,
break;
cond_resched();
} while (1);
-
- /* drop submission reference */
- io_put_req(req);
}
+
+ /* drop submission reference */
+ io_put_req(req);
+
if (ret) {
io_cqring_add_event(ctx, sqe->user_data, ret, 0);
io_put_req(req);
if (unlikely(ret))
goto out;
- ret = __io_submit_sqe(ctx, req, s, true, state);
- if (ret == -EAGAIN) {
+ ret = __io_submit_sqe(ctx, req, s, true);
+ if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
struct io_uring_sqe *sqe_copy;
sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
static void io_submit_state_end(struct io_submit_state *state)
{
blk_finish_plug(&state->plug);
- io_file_put(state, NULL);
+ io_file_put(state);
if (state->free_reqs)
kmem_cache_free_bulk(req_cachep, state->free_reqs,
&state->reqs[state->cur_req]);
* write new data to them.
*/
smp_store_release(&ring->r.head, ctx->cached_sq_head);
-
- /*
- * write side barrier of head update, app has read side. See
- * comment at the top of this file
- */
- smp_wmb();
}
}
-/*
- * Undo last io_get_sqring()
- */
-static void io_drop_sqring(struct io_ring_ctx *ctx)
-{
- ctx->cached_sq_head--;
-}
-
/*
* Fetch an sqe, if one is available. Note that s->sqe will point to memory
* that is mapped by userspace. This means that care needs to be taken to
* though the application is the one updating it.
*/
head = ctx->cached_sq_head;
- /* See comment at the top of this file */
- smp_rmb();
- if (head == READ_ONCE(ring->r.tail))
+ /* make sure SQ entry isn't read before tail */
+ if (head == smp_load_acquire(&ring->r.tail))
return false;
head = READ_ONCE(ring->array[head & ctx->sq_mask]);
/* drop invalid entries */
ctx->cached_sq_head++;
ring->dropped++;
- /* See comment at the top of this file */
- smp_wmb();
return false;
}
/* Tell userspace we may need a wakeup call */
ctx->sq_ring->flags |= IORING_SQ_NEED_WAKEUP;
- smp_wmb();
+ /* make sure to read SQ tail after writing flags */
+ smp_mb();
if (!io_get_sqring(ctx, &sqes[0])) {
if (kthread_should_stop()) {
finish_wait(&ctx->sqo_wait, &wait);
ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
- smp_wmb();
continue;
}
finish_wait(&ctx->sqo_wait, &wait);
ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
- smp_wmb();
}
i = 0;
unuse_mm(cur_mm);
mmput(cur_mm);
}
+
+ if (kthread_should_park())
+ kthread_parkme();
+
return 0;
}
static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
{
struct io_submit_state state, *statep = NULL;
- int i, ret = 0, submit = 0;
+ int i, submit = 0;
if (to_submit > IO_PLUG_THRESHOLD) {
io_submit_state_start(&state, ctx, to_submit);
for (i = 0; i < to_submit; i++) {
struct sqe_submit s;
+ int ret;
if (!io_get_sqring(ctx, &s))
break;
s.has_user = true;
s.needs_lock = false;
s.needs_fixed_file = false;
+ submit++;
ret = io_submit_sqe(ctx, &s, statep);
- if (ret) {
- io_drop_sqring(ctx);
- break;
- }
-
- submit++;
+ if (ret)
+ io_cqring_add_event(ctx, s.sqe->user_data, ret, 0);
}
io_commit_sqring(ctx);
if (statep)
io_submit_state_end(statep);
- return submit ? submit : ret;
+ return submit;
}
static unsigned io_cqring_events(struct io_cq_ring *ring)
if (ctx->sqo_thread) {
ctx->sqo_stop = 1;
mb();
+ kthread_park(ctx->sqo_thread);
kthread_stop(ctx->sqo_thread);
ctx->sqo_thread = NULL;
}
mmgrab(current->mm);
ctx->sqo_mm = current->mm;
- ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
- if (!ctx->sq_thread_idle)
- ctx->sq_thread_idle = HZ;
-
- ret = -EINVAL;
- if (!cpu_possible(p->sq_thread_cpu))
- goto err;
-
if (ctx->flags & IORING_SETUP_SQPOLL) {
ret = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto err;
+ ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
+ if (!ctx->sq_thread_idle)
+ ctx->sq_thread_idle = HZ;
+
if (p->flags & IORING_SETUP_SQ_AFF) {
- int cpu;
+ int cpu = array_index_nospec(p->sq_thread_cpu,
+ nr_cpu_ids);
+
+ ret = -EINVAL;
+ if (!cpu_possible(cpu))
+ goto err;
- cpu = array_index_nospec(p->sq_thread_cpu, NR_CPUS);
ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread,
ctx, cpu,
"io_uring-sq");
static void io_mem_free(void *ptr)
{
- struct page *page = virt_to_head_page(ptr);
+ struct page *page;
+
+ if (!ptr)
+ return;
+ page = virt_to_head_page(ptr);
if (put_page_testzero(page))
free_compound_page(page);
}
if (ctx->account_mem)
io_unaccount_mem(ctx->user, imu->nr_bvecs);
- kfree(imu->bvec);
+ kvfree(imu->bvec);
imu->nr_bvecs = 0;
}
if (!pages || nr_pages > got_pages) {
kfree(vmas);
kfree(pages);
- pages = kmalloc_array(nr_pages, sizeof(struct page *),
+ pages = kvmalloc_array(nr_pages, sizeof(struct page *),
GFP_KERNEL);
- vmas = kmalloc_array(nr_pages,
+ vmas = kvmalloc_array(nr_pages,
sizeof(struct vm_area_struct *),
GFP_KERNEL);
if (!pages || !vmas) {
got_pages = nr_pages;
}
- imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec),
+ imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec),
GFP_KERNEL);
ret = -ENOMEM;
if (!imu->bvec) {
}
if (ctx->account_mem)
io_unaccount_mem(ctx->user, nr_pages);
+ kvfree(imu->bvec);
goto err;
}
ctx->nr_user_bufs++;
}
- kfree(pages);
- kfree(vmas);
+ kvfree(pages);
+ kvfree(vmas);
return 0;
err:
- kfree(pages);
- kfree(vmas);
+ kvfree(pages);
+ kvfree(vmas);
io_sqe_buffer_unregister(ctx);
return ret;
}
__poll_t mask = 0;
poll_wait(file, &ctx->cq_wait, wait);
- /* See comment at the top of this file */
+ /*
+ * synchronizes with barrier from wq_has_sleeper call in
+ * io_commit_cqring
+ */
smp_rmb();
- if (READ_ONCE(ctx->sq_ring->r.tail) + 1 != ctx->cached_sq_head)
+ if (READ_ONCE(ctx->sq_ring->r.tail) - ctx->cached_sq_head !=
+ ctx->sq_ring->ring_entries)
mask |= EPOLLOUT | EPOLLWRNORM;
if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail)
mask |= EPOLLIN | EPOLLRDNORM;
mutex_lock(&ctx->uring_lock);
submitted = io_ring_submit(ctx, to_submit);
mutex_unlock(&ctx->uring_lock);
-
- if (submitted < 0)
- goto out_ctx;
}
if (flags & IORING_ENTER_GETEVENTS) {
unsigned nr_events = 0;
min_complete = min(min_complete, ctx->cq_entries);
- /*
- * The application could have included the 'to_submit' count
- * in how many events it wanted to wait for. If we failed to
- * submit the desired count, we may need to adjust the number
- * of events to poll/wait for.
- */
- if (submitted < to_submit)
- min_complete = min_t(unsigned, submitted, min_complete);
-
if (ctx->flags & IORING_SETUP_IOPOLL) {
mutex_lock(&ctx->uring_lock);
ret = io_iopoll_check(ctx, &nr_events, min_complete);
return -EOVERFLOW;
ctx->sq_sqes = io_mem_alloc(size);
- if (!ctx->sq_sqes) {
- io_mem_free(ctx->sq_ring);
+ if (!ctx->sq_sqes)
return -ENOMEM;
- }
cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries));
- if (!cq_ring) {
- io_mem_free(ctx->sq_ring);
- io_mem_free(ctx->sq_sqes);
+ if (!cq_ring)
return -ENOMEM;
- }
ctx->cq_ring = cq_ring;
cq_ring->ring_mask = p->cq_entries - 1;
static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
void __user *arg, unsigned nr_args)
+ __releases(ctx->uring_lock)
+ __acquires(ctx->uring_lock)
{
int ret;
+ /*
+ * We're inside the ring mutex, if the ref is already dying, then
+ * someone else killed the ctx or is already going through
+ * io_uring_register().
+ */
+ if (percpu_ref_is_dying(&ctx->refs))
+ return -ENXIO;
+
percpu_ref_kill(&ctx->refs);
+
+ /*
+ * Drop uring mutex before waiting for references to exit. If another
+ * thread is currently inside io_uring_enter() it might need to grab
+ * the uring_lock to make progress. If we hold it here across the drain
+ * wait, then we can deadlock. It's safe to drop the mutex here, since
+ * no new references will come in after we've killed the percpu ref.
+ */
+ mutex_unlock(&ctx->uring_lock);
wait_for_completion(&ctx->ctx_done);
+ mutex_lock(&ctx->uring_lock);
switch (opcode) {
case IORING_REGISTER_BUFFERS:
struct nfsd3_readdirargs *argp = rqstp->rq_argp;
struct nfsd3_readdirres *resp = rqstp->rq_resp;
__be32 nfserr;
- int count;
+ int count = 0;
+ struct page **p;
+ caddr_t page_addr = NULL;
dprintk("nfsd: READDIR(3) %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
nfserr = nfsd_readdir(rqstp, &resp->fh, (loff_t*) &argp->cookie,
&resp->common, nfs3svc_encode_entry);
memcpy(resp->verf, argp->verf, 8);
- resp->count = resp->buffer - argp->buffer;
+ count = 0;
+ for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
+ page_addr = page_address(*p);
+
+ if (((caddr_t)resp->buffer >= page_addr) &&
+ ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {
+ count += (caddr_t)resp->buffer - page_addr;
+ break;
+ }
+ count += PAGE_SIZE;
+ }
+ resp->count = count >> 2;
if (resp->offset) {
loff_t offset = argp->cookie;
nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd3_readdirargs *args = rqstp->rq_argp;
+ int len;
u32 max_blocksize = svc_max_payload(rqstp);
p = decode_fh(p, &args->fh);
args->verf = p; p += 2;
args->dircount = ~0;
args->count = ntohl(*p++);
- args->count = min_t(u32, args->count, max_blocksize);
- args->buffer = page_address(*(rqstp->rq_next_page++));
+ len = args->count = min_t(u32, args->count, max_blocksize);
+
+ while (len > 0) {
+ struct page *p = *(rqstp->rq_next_page++);
+ if (!args->buffer)
+ args->buffer = page_address(p);
+ len -= PAGE_SIZE;
+ }
return xdr_argsize_check(rqstp, p);
}
cb->cb_seq_status = 1;
cb->cb_status = 0;
if (minorversion) {
- if (!nfsd41_cb_get_slot(clp, task))
+ if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task))
return;
+ cb->cb_holds_slot = true;
}
rpc_call_start(task);
}
return true;
}
+ if (!cb->cb_holds_slot)
+ goto need_restart;
+
switch (cb->cb_seq_status) {
case 0:
/*
cb->cb_seq_status);
}
+ cb->cb_holds_slot = false;
clear_bit(0, &clp->cl_cb_slot_busy);
rpc_wake_up_next(&clp->cl_cb_waitq);
dprintk("%s: freed slot, new seqid=%d\n", __func__,
cb->cb_seq_status = 1;
cb->cb_status = 0;
cb->cb_need_restart = false;
+ cb->cb_holds_slot = false;
}
void nfsd4_run_cb(struct nfsd4_callback *cb)
static void
free_blocked_lock(struct nfsd4_blocked_lock *nbl)
{
+ locks_delete_block(&nbl->nbl_lock);
locks_release_private(&nbl->nbl_lock);
kfree(nbl);
}
nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock,
nbl_lru);
list_del_init(&nbl->nbl_lru);
- locks_delete_block(&nbl->nbl_lock);
free_blocked_lock(nbl);
}
}
+static void
+nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb)
+{
+ struct nfsd4_blocked_lock *nbl = container_of(cb,
+ struct nfsd4_blocked_lock, nbl_cb);
+ locks_delete_block(&nbl->nbl_lock);
+}
+
static int
nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task)
{
}
static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
+ .prepare = nfsd4_cb_notify_lock_prepare,
.done = nfsd4_cb_notify_lock_done,
.release = nfsd4_cb_notify_lock_release,
};
nbl = list_first_entry(&reaplist,
struct nfsd4_blocked_lock, nbl_lru);
list_del_init(&nbl->nbl_lru);
- locks_delete_block(&nbl->nbl_lock);
free_blocked_lock(nbl);
}
out:
int cb_seq_status;
int cb_status;
bool cb_need_restart;
+ bool cb_holds_slot;
};
struct nfsd4_callback_ops {
__kernel_fsid_t fsid = {};
fsnotify_foreach_obj_type(type) {
+ struct fsnotify_mark_connector *conn;
+
if (!fsnotify_iter_should_report_type(iter_info, type))
continue;
- fsid = iter_info->marks[type]->connector->fsid;
+ conn = READ_ONCE(iter_info->marks[type]->connector);
+ /* Mark is just getting destroyed or created? */
+ if (!conn)
+ continue;
+ fsid = conn->fsid;
if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
continue;
return fsid;
return 0;
}
- if (FAN_GROUP_FLAG(group, FAN_REPORT_FID))
+ if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
fsid = fanotify_get_fsid(iter_info);
+ /* Racing with mark destruction or creation? */
+ if (!fsid.val[0] && !fsid.val[1])
+ return 0;
+ }
event = fanotify_alloc_event(group, inode, mask, data, data_type,
&fsid);
void fsnotify_put_mark(struct fsnotify_mark *mark)
{
- struct fsnotify_mark_connector *conn;
+ struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector);
void *objp = NULL;
unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED;
bool free_conn = false;
/* Catch marks that were actually never attached to object */
- if (!mark->connector) {
+ if (!conn) {
if (refcount_dec_and_test(&mark->refcnt))
fsnotify_final_mark_destroy(mark);
return;
* We have to be careful so that traversals of obj_list under lock can
* safely grab mark reference.
*/
- if (!refcount_dec_and_lock(&mark->refcnt, &mark->connector->lock))
+ if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock))
return;
- conn = mark->connector;
hlist_del_init_rcu(&mark->obj_list);
if (hlist_empty(&conn->list)) {
objp = fsnotify_detach_connector_from_object(conn, &type);
} else {
__fsnotify_recalc_mask(conn);
}
- mark->connector = NULL;
+ WRITE_ONCE(mark->connector, NULL);
spin_unlock(&conn->lock);
fsnotify_drop_object(type, objp);
/* mark should be the last entry. last is the current last entry */
hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
added:
- mark->connector = conn;
+ WRITE_ONCE(mark->connector, conn);
out_err:
spin_unlock(&conn->lock);
spin_unlock(&mark->lock);
refcount_set(&mark->refcnt, 1);
fsnotify_get_group(group);
mark->group = group;
+ WRITE_ONCE(mark->connector, NULL);
}
/*
static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- struct stack_trace trace;
unsigned long *entries;
int err;
if (!entries)
return -ENOMEM;
- trace.nr_entries = 0;
- trace.max_entries = MAX_STACK_TRACE_DEPTH;
- trace.entries = entries;
- trace.skip = 0;
-
err = lock_trace(task);
if (!err) {
- unsigned int i;
+ unsigned int i, nr_entries;
- save_stack_trace_tsk(task, &trace);
+ nr_entries = stack_trace_save_tsk(task, entries,
+ MAX_STACK_TRACE_DEPTH, 0);
- for (i = 0; i < trace.nr_entries; i++) {
+ for (i = 0; i < nr_entries; i++) {
seq_printf(m, "[<0>] %pB\n", (void *)entries[i]);
}
+
unlock_trace(task);
}
kfree(entries);
lr->count, lr->time, lr->max);
for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
unsigned long bt = lr->backtrace[q];
+
if (!bt)
break;
- if (bt == ULONG_MAX)
- break;
seq_printf(m, " %ps", (void *)bt);
}
seq_putc(m, '\n');
if (--header->nreg)
return;
- if (parent)
+ if (parent) {
put_links(header);
- start_unregistering(header);
+ start_unregistering(header);
+ }
+
if (!--header->count)
kfree_rcu(header, rcu);
count = -EINTR;
goto out_mm;
}
+ /*
+ * Avoid to modify vma->vm_flags
+ * without locked ops while the
+ * coredump reads the vm_flags.
+ */
+ if (!mmget_still_valid(mm)) {
+ /*
+ * Silently return "count"
+ * like if get_task_mm()
+ * failed. FIXME: should this
+ * function have returned
+ * -ESRCH if get_task_mm()
+ * failed like if
+ * get_proc_task() fails?
+ */
+ up_write(&mm->mmap_sem);
+ goto out_mm;
+ }
for (vma = mm->mmap; vma; vma = vma->vm_next) {
vma->vm_flags &= ~VM_SOFTDIRTY;
vma_set_page_prot(vma);
.get = generic_pipe_buf_get,
};
-static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
+int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
{
return 1;
}
struct super_block *sb;
int error;
- if (fc->fs_type->fs_flags & FS_REQUIRES_DEV && !fc->source) {
- errorf(fc, "Filesystem requires source device");
- return -ENOENT;
- }
-
if (fc->root)
return -EBUSY;
case UFS_UID_44BSD:
return fs32_to_cpu(sb, inode->ui_u3.ui_44.ui_gid);
case UFS_UID_EFT:
- if (inode->ui_u1.oldids.ui_suid == 0xFFFF)
+ if (inode->ui_u1.oldids.ui_sgid == 0xFFFF)
return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid);
/* Fall through */
default:
/* the various vma->vm_userfaultfd_ctx still points to it */
down_write(&mm->mmap_sem);
+ /* no task can run (and in turn coredump) yet */
+ VM_WARN_ON(!mmget_still_valid(mm));
for (vma = mm->mmap; vma; vma = vma->vm_next)
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
* taking the mmap_sem for writing.
*/
down_write(&mm->mmap_sem);
+ if (!mmget_still_valid(mm))
+ goto skip_mm;
prev = NULL;
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cond_resched();
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
+skip_mm:
up_write(&mm->mmap_sem);
mmput(mm);
wakeup:
goto out;
down_write(&mm->mmap_sem);
+ if (!mmget_still_valid(mm))
+ goto out_unlock;
vma = find_vma_prev(mm, start, &prev);
if (!vma)
goto out_unlock;
goto out;
down_write(&mm->mmap_sem);
+ if (!mmget_still_valid(mm))
+ goto out_unlock;
vma = find_vma_prev(mm, start, &prev);
if (!vma)
goto out_unlock;
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_RWSEM_H
-#define _ASM_GENERIC_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
-#endif
-
-#ifdef __KERNEL__
-
-/*
- * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
- * Adapted largely from include/asm-i386/rwsem.h
- * by Paul Mackerras <paulus@samba.org>.
- */
-
-/*
- * the semaphore definition
- */
-#ifdef CONFIG_64BIT
-# define RWSEM_ACTIVE_MASK 0xffffffffL
-#else
-# define RWSEM_ACTIVE_MASK 0x0000ffffL
-#endif
-
-#define RWSEM_UNLOCKED_VALUE 0x00000000L
-#define RWSEM_ACTIVE_BIAS 0x00000001L
-#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1)
-#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
- if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0))
- rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
- if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
- if (IS_ERR(rwsem_down_read_failed_killable(sem)))
- return -EINTR;
- }
-
- return 0;
-}
-
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
- long tmp;
-
- while ((tmp = atomic_long_read(&sem->count)) >= 0) {
- if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
- tmp + RWSEM_ACTIVE_READ_BIAS)) {
- return 1;
- }
- }
- return 0;
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write(struct rw_semaphore *sem)
-{
- long tmp;
-
- tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
- &sem->count);
- if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
- rwsem_down_write_failed(sem);
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
- long tmp;
-
- tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
- &sem->count);
- if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
- if (IS_ERR(rwsem_down_write_failed_killable(sem)))
- return -EINTR;
- return 0;
-}
-
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
- long tmp;
-
- tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
- RWSEM_ACTIVE_WRITE_BIAS);
- return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
- long tmp;
-
- tmp = atomic_long_dec_return_release(&sem->count);
- if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
- rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
- if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS,
- &sem->count) < 0))
- rwsem_wake(sem);
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
- long tmp;
-
- /*
- * When downgrading from exclusive to shared ownership,
- * anything inside the write-locked region cannot leak
- * into the read side. In contrast, anything in the
- * read-locked region is ok to be re-ordered into the
- * write side. As such, rely on RELEASE semantics.
- */
- tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count);
- if (tmp < 0)
- rwsem_downgrade_wake(sem);
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_GENERIC_RWSEM_H */
#include <linux/swap.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
#ifdef CONFIG_MMU
+/*
+ * Generic MMU-gather implementation.
+ *
+ * The mmu_gather data structure is used by the mm code to implement the
+ * correct and efficient ordering of freeing pages and TLB invalidations.
+ *
+ * This correct ordering is:
+ *
+ * 1) unhook page
+ * 2) TLB invalidate page
+ * 3) free page
+ *
+ * That is, we must never free a page before we have ensured there are no live
+ * translations left to it. Otherwise it might be possible to observe (or
+ * worse, change) the page content after it has been reused.
+ *
+ * The mmu_gather API consists of:
+ *
+ * - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather
+ *
+ * Finish in particular will issue a (final) TLB invalidate and free
+ * all (remaining) queued pages.
+ *
+ * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA
+ *
+ * Defaults to flushing at tlb_end_vma() to reset the range; helps when
+ * there's large holes between the VMAs.
+ *
+ * - tlb_remove_page() / __tlb_remove_page()
+ * - tlb_remove_page_size() / __tlb_remove_page_size()
+ *
+ * __tlb_remove_page_size() is the basic primitive that queues a page for
+ * freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a
+ * boolean indicating if the queue is (now) full and a call to
+ * tlb_flush_mmu() is required.
+ *
+ * tlb_remove_page() and tlb_remove_page_size() imply the call to
+ * tlb_flush_mmu() when required and has no return value.
+ *
+ * - tlb_change_page_size()
+ *
+ * call before __tlb_remove_page*() to set the current page-size; implies a
+ * possible tlb_flush_mmu() call.
+ *
+ * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly()
+ *
+ * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets
+ * related state, like the range)
+ *
+ * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees
+ * whatever pages are still batched.
+ *
+ * - mmu_gather::fullmm
+ *
+ * A flag set by tlb_gather_mmu() to indicate we're going to free
+ * the entire mm; this allows a number of optimizations.
+ *
+ * - We can ignore tlb_{start,end}_vma(); because we don't
+ * care about ranges. Everything will be shot down.
+ *
+ * - (RISC) architectures that use ASIDs can cycle to a new ASID
+ * and delay the invalidation until ASID space runs out.
+ *
+ * - mmu_gather::need_flush_all
+ *
+ * A flag that can be set by the arch code if it wants to force
+ * flush the entire TLB irrespective of the range. For instance
+ * x86-PAE needs this when changing top-level entries.
+ *
+ * And allows the architecture to provide and implement tlb_flush():
+ *
+ * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make
+ * use of:
+ *
+ * - mmu_gather::start / mmu_gather::end
+ *
+ * which provides the range that needs to be flushed to cover the pages to
+ * be freed.
+ *
+ * - mmu_gather::freed_tables
+ *
+ * set when we freed page table pages
+ *
+ * - tlb_get_unmap_shift() / tlb_get_unmap_size()
+ *
+ * returns the smallest TLB entry size unmapped in this range.
+ *
+ * If an architecture does not provide tlb_flush() a default implementation
+ * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is
+ * specified, in which case we'll default to flush_tlb_mm().
+ *
+ * Additionally there are a few opt-in features:
+ *
+ * HAVE_MMU_GATHER_PAGE_SIZE
+ *
+ * This ensures we call tlb_flush() every time tlb_change_page_size() actually
+ * changes the size and provides mmu_gather::page_size to tlb_flush().
+ *
+ * HAVE_RCU_TABLE_FREE
+ *
+ * This provides tlb_remove_table(), to be used instead of tlb_remove_page()
+ * for page directores (__p*_free_tlb()). This provides separate freeing of
+ * the page-table pages themselves in a semi-RCU fashion (see comment below).
+ * Useful if your architecture doesn't use IPIs for remote TLB invalidates
+ * and therefore doesn't naturally serialize with software page-table walkers.
+ *
+ * When used, an architecture is expected to provide __tlb_remove_table()
+ * which does the actual freeing of these pages.
+ *
+ * HAVE_RCU_TABLE_NO_INVALIDATE
+ *
+ * This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before
+ * freeing the page-table pages. This can be avoided if you use
+ * HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux
+ * page-tables natively.
+ *
+ * MMU_GATHER_NO_RANGE
+ *
+ * Use this if your architecture lacks an efficient flush_tlb_range().
+ */
+
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
/*
* Semi RCU freeing of the page directories.
#define MAX_TABLE_BATCH \
((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-extern void tlb_table_flush(struct mmu_gather *tlb);
extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
#endif
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
/*
* If we can't allocate a page to make a big batch of page pointers
* to work on, then just handle a few from the on-stack structure.
*/
#define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH)
-/* struct mmu_gather is an opaque type used by the mm code for passing around
+extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
+ int page_size);
+#endif
+
+/*
+ * struct mmu_gather is an opaque type used by the mm code for passing around
* any data needed by arch specific code for tlb_remove_page.
*/
struct mmu_gather {
struct mm_struct *mm;
+
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
struct mmu_table_batch *batch;
#endif
+
unsigned long start;
unsigned long end;
/*
unsigned int cleared_puds : 1;
unsigned int cleared_p4ds : 1;
+ /*
+ * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma
+ */
+ unsigned int vma_exec : 1;
+ unsigned int vma_huge : 1;
+
+ unsigned int batch_count;
+
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
struct mmu_gather_batch *active;
struct mmu_gather_batch local;
struct page *__pages[MMU_GATHER_BUNDLE];
- unsigned int batch_count;
- int page_size;
-};
-#define HAVE_GENERIC_MMU_GATHER
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+ unsigned int page_size;
+#endif
+#endif
+};
void arch_tlb_gather_mmu(struct mmu_gather *tlb,
struct mm_struct *mm, unsigned long start, unsigned long end);
void tlb_flush_mmu(struct mmu_gather *tlb);
void arch_tlb_finish_mmu(struct mmu_gather *tlb,
unsigned long start, unsigned long end, bool force);
-void tlb_flush_mmu_free(struct mmu_gather *tlb);
-extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
- int page_size);
static inline void __tlb_adjust_range(struct mmu_gather *tlb,
unsigned long address,
tlb->cleared_pmds = 0;
tlb->cleared_puds = 0;
tlb->cleared_p4ds = 0;
+ /*
+ * Do not reset mmu_gather::vma_* fields here, we do not
+ * call into tlb_start_vma() again to set them if there is an
+ * intermediate flush.
+ */
+}
+
+#ifdef CONFIG_MMU_GATHER_NO_RANGE
+
+#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma)
+#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma()
+#endif
+
+/*
+ * When an architecture does not have efficient means of range flushing TLBs
+ * there is no point in doing intermediate flushes on tlb_end_vma() to keep the
+ * range small. We equally don't have to worry about page granularity or other
+ * things.
+ *
+ * All we need to do is issue a full flush for any !0 range.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+ if (tlb->end)
+ flush_tlb_mm(tlb->mm);
+}
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#define tlb_end_vma tlb_end_vma
+static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#else /* CONFIG_MMU_GATHER_NO_RANGE */
+
+#ifndef tlb_flush
+
+#if defined(tlb_start_vma) || defined(tlb_end_vma)
+#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma()
+#endif
+
+/*
+ * When an architecture does not provide its own tlb_flush() implementation
+ * but does have a reasonably efficient flush_vma_range() implementation
+ * use that.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+ if (tlb->fullmm || tlb->need_flush_all) {
+ flush_tlb_mm(tlb->mm);
+ } else if (tlb->end) {
+ struct vm_area_struct vma = {
+ .vm_mm = tlb->mm,
+ .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) |
+ (tlb->vma_huge ? VM_HUGETLB : 0),
+ };
+
+ flush_tlb_range(&vma, tlb->start, tlb->end);
+ }
}
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+ /*
+ * flush_tlb_range() implementations that look at VM_HUGETLB (tile,
+ * mips-4k) flush only large pages.
+ *
+ * flush_tlb_range() implementations that flush I-TLB also flush D-TLB
+ * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing
+ * range.
+ *
+ * We rely on tlb_end_vma() to issue a flush, such that when we reset
+ * these values the batch is empty.
+ */
+ tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB);
+ tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
+}
+
+#else
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#endif
+
+#endif /* CONFIG_MMU_GATHER_NO_RANGE */
+
static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
{
if (!tlb->end)
return tlb_remove_page_size(tlb, page, PAGE_SIZE);
}
-#ifndef tlb_remove_check_page_size_change
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
+static inline void tlb_change_page_size(struct mmu_gather *tlb,
unsigned int page_size)
{
- /*
- * We don't care about page size change, just update
- * mmu_gather page size here so that debug checks
- * doesn't throw false warning.
- */
-#ifdef CONFIG_DEBUG_VM
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+ if (tlb->page_size && tlb->page_size != page_size) {
+ if (!tlb->fullmm)
+ tlb_flush_mmu(tlb);
+ }
+
tlb->page_size = page_size;
#endif
}
-#endif
static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb)
{
* the vmas are adjusted to only cover the region to be torn down.
*/
#ifndef tlb_start_vma
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#endif
+static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+ if (tlb->fullmm)
+ return;
-#define __tlb_end_vma(tlb, vma) \
- do { \
- if (!tlb->fullmm) \
- tlb_flush_mmu_tlbonly(tlb); \
- } while (0)
+ tlb_update_vma_flags(tlb, vma);
+ flush_cache_range(vma, vma->vm_start, vma->vm_end);
+}
+#endif
#ifndef tlb_end_vma
-#define tlb_end_vma __tlb_end_vma
+static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+ if (tlb->fullmm)
+ return;
+
+ /*
+ * Do a TLB flush and reset the range at VMA boundaries; this avoids
+ * the ranges growing with the unused space between consecutive VMAs,
+ * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on
+ * this.
+ */
+ tlb_flush_mmu_tlbonly(tlb);
+}
#endif
#ifndef __tlb_remove_tlb_entry
#endif /* CONFIG_MMU */
-#define tlb_migrate_finish(mm) do {} while (0)
-
#endif /* _ASM_GENERIC__TLB_H */
/**
* Protected by ttm_global_mutex.
*/
- unsigned int use_count;
struct list_head device_list;
/**
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018-2019 SiFive, Inc.
+ * Wesley Terpstra
+ * Paul Walmsley
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H
+#define __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H
+
+/* Clock indexes for use by Device Tree data and the PRCI driver */
+
+#define PRCI_CLK_COREPLL 0
+#define PRCI_CLK_DDRPLL 1
+#define PRCI_CLK_GEMGXLPLL 2
+#define PRCI_CLK_TLCLK 3
+
+#endif
struct rcu_head rcu_head;
wait_queue_head_t mq_freeze_wq;
struct percpu_ref q_usage_counter;
- struct list_head all_q_node;
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
} \
_out: \
rcu_read_unlock(); \
- preempt_enable_no_resched(); \
+ preempt_enable(); \
_ret; \
})
bv->bv_page = nth_page(bv->bv_page, 1);
bv->bv_offset = 0;
} else {
- bv->bv_page = bvec->bv_page;
- bv->bv_offset = bvec->bv_offset;
+ bv->bv_page = bvec_nth_page(bvec->bv_page, bvec->bv_offset /
+ PAGE_SIZE);
+ bv->bv_offset = bvec->bv_offset & ~PAGE_MASK;
}
bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset,
bvec->bv_len - iter_all->done);
return true;
}
+static inline int clk_set_rate_range(struct clk *clk, unsigned long min,
+ unsigned long max)
+{
+ return 0;
+}
+
+static inline int clk_set_min_rate(struct clk *clk, unsigned long rate)
+{
+ return 0;
+}
+
+static inline int clk_set_max_rate(struct clk *clk, unsigned long rate)
+{
+ return 0;
+}
+
static inline int clk_set_parent(struct clk *clk, struct clk *parent)
{
return 0;
.line = __LINE__, \
}; \
______r = !!(cond); \
- ______f.miss_hit[______r]++; \
+ ______r ? ______f.miss_hit[1]++ : ______f.miss_hit[0]++;\
______r; \
}))
#endif /* CONFIG_PROFILE_ALL_BRANCHES */
return freeze_secondary_cpus(0);
}
extern void enable_nonboot_cpus(void);
+
+static inline int suspend_disable_secondary_cpus(void)
+{
+ int cpu = 0;
+
+ if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU))
+ cpu = -1;
+
+ return freeze_secondary_cpus(cpu);
+}
+static inline void suspend_enable_secondary_cpus(void)
+{
+ return enable_nonboot_cpus();
+}
+
#else /* !CONFIG_PM_SLEEP_SMP */
static inline int disable_nonboot_cpus(void) { return 0; }
static inline void enable_nonboot_cpus(void) {}
+static inline int suspend_disable_secondary_cpus(void) { return 0; }
+static inline void suspend_enable_secondary_cpus(void) { }
#endif /* !CONFIG_PM_SLEEP_SMP */
void cpu_startup_entry(enum cpuhp_state state);
CPU_SMT_DISABLED,
CPU_SMT_FORCE_DISABLED,
CPU_SMT_NOT_SUPPORTED,
+ CPU_SMT_NOT_IMPLEMENTED,
};
#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
extern void cpu_smt_disable(bool force);
extern void cpu_smt_check_topology(void);
#else
-# define cpu_smt_control (CPU_SMT_ENABLED)
+# define cpu_smt_control (CPU_SMT_NOT_IMPLEMENTED)
static inline void cpu_smt_disable(bool force) { }
static inline void cpu_smt_check_topology(void) { }
#endif
+/*
+ * These are used for a global "mitigations=" cmdline option for toggling
+ * optional CPU mitigations.
+ */
+enum cpu_mitigations {
+ CPU_MITIGATIONS_OFF,
+ CPU_MITIGATIONS_AUTO,
+ CPU_MITIGATIONS_AUTO_NOSMT,
+};
+
+extern enum cpu_mitigations cpu_mitigations;
+
+/* mitigations=off */
+static inline bool cpu_mitigations_off(void)
+{
+ return cpu_mitigations == CPU_MITIGATIONS_OFF;
+}
+
+/* mitigations=auto,nosmt */
+static inline bool cpu_mitigations_auto_nosmt(void)
+{
+ return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
+}
+
#endif /* _LINUX_CPU_H_ */
extern const char * dmi_get_system_info(int field);
extern const struct dmi_device * dmi_find_device(int type, const char *name,
const struct dmi_device *from);
-extern void dmi_scan_machine(void);
-extern void dmi_memdev_walk(void);
-extern void dmi_set_dump_stack_arch_desc(void);
+extern void dmi_setup(void);
extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp);
extern int dmi_get_bios_year(void);
extern int dmi_name_in_vendors(const char *str);
static inline const char * dmi_get_system_info(int field) { return NULL; }
static inline const struct dmi_device * dmi_find_device(int type, const char *name,
const struct dmi_device *from) { return NULL; }
-static inline void dmi_scan_machine(void) { return; }
-static inline void dmi_memdev_walk(void) { }
-static inline void dmi_set_dump_stack_arch_desc(void) { }
+static inline void dmi_setup(void) { }
static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp)
{
if (yearp)
struct screen_info *si, efi_guid_t *proto,
unsigned long size);
-bool efi_runtime_disabled(void);
+#ifdef CONFIG_EFI
+extern bool efi_runtime_disabled(void);
+#else
+static inline bool efi_runtime_disabled(void) { return true; }
+#endif
+
extern void efi_call_virt_check_flags(unsigned long flags, const char *call);
extern unsigned long efi_call_virt_save_flags(void);
void (*exit_sched)(struct elevator_queue *);
int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
+ void (*depth_updated)(struct blk_mq_hw_ctx *);
bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);
u64_to_ether_addr(u, addr);
}
+/**
+ * eth_addr_inc() - Increment the given MAC address.
+ * @addr: Pointer to a six-byte array containing Ethernet address to increment.
+ */
+static inline void eth_addr_inc(u8 *addr)
+{
+ u64 u = ether_addr_to_u64(addr);
+
+ u++;
+ u64_to_ether_addr(u, addr);
+}
+
/**
* is_etherdev_addr - Tell if given Ethernet address belongs to the device.
* @dev: Pointer to a device structure
#ifdef CONFIG_STACK_TRACER
-#define STACK_TRACE_ENTRIES 500
-
-struct stack_trace;
-
-extern unsigned stack_trace_index[];
-extern struct stack_trace stack_trace_max;
-extern unsigned long stack_trace_max_size;
-extern arch_spinlock_t stack_trace_max_lock;
-
extern int stack_tracer_enabled;
-void stack_trace_print(void);
-int
-stack_trace_sysctl(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos);
+
+int stack_trace_sysctl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
/* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
DECLARE_PER_CPU(int, disable_stack_tracer);
extern void tasklet_init(struct tasklet_struct *t,
void (*func)(unsigned long), unsigned long data);
-struct tasklet_hrtimer {
- struct hrtimer timer;
- struct tasklet_struct tasklet;
- enum hrtimer_restart (*function)(struct hrtimer *);
-};
-
-extern void
-tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
- enum hrtimer_restart (*function)(struct hrtimer *),
- clockid_t which_clock, enum hrtimer_mode mode);
-
-static inline
-void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
- const enum hrtimer_mode mode)
-{
- hrtimer_start(&ttimer->timer, time, mode);
-}
-
-static inline
-void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
-{
- hrtimer_cancel(&ttimer->timer);
- tasklet_kill(&ttimer->tasklet);
-}
-
/*
* Autoprobing for irqs:
*
struct delayed_work work;
};
-extern void static_key_slow_dec_deferred(struct static_key_deferred *key);
-extern void static_key_deferred_flush(struct static_key_deferred *key);
+struct static_key_true_deferred {
+ struct static_key_true key;
+ unsigned long timeout;
+ struct delayed_work work;
+};
+
+struct static_key_false_deferred {
+ struct static_key_false key;
+ unsigned long timeout;
+ struct delayed_work work;
+};
+
+#define static_key_slow_dec_deferred(x) \
+ __static_key_slow_dec_deferred(&(x)->key, &(x)->work, (x)->timeout)
+#define static_branch_slow_dec_deferred(x) \
+ __static_key_slow_dec_deferred(&(x)->key.key, &(x)->work, (x)->timeout)
+
+#define static_key_deferred_flush(x) \
+ __static_key_deferred_flush((x), &(x)->work)
+
+extern void
+__static_key_slow_dec_deferred(struct static_key *key,
+ struct delayed_work *work,
+ unsigned long timeout);
+extern void __static_key_deferred_flush(void *key, struct delayed_work *work);
extern void
jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl);
+extern void jump_label_update_timeout(struct work_struct *work);
+
+#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl) \
+ struct static_key_true_deferred name = { \
+ .key = { STATIC_KEY_INIT_TRUE }, \
+ .timeout = (rl), \
+ .work = __DELAYED_WORK_INITIALIZER((name).work, \
+ jump_label_update_timeout, \
+ 0), \
+ }
+
+#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl) \
+ struct static_key_false_deferred name = { \
+ .key = { STATIC_KEY_INIT_FALSE }, \
+ .timeout = (rl), \
+ .work = __DELAYED_WORK_INITIALIZER((name).work, \
+ jump_label_update_timeout, \
+ 0), \
+ }
+
+#define static_branch_deferred_inc(x) static_branch_inc(&(x)->key)
+
#else /* !CONFIG_JUMP_LABEL */
struct static_key_deferred {
struct static_key key;
};
+struct static_key_true_deferred {
+ struct static_key_true key;
+};
+struct static_key_false_deferred {
+ struct static_key_false key;
+};
+#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl) \
+ struct static_key_true_deferred name = { STATIC_KEY_TRUE_INIT }
+#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl) \
+ struct static_key_false_deferred name = { STATIC_KEY_FALSE_INIT }
+
+#define static_branch_slow_dec_deferred(x) static_branch_dec(&(x)->key)
+
static inline void static_key_slow_dec_deferred(struct static_key_deferred *key)
{
STATIC_KEY_CHECK_USE(key);
static_key_slow_dec(&key->key);
}
-static inline void static_key_deferred_flush(struct static_key_deferred *key)
+static inline void static_key_deferred_flush(void *key)
{
STATIC_KEY_CHECK_USE(key);
}
struct kretprobe *rp;
kprobe_opcode_t *ret_addr;
struct task_struct *task;
+ void *fp;
char data[0];
};
#include <linux/irqbypass.h>
#include <linux/swait.h>
#include <linux/refcount.h>
+#include <linux/nospec.h>
#include <asm/signal.h>
#include <linux/kvm.h>
static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
{
- /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case
- * the caller has read kvm->online_vcpus before (as is the case
- * for kvm_for_each_vcpu, for example).
- */
+ int num_vcpus = atomic_read(&kvm->online_vcpus);
+ i = array_index_nospec(i, num_vcpus);
+
+ /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */
smp_rmb();
return kvm->vcpus[i];
}
static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
{
+ as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
lockdep_is_held(&kvm->slots_lock) ||
!refcount_read(&kvm->users_count));
extern struct lock_class_key __lockdep_no_validate__;
+struct lock_trace {
+ unsigned int nr_entries;
+ unsigned int offset;
+};
+
#define LOCKSTAT_POINTS 4
/*
* IRQ/softirq usage tracking bits:
*/
unsigned long usage_mask;
- struct stack_trace usage_traces[XXX_LOCK_USAGE_STATES];
+ struct lock_trace usage_traces[XXX_LOCK_USAGE_STATES];
/*
* Generation counter, when doing certain classes of graph walking,
struct list_head entry;
struct lock_class *class;
struct lock_class *links_to;
- struct stack_trace trace;
+ struct lock_trace trace;
int distance;
/*
#define NIL_COOKIE (struct pin_cookie){ }
-#define lockdep_pin_lock(l) ({ struct pin_cookie cookie; cookie; })
+#define lockdep_pin_lock(l) ({ struct pin_cookie cookie = { }; cookie; })
#define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0)
#define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0)
* @IFF_FAILOVER: device is a failover master device
* @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
* @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
+ * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running
*/
enum netdev_priv_flags {
IFF_802_1Q_VLAN = 1<<0,
IFF_FAILOVER = 1<<27,
IFF_FAILOVER_SLAVE = 1<<28,
IFF_L3MDEV_RX_HANDLER = 1<<29,
+ IFF_LIVE_RENAME_OK = 1<<30,
};
#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
#define IFF_FAILOVER IFF_FAILOVER
#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE
#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER
+#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK
/**
* struct net_device - The DEVICE structure.
#define PERF_PMU_CAP_NO_INTERRUPT 0x01
#define PERF_PMU_CAP_NO_NMI 0x02
#define PERF_PMU_CAP_AUX_NO_SG 0x04
-#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x08
#define PERF_PMU_CAP_EXCLUSIVE 0x10
#define PERF_PMU_CAP_ITRACE 0x20
#define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40
/**
* struct perf_addr_filter - address range filter definition
* @entry: event's filter list linkage
- * @inode: object file's inode for file-based filters
+ * @path: object file's path for file-based filters
* @offset: filter range offset
* @size: filter range size (size==0 means single address trigger)
* @action: filter/start/stop
extern void perf_sched_cb_inc(struct pmu *pmu);
extern int perf_event_task_disable(void);
extern int perf_event_task_enable(void);
+
+extern void perf_pmu_resched(struct pmu *pmu);
+
extern int perf_event_refresh(struct perf_event *event, int refresh);
extern void perf_event_update_userpage(struct perf_event *event);
extern int perf_event_release_kernel(struct perf_event *event);
#endif
/*
- * Take a snapshot of the regs. Skip ip and frame pointer to
- * the nth caller. We only need a few of the regs:
+ * When generating a perf sample in-line, instead of from an interrupt /
+ * exception, we lack a pt_regs. This is typically used from software events
+ * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints.
+ *
+ * We typically don't need a full set, but (for x86) do require:
* - ip for PERF_SAMPLE_IP
* - cs for user_mode() tests
- * - bp for callchains
- * - eflags, for future purposes, just in case
+ * - sp for PERF_SAMPLE_CALLCHAIN
+ * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs())
+ *
+ * NOTE: assumes @regs is otherwise already 0 filled; this is important for
+ * things like PERF_SAMPLE_REGS_INTR.
*/
static inline void perf_fetch_caller_regs(struct pt_regs *regs)
{
bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
+int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *);
void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
void pipe_buf_mark_unmergeable(struct pipe_buffer *buf);
static inline bool
rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f)
{
- if (READ_ONCE(rhp->func) == f)
+ rcu_callback_t func = READ_ONCE(rhp->func);
+
+ if (func == f)
return true;
- WARN_ON_ONCE(READ_ONCE(rhp->func) != (rcu_callback_t)~0L);
+ WARN_ON_ONCE(func != (rcu_callback_t)~0L);
return false;
}
* awoken.
*/
struct rcuwait {
- struct task_struct *task;
+ struct task_struct __rcu *task;
};
#define __RCUWAIT_INITIALIZER(name) \
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/* rwsem-spinlock.h: fallback C implementation
- *
- * Copyright (c) 2001 David Howells (dhowells@redhat.com).
- * - Derived partially from ideas by Andrea Arcangeli <andrea@suse.de>
- * - Derived also from comments by Linus
- */
-
-#ifndef _LINUX_RWSEM_SPINLOCK_H
-#define _LINUX_RWSEM_SPINLOCK_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-/*
- * the rw-semaphore definition
- * - if count is 0 then there are no active readers or writers
- * - if count is +ve then that is the number of active readers
- * - if count is -1 then there is one active writer
- * - if wait_list is not empty, then there are processes waiting for the semaphore
- */
-struct rw_semaphore {
- __s32 count;
- raw_spinlock_t wait_lock;
- struct list_head wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- struct lockdep_map dep_map;
-#endif
-};
-
-#define RWSEM_UNLOCKED_VALUE 0x00000000
-
-extern void __down_read(struct rw_semaphore *sem);
-extern int __must_check __down_read_killable(struct rw_semaphore *sem);
-extern int __down_read_trylock(struct rw_semaphore *sem);
-extern void __down_write(struct rw_semaphore *sem);
-extern int __must_check __down_write_killable(struct rw_semaphore *sem);
-extern int __down_write_trylock(struct rw_semaphore *sem);
-extern void __up_read(struct rw_semaphore *sem);
-extern void __up_write(struct rw_semaphore *sem);
-extern void __downgrade_write(struct rw_semaphore *sem);
-extern int rwsem_is_locked(struct rw_semaphore *sem);
-
-#endif /* __KERNEL__ */
-#endif /* _LINUX_RWSEM_SPINLOCK_H */
#include <linux/osq_lock.h>
#endif
-struct rw_semaphore;
-
-#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
-#include <linux/rwsem-spinlock.h> /* use a generic implementation */
-#define __RWSEM_INIT_COUNT(name) .count = RWSEM_UNLOCKED_VALUE
-#else
-/* All arch specific implementations share the same struct */
+/*
+ * For an uncontended rwsem, count and owner are the only fields a task
+ * needs to touch when acquiring the rwsem. So they are put next to each
+ * other to increase the chance that they will share the same cacheline.
+ *
+ * In a contended rwsem, the owner is likely the most frequently accessed
+ * field in the structure as the optimistic waiter that holds the osq lock
+ * will spin on owner. For an embedded rwsem, other hot fields in the
+ * containing structure should be moved further away from the rwsem to
+ * reduce the chance that they will share the same cacheline causing
+ * cacheline bouncing problem.
+ */
struct rw_semaphore {
atomic_long_t count;
- struct list_head wait_list;
- raw_spinlock_t wait_lock;
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
- struct optimistic_spin_queue osq; /* spinner MCS lock */
/*
* Write owner. Used as a speculative check to see
* if the owner is running on the cpu.
*/
struct task_struct *owner;
+ struct optimistic_spin_queue osq; /* spinner MCS lock */
#endif
+ raw_spinlock_t wait_lock;
+ struct list_head wait_list;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif
*/
#define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-2L)
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-/* Include the arch specific part */
-#include <asm/rwsem.h>
-
/* In all implementations count != 0 means locked */
static inline int rwsem_is_locked(struct rw_semaphore *sem)
{
return atomic_long_read(&sem->count) != 0;
}
+#define RWSEM_UNLOCKED_VALUE 0L
#define __RWSEM_INIT_COUNT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE)
-#endif
/* Common initializer macros and functions */
#ifdef CONFIG_RSEQ
struct rseq __user *rseq;
- u32 rseq_len;
u32 rseq_sig;
/*
* RmW on rseq_event_mask must be performed atomically
{
if (clone_flags & CLONE_THREAD) {
t->rseq = NULL;
- t->rseq_len = 0;
t->rseq_sig = 0;
t->rseq_event_mask = 0;
} else {
t->rseq = current->rseq;
- t->rseq_len = current->rseq_len;
t->rseq_sig = current->rseq_sig;
t->rseq_event_mask = current->rseq_event_mask;
}
static inline void rseq_execve(struct task_struct *t)
{
t->rseq = NULL;
- t->rseq_len = 0;
t->rseq_sig = 0;
t->rseq_event_mask = 0;
}
__mmdrop(mm);
}
+/*
+ * This has to be called after a get_task_mm()/mmget_not_zero()
+ * followed by taking the mmap_sem for writing before modifying the
+ * vmas or anything the coredump pretends not to change from under it.
+ *
+ * NOTE: find_extend_vma() called from GUP context is the only place
+ * that can modify the "mm" (notably the vm_start/end) under mmap_sem
+ * for reading and outside the context of the process, so it is also
+ * the only case that holds the mmap_sem for reading that must call
+ * this function. Generally if the mmap_sem is hold for reading
+ * there's no need of this check after get_task_mm()/mmget_not_zero().
+ *
+ * This function can be obsoleted and the check can be removed, after
+ * the coredump code will hold the mmap_sem for writing before
+ * invoking the ->core_dump methods.
+ */
+static inline bool mmget_still_valid(struct mm_struct *mm)
+{
+ return likely(!mm->core_state);
+}
+
/**
* mmget() - Pin the address space associated with a &struct mm_struct.
* @mm: The address space to pin.
struct sched_domain {
/* These fields must be setup */
- struct sched_domain *parent; /* top domain must be null terminated */
- struct sched_domain *child; /* bottom domain must be null terminated */
+ struct sched_domain __rcu *parent; /* top domain must be null terminated */
+ struct sched_domain __rcu *child; /* bottom domain must be null terminated */
struct sched_group *groups; /* the balancing groups of the domain */
unsigned long min_interval; /* Minimum balance interval ms */
unsigned long max_interval; /* Maximum balance interval ms */
struct list_head swaplist; /* chain of maybes on swap */
struct shared_policy policy; /* NUMA memory alloc policy */
struct simple_xattrs xattrs; /* list of xattrs */
+ atomic_t stop_eviction; /* hold when working on inode */
struct inode vfs_inode;
};
* @thread_comm: The base name of the thread
*/
struct smp_hotplug_thread {
- struct task_struct __percpu **store;
+ struct task_struct * __percpu *store;
struct list_head list;
int (*thread_should_run)(unsigned int cpu);
void (*thread_fn)(unsigned int cpu);
void call_srcu(struct srcu_struct *ssp, struct rcu_head *head,
void (*func)(struct rcu_head *head));
-void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced);
+void cleanup_srcu_struct(struct srcu_struct *ssp);
int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp);
void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp);
void synchronize_srcu(struct srcu_struct *ssp);
-/**
- * cleanup_srcu_struct - deconstruct a sleep-RCU structure
- * @ssp: structure to clean up.
- *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.
- */
-static inline void cleanup_srcu_struct(struct srcu_struct *ssp)
-{
- _cleanup_srcu_struct(ssp, false);
-}
-
-/**
- * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure
- * @ssp: structure to clean up.
- *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory. Also,
- * all grace-period processing must have completed.
- *
- * "Completed" means that the last synchronize_srcu() and
- * synchronize_srcu_expedited() calls must have returned before the call
- * to cleanup_srcu_struct_quiesced(). It also means that the callback
- * from the last call_srcu() must have been invoked before the call to
- * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help
- * with this last. Violating these rules will get you a WARN_ON() splat
- * (with high probability, anyway), and will also cause the srcu_struct
- * to be leaked.
- */
-static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *ssp)
-{
- _cleanup_srcu_struct(ssp, true);
-}
-
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
typedef u32 depot_stack_handle_t;
-struct stack_trace;
+depot_stack_handle_t stack_depot_save(unsigned long *entries,
+ unsigned int nr_entries, gfp_t gfp_flags);
-depot_stack_handle_t depot_save_stack(struct stack_trace *trace, gfp_t flags);
-
-void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace);
+unsigned int stack_depot_fetch(depot_stack_handle_t handle,
+ unsigned long **entries);
#endif
#define __LINUX_STACKTRACE_H
#include <linux/types.h>
+#include <asm/errno.h>
struct task_struct;
struct pt_regs;
#ifdef CONFIG_STACKTRACE
+void stack_trace_print(unsigned long *trace, unsigned int nr_entries,
+ int spaces);
+int stack_trace_snprint(char *buf, size_t size, unsigned long *entries,
+ unsigned int nr_entries, int spaces);
+unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+ unsigned int skipnr);
+unsigned int stack_trace_save_tsk(struct task_struct *task,
+ unsigned long *store, unsigned int size,
+ unsigned int skipnr);
+unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
+ unsigned int size, unsigned int skipnr);
+unsigned int stack_trace_save_user(unsigned long *store, unsigned int size);
+
+/* Internal interfaces. Do not use in generic code */
+#ifdef CONFIG_ARCH_STACKWALK
+
+/**
+ * stack_trace_consume_fn - Callback for arch_stack_walk()
+ * @cookie: Caller supplied pointer handed back by arch_stack_walk()
+ * @addr: The stack entry address to consume
+ * @reliable: True when the stack entry is reliable. Required by
+ * some printk based consumers.
+ *
+ * Return: True, if the entry was consumed or skipped
+ * False, if there is no space left to store
+ */
+typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr,
+ bool reliable);
+/**
+ * arch_stack_walk - Architecture specific function to walk the stack
+ * @consume_entry: Callback which is invoked by the architecture code for
+ * each entry.
+ * @cookie: Caller supplied pointer which is handed back to
+ * @consume_entry
+ * @task: Pointer to a task struct, can be NULL
+ * @regs: Pointer to registers, can be NULL
+ *
+ * ============ ======= ============================================
+ * task regs
+ * ============ ======= ============================================
+ * task NULL Stack trace from task (can be current)
+ * current regs Stack trace starting on regs->stackpointer
+ * ============ ======= ============================================
+ */
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+ struct task_struct *task, struct pt_regs *regs);
+int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie,
+ struct task_struct *task);
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+ const struct pt_regs *regs);
+
+#else /* CONFIG_ARCH_STACKWALK */
struct stack_trace {
unsigned int nr_entries, max_entries;
unsigned long *entries;
struct stack_trace *trace);
extern int save_stack_trace_tsk_reliable(struct task_struct *tsk,
struct stack_trace *trace);
-
-extern void print_stack_trace(struct stack_trace *trace, int spaces);
-extern int snprint_stack_trace(char *buf, size_t size,
- struct stack_trace *trace, int spaces);
-
-#ifdef CONFIG_USER_STACKTRACE_SUPPORT
extern void save_stack_trace_user(struct stack_trace *trace);
+#endif /* !CONFIG_ARCH_STACKWALK */
+#endif /* CONFIG_STACKTRACE */
+
+#if defined(CONFIG_STACKTRACE) && defined(CONFIG_HAVE_RELIABLE_STACKTRACE)
+int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
+ unsigned int size);
#else
-# define save_stack_trace_user(trace) do { } while (0)
+static inline int stack_trace_save_tsk_reliable(struct task_struct *tsk,
+ unsigned long *store,
+ unsigned int size)
+{
+ return -ENOSYS;
+}
#endif
-#else /* !CONFIG_STACKTRACE */
-# define save_stack_trace(trace) do { } while (0)
-# define save_stack_trace_tsk(tsk, trace) do { } while (0)
-# define save_stack_trace_user(trace) do { } while (0)
-# define print_stack_trace(trace, spaces) do { } while (0)
-# define snprint_stack_trace(buf, size, trace, spaces) do { } while (0)
-# define save_stack_trace_tsk_reliable(tsk, trace) ({ -ENOSYS; })
-#endif /* CONFIG_STACKTRACE */
-
#endif /* __LINUX_STACKTRACE_H */
static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { }
#endif /* BROADCAST */
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_offline_cpu(unsigned int cpu);
+#else
+static inline void tick_offline_cpu(unsigned int cpu) { }
+#endif
+
#ifdef CONFIG_GENERIC_CLOCKEVENTS
extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state);
#else
#define KTIME_MAX ((s64)~((u64)1 << 63))
#define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC)
+/*
+ * Limits for settimeofday():
+ *
+ * To prevent setting the time close to the wraparound point time setting
+ * is limited so a reasonable uptime can be accomodated. Uptime of 30 years
+ * should be really sufficient, which means the cutoff is 2232. At that
+ * point the cutoff is just a small part of the larger problem.
+ */
+#define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600)
+#define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX)
+
static inline int timespec64_equal(const struct timespec64 *a,
const struct timespec64 *b)
{
return true;
}
+static inline bool timespec64_valid_settod(const struct timespec64 *ts)
+{
+ if (!timespec64_valid(ts))
+ return false;
+ /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */
+ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX)
+ return false;
+ return true;
+}
+
/**
* timespec64_to_ns - Convert timespec64 to nanoseconds
* @ts: pointer to the timespec64 variable to be converted
#define user_access_end() do { } while (0)
#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0)
#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0)
+static inline unsigned long user_access_save(void) { return 0UL; }
+static inline void user_access_restore(unsigned long flags) { }
#endif
#ifdef CONFIG_HARDENED_USERCOPY
static inline enum iter_type iov_iter_type(const struct iov_iter *i)
{
- return i->type & ~(READ | WRITE);
+ return i->type & ~(READ | WRITE | ITER_BVEC_FLAG_NO_REF);
}
static inline bool iter_is_iovec(const struct iov_iter *i)
* @dev: driver model's view of this device
* @usb_dev: if an interface is bound to the USB major, this will point
* to the sysfs representation for that device.
- * @pm_usage_cnt: PM usage counter for this interface
* @reset_ws: Used for scheduling resets from atomic context.
* @resetting_device: USB core reset the device, so use alt setting 0 as
* current; needs bandwidth alloc after reset.
struct device dev; /* interface specific device info */
struct device *usb_dev;
- atomic_t pm_usage_cnt; /* usage counter for autosuspend */
struct work_struct reset_ws; /* for resets in atomic context */
};
#define to_usb_interface(d) container_of(d, struct usb_interface, dev)
rxrpc_user_attach_call_t, unsigned long, gfp_t,
unsigned int);
void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
-u32 rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *);
+bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *,
+ u32 *);
void rxrpc_kernel_probe_life(struct socket *, struct rxrpc_call *);
u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *);
bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *,
ktime_t *);
+bool rxrpc_kernel_call_is_complete(struct rxrpc_call *);
#endif /* _NET_RXRPC_H */
#define wiphy_info(wiphy, format, args...) \
dev_info(&(wiphy)->dev, format, ##args)
+#define wiphy_err_ratelimited(wiphy, format, args...) \
+ dev_err_ratelimited(&(wiphy)->dev, format, ##args)
+#define wiphy_warn_ratelimited(wiphy, format, args...) \
+ dev_warn_ratelimited(&(wiphy)->dev, format, ##args)
+
#define wiphy_debug(wiphy, format, args...) \
wiphy_printk(KERN_DEBUG, wiphy, format, ##args)
* @hw: pointer as obtained from ieee80211_alloc_hw()
* @ac: AC number to return packets from.
*
- * Should only be called between calls to ieee80211_txq_schedule_start()
- * and ieee80211_txq_schedule_end().
* Returns the next txq if successful, %NULL if no queue is eligible. If a txq
* is returned, it should be returned with ieee80211_return_txq() after the
* driver has finished scheduling it.
struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac);
/**
- * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq()
- *
- * @hw: pointer as obtained from ieee80211_alloc_hw()
- * @txq: pointer obtained from station or virtual interface
- *
- * Should only be called between calls to ieee80211_txq_schedule_start()
- * and ieee80211_txq_schedule_end().
- */
-void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq);
-
-/**
- * ieee80211_txq_schedule_start - acquire locks for safe scheduling of an AC
+ * ieee80211_txq_schedule_start - start new scheduling round for TXQs
*
* @hw: pointer as obtained from ieee80211_alloc_hw()
* @ac: AC number to acquire locks for
*
- * Acquire locks needed to schedule TXQs from the given AC. Should be called
- * before ieee80211_next_txq() or ieee80211_return_txq().
+ * Should be called before ieee80211_next_txq() or ieee80211_return_txq().
+ * The driver must not call multiple TXQ scheduling rounds concurrently.
*/
-void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
- __acquires(txq_lock);
+void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac);
+
+/* (deprecated) */
+static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
+{
+}
+
+void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
+ struct ieee80211_txq *txq, bool force);
/**
- * ieee80211_txq_schedule_end - release locks for safe scheduling of an AC
+ * ieee80211_schedule_txq - schedule a TXQ for transmission
*
* @hw: pointer as obtained from ieee80211_alloc_hw()
- * @ac: AC number to acquire locks for
+ * @txq: pointer obtained from station or virtual interface
*
- * Release locks previously acquired by ieee80211_txq_schedule_end().
+ * Schedules a TXQ for transmission if it is not already scheduled,
+ * even if mac80211 does not have any packets buffered.
+ *
+ * The driver may call this function if it has buffered packets for
+ * this TXQ internally.
*/
-void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
- __releases(txq_lock);
+static inline void
+ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
+{
+ __ieee80211_schedule_txq(hw, txq, true);
+}
/**
- * ieee80211_schedule_txq - schedule a TXQ for transmission
+ * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq()
*
* @hw: pointer as obtained from ieee80211_alloc_hw()
* @txq: pointer obtained from station or virtual interface
+ * @force: schedule txq even if mac80211 does not have any buffered packets.
*
- * Schedules a TXQ for transmission if it is not already scheduled. Takes a
- * lock, which means it must *not* be called between
- * ieee80211_txq_schedule_start() and ieee80211_txq_schedule_end()
+ * The driver may set force=true if it has buffered packets for this TXQ
+ * internally.
*/
-void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
- __acquires(txq_lock) __releases(txq_lock);
+static inline void
+ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq,
+ bool force)
+{
+ __ieee80211_schedule_txq(hw, txq, force);
+}
/**
* ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit
gfp_t flags);
void nf_ct_tmpl_free(struct nf_conn *tmpl);
+u32 nf_ct_get_id(const struct nf_conn *ct);
+
static inline void
nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info)
{
bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_tuple *orig);
+int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb,
+ unsigned int dataoff,
+ const struct nf_hook_state *state,
+ u8 l4proto,
+ union nf_inet_addr *outer_daddr);
+
int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
struct sk_buff *skb,
unsigned int dataoff,
int nr_t1timer_running(struct sock *);
/* sysctl_net_netrom.c */
-void nr_register_sysctl(void);
+int nr_register_sysctl(void);
void nr_unregister_sysctl(void);
#endif
SCTP_CMD_T1_RETRAN, /* Mark for retransmission after T1 timeout */
SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
SCTP_CMD_SEND_MSG, /* Send the whole use message */
- SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/
SCTP_CMD_SET_ASOC, /* Restore association context */
SCTP_CMD_LAST
* @p: poll_table
*
* See the comments in the wq_has_sleeper function.
- *
- * Do not derive sock from filp->private_data here. An SMC socket establishes
- * an internal TCP socket that is used in the fallback case. All socket
- * operations on the SMC socket are then forwarded to the TCP socket. In case of
- * poll, the filp->private_data pointer references the SMC socket because the
- * TCP socket has no file assigned.
*/
static inline void sock_poll_wait(struct file *filp, struct socket *sock,
poll_table *p)
int tls_device_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
void tls_device_sk_destruct(struct sock *sk);
+void tls_device_free_resources_tx(struct sock *sk);
void tls_device_init(void);
void tls_device_cleanup(void);
int tls_tx_records(struct sock *sk, int flags);
int flags);
int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
int flags);
+bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
static inline struct tls_msg *tls_msg(struct sk_buff *skb)
{
static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
{
#ifdef CONFIG_SOCK_VALIDATE_XMIT
- return sk_fullsock(sk) &
+ return sk_fullsock(sk) &&
(smp_load_acquire(&sk->sk_validate_xmit_skb) ==
&tls_validate_xmit_skb);
#else
struct xfrm_stats stats;
struct xfrm_lifetime_cur curlft;
- struct tasklet_hrtimer mtimer;
+ struct hrtimer mtimer;
struct xfrm_state_offload xso;
};
struct xfrm_if_cb {
- struct xfrm_if *(*decode_session)(struct sk_buff *skb);
+ struct xfrm_if *(*decode_session)(struct sk_buff *skb,
+ unsigned short family);
};
void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb);
return atomic_read(&x->tunnel_users);
}
+static inline bool xfrm_id_proto_valid(u8 proto)
+{
+ switch (proto) {
+ case IPPROTO_AH:
+ case IPPROTO_ESP:
+ case IPPROTO_COMP:
+#if IS_ENABLED(CONFIG_IPV6)
+ case IPPROTO_ROUTING:
+ case IPPROTO_DSTOPTS:
+#endif
+ return true;
+ default:
+ return false;
+ }
+}
+
+/* IPSEC_PROTO_ANY only matches 3 IPsec protocols, 0 could match all. */
static inline int xfrm_id_proto_match(u8 proto, u8 userproto)
{
return (!userproto || proto == userproto ||
__entry->flags = flags;
),
- TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
+ TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
__entry->timer, __entry->function, __entry->expires,
(long)__entry->expires - __entry->now,
__entry->flags & TIMER_CPUMASK,
*/
TRACE_EVENT(timer_expire_entry,
- TP_PROTO(struct timer_list *timer),
+ TP_PROTO(struct timer_list *timer, unsigned long baseclk),
- TP_ARGS(timer),
+ TP_ARGS(timer, baseclk),
TP_STRUCT__entry(
__field( void *, timer )
__field( unsigned long, now )
__field( void *, function)
+ __field( unsigned long, baseclk )
),
TP_fast_assign(
__entry->timer = timer;
__entry->now = jiffies;
__entry->function = timer->function;
+ __entry->baseclk = baseclk;
),
- TP_printk("timer=%p function=%pf now=%lu", __entry->timer, __entry->function,__entry->now)
+ TP_printk("timer=%p function=%ps now=%lu baseclk=%lu",
+ __entry->timer, __entry->function, __entry->now,
+ __entry->baseclk)
);
/**
__entry->mode = mode;
),
- TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu "
+ TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu "
"mode=%s", __entry->hrtimer, __entry->function,
(unsigned long long) __entry->expires,
(unsigned long long) __entry->softexpires,
__entry->function = hrtimer->function;
),
- TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function,
+ TP_printk("hrtimer=%p function=%ps now=%llu",
+ __entry->hrtimer, __entry->function,
(unsigned long long) __entry->now)
);
#define KEY_TITLE 0x171
#define KEY_SUBTITLE 0x172
#define KEY_ANGLE 0x173
-#define KEY_ZOOM 0x174
+#define KEY_FULL_SCREEN 0x174 /* AC View Toggle */
+#define KEY_ZOOM KEY_FULL_SCREEN
#define KEY_MODE 0x175
#define KEY_KEYBOARD 0x176
-#define KEY_SCREEN 0x177
+#define KEY_ASPECT_RATIO 0x177 /* HUTRR37: Aspect */
+#define KEY_SCREEN KEY_ASPECT_RATIO
#define KEY_PC 0x178 /* Media Select Computer */
#define KEY_TV 0x179 /* Media Select TV */
#define KEY_TV2 0x17a /* Media Select Cable */
MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP = 1 << 0,
MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD = 1 << 1,
MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE = 1 << 2,
+ MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT = 1 << 3,
};
enum mlx5_ib_tunnel_offloads {
page_alloc_init();
pr_notice("Kernel command line: %s\n", boot_command_line);
+ /* parameters may set static keys */
+ jump_label_init();
parse_early_param();
after_dashes = parse_args("Booting kernel",
static_command_line, __start___param,
parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
NULL, set_init_arg);
- jump_label_init();
-
/*
* These use large bootmem allocations and must precede
* kmem_cache_init()
config RWSEM_SPIN_ON_OWNER
def_bool y
- depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
+ depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW
config LOCK_SPIN_ON_OWNER
def_bool y
# Don't self-instrument.
KCOV_INSTRUMENT_kcov.o := n
KASAN_SANITIZE_kcov.o := n
+CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
# cond_syscall is currently not LTO compatible
CFLAGS_sys_ni.o = $(DISABLE_LTO)
#ifdef CONFIG_STACKTRACE
static void backtrace_test_saved(void)
{
- struct stack_trace trace;
unsigned long entries[8];
+ unsigned int nr_entries;
pr_info("Testing a saved backtrace.\n");
pr_info("The following trace is a kernel self test and not a bug!\n");
- trace.nr_entries = 0;
- trace.max_entries = ARRAY_SIZE(entries);
- trace.entries = entries;
- trace.skip = 0;
-
- save_stack_trace(&trace);
- print_stack_trace(&trace, 0);
+ nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+ stack_trace_print(entries, nr_entries, 0);
}
#else
static void backtrace_test_saved(void)
return 0;
}
+static void __find_good_pkt_pointers(struct bpf_func_state *state,
+ struct bpf_reg_state *dst_reg,
+ enum bpf_reg_type type, u16 new_range)
+{
+ struct bpf_reg_state *reg;
+ int i;
+
+ for (i = 0; i < MAX_BPF_REG; i++) {
+ reg = &state->regs[i];
+ if (reg->type == type && reg->id == dst_reg->id)
+ /* keep the maximum range already checked */
+ reg->range = max(reg->range, new_range);
+ }
+
+ bpf_for_each_spilled_reg(i, state, reg) {
+ if (!reg)
+ continue;
+ if (reg->type == type && reg->id == dst_reg->id)
+ reg->range = max(reg->range, new_range);
+ }
+}
+
static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
struct bpf_reg_state *dst_reg,
enum bpf_reg_type type,
bool range_right_open)
{
- struct bpf_func_state *state = vstate->frame[vstate->curframe];
- struct bpf_reg_state *regs = state->regs, *reg;
u16 new_range;
- int i, j;
+ int i;
if (dst_reg->off < 0 ||
(dst_reg->off == 0 && range_right_open))
* the range won't allow anything.
* dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
*/
- for (i = 0; i < MAX_BPF_REG; i++)
- if (regs[i].type == type && regs[i].id == dst_reg->id)
- /* keep the maximum range already checked */
- regs[i].range = max(regs[i].range, new_range);
-
- for (j = 0; j <= vstate->curframe; j++) {
- state = vstate->frame[j];
- bpf_for_each_spilled_reg(i, state, reg) {
- if (!reg)
- continue;
- if (reg->type == type && reg->id == dst_reg->id)
- reg->range = max(reg->range, new_range);
- }
- }
+ for (i = 0; i <= vstate->curframe; i++)
+ __find_good_pkt_pointers(vstate->frame[i], dst_reg, type,
+ new_range);
}
/* compute branch direction of the expression "if (reg opcode val) goto target;"
}
}
+static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id,
+ bool is_null)
+{
+ struct bpf_reg_state *reg;
+ int i;
+
+ for (i = 0; i < MAX_BPF_REG; i++)
+ mark_ptr_or_null_reg(state, &state->regs[i], id, is_null);
+
+ bpf_for_each_spilled_reg(i, state, reg) {
+ if (!reg)
+ continue;
+ mark_ptr_or_null_reg(state, reg, id, is_null);
+ }
+}
+
/* The logic is similar to find_good_pkt_pointers(), both could eventually
* be folded together at some point.
*/
bool is_null)
{
struct bpf_func_state *state = vstate->frame[vstate->curframe];
- struct bpf_reg_state *reg, *regs = state->regs;
+ struct bpf_reg_state *regs = state->regs;
u32 ref_obj_id = regs[regno].ref_obj_id;
u32 id = regs[regno].id;
- int i, j;
+ int i;
if (ref_obj_id && ref_obj_id == id && is_null)
/* regs[regno] is in the " == NULL" branch.
*/
WARN_ON_ONCE(release_reference_state(state, id));
- for (i = 0; i < MAX_BPF_REG; i++)
- mark_ptr_or_null_reg(state, ®s[i], id, is_null);
-
- for (j = 0; j <= vstate->curframe; j++) {
- state = vstate->frame[j];
- bpf_for_each_spilled_reg(i, state, reg) {
- if (!reg)
- continue;
- mark_ptr_or_null_reg(state, reg, id, is_null);
- }
- }
+ for (i = 0; i <= vstate->curframe; i++)
+ __mark_ptr_or_null_regs(vstate->frame[i], id, is_null);
}
static bool try_match_pkt_pointers(const struct bpf_insn *insn,
* Must be called with cpuset_mutex held.
*
* The three key local variables below are:
- * q - a linked-list queue of cpuset pointers, used to implement a
- * top-down scan of all cpusets. This scan loads a pointer
- * to each cpuset marked is_sched_load_balance into the
- * array 'csa'. For our purposes, rebuilding the schedulers
- * sched domains, we can ignore !is_sched_load_balance cpusets.
+ * cp - cpuset pointer, used (together with pos_css) to perform a
+ * top-down scan of all cpusets. For our purposes, rebuilding
+ * the schedulers sched domains, we can ignore !is_sched_load_
+ * balance cpusets.
* csa - (for CpuSet Array) Array of pointers to all the cpusets
* that need to be load balanced, for convenient iterative
* access by the subsequent code that finds the best partition,
static int generate_sched_domains(cpumask_var_t **domains,
struct sched_domain_attr **attributes)
{
- struct cpuset *cp; /* scans q */
+ struct cpuset *cp; /* top-down scan of cpusets */
struct cpuset **csa; /* array of all cpuset ptrs */
int csn; /* how many cpuset ptrs in csa so far */
int i, j, k; /* indices for partition finding loops */
#include <linux/notifier.h>
#include <linux/sched/signal.h>
#include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
#include <linux/sched/task.h>
#include <linux/sched/smt.h>
#include <linux/unistd.h>
/* Give up timekeeping duties */
tick_handover_do_timer();
+ /* Remove CPU from timer broadcasting */
+ tick_offline_cpu(cpu);
/* Park the stopper thread */
stop_machine_park(cpu);
return 0;
int cpu, error = 0;
cpu_maps_update_begin();
- if (!cpu_online(primary))
+ if (primary == -1) {
primary = cpumask_first(cpu_online_mask);
+ if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
+ primary = housekeeping_any_cpu(HK_FLAG_TIMER);
+ } else {
+ if (!cpu_online(primary))
+ primary = cpumask_first(cpu_online_mask);
+ }
+
/*
* We take down all of the non-boot CPUs in one shot to avoid races
* with the userspace trying to use the CPU hotplug at the same time
#ifdef CONFIG_HOTPLUG_SMT
-static const char *smt_states[] = {
- [CPU_SMT_ENABLED] = "on",
- [CPU_SMT_DISABLED] = "off",
- [CPU_SMT_FORCE_DISABLED] = "forceoff",
- [CPU_SMT_NOT_SUPPORTED] = "notsupported",
-};
-
-static ssize_t
-show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
-{
- return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
-}
-
static void cpuhp_offline_cpu_device(unsigned int cpu)
{
struct device *dev = get_cpu_device(cpu);
return ret;
}
+
static ssize_t
-store_smt_control(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+__store_smt_control(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
int ctrlval, ret;
unlock_device_hotplug();
return ret ? ret : count;
}
+
+#else /* !CONFIG_HOTPLUG_SMT */
+static ssize_t
+__store_smt_control(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ return -ENODEV;
+}
+#endif /* CONFIG_HOTPLUG_SMT */
+
+static const char *smt_states[] = {
+ [CPU_SMT_ENABLED] = "on",
+ [CPU_SMT_DISABLED] = "off",
+ [CPU_SMT_FORCE_DISABLED] = "forceoff",
+ [CPU_SMT_NOT_SUPPORTED] = "notsupported",
+ [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented",
+};
+
+static ssize_t
+show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ const char *state = smt_states[cpu_smt_control];
+
+ return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
+}
+
+static ssize_t
+store_smt_control(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ return __store_smt_control(dev, attr, buf, count);
+}
static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
static ssize_t
show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
{
- bool active = topology_max_smt_threads() > 1;
-
- return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
+ return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active());
}
static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
NULL
};
-static int __init cpu_smt_state_init(void)
+static int __init cpu_smt_sysfs_init(void)
{
return sysfs_create_group(&cpu_subsys.dev_root->kobj,
&cpuhp_smt_attr_group);
}
-#else
-static inline int cpu_smt_state_init(void) { return 0; }
-#endif
-
static int __init cpuhp_sysfs_init(void)
{
int cpu, ret;
- ret = cpu_smt_state_init();
+ ret = cpu_smt_sysfs_init();
if (ret)
return ret;
return 0;
}
device_initcall(cpuhp_sysfs_init);
-#endif
+#endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */
/*
* cpu_bit_bitmap[] is a special, "compressed" data structure that
#endif
this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
}
+
+enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
+
+static int __init mitigations_parse_cmdline(char *arg)
+{
+ if (!strcmp(arg, "off"))
+ cpu_mitigations = CPU_MITIGATIONS_OFF;
+ else if (!strcmp(arg, "auto"))
+ cpu_mitigations = CPU_MITIGATIONS_AUTO;
+ else if (!strcmp(arg, "auto,nosmt"))
+ cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
+
+ return 0;
+}
+early_param("mitigations", mitigations_parse_cmdline);
int sg_mapped_ents;
enum map_err_types map_err_type;
#ifdef CONFIG_STACKTRACE
- struct stack_trace stacktrace;
- unsigned long st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
+ unsigned int stack_len;
+ unsigned long stack_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
#endif
};
#ifdef CONFIG_STACKTRACE
if (entry) {
pr_warning("Mapped at:\n");
- print_stack_trace(&entry->stacktrace, 0);
+ stack_trace_print(entry->stack_entries, entry->stack_len, 0);
}
#endif
}
spin_unlock_irqrestore(&free_entries_lock, flags);
#ifdef CONFIG_STACKTRACE
- entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
- entry->stacktrace.entries = entry->st_entries;
- entry->stacktrace.skip = 1;
- save_stack_trace(&entry->stacktrace);
+ entry->stack_len = stack_trace_save(entry->stack_entries,
+ ARRAY_SIZE(entry->stack_entries),
+ 1);
#endif
-
return entry;
}
perf_pmu_enable(cpuctx->ctx.pmu);
}
+void perf_pmu_resched(struct pmu *pmu)
+{
+ struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+ struct perf_event_context *task_ctx = cpuctx->task_ctx;
+
+ perf_ctx_lock(cpuctx, task_ctx);
+ ctx_resched(cpuctx, task_ctx, EVENT_ALL|EVENT_CPU);
+ perf_ctx_unlock(cpuctx, task_ctx);
+}
+
/*
* Cross CPU call to install and enable a performance event
*
if (task == TASK_TOMBSTONE)
return;
- if (!ifh->nr_file_filters)
- return;
-
- mm = get_task_mm(event->ctx->task);
- if (!mm)
- goto restart;
+ if (ifh->nr_file_filters) {
+ mm = get_task_mm(event->ctx->task);
+ if (!mm)
+ goto restart;
- down_read(&mm->mmap_sem);
+ down_read(&mm->mmap_sem);
+ }
raw_spin_lock_irqsave(&ifh->lock, flags);
list_for_each_entry(filter, &ifh->list, entry) {
- event->addr_filter_ranges[count].start = 0;
- event->addr_filter_ranges[count].size = 0;
+ if (filter->path.dentry) {
+ /*
+ * Adjust base offset if the filter is associated to a
+ * binary that needs to be mapped:
+ */
+ event->addr_filter_ranges[count].start = 0;
+ event->addr_filter_ranges[count].size = 0;
- /*
- * Adjust base offset if the filter is associated to a binary
- * that needs to be mapped:
- */
- if (filter->path.dentry)
perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]);
+ } else {
+ event->addr_filter_ranges[count].start = filter->offset;
+ event->addr_filter_ranges[count].size = filter->size;
+ }
count++;
}
event->addr_filters_gen++;
raw_spin_unlock_irqrestore(&ifh->lock, flags);
- up_read(&mm->mmap_sem);
+ if (ifh->nr_file_filters) {
+ up_read(&mm->mmap_sem);
- mmput(mm);
+ mmput(mm);
+ }
restart:
perf_event_stop(event, 1);
}
}
-void perf_swevent_init_cpu(unsigned int cpu)
+static void perf_swevent_init_cpu(unsigned int cpu)
{
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
rb->aux_head += size;
}
- if (size || handle->aux_flags) {
- /*
- * Only send RECORD_AUX if we have something useful to communicate
- *
- * Note: the OVERWRITE records by themselves are not considered
- * useful, as they don't communicate any *new* information,
- * aside from the short-lived offset, that becomes history at
- * the next event sched-in and therefore isn't useful.
- * The userspace that needs to copy out AUX data in overwrite
- * mode should know to use user_page::aux_head for the actual
- * offset. So, from now on we don't output AUX records that
- * have *only* OVERWRITE flag set.
- */
-
- if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
- perf_event_aux_event(handle->event, aux_head, size,
- handle->aux_flags);
- }
+ /*
+ * Only send RECORD_AUX if we have something useful to communicate
+ *
+ * Note: the OVERWRITE records by themselves are not considered
+ * useful, as they don't communicate any *new* information,
+ * aside from the short-lived offset, that becomes history at
+ * the next event sched-in and therefore isn't useful.
+ * The userspace that needs to copy out AUX data in overwrite
+ * mode should know to use user_page::aux_head for the actual
+ * offset. So, from now on we don't output AUX records that
+ * have *only* OVERWRITE flag set.
+ */
+ if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE))
+ perf_event_aux_event(handle->event, aux_head, size,
+ handle->aux_flags);
rb->user_page->aux_head = rb->aux_head;
if (rb_need_aux_wakeup(rb))
* PMU requests more than one contiguous chunks of memory
* for SW double buffering
*/
- if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
- !overwrite) {
+ if (!overwrite) {
if (!max_order)
return -EINVAL;
*
* MEMREMAP_WB - matches the default mapping for System RAM on
* the architecture. This is usually a read-allocate write-back cache.
- * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM
+ * Moreover, if MEMREMAP_WB is specified and the requested remap region is RAM
* memremap() will bypass establishing a new mapping and instead return
* a pointer into the direct map.
*
/* Try all mapping types requested until one returns non-NULL */
if (flags & MEMREMAP_WB) {
/*
- * MEMREMAP_WB is special in that it can be satisifed
+ * MEMREMAP_WB is special in that it can be satisfied
* from the direct map. Some archs depend on the
* capability of memremap() to autodetect cases where
* the requested range is potentially in System RAM.
irq_flow_handler_t handler)
{
struct irq_chip_generic *gc;
- unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type);
- gc = devm_kzalloc(dev, sz, GFP_KERNEL);
+ gc = devm_kzalloc(dev, struct_size(gc, chip_types, num_ct), GFP_KERNEL);
if (gc)
irq_init_generic_chip(gc, name, num_ct,
irq_base, reg_base, handler);
desc->affinity_notify = notify;
raw_spin_unlock_irqrestore(&desc->lock, flags);
- if (old_notify)
+ if (old_notify) {
+ cancel_work_sync(&old_notify->work);
kref_put(&old_notify->kref, old_notify->release);
+ }
return 0;
}
#include <linux/idr.h>
#include <linux/irq.h>
#include <linux/math64.h>
+#include <linux/log2.h>
#include <trace/events/irq.h>
DEFINE_PER_CPU(struct irq_timings, irq_timings);
-struct irqt_stat {
- u64 next_evt;
- u64 last_ts;
- u64 variance;
- u32 avg;
- u32 nr_samples;
- int anomalies;
- int valid;
-};
-
static DEFINE_IDR(irqt_stats);
void irq_timings_enable(void)
static_branch_disable(&irq_timing_enabled);
}
-/**
- * irqs_update - update the irq timing statistics with a new timestamp
+/*
+ * The main goal of this algorithm is to predict the next interrupt
+ * occurrence on the current CPU.
+ *
+ * Currently, the interrupt timings are stored in a circular array
+ * buffer every time there is an interrupt, as a tuple: the interrupt
+ * number and the associated timestamp when the event occurred <irq,
+ * timestamp>.
+ *
+ * For every interrupt occurring in a short period of time, we can
+ * measure the elapsed time between the occurrences for the same
+ * interrupt and we end up with a suite of intervals. The experience
+ * showed the interrupts are often coming following a periodic
+ * pattern.
+ *
+ * The objective of the algorithm is to find out this periodic pattern
+ * in a fastest way and use its period to predict the next irq event.
+ *
+ * When the next interrupt event is requested, we are in the situation
+ * where the interrupts are disabled and the circular buffer
+ * containing the timings is filled with the events which happened
+ * after the previous next-interrupt-event request.
+ *
+ * At this point, we read the circular buffer and we fill the irq
+ * related statistics structure. After this step, the circular array
+ * containing the timings is empty because all the values are
+ * dispatched in their corresponding buffers.
+ *
+ * Now for each interrupt, we can predict the next event by using the
+ * suffix array, log interval and exponential moving average
+ *
+ * 1. Suffix array
+ *
+ * Suffix array is an array of all the suffixes of a string. It is
+ * widely used as a data structure for compression, text search, ...
+ * For instance for the word 'banana', the suffixes will be: 'banana'
+ * 'anana' 'nana' 'ana' 'na' 'a'
+ *
+ * Usually, the suffix array is sorted but for our purpose it is
+ * not necessary and won't provide any improvement in the context of
+ * the solved problem where we clearly define the boundaries of the
+ * search by a max period and min period.
+ *
+ * The suffix array will build a suite of intervals of different
+ * length and will look for the repetition of each suite. If the suite
+ * is repeating then we have the period because it is the length of
+ * the suite whatever its position in the buffer.
+ *
+ * 2. Log interval
+ *
+ * We saw the irq timings allow to compute the interval of the
+ * occurrences for a specific interrupt. We can reasonibly assume the
+ * longer is the interval, the higher is the error for the next event
+ * and we can consider storing those interval values into an array
+ * where each slot in the array correspond to an interval at the power
+ * of 2 of the index. For example, index 12 will contain values
+ * between 2^11 and 2^12.
+ *
+ * At the end we have an array of values where at each index defines a
+ * [2^index - 1, 2 ^ index] interval values allowing to store a large
+ * number of values inside a small array.
+ *
+ * For example, if we have the value 1123, then we store it at
+ * ilog2(1123) = 10 index value.
+ *
+ * Storing those value at the specific index is done by computing an
+ * exponential moving average for this specific slot. For instance,
+ * for values 1800, 1123, 1453, ... fall under the same slot (10) and
+ * the exponential moving average is computed every time a new value
+ * is stored at this slot.
+ *
+ * 3. Exponential Moving Average
+ *
+ * The EMA is largely used to track a signal for stocks or as a low
+ * pass filter. The magic of the formula, is it is very simple and the
+ * reactivity of the average can be tuned with the factors called
+ * alpha.
+ *
+ * The higher the alphas are, the faster the average respond to the
+ * signal change. In our case, if a slot in the array is a big
+ * interval, we can have numbers with a big difference between
+ * them. The impact of those differences in the average computation
+ * can be tuned by changing the alpha value.
+ *
+ *
+ * -- The algorithm --
+ *
+ * We saw the different processing above, now let's see how they are
+ * used together.
+ *
+ * For each interrupt:
+ * For each interval:
+ * Compute the index = ilog2(interval)
+ * Compute a new_ema(buffer[index], interval)
+ * Store the index in a circular buffer
+ *
+ * Compute the suffix array of the indexes
+ *
+ * For each suffix:
+ * If the suffix is reverse-found 3 times
+ * Return suffix
+ *
+ * Return Not found
+ *
+ * However we can not have endless suffix array to be build, it won't
+ * make sense and it will add an extra overhead, so we can restrict
+ * this to a maximum suffix length of 5 and a minimum suffix length of
+ * 2. The experience showed 5 is the majority of the maximum pattern
+ * period found for different devices.
+ *
+ * The result is a pattern finding less than 1us for an interrupt.
*
- * @irqs: an irqt_stat struct pointer
- * @ts: the new timestamp
+ * Example based on real values:
*
- * The statistics are computed online, in other words, the code is
- * designed to compute the statistics on a stream of values rather
- * than doing multiple passes on the values to compute the average,
- * then the variance. The integer division introduces a loss of
- * precision but with an acceptable error margin regarding the results
- * we would have with the double floating precision: we are dealing
- * with nanosec, so big numbers, consequently the mantisse is
- * negligeable, especially when converting the time in usec
- * afterwards.
+ * Example 1 : MMC write/read interrupt interval:
*
- * The computation happens at idle time. When the CPU is not idle, the
- * interrupts' timestamps are stored in the circular buffer, when the
- * CPU goes idle and this routine is called, all the buffer's values
- * are injected in the statistical model continuying to extend the
- * statistics from the previous busy-idle cycle.
+ * 223947, 1240, 1384, 1386, 1386,
+ * 217416, 1236, 1384, 1386, 1387,
+ * 214719, 1241, 1386, 1387, 1384,
+ * 213696, 1234, 1384, 1386, 1388,
+ * 219904, 1240, 1385, 1389, 1385,
+ * 212240, 1240, 1386, 1386, 1386,
+ * 214415, 1236, 1384, 1386, 1387,
+ * 214276, 1234, 1384, 1388, ?
*
- * The observations showed a device will trigger a burst of periodic
- * interrupts followed by one or two peaks of longer time, for
- * instance when a SD card device flushes its cache, then the periodic
- * intervals occur again. A one second inactivity period resets the
- * stats, that gives us the certitude the statistical values won't
- * exceed 1x10^9, thus the computation won't overflow.
+ * For each element, apply ilog2(value)
*
- * Basically, the purpose of the algorithm is to watch the periodic
- * interrupts and eliminate the peaks.
+ * 15, 8, 8, 8, 8,
+ * 15, 8, 8, 8, 8,
+ * 15, 8, 8, 8, 8,
+ * 15, 8, 8, 8, 8,
+ * 15, 8, 8, 8, 8,
+ * 15, 8, 8, 8, 8,
+ * 15, 8, 8, 8, 8,
+ * 15, 8, 8, 8, ?
*
- * An interrupt is considered periodically stable if the interval of
- * its occurences follow the normal distribution, thus the values
- * comply with:
+ * Max period of 5, we take the last (max_period * 3) 15 elements as
+ * we can be confident if the pattern repeats itself three times it is
+ * a repeating pattern.
*
- * avg - 3 x stddev < value < avg + 3 x stddev
+ * 8,
+ * 15, 8, 8, 8, 8,
+ * 15, 8, 8, 8, 8,
+ * 15, 8, 8, 8, ?
*
- * Which can be simplified to:
+ * Suffixes are:
*
- * -3 x stddev < value - avg < 3 x stddev
+ * 1) 8, 15, 8, 8, 8 <- max period
+ * 2) 8, 15, 8, 8
+ * 3) 8, 15, 8
+ * 4) 8, 15 <- min period
*
- * abs(value - avg) < 3 x stddev
+ * From there we search the repeating pattern for each suffix.
*
- * In order to save a costly square root computation, we use the
- * variance. For the record, stddev = sqrt(variance). The equation
- * above becomes:
+ * buffer: 8, 15, 8, 8, 8, 8, 15, 8, 8, 8, 8, 15, 8, 8, 8
+ * | | | | | | | | | | | | | | |
+ * 8, 15, 8, 8, 8 | | | | | | | | | |
+ * 8, 15, 8, 8, 8 | | | | |
+ * 8, 15, 8, 8, 8
*
- * abs(value - avg) < 3 x sqrt(variance)
+ * When moving the suffix, we found exactly 3 matches.
*
- * And finally we square it:
+ * The first suffix with period 5 is repeating.
*
- * (value - avg) ^ 2 < (3 x sqrt(variance)) ^ 2
+ * The next event is (3 * max_period) % suffix_period
*
- * (value - avg) x (value - avg) < 9 x variance
+ * In this example, the result 0, so the next event is suffix[0] => 8
*
- * Statistically speaking, any values out of this interval is
- * considered as an anomaly and is discarded. However, a normal
- * distribution appears when the number of samples is 30 (it is the
- * rule of thumb in statistics, cf. "30 samples" on Internet). When
- * there are three consecutive anomalies, the statistics are resetted.
+ * However, 8 is the index in the array of exponential moving average
+ * which was calculated on the fly when storing the values, so the
+ * interval is ema[8] = 1366
*
+ *
+ * Example 2:
+ *
+ * 4, 3, 5, 100,
+ * 3, 3, 5, 117,
+ * 4, 4, 5, 112,
+ * 4, 3, 4, 110,
+ * 3, 5, 3, 117,
+ * 4, 4, 5, 112,
+ * 4, 3, 4, 110,
+ * 3, 4, 5, 112,
+ * 4, 3, 4, 110
+ *
+ * ilog2
+ *
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4
+ *
+ * Max period 5:
+ * 0, 0, 4,
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4,
+ * 0, 0, 0, 4
+ *
+ * Suffixes:
+ *
+ * 1) 0, 0, 4, 0, 0
+ * 2) 0, 0, 4, 0
+ * 3) 0, 0, 4
+ * 4) 0, 0
+ *
+ * buffer: 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4
+ * | | | | | | X
+ * 0, 0, 4, 0, 0, | X
+ * 0, 0
+ *
+ * buffer: 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4
+ * | | | | | | | | | | | | | | |
+ * 0, 0, 4, 0, | | | | | | | | | | |
+ * 0, 0, 4, 0, | | | | | | |
+ * 0, 0, 4, 0, | | |
+ * 0 0 4
+ *
+ * Pattern is found 3 times, the remaining is 1 which results from
+ * (max_period * 3) % suffix_period. This value is the index in the
+ * suffix arrays. The suffix array for a period 4 has the value 4
+ * at index 1.
+ */
+#define EMA_ALPHA_VAL 64
+#define EMA_ALPHA_SHIFT 7
+
+#define PREDICTION_PERIOD_MIN 2
+#define PREDICTION_PERIOD_MAX 5
+#define PREDICTION_FACTOR 4
+#define PREDICTION_MAX 10 /* 2 ^ PREDICTION_MAX useconds */
+#define PREDICTION_BUFFER_SIZE 16 /* slots for EMAs, hardly more than 16 */
+
+struct irqt_stat {
+ u64 last_ts;
+ u64 ema_time[PREDICTION_BUFFER_SIZE];
+ int timings[IRQ_TIMINGS_SIZE];
+ int circ_timings[IRQ_TIMINGS_SIZE];
+ int count;
+};
+
+/*
+ * Exponential moving average computation
*/
-static void irqs_update(struct irqt_stat *irqs, u64 ts)
+static u64 irq_timings_ema_new(u64 value, u64 ema_old)
+{
+ s64 diff;
+
+ if (unlikely(!ema_old))
+ return value;
+
+ diff = (value - ema_old) * EMA_ALPHA_VAL;
+ /*
+ * We can use a s64 type variable to be added with the u64
+ * ema_old variable as this one will never have its topmost
+ * bit set, it will be always smaller than 2^63 nanosec
+ * interrupt interval (292 years).
+ */
+ return ema_old + (diff >> EMA_ALPHA_SHIFT);
+}
+
+static int irq_timings_next_event_index(int *buffer, size_t len, int period_max)
+{
+ int i;
+
+ /*
+ * The buffer contains the suite of intervals, in a ilog2
+ * basis, we are looking for a repetition. We point the
+ * beginning of the search three times the length of the
+ * period beginning at the end of the buffer. We do that for
+ * each suffix.
+ */
+ for (i = period_max; i >= PREDICTION_PERIOD_MIN ; i--) {
+
+ int *begin = &buffer[len - (i * 3)];
+ int *ptr = begin;
+
+ /*
+ * We look if the suite with period 'i' repeat
+ * itself. If it is truncated at the end, as it
+ * repeats we can use the period to find out the next
+ * element.
+ */
+ while (!memcmp(ptr, begin, i * sizeof(*ptr))) {
+ ptr += i;
+ if (ptr >= &buffer[len])
+ return begin[((i * 3) % i)];
+ }
+ }
+
+ return -1;
+}
+
+static u64 __irq_timings_next_event(struct irqt_stat *irqs, int irq, u64 now)
+{
+ int index, i, period_max, count, start, min = INT_MAX;
+
+ if ((now - irqs->last_ts) >= NSEC_PER_SEC) {
+ irqs->count = irqs->last_ts = 0;
+ return U64_MAX;
+ }
+
+ /*
+ * As we want to find three times the repetition, we need a
+ * number of intervals greater or equal to three times the
+ * maximum period, otherwise we truncate the max period.
+ */
+ period_max = irqs->count > (3 * PREDICTION_PERIOD_MAX) ?
+ PREDICTION_PERIOD_MAX : irqs->count / 3;
+
+ /*
+ * If we don't have enough irq timings for this prediction,
+ * just bail out.
+ */
+ if (period_max <= PREDICTION_PERIOD_MIN)
+ return U64_MAX;
+
+ /*
+ * 'count' will depends if the circular buffer wrapped or not
+ */
+ count = irqs->count < IRQ_TIMINGS_SIZE ?
+ irqs->count : IRQ_TIMINGS_SIZE;
+
+ start = irqs->count < IRQ_TIMINGS_SIZE ?
+ 0 : (irqs->count & IRQ_TIMINGS_MASK);
+
+ /*
+ * Copy the content of the circular buffer into another buffer
+ * in order to linearize the buffer instead of dealing with
+ * wrapping indexes and shifted array which will be prone to
+ * error and extremelly difficult to debug.
+ */
+ for (i = 0; i < count; i++) {
+ int index = (start + i) & IRQ_TIMINGS_MASK;
+
+ irqs->timings[i] = irqs->circ_timings[index];
+ min = min_t(int, irqs->timings[i], min);
+ }
+
+ index = irq_timings_next_event_index(irqs->timings, count, period_max);
+ if (index < 0)
+ return irqs->last_ts + irqs->ema_time[min];
+
+ return irqs->last_ts + irqs->ema_time[index];
+}
+
+static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts)
{
u64 old_ts = irqs->last_ts;
- u64 variance = 0;
u64 interval;
- s64 diff;
+ int index;
/*
* The timestamps are absolute time values, we need to compute
* want as we need another timestamp to compute an interval.
*/
if (interval >= NSEC_PER_SEC) {
- memset(irqs, 0, sizeof(*irqs));
- irqs->last_ts = ts;
+ irqs->count = 0;
return;
}
/*
- * Pre-compute the delta with the average as the result is
- * used several times in this function.
- */
- diff = interval - irqs->avg;
-
- /*
- * Increment the number of samples.
- */
- irqs->nr_samples++;
-
- /*
- * Online variance divided by the number of elements if there
- * is more than one sample. Normally the formula is division
- * by nr_samples - 1 but we assume the number of element will be
- * more than 32 and dividing by 32 instead of 31 is enough
- * precise.
- */
- if (likely(irqs->nr_samples > 1))
- variance = irqs->variance >> IRQ_TIMINGS_SHIFT;
-
- /*
- * The rule of thumb in statistics for the normal distribution
- * is having at least 30 samples in order to have the model to
- * apply. Values outside the interval are considered as an
- * anomaly.
- */
- if ((irqs->nr_samples >= 30) && ((diff * diff) > (9 * variance))) {
- /*
- * After three consecutive anomalies, we reset the
- * stats as it is no longer stable enough.
- */
- if (irqs->anomalies++ >= 3) {
- memset(irqs, 0, sizeof(*irqs));
- irqs->last_ts = ts;
- return;
- }
- } else {
- /*
- * The anomalies must be consecutives, so at this
- * point, we reset the anomalies counter.
- */
- irqs->anomalies = 0;
- }
-
- /*
- * The interrupt is considered stable enough to try to predict
- * the next event on it.
+ * Get the index in the ema table for this interrupt. The
+ * PREDICTION_FACTOR increase the interval size for the array
+ * of exponential average.
*/
- irqs->valid = 1;
+ index = likely(interval) ?
+ ilog2((interval >> 10) / PREDICTION_FACTOR) : 0;
/*
- * Online average algorithm:
- *
- * new_average = average + ((value - average) / count)
- *
- * The variance computation depends on the new average
- * to be computed here first.
- *
+ * Store the index as an element of the pattern in another
+ * circular array.
*/
- irqs->avg = irqs->avg + (diff >> IRQ_TIMINGS_SHIFT);
+ irqs->circ_timings[irqs->count & IRQ_TIMINGS_MASK] = index;
- /*
- * Online variance algorithm:
- *
- * new_variance = variance + (value - average) x (value - new_average)
- *
- * Warning: irqs->avg is updated with the line above, hence
- * 'interval - irqs->avg' is no longer equal to 'diff'
- */
- irqs->variance = irqs->variance + (diff * (interval - irqs->avg));
+ irqs->ema_time[index] = irq_timings_ema_new(interval,
+ irqs->ema_time[index]);
- /*
- * Update the next event
- */
- irqs->next_evt = ts + irqs->avg;
+ irqs->count++;
}
/**
*/
lockdep_assert_irqs_disabled();
+ if (!irqts->count)
+ return next_evt;
+
/*
* Number of elements in the circular buffer: If it happens it
* was flushed before, then the number of elements could be
* type but with the cost of extra computation in the
* interrupt handler hot path. We choose efficiency.
*
- * Inject measured irq/timestamp to the statistical model
- * while decrementing the counter because we consume the data
- * from our circular buffer.
+ * Inject measured irq/timestamp to the pattern prediction
+ * model while decrementing the counter because we consume the
+ * data from our circular buffer.
*/
- for (i = irqts->count & IRQ_TIMINGS_MASK,
- irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count);
- irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) {
- irq = irq_timing_decode(irqts->values[i], &ts);
+ i = (irqts->count & IRQ_TIMINGS_MASK) - 1;
+ irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count);
+ for (; irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) {
+ irq = irq_timing_decode(irqts->values[i], &ts);
s = idr_find(&irqt_stats, irq);
- if (s) {
- irqs = this_cpu_ptr(s);
- irqs_update(irqs, ts);
- }
+ if (s)
+ irq_timings_store(irq, this_cpu_ptr(s), ts);
}
/*
irqs = this_cpu_ptr(s);
- if (!irqs->valid)
- continue;
+ ts = __irq_timings_next_event(irqs, i, now);
+ if (ts <= now)
+ return now;
- if (irqs->next_evt <= now) {
- irq = i;
- next_evt = now;
-
- /*
- * This interrupt mustn't use in the future
- * until new events occur and update the
- * statistics.
- */
- irqs->valid = 0;
- break;
- }
-
- if (irqs->next_evt < next_evt) {
- irq = i;
- next_evt = irqs->next_evt;
- }
+ if (ts < next_evt)
+ next_evt = ts;
}
return next_evt;
*/
}
-/*
- * Enqueue the irq_work @work on @cpu unless it's already pending
- * somewhere.
- *
- * Can be re-enqueued while the callback is still in progress.
- */
-bool irq_work_queue_on(struct irq_work *work, int cpu)
+/* Enqueue on current CPU, work must already be claimed and preempt disabled */
+static void __irq_work_queue_local(struct irq_work *work)
{
- /* All work should have been flushed before going offline */
- WARN_ON_ONCE(cpu_is_offline(cpu));
-
-#ifdef CONFIG_SMP
-
- /* Arch remote IPI send/receive backend aren't NMI safe */
- WARN_ON_ONCE(in_nmi());
+ /* If the work is "lazy", handle it from next tick if any */
+ if (work->flags & IRQ_WORK_LAZY) {
+ if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
+ tick_nohz_tick_stopped())
+ arch_irq_work_raise();
+ } else {
+ if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
+ arch_irq_work_raise();
+ }
+}
+/* Enqueue the irq work @work on the current CPU */
+bool irq_work_queue(struct irq_work *work)
+{
/* Only queue if not already pending */
if (!irq_work_claim(work))
return false;
- if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
- arch_send_call_function_single_ipi(cpu);
-
-#else /* #ifdef CONFIG_SMP */
- irq_work_queue(work);
-#endif /* #else #ifdef CONFIG_SMP */
+ /* Queue the entry and raise the IPI if needed. */
+ preempt_disable();
+ __irq_work_queue_local(work);
+ preempt_enable();
return true;
}
+EXPORT_SYMBOL_GPL(irq_work_queue);
-/* Enqueue the irq work @work on the current CPU */
-bool irq_work_queue(struct irq_work *work)
+/*
+ * Enqueue the irq_work @work on @cpu unless it's already pending
+ * somewhere.
+ *
+ * Can be re-enqueued while the callback is still in progress.
+ */
+bool irq_work_queue_on(struct irq_work *work, int cpu)
{
+#ifndef CONFIG_SMP
+ return irq_work_queue(work);
+
+#else /* CONFIG_SMP: */
+ /* All work should have been flushed before going offline */
+ WARN_ON_ONCE(cpu_is_offline(cpu));
+
/* Only queue if not already pending */
if (!irq_work_claim(work))
return false;
- /* Queue the entry and raise the IPI if needed. */
preempt_disable();
-
- /* If the work is "lazy", handle it from next tick if any */
- if (work->flags & IRQ_WORK_LAZY) {
- if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
- tick_nohz_tick_stopped())
- arch_irq_work_raise();
+ if (cpu != smp_processor_id()) {
+ /* Arch remote IPI send/receive backend aren't NMI safe */
+ WARN_ON_ONCE(in_nmi());
+ if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
+ arch_send_call_function_single_ipi(cpu);
} else {
- if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
- arch_irq_work_raise();
+ __irq_work_queue_local(work);
}
-
preempt_enable();
return true;
+#endif /* CONFIG_SMP */
}
-EXPORT_SYMBOL_GPL(irq_work_queue);
+
bool irq_work_needs_cpu(void)
{
}
EXPORT_SYMBOL_GPL(static_key_disable);
-static void __static_key_slow_dec_cpuslocked(struct static_key *key,
- unsigned long rate_limit,
- struct delayed_work *work)
+static bool static_key_slow_try_dec(struct static_key *key)
{
- lockdep_assert_cpus_held();
+ int val;
+
+ val = atomic_fetch_add_unless(&key->enabled, -1, 1);
+ if (val == 1)
+ return false;
/*
* The negative count check is valid even when a negative
* returns is unbalanced, because all other static_key_slow_inc()
* instances block while the update is in progress.
*/
- if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
- WARN(atomic_read(&key->enabled) < 0,
- "jump label: negative count!\n");
+ WARN(val < 0, "jump label: negative count!\n");
+ return true;
+}
+
+static void __static_key_slow_dec_cpuslocked(struct static_key *key)
+{
+ lockdep_assert_cpus_held();
+
+ if (static_key_slow_try_dec(key))
return;
- }
- if (rate_limit) {
- atomic_inc(&key->enabled);
- schedule_delayed_work(work, rate_limit);
- } else {
+ jump_label_lock();
+ if (atomic_dec_and_test(&key->enabled))
jump_label_update(key);
- }
jump_label_unlock();
}
-static void __static_key_slow_dec(struct static_key *key,
- unsigned long rate_limit,
- struct delayed_work *work)
+static void __static_key_slow_dec(struct static_key *key)
{
cpus_read_lock();
- __static_key_slow_dec_cpuslocked(key, rate_limit, work);
+ __static_key_slow_dec_cpuslocked(key);
cpus_read_unlock();
}
-static void jump_label_update_timeout(struct work_struct *work)
+void jump_label_update_timeout(struct work_struct *work)
{
struct static_key_deferred *key =
container_of(work, struct static_key_deferred, work.work);
- __static_key_slow_dec(&key->key, 0, NULL);
+ __static_key_slow_dec(&key->key);
}
+EXPORT_SYMBOL_GPL(jump_label_update_timeout);
void static_key_slow_dec(struct static_key *key)
{
STATIC_KEY_CHECK_USE(key);
- __static_key_slow_dec(key, 0, NULL);
+ __static_key_slow_dec(key);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec);
void static_key_slow_dec_cpuslocked(struct static_key *key)
{
STATIC_KEY_CHECK_USE(key);
- __static_key_slow_dec_cpuslocked(key, 0, NULL);
+ __static_key_slow_dec_cpuslocked(key);
}
-void static_key_slow_dec_deferred(struct static_key_deferred *key)
+void __static_key_slow_dec_deferred(struct static_key *key,
+ struct delayed_work *work,
+ unsigned long timeout)
{
STATIC_KEY_CHECK_USE(key);
- __static_key_slow_dec(&key->key, key->timeout, &key->work);
+
+ if (static_key_slow_try_dec(key))
+ return;
+
+ schedule_delayed_work(work, timeout);
}
-EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
+EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred);
-void static_key_deferred_flush(struct static_key_deferred *key)
+void __static_key_deferred_flush(void *key, struct delayed_work *work)
{
STATIC_KEY_CHECK_USE(key);
- flush_delayed_work(&key->work);
+ flush_delayed_work(work);
}
-EXPORT_SYMBOL_GPL(static_key_deferred_flush);
+EXPORT_SYMBOL_GPL(__static_key_deferred_flush);
void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
error = dpm_suspend_end(PMSG_FREEZE);
if (error)
goto Resume_devices;
- error = disable_nonboot_cpus();
+ error = suspend_disable_secondary_cpus();
if (error)
goto Enable_cpus;
local_irq_disable();
Enable_irqs:
local_irq_enable();
Enable_cpus:
- enable_nonboot_cpus();
+ suspend_enable_secondary_cpus();
dpm_resume_start(PMSG_RESTORE);
Resume_devices:
dpm_resume_end(PMSG_RESTORE);
static int reuse_unused_kprobe(struct kprobe *ap)
{
struct optimized_kprobe *op;
- int ret;
/*
* Unused kprobe MUST be on the way of delayed unoptimizing (means
/* Enable the probe again */
ap->flags &= ~KPROBE_FLAG_DISABLED;
/* Optimize it again (remove from op->list) */
- ret = kprobe_optready(ap);
- if (ret)
- return ret;
+ if (!kprobe_optready(ap))
+ return -EINVAL;
optimize_kprobe(ap);
return 0;
break;
}
- /* 0 and ULONG_MAX entries mean end of backtrace: */
- if (record == 0 || record == ULONG_MAX)
+ /* 0 entry marks end of backtrace: */
+ if (!record)
break;
}
if (same) {
memcpy(&latency_record[i], lat, sizeof(struct latency_record));
}
-/*
- * Iterator to store a backtrace into a latency record entry
- */
-static inline void store_stacktrace(struct task_struct *tsk,
- struct latency_record *lat)
-{
- struct stack_trace trace;
-
- memset(&trace, 0, sizeof(trace));
- trace.max_entries = LT_BACKTRACEDEPTH;
- trace.entries = &lat->backtrace[0];
- save_stack_trace_tsk(tsk, &trace);
-}
-
/**
* __account_scheduler_latency - record an occurred latency
* @tsk - the task struct of the task hitting the latency
lat.count = 1;
lat.time = usecs;
lat.max = usecs;
- store_stacktrace(tsk, &lat);
+
+ stack_trace_save_tsk(tsk, lat.backtrace, LT_BACKTRACEDEPTH, 0);
raw_spin_lock_irqsave(&latency_lock, flags);
break;
}
- /* 0 and ULONG_MAX entries mean end of backtrace: */
- if (record == 0 || record == ULONG_MAX)
+ /* 0 entry is end of backtrace */
+ if (!record)
break;
}
if (same) {
lr->count, lr->time, lr->max);
for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
unsigned long bt = lr->backtrace[q];
+
if (!bt)
break;
- if (bt == ULONG_MAX)
- break;
+
seq_printf(m, " %ps", (void *)bt);
}
seq_puts(m, "\n");
* Determine whether the given stack trace includes any references to a
* to-be-patched or to-be-unpatched function.
*/
-static int klp_check_stack_func(struct klp_func *func,
- struct stack_trace *trace)
+static int klp_check_stack_func(struct klp_func *func, unsigned long *entries,
+ unsigned int nr_entries)
{
unsigned long func_addr, func_size, address;
struct klp_ops *ops;
int i;
- for (i = 0; i < trace->nr_entries; i++) {
- address = trace->entries[i];
+ for (i = 0; i < nr_entries; i++) {
+ address = entries[i];
if (klp_target_state == KLP_UNPATCHED) {
/*
static int klp_check_stack(struct task_struct *task, char *err_buf)
{
static unsigned long entries[MAX_STACK_ENTRIES];
- struct stack_trace trace;
struct klp_object *obj;
struct klp_func *func;
- int ret;
+ int ret, nr_entries;
- trace.skip = 0;
- trace.nr_entries = 0;
- trace.max_entries = MAX_STACK_ENTRIES;
- trace.entries = entries;
- ret = save_stack_trace_tsk_reliable(task, &trace);
+ ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries));
WARN_ON_ONCE(ret == -ENOSYS);
- if (ret) {
+ if (ret < 0) {
snprintf(err_buf, STACK_ERR_BUF_SIZE,
"%s: %s:%d has an unreliable stack\n",
__func__, task->comm, task->pid);
return ret;
}
+ nr_entries = ret;
klp_for_each_object(klp_transition_patch, obj) {
if (!obj->patched)
continue;
klp_for_each_func(obj, func) {
- ret = klp_check_stack_func(func, &trace);
+ ret = klp_check_stack_func(func, entries, nr_entries);
if (ret) {
snprintf(err_buf, STACK_ERR_BUF_SIZE,
"%s: %s:%d is sleeping on function %s\n",
# and is generally not a function of system call inputs.
KCOV_INSTRUMENT := n
-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
+obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o rwsem-xadd.o
ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
-obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
-obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o
+obj-$(CONFIG_LOCK_EVENT_COUNTS) += lock_events.o
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <waiman.long@hpe.com>
+ */
+
+/*
+ * Collect locking event counts
+ */
+#include <linux/debugfs.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/fs.h>
+
+#include "lock_events.h"
+
+#undef LOCK_EVENT
+#define LOCK_EVENT(name) [LOCKEVENT_ ## name] = #name,
+
+#define LOCK_EVENTS_DIR "lock_event_counts"
+
+/*
+ * When CONFIG_LOCK_EVENT_COUNTS is enabled, event counts of different
+ * types of locks will be reported under the <debugfs>/lock_event_counts/
+ * directory. See lock_events_list.h for the list of available locking
+ * events.
+ *
+ * Writing to the special ".reset_counts" file will reset all the above
+ * locking event counts. This is a very slow operation and so should not
+ * be done frequently.
+ *
+ * These event counts are implemented as per-cpu variables which are
+ * summed and computed whenever the corresponding debugfs files are read. This
+ * minimizes added overhead making the counts usable even in a production
+ * environment.
+ */
+static const char * const lockevent_names[lockevent_num + 1] = {
+
+#include "lock_events_list.h"
+
+ [LOCKEVENT_reset_cnts] = ".reset_counts",
+};
+
+/*
+ * Per-cpu counts
+ */
+DEFINE_PER_CPU(unsigned long, lockevents[lockevent_num]);
+
+/*
+ * The lockevent_read() function can be overridden.
+ */
+ssize_t __weak lockevent_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ char buf[64];
+ int cpu, id, len;
+ u64 sum = 0;
+
+ /*
+ * Get the counter ID stored in file->f_inode->i_private
+ */
+ id = (long)file_inode(file)->i_private;
+
+ if (id >= lockevent_num)
+ return -EBADF;
+
+ for_each_possible_cpu(cpu)
+ sum += per_cpu(lockevents[id], cpu);
+ len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum);
+
+ return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+/*
+ * Function to handle write request
+ *
+ * When idx = reset_cnts, reset all the counts.
+ */
+static ssize_t lockevent_write(struct file *file, const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ int cpu;
+
+ /*
+ * Get the counter ID stored in file->f_inode->i_private
+ */
+ if ((long)file_inode(file)->i_private != LOCKEVENT_reset_cnts)
+ return count;
+
+ for_each_possible_cpu(cpu) {
+ int i;
+ unsigned long *ptr = per_cpu_ptr(lockevents, cpu);
+
+ for (i = 0 ; i < lockevent_num; i++)
+ WRITE_ONCE(ptr[i], 0);
+ }
+ return count;
+}
+
+/*
+ * Debugfs data structures
+ */
+static const struct file_operations fops_lockevent = {
+ .read = lockevent_read,
+ .write = lockevent_write,
+ .llseek = default_llseek,
+};
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#include <asm/paravirt.h>
+
+static bool __init skip_lockevent(const char *name)
+{
+ static int pv_on __initdata = -1;
+
+ if (pv_on < 0)
+ pv_on = !pv_is_native_spin_unlock();
+ /*
+ * Skip PV qspinlock events on bare metal.
+ */
+ if (!pv_on && !memcmp(name, "pv_", 3))
+ return true;
+ return false;
+}
+#else
+static inline bool skip_lockevent(const char *name)
+{
+ return false;
+}
+#endif
+
+/*
+ * Initialize debugfs for the locking event counts.
+ */
+static int __init init_lockevent_counts(void)
+{
+ struct dentry *d_counts = debugfs_create_dir(LOCK_EVENTS_DIR, NULL);
+ int i;
+
+ if (!d_counts)
+ goto out;
+
+ /*
+ * Create the debugfs files
+ *
+ * As reading from and writing to the stat files can be slow, only
+ * root is allowed to do the read/write to limit impact to system
+ * performance.
+ */
+ for (i = 0; i < lockevent_num; i++) {
+ if (skip_lockevent(lockevent_names[i]))
+ continue;
+ if (!debugfs_create_file(lockevent_names[i], 0400, d_counts,
+ (void *)(long)i, &fops_lockevent))
+ goto fail_undo;
+ }
+
+ if (!debugfs_create_file(lockevent_names[LOCKEVENT_reset_cnts], 0200,
+ d_counts, (void *)(long)LOCKEVENT_reset_cnts,
+ &fops_lockevent))
+ goto fail_undo;
+
+ return 0;
+fail_undo:
+ debugfs_remove_recursive(d_counts);
+out:
+ pr_warn("Could not create '%s' debugfs entries\n", LOCK_EVENTS_DIR);
+ return -ENOMEM;
+}
+fs_initcall(init_lockevent_counts);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ */
+
+#ifndef __LOCKING_LOCK_EVENTS_H
+#define __LOCKING_LOCK_EVENTS_H
+
+enum lock_events {
+
+#include "lock_events_list.h"
+
+ lockevent_num, /* Total number of lock event counts */
+ LOCKEVENT_reset_cnts = lockevent_num,
+};
+
+#ifdef CONFIG_LOCK_EVENT_COUNTS
+/*
+ * Per-cpu counters
+ */
+DECLARE_PER_CPU(unsigned long, lockevents[lockevent_num]);
+
+/*
+ * Increment the PV qspinlock statistical counters
+ */
+static inline void __lockevent_inc(enum lock_events event, bool cond)
+{
+ if (cond)
+ __this_cpu_inc(lockevents[event]);
+}
+
+#define lockevent_inc(ev) __lockevent_inc(LOCKEVENT_ ##ev, true)
+#define lockevent_cond_inc(ev, c) __lockevent_inc(LOCKEVENT_ ##ev, c)
+
+static inline void __lockevent_add(enum lock_events event, int inc)
+{
+ __this_cpu_add(lockevents[event], inc);
+}
+
+#define lockevent_add(ev, c) __lockevent_add(LOCKEVENT_ ##ev, c)
+
+#else /* CONFIG_LOCK_EVENT_COUNTS */
+
+#define lockevent_inc(ev)
+#define lockevent_add(ev, c)
+#define lockevent_cond_inc(ev, c)
+
+#endif /* CONFIG_LOCK_EVENT_COUNTS */
+#endif /* __LOCKING_LOCK_EVENTS_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ */
+
+#ifndef LOCK_EVENT
+#define LOCK_EVENT(name) LOCKEVENT_ ## name,
+#endif
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+/*
+ * Locking events for PV qspinlock.
+ */
+LOCK_EVENT(pv_hash_hops) /* Average # of hops per hashing operation */
+LOCK_EVENT(pv_kick_unlock) /* # of vCPU kicks issued at unlock time */
+LOCK_EVENT(pv_kick_wake) /* # of vCPU kicks for pv_latency_wake */
+LOCK_EVENT(pv_latency_kick) /* Average latency (ns) of vCPU kick */
+LOCK_EVENT(pv_latency_wake) /* Average latency (ns) of kick-to-wakeup */
+LOCK_EVENT(pv_lock_stealing) /* # of lock stealing operations */
+LOCK_EVENT(pv_spurious_wakeup) /* # of spurious wakeups in non-head vCPUs */
+LOCK_EVENT(pv_wait_again) /* # of wait's after queue head vCPU kick */
+LOCK_EVENT(pv_wait_early) /* # of early vCPU wait's */
+LOCK_EVENT(pv_wait_head) /* # of vCPU wait's at the queue head */
+LOCK_EVENT(pv_wait_node) /* # of vCPU wait's at non-head queue node */
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+/*
+ * Locking events for qspinlock
+ *
+ * Subtracting lock_use_node[234] from lock_slowpath will give you
+ * lock_use_node1.
+ */
+LOCK_EVENT(lock_pending) /* # of locking ops via pending code */
+LOCK_EVENT(lock_slowpath) /* # of locking ops via MCS lock queue */
+LOCK_EVENT(lock_use_node2) /* # of locking ops that use 2nd percpu node */
+LOCK_EVENT(lock_use_node3) /* # of locking ops that use 3rd percpu node */
+LOCK_EVENT(lock_use_node4) /* # of locking ops that use 4th percpu node */
+LOCK_EVENT(lock_no_node) /* # of locking ops w/o using percpu node */
+#endif /* CONFIG_QUEUED_SPINLOCKS */
+
+/*
+ * Locking events for rwsem
+ */
+LOCK_EVENT(rwsem_sleep_reader) /* # of reader sleeps */
+LOCK_EVENT(rwsem_sleep_writer) /* # of writer sleeps */
+LOCK_EVENT(rwsem_wake_reader) /* # of reader wakeups */
+LOCK_EVENT(rwsem_wake_writer) /* # of writer wakeups */
+LOCK_EVENT(rwsem_opt_wlock) /* # of write locks opt-spin acquired */
+LOCK_EVENT(rwsem_opt_fail) /* # of failed opt-spinnings */
+LOCK_EVENT(rwsem_rlock) /* # of read locks acquired */
+LOCK_EVENT(rwsem_rlock_fast) /* # of fast read locks acquired */
+LOCK_EVENT(rwsem_rlock_fail) /* # of failed read lock acquisitions */
+LOCK_EVENT(rwsem_rtrylock) /* # of read trylock calls */
+LOCK_EVENT(rwsem_wlock) /* # of write locks acquired */
+LOCK_EVENT(rwsem_wlock_fail) /* # of failed write lock acquisitions */
+LOCK_EVENT(rwsem_wtrylock) /* # of write trylock calls */
#endif
}
-static int save_trace(struct stack_trace *trace)
+static int save_trace(struct lock_trace *trace)
{
- trace->nr_entries = 0;
- trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
- trace->entries = stack_trace + nr_stack_trace_entries;
-
- trace->skip = 3;
-
- save_stack_trace(trace);
-
- /*
- * Some daft arches put -1 at the end to indicate its a full trace.
- *
- * <rant> this is buggy anyway, since it takes a whole extra entry so a
- * complete trace that maxes out the entries provided will be reported
- * as incomplete, friggin useless </rant>
- */
- if (trace->nr_entries != 0 &&
- trace->entries[trace->nr_entries-1] == ULONG_MAX)
- trace->nr_entries--;
-
- trace->max_entries = trace->nr_entries;
+ unsigned long *entries = stack_trace + nr_stack_trace_entries;
+ unsigned int max_entries;
+ trace->offset = nr_stack_trace_entries;
+ max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
+ trace->nr_entries = stack_trace_save(entries, max_entries, 3);
nr_stack_trace_entries += trace->nr_entries;
if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) {
{
char c = '.';
- if (class->usage_mask & lock_flag(bit + 2))
+ if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK))
c = '+';
if (class->usage_mask & lock_flag(bit)) {
c = '-';
- if (class->usage_mask & lock_flag(bit + 2))
+ if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK))
c = '?';
}
static int add_lock_to_list(struct lock_class *this,
struct lock_class *links_to, struct list_head *head,
unsigned long ip, int distance,
- struct stack_trace *trace)
+ struct lock_trace *trace)
{
struct lock_list *entry;
/*
* checking.
*/
+static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
+{
+ unsigned long *entries = stack_trace + trace->offset;
+
+ stack_trace_print(entries, trace->nr_entries, spaces);
+}
+
/*
* Print a dependency chain entry (this is only done when a deadlock
* has been detected):
printk("\n-> #%u", depth);
print_lock_name(target->class);
printk(KERN_CONT ":\n");
- print_stack_trace(&target->trace, 6);
-
+ print_lock_trace(&target->trace, 6);
return 0;
}
}
static noinline int print_circular_bug(struct lock_list *this,
- struct lock_list *target,
- struct held_lock *check_src,
- struct held_lock *check_tgt,
- struct stack_trace *trace)
+ struct lock_list *target,
+ struct held_lock *check_src,
+ struct held_lock *check_tgt)
{
struct task_struct *curr = current;
struct lock_list *parent;
}
#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+
+static inline int usage_accumulate(struct lock_list *entry, void *mask)
+{
+ *(unsigned long *)mask |= entry->class->usage_mask;
+
+ return 0;
+}
+
/*
* Forwards and backwards subgraph searching, for the purposes of
* proving that two subgraphs can be connected by a new dependency
* without creating any illegal irq-safe -> irq-unsafe lock dependency.
*/
-static inline int usage_match(struct lock_list *entry, void *bit)
+static inline int usage_match(struct lock_list *entry, void *mask)
{
- return entry->class->usage_mask & (1 << (enum lock_usage_bit)bit);
+ return entry->class->usage_mask & *(unsigned long *)mask;
}
-
-
/*
* Find a node in the forwards-direction dependency sub-graph starting
* at @root->class that matches @bit.
* Return <0 on error.
*/
static int
-find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
+find_usage_forwards(struct lock_list *root, unsigned long usage_mask,
struct lock_list **target_entry)
{
int result;
debug_atomic_inc(nr_find_usage_forwards_checks);
- result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
+ result = __bfs_forwards(root, &usage_mask, usage_match, target_entry);
return result;
}
* Return <0 on error.
*/
static int
-find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit,
+find_usage_backwards(struct lock_list *root, unsigned long usage_mask,
struct lock_list **target_entry)
{
int result;
debug_atomic_inc(nr_find_usage_backwards_checks);
- result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
+ result = __bfs_backwards(root, &usage_mask, usage_match, target_entry);
return result;
}
len += printk("%*s %s", depth, "", usage_str[bit]);
len += printk(KERN_CONT " at:\n");
- print_stack_trace(class->usage_traces + bit, len);
+ print_lock_trace(class->usage_traces + bit, len);
}
}
printk("%*s }\n", depth, "");
do {
print_lock_class_header(entry->class, depth);
printk("%*s ... acquired at:\n", depth, "");
- print_stack_trace(&entry->trace, 2);
+ print_lock_trace(&entry->trace, 2);
printk("\n");
if (depth == 0 && (entry != root)) {
print_lock_name(backwards_entry->class);
pr_warn("\n... which became %s-irq-safe at:\n", irqclass);
- print_stack_trace(backwards_entry->class->usage_traces + bit1, 1);
+ print_lock_trace(backwards_entry->class->usage_traces + bit1, 1);
pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass);
print_lock_name(forwards_entry->class);
pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass);
pr_warn("...");
- print_stack_trace(forwards_entry->class->usage_traces + bit2, 1);
+ print_lock_trace(forwards_entry->class->usage_traces + bit2, 1);
pr_warn("\nother info that might help us debug this:\n\n");
print_irq_lock_scenario(backwards_entry, forwards_entry,
return 0;
}
-static int
-check_usage(struct task_struct *curr, struct held_lock *prev,
- struct held_lock *next, enum lock_usage_bit bit_backwards,
- enum lock_usage_bit bit_forwards, const char *irqclass)
-{
- int ret;
- struct lock_list this, that;
- struct lock_list *uninitialized_var(target_entry);
- struct lock_list *uninitialized_var(target_entry1);
-
- this.parent = NULL;
-
- this.class = hlock_class(prev);
- ret = find_usage_backwards(&this, bit_backwards, &target_entry);
- if (ret < 0)
- return print_bfs_bug(ret);
- if (ret == 1)
- return ret;
-
- that.parent = NULL;
- that.class = hlock_class(next);
- ret = find_usage_forwards(&that, bit_forwards, &target_entry1);
- if (ret < 0)
- return print_bfs_bug(ret);
- if (ret == 1)
- return ret;
-
- return print_bad_irq_dependency(curr, &this, &that,
- target_entry, target_entry1,
- prev, next,
- bit_backwards, bit_forwards, irqclass);
-}
-
static const char *state_names[] = {
#define LOCKDEP_STATE(__STATE) \
__stringify(__STATE),
static inline const char *state_name(enum lock_usage_bit bit)
{
- return (bit & LOCK_USAGE_READ_MASK) ? state_rnames[bit >> 2] : state_names[bit >> 2];
+ if (bit & LOCK_USAGE_READ_MASK)
+ return state_rnames[bit >> LOCK_USAGE_DIR_MASK];
+ else
+ return state_names[bit >> LOCK_USAGE_DIR_MASK];
}
+/*
+ * The bit number is encoded like:
+ *
+ * bit0: 0 exclusive, 1 read lock
+ * bit1: 0 used in irq, 1 irq enabled
+ * bit2-n: state
+ */
static int exclusive_bit(int new_bit)
{
int state = new_bit & LOCK_USAGE_STATE_MASK;
return state | (dir ^ LOCK_USAGE_DIR_MASK);
}
+/*
+ * Observe that when given a bitmask where each bitnr is encoded as above, a
+ * right shift of the mask transforms the individual bitnrs as -1 and
+ * conversely, a left shift transforms into +1 for the individual bitnrs.
+ *
+ * So for all bits whose number have LOCK_ENABLED_* set (bitnr1 == 1), we can
+ * create the mask with those bit numbers using LOCK_USED_IN_* (bitnr1 == 0)
+ * instead by subtracting the bit number by 2, or shifting the mask right by 2.
+ *
+ * Similarly, bitnr1 == 0 becomes bitnr1 == 1 by adding 2, or shifting left 2.
+ *
+ * So split the mask (note that LOCKF_ENABLED_IRQ_ALL|LOCKF_USED_IN_IRQ_ALL is
+ * all bits set) and recompose with bitnr1 flipped.
+ */
+static unsigned long invert_dir_mask(unsigned long mask)
+{
+ unsigned long excl = 0;
+
+ /* Invert dir */
+ excl |= (mask & LOCKF_ENABLED_IRQ_ALL) >> LOCK_USAGE_DIR_MASK;
+ excl |= (mask & LOCKF_USED_IN_IRQ_ALL) << LOCK_USAGE_DIR_MASK;
+
+ return excl;
+}
+
+/*
+ * As above, we clear bitnr0 (LOCK_*_READ off) with bitmask ops. First, for all
+ * bits with bitnr0 set (LOCK_*_READ), add those with bitnr0 cleared (LOCK_*).
+ * And then mask out all bitnr0.
+ */
+static unsigned long exclusive_mask(unsigned long mask)
+{
+ unsigned long excl = invert_dir_mask(mask);
+
+ /* Strip read */
+ excl |= (excl & LOCKF_IRQ_READ) >> LOCK_USAGE_READ_MASK;
+ excl &= ~LOCKF_IRQ_READ;
+
+ return excl;
+}
+
+/*
+ * Retrieve the _possible_ original mask to which @mask is
+ * exclusive. Ie: this is the opposite of exclusive_mask().
+ * Note that 2 possible original bits can match an exclusive
+ * bit: one has LOCK_USAGE_READ_MASK set, the other has it
+ * cleared. So both are returned for each exclusive bit.
+ */
+static unsigned long original_mask(unsigned long mask)
+{
+ unsigned long excl = invert_dir_mask(mask);
+
+ /* Include read in existing usages */
+ excl |= (excl & LOCKF_IRQ) << LOCK_USAGE_READ_MASK;
+
+ return excl;
+}
+
+/*
+ * Find the first pair of bit match between an original
+ * usage mask and an exclusive usage mask.
+ */
+static int find_exclusive_match(unsigned long mask,
+ unsigned long excl_mask,
+ enum lock_usage_bit *bitp,
+ enum lock_usage_bit *excl_bitp)
+{
+ int bit, excl;
+
+ for_each_set_bit(bit, &mask, LOCK_USED) {
+ excl = exclusive_bit(bit);
+ if (excl_mask & lock_flag(excl)) {
+ *bitp = bit;
+ *excl_bitp = excl;
+ return 0;
+ }
+ }
+ return -1;
+}
+
+/*
+ * Prove that the new dependency does not connect a hardirq-safe(-read)
+ * lock with a hardirq-unsafe lock - to achieve this we search
+ * the backwards-subgraph starting at <prev>, and the
+ * forwards-subgraph starting at <next>:
+ */
static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
- struct held_lock *next, enum lock_usage_bit bit)
+ struct held_lock *next)
{
+ unsigned long usage_mask = 0, forward_mask, backward_mask;
+ enum lock_usage_bit forward_bit = 0, backward_bit = 0;
+ struct lock_list *uninitialized_var(target_entry1);
+ struct lock_list *uninitialized_var(target_entry);
+ struct lock_list this, that;
+ int ret;
+
/*
- * Prove that the new dependency does not connect a hardirq-safe
- * lock with a hardirq-unsafe lock - to achieve this we search
- * the backwards-subgraph starting at <prev>, and the
- * forwards-subgraph starting at <next>:
+ * Step 1: gather all hard/soft IRQs usages backward in an
+ * accumulated usage mask.
*/
- if (!check_usage(curr, prev, next, bit,
- exclusive_bit(bit), state_name(bit)))
- return 0;
+ this.parent = NULL;
+ this.class = hlock_class(prev);
- bit++; /* _READ */
+ ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, NULL);
+ if (ret < 0)
+ return print_bfs_bug(ret);
+
+ usage_mask &= LOCKF_USED_IN_IRQ_ALL;
+ if (!usage_mask)
+ return 1;
/*
- * Prove that the new dependency does not connect a hardirq-safe-read
- * lock with a hardirq-unsafe lock - to achieve this we search
- * the backwards-subgraph starting at <prev>, and the
- * forwards-subgraph starting at <next>:
+ * Step 2: find exclusive uses forward that match the previous
+ * backward accumulated mask.
*/
- if (!check_usage(curr, prev, next, bit,
- exclusive_bit(bit), state_name(bit)))
- return 0;
+ forward_mask = exclusive_mask(usage_mask);
- return 1;
-}
+ that.parent = NULL;
+ that.class = hlock_class(next);
-static int
-check_prev_add_irq(struct task_struct *curr, struct held_lock *prev,
- struct held_lock *next)
-{
-#define LOCKDEP_STATE(__STATE) \
- if (!check_irq_usage(curr, prev, next, LOCK_USED_IN_##__STATE)) \
- return 0;
-#include "lockdep_states.h"
-#undef LOCKDEP_STATE
+ ret = find_usage_forwards(&that, forward_mask, &target_entry1);
+ if (ret < 0)
+ return print_bfs_bug(ret);
+ if (ret == 1)
+ return ret;
- return 1;
+ /*
+ * Step 3: we found a bad match! Now retrieve a lock from the backward
+ * list whose usage mask matches the exclusive usage mask from the
+ * lock found on the forward list.
+ */
+ backward_mask = original_mask(target_entry1->class->usage_mask);
+
+ ret = find_usage_backwards(&this, backward_mask, &target_entry);
+ if (ret < 0)
+ return print_bfs_bug(ret);
+ if (DEBUG_LOCKS_WARN_ON(ret == 1))
+ return 1;
+
+ /*
+ * Step 4: narrow down to a pair of incompatible usage bits
+ * and report it.
+ */
+ ret = find_exclusive_match(target_entry->class->usage_mask,
+ target_entry1->class->usage_mask,
+ &backward_bit, &forward_bit);
+ if (DEBUG_LOCKS_WARN_ON(ret == -1))
+ return 1;
+
+ return print_bad_irq_dependency(curr, &this, &that,
+ target_entry, target_entry1,
+ prev, next,
+ backward_bit, forward_bit,
+ state_name(backward_bit));
}
static void inc_chains(void)
#else
-static inline int
-check_prev_add_irq(struct task_struct *curr, struct held_lock *prev,
- struct held_lock *next)
+static inline int check_irq_usage(struct task_struct *curr,
+ struct held_lock *prev, struct held_lock *next)
{
return 1;
}
*/
static int
check_prev_add(struct task_struct *curr, struct held_lock *prev,
- struct held_lock *next, int distance, struct stack_trace *trace,
- int (*save)(struct stack_trace *trace))
+ struct held_lock *next, int distance, struct lock_trace *trace)
{
struct lock_list *uninitialized_var(target_entry);
struct lock_list *entry;
this.parent = NULL;
ret = check_noncircular(&this, hlock_class(prev), &target_entry);
if (unlikely(!ret)) {
- if (!trace->entries) {
+ if (!trace->nr_entries) {
/*
- * If @save fails here, the printing might trigger
- * a WARN but because of the !nr_entries it should
- * not do bad things.
+ * If save_trace fails here, the printing might
+ * trigger a WARN but because of the !nr_entries it
+ * should not do bad things.
*/
- save(trace);
+ save_trace(trace);
}
- return print_circular_bug(&this, target_entry, next, prev, trace);
+ return print_circular_bug(&this, target_entry, next, prev);
}
else if (unlikely(ret < 0))
return print_bfs_bug(ret);
- if (!check_prev_add_irq(curr, prev, next))
+ if (!check_irq_usage(curr, prev, next))
return 0;
/*
return print_bfs_bug(ret);
- if (!trace->entries && !save(trace))
+ if (!trace->nr_entries && !save_trace(trace))
return 0;
/*
static int
check_prevs_add(struct task_struct *curr, struct held_lock *next)
{
+ struct lock_trace trace = { .nr_entries = 0 };
int depth = curr->lockdep_depth;
struct held_lock *hlock;
- struct stack_trace trace = {
- .nr_entries = 0,
- .max_entries = 0,
- .entries = NULL,
- .skip = 0,
- };
/*
* Debugging checks.
* added:
*/
if (hlock->read != 2 && hlock->check) {
- int ret = check_prev_add(curr, hlock, next, distance, &trace, save_trace);
+ int ret = check_prev_add(curr, hlock, next, distance,
+ &trace);
if (!ret)
return 0;
{
return 1;
}
+
+static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
+{
+}
#endif
/*
#endif
}
+static int mark_lock(struct task_struct *curr, struct held_lock *this,
+ enum lock_usage_bit new_bit);
+
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+
+
static void
print_usage_bug_scenario(struct held_lock *lock)
{
print_lock(this);
pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]);
- print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1);
+ print_lock_trace(hlock_class(this)->usage_traces + prev_bit, 1);
print_irqtrace_events(curr);
pr_warn("\nother info that might help us debug this:\n");
return 1;
}
-static int mark_lock(struct task_struct *curr, struct held_lock *this,
- enum lock_usage_bit new_bit);
-
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
/*
* print irq inversion bug:
root.parent = NULL;
root.class = hlock_class(this);
- ret = find_usage_forwards(&root, bit, &target_entry);
+ ret = find_usage_forwards(&root, lock_flag(bit), &target_entry);
if (ret < 0)
return print_bfs_bug(ret);
if (ret == 1)
root.parent = NULL;
root.class = hlock_class(this);
- ret = find_usage_backwards(&root, bit, &target_entry);
+ ret = find_usage_backwards(&root, lock_flag(bit), &target_entry);
if (ret < 0)
return print_bfs_bug(ret);
if (ret == 1)
static inline int state_verbose(enum lock_usage_bit bit,
struct lock_class *class)
{
- return state_verbose_f[bit >> 2](class);
+ return state_verbose_f[bit >> LOCK_USAGE_DIR_MASK](class);
}
typedef int (*check_usage_f)(struct task_struct *, struct held_lock *,
/*
* See the fine text that goes along with this variable definition.
*/
- if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled)))
+ if (DEBUG_LOCKS_WARN_ON(early_boot_irqs_disabled))
return;
/*
return;
raw_local_irq_save(flags);
- arch_spin_lock(&lockdep_lock);
- current->lockdep_recursion = 1;
+ if (!graph_lock())
+ goto out_irq;
+
pf = get_pending_free();
hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
if (k == key) {
WARN_ON_ONCE(!found);
__lockdep_free_key_range(pf, key, 1);
call_rcu_zapped(pf);
- current->lockdep_recursion = 0;
- arch_spin_unlock(&lockdep_lock);
+ graph_unlock();
+out_irq:
raw_local_irq_restore(flags);
/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
__LOCKF(USED)
};
-#define LOCKF_ENABLED_IRQ (LOCKF_ENABLED_HARDIRQ | LOCKF_ENABLED_SOFTIRQ)
-#define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ)
+#define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE |
+static const unsigned long LOCKF_ENABLED_IRQ =
+#include "lockdep_states.h"
+ 0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE) LOCKF_USED_IN_##__STATE |
+static const unsigned long LOCKF_USED_IN_IRQ =
+#include "lockdep_states.h"
+ 0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE##_READ |
+static const unsigned long LOCKF_ENABLED_IRQ_READ =
+#include "lockdep_states.h"
+ 0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE) LOCKF_USED_IN_##__STATE##_READ |
+static const unsigned long LOCKF_USED_IN_IRQ_READ =
+#include "lockdep_states.h"
+ 0;
+#undef LOCKDEP_STATE
+
+#define LOCKF_ENABLED_IRQ_ALL (LOCKF_ENABLED_IRQ | LOCKF_ENABLED_IRQ_READ)
+#define LOCKF_USED_IN_IRQ_ALL (LOCKF_USED_IN_IRQ | LOCKF_USED_IN_IRQ_READ)
-#define LOCKF_ENABLED_IRQ_READ \
- (LOCKF_ENABLED_HARDIRQ_READ | LOCKF_ENABLED_SOFTIRQ_READ)
-#define LOCKF_USED_IN_IRQ_READ \
- (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
+#define LOCKF_IRQ (LOCKF_ENABLED_IRQ | LOCKF_USED_IN_IRQ)
+#define LOCKF_IRQ_READ (LOCKF_ENABLED_IRQ_READ | LOCKF_USED_IN_IRQ_READ)
/*
* CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text,
"End of test: SUCCESS");
kfree(cxt.lwsa);
+ cxt.lwsa = NULL;
kfree(cxt.lrsa);
+ cxt.lrsa = NULL;
end:
torture_cleanup_end();
#include <linux/sched.h>
#include <linux/errno.h>
+#include "rwsem.h"
+
int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
const char *name, struct lock_class_key *rwsem_key)
{
* 0,1,0 -> 0,0,1
*/
clear_pending_set_locked(lock);
- qstat_inc(qstat_lock_pending, true);
+ lockevent_inc(lock_pending);
return;
/*
* queuing.
*/
queue:
- qstat_inc(qstat_lock_slowpath, true);
+ lockevent_inc(lock_slowpath);
pv_queue:
node = this_cpu_ptr(&qnodes[0].mcs);
idx = node->count++;
* simple enough.
*/
if (unlikely(idx >= MAX_NODES)) {
- qstat_inc(qstat_lock_no_node, true);
+ lockevent_inc(lock_no_node);
while (!queued_spin_trylock(lock))
cpu_relax();
goto release;
/*
* Keep counts of non-zero index values:
*/
- qstat_inc(qstat_lock_use_node2 + idx - 1, idx);
+ lockevent_cond_inc(lock_use_node2 + idx - 1, idx);
/*
* Ensure that we increment the head node->count before initialising
if (!(val & _Q_LOCKED_PENDING_MASK) &&
(cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
- qstat_inc(qstat_pv_lock_stealing, true);
+ lockevent_inc(pv_lock_stealing);
return true;
}
if (!(val & _Q_TAIL_MASK) || (val & _Q_PENDING_MASK))
hopcnt++;
if (!cmpxchg(&he->lock, NULL, lock)) {
WRITE_ONCE(he->node, node);
- qstat_hop(hopcnt);
+ lockevent_pv_hop(hopcnt);
return &he->lock;
}
}
smp_store_mb(pn->state, vcpu_halted);
if (!READ_ONCE(node->locked)) {
- qstat_inc(qstat_pv_wait_node, true);
- qstat_inc(qstat_pv_wait_early, wait_early);
+ lockevent_inc(pv_wait_node);
+ lockevent_cond_inc(pv_wait_early, wait_early);
pv_wait(&pn->state, vcpu_halted);
}
* So it is better to spin for a while in the hope that the
* MCS lock will be released soon.
*/
- qstat_inc(qstat_pv_spurious_wakeup, !READ_ONCE(node->locked));
+ lockevent_cond_inc(pv_spurious_wakeup,
+ !READ_ONCE(node->locked));
}
/*
/*
* Tracking # of slowpath locking operations
*/
- qstat_inc(qstat_lock_slowpath, true);
+ lockevent_inc(lock_slowpath);
for (;; waitcnt++) {
/*
}
}
WRITE_ONCE(pn->state, vcpu_hashed);
- qstat_inc(qstat_pv_wait_head, true);
- qstat_inc(qstat_pv_wait_again, waitcnt);
+ lockevent_inc(pv_wait_head);
+ lockevent_cond_inc(pv_wait_again, waitcnt);
pv_wait(&lock->locked, _Q_SLOW_VAL);
/*
* vCPU is harmless other than the additional latency in completing
* the unlock.
*/
- qstat_inc(qstat_pv_kick_unlock, true);
+ lockevent_inc(pv_kick_unlock);
pv_kick(node->cpu);
}
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * Authors: Waiman Long <waiman.long@hpe.com>
+ * Authors: Waiman Long <longman@redhat.com>
*/
-/*
- * When queued spinlock statistical counters are enabled, the following
- * debugfs files will be created for reporting the counter values:
- *
- * <debugfs>/qlockstat/
- * pv_hash_hops - average # of hops per hashing operation
- * pv_kick_unlock - # of vCPU kicks issued at unlock time
- * pv_kick_wake - # of vCPU kicks used for computing pv_latency_wake
- * pv_latency_kick - average latency (ns) of vCPU kick operation
- * pv_latency_wake - average latency (ns) from vCPU kick to wakeup
- * pv_lock_stealing - # of lock stealing operations
- * pv_spurious_wakeup - # of spurious wakeups in non-head vCPUs
- * pv_wait_again - # of wait's after a queue head vCPU kick
- * pv_wait_early - # of early vCPU wait's
- * pv_wait_head - # of vCPU wait's at the queue head
- * pv_wait_node - # of vCPU wait's at a non-head queue node
- * lock_pending - # of locking operations via pending code
- * lock_slowpath - # of locking operations via MCS lock queue
- * lock_use_node2 - # of locking operations that use 2nd per-CPU node
- * lock_use_node3 - # of locking operations that use 3rd per-CPU node
- * lock_use_node4 - # of locking operations that use 4th per-CPU node
- * lock_no_node - # of locking operations without using per-CPU node
- *
- * Subtracting lock_use_node[234] from lock_slowpath will give you
- * lock_use_node1.
- *
- * Writing to the "reset_counters" file will reset all the above counter
- * values.
- *
- * These statistical counters are implemented as per-cpu variables which are
- * summed and computed whenever the corresponding debugfs files are read. This
- * minimizes added overhead making the counters usable even in a production
- * environment.
- *
- * There may be slight difference between pv_kick_wake and pv_kick_unlock.
- */
-enum qlock_stats {
- qstat_pv_hash_hops,
- qstat_pv_kick_unlock,
- qstat_pv_kick_wake,
- qstat_pv_latency_kick,
- qstat_pv_latency_wake,
- qstat_pv_lock_stealing,
- qstat_pv_spurious_wakeup,
- qstat_pv_wait_again,
- qstat_pv_wait_early,
- qstat_pv_wait_head,
- qstat_pv_wait_node,
- qstat_lock_pending,
- qstat_lock_slowpath,
- qstat_lock_use_node2,
- qstat_lock_use_node3,
- qstat_lock_use_node4,
- qstat_lock_no_node,
- qstat_num, /* Total number of statistical counters */
- qstat_reset_cnts = qstat_num,
-};
+#include "lock_events.h"
-#ifdef CONFIG_QUEUED_LOCK_STAT
+#ifdef CONFIG_LOCK_EVENT_COUNTS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
/*
- * Collect pvqspinlock statistics
+ * Collect pvqspinlock locking event counts
*/
-#include <linux/debugfs.h>
#include <linux/sched.h>
#include <linux/sched/clock.h>
#include <linux/fs.h>
-static const char * const qstat_names[qstat_num + 1] = {
- [qstat_pv_hash_hops] = "pv_hash_hops",
- [qstat_pv_kick_unlock] = "pv_kick_unlock",
- [qstat_pv_kick_wake] = "pv_kick_wake",
- [qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
- [qstat_pv_latency_kick] = "pv_latency_kick",
- [qstat_pv_latency_wake] = "pv_latency_wake",
- [qstat_pv_lock_stealing] = "pv_lock_stealing",
- [qstat_pv_wait_again] = "pv_wait_again",
- [qstat_pv_wait_early] = "pv_wait_early",
- [qstat_pv_wait_head] = "pv_wait_head",
- [qstat_pv_wait_node] = "pv_wait_node",
- [qstat_lock_pending] = "lock_pending",
- [qstat_lock_slowpath] = "lock_slowpath",
- [qstat_lock_use_node2] = "lock_use_node2",
- [qstat_lock_use_node3] = "lock_use_node3",
- [qstat_lock_use_node4] = "lock_use_node4",
- [qstat_lock_no_node] = "lock_no_node",
- [qstat_reset_cnts] = "reset_counters",
-};
+#define EVENT_COUNT(ev) lockevents[LOCKEVENT_ ## ev]
/*
- * Per-cpu counters
+ * PV specific per-cpu counter
*/
-static DEFINE_PER_CPU(unsigned long, qstats[qstat_num]);
static DEFINE_PER_CPU(u64, pv_kick_time);
/*
- * Function to read and return the qlock statistical counter values
+ * Function to read and return the PV qspinlock counts.
*
* The following counters are handled specially:
- * 1. qstat_pv_latency_kick
+ * 1. pv_latency_kick
* Average kick latency (ns) = pv_latency_kick/pv_kick_unlock
- * 2. qstat_pv_latency_wake
+ * 2. pv_latency_wake
* Average wake latency (ns) = pv_latency_wake/pv_kick_wake
- * 3. qstat_pv_hash_hops
+ * 3. pv_hash_hops
* Average hops/hash = pv_hash_hops/pv_kick_unlock
*/
-static ssize_t qstat_read(struct file *file, char __user *user_buf,
- size_t count, loff_t *ppos)
+ssize_t lockevent_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
{
char buf[64];
- int cpu, counter, len;
- u64 stat = 0, kicks = 0;
+ int cpu, id, len;
+ u64 sum = 0, kicks = 0;
/*
* Get the counter ID stored in file->f_inode->i_private
*/
- counter = (long)file_inode(file)->i_private;
+ id = (long)file_inode(file)->i_private;
- if (counter >= qstat_num)
+ if (id >= lockevent_num)
return -EBADF;
for_each_possible_cpu(cpu) {
- stat += per_cpu(qstats[counter], cpu);
+ sum += per_cpu(lockevents[id], cpu);
/*
- * Need to sum additional counter for some of them
+ * Need to sum additional counters for some of them
*/
- switch (counter) {
+ switch (id) {
- case qstat_pv_latency_kick:
- case qstat_pv_hash_hops:
- kicks += per_cpu(qstats[qstat_pv_kick_unlock], cpu);
+ case LOCKEVENT_pv_latency_kick:
+ case LOCKEVENT_pv_hash_hops:
+ kicks += per_cpu(EVENT_COUNT(pv_kick_unlock), cpu);
break;
- case qstat_pv_latency_wake:
- kicks += per_cpu(qstats[qstat_pv_kick_wake], cpu);
+ case LOCKEVENT_pv_latency_wake:
+ kicks += per_cpu(EVENT_COUNT(pv_kick_wake), cpu);
break;
}
}
- if (counter == qstat_pv_hash_hops) {
+ if (id == LOCKEVENT_pv_hash_hops) {
u64 frac = 0;
if (kicks) {
- frac = 100ULL * do_div(stat, kicks);
+ frac = 100ULL * do_div(sum, kicks);
frac = DIV_ROUND_CLOSEST_ULL(frac, kicks);
}
/*
* Return a X.XX decimal number
*/
- len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n", stat, frac);
+ len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n",
+ sum, frac);
} else {
/*
* Round to the nearest ns
*/
- if ((counter == qstat_pv_latency_kick) ||
- (counter == qstat_pv_latency_wake)) {
+ if ((id == LOCKEVENT_pv_latency_kick) ||
+ (id == LOCKEVENT_pv_latency_wake)) {
if (kicks)
- stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
+ sum = DIV_ROUND_CLOSEST_ULL(sum, kicks);
}
- len = snprintf(buf, sizeof(buf) - 1, "%llu\n", stat);
+ len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum);
}
return simple_read_from_buffer(user_buf, count, ppos, buf, len);
}
-/*
- * Function to handle write request
- *
- * When counter = reset_cnts, reset all the counter values.
- * Since the counter updates aren't atomic, the resetting is done twice
- * to make sure that the counters are very likely to be all cleared.
- */
-static ssize_t qstat_write(struct file *file, const char __user *user_buf,
- size_t count, loff_t *ppos)
-{
- int cpu;
-
- /*
- * Get the counter ID stored in file->f_inode->i_private
- */
- if ((long)file_inode(file)->i_private != qstat_reset_cnts)
- return count;
-
- for_each_possible_cpu(cpu) {
- int i;
- unsigned long *ptr = per_cpu_ptr(qstats, cpu);
-
- for (i = 0 ; i < qstat_num; i++)
- WRITE_ONCE(ptr[i], 0);
- }
- return count;
-}
-
-/*
- * Debugfs data structures
- */
-static const struct file_operations fops_qstat = {
- .read = qstat_read,
- .write = qstat_write,
- .llseek = default_llseek,
-};
-
-/*
- * Initialize debugfs for the qspinlock statistical counters
- */
-static int __init init_qspinlock_stat(void)
-{
- struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL);
- int i;
-
- if (!d_qstat)
- goto out;
-
- /*
- * Create the debugfs files
- *
- * As reading from and writing to the stat files can be slow, only
- * root is allowed to do the read/write to limit impact to system
- * performance.
- */
- for (i = 0; i < qstat_num; i++)
- if (!debugfs_create_file(qstat_names[i], 0400, d_qstat,
- (void *)(long)i, &fops_qstat))
- goto fail_undo;
-
- if (!debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat,
- (void *)(long)qstat_reset_cnts, &fops_qstat))
- goto fail_undo;
-
- return 0;
-fail_undo:
- debugfs_remove_recursive(d_qstat);
-out:
- pr_warn("Could not create 'qlockstat' debugfs entries\n");
- return -ENOMEM;
-}
-fs_initcall(init_qspinlock_stat);
-
-/*
- * Increment the PV qspinlock statistical counters
- */
-static inline void qstat_inc(enum qlock_stats stat, bool cond)
-{
- if (cond)
- this_cpu_inc(qstats[stat]);
-}
-
/*
* PV hash hop count
*/
-static inline void qstat_hop(int hopcnt)
+static inline void lockevent_pv_hop(int hopcnt)
{
- this_cpu_add(qstats[qstat_pv_hash_hops], hopcnt);
+ this_cpu_add(EVENT_COUNT(pv_hash_hops), hopcnt);
}
/*
per_cpu(pv_kick_time, cpu) = start;
pv_kick(cpu);
- this_cpu_add(qstats[qstat_pv_latency_kick], sched_clock() - start);
+ this_cpu_add(EVENT_COUNT(pv_latency_kick), sched_clock() - start);
}
/*
*pkick_time = 0;
pv_wait(ptr, val);
if (*pkick_time) {
- this_cpu_add(qstats[qstat_pv_latency_wake],
+ this_cpu_add(EVENT_COUNT(pv_latency_wake),
sched_clock() - *pkick_time);
- qstat_inc(qstat_pv_kick_wake, true);
+ lockevent_inc(pv_kick_wake);
}
}
#define pv_kick(c) __pv_kick(c)
#define pv_wait(p, v) __pv_wait(p, v)
-#else /* CONFIG_QUEUED_LOCK_STAT */
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#else /* CONFIG_LOCK_EVENT_COUNTS */
-static inline void qstat_inc(enum qlock_stats stat, bool cond) { }
-static inline void qstat_hop(int hopcnt) { }
+static inline void lockevent_pv_hop(int hopcnt) { }
-#endif /* CONFIG_QUEUED_LOCK_STAT */
+#endif /* CONFIG_LOCK_EVENT_COUNTS */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
- * generic spinlock implementation
- *
- * Copyright (c) 2001 David Howells (dhowells@redhat.com).
- * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
- * - Derived also from comments by Linus
- */
-#include <linux/rwsem.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/debug.h>
-#include <linux/export.h>
-
-enum rwsem_waiter_type {
- RWSEM_WAITING_FOR_WRITE,
- RWSEM_WAITING_FOR_READ
-};
-
-struct rwsem_waiter {
- struct list_head list;
- struct task_struct *task;
- enum rwsem_waiter_type type;
-};
-
-int rwsem_is_locked(struct rw_semaphore *sem)
-{
- int ret = 1;
- unsigned long flags;
-
- if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
- ret = (sem->count != 0);
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- }
- return ret;
-}
-EXPORT_SYMBOL(rwsem_is_locked);
-
-/*
- * initialise the semaphore
- */
-void __init_rwsem(struct rw_semaphore *sem, const char *name,
- struct lock_class_key *key)
-{
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- /*
- * Make sure we are not reinitializing a held semaphore:
- */
- debug_check_no_locks_freed((void *)sem, sizeof(*sem));
- lockdep_init_map(&sem->dep_map, name, key, 0);
-#endif
- sem->count = 0;
- raw_spin_lock_init(&sem->wait_lock);
- INIT_LIST_HEAD(&sem->wait_list);
-}
-EXPORT_SYMBOL(__init_rwsem);
-
-/*
- * handle the lock release when processes blocked on it that can now run
- * - if we come here, then:
- * - the 'active count' _reached_ zero
- * - the 'waiting count' is non-zero
- * - the spinlock must be held by the caller
- * - woken process blocks are discarded from the list after having task zeroed
- * - writers are only woken if wakewrite is non-zero
- */
-static inline struct rw_semaphore *
-__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
-{
- struct rwsem_waiter *waiter;
- struct task_struct *tsk;
- int woken;
-
- waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
-
- if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
- if (wakewrite)
- /* Wake up a writer. Note that we do not grant it the
- * lock - it will have to acquire it when it runs. */
- wake_up_process(waiter->task);
- goto out;
- }
-
- /* grant an infinite number of read locks to the front of the queue */
- woken = 0;
- do {
- struct list_head *next = waiter->list.next;
-
- list_del(&waiter->list);
- tsk = waiter->task;
- /*
- * Make sure we do not wakeup the next reader before
- * setting the nil condition to grant the next reader;
- * otherwise we could miss the wakeup on the other
- * side and end up sleeping again. See the pairing
- * in rwsem_down_read_failed().
- */
- smp_mb();
- waiter->task = NULL;
- wake_up_process(tsk);
- put_task_struct(tsk);
- woken++;
- if (next == &sem->wait_list)
- break;
- waiter = list_entry(next, struct rwsem_waiter, list);
- } while (waiter->type != RWSEM_WAITING_FOR_WRITE);
-
- sem->count += woken;
-
- out:
- return sem;
-}
-
-/*
- * wake a single writer
- */
-static inline struct rw_semaphore *
-__rwsem_wake_one_writer(struct rw_semaphore *sem)
-{
- struct rwsem_waiter *waiter;
-
- waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
- wake_up_process(waiter->task);
-
- return sem;
-}
-
-/*
- * get a read lock on the semaphore
- */
-int __sched __down_read_common(struct rw_semaphore *sem, int state)
-{
- struct rwsem_waiter waiter;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
- if (sem->count >= 0 && list_empty(&sem->wait_list)) {
- /* granted */
- sem->count++;
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- goto out;
- }
-
- /* set up my own style of waitqueue */
- waiter.task = current;
- waiter.type = RWSEM_WAITING_FOR_READ;
- get_task_struct(current);
-
- list_add_tail(&waiter.list, &sem->wait_list);
-
- /* wait to be given the lock */
- for (;;) {
- if (!waiter.task)
- break;
- if (signal_pending_state(state, current))
- goto out_nolock;
- set_current_state(state);
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- schedule();
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
- }
-
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- out:
- return 0;
-
-out_nolock:
- /*
- * We didn't take the lock, so that there is a writer, which
- * is owner or the first waiter of the sem. If it's a waiter,
- * it will be woken by current owner. Not need to wake anybody.
- */
- list_del(&waiter.list);
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- return -EINTR;
-}
-
-void __sched __down_read(struct rw_semaphore *sem)
-{
- __down_read_common(sem, TASK_UNINTERRUPTIBLE);
-}
-
-int __sched __down_read_killable(struct rw_semaphore *sem)
-{
- return __down_read_common(sem, TASK_KILLABLE);
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-int __down_read_trylock(struct rw_semaphore *sem)
-{
- unsigned long flags;
- int ret = 0;
-
-
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
- if (sem->count >= 0 && list_empty(&sem->wait_list)) {
- /* granted */
- sem->count++;
- ret = 1;
- }
-
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
- return ret;
-}
-
-/*
- * get a write lock on the semaphore
- */
-int __sched __down_write_common(struct rw_semaphore *sem, int state)
-{
- struct rwsem_waiter waiter;
- unsigned long flags;
- int ret = 0;
-
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
- /* set up my own style of waitqueue */
- waiter.task = current;
- waiter.type = RWSEM_WAITING_FOR_WRITE;
- list_add_tail(&waiter.list, &sem->wait_list);
-
- /* wait for someone to release the lock */
- for (;;) {
- /*
- * That is the key to support write lock stealing: allows the
- * task already on CPU to get the lock soon rather than put
- * itself into sleep and waiting for system woke it or someone
- * else in the head of the wait list up.
- */
- if (sem->count == 0)
- break;
- if (signal_pending_state(state, current))
- goto out_nolock;
-
- set_current_state(state);
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- schedule();
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
- }
- /* got the lock */
- sem->count = -1;
- list_del(&waiter.list);
-
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
- return ret;
-
-out_nolock:
- list_del(&waiter.list);
- if (!list_empty(&sem->wait_list) && sem->count >= 0)
- __rwsem_do_wake(sem, 0);
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
- return -EINTR;
-}
-
-void __sched __down_write(struct rw_semaphore *sem)
-{
- __down_write_common(sem, TASK_UNINTERRUPTIBLE);
-}
-
-int __sched __down_write_killable(struct rw_semaphore *sem)
-{
- return __down_write_common(sem, TASK_KILLABLE);
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-int __down_write_trylock(struct rw_semaphore *sem)
-{
- unsigned long flags;
- int ret = 0;
-
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
- if (sem->count == 0) {
- /* got the lock */
- sem->count = -1;
- ret = 1;
- }
-
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
- return ret;
-}
-
-/*
- * release a read lock on the semaphore
- */
-void __up_read(struct rw_semaphore *sem)
-{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
- if (--sem->count == 0 && !list_empty(&sem->wait_list))
- sem = __rwsem_wake_one_writer(sem);
-
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
-/*
- * release a write lock on the semaphore
- */
-void __up_write(struct rw_semaphore *sem)
-{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
- sem->count = 0;
- if (!list_empty(&sem->wait_list))
- sem = __rwsem_do_wake(sem, 1);
-
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
-/*
- * downgrade a write lock into a read lock
- * - just wake up any readers at the front of the queue
- */
-void __downgrade_write(struct rw_semaphore *sem)
-{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
- sem->count = 1;
- if (!list_empty(&sem->wait_list))
- sem = __rwsem_do_wake(sem, 0);
-
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
* will notice the queued writer.
*/
wake_q_add(wake_q, waiter->task);
+ lockevent_inc(rwsem_wake_writer);
}
return;
goto try_reader_grant;
}
/*
- * It is not really necessary to set it to reader-owned here,
- * but it gives the spinners an early indication that the
- * readers now have the lock.
+ * Set it to reader-owned to give spinners an early
+ * indication that readers now have the lock.
*/
__rwsem_set_reader_owned(sem, waiter->task);
}
}
adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
+ lockevent_cond_inc(rwsem_wake_reader, woken);
if (list_empty(&sem->wait_list)) {
/* hit end of list above */
adjustment -= RWSEM_WAITING_BIAS;
atomic_long_add(adjustment, &sem->count);
}
-/*
- * Wait for the read lock to be granted
- */
-static inline struct rw_semaphore __sched *
-__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
-{
- long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
- struct rwsem_waiter waiter;
- DEFINE_WAKE_Q(wake_q);
-
- waiter.task = current;
- waiter.type = RWSEM_WAITING_FOR_READ;
-
- raw_spin_lock_irq(&sem->wait_lock);
- if (list_empty(&sem->wait_list)) {
- /*
- * In case the wait queue is empty and the lock isn't owned
- * by a writer, this reader can exit the slowpath and return
- * immediately as its RWSEM_ACTIVE_READ_BIAS has already
- * been set in the count.
- */
- if (atomic_long_read(&sem->count) >= 0) {
- raw_spin_unlock_irq(&sem->wait_lock);
- return sem;
- }
- adjustment += RWSEM_WAITING_BIAS;
- }
- list_add_tail(&waiter.list, &sem->wait_list);
-
- /* we're now waiting on the lock, but no longer actively locking */
- count = atomic_long_add_return(adjustment, &sem->count);
-
- /*
- * If there are no active locks, wake the front queued process(es).
- *
- * If there are no writers and we are first in the queue,
- * wake our own waiter to join the existing active readers !
- */
- if (count == RWSEM_WAITING_BIAS ||
- (count > RWSEM_WAITING_BIAS &&
- adjustment != -RWSEM_ACTIVE_READ_BIAS))
- __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
- raw_spin_unlock_irq(&sem->wait_lock);
- wake_up_q(&wake_q);
-
- /* wait to be given the lock */
- while (true) {
- set_current_state(state);
- if (!waiter.task)
- break;
- if (signal_pending_state(state, current)) {
- raw_spin_lock_irq(&sem->wait_lock);
- if (waiter.task)
- goto out_nolock;
- raw_spin_unlock_irq(&sem->wait_lock);
- break;
- }
- schedule();
- }
-
- __set_current_state(TASK_RUNNING);
- return sem;
-out_nolock:
- list_del(&waiter.list);
- if (list_empty(&sem->wait_list))
- atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
- raw_spin_unlock_irq(&sem->wait_lock);
- __set_current_state(TASK_RUNNING);
- return ERR_PTR(-EINTR);
-}
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed(struct rw_semaphore *sem)
-{
- return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed);
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed_killable(struct rw_semaphore *sem)
-{
- return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed_killable);
-
/*
* This function must be called with the sem->wait_lock held to prevent
* race conditions between checking the rwsem wait list and setting the
*/
static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
{
- long old, count = atomic_long_read(&sem->count);
-
- while (true) {
- if (!(count == 0 || count == RWSEM_WAITING_BIAS))
- return false;
+ long count = atomic_long_read(&sem->count);
- old = atomic_long_cmpxchg_acquire(&sem->count, count,
- count + RWSEM_ACTIVE_WRITE_BIAS);
- if (old == count) {
+ while (!count || count == RWSEM_WAITING_BIAS) {
+ if (atomic_long_try_cmpxchg_acquire(&sem->count, &count,
+ count + RWSEM_ACTIVE_WRITE_BIAS)) {
rwsem_set_owner(sem);
+ lockevent_inc(rwsem_opt_wlock);
return true;
}
-
- count = old;
}
+ return false;
}
static inline bool owner_on_cpu(struct task_struct *owner)
osq_unlock(&sem->osq);
done:
preempt_enable();
+ lockevent_cond_inc(rwsem_opt_fail, !taken);
return taken;
}
}
#endif
+/*
+ * Wait for the read lock to be granted
+ */
+static inline struct rw_semaphore __sched *
+__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
+{
+ long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
+ struct rwsem_waiter waiter;
+ DEFINE_WAKE_Q(wake_q);
+
+ waiter.task = current;
+ waiter.type = RWSEM_WAITING_FOR_READ;
+
+ raw_spin_lock_irq(&sem->wait_lock);
+ if (list_empty(&sem->wait_list)) {
+ /*
+ * In case the wait queue is empty and the lock isn't owned
+ * by a writer, this reader can exit the slowpath and return
+ * immediately as its RWSEM_ACTIVE_READ_BIAS has already
+ * been set in the count.
+ */
+ if (atomic_long_read(&sem->count) >= 0) {
+ raw_spin_unlock_irq(&sem->wait_lock);
+ rwsem_set_reader_owned(sem);
+ lockevent_inc(rwsem_rlock_fast);
+ return sem;
+ }
+ adjustment += RWSEM_WAITING_BIAS;
+ }
+ list_add_tail(&waiter.list, &sem->wait_list);
+
+ /* we're now waiting on the lock, but no longer actively locking */
+ count = atomic_long_add_return(adjustment, &sem->count);
+
+ /*
+ * If there are no active locks, wake the front queued process(es).
+ *
+ * If there are no writers and we are first in the queue,
+ * wake our own waiter to join the existing active readers !
+ */
+ if (count == RWSEM_WAITING_BIAS ||
+ (count > RWSEM_WAITING_BIAS &&
+ adjustment != -RWSEM_ACTIVE_READ_BIAS))
+ __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+
+ raw_spin_unlock_irq(&sem->wait_lock);
+ wake_up_q(&wake_q);
+
+ /* wait to be given the lock */
+ while (true) {
+ set_current_state(state);
+ if (!waiter.task)
+ break;
+ if (signal_pending_state(state, current)) {
+ raw_spin_lock_irq(&sem->wait_lock);
+ if (waiter.task)
+ goto out_nolock;
+ raw_spin_unlock_irq(&sem->wait_lock);
+ break;
+ }
+ schedule();
+ lockevent_inc(rwsem_sleep_reader);
+ }
+
+ __set_current_state(TASK_RUNNING);
+ lockevent_inc(rwsem_rlock);
+ return sem;
+out_nolock:
+ list_del(&waiter.list);
+ if (list_empty(&sem->wait_list))
+ atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
+ raw_spin_unlock_irq(&sem->wait_lock);
+ __set_current_state(TASK_RUNNING);
+ lockevent_inc(rwsem_rlock_fail);
+ return ERR_PTR(-EINTR);
+}
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+ return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(rwsem_down_read_failed);
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed_killable(struct rw_semaphore *sem)
+{
+ return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(rwsem_down_read_failed_killable);
+
/*
* Wait until we successfully acquire the write lock
*/
goto out_nolock;
schedule();
+ lockevent_inc(rwsem_sleep_writer);
set_current_state(state);
} while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK);
__set_current_state(TASK_RUNNING);
list_del(&waiter.list);
raw_spin_unlock_irq(&sem->wait_lock);
+ lockevent_inc(rwsem_wlock);
return ret;
__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
raw_spin_unlock_irq(&sem->wait_lock);
wake_up_q(&wake_q);
+ lockevent_inc(rwsem_wlock_fail);
return ERR_PTR(-EINTR);
}
rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
- rwsem_set_reader_owned(sem);
}
EXPORT_SYMBOL(down_read);
return -EINTR;
}
- rwsem_set_reader_owned(sem);
return 0;
}
{
int ret = __down_read_trylock(sem);
- if (ret == 1) {
+ if (ret == 1)
rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
- rwsem_set_reader_owned(sem);
- }
return ret;
}
rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
- rwsem_set_owner(sem);
}
EXPORT_SYMBOL(down_write);
return -EINTR;
}
- rwsem_set_owner(sem);
return 0;
}
{
int ret = __down_write_trylock(sem);
- if (ret == 1) {
+ if (ret == 1)
rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_);
- rwsem_set_owner(sem);
- }
return ret;
}
void up_read(struct rw_semaphore *sem)
{
rwsem_release(&sem->dep_map, 1, _RET_IP_);
- DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED));
- rwsem_clear_reader_owned(sem);
__up_read(sem);
}
void up_write(struct rw_semaphore *sem)
{
rwsem_release(&sem->dep_map, 1, _RET_IP_);
- DEBUG_RWSEMS_WARN_ON(sem->owner != current);
- rwsem_clear_owner(sem);
__up_write(sem);
}
void downgrade_write(struct rw_semaphore *sem)
{
lock_downgrade(&sem->dep_map, _RET_IP_);
- DEBUG_RWSEMS_WARN_ON(sem->owner != current);
- rwsem_set_reader_owned(sem);
__downgrade_write(sem);
}
rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
- rwsem_set_reader_owned(sem);
}
EXPORT_SYMBOL(down_read_nested);
rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
- rwsem_set_owner(sem);
}
EXPORT_SYMBOL(_down_write_nest_lock);
rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
- rwsem_set_owner(sem);
}
EXPORT_SYMBOL(down_write_nested);
return -EINTR;
}
- rwsem_set_owner(sem);
return 0;
}
void up_read_non_owner(struct rw_semaphore *sem)
{
- DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED));
+ DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED),
+ sem);
__up_read(sem);
}
* is involved. Ideally we would like to track all the readers that own
* a rwsem, but the overhead is simply too big.
*/
+#include "lock_events.h"
+
#define RWSEM_READER_OWNED (1UL << 0)
#define RWSEM_ANONYMOUSLY_OWNED (1UL << 1)
#ifdef CONFIG_DEBUG_RWSEMS
-# define DEBUG_RWSEMS_WARN_ON(c) DEBUG_LOCKS_WARN_ON(c)
+# define DEBUG_RWSEMS_WARN_ON(c, sem) do { \
+ if (!debug_locks_silent && \
+ WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\
+ #c, atomic_long_read(&(sem)->count), \
+ (long)((sem)->owner), (long)current, \
+ list_empty(&(sem)->wait_list) ? "" : "not ")) \
+ debug_locks_off(); \
+ } while (0)
+#else
+# define DEBUG_RWSEMS_WARN_ON(c, sem)
+#endif
+
+/*
+ * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
+ * Adapted largely from include/asm-i386/rwsem.h
+ * by Paul Mackerras <paulus@samba.org>.
+ */
+
+/*
+ * the semaphore definition
+ */
+#ifdef CONFIG_64BIT
+# define RWSEM_ACTIVE_MASK 0xffffffffL
#else
-# define DEBUG_RWSEMS_WARN_ON(c)
+# define RWSEM_ACTIVE_MASK 0x0000ffffL
#endif
+#define RWSEM_ACTIVE_BIAS 0x00000001L
+#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1)
+#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
/*
* All writes to owner are protected by WRITE_ONCE() to make sure that
{
}
#endif
+
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+ if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
+ rwsem_down_read_failed(sem);
+ DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner &
+ RWSEM_READER_OWNED), sem);
+ } else {
+ rwsem_set_reader_owned(sem);
+ }
+}
+
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+ if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
+ if (IS_ERR(rwsem_down_read_failed_killable(sem)))
+ return -EINTR;
+ DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner &
+ RWSEM_READER_OWNED), sem);
+ } else {
+ rwsem_set_reader_owned(sem);
+ }
+ return 0;
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+ /*
+ * Optimize for the case when the rwsem is not locked at all.
+ */
+ long tmp = RWSEM_UNLOCKED_VALUE;
+
+ lockevent_inc(rwsem_rtrylock);
+ do {
+ if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+ tmp + RWSEM_ACTIVE_READ_BIAS)) {
+ rwsem_set_reader_owned(sem);
+ return 1;
+ }
+ } while (tmp >= 0);
+ return 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write(struct rw_semaphore *sem)
+{
+ long tmp;
+
+ tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
+ &sem->count);
+ if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
+ rwsem_down_write_failed(sem);
+ rwsem_set_owner(sem);
+}
+
+static inline int __down_write_killable(struct rw_semaphore *sem)
+{
+ long tmp;
+
+ tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
+ &sem->count);
+ if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
+ if (IS_ERR(rwsem_down_write_failed_killable(sem)))
+ return -EINTR;
+ rwsem_set_owner(sem);
+ return 0;
+}
+
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+ long tmp;
+
+ lockevent_inc(rwsem_wtrylock);
+ tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
+ RWSEM_ACTIVE_WRITE_BIAS);
+ if (tmp == RWSEM_UNLOCKED_VALUE) {
+ rwsem_set_owner(sem);
+ return true;
+ }
+ return false;
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+ long tmp;
+
+ DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED),
+ sem);
+ rwsem_clear_reader_owned(sem);
+ tmp = atomic_long_dec_return_release(&sem->count);
+ if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
+ rwsem_wake(sem);
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+ DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem);
+ rwsem_clear_owner(sem);
+ if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS,
+ &sem->count) < 0))
+ rwsem_wake(sem);
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+ long tmp;
+
+ /*
+ * When downgrading from exclusive to shared ownership,
+ * anything inside the write-locked region cannot leak
+ * into the read side. In contrast, anything in the
+ * read-locked region is ok to be re-ordered into the
+ * write side. As such, rely on RELEASE semantics.
+ */
+ DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem);
+ tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count);
+ rwsem_set_reader_owned(sem);
+ if (tmp < 0)
+ rwsem_downgrade_wake(sem);
+}
depends on PM_SLEEP
select HOTPLUG_CPU
+config PM_SLEEP_SMP_NONZERO_CPU
+ def_bool y
+ depends on PM_SLEEP_SMP
+ depends on ARCH_SUSPEND_NONZERO_CPU
+ ---help---
+ If an arch can suspend (for suspend, hibernate, kexec, etc) on a
+ non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This
+ will allow nohz_full mask to include CPU0.
+
config PM_AUTOSLEEP
bool "Opportunistic sleep"
depends on PM_SLEEP
if (error || hibernation_test(TEST_PLATFORM))
goto Platform_finish;
- error = disable_nonboot_cpus();
+ error = suspend_disable_secondary_cpus();
if (error || hibernation_test(TEST_CPUS))
goto Enable_cpus;
local_irq_enable();
Enable_cpus:
- enable_nonboot_cpus();
+ suspend_enable_secondary_cpus();
Platform_finish:
platform_finish(platform_mode);
int __weak hibernate_resume_nonboot_cpu_disable(void)
{
- return disable_nonboot_cpus();
+ return suspend_disable_secondary_cpus();
}
/**
local_irq_enable();
Enable_cpus:
- enable_nonboot_cpus();
+ suspend_enable_secondary_cpus();
Cleanup:
platform_restore_cleanup(platform_mode);
if (error)
goto Platform_finish;
- error = disable_nonboot_cpus();
+ error = suspend_disable_secondary_cpus();
if (error)
goto Enable_cpus;
local_irq_enable();
Enable_cpus:
- enable_nonboot_cpus();
+ suspend_enable_secondary_cpus();
Platform_finish:
hibernation_ops->finish();
if (suspend_test(TEST_PLATFORM))
goto Platform_wake;
- error = disable_nonboot_cpus();
+ error = suspend_disable_secondary_cpus();
if (error || suspend_test(TEST_CPUS))
goto Enable_cpus;
BUG_ON(irqs_disabled());
Enable_cpus:
- enable_nonboot_cpus();
+ suspend_enable_secondary_cpus();
Platform_wake:
platform_resume_noirq(state);
#ifdef CONFIG_RCU_STALL_COMMON
extern int rcu_cpu_stall_suppress;
+extern int rcu_cpu_stall_timeout;
int rcu_jiffies_till_stall_check(void);
#define rcu_ftrace_dump_stall_suppress() \
if (torture_cleanup_begin())
return;
+ if (!cur_ops) {
+ torture_cleanup_end();
+ return;
+ }
if (reader_tasks) {
for (i = 0; i < nrealreaders; i++)
pr_cont("\n");
WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST));
firsterr = -EINVAL;
+ cur_ops = NULL;
goto unwind;
}
if (cur_ops->init)
int irq_capable;
int can_boost;
int extendables;
- int ext_irq_conflict;
const char *name;
};
static void srcu_torture_cleanup(void)
{
- static DEFINE_TORTURE_RANDOM(rand);
-
- if (torture_random(&rand) & 0x800)
- cleanup_srcu_struct(&srcu_ctld);
- else
- cleanup_srcu_struct_quiesced(&srcu_ctld);
+ cleanup_srcu_struct(&srcu_ctld);
srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
}
unsigned long randmask2 = randmask1 >> 3;
WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
- /* Most of the time lots of bits, half the time only one bit. */
+ /* Mostly only one bit (need preemption!), sometimes lots of bits. */
if (!(randmask1 & 0x7))
mask = mask & randmask2;
else
((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) ||
(!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH))))
mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
- if ((mask & RCUTORTURE_RDR_IRQ) &&
- !(mask & cur_ops->ext_irq_conflict) &&
- (oldmask & cur_ops->ext_irq_conflict))
- mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */
return mask ?: RCUTORTURE_RDR_RCU;
}
WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
__func__);
rcu_torture_fwd_cb_hist();
- rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat) / 2));
+ rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat)) / 2);
WRITE_ONCE(rcu_fwd_emergency_stop, true);
smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
pr_info("%s: Freed %lu RCU callbacks.\n",
cur_ops->cb_barrier();
return;
}
+ if (!cur_ops) {
+ torture_cleanup_end();
+ return;
+ }
rcu_torture_barrier_cleanup();
torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
pr_cont("\n");
WARN_ON(!IS_MODULE(CONFIG_RCU_TORTURE_TEST));
firsterr = -EINVAL;
+ cur_ops = NULL;
goto unwind;
}
if (cur_ops->fqs == NULL && fqs_duration != 0) {
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
*/
-void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
+void cleanup_srcu_struct(struct srcu_struct *ssp)
{
WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
- if (quiesced)
- WARN_ON(work_pending(&ssp->srcu_work));
- else
- flush_work(&ssp->srcu_work);
+ flush_work(&ssp->srcu_work);
WARN_ON(ssp->srcu_gp_running);
WARN_ON(ssp->srcu_gp_waiting);
WARN_ON(ssp->srcu_cb_head);
WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail);
}
-EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
/*
* Removes the count for the old reader from the appropriate element of
return SRCU_INTERVAL;
}
-/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
-void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
+/**
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @ssp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+void cleanup_srcu_struct(struct srcu_struct *ssp)
{
int cpu;
return; /* Just leak it! */
if (WARN_ON(srcu_readers_active(ssp)))
return; /* Just leak it! */
- if (quiesced) {
- if (WARN_ON(delayed_work_pending(&ssp->work)))
- return; /* Just leak it! */
- } else {
- flush_delayed_work(&ssp->work);
- }
+ flush_delayed_work(&ssp->work);
for_each_possible_cpu(cpu) {
struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
- if (quiesced) {
- if (WARN_ON(timer_pending(&sdp->delay_work)))
- return; /* Just leak it! */
- if (WARN_ON(work_pending(&sdp->work)))
- return; /* Just leak it! */
- } else {
- del_timer_sync(&sdp->delay_work);
- flush_work(&sdp->work);
- }
+ del_timer_sync(&sdp->delay_work);
+ flush_work(&sdp->work);
+ if (WARN_ON(rcu_segcblist_n_cbs(&sdp->srcu_cblist)))
+ return; /* Forgot srcu_barrier(), so just leak it! */
}
if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
WARN_ON(srcu_readers_active(ssp))) {
free_percpu(ssp->sda);
ssp->sda = NULL;
}
-EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
/*
* Counts the new reader in the appropriate per-CPU element of the
local_irq_save(flags);
if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
- raise_softirq(RCU_SOFTIRQ);
+ raise_softirq_irqoff(RCU_SOFTIRQ);
}
local_irq_restore(flags);
}
/* Number of rcu_nodes at specified level. */
int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
-/* panic() on RCU Stall sysctl. */
-int sysctl_panic_on_rcu_stall __read_mostly;
-/* Commandeer a sysrq key to dump RCU's tree. */
-static bool sysrq_rcu;
-module_param(sysrq_rcu, bool, 0444);
/*
* The rcu_scheduler_active variable is initialized to the value
/* rcuc/rcub kthread realtime priority */
static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
-module_param(kthread_prio, int, 0644);
+module_param(kthread_prio, int, 0444);
/* Delay in jiffies for grace-period initialization delays, debug only. */
*/
static ulong jiffies_till_sched_qs = ULONG_MAX;
module_param(jiffies_till_sched_qs, ulong, 0444);
-static ulong jiffies_to_sched_qs; /* Adjusted version of above if not default */
+static ulong jiffies_to_sched_qs; /* See adjust_jiffies_till_sched_qs(). */
module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */
/*
WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs);
return;
}
+ /* Otherwise, set to third fqs scan, but bound below on large system. */
j = READ_ONCE(jiffies_till_first_fqs) +
2 * READ_ONCE(jiffies_till_next_fqs);
if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV)
return gp_state_names[gs];
}
-/*
- * Show the state of the grace-period kthreads.
- */
-void show_rcu_gp_kthreads(void)
-{
- int cpu;
- unsigned long j;
- unsigned long ja;
- unsigned long jr;
- unsigned long jw;
- struct rcu_data *rdp;
- struct rcu_node *rnp;
-
- j = jiffies;
- ja = j - READ_ONCE(rcu_state.gp_activity);
- jr = j - READ_ONCE(rcu_state.gp_req_activity);
- jw = j - READ_ONCE(rcu_state.gp_wake_time);
- pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
- rcu_state.name, gp_state_getname(rcu_state.gp_state),
- rcu_state.gp_state,
- rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
- ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
- (long)READ_ONCE(rcu_state.gp_seq),
- (long)READ_ONCE(rcu_get_root()->gp_seq_needed),
- READ_ONCE(rcu_state.gp_flags));
- rcu_for_each_node_breadth_first(rnp) {
- if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
- continue;
- pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
- rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
- (long)rnp->gp_seq_needed);
- if (!rcu_is_leaf_node(rnp))
- continue;
- for_each_leaf_node_possible_cpu(rnp, cpu) {
- rdp = per_cpu_ptr(&rcu_data, cpu);
- if (rdp->gpwrap ||
- ULONG_CMP_GE(rcu_state.gp_seq,
- rdp->gp_seq_needed))
- continue;
- pr_info("\tcpu %d ->gp_seq_needed %ld\n",
- cpu, (long)rdp->gp_seq_needed);
- }
- }
- /* sched_show_task(rcu_state.gp_kthread); */
-}
-EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
-
-/* Dump grace-period-request information due to commandeered sysrq. */
-static void sysrq_show_rcu(int key)
-{
- show_rcu_gp_kthreads();
-}
-
-static struct sysrq_key_op sysrq_rcudump_op = {
- .handler = sysrq_show_rcu,
- .help_msg = "show-rcu(y)",
- .action_msg = "Show RCU tree",
- .enable_mask = SYSRQ_ENABLE_DUMP,
-};
-
-static int __init rcu_sysrq_init(void)
-{
- if (sysrq_rcu)
- return register_sysrq_key('y', &sysrq_rcudump_op);
- return 0;
-}
-early_initcall(rcu_sysrq_init);
-
/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
return 0;
}
-/*
- * Handler for the irq_work request posted when a grace period has
- * gone on for too long, but not yet long enough for an RCU CPU
- * stall warning. Set state appropriately, but just complain if
- * there is unexpected state on entry.
- */
-static void rcu_iw_handler(struct irq_work *iwp)
-{
- struct rcu_data *rdp;
- struct rcu_node *rnp;
-
- rdp = container_of(iwp, struct rcu_data, rcu_iw);
- rnp = rdp->mynode;
- raw_spin_lock_rcu_node(rnp);
- if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
- rdp->rcu_iw_gp_seq = rnp->gp_seq;
- rdp->rcu_iw_pending = false;
- }
- raw_spin_unlock_rcu_node(rnp);
-}
-
/*
* Return true if the specified CPU has passed through a quiescent
* state by virtue of being in or having passed through an dynticks
return 0;
}
-static void record_gp_stall_check_time(void)
-{
- unsigned long j = jiffies;
- unsigned long j1;
-
- rcu_state.gp_start = j;
- j1 = rcu_jiffies_till_stall_check();
- /* Record ->gp_start before ->jiffies_stall. */
- smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
- rcu_state.jiffies_resched = j + j1 / 2;
- rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
-}
-
-/*
- * Complain about starvation of grace-period kthread.
- */
-static void rcu_check_gp_kthread_starvation(void)
-{
- struct task_struct *gpk = rcu_state.gp_kthread;
- unsigned long j;
-
- j = jiffies - READ_ONCE(rcu_state.gp_activity);
- if (j > 2 * HZ) {
- pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
- rcu_state.name, j,
- (long)rcu_seq_current(&rcu_state.gp_seq),
- READ_ONCE(rcu_state.gp_flags),
- gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
- gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
- if (gpk) {
- pr_err("RCU grace-period kthread stack dump:\n");
- sched_show_task(gpk);
- wake_up_process(gpk);
- }
- }
-}
-
-/*
- * Dump stacks of all tasks running on stalled CPUs. First try using
- * NMIs, but fall back to manual remote stack tracing on architectures
- * that don't support NMI-based stack dumps. The NMI-triggered stack
- * traces are more accurate because they are printed by the target CPU.
- */
-static void rcu_dump_cpu_stacks(void)
-{
- int cpu;
- unsigned long flags;
- struct rcu_node *rnp;
-
- rcu_for_each_leaf_node(rnp) {
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- for_each_leaf_node_possible_cpu(rnp, cpu)
- if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
- if (!trigger_single_cpu_backtrace(cpu))
- dump_cpu_task(cpu);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- }
-}
-
-/*
- * If too much time has passed in the current grace period, and if
- * so configured, go kick the relevant kthreads.
- */
-static void rcu_stall_kick_kthreads(void)
-{
- unsigned long j;
-
- if (!rcu_kick_kthreads)
- return;
- j = READ_ONCE(rcu_state.jiffies_kick_kthreads);
- if (time_after(jiffies, j) && rcu_state.gp_kthread &&
- (rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) {
- WARN_ONCE(1, "Kicking %s grace-period kthread\n",
- rcu_state.name);
- rcu_ftrace_dump(DUMP_ALL);
- wake_up_process(rcu_state.gp_kthread);
- WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ);
- }
-}
-
-static void panic_on_rcu_stall(void)
-{
- if (sysctl_panic_on_rcu_stall)
- panic("RCU Stall\n");
-}
-
-static void print_other_cpu_stall(unsigned long gp_seq)
-{
- int cpu;
- unsigned long flags;
- unsigned long gpa;
- unsigned long j;
- int ndetected = 0;
- struct rcu_node *rnp = rcu_get_root();
- long totqlen = 0;
-
- /* Kick and suppress, if so configured. */
- rcu_stall_kick_kthreads();
- if (rcu_cpu_stall_suppress)
- return;
-
- /*
- * OK, time to rat on our buddy...
- * See Documentation/RCU/stallwarn.txt for info on how to debug
- * RCU CPU stall warnings.
- */
- pr_err("INFO: %s detected stalls on CPUs/tasks:", rcu_state.name);
- print_cpu_stall_info_begin();
- rcu_for_each_leaf_node(rnp) {
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- ndetected += rcu_print_task_stall(rnp);
- if (rnp->qsmask != 0) {
- for_each_leaf_node_possible_cpu(rnp, cpu)
- if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
- print_cpu_stall_info(cpu);
- ndetected++;
- }
- }
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- }
-
- print_cpu_stall_info_end();
- for_each_possible_cpu(cpu)
- totqlen += rcu_get_n_cbs_cpu(cpu);
- pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
- smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
- (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
- if (ndetected) {
- rcu_dump_cpu_stacks();
-
- /* Complain about tasks blocking the grace period. */
- rcu_print_detail_task_stall();
- } else {
- if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) {
- pr_err("INFO: Stall ended before state dump start\n");
- } else {
- j = jiffies;
- gpa = READ_ONCE(rcu_state.gp_activity);
- pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
- rcu_state.name, j - gpa, j, gpa,
- READ_ONCE(jiffies_till_next_fqs),
- rcu_get_root()->qsmask);
- /* In this case, the current CPU might be at fault. */
- sched_show_task(current);
- }
- }
- /* Rewrite if needed in case of slow consoles. */
- if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
- WRITE_ONCE(rcu_state.jiffies_stall,
- jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-
- rcu_check_gp_kthread_starvation();
-
- panic_on_rcu_stall();
-
- rcu_force_quiescent_state(); /* Kick them all. */
-}
-
-static void print_cpu_stall(void)
-{
- int cpu;
- unsigned long flags;
- struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
- struct rcu_node *rnp = rcu_get_root();
- long totqlen = 0;
-
- /* Kick and suppress, if so configured. */
- rcu_stall_kick_kthreads();
- if (rcu_cpu_stall_suppress)
- return;
-
- /*
- * OK, time to rat on ourselves...
- * See Documentation/RCU/stallwarn.txt for info on how to debug
- * RCU CPU stall warnings.
- */
- pr_err("INFO: %s self-detected stall on CPU", rcu_state.name);
- print_cpu_stall_info_begin();
- raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
- print_cpu_stall_info(smp_processor_id());
- raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
- print_cpu_stall_info_end();
- for_each_possible_cpu(cpu)
- totqlen += rcu_get_n_cbs_cpu(cpu);
- pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
- jiffies - rcu_state.gp_start,
- (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
-
- rcu_check_gp_kthread_starvation();
-
- rcu_dump_cpu_stacks();
-
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- /* Rewrite if needed in case of slow consoles. */
- if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
- WRITE_ONCE(rcu_state.jiffies_stall,
- jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
- panic_on_rcu_stall();
-
- /*
- * Attempt to revive the RCU machinery by forcing a context switch.
- *
- * A context switch would normally allow the RCU state machine to make
- * progress and it could be we're stuck in kernel space without context
- * switches for an entirely unreasonable amount of time.
- */
- set_tsk_need_resched(current);
- set_preempt_need_resched();
-}
-
-static void check_cpu_stall(struct rcu_data *rdp)
-{
- unsigned long gs1;
- unsigned long gs2;
- unsigned long gps;
- unsigned long j;
- unsigned long jn;
- unsigned long js;
- struct rcu_node *rnp;
-
- if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
- !rcu_gp_in_progress())
- return;
- rcu_stall_kick_kthreads();
- j = jiffies;
-
- /*
- * Lots of memory barriers to reject false positives.
- *
- * The idea is to pick up rcu_state.gp_seq, then
- * rcu_state.jiffies_stall, then rcu_state.gp_start, and finally
- * another copy of rcu_state.gp_seq. These values are updated in
- * the opposite order with memory barriers (or equivalent) during
- * grace-period initialization and cleanup. Now, a false positive
- * can occur if we get an new value of rcu_state.gp_start and a old
- * value of rcu_state.jiffies_stall. But given the memory barriers,
- * the only way that this can happen is if one grace period ends
- * and another starts between these two fetches. This is detected
- * by comparing the second fetch of rcu_state.gp_seq with the
- * previous fetch from rcu_state.gp_seq.
- *
- * Given this check, comparisons of jiffies, rcu_state.jiffies_stall,
- * and rcu_state.gp_start suffice to forestall false positives.
- */
- gs1 = READ_ONCE(rcu_state.gp_seq);
- smp_rmb(); /* Pick up ->gp_seq first... */
- js = READ_ONCE(rcu_state.jiffies_stall);
- smp_rmb(); /* ...then ->jiffies_stall before the rest... */
- gps = READ_ONCE(rcu_state.gp_start);
- smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
- gs2 = READ_ONCE(rcu_state.gp_seq);
- if (gs1 != gs2 ||
- ULONG_CMP_LT(j, js) ||
- ULONG_CMP_GE(gps, js))
- return; /* No stall or GP completed since entering function. */
- rnp = rdp->mynode;
- jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
- if (rcu_gp_in_progress() &&
- (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
- cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
- /* We haven't checked in, so go dump stack. */
- print_cpu_stall();
-
- } else if (rcu_gp_in_progress() &&
- ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
- cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
- /* They had a few time units to dump stack, so complain. */
- print_other_cpu_stall(gs2);
- }
-}
-
-/**
- * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
- *
- * Set the stall-warning timeout way off into the future, thus preventing
- * any RCU CPU stall-warning messages from appearing in the current set of
- * RCU grace periods.
- *
- * The caller must disable hard irqs.
- */
-void rcu_cpu_stall_reset(void)
-{
- WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2);
-}
-
/* Trace-event wrapper function for trace_rcu_future_grace_period. */
static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
unsigned long gp_seq_req, const char *s)
static void rcu_gp_kthread_wake(void)
{
if ((current == rcu_state.gp_kthread &&
- !in_interrupt() && !in_serving_softirq()) ||
+ !in_irq() && !in_serving_softirq()) ||
!READ_ONCE(rcu_state.gp_flags) ||
!rcu_state.gp_kthread)
return;
return;
}
mask = rdp->grpmask;
+ rdp->core_needs_qs = false;
if ((rnp->qsmask & mask) == 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
} else {
- rdp->core_needs_qs = false;
-
/*
* This GP can't end until cpu checks in, so all of our
* callbacks can be processed during the next GP.
}
/*
- * Scan the leaf rcu_node structures, processing dyntick state for any that
- * have not yet encountered a quiescent state, using the function specified.
- * Also initiate boosting for any threads blocked on the root rcu_node.
- *
- * The caller must have suppressed start of new grace periods.
+ * Scan the leaf rcu_node structures. For each structure on which all
+ * CPUs have reported a quiescent state and on which there are tasks
+ * blocking the current grace period, initiate RCU priority boosting.
+ * Otherwise, invoke the specified function to check dyntick state for
+ * each CPU that has not yet reported a quiescent state.
*/
static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
{
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
-/*
- * This function checks for grace-period requests that fail to motivate
- * RCU to come out of its idle mode.
- */
-void
-rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
- const unsigned long gpssdelay)
-{
- unsigned long flags;
- unsigned long j;
- struct rcu_node *rnp_root = rcu_get_root();
- static atomic_t warned = ATOMIC_INIT(0);
-
- if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
- ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
- return;
- j = jiffies; /* Expensive access, and in common case don't get here. */
- if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
- time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
- atomic_read(&warned))
- return;
-
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- j = jiffies;
- if (rcu_gp_in_progress() ||
- ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
- time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
- time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
- atomic_read(&warned)) {
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- return;
- }
- /* Hold onto the leaf lock to make others see warned==1. */
-
- if (rnp_root != rnp)
- raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
- j = jiffies;
- if (rcu_gp_in_progress() ||
- ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
- time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
- time_before(j, rcu_state.gp_activity + gpssdelay) ||
- atomic_xchg(&warned, 1)) {
- raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- return;
- }
- WARN_ON(1);
- if (rnp_root != rnp)
- raw_spin_unlock_rcu_node(rnp_root);
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- show_rcu_gp_kthreads();
-}
-
-/*
- * Do a forward-progress check for rcutorture. This is normally invoked
- * due to an OOM event. The argument "j" gives the time period during
- * which rcutorture would like progress to have been made.
- */
-void rcu_fwd_progress_check(unsigned long j)
-{
- unsigned long cbs;
- int cpu;
- unsigned long max_cbs = 0;
- int max_cpu = -1;
- struct rcu_data *rdp;
-
- if (rcu_gp_in_progress()) {
- pr_info("%s: GP age %lu jiffies\n",
- __func__, jiffies - rcu_state.gp_start);
- show_rcu_gp_kthreads();
- } else {
- pr_info("%s: Last GP end %lu jiffies ago\n",
- __func__, jiffies - rcu_state.gp_end);
- preempt_disable();
- rdp = this_cpu_ptr(&rcu_data);
- rcu_check_gp_start_stall(rdp->mynode, rdp, j);
- preempt_enable();
- }
- for_each_possible_cpu(cpu) {
- cbs = rcu_get_n_cbs_cpu(cpu);
- if (!cbs)
- continue;
- if (max_cpu < 0)
- pr_info("%s: callbacks", __func__);
- pr_cont(" %d: %lu", cpu, cbs);
- if (cbs <= max_cbs)
- continue;
- max_cbs = cbs;
- max_cpu = cpu;
- }
- if (max_cpu >= 0)
- pr_cont("\n");
-}
-EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
-
/* Perform RCU core processing work for the current CPU. */
static __latent_entropy void rcu_core(struct softirq_action *unused)
{
switch (action) {
case PM_HIBERNATION_PREPARE:
case PM_SUSPEND_PREPARE:
- if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
- rcu_expedite_gp();
+ rcu_expedite_gp();
break;
case PM_POST_HIBERNATION:
case PM_POST_SUSPEND:
- if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
- rcu_unexpedite_gp();
+ rcu_unexpedite_gp();
break;
default:
break;
jiffies_till_first_fqs = d;
if (jiffies_till_next_fqs == ULONG_MAX)
jiffies_till_next_fqs = d;
- if (jiffies_till_sched_qs == ULONG_MAX)
- adjust_jiffies_till_sched_qs();
+ adjust_jiffies_till_sched_qs();
/* If the compile-time values are accurate, just leave. */
if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
srcu_init();
}
+#include "tree_stall.h"
#include "tree_exp.h"
#include "tree_plugin.h"
int rcu_dynticks_snap(struct rcu_data *rdp);
-/* Forward declarations for rcutree_plugin.h */
+/* Forward declarations for tree_plugin.h */
static void rcu_bootup_announce(void);
static void rcu_qs(void);
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-static void rcu_print_detail_task_stall(void);
-static int rcu_print_task_stall(struct rcu_node *rnp);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
static void rcu_flavor_sched_clock_irq(int user);
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
static void rcu_preempt_deferred_qs(struct task_struct *t);
-static void print_cpu_stall_info_begin(void);
-static void print_cpu_stall_info(int cpu);
-static void print_cpu_stall_info_end(void);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static bool rcu_nocb_cpu_needs_barrier(int cpu);
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
static bool rcu_nohz_full_cpu(void);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
+
+/* Forward declarations for tree_stall.h */
+static void record_gp_stall_check_time(void);
+static void rcu_iw_handler(struct irq_work *iwp);
+static void check_cpu_stall(struct rcu_data *rdp);
+static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
+ const unsigned long gpssdelay);
#include <linux/lockdep.h>
static void rcu_exp_handler(void *unused);
+static int rcu_print_task_exp_stall(struct rcu_node *rnp);
/*
* Record the start of an expedited grace period.
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rnp->expmask & rdp->grpmask) {
rdp->deferred_qs = true;
- WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
+ t->rcu_read_unlock_special.b.exp_hint = true;
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
*
* If the CPU is fully enabled (or if some buggy RCU-preempt
* read-side critical section is being used from idle), just
- * invoke rcu_preempt_defer_qs() to immediately report the
+ * invoke rcu_preempt_deferred_qs() to immediately report the
* quiescent state. We cannot use rcu_read_unlock_special()
* because we are in an interrupt handler, which will cause that
* function to take an early exit without doing anything.
{
}
+/*
+ * Scan the current list of tasks blocked within RCU read-side critical
+ * sections, printing out the tid of each that is blocking the current
+ * expedited grace period.
+ */
+static int rcu_print_task_exp_stall(struct rcu_node *rnp)
+{
+ struct task_struct *t;
+ int ndetected = 0;
+
+ if (!rnp->exp_tasks)
+ return 0;
+ t = list_entry(rnp->exp_tasks->prev,
+ struct task_struct, rcu_node_entry);
+ list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+ pr_cont(" P%d", t->pid);
+ ndetected++;
+ }
+ return ndetected;
+}
+
#else /* #ifdef CONFIG_PREEMPT_RCU */
/* Invoked on each online non-idle CPU for expedited quiescent state. */
WARN_ON_ONCE(ret);
}
+/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections that are
+ * blocking the current expedited grace period.
+ */
+static int rcu_print_task_exp_stall(struct rcu_node *rnp)
+{
+ return 0;
+}
+
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
/**
TPS("cpuqs"));
__this_cpu_write(rcu_data.cpu_no_qs.b.norm, false);
barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */
- current->rcu_read_unlock_special.b.need_qs = false;
+ WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, false);
}
}
rcu_preempt_deferred_qs_irqrestore(t, flags);
}
-/*
- * Dump detailed information for all tasks blocking the current RCU
- * grace period on the specified rcu_node structure.
- */
-static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
-{
- unsigned long flags;
- struct task_struct *t;
-
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if (!rcu_preempt_blocked_readers_cgp(rnp)) {
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- return;
- }
- t = list_entry(rnp->gp_tasks->prev,
- struct task_struct, rcu_node_entry);
- list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
- /*
- * We could be printing a lot while holding a spinlock.
- * Avoid triggering hard lockup.
- */
- touch_nmi_watchdog();
- sched_show_task(t);
- }
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-}
-
-/*
- * Dump detailed information for all tasks blocking the current RCU
- * grace period.
- */
-static void rcu_print_detail_task_stall(void)
-{
- struct rcu_node *rnp = rcu_get_root();
-
- rcu_print_detail_task_stall_rnp(rnp);
- rcu_for_each_leaf_node(rnp)
- rcu_print_detail_task_stall_rnp(rnp);
-}
-
-static void rcu_print_task_stall_begin(struct rcu_node *rnp)
-{
- pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
- rnp->level, rnp->grplo, rnp->grphi);
-}
-
-static void rcu_print_task_stall_end(void)
-{
- pr_cont("\n");
-}
-
-/*
- * Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each.
- */
-static int rcu_print_task_stall(struct rcu_node *rnp)
-{
- struct task_struct *t;
- int ndetected = 0;
-
- if (!rcu_preempt_blocked_readers_cgp(rnp))
- return 0;
- rcu_print_task_stall_begin(rnp);
- t = list_entry(rnp->gp_tasks->prev,
- struct task_struct, rcu_node_entry);
- list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
- pr_cont(" P%d", t->pid);
- ndetected++;
- }
- rcu_print_task_stall_end();
- return ndetected;
-}
-
-/*
- * Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each that is blocking the current
- * expedited grace period.
- */
-static int rcu_print_task_exp_stall(struct rcu_node *rnp)
-{
- struct task_struct *t;
- int ndetected = 0;
-
- if (!rnp->exp_tasks)
- return 0;
- t = list_entry(rnp->exp_tasks->prev,
- struct task_struct, rcu_node_entry);
- list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
- pr_cont(" P%d", t->pid);
- ndetected++;
- }
- return ndetected;
-}
-
/*
* Check that the list of blocked tasks for the newly completed grace
* period is in fact empty. It is a serious bug to complete a grace
/*
* Check for a task exiting while in a preemptible-RCU read-side
- * critical section, clean up if so. No need to issue warnings,
- * as debug_check_no_locks_held() already does this if lockdep
- * is enabled.
+ * critical section, clean up if so. No need to issue warnings, as
+ * debug_check_no_locks_held() already does this if lockdep is enabled.
+ * Besides, if this function does anything other than just immediately
+ * return, there was a bug of some sort. Spewing warnings from this
+ * function is like as not to simply obscure important prior warnings.
*/
void exit_rcu(void)
{
struct task_struct *t = current;
- if (likely(list_empty(¤t->rcu_node_entry)))
+ if (unlikely(!list_empty(¤t->rcu_node_entry))) {
+ t->rcu_read_lock_nesting = 1;
+ barrier();
+ WRITE_ONCE(t->rcu_read_unlock_special.b.blocked, true);
+ } else if (unlikely(t->rcu_read_lock_nesting)) {
+ t->rcu_read_lock_nesting = 1;
+ } else {
return;
- t->rcu_read_lock_nesting = 1;
- barrier();
- t->rcu_read_unlock_special.b.blocked = true;
+ }
__rcu_read_unlock();
rcu_preempt_deferred_qs(current);
}
}
static void rcu_preempt_deferred_qs(struct task_struct *t) { }
-/*
- * Because preemptible RCU does not exist, we never have to check for
- * tasks blocked within RCU read-side critical sections.
- */
-static void rcu_print_detail_task_stall(void)
-{
-}
-
-/*
- * Because preemptible RCU does not exist, we never have to check for
- * tasks blocked within RCU read-side critical sections.
- */
-static int rcu_print_task_stall(struct rcu_node *rnp)
-{
- return 0;
-}
-
-/*
- * Because preemptible RCU does not exist, we never have to check for
- * tasks blocked within RCU read-side critical sections that are
- * blocking the current expedited grace period.
- */
-static int rcu_print_task_exp_stall(struct rcu_node *rnp)
-{
- return 0;
-}
-
/*
* Because there is no preemptible RCU, there can be no readers blocked,
* so there is no need to check for blocked tasks. So check only for
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
- struct task_struct *t;
-
raw_lockdep_assert_held_rcu_node(rnp);
if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (rnp->exp_tasks == NULL)
rnp->boost_tasks = rnp->gp_tasks;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- t = rnp->boost_kthread_task;
- if (t)
- rcu_wake_cond(t, rnp->boost_kthread_status);
+ rcu_wake_cond(rnp->boost_kthread_task,
+ rnp->boost_kthread_status);
} else {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
-#ifdef CONFIG_RCU_FAST_NO_HZ
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
- struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-
- sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
- rdp->last_accelerate & 0xffff, jiffies & 0xffff,
- ".l"[rdp->all_lazy],
- ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
- ".D"[!rdp->tick_nohz_enabled_snap]);
-}
-
-#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
- *cp = '\0';
-}
-
-#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
-
-/* Initiate the stall-info list. */
-static void print_cpu_stall_info_begin(void)
-{
- pr_cont("\n");
-}
-
-/*
- * Print out diagnostic information for the specified stalled CPU.
- *
- * If the specified CPU is aware of the current RCU grace period, then
- * print the number of scheduling clock interrupts the CPU has taken
- * during the time that it has been aware. Otherwise, print the number
- * of RCU grace periods that this CPU is ignorant of, for example, "1"
- * if the CPU was aware of the previous grace period.
- *
- * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
- */
-static void print_cpu_stall_info(int cpu)
-{
- unsigned long delta;
- char fast_no_hz[72];
- struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
- char *ticks_title;
- unsigned long ticks_value;
-
- /*
- * We could be printing a lot while holding a spinlock. Avoid
- * triggering hard lockup.
- */
- touch_nmi_watchdog();
-
- ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq);
- if (ticks_value) {
- ticks_title = "GPs behind";
- } else {
- ticks_title = "ticks this GP";
- ticks_value = rdp->ticks_this_gp;
- }
- print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
- delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
- pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
- cpu,
- "O."[!!cpu_online(cpu)],
- "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
- "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
- !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' :
- rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
- "!."[!delta],
- ticks_value, ticks_title,
- rcu_dynticks_snap(rdp) & 0xfff,
- rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
- rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
- READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
- fast_no_hz);
-}
-
-/* Terminate the stall-info list. */
-static void print_cpu_stall_info_end(void)
-{
- pr_err("\t");
-}
-
-/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */
-static void zero_cpu_stall_ticks(struct rcu_data *rdp)
-{
- rdp->ticks_this_gp = 0;
- rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id());
- WRITE_ONCE(rdp->last_fqs_resched, jiffies);
-}
-
#ifdef CONFIG_RCU_NOCB_CPU
/*
*/
-/* Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. */
+/*
+ * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters.
+ * The string after the "rcu_nocbs=" is either "all" for all CPUs, or a
+ * comma-separated list of CPUs and/or CPU ranges. If an invalid list is
+ * given, a warning is emitted and all CPUs are offloaded.
+ */
static int __init rcu_nocb_setup(char *str)
{
alloc_bootmem_cpumask_var(&rcu_nocb_mask);
- cpulist_parse(str, rcu_nocb_mask);
+ if (!strcasecmp(str, "all"))
+ cpumask_setall(rcu_nocb_mask);
+ else
+ if (cpulist_parse(str, rcu_nocb_mask)) {
+ pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n");
+ cpumask_setall(rcu_nocb_mask);
+ }
return 1;
}
__setup("rcu_nocbs=", rcu_nocb_setup);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * RCU CPU stall warnings for normal RCU grace periods
+ *
+ * Copyright IBM Corporation, 2019
+ *
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
+ */
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// Controlling CPU stall warnings, including delay calculation.
+
+/* panic() on RCU Stall sysctl. */
+int sysctl_panic_on_rcu_stall __read_mostly;
+
+#ifdef CONFIG_PROVE_RCU
+#define RCU_STALL_DELAY_DELTA (5 * HZ)
+#else
+#define RCU_STALL_DELAY_DELTA 0
+#endif
+
+/* Limit-check stall timeouts specified at boottime and runtime. */
+int rcu_jiffies_till_stall_check(void)
+{
+ int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
+
+ /*
+ * Limit check must be consistent with the Kconfig limits
+ * for CONFIG_RCU_CPU_STALL_TIMEOUT.
+ */
+ if (till_stall_check < 3) {
+ WRITE_ONCE(rcu_cpu_stall_timeout, 3);
+ till_stall_check = 3;
+ } else if (till_stall_check > 300) {
+ WRITE_ONCE(rcu_cpu_stall_timeout, 300);
+ till_stall_check = 300;
+ }
+ return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
+}
+EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
+
+/* Don't do RCU CPU stall warnings during long sysrq printouts. */
+void rcu_sysrq_start(void)
+{
+ if (!rcu_cpu_stall_suppress)
+ rcu_cpu_stall_suppress = 2;
+}
+
+void rcu_sysrq_end(void)
+{
+ if (rcu_cpu_stall_suppress == 2)
+ rcu_cpu_stall_suppress = 0;
+}
+
+/* Don't print RCU CPU stall warnings during a kernel panic. */
+static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
+{
+ rcu_cpu_stall_suppress = 1;
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block rcu_panic_block = {
+ .notifier_call = rcu_panic,
+};
+
+static int __init check_cpu_stall_init(void)
+{
+ atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
+ return 0;
+}
+early_initcall(check_cpu_stall_init);
+
+/* If so specified via sysctl, panic, yielding cleaner stall-warning output. */
+static void panic_on_rcu_stall(void)
+{
+ if (sysctl_panic_on_rcu_stall)
+ panic("RCU Stall\n");
+}
+
+/**
+ * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
+ *
+ * Set the stall-warning timeout way off into the future, thus preventing
+ * any RCU CPU stall-warning messages from appearing in the current set of
+ * RCU grace periods.
+ *
+ * The caller must disable hard irqs.
+ */
+void rcu_cpu_stall_reset(void)
+{
+ WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2);
+}
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// Interaction with RCU grace periods
+
+/* Start of new grace period, so record stall time (and forcing times). */
+static void record_gp_stall_check_time(void)
+{
+ unsigned long j = jiffies;
+ unsigned long j1;
+
+ rcu_state.gp_start = j;
+ j1 = rcu_jiffies_till_stall_check();
+ /* Record ->gp_start before ->jiffies_stall. */
+ smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
+ rcu_state.jiffies_resched = j + j1 / 2;
+ rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
+}
+
+/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */
+static void zero_cpu_stall_ticks(struct rcu_data *rdp)
+{
+ rdp->ticks_this_gp = 0;
+ rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id());
+ WRITE_ONCE(rdp->last_fqs_resched, jiffies);
+}
+
+/*
+ * If too much time has passed in the current grace period, and if
+ * so configured, go kick the relevant kthreads.
+ */
+static void rcu_stall_kick_kthreads(void)
+{
+ unsigned long j;
+
+ if (!rcu_kick_kthreads)
+ return;
+ j = READ_ONCE(rcu_state.jiffies_kick_kthreads);
+ if (time_after(jiffies, j) && rcu_state.gp_kthread &&
+ (rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) {
+ WARN_ONCE(1, "Kicking %s grace-period kthread\n",
+ rcu_state.name);
+ rcu_ftrace_dump(DUMP_ALL);
+ wake_up_process(rcu_state.gp_kthread);
+ WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ);
+ }
+}
+
+/*
+ * Handler for the irq_work request posted about halfway into the RCU CPU
+ * stall timeout, and used to detect excessive irq disabling. Set state
+ * appropriately, but just complain if there is unexpected state on entry.
+ */
+static void rcu_iw_handler(struct irq_work *iwp)
+{
+ struct rcu_data *rdp;
+ struct rcu_node *rnp;
+
+ rdp = container_of(iwp, struct rcu_data, rcu_iw);
+ rnp = rdp->mynode;
+ raw_spin_lock_rcu_node(rnp);
+ if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
+ rdp->rcu_iw_gp_seq = rnp->gp_seq;
+ rdp->rcu_iw_pending = false;
+ }
+ raw_spin_unlock_rcu_node(rnp);
+}
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// Printing RCU CPU stall warnings
+
+#ifdef CONFIG_PREEMPT
+
+/*
+ * Dump detailed information for all tasks blocking the current RCU
+ * grace period on the specified rcu_node structure.
+ */
+static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
+{
+ unsigned long flags;
+ struct task_struct *t;
+
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ if (!rcu_preempt_blocked_readers_cgp(rnp)) {
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ return;
+ }
+ t = list_entry(rnp->gp_tasks->prev,
+ struct task_struct, rcu_node_entry);
+ list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+ /*
+ * We could be printing a lot while holding a spinlock.
+ * Avoid triggering hard lockup.
+ */
+ touch_nmi_watchdog();
+ sched_show_task(t);
+ }
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+}
+
+/*
+ * Scan the current list of tasks blocked within RCU read-side critical
+ * sections, printing out the tid of each.
+ */
+static int rcu_print_task_stall(struct rcu_node *rnp)
+{
+ struct task_struct *t;
+ int ndetected = 0;
+
+ if (!rcu_preempt_blocked_readers_cgp(rnp))
+ return 0;
+ pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
+ rnp->level, rnp->grplo, rnp->grphi);
+ t = list_entry(rnp->gp_tasks->prev,
+ struct task_struct, rcu_node_entry);
+ list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+ pr_cont(" P%d", t->pid);
+ ndetected++;
+ }
+ pr_cont("\n");
+ return ndetected;
+}
+
+#else /* #ifdef CONFIG_PREEMPT */
+
+/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
+static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
+{
+}
+
+/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
+static int rcu_print_task_stall(struct rcu_node *rnp)
+{
+ return 0;
+}
+#endif /* #else #ifdef CONFIG_PREEMPT */
+
+/*
+ * Dump stacks of all tasks running on stalled CPUs. First try using
+ * NMIs, but fall back to manual remote stack tracing on architectures
+ * that don't support NMI-based stack dumps. The NMI-triggered stack
+ * traces are more accurate because they are printed by the target CPU.
+ */
+static void rcu_dump_cpu_stacks(void)
+{
+ int cpu;
+ unsigned long flags;
+ struct rcu_node *rnp;
+
+ rcu_for_each_leaf_node(rnp) {
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ for_each_leaf_node_possible_cpu(rnp, cpu)
+ if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+ if (!trigger_single_cpu_backtrace(cpu))
+ dump_cpu_task(cpu);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ }
+}
+
+#ifdef CONFIG_RCU_FAST_NO_HZ
+
+static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
+{
+ struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+
+ sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
+ rdp->last_accelerate & 0xffff, jiffies & 0xffff,
+ ".l"[rdp->all_lazy],
+ ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
+ ".D"[!!rdp->tick_nohz_enabled_snap]);
+}
+
+#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
+
+static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
+{
+ *cp = '\0';
+}
+
+#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
+
+/*
+ * Print out diagnostic information for the specified stalled CPU.
+ *
+ * If the specified CPU is aware of the current RCU grace period, then
+ * print the number of scheduling clock interrupts the CPU has taken
+ * during the time that it has been aware. Otherwise, print the number
+ * of RCU grace periods that this CPU is ignorant of, for example, "1"
+ * if the CPU was aware of the previous grace period.
+ *
+ * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
+ */
+static void print_cpu_stall_info(int cpu)
+{
+ unsigned long delta;
+ char fast_no_hz[72];
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ char *ticks_title;
+ unsigned long ticks_value;
+
+ /*
+ * We could be printing a lot while holding a spinlock. Avoid
+ * triggering hard lockup.
+ */
+ touch_nmi_watchdog();
+
+ ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq);
+ if (ticks_value) {
+ ticks_title = "GPs behind";
+ } else {
+ ticks_title = "ticks this GP";
+ ticks_value = rdp->ticks_this_gp;
+ }
+ print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
+ delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
+ pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
+ cpu,
+ "O."[!!cpu_online(cpu)],
+ "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
+ "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
+ !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' :
+ rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
+ "!."[!delta],
+ ticks_value, ticks_title,
+ rcu_dynticks_snap(rdp) & 0xfff,
+ rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
+ rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
+ READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
+ fast_no_hz);
+}
+
+/* Complain about starvation of grace-period kthread. */
+static void rcu_check_gp_kthread_starvation(void)
+{
+ struct task_struct *gpk = rcu_state.gp_kthread;
+ unsigned long j;
+
+ j = jiffies - READ_ONCE(rcu_state.gp_activity);
+ if (j > 2 * HZ) {
+ pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
+ rcu_state.name, j,
+ (long)rcu_seq_current(&rcu_state.gp_seq),
+ READ_ONCE(rcu_state.gp_flags),
+ gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
+ gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
+ if (gpk) {
+ pr_err("RCU grace-period kthread stack dump:\n");
+ sched_show_task(gpk);
+ wake_up_process(gpk);
+ }
+ }
+}
+
+static void print_other_cpu_stall(unsigned long gp_seq)
+{
+ int cpu;
+ unsigned long flags;
+ unsigned long gpa;
+ unsigned long j;
+ int ndetected = 0;
+ struct rcu_node *rnp;
+ long totqlen = 0;
+
+ /* Kick and suppress, if so configured. */
+ rcu_stall_kick_kthreads();
+ if (rcu_cpu_stall_suppress)
+ return;
+
+ /*
+ * OK, time to rat on our buddy...
+ * See Documentation/RCU/stallwarn.txt for info on how to debug
+ * RCU CPU stall warnings.
+ */
+ pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
+ rcu_for_each_leaf_node(rnp) {
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ ndetected += rcu_print_task_stall(rnp);
+ if (rnp->qsmask != 0) {
+ for_each_leaf_node_possible_cpu(rnp, cpu)
+ if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
+ print_cpu_stall_info(cpu);
+ ndetected++;
+ }
+ }
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ }
+
+ for_each_possible_cpu(cpu)
+ totqlen += rcu_get_n_cbs_cpu(cpu);
+ pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
+ smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
+ (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
+ if (ndetected) {
+ rcu_dump_cpu_stacks();
+
+ /* Complain about tasks blocking the grace period. */
+ rcu_for_each_leaf_node(rnp)
+ rcu_print_detail_task_stall_rnp(rnp);
+ } else {
+ if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) {
+ pr_err("INFO: Stall ended before state dump start\n");
+ } else {
+ j = jiffies;
+ gpa = READ_ONCE(rcu_state.gp_activity);
+ pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
+ rcu_state.name, j - gpa, j, gpa,
+ READ_ONCE(jiffies_till_next_fqs),
+ rcu_get_root()->qsmask);
+ /* In this case, the current CPU might be at fault. */
+ sched_show_task(current);
+ }
+ }
+ /* Rewrite if needed in case of slow consoles. */
+ if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
+ WRITE_ONCE(rcu_state.jiffies_stall,
+ jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
+
+ rcu_check_gp_kthread_starvation();
+
+ panic_on_rcu_stall();
+
+ rcu_force_quiescent_state(); /* Kick them all. */
+}
+
+static void print_cpu_stall(void)
+{
+ int cpu;
+ unsigned long flags;
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+ struct rcu_node *rnp = rcu_get_root();
+ long totqlen = 0;
+
+ /* Kick and suppress, if so configured. */
+ rcu_stall_kick_kthreads();
+ if (rcu_cpu_stall_suppress)
+ return;
+
+ /*
+ * OK, time to rat on ourselves...
+ * See Documentation/RCU/stallwarn.txt for info on how to debug
+ * RCU CPU stall warnings.
+ */
+ pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
+ raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
+ print_cpu_stall_info(smp_processor_id());
+ raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
+ for_each_possible_cpu(cpu)
+ totqlen += rcu_get_n_cbs_cpu(cpu);
+ pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n",
+ jiffies - rcu_state.gp_start,
+ (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
+
+ rcu_check_gp_kthread_starvation();
+
+ rcu_dump_cpu_stacks();
+
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ /* Rewrite if needed in case of slow consoles. */
+ if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
+ WRITE_ONCE(rcu_state.jiffies_stall,
+ jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+ panic_on_rcu_stall();
+
+ /*
+ * Attempt to revive the RCU machinery by forcing a context switch.
+ *
+ * A context switch would normally allow the RCU state machine to make
+ * progress and it could be we're stuck in kernel space without context
+ * switches for an entirely unreasonable amount of time.
+ */
+ set_tsk_need_resched(current);
+ set_preempt_need_resched();
+}
+
+static void check_cpu_stall(struct rcu_data *rdp)
+{
+ unsigned long gs1;
+ unsigned long gs2;
+ unsigned long gps;
+ unsigned long j;
+ unsigned long jn;
+ unsigned long js;
+ struct rcu_node *rnp;
+
+ if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
+ !rcu_gp_in_progress())
+ return;
+ rcu_stall_kick_kthreads();
+ j = jiffies;
+
+ /*
+ * Lots of memory barriers to reject false positives.
+ *
+ * The idea is to pick up rcu_state.gp_seq, then
+ * rcu_state.jiffies_stall, then rcu_state.gp_start, and finally
+ * another copy of rcu_state.gp_seq. These values are updated in
+ * the opposite order with memory barriers (or equivalent) during
+ * grace-period initialization and cleanup. Now, a false positive
+ * can occur if we get an new value of rcu_state.gp_start and a old
+ * value of rcu_state.jiffies_stall. But given the memory barriers,
+ * the only way that this can happen is if one grace period ends
+ * and another starts between these two fetches. This is detected
+ * by comparing the second fetch of rcu_state.gp_seq with the
+ * previous fetch from rcu_state.gp_seq.
+ *
+ * Given this check, comparisons of jiffies, rcu_state.jiffies_stall,
+ * and rcu_state.gp_start suffice to forestall false positives.
+ */
+ gs1 = READ_ONCE(rcu_state.gp_seq);
+ smp_rmb(); /* Pick up ->gp_seq first... */
+ js = READ_ONCE(rcu_state.jiffies_stall);
+ smp_rmb(); /* ...then ->jiffies_stall before the rest... */
+ gps = READ_ONCE(rcu_state.gp_start);
+ smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
+ gs2 = READ_ONCE(rcu_state.gp_seq);
+ if (gs1 != gs2 ||
+ ULONG_CMP_LT(j, js) ||
+ ULONG_CMP_GE(gps, js))
+ return; /* No stall or GP completed since entering function. */
+ rnp = rdp->mynode;
+ jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+ if (rcu_gp_in_progress() &&
+ (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+ cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
+
+ /* We haven't checked in, so go dump stack. */
+ print_cpu_stall();
+
+ } else if (rcu_gp_in_progress() &&
+ ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+ cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
+
+ /* They had a few time units to dump stack, so complain. */
+ print_other_cpu_stall(gs2);
+ }
+}
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// RCU forward-progress mechanisms, including of callback invocation.
+
+
+/*
+ * Show the state of the grace-period kthreads.
+ */
+void show_rcu_gp_kthreads(void)
+{
+ int cpu;
+ unsigned long j;
+ unsigned long ja;
+ unsigned long jr;
+ unsigned long jw;
+ struct rcu_data *rdp;
+ struct rcu_node *rnp;
+
+ j = jiffies;
+ ja = j - READ_ONCE(rcu_state.gp_activity);
+ jr = j - READ_ONCE(rcu_state.gp_req_activity);
+ jw = j - READ_ONCE(rcu_state.gp_wake_time);
+ pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
+ rcu_state.name, gp_state_getname(rcu_state.gp_state),
+ rcu_state.gp_state,
+ rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
+ ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
+ (long)READ_ONCE(rcu_state.gp_seq),
+ (long)READ_ONCE(rcu_get_root()->gp_seq_needed),
+ READ_ONCE(rcu_state.gp_flags));
+ rcu_for_each_node_breadth_first(rnp) {
+ if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
+ continue;
+ pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
+ rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
+ (long)rnp->gp_seq_needed);
+ if (!rcu_is_leaf_node(rnp))
+ continue;
+ for_each_leaf_node_possible_cpu(rnp, cpu) {
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ if (rdp->gpwrap ||
+ ULONG_CMP_GE(rcu_state.gp_seq,
+ rdp->gp_seq_needed))
+ continue;
+ pr_info("\tcpu %d ->gp_seq_needed %ld\n",
+ cpu, (long)rdp->gp_seq_needed);
+ }
+ }
+ /* sched_show_task(rcu_state.gp_kthread); */
+}
+EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
+
+/*
+ * This function checks for grace-period requests that fail to motivate
+ * RCU to come out of its idle mode.
+ */
+static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
+ const unsigned long gpssdelay)
+{
+ unsigned long flags;
+ unsigned long j;
+ struct rcu_node *rnp_root = rcu_get_root();
+ static atomic_t warned = ATOMIC_INIT(0);
+
+ if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
+ ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+ return;
+ j = jiffies; /* Expensive access, and in common case don't get here. */
+ if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
+ time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
+ atomic_read(&warned))
+ return;
+
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ j = jiffies;
+ if (rcu_gp_in_progress() ||
+ ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+ time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
+ time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
+ atomic_read(&warned)) {
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ return;
+ }
+ /* Hold onto the leaf lock to make others see warned==1. */
+
+ if (rnp_root != rnp)
+ raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+ j = jiffies;
+ if (rcu_gp_in_progress() ||
+ ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+ time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
+ time_before(j, rcu_state.gp_activity + gpssdelay) ||
+ atomic_xchg(&warned, 1)) {
+ raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ return;
+ }
+ WARN_ON(1);
+ if (rnp_root != rnp)
+ raw_spin_unlock_rcu_node(rnp_root);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ show_rcu_gp_kthreads();
+}
+
+/*
+ * Do a forward-progress check for rcutorture. This is normally invoked
+ * due to an OOM event. The argument "j" gives the time period during
+ * which rcutorture would like progress to have been made.
+ */
+void rcu_fwd_progress_check(unsigned long j)
+{
+ unsigned long cbs;
+ int cpu;
+ unsigned long max_cbs = 0;
+ int max_cpu = -1;
+ struct rcu_data *rdp;
+
+ if (rcu_gp_in_progress()) {
+ pr_info("%s: GP age %lu jiffies\n",
+ __func__, jiffies - rcu_state.gp_start);
+ show_rcu_gp_kthreads();
+ } else {
+ pr_info("%s: Last GP end %lu jiffies ago\n",
+ __func__, jiffies - rcu_state.gp_end);
+ preempt_disable();
+ rdp = this_cpu_ptr(&rcu_data);
+ rcu_check_gp_start_stall(rdp->mynode, rdp, j);
+ preempt_enable();
+ }
+ for_each_possible_cpu(cpu) {
+ cbs = rcu_get_n_cbs_cpu(cpu);
+ if (!cbs)
+ continue;
+ if (max_cpu < 0)
+ pr_info("%s: callbacks", __func__);
+ pr_cont(" %d: %lu", cpu, cbs);
+ if (cbs <= max_cbs)
+ continue;
+ max_cbs = cbs;
+ max_cpu = cpu;
+ }
+ if (max_cpu >= 0)
+ pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
+
+/* Commandeer a sysrq key to dump RCU's tree. */
+static bool sysrq_rcu;
+module_param(sysrq_rcu, bool, 0444);
+
+/* Dump grace-period-request information due to commandeered sysrq. */
+static void sysrq_show_rcu(int key)
+{
+ show_rcu_gp_kthreads();
+}
+
+static struct sysrq_key_op sysrq_rcudump_op = {
+ .handler = sysrq_show_rcu,
+ .help_msg = "show-rcu(y)",
+ .action_msg = "Show RCU tree",
+ .enable_mask = SYSRQ_ENABLE_DUMP,
+};
+
+static int __init rcu_sysrq_init(void)
+{
+ if (sysrq_rcu)
+ return register_sysrq_key('y', &sysrq_rcudump_op);
+ return 0;
+}
+early_initcall(rcu_sysrq_init);
#endif
#ifdef CONFIG_RCU_STALL_COMMON
-
-#ifdef CONFIG_PROVE_RCU
-#define RCU_STALL_DELAY_DELTA (5 * HZ)
-#else
-#define RCU_STALL_DELAY_DELTA 0
-#endif
-
int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
-static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
-
module_param(rcu_cpu_stall_suppress, int, 0644);
+int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
module_param(rcu_cpu_stall_timeout, int, 0644);
-
-int rcu_jiffies_till_stall_check(void)
-{
- int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
-
- /*
- * Limit check must be consistent with the Kconfig limits
- * for CONFIG_RCU_CPU_STALL_TIMEOUT.
- */
- if (till_stall_check < 3) {
- WRITE_ONCE(rcu_cpu_stall_timeout, 3);
- till_stall_check = 3;
- } else if (till_stall_check > 300) {
- WRITE_ONCE(rcu_cpu_stall_timeout, 300);
- till_stall_check = 300;
- }
- return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
-}
-EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
-
-void rcu_sysrq_start(void)
-{
- if (!rcu_cpu_stall_suppress)
- rcu_cpu_stall_suppress = 2;
-}
-
-void rcu_sysrq_end(void)
-{
- if (rcu_cpu_stall_suppress == 2)
- rcu_cpu_stall_suppress = 0;
-}
-
-static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
-{
- rcu_cpu_stall_suppress = 1;
- return NOTIFY_DONE;
-}
-
-static struct notifier_block rcu_panic_block = {
- .notifier_call = rcu_panic,
-};
-
-static int __init check_cpu_stall_init(void)
-{
- atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
- return 0;
-}
-early_initcall(check_cpu_stall_init);
-
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
#ifdef CONFIG_TASKS_RCU
int region_intersects(resource_size_t start, size_t size, unsigned long flags,
unsigned long desc)
{
- resource_size_t end = start + size - 1;
+ struct resource res;
int type = 0; int other = 0;
struct resource *p;
+ res.start = start;
+ res.end = start + size - 1;
+
read_lock(&resource_lock);
for (p = iomem_resource.child; p ; p = p->sibling) {
bool is_type = (((p->flags & flags) == flags) &&
((desc == IORES_DESC_NONE) ||
(desc == p->desc)));
- if (start >= p->start && start <= p->end)
- is_type ? type++ : other++;
- if (end >= p->start && end <= p->end)
- is_type ? type++ : other++;
- if (p->start >= start && p->end <= end)
+ if (resource_overlaps(p, &res))
is_type ? type++ : other++;
}
read_unlock(&resource_lock);
* - signal delivery,
* and return to user-space.
*
- * This is how we can ensure that the entire rseq critical section,
- * consisting of both the C part and the assembly instruction sequence,
+ * This is how we can ensure that the entire rseq critical section
* will issue the commit instruction only if executed atomically with
* respect to other threads scheduled on the same CPU, and with respect
* to signal handlers.
/* Unregister rseq for current thread. */
if (current->rseq != rseq || !current->rseq)
return -EINVAL;
- if (current->rseq_len != rseq_len)
+ if (rseq_len != sizeof(*rseq))
return -EINVAL;
if (current->rseq_sig != sig)
return -EPERM;
if (ret)
return ret;
current->rseq = NULL;
- current->rseq_len = 0;
current->rseq_sig = 0;
return 0;
}
* the provided address differs from the prior
* one.
*/
- if (current->rseq != rseq || current->rseq_len != rseq_len)
+ if (current->rseq != rseq || rseq_len != sizeof(*rseq))
return -EINVAL;
if (current->rseq_sig != sig)
return -EPERM;
if (!access_ok(rseq, rseq_len))
return -EFAULT;
current->rseq = rseq;
- current->rseq_len = rseq_len;
current->rseq_sig = sig;
/*
* If rseq was previously inactive, and has just been
rq->nr_uninterruptible--;
enqueue_task(rq, p, flags);
+
+ p->on_rq = TASK_ON_RQ_QUEUED;
}
void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{
+ p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
+
if (task_contributes_to_load(p))
rq->nr_uninterruptible++;
}
/*
- * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
* __set_cpus_allowed_ptr() and select_fallback_rq().
*/
static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
/* Need help from migration thread: drop lock and wait. */
task_rq_unlock(rq, p, &rf);
stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
- tlb_migrate_finish(p->mm);
return 0;
} else if (task_on_rq_queued(p)) {
/*
rq_pin_lock(src_rq, &srf);
rq_pin_lock(dst_rq, &drf);
- p->on_rq = TASK_ON_RQ_MIGRATING;
deactivate_task(src_rq, p, 0);
set_task_cpu(p, cpu);
activate_task(dst_rq, p, 0);
- p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(dst_rq, p, 0);
rq_unpin_lock(dst_rq, &drf);
__schedstat_inc(p->se.statistics.nr_wakeups_sync);
}
-static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
-{
- activate_task(rq, p, en_flags);
- p->on_rq = TASK_ON_RQ_QUEUED;
-
- /* If a worker is waking up, notify the workqueue: */
- if (p->flags & PF_WQ_WORKER)
- wq_worker_waking_up(p, cpu_of(rq));
-}
-
/*
* Mark the task runnable and perform wakeup-preemption.
*/
en_flags |= ENQUEUE_MIGRATED;
#endif
- ttwu_activate(rq, p, en_flags);
+ activate_task(rq, p, en_flags);
ttwu_do_wakeup(rq, p, wake_flags, rf);
}
return success;
}
-/**
- * try_to_wake_up_local - try to wake up a local task with rq lock held
- * @p: the thread to be awakened
- * @rf: request-queue flags for pinning
- *
- * Put @p on the run-queue if it's not already there. The caller must
- * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.
- */
-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
-{
- struct rq *rq = task_rq(p);
-
- if (WARN_ON_ONCE(rq != this_rq()) ||
- WARN_ON_ONCE(p == current))
- return;
-
- lockdep_assert_held(&rq->lock);
-
- if (!raw_spin_trylock(&p->pi_lock)) {
- /*
- * This is OK, because current is on_cpu, which avoids it being
- * picked for load-balance and preemption/IRQs are still
- * disabled avoiding further scheduler activity on it and we've
- * not yet picked a replacement task.
- */
- rq_unlock(rq, rf);
- raw_spin_lock(&p->pi_lock);
- rq_relock(rq, rf);
- }
-
- if (!(p->state & TASK_NORMAL))
- goto out;
-
- trace_sched_waking(p);
-
- if (!task_on_rq_queued(p)) {
- if (p->in_iowait) {
- delayacct_blkio_end(p);
- atomic_dec(&rq->nr_iowait);
- }
- ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
- }
-
- ttwu_do_wakeup(rq, p, 0, rf);
- ttwu_stat(p, smp_processor_id(), 0);
-out:
- raw_spin_unlock(&p->pi_lock);
-}
-
/**
* wake_up_process - Wake up a specific process
* @p: The process to be woken up.
post_init_entity_util_avg(p);
activate_task(rq, p, ENQUEUE_NOCLOCK);
- p->on_rq = TASK_ON_RQ_QUEUED;
trace_sched_wakeup_new(p);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
prev->state = TASK_RUNNING;
} else {
deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
- prev->on_rq = 0;
if (prev->in_iowait) {
atomic_inc(&rq->nr_iowait);
delayacct_blkio_start();
}
-
- /*
- * If a worker went to sleep, notify and ask workqueue
- * whether it wants to wake up a task to maintain
- * concurrency.
- */
- if (prev->flags & PF_WQ_WORKER) {
- struct task_struct *to_wakeup;
-
- to_wakeup = wq_worker_sleeping(prev);
- if (to_wakeup)
- try_to_wake_up_local(to_wakeup, &rf);
- }
}
switch_count = &prev->nvcsw;
}
{
if (!tsk->state || tsk_is_pi_blocked(tsk))
return;
+
+ /*
+ * If a worker went to sleep, notify and ask workqueue whether
+ * it wants to wake up a task to maintain concurrency.
+ * As this function is called inside the schedule() context,
+ * we disable preemption to avoid it calling schedule() again
+ * in the possible wakeup of a kworker.
+ */
+ if (tsk->flags & PF_WQ_WORKER) {
+ preempt_disable();
+ wq_worker_sleeping(tsk);
+ preempt_enable_no_resched();
+ }
+
/*
* If we are going to sleep and we have plugged IO queued,
* make sure to submit it to avoid deadlocks.
blk_schedule_flush_plug(tsk);
}
+static void sched_update_worker(struct task_struct *tsk)
+{
+ if (tsk->flags & PF_WQ_WORKER)
+ wq_worker_running(tsk);
+}
+
asmlinkage __visible void __sched schedule(void)
{
struct task_struct *tsk = current;
__schedule(false);
sched_preempt_enable_no_resched();
} while (need_resched());
+ sched_update_worker(tsk);
}
EXPORT_SYMBOL(schedule);
static int __init migration_init(void)
{
- sched_rq_cpu_starting(smp_processor_id());
+ sched_cpu_starting(smp_processor_id());
return 0;
}
early_initcall(migration_init);
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 shareval)
{
+ if (shareval > scale_load_down(ULONG_MAX))
+ shareval = MAX_SHARES;
return sched_group_set_shares(css_tg(css), scale_load(shareval));
}
static DEFINE_MUTEX(cfs_constraints_mutex);
const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
-const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
return ret;
}
-int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
+static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
{
u64 quota, period;
period = ktime_to_ns(tg->cfs_bandwidth.period);
if (cfs_quota_us < 0)
quota = RUNTIME_INF;
- else
+ else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
quota = (u64)cfs_quota_us * NSEC_PER_USEC;
+ else
+ return -EINVAL;
return tg_set_cfs_bandwidth(tg, period, quota);
}
-long tg_get_cfs_quota(struct task_group *tg)
+static long tg_get_cfs_quota(struct task_group *tg)
{
u64 quota_us;
return quota_us;
}
-int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
+static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
{
u64 quota, period;
+ if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
+
period = (u64)cfs_period_us * NSEC_PER_USEC;
quota = tg->cfs_bandwidth.quota;
return tg_set_cfs_bandwidth(tg, period, quota);
}
-long tg_get_cfs_period(struct task_group *tg)
+static long tg_get_cfs_period(struct task_group *tg)
{
u64 cfs_period_us;
*/
#include "sched.h"
-DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
/**
* cpufreq_add_update_util_hook - Populate the CPU's update_util_data pointer.
return 0;
fail:
+ kobject_put(&tunables->attr_set.kobj);
policy->governor_data = NULL;
sugov_tunables_free(tunables);
if (dl_entity_is_special(dl_se))
return;
- WARN_ON(hrtimer_active(&dl_se->inactive_timer));
WARN_ON(dl_se->dl_non_contending);
zerolag_time = dl_se->deadline -
* If the "0-lag time" already passed, decrease the active
* utilization now, instead of starting a timer
*/
- if (zerolag_time < 0) {
+ if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
if (dl_task(p))
sub_running_bw(dl_se, dl_rq);
if (!dl_task(p) || p->state == TASK_DEAD) {
static const char *sched_tunable_scaling_names[] = {
"none",
- "logaritmic",
+ "logarithmic",
"linear"
};
if (p->last_task_numa_placement) {
delta = runtime - p->last_sum_exec_runtime;
*period = now - p->last_task_numa_placement;
+
+ /* Avoid time going backwards, prevent potential divide error: */
+ if (unlikely((s64)*period < 0))
+ *period = 0;
} else {
delta = p->se.avg.load_sum;
*period = LOAD_AVG_MAX;
/*
* Drive the periodic memory faults..
*/
-void task_tick_numa(struct rq *rq, struct task_struct *curr)
+static void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
struct callback_head *work = &curr->numa_work;
u64 period, now;
* Synchronize entity load avg of dequeued entity without locking
* the previous rq.
*/
-void sync_entity_load_avg(struct sched_entity *se)
+static void sync_entity_load_avg(struct sched_entity *se)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
u64 last_update_time;
* Task first catches up with cfs_rq, and then subtract
* itself from the cfs_rq (task must be off the queue now).
*/
-void remove_entity_load_avg(struct sched_entity *se)
+static void remove_entity_load_avg(struct sched_entity *se)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
unsigned long flags;
return HRTIMER_NORESTART;
}
+extern const u64 max_cfs_quota_period;
+
static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
{
struct cfs_bandwidth *cfs_b =
unsigned long flags;
int overrun;
int idle = 0;
+ int count = 0;
raw_spin_lock_irqsave(&cfs_b->lock, flags);
for (;;) {
if (!overrun)
break;
+ if (++count > 3) {
+ u64 new, old = ktime_to_ns(cfs_b->period);
+
+ new = (old * 147) / 128; /* ~115% */
+ new = min(new, max_cfs_quota_period);
+
+ cfs_b->period = ns_to_ktime(new);
+
+ /* since max is 1s, this is limited to 1e9^2, which fits in u64 */
+ cfs_b->quota *= new;
+ cfs_b->quota = div64_u64(cfs_b->quota, old);
+
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(new, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+
+ /* reset count so we don't come right back in here */
+ count = 0;
+ }
+
idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
}
if (idle)
#ifdef CONFIG_SMP
static inline unsigned long cpu_util(int cpu);
-static unsigned long capacity_of(int cpu);
static inline bool cpu_overutilized(int cpu)
{
{
lockdep_assert_held(&env->src_rq->lock);
- p->on_rq = TASK_ON_RQ_MIGRATING;
deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
set_task_cpu(p, env->dst_cpu);
}
BUG_ON(task_rq(p) != rq);
activate_task(rq, p, ENQUEUE_NOCLOCK);
- p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(rq, p, 0);
}
* - When one of the busy CPUs notice that there may be an idle rebalancing
* needed, they will kick the idle load balancer, which then does idle
* load balancing for all the idle CPUs.
+ * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set
+ * anywhere yet.
*/
static inline int find_new_ilb(void)
{
- int ilb = cpumask_first(nohz.idle_cpus_mask);
+ int ilb;
- if (ilb < nr_cpu_ids && idle_cpu(ilb))
- return ilb;
+ for_each_cpu_and(ilb, nohz.idle_cpus_mask,
+ housekeeping_cpumask(HK_FLAG_MISC)) {
+ if (idle_cpu(ilb))
+ return ilb;
+ }
return nr_cpu_ids;
}
/*
- * Kick a CPU to do the nohz balancing, if it is time for it. We pick the
- * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
- * CPU (if there is one).
+ * Kick a CPU to do the nohz balancing, if it is time for it. We pick any
+ * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one).
*/
static void kick_ilb(unsigned int flags)
{
static int __init housekeeping_setup(char *str, enum hk_flags flags)
{
cpumask_var_t non_housekeeping_mask;
+ cpumask_var_t tmp;
int err;
alloc_bootmem_cpumask_var(&non_housekeeping_mask);
return 0;
}
+ alloc_bootmem_cpumask_var(&tmp);
if (!housekeeping_flags) {
alloc_bootmem_cpumask_var(&housekeeping_mask);
cpumask_andnot(housekeeping_mask,
cpu_possible_mask, non_housekeeping_mask);
- if (cpumask_empty(housekeeping_mask))
+
+ cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+ if (cpumask_empty(tmp)) {
+ pr_warn("Housekeeping: must include one present CPU, "
+ "using boot CPU:%d\n", smp_processor_id());
__cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
+ __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
+ }
} else {
- cpumask_var_t tmp;
-
- alloc_bootmem_cpumask_var(&tmp);
+ cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+ if (cpumask_empty(tmp))
+ __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask);
if (!cpumask_equal(tmp, housekeeping_mask)) {
pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
free_bootmem_cpumask_var(non_housekeeping_mask);
return 0;
}
- free_bootmem_cpumask_var(tmp);
}
+ free_bootmem_cpumask_var(tmp);
if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
if (rt_runtime_us < 0)
rt_runtime = RUNTIME_INF;
+ else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}
{
u64 rt_runtime, rt_period;
+ if (rt_period_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
+
rt_period = rt_period_us * NSEC_PER_USEC;
rt_runtime = tg->rt_bandwidth.rt_runtime;
* NULL-terminated list of performance domains intersecting with the
* CPUs of the rd. Protected by RCU.
*/
- struct perf_domain *pd;
+ struct perf_domain __rcu *pd;
};
extern struct root_domain def_root_domain;
atomic_t nr_iowait;
#ifdef CONFIG_SMP
- struct root_domain *rd;
- struct sched_domain *sd;
+ struct root_domain *rd;
+ struct sched_domain __rcu *sd;
unsigned long cpu_capacity;
unsigned long cpu_capacity_orig;
return sd;
}
-DECLARE_PER_CPU(struct sched_domain *, sd_llc);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_size);
DECLARE_PER_CPU(int, sd_llc_id);
-DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DECLARE_PER_CPU(struct sched_domain *, sd_numa);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
extern struct static_key_false sched_asym_cpucapacity;
struct sched_group_capacity {
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
#ifdef CONFIG_CPU_FREQ
-DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
/**
* cpufreq_update_util - Take a note about CPU utilization changes.
* the cpumask of the domain), this allows us to quickly tell if
* two CPUs are in the same cache domain, see cpus_share_cache().
*/
-DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
-DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
static void update_top_cache_domain(int cpu)
struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
struct sched_domain *child = sd->child;
struct sched_group *sg;
+ bool already_visited;
if (child)
cpu = cpumask_first(sched_domain_span(child));
sg = *per_cpu_ptr(sdd->sg, cpu);
sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
- /* For claim_allocations: */
- atomic_inc(&sg->ref);
- atomic_inc(&sg->sgc->ref);
+ /* Increase refcounts for claim_allocations: */
+ already_visited = atomic_inc_return(&sg->ref) > 1;
+ /* sgc visits should follow a similar trend as sg */
+ WARN_ON(already_visited != (atomic_inc_return(&sg->sgc->ref) > 1));
+
+ /* If we have already visited that group, it's already initialized. */
+ if (already_visited)
+ return sg;
if (child) {
cpumask_copy(sched_group_span(sg), sched_domain_span(child));
/*
* build_sched_groups will build a circular linked list of the groups
- * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_capacity to 0.
+ * covered by the given span, will set each group's ->cpumask correctly,
+ * and will initialize their ->sgc.
*
* Assumes the sched_domain tree is fully constructed
*/
}
/*
- * Set up scheduler domains and groups. Callers must hold the hotplug lock.
- * For now this just excludes isolated CPUs, but could be used to
- * exclude other special cases in the future.
+ * Set up scheduler domains and groups. For now this just excludes isolated
+ * CPUs, but could be used to exclude other special cases in the future.
*/
int sched_init_domains(const struct cpumask *cpu_map)
{
*
* Caller must be holding current->sighand->siglock lock.
*
- * Returns 0 on success, -ve on error.
+ * Returns 0 on success, -ve on error, or
+ * - in TSYNC mode: the pid of a thread which was either not in the correct
+ * seccomp mode or did not have an ancestral seccomp filter
+ * - in NEW_LISTENER mode: the fd of the new listener
*/
static long seccomp_attach_filter(unsigned int flags,
struct seccomp_filter *filter)
if (flags & ~SECCOMP_FILTER_FLAG_MASK)
return -EINVAL;
+ /*
+ * In the successful case, NEW_LISTENER returns the new listener fd.
+ * But in the failure case, TSYNC returns the thread that died. If you
+ * combine these two flags, there's no way to tell whether something
+ * succeeded or failed. So, let's disallow this combination.
+ */
+ if ((flags & SECCOMP_FILTER_FLAG_TSYNC) &&
+ (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER))
+ return -EINVAL;
+
/* Prepare the new filter before holding any locks. */
prepared = seccomp_prepare_user_filter(filter);
if (IS_ERR(prepared))
mutex_unlock(¤t->signal->cred_guard_mutex);
out_put_fd:
if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) {
- if (ret < 0) {
+ if (ret) {
listener_f->private_data = NULL;
fput(listener_f);
put_unused_fd(listener);
if (flags)
return -EINVAL;
- f = fdget_raw(pidfd);
+ f = fdget(pidfd);
if (!f.file)
return -EBADF;
}
EXPORT_SYMBOL(tasklet_kill);
-/*
- * tasklet_hrtimer
- */
-
-/*
- * The trampoline is called when the hrtimer expires. It schedules a tasklet
- * to run __tasklet_hrtimer_trampoline() which in turn will call the intended
- * hrtimer callback, but from softirq context.
- */
-static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
-{
- struct tasklet_hrtimer *ttimer =
- container_of(timer, struct tasklet_hrtimer, timer);
-
- tasklet_hi_schedule(&ttimer->tasklet);
- return HRTIMER_NORESTART;
-}
-
-/*
- * Helper function which calls the hrtimer callback from
- * tasklet/softirq context
- */
-static void __tasklet_hrtimer_trampoline(unsigned long data)
-{
- struct tasklet_hrtimer *ttimer = (void *)data;
- enum hrtimer_restart restart;
-
- restart = ttimer->function(&ttimer->timer);
- if (restart != HRTIMER_NORESTART)
- hrtimer_restart(&ttimer->timer);
-}
-
-/**
- * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
- * @ttimer: tasklet_hrtimer which is initialized
- * @function: hrtimer callback function which gets called from softirq context
- * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
- * @mode: hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
- */
-void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
- enum hrtimer_restart (*function)(struct hrtimer *),
- clockid_t which_clock, enum hrtimer_mode mode)
-{
- hrtimer_init(&ttimer->timer, which_clock, mode);
- ttimer->timer.function = __hrtimer_tasklet_trampoline;
- tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
- (unsigned long)ttimer);
- ttimer->function = function;
-}
-EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
-
void __init softirq_init(void)
{
int cpu;
*
* Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*/
+#include <linux/sched/task_stack.h>
+#include <linux/sched/debug.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/kallsyms.h>
#include <linux/stacktrace.h>
-void print_stack_trace(struct stack_trace *trace, int spaces)
+/**
+ * stack_trace_print - Print the entries in the stack trace
+ * @entries: Pointer to storage array
+ * @nr_entries: Number of entries in the storage array
+ * @spaces: Number of leading spaces to print
+ */
+void stack_trace_print(unsigned long *entries, unsigned int nr_entries,
+ int spaces)
{
- int i;
+ unsigned int i;
- if (WARN_ON(!trace->entries))
+ if (WARN_ON(!entries))
return;
- for (i = 0; i < trace->nr_entries; i++)
- printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);
+ for (i = 0; i < nr_entries; i++)
+ printk("%*c%pS\n", 1 + spaces, ' ', (void *)entries[i]);
}
-EXPORT_SYMBOL_GPL(print_stack_trace);
+EXPORT_SYMBOL_GPL(stack_trace_print);
-int snprint_stack_trace(char *buf, size_t size,
- struct stack_trace *trace, int spaces)
+/**
+ * stack_trace_snprint - Print the entries in the stack trace into a buffer
+ * @buf: Pointer to the print buffer
+ * @size: Size of the print buffer
+ * @entries: Pointer to storage array
+ * @nr_entries: Number of entries in the storage array
+ * @spaces: Number of leading spaces to print
+ *
+ * Return: Number of bytes printed.
+ */
+int stack_trace_snprint(char *buf, size_t size, unsigned long *entries,
+ unsigned int nr_entries, int spaces)
{
- int i;
- int generated;
- int total = 0;
+ unsigned int generated, i, total = 0;
- if (WARN_ON(!trace->entries))
+ if (WARN_ON(!entries))
return 0;
- for (i = 0; i < trace->nr_entries; i++) {
+ for (i = 0; i < nr_entries && size; i++) {
generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ',
- (void *)trace->entries[i]);
+ (void *)entries[i]);
total += generated;
-
- /* Assume that generated isn't a negative number */
if (generated >= size) {
buf += size;
size = 0;
return total;
}
-EXPORT_SYMBOL_GPL(snprint_stack_trace);
+EXPORT_SYMBOL_GPL(stack_trace_snprint);
+
+#ifdef CONFIG_ARCH_STACKWALK
+
+struct stacktrace_cookie {
+ unsigned long *store;
+ unsigned int size;
+ unsigned int skip;
+ unsigned int len;
+};
+
+static bool stack_trace_consume_entry(void *cookie, unsigned long addr,
+ bool reliable)
+{
+ struct stacktrace_cookie *c = cookie;
+
+ if (c->len >= c->size)
+ return false;
+
+ if (c->skip > 0) {
+ c->skip--;
+ return true;
+ }
+ c->store[c->len++] = addr;
+ return c->len < c->size;
+}
+
+static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr,
+ bool reliable)
+{
+ if (in_sched_functions(addr))
+ return true;
+ return stack_trace_consume_entry(cookie, addr, reliable);
+}
+
+/**
+ * stack_trace_save - Save a stack trace into a storage array
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ * @skipnr: Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+ unsigned int skipnr)
+{
+ stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+ struct stacktrace_cookie c = {
+ .store = store,
+ .size = size,
+ .skip = skipnr + 1,
+ };
+
+ arch_stack_walk(consume_entry, &c, current, NULL);
+ return c.len;
+}
+EXPORT_SYMBOL_GPL(stack_trace_save);
+
+/**
+ * stack_trace_save_tsk - Save a task stack trace into a storage array
+ * @task: The task to examine
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ * @skipnr: Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store,
+ unsigned int size, unsigned int skipnr)
+{
+ stack_trace_consume_fn consume_entry = stack_trace_consume_entry_nosched;
+ struct stacktrace_cookie c = {
+ .store = store,
+ .size = size,
+ .skip = skipnr + 1,
+ };
+
+ if (!try_get_task_stack(tsk))
+ return 0;
+
+ arch_stack_walk(consume_entry, &c, tsk, NULL);
+ put_task_stack(tsk);
+ return c.len;
+}
+
+/**
+ * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
+ * @regs: Pointer to pt_regs to examine
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ * @skipnr: Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
+ unsigned int size, unsigned int skipnr)
+{
+ stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+ struct stacktrace_cookie c = {
+ .store = store,
+ .size = size,
+ .skip = skipnr,
+ };
+
+ arch_stack_walk(consume_entry, &c, current, regs);
+ return c.len;
+}
+
+#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
+/**
+ * stack_trace_save_tsk_reliable - Save task stack with verification
+ * @tsk: Pointer to the task to examine
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ *
+ * Return: An error if it detects any unreliable features of the
+ * stack. Otherwise it guarantees that the stack trace is
+ * reliable and returns the number of entries stored.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
+ unsigned int size)
+{
+ stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+ struct stacktrace_cookie c = {
+ .store = store,
+ .size = size,
+ };
+ int ret;
+
+ /*
+ * If the task doesn't have a stack (e.g., a zombie), the stack is
+ * "reliably" empty.
+ */
+ if (!try_get_task_stack(tsk))
+ return 0;
+
+ ret = arch_stack_walk_reliable(consume_entry, &c, tsk);
+ put_task_stack(tsk);
+ return ret;
+}
+#endif
+
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
+/**
+ * stack_trace_save_user - Save a user space stack trace into a storage array
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
+{
+ stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+ struct stacktrace_cookie c = {
+ .store = store,
+ .size = size,
+ };
+
+ /* Trace user stack if not a kernel thread */
+ if (!current->mm)
+ return 0;
+
+ arch_stack_walk_user(consume_entry, &c, task_pt_regs(current));
+ return c.len;
+}
+#endif
+
+#else /* CONFIG_ARCH_STACKWALK */
/*
* Architectures that do not implement save_stack_trace_*()
WARN_ONCE(1, KERN_INFO "save_stack_tsk_reliable() not implemented yet.\n");
return -ENOSYS;
}
+
+/**
+ * stack_trace_save - Save a stack trace into a storage array
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ * @skipnr: Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+ unsigned int skipnr)
+{
+ struct stack_trace trace = {
+ .entries = store,
+ .max_entries = size,
+ .skip = skipnr + 1,
+ };
+
+ save_stack_trace(&trace);
+ return trace.nr_entries;
+}
+EXPORT_SYMBOL_GPL(stack_trace_save);
+
+/**
+ * stack_trace_save_tsk - Save a task stack trace into a storage array
+ * @task: The task to examine
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ * @skipnr: Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save_tsk(struct task_struct *task,
+ unsigned long *store, unsigned int size,
+ unsigned int skipnr)
+{
+ struct stack_trace trace = {
+ .entries = store,
+ .max_entries = size,
+ .skip = skipnr + 1,
+ };
+
+ save_stack_trace_tsk(task, &trace);
+ return trace.nr_entries;
+}
+
+/**
+ * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
+ * @regs: Pointer to pt_regs to examine
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ * @skipnr: Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
+ unsigned int size, unsigned int skipnr)
+{
+ struct stack_trace trace = {
+ .entries = store,
+ .max_entries = size,
+ .skip = skipnr,
+ };
+
+ save_stack_trace_regs(regs, &trace);
+ return trace.nr_entries;
+}
+
+#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
+/**
+ * stack_trace_save_tsk_reliable - Save task stack with verification
+ * @tsk: Pointer to the task to examine
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ *
+ * Return: An error if it detects any unreliable features of the
+ * stack. Otherwise it guarantees that the stack trace is
+ * reliable and returns the number of entries stored.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
+ unsigned int size)
+{
+ struct stack_trace trace = {
+ .entries = store,
+ .max_entries = size,
+ };
+ int ret = save_stack_trace_tsk_reliable(tsk, &trace);
+
+ return ret ? ret : trace.nr_entries;
+}
+#endif
+
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
+/**
+ * stack_trace_save_user - Save a user space stack trace into a storage array
+ * @store: Pointer to storage array
+ * @size: Size of the storage array
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
+{
+ struct stack_trace trace = {
+ .entries = store,
+ .max_entries = size,
+ };
+
+ save_stack_trace_user(&trace);
+ return trace.nr_entries;
+}
+#endif /* CONFIG_USER_STACKTRACE_SUPPORT */
+
+#endif /* !CONFIG_ARCH_STACKWALK */
}
#ifdef CONFIG_HOTPLUG_CPU
+
+# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+/**
+ * tick_offline_cpu - Take CPU out of the broadcast mechanism
+ * @cpu: The outgoing CPU
+ *
+ * Called on the outgoing CPU after it took itself offline.
+ */
+void tick_offline_cpu(unsigned int cpu)
+{
+ raw_spin_lock(&clockevents_lock);
+ tick_broadcast_offline(cpu);
+ raw_spin_unlock(&clockevents_lock);
+}
+# endif
+
/**
* tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu
*/
raw_spin_lock_irqsave(&clockevents_lock, flags);
- tick_shutdown_broadcast_oneshot(cpu);
- tick_shutdown_broadcast(cpu);
tick_shutdown(cpu);
/*
* Unregister the clock event devices which were
#if (BITS_PER_LONG < 64)
u64 get_jiffies_64(void)
{
- unsigned long seq;
+ unsigned int seq;
u64 ret;
do {
unsigned long long notrace sched_clock(void)
{
u64 cyc, res;
- unsigned long seq;
+ unsigned int seq;
struct clock_read_data *rd;
do {
*/
static u64 notrace suspended_sched_clock_read(void)
{
- unsigned long seq = raw_read_seqcount(&cd.seq);
+ unsigned int seq = raw_read_seqcount(&cd.seq);
return cd.read_data[seq & 1].epoch_cyc;
}
-static int sched_clock_suspend(void)
+int sched_clock_suspend(void)
{
struct clock_read_data *rd = &cd.read_data[0];
return 0;
}
-static void sched_clock_resume(void)
+void sched_clock_resume(void)
{
struct clock_read_data *rd = &cd.read_data[0];
static void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
static void tick_broadcast_clear_oneshot(int cpu);
static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
+# ifdef CONFIG_HOTPLUG_CPU
+static void tick_broadcast_oneshot_offline(unsigned int cpu);
+# endif
#else
static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
static inline void tick_broadcast_clear_oneshot(int cpu) { }
static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { }
+# ifdef CONFIG_HOTPLUG_CPU
+static inline void tick_broadcast_oneshot_offline(unsigned int cpu) { }
+# endif
#endif
/*
}
#ifdef CONFIG_HOTPLUG_CPU
-/*
- * Remove a CPU from broadcasting
- */
-void tick_shutdown_broadcast(unsigned int cpu)
+static void tick_shutdown_broadcast(void)
{
- struct clock_event_device *bc;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
- bc = tick_broadcast_device.evtdev;
- cpumask_clear_cpu(cpu, tick_broadcast_mask);
- cpumask_clear_cpu(cpu, tick_broadcast_on);
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
if (bc && cpumask_empty(tick_broadcast_mask))
clockevents_shutdown(bc);
}
+}
- raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+/*
+ * Remove a CPU from broadcasting
+ */
+void tick_broadcast_offline(unsigned int cpu)
+{
+ raw_spin_lock(&tick_broadcast_lock);
+ cpumask_clear_cpu(cpu, tick_broadcast_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_on);
+ tick_broadcast_oneshot_offline(cpu);
+ tick_shutdown_broadcast();
+ raw_spin_unlock(&tick_broadcast_lock);
}
+
#endif
void tick_suspend_broadcast(void)
* either the CPU handling the broadcast
* interrupt or we got woken by something else.
*
- * We are not longer in the broadcast mask, so
+ * We are no longer in the broadcast mask, so
* if the cpu local expiry time is already
* reached, we would reprogram the cpu local
* timer with an already expired event.
*
* This can lead to a ping-pong when we return
- * to idle and therefor rearm the broadcast
+ * to idle and therefore rearm the broadcast
* timer before the cpu local timer was able
* to fire. This happens because the forced
* reprogramming makes sure that the event
}
/*
- * Remove a dead CPU from broadcasting
+ * Remove a dying CPU from broadcasting
*/
-void tick_shutdown_broadcast_oneshot(unsigned int cpu)
+static void tick_broadcast_oneshot_offline(unsigned int cpu)
{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
/*
* Clear the broadcast masks for the dead cpu, but do not stop
* the broadcast device!
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
-
- raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
#endif
* procedure also covers cpu hotplug.
*/
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
+#ifdef CONFIG_NO_HZ_FULL
+/*
+ * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns
+ * tick_do_timer_cpu and it should be taken over by an eligible secondary
+ * when one comes online.
+ */
+static int tick_do_timer_boot_cpu __read_mostly = -1;
+#endif
/*
* Debugging: see timer_list.c
!tick_broadcast_oneshot_active()) {
clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
} else {
- unsigned long seq;
+ unsigned int seq;
ktime_t next;
do {
}
}
+#ifdef CONFIG_NO_HZ_FULL
+static void giveup_do_timer(void *info)
+{
+ int cpu = *(unsigned int *)info;
+
+ WARN_ON(tick_do_timer_cpu != smp_processor_id());
+
+ tick_do_timer_cpu = cpu;
+}
+
+static void tick_take_do_timer_from_boot(void)
+{
+ int cpu = smp_processor_id();
+ int from = tick_do_timer_boot_cpu;
+
+ if (from >= 0 && from != cpu)
+ smp_call_function_single(from, giveup_do_timer, &cpu, 1);
+}
+#endif
+
/*
* Setup the tick device
*/
* this cpu:
*/
if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
- if (!tick_nohz_full_cpu(cpu))
- tick_do_timer_cpu = cpu;
- else
- tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+ tick_do_timer_cpu = cpu;
+
tick_next_period = ktime_get();
tick_period = NSEC_PER_SEC / HZ;
+#ifdef CONFIG_NO_HZ_FULL
+ /*
+ * The boot CPU may be nohz_full, in which case set
+ * tick_do_timer_boot_cpu so the first housekeeping
+ * secondary that comes up will take do_timer from
+ * us.
+ */
+ if (tick_nohz_full_cpu(cpu))
+ tick_do_timer_boot_cpu = cpu;
+
+ } else if (tick_do_timer_boot_cpu != -1 &&
+ !tick_nohz_full_cpu(cpu)) {
+ tick_take_do_timer_from_boot();
+ tick_do_timer_boot_cpu = -1;
+ WARN_ON(tick_do_timer_cpu != cpu);
+#endif
}
/*
trace_suspend_resume(TPS("timekeeping_freeze"),
smp_processor_id(), true);
system_state = SYSTEM_SUSPEND;
+ sched_clock_suspend();
timekeeping_suspend();
} else {
tick_suspend_local();
if (tick_freeze_depth == num_online_cpus()) {
timekeeping_resume();
+ sched_clock_resume();
system_state = SYSTEM_RUNNING;
trace_suspend_resume(TPS("timekeeping_freeze"),
smp_processor_id(), false);
extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
extern void tick_install_broadcast_device(struct clock_event_device *dev);
extern int tick_is_broadcast_device(struct clock_event_device *dev);
-extern void tick_shutdown_broadcast(unsigned int cpu);
extern void tick_suspend_broadcast(void);
extern void tick_resume_broadcast(void);
extern bool tick_resume_check_broadcast(void);
static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; }
static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; }
static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
-static inline void tick_shutdown_broadcast(unsigned int cpu) { }
static inline void tick_suspend_broadcast(void) { }
static inline void tick_resume_broadcast(void) { }
static inline bool tick_resume_check_broadcast(void) { return false; }
/* Functions related to oneshot broadcasting */
#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
extern void tick_broadcast_switch_to_oneshot(void);
-extern void tick_shutdown_broadcast_oneshot(unsigned int cpu);
extern int tick_broadcast_oneshot_active(void);
extern void tick_check_oneshot_broadcast_this_cpu(void);
bool tick_broadcast_oneshot_available(void);
extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
#else /* !(BROADCAST && ONESHOT): */
static inline void tick_broadcast_switch_to_oneshot(void) { }
-static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { }
static inline int tick_broadcast_oneshot_active(void) { return 0; }
static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
#endif /* !(BROADCAST && ONESHOT) */
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_broadcast_offline(unsigned int cpu);
+#else
+static inline void tick_broadcast_offline(unsigned int cpu) { }
+#endif
+
/* NO_HZ_FULL internal */
#ifdef CONFIG_NO_HZ_FULL
extern void tick_nohz_init(void);
* into a long sleep. If two CPUs happen to assign themselves to
* this duty, then the jiffies update is still serialized by
* jiffies_lock.
+ *
+ * If nohz_full is enabled, this should not happen because the
+ * tick_do_timer_cpu never relinquishes.
*/
- if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)
- && !tick_nohz_full_cpu(cpu))
+ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
+#ifdef CONFIG_NO_HZ_FULL
+ WARN_ON(tick_nohz_full_running);
+#endif
tick_do_timer_cpu = cpu;
+ }
#endif
/* Check, if the jiffies need an update */
static int tick_nohz_cpu_down(unsigned int cpu)
{
/*
- * The boot CPU handles housekeeping duty (unbound timers,
- * workqueues, timekeeping, ...) on behalf of full dynticks
+ * The tick_do_timer_cpu CPU handles housekeeping duty (unbound
+ * timers, workqueues, timekeeping, ...) on behalf of full dynticks
* CPUs. It must remain online when nohz full is enabled.
*/
if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
return;
}
- cpu = smp_processor_id();
+ if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) &&
+ !IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) {
+ cpu = smp_processor_id();
- if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
- pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n",
- cpu);
- cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+ if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
+ pr_warn("NO_HZ: Clearing %d from nohz_full range "
+ "for timekeeping\n", cpu);
+ cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+ }
}
for_each_cpu(cpu, tick_nohz_full_mask)
static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
{
u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
- unsigned long seq, basejiff;
+ unsigned long basejiff;
+ unsigned int seq;
/* Read jiffies and the time when jiffies were updated last */
do {
/*
* Boot safety: make sure the timekeeping duty has been
* assigned before entering dyntick-idle mode,
+ * tick_do_timer_cpu is TICK_DO_TIMER_BOOT
*/
- if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT))
+ return false;
+
+ /* Should not happen for nohz-full */
+ if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
return false;
}
* struct tick_sched - sched tick emulation and no idle tick control/stats
* @sched_timer: hrtimer to schedule the periodic tick in high
* resolution mode
+ * @check_clocks: Notification mechanism about clocksource changes
+ * @nohz_mode: Mode - one state of tick_nohz_mode
+ * @inidle: Indicator that the CPU is in the tick idle mode
+ * @tick_stopped: Indicator that the idle tick has been stopped
+ * @idle_active: Indicator that the CPU is actively in the tick idle mode;
+ * it is resetted during irq handling phases.
+ * @do_timer_lst: CPU was the last one doing do_timer before going idle
+ * @got_idle_tick: Tick timer function has run with @inidle set
* @last_tick: Store the last tick expiry time when the tick
* timer is modified for nohz sleeps. This is necessary
* to resume the tick timer operation in the timeline
* when the CPU returns from nohz sleep.
* @next_tick: Next tick to be fired when in dynticks mode.
- * @tick_stopped: Indicator that the idle tick has been stopped
* @idle_jiffies: jiffies at the entry to idle for idle time accounting
* @idle_calls: Total number of idle calls
* @idle_sleeps: Number of idle calls, where the sched tick was stopped
* @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding
* @timer_expires: Anticipated timer expiration time (in case sched tick is stopped)
* @timer_expires_base: Base time clock monotonic for @timer_expires
- * @do_timer_lst: CPU was the last one doing do_timer before going idle
- * @got_idle_tick: Tick timer function has run with @inidle set
+ * @next_timer: Expiry time of next expiring timer for debugging purpose only
+ * @tick_dep_mask: Tick dependency mask - is set, if someone needs the tick
*/
struct tick_sched {
struct hrtimer sched_timer;
static int firsttime = 1;
int error = 0;
- if (tv && !timespec64_valid(tv))
+ if (tv && !timespec64_valid_settod(tv))
return -EINVAL;
error = security_settime64(tv, tz);
void ktime_get_real_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned long seq;
+ unsigned int seq;
u64 nsecs;
WARN_ON(timekeeping_suspended);
ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs)
{
ktime_t *offset = offsets[offs];
- unsigned long seq;
+ unsigned int seq;
ktime_t tconv;
do {
void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned long seq;
+ unsigned int seq;
ktime_t base_raw;
ktime_t base_real;
u64 nsec_raw;
ktime_t base_real, base_raw;
u64 nsec_real, nsec_raw;
u8 cs_was_changed_seq;
- unsigned long seq;
+ unsigned int seq;
bool do_interp;
int ret;
unsigned long flags;
int ret = 0;
- if (!timespec64_valid_strict(ts))
+ if (!timespec64_valid_settod(ts))
return -EINVAL;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
/* Make sure the proposed value is valid */
tmp = timespec64_add(tk_xtime(tk), *ts);
if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 ||
- !timespec64_valid_strict(&tmp)) {
+ !timespec64_valid_settod(&tmp)) {
ret = -EINVAL;
goto error;
}
void ktime_get_raw_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned long seq;
+ unsigned int seq;
u64 nsecs;
do {
int timekeeping_valid_for_hres(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned long seq;
+ unsigned int seq;
int ret;
do {
u64 timekeeping_max_deferment(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned long seq;
+ unsigned int seq;
u64 ret;
do {
unsigned long flags;
read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
- if (timespec64_valid_strict(&wall_time) &&
+ if (timespec64_valid_settod(&wall_time) &&
timespec64_to_ns(&wall_time) > 0) {
persistent_clock_exists = true;
} else if (timespec64_to_ns(&wall_time) != 0) {
void ktime_get_coarse_real_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned long seq;
+ unsigned int seq;
do {
seq = read_seqcount_begin(&tk_core.seq);
{
struct timekeeper *tk = &tk_core.timekeeper;
struct timespec64 now, mono;
- unsigned long seq;
+ unsigned int seq;
do {
seq = read_seqcount_begin(&tk_core.seq);
extern void timekeeping_warp_clock(void);
extern int timekeeping_suspend(void);
extern void timekeeping_resume(void);
+#ifdef CONFIG_GENERIC_SCHED_CLOCK
+extern int sched_clock_suspend(void);
+extern void sched_clock_resume(void);
+#else
+static inline int sched_clock_suspend(void) { return 0; }
+static inline void sched_clock_resume(void) { }
+#endif
extern void do_timer(unsigned long ticks);
extern void update_wall_time(void);
hlist_add_head(&timer->entry, base->vectors + idx);
__set_bit(idx, base->pending_map);
timer_set_idx(timer, idx);
+
+ trace_timer_start(timer, timer->expires, timer->flags);
}
static void
trace_timer_init(timer);
}
-static inline void
-debug_activate(struct timer_list *timer, unsigned long expires)
-{
- debug_timer_activate(timer);
- trace_timer_start(timer, expires, timer->flags);
-}
-
static inline void debug_deactivate(struct timer_list *timer)
{
debug_timer_deactivate(timer);
}
}
- debug_activate(timer, expires);
+ debug_timer_activate(timer);
timer->expires = expires;
/*
}
forward_timer_base(base);
- debug_activate(timer, timer->expires);
+ debug_timer_activate(timer);
internal_add_timer(base, timer);
raw_spin_unlock_irqrestore(&base->lock, flags);
}
EXPORT_SYMBOL(del_timer_sync);
#endif
-static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *))
+static void call_timer_fn(struct timer_list *timer,
+ void (*fn)(struct timer_list *),
+ unsigned long baseclk)
{
int count = preempt_count();
*/
lock_map_acquire(&lockdep_map);
- trace_timer_expire_entry(timer);
+ trace_timer_expire_entry(timer, baseclk);
fn(timer);
trace_timer_expire_exit(timer);
static void expire_timers(struct timer_base *base, struct hlist_head *head)
{
+ /*
+ * This value is required only for tracing. base->clk was
+ * incremented directly before expire_timers was called. But expiry
+ * is related to the old base->clk value.
+ */
+ unsigned long baseclk = base->clk - 1;
+
while (!hlist_empty(head)) {
struct timer_list *timer;
void (*fn)(struct timer_list *);
if (timer->flags & TIMER_IRQSAFE) {
raw_spin_unlock(&base->lock);
- call_timer_fn(timer, fn);
+ call_timer_fn(timer, fn, baseclk);
raw_spin_lock(&base->lock);
} else {
raw_spin_unlock_irq(&base->lock);
- call_timer_fn(timer, fn);
+ call_timer_fn(timer, fn, baseclk);
raw_spin_lock_irq(&base->lock);
}
}
if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
return false;
+ if (num_online_cpus() <= 1)
+ return false; /* Can't offline the last CPU. */
if (verbose > 1)
pr_alert("%s" TORTURE_FLAG
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/rcupdate.h>
+#include <linux/kprobes.h>
#include <trace/events/sched.h>
tr->ops->func = ftrace_stub;
}
-static inline void
+static nokprobe_inline void
__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ignored, struct pt_regs *regs)
{
{
__ftrace_ops_list_func(ip, parent_ip, NULL, regs);
}
+NOKPROBE_SYMBOL(ftrace_ops_list_func);
#else
static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
{
__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
}
+NOKPROBE_SYMBOL(ftrace_ops_no_ops);
#endif
/*
preempt_enable_notrace();
trace_clear_recursion(bit);
}
+NOKPROBE_SYMBOL(ftrace_ops_assist_func);
/**
* ftrace_ops_get_func - get the function a trampoline should call
preempt_disable_notrace();
time = rb_time_stamp(buffer);
- preempt_enable_no_resched_notrace();
+ preempt_enable_notrace();
return time;
}
#endif /* CONFIG_TRACE_EVAL_MAP_FILE */
static int tracing_set_tracer(struct trace_array *tr, const char *buf);
+static void ftrace_trace_userstack(struct ring_buffer *buffer,
+ unsigned long flags, int pc);
#define MAX_TRACER_SIZE 100
static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
* not modified.
*/
pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
- if (!pid_list)
+ if (!pid_list) {
+ trace_parser_put(&parser);
return -ENOMEM;
+ }
pid_list->pid_max = READ_ONCE(pid_max);
pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
if (!pid_list->pids) {
+ trace_parser_put(&parser);
kfree(pid_list);
return -ENOMEM;
}
#ifdef CONFIG_STACKTRACE
-#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
+/* Allow 4 levels of nesting: normal, softirq, irq, NMI */
+#define FTRACE_KSTACK_NESTING 4
+
+#define FTRACE_KSTACK_ENTRIES (PAGE_SIZE / FTRACE_KSTACK_NESTING)
+
struct ftrace_stack {
- unsigned long calls[FTRACE_STACK_MAX_ENTRIES];
+ unsigned long calls[FTRACE_KSTACK_ENTRIES];
+};
+
+
+struct ftrace_stacks {
+ struct ftrace_stack stacks[FTRACE_KSTACK_NESTING];
};
-static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
+static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks);
static DEFINE_PER_CPU(int, ftrace_stack_reserve);
static void __ftrace_trace_stack(struct ring_buffer *buffer,
{
struct trace_event_call *call = &event_kernel_stack;
struct ring_buffer_event *event;
+ unsigned int size, nr_entries;
+ struct ftrace_stack *fstack;
struct stack_entry *entry;
- struct stack_trace trace;
- int use_stack;
- int size = FTRACE_STACK_ENTRIES;
-
- trace.nr_entries = 0;
- trace.skip = skip;
+ int stackidx;
/*
* Add one, for this function and the call to save_stack_trace()
*/
#ifndef CONFIG_UNWINDER_ORC
if (!regs)
- trace.skip++;
+ skip++;
#endif
/*
*/
preempt_disable_notrace();
- use_stack = __this_cpu_inc_return(ftrace_stack_reserve);
+ stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;
+
+ /* This should never happen. If it does, yell once and skip */
+ if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING))
+ goto out;
+
/*
- * We don't need any atomic variables, just a barrier.
- * If an interrupt comes in, we don't care, because it would
- * have exited and put the counter back to what we want.
- * We just need a barrier to keep gcc from moving things
- * around.
+ * The above __this_cpu_inc_return() is 'atomic' cpu local. An
+ * interrupt will either see the value pre increment or post
+ * increment. If the interrupt happens pre increment it will have
+ * restored the counter when it returns. We just need a barrier to
+ * keep gcc from moving things around.
*/
barrier();
- if (use_stack == 1) {
- trace.entries = this_cpu_ptr(ftrace_stack.calls);
- trace.max_entries = FTRACE_STACK_MAX_ENTRIES;
- if (regs)
- save_stack_trace_regs(regs, &trace);
- else
- save_stack_trace(&trace);
+ fstack = this_cpu_ptr(ftrace_stacks.stacks) + stackidx;
+ size = ARRAY_SIZE(fstack->calls);
- if (trace.nr_entries > size)
- size = trace.nr_entries;
- } else
- /* From now on, use_stack is a boolean */
- use_stack = 0;
-
- size *= sizeof(unsigned long);
+ if (regs) {
+ nr_entries = stack_trace_save_regs(regs, fstack->calls,
+ size, skip);
+ } else {
+ nr_entries = stack_trace_save(fstack->calls, size, skip);
+ }
+ size = nr_entries * sizeof(unsigned long);
event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
sizeof(*entry) + size, flags, pc);
if (!event)
goto out;
entry = ring_buffer_event_data(event);
- memset(&entry->caller, 0, size);
-
- if (use_stack)
- memcpy(&entry->caller, trace.entries,
- trace.nr_entries * sizeof(unsigned long));
- else {
- trace.max_entries = FTRACE_STACK_ENTRIES;
- trace.entries = entry->caller;
- if (regs)
- save_stack_trace_regs(regs, &trace);
- else
- save_stack_trace(&trace);
- }
-
- entry->size = trace.nr_entries;
+ memcpy(&entry->caller, fstack->calls, size);
+ entry->size = nr_entries;
if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
}
EXPORT_SYMBOL_GPL(trace_dump_stack);
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
static DEFINE_PER_CPU(int, user_stack_count);
-void
+static void
ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
{
struct trace_event_call *call = &event_user_stack;
struct ring_buffer_event *event;
struct userstack_entry *entry;
- struct stack_trace trace;
if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE))
return;
entry->tgid = current->tgid;
memset(&entry->caller, 0, sizeof(entry->caller));
- trace.nr_entries = 0;
- trace.max_entries = FTRACE_STACK_ENTRIES;
- trace.skip = 0;
- trace.entries = entry->caller;
-
- save_stack_trace_user(&trace);
+ stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES);
if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
out:
preempt_enable();
}
-
-#ifdef UNUSED
-static void __trace_userstack(struct trace_array *tr, unsigned long flags)
+#else /* CONFIG_USER_STACKTRACE_SUPPORT */
+static void ftrace_trace_userstack(struct ring_buffer *buffer,
+ unsigned long flags, int pc)
{
- ftrace_trace_userstack(tr, flags, preempt_count());
}
-#endif /* UNUSED */
+#endif /* !CONFIG_USER_STACKTRACE_SUPPORT */
#endif /* CONFIG_STACKTRACE */
struct ring_buffer *buffer;
void *page;
int cpu;
- int ref;
+ refcount_t refcount;
};
+static void buffer_ref_release(struct buffer_ref *ref)
+{
+ if (!refcount_dec_and_test(&ref->refcount))
+ return;
+ ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
+ kfree(ref);
+}
+
static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct buffer_ref *ref = (struct buffer_ref *)buf->private;
- if (--ref->ref)
- return;
-
- ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
- kfree(ref);
+ buffer_ref_release(ref);
buf->private = 0;
}
{
struct buffer_ref *ref = (struct buffer_ref *)buf->private;
- if (ref->ref > INT_MAX/2)
+ if (refcount_read(&ref->refcount) > INT_MAX/2)
return false;
- ref->ref++;
+ refcount_inc(&ref->refcount);
return true;
}
static const struct pipe_buf_operations buffer_pipe_buf_ops = {
.confirm = generic_pipe_buf_confirm,
.release = buffer_pipe_buf_release,
- .steal = generic_pipe_buf_steal,
+ .steal = generic_pipe_buf_nosteal,
.get = buffer_pipe_buf_get,
};
struct buffer_ref *ref =
(struct buffer_ref *)spd->partial[i].private;
- if (--ref->ref)
- return;
-
- ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
- kfree(ref);
+ buffer_ref_release(ref);
spd->partial[i].private = 0;
}
break;
}
- ref->ref = 1;
+ refcount_set(&ref->refcount, 1);
ref->buffer = iter->trace_buffer->buffer;
ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
if (IS_ERR(ref->page)) {
#endif /* CONFIG_TRACER_MAX_TRACE */
#ifdef CONFIG_STACKTRACE
-void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
- int pc);
-
void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
int pc);
#else
-static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
- unsigned long flags, int pc)
-{
-}
-
static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
int skip, int pc)
{
void ftrace_likely_update(struct ftrace_likely_data *f, int val,
int expect, int is_constant)
{
+ unsigned long flags = user_access_save();
+
/* A constant is always correct */
if (is_constant) {
f->constant++;
f->data.correct++;
else
f->data.incorrect++;
+
+ user_access_restore(flags);
}
EXPORT_SYMBOL(ftrace_likely_update);
u64 var_ref_vals[TRACING_MAP_VARS_MAX];
char compound_key[HIST_KEY_SIZE_MAX];
struct tracing_map_elt *elt = NULL;
- struct stack_trace stacktrace;
struct hist_field *key_field;
u64 field_contents;
void *key = NULL;
key_field = hist_data->fields[i];
if (key_field->flags & HIST_FIELD_FL_STACKTRACE) {
- stacktrace.max_entries = HIST_STACKTRACE_DEPTH;
- stacktrace.entries = entries;
- stacktrace.nr_entries = 0;
- stacktrace.skip = HIST_STACKTRACE_SKIP;
-
- memset(stacktrace.entries, 0, HIST_STACKTRACE_SIZE);
- save_stack_trace(&stacktrace);
-
+ memset(entries, 0, HIST_STACKTRACE_SIZE);
+ stack_trace_save(entries, HIST_STACKTRACE_DEPTH,
+ HIST_STACKTRACE_SKIP);
key = entries;
} else {
field_contents = key_field->fn(key_field, elt, rbe, rec);
unsigned int i;
for (i = 0; i < max_entries; i++) {
- if (stacktrace_entries[i] == ULONG_MAX)
+ if (!stacktrace_entries[i])
return;
seq_printf(m, "%*c", 1 + spaces, ' ');
#include "trace.h"
-static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
- { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
-unsigned stack_trace_index[STACK_TRACE_ENTRIES];
+#define STACK_TRACE_ENTRIES 500
-/*
- * Reserve one entry for the passed in ip. This will allow
- * us to remove most or all of the stack size overhead
- * added by the stack tracer itself.
- */
-struct stack_trace stack_trace_max = {
- .max_entries = STACK_TRACE_ENTRIES - 1,
- .entries = &stack_dump_trace[0],
-};
+static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES];
+static unsigned stack_trace_index[STACK_TRACE_ENTRIES];
-unsigned long stack_trace_max_size;
-arch_spinlock_t stack_trace_max_lock =
+static unsigned int stack_trace_nr_entries;
+static unsigned long stack_trace_max_size;
+static arch_spinlock_t stack_trace_max_lock =
(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
DEFINE_PER_CPU(int, disable_stack_tracer);
static DEFINE_MUTEX(stack_sysctl_mutex);
int stack_tracer_enabled;
-static int last_stack_tracer_enabled;
-void stack_trace_print(void)
+static void print_max_stack(void)
{
long i;
int size;
pr_emerg(" Depth Size Location (%d entries)\n"
" ----- ---- --------\n",
- stack_trace_max.nr_entries);
+ stack_trace_nr_entries);
- for (i = 0; i < stack_trace_max.nr_entries; i++) {
- if (stack_dump_trace[i] == ULONG_MAX)
- break;
- if (i+1 == stack_trace_max.nr_entries ||
- stack_dump_trace[i+1] == ULONG_MAX)
+ for (i = 0; i < stack_trace_nr_entries; i++) {
+ if (i + 1 == stack_trace_nr_entries)
size = stack_trace_index[i];
else
size = stack_trace_index[i] - stack_trace_index[i+1];
}
}
-/*
- * When arch-specific code overrides this function, the following
- * data should be filled up, assuming stack_trace_max_lock is held to
- * prevent concurrent updates.
- * stack_trace_index[]
- * stack_trace_max
- * stack_trace_max_size
- */
-void __weak
-check_stack(unsigned long ip, unsigned long *stack)
+static void check_stack(unsigned long ip, unsigned long *stack)
{
unsigned long this_size, flags; unsigned long *p, *top, *start;
static int tracer_frame;
stack_trace_max_size = this_size;
- stack_trace_max.nr_entries = 0;
- stack_trace_max.skip = 0;
-
- save_stack_trace(&stack_trace_max);
+ stack_trace_nr_entries = stack_trace_save(stack_dump_trace,
+ ARRAY_SIZE(stack_dump_trace) - 1,
+ 0);
/* Skip over the overhead of the stack tracer itself */
- for (i = 0; i < stack_trace_max.nr_entries; i++) {
+ for (i = 0; i < stack_trace_nr_entries; i++) {
if (stack_dump_trace[i] == ip)
break;
}
* Some archs may not have the passed in ip in the dump.
* If that happens, we need to show everything.
*/
- if (i == stack_trace_max.nr_entries)
+ if (i == stack_trace_nr_entries)
i = 0;
/*
* loop will only happen once. This code only takes place
* on a new max, so it is far from a fast path.
*/
- while (i < stack_trace_max.nr_entries) {
+ while (i < stack_trace_nr_entries) {
int found = 0;
stack_trace_index[x] = this_size;
p = start;
- for (; p < top && i < stack_trace_max.nr_entries; p++) {
- if (stack_dump_trace[i] == ULONG_MAX)
- break;
+ for (; p < top && i < stack_trace_nr_entries; p++) {
/*
* The READ_ONCE_NOCHECK is used to let KASAN know that
* this is not a stack-out-of-bounds error.
i++;
}
- stack_trace_max.nr_entries = x;
- for (; x < i; x++)
- stack_dump_trace[x] = ULONG_MAX;
+ stack_trace_nr_entries = x;
if (task_stack_end_corrupted(current)) {
- stack_trace_print();
+ print_max_stack();
BUG();
}
{
long n = *pos - 1;
- if (n >= stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX)
+ if (n >= stack_trace_nr_entries)
return NULL;
m->private = (void *)n;
seq_printf(m, " Depth Size Location"
" (%d entries)\n"
" ----- ---- --------\n",
- stack_trace_max.nr_entries);
+ stack_trace_nr_entries);
if (!stack_tracer_enabled && !stack_trace_max_size)
print_disabled(m);
i = *(long *)v;
- if (i >= stack_trace_max.nr_entries ||
- stack_dump_trace[i] == ULONG_MAX)
+ if (i >= stack_trace_nr_entries)
return 0;
- if (i+1 == stack_trace_max.nr_entries ||
- stack_dump_trace[i+1] == ULONG_MAX)
+ if (i + 1 == stack_trace_nr_entries)
size = stack_trace_index[i];
else
size = stack_trace_index[i] - stack_trace_index[i+1];
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
+ int was_enabled;
int ret;
mutex_lock(&stack_sysctl_mutex);
+ was_enabled = !!stack_tracer_enabled;
ret = proc_dointvec(table, write, buffer, lenp, ppos);
- if (ret || !write ||
- (last_stack_tracer_enabled == !!stack_tracer_enabled))
+ if (ret || !write || (was_enabled == !!stack_tracer_enabled))
goto out;
- last_stack_tracer_enabled = !!stack_tracer_enabled;
-
if (stack_tracer_enabled)
register_ftrace_function(&trace_ops);
else
unregister_ftrace_function(&trace_ops);
-
out:
mutex_unlock(&stack_sysctl_mutex);
return ret;
strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE);
stack_tracer_enabled = 1;
- last_stack_tracer_enabled = 1;
return 1;
}
__setup("stacktrace", enable_stacktrace);
* Create the watchdog thread infrastructure and configure the detector(s).
*
* The threads are not unparked as watchdog_allowed_mask is empty. When
- * the threads are sucessfully initialized, take the proper locks and
+ * the threads are successfully initialized, take the proper locks and
* unpark the threads in the watchdog_cpumask if the watchdog is enabled.
*/
static __init void lockup_detector_setup(void)
if (__this_cpu_read(hard_watchdog_warn) == true)
return;
- pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+ pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n",
+ this_cpu);
print_modules();
print_irqtrace_events(current);
if (regs)
}
/**
- * wq_worker_waking_up - a worker is waking up
+ * wq_worker_running - a worker is running again
* @task: task waking up
- * @cpu: CPU @task is waking up to
*
- * This function is called during try_to_wake_up() when a worker is
- * being awoken.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
+ * This function is called when a worker returns from schedule()
*/
-void wq_worker_waking_up(struct task_struct *task, int cpu)
+void wq_worker_running(struct task_struct *task)
{
struct worker *worker = kthread_data(task);
- if (!(worker->flags & WORKER_NOT_RUNNING)) {
- WARN_ON_ONCE(worker->pool->cpu != cpu);
+ if (!worker->sleeping)
+ return;
+ if (!(worker->flags & WORKER_NOT_RUNNING))
atomic_inc(&worker->pool->nr_running);
- }
+ worker->sleeping = 0;
}
/**
* wq_worker_sleeping - a worker is going to sleep
* @task: task going to sleep
*
- * This function is called during schedule() when a busy worker is
- * going to sleep. Worker on the same cpu can be woken up by
- * returning pointer to its task.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
- *
- * Return:
- * Worker task on @cpu to wake up, %NULL if none.
+ * This function is called from schedule() when a busy worker is
+ * going to sleep.
*/
-struct task_struct *wq_worker_sleeping(struct task_struct *task)
+void wq_worker_sleeping(struct task_struct *task)
{
- struct worker *worker = kthread_data(task), *to_wakeup = NULL;
+ struct worker *next, *worker = kthread_data(task);
struct worker_pool *pool;
/*
* checking NOT_RUNNING.
*/
if (worker->flags & WORKER_NOT_RUNNING)
- return NULL;
+ return;
pool = worker->pool;
- /* this can only happen on the local cpu */
- if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id()))
- return NULL;
+ if (WARN_ON_ONCE(worker->sleeping))
+ return;
+
+ worker->sleeping = 1;
+ spin_lock_irq(&pool->lock);
/*
* The counterpart of the following dec_and_test, implied mb,
* lock is safe.
*/
if (atomic_dec_and_test(&pool->nr_running) &&
- !list_empty(&pool->worklist))
- to_wakeup = first_idle_worker(pool);
- return to_wakeup ? to_wakeup->task : NULL;
+ !list_empty(&pool->worklist)) {
+ next = first_idle_worker(pool);
+ if (next)
+ wake_up_process(next->task);
+ }
+ spin_unlock_irq(&pool->lock);
}
/**
*
* WRITE_ONCE() is necessary because @worker->flags may be
* tested without holding any lock in
- * wq_worker_waking_up(). Without it, NOT_RUNNING test may
+ * wq_worker_running(). Without it, NOT_RUNNING test may
* fail incorrectly leading to premature concurrency
* management operations.
*/
unsigned long last_active; /* L: last active timestamp */
unsigned int flags; /* X: flags */
int id; /* I: worker id */
+ int sleeping; /* None */
/*
* Opaque string set with work_set_desc(). Printed out with task
* Scheduler hooks for concurrency managed workqueue. Only to be used from
* sched/ and workqueue.c.
*/
-void wq_worker_waking_up(struct task_struct *task, int cpu);
-struct task_struct *wq_worker_sleeping(struct task_struct *task);
+void wq_worker_running(struct task_struct *task);
+void wq_worker_sleeping(struct task_struct *task);
work_func_t wq_worker_last_func(struct task_struct *task);
#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
config ARCH_HAS_UACCESS_MCSAFE
bool
+# Temporary. Goes away when all archs are cleaned up
+config ARCH_STACKWALK
+ bool
+
config STACKDEPOT
bool
select STACKTRACE
config ARCH_HAS_KCOV
bool
help
- KCOV does not have any arch-specific code, but currently it is enabled
- only for x86_64. KCOV requires testing on other archs, and most likely
- disabling of instrumentation for some early boot code.
+ An architecture should select this when it can successfully
+ build and run with CONFIG_KCOV. This typically requires
+ disabling instrumentation for some early boot code.
config CC_HAS_SANCOV_TRACE_PC
def_bool $(cc-option,-fsanitize-coverage=trace-pc)
depends on m
depends on BLOCK && (64BIT || LBDAF) # for XFS, BTRFS
depends on NETDEVICES && NET_CORE && INET # for TUN
+ depends on BLOCK
select TEST_LKM
select XFS_FS
select TUN
KCOV_INSTRUMENT_debugobjects.o := n
KCOV_INSTRUMENT_dynamic_debug.o := n
+# Early boot use of cmdline, don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KASAN_SANITIZE_string.o := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_string.o = -pg
+endif
+
+CFLAGS_string.o := $(call cc-option, -fno-stack-protector)
+endif
+
lib-y := ctype.o string.o vsprintf.o cmdline.o \
rbtree.o radix-tree.o timerqueue.o xarray.o \
idr.o int_sqrt.o extable.o \
obj-$(CONFIG_UBSAN) += ubsan.o
UBSAN_SANITIZE_ubsan.o := n
+CFLAGS_ubsan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
obj-$(CONFIG_SBITMAP) += sbitmap.o
static bool fail_stacktrace(struct fault_attr *attr)
{
- struct stack_trace trace;
int depth = attr->stacktrace_depth;
unsigned long entries[MAX_STACK_TRACE_DEPTH];
- int n;
+ int n, nr_entries;
bool found = (attr->require_start == 0 && attr->require_end == ULONG_MAX);
if (depth == 0)
return found;
- trace.nr_entries = 0;
- trace.entries = entries;
- trace.max_entries = depth;
- trace.skip = 1;
-
- save_stack_trace(&trace);
- for (n = 0; n < trace.nr_entries; n++) {
+ nr_entries = stack_trace_save(entries, depth, 1);
+ for (n = 0; n < nr_entries; n++) {
if (attr->reject_start <= entries[n] &&
entries[n] < attr->reject_end)
return false;
return NULL;
}
-void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace)
+/**
+ * stack_depot_fetch - Fetch stack entries from a depot
+ *
+ * @handle: Stack depot handle which was returned from
+ * stack_depot_save().
+ * @entries: Pointer to store the entries address
+ *
+ * Return: The number of trace entries for this depot.
+ */
+unsigned int stack_depot_fetch(depot_stack_handle_t handle,
+ unsigned long **entries)
{
union handle_parts parts = { .handle = handle };
void *slab = stack_slabs[parts.slabindex];
size_t offset = parts.offset << STACK_ALLOC_ALIGN;
struct stack_record *stack = slab + offset;
- trace->nr_entries = trace->max_entries = stack->size;
- trace->entries = stack->entries;
- trace->skip = 0;
+ *entries = stack->entries;
+ return stack->size;
}
-EXPORT_SYMBOL_GPL(depot_fetch_stack);
+EXPORT_SYMBOL_GPL(stack_depot_fetch);
/**
- * depot_save_stack - save stack in a stack depot.
- * @trace - the stacktrace to save.
- * @alloc_flags - flags for allocating additional memory if required.
+ * stack_depot_save - Save a stack trace from an array
+ *
+ * @entries: Pointer to storage array
+ * @nr_entries: Size of the storage array
+ * @alloc_flags: Allocation gfp flags
*
- * Returns the handle of the stack struct stored in depot.
+ * Return: The handle of the stack struct stored in depot
*/
-depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
- gfp_t alloc_flags)
+depot_stack_handle_t stack_depot_save(unsigned long *entries,
+ unsigned int nr_entries,
+ gfp_t alloc_flags)
{
- u32 hash;
- depot_stack_handle_t retval = 0;
struct stack_record *found = NULL, **bucket;
- unsigned long flags;
+ depot_stack_handle_t retval = 0;
struct page *page = NULL;
void *prealloc = NULL;
+ unsigned long flags;
+ u32 hash;
- if (unlikely(trace->nr_entries == 0))
+ if (unlikely(nr_entries == 0))
goto fast_exit;
- hash = hash_stack(trace->entries, trace->nr_entries);
+ hash = hash_stack(entries, nr_entries);
bucket = &stack_table[hash & STACK_HASH_MASK];
/*
* The smp_load_acquire() here pairs with smp_store_release() to
* |bucket| below.
*/
- found = find_stack(smp_load_acquire(bucket), trace->entries,
- trace->nr_entries, hash);
+ found = find_stack(smp_load_acquire(bucket), entries,
+ nr_entries, hash);
if (found)
goto exit;
spin_lock_irqsave(&depot_lock, flags);
- found = find_stack(*bucket, trace->entries, trace->nr_entries, hash);
+ found = find_stack(*bucket, entries, nr_entries, hash);
if (!found) {
struct stack_record *new =
- depot_alloc_stack(trace->entries, trace->nr_entries,
+ depot_alloc_stack(entries, nr_entries,
hash, &prealloc, alloc_flags);
if (new) {
new->next = *bucket;
fast_exit:
return retval;
}
-EXPORT_SYMBOL_GPL(depot_save_stack);
+EXPORT_SYMBOL_GPL(stack_depot_save);
* hit it), 'max' is the address space maximum (and we return
* -EFAULT if we hit it).
*/
-static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
+static inline long do_strncpy_from_user(char *dst, const char __user *src,
+ unsigned long count, unsigned long max)
{
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
- long res = 0;
+ unsigned long res = 0;
/*
* Truncate 'max' to the user-specified limit, so that
static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max)
{
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
- long align, res = 0;
+ unsigned long align, res = 0;
unsigned long c;
/*
* Do everything aligned. But that means that we
* need to also expand the maximum..
*/
- align = (sizeof(long) - 1) & (unsigned long)src;
+ align = (sizeof(unsigned long) - 1) & (unsigned long)src;
src -= align;
max += align;
static int test_func(void *private)
{
struct test_driver *t = private;
- cpumask_t newmask = CPU_MASK_NONE;
int random_array[ARRAY_SIZE(test_case_array)];
int index, i, j, ret;
ktime_t kt;
u64 delta;
- cpumask_set_cpu(t->cpu, &newmask);
- set_cpus_allowed_ptr(current, &newmask);
+ ret = set_cpus_allowed_ptr(current, cpumask_of(t->cpu));
+ if (ret < 0)
+ pr_err("Failed to set affinity to %d CPU\n", t->cpu);
for (i = 0; i < ARRAY_SIZE(test_case_array); i++)
random_array[i] = i;
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/sched.h>
+#include <linux/uaccess.h>
#include "ubsan.h"
return bits <= inline_bits;
}
-static s_max get_signed_val(struct type_descriptor *type, unsigned long val)
+static s_max get_signed_val(struct type_descriptor *type, void *val)
{
if (is_inline_int(type)) {
unsigned extra_bits = sizeof(s_max)*8 - type_bit_width(type);
- return ((s_max)val) << extra_bits >> extra_bits;
+ unsigned long ulong_val = (unsigned long)val;
+
+ return ((s_max)ulong_val) << extra_bits >> extra_bits;
}
if (type_bit_width(type) == 64)
return *(s_max *)val;
}
-static bool val_is_negative(struct type_descriptor *type, unsigned long val)
+static bool val_is_negative(struct type_descriptor *type, void *val)
{
return type_is_signed(type) && get_signed_val(type, val) < 0;
}
-static u_max get_unsigned_val(struct type_descriptor *type, unsigned long val)
+static u_max get_unsigned_val(struct type_descriptor *type, void *val)
{
if (is_inline_int(type))
- return val;
+ return (unsigned long)val;
if (type_bit_width(type) == 64)
return *(u64 *)val;
}
static void val_to_string(char *str, size_t size, struct type_descriptor *type,
- unsigned long value)
+ void *value)
{
if (type_is_int(type)) {
if (type_bit_width(type) == 128) {
current->in_ubsan--;
}
-static void handle_overflow(struct overflow_data *data, unsigned long lhs,
- unsigned long rhs, char op)
+static void handle_overflow(struct overflow_data *data, void *lhs,
+ void *rhs, char op)
{
struct type_descriptor *type = data->type;
}
void __ubsan_handle_add_overflow(struct overflow_data *data,
- unsigned long lhs,
- unsigned long rhs)
+ void *lhs, void *rhs)
{
handle_overflow(data, lhs, rhs, '+');
EXPORT_SYMBOL(__ubsan_handle_add_overflow);
void __ubsan_handle_sub_overflow(struct overflow_data *data,
- unsigned long lhs,
- unsigned long rhs)
+ void *lhs, void *rhs)
{
handle_overflow(data, lhs, rhs, '-');
}
EXPORT_SYMBOL(__ubsan_handle_sub_overflow);
void __ubsan_handle_mul_overflow(struct overflow_data *data,
- unsigned long lhs,
- unsigned long rhs)
+ void *lhs, void *rhs)
{
handle_overflow(data, lhs, rhs, '*');
}
EXPORT_SYMBOL(__ubsan_handle_mul_overflow);
void __ubsan_handle_negate_overflow(struct overflow_data *data,
- unsigned long old_val)
+ void *old_val)
{
unsigned long flags;
char old_val_str[VALUE_LENGTH];
void __ubsan_handle_divrem_overflow(struct overflow_data *data,
- unsigned long lhs,
- unsigned long rhs)
+ void *lhs, void *rhs)
{
unsigned long flags;
char rhs_val_str[VALUE_LENGTH];
static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data,
unsigned long ptr)
{
+ unsigned long flags = user_access_save();
if (!ptr)
handle_null_ptr_deref(data);
handle_misaligned_access(data, ptr);
else
handle_object_size_mismatch(data, ptr);
+
+ user_access_restore(flags);
}
void __ubsan_handle_type_mismatch(struct type_mismatch_data *data,
- unsigned long ptr)
+ void *ptr)
{
struct type_mismatch_data_common common_data = {
.location = &data->location,
.type_check_kind = data->type_check_kind
};
- ubsan_type_mismatch_common(&common_data, ptr);
+ ubsan_type_mismatch_common(&common_data, (unsigned long)ptr);
}
EXPORT_SYMBOL(__ubsan_handle_type_mismatch);
void __ubsan_handle_type_mismatch_v1(struct type_mismatch_data_v1 *data,
- unsigned long ptr)
+ void *ptr)
{
struct type_mismatch_data_common common_data = {
.type_check_kind = data->type_check_kind
};
- ubsan_type_mismatch_common(&common_data, ptr);
+ ubsan_type_mismatch_common(&common_data, (unsigned long)ptr);
}
EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1);
-void __ubsan_handle_vla_bound_not_positive(struct vla_bound_data *data,
- unsigned long bound)
-{
- unsigned long flags;
- char bound_str[VALUE_LENGTH];
-
- if (suppress_report(&data->location))
- return;
-
- ubsan_prologue(&data->location, &flags);
-
- val_to_string(bound_str, sizeof(bound_str), data->type, bound);
- pr_err("variable length array bound value %s <= 0\n", bound_str);
-
- ubsan_epilogue(&flags);
-}
-EXPORT_SYMBOL(__ubsan_handle_vla_bound_not_positive);
-
-void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data,
- unsigned long index)
+void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index)
{
unsigned long flags;
char index_str[VALUE_LENGTH];
EXPORT_SYMBOL(__ubsan_handle_out_of_bounds);
void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
- unsigned long lhs, unsigned long rhs)
+ void *lhs, void *rhs)
{
unsigned long flags;
struct type_descriptor *rhs_type = data->rhs_type;
EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable);
void __ubsan_handle_load_invalid_value(struct invalid_value_data *data,
- unsigned long val)
+ void *val)
{
unsigned long flags;
char val_str[VALUE_LENGTH];
int arg_index;
};
-struct vla_bound_data {
- struct source_location location;
- struct type_descriptor *type;
-};
-
struct out_of_bounds_data {
struct source_location location;
struct type_descriptor *array_type;
struct mm_struct *mm = tlb->mm;
bool ret = false;
- tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+ tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
ptl = pmd_trans_huge_lock(pmd, vma);
if (!ptl)
pmd_t orig_pmd;
spinlock_t *ptl;
- tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+ tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
ptl = __pmd_trans_huge_lock(pmd, vma);
if (!ptl)
* This is a hugetlb vma, all the pte entries should point
* to huge page.
*/
- tlb_remove_check_page_size_change(tlb, sz);
+ tlb_change_page_size(tlb, sz);
tlb_start_vma(tlb, vma);
/*
KASAN_SANITIZE := n
UBSAN_SANITIZE_common.o := n
UBSAN_SANITIZE_generic.o := n
+UBSAN_SANITIZE_generic_report.o := n
UBSAN_SANITIZE_tags.o := n
KCOV_INSTRUMENT := n
CFLAGS_REMOVE_common.o = -pg
CFLAGS_REMOVE_generic.o = -pg
+CFLAGS_REMOVE_generic_report.o = -pg
CFLAGS_REMOVE_tags.o = -pg
# Function splitter causes unnecessary splits in __asan_load1/__asan_store1
CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
obj-$(CONFIG_KASAN) := common.o init.o report.o
#include <linux/types.h>
#include <linux/vmalloc.h>
#include <linux/bug.h>
+#include <linux/uaccess.h>
#include "kasan.h"
#include "../slab.h"
ptr < (unsigned long)&__softirqentry_text_end);
}
-static inline void filter_irq_stacks(struct stack_trace *trace)
+static inline unsigned int filter_irq_stacks(unsigned long *entries,
+ unsigned int nr_entries)
{
- int i;
+ unsigned int i;
- if (!trace->nr_entries)
- return;
- for (i = 0; i < trace->nr_entries; i++)
- if (in_irqentry_text(trace->entries[i])) {
+ for (i = 0; i < nr_entries; i++) {
+ if (in_irqentry_text(entries[i])) {
/* Include the irqentry function into the stack. */
- trace->nr_entries = i + 1;
- break;
+ return i + 1;
}
+ }
+ return nr_entries;
}
static inline depot_stack_handle_t save_stack(gfp_t flags)
{
unsigned long entries[KASAN_STACK_DEPTH];
- struct stack_trace trace = {
- .nr_entries = 0,
- .entries = entries,
- .max_entries = KASAN_STACK_DEPTH,
- .skip = 0
- };
+ unsigned int nr_entries;
- save_stack_trace(&trace);
- filter_irq_stacks(&trace);
- if (trace.nr_entries != 0 &&
- trace.entries[trace.nr_entries-1] == ULONG_MAX)
- trace.nr_entries--;
-
- return depot_save_stack(&trace, flags);
+ nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+ nr_entries = filter_irq_stacks(entries, nr_entries);
+ return stack_depot_save(entries, nr_entries, flags);
}
static inline void set_track(struct kasan_track *track, gfp_t flags)
vfree(kasan_mem_to_shadow(vm->addr));
}
+extern void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip);
+
+void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip)
+{
+ unsigned long flags = user_access_save();
+ __kasan_report(addr, size, is_write, ip);
+ user_access_restore(flags);
+}
+
#ifdef CONFIG_MEMORY_HOTPLUG
static bool shadow_mapped(unsigned long addr)
{
{
pr_err("%s by task %u:\n", prefix, track->pid);
if (track->stack) {
- struct stack_trace trace;
+ unsigned long *entries;
+ unsigned int nr_entries;
- depot_fetch_stack(track->stack, &trace);
- print_stack_trace(&trace, 0);
+ nr_entries = stack_depot_fetch(track->stack, &entries);
+ stack_trace_print(entries, nr_entries, 0);
} else {
pr_err("(stack is not available)\n");
}
end_report(&flags);
}
-void kasan_report(unsigned long addr, size_t size,
- bool is_write, unsigned long ip)
+void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip)
{
struct kasan_access_info info;
void *tagged_addr;
*/
static void dump_object_info(struct kmemleak_object *object)
{
- struct stack_trace trace;
-
- trace.nr_entries = object->trace_len;
- trace.entries = object->trace;
-
pr_notice("Object 0x%08lx (size %zu):\n",
object->pointer, object->size);
pr_notice(" comm \"%s\", pid %d, jiffies %lu\n",
pr_notice(" flags = 0x%x\n", object->flags);
pr_notice(" checksum = %u\n", object->checksum);
pr_notice(" backtrace:\n");
- print_stack_trace(&trace, 4);
+ stack_trace_print(object->trace, object->trace_len, 4);
}
/*
*/
static int __save_stack_trace(unsigned long *trace)
{
- struct stack_trace stack_trace;
-
- stack_trace.max_entries = MAX_TRACE;
- stack_trace.nr_entries = 0;
- stack_trace.entries = trace;
- stack_trace.skip = 2;
- save_stack_trace(&stack_trace);
-
- return stack_trace.nr_entries;
+ return stack_trace_save(trace, MAX_TRACE, 2);
}
/*
/*
* Scan a large memory block in MAX_SCAN_SIZE chunks to reduce the latency.
*/
+#ifdef CONFIG_SMP
static void scan_large_block(void *start, void *end)
{
void *next;
cond_resched();
}
}
+#endif
/*
* Scan a memory block corresponding to a kmemleak_object. A condition is
static void __init print_log_trace(struct early_log *log)
{
- struct stack_trace trace;
-
- trace.nr_entries = log->trace_len;
- trace.entries = log->trace;
-
pr_notice("Early log backtrace:\n");
- print_stack_trace(&trace, 2);
+ stack_trace_print(log->trace, log->trace_len, 2);
}
/*
if (pmd_trans_unstable(pmd))
return 0;
- tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+ tlb_change_page_size(tlb, PAGE_SIZE);
orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
* We add page table cache pages with PAGE_SIZE,
* (see pte_free_tlb()), flush the tlb if we need
*/
- tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+ tlb_change_page_size(tlb, PAGE_SIZE);
pgd = pgd_offset(tlb->mm, addr);
do {
next = pgd_addr_end(addr, end);
pte_t *pte;
swp_entry_t entry;
- tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+ tlb_change_page_size(tlb, PAGE_SIZE);
again:
init_rss_vec(rss);
start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
*/
if (force_flush) {
force_flush = 0;
- tlb_flush_mmu_free(tlb);
+ tlb_flush_mmu(tlb);
if (addr != end)
goto again;
}
*/
mem = find_memory_block(__pfn_to_section(pfn));
nid = mem->nid;
+ put_device(&mem->dev);
/* associate pfn range with the zone */
zone = move_pfn_range(online_type, nid, pfn, nr_pages);
#include <linux/moduleparam.h>
#include <linux/pkeys.h>
#include <linux/oom.h>
+#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
vma = find_vma_prev(mm, addr, &prev);
if (vma && (vma->vm_start <= addr))
return vma;
- if (!prev || expand_stack(prev, addr))
+ /* don't alter vm_end if the coredump is running */
+ if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr))
return NULL;
if (prev->vm_flags & VM_LOCKED)
populate_vma_page_range(prev, addr, prev->vm_end, NULL);
return vma;
if (!(vma->vm_flags & VM_GROWSDOWN))
return NULL;
+ /* don't alter vm_start if the coredump is running */
+ if (!mmget_still_valid(mm))
+ return NULL;
start = vma->vm_start;
if (expand_stack(vma, addr))
return NULL;
#include <asm/pgalloc.h>
#include <asm/tlb.h>
-#ifdef HAVE_GENERIC_MMU_GATHER
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
static bool tlb_next_batch(struct mmu_gather *tlb)
{
return true;
}
-void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- tlb->mm = mm;
-
- /* Is it from 0 to ~0? */
- tlb->fullmm = !(start | (end+1));
- tlb->need_flush_all = 0;
- tlb->local.next = NULL;
- tlb->local.nr = 0;
- tlb->local.max = ARRAY_SIZE(tlb->__pages);
- tlb->active = &tlb->local;
- tlb->batch_count = 0;
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
- tlb->batch = NULL;
-#endif
- tlb->page_size = 0;
-
- __tlb_reset_range(tlb);
-}
-
-void tlb_flush_mmu_free(struct mmu_gather *tlb)
+static void tlb_batch_pages_flush(struct mmu_gather *tlb)
{
struct mmu_gather_batch *batch;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
- tlb_table_flush(tlb);
-#endif
for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
free_pages_and_swap_cache(batch->pages, batch->nr);
batch->nr = 0;
tlb->active = &tlb->local;
}
-void tlb_flush_mmu(struct mmu_gather *tlb)
-{
- tlb_flush_mmu_tlbonly(tlb);
- tlb_flush_mmu_free(tlb);
-}
-
-/* tlb_finish_mmu
- * Called at the end of the shootdown operation to free up any resources
- * that were required.
- */
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end, bool force)
+static void tlb_batch_list_free(struct mmu_gather *tlb)
{
struct mmu_gather_batch *batch, *next;
- if (force) {
- __tlb_reset_range(tlb);
- __tlb_adjust_range(tlb, start, end - start);
- }
-
- tlb_flush_mmu(tlb);
-
- /* keep the page table cache within bounds */
- check_pgt_cache();
-
for (batch = tlb->local.next; batch; batch = next) {
next = batch->next;
free_pages((unsigned long)batch, 0);
tlb->local.next = NULL;
}
-/* __tlb_remove_page
- * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
- * handling the additional races in SMP caused by other CPUs caching valid
- * mappings in their TLBs. Returns the number of free page slots left.
- * When out of page slots we must call tlb_flush_mmu().
- *returns true if the caller should flush.
- */
bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
{
struct mmu_gather_batch *batch;
VM_BUG_ON(!tlb->end);
+
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
VM_WARN_ON(tlb->page_size != page_size);
+#endif
batch = tlb->active;
/*
return false;
}
-#endif /* HAVE_GENERIC_MMU_GATHER */
+#endif /* HAVE_MMU_GATHER_NO_GATHER */
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
*/
static inline void tlb_table_invalidate(struct mmu_gather *tlb)
{
-#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
+#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
/*
* Invalidate page-table caches used by hardware walkers. Then we still
* need to RCU-sched wait while freeing the pages because software
free_page((unsigned long)batch);
}
-void tlb_table_flush(struct mmu_gather *tlb)
+static void tlb_table_flush(struct mmu_gather *tlb)
{
struct mmu_table_batch **batch = &tlb->batch;
#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+static void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+ tlb_table_flush(tlb);
+#endif
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+ tlb_batch_pages_flush(tlb);
+#endif
+}
+
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+ tlb_flush_mmu_tlbonly(tlb);
+ tlb_flush_mmu_free(tlb);
+}
+
/**
* tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
* @tlb: the mmu_gather structure to initialize
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
unsigned long start, unsigned long end)
{
- arch_tlb_gather_mmu(tlb, mm, start, end);
+ tlb->mm = mm;
+
+ /* Is it from 0 to ~0? */
+ tlb->fullmm = !(start | (end+1));
+
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+ tlb->need_flush_all = 0;
+ tlb->local.next = NULL;
+ tlb->local.nr = 0;
+ tlb->local.max = ARRAY_SIZE(tlb->__pages);
+ tlb->active = &tlb->local;
+ tlb->batch_count = 0;
+#endif
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+ tlb->batch = NULL;
+#endif
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+ tlb->page_size = 0;
+#endif
+
+ __tlb_reset_range(tlb);
inc_tlb_flush_pending(tlb->mm);
}
+/**
+ * tlb_finish_mmu - finish an mmu_gather structure
+ * @tlb: the mmu_gather structure to finish
+ * @start: start of the region that will be removed from the page-table
+ * @end: end of the region that will be removed from the page-table
+ *
+ * Called at the end of the shootdown operation to free up any resources that
+ * were required.
+ */
void tlb_finish_mmu(struct mmu_gather *tlb,
unsigned long start, unsigned long end)
{
* the TLB by observing pte_none|!pte_dirty, for example so flush TLB
* forcefully if we detect parallel PTE batching threads.
*/
- bool force = mm_tlb_flush_nested(tlb->mm);
+ if (mm_tlb_flush_nested(tlb->mm)) {
+ __tlb_reset_range(tlb);
+ __tlb_adjust_range(tlb, start, end - start);
+ }
- arch_tlb_finish_mmu(tlb, start, end, force);
+ tlb_flush_mmu(tlb);
+
+ /* keep the page table cache within bounds */
+ check_pgt_cache();
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+ tlb_batch_list_free(tlb);
+#endif
dec_tlb_flush_pending(tlb->mm);
}
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
+#ifdef CONFIG_DISCONTIGMEM
+/*
+ * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges
+ * are not on separate NUMA nodes. Functionally this works but with
+ * watermark_boost_factor, it can reclaim prematurely as the ranges can be
+ * quite small. By default, do not boost watermarks on discontigmem as in
+ * many cases very high-order allocations like THP are likely to be
+ * unsupported and the premature reclaim offsets the advantage of long-term
+ * fragmentation avoidance.
+ */
+int watermark_boost_factor __read_mostly;
+#else
int watermark_boost_factor __read_mostly = 15000;
+#endif
int watermark_scale_factor = 10;
static unsigned long nr_kernel_pages __initdata;
alloc_flags |= ALLOC_KSWAPD;
#ifdef CONFIG_ZONE_DMA32
+ if (!zone)
+ return alloc_flags;
+
if (zone_idx(zone) != ZONE_NORMAL)
- goto out;
+ return alloc_flags;
/*
* If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and
*/
BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1);
if (nr_online_nodes > 1 && !populated_zone(--zone))
- goto out;
+ return alloc_flags;
-out:
+ alloc_flags |= ALLOC_NOFRAGMENT;
#endif /* CONFIG_ZONE_DMA32 */
return alloc_flags;
}
memalloc_noreclaim_restore(noreclaim_flag);
psi_memstall_leave(&pflags);
- if (*compact_result <= COMPACT_INACTIVE) {
- WARN_ON_ONCE(page);
- return NULL;
- }
-
/*
* At least in one zone compaction wasn't deferred or skipped, so let's
* count a compaction stall
bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
int migratetype, int flags)
{
- unsigned long pfn, iter, found;
+ unsigned long found;
+ unsigned long iter = 0;
+ unsigned long pfn = page_to_pfn(page);
+ const char *reason = "unmovable page";
/*
* TODO we could make this much more efficient by not checking every
* can still lead to having bootmem allocations in zone_movable.
*/
- /*
- * CMA allocations (alloc_contig_range) really need to mark isolate
- * CMA pageblocks even when they are not movable in fact so consider
- * them movable here.
- */
- if (is_migrate_cma(migratetype) &&
- is_migrate_cma(get_pageblock_migratetype(page)))
- return false;
+ if (is_migrate_cma_page(page)) {
+ /*
+ * CMA allocations (alloc_contig_range) really need to mark
+ * isolate CMA pageblocks even when they are not movable in fact
+ * so consider them movable here.
+ */
+ if (is_migrate_cma(migratetype))
+ return false;
+
+ reason = "CMA page";
+ goto unmovable;
+ }
- pfn = page_to_pfn(page);
- for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
+ for (found = 0; iter < pageblock_nr_pages; iter++) {
unsigned long check = pfn + iter;
if (!pfn_valid_within(check))
unmovable:
WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
if (flags & REPORT_FAILURE)
- dump_page(pfn_to_page(pfn+iter), "unmovable page");
+ dump_page(pfn_to_page(pfn + iter), reason);
return true;
}
static __always_inline depot_stack_handle_t create_dummy_stack(void)
{
unsigned long entries[4];
- struct stack_trace dummy;
+ unsigned int nr_entries;
- dummy.nr_entries = 0;
- dummy.max_entries = ARRAY_SIZE(entries);
- dummy.entries = &entries[0];
- dummy.skip = 0;
-
- save_stack_trace(&dummy);
- return depot_save_stack(&dummy, GFP_KERNEL);
+ nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+ return stack_depot_save(entries, nr_entries, GFP_KERNEL);
}
static noinline void register_dummy_stack(void)
}
}
-static inline bool check_recursive_alloc(struct stack_trace *trace,
- unsigned long ip)
+static inline bool check_recursive_alloc(unsigned long *entries,
+ unsigned int nr_entries,
+ unsigned long ip)
{
- int i;
-
- if (!trace->nr_entries)
- return false;
+ unsigned int i;
- for (i = 0; i < trace->nr_entries; i++) {
- if (trace->entries[i] == ip)
+ for (i = 0; i < nr_entries; i++) {
+ if (entries[i] == ip)
return true;
}
-
return false;
}
static noinline depot_stack_handle_t save_stack(gfp_t flags)
{
unsigned long entries[PAGE_OWNER_STACK_DEPTH];
- struct stack_trace trace = {
- .nr_entries = 0,
- .entries = entries,
- .max_entries = PAGE_OWNER_STACK_DEPTH,
- .skip = 2
- };
depot_stack_handle_t handle;
+ unsigned int nr_entries;
- save_stack_trace(&trace);
- if (trace.nr_entries != 0 &&
- trace.entries[trace.nr_entries-1] == ULONG_MAX)
- trace.nr_entries--;
+ nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
/*
- * We need to check recursion here because our request to stackdepot
- * could trigger memory allocation to save new entry. New memory
- * allocation would reach here and call depot_save_stack() again
- * if we don't catch it. There is still not enough memory in stackdepot
- * so it would try to allocate memory again and loop forever.
+ * We need to check recursion here because our request to
+ * stackdepot could trigger memory allocation to save new
+ * entry. New memory allocation would reach here and call
+ * stack_depot_save_entries() again if we don't catch it. There is
+ * still not enough memory in stackdepot so it would try to
+ * allocate memory again and loop forever.
*/
- if (check_recursive_alloc(&trace, _RET_IP_))
+ if (check_recursive_alloc(entries, nr_entries, _RET_IP_))
return dummy_handle;
- handle = depot_save_stack(&trace, flags);
+ handle = stack_depot_save(entries, nr_entries, flags);
if (!handle)
handle = failure_handle;
struct page *page, struct page_owner *page_owner,
depot_stack_handle_t handle)
{
- int ret;
- int pageblock_mt, page_mt;
+ int ret, pageblock_mt, page_mt;
+ unsigned long *entries;
+ unsigned int nr_entries;
char *kbuf;
- unsigned long entries[PAGE_OWNER_STACK_DEPTH];
- struct stack_trace trace = {
- .nr_entries = 0,
- .entries = entries,
- .max_entries = PAGE_OWNER_STACK_DEPTH,
- .skip = 0
- };
count = min_t(size_t, count, PAGE_SIZE);
kbuf = kmalloc(count, GFP_KERNEL);
if (ret >= count)
goto err;
- depot_fetch_stack(handle, &trace);
- ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
+ nr_entries = stack_depot_fetch(handle, &entries);
+ ret += stack_trace_snprint(kbuf + ret, count - ret, entries, nr_entries, 0);
if (ret >= count)
goto err;
{
struct page_ext *page_ext = lookup_page_ext(page);
struct page_owner *page_owner;
- unsigned long entries[PAGE_OWNER_STACK_DEPTH];
- struct stack_trace trace = {
- .nr_entries = 0,
- .entries = entries,
- .max_entries = PAGE_OWNER_STACK_DEPTH,
- .skip = 0
- };
depot_stack_handle_t handle;
+ unsigned long *entries;
+ unsigned int nr_entries;
gfp_t gfp_mask;
int mt;
return;
}
- depot_fetch_stack(handle, &trace);
+ nr_entries = stack_depot_fetch(handle, &entries);
pr_alert("page allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n",
page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask);
- print_stack_trace(&trace, 0);
+ stack_trace_print(entries, nr_entries, 0);
if (page_owner->last_migrate_reason != -1)
pr_alert("page has been migrated, last migrate reason: %s\n",
ai->groups[group].base_offset = areas[group] - base;
}
- pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
- PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,
+ pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n",
+ PFN_DOWN(size_sum), ai->static_size, ai->reserved_size,
ai->dyn_size, ai->unit_size);
rc = pcpu_setup_first_chunk(ai, base);
}
/* we're ready, commit */
- pr_info("%d %s pages/cpu @%p s%zu r%zu d%zu\n",
- unit_pages, psize_str, vm.addr, ai->static_size,
+ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n",
+ unit_pages, psize_str, ai->static_size,
ai->reserved_size, ai->dyn_size);
rc = pcpu_setup_first_chunk(ai, vm.addr);
}
spin_unlock(&sbinfo->shrinklist_lock);
}
- if (!list_empty(&info->swaplist)) {
+ while (!list_empty(&info->swaplist)) {
+ /* Wait while shmem_unuse() is scanning this inode... */
+ wait_var_event(&info->stop_eviction,
+ !atomic_read(&info->stop_eviction));
mutex_lock(&shmem_swaplist_mutex);
- list_del_init(&info->swaplist);
+ /* ...but beware of the race if we peeked too early */
+ if (!atomic_read(&info->stop_eviction))
+ list_del_init(&info->swaplist);
mutex_unlock(&shmem_swaplist_mutex);
}
}
static int shmem_find_swap_entries(struct address_space *mapping,
pgoff_t start, unsigned int nr_entries,
struct page **entries, pgoff_t *indices,
- bool frontswap)
+ unsigned int type, bool frontswap)
{
XA_STATE(xas, &mapping->i_pages, start);
struct page *page;
+ swp_entry_t entry;
unsigned int ret = 0;
if (!nr_entries)
if (!xa_is_value(page))
continue;
- if (frontswap) {
- swp_entry_t entry = radix_to_swp_entry(page);
-
- if (!frontswap_test(swap_info[swp_type(entry)],
- swp_offset(entry)))
- continue;
- }
+ entry = radix_to_swp_entry(page);
+ if (swp_type(entry) != type)
+ continue;
+ if (frontswap &&
+ !frontswap_test(swap_info[type], swp_offset(entry)))
+ continue;
indices[ret] = xas.xa_index;
entries[ret] = page;
pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries,
pvec.pages, indices,
- frontswap);
+ type, frontswap);
if (pvec.nr == 0) {
ret = 0;
break;
unsigned long *fs_pages_to_unuse)
{
struct shmem_inode_info *info, *next;
- struct inode *inode;
- struct inode *prev_inode = NULL;
int error = 0;
if (list_empty(&shmem_swaplist))
return 0;
mutex_lock(&shmem_swaplist_mutex);
-
- /*
- * The extra refcount on the inode is necessary to safely dereference
- * p->next after re-acquiring the lock. New shmem inodes with swap
- * get added to the end of the list and we will scan them all.
- */
list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) {
if (!info->swapped) {
list_del_init(&info->swaplist);
continue;
}
-
- inode = igrab(&info->vfs_inode);
- if (!inode)
- continue;
-
+ /*
+ * Drop the swaplist mutex while searching the inode for swap;
+ * but before doing so, make sure shmem_evict_inode() will not
+ * remove placeholder inode from swaplist, nor let it be freed
+ * (igrab() would protect from unlink, but not from unmount).
+ */
+ atomic_inc(&info->stop_eviction);
mutex_unlock(&shmem_swaplist_mutex);
- if (prev_inode)
- iput(prev_inode);
- prev_inode = inode;
- error = shmem_unuse_inode(inode, type, frontswap,
+ error = shmem_unuse_inode(&info->vfs_inode, type, frontswap,
fs_pages_to_unuse);
cond_resched();
next = list_next_entry(info, swaplist);
if (!info->swapped)
list_del_init(&info->swaplist);
+ if (atomic_dec_and_test(&info->stop_eviction))
+ wake_up_var(&info->stop_eviction);
if (error)
break;
}
mutex_unlock(&shmem_swaplist_mutex);
- if (prev_inode)
- iput(prev_inode);
-
return error;
}
info = SHMEM_I(inode);
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
+ atomic_set(&info->stop_eviction, 0);
info->seals = F_SEAL_SEAL;
info->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(&info->shrinklist);
/* Slab management obj is off-slab. */
freelist = kmem_cache_alloc_node(cachep->freelist_cache,
local_flags, nodeid);
- freelist = kasan_reset_tag(freelist);
if (!freelist)
return NULL;
} else {
if (addr) {
#ifdef CONFIG_STACKTRACE
- struct stack_trace trace;
- int i;
+ unsigned int nr_entries;
- trace.nr_entries = 0;
- trace.max_entries = TRACK_ADDRS_COUNT;
- trace.entries = p->addrs;
- trace.skip = 3;
metadata_access_enable();
- save_stack_trace(&trace);
+ nr_entries = stack_trace_save(p->addrs, TRACK_ADDRS_COUNT, 3);
metadata_access_disable();
- /* See rant in lockdep.c */
- if (trace.nr_entries != 0 &&
- trace.entries[trace.nr_entries - 1] == ULONG_MAX)
- trace.nr_entries--;
-
- for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++)
- p->addrs[i] = 0;
+ if (nr_entries < TRACK_ADDRS_COUNT)
+ p->addrs[nr_entries] = 0;
#endif
p->addr = addr;
p->cpu = smp_processor_id();
p->pid = current->pid;
p->when = jiffies;
- } else
+ } else {
memset(p, 0, sizeof(struct track));
+ }
}
static void init_tracking(struct kmem_cache *s, void *object)
* If the boolean frontswap is true, only unuse pages_to_unuse pages;
* pages_to_unuse==0 means all pages; ignored if frontswap is false
*/
-#define SWAP_UNUSE_MAX_TRIES 3
int try_to_unuse(unsigned int type, bool frontswap,
unsigned long pages_to_unuse)
{
struct page *page;
swp_entry_t entry;
unsigned int i;
- int retries = 0;
if (!si->inuse_pages)
return 0;
spin_lock(&mmlist_lock);
p = &init_mm.mmlist;
- while ((p = p->next) != &init_mm.mmlist) {
- if (signal_pending(current)) {
- retval = -EINTR;
- break;
- }
+ while (si->inuse_pages &&
+ !signal_pending(current) &&
+ (p = p->next) != &init_mm.mmlist) {
mm = list_entry(p, struct mm_struct, mmlist);
if (!mmget_not_zero(mm))
mmput(prev_mm);
i = 0;
- while ((i = find_next_to_unuse(si, i, frontswap)) != 0) {
+ while (si->inuse_pages &&
+ !signal_pending(current) &&
+ (i = find_next_to_unuse(si, i, frontswap)) != 0) {
entry = swp_entry(type, i);
page = find_get_page(swap_address_space(entry), i);
* If yes, we would need to do retry the unuse logic again.
* Under global memory pressure, swap entries can be reinserted back
* into process space after the mmlist loop above passes over them.
- * Its not worth continuosuly retrying to unuse the swap in this case.
- * So we try SWAP_UNUSE_MAX_TRIES times.
+ *
+ * Limit the number of retries? No: when mmget_not_zero() above fails,
+ * that mm is likely to be freeing swap from exit_mmap(), which proceeds
+ * at its own independent pace; and even shmem_writepage() could have
+ * been preempted after get_swap_page(), temporarily hiding that swap.
+ * It's easy and robust (though cpu-intensive) just to keep retrying.
*/
- if (++retries >= SWAP_UNUSE_MAX_TRIES)
- retval = -EBUSY;
- else if (si->inuse_pages)
- goto retry;
-
+ if (si->inuse_pages) {
+ if (!signal_pending(current))
+ goto retry;
+ retval = -EINTR;
+ }
out:
return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval;
}
* 10TB 320 32GB
*/
static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
- struct mem_cgroup *memcg,
struct scan_control *sc, bool actual_reclaim)
{
enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
- if (memcg)
- refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
- else
- refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
/*
* When refaults are being observed, it means a new workingset
* is being established. Disable active list protection to get
* rid of the stale workingset quickly.
*/
+ refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
if (file && actual_reclaim && lruvec->refaults != refaults) {
inactive_ratio = 0;
} else {
}
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
- struct lruvec *lruvec, struct mem_cgroup *memcg,
- struct scan_control *sc)
+ struct lruvec *lruvec, struct scan_control *sc)
{
if (is_active_lru(lru)) {
- if (inactive_list_is_low(lruvec, is_file_lru(lru),
- memcg, sc, true))
+ if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true))
shrink_active_list(nr_to_scan, lruvec, sc, lru);
return 0;
}
* anonymous pages on the LRU in eligible zones.
* Otherwise, the small LRU gets thrashed.
*/
- if (!inactive_list_is_low(lruvec, false, memcg, sc, false) &&
+ if (!inactive_list_is_low(lruvec, false, sc, false) &&
lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
>> sc->priority) {
scan_balance = SCAN_ANON;
* lruvec even if it has plenty of old anonymous pages unless the
* system is under heavy pressure.
*/
- if (!inactive_list_is_low(lruvec, true, memcg, sc, false) &&
+ if (!inactive_list_is_low(lruvec, true, sc, false) &&
lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
scan_balance = SCAN_FILE;
goto out;
nr[lru] -= nr_to_scan;
nr_reclaimed += shrink_list(lru, nr_to_scan,
- lruvec, memcg, sc);
+ lruvec, sc);
}
}
* Even if we did not try to evict anon pages at all, we want to
* rebalance the anon lru active/inactive ratio.
*/
- if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+ if (inactive_list_is_low(lruvec, false, sc, true))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
}
unsigned long refaults;
struct lruvec *lruvec;
- if (memcg)
- refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
- else
- refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
lruvec->refaults = refaults;
} while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
}
do {
struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
- if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+ if (inactive_list_is_low(lruvec, false, sc, true))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
#endif
#endif /* CONFIG_MEMORY_BALLOON */
#ifdef CONFIG_DEBUG_TLBFLUSH
-#ifdef CONFIG_SMP
"nr_tlb_remote_flush",
"nr_tlb_remote_flush_received",
-#else
- "", /* nr_tlb_remote_flush */
- "", /* nr_tlb_remote_flush_received */
-#endif /* CONFIG_SMP */
"nr_tlb_local_flush_all",
"nr_tlb_local_flush_one",
#endif /* CONFIG_DEBUG_TLBFLUSH */
ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv);
if (!ddp_dl) {
pr_crit("Unable to register DDP with SNAP.\n");
+ rc = -ENOMEM;
goto out_sock;
}
static int lec_mcast_attach(struct atm_vcc *vcc, int arg)
{
- if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg])
+ if (arg < 0 || arg >= MAX_LEC_ITF)
+ return -EINVAL;
+ arg = array_index_nospec(arg, MAX_LEC_ITF);
+ if (!dev_lec[arg])
return -EINVAL;
vcc->proto_data = dev_lec[arg];
return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc);
i = arg;
if (arg >= MAX_LEC_ITF)
return -EINVAL;
+ i = array_index_nospec(arg, MAX_LEC_ITF);
if (!dev_lec[i]) {
int size;
struct sock *sk = sock->sk;
int err = 0;
- BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr);
-
if (!addr || addr_len < sizeof(struct sockaddr_sco) ||
addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr);
+
lock_sock(sk);
if (sk->sk_state != BT_OPEN) {
/* note: already called with rcu_read_lock */
static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net_bridge_port *p = br_port_get_rcu(skb->dev);
-
__br_handle_local_finish(skb);
- BR_INPUT_SKB_CB(skb)->brdev = p->br->dev;
- br_pass_frame_up(skb);
- return 0;
+ /* return 1 to signal the okfn() was called so it's ok to use the skb */
+ return 1;
}
/*
goto forward;
}
- /* Deliver packet to local host only */
- NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev),
- NULL, skb, skb->dev, NULL, br_handle_local_finish);
- return RX_HANDLER_CONSUMED;
+ /* The else clause should be hit when nf_hook():
+ * - returns < 0 (drop/error)
+ * - returns = 0 (stolen/nf_queue)
+ * Thus return 1 from the okfn() to signal the skb is ok to pass
+ */
+ if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
+ dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+ br_handle_local_finish) == 1) {
+ return RX_HANDLER_PASS;
+ } else {
+ return RX_HANDLER_CONSUMED;
+ }
}
forward:
__br_multicast_open(br, query);
- list_for_each_entry(port, &br->port_list, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &br->port_list, list) {
if (port->state == BR_STATE_DISABLED ||
port->state == BR_STATE_BLOCKING)
continue;
br_multicast_enable(&port->ip6_own_query);
#endif
}
+ rcu_read_unlock();
}
int br_multicast_toggle(struct net_bridge *br, unsigned long val)
nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED,
br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) ||
nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT,
- br_opt_get(br, IFLA_BR_VLAN_STATS_PER_PORT)))
+ br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)))
return -EMSGSIZE;
#endif
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
if (match_kern)
match_kern->match_size = ret;
- if (WARN_ON(type == EBT_COMPAT_TARGET && size_left))
+ /* rule should have no remaining data after target */
+ if (type == EBT_COMPAT_TARGET && size_left)
return -EINVAL;
match32 = (struct compat_ebt_entry_mwt *) buf;
BUG_ON(!dev_net(dev));
net = dev_net(dev);
- if (dev->flags & IFF_UP)
+
+ /* Some auto-enslaved devices e.g. failover slaves are
+ * special, as userspace might rename the device after
+ * the interface had been brought up and running since
+ * the point kernel initiated auto-enslavement. Allow
+ * live name change even when these slave devices are
+ * up and running.
+ *
+ * Typically, users of these auto-enslaving devices
+ * don't actually care about slave name change, as
+ * they are supposed to operate on master interface
+ * directly.
+ */
+ if (dev->flags & IFF_UP &&
+ likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
return -EBUSY;
write_seqcount_begin(&devnet_rename_seq);
goto err_upper_link;
}
- slave_dev->priv_flags |= IFF_FAILOVER_SLAVE;
+ slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
if (fops && fops->slave_register &&
!fops->slave_register(slave_dev, failover_dev))
return NOTIFY_OK;
netdev_upper_dev_unlink(slave_dev, failover_dev);
- slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+ slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
err_upper_link:
netdev_rx_handler_unregister(slave_dev);
done:
netdev_rx_handler_unregister(slave_dev);
netdev_upper_dev_unlink(slave_dev, failover_dev);
- slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+ slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
if (fops && fops->slave_unregister &&
!fops->slave_unregister(slave_dev, failover_dev))
* Only binding to IP is supported.
*/
err = -EINVAL;
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return err;
if (addr->sa_family == AF_INET) {
if (addr_len < sizeof(struct sockaddr_in))
return err;
error = device_add(dev);
if (error)
- goto error_put_device;
+ return error;
error = register_queue_kobjects(ndev);
- if (error)
- goto error_device_del;
+ if (error) {
+ device_del(dev);
+ return error;
+ }
pm_runtime_set_memalloc_noio(dev, true);
- return 0;
-
-error_device_del:
- device_del(dev);
-error_put_device:
- put_device(dev);
return error;
}
{ 0x16, 0, 0, 0x00000000 },
{ 0x06, 0, 0, 0x00000000 },
};
- struct sock_fprog_kern ptp_prog = {
- .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
- };
+ struct sock_fprog_kern ptp_prog;
+
+ ptp_prog.len = ARRAY_SIZE(ptp_filter);
+ ptp_prog.filter = ptp_filter;
BUG_ON(bpf_prog_create(&ptp_insns, &ptp_prog));
}
{
struct if_stats_msg *ifsm;
- if (nlh->nlmsg_len < sizeof(*ifsm)) {
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifsm))) {
NL_SET_ERR_MSG(extack, "Invalid header for stats dump");
return -EINVAL;
}
static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
{
- int mac_len;
+ int mac_len, meta_len;
+ void *meta;
if (skb_cow(skb, skb_headroom(skb)) < 0) {
kfree_skb(skb);
memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
mac_len - VLAN_HLEN - ETH_TLEN);
}
+
+ meta_len = skb_metadata_len(skb);
+ if (meta_len) {
+ meta = skb_metadata_end(skb) - meta_len;
+ memmove(meta + VLAN_HLEN, meta, meta_len);
+ }
+
skb->mac_header += VLAN_HLEN;
return skb;
}
tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ;
}
- if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+ if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec };
*(struct old_timeval32 *)optval = tv32;
return sizeof(tv32);
{
struct __kernel_sock_timeval tv;
- if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+ if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
struct old_timeval32 tv32;
if (optlen < sizeof(tv32))
tail[plen - 1] = proto;
}
-static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
{
int encap_type;
struct udphdr *uh;
__be16 sport, dport;
struct xfrm_encap_tmpl *encap = x->encap;
struct ip_esp_hdr *esph = esp->esph;
+ unsigned int len;
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
encap_type = encap->encap_type;
spin_unlock_bh(&x->lock);
+ len = skb->len + esp->tailen - skb_transport_offset(skb);
+ if (len + sizeof(struct iphdr) >= IP_MAX_MTU)
+ return -EMSGSIZE;
+
uh = (struct udphdr *)esph;
uh->source = sport;
uh->dest = dport;
- uh->len = htons(skb->len + esp->tailen
- - skb_transport_offset(skb));
+ uh->len = htons(len);
uh->check = 0;
switch (encap_type) {
*skb_mac_header(skb) = IPPROTO_UDP;
esp->esph = esph;
+
+ return 0;
}
int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
int tailen = esp->tailen;
/* this is non-NULL only with UDP Encapsulation */
- if (x->encap)
- esp_output_udp_encap(x, skb, esp);
+ if (x->encap) {
+ int err = esp_output_udp_encap(x, skb, esp);
+
+ if (err < 0)
+ return err;
+ }
if (!skb_cloned(skb)) {
if (tailen <= skb_tailroom(skb)) {
goto out;
if (sp->len == XFRM_MAX_DEPTH)
- goto out;
+ goto out_reset;
x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
(xfrm_address_t *)&ip_hdr(skb)->daddr,
spi, IPPROTO_ESP, AF_INET);
if (!x)
- goto out;
+ goto out_reset;
sp->xvec[sp->len++] = x;
sp->olen++;
xo = xfrm_offload(skb);
if (!xo) {
xfrm_state_put(x);
- goto out;
+ goto out_reset;
}
}
xfrm_input(skb, IPPROTO_ESP, spi, -2);
return ERR_PTR(-EINPROGRESS);
+out_reset:
+ secpath_reset(skb);
out:
skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
struct guehdr *guehdr;
void *data;
u16 doffset = 0;
+ u8 proto_ctype;
if (!fou)
return 1;
if (unlikely(guehdr->control))
return gue_control_message(skb, guehdr);
+ proto_ctype = guehdr->proto_ctype;
__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
skb_reset_transport_header(skb);
if (iptunnel_pull_offloads(skb))
goto drop;
- return -guehdr->proto_ctype;
+ return -proto_ctype;
drop:
kfree_skb(skb);
to->pkt_type = from->pkt_type;
to->priority = from->priority;
to->protocol = from->protocol;
+ to->skb_iif = from->skb_iif;
skb_dst_drop(to);
skb_dst_copy(to, from);
to->dev = from->dev;
msg = "ipip tunnel";
err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
- if (err < 0) {
- pr_info("%s: cant't register tunnel\n",__func__);
+ if (err < 0)
goto xfrm_tunnel_failed;
- }
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
return err;
rtnl_link_failed:
- xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
-xfrm_tunnel_failed:
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+xfrm_tunnel_failed:
+ xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
static void __exit vti_fini(void)
{
rtnl_link_unregister(&vti_link_ops);
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
#endif
enum clusterip_hashmode hash_mode; /* which hashing mode */
u_int32_t hash_initval; /* hash initialization */
- struct rcu_head rcu; /* for call_rcu_bh */
+ struct rcu_head rcu; /* for call_rcu */
struct net *net; /* netns for pernet list */
char ifname[IFNAMSIZ]; /* device ifname */
};
return dst;
}
+static void ipv4_send_dest_unreach(struct sk_buff *skb)
+{
+ struct ip_options opt;
+ int res;
+
+ /* Recompile ip options since IPCB may not be valid anymore.
+ * Also check we have a reasonable ipv4 header.
+ */
+ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) ||
+ ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5)
+ return;
+
+ memset(&opt, 0, sizeof(opt));
+ if (ip_hdr(skb)->ihl > 5) {
+ if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4))
+ return;
+ opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
+
+ rcu_read_lock();
+ res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+ rcu_read_unlock();
+
+ if (res)
+ return;
+ }
+ __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
+}
+
static void ipv4_link_failure(struct sk_buff *skb)
{
struct rtable *rt;
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+ ipv4_send_dest_unreach(skb);
rt = skb_rtable(skb);
if (rt)
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
static int comp_sack_nr_max = 255;
static u32 u32_max_div_HZ = UINT_MAX / HZ;
+static int one_day_secs = 24 * 3600;
/* obsolete */
static int sysctl_tcp_low_latency __read_mostly;
.data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one_day_secs
},
{
.procname = "tcp_autocorking",
#define DCTCP_MAX_ALPHA 1024U
struct dctcp {
- u32 acked_bytes_ecn;
- u32 acked_bytes_total;
- u32 prior_snd_una;
+ u32 old_delivered;
+ u32 old_delivered_ce;
u32 prior_rcv_nxt;
u32 dctcp_alpha;
u32 next_seq;
{
ca->next_seq = tp->snd_nxt;
- ca->acked_bytes_ecn = 0;
- ca->acked_bytes_total = 0;
+ ca->old_delivered = tp->delivered;
+ ca->old_delivered_ce = tp->delivered_ce;
}
static void dctcp_init(struct sock *sk)
sk->sk_state == TCP_CLOSE)) {
struct dctcp *ca = inet_csk_ca(sk);
- ca->prior_snd_una = tp->snd_una;
ca->prior_rcv_nxt = tp->rcv_nxt;
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
{
const struct tcp_sock *tp = tcp_sk(sk);
struct dctcp *ca = inet_csk_ca(sk);
- u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
-
- /* If ack did not advance snd_una, count dupack as MSS size.
- * If ack did update window, do not count it at all.
- */
- if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
- acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
- if (acked_bytes) {
- ca->acked_bytes_total += acked_bytes;
- ca->prior_snd_una = tp->snd_una;
-
- if (flags & CA_ACK_ECE)
- ca->acked_bytes_ecn += acked_bytes;
- }
/* Expired RTT */
if (!before(tp->snd_una, ca->next_seq)) {
- u64 bytes_ecn = ca->acked_bytes_ecn;
+ u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
u32 alpha = ca->dctcp_alpha;
/* alpha = (1 - g) * alpha + g * F */
alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
- if (bytes_ecn) {
+ if (delivered_ce) {
+ u32 delivered = tp->delivered - ca->old_delivered;
+
/* If dctcp_shift_g == 1, a 32bit value would overflow
- * after 8 Mbytes.
+ * after 8 M packets.
*/
- bytes_ecn <<= (10 - dctcp_shift_g);
- do_div(bytes_ecn, max(1U, ca->acked_bytes_total));
+ delivered_ce <<= (10 - dctcp_shift_g);
+ delivered_ce /= max(1U, delivered);
- alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA);
+ alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
}
/* dctcp_alpha can be read from dctcp_get_info() without
* synchro, so we ask compiler to not use dctcp_alpha
union tcp_cc_info *info)
{
const struct dctcp *ca = inet_csk_ca(sk);
+ const struct tcp_sock *tp = tcp_sk(sk);
/* Fill it also in case of VEGASINFO due to req struct limits.
* We can still correctly retrieve it later.
info->dctcp.dctcp_enabled = 1;
info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
info->dctcp.dctcp_alpha = ca->dctcp_alpha;
- info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
- info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
+ info->dctcp.dctcp_ab_ecn = tp->mss_cache *
+ (tp->delivered_ce - ca->old_delivered_ce);
+ info->dctcp.dctcp_ab_tot = tp->mss_cache *
+ (tp->delivered - ca->old_delivered);
}
*attr = INET_DIAG_DCTCPINFO;
static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
+ int room;
+
+ room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh;
/* Check #1 */
- if (tp->rcv_ssthresh < tp->window_clamp &&
- (int)tp->rcv_ssthresh < tcp_space(sk) &&
- !tcp_under_memory_pressure(sk)) {
+ if (room > 0 && !tcp_under_memory_pressure(sk)) {
int incr;
/* Check #2. Increase window, if skb with such overhead
if (incr) {
incr = max_t(int, incr, 2 * skb->len);
- tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
- tp->window_clamp);
+ tp->rcv_ssthresh += min(room, incr);
inet_csk(sk)->icsk_ack.quick |= 1;
}
}
if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq ||
TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield ||
((TCP_SKB_CB(tail)->tcp_flags |
- TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_URG) ||
+ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) ||
+ !((TCP_SKB_CB(tail)->tcp_flags &
+ TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) ||
((TCP_SKB_CB(tail)->tcp_flags ^
TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
#ifdef CONFIG_TLS_DEVICE
if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))
TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
+ /* We have to update both TCP_SKB_CB(tail)->tcp_flags and
+ * thtail->fin, so that the fast path in tcp_rcv_established()
+ * is not entered if we append a packet with a FIN.
+ * SYN, RST, URG are not present.
+ * ACK is set on both packets.
+ * PSH : we do not really care in TCP stack,
+ * at least for 'GRO' packets.
+ */
+ thtail->fin |= th->fin;
TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
if (TCP_SKB_CB(skb)->has_rxtstamp) {
struct sk_buff *pp = NULL;
struct udphdr *uh2;
struct sk_buff *p;
+ unsigned int ulen;
/* requires non zero csum, for symmetry with GSO */
if (!uh->check) {
return NULL;
}
+ /* Do not deal with padded or malicious packets, sorry ! */
+ ulen = ntohs(uh->len);
+ if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) {
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+ }
/* pull encapsulating udp header */
skb_gro_pull(skb, sizeof(struct udphdr));
skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
/* Terminate the flow on len mismatch or if it grow "too much".
* Under small packet flood GRO count could elsewhere grow a lot
- * leading to execessive truesize values
+ * leading to excessive truesize values.
+ * On len mismatch merge the first packet shorter than gso_size,
+ * otherwise complete the GRO packet.
*/
- if (!skb_gro_receive(p, skb) &&
+ if (ulen > ntohs(uh2->len) || skb_gro_receive(p, skb) ||
+ ulen != ntohs(uh2->len) ||
NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
pp = p;
- else if (uh->len != uh2->len)
- pp = p;
return pp;
}
_decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
{
const struct iphdr *iph = ip_hdr(skb);
- u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
+ int ihl = iph->ihl;
+ u8 *xprth = skb_network_header(skb) + ihl * 4;
struct flowi4 *fl4 = &fl->u.ip4;
int oif = 0;
fl4->flowi4_mark = skb->mark;
fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
+ fl4->flowi4_proto = iph->protocol;
+ fl4->daddr = reverse ? iph->saddr : iph->daddr;
+ fl4->saddr = reverse ? iph->daddr : iph->saddr;
+ fl4->flowi4_tos = iph->tos;
+
if (!ip_is_fragment(iph)) {
switch (iph->protocol) {
case IPPROTO_UDP:
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ports;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
ports = (__be16 *)xprth;
fl4->fl4_sport = ports[!!reverse];
pskb_may_pull(skb, xprth + 2 - skb->data)) {
u8 *icmp;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
icmp = xprth;
fl4->fl4_icmp_type = icmp[0];
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be32 *ehdr;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
ehdr = (__be32 *)xprth;
fl4->fl4_ipsec_spi = ehdr[0];
pskb_may_pull(skb, xprth + 8 - skb->data)) {
__be32 *ah_hdr;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
ah_hdr = (__be32 *)xprth;
fl4->fl4_ipsec_spi = ah_hdr[1];
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ipcomp_hdr;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
ipcomp_hdr = (__be16 *)xprth;
fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
__be16 *greflags;
__be32 *gre_hdr;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
greflags = (__be16 *)xprth;
gre_hdr = (__be32 *)xprth;
break;
}
}
- fl4->flowi4_proto = iph->protocol;
- fl4->daddr = reverse ? iph->saddr : iph->daddr;
- fl4->saddr = reverse ? iph->daddr : iph->saddr;
- fl4->flowi4_tos = iph->tos;
}
static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
}
if (nlmsg_attrlen(nlh, sizeof(*ifal))) {
- NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump requewst");
+ NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump request");
return -EINVAL;
}
goto out;
if (sp->len == XFRM_MAX_DEPTH)
- goto out;
+ goto out_reset;
x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
(xfrm_address_t *)&ipv6_hdr(skb)->daddr,
spi, IPPROTO_ESP, AF_INET6);
if (!x)
- goto out;
+ goto out_reset;
sp->xvec[sp->len++] = x;
sp->olen++;
xo = xfrm_offload(skb);
if (!xo) {
xfrm_state_put(x);
- goto out;
+ goto out_reset;
}
}
xfrm_input(skb, IPPROTO_ESP, spi, -2);
return ERR_PTR(-EINPROGRESS);
+out_reset:
+ secpath_reset(skb);
out:
skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
if (pcpu_rt) {
struct fib6_info *from;
- from = rcu_dereference_protected(pcpu_rt->from,
- lockdep_is_held(&table->tb6_lock));
- rcu_assign_pointer(pcpu_rt->from, NULL);
+ from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
fib6_info_release(from);
}
}
return fl;
}
+static void fl_free_rcu(struct rcu_head *head)
+{
+ struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu);
+
+ if (fl->share == IPV6_FL_S_PROCESS)
+ put_pid(fl->owner.pid);
+ kfree(fl->opt);
+ kfree(fl);
+}
+
static void fl_free(struct ip6_flowlabel *fl)
{
- if (fl) {
- if (fl->share == IPV6_FL_S_PROCESS)
- put_pid(fl->owner.pid);
- kfree(fl->opt);
- kfree_rcu(fl, rcu);
- }
+ if (fl)
+ call_rcu(&fl->rcu, fl_free_rcu);
}
static void fl_release(struct ip6_flowlabel *fl)
if (fl1->share == IPV6_FL_S_EXCL ||
fl1->share != fl->share ||
((fl1->share == IPV6_FL_S_PROCESS) &&
- (fl1->owner.pid == fl->owner.pid)) ||
+ (fl1->owner.pid != fl->owner.pid)) ||
((fl1->share == IPV6_FL_S_USER) &&
- uid_eq(fl1->owner.uid, fl->owner.uid)))
+ !uid_eq(fl1->owner.uid, fl->owner.uid)))
goto release;
err = -ENOMEM;
in6_dev_put(idev);
}
- rcu_read_lock();
- from = rcu_dereference(rt->from);
- rcu_assign_pointer(rt->from, NULL);
+ from = xchg((__force struct fib6_info **)&rt->from, NULL);
fib6_info_release(from);
- rcu_read_unlock();
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
/* purge completely the exception to allow releasing the held resources:
* some [sk] cache may keep the dst around for unlimited time
*/
- from = rcu_dereference_protected(rt6_ex->rt6i->from,
- lockdep_is_held(&rt6_exception_lock));
- rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+ from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
fib6_info_release(from);
dst_dev_put(&rt6_ex->rt6i->dst);
rcu_read_lock();
from = rcu_dereference(rt6->from);
+ if (!from) {
+ rcu_read_unlock();
+ return;
+ }
nrt6 = ip6_rt_cache_alloc(from, daddr, saddr);
if (nrt6) {
rt6_do_update_pmtu(nrt6, mtu);
rcu_read_lock();
from = rcu_dereference(rt->from);
- /* This fib6_info_hold() is safe here because we hold reference to rt
- * and rt already holds reference to fib6_info.
- */
- fib6_info_hold(from);
- rcu_read_unlock();
+ if (!from)
+ goto out;
nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
if (!nrt)
nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
- /* No need to remove rt from the exception table if rt is
- * a cached route because rt6_insert_exception() will
- * takes care of it
- */
+ /* rt6_insert_exception() will take care of duplicated exceptions */
if (rt6_insert_exception(nrt, from)) {
dst_release_immediate(&nrt->dst);
goto out;
call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
out:
- fib6_info_release(from);
+ rcu_read_unlock();
neigh_release(neigh);
}
static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
{
- int type;
struct dst_entry *dst = skb_dst(skb);
+ struct net *net = dev_net(dst->dev);
+ struct inet6_dev *idev;
+ int type;
+
+ if (netif_is_l3_master(skb->dev) &&
+ dst->dev == net->loopback_dev)
+ idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
+ else
+ idev = ip6_dst_idev(dst);
+
switch (ipstats_mib_noroutes) {
case IPSTATS_MIB_INNOROUTES:
type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
if (type == IPV6_ADDR_ANY) {
- IP6_INC_STATS(dev_net(dst->dev),
- __in6_dev_get_safely(skb->dev),
- IPSTATS_MIB_INADDRERRORS);
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
break;
}
/* FALLTHROUGH */
case IPSTATS_MIB_OUTNOROUTES:
- IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
- ipstats_mib_noroutes);
+ IP6_INC_STATS(net, idev, ipstats_mib_noroutes);
break;
}
+
+ /* Start over by dropping the dst for l3mdev case */
+ if (netif_is_l3_master(skb->dev))
+ skb_dst_drop(skb);
+
icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
kfree_skb(skb);
return 0;
rcu_read_lock();
from = rcu_dereference(rt->from);
-
- if (fibmatch)
- err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif,
- RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, 0);
- else
- err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
- &fl6.saddr, iif, RTM_NEWROUTE,
- NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
- 0);
+ if (from) {
+ if (fibmatch)
+ err = rt6_fill_node(net, skb, from, NULL, NULL, NULL,
+ iif, RTM_NEWROUTE,
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0);
+ else
+ err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
+ &fl6.saddr, iif, RTM_NEWROUTE,
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0);
+ } else {
+ err = -ENETUNREACH;
+ }
rcu_read_unlock();
if (err < 0) {
static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
/* The following checks are replicated from __ip6_datagram_connect()
* and intended to prevent BPF program called below from accessing
* bytes that are out of the bound specified by user in addr_len.
unsigned int i;
xfrm_flush_gc();
- xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
+ xfrm_state_flush(net, 0, false, true);
for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6);
xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6);
unregister_pernet_subsys(&xfrm6_tunnel_net_ops);
+ /* Someone maybe has gotten the xfrm6_tunnel_spi.
+ * So need to wait it.
+ */
+ rcu_barrier();
kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
}
if (rq->sadb_x_ipsecrequest_mode == 0)
return -EINVAL;
+ if (!xfrm_id_proto_valid(rq->sadb_x_ipsecrequest_proto))
+ return -EINVAL;
- t->id.proto = rq->sadb_x_ipsecrequest_proto; /* XXX check proto */
+ t->id.proto = rq->sadb_x_ipsecrequest_proto;
if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0)
return -EINVAL;
t->mode = mode;
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (tunnel->tunnel_id == tunnel_id) {
- l2tp_tunnel_inc_refcount(tunnel);
+ if (tunnel->tunnel_id == tunnel_id &&
+ refcount_inc_not_zero(&tunnel->ref_count)) {
rcu_read_unlock_bh();
return tunnel;
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (++count > nth) {
- l2tp_tunnel_inc_refcount(tunnel);
+ if (++count > nth &&
+ refcount_inc_not_zero(&tunnel->ref_count)) {
rcu_read_unlock_bh();
return tunnel;
}
{
struct l2tp_tunnel *tunnel;
- tunnel = l2tp_tunnel(sk);
+ tunnel = rcu_dereference_sk_user_data(sk);
if (tunnel == NULL)
goto pass_up;
struct llc_sap *sap;
int rc = -EINVAL;
- dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
-
lock_sock(sk);
if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr)))
goto out;
rc = -EAFNOSUPPORT;
if (unlikely(addr->sllc_family != AF_LLC))
goto out;
+ dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
rc = -ENODEV;
rcu_read_lock();
if (sk->sk_bound_dev_if) {
dir = sdata->vif.debugfs_dir;
- if (!dir)
+ if (IS_ERR_OR_NULL(dir))
return;
sprintf(buf, "netdev:%s", sdata->name);
{
struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif);
+ if (local->in_reconfig)
+ return;
+
if (!check_sdata_in_driver(sdata))
return;
IEEE80211_HT_CAP_TX_STBC);
/* Allow user to configure RX STBC bits */
- if (ht_capa_mask->cap_info & IEEE80211_HT_CAP_RX_STBC)
- ht_cap->cap |= ht_capa->cap_info & IEEE80211_HT_CAP_RX_STBC;
+ if (ht_capa_mask->cap_info & cpu_to_le16(IEEE80211_HT_CAP_RX_STBC))
+ ht_cap->cap |= le16_to_cpu(ht_capa->cap_info) &
+ IEEE80211_HT_CAP_RX_STBC;
/* Allow user to decrease AMPDU factor */
if (ht_capa_mask->ampdu_params_info &
list_del_rcu(&sdata->list);
mutex_unlock(&sdata->local->iflist_mtx);
+ if (sdata->vif.txq)
+ ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq));
+
synchronize_rcu();
if (sdata->dev) {
* The driver doesn't know anything about VLAN interfaces.
* Hence, don't send GTKs for VLAN interfaces to the driver.
*/
- if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE))
+ if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) {
+ ret = 1;
goto out_unsupported;
+ }
}
ret = drv_set_key(key->local, SET_KEY, sdata,
/* all of these we can do in software - if driver can */
if (ret == 1)
return 0;
- if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) {
- if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
- return 0;
+ if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL))
return -EINVAL;
- }
return 0;
default:
return -EINVAL;
static u32 mesh_table_hash(const void *addr, u32 len, u32 seed)
{
/* Use last four bytes of hw addr as hash index */
- return jhash_1word(*(u32 *)(addr+2), seed);
+ return jhash_1word(__get_unaligned_cpu32((u8 *)addr + 2), seed);
}
static const struct rhashtable_params mesh_rht_params = {
return;
for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) {
- if (txq_has_queue(sta->sta.txq[tid]))
+ struct ieee80211_txq *txq = sta->sta.txq[tid];
+ struct txq_info *txqi = to_txq_info(txq);
+
+ spin_lock(&local->active_txq_lock[txq->ac]);
+ if (!list_empty(&txqi->schedule_order))
+ list_del_init(&txqi->schedule_order);
+ spin_unlock(&local->active_txq_lock[txq->ac]);
+
+ if (txq_has_queue(txq))
set_bit(tid, &sta->txq_buffered_tids);
else
clear_bit(tid, &sta->txq_buffered_tids);
/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Portions of this file
+ * Copyright (C) 2019 Intel Corporation
+ */
+
#ifdef CONFIG_MAC80211_MESSAGE_TRACING
#if !defined(__MAC80211_MSG_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ)
#undef TRACE_SYSTEM
#define TRACE_SYSTEM mac80211_msg
-#define MAX_MSG_LEN 100
+#define MAX_MSG_LEN 120
DECLARE_EVENT_CLASS(mac80211_msg_event,
TP_PROTO(struct va_format *vaf),
u8 max_subframes = sta->sta.max_amsdu_subframes;
int max_frags = local->hw.max_tx_fragments;
int max_amsdu_len = sta->sta.max_amsdu_len;
+ int orig_truesize;
__be16 len;
void *data;
bool ret = false;
if (!head || skb_is_gso(head))
goto out;
+ orig_truesize = head->truesize;
orig_len = head->len;
if (skb->len + head->len > max_amsdu_len)
*frag_tail = skb;
out_recalc:
+ fq->memory_usage += head->truesize - orig_truesize;
if (head->len != orig_len) {
flow->backlog += head->len - orig_len;
tin->backlog_bytes += head->len - orig_len;
struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
{
struct ieee80211_local *local = hw_to_local(hw);
+ struct ieee80211_txq *ret = NULL;
struct txq_info *txqi = NULL;
- lockdep_assert_held(&local->active_txq_lock[ac]);
+ spin_lock_bh(&local->active_txq_lock[ac]);
begin:
txqi = list_first_entry_or_null(&local->active_txqs[ac],
struct txq_info,
schedule_order);
if (!txqi)
- return NULL;
+ goto out;
if (txqi->txq.sta) {
struct sta_info *sta = container_of(txqi->txq.sta,
if (txqi->schedule_round == local->schedule_round[ac])
- return NULL;
+ goto out;
list_del_init(&txqi->schedule_order);
txqi->schedule_round = local->schedule_round[ac];
- return &txqi->txq;
+ ret = &txqi->txq;
+
+out:
+ spin_unlock_bh(&local->active_txq_lock[ac]);
+ return ret;
}
EXPORT_SYMBOL(ieee80211_next_txq);
-void ieee80211_return_txq(struct ieee80211_hw *hw,
- struct ieee80211_txq *txq)
+void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
+ struct ieee80211_txq *txq,
+ bool force)
{
struct ieee80211_local *local = hw_to_local(hw);
struct txq_info *txqi = to_txq_info(txq);
- lockdep_assert_held(&local->active_txq_lock[txq->ac]);
+ spin_lock_bh(&local->active_txq_lock[txq->ac]);
if (list_empty(&txqi->schedule_order) &&
- (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) {
+ (force || !skb_queue_empty(&txqi->frags) ||
+ txqi->tin.backlog_packets)) {
/* If airtime accounting is active, always enqueue STAs at the
* head of the list to ensure that they only get moved to the
* back by the airtime DRR scheduler once they have a negative
list_add_tail(&txqi->schedule_order,
&local->active_txqs[txq->ac]);
}
-}
-EXPORT_SYMBOL(ieee80211_return_txq);
-void ieee80211_schedule_txq(struct ieee80211_hw *hw,
- struct ieee80211_txq *txq)
- __acquires(txq_lock) __releases(txq_lock)
-{
- struct ieee80211_local *local = hw_to_local(hw);
-
- spin_lock_bh(&local->active_txq_lock[txq->ac]);
- ieee80211_return_txq(hw, txq);
spin_unlock_bh(&local->active_txq_lock[txq->ac]);
}
-EXPORT_SYMBOL(ieee80211_schedule_txq);
+EXPORT_SYMBOL(__ieee80211_schedule_txq);
bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
struct ieee80211_txq *txq)
struct sta_info *sta;
u8 ac = txq->ac;
- lockdep_assert_held(&local->active_txq_lock[ac]);
+ spin_lock_bh(&local->active_txq_lock[ac]);
if (!txqi->txq.sta)
goto out;
sta->airtime[ac].deficit += sta->airtime_weight;
list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]);
+ spin_unlock_bh(&local->active_txq_lock[ac]);
return false;
out:
if (!list_empty(&txqi->schedule_order))
list_del_init(&txqi->schedule_order);
+ spin_unlock_bh(&local->active_txq_lock[ac]);
return true;
}
EXPORT_SYMBOL(ieee80211_txq_may_transmit);
void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
- __acquires(txq_lock)
{
struct ieee80211_local *local = hw_to_local(hw);
spin_lock_bh(&local->active_txq_lock[ac]);
local->schedule_round[ac]++;
-}
-EXPORT_SYMBOL(ieee80211_txq_schedule_start);
-
-void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
- __releases(txq_lock)
-{
- struct ieee80211_local *local = hw_to_local(hw);
-
spin_unlock_bh(&local->active_txq_lock[ac]);
}
-EXPORT_SYMBOL(ieee80211_txq_schedule_end);
+EXPORT_SYMBOL(ieee80211_txq_schedule_start);
void __ieee80211_subif_start_xmit(struct sk_buff *skb,
struct net_device *dev,
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <net/ncsi.h>
ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
memcpy(saddr.sa_data, &rsp->data[BCM_MAC_ADDR_OFFSET], ETH_ALEN);
/* Increase mac address by 1 for BMC's address */
- saddr.sa_data[ETH_ALEN - 1]++;
+ eth_addr_inc((u8 *)saddr.sa_data);
+ if (!is_valid_ether_addr((const u8 *)saddr.sa_data))
+ return -ENXIO;
+
ret = ops->ndo_set_mac_address(ndev, &saddr);
if (ret < 0)
netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n");
if (!cp) {
int v;
- if (!sysctl_schedule_icmp(ipvs))
+ if (ipip || !sysctl_schedule_icmp(ipvs))
return NF_ACCEPT;
if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph))
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/jhash.h>
+#include <linux/siphash.h>
#include <linux/err.h>
#include <linux/percpu.h>
#include <linux/moduleparam.h>
}
EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
+/* Generate a almost-unique pseudo-id for a given conntrack.
+ *
+ * intentionally doesn't re-use any of the seeds used for hash
+ * table location, we assume id gets exposed to userspace.
+ *
+ * Following nf_conn items do not change throughout lifetime
+ * of the nf_conn after it has been committed to main hash table:
+ *
+ * 1. nf_conn address
+ * 2. nf_conn->ext address
+ * 3. nf_conn->master address (normally NULL)
+ * 4. tuple
+ * 5. the associated net namespace
+ */
+u32 nf_ct_get_id(const struct nf_conn *ct)
+{
+ static __read_mostly siphash_key_t ct_id_seed;
+ unsigned long a, b, c, d;
+
+ net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
+
+ a = (unsigned long)ct;
+ b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct));
+ c = (unsigned long)ct->ext;
+ d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash),
+ &ct_id_seed);
+#ifdef CONFIG_64BIT
+ return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
+#else
+ return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed);
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_get_id);
+
static void
clean_from_lists(struct nf_conn *ct)
{
/* set conntrack timestamp, if enabled. */
tstamp = nf_conn_tstamp_find(ct);
- if (tstamp) {
- if (skb->tstamp == 0)
- __net_timestamp(skb);
+ if (tstamp)
+ tstamp->start = ktime_get_real_ns();
- tstamp->start = ktime_to_ns(skb->tstamp);
- }
/* Since the lookup is lockless, hash insertion must be done after
* starting the timer and setting the CONFIRMED bit. The RCU barriers
* guarantee that no other CPU can find the conntrack before the above
/* save hash for reusing when confirming */
*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
ct->status = 0;
+ ct->timeout = 0;
write_pnet(&ct->ct_net, net);
memset(&ct->__nfct_init_offset[0], 0,
offsetof(struct nf_conn, proto) -
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
+#include <linux/siphash.h>
#include <linux/netfilter.h>
#include <net/netlink.h>
static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct)
{
- if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct)))
+ __be32 id = (__force __be32)nf_ct_get_id(ct);
+
+ if (nla_put_be32(skb, CTA_ID, id))
goto nla_put_failure;
return 0;
}
if (cda[CTA_ID]) {
- u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID]));
- if (id != (u32)(unsigned long)ct) {
+ __be32 id = nla_get_be32(cda[CTA_ID]);
+
+ if (id != (__force __be32)nf_ct_get_id(ct)) {
nf_ct_put(ct);
return -ENOENT;
}
static const union nf_inet_addr any_addr;
+static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp)
+{
+ static __read_mostly siphash_key_t exp_id_seed;
+ unsigned long a, b, c, d;
+
+ net_get_random_once(&exp_id_seed, sizeof(exp_id_seed));
+
+ a = (unsigned long)exp;
+ b = (unsigned long)exp->helper;
+ c = (unsigned long)exp->master;
+ d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed);
+
+#ifdef CONFIG_64BIT
+ return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed);
+#else
+ return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed);
+#endif
+}
+
static int
ctnetlink_exp_dump_expect(struct sk_buff *skb,
const struct nf_conntrack_expect *exp)
}
#endif
if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) ||
- nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) ||
+ nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) ||
nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) ||
nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class)))
goto nla_put_failure;
if (cda[CTA_EXPECT_ID]) {
__be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
- if (ntohl(id) != (u32)(unsigned long)exp) {
+
+ if (id != nf_expect_get_id(exp)) {
nf_ct_expect_put(exp);
return -ENOENT;
}
struct va_format vaf;
va_list args;
- if (net->ct.sysctl_log_invalid != protonum ||
+ if (net->ct.sysctl_log_invalid != protonum &&
net->ct.sysctl_log_invalid != IPPROTO_RAW)
return;
return NF_ACCEPT;
}
-/* Returns conntrack if it dealt with ICMP, and filled in skb fields */
-static int
-icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb,
- const struct nf_hook_state *state)
+/* Check inner header is related to any of the existing connections */
+int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb,
+ unsigned int dataoff,
+ const struct nf_hook_state *state,
+ u8 l4proto, union nf_inet_addr *outer_daddr)
{
struct nf_conntrack_tuple innertuple, origtuple;
const struct nf_conntrack_tuple_hash *h;
const struct nf_conntrack_zone *zone;
enum ip_conntrack_info ctinfo;
struct nf_conntrack_zone tmp;
+ union nf_inet_addr *ct_daddr;
+ enum ip_conntrack_dir dir;
+ struct nf_conn *ct;
WARN_ON(skb_nfct(skb));
zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
/* Are they talking about one of our connections? */
- if (!nf_ct_get_tuplepr(skb,
- skb_network_offset(skb) + ip_hdrlen(skb)
- + sizeof(struct icmphdr),
- PF_INET, state->net, &origtuple)) {
- pr_debug("icmp_error_message: failed to get tuple\n");
+ if (!nf_ct_get_tuplepr(skb, dataoff,
+ state->pf, state->net, &origtuple))
return -NF_ACCEPT;
- }
/* Ordinarily, we'd expect the inverted tupleproto, but it's
been preserved inside the ICMP. */
- if (!nf_ct_invert_tuple(&innertuple, &origtuple)) {
- pr_debug("icmp_error_message: no match\n");
+ if (!nf_ct_invert_tuple(&innertuple, &origtuple))
return -NF_ACCEPT;
- }
-
- ctinfo = IP_CT_RELATED;
h = nf_conntrack_find_get(state->net, zone, &innertuple);
- if (!h) {
- pr_debug("icmp_error_message: no match\n");
+ if (!h)
+ return -NF_ACCEPT;
+
+ /* Consider: A -> T (=This machine) -> B
+ * Conntrack entry will look like this:
+ * Original: A->B
+ * Reply: B->T (SNAT case) OR A
+ *
+ * When this function runs, we got packet that looks like this:
+ * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..).
+ *
+ * Above nf_conntrack_find_get() makes lookup based on inner_hdr,
+ * so we should expect that destination of the found connection
+ * matches outer header destination address.
+ *
+ * In above example, we can consider these two cases:
+ * 1. Error coming in reply direction from B or M (middle box) to
+ * T (SNAT case) or A.
+ * Inner saddr will be B, dst will be T or A.
+ * The found conntrack will be reply tuple (B->T/A).
+ * 2. Error coming in original direction from A or M to B.
+ * Inner saddr will be A, inner daddr will be B.
+ * The found conntrack will be original tuple (A->B).
+ *
+ * In both cases, conntrack[dir].dst == inner.dst.
+ *
+ * A bogus packet could look like this:
+ * Inner: B->T
+ * Outer: B->X (other machine reachable by T).
+ *
+ * In this case, lookup yields connection A->B and will
+ * set packet from B->X as *RELATED*, even though no connection
+ * from X was ever seen.
+ */
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ dir = NF_CT_DIRECTION(h);
+ ct_daddr = &ct->tuplehash[dir].tuple.dst.u3;
+ if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) {
+ if (state->pf == AF_INET) {
+ nf_l4proto_log_invalid(skb, state->net, state->pf,
+ l4proto,
+ "outer daddr %pI4 != inner %pI4",
+ &outer_daddr->ip, &ct_daddr->ip);
+ } else if (state->pf == AF_INET6) {
+ nf_l4proto_log_invalid(skb, state->net, state->pf,
+ l4proto,
+ "outer daddr %pI6 != inner %pI6",
+ &outer_daddr->ip6, &ct_daddr->ip6);
+ }
+ nf_ct_put(ct);
return -NF_ACCEPT;
}
- if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
+ ctinfo = IP_CT_RELATED;
+ if (dir == IP_CT_DIR_REPLY)
ctinfo += IP_CT_IS_REPLY;
/* Update skb to refer to this connection */
- nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
+ nf_ct_set(skb, ct, ctinfo);
return NF_ACCEPT;
}
struct sk_buff *skb, unsigned int dataoff,
const struct nf_hook_state *state)
{
+ union nf_inet_addr outer_daddr;
const struct icmphdr *icmph;
struct icmphdr _ih;
/* Not enough header? */
- icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih);
+ icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
if (icmph == NULL) {
icmp_error_log(skb, state, "short packet");
return -NF_ACCEPT;
icmph->type != ICMP_REDIRECT)
return NF_ACCEPT;
- return icmp_error_message(tmpl, skb, state);
+ memset(&outer_daddr, 0, sizeof(outer_daddr));
+ outer_daddr.ip = ip_hdr(skb)->daddr;
+
+ dataoff += sizeof(*icmph);
+ return nf_conntrack_inet_error(tmpl, skb, dataoff, state,
+ IPPROTO_ICMP, &outer_daddr);
}
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
return NF_ACCEPT;
}
-static int
-icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
- struct sk_buff *skb,
- unsigned int icmp6off)
-{
- struct nf_conntrack_tuple intuple, origtuple;
- const struct nf_conntrack_tuple_hash *h;
- enum ip_conntrack_info ctinfo;
- struct nf_conntrack_zone tmp;
-
- WARN_ON(skb_nfct(skb));
-
- /* Are they talking about one of our connections? */
- if (!nf_ct_get_tuplepr(skb,
- skb_network_offset(skb)
- + sizeof(struct ipv6hdr)
- + sizeof(struct icmp6hdr),
- PF_INET6, net, &origtuple)) {
- pr_debug("icmpv6_error: Can't get tuple\n");
- return -NF_ACCEPT;
- }
-
- /* Ordinarily, we'd expect the inverted tupleproto, but it's
- been preserved inside the ICMP. */
- if (!nf_ct_invert_tuple(&intuple, &origtuple)) {
- pr_debug("icmpv6_error: Can't invert tuple\n");
- return -NF_ACCEPT;
- }
-
- ctinfo = IP_CT_RELATED;
-
- h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp),
- &intuple);
- if (!h) {
- pr_debug("icmpv6_error: no match\n");
- return -NF_ACCEPT;
- } else {
- if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
- ctinfo += IP_CT_IS_REPLY;
- }
-
- /* Update skb to refer to this connection */
- nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
- return NF_ACCEPT;
-}
static void icmpv6_error_log(const struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int dataoff,
const struct nf_hook_state *state)
{
+ union nf_inet_addr outer_daddr;
const struct icmp6hdr *icmp6h;
struct icmp6hdr _ih;
int type;
if (icmp6h->icmp6_type >= 128)
return NF_ACCEPT;
- return icmpv6_error_message(state->net, tmpl, skb, dataoff);
+ memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr,
+ sizeof(outer_daddr.ip6));
+ dataoff += sizeof(*icmp6h);
+ return nf_conntrack_inet_error(tmpl, skb, dataoff, state,
+ IPPROTO_ICMPV6, &outer_daddr);
}
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
case IPPROTO_ICMPV6:
/* id is same for either direction... */
keyptr = &tuple->src.u.icmp.id;
- min = range->min_proto.icmp.id;
- range_size = ntohs(range->max_proto.icmp.id) -
- ntohs(range->min_proto.icmp.id) + 1;
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
+ min = 0;
+ range_size = 65536;
+ } else {
+ min = ntohs(range->min_proto.icmp.id);
+ range_size = ntohs(range->max_proto.icmp.id) -
+ ntohs(range->min_proto.icmp.id) + 1;
+ }
goto find_free_id;
#if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE)
case IPPROTO_GRE:
if (IS_ERR(type))
return PTR_ERR(type);
}
- if (!(type->hook_mask & (1 << hook->num)))
+ if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
return -EOPNOTSUPP;
if (type->type == NFT_CHAIN_T_NAT &&
goto nla_put_failure;
}
- if (skb->tstamp) {
+ if (hooknum <= NF_INET_FORWARD && skb->tstamp) {
struct nfulnl_msg_packet_timestamp ts;
struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
ts.sec = cpu_to_be64(kts.tv_sec);
if (nfqnl_put_bridge(entry, skb) < 0)
goto nla_put_failure;
- if (entskb->tstamp) {
+ if (entry->state.hook <= NF_INET_FORWARD && entskb->tstamp) {
struct nfqnl_msg_packet_timestamp ts;
struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);
s64 stamp;
/*
- * We cannot use get_seconds() instead of __net_timestamp() here.
+ * We need real time here, but we can neither use skb->tstamp
+ * nor __net_timestamp().
+ *
+ * skb->tstamp and skb->skb_mstamp_ns overlap, however, they
+ * use different clock types (real vs monotonic).
+ *
* Suppose you have two rules:
- * 1. match before 13:00
- * 2. match after 13:00
+ * 1. match before 13:00
+ * 2. match after 13:00
+ *
* If you match against processing time (get_seconds) it
* may happen that the same packet matches both rules if
- * it arrived at the right moment before 13:00.
+ * it arrived at the right moment before 13:00, so it would be
+ * better to check skb->tstamp and set it via __net_timestamp()
+ * if needed. This however breaks outgoing packets tx timestamp,
+ * and causes them to get delayed forever by fq packet scheduler.
*/
- if (skb->tstamp == 0)
- __net_timestamp((struct sk_buff *)skb);
-
- stamp = ktime_to_ns(skb->tstamp);
- stamp = div_s64(stamp, NSEC_PER_SEC);
+ stamp = get_seconds();
if (info->flags & XT_TIME_LOCAL_TZ)
/* Adjust for local timezone */
struct netlink_sock *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err = 0;
- unsigned long groups = nladdr->nl_groups;
+ unsigned long groups;
bool bound;
if (addr_len < sizeof(struct sockaddr_nl))
if (nladdr->nl_family != AF_NETLINK)
return -EINVAL;
+ groups = nladdr->nl_groups;
/* Only superuser is allowed to listen multicasts */
if (groups) {
} else
family->attrbuf = NULL;
- family->id = idr_alloc(&genl_fam_idr, family,
- start, end + 1, GFP_KERNEL);
+ family->id = idr_alloc_cyclic(&genl_fam_idr, family,
+ start, end + 1, GFP_KERNEL);
if (family->id < 0) {
err = family->id;
goto errout_free;
int i;
int rc = proto_register(&nr_proto, 0);
- if (rc != 0)
- goto out;
+ if (rc)
+ return rc;
if (nr_ndevs > 0x7fffffff/sizeof(struct net_device *)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - nr_ndevs parameter to large\n");
- return -1;
+ pr_err("NET/ROM: %s - nr_ndevs parameter too large\n",
+ __func__);
+ rc = -EINVAL;
+ goto unregister_proto;
}
dev_nr = kcalloc(nr_ndevs, sizeof(struct net_device *), GFP_KERNEL);
- if (dev_nr == NULL) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device array\n");
- return -1;
+ if (!dev_nr) {
+ pr_err("NET/ROM: %s - unable to allocate device array\n",
+ __func__);
+ rc = -ENOMEM;
+ goto unregister_proto;
}
for (i = 0; i < nr_ndevs; i++) {
sprintf(name, "nr%d", i);
dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup);
if (!dev) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device structure\n");
+ rc = -ENOMEM;
goto fail;
}
dev->base_addr = i;
- if (register_netdev(dev)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register network device\n");
+ rc = register_netdev(dev);
+ if (rc) {
free_netdev(dev);
goto fail;
}
dev_nr[i] = dev;
}
- if (sock_register(&nr_family_ops)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register socket family\n");
+ rc = sock_register(&nr_family_ops);
+ if (rc)
goto fail;
- }
- register_netdevice_notifier(&nr_dev_notifier);
+ rc = register_netdevice_notifier(&nr_dev_notifier);
+ if (rc)
+ goto out_sock;
ax25_register_pid(&nr_pid);
ax25_linkfail_register(&nr_linkfail_notifier);
#ifdef CONFIG_SYSCTL
- nr_register_sysctl();
+ rc = nr_register_sysctl();
+ if (rc)
+ goto out_sysctl;
#endif
nr_loopback_init();
- proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops);
- proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops);
- proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops);
-out:
- return rc;
+ rc = -ENOMEM;
+ if (!proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops))
+ goto proc_remove1;
+ if (!proc_create_seq("nr_neigh", 0444, init_net.proc_net,
+ &nr_neigh_seqops))
+ goto proc_remove2;
+ if (!proc_create_seq("nr_nodes", 0444, init_net.proc_net,
+ &nr_node_seqops))
+ goto proc_remove3;
+
+ return 0;
+
+proc_remove3:
+ remove_proc_entry("nr_neigh", init_net.proc_net);
+proc_remove2:
+ remove_proc_entry("nr", init_net.proc_net);
+proc_remove1:
+
+ nr_loopback_clear();
+ nr_rt_free();
+
+#ifdef CONFIG_SYSCTL
+ nr_unregister_sysctl();
+out_sysctl:
+#endif
+ ax25_linkfail_release(&nr_linkfail_notifier);
+ ax25_protocol_release(AX25_P_NETROM);
+ unregister_netdevice_notifier(&nr_dev_notifier);
+out_sock:
+ sock_unregister(PF_NETROM);
fail:
while (--i >= 0) {
unregister_netdev(dev_nr[i]);
free_netdev(dev_nr[i]);
}
kfree(dev_nr);
+unregister_proto:
proto_unregister(&nr_proto);
- rc = -1;
- goto out;
+ return rc;
}
module_init(nr_proto_init);
}
}
-void __exit nr_loopback_clear(void)
+void nr_loopback_clear(void)
{
del_timer_sync(&loopback_timer);
skb_queue_purge(&loopback_queue);
/*
* Free all memory associated with the nodes and routes lists.
*/
-void __exit nr_rt_free(void)
+void nr_rt_free(void)
{
struct nr_neigh *s = NULL;
struct nr_node *t = NULL;
{ }
};
-void __init nr_register_sysctl(void)
+int __init nr_register_sysctl(void)
{
nr_table_header = register_net_sysctl(&init_net, "net/netrom", nr_table);
+ if (!nr_table_header)
+ return -ENOMEM;
+ return 0;
}
void nr_unregister_sysctl(void)
void *ph;
DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
+ unsigned char *addr = NULL;
int tp_len, size_max;
- unsigned char *addr;
void *data;
int len_sum = 0;
int status = TP_STATUS_AVAILABLE;
if (likely(saddr == NULL)) {
dev = packet_cached_dev_get(po);
proto = po->num;
- addr = NULL;
} else {
err = -EINVAL;
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
sll_addr)))
goto out;
proto = saddr->sll_protocol;
- addr = saddr->sll_halen ? saddr->sll_addr : NULL;
dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
- if (addr && dev && saddr->sll_halen < dev->addr_len)
- goto out_put;
+ if (po->sk.sk_socket->type == SOCK_DGRAM) {
+ if (dev && msg->msg_namelen < dev->addr_len +
+ offsetof(struct sockaddr_ll, sll_addr))
+ goto out_put;
+ addr = saddr->sll_addr;
+ }
}
err = -ENXIO;
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- unsigned char *addr;
+ unsigned char *addr = NULL;
int err, reserve = 0;
struct sockcm_cookie sockc;
struct virtio_net_hdr vnet_hdr = { 0 };
if (likely(saddr == NULL)) {
dev = packet_cached_dev_get(po);
proto = po->num;
- addr = NULL;
} else {
err = -EINVAL;
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
goto out;
proto = saddr->sll_protocol;
- addr = saddr->sll_halen ? saddr->sll_addr : NULL;
dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
- if (addr && dev && saddr->sll_halen < dev->addr_len)
- goto out_unlock;
+ if (sock->type == SOCK_DGRAM) {
+ if (dev && msg->msg_namelen < dev->addr_len +
+ offsetof(struct sockaddr_ll, sll_addr))
+ goto out_unlock;
+ addr = saddr->sll_addr;
+ }
}
err = -ENXIO;
sock_recv_ts_and_drops(msg, sk, skb);
if (msg->msg_name) {
+ int copy_len;
+
/* If the address length field is there to be filled
* in, we fill it in now.
*/
if (sock->type == SOCK_PACKET) {
__sockaddr_check_size(sizeof(struct sockaddr_pkt));
msg->msg_namelen = sizeof(struct sockaddr_pkt);
+ copy_len = msg->msg_namelen;
} else {
struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
msg->msg_namelen = sll->sll_halen +
offsetof(struct sockaddr_ll, sll_addr);
+ copy_len = msg->msg_namelen;
+ if (msg->msg_namelen < sizeof(struct sockaddr_ll)) {
+ memset(msg->msg_name +
+ offsetof(struct sockaddr_ll, sll_addr),
+ 0, sizeof(sll->sll_addr));
+ msg->msg_namelen = sizeof(struct sockaddr_ll);
+ }
}
- memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
- msg->msg_namelen);
+ memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len);
}
if (pkt_sk(sk)->auxdata) {
struct rds_sock *rs = rds_sk_to_rs(sk);
int ret = 0;
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
+
lock_sock(sk);
switch (uaddr->sa_family) {
/* We allow an RDS socket to be bound to either IPv4 or IPv6
* address.
*/
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
if (uaddr->sa_family == AF_INET) {
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
else
pool = rds_ibdev->mr_1m_pool;
+ if (atomic_read(&pool->dirty_count) >= pool->max_items / 10)
+ queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
+
+ /* Switch pools if one of the pool is reaching upper limit */
+ if (atomic_read(&pool->dirty_count) >= pool->max_items * 9 / 10) {
+ if (pool->pool_type == RDS_IB_MR_8K_POOL)
+ pool = rds_ibdev->mr_1m_pool;
+ else
+ pool = rds_ibdev->mr_8k_pool;
+ }
+
ibmr = rds_ib_try_reuse_ibmr(pool);
if (ibmr)
return ibmr;
struct rds_ib_mr *ibmr = NULL;
int iter = 0;
- if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10)
- queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
-
while (1) {
ibmr = rds_ib_reuse_mr(pool);
if (ibmr)
unsigned long frag_off;
unsigned long to_copy;
unsigned long copied;
- uint64_t uncongested = 0;
+ __le64 uncongested = 0;
void *addr;
/* catch completely corrupt packets */
copied = 0;
while (copied < RDS_CONG_MAP_BYTES) {
- uint64_t *src, *dst;
+ __le64 *src, *dst;
unsigned int k;
to_copy = min(RDS_FRAG_SIZE - frag_off, PAGE_SIZE - map_off);
}
/* the congestion map is in little endian order */
- uncongested = le64_to_cpu(uncongested);
-
- rds_cong_map_updated(map, uncongested);
+ rds_cong_map_updated(map, le64_to_cpu(uncongested));
}
static void rds_ib_process_recv(struct rds_connection *conn,
#include <linux/init.h>
static struct sk_buff_head loopback_queue;
+#define ROSE_LOOPBACK_LIMIT 1000
static struct timer_list loopback_timer;
static void rose_set_loopback_timer(void);
int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh)
{
- struct sk_buff *skbn;
+ struct sk_buff *skbn = NULL;
- skbn = skb_clone(skb, GFP_ATOMIC);
+ if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT)
+ skbn = skb_clone(skb, GFP_ATOMIC);
- kfree_skb(skb);
-
- if (skbn != NULL) {
+ if (skbn) {
+ consume_skb(skb);
skb_queue_tail(&loopback_queue, skbn);
if (!rose_loopback_running())
rose_set_loopback_timer();
+ } else {
+ kfree_skb(skb);
}
return 1;
}
-
static void rose_set_loopback_timer(void)
{
- del_timer(&loopback_timer);
-
- loopback_timer.expires = jiffies + 10;
- add_timer(&loopback_timer);
+ mod_timer(&loopback_timer, jiffies + 10);
}
static void rose_loopback_timer(struct timer_list *unused)
struct sock *sk;
unsigned short frametype;
unsigned int lci_i, lci_o;
+ int count;
- while ((skb = skb_dequeue(&loopback_queue)) != NULL) {
+ for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) {
+ skb = skb_dequeue(&loopback_queue);
+ if (!skb)
+ return;
if (skb->len < ROSE_MIN_LEN) {
kfree_skb(skb);
continue;
kfree_skb(skb);
}
}
+ if (!skb_queue_empty(&loopback_queue))
+ mod_timer(&loopback_timer, jiffies + 1);
}
void __exit rose_loopback_clear(void)
struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr;
struct rxrpc_local *local;
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
- u16 service_id = srx->srx_service;
+ u16 service_id;
int ret;
_enter("%p,%p,%d", rx, saddr, len);
ret = rxrpc_validate_address(rx, srx, len);
if (ret < 0)
goto error;
+ service_id = srx->srx_service;
lock_sock(&rx->sk);
* rxrpc_kernel_check_life - Check to see whether a call is still alive
* @sock: The socket the call is on
* @call: The call to check
+ * @_life: Where to store the life value
*
* Allow a kernel service to find out whether a call is still alive - ie. we're
- * getting ACKs from the server. Returns a number representing the life state
- * which can be compared to that returned by a previous call.
+ * getting ACKs from the server. Passes back in *_life a number representing
+ * the life state which can be compared to that returned by a previous call and
+ * return true if the call is still alive.
*
* If the life state stalls, rxrpc_kernel_probe_life() should be called and
* then 2RTT waited.
*/
-u32 rxrpc_kernel_check_life(const struct socket *sock,
- const struct rxrpc_call *call)
+bool rxrpc_kernel_check_life(const struct socket *sock,
+ const struct rxrpc_call *call,
+ u32 *_life)
{
- return call->acks_latest;
+ *_life = call->acks_latest;
+ return call->state != RXRPC_CALL_COMPLETE;
}
EXPORT_SYMBOL(rxrpc_kernel_check_life);
u8 ackr_reason; /* reason to ACK */
u16 ackr_skew; /* skew on packet being ACK'd */
rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */
+ rxrpc_serial_t ackr_first_seq; /* first sequence number received */
rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */
rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */
rxrpc_seq_t ackr_seen; /* Highest packet shown seen */
_enter("");
- if (list_empty(&rxnet->calls))
- return;
+ if (!list_empty(&rxnet->calls)) {
+ write_lock(&rxnet->call_lock);
- write_lock(&rxnet->call_lock);
+ while (!list_empty(&rxnet->calls)) {
+ call = list_entry(rxnet->calls.next,
+ struct rxrpc_call, link);
+ _debug("Zapping call %p", call);
- while (!list_empty(&rxnet->calls)) {
- call = list_entry(rxnet->calls.next, struct rxrpc_call, link);
- _debug("Zapping call %p", call);
+ rxrpc_see_call(call);
+ list_del_init(&call->link);
- rxrpc_see_call(call);
- list_del_init(&call->link);
+ pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
+ call, atomic_read(&call->usage),
+ rxrpc_call_states[call->state],
+ call->flags, call->events);
- pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
- call, atomic_read(&call->usage),
- rxrpc_call_states[call->state],
- call->flags, call->events);
+ write_unlock(&rxnet->call_lock);
+ cond_resched();
+ write_lock(&rxnet->call_lock);
+ }
write_unlock(&rxnet->call_lock);
- cond_resched();
- write_lock(&rxnet->call_lock);
}
- write_unlock(&rxnet->call_lock);
-
atomic_dec(&rxnet->nr_calls);
wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls));
}
* pass a connection-level abort onto all calls on that connection
*/
static void rxrpc_abort_calls(struct rxrpc_connection *conn,
- enum rxrpc_call_completion compl)
+ enum rxrpc_call_completion compl,
+ rxrpc_serial_t serial)
{
struct rxrpc_call *call;
int i;
call->call_id, 0,
conn->abort_code,
conn->error);
+ else
+ trace_rxrpc_rx_abort(call, serial,
+ conn->abort_code);
if (rxrpc_set_call_completion(call, compl,
conn->abort_code,
conn->error))
conn->state = RXRPC_CONN_LOCALLY_ABORTED;
spin_unlock_bh(&conn->state_lock);
- rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED);
-
msg.msg_name = &conn->params.peer->srx.transport;
msg.msg_namelen = conn->params.peer->srx.transport_len;
msg.msg_control = NULL;
len = iov[0].iov_len + iov[1].iov_len;
serial = atomic_inc_return(&conn->serial);
+ rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial);
whdr.serial = htonl(serial);
_proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code);
conn->error = -ECONNABORTED;
conn->abort_code = abort_code;
conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED);
+ rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
return -ECONNABORTED;
case RXRPC_PACKET_TYPE_CHALLENGE:
u8 acks[RXRPC_MAXACKS];
} buf;
rxrpc_serial_t acked_serial;
- rxrpc_seq_t first_soft_ack, hard_ack;
+ rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
int nr_acks, offset, ioffset;
_enter("");
acked_serial = ntohl(buf.ack.serial);
first_soft_ack = ntohl(buf.ack.firstPacket);
+ prev_pkt = ntohl(buf.ack.previousPacket);
hard_ack = first_soft_ack - 1;
nr_acks = buf.ack.nAcks;
summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ?
buf.ack.reason : RXRPC_ACK__INVALID);
trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial,
- first_soft_ack, ntohl(buf.ack.previousPacket),
+ first_soft_ack, prev_pkt,
summary.ack_reason, nr_acks);
if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE)
rxrpc_propose_ack_respond_to_ack);
}
- /* Discard any out-of-order or duplicate ACKs. */
- if (before_eq(sp->hdr.serial, call->acks_latest))
+ /* Discard any out-of-order or duplicate ACKs (outside lock). */
+ if (before(first_soft_ack, call->ackr_first_seq) ||
+ before(prev_pkt, call->ackr_prev_seq))
return;
buf.info.rxMTU = 0;
spin_lock(&call->input_lock);
- /* Discard any out-of-order or duplicate ACKs. */
- if (before_eq(sp->hdr.serial, call->acks_latest))
+ /* Discard any out-of-order or duplicate ACKs (inside lock). */
+ if (before(first_soft_ack, call->ackr_first_seq) ||
+ before(prev_pkt, call->ackr_prev_seq))
goto out;
call->acks_latest_ts = skb->tstamp;
call->acks_latest = sp->hdr.serial;
+ call->ackr_first_seq = first_soft_ack;
+ call->ackr_prev_seq = prev_pkt;
+
/* Parse rwind and mtu sizes if provided. */
if (buf.info.rxMTU)
rxrpc_input_ackinfo(call, skb, &buf.info);
* handle data received on the local endpoint
* - may be called in interrupt context
*
- * The socket is locked by the caller and this prevents the socket from being
- * shut down and the local endpoint from going away, thus sk_user_data will not
- * be cleared until this function returns.
+ * [!] Note that as this is called from the encap_rcv hook, the socket is not
+ * held locked by the caller and nothing prevents sk_user_data on the UDP from
+ * being cleared in the middle of processing this function.
*
* Called with the RCU read lock held from the IP layer via UDP.
*/
int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
{
+ struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk);
struct rxrpc_connection *conn;
struct rxrpc_channel *chan;
struct rxrpc_call *call = NULL;
struct rxrpc_skb_priv *sp;
- struct rxrpc_local *local = udp_sk->sk_user_data;
struct rxrpc_peer *peer = NULL;
struct rxrpc_sock *rx = NULL;
unsigned int channel;
_enter("%p", udp_sk);
+ if (unlikely(!local)) {
+ kfree_skb(skb);
+ return 0;
+ }
if (skb->tstamp == 0)
skb->tstamp = ktime_get_real();
ret = -ENOMEM;
sock_error:
mutex_unlock(&rxnet->local_mutex);
- kfree(local);
+ if (local)
+ call_rcu(&local->rcu, rxrpc_local_rcu);
_leave(" = %d", ret);
return ERR_PTR(ret);
_enter("%p{%d}", sk, local->debug_id);
+ /* Clear the outstanding error value on the socket so that it doesn't
+ * cause kernel_sendmsg() to return it later.
+ */
+ sock_error(sk);
+
skb = sock_dequeue_err_skb(sk);
if (!skb) {
_leave("UDP socket errqueue empty");
}
/*
- * Queue a DATA packet for transmission, set the resend timeout and send the
- * packet immediately
+ * Queue a DATA packet for transmission, set the resend timeout and send
+ * the packet immediately. Returns the error from rxrpc_send_data_packet()
+ * in case the caller wants to do something with it.
*/
-static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
- struct sk_buff *skb, bool last,
- rxrpc_notify_end_tx_t notify_end_tx)
+static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
+ struct sk_buff *skb, bool last,
+ rxrpc_notify_end_tx_t notify_end_tx)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
unsigned long now;
out:
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
- _leave("");
+ _leave(" = %d", ret);
+ return ret;
}
/*
if (ret < 0)
goto out;
- rxrpc_queue_packet(rx, call, skb,
- !msg_data_left(msg) && !more,
- notify_end_tx);
+ ret = rxrpc_queue_packet(rx, call, skb,
+ !msg_data_left(msg) && !more,
+ notify_end_tx);
+ /* Should check for failure here */
skb = NULL;
}
} while (msg_data_left(msg) > 0);
}
-/* Sent the next ASCONF packet currently stored in the association.
- * This happens after the ASCONF_ACK was succeffully processed.
- */
-static void sctp_cmd_send_asconf(struct sctp_association *asoc)
-{
- struct net *net = sock_net(asoc->base.sk);
-
- /* Send the next asconf chunk from the addip chunk
- * queue.
- */
- if (!list_empty(&asoc->addip_chunk_list)) {
- struct list_head *entry = asoc->addip_chunk_list.next;
- struct sctp_chunk *asconf = list_entry(entry,
- struct sctp_chunk, list);
- list_del_init(entry);
-
- /* Hold the chunk until an ASCONF_ACK is received. */
- sctp_chunk_hold(asconf);
- if (sctp_primitive_ASCONF(net, asoc, asconf))
- sctp_chunk_free(asconf);
- else
- asoc->addip_last_asconf = asconf;
- }
-}
-
-
/* These three macros allow us to pull the debugging code out of the
* main flow of sctp_do_sm() to keep attention focused on the real
* functionality there.
}
sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp);
break;
- case SCTP_CMD_SEND_NEXT_ASCONF:
- sctp_cmd_send_asconf(asoc);
- break;
case SCTP_CMD_PURGE_ASCONF_QUEUE:
sctp_asconf_queue_teardown(asoc);
break;
return SCTP_DISPOSITION_CONSUME;
}
+static enum sctp_disposition sctp_send_next_asconf(
+ struct net *net,
+ const struct sctp_endpoint *ep,
+ struct sctp_association *asoc,
+ const union sctp_subtype type,
+ struct sctp_cmd_seq *commands)
+{
+ struct sctp_chunk *asconf;
+ struct list_head *entry;
+
+ if (list_empty(&asoc->addip_chunk_list))
+ return SCTP_DISPOSITION_CONSUME;
+
+ entry = asoc->addip_chunk_list.next;
+ asconf = list_entry(entry, struct sctp_chunk, list);
+
+ list_del_init(entry);
+ sctp_chunk_hold(asconf);
+ asoc->addip_last_asconf = asconf;
+
+ return sctp_sf_do_prm_asconf(net, ep, asoc, type, asconf, commands);
+}
+
/*
* ADDIP Section 4.3 General rules for address manipulation
* When building TLV parameters for the ASCONF Chunk that will add or
SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
if (!sctp_process_asconf_ack((struct sctp_association *)asoc,
- asconf_ack)) {
- /* Successfully processed ASCONF_ACK. We can
- * release the next asconf if we have one.
- */
- sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF,
- SCTP_NULL());
- return SCTP_DISPOSITION_CONSUME;
- }
+ asconf_ack))
+ return sctp_send_next_asconf(net, ep,
+ (struct sctp_association *)asoc,
+ type, commands);
abort = sctp_make_abort(asoc, asconf_ack,
sizeof(struct sctp_errhdr));
}
/* Validate addr_len before calling common connect/connectx routine. */
- af = sctp_get_af_specific(addr->sa_family);
+ af = addr_len < offsetofend(struct sockaddr, sa_family) ? NULL :
+ sctp_get_af_specific(addr->sa_family);
if (!af || addr_len < af->sockaddr_len) {
err = -EINVAL;
} else {
if (sk->sk_state == SMC_CLOSED) {
if (smc->clcsock) {
- mutex_lock(&smc->clcsock_release_lock);
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- mutex_unlock(&smc->clcsock_release_lock);
+ release_sock(sk);
+ smc_clcsock_release(smc);
+ lock_sock(sk);
}
if (!smc->use_fallback)
smc_conn_free(&smc->conn);
link->peer_mtu = clc->qp_mtu;
}
+static void smc_switch_to_fallback(struct smc_sock *smc)
+{
+ smc->use_fallback = true;
+ if (smc->sk.sk_socket && smc->sk.sk_socket->file) {
+ smc->clcsock->file = smc->sk.sk_socket->file;
+ smc->clcsock->file->private_data = smc->clcsock;
+ }
+}
+
/* fall back during connect */
static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
{
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = reason_code;
smc_copy_sock_settings_to_clc(smc);
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_err = -rc;
out:
- if (smc->sk.sk_err)
- smc->sk.sk_state_change(&smc->sk);
- else
- smc->sk.sk_write_space(&smc->sk);
+ if (!sock_flag(&smc->sk, SOCK_DEAD)) {
+ if (smc->sk.sk_err) {
+ smc->sk.sk_state_change(&smc->sk);
+ } else { /* allow polling before and after fallback decision */
+ smc->clcsock->sk->sk_write_space(smc->clcsock->sk);
+ smc->sk.sk_write_space(&smc->sk);
+ }
+ }
kfree(smc->connect_info);
smc->connect_info = NULL;
release_sock(&smc->sk);
if (rc < 0)
lsk->sk_err = -rc;
if (rc < 0 || lsk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (new_clcsock)
sock_release(new_clcsock);
new_sk->sk_state = SMC_CLOSED;
sock_set_flag(new_sk, SOCK_DEAD);
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
*new_smc = NULL;
goto out;
smc_accept_unlink(new_sk);
if (new_sk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (isk->clcsock) {
sock_release(isk->clcsock);
isk->clcsock = NULL;
}
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
continue;
}
- if (new_sock)
+ if (new_sock) {
sock_graft(new_sk, new_sock);
+ if (isk->use_fallback) {
+ smc_sk(new_sk)->clcsock->file = new_sock->file;
+ isk->clcsock->file->private_data = isk->clcsock;
+ }
+ }
return new_sk;
}
return NULL;
sock_set_flag(sk, SOCK_DEAD);
sk->sk_shutdown |= SHUTDOWN_MASK;
}
+ sk->sk_prot->unhash(sk);
if (smc->clcsock) {
struct socket *tcp;
smc_conn_free(&smc->conn);
}
release_sock(sk);
- sk->sk_prot->unhash(sk);
sock_put(sk); /* final sock_put */
}
struct smc_sock *lsmc = new_smc->listen_smc;
struct sock *newsmcsk = &new_smc->sk;
- lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
if (lsmc->sk.sk_state == SMC_LISTEN) {
+ lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
smc_accept_enqueue(&lsmc->sk, newsmcsk);
+ release_sock(&lsmc->sk);
} else { /* no longer listening */
smc_close_non_accepted(newsmcsk);
}
- release_sock(&lsmc->sk);
/* Wake up accept */
lsmc->sk.sk_data_ready(&lsmc->sk);
return;
}
smc_conn_free(&new_smc->conn);
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = reason_code;
if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
if (smc_clc_send_decline(new_smc, reason_code) < 0) {
int rc = 0;
u8 ibport;
+ if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
+ return smc_listen_out_err(new_smc);
+
if (new_smc->use_fallback) {
smc_listen_out_connected(new_smc);
return;
/* check if peer is smc capable */
if (!tcp_sk(newclcsock->sk)->syn_smc) {
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
smc_listen_out_connected(new_smc);
return;
if (msg->msg_flags & MSG_FASTOPEN) {
if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
rc = -EINVAL;
case TCP_FASTOPEN_NO_COOKIE:
/* option not supported by SMC */
if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
if (!smc->use_fallback)
#define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME (5 * HZ)
+/* release the clcsock that is assigned to the smc_sock */
+void smc_clcsock_release(struct smc_sock *smc)
+{
+ struct socket *tcp;
+
+ if (smc->listen_smc && current_work() != &smc->smc_listen_work)
+ cancel_work_sync(&smc->smc_listen_work);
+ mutex_lock(&smc->clcsock_release_lock);
+ if (smc->clcsock) {
+ tcp = smc->clcsock;
+ smc->clcsock = NULL;
+ sock_release(tcp);
+ }
+ mutex_unlock(&smc->clcsock_release_lock);
+}
+
static void smc_close_cleanup_listen(struct sock *parent)
{
struct sock *sk;
close_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
struct smc_cdc_conn_state_flags *rxflags;
+ bool release_clcsock = false;
struct sock *sk = &smc->sk;
int old_state;
if ((sk->sk_state == SMC_CLOSED) &&
(sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
smc_conn_free(conn);
- if (smc->clcsock) {
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- }
+ if (smc->clcsock)
+ release_clcsock = true;
}
}
release_sock(sk);
+ if (release_clcsock)
+ smc_clcsock_release(smc);
sock_put(sk); /* sock_hold done by schedulers of close_work */
}
int smc_close_active(struct smc_sock *smc);
int smc_close_shutdown_write(struct smc_sock *smc);
void smc_close_init(struct smc_sock *smc);
+void smc_clcsock_release(struct smc_sock *smc);
#endif /* SMC_CLOSE_H */
INIT_LIST_HEAD(&smcd->vlan);
smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
WQ_MEM_RECLAIM, name);
+ if (!smcd->event_wq) {
+ kfree(smcd->conn);
+ kfree(smcd);
+ return NULL;
+ }
return smcd;
}
EXPORT_SYMBOL_GPL(smcd_alloc_dev);
{
struct net *net = genl_info_net(info);
- return smc_pnet_remove_by_pnetid(net, NULL);
+ smc_pnet_remove_by_pnetid(net, NULL);
+ return 0;
}
/* SMC_PNETID generic netlink operation definition */
/* We are going to append to the frags_list of head.
* Need to unshare the frag_list.
*/
- if (skb_has_frag_list(head)) {
- err = skb_unclone(head, GFP_ATOMIC);
- if (err) {
- STRP_STATS_INCR(strp->stats.mem_fail);
- desc->error = err;
- return 0;
- }
+ err = skb_unclone(head, GFP_ATOMIC);
+ if (err) {
+ STRP_STATS_INCR(strp->stats.mem_fail);
+ desc->error = err;
+ return 0;
}
if (unlikely(skb_shinfo(head)->frag_list)) {
h->last_refresh = now;
}
+static inline int cache_is_valid(struct cache_head *h);
static void cache_fresh_locked(struct cache_head *head, time_t expiry,
struct cache_detail *detail);
static void cache_fresh_unlocked(struct cache_head *head,
if (cache_is_expired(detail, tmp)) {
hlist_del_init_rcu(&tmp->cache_list);
detail->entries --;
+ if (cache_is_valid(tmp) == -EAGAIN)
+ set_bit(CACHE_NEGATIVE, &tmp->flags);
cache_fresh_locked(tmp, 0, detail);
freeme = tmp;
break;
* test first.
*/
if (rpc_task_transmitted(task)) {
- if (task->tk_status == 0)
- xprt_request_wait_receive(task);
+ task->tk_status = 0;
+ xprt_request_wait_receive(task);
return;
}
{
struct rpc_rqst *req = task->tk_rqstp;
+ if (rpc_task_transmitted(task))
+ task->tk_status = 0;
+
dprint_status(task);
switch (task->tk_status) {
__skb_queue_head_init(&list);
l->in_session = false;
+ /* Force re-synch of peer session number before establishing */
+ l->peer_session--;
l->session++;
l->mtu = l->advertised_mtu;
for (; i < TIPC_NAMETBL_SIZE; i++) {
head = &tn->nametbl->services[i];
- if (*last_type) {
+ if (*last_type ||
+ (!i && *last_key && (*last_lower == *last_key))) {
service = tipc_service_find(net, *last_type);
if (!service)
return -EPIPE;
#include <linux/sysctl.h>
+static int zero;
+static int one = 1;
static struct ctl_table_header *tipc_ctl_hdr;
static struct ctl_table tipc_table[] = {
.data = &sysctl_tipc_rmem,
.maxlen = sizeof(sysctl_tipc_rmem),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "named_timeout",
.data = &sysctl_tipc_named_timeout,
.maxlen = sizeof(sysctl_tipc_named_timeout),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "sk_filter",
static void tls_device_free_ctx(struct tls_context *ctx)
{
- if (ctx->tx_conf == TLS_HW)
+ if (ctx->tx_conf == TLS_HW) {
kfree(tls_offload_ctx_tx(ctx));
+ kfree(ctx->tx.rec_seq);
+ kfree(ctx->tx.iv);
+ }
if (ctx->rx_conf == TLS_HW)
kfree(tls_offload_ctx_rx(ctx));
}
EXPORT_SYMBOL(tls_device_sk_destruct);
+void tls_device_free_resources_tx(struct sock *sk)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+
+ tls_free_partial_record(sk, tls_ctx);
+}
+
static void tls_append_frag(struct tls_record_info *record,
struct page_frag *pfrag,
int size)
static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
{
struct strp_msg *rxm = strp_msg(skb);
- int err = 0, offset = rxm->offset, copy, nsg;
+ int err = 0, offset = rxm->offset, copy, nsg, data_len, pos;
struct sk_buff *skb_iter, *unused;
struct scatterlist sg[1];
char *orig_buf, *buf;
else
err = 0;
- copy = min_t(int, skb_pagelen(skb) - offset,
- rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+ data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE;
- if (skb->decrypted)
- skb_store_bits(skb, offset, buf, copy);
+ if (skb_pagelen(skb) > offset) {
+ copy = min_t(int, skb_pagelen(skb) - offset, data_len);
- offset += copy;
- buf += copy;
+ if (skb->decrypted)
+ skb_store_bits(skb, offset, buf, copy);
+
+ offset += copy;
+ buf += copy;
+ }
+ pos = skb_pagelen(skb);
skb_walk_frags(skb, skb_iter) {
- copy = min_t(int, skb_iter->len,
- rxm->full_len - offset + rxm->offset -
- TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+ int frag_pos;
+
+ /* Practically all frags must belong to msg if reencrypt
+ * is needed with current strparser and coalescing logic,
+ * but strparser may "get optimized", so let's be safe.
+ */
+ if (pos + skb_iter->len <= offset)
+ goto done_with_frag;
+ if (pos >= data_len + rxm->offset)
+ break;
+
+ frag_pos = offset - pos;
+ copy = min_t(int, skb_iter->len - frag_pos,
+ data_len + rxm->offset - offset);
if (skb_iter->decrypted)
- skb_store_bits(skb_iter, offset, buf, copy);
+ skb_store_bits(skb_iter, frag_pos, buf, copy);
offset += copy;
buf += copy;
+done_with_frag:
+ pos += skb_iter->len;
}
free_buf:
goto release_netdev;
free_sw_resources:
+ up_read(&device_offload_lock);
tls_sw_free_resources_rx(sk);
+ down_read(&device_offload_lock);
release_ctx:
ctx->priv_ctx_rx = NULL;
release_netdev:
}
out:
up_read(&device_offload_lock);
- kfree(tls_ctx->rx.rec_seq);
- kfree(tls_ctx->rx.iv);
tls_sw_release_resources_rx(sk);
}
static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
{
+ struct sock *sk = skb->sk;
+ int delta;
+
skb_copy_header(nskb, skb);
skb_put(nskb, skb->len);
memcpy(nskb->data, skb->data, headln);
- update_chksum(nskb, headln);
nskb->destructor = skb->destructor;
- nskb->sk = skb->sk;
+ nskb->sk = sk;
skb->destructor = NULL;
skb->sk = NULL;
- refcount_add(nskb->truesize - skb->truesize,
- &nskb->sk->sk_wmem_alloc);
+
+ update_chksum(nskb, headln);
+
+ delta = nskb->truesize - skb->truesize;
+ if (likely(delta < 0))
+ WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
+ else if (delta)
+ refcount_add(delta, &sk->sk_wmem_alloc);
}
/* This function may be called after the user socket is already
return tls_push_sg(sk, ctx, sg, offset, flags);
}
+bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx)
+{
+ struct scatterlist *sg;
+
+ sg = ctx->partially_sent_record;
+ if (!sg)
+ return false;
+
+ while (1) {
+ put_page(sg_page(sg));
+ sk_mem_uncharge(sk, sg->length);
+
+ if (sg_is_last(sg))
+ break;
+ sg++;
+ }
+ ctx->partially_sent_record = NULL;
+ return true;
+}
+
static void tls_write_space(struct sock *sk)
{
struct tls_context *ctx = tls_get_ctx(sk);
kfree(ctx->tx.rec_seq);
kfree(ctx->tx.iv);
tls_sw_free_resources_tx(sk);
+#ifdef CONFIG_TLS_DEVICE
+ } else if (ctx->tx_conf == TLS_HW) {
+ tls_device_free_resources_tx(sk);
+#endif
}
- if (ctx->rx_conf == TLS_SW) {
- kfree(ctx->rx.rec_seq);
- kfree(ctx->rx.iv);
+ if (ctx->rx_conf == TLS_SW)
tls_sw_free_resources_rx(sk);
- }
#ifdef CONFIG_TLS_DEVICE
if (ctx->rx_conf == TLS_HW)
/* Free up un-sent records in tx_list. First, free
* the partially sent record if any at head of tx_list.
*/
- if (tls_ctx->partially_sent_record) {
- struct scatterlist *sg = tls_ctx->partially_sent_record;
-
- while (1) {
- put_page(sg_page(sg));
- sk_mem_uncharge(sk, sg->length);
-
- if (sg_is_last(sg))
- break;
- sg++;
- }
-
- tls_ctx->partially_sent_record = NULL;
-
+ if (tls_free_partial_record(sk, tls_ctx)) {
rec = list_first_entry(&ctx->tx_list,
struct tls_rec, list);
list_del(&rec->list);
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+ kfree(tls_ctx->rx.rec_seq);
+ kfree(tls_ctx->rx.iv);
+
if (ctx->aead_recv) {
kfree_skb(ctx->recv_pkt);
ctx->recv_pkt = NULL;
.policy = nl80211_policy,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEAUTHENTICATE,
.policy = nl80211_policy,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS,
.policy = nl80211_policy,
.flags = GENL_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DISCONNECT,
.policy = nl80211_policy,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEL_PMKSA,
.policy = nl80211_policy,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_WIPHY |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_SET_QOS_MAP,
.doit = nl80211_set_pmk,
.policy = nl80211_policy,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEL_PMK,
return dfs_region1;
}
+static void reg_wmm_rules_intersect(const struct ieee80211_wmm_ac *wmm_ac1,
+ const struct ieee80211_wmm_ac *wmm_ac2,
+ struct ieee80211_wmm_ac *intersect)
+{
+ intersect->cw_min = max_t(u16, wmm_ac1->cw_min, wmm_ac2->cw_min);
+ intersect->cw_max = max_t(u16, wmm_ac1->cw_max, wmm_ac2->cw_max);
+ intersect->cot = min_t(u16, wmm_ac1->cot, wmm_ac2->cot);
+ intersect->aifsn = max_t(u8, wmm_ac1->aifsn, wmm_ac2->aifsn);
+}
+
/*
* Helper for regdom_intersect(), this does the real
* mathematical intersection fun
struct ieee80211_freq_range *freq_range;
const struct ieee80211_power_rule *power_rule1, *power_rule2;
struct ieee80211_power_rule *power_rule;
+ const struct ieee80211_wmm_rule *wmm_rule1, *wmm_rule2;
+ struct ieee80211_wmm_rule *wmm_rule;
u32 freq_diff, max_bandwidth1, max_bandwidth2;
freq_range1 = &rule1->freq_range;
power_rule2 = &rule2->power_rule;
power_rule = &intersected_rule->power_rule;
+ wmm_rule1 = &rule1->wmm_rule;
+ wmm_rule2 = &rule2->wmm_rule;
+ wmm_rule = &intersected_rule->wmm_rule;
+
freq_range->start_freq_khz = max(freq_range1->start_freq_khz,
freq_range2->start_freq_khz);
freq_range->end_freq_khz = min(freq_range1->end_freq_khz,
intersected_rule->dfs_cac_ms = max(rule1->dfs_cac_ms,
rule2->dfs_cac_ms);
+ if (rule1->has_wmm && rule2->has_wmm) {
+ u8 ac;
+
+ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+ reg_wmm_rules_intersect(&wmm_rule1->client[ac],
+ &wmm_rule2->client[ac],
+ &wmm_rule->client[ac]);
+ reg_wmm_rules_intersect(&wmm_rule1->ap[ac],
+ &wmm_rule2->ap[ac],
+ &wmm_rule->ap[ac]);
+ }
+
+ intersected_rule->has_wmm = true;
+ } else if (rule1->has_wmm) {
+ *wmm_rule = *wmm_rule1;
+ intersected_rule->has_wmm = true;
+ } else if (rule2->has_wmm) {
+ *wmm_rule = *wmm_rule2;
+ intersected_rule->has_wmm = true;
+ } else {
+ intersected_rule->has_wmm = false;
+ }
+
if (!is_valid_reg_rule(intersected_rule))
return -EINVAL;
/*
* The last request may have been received before this
* registration call. Call the driver notifier if
- * initiator is USER and user type is CELL_BASE.
+ * initiator is USER.
*/
- if (lr->initiator == NL80211_REGDOM_SET_BY_USER &&
- lr->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE)
+ if (lr->initiator == NL80211_REGDOM_SET_BY_USER)
reg_call_notifier(wiphy, lr);
}
/* copy subelement as we need to change its content to
* mark an ie after it is processed.
*/
- sub_copy = kmalloc(subie_len, gfp);
+ sub_copy = kmemdup(subelement, subie_len, gfp);
if (!sub_copy)
return 0;
- memcpy(sub_copy, subelement, subie_len);
pos = &new_ie[0];
else if (rate->bw == RATE_INFO_BW_HE_RU &&
rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26)
result = rates_26[rate->he_gi];
- else if (WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
- rate->bw, rate->he_ru_alloc))
+ else {
+ WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
+ rate->bw, rate->he_ru_alloc);
return 0;
+ }
/* now scale to the appropriate MCS */
tmp = result;
return NULL;
}
-static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb)
+static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb,
+ unsigned short family)
{
struct xfrmi_net *xfrmn;
- int ifindex;
struct xfrm_if *xi;
+ int ifindex = 0;
if (!secpath_exists(skb) || !skb->dev)
return NULL;
+ switch (family) {
+ case AF_INET6:
+ ifindex = inet6_sdif(skb);
+ break;
+ case AF_INET:
+ ifindex = inet_sdif(skb);
+ break;
+ }
+ if (!ifindex)
+ ifindex = skb->dev->ifindex;
+
xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id);
- ifindex = skb->dev->ifindex;
for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
if (ifindex == xi->dev->ifindex &&
ifcb = xfrm_if_get_cb();
if (ifcb) {
- xi = ifcb->decode_session(skb);
+ xi = ifcb->decode_session(skb, family);
if (xi) {
if_id = xi->p.if_id;
net = xi->net;
static void ___xfrm_state_destroy(struct xfrm_state *x)
{
- tasklet_hrtimer_cancel(&x->mtimer);
+ hrtimer_cancel(&x->mtimer);
del_timer_sync(&x->rtimer);
kfree(x->aead);
kfree(x->aalg);
static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
{
- struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
- struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
+ struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer);
+ enum hrtimer_restart ret = HRTIMER_NORESTART;
time64_t now = ktime_get_real_seconds();
time64_t next = TIME64_MAX;
int warn = 0;
km_state_expired(x, 0, 0);
resched:
if (next != TIME64_MAX) {
- tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
+ hrtimer_forward_now(&x->mtimer, ktime_set(next, 0));
+ ret = HRTIMER_RESTART;
}
goto out;
out:
spin_unlock(&x->lock);
- return HRTIMER_NORESTART;
+ return ret;
}
static void xfrm_replay_timer_handler(struct timer_list *t);
INIT_HLIST_NODE(&x->bydst);
INIT_HLIST_NODE(&x->bysrc);
INIT_HLIST_NODE(&x->byspi);
- tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler,
- CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
+ hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT);
+ x->mtimer.function = xfrm_timer_handler;
timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0);
x->curlft.add_time = ktime_get_real_seconds();
x->lft.soft_byte_limit = XFRM_INF;
hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
}
x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
- tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+ hrtimer_start(&x->mtimer,
+ ktime_set(net->xfrm.sysctl_acq_expires, 0),
+ HRTIMER_MODE_REL_SOFT);
net->xfrm.state_num++;
xfrm_hash_grow_check(net, x->bydst.next != NULL);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
}
- tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+ hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
if (x->replay_maxage)
mod_timer(&x->rtimer, jiffies + x->replay_maxage);
x->mark.m = m->m;
x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
xfrm_state_hold(x);
- tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+ hrtimer_start(&x->mtimer,
+ ktime_set(net->xfrm.sysctl_acq_expires, 0),
+ HRTIMER_MODE_REL_SOFT);
list_add(&x->km.all, &net->xfrm.state_all);
hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
h = xfrm_src_hash(net, daddr, saddr, family);
memcpy(&x1->lft, &x->lft, sizeof(x1->lft));
x1->km.dying = 0;
- tasklet_hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+ hrtimer_start(&x1->mtimer, ktime_set(1, 0),
+ HRTIMER_MODE_REL_SOFT);
if (x1->curlft.use_time)
xfrm_state_check_expire(x1);
if (x->curlft.bytes >= x->lft.hard_byte_limit ||
x->curlft.packets >= x->lft.hard_packet_limit) {
x->km.state = XFRM_STATE_EXPIRED;
- tasklet_hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL);
+ hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT);
return -EINVAL;
}
flush_work(&net->xfrm.state_hash_work);
flush_work(&xfrm_state_gc_work);
- xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
+ xfrm_state_flush(net, 0, false, true);
WARN_ON(!list_empty(&net->xfrm.state_all));
ret = verify_policy_dir(p->dir);
if (ret)
return ret;
- if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir))
+ if (p->index && (xfrm_policy_id2dir(p->index) != p->dir))
return -EINVAL;
return 0;
return -EINVAL;
}
- switch (ut[i].id.proto) {
- case IPPROTO_AH:
- case IPPROTO_ESP:
- case IPPROTO_COMP:
-#if IS_ENABLED(CONFIG_IPV6)
- case IPPROTO_ROUTING:
- case IPPROTO_DSTOPTS:
-#endif
- case IPSEC_PROTO_ANY:
- break;
- default:
+ if (!xfrm_id_proto_valid(ut[i].id.proto))
return -EINVAL;
- }
-
}
return 0;
ifdef CONFIG_RETPOLINE
objtool_args += --retpoline
endif
+ifdef CONFIG_X86_SMAP
+ objtool_args += --uaccess
+endif
# 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory
# 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file
CFLAGS_UBSAN += $(call cc-option, -fsanitize=shift)
CFLAGS_UBSAN += $(call cc-option, -fsanitize=integer-divide-by-zero)
CFLAGS_UBSAN += $(call cc-option, -fsanitize=unreachable)
- CFLAGS_UBSAN += $(call cc-option, -fsanitize=vla-bound)
CFLAGS_UBSAN += $(call cc-option, -fsanitize=signed-integer-overflow)
CFLAGS_UBSAN += $(call cc-option, -fsanitize=bounds)
CFLAGS_UBSAN += $(call cc-option, -fsanitize=object-size)
gen-atomic-fallback.sh linux/atomic-fallback.h
EOF
while read script header; do
- ${ATOMICDIR}/${script} ${ATOMICTBL} > ${LINUXDIR}/include/${header}
+ /bin/sh ${ATOMICDIR}/${script} ${ATOMICTBL} > ${LINUXDIR}/include/${header}
HASH="$(sha1sum ${LINUXDIR}/include/${header})"
HASH="${HASH%% *}"
printf "// %s\n" "${HASH}" >> ${LINUXDIR}/include/${header}
#include <string.h>
#include <errno.h>
#include <ctype.h>
-#include <sys/socket.h>
struct security_class_mapping {
const char *name;
#include <stdlib.h>
#include <unistd.h>
#include <string.h>
-#include <sys/socket.h>
static void usage(char *name)
{
return 0;
}
-static void aafs_evict_inode(struct inode *inode)
+static void aafs_i_callback(struct rcu_head *head)
{
- truncate_inode_pages_final(&inode->i_data);
- clear_inode(inode);
+ struct inode *inode = container_of(head, struct inode, i_rcu);
if (S_ISLNK(inode->i_mode))
kfree(inode->i_link);
+ free_inode_nonrcu(inode);
+}
+
+static void aafs_destroy_inode(struct inode *inode)
+{
+ call_rcu(&inode->i_rcu, aafs_i_callback);
}
static const struct super_operations aafs_super_ops = {
.statfs = simple_statfs,
- .evict_inode = aafs_evict_inode,
+ .destroy_inode = aafs_destroy_inode,
.show_path = aafs_show_path,
};
devcg->behavior == DEVCG_DEFAULT_ALLOW) {
rc = dev_exception_add(devcg, ex);
if (rc)
- break;
+ return rc;
} else {
/*
* in the other possible cases:
static struct vfsmount *mount;
static int mount_count;
-static void securityfs_evict_inode(struct inode *inode)
+static void securityfs_i_callback(struct rcu_head *head)
{
- truncate_inode_pages_final(&inode->i_data);
- clear_inode(inode);
+ struct inode *inode = container_of(head, struct inode, i_rcu);
if (S_ISLNK(inode->i_mode))
kfree(inode->i_link);
+ free_inode_nonrcu(inode);
+}
+
+static void securityfs_destroy_inode(struct inode *inode)
+{
+ call_rcu(&inode->i_rcu, securityfs_i_callback);
}
static const struct super_operations securityfs_super_operations = {
.statfs = simple_statfs,
- .evict_inode = securityfs_evict_inode,
+ .destroy_inode = securityfs_destroy_inode,
};
static int fill_super(struct super_block *sb, void *data, int silent)
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/capability.h>
+#include <linux/socket.h>
#define COMMON_FILE_SOCK_PERMS "ioctl", "read", "write", "create", \
"getattr", "setattr", "lock", "relabelfrom", "relabelto", "append", "map"
INIT_LIST_HEAD(&entry->list);
entry->parent = parent;
entry->module = module;
- if (parent)
+ if (parent) {
+ mutex_lock(&parent->access);
list_add_tail(&entry->list, &parent->children);
+ mutex_unlock(&parent->access);
+ }
return entry;
}
list_for_each_entry_safe(p, n, &entry->children, list)
snd_info_free_entry(p);
- list_del(&entry->list);
+ p = entry->parent;
+ if (p) {
+ mutex_lock(&p->access);
+ list_del(&entry->list);
+ mutex_unlock(&p->access);
+ }
kfree(entry->name);
if (entry->private_free)
entry->private_free(entry);
card->shutdown = 1;
spin_unlock(&card->files_lock);
- /* phase 1: disable fops (user space) operations for ALSA API */
- mutex_lock(&snd_card_mutex);
- snd_cards[card->number] = NULL;
- clear_bit(card->number, snd_cards_lock);
- mutex_unlock(&snd_card_mutex);
-
- /* phase 2: replace file->f_op with special dummy operations */
-
+ /* replace file->f_op with special dummy operations */
spin_lock(&card->files_lock);
list_for_each_entry(mfile, &card->files_list, list) {
/* it's critical part, use endless loop */
}
spin_unlock(&card->files_lock);
- /* phase 3: notify all connected devices about disconnection */
+ /* notify all connected devices about disconnection */
/* at this point, they cannot respond to any calls except release() */
#if IS_ENABLED(CONFIG_SND_MIXER_OSS)
device_del(&card->card_dev);
card->registered = false;
}
+
+ /* disable fops (user space) operations for ALSA API */
+ mutex_lock(&snd_card_mutex);
+ snd_cards[card->number] = NULL;
+ clear_bit(card->number, snd_cards_lock);
+ mutex_unlock(&snd_card_mutex);
+
#ifdef CONFIG_PM
wake_up(&card->power_sleep);
#endif
/* power-up all before initialization */
hda_set_power_state(codec, AC_PWRST_D0);
+ codec->core.dev.power.power_state = PMSG_ON;
snd_hda_codec_proc_new(codec);
return;
spec->gen.preferred_dacs = preferred_pairs;
+ spec->gen.auto_mute_via_amp = 1;
+ codec->power_save_node = 0;
}
/* The DAC of NID 0x3 will introduce click/pop noise on headphones, so invalidate it */
{0x12, 0x90a60140},
{0x14, 0x90170150},
{0x21, 0x02211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x21, 0x02211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x12, 0x40000000},
+ {0x14, 0x90170110},
+ {0x21, 0x02211020}),
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
{0x14, 0x90170110},
{0x21, 0x02211020}),
{0x21, 0x0221101f}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC256_STANDARD_PINS),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x14, 0x90170110},
+ {0x1b, 0x01011020},
+ {0x21, 0x0221101f}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC,
{0x14, 0x90170110},
{0x1b, 0x90a70130},
{0x12, 0x90a60130},
{0x17, 0x90170110},
{0x21, 0x04211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC294_FIXUP_ASUS_SPK,
+ {0x12, 0x90a60130},
+ {0x17, 0x90170110},
+ {0x21, 0x03211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x14, 0x90170110},
+ {0x21, 0x04211020}),
SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC295_STANDARD_PINS,
{0x17, 0x21014020},
{
struct usb_device *usbdev = line6->usbdev;
int ret;
- unsigned char len;
+ unsigned char *len;
unsigned count;
if (address > 0xffff || datalen > 0xff)
return -EINVAL;
+ len = kmalloc(sizeof(*len), GFP_KERNEL);
+ if (!len)
+ return -ENOMEM;
+
/* query the serial number: */
ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67,
USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
if (ret < 0) {
dev_err(line6->ifcdev, "read request failed (error %d)\n", ret);
- return ret;
+ goto exit;
}
/* Wait for data length. We'll get 0xff until length arrives. */
ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67,
USB_TYPE_VENDOR | USB_RECIP_DEVICE |
USB_DIR_IN,
- 0x0012, 0x0000, &len, 1,
+ 0x0012, 0x0000, len, 1,
LINE6_TIMEOUT * HZ);
if (ret < 0) {
dev_err(line6->ifcdev,
"receive length failed (error %d)\n", ret);
- return ret;
+ goto exit;
}
- if (len != 0xff)
+ if (*len != 0xff)
break;
}
- if (len == 0xff) {
+ ret = -EIO;
+ if (*len == 0xff) {
dev_err(line6->ifcdev, "read failed after %d retries\n",
count);
- return -EIO;
- } else if (len != datalen) {
+ goto exit;
+ } else if (*len != datalen) {
/* should be equal or something went wrong */
dev_err(line6->ifcdev,
"length mismatch (expected %d, got %d)\n",
- (int)datalen, (int)len);
- return -EIO;
+ (int)datalen, (int)*len);
+ goto exit;
}
/* receive the result: */
0x0013, 0x0000, data, datalen,
LINE6_TIMEOUT * HZ);
- if (ret < 0) {
+ if (ret < 0)
dev_err(line6->ifcdev, "read failed (error %d)\n", ret);
- return ret;
- }
- return 0;
+exit:
+ kfree(len);
+ return ret;
}
EXPORT_SYMBOL_GPL(line6_read_data);
{
struct usb_device *usbdev = line6->usbdev;
int ret;
- unsigned char status;
+ unsigned char *status;
int count;
if (address > 0xffff || datalen > 0xffff)
return -EINVAL;
+ status = kmalloc(sizeof(*status), GFP_KERNEL);
+ if (!status)
+ return -ENOMEM;
+
ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67,
USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
0x0022, address, data, datalen,
if (ret < 0) {
dev_err(line6->ifcdev,
"write request failed (error %d)\n", ret);
- return ret;
+ goto exit;
}
for (count = 0; count < LINE6_READ_WRITE_MAX_RETRIES; count++) {
USB_TYPE_VENDOR | USB_RECIP_DEVICE |
USB_DIR_IN,
0x0012, 0x0000,
- &status, 1, LINE6_TIMEOUT * HZ);
+ status, 1, LINE6_TIMEOUT * HZ);
if (ret < 0) {
dev_err(line6->ifcdev,
"receiving status failed (error %d)\n", ret);
- return ret;
+ goto exit;
}
- if (status != 0xff)
+ if (*status != 0xff)
break;
}
- if (status == 0xff) {
+ if (*status == 0xff) {
dev_err(line6->ifcdev, "write failed after %d retries\n",
count);
- return -EIO;
- } else if (status != 0) {
+ ret = -EIO;
+ } else if (*status != 0) {
dev_err(line6->ifcdev, "write failed (error %d)\n", ret);
- return -EIO;
+ ret = -EIO;
}
-
- return 0;
+exit:
+ kfree(status);
+ return ret;
}
EXPORT_SYMBOL_GPL(line6_write_data);
static int podhd_dev_start(struct usb_line6_podhd *pod)
{
int ret;
- u8 init_bytes[8];
+ u8 *init_bytes;
int i;
struct usb_device *usbdev = pod->line6.usbdev;
+ init_bytes = kmalloc(8, GFP_KERNEL);
+ if (!init_bytes)
+ return -ENOMEM;
+
ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0),
0x67, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
0x11, 0,
NULL, 0, LINE6_TIMEOUT * HZ);
if (ret < 0) {
dev_err(pod->line6.ifcdev, "read request failed (error %d)\n", ret);
- return ret;
+ goto exit;
}
/* NOTE: looks like some kind of ping message */
ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67,
USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
0x11, 0x0,
- &init_bytes, 3, LINE6_TIMEOUT * HZ);
+ init_bytes, 3, LINE6_TIMEOUT * HZ);
if (ret < 0) {
dev_err(pod->line6.ifcdev,
"receive length failed (error %d)\n", ret);
- return ret;
+ goto exit;
}
pod->firmware_version =
for (i = 0; i <= 16; i++) {
ret = line6_read_data(&pod->line6, 0xf000 + 0x08 * i, init_bytes, 8);
if (ret < 0)
- return ret;
+ goto exit;
}
ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0),
USB_TYPE_STANDARD | USB_RECIP_DEVICE | USB_DIR_OUT,
1, 0,
NULL, 0, LINE6_TIMEOUT * HZ);
- if (ret < 0)
- return ret;
-
- return 0;
+exit:
+ kfree(init_bytes);
+ return ret;
}
static void podhd_startup_workqueue(struct work_struct *work)
/*
Setup Toneport device.
*/
-static void toneport_setup(struct usb_line6_toneport *toneport)
+static int toneport_setup(struct usb_line6_toneport *toneport)
{
- u32 ticks;
+ u32 *ticks;
struct usb_line6 *line6 = &toneport->line6;
struct usb_device *usbdev = line6->usbdev;
+ ticks = kmalloc(sizeof(*ticks), GFP_KERNEL);
+ if (!ticks)
+ return -ENOMEM;
+
/* sync time on device with host: */
/* note: 32-bit timestamps overflow in year 2106 */
- ticks = (u32)ktime_get_real_seconds();
- line6_write_data(line6, 0x80c6, &ticks, 4);
+ *ticks = (u32)ktime_get_real_seconds();
+ line6_write_data(line6, 0x80c6, ticks, 4);
+ kfree(ticks);
/* enable device: */
toneport_send_cmd(usbdev, 0x0301, 0x0000);
toneport_update_led(toneport);
mod_timer(&toneport->timer, jiffies + TONEPORT_PCM_DELAY * HZ);
+ return 0;
}
/*
return err;
}
- toneport_setup(toneport);
+ err = toneport_setup(toneport);
+ if (err)
+ return err;
/* register audio system: */
return snd_card_register(line6->card);
*/
static int toneport_reset_resume(struct usb_interface *interface)
{
- toneport_setup(usb_get_intfdata(interface));
+ int err;
+
+ err = toneport_setup(usb_get_intfdata(interface));
+ if (err)
+ return err;
return line6_resume(interface);
}
#endif
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/******** no-legacy-syscalls-ABI *******/
+
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
+#define _UAPI_ASM_ARC_UNISTD_H
+
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#define sys_mmap2 sys_mmap_pgoff
+
+#include <asm-generic/unistd.h>
+
+#define NR_syscalls __NR_syscalls
+
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs (__NR_arch_specific_syscall + 3)
+
+/* ARC specific syscall */
+#define __NR_cacheflush (__NR_arch_specific_syscall + 0)
+#define __NR_arc_settls (__NR_arch_specific_syscall + 1)
+#define __NR_arc_gettls (__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg (__NR_arch_specific_syscall + 4)
+
+__SYSCALL(__NR_cacheflush, sys_cacheflush)
+__SYSCALL(__NR_arc_settls, sys_arc_settls)
+__SYSCALL(__NR_arc_gettls, sys_arc_gettls)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
+__SYSCALL(__NR_sysfs, sys_sysfs)
+
+#undef __SYSCALL
+
+#endif
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Syscall support for Hexagon
+ *
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+/*
+ * The kernel pulls this unistd.h in three different ways:
+ * 1. the "normal" way which gets all the __NR defines
+ * 2. with __SYSCALL defined to produce function declarations
+ * 3. with __SYSCALL defined to produce syscall table initialization
+ * See also: syscalltab.c
+ */
+
+#define sys_mmap2 sys_mmap_pgoff
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#include <asm-generic/unistd.h>
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2018 David Abdurachmanov <david.abdurachmanov@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifdef __LP64__
+#define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#endif /* __LP64__ */
+
+#include <asm-generic/unistd.h>
+
+/*
+ * Allows the instruction cache to be flushed from userspace. Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart. There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller. We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#ifndef __NR_riscv_flush_icache
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+#endif
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
+#define VMX_ABORT_VMCS_CORRUPTED 3
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
return -1;
}
NEXT_ARG();
+ } else {
+ p_err("unknown arg %s", *argv);
+ return -1;
}
}
sdt \
setns \
libaio \
+ libzstd \
disassembler-four-args
# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
get_cpuid \
bpf \
libaio \
+ libzstd \
disassembler-four-args
# Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
test-clang.bin \
test-llvm.bin \
test-llvm-version.bin \
- test-libaio.bin
+ test-libaio.bin \
+ test-libzstd.bin
FILES := $(addprefix $(OUTPUT),$(FILES))
$(OUTPUT)test-libaio.bin:
$(BUILD) -lrt
+$(OUTPUT)test-libzstd.bin:
+ $(BUILD) -lzstd
+
###############################
clean:
# include "test-disassembler-four-args.c"
#undef main
+#define main main_test_zstd
+# include "test-libzstd.c"
+#undef main
+
int main(int argc, char *argv[])
{
main_test_libpython();
main_test_libaio();
main_test_reallocarray();
main_test_disassembler_four_args();
+ main_test_libzstd();
return 0;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <zstd.h>
+
+int main(void)
+{
+ ZSTD_CStream *cstream;
+
+ cstream = ZSTD_createCStream();
+ ZSTD_freeCStream(cstream);
+
+ return 0;
+}
#ifndef __KERNEL__
#include <stdlib.h>
+#include <time.h>
#endif
/*
libbpf_version.h
FEATURE-DUMP.libbpf
test_libbpf
+libbpf.so.*
#include "event-parse-local.h"
#include "event-utils.h"
+/**
+ * tep_get_event - returns the event with the given index
+ * @tep: a handle to the tep_handle
+ * @index: index of the requested event, in the range 0 .. nr_events
+ *
+ * This returns pointer to the element of the events array with the given index
+ * If @tep is NULL, or @index is not in the range 0 .. nr_events, NULL is returned.
+ */
+struct tep_event *tep_get_event(struct tep_handle *tep, int index)
+{
+ if (tep && tep->events && index < tep->nr_events)
+ return tep->events[index];
+
+ return NULL;
+}
+
/**
* tep_get_first_event - returns the first event in the events array
* @tep: a handle to the tep_handle
*/
struct tep_event *tep_get_first_event(struct tep_handle *tep)
{
- if (tep && tep->events)
- return tep->events[0];
-
- return NULL;
+ return tep_get_event(tep, 0);
}
/**
*/
int tep_get_events_count(struct tep_handle *tep)
{
- if(tep)
+ if (tep)
return tep->nr_events;
return 0;
}
* @flag: flag, or combination of flags to be set
* can be any combination from enum tep_flag
*
- * This sets a flag or mbination of flags from enum tep_flag
- */
+ * This sets a flag or combination of flags from enum tep_flag
+ */
void tep_set_flag(struct tep_handle *tep, int flag)
{
- if(tep)
+ if (tep)
tep->flags |= flag;
}
-unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data)
+/**
+ * tep_clear_flag - clear event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be cleared
+ *
+ * This clears a tep flag
+ */
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+ if (tep)
+ tep->flags &= ~flag;
+}
+
+/**
+ * tep_test_flag - check the state of event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be checked
+ *
+ * This returns the state of the requested tep flag.
+ * Returns: true if the flag is set, false otherwise.
+ */
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+ if (tep)
+ return tep->flags & flag;
+ return false;
+}
+
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data)
{
unsigned short swap;
- if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+ if (!tep || tep->host_bigendian == tep->file_bigendian)
return data;
swap = ((data & 0xffULL) << 8) |
return swap;
}
-unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data)
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data)
{
unsigned int swap;
- if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+ if (!tep || tep->host_bigendian == tep->file_bigendian)
return data;
swap = ((data & 0xffULL) << 24) |
}
unsigned long long
-tep_data2host8(struct tep_handle *pevent, unsigned long long data)
+tep_data2host8(struct tep_handle *tep, unsigned long long data)
{
unsigned long long swap;
- if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+ if (!tep || tep->host_bigendian == tep->file_bigendian)
return data;
swap = ((data & 0xffULL) << 56) |
/**
* tep_get_header_page_size - get size of the header page
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
*
* This returns size of the header page
- * If @pevent is NULL, 0 is returned.
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_header_page_size(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->header_page_size_size;
+ return 0;
+}
+
+/**
+ * tep_get_header_timestamp_size - get size of the timestamp in the header page
+ * @tep: a handle to the tep_handle
+ *
+ * This returns size of the timestamp in the header page
+ * If @tep is NULL, 0 is returned.
*/
-int tep_get_header_page_size(struct tep_handle *pevent)
+int tep_get_header_timestamp_size(struct tep_handle *tep)
{
- if(pevent)
- return pevent->header_page_size_size;
+ if (tep)
+ return tep->header_page_ts_size;
return 0;
}
/**
* tep_get_cpus - get the number of CPUs
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
*
* This returns the number of CPUs
- * If @pevent is NULL, 0 is returned.
+ * If @tep is NULL, 0 is returned.
*/
-int tep_get_cpus(struct tep_handle *pevent)
+int tep_get_cpus(struct tep_handle *tep)
{
- if(pevent)
- return pevent->cpus;
+ if (tep)
+ return tep->cpus;
return 0;
}
/**
* tep_set_cpus - set the number of CPUs
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
*
* This sets the number of CPUs
*/
-void tep_set_cpus(struct tep_handle *pevent, int cpus)
+void tep_set_cpus(struct tep_handle *tep, int cpus)
{
- if(pevent)
- pevent->cpus = cpus;
+ if (tep)
+ tep->cpus = cpus;
}
/**
- * tep_get_long_size - get the size of a long integer on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_get_long_size - get the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
*
- * This returns the size of a long integer on the current machine
- * If @pevent is NULL, 0 is returned.
+ * This returns the size of a long integer on the traced machine
+ * If @tep is NULL, 0 is returned.
*/
-int tep_get_long_size(struct tep_handle *pevent)
+int tep_get_long_size(struct tep_handle *tep)
{
- if(pevent)
- return pevent->long_size;
+ if (tep)
+ return tep->long_size;
return 0;
}
/**
- * tep_set_long_size - set the size of a long integer on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_set_long_size - set the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
* @size: size, in bytes, of a long integer
*
- * This sets the size of a long integer on the current machine
+ * This sets the size of a long integer on the traced machine
*/
-void tep_set_long_size(struct tep_handle *pevent, int long_size)
+void tep_set_long_size(struct tep_handle *tep, int long_size)
{
- if(pevent)
- pevent->long_size = long_size;
+ if (tep)
+ tep->long_size = long_size;
}
/**
- * tep_get_page_size - get the size of a memory page on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_get_page_size - get the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
*
- * This returns the size of a memory page on the current machine
- * If @pevent is NULL, 0 is returned.
+ * This returns the size of a memory page on the traced machine
+ * If @tep is NULL, 0 is returned.
*/
-int tep_get_page_size(struct tep_handle *pevent)
+int tep_get_page_size(struct tep_handle *tep)
{
- if(pevent)
- return pevent->page_size;
+ if (tep)
+ return tep->page_size;
return 0;
}
/**
- * tep_set_page_size - set the size of a memory page on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_set_page_size - set the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
* @_page_size: size of a memory page, in bytes
*
- * This sets the size of a memory page on the current machine
+ * This sets the size of a memory page on the traced machine
*/
-void tep_set_page_size(struct tep_handle *pevent, int _page_size)
+void tep_set_page_size(struct tep_handle *tep, int _page_size)
{
- if(pevent)
- pevent->page_size = _page_size;
+ if (tep)
+ tep->page_size = _page_size;
}
/**
- * tep_file_bigendian - get if the file is in big endian order
- * @pevent: a handle to the tep_handle
+ * tep_is_file_bigendian - return the endian of the file
+ * @tep: a handle to the tep_handle
*
- * This returns if the file is in big endian order
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the file is in big endian order
+ * If @tep is NULL, false is returned.
*/
-int tep_file_bigendian(struct tep_handle *pevent)
+bool tep_is_file_bigendian(struct tep_handle *tep)
{
- if(pevent)
- return pevent->file_bigendian;
- return 0;
+ if (tep)
+ return (tep->file_bigendian == TEP_BIG_ENDIAN);
+ return false;
}
/**
* tep_set_file_bigendian - set if the file is in big endian order
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
* @endian: non zero, if the file is in big endian order
*
* This sets if the file is in big endian order
*/
-void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian)
{
- if(pevent)
- pevent->file_bigendian = endian;
+ if (tep)
+ tep->file_bigendian = endian;
}
/**
- * tep_is_host_bigendian - get if the order of the current host is big endian
- * @pevent: a handle to the tep_handle
+ * tep_is_local_bigendian - return the endian of the saved local machine
+ * @tep: a handle to the tep_handle
*
- * This gets if the order of the current host is big endian
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the saved local machine in @tep is big endian.
+ * If @tep is NULL, false is returned.
*/
-int tep_is_host_bigendian(struct tep_handle *pevent)
+bool tep_is_local_bigendian(struct tep_handle *tep)
{
- if(pevent)
- return pevent->host_bigendian;
+ if (tep)
+ return (tep->host_bigendian == TEP_BIG_ENDIAN);
return 0;
}
/**
- * tep_set_host_bigendian - set the order of the local host
- * @pevent: a handle to the tep_handle
+ * tep_set_local_bigendian - set the stored local machine endian order
+ * @tep: a handle to the tep_handle
* @endian: non zero, if the local host has big endian order
*
- * This sets the order of the local host
+ * This sets the endian order for the local machine.
*/
-void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian)
{
- if(pevent)
- pevent->host_bigendian = endian;
+ if (tep)
+ tep->host_bigendian = endian;
}
/**
* tep_is_latency_format - get if the latency output format is configured
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
*
- * This gets if the latency output format is configured
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the latency output format is configured
+ * If @tep is NULL, false is returned.
*/
-int tep_is_latency_format(struct tep_handle *pevent)
+bool tep_is_latency_format(struct tep_handle *tep)
{
- if(pevent)
- return pevent->latency_format;
- return 0;
+ if (tep)
+ return (tep->latency_format);
+ return false;
}
/**
* tep_set_latency_format - set the latency output format
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
* @lat: non zero for latency output format
*
* This sets the latency output format
*/
-void tep_set_latency_format(struct tep_handle *pevent, int lat)
+void tep_set_latency_format(struct tep_handle *tep, int lat)
+{
+ if (tep)
+ tep->latency_format = lat;
+}
+
+/**
+ * tep_is_old_format - get if an old kernel is used
+ * @tep: a handle to the tep_handle
+ *
+ * This returns true, if an old kernel is used to generate the tracing events or
+ * false if a new kernel is used. Old kernels did not have header page info.
+ * If @tep is NULL, false is returned.
+ */
+bool tep_is_old_format(struct tep_handle *tep)
+{
+ if (tep)
+ return tep->old_format;
+ return false;
+}
+
+/**
+ * tep_set_print_raw - set a flag to force print in raw format
+ * @tep: a handle to the tep_handle
+ * @print_raw: the new value of the print_raw flag
+ *
+ * This sets a flag to force print in raw format
+ */
+void tep_set_print_raw(struct tep_handle *tep, int print_raw)
+{
+ if (tep)
+ tep->print_raw = print_raw;
+}
+
+/**
+ * tep_set_test_filters - set a flag to test a filter string
+ * @tep: a handle to the tep_handle
+ * @test_filters: the new value of the test_filters flag
+ *
+ * This sets a flag to test a filter string. If this flag is set, when
+ * tep_filter_add_filter_str() API as called,it will print the filter string
+ * instead of adding it.
+ */
+void tep_set_test_filters(struct tep_handle *tep, int test_filters)
{
- if(pevent)
- pevent->latency_format = lat;
+ if (tep)
+ tep->test_filters = test_filters;
}
void tep_free_event(struct tep_event *event);
void tep_free_format_field(struct tep_format_field *field);
-unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data);
-unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data);
-unsigned long long tep_data2host8(struct tep_handle *pevent, unsigned long long data);
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data);
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data);
+unsigned long long tep_data2host8(struct tep_handle *tep, unsigned long long data);
#endif /* _PARSE_EVENTS_INT_H */
int pid;
};
-static int cmdline_init(struct tep_handle *pevent)
+static int cmdline_init(struct tep_handle *tep)
{
- struct cmdline_list *cmdlist = pevent->cmdlist;
+ struct cmdline_list *cmdlist = tep->cmdlist;
struct cmdline_list *item;
struct tep_cmdline *cmdlines;
int i;
- cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count);
+ cmdlines = malloc(sizeof(*cmdlines) * tep->cmdline_count);
if (!cmdlines)
return -1;
free(item);
}
- qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+ qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
- pevent->cmdlines = cmdlines;
- pevent->cmdlist = NULL;
+ tep->cmdlines = cmdlines;
+ tep->cmdlist = NULL;
return 0;
}
-static const char *find_cmdline(struct tep_handle *pevent, int pid)
+static const char *find_cmdline(struct tep_handle *tep, int pid)
{
const struct tep_cmdline *comm;
struct tep_cmdline key;
if (!pid)
return "<idle>";
- if (!pevent->cmdlines && cmdline_init(pevent))
+ if (!tep->cmdlines && cmdline_init(tep))
return "<not enough memory for cmdlines!>";
key.pid = pid;
- comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
- sizeof(*pevent->cmdlines), cmdline_cmp);
+ comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+ sizeof(*tep->cmdlines), cmdline_cmp);
if (comm)
return comm->comm;
}
/**
- * tep_pid_is_registered - return if a pid has a cmdline registered
- * @pevent: handle for the pevent
+ * tep_is_pid_registered - return if a pid has a cmdline registered
+ * @tep: a handle to the trace event parser context
* @pid: The pid to check if it has a cmdline registered with.
*
- * Returns 1 if the pid has a cmdline mapped to it
- * 0 otherwise.
+ * Returns true if the pid has a cmdline mapped to it
+ * false otherwise.
*/
-int tep_pid_is_registered(struct tep_handle *pevent, int pid)
+bool tep_is_pid_registered(struct tep_handle *tep, int pid)
{
const struct tep_cmdline *comm;
struct tep_cmdline key;
if (!pid)
- return 1;
+ return true;
- if (!pevent->cmdlines && cmdline_init(pevent))
- return 0;
+ if (!tep->cmdlines && cmdline_init(tep))
+ return false;
key.pid = pid;
- comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
- sizeof(*pevent->cmdlines), cmdline_cmp);
+ comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+ sizeof(*tep->cmdlines), cmdline_cmp);
if (comm)
- return 1;
- return 0;
+ return true;
+ return false;
}
/*
* we must add this pid. This is much slower than when cmdlines
* are added before the array is initialized.
*/
-static int add_new_comm(struct tep_handle *pevent,
+static int add_new_comm(struct tep_handle *tep,
const char *comm, int pid, bool override)
{
- struct tep_cmdline *cmdlines = pevent->cmdlines;
+ struct tep_cmdline *cmdlines = tep->cmdlines;
struct tep_cmdline *cmdline;
struct tep_cmdline key;
char *new_comm;
/* avoid duplicates */
key.pid = pid;
- cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
- sizeof(*pevent->cmdlines), cmdline_cmp);
+ cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+ sizeof(*tep->cmdlines), cmdline_cmp);
if (cmdline) {
if (!override) {
errno = EEXIST;
return 0;
}
- cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1));
+ cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (tep->cmdline_count + 1));
if (!cmdlines) {
errno = ENOMEM;
return -1;
}
- cmdlines[pevent->cmdline_count].comm = strdup(comm);
- if (!cmdlines[pevent->cmdline_count].comm) {
+ cmdlines[tep->cmdline_count].comm = strdup(comm);
+ if (!cmdlines[tep->cmdline_count].comm) {
free(cmdlines);
errno = ENOMEM;
return -1;
}
- cmdlines[pevent->cmdline_count].pid = pid;
+ cmdlines[tep->cmdline_count].pid = pid;
- if (cmdlines[pevent->cmdline_count].comm)
- pevent->cmdline_count++;
+ if (cmdlines[tep->cmdline_count].comm)
+ tep->cmdline_count++;
- qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
- pevent->cmdlines = cmdlines;
+ qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+ tep->cmdlines = cmdlines;
return 0;
}
-static int _tep_register_comm(struct tep_handle *pevent,
+static int _tep_register_comm(struct tep_handle *tep,
const char *comm, int pid, bool override)
{
struct cmdline_list *item;
- if (pevent->cmdlines)
- return add_new_comm(pevent, comm, pid, override);
+ if (tep->cmdlines)
+ return add_new_comm(tep, comm, pid, override);
item = malloc(sizeof(*item));
if (!item)
return -1;
}
item->pid = pid;
- item->next = pevent->cmdlist;
+ item->next = tep->cmdlist;
- pevent->cmdlist = item;
- pevent->cmdline_count++;
+ tep->cmdlist = item;
+ tep->cmdline_count++;
return 0;
}
/**
* tep_register_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @comm: the command line to register
* @pid: the pid to map the command line to
*
* a given pid. The comm is duplicated. If a command with the same pid
* already exist, -1 is returned and errno is set to EEXIST
*/
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid)
{
- return _tep_register_comm(pevent, comm, pid, false);
+ return _tep_register_comm(tep, comm, pid, false);
}
/**
* tep_override_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @comm: the command line to register
* @pid: the pid to map the command line to
*
* a given pid. The comm is duplicated. If a command with the same pid
* already exist, the command string is udapted with the new one
*/
-int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid)
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid)
{
- if (!pevent->cmdlines && cmdline_init(pevent)) {
+ if (!tep->cmdlines && cmdline_init(tep)) {
errno = ENOMEM;
return -1;
}
- return _tep_register_comm(pevent, comm, pid, true);
+ return _tep_register_comm(tep, comm, pid, true);
}
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock)
+int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock)
{
- pevent->trace_clock = strdup(trace_clock);
- if (!pevent->trace_clock) {
+ tep->trace_clock = strdup(trace_clock);
+ if (!tep->trace_clock) {
errno = ENOMEM;
return -1;
}
return 1;
}
-static int func_map_init(struct tep_handle *pevent)
+static int func_map_init(struct tep_handle *tep)
{
struct func_list *funclist;
struct func_list *item;
struct func_map *func_map;
int i;
- func_map = malloc(sizeof(*func_map) * (pevent->func_count + 1));
+ func_map = malloc(sizeof(*func_map) * (tep->func_count + 1));
if (!func_map)
return -1;
- funclist = pevent->funclist;
+ funclist = tep->funclist;
i = 0;
while (funclist) {
free(item);
}
- qsort(func_map, pevent->func_count, sizeof(*func_map), func_cmp);
+ qsort(func_map, tep->func_count, sizeof(*func_map), func_cmp);
/*
* Add a special record at the end.
*/
- func_map[pevent->func_count].func = NULL;
- func_map[pevent->func_count].addr = 0;
- func_map[pevent->func_count].mod = NULL;
+ func_map[tep->func_count].func = NULL;
+ func_map[tep->func_count].addr = 0;
+ func_map[tep->func_count].mod = NULL;
- pevent->func_map = func_map;
- pevent->funclist = NULL;
+ tep->func_map = func_map;
+ tep->funclist = NULL;
return 0;
}
static struct func_map *
-__find_func(struct tep_handle *pevent, unsigned long long addr)
+__find_func(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *func;
struct func_map key;
- if (!pevent->func_map)
- func_map_init(pevent);
+ if (!tep->func_map)
+ func_map_init(tep);
key.addr = addr;
- func = bsearch(&key, pevent->func_map, pevent->func_count,
- sizeof(*pevent->func_map), func_bcmp);
+ func = bsearch(&key, tep->func_map, tep->func_count,
+ sizeof(*tep->func_map), func_bcmp);
return func;
}
/**
* tep_set_function_resolver - set an alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @resolver: function to be used
* @priv: resolver function private state.
*
* Some tools may have already a way to resolve kernel functions, allow them to
- * keep using it instead of duplicating all the entries inside
- * pevent->funclist.
+ * keep using it instead of duplicating all the entries inside tep->funclist.
*/
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
tep_func_resolver_t *func, void *priv)
{
struct func_resolver *resolver = malloc(sizeof(*resolver));
resolver->func = func;
resolver->priv = priv;
- free(pevent->func_resolver);
- pevent->func_resolver = resolver;
+ free(tep->func_resolver);
+ tep->func_resolver = resolver;
return 0;
}
/**
* tep_reset_function_resolver - reset alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
*
* Stop using whatever alternative resolver was set, use the default
* one instead.
*/
-void tep_reset_function_resolver(struct tep_handle *pevent)
+void tep_reset_function_resolver(struct tep_handle *tep)
{
- free(pevent->func_resolver);
- pevent->func_resolver = NULL;
+ free(tep->func_resolver);
+ tep->func_resolver = NULL;
}
static struct func_map *
-find_func(struct tep_handle *pevent, unsigned long long addr)
+find_func(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *map;
- if (!pevent->func_resolver)
- return __find_func(pevent, addr);
+ if (!tep->func_resolver)
+ return __find_func(tep, addr);
- map = &pevent->func_resolver->map;
+ map = &tep->func_resolver->map;
map->mod = NULL;
map->addr = addr;
- map->func = pevent->func_resolver->func(pevent->func_resolver->priv,
- &map->addr, &map->mod);
+ map->func = tep->func_resolver->func(tep->func_resolver->priv,
+ &map->addr, &map->mod);
if (map->func == NULL)
return NULL;
/**
* tep_find_function - find a function by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @addr: the address to find the function with
*
* Returns a pointer to the function stored that has the given
* address. Note, the address does not have to be exact, it
* will select the function that would contain the address.
*/
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr)
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *map;
- map = find_func(pevent, addr);
+ map = find_func(tep, addr);
if (!map)
return NULL;
/**
* tep_find_function_address - find a function address by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @addr: the address to find the function with
*
* Returns the address the function starts at. This can be used in
* name and the function offset.
*/
unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr)
{
struct func_map *map;
- map = find_func(pevent, addr);
+ map = find_func(tep, addr);
if (!map)
return 0;
/**
* tep_register_function - register a function with a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @function: the function name to register
* @addr: the address the function starts at
* @mod: the kernel module the function may be in (NULL for none)
* This registers a function name with an address and module.
* The @func passed in is duplicated.
*/
-int tep_register_function(struct tep_handle *pevent, char *func,
+int tep_register_function(struct tep_handle *tep, char *func,
unsigned long long addr, char *mod)
{
struct func_list *item = malloc(sizeof(*item));
if (!item)
return -1;
- item->next = pevent->funclist;
+ item->next = tep->funclist;
item->func = strdup(func);
if (!item->func)
goto out_free;
item->mod = NULL;
item->addr = addr;
- pevent->funclist = item;
- pevent->func_count++;
+ tep->funclist = item;
+ tep->func_count++;
return 0;
/**
* tep_print_funcs - print out the stored functions
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
*
* This prints out the stored functions.
*/
-void tep_print_funcs(struct tep_handle *pevent)
+void tep_print_funcs(struct tep_handle *tep)
{
int i;
- if (!pevent->func_map)
- func_map_init(pevent);
+ if (!tep->func_map)
+ func_map_init(tep);
- for (i = 0; i < (int)pevent->func_count; i++) {
+ for (i = 0; i < (int)tep->func_count; i++) {
printf("%016llx %s",
- pevent->func_map[i].addr,
- pevent->func_map[i].func);
- if (pevent->func_map[i].mod)
- printf(" [%s]\n", pevent->func_map[i].mod);
+ tep->func_map[i].addr,
+ tep->func_map[i].func);
+ if (tep->func_map[i].mod)
+ printf(" [%s]\n", tep->func_map[i].mod);
else
printf("\n");
}
return 0;
}
-static int printk_map_init(struct tep_handle *pevent)
+static int printk_map_init(struct tep_handle *tep)
{
struct printk_list *printklist;
struct printk_list *item;
struct printk_map *printk_map;
int i;
- printk_map = malloc(sizeof(*printk_map) * (pevent->printk_count + 1));
+ printk_map = malloc(sizeof(*printk_map) * (tep->printk_count + 1));
if (!printk_map)
return -1;
- printklist = pevent->printklist;
+ printklist = tep->printklist;
i = 0;
while (printklist) {
free(item);
}
- qsort(printk_map, pevent->printk_count, sizeof(*printk_map), printk_cmp);
+ qsort(printk_map, tep->printk_count, sizeof(*printk_map), printk_cmp);
- pevent->printk_map = printk_map;
- pevent->printklist = NULL;
+ tep->printk_map = printk_map;
+ tep->printklist = NULL;
return 0;
}
static struct printk_map *
-find_printk(struct tep_handle *pevent, unsigned long long addr)
+find_printk(struct tep_handle *tep, unsigned long long addr)
{
struct printk_map *printk;
struct printk_map key;
- if (!pevent->printk_map && printk_map_init(pevent))
+ if (!tep->printk_map && printk_map_init(tep))
return NULL;
key.addr = addr;
- printk = bsearch(&key, pevent->printk_map, pevent->printk_count,
- sizeof(*pevent->printk_map), printk_cmp);
+ printk = bsearch(&key, tep->printk_map, tep->printk_count,
+ sizeof(*tep->printk_map), printk_cmp);
return printk;
}
/**
* tep_register_print_string - register a string by its address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @fmt: the string format to register
* @addr: the address the string was located at
*
* This registers a string by the address it was stored in the kernel.
* The @fmt passed in is duplicated.
*/
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
unsigned long long addr)
{
struct printk_list *item = malloc(sizeof(*item));
if (!item)
return -1;
- item->next = pevent->printklist;
+ item->next = tep->printklist;
item->addr = addr;
/* Strip off quotes and '\n' from the end */
if (strcmp(p, "\\n") == 0)
*p = 0;
- pevent->printklist = item;
- pevent->printk_count++;
+ tep->printklist = item;
+ tep->printk_count++;
return 0;
/**
* tep_print_printk - print out the stored strings
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
*
* This prints the string formats that were stored.
*/
-void tep_print_printk(struct tep_handle *pevent)
+void tep_print_printk(struct tep_handle *tep)
{
int i;
- if (!pevent->printk_map)
- printk_map_init(pevent);
+ if (!tep->printk_map)
+ printk_map_init(tep);
- for (i = 0; i < (int)pevent->printk_count; i++) {
+ for (i = 0; i < (int)tep->printk_count; i++) {
printf("%016llx %s\n",
- pevent->printk_map[i].addr,
- pevent->printk_map[i].printk);
+ tep->printk_map[i].addr,
+ tep->printk_map[i].printk);
}
}
return calloc(1, sizeof(struct tep_event));
}
-static int add_event(struct tep_handle *pevent, struct tep_event *event)
+static int add_event(struct tep_handle *tep, struct tep_event *event)
{
int i;
- struct tep_event **events = realloc(pevent->events, sizeof(event) *
- (pevent->nr_events + 1));
+ struct tep_event **events = realloc(tep->events, sizeof(event) *
+ (tep->nr_events + 1));
if (!events)
return -1;
- pevent->events = events;
+ tep->events = events;
- for (i = 0; i < pevent->nr_events; i++) {
- if (pevent->events[i]->id > event->id)
+ for (i = 0; i < tep->nr_events; i++) {
+ if (tep->events[i]->id > event->id)
break;
}
- if (i < pevent->nr_events)
- memmove(&pevent->events[i + 1],
- &pevent->events[i],
- sizeof(event) * (pevent->nr_events - i));
+ if (i < tep->nr_events)
+ memmove(&tep->events[i + 1],
+ &tep->events[i],
+ sizeof(event) * (tep->nr_events - i));
- pevent->events[i] = event;
- pevent->nr_events++;
+ tep->events[i] = event;
+ tep->nr_events++;
- event->pevent = pevent;
+ event->tep = tep;
return 0;
}
}
/**
- * tep_read_token - access to utilities to use the pevent parser
+ * tep_read_token - access to utilities to use the tep parser
* @tok: The token to return
*
* This will parse tokens from the string given by
else if (field->flags & TEP_FIELD_IS_STRING)
field->elementsize = 1;
else if (field->flags & TEP_FIELD_IS_LONG)
- field->elementsize = event->pevent ?
- event->pevent->long_size :
+ field->elementsize = event->tep ?
+ event->tep->long_size :
sizeof(long);
} else
field->elementsize = field->size;
return val & 0xffffffff;
if (strcmp(type, "u64") == 0 ||
- strcmp(type, "s64"))
+ strcmp(type, "s64") == 0)
return val;
if (strcmp(type, "s8") == 0)
}
static struct tep_function_handler *
-find_func_handler(struct tep_handle *pevent, char *func_name)
+find_func_handler(struct tep_handle *tep, char *func_name)
{
struct tep_function_handler *func;
- if (!pevent)
+ if (!tep)
return NULL;
- for (func = pevent->func_handlers; func; func = func->next) {
+ for (func = tep->func_handlers; func; func = func->next) {
if (strcmp(func->name, func_name) == 0)
break;
}
return func;
}
-static void remove_func_handler(struct tep_handle *pevent, char *func_name)
+static void remove_func_handler(struct tep_handle *tep, char *func_name)
{
struct tep_function_handler *func;
struct tep_function_handler **next;
- next = &pevent->func_handlers;
+ next = &tep->func_handlers;
while ((func = *next)) {
if (strcmp(func->name, func_name) == 0) {
*next = func->next;
return process_dynamic_array_len(event, arg, tok);
}
- func = find_func_handler(event->pevent, token);
+ func = find_func_handler(event->tep, token);
if (func) {
free_token(token);
return process_func_handler(event, func, arg, tok);
/**
* tep_read_number - read a number from data
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
* @ptr: the raw data
* @size: the size of the data that holds the number
*
* Returns the number (converted to host) from the
* raw data.
*/
-unsigned long long tep_read_number(struct tep_handle *pevent,
+unsigned long long tep_read_number(struct tep_handle *tep,
const void *ptr, int size)
{
unsigned long long val;
case 1:
return *(unsigned char *)ptr;
case 2:
- return tep_data2host2(pevent, *(unsigned short *)ptr);
+ return tep_data2host2(tep, *(unsigned short *)ptr);
case 4:
- return tep_data2host4(pevent, *(unsigned int *)ptr);
+ return tep_data2host4(tep, *(unsigned int *)ptr);
case 8:
memcpy(&val, (ptr), sizeof(unsigned long long));
- return tep_data2host8(pevent, val);
+ return tep_data2host8(tep, val);
default:
/* BUG! */
return 0;
case 2:
case 4:
case 8:
- *value = tep_read_number(field->event->pevent,
+ *value = tep_read_number(field->event->tep,
data + field->offset, field->size);
return 0;
default:
}
}
-static int get_common_info(struct tep_handle *pevent,
+static int get_common_info(struct tep_handle *tep,
const char *type, int *offset, int *size)
{
struct tep_event *event;
* All events should have the same common elements.
* Pick any event to find where the type is;
*/
- if (!pevent->events) {
+ if (!tep->events) {
do_warning("no event_list!");
return -1;
}
- event = pevent->events[0];
+ event = tep->events[0];
field = tep_find_common_field(event, type);
if (!field)
return -1;
return 0;
}
-static int __parse_common(struct tep_handle *pevent, void *data,
+static int __parse_common(struct tep_handle *tep, void *data,
int *size, int *offset, const char *name)
{
int ret;
if (!*size) {
- ret = get_common_info(pevent, name, offset, size);
+ ret = get_common_info(tep, name, offset, size);
if (ret < 0)
return ret;
}
- return tep_read_number(pevent, data + *offset, *size);
+ return tep_read_number(tep, data + *offset, *size);
}
-static int trace_parse_common_type(struct tep_handle *pevent, void *data)
+static int trace_parse_common_type(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->type_size, &pevent->type_offset,
+ return __parse_common(tep, data,
+ &tep->type_size, &tep->type_offset,
"common_type");
}
-static int parse_common_pid(struct tep_handle *pevent, void *data)
+static int parse_common_pid(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->pid_size, &pevent->pid_offset,
+ return __parse_common(tep, data,
+ &tep->pid_size, &tep->pid_offset,
"common_pid");
}
-static int parse_common_pc(struct tep_handle *pevent, void *data)
+static int parse_common_pc(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->pc_size, &pevent->pc_offset,
+ return __parse_common(tep, data,
+ &tep->pc_size, &tep->pc_offset,
"common_preempt_count");
}
-static int parse_common_flags(struct tep_handle *pevent, void *data)
+static int parse_common_flags(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->flags_size, &pevent->flags_offset,
+ return __parse_common(tep, data,
+ &tep->flags_size, &tep->flags_offset,
"common_flags");
}
-static int parse_common_lock_depth(struct tep_handle *pevent, void *data)
+static int parse_common_lock_depth(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->ld_size, &pevent->ld_offset,
+ return __parse_common(tep, data,
+ &tep->ld_size, &tep->ld_offset,
"common_lock_depth");
}
-static int parse_common_migrate_disable(struct tep_handle *pevent, void *data)
+static int parse_common_migrate_disable(struct tep_handle *tep, void *data)
{
- return __parse_common(pevent, data,
- &pevent->ld_size, &pevent->ld_offset,
+ return __parse_common(tep, data,
+ &tep->ld_size, &tep->ld_offset,
"common_migrate_disable");
}
/**
* tep_find_event - find an event by given id
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @id: the id of the event
*
* Returns an event that has a given @id.
*/
-struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
+struct tep_event *tep_find_event(struct tep_handle *tep, int id)
{
struct tep_event **eventptr;
struct tep_event key;
struct tep_event *pkey = &key;
/* Check cache first */
- if (pevent->last_event && pevent->last_event->id == id)
- return pevent->last_event;
+ if (tep->last_event && tep->last_event->id == id)
+ return tep->last_event;
key.id = id;
- eventptr = bsearch(&pkey, pevent->events, pevent->nr_events,
- sizeof(*pevent->events), events_id_cmp);
+ eventptr = bsearch(&pkey, tep->events, tep->nr_events,
+ sizeof(*tep->events), events_id_cmp);
if (eventptr) {
- pevent->last_event = *eventptr;
+ tep->last_event = *eventptr;
return *eventptr;
}
/**
* tep_find_event_by_name - find an event by given name
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @sys: the system name to search for
* @name: the name of the event to search for
*
* @sys. If @sys is NULL the first event with @name is returned.
*/
struct tep_event *
-tep_find_event_by_name(struct tep_handle *pevent,
+tep_find_event_by_name(struct tep_handle *tep,
const char *sys, const char *name)
{
struct tep_event *event = NULL;
int i;
- if (pevent->last_event &&
- strcmp(pevent->last_event->name, name) == 0 &&
- (!sys || strcmp(pevent->last_event->system, sys) == 0))
- return pevent->last_event;
+ if (tep->last_event &&
+ strcmp(tep->last_event->name, name) == 0 &&
+ (!sys || strcmp(tep->last_event->system, sys) == 0))
+ return tep->last_event;
- for (i = 0; i < pevent->nr_events; i++) {
- event = pevent->events[i];
+ for (i = 0; i < tep->nr_events; i++) {
+ event = tep->events[i];
if (strcmp(event->name, name) == 0) {
if (!sys)
break;
break;
}
}
- if (i == pevent->nr_events)
+ if (i == tep->nr_events)
event = NULL;
- pevent->last_event = event;
+ tep->last_event = event;
return event;
}
static unsigned long long
eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg *arg)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long val = 0;
unsigned long long left, right;
struct tep_print_arg *typearg = NULL;
}
/* must be a number */
- val = tep_read_number(pevent, data + arg->field.field->offset,
+ val = tep_read_number(tep, data + arg->field.field->offset,
arg->field.field->size);
break;
case TEP_PRINT_FLAGS:
}
/* Default to long size */
- field_size = pevent->long_size;
+ field_size = tep->long_size;
switch (larg->type) {
case TEP_PRINT_DYNAMIC_ARRAY:
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + larg->dynarray.field->offset,
larg->dynarray.field->size);
if (larg->dynarray.field->elementsize)
default:
goto default_op; /* oops, all bets off */
}
- val = tep_read_number(pevent,
+ val = tep_read_number(tep,
data + offset, field_size);
if (typearg)
val = eval_type(val, typearg, 1);
}
break;
case TEP_PRINT_DYNAMIC_ARRAY_LEN:
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + arg->dynarray.field->offset,
arg->dynarray.field->size);
/*
break;
case TEP_PRINT_DYNAMIC_ARRAY:
/* Without [], we pass the address to the dynamic data */
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + arg->dynarray.field->offset,
arg->dynarray.field->size);
/*
trace_seq_printf(s, format, str);
}
-static void print_bitmask_to_seq(struct tep_handle *pevent,
+static void print_bitmask_to_seq(struct tep_handle *tep,
struct trace_seq *s, const char *format,
int len_arg, const void *data, int size)
{
* In the kernel, this is an array of long words, thus
* endianness is very important.
*/
- if (pevent->file_bigendian)
+ if (tep->file_bigendian)
index = size - (len + 1);
else
index = len;
struct tep_event *event, const char *format,
int len_arg, struct tep_print_arg *arg)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
struct tep_print_flag_sym *flag;
struct tep_format_field *field;
struct printk_map *printk;
* is a pointer.
*/
if (!(field->flags & TEP_FIELD_IS_ARRAY) &&
- field->size == pevent->long_size) {
+ field->size == tep->long_size) {
/* Handle heterogeneous recording and processing
* architectures
* on 32-bit devices:
* In this case, 64 bits must be read.
*/
- addr = (pevent->long_size == 8) ?
+ addr = (tep->long_size == 8) ?
*(unsigned long long *)(data + field->offset) :
(unsigned long long)*(unsigned int *)(data + field->offset);
/* Check if it matches a print format */
- printk = find_printk(pevent, addr);
+ printk = find_printk(tep, addr);
if (printk)
trace_seq_puts(s, printk->printk);
else
case TEP_PRINT_HEX_STR:
if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
unsigned long offset;
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + arg->hex.field->dynarray.field->offset,
arg->hex.field->dynarray.field->size);
hex = data + (offset & 0xffff);
unsigned long offset;
struct tep_format_field *field =
arg->int_array.field->dynarray.field;
- offset = tep_read_number(pevent,
+ offset = tep_read_number(tep,
data + field->offset,
field->size);
num = data + (offset & 0xffff);
f = tep_find_any_field(event, arg->string.string);
arg->string.offset = f->offset;
}
- str_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->string.offset));
+ str_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->string.offset));
str_offset &= 0xffff;
print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset);
break;
f = tep_find_any_field(event, arg->bitmask.bitmask);
arg->bitmask.offset = f->offset;
}
- bitmask_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->bitmask.offset));
+ bitmask_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset));
bitmask_size = bitmask_offset >> 16;
bitmask_offset &= 0xffff;
- print_bitmask_to_seq(pevent, s, format, len_arg,
+ print_bitmask_to_seq(tep, s, format, len_arg,
data + bitmask_offset, bitmask_size);
break;
}
static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event *event)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
struct tep_format_field *field, *ip_field;
struct tep_print_arg *args, *arg, **next;
unsigned long long ip, val;
void *bptr;
int vsize = 0;
- field = pevent->bprint_buf_field;
- ip_field = pevent->bprint_ip_field;
+ field = tep->bprint_buf_field;
+ ip_field = tep->bprint_ip_field;
if (!field) {
field = tep_find_field(event, "buf");
do_warning_event(event, "can't find ip field for binary printk");
return NULL;
}
- pevent->bprint_buf_field = field;
- pevent->bprint_ip_field = ip_field;
+ tep->bprint_buf_field = field;
+ tep->bprint_ip_field = ip_field;
}
- ip = tep_read_number(pevent, data + ip_field->offset, ip_field->size);
+ ip = tep_read_number(tep, data + ip_field->offset, ip_field->size);
/*
* The first arg is the IP pointer.
case 'S':
case 'f':
case 'F':
+ case 'x':
break;
default:
/*
vsize = 4;
break;
case 1:
- vsize = pevent->long_size;
+ vsize = tep->long_size;
break;
case 2:
vsize = 8;
/* the pointers are always 4 bytes aligned */
bptr = (void *)(((unsigned long)bptr + 3) &
~3);
- val = tep_read_number(pevent, bptr, vsize);
+ val = tep_read_number(tep, bptr, vsize);
bptr += vsize;
arg = alloc_arg();
if (!arg) {
get_bprint_format(void *data, int size __maybe_unused,
struct tep_event *event)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long addr;
struct tep_format_field *field;
struct printk_map *printk;
char *format;
- field = pevent->bprint_fmt_field;
+ field = tep->bprint_fmt_field;
if (!field) {
field = tep_find_field(event, "fmt");
do_warning_event(event, "can't find format field for binary printk");
return NULL;
}
- pevent->bprint_fmt_field = field;
+ tep->bprint_fmt_field = field;
}
- addr = tep_read_number(pevent, data + field->offset, field->size);
+ addr = tep_read_number(tep, data + field->offset, field->size);
- printk = find_printk(pevent, addr);
+ printk = find_printk(tep, addr);
if (!printk) {
if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0)
return NULL;
{
unsigned long long val;
unsigned int offset, len, i;
- struct tep_handle *pevent = field->event->pevent;
+ struct tep_handle *tep = field->event->tep;
if (field->flags & TEP_FIELD_IS_ARRAY) {
offset = field->offset;
len = field->size;
if (field->flags & TEP_FIELD_IS_DYNAMIC) {
- val = tep_read_number(pevent, data + offset, len);
+ val = tep_read_number(tep, data + offset, len);
offset = val;
len = offset >> 16;
offset &= 0xffff;
field->flags &= ~TEP_FIELD_IS_STRING;
}
} else {
- val = tep_read_number(pevent, data + field->offset,
+ val = tep_read_number(tep, data + field->offset,
field->size);
if (field->flags & TEP_FIELD_IS_POINTER) {
trace_seq_printf(s, "0x%llx", val);
static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event *event)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
struct tep_print_fmt *print_fmt = &event->print_fmt;
struct tep_print_arg *arg = print_fmt->args;
struct tep_print_arg *args = NULL;
case '-':
goto cont_process;
case 'p':
- if (pevent->long_size == 4)
+ if (tep->long_size == 4)
ls = 1;
else
ls = 2;
arg = arg->next;
if (show_func) {
- func = find_func(pevent, val);
+ func = find_func(tep, val);
if (func) {
trace_seq_puts(s, func->func);
if (show_func == 'F')
break;
}
}
- if (pevent->long_size == 8 && ls == 1 &&
+ if (tep->long_size == 8 && ls == 1 &&
sizeof(long) != 8) {
char *p;
}
/**
- * tep_data_lat_fmt - parse the data for the latency format
- * @pevent: a handle to the pevent
+ * tep_data_latency_format - parse the data for the latency format
+ * @tep: a handle to the trace event parser context
* @s: the trace_seq to write to
* @record: the record to read from
*
* need rescheduling, in hard/soft interrupt, preempt count
* and lock depth) and places it into the trace_seq.
*/
-void tep_data_lat_fmt(struct tep_handle *pevent,
- struct trace_seq *s, struct tep_record *record)
+void tep_data_latency_format(struct tep_handle *tep,
+ struct trace_seq *s, struct tep_record *record)
{
static int check_lock_depth = 1;
static int check_migrate_disable = 1;
int softirq;
void *data = record->data;
- lat_flags = parse_common_flags(pevent, data);
- pc = parse_common_pc(pevent, data);
+ lat_flags = parse_common_flags(tep, data);
+ pc = parse_common_pc(tep, data);
/* lock_depth may not always exist */
if (lock_depth_exists)
- lock_depth = parse_common_lock_depth(pevent, data);
+ lock_depth = parse_common_lock_depth(tep, data);
else if (check_lock_depth) {
- lock_depth = parse_common_lock_depth(pevent, data);
+ lock_depth = parse_common_lock_depth(tep, data);
if (lock_depth < 0)
check_lock_depth = 0;
else
/* migrate_disable may not always exist */
if (migrate_disable_exists)
- migrate_disable = parse_common_migrate_disable(pevent, data);
+ migrate_disable = parse_common_migrate_disable(tep, data);
else if (check_migrate_disable) {
- migrate_disable = parse_common_migrate_disable(pevent, data);
+ migrate_disable = parse_common_migrate_disable(tep, data);
if (migrate_disable < 0)
check_migrate_disable = 0;
else
/**
* tep_data_type - parse out the given event type
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to read from
*
* This returns the event id from the @rec.
*/
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec)
{
- return trace_parse_common_type(pevent, rec->data);
+ return trace_parse_common_type(tep, rec->data);
}
/**
* tep_data_pid - parse the PID from record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to parse
*
* This returns the PID from a record.
*/
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec)
{
- return parse_common_pid(pevent, rec->data);
+ return parse_common_pid(tep, rec->data);
}
/**
* tep_data_preempt_count - parse the preempt count from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to parse
*
* This returns the preempt count from a record.
*/
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec)
{
- return parse_common_pc(pevent, rec->data);
+ return parse_common_pc(tep, rec->data);
}
/**
* tep_data_flags - parse the latency flags from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @rec: the record to parse
*
* This returns the latency flags from a record.
*
* Use trace_flag_type enum for the flags (see event-parse.h).
*/
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec)
{
- return parse_common_flags(pevent, rec->data);
+ return parse_common_flags(tep, rec->data);
}
/**
* tep_data_comm_from_pid - return the command line from PID
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @pid: the PID of the task to search for
*
* This returns a pointer to the command line that has the given
* @pid.
*/
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid)
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid)
{
const char *comm;
- comm = find_cmdline(pevent, pid);
+ comm = find_cmdline(tep, pid);
return comm;
}
static struct tep_cmdline *
-pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next)
+pid_from_cmdlist(struct tep_handle *tep, const char *comm, struct tep_cmdline *next)
{
struct cmdline_list *cmdlist = (struct cmdline_list *)next;
if (cmdlist)
cmdlist = cmdlist->next;
else
- cmdlist = pevent->cmdlist;
+ cmdlist = tep->cmdlist;
while (cmdlist && strcmp(cmdlist->comm, comm) != 0)
cmdlist = cmdlist->next;
/**
* tep_data_pid_from_comm - return the pid from a given comm
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @comm: the cmdline to find the pid from
* @next: the cmdline structure to find the next comm
*
* next pid.
* Also, it does a linear search, so it may be slow.
*/
-struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
struct tep_cmdline *next)
{
struct tep_cmdline *cmdline;
* If the cmdlines have not been converted yet, then use
* the list.
*/
- if (!pevent->cmdlines)
- return pid_from_cmdlist(pevent, comm, next);
+ if (!tep->cmdlines)
+ return pid_from_cmdlist(tep, comm, next);
if (next) {
/*
* The next pointer could have been still from
* a previous call before cmdlines were created
*/
- if (next < pevent->cmdlines ||
- next >= pevent->cmdlines + pevent->cmdline_count)
+ if (next < tep->cmdlines ||
+ next >= tep->cmdlines + tep->cmdline_count)
next = NULL;
else
cmdline = next++;
}
if (!next)
- cmdline = pevent->cmdlines;
+ cmdline = tep->cmdlines;
- while (cmdline < pevent->cmdlines + pevent->cmdline_count) {
+ while (cmdline < tep->cmdlines + tep->cmdline_count) {
if (strcmp(cmdline->comm, comm) == 0)
return cmdline;
cmdline++;
/**
* tep_cmdline_pid - return the pid associated to a given cmdline
+ * @tep: a handle to the trace event parser context
* @cmdline: The cmdline structure to get the pid from
*
* Returns the pid for a give cmdline. If @cmdline is NULL, then
* -1 is returned.
*/
-int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline)
{
struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline;
* If cmdlines have not been created yet, or cmdline is
* not part of the array, then treat it as a cmdlist instead.
*/
- if (!pevent->cmdlines ||
- cmdline < pevent->cmdlines ||
- cmdline >= pevent->cmdlines + pevent->cmdline_count)
+ if (!tep->cmdlines ||
+ cmdline < tep->cmdlines ||
+ cmdline >= tep->cmdlines + tep->cmdline_count)
return cmdlist->pid;
return cmdline->pid;
{
int print_pretty = 1;
- if (event->pevent->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
+ if (event->tep->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
tep_print_fields(s, record->data, record->size, event);
else {
return true;
if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global")
- || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf"))
+ || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf")
+ || !strncmp(trace_clock, "mono", 4))
return true;
/* trace_clock is setting in tsc or counter mode */
/**
* tep_find_event_by_record - return the event from a given record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @record: The record to get the event from
*
* Returns the associated event for a given record, or NULL if non is
* is found.
*/
struct tep_event *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record)
{
int type;
return NULL;
}
- type = trace_parse_common_type(pevent, record->data);
+ type = trace_parse_common_type(tep, record->data);
- return tep_find_event(pevent, type);
+ return tep_find_event(tep, type);
}
/**
* tep_print_event_task - Write the event task comm, pid and CPU
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @s: the trace_seq to write to
* @event: the handle to the record's event
* @record: The record to get the event from
*
* Writes the tasks comm, pid and CPU to @s.
*/
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record)
{
const char *comm;
int pid;
- pid = parse_common_pid(pevent, data);
- comm = find_cmdline(pevent, pid);
+ pid = parse_common_pid(tep, data);
+ comm = find_cmdline(tep, pid);
- if (pevent->latency_format) {
- trace_seq_printf(s, "%8.8s-%-5d %3d",
- comm, pid, record->cpu);
- } else
+ if (tep->latency_format)
+ trace_seq_printf(s, "%8.8s-%-5d %3d", comm, pid, record->cpu);
+ else
trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
}
/**
* tep_print_event_time - Write the event timestamp
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @s: the trace_seq to write to
* @event: the handle to the record's event
* @record: The record to get the event from
- * @use_trace_clock: Set to parse according to the @pevent->trace_clock
+ * @use_trace_clock: Set to parse according to the @tep->trace_clock
*
* Writes the timestamp of the record into @s.
*/
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record,
bool use_trace_clock)
int p;
bool use_usec_format;
- use_usec_format = is_timestamp_in_us(pevent->trace_clock,
- use_trace_clock);
+ use_usec_format = is_timestamp_in_us(tep->trace_clock, use_trace_clock);
if (use_usec_format) {
secs = record->ts / NSEC_PER_SEC;
nsecs = record->ts - secs * NSEC_PER_SEC;
}
- if (pevent->latency_format) {
- tep_data_lat_fmt(pevent, s, record);
+ if (tep->latency_format) {
+ tep_data_latency_format(tep, s, record);
}
if (use_usec_format) {
- if (pevent->flags & TEP_NSEC_OUTPUT) {
+ if (tep->flags & TEP_NSEC_OUTPUT) {
usecs = nsecs;
p = 9;
} else {
/**
* tep_print_event_data - Write the event data section
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
* @s: the trace_seq to write to
* @event: the handle to the record's event
* @record: The record to get the event from
*
* Writes the parsing of the record's data to @s.
*/
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record)
{
tep_event_info(s, event, record);
}
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
struct tep_record *record, bool use_trace_clock)
{
struct tep_event *event;
- event = tep_find_event_by_record(pevent, record);
+ event = tep_find_event_by_record(tep, record);
if (!event) {
int i;
- int type = trace_parse_common_type(pevent, record->data);
+ int type = trace_parse_common_type(tep, record->data);
do_warning("ug! no event found for type %d", type);
trace_seq_printf(s, "[UNKNOWN TYPE %d]", type);
return;
}
- tep_print_event_task(pevent, s, event, record);
- tep_print_event_time(pevent, s, event, record, use_trace_clock);
- tep_print_event_data(pevent, s, event, record);
+ tep_print_event_task(tep, s, event, record);
+ tep_print_event_time(tep, s, event, record, use_trace_clock);
+ tep_print_event_data(tep, s, event, record);
}
static int events_id_cmp(const void *a, const void *b)
return events_id_cmp(a, b);
}
-struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type sort_type)
+static struct tep_event **list_events_copy(struct tep_handle *tep)
{
struct tep_event **events;
- int (*sort)(const void *a, const void *b);
-
- events = pevent->sort_events;
-
- if (events && pevent->last_type == sort_type)
- return events;
- if (!events) {
- events = malloc(sizeof(*events) * (pevent->nr_events + 1));
- if (!events)
- return NULL;
+ if (!tep)
+ return NULL;
- memcpy(events, pevent->events, sizeof(*events) * pevent->nr_events);
- events[pevent->nr_events] = NULL;
+ events = malloc(sizeof(*events) * (tep->nr_events + 1));
+ if (!events)
+ return NULL;
- pevent->sort_events = events;
+ memcpy(events, tep->events, sizeof(*events) * tep->nr_events);
+ events[tep->nr_events] = NULL;
+ return events;
+}
- /* the internal events are sorted by id */
- if (sort_type == TEP_EVENT_SORT_ID) {
- pevent->last_type = sort_type;
- return events;
- }
- }
+static void list_events_sort(struct tep_event **events, int nr_events,
+ enum tep_event_sort_type sort_type)
+{
+ int (*sort)(const void *a, const void *b);
switch (sort_type) {
case TEP_EVENT_SORT_ID:
sort = events_system_cmp;
break;
default:
+ sort = NULL;
+ }
+
+ if (sort)
+ qsort(events, nr_events, sizeof(*events), sort);
+}
+
+/**
+ * tep_list_events - Get events, sorted by given criteria.
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * memory must not be freed, it is managed by the library.
+ * The function is not thread safe.
+ */
+struct tep_event **tep_list_events(struct tep_handle *tep,
+ enum tep_event_sort_type sort_type)
+{
+ struct tep_event **events;
+
+ if (!tep)
+ return NULL;
+
+ events = tep->sort_events;
+ if (events && tep->last_type == sort_type)
return events;
+
+ if (!events) {
+ events = list_events_copy(tep);
+ if (!events)
+ return NULL;
+
+ tep->sort_events = events;
+
+ /* the internal events are sorted by id */
+ if (sort_type == TEP_EVENT_SORT_ID) {
+ tep->last_type = sort_type;
+ return events;
+ }
}
- qsort(events, pevent->nr_events, sizeof(*events), sort);
- pevent->last_type = sort_type;
+ list_events_sort(events, tep->nr_events, sort_type);
+ tep->last_type = sort_type;
+
+ return events;
+}
+
+
+/**
+ * tep_list_events_copy - Thread safe version of tep_list_events()
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * array is newly allocated inside the function and must be freed by the caller
+ */
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+ enum tep_event_sort_type sort_type)
+{
+ struct tep_event **events;
+
+ if (!tep)
+ return NULL;
+
+ events = list_events_copy(tep);
+ if (!events)
+ return NULL;
+
+ /* the internal events are sorted by id */
+ if (sort_type == TEP_EVENT_SORT_ID)
+ return events;
+
+ list_events_sort(events, tep->nr_events, sort_type);
return events;
}
/**
* tep_parse_header_page - parse the data stored in the header page
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @buf: the buffer storing the header page format string
* @size: the size of @buf
* @long_size: the long size to use if there is no header
*
* /sys/kernel/debug/tracing/events/header_page
*/
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
int long_size)
{
int ignore;
* Old kernels did not have header page info.
* Sorry but we just use what we find here in user space.
*/
- pevent->header_page_ts_size = sizeof(long long);
- pevent->header_page_size_size = long_size;
- pevent->header_page_data_offset = sizeof(long long) + long_size;
- pevent->old_format = 1;
+ tep->header_page_ts_size = sizeof(long long);
+ tep->header_page_size_size = long_size;
+ tep->header_page_data_offset = sizeof(long long) + long_size;
+ tep->old_format = 1;
return -1;
}
init_input_buf(buf, size);
- parse_header_field("timestamp", &pevent->header_page_ts_offset,
- &pevent->header_page_ts_size, 1);
- parse_header_field("commit", &pevent->header_page_size_offset,
- &pevent->header_page_size_size, 1);
- parse_header_field("overwrite", &pevent->header_page_overwrite,
+ parse_header_field("timestamp", &tep->header_page_ts_offset,
+ &tep->header_page_ts_size, 1);
+ parse_header_field("commit", &tep->header_page_size_offset,
+ &tep->header_page_size_size, 1);
+ parse_header_field("overwrite", &tep->header_page_overwrite,
&ignore, 0);
- parse_header_field("data", &pevent->header_page_data_offset,
- &pevent->header_page_data_size, 1);
+ parse_header_field("data", &tep->header_page_data_offset,
+ &tep->header_page_data_size, 1);
return 0;
}
free(handle);
}
-static int find_event_handle(struct tep_handle *pevent, struct tep_event *event)
+static int find_event_handle(struct tep_handle *tep, struct tep_event *event)
{
struct event_handler *handle, **next;
- for (next = &pevent->handlers; *next;
+ for (next = &tep->handlers; *next;
next = &(*next)->next) {
handle = *next;
if (event_matches(event, handle->id,
* /sys/kernel/debug/tracing/events/.../.../format
*/
enum tep_errno __tep_parse_format(struct tep_event **eventp,
- struct tep_handle *pevent, const char *buf,
+ struct tep_handle *tep, const char *buf,
unsigned long size, const char *sys)
{
struct tep_event *event;
goto event_alloc_failed;
}
- /* Add pevent to event so that it can be referenced */
- event->pevent = pevent;
+ /* Add tep to event so that it can be referenced */
+ event->tep = tep;
ret = event_read_format(event);
if (ret < 0) {
* If the event has an override, don't print warnings if the event
* print format fails to parse.
*/
- if (pevent && find_event_handle(pevent, event))
+ if (tep && find_event_handle(tep, event))
show_warning = 0;
ret = event_read_print(event);
}
static enum tep_errno
-__parse_event(struct tep_handle *pevent,
+__parse_event(struct tep_handle *tep,
struct tep_event **eventp,
const char *buf, unsigned long size,
const char *sys)
{
- int ret = __tep_parse_format(eventp, pevent, buf, size, sys);
+ int ret = __tep_parse_format(eventp, tep, buf, size, sys);
struct tep_event *event = *eventp;
if (event == NULL)
return ret;
- if (pevent && add_event(pevent, event)) {
+ if (tep && add_event(tep, event)) {
ret = TEP_ERRNO__MEM_ALLOC_FAILED;
goto event_add_failed;
}
/**
* tep_parse_format - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @eventp: returned format
* @buf: the buffer storing the event format string
* @size: the size of @buf
*
* /sys/kernel/debug/tracing/events/.../.../format
*/
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
struct tep_event **eventp,
const char *buf,
unsigned long size, const char *sys)
{
- return __parse_event(pevent, eventp, buf, size, sys);
+ return __parse_event(tep, eventp, buf, size, sys);
}
/**
* tep_parse_event - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @buf: the buffer storing the event format string
* @size: the size of @buf
* @sys: the system the event belongs to
*
* /sys/kernel/debug/tracing/events/.../.../format
*/
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
unsigned long size, const char *sys)
{
struct tep_event *event = NULL;
- return __parse_event(pevent, &event, buf, size, sys);
+ return __parse_event(tep, &event, buf, size, sys);
}
int get_field_val(struct trace_seq *s, struct tep_format_field *field,
offset = field->offset;
if (field->flags & TEP_FIELD_IS_DYNAMIC) {
- offset = tep_read_number(event->pevent,
- data + offset, field->size);
+ offset = tep_read_number(event->tep,
+ data + offset, field->size);
*len = offset >> 16;
offset &= 0xffff;
} else
* @record: The record with the field name.
* @err: print default error if failed.
*
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
*/
int tep_print_num_field(struct trace_seq *s, const char *fmt,
struct tep_event *event, const char *name,
* @record: The record with the field name.
* @err: print default error if failed.
*
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
*/
int tep_print_func_field(struct trace_seq *s, const char *fmt,
struct tep_event *event, const char *name,
struct tep_record *record, int err)
{
struct tep_format_field *field = tep_find_field(event, name);
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long val;
struct func_map *func;
char tmp[128];
if (tep_read_number_field(field, record->data, &val))
goto failed;
- func = find_func(pevent, val);
+ func = find_func(tep, val);
if (func)
snprintf(tmp, 128, "%s/0x%llx", func->func, func->addr - val);
/**
* tep_register_print_function - register a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @func: the function to process the helper function
* @ret_type: the return type of the helper function
* @name: the name of the helper function
* The @parameters is a variable list of tep_func_arg_type enums that
* must end with TEP_FUNC_ARG_VOID.
*/
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
tep_func_handler func,
enum tep_func_arg_type ret_type,
char *name, ...)
va_list ap;
int ret;
- func_handle = find_func_handler(pevent, name);
+ func_handle = find_func_handler(tep, name);
if (func_handle) {
/*
* This is most like caused by the users own
* system defaults.
*/
pr_stat("override of function helper '%s'", name);
- remove_func_handler(pevent, name);
+ remove_func_handler(tep, name);
}
func_handle = calloc(1, sizeof(*func_handle));
}
va_end(ap);
- func_handle->next = pevent->func_handlers;
- pevent->func_handlers = func_handle;
+ func_handle->next = tep->func_handlers;
+ tep->func_handlers = func_handle;
return 0;
out_free:
/**
* tep_unregister_print_function - unregister a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @func: the function to process the helper function
* @name: the name of the helper function
*
*
* Returns 0 if the handler was removed successully, -1 otherwise.
*/
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
tep_func_handler func, char *name)
{
struct tep_function_handler *func_handle;
- func_handle = find_func_handler(pevent, name);
+ func_handle = find_func_handler(tep, name);
if (func_handle && func_handle->func == func) {
- remove_func_handler(pevent, name);
+ remove_func_handler(tep, name);
return 0;
}
return -1;
}
-static struct tep_event *search_event(struct tep_handle *pevent, int id,
+static struct tep_event *search_event(struct tep_handle *tep, int id,
const char *sys_name,
const char *event_name)
{
if (id >= 0) {
/* search by id */
- event = tep_find_event(pevent, id);
+ event = tep_find_event(tep, id);
if (!event)
return NULL;
if (event_name && (strcmp(event_name, event->name) != 0))
if (sys_name && (strcmp(sys_name, event->system) != 0))
return NULL;
} else {
- event = tep_find_event_by_name(pevent, sys_name, event_name);
+ event = tep_find_event_by_name(tep, sys_name, event_name);
if (!event)
return NULL;
}
/**
* tep_register_event_handler - register a way to parse an event
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @id: the id of the event to register
* @sys_name: the system name the event belongs to
* @event_name: the name of the event
* negative TEP_ERRNO_... in case of an error
*
*/
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+int tep_register_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context)
{
struct tep_event *event;
struct event_handler *handle;
- event = search_event(pevent, id, sys_name, event_name);
+ event = search_event(tep, id, sys_name, event_name);
if (event == NULL)
goto not_found;
}
handle->func = func;
- handle->next = pevent->handlers;
- pevent->handlers = handle;
+ handle->next = tep->handlers;
+ tep->handlers = handle;
handle->context = context;
return TEP_REGISTER_SUCCESS;
/**
* tep_unregister_event_handler - unregister an existing event handler
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
* @id: the id of the event to unregister
* @sys_name: the system name the handler belongs to
* @event_name: the name of the event handler
*
* Returns 0 if handler was removed successfully, -1 if event was not found.
*/
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context)
{
struct event_handler *handle;
struct event_handler **next;
- event = search_event(pevent, id, sys_name, event_name);
+ event = search_event(tep, id, sys_name, event_name);
if (event == NULL)
goto not_found;
}
not_found:
- for (next = &pevent->handlers; *next; next = &(*next)->next) {
+ for (next = &tep->handlers; *next; next = &(*next)->next) {
handle = *next;
if (handle_matches(handle, id, sys_name, event_name,
func, context))
}
/**
- * tep_alloc - create a pevent handle
+ * tep_alloc - create a tep handle
*/
struct tep_handle *tep_alloc(void)
{
- struct tep_handle *pevent = calloc(1, sizeof(*pevent));
+ struct tep_handle *tep = calloc(1, sizeof(*tep));
- if (pevent) {
- pevent->ref_count = 1;
- pevent->host_bigendian = tep_host_bigendian();
+ if (tep) {
+ tep->ref_count = 1;
+ tep->host_bigendian = tep_is_bigendian();
}
- return pevent;
+ return tep;
}
-void tep_ref(struct tep_handle *pevent)
+void tep_ref(struct tep_handle *tep)
{
- pevent->ref_count++;
+ tep->ref_count++;
}
int tep_get_ref(struct tep_handle *tep)
}
/**
- * tep_free - free a pevent handle
- * @pevent: the pevent handle to free
+ * tep_free - free a tep handle
+ * @tep: the tep handle to free
*/
-void tep_free(struct tep_handle *pevent)
+void tep_free(struct tep_handle *tep)
{
struct cmdline_list *cmdlist, *cmdnext;
struct func_list *funclist, *funcnext;
struct event_handler *handle;
int i;
- if (!pevent)
+ if (!tep)
return;
- cmdlist = pevent->cmdlist;
- funclist = pevent->funclist;
- printklist = pevent->printklist;
+ cmdlist = tep->cmdlist;
+ funclist = tep->funclist;
+ printklist = tep->printklist;
- pevent->ref_count--;
- if (pevent->ref_count)
+ tep->ref_count--;
+ if (tep->ref_count)
return;
- if (pevent->cmdlines) {
- for (i = 0; i < pevent->cmdline_count; i++)
- free(pevent->cmdlines[i].comm);
- free(pevent->cmdlines);
+ if (tep->cmdlines) {
+ for (i = 0; i < tep->cmdline_count; i++)
+ free(tep->cmdlines[i].comm);
+ free(tep->cmdlines);
}
while (cmdlist) {
cmdlist = cmdnext;
}
- if (pevent->func_map) {
- for (i = 0; i < (int)pevent->func_count; i++) {
- free(pevent->func_map[i].func);
- free(pevent->func_map[i].mod);
+ if (tep->func_map) {
+ for (i = 0; i < (int)tep->func_count; i++) {
+ free(tep->func_map[i].func);
+ free(tep->func_map[i].mod);
}
- free(pevent->func_map);
+ free(tep->func_map);
}
while (funclist) {
funclist = funcnext;
}
- while (pevent->func_handlers) {
- func_handler = pevent->func_handlers;
- pevent->func_handlers = func_handler->next;
+ while (tep->func_handlers) {
+ func_handler = tep->func_handlers;
+ tep->func_handlers = func_handler->next;
free_func_handle(func_handler);
}
- if (pevent->printk_map) {
- for (i = 0; i < (int)pevent->printk_count; i++)
- free(pevent->printk_map[i].printk);
- free(pevent->printk_map);
+ if (tep->printk_map) {
+ for (i = 0; i < (int)tep->printk_count; i++)
+ free(tep->printk_map[i].printk);
+ free(tep->printk_map);
}
while (printklist) {
printklist = printknext;
}
- for (i = 0; i < pevent->nr_events; i++)
- tep_free_event(pevent->events[i]);
+ for (i = 0; i < tep->nr_events; i++)
+ tep_free_event(tep->events[i]);
- while (pevent->handlers) {
- handle = pevent->handlers;
- pevent->handlers = handle->next;
+ while (tep->handlers) {
+ handle = tep->handlers;
+ tep->handlers = handle->next;
free_handler(handle);
}
- free(pevent->trace_clock);
- free(pevent->events);
- free(pevent->sort_events);
- free(pevent->func_resolver);
+ free(tep->trace_clock);
+ free(tep->events);
+ free(tep->sort_events);
+ free(tep->func_resolver);
- free(pevent);
+ free(tep);
}
-void tep_unref(struct tep_handle *pevent)
+void tep_unref(struct tep_handle *tep)
{
- tep_free(pevent);
+ tep_free(tep);
}
struct tep_event *event,
void *context);
-typedef int (*tep_plugin_load_func)(struct tep_handle *pevent);
-typedef int (*tep_plugin_unload_func)(struct tep_handle *pevent);
+typedef int (*tep_plugin_load_func)(struct tep_handle *tep);
+typedef int (*tep_plugin_unload_func)(struct tep_handle *tep);
struct tep_plugin_option {
struct tep_plugin_option *next;
* TEP_PLUGIN_LOADER: (required)
* The function name to initialized the plugin.
*
- * int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+ * int TEP_PLUGIN_LOADER(struct tep_handle *tep)
*
* TEP_PLUGIN_UNLOADER: (optional)
* The function called just before unloading
*
- * int TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+ * int TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
*
* TEP_PLUGIN_OPTIONS: (optional)
* Plugin options that can be set before loading
};
struct tep_event {
- struct tep_handle *pevent;
+ struct tep_handle *tep;
char *name;
int id;
int flags;
#define INVALID_PLUGIN_LIST_OPTION ((char **)((unsigned long)-1))
-struct tep_plugin_list *tep_load_plugins(struct tep_handle *pevent);
+struct tep_plugin_list *tep_load_plugins(struct tep_handle *tep);
void tep_unload_plugins(struct tep_plugin_list *plugin_list,
- struct tep_handle *pevent);
+ struct tep_handle *tep);
char **tep_plugin_list_options(void);
void tep_plugin_free_options_list(char **list);
int tep_plugin_add_options(const char *name,
typedef char *(tep_func_resolver_t)(void *priv,
unsigned long long *addrp, char **modp);
void tep_set_flag(struct tep_handle *tep, int flag);
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag);
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flags);
-static inline int tep_host_bigendian(void)
+static inline int tep_is_bigendian(void)
{
unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 };
unsigned int val;
TRACE_FLAG_SOFTIRQ = 0x10,
};
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
tep_func_resolver_t *func, void *priv);
-void tep_reset_function_resolver(struct tep_handle *pevent);
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid);
-int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid);
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock);
-int tep_register_function(struct tep_handle *pevent, char *name,
+void tep_reset_function_resolver(struct tep_handle *tep);
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock);
+int tep_register_function(struct tep_handle *tep, char *name,
unsigned long long addr, char *mod);
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
unsigned long long addr);
-int tep_pid_is_registered(struct tep_handle *pevent, int pid);
+bool tep_is_pid_registered(struct tep_handle *tep, int pid);
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record);
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record,
bool use_trace_clock);
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
struct tep_event *event,
struct tep_record *record);
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
struct tep_record *record, bool use_trace_clock);
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
int long_size);
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
unsigned long size, const char *sys);
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
struct tep_event **eventp,
const char *buf,
unsigned long size, const char *sys);
TEP_REGISTER_SUCCESS_OVERWRITE,
};
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+int tep_register_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context);
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
const char *sys_name, const char *event_name,
tep_event_handler_func func, void *context);
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
tep_func_handler func,
enum tep_func_arg_type ret_type,
char *name, ...);
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
tep_func_handler func, char *name);
struct tep_format_field *tep_find_common_field(struct tep_event *event, const char *name);
struct tep_format_field *tep_find_field(struct tep_event *event, const char *name);
struct tep_format_field *tep_find_any_field(struct tep_event *event, const char *name);
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr);
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr);
unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr);
-unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, int size);
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr);
+unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size);
int tep_read_number_field(struct tep_format_field *field, const void *data,
unsigned long long *value);
struct tep_event *tep_get_first_event(struct tep_handle *tep);
int tep_get_events_count(struct tep_handle *tep);
-struct tep_event *tep_find_event(struct tep_handle *pevent, int id);
+struct tep_event *tep_find_event(struct tep_handle *tep, int id);
struct tep_event *
-tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name);
+tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name);
struct tep_event *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
-
-void tep_data_lat_fmt(struct tep_handle *pevent,
- struct trace_seq *s, struct tep_record *record);
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid);
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record);
+
+void tep_data_latency_format(struct tep_handle *tep,
+ struct trace_seq *s, struct tep_record *record);
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec);
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid);
struct tep_cmdline;
-struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
struct tep_cmdline *next);
-int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline);
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline);
void tep_print_field(struct trace_seq *s, void *data,
struct tep_format_field *field);
int size __maybe_unused, struct tep_event *event);
void tep_event_info(struct trace_seq *s, struct tep_event *event,
struct tep_record *record);
-int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum,
+int tep_strerror(struct tep_handle *tep, enum tep_errno errnum,
char *buf, size_t buflen);
-struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type);
+struct tep_event **tep_list_events(struct tep_handle *tep, enum tep_event_sort_type);
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+ enum tep_event_sort_type);
struct tep_format_field **tep_event_common_fields(struct tep_event *event);
struct tep_format_field **tep_event_fields(struct tep_event *event);
TEP_LITTLE_ENDIAN = 0,
TEP_BIG_ENDIAN
};
-int tep_get_cpus(struct tep_handle *pevent);
-void tep_set_cpus(struct tep_handle *pevent, int cpus);
-int tep_get_long_size(struct tep_handle *pevent);
-void tep_set_long_size(struct tep_handle *pevent, int long_size);
-int tep_get_page_size(struct tep_handle *pevent);
-void tep_set_page_size(struct tep_handle *pevent, int _page_size);
-int tep_file_bigendian(struct tep_handle *pevent);
-void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian);
-int tep_is_host_bigendian(struct tep_handle *pevent);
-void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian);
-int tep_is_latency_format(struct tep_handle *pevent);
-void tep_set_latency_format(struct tep_handle *pevent, int lat);
-int tep_get_header_page_size(struct tep_handle *pevent);
+int tep_get_cpus(struct tep_handle *tep);
+void tep_set_cpus(struct tep_handle *tep, int cpus);
+int tep_get_long_size(struct tep_handle *tep);
+void tep_set_long_size(struct tep_handle *tep, int long_size);
+int tep_get_page_size(struct tep_handle *tep);
+void tep_set_page_size(struct tep_handle *tep, int _page_size);
+bool tep_is_file_bigendian(struct tep_handle *tep);
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian);
+bool tep_is_local_bigendian(struct tep_handle *tep);
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian);
+bool tep_is_latency_format(struct tep_handle *tep);
+void tep_set_latency_format(struct tep_handle *tep, int lat);
+int tep_get_header_page_size(struct tep_handle *tep);
+int tep_get_header_timestamp_size(struct tep_handle *tep);
+bool tep_is_old_format(struct tep_handle *tep);
+void tep_set_print_raw(struct tep_handle *tep, int print_raw);
+void tep_set_test_filters(struct tep_handle *tep, int test_filters);
struct tep_handle *tep_alloc(void);
-void tep_free(struct tep_handle *pevent);
-void tep_ref(struct tep_handle *pevent);
-void tep_unref(struct tep_handle *pevent);
+void tep_free(struct tep_handle *tep);
+void tep_ref(struct tep_handle *tep);
+void tep_unref(struct tep_handle *tep);
int tep_get_ref(struct tep_handle *tep);
/* access to the internal parser */
unsigned long long tep_get_input_buf_ptr(void);
/* for debugging */
-void tep_print_funcs(struct tep_handle *pevent);
-void tep_print_printk(struct tep_handle *pevent);
+void tep_print_funcs(struct tep_handle *tep);
+void tep_print_printk(struct tep_handle *tep);
/* ----------------------- filtering ----------------------- */
#define TEP_FILTER_ERROR_BUFSZ 1024
struct tep_event_filter {
- struct tep_handle *pevent;
+ struct tep_handle *tep;
int filters;
struct tep_filter_type *event_filters;
char error_buffer[TEP_FILTER_ERROR_BUFSZ];
};
-struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep);
/* for backward compatibility */
#define FILTER_NONE TEP_ERRNO__NO_FILTER
#define FILTER_MISS TEP_ERRNO__FILTER_MISS
#define FILTER_MATCH TEP_ERRNO__FILTER_MATCH
-enum tep_filter_trivial_type {
- TEP_FILTER_TRIVIAL_FALSE,
- TEP_FILTER_TRIVIAL_TRUE,
- TEP_FILTER_TRIVIAL_BOTH,
-};
-
enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
const char *filter_str);
void tep_filter_reset(struct tep_event_filter *filter);
-int tep_filter_clear_trivial(struct tep_event_filter *filter,
- enum tep_filter_trivial_type type);
-
void tep_filter_free(struct tep_event_filter *filter);
char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
int tep_filter_remove_event(struct tep_event_filter *filter,
int event_id);
-int tep_filter_event_has_trivial(struct tep_event_filter *filter,
- int event_id,
- enum tep_filter_trivial_type type);
-
int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source);
-int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
- enum tep_filter_trivial_type type);
-
int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2);
#endif /* _PARSE_EVENTS_H */
}
static void
-load_plugin(struct tep_handle *pevent, const char *path,
+load_plugin(struct tep_handle *tep, const char *path,
const char *file, void *data)
{
struct tep_plugin_list **plugin_list = data;
*plugin_list = list;
pr_stat("registering plugin: %s", plugin);
- func(pevent);
+ func(tep);
return;
out_free:
}
static void
-load_plugins_dir(struct tep_handle *pevent, const char *suffix,
+load_plugins_dir(struct tep_handle *tep, const char *suffix,
const char *path,
- void (*load_plugin)(struct tep_handle *pevent,
+ void (*load_plugin)(struct tep_handle *tep,
const char *path,
const char *name,
void *data),
if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0)
continue;
- load_plugin(pevent, path, name, data);
+ load_plugin(tep, path, name, data);
}
closedir(dir);
}
static void
-load_plugins(struct tep_handle *pevent, const char *suffix,
- void (*load_plugin)(struct tep_handle *pevent,
+load_plugins(struct tep_handle *tep, const char *suffix,
+ void (*load_plugin)(struct tep_handle *tep,
const char *path,
const char *name,
void *data),
char *envdir;
int ret;
- if (pevent->flags & TEP_DISABLE_PLUGINS)
+ if (tep->flags & TEP_DISABLE_PLUGINS)
return;
/*
* check that first.
*/
#ifdef PLUGIN_DIR
- if (!(pevent->flags & TEP_DISABLE_SYS_PLUGINS))
- load_plugins_dir(pevent, suffix, PLUGIN_DIR,
+ if (!(tep->flags & TEP_DISABLE_SYS_PLUGINS))
+ load_plugins_dir(tep, suffix, PLUGIN_DIR,
load_plugin, data);
#endif
*/
envdir = getenv("TRACEEVENT_PLUGIN_DIR");
if (envdir)
- load_plugins_dir(pevent, suffix, envdir, load_plugin, data);
+ load_plugins_dir(tep, suffix, envdir, load_plugin, data);
/*
* Now let the home directory override the environment
return;
}
- load_plugins_dir(pevent, suffix, path, load_plugin, data);
+ load_plugins_dir(tep, suffix, path, load_plugin, data);
free(path);
}
struct tep_plugin_list*
-tep_load_plugins(struct tep_handle *pevent)
+tep_load_plugins(struct tep_handle *tep)
{
struct tep_plugin_list *list = NULL;
- load_plugins(pevent, ".so", load_plugin, &list);
+ load_plugins(tep, ".so", load_plugin, &list);
return list;
}
void
-tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *pevent)
+tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *tep)
{
tep_plugin_unload_func func;
struct tep_plugin_list *list;
plugin_list = list->next;
func = dlsym(list->handle, TEP_PLUGIN_UNLOADER_NAME);
if (func)
- func(pevent);
+ func(tep);
dlclose(list->handle);
free(list->name);
free(list);
{
return kbuf->start;
}
+
+/**
+ * kbuffer_raw_get - get raw buffer info
+ * @kbuf: The kbuffer
+ * @subbuf: Start of mapped subbuffer
+ * @info: Info descriptor to fill in
+ *
+ * For debugging. This can return internals of the ring buffer.
+ * Expects to have info->next set to what it will read.
+ * The type, length and timestamp delta will be filled in, and
+ * @info->next will be updated to the next element.
+ * The @subbuf is used to know if the info is passed the end of
+ * data and NULL will be returned if it is.
+ */
+struct kbuffer_raw_info *
+kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, struct kbuffer_raw_info *info)
+{
+ unsigned long long flags;
+ unsigned long long delta;
+ unsigned int type_len;
+ unsigned int size;
+ int start;
+ int length;
+ void *ptr = info->next;
+
+ if (!kbuf || !subbuf)
+ return NULL;
+
+ if (kbuf->flags & KBUFFER_FL_LONG_8)
+ start = 16;
+ else
+ start = 12;
+
+ flags = read_long(kbuf, subbuf + 8);
+ size = (unsigned int)flags & COMMIT_MASK;
+
+ if (ptr < subbuf || ptr >= subbuf + start + size)
+ return NULL;
+
+ type_len = translate_data(kbuf, ptr, &ptr, &delta, &length);
+
+ info->next = ptr + length;
+
+ info->type = type_len;
+ info->delta = delta;
+ info->length = length;
+
+ return info;
+}
void kbuffer_set_old_format(struct kbuffer *kbuf);
int kbuffer_start_of_data(struct kbuffer *kbuf);
+/* Debugging */
+
+struct kbuffer_raw_info {
+ int type;
+ int length;
+ unsigned long long delta;
+ void *next;
+};
+
+/* Read raw data */
+struct kbuffer_raw_info *kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf,
+ struct kbuffer_raw_info *info);
+
#endif /* _K_BUFFER_H */
filter_type = &filter->event_filters[i];
filter_type->event_id = id;
- filter_type->event = tep_find_event(filter->pevent, id);
+ filter_type->event = tep_find_event(filter->tep, id);
filter_type->filter = NULL;
filter->filters++;
/**
* tep_filter_alloc - create a new event filter
- * @pevent: The pevent that this filter is associated with
+ * @tep: The tep that this filter is associated with
*/
-struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent)
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep)
{
struct tep_event_filter *filter;
return NULL;
memset(filter, 0, sizeof(*filter));
- filter->pevent = pevent;
- tep_ref(pevent);
+ filter->tep = tep;
+ tep_ref(tep);
return filter;
}
}
static enum tep_errno
-find_event(struct tep_handle *pevent, struct event_list **events,
+find_event(struct tep_handle *tep, struct event_list **events,
char *sys_name, char *event_name)
{
struct tep_event *event;
}
}
- for (i = 0; i < pevent->nr_events; i++) {
- event = pevent->events[i];
+ for (i = 0; i < tep->nr_events; i++) {
+ event = tep->events[i];
if (event_match(event, sys_name ? &sreg : NULL, &ereg)) {
match = 1;
if (add_event(events, event) < 0) {
enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
const char *filter_str)
{
- struct tep_handle *pevent = filter->pevent;
+ struct tep_handle *tep = filter->tep;
struct event_list *event;
struct event_list *events = NULL;
const char *filter_start;
}
/* Find this event */
- ret = find_event(pevent, &events, strim(sys_name), strim(event_name));
+ ret = find_event(tep, &events, strim(sys_name), strim(event_name));
if (ret < 0) {
free_events(events);
free(this_event);
if (ret < 0)
rtn = ret;
- if (ret >= 0 && pevent->test_filters) {
+ if (ret >= 0 && tep->test_filters) {
char *test;
test = tep_filter_make_string(filter, event->event->id);
if (test) {
free_events(events);
- if (rtn >= 0 && pevent->test_filters)
- exit(0);
-
return rtn;
}
return 0;
}
- return tep_strerror(filter->pevent, err, buf, buflen);
+ return tep_strerror(filter->tep, err, buf, buflen);
}
/**
void tep_filter_free(struct tep_event_filter *filter)
{
- tep_unref(filter->pevent);
+ tep_unref(filter->tep);
tep_filter_reset(filter);
const char *name;
char *str;
- /* Can't assume that the pevent's are the same */
+ /* Can't assume that the tep's are the same */
sys = filter_type->event->system;
name = filter_type->event->name;
- event = tep_find_event_by_name(filter->pevent, sys, name);
+ event = tep_find_event_by_name(filter->tep, sys, name);
if (!event)
return -1;
return ret;
}
-
-/**
- * tep_update_trivial - update the trivial filters with the given filter
- * @dest - the filter to update
- * @source - the filter as the source of the update
- * @type - the type of trivial filter to update.
- *
- * Scan dest for trivial events matching @type to replace with the source.
- *
- * Returns 0 on success and -1 if there was a problem updating, but
- * events may have still been updated on error.
- */
-int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
- enum tep_filter_trivial_type type)
-{
- struct tep_handle *src_pevent;
- struct tep_handle *dest_pevent;
- struct tep_event *event;
- struct tep_filter_type *filter_type;
- struct tep_filter_arg *arg;
- char *str;
- int i;
-
- src_pevent = source->pevent;
- dest_pevent = dest->pevent;
-
- /* Do nothing if either of the filters has nothing to filter */
- if (!dest->filters || !source->filters)
- return 0;
-
- for (i = 0; i < dest->filters; i++) {
- filter_type = &dest->event_filters[i];
- arg = filter_type->filter;
- if (arg->type != TEP_FILTER_ARG_BOOLEAN)
- continue;
- if ((arg->boolean.value && type == TEP_FILTER_TRIVIAL_FALSE) ||
- (!arg->boolean.value && type == TEP_FILTER_TRIVIAL_TRUE))
- continue;
-
- event = filter_type->event;
-
- if (src_pevent != dest_pevent) {
- /* do a look up */
- event = tep_find_event_by_name(src_pevent,
- event->system,
- event->name);
- if (!event)
- return -1;
- }
-
- str = tep_filter_make_string(source, event->id);
- if (!str)
- continue;
-
- /* Don't bother if the filter is trivial too */
- if (strcmp(str, "TRUE") != 0 && strcmp(str, "FALSE") != 0)
- filter_event(dest, event, str, NULL);
- free(str);
- }
- return 0;
-}
-
-/**
- * tep_filter_clear_trivial - clear TRUE and FALSE filters
- * @filter: the filter to remove trivial filters from
- * @type: remove only true, false, or both
- *
- * Removes filters that only contain a TRUE or FALES boolean arg.
- *
- * Returns 0 on success and -1 if there was a problem.
- */
-int tep_filter_clear_trivial(struct tep_event_filter *filter,
- enum tep_filter_trivial_type type)
-{
- struct tep_filter_type *filter_type;
- int count = 0;
- int *ids = NULL;
- int i;
-
- if (!filter->filters)
- return 0;
-
- /*
- * Two steps, first get all ids with trivial filters.
- * then remove those ids.
- */
- for (i = 0; i < filter->filters; i++) {
- int *new_ids;
-
- filter_type = &filter->event_filters[i];
- if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
- continue;
- switch (type) {
- case TEP_FILTER_TRIVIAL_FALSE:
- if (filter_type->filter->boolean.value)
- continue;
- break;
- case TEP_FILTER_TRIVIAL_TRUE:
- if (!filter_type->filter->boolean.value)
- continue;
- default:
- break;
- }
-
- new_ids = realloc(ids, sizeof(*ids) * (count + 1));
- if (!new_ids) {
- free(ids);
- return -1;
- }
-
- ids = new_ids;
- ids[count++] = filter_type->event_id;
- }
-
- if (!count)
- return 0;
-
- for (i = 0; i < count; i++)
- tep_filter_remove_event(filter, ids[i]);
-
- free(ids);
- return 0;
-}
-
-/**
- * tep_filter_event_has_trivial - return true event contains trivial filter
- * @filter: the filter with the information
- * @event_id: the id of the event to test
- * @type: trivial type to test for (TRUE, FALSE, EITHER)
- *
- * Returns 1 if the event contains a matching trivial type
- * otherwise 0.
- */
-int tep_filter_event_has_trivial(struct tep_event_filter *filter,
- int event_id,
- enum tep_filter_trivial_type type)
-{
- struct tep_filter_type *filter_type;
-
- if (!filter->filters)
- return 0;
-
- filter_type = find_filter_type(filter, event_id);
-
- if (!filter_type)
- return 0;
-
- if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
- return 0;
-
- switch (type) {
- case TEP_FILTER_TRIVIAL_FALSE:
- return !filter_type->filter->boolean.value;
-
- case TEP_FILTER_TRIVIAL_TRUE:
- return filter_type->filter->boolean.value;
- default:
- return 1;
- }
-}
-
static int test_filter(struct tep_event *event, struct tep_filter_arg *arg,
struct tep_record *record, enum tep_errno *err);
const char *comm;
int pid;
- pid = tep_data_pid(event->pevent, record);
- comm = tep_data_comm_from_pid(event->pevent, pid);
+ pid = tep_data_pid(event->tep, record);
+ comm = tep_data_comm_from_pid(event->tep, pid);
return comm;
}
static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record)
{
struct tep_event *event;
- struct tep_handle *pevent;
+ struct tep_handle *tep;
unsigned long long addr;
const char *val = NULL;
unsigned int size;
} else {
event = arg->str.field->event;
- pevent = event->pevent;
+ tep = event->tep;
addr = get_value(event, arg->str.field, record);
if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG))
/* convert to a kernel symbol */
- val = tep_find_function(pevent, addr);
+ val = tep_find_function(tep, addr);
if (val == NULL) {
/* just use the hex of the string name */
enum tep_errno tep_filter_match(struct tep_event_filter *filter,
struct tep_record *record)
{
- struct tep_handle *pevent = filter->pevent;
+ struct tep_handle *tep = filter->tep;
struct tep_filter_type *filter_type;
int event_id;
int ret;
if (!filter->filters)
return TEP_ERRNO__NO_FILTER;
- event_id = tep_data_type(pevent, record);
+ event_id = tep_data_type(tep, record);
filter_type = find_filter_type(filter, event_id);
if (!filter_type)
break;
if (filter_type1->filter->type != filter_type2->filter->type)
break;
- switch (filter_type1->filter->type) {
- case TEP_FILTER_TRIVIAL_FALSE:
- case TEP_FILTER_TRIVIAL_TRUE:
- /* trivial types just need the type compared */
- continue;
- default:
- break;
- }
/* The best way to compare complex filters is with strings */
str1 = arg_to_str(filter1, filter_type1->filter);
str2 = arg_to_str(filter2, filter_type2->filter);
void __vwarning(const char *fmt, va_list ap)
{
if (errno)
- perror("trace-cmd");
+ perror("libtraceevent");
errno = 0;
fprintf(stderr, " ");
return val ? (long long) le16toh(*val) : 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process___le16_to_cpup,
TEP_FUNC_ARG_INT,
"__le16_to_cpup",
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process___le16_to_cpup,
+ tep_unregister_print_function(tep, process___le16_to_cpup,
"__le16_to_cpup");
}
static int function_handler(struct trace_seq *s, struct tep_record *record,
struct tep_event *event, void *context)
{
- struct tep_handle *pevent = event->pevent;
+ struct tep_handle *tep = event->tep;
unsigned long long function;
unsigned long long pfunction;
const char *func;
if (tep_get_field_val(s, event, "ip", record, &function, 1))
return trace_seq_putc(s, '!');
- func = tep_find_function(pevent, function);
+ func = tep_find_function(tep, function);
if (tep_get_field_val(s, event, "parent_ip", record, &pfunction, 1))
return trace_seq_putc(s, '!');
- parent = tep_find_function(pevent, pfunction);
+ parent = tep_find_function(tep, pfunction);
if (parent && ftrace_indent->set)
index = add_and_get_index(parent, func, record->cpu);
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "ftrace", "function",
+ tep_register_event_handler(tep, -1, "ftrace", "function",
function_handler, NULL);
tep_plugin_add_options("ftrace", plugin_options);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
int i, x;
- tep_unregister_event_handler(pevent, -1, "ftrace", "function",
+ tep_unregister_event_handler(tep, -1, "ftrace", "function",
function_handler, NULL);
for (i = 0; i <= cpus; i++) {
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1,
+ tep_register_event_handler(tep, -1,
"timer", "hrtimer_expire_entry",
timer_expire_handler, NULL);
- tep_register_event_handler(pevent, -1, "timer", "hrtimer_start",
+ tep_register_event_handler(tep, -1, "timer", "hrtimer_start",
timer_start_handler, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1,
+ tep_unregister_event_handler(tep, -1,
"timer", "hrtimer_expire_entry",
timer_expire_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "timer", "hrtimer_start",
+ tep_unregister_event_handler(tep, -1, "timer", "hrtimer_start",
timer_start_handler, NULL);
}
return jiffies;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_jbd2_dev_to_name,
TEP_FUNC_ARG_STRING,
"jbd2_dev_to_name",
TEP_FUNC_ARG_INT,
TEP_FUNC_ARG_VOID);
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_jiffies_to_msecs,
TEP_FUNC_ARG_LONG,
"jiffies_to_msecs",
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process_jbd2_dev_to_name,
+ tep_unregister_print_function(tep, process_jbd2_dev_to_name,
"jbd2_dev_to_name");
- tep_unregister_print_function(pevent, process_jiffies_to_msecs,
+ tep_unregister_print_function(tep, process_jiffies_to_msecs,
"jiffies_to_msecs");
}
if (tep_read_number_field(field, data, &val))
return 1;
- func = tep_find_function(event->pevent, val);
+ func = tep_find_function(event->tep, val);
if (!func)
return 1;
- addr = tep_find_function_address(event->pevent, val);
+ addr = tep_find_function_address(event->tep, val);
trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr));
return 1;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "kmem", "kfree",
+ tep_register_event_handler(tep, -1, "kmem", "kfree",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmalloc",
+ tep_register_event_handler(tep, -1, "kmem", "kmalloc",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmalloc_node",
+ tep_register_event_handler(tep, -1, "kmem", "kmalloc_node",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+ tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem",
+ tep_register_event_handler(tep, -1, "kmem",
"kmem_cache_alloc_node",
call_site_handler, NULL);
- tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+ tep_register_event_handler(tep, -1, "kmem", "kmem_cache_free",
call_site_handler, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "kmem", "kfree",
+ tep_unregister_event_handler(tep, -1, "kmem", "kfree",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmalloc",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc_node",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmalloc_node",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem",
+ tep_unregister_event_handler(tep, -1, "kmem",
"kmem_cache_alloc_node",
call_site_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+ tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_free",
call_site_handler, NULL);
}
* We can only use the structure if file is of the same
* endianness.
*/
- if (tep_file_bigendian(event->pevent) ==
- tep_is_host_bigendian(event->pevent)) {
+ if (tep_is_file_bigendian(event->tep) ==
+ tep_is_local_bigendian(event->tep)) {
trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s",
role.level,
return pte & PT_WRITABLE_MASK;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
init_disassembler();
- tep_register_event_handler(pevent, -1, "kvm", "kvm_exit",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_exit",
kvm_exit_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
kvm_emulate_insn_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
kvm_nested_vmexit_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+ tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
kvm_nested_vmexit_inject_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+ tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
kvm_mmu_get_page_handler, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+ tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
kvm_mmu_print_role, NULL);
- tep_register_event_handler(pevent, -1,
+ tep_register_event_handler(tep, -1,
"kvmmmu", "kvm_mmu_unsync_page",
kvm_mmu_print_role, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+ tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
kvm_mmu_print_role, NULL);
- tep_register_event_handler(pevent, -1, "kvmmmu",
+ tep_register_event_handler(tep, -1, "kvmmmu",
"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
NULL);
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_is_writable_pte,
TEP_FUNC_ARG_INT,
"is_writable_pte",
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_exit",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_exit",
kvm_exit_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
kvm_emulate_insn_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
kvm_nested_vmexit_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+ tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
kvm_nested_vmexit_inject_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+ tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
kvm_mmu_get_page_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+ tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
kvm_mmu_print_role, NULL);
- tep_unregister_event_handler(pevent, -1,
+ tep_unregister_event_handler(tep, -1,
"kvmmmu", "kvm_mmu_unsync_page",
kvm_mmu_print_role, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+ tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
kvm_mmu_print_role, NULL);
- tep_unregister_event_handler(pevent, -1, "kvmmmu",
+ tep_unregister_event_handler(tep, -1, "kvmmmu",
"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
NULL);
- tep_unregister_print_function(pevent, process_is_writable_pte,
+ tep_unregister_print_function(tep, process_is_writable_pte,
"is_writable_pte");
}
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "mac80211",
+ tep_register_event_handler(tep, -1, "mac80211",
"drv_bss_info_changed",
drv_bss_info_changed, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "mac80211",
+ tep_unregister_event_handler(tep, -1, "mac80211",
"drv_bss_info_changed",
drv_bss_info_changed, NULL);
}
comm = &s->buffer[len];
/* Help out the comm to ids. This will handle dups */
- tep_register_comm(field->event->pevent, comm, pid);
+ tep_register_comm(field->event->tep, comm, pid);
}
static int sched_wakeup_handler(struct trace_seq *s,
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_event_handler(pevent, -1, "sched", "sched_switch",
+ tep_register_event_handler(tep, -1, "sched", "sched_switch",
sched_switch_handler, NULL);
- tep_register_event_handler(pevent, -1, "sched", "sched_wakeup",
+ tep_register_event_handler(tep, -1, "sched", "sched_wakeup",
sched_wakeup_handler, NULL);
- tep_register_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+ tep_register_event_handler(tep, -1, "sched", "sched_wakeup_new",
sched_wakeup_handler, NULL);
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_event_handler(pevent, -1, "sched", "sched_switch",
+ tep_unregister_event_handler(tep, -1, "sched", "sched_switch",
sched_switch_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup",
+ tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup",
sched_wakeup_handler, NULL);
- tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+ tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup_new",
sched_wakeup_handler, NULL);
}
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_scsi_trace_parse_cdb,
TEP_FUNC_ARG_STRING,
"scsi_trace_parse_cdb",
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process_scsi_trace_parse_cdb,
+ tep_unregister_print_function(tep, process_scsi_trace_parse_cdb,
"scsi_trace_parse_cdb");
}
return 0;
}
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
{
- tep_register_print_function(pevent,
+ tep_register_print_function(tep,
process_xen_hypercall_name,
TEP_FUNC_ARG_STRING,
"xen_hypercall_name",
return 0;
}
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
{
- tep_unregister_print_function(pevent, process_xen_hypercall_name,
+ tep_unregister_print_function(tep, process_xen_hypercall_name,
"xen_hypercall_name");
}
19. AND THEN THERE WAS ALPHA
20. THE HAPPENS-BEFORE RELATION: hb
21. THE PROPAGATES-BEFORE RELATION: pb
- 22. RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
+ 22. RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
23. LOCKING
24. ODDS AND ENDS
the content of the LKMM's "propagation" axiom.
-RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
-----------------------------------------------------
+RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
+-------------------------------------------------------------
RCU (Read-Copy-Update) is a powerful synchronization mechanism. It
rests on two concepts: grace periods and read-side critical sections.
Grace-Period Guarantee, which states that a critical section can never
span a full grace period. In more detail, the Guarantee says:
- If a critical section starts before a grace period then it
- must end before the grace period does. In addition, every
- store that propagates to the critical section's CPU before the
- end of the critical section must propagate to every CPU before
- the end of the grace period.
+ For any critical section C and any grace period G, at least
+ one of the following statements must hold:
- If a critical section ends after a grace period ends then it
- must start after the grace period does. In addition, every
- store that propagates to the grace period's CPU before the
- start of the grace period must propagate to every CPU before
- the start of the critical section.
+(1) C ends before G does, and in addition, every store that
+ propagates to C's CPU before the end of C must propagate to
+ every CPU before G ends.
+
+(2) G starts before C does, and in addition, every store that
+ propagates to G's CPU before the start of G must propagate
+ to every CPU before C starts.
+
+In particular, it is not possible for a critical section to both start
+before and end after a grace period.
Here is a simple example of RCU in action:
never end with r1 = 1 and r2 = 0. The reasoning is as follows. r1 = 1
means that P0's store to x propagated to P1 before P1 called
synchronize_rcu(), so P0's critical section must have started before
-P1's grace period. On the other hand, r2 = 0 means that P0's store to
-y, which occurs before the end of the critical section, did not
-propagate to P1 before the end of the grace period, violating the
-Guarantee.
+P1's grace period, contrary to part (2) of the Guarantee. On the
+other hand, r2 = 0 means that P0's store to y, which occurs before the
+end of the critical section, did not propagate to P1 before the end of
+the grace period, contrary to part (1). Together the results violate
+the Guarantee.
In the kernel's implementations of RCU, the requirements for stores
to propagate to every CPU are fulfilled by placing strong fences at
are pretty obvious, as in the example above, but the details aren't
entirely clear. The LKMM formalizes this notion by means of the
rcu-link relation. rcu-link encompasses a very general notion of
-"before": Among other things, X ->rcu-link Z includes cases where X
-happens-before or is equal to some event Y which is equal to or comes
-before Z in the coherence order. When Y = Z this says that X ->rfe Z
-implies X ->rcu-link Z. In addition, when Y = X it says that X ->fr Z
-and X ->co Z each imply X ->rcu-link Z.
+"before": If E and F are RCU fence events (i.e., rcu_read_lock(),
+rcu_read_unlock(), or synchronize_rcu()) then among other things,
+E ->rcu-link F includes cases where E is po-before some memory-access
+event X, F is po-after some memory-access event Y, and we have any of
+X ->rfe Y, X ->co Y, or X ->fr Y.
The formal definition of the rcu-link relation is more than a little
obscure, and we won't give it here. It is closely related to the pb
a somewhat lengthy formal proof. Pretty much all you need to know
about rcu-link is the information in the preceding paragraph.
-The LKMM also defines the gp and rscs relations. They bring grace
-periods and read-side critical sections into the picture, in the
+The LKMM also defines the rcu-gp and rcu-rscsi relations. They bring
+grace periods and read-side critical sections into the picture, in the
following way:
- E ->gp F means there is a synchronize_rcu() fence event S such
- that E ->po S and either S ->po F or S = F. In simple terms,
- there is a grace period po-between E and F.
+ E ->rcu-gp F means that E and F are in fact the same event,
+ and that event is a synchronize_rcu() fence (i.e., a grace
+ period).
- E ->rscs F means there is a critical section delimited by an
- rcu_read_lock() fence L and an rcu_read_unlock() fence U, such
- that E ->po U and either L ->po F or L = F. You can think of
- this as saying that E and F are in the same critical section
- (in fact, it also allows E to be po-before the start of the
- critical section and F to be po-after the end).
+ E ->rcu-rscsi F means that E and F are the rcu_read_unlock()
+ and rcu_read_lock() fence events delimiting some read-side
+ critical section. (The 'i' at the end of the name emphasizes
+ that this relation is "inverted": It links the end of the
+ critical section to the start.)
If we think of the rcu-link relation as standing for an extended
-"before", then X ->gp Y ->rcu-link Z says that X executes before a
-grace period which ends before Z executes. (In fact it covers more
-than this, because it also includes cases where X executes before a
-grace period and some store propagates to Z's CPU before Z executes
-but doesn't propagate to some other CPU until after the grace period
-ends.) Similarly, X ->rscs Y ->rcu-link Z says that X is part of (or
-before the start of) a critical section which starts before Z
-executes.
-
-The LKMM goes on to define the rcu-fence relation as a sequence of gp
-and rscs links separated by rcu-link links, in which the number of gp
-links is >= the number of rscs links. For example:
+"before", then X ->rcu-gp Y ->rcu-link Z roughly says that X is a
+grace period which ends before Z begins. (In fact it covers more than
+this, because it also includes cases where some store propagates to
+Z's CPU before Z begins but doesn't propagate to some other CPU until
+after X ends.) Similarly, X ->rcu-rscsi Y ->rcu-link Z says that X is
+the end of a critical section which starts before Z begins.
+
+The LKMM goes on to define the rcu-fence relation as a sequence of
+rcu-gp and rcu-rscsi links separated by rcu-link links, in which the
+number of rcu-gp links is >= the number of rcu-rscsi links. For
+example:
- X ->gp Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+ X ->rcu-gp Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
would imply that X ->rcu-fence V, because this sequence contains two
-gp links and only one rscs link. (It also implies that X ->rcu-fence T
-and Z ->rcu-fence V.) On the other hand:
+rcu-gp links and one rcu-rscsi link. (It also implies that
+X ->rcu-fence T and Z ->rcu-fence V.) On the other hand:
- X ->rscs Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+ X ->rcu-rscsi Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
does not imply X ->rcu-fence V, because the sequence contains only
-one gp link but two rscs links.
+one rcu-gp link but two rcu-rscsi links.
The rcu-fence relation is important because the Grace Period Guarantee
means that rcu-fence acts kind of like a strong fence. In particular,
-if W is a write and we have W ->rcu-fence Z, the Guarantee says that W
-will propagate to every CPU before Z executes.
+E ->rcu-fence F implies not only that E begins before F ends, but also
+that any write po-before E will propagate to every CPU before any
+instruction po-after F can execute. (However, it does not imply that
+E must execute before F; in fact, each synchronize_rcu() fence event
+is linked to itself by rcu-fence as a degenerate case.)
To prove this in full generality requires some intellectual effort.
We'll consider just a very simple case:
- W ->gp X ->rcu-link Y ->rscs Z.
+ G ->rcu-gp W ->rcu-link Z ->rcu-rscsi F.
-This formula means that there is a grace period G and a critical
-section C such that:
+This formula means that G and W are the same event (a grace period),
+and there are events X, Y and a read-side critical section C such that:
- 1. W is po-before G;
+ 1. G = W is po-before or equal to X;
- 2. X is equal to or po-after G;
+ 2. X comes "before" Y in some sense (including rfe, co and fr);
- 3. X comes "before" Y in some sense;
+ 2. Y is po-before Z;
- 4. Y is po-before the end of C;
+ 4. Z is the rcu_read_unlock() event marking the end of C;
- 5. Z is equal to or po-after the start of C.
+ 5. F is the rcu_read_lock() event marking the start of C.
-From 2 - 4 we deduce that the grace period G ends before the critical
-section C. Then the second part of the Grace Period Guarantee says
-not only that G starts before C does, but also that W (which executes
-on G's CPU before G starts) must propagate to every CPU before C
-starts. In particular, W propagates to every CPU before Z executes
-(or finishes executing, in the case where Z is equal to the
-rcu_read_lock() fence event which starts C.) This sort of reasoning
-can be expanded to handle all the situations covered by rcu-fence.
+From 1 - 4 we deduce that the grace period G ends before the critical
+section C. Then part (2) of the Grace Period Guarantee says not only
+that G starts before C does, but also that any write which executes on
+G's CPU before G starts must propagate to every CPU before C starts.
+In particular, the write propagates to every CPU before F finishes
+executing and hence before any instruction po-after F can execute.
+This sort of reasoning can be extended to handle all the situations
+covered by rcu-fence.
Finally, the LKMM defines the RCU-before (rb) relation in terms of
rcu-fence. This is done in essentially the same way as the pb
relation was defined in terms of strong-fence. We will omit the
-details; the end result is that E ->rb F implies E must execute before
-F, just as E ->pb F does (and for much the same reasons).
+details; the end result is that E ->rb F implies E must execute
+before F, just as E ->pb F does (and for much the same reasons).
Putting this all together, the LKMM expresses the Grace Period
Guarantee by requiring that the rb relation does not contain a cycle.
-Equivalently, this "rcu" axiom requires that there are no events E and
-F with E ->rcu-link F ->rcu-fence E. Or to put it a third way, the
-axiom requires that there are no cycles consisting of gp and rscs
-alternating with rcu-link, where the number of gp links is >= the
-number of rscs links.
+Equivalently, this "rcu" axiom requires that there are no events E
+and F with E ->rcu-link F ->rcu-fence E. Or to put it a third way,
+the axiom requires that there are no cycles consisting of rcu-gp and
+rcu-rscsi alternating with rcu-link, where the number of rcu-gp links
+is >= the number of rcu-rscsi links.
Justifying the axiom isn't easy, but it is in fact a valid
formalization of the Grace Period Guarantee. We won't attempt to go
through the detailed argument, but the following analysis gives a
-taste of what is involved. Suppose we have a violation of the first
-part of the Guarantee: A critical section starts before a grace
-period, and some store propagates to the critical section's CPU before
-the end of the critical section but doesn't propagate to some other
-CPU until after the end of the grace period.
+taste of what is involved. Suppose both parts of the Guarantee are
+violated: A critical section starts before a grace period, and some
+store propagates to the critical section's CPU before the end of the
+critical section but doesn't propagate to some other CPU until after
+the end of the grace period.
Putting symbols to these ideas, let L and U be the rcu_read_lock() and
rcu_read_unlock() fence events delimiting the critical section in
question, and let S be the synchronize_rcu() fence event for the grace
period. Saying that the critical section starts before S means there
-are events E and F where E is po-after L (which marks the start of the
-critical section), E is "before" F in the sense of the rcu-link
-relation, and F is po-before the grace period S:
+are events Q and R where Q is po-after L (which marks the start of the
+critical section), Q is "before" R in the sense used by the rcu-link
+relation, and R is po-before the grace period S. Thus we have:
- L ->po E ->rcu-link F ->po S.
+ L ->rcu-link S.
-Let W be the store mentioned above, let Z come before the end of the
+Let W be the store mentioned above, let Y come before the end of the
critical section and witness that W propagates to the critical
-section's CPU by reading from W, and let Y on some arbitrary CPU be a
-witness that W has not propagated to that CPU, where Y happens after
+section's CPU by reading from W, and let Z on some arbitrary CPU be a
+witness that W has not propagated to that CPU, where Z happens after
some event X which is po-after S. Symbolically, this amounts to:
- S ->po X ->hb* Y ->fr W ->rf Z ->po U.
+ S ->po X ->hb* Z ->fr W ->rf Y ->po U.
-The fr link from Y to W indicates that W has not propagated to Y's CPU
-at the time that Y executes. From this, it can be shown (see the
-discussion of the rcu-link relation earlier) that X and Z are related
-by rcu-link, yielding:
+The fr link from Z to W indicates that W has not propagated to Z's CPU
+at the time that Z executes. From this, it can be shown (see the
+discussion of the rcu-link relation earlier) that S and U are related
+by rcu-link:
- S ->po X ->rcu-link Z ->po U.
+ S ->rcu-link U.
-The formulas say that S is po-between F and X, hence F ->gp X. They
-also say that Z comes before the end of the critical section and E
-comes after its start, hence Z ->rscs E. From all this we obtain:
+Since S is a grace period we have S ->rcu-gp S, and since L and U are
+the start and end of the critical section C we have U ->rcu-rscsi L.
+From this we obtain:
- F ->gp X ->rcu-link Z ->rscs E ->rcu-link F,
+ S ->rcu-gp S ->rcu-link U ->rcu-rscsi L ->rcu-link S,
a forbidden cycle. Thus the "rcu" axiom rules out this violation of
the Grace Period Guarantee.
For something a little more down-to-earth, let's see how the axiom
works out in practice. Consider the RCU code example from above, this
-time with statement labels added to the memory access instructions:
+time with statement labels added:
int x, y;
P0()
{
- rcu_read_lock();
- W: WRITE_ONCE(x, 1);
- X: WRITE_ONCE(y, 1);
- rcu_read_unlock();
+ L: rcu_read_lock();
+ X: WRITE_ONCE(x, 1);
+ Y: WRITE_ONCE(y, 1);
+ U: rcu_read_unlock();
}
P1()
{
int r1, r2;
- Y: r1 = READ_ONCE(x);
- synchronize_rcu();
- Z: r2 = READ_ONCE(y);
+ Z: r1 = READ_ONCE(x);
+ S: synchronize_rcu();
+ W: r2 = READ_ONCE(y);
}
-If r2 = 0 at the end then P0's store at X overwrites the value that
-P1's load at Z reads from, so we have Z ->fre X and thus Z ->rcu-link X.
-In addition, there is a synchronize_rcu() between Y and Z, so therefore
-we have Y ->gp Z.
+If r2 = 0 at the end then P0's store at Y overwrites the value that
+P1's load at W reads from, so we have W ->fre Y. Since S ->po W and
+also Y ->po U, we get S ->rcu-link U. In addition, S ->rcu-gp S
+because S is a grace period.
-If r1 = 1 at the end then P1's load at Y reads from P0's store at W,
-so we have W ->rcu-link Y. In addition, W and X are in the same critical
-section, so therefore we have X ->rscs W.
+If r1 = 1 at the end then P1's load at Z reads from P0's store at X,
+so we have X ->rfe Z. Together with L ->po X and Z ->po S, this
+yields L ->rcu-link S. And since L and U are the start and end of a
+critical section, we have U ->rcu-rscsi L.
-Then X ->rscs W ->rcu-link Y ->gp Z ->rcu-link X is a forbidden cycle,
-violating the "rcu" axiom. Hence the outcome is not allowed by the
-LKMM, as we would expect.
+Then U ->rcu-rscsi L ->rcu-link S ->rcu-gp S ->rcu-link U is a
+forbidden cycle, violating the "rcu" axiom. Hence the outcome is not
+allowed by the LKMM, as we would expect.
For contrast, let's see what can happen in a more complicated example:
{
int r0;
- rcu_read_lock();
- W: r0 = READ_ONCE(x);
- X: WRITE_ONCE(y, 1);
- rcu_read_unlock();
+ L0: rcu_read_lock();
+ r0 = READ_ONCE(x);
+ WRITE_ONCE(y, 1);
+ U0: rcu_read_unlock();
}
P1()
{
int r1;
- Y: r1 = READ_ONCE(y);
- synchronize_rcu();
- Z: WRITE_ONCE(z, 1);
+ r1 = READ_ONCE(y);
+ S1: synchronize_rcu();
+ WRITE_ONCE(z, 1);
}
P2()
{
int r2;
- rcu_read_lock();
- U: r2 = READ_ONCE(z);
- V: WRITE_ONCE(x, 1);
- rcu_read_unlock();
+ L2: rcu_read_lock();
+ r2 = READ_ONCE(z);
+ WRITE_ONCE(x, 1);
+ U2: rcu_read_unlock();
}
If r0 = r1 = r2 = 1 at the end, then similar reasoning to before shows
-that W ->rscs X ->rcu-link Y ->gp Z ->rcu-link U ->rscs V ->rcu-link W.
-However this cycle is not forbidden, because the sequence of relations
-contains fewer instances of gp (one) than of rscs (two). Consequently
-the outcome is allowed by the LKMM. The following instruction timing
-diagram shows how it might actually occur:
+that U0 ->rcu-rscsi L0 ->rcu-link S1 ->rcu-gp S1 ->rcu-link U2 ->rcu-rscsi
+L2 ->rcu-link U0. However this cycle is not forbidden, because the
+sequence of relations contains fewer instances of rcu-gp (one) than of
+rcu-rscsi (two). Consequently the outcome is allowed by the LKMM.
+The following instruction timing diagram shows how it might actually
+occur:
P0 P1 P2
-------------------- -------------------- --------------------
rcu_read_lock()
-X: WRITE_ONCE(y, 1)
- Y: r1 = READ_ONCE(y)
+WRITE_ONCE(y, 1)
+ r1 = READ_ONCE(y)
synchronize_rcu() starts
. rcu_read_lock()
- . V: WRITE_ONCE(x, 1)
-W: r0 = READ_ONCE(x) .
+ . WRITE_ONCE(x, 1)
+r0 = READ_ONCE(x) .
rcu_read_unlock() .
synchronize_rcu() ends
- Z: WRITE_ONCE(z, 1)
- U: r2 = READ_ONCE(z)
+ WRITE_ONCE(z, 1)
+ r2 = READ_ONCE(z)
rcu_read_unlock()
This requires P0 and P2 to execute their loads and stores out of
before it does, and the critical section in P2 both starts after P1's
grace period does and ends after it does.
+Addendum: The LKMM now supports SRCU (Sleepable Read-Copy-Update) in
+addition to normal RCU. The ideas involved are much the same as
+above, with new relations srcu-gp and srcu-rscsi added to represent
+SRCU grace periods and read-side critical sections. There is a
+restriction on the srcu-gp and srcu-rscsi links that can appear in an
+rcu-fence sequence (the srcu-rscsi links must be paired with srcu-gp
+links having the same SRCU domain with proper nesting); the details
+are relatively unimportant.
+
LOCKING
-------
REQUIREMENTS
============
-Version 7.49 of the "herd7" and "klitmus7" tools must be downloaded
-separately:
+Version 7.52 or higher of the "herd7" and "klitmus7" tools must be
+downloaded separately:
https://github.com/herd/herdtools7
See "herdtools7/INSTALL.md" for installation instructions.
+Note that although these tools usually provide backwards compatibility,
+this is not absolutely guaranteed. Therefore, if a later version does
+not work, please try using the exact version called out above.
+
==================
BASIC USAGE: HERD7
additional call_rcu() process to the site of the
emulated rcu-barrier().
- e. Sleepable RCU (SRCU) is not modeled. It can be
- emulated, but perhaps not simply.
+ e. Although sleepable RCU (SRCU) is now modeled, there
+ are some subtle differences between its semantics and
+ those in the Linux kernel. For example, the kernel
+ might interpret the following sequence as two partially
+ overlapping SRCU read-side critical sections:
+
+ 1 r1 = srcu_read_lock(&my_srcu);
+ 2 do_something_1();
+ 3 r2 = srcu_read_lock(&my_srcu);
+ 4 do_something_2();
+ 5 srcu_read_unlock(&my_srcu, r1);
+ 6 do_something_3();
+ 7 srcu_read_unlock(&my_srcu, r2);
+
+ In contrast, LKMM will interpret this as a nested pair of
+ SRCU read-side critical sections, with the outer critical
+ section spanning lines 1-7 and the inner critical section
+ spanning lines 3-5.
+
+ This difference would be more of a concern had anyone
+ identified a reasonable use case for partially overlapping
+ SRCU read-side critical sections. For more information,
+ please see: https://paulmck.livejournal.com/40593.html
f. Reader-writer locking is not modeled. It can be
emulated in litmus tests using atomic read-modify-write
'after-unlock-lock (*smp_mb__after_unlock_lock*)
instructions F[Barriers]
+(* SRCU *)
+enum SRCU = 'srcu-lock || 'srcu-unlock || 'sync-srcu
+instructions SRCU[SRCU]
+(* All srcu events *)
+let Srcu = Srcu-lock | Srcu-unlock | Sync-srcu
+
(* Compute matching pairs of nested Rcu-lock and Rcu-unlock *)
-let matched = let rec
+let rcu-rscs = let rec
unmatched-locks = Rcu-lock \ domain(matched)
and unmatched-unlocks = Rcu-unlock \ range(matched)
and unmatched = unmatched-locks | unmatched-unlocks
in matched
(* Validate nesting *)
-flag ~empty Rcu-lock \ domain(matched) as unbalanced-rcu-locking
-flag ~empty Rcu-unlock \ range(matched) as unbalanced-rcu-locking
+flag ~empty Rcu-lock \ domain(rcu-rscs) as unbalanced-rcu-locking
+flag ~empty Rcu-unlock \ range(rcu-rscs) as unbalanced-rcu-locking
+
+(* Compute matching pairs of nested Srcu-lock and Srcu-unlock *)
+let srcu-rscs = let rec
+ unmatched-locks = Srcu-lock \ domain(matched)
+ and unmatched-unlocks = Srcu-unlock \ range(matched)
+ and unmatched = unmatched-locks | unmatched-unlocks
+ and unmatched-po = ([unmatched] ; po ; [unmatched]) & loc
+ and unmatched-locks-to-unlocks =
+ ([unmatched-locks] ; po ; [unmatched-unlocks]) & loc
+ and matched = matched | (unmatched-locks-to-unlocks \
+ (unmatched-po ; unmatched-po))
+ in matched
+
+(* Validate nesting *)
+flag ~empty Srcu-lock \ domain(srcu-rscs) as unbalanced-srcu-locking
+flag ~empty Srcu-unlock \ range(srcu-rscs) as unbalanced-srcu-locking
+
+(* Check for use of synchronize_srcu() inside an RCU critical section *)
+flag ~empty rcu-rscs & (po ; [Sync-srcu] ; po) as invalid-sleep
-(* Outermost level of nesting only *)
-let crit = matched \ (po^-1 ; matched ; po^-1)
+(* Validate SRCU dynamic match *)
+flag ~empty different-values(srcu-rscs) as srcu-bad-nesting
([M] ; po? ; [LKW] ; fencerel(After-spinlock) ; [M]) |
([M] ; po ; [UL] ; (co | po) ; [LKW] ;
fencerel(After-unlock-lock) ; [M])
-let gp = po ; [Sync-rcu] ; po?
+let gp = po ; [Sync-rcu | Sync-srcu] ; po?
let strong-fence = mb | gp
(*******)
(*
- * Effect of read-side critical section proceeds from the rcu_read_lock()
- * onward on the one hand and from the rcu_read_unlock() backwards on the
- * other hand.
+ * Effects of read-side critical sections proceed from the rcu_read_unlock()
+ * or srcu_read_unlock() backwards on the one hand, and from the
+ * rcu_read_lock() or srcu_read_lock() forwards on the other hand.
+ *
+ * In the definition of rcu-fence below, the po term at the left-hand side
+ * of each disjunct and the po? term at the right-hand end have been factored
+ * out. They have been moved into the definitions of rcu-link and rb.
+ * This was necessary in order to apply the "& loc" tests correctly.
*)
-let rscs = po ; crit^-1 ; po?
+let rcu-gp = [Sync-rcu] (* Compare with gp *)
+let srcu-gp = [Sync-srcu]
+let rcu-rscsi = rcu-rscs^-1
+let srcu-rscsi = srcu-rscs^-1
(*
* The synchronize_rcu() strong fence is special in that it can order not
* one but two non-rf relations, but only in conjunction with an RCU
* read-side critical section.
*)
-let rcu-link = hb* ; pb* ; prop
+let rcu-link = po? ; hb* ; pb* ; prop ; po
(*
* Any sequence containing at least as many grace periods as RCU read-side
* critical sections (joined by rcu-link) acts as a generalized strong fence.
+ * Likewise for SRCU grace periods and read-side critical sections, provided
+ * the synchronize_srcu() and srcu_read_[un]lock() calls refer to the same
+ * struct srcu_struct location.
*)
-let rec rcu-fence = gp |
- (gp ; rcu-link ; rscs) |
- (rscs ; rcu-link ; gp) |
- (gp ; rcu-link ; rcu-fence ; rcu-link ; rscs) |
- (rscs ; rcu-link ; rcu-fence ; rcu-link ; gp) |
+let rec rcu-fence = rcu-gp | srcu-gp |
+ (rcu-gp ; rcu-link ; rcu-rscsi) |
+ ((srcu-gp ; rcu-link ; srcu-rscsi) & loc) |
+ (rcu-rscsi ; rcu-link ; rcu-gp) |
+ ((srcu-rscsi ; rcu-link ; srcu-gp) & loc) |
+ (rcu-gp ; rcu-link ; rcu-fence ; rcu-link ; rcu-rscsi) |
+ ((srcu-gp ; rcu-link ; rcu-fence ; rcu-link ; srcu-rscsi) & loc) |
+ (rcu-rscsi ; rcu-link ; rcu-fence ; rcu-link ; rcu-gp) |
+ ((srcu-rscsi ; rcu-link ; rcu-fence ; rcu-link ; srcu-gp) & loc) |
(rcu-fence ; rcu-link ; rcu-fence)
(* rb orders instructions just as pb does *)
-let rb = prop ; rcu-fence ; hb* ; pb*
+let rb = prop ; po ; rcu-fence ; po? ; hb* ; pb*
irreflexive rb as rcu
synchronize_rcu() { __fence{sync-rcu}; }
synchronize_rcu_expedited() { __fence{sync-rcu}; }
+// SRCU
+srcu_read_lock(X) __srcu{srcu-lock}(X)
+srcu_read_unlock(X,Y) { __srcu{srcu-unlock}(X,Y); }
+synchronize_srcu(X) { __srcu{sync-srcu}(X); }
+synchronize_srcu_expedited(X) { __srcu{sync-srcu}(X); }
+
// Atomic
atomic_read(X) READ_ONCE(*X)
atomic_set(X,V) { WRITE_ONCE(*X,V); }
(*
* Generate coherence orders and handle lock operations
- *
- * Warning: spin_is_locked() crashes herd7 versions strictly before 7.48.
- * spin_is_locked() is functional from herd7 version 7.49.
*)
include "cross.cat"
#define INSN_STACK 8
#define INSN_BUG 9
#define INSN_NOP 10
-#define INSN_OTHER 11
+#define INSN_STAC 11
+#define INSN_CLAC 12
+#define INSN_STD 13
+#define INSN_CLD 14
+#define INSN_OTHER 15
#define INSN_LAST INSN_OTHER
enum op_dest_type {
OP_DEST_REG_INDIRECT,
OP_DEST_MEM,
OP_DEST_PUSH,
+ OP_DEST_PUSHF,
OP_DEST_LEAVE,
};
OP_SRC_REG_INDIRECT,
OP_SRC_CONST,
OP_SRC_POP,
+ OP_SRC_POPF,
OP_SRC_ADD,
OP_SRC_AND,
};
/* pushf */
*type = INSN_STACK;
op->src.type = OP_SRC_CONST;
- op->dest.type = OP_DEST_PUSH;
+ op->dest.type = OP_DEST_PUSHF;
break;
case 0x9d:
/* popf */
*type = INSN_STACK;
- op->src.type = OP_SRC_POP;
+ op->src.type = OP_SRC_POPF;
op->dest.type = OP_DEST_MEM;
break;
case 0x0f:
- if (op2 >= 0x80 && op2 <= 0x8f) {
+ if (op2 == 0x01) {
+
+ if (modrm == 0xca)
+ *type = INSN_CLAC;
+ else if (modrm == 0xcb)
+ *type = INSN_STAC;
+
+ } else if (op2 >= 0x80 && op2 <= 0x8f) {
*type = INSN_JUMP_CONDITIONAL;
*type = INSN_CALL;
break;
+ case 0xfc:
+ *type = INSN_CLD;
+ break;
+
+ case 0xfd:
+ *type = INSN_STD;
+ break;
+
case 0xff:
if (modrm_reg == 2 || modrm_reg == 3)
#include "builtin.h"
#include "check.h"
-bool no_fp, no_unreachable, retpoline, module;
+bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
static const char * const check_usage[] = {
"objtool check [<options>] file.o",
OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"),
OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"),
OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"),
+ OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"),
+ OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"),
OPT_END(),
};
#include <subcmd/parse-options.h>
extern const struct option check_options[];
-extern bool no_fp, no_unreachable, retpoline, module;
+extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
extern int cmd_check(int argc, const char **argv);
extern int cmd_orc(int argc, const char **argv);
struct alternative {
struct list_head list;
struct instruction *insn;
+ bool skip_orig;
};
const char *objname;
for (insn = next_insn_same_sec(file, insn); insn; \
insn = next_insn_same_sec(file, insn))
-/*
- * Check if the function has been manually whitelisted with the
- * STACK_FRAME_NON_STANDARD macro, or if it should be automatically whitelisted
- * due to its use of a context switching instruction.
- */
-static bool ignore_func(struct objtool_file *file, struct symbol *func)
-{
- struct rela *rela;
-
- /* check for STACK_FRAME_NON_STANDARD */
- if (file->whitelist && file->whitelist->rela)
- list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) {
- if (rela->sym->type == STT_SECTION &&
- rela->sym->sec == func->sec &&
- rela->addend == func->offset)
- return true;
- if (rela->sym->type == STT_FUNC && rela->sym == func)
- return true;
- }
-
- return false;
-}
-
/*
* This checks to see if the given function is a "noreturn" function.
*
struct instruction *insn;
struct section *sec;
struct symbol *func;
+ struct rela *rela;
- for_each_sec(file, sec) {
- list_for_each_entry(func, &sec->symbol_list, list) {
- if (func->type != STT_FUNC)
- continue;
+ sec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard");
+ if (!sec)
+ return;
- if (!ignore_func(file, func))
+ list_for_each_entry(rela, &sec->rela_list, list) {
+ switch (rela->sym->type) {
+ case STT_FUNC:
+ func = rela->sym;
+ break;
+
+ case STT_SECTION:
+ func = find_symbol_by_offset(rela->sym->sec, rela->addend);
+ if (!func || func->type != STT_FUNC)
continue;
+ break;
- func_for_each_insn_all(file, func, insn)
- insn->ignore = true;
+ default:
+ WARN("unexpected relocation symbol type in %s: %d", sec->name, rela->sym->type);
+ continue;
}
+
+ func_for_each_insn_all(file, func, insn)
+ insn->ignore = true;
+ }
+}
+
+/*
+ * This is a whitelist of functions that is allowed to be called with AC set.
+ * The list is meant to be minimal and only contains compiler instrumentation
+ * ABI and a few functions used to implement *_{to,from}_user() functions.
+ *
+ * These functions must not directly change AC, but may PUSHF/POPF.
+ */
+static const char *uaccess_safe_builtin[] = {
+ /* KASAN */
+ "kasan_report",
+ "check_memory_region",
+ /* KASAN out-of-line */
+ "__asan_loadN_noabort",
+ "__asan_load1_noabort",
+ "__asan_load2_noabort",
+ "__asan_load4_noabort",
+ "__asan_load8_noabort",
+ "__asan_load16_noabort",
+ "__asan_storeN_noabort",
+ "__asan_store1_noabort",
+ "__asan_store2_noabort",
+ "__asan_store4_noabort",
+ "__asan_store8_noabort",
+ "__asan_store16_noabort",
+ /* KASAN in-line */
+ "__asan_report_load_n_noabort",
+ "__asan_report_load1_noabort",
+ "__asan_report_load2_noabort",
+ "__asan_report_load4_noabort",
+ "__asan_report_load8_noabort",
+ "__asan_report_load16_noabort",
+ "__asan_report_store_n_noabort",
+ "__asan_report_store1_noabort",
+ "__asan_report_store2_noabort",
+ "__asan_report_store4_noabort",
+ "__asan_report_store8_noabort",
+ "__asan_report_store16_noabort",
+ /* KCOV */
+ "write_comp_data",
+ "__sanitizer_cov_trace_pc",
+ "__sanitizer_cov_trace_const_cmp1",
+ "__sanitizer_cov_trace_const_cmp2",
+ "__sanitizer_cov_trace_const_cmp4",
+ "__sanitizer_cov_trace_const_cmp8",
+ "__sanitizer_cov_trace_cmp1",
+ "__sanitizer_cov_trace_cmp2",
+ "__sanitizer_cov_trace_cmp4",
+ "__sanitizer_cov_trace_cmp8",
+ /* UBSAN */
+ "ubsan_type_mismatch_common",
+ "__ubsan_handle_type_mismatch",
+ "__ubsan_handle_type_mismatch_v1",
+ /* misc */
+ "csum_partial_copy_generic",
+ "__memcpy_mcsafe",
+ "ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */
+ NULL
+};
+
+static void add_uaccess_safe(struct objtool_file *file)
+{
+ struct symbol *func;
+ const char **name;
+
+ if (!uaccess)
+ return;
+
+ for (name = uaccess_safe_builtin; *name; name++) {
+ func = find_symbol_by_name(file->elf, *name);
+ if (!func)
+ continue;
+
+ func->alias->uaccess_safe = true;
}
}
* But it at least allows objtool to understand the control flow *around* the
* retpoline.
*/
-static int add_nospec_ignores(struct objtool_file *file)
+static int add_ignore_alternatives(struct objtool_file *file)
{
struct section *sec;
struct rela *rela;
struct instruction *insn;
- sec = find_section_by_name(file->elf, ".rela.discard.nospec");
+ sec = find_section_by_name(file->elf, ".rela.discard.ignore_alts");
if (!sec)
return 0;
insn = find_insn(file, rela->sym->sec, rela->addend);
if (!insn) {
- WARN("bad .discard.nospec entry");
+ WARN("bad .discard.ignore_alts entry");
return -1;
}
continue;
} else {
/* sibling call */
- insn->jump_dest = 0;
+ insn->call_dest = rela->sym;
+ insn->jump_dest = NULL;
continue;
}
}
/*
- * For GCC 8+, create parent/child links for any cold
- * subfunctions. This is _mostly_ redundant with a similar
- * initialization in read_symbols().
- *
- * If a function has aliases, we want the *first* such function
- * in the symbol table to be the subfunction's parent. In that
- * case we overwrite the initialization done in read_symbols().
- *
- * However this code can't completely replace the
- * read_symbols() code because this doesn't detect the case
- * where the parent function's only reference to a subfunction
- * is through a switch table.
+ * Cross-function jump.
*/
if (insn->func && insn->jump_dest->func &&
- insn->func != insn->jump_dest->func &&
- !strstr(insn->func->name, ".cold.") &&
- strstr(insn->jump_dest->func->name, ".cold.")) {
- insn->func->cfunc = insn->jump_dest->func;
- insn->jump_dest->func->pfunc = insn->func;
+ insn->func != insn->jump_dest->func) {
+
+ /*
+ * For GCC 8+, create parent/child links for any cold
+ * subfunctions. This is _mostly_ redundant with a
+ * similar initialization in read_symbols().
+ *
+ * If a function has aliases, we want the *first* such
+ * function in the symbol table to be the subfunction's
+ * parent. In that case we overwrite the
+ * initialization done in read_symbols().
+ *
+ * However this code can't completely replace the
+ * read_symbols() code because this doesn't detect the
+ * case where the parent function's only reference to a
+ * subfunction is through a switch table.
+ */
+ if (!strstr(insn->func->name, ".cold.") &&
+ strstr(insn->jump_dest->func->name, ".cold.")) {
+ insn->func->cfunc = insn->jump_dest->func;
+ insn->jump_dest->func->pfunc = insn->func;
+
+ } else if (insn->jump_dest->func->pfunc != insn->func->pfunc &&
+ insn->jump_dest->offset == insn->jump_dest->func->offset) {
+
+ /* sibling class */
+ insn->call_dest = insn->jump_dest->func;
+ insn->jump_dest = NULL;
+ }
}
}
* conditionally jumps to the _end_ of the entry. We have to modify these
* jumps' destinations to point back to .text rather than the end of the
* entry in .altinstr_replacement.
- *
- * 4. It has been requested that we don't validate the !POPCNT feature path
- * which is a "very very small percentage of machines".
*/
static int handle_group_alt(struct objtool_file *file,
struct special_alt *special_alt,
if (insn->offset >= special_alt->orig_off + special_alt->orig_len)
break;
- if (special_alt->skip_orig)
- insn->type = INSN_NOP;
-
insn->alt_group = true;
last_orig_insn = insn;
}
last_new_insn = insn;
insn->ignore = orig_insn->ignore_alts;
+ insn->func = orig_insn->func;
if (insn->type != INSN_JUMP_CONDITIONAL &&
insn->type != INSN_JUMP_UNCONDITIONAL)
}
alt->insn = new_insn;
+ alt->skip_orig = special_alt->skip_orig;
+ orig_insn->ignore_alts |= special_alt->skip_alt;
list_add_tail(&alt->list, &orig_insn->alts);
list_del(&special_alt->list);
return ret;
add_ignores(file);
+ add_uaccess_safe(file);
- ret = add_nospec_ignores(file);
+ ret = add_ignore_alternatives(file);
if (ret)
return ret;
return 0;
/* push */
- if (op->dest.type == OP_DEST_PUSH)
+ if (op->dest.type == OP_DEST_PUSH || op->dest.type == OP_DEST_PUSHF)
cfa->offset += 8;
/* pop */
- if (op->src.type == OP_SRC_POP)
+ if (op->src.type == OP_SRC_POP || op->src.type == OP_SRC_POPF)
cfa->offset -= 8;
/* add immediate to sp */
break;
case OP_SRC_POP:
+ case OP_SRC_POPF:
if (!state->drap && op->dest.type == OP_DEST_REG &&
op->dest.reg == cfa->base) {
break;
case OP_DEST_PUSH:
+ case OP_DEST_PUSHF:
state->stack_size += 8;
if (cfa->base == CFI_SP)
cfa->offset += 8;
break;
case OP_DEST_MEM:
- if (op->src.type != OP_SRC_POP) {
+ if (op->src.type != OP_SRC_POP && op->src.type != OP_SRC_POPF) {
WARN_FUNC("unknown stack-related memory operation",
insn->sec, insn->offset);
return -1;
return false;
}
+static inline bool func_uaccess_safe(struct symbol *func)
+{
+ if (func)
+ return func->alias->uaccess_safe;
+
+ return false;
+}
+
+static inline const char *insn_dest_name(struct instruction *insn)
+{
+ if (insn->call_dest)
+ return insn->call_dest->name;
+
+ return "{dynamic}";
+}
+
+static int validate_call(struct instruction *insn, struct insn_state *state)
+{
+ if (state->uaccess && !func_uaccess_safe(insn->call_dest)) {
+ WARN_FUNC("call to %s() with UACCESS enabled",
+ insn->sec, insn->offset, insn_dest_name(insn));
+ return 1;
+ }
+
+ if (state->df) {
+ WARN_FUNC("call to %s() with DF set",
+ insn->sec, insn->offset, insn_dest_name(insn));
+ return 1;
+ }
+
+ return 0;
+}
+
+static int validate_sibling_call(struct instruction *insn, struct insn_state *state)
+{
+ if (has_modified_stack_frame(state)) {
+ WARN_FUNC("sibling call from callable instruction with modified stack frame",
+ insn->sec, insn->offset);
+ return 1;
+ }
+
+ return validate_call(insn, state);
+}
+
/*
* Follow the branch starting at the given instruction, and recursively follow
* any other branches (jumps). Meanwhile, track the frame pointer state at
if (!insn->hint && !insn_state_match(insn, &state))
return 1;
- return 0;
+ /* If we were here with AC=0, but now have AC=1, go again */
+ if (insn->state.uaccess || !state.uaccess)
+ return 0;
}
if (insn->hint) {
insn->visited = true;
if (!insn->ignore_alts) {
+ bool skip_orig = false;
+
list_for_each_entry(alt, &insn->alts, list) {
+ if (alt->skip_orig)
+ skip_orig = true;
+
ret = validate_branch(file, alt->insn, state);
- if (ret)
- return 1;
+ if (ret) {
+ if (backtrace)
+ BT_FUNC("(alt)", insn);
+ return ret;
+ }
}
+
+ if (skip_orig)
+ return 0;
}
switch (insn->type) {
case INSN_RETURN:
+ if (state.uaccess && !func_uaccess_safe(func)) {
+ WARN_FUNC("return with UACCESS enabled", sec, insn->offset);
+ return 1;
+ }
+
+ if (!state.uaccess && func_uaccess_safe(func)) {
+ WARN_FUNC("return with UACCESS disabled from a UACCESS-safe function", sec, insn->offset);
+ return 1;
+ }
+
+ if (state.df) {
+ WARN_FUNC("return with DF set", sec, insn->offset);
+ return 1;
+ }
+
if (func && has_modified_stack_frame(&state)) {
WARN_FUNC("return with modified stack frame",
sec, insn->offset);
return 0;
case INSN_CALL:
- if (is_fentry_call(insn))
- break;
+ case INSN_CALL_DYNAMIC:
+ ret = validate_call(insn, &state);
+ if (ret)
+ return ret;
- ret = dead_end_function(file, insn->call_dest);
- if (ret == 1)
- return 0;
- if (ret == -1)
- return 1;
+ if (insn->type == INSN_CALL) {
+ if (is_fentry_call(insn))
+ break;
+
+ ret = dead_end_function(file, insn->call_dest);
+ if (ret == 1)
+ return 0;
+ if (ret == -1)
+ return 1;
+ }
- /* fallthrough */
- case INSN_CALL_DYNAMIC:
if (!no_fp && func && !has_valid_stack_frame(&state)) {
WARN_FUNC("call without frame pointer save/setup",
sec, insn->offset);
case INSN_JUMP_CONDITIONAL:
case INSN_JUMP_UNCONDITIONAL:
- if (insn->jump_dest &&
- (!func || !insn->jump_dest->func ||
- insn->jump_dest->func->pfunc == func)) {
- ret = validate_branch(file, insn->jump_dest,
- state);
+ if (func && !insn->jump_dest) {
+ ret = validate_sibling_call(insn, &state);
if (ret)
- return 1;
+ return ret;
- } else if (func && has_modified_stack_frame(&state)) {
- WARN_FUNC("sibling call from callable instruction with modified stack frame",
- sec, insn->offset);
- return 1;
+ } else if (insn->jump_dest &&
+ (!func || !insn->jump_dest->func ||
+ insn->jump_dest->func->pfunc == func)) {
+ ret = validate_branch(file, insn->jump_dest,
+ state);
+ if (ret) {
+ if (backtrace)
+ BT_FUNC("(branch)", insn);
+ return ret;
+ }
}
if (insn->type == INSN_JUMP_UNCONDITIONAL)
break;
case INSN_JUMP_DYNAMIC:
- if (func && list_empty(&insn->alts) &&
- has_modified_stack_frame(&state)) {
- WARN_FUNC("sibling call from callable instruction with modified stack frame",
- sec, insn->offset);
- return 1;
+ if (func && list_empty(&insn->alts)) {
+ ret = validate_sibling_call(insn, &state);
+ if (ret)
+ return ret;
}
return 0;
if (update_insn_state(insn, &state))
return 1;
+ if (insn->stack_op.dest.type == OP_DEST_PUSHF) {
+ if (!state.uaccess_stack) {
+ state.uaccess_stack = 1;
+ } else if (state.uaccess_stack >> 31) {
+ WARN_FUNC("PUSHF stack exhausted", sec, insn->offset);
+ return 1;
+ }
+ state.uaccess_stack <<= 1;
+ state.uaccess_stack |= state.uaccess;
+ }
+
+ if (insn->stack_op.src.type == OP_SRC_POPF) {
+ if (state.uaccess_stack) {
+ state.uaccess = state.uaccess_stack & 1;
+ state.uaccess_stack >>= 1;
+ if (state.uaccess_stack == 1)
+ state.uaccess_stack = 0;
+ }
+ }
+
+ break;
+
+ case INSN_STAC:
+ if (state.uaccess) {
+ WARN_FUNC("recursive UACCESS enable", sec, insn->offset);
+ return 1;
+ }
+
+ state.uaccess = true;
+ break;
+
+ case INSN_CLAC:
+ if (!state.uaccess && insn->func) {
+ WARN_FUNC("redundant UACCESS disable", sec, insn->offset);
+ return 1;
+ }
+
+ if (func_uaccess_safe(func) && !state.uaccess_stack) {
+ WARN_FUNC("UACCESS-safe disables UACCESS", sec, insn->offset);
+ return 1;
+ }
+
+ state.uaccess = false;
+ break;
+
+ case INSN_STD:
+ if (state.df)
+ WARN_FUNC("recursive STD", sec, insn->offset);
+
+ state.df = true;
+ break;
+
+ case INSN_CLD:
+ if (!state.df && insn->func)
+ WARN_FUNC("redundant CLD", sec, insn->offset);
+
+ state.df = false;
break;
default:
for_each_insn(file, insn) {
if (insn->hint && !insn->visited) {
ret = validate_branch(file, insn, state);
+ if (ret && backtrace)
+ BT_FUNC("<=== (hint)", insn);
warnings += ret;
}
}
if (!insn || insn->ignore)
continue;
+ state.uaccess = func->alias->uaccess_safe;
+
ret = validate_branch(file, insn, state);
+ if (ret && backtrace)
+ BT_FUNC("<=== (func)", insn);
warnings += ret;
}
}
INIT_LIST_HEAD(&file.insn_list);
hash_init(file.insn_hash);
- file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard");
file.c_file = find_section_by_name(file.elf, ".comment");
file.ignore_unreachables = no_unreachable;
file.hints = false;
int stack_size;
unsigned char type;
bool bp_scratch;
- bool drap, end;
+ bool drap, end, uaccess, df;
+ unsigned int uaccess_stack;
int drap_reg, drap_offset;
struct cfi_reg vals[CFI_NUM_REGS];
};
struct elf *elf;
struct list_head insn_list;
DECLARE_HASHTABLE(insn_hash, 16);
- struct section *whitelist;
bool ignore_unreachables, c_file, hints, rodata;
};
static int read_symbols(struct elf *elf)
{
struct section *symtab, *sec;
- struct symbol *sym, *pfunc;
+ struct symbol *sym, *pfunc, *alias;
struct list_head *entry, *tmp;
int symbols_nr, i;
char *coldstr;
return -1;
}
memset(sym, 0, sizeof(*sym));
+ alias = sym;
sym->idx = i;
break;
}
- if (sym->offset == s->offset && sym->len >= s->len) {
- entry = tmp;
- break;
+ if (sym->offset == s->offset) {
+ if (sym->len == s->len && alias == sym)
+ alias = s;
+
+ if (sym->len >= s->len) {
+ entry = tmp;
+ break;
+ }
}
}
+ sym->alias = alias;
list_add(&sym->list, entry);
hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
}
unsigned char bind, type;
unsigned long offset;
unsigned int len;
- struct symbol *pfunc, *cfunc;
+ struct symbol *pfunc, *cfunc, *alias;
+ bool uaccess_safe;
};
struct rela {
#include <stdlib.h>
#include <string.h>
+#include "builtin.h"
#include "special.h"
#include "warn.h"
#define ALT_NEW_LEN_OFFSET 11
#define X86_FEATURE_POPCNT (4*32+23)
+#define X86_FEATURE_SMAP (9*32+20)
struct special_entry {
const char *sec;
*/
if (feature == X86_FEATURE_POPCNT)
alt->skip_orig = true;
+
+ /*
+ * If UACCESS validation is enabled; force that alternative;
+ * otherwise force it the other way.
+ *
+ * What we want to avoid is having both the original and the
+ * alternative code flow at the same time, in that case we can
+ * find paths that see the STAC but take the NOP instead of
+ * CLAC and the other way around.
+ */
+ if (feature == X86_FEATURE_SMAP) {
+ if (uaccess)
+ alt->skip_orig = true;
+ else
+ alt->skip_alt = true;
+ }
}
orig_rela = find_rela_by_dest(sec, offset + entry->orig);
bool group;
bool skip_orig;
+ bool skip_alt;
bool jump_or_nop;
struct section *orig_sec;
free(_str); \
})
+#define BT_FUNC(format, insn, ...) \
+({ \
+ struct instruction *_insn = (insn); \
+ char *_str = offstr(_insn->sec, _insn->offset); \
+ WARN(" %s: " format, _str, ##__VA_ARGS__); \
+ free(_str); \
+})
+
#define WARN_ELF(format, ...) \
WARN(format ": %s", ##__VA_ARGS__, elf_errmsg(-1))
node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
cpu - thread affinity mask is set to cpu of the processed mmap buffer
+--mmap-flush=number::
+
+Specify minimal number of bytes that is extracted from mmap data pages and
+processed for output. One can specify the number using B/K/M/G suffixes.
+
+The maximal allowed value is a quarter of the size of mmaped data pages.
+
+The default option value is 1 byte which means that every time that the output
+writing thread finds some new data in the mmaped buffer the data is extracted,
+possibly compressed (-z) and written to the output, perf.data or pipe.
+
+Larger data chunks are compressed more effectively in comparison to smaller
+chunks so extraction of larger chunks from the mmap data pages is preferable
+from the perspective of output size reduction.
+
+Also at some cases executing less output write syscalls with bigger data size
+can take less time than executing more output write syscalls with smaller data
+size thus lowering runtime profiling overhead.
+
--all-kernel::
Configure all used events to run in kernel space.
FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
+ifdef LIBZSTD_DIR
+ LIBZSTD_CFLAGS := -I$(LIBZSTD_DIR)/lib
+ LIBZSTD_LDFLAGS := -L$(LIBZSTD_DIR)/lib
+endif
+FEATURE_CHECK_CFLAGS-libzstd := $(LIBZSTD_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libzstd := $(LIBZSTD_LDFLAGS)
+
FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
# include ARCH specific config
-include $(src-perf)/arch/$(SRCARCH)/Makefile
FEATURE_CHECK_LDFLAGS-libaio = -lrt
-FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes
+FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
CFLAGS += -fno-omit-frame-pointer
CFLAGS += -ggdb3
endif
endif
+ifndef NO_LIBZSTD
+ ifeq ($(feature-libzstd), 1)
+ CFLAGS += -DHAVE_ZSTD_SUPPORT
+ CFLAGS += $(LIBZSTD_CFLAGS)
+ LDFLAGS += $(LIBZSTD_LDFLAGS)
+ EXTLIBS += -lzstd
+ $(call detected,CONFIG_ZSTD)
+ else
+ msg := $(warning No libzstd found, disables trace compression, please install libzstd-dev[el] and/or set LIBZSTD_DIR);
+ NO_LIBZSTD := 1
+ endif
+endif
+
ifndef NO_BACKTRACE
ifeq ($(feature-backtrace), 1)
CFLAGS += -DHAVE_BACKTRACE_SUPPORT
# streaming for record mode. Currently Posix AIO trace streaming is
# supported only when linking with glibc.
#
+# Define NO_LIBZSTD if you do not want support of Zstandard based runtime
+# trace compression in record mode.
+#
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
#include <numa.h>
#include <numaif.h>
+#ifndef RUSAGE_THREAD
+# define RUSAGE_THREAD 1
+#endif
+
/*
* Regular printout to the terminal, supressed if -q is specified:
*/
goto out_delete;
}
- kmem_page_size = tep_get_page_size(evsel->tp_format->pevent);
+ kmem_page_size = tep_get_page_size(evsel->tp_format->tep);
symbol_conf.use_callchain = true;
}
print_symbol_events(NULL, PERF_TYPE_HARDWARE,
event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
else if (strcmp(argv[i], "sw") == 0 ||
- strcmp(argv[i], "software") == 0)
+ strcmp(argv[i], "software") == 0) {
print_symbol_events(NULL, PERF_TYPE_SOFTWARE,
event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
- else if (strcmp(argv[i], "cache") == 0 ||
+ print_tool_events(NULL, raw_dump);
+ } else if (strcmp(argv[i], "cache") == 0 ||
strcmp(argv[i], "hwcache") == 0)
print_hwcache_events(NULL, raw_dump);
else if (strcmp(argv[i], "pmu") == 0)
event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
print_symbol_events(s, PERF_TYPE_SOFTWARE,
event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
+ print_tool_events(s, raw_dump);
print_hwcache_events(s, raw_dump);
print_pmu_events(s, raw_dump, !desc_flag,
long_desc_flag,
return rec->opts.nr_cblocks > 0;
}
+#define MMAP_FLUSH_DEFAULT 1
+static int record__mmap_flush_parse(const struct option *opt,
+ const char *str,
+ int unset)
+{
+ int flush_max;
+ struct record_opts *opts = (struct record_opts *)opt->value;
+ static struct parse_tag tags[] = {
+ { .tag = 'B', .mult = 1 },
+ { .tag = 'K', .mult = 1 << 10 },
+ { .tag = 'M', .mult = 1 << 20 },
+ { .tag = 'G', .mult = 1 << 30 },
+ { .tag = 0 },
+ };
+
+ if (unset)
+ return 0;
+
+ if (str) {
+ opts->mmap_flush = parse_tag_value(str, tags);
+ if (opts->mmap_flush == (int)-1)
+ opts->mmap_flush = strtol(str, NULL, 0);
+ }
+
+ if (!opts->mmap_flush)
+ opts->mmap_flush = MMAP_FLUSH_DEFAULT;
+
+ flush_max = perf_evlist__mmap_size(opts->mmap_pages);
+ flush_max /= 4;
+ if (opts->mmap_flush > flush_max)
+ opts->mmap_flush = flush_max;
+
+ return 0;
+}
+
static int process_synthesized_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
opts->auxtrace_mmap_pages,
opts->auxtrace_snapshot_mode,
- opts->nr_cblocks, opts->affinity) < 0) {
+ opts->nr_cblocks, opts->affinity,
+ opts->mmap_flush) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
}
static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
- bool overwrite)
+ bool overwrite, bool synch)
{
u64 bytes_written = rec->bytes_written;
int i;
off = record__aio_get_pos(trace_fd);
for (i = 0; i < evlist->nr_mmaps; i++) {
+ u64 flush = 0;
struct perf_mmap *map = &maps[i];
if (map->base) {
record__adjust_affinity(rec, map);
+ if (synch) {
+ flush = map->flush;
+ map->flush = 1;
+ }
if (!record__aio_enabled(rec)) {
if (perf_mmap__push(map, rec, record__pushfn) != 0) {
+ if (synch)
+ map->flush = flush;
rc = -1;
goto out;
}
idx = record__aio_sync(map, false);
if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) {
record__aio_set_pos(trace_fd, off);
+ if (synch)
+ map->flush = flush;
rc = -1;
goto out;
}
}
+ if (synch)
+ map->flush = flush;
}
if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
return rc;
}
-static int record__mmap_read_all(struct record *rec)
+static int record__mmap_read_all(struct record *rec, bool synch)
{
int err;
- err = record__mmap_read_evlist(rec, rec->evlist, false);
+ err = record__mmap_read_evlist(rec, rec->evlist, false, synch);
if (err)
return err;
- return record__mmap_read_evlist(rec, rec->evlist, true);
+ return record__mmap_read_evlist(rec, rec->evlist, true, synch);
}
static void record__init_features(struct record *rec)
if (trigger_is_hit(&switch_output_trigger) || done || draining)
perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
- if (record__mmap_read_all(rec) < 0) {
+ if (record__mmap_read_all(rec, false) < 0) {
trigger_error(&auxtrace_snapshot_trigger);
trigger_error(&switch_output_trigger);
err = -1;
record__synthesize_workload(rec, true);
out_child:
+ record__mmap_read_all(rec, true);
record__aio_mmap_read_sync(rec);
if (forks) {
.uses_mmap = true,
.default_per_cpu = true,
},
+ .mmap_flush = MMAP_FLUSH_DEFAULT,
},
.tool = {
.sample = process_sample_event,
OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
"number of mmap data pages and AUX area tracing mmap pages",
record__parse_mmap_pages),
+ OPT_CALLBACK(0, "mmap-flush", &record.opts, "number",
+ "Minimal number of bytes that is extracted from mmap data pages (default: 1)",
+ record__mmap_flush_parse),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &callchain_param,
pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);
pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+ pr_debug("mmap flush: %d\n", rec->opts.mmap_flush);
err = __cmd_record(&record, argc, argv);
out:
process_synthesized_event, NULL);
}
+static int read_single_counter(struct perf_evsel *counter, int cpu,
+ int thread, struct timespec *rs)
+{
+ if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
+ u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
+ struct perf_counts_values *count =
+ perf_counts(counter->counts, cpu, thread);
+ count->ena = count->run = val;
+ count->val = val;
+ return 0;
+ }
+ return perf_evsel__read_counter(counter, cpu, thread);
+}
+
/*
* Read out the results of a single counter:
* do not aggregate counts across CPUs in system-wide mode
*/
-static int read_counter(struct perf_evsel *counter)
+static int read_counter(struct perf_evsel *counter, struct timespec *rs)
{
int nthreads = thread_map__nr(evsel_list->threads);
int ncpus, cpu, thread;
* (via perf_evsel__read_counter) and sets threir count->loaded.
*/
if (!count->loaded &&
- perf_evsel__read_counter(counter, cpu, thread)) {
+ read_single_counter(counter, cpu, thread, rs)) {
counter->counts->scaled = -1;
perf_counts(counter->counts, cpu, thread)->ena = 0;
perf_counts(counter->counts, cpu, thread)->run = 0;
return 0;
}
-static void read_counters(void)
+static void read_counters(struct timespec *rs)
{
struct perf_evsel *counter;
int ret;
evlist__for_each_entry(evsel_list, counter) {
- ret = read_counter(counter);
+ ret = read_counter(counter, rs);
if (ret)
pr_debug("failed to read counter %s\n", counter->name);
{
struct timespec ts, rs;
- read_counters();
-
clock_gettime(CLOCK_MONOTONIC, &ts);
diff_timespec(&rs, &ts, &ref_time);
+ read_counters(&rs);
+
if (STAT_RECORD) {
if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL))
pr_err("failed to write stat round event\n");
* avoid arbitrary skew, we must read all counters before closing any
* group leaders.
*/
- read_counters();
+ read_counters(&(struct timespec) { .tv_nsec = t1-t0 });
perf_evlist__close(evsel_list);
return WEXITSTATUS(status);
for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
perf_header__set_feat(&session->header, feat);
+ perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
* */
.overwrite = 0,
.sample_time = true,
+ .sample_time_set = true,
},
.max_stack = sysctl__max_stack(),
.annotation_opts = annotation__default_options,
STATUS(HAVE_LZMA_SUPPORT, lzma);
STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid);
STATUS(HAVE_LIBBPF_SUPPORT, bpf);
+ STATUS(HAVE_AIO_SUPPORT, aio);
+ STATUS(HAVE_ZSTD_SUPPORT, zstd);
}
int cmd_version(int argc, const char **argv)
*/
#include <unistd.h>
+#include <linux/limits.h>
#include <pid_filter.h>
/* bpf-output associated map */
struct augmented_filename {
unsigned int size;
int reserved;
- char value[256];
+ char value[PATH_MAX];
};
-#define SYS_OPEN 2
-#define SYS_ACCESS 21
-#define SYS_OPENAT 257
+/* syscalls where the first arg is a string */
+#define SYS_OPEN 2
+#define SYS_STAT 4
+#define SYS_LSTAT 6
+#define SYS_ACCESS 21
+#define SYS_EXECVE 59
+#define SYS_TRUNCATE 76
+#define SYS_CHDIR 80
+#define SYS_RENAME 82
+#define SYS_MKDIR 83
+#define SYS_RMDIR 84
+#define SYS_CREAT 85
+#define SYS_LINK 86
+#define SYS_UNLINK 87
+#define SYS_SYMLINK 88
+#define SYS_READLINK 89
+#define SYS_CHMOD 90
+#define SYS_CHOWN 92
+#define SYS_LCHOWN 94
+#define SYS_MKNOD 133
+#define SYS_STATFS 137
+#define SYS_PIVOT_ROOT 155
+#define SYS_CHROOT 161
+#define SYS_ACCT 163
+#define SYS_SWAPON 167
+#define SYS_SWAPOFF 168
+#define SYS_DELETE_MODULE 176
+#define SYS_SETXATTR 188
+#define SYS_LSETXATTR 189
+#define SYS_GETXATTR 191
+#define SYS_LGETXATTR 192
+#define SYS_LISTXATTR 194
+#define SYS_LLISTXATTR 195
+#define SYS_REMOVEXATTR 197
+#define SYS_LREMOVEXATTR 198
+#define SYS_MQ_OPEN 240
+#define SYS_MQ_UNLINK 241
+#define SYS_ADD_KEY 248
+#define SYS_REQUEST_KEY 249
+#define SYS_SYMLINKAT 266
+#define SYS_MEMFD_CREATE 319
+
+/* syscalls where the first arg is a string */
+
+#define SYS_PWRITE64 18
+#define SYS_EXECVE 59
+#define SYS_RENAME 82
+#define SYS_QUOTACTL 179
+#define SYS_FSETXATTR 190
+#define SYS_FGETXATTR 193
+#define SYS_FREMOVEXATTR 199
+#define SYS_MQ_TIMEDSEND 242
+#define SYS_REQUEST_KEY 249
+#define SYS_INOTIFY_ADD_WATCH 254
+#define SYS_OPENAT 257
+#define SYS_MKDIRAT 258
+#define SYS_MKNODAT 259
+#define SYS_FCHOWNAT 260
+#define SYS_FUTIMESAT 261
+#define SYS_NEWFSTATAT 262
+#define SYS_UNLINKAT 263
+#define SYS_RENAMEAT 264
+#define SYS_LINKAT 265
+#define SYS_READLINKAT 267
+#define SYS_FCHMODAT 268
+#define SYS_FACCESSAT 269
+#define SYS_UTIMENSAT 280
+#define SYS_NAME_TO_HANDLE_AT 303
+#define SYS_FINIT_MODULE 313
+#define SYS_RENAMEAT2 316
+#define SYS_EXECVEAT 322
+#define SYS_STATX 332
pid_filter(pids_filtered);
+struct augmented_args_filename {
+ struct syscall_enter_args args;
+ struct augmented_filename filename;
+};
+
+bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1);
+
SEC("raw_syscalls:sys_enter")
int sys_enter(struct syscall_enter_args *args)
{
- struct {
- struct syscall_enter_args args;
- struct augmented_filename filename;
- } augmented_args;
- struct syscall *syscall;
- unsigned int len = sizeof(augmented_args);
+ struct augmented_args_filename *augmented_args;
+ unsigned int len = sizeof(*augmented_args);
const void *filename_arg = NULL;
+ struct syscall *syscall;
+ int key = 0;
+
+ augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key);
+ if (augmented_args == NULL)
+ return 1;
if (pid_filter__has(&pids_filtered, getpid()))
return 0;
- probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+ probe_read(&augmented_args->args, sizeof(augmented_args->args), args);
- syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr);
+ syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr);
if (syscall == NULL || !syscall->enabled)
return 0;
/*
*
* after the ctx memory access to prevent their down stream merging.
*/
- switch (augmented_args.args.syscall_nr) {
+ /*
+ * This table of what args are strings will be provided by userspace,
+ * in the syscalls map, i.e. we will already have to do the lookup to
+ * see if this specific syscall is filtered, so we can as well get more
+ * info about what syscall args are strings or pointers, and how many
+ * bytes to copy, per arg, etc.
+ *
+ * For now hard code it, till we have all the basic mechanisms in place
+ * to automate everything and make the kernel part be completely driven
+ * by information obtained in userspace for each kernel version and
+ * processor architecture, making the kernel part the same no matter what
+ * kernel version or processor architecture it runs on.
+ */
+ switch (augmented_args->args.syscall_nr) {
+ case SYS_ACCT:
+ case SYS_ADD_KEY:
+ case SYS_CHDIR:
+ case SYS_CHMOD:
+ case SYS_CHOWN:
+ case SYS_CHROOT:
+ case SYS_CREAT:
+ case SYS_DELETE_MODULE:
+ case SYS_EXECVE:
+ case SYS_GETXATTR:
+ case SYS_LCHOWN:
+ case SYS_LGETXATTR:
+ case SYS_LINK:
+ case SYS_LISTXATTR:
+ case SYS_LLISTXATTR:
+ case SYS_LREMOVEXATTR:
+ case SYS_LSETXATTR:
+ case SYS_LSTAT:
+ case SYS_MEMFD_CREATE:
+ case SYS_MKDIR:
+ case SYS_MKNOD:
+ case SYS_MQ_OPEN:
+ case SYS_MQ_UNLINK:
+ case SYS_PIVOT_ROOT:
+ case SYS_READLINK:
+ case SYS_REMOVEXATTR:
+ case SYS_RENAME:
+ case SYS_REQUEST_KEY:
+ case SYS_RMDIR:
+ case SYS_SETXATTR:
+ case SYS_STAT:
+ case SYS_STATFS:
+ case SYS_SWAPOFF:
+ case SYS_SWAPON:
+ case SYS_SYMLINK:
+ case SYS_SYMLINKAT:
+ case SYS_TRUNCATE:
+ case SYS_UNLINK:
case SYS_ACCESS:
case SYS_OPEN: filename_arg = (const void *)args->args[0];
__asm__ __volatile__("": : :"memory");
break;
+ case SYS_EXECVEAT:
+ case SYS_FACCESSAT:
+ case SYS_FCHMODAT:
+ case SYS_FCHOWNAT:
+ case SYS_FGETXATTR:
+ case SYS_FINIT_MODULE:
+ case SYS_FREMOVEXATTR:
+ case SYS_FSETXATTR:
+ case SYS_FUTIMESAT:
+ case SYS_INOTIFY_ADD_WATCH:
+ case SYS_LINKAT:
+ case SYS_MKDIRAT:
+ case SYS_MKNODAT:
+ case SYS_MQ_TIMEDSEND:
+ case SYS_NAME_TO_HANDLE_AT:
+ case SYS_NEWFSTATAT:
+ case SYS_PWRITE64:
+ case SYS_QUOTACTL:
+ case SYS_READLINKAT:
+ case SYS_RENAMEAT:
+ case SYS_RENAMEAT2:
+ case SYS_STATX:
+ case SYS_UNLINKAT:
+ case SYS_UTIMENSAT:
case SYS_OPENAT: filename_arg = (const void *)args->args[1];
break;
}
if (filename_arg != NULL) {
- augmented_args.filename.reserved = 0;
- augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
- sizeof(augmented_args.filename.value),
+ augmented_args->filename.reserved = 0;
+ augmented_args->filename.size = probe_read_str(&augmented_args->filename.value,
+ sizeof(augmented_args->filename.value),
filename_arg);
- if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
- len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
- len &= sizeof(augmented_args.filename.value) - 1;
+ if (augmented_args->filename.size < sizeof(augmented_args->filename.value)) {
+ len -= sizeof(augmented_args->filename.value) - augmented_args->filename.size;
+ len &= sizeof(augmented_args->filename.value) - 1;
}
} else {
- len = sizeof(augmented_args.args);
+ len = sizeof(augmented_args->args);
}
/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
- return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
+ return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
}
SEC("raw_syscalls:sys_exit")
u64 clockid_res_ns;
int nr_cblocks;
int affinity;
+ int mmap_flush;
};
enum perf_affinity {
"EventCode": "128",
"EventName": "L1D_RO_EXCL_WRITES",
"BriefDescription": "L1D Read-only Exclusive Writes",
- "PublicDescription": "Counter:128 Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+ "PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
},
{
"Unit": "CPU-M-CF",
"UMask": "0x1",
"EventName": "UOPS.MS_CYCLES",
"SampleAfterValue": "2000000",
- "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ. ",
+ "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ.",
"CounterMask": "1"
}
]
\ No newline at end of file
"UMask": "0x8",
"EventName": "BR_MISSP_TYPE_RETIRED.IND_CALL",
"SampleAfterValue": "200000",
- "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect. "
+ "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect."
},
{
"EventCode": "0x89",
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Instruction per taken branch",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "IpTB"
+ },
+ {
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Branch instructions per taken branch. ",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "BpTB"
+ },
+ {
"MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
- "MetricGroup": "Frontend",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+ "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+ "MetricGroup": "Instruction_Type;L1_Bound",
+ "MetricName": "IpL"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+ "BriefDescription": "Instructions per Store",
+ "MetricGroup": "Instruction_Type;Store_Bound",
+ "MetricName": "IpS"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Instructions per Branch",
+ "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+ "MetricName": "IpB"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "BriefDescription": "Instruction per (near) call",
+ "MetricGroup": "Branches",
+ "MetricName": "IpCall"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS",
+ "MetricName": "FLOPc"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS_SMT",
+ "MetricName": "FLOPc_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
- "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
- "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
- "MetricGroup": "Unknown_Branches",
- "MetricName": "BAClear_Cost"
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "Branch_Misprediction_Cost"
},
{
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts_SMT",
+ "MetricName": "Branch_Misprediction_Cost_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "IpMispredict"
+ },
+ {
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
- "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
- "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
+ "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / cycles",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
- "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
- "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricGroup": "TLB_SMT",
+ "MetricName": "Page_Walks_Utilization_SMT"
+ },
+ {
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L1MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI"
+ },
+ {
+ "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2HPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L3MPKI"
+ },
+ {
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
+ "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+ "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.",
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x41",
+ "UMask": "0xc1",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "Demand Data Read requests that hit L2 cache",
{
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x42",
+ "UMask": "0xc2",
"EventName": "L2_RQSTS.RFO_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "RFO requests that hit L2 cache.",
{
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x44",
+ "UMask": "0xc4",
"EventName": "L2_RQSTS.CODE_RD_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "L2 cache hits when fetching instructions, code reads.",
"PublicDescription": "This event counts the number of requests from the L2 hardware prefetchers that hit L2 cache. L3 prefetch new types.",
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x50",
+ "UMask": "0xd0",
"EventName": "L2_RQSTS.L2_PF_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "L2 prefetch requests that hit L2 cache",
},
{
"PEBS": "1",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x41",
},
{
"PEBS": "1",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x42",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010001 ",
+ "MSRValue": "0x0000010001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that have any response type.",
+ "BriefDescription": "Counts demand data reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020001 ",
+ "MSRValue": "0x0080020001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020001 ",
+ "MSRValue": "0x0100020001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020001 ",
+ "MSRValue": "0x0200020001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020001 ",
+ "MSRValue": "0x0400020001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020001 ",
+ "MSRValue": "0x1000020001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020001 ",
+ "MSRValue": "0x3F80020001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0001 ",
+ "MSRValue": "0x00803C0001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0001 ",
+ "MSRValue": "0x01003C0001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0001 ",
+ "MSRValue": "0x02003C0001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0001 ",
+ "MSRValue": "0x04003C0001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0001 ",
+ "MSRValue": "0x10003C0001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0001 ",
+ "MSRValue": "0x3F803C0001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3.",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010002 ",
+ "MSRValue": "0x0000010002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.",
+ "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0002 ",
+ "MSRValue": "0x00803C0002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0002 ",
+ "MSRValue": "0x01003C0002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0002 ",
+ "MSRValue": "0x02003C0002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0002 ",
+ "MSRValue": "0x04003C0002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0002 ",
+ "MSRValue": "0x10003C0002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0002 ",
+ "MSRValue": "0x3F803C0002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010004 ",
+ "MSRValue": "0x0000010004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that have any response type.",
+ "BriefDescription": "Counts all demand code reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020004 ",
+ "MSRValue": "0x0080020004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020004 ",
+ "MSRValue": "0x0100020004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020004 ",
+ "MSRValue": "0x0200020004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020004 ",
+ "MSRValue": "0x0400020004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020004 ",
+ "MSRValue": "0x1000020004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020004 ",
+ "MSRValue": "0x3F80020004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0004 ",
+ "MSRValue": "0x00803C0004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0004 ",
+ "MSRValue": "0x01003C0004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0004 ",
+ "MSRValue": "0x02003C0004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0004 ",
+ "MSRValue": "0x04003C0004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0004 ",
+ "MSRValue": "0x10003C0004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0004 ",
+ "MSRValue": "0x3F803C0004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that hit in the L3.",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts writebacks (modified to exclusive) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive) have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010008 ",
+ "MSRValue": "0x0000010008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts writebacks (modified to exclusive) that have any response type.",
+ "BriefDescription": "Counts writebacks (modified to exclusive) have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020008 ",
+ "MSRValue": "0x0080020008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020008 ",
+ "MSRValue": "0x0100020008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020008 ",
+ "MSRValue": "0x0200020008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020008 ",
+ "MSRValue": "0x0400020008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020008 ",
+ "MSRValue": "0x1000020008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020008 ",
+ "MSRValue": "0x3F80020008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0008 ",
+ "MSRValue": "0x00803C0008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0008 ",
+ "MSRValue": "0x01003C0008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0008 ",
+ "MSRValue": "0x02003C0008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0008 ",
+ "MSRValue": "0x04003C0008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0008 ",
+ "MSRValue": "0x10003C0008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0008 ",
+ "MSRValue": "0x3F803C0008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3.",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010010 ",
+ "MSRValue": "0x0000010010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020010 ",
+ "MSRValue": "0x0080020010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020010 ",
+ "MSRValue": "0x0100020010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020010 ",
+ "MSRValue": "0x0200020010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020010 ",
+ "MSRValue": "0x0400020010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020010 ",
+ "MSRValue": "0x1000020010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020010 ",
+ "MSRValue": "0x3F80020010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0010 ",
+ "MSRValue": "0x00803C0010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0010 ",
+ "MSRValue": "0x01003C0010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0010 ",
+ "MSRValue": "0x02003C0010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0010 ",
+ "MSRValue": "0x04003C0010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0010 ",
+ "MSRValue": "0x10003C0010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0010 ",
+ "MSRValue": "0x3F803C0010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010020 ",
+ "MSRValue": "0x0000010020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020020 ",
+ "MSRValue": "0x0080020020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020020 ",
+ "MSRValue": "0x0100020020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020020 ",
+ "MSRValue": "0x0200020020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020020 ",
+ "MSRValue": "0x0400020020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020020 ",
+ "MSRValue": "0x1000020020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020020 ",
+ "MSRValue": "0x3F80020020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0020 ",
+ "MSRValue": "0x00803C0020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0020 ",
+ "MSRValue": "0x01003C0020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0020 ",
+ "MSRValue": "0x02003C0020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0020 ",
+ "MSRValue": "0x04003C0020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0020 ",
+ "MSRValue": "0x10003C0020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0020 ",
+ "MSRValue": "0x3F803C0020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010040 ",
+ "MSRValue": "0x0000010040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020040 ",
+ "MSRValue": "0x0080020040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020040 ",
+ "MSRValue": "0x0100020040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020040 ",
+ "MSRValue": "0x0200020040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020040 ",
+ "MSRValue": "0x0400020040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020040 ",
+ "MSRValue": "0x1000020040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020040 ",
+ "MSRValue": "0x3F80020040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0040 ",
+ "MSRValue": "0x00803C0040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0040 ",
+ "MSRValue": "0x01003C0040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0040 ",
+ "MSRValue": "0x02003C0040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0040 ",
+ "MSRValue": "0x04003C0040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0040 ",
+ "MSRValue": "0x10003C0040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0040 ",
+ "MSRValue": "0x3F803C0040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010080 ",
+ "MSRValue": "0x0000010080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020080 ",
+ "MSRValue": "0x0080020080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020080 ",
+ "MSRValue": "0x0100020080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020080 ",
+ "MSRValue": "0x0200020080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020080 ",
+ "MSRValue": "0x0400020080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020080 ",
+ "MSRValue": "0x1000020080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020080 ",
+ "MSRValue": "0x3F80020080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0080 ",
+ "MSRValue": "0x00803C0080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0080 ",
+ "MSRValue": "0x01003C0080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0080 ",
+ "MSRValue": "0x02003C0080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0080 ",
+ "MSRValue": "0x04003C0080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0080 ",
+ "MSRValue": "0x10003C0080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0080 ",
+ "MSRValue": "0x3F803C0080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010100 ",
+ "MSRValue": "0x0000010100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020100 ",
+ "MSRValue": "0x0080020100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020100 ",
+ "MSRValue": "0x0100020100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020100 ",
+ "MSRValue": "0x0200020100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020100 ",
+ "MSRValue": "0x0400020100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020100 ",
+ "MSRValue": "0x1000020100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020100 ",
+ "MSRValue": "0x3F80020100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0100 ",
+ "MSRValue": "0x00803C0100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0100 ",
+ "MSRValue": "0x01003C0100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0100 ",
+ "MSRValue": "0x02003C0100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0100 ",
+ "MSRValue": "0x04003C0100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0100 ",
+ "MSRValue": "0x10003C0100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0100 ",
+ "MSRValue": "0x3F803C0100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010200 ",
+ "MSRValue": "0x0000010200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type.",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020200 ",
+ "MSRValue": "0x0080020200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020200 ",
+ "MSRValue": "0x0100020200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020200 ",
+ "MSRValue": "0x0200020200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020200 ",
+ "MSRValue": "0x0400020200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020200 ",
+ "MSRValue": "0x1000020200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020200 ",
+ "MSRValue": "0x3F80020200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0200 ",
+ "MSRValue": "0x00803C0200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0200 ",
+ "MSRValue": "0x01003C0200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0200 ",
+ "MSRValue": "0x02003C0200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0200 ",
+ "MSRValue": "0x04003C0200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0200 ",
+ "MSRValue": "0x10003C0200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0200 ",
+ "MSRValue": "0x3F803C0200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3.",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000018000 ",
+ "MSRValue": "0x0000018000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts any other requests that have any response type.",
+ "BriefDescription": "Counts any other requests have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080028000 ",
+ "MSRValue": "0x0080028000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100028000 ",
+ "MSRValue": "0x0100028000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200028000 ",
+ "MSRValue": "0x0200028000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400028000 ",
+ "MSRValue": "0x0400028000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000028000 ",
+ "MSRValue": "0x1000028000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80028000 ",
+ "MSRValue": "0x3F80028000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c8000 ",
+ "MSRValue": "0x00803C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c8000 ",
+ "MSRValue": "0x01003C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts any other requests that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c8000 ",
+ "MSRValue": "0x02003C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts any other requests that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c8000 ",
+ "MSRValue": "0x04003C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c8000 ",
+ "MSRValue": "0x10003C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c8000 ",
+ "MSRValue": "0x3F803C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts any other requests that hit in the L3.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010090 ",
+ "MSRValue": "0x0000010090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch data reads that have any response type.",
+ "BriefDescription": "Counts all prefetch data reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020090 ",
+ "MSRValue": "0x0080020090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020090 ",
+ "MSRValue": "0x0100020090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020090 ",
+ "MSRValue": "0x0200020090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020090 ",
+ "MSRValue": "0x0400020090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020090 ",
+ "MSRValue": "0x1000020090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020090 ",
+ "MSRValue": "0x3F80020090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0090 ",
+ "MSRValue": "0x00803C0090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0090 ",
+ "MSRValue": "0x01003C0090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0090 ",
+ "MSRValue": "0x02003C0090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0090 ",
+ "MSRValue": "0x04003C0090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0090 ",
+ "MSRValue": "0x10003C0090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0090 ",
+ "MSRValue": "0x3F803C0090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3.",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010120 ",
+ "MSRValue": "0x0000010120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch RFOs that have any response type.",
+ "BriefDescription": "Counts prefetch RFOs have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020120 ",
+ "MSRValue": "0x0080020120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020120 ",
+ "MSRValue": "0x0100020120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020120 ",
+ "MSRValue": "0x0200020120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020120 ",
+ "MSRValue": "0x0400020120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020120 ",
+ "MSRValue": "0x1000020120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020120 ",
+ "MSRValue": "0x3F80020120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0120 ",
+ "MSRValue": "0x00803C0120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0120 ",
+ "MSRValue": "0x01003C0120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0120 ",
+ "MSRValue": "0x02003C0120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0120 ",
+ "MSRValue": "0x04003C0120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0120 ",
+ "MSRValue": "0x10003C0120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0120 ",
+ "MSRValue": "0x3F803C0120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3.",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010240 ",
+ "MSRValue": "0x0000010240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch code reads that have any response type.",
+ "BriefDescription": "Counts all prefetch code reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020240 ",
+ "MSRValue": "0x0080020240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020240 ",
+ "MSRValue": "0x0100020240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020240 ",
+ "MSRValue": "0x0200020240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020240 ",
+ "MSRValue": "0x0400020240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020240 ",
+ "MSRValue": "0x1000020240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020240 ",
+ "MSRValue": "0x3F80020240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0240 ",
+ "MSRValue": "0x00803C0240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0240 ",
+ "MSRValue": "0x01003C0240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0240 ",
+ "MSRValue": "0x02003C0240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0240 ",
+ "MSRValue": "0x04003C0240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0240 ",
+ "MSRValue": "0x10003C0240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0240 ",
+ "MSRValue": "0x3F803C0240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch code reads that hit in the L3.",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010091 ",
+ "MSRValue": "0x0000010091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that have any response type.",
+ "BriefDescription": "Counts all demand & prefetch data reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020091 ",
+ "MSRValue": "0x0080020091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020091 ",
+ "MSRValue": "0x0100020091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020091 ",
+ "MSRValue": "0x0200020091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020091 ",
+ "MSRValue": "0x0400020091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020091 ",
+ "MSRValue": "0x1000020091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020091 ",
+ "MSRValue": "0x3F80020091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0091 ",
+ "MSRValue": "0x00803C0091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0091 ",
+ "MSRValue": "0x01003C0091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0091 ",
+ "MSRValue": "0x02003C0091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0091 ",
+ "MSRValue": "0x04003C0091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0091 ",
+ "MSRValue": "0x10003C0091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0091 ",
+ "MSRValue": "0x3F803C0091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010122 ",
+ "MSRValue": "0x0000010122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.",
+ "BriefDescription": "Counts all demand & prefetch RFOs have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020122 ",
+ "MSRValue": "0x0080020122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020122 ",
+ "MSRValue": "0x0100020122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020122 ",
+ "MSRValue": "0x0200020122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020122 ",
+ "MSRValue": "0x0400020122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020122 ",
+ "MSRValue": "0x1000020122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f80020122 ",
+ "MSRValue": "0x3F80020122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00803c0122 ",
+ "MSRValue": "0x00803C0122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01003c0122 ",
+ "MSRValue": "0x01003C0122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02003c0122 ",
+ "MSRValue": "0x02003C0122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0122 ",
+ "MSRValue": "0x04003C0122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0122 ",
+ "MSRValue": "0x10003C0122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0122 ",
+ "MSRValue": "0x3F803C0122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
}
[
{
- "PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
"EventCode": "0xC1",
"Counter": "0,1,2,3",
"UMask": "0x8",
"Errata": "BDM30",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
+ "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
"EventCode": "0xC1",
"Counter": "0,1,2,3",
"UMask": "0x10",
"Errata": "BDM30",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
+ "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"UMask": "0x3",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)",
"CounterHTOff": "0,1,2,3"
},
{
"UMask": "0x4",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
},
{
"UMask": "0x8",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
},
{
"UMask": "0x10",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
},
{
"UMask": "0x15",
"EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
"SampleAfterValue": "2000006",
- "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+ "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
},
{
"UMask": "0x20",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
},
{
"UMask": "0x2a",
"EventName": "FP_ARITH_INST_RETIRED.SINGLE",
"SampleAfterValue": "2000005",
- "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+ "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"CounterHTOff": "0,1,2,3"
},
{
"UMask": "0x3c",
"EventName": "FP_ARITH_INST_RETIRED.PACKED",
"SampleAfterValue": "2000004",
- "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "FP_ASSIST.X87_OUTPUT",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of X87 assists due to output value.",
+ "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "FP_ASSIST.X87_INPUT",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of X87 assists due to input value.",
+ "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of SIMD FP assists due to Output values",
+ "BriefDescription": "SSE* FP micro-code assist when output value is invalid. (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts any input SSE* floating-point (FP) assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "FP_ASSIST.SIMD_INPUT",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of SIMD FP assists due to input values",
+ "BriefDescription": "Any input SSE* FP Assist - (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
+ "PEBS": "1",
+ "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1. Uses PEBS.",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x1e",
"EventName": "FP_ASSIST.ANY",
"SampleAfterValue": "100003",
- "BriefDescription": "Cycles with any input/output SSE or FP assist",
+ "BriefDescription": "Counts any FP_ASSIST umask was incrementing (Precise Event)",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
}
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
+ "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+ "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
"EventCode": "0xAB",
"Counter": "0,1,2,3",
"UMask": "0x2",
},
{
"PEBS": "2",
- "PublicDescription": "This event counts loads with latency value being above four.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above four.",
"EventCode": "0xCD",
"MSRValue": "0x4",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"SampleAfterValue": "100003",
- "BriefDescription": "Loads with latency value being above 4",
+ "BriefDescription": "Randomly selected loads with latency value being above 4",
"TakenAlone": "1",
"CounterHTOff": "3"
},
{
"PEBS": "2",
- "PublicDescription": "This event counts loads with latency value being above eight.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above eight.",
"EventCode": "0xCD",
"MSRValue": "0x8",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"SampleAfterValue": "50021",
- "BriefDescription": "Loads with latency value being above 8",
+ "BriefDescription": "Randomly selected loads with latency value being above 8",
"TakenAlone": "1",
"CounterHTOff": "3"
},
{
"PEBS": "2",
- "PublicDescription": "This event counts loads with latency value being above 16.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 16.",
"EventCode": "0xCD",
"MSRValue": "0x10",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"SampleAfterValue": "20011",
- "BriefDescription": "Loads with latency value being above 16",
+ "BriefDescription": "Randomly selected loads with latency value being above 16",
"TakenAlone": "1",
"CounterHTOff": "3"
},
{
"PEBS": "2",
- "PublicDescription": "This event counts loads with latency value being above 32.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 32.",
"EventCode": "0xCD",
"MSRValue": "0x20",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"SampleAfterValue": "100007",
- "BriefDescription": "Loads with latency value being above 32",
+ "BriefDescription": "Randomly selected loads with latency value being above 32",
"TakenAlone": "1",
"CounterHTOff": "3"
},
{
"PEBS": "2",
- "PublicDescription": "This event counts loads with latency value being above 64.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 64.",
"EventCode": "0xCD",
"MSRValue": "0x40",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"SampleAfterValue": "2003",
- "BriefDescription": "Loads with latency value being above 64",
+ "BriefDescription": "Randomly selected loads with latency value being above 64",
"TakenAlone": "1",
"CounterHTOff": "3"
},
{
"PEBS": "2",
- "PublicDescription": "This event counts loads with latency value being above 128.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 128.",
"EventCode": "0xCD",
"MSRValue": "0x80",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"SampleAfterValue": "1009",
- "BriefDescription": "Loads with latency value being above 128",
+ "BriefDescription": "Randomly selected loads with latency value being above 128",
"TakenAlone": "1",
"CounterHTOff": "3"
},
{
"PEBS": "2",
- "PublicDescription": "This event counts loads with latency value being above 256.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 256.",
"EventCode": "0xCD",
"MSRValue": "0x100",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"SampleAfterValue": "503",
- "BriefDescription": "Loads with latency value being above 256",
+ "BriefDescription": "Randomly selected loads with latency value being above 256",
"TakenAlone": "1",
"CounterHTOff": "3"
},
{
"PEBS": "2",
- "PublicDescription": "This event counts loads with latency value being above 512.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 512.",
"EventCode": "0xCD",
"MSRValue": "0x200",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"SampleAfterValue": "101",
- "BriefDescription": "Loads with latency value being above 512",
+ "BriefDescription": "Randomly selected loads with latency value being above 512",
"TakenAlone": "1",
"CounterHTOff": "3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020001 ",
+ "MSRValue": "0x2000020001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0001 ",
+ "MSRValue": "0x20003C0001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000001 ",
+ "MSRValue": "0x0084000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000001 ",
+ "MSRValue": "0x0104000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000001 ",
+ "MSRValue": "0x0204000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000001 ",
+ "MSRValue": "0x0404000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000001 ",
+ "MSRValue": "0x1004000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000001 ",
+ "MSRValue": "0x2004000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000001 ",
+ "MSRValue": "0x3F84000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000001 ",
+ "MSRValue": "0x00BC000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000001 ",
+ "MSRValue": "0x013C000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000001 ",
+ "MSRValue": "0x023C000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000001 ",
+ "MSRValue": "0x043C000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0002 ",
+ "MSRValue": "0x20003C0002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000002 ",
+ "MSRValue": "0x3F84000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000002 ",
+ "MSRValue": "0x00BC000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000002 ",
+ "MSRValue": "0x013C000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000002 ",
+ "MSRValue": "0x023C000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000002 ",
+ "MSRValue": "0x043C000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020004 ",
+ "MSRValue": "0x2000020004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0004 ",
+ "MSRValue": "0x20003C0004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000004 ",
+ "MSRValue": "0x0084000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000004 ",
+ "MSRValue": "0x0104000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000004 ",
+ "MSRValue": "0x0204000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000004 ",
+ "MSRValue": "0x0404000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000004 ",
+ "MSRValue": "0x1004000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000004 ",
+ "MSRValue": "0x2004000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000004 ",
+ "MSRValue": "0x3F84000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000004 ",
+ "MSRValue": "0x00BC000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000004 ",
+ "MSRValue": "0x013C000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000004 ",
+ "MSRValue": "0x023C000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000004 ",
+ "MSRValue": "0x043C000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020008 ",
+ "MSRValue": "0x2000020008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0008 ",
+ "MSRValue": "0x20003C0008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000008 ",
+ "MSRValue": "0x0084000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000008 ",
+ "MSRValue": "0x0104000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000008 ",
+ "MSRValue": "0x0204000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000008 ",
+ "MSRValue": "0x0404000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000008 ",
+ "MSRValue": "0x1004000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000008 ",
+ "MSRValue": "0x2004000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000008 ",
+ "MSRValue": "0x3F84000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000008 ",
+ "MSRValue": "0x00BC000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000008 ",
+ "MSRValue": "0x013C000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000008 ",
+ "MSRValue": "0x023C000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts writebacks (modified to exclusive)",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000008 ",
+ "MSRValue": "0x043C000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "COREWB & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts writebacks (modified to exclusive)",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020010 ",
+ "MSRValue": "0x2000020010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0010 ",
+ "MSRValue": "0x20003C0010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000010 ",
+ "MSRValue": "0x0084000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000010 ",
+ "MSRValue": "0x0104000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000010 ",
+ "MSRValue": "0x0204000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000010 ",
+ "MSRValue": "0x0404000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000010 ",
+ "MSRValue": "0x1004000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000010 ",
+ "MSRValue": "0x2004000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000010 ",
+ "MSRValue": "0x3F84000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000010 ",
+ "MSRValue": "0x00BC000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000010 ",
+ "MSRValue": "0x013C000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000010 ",
+ "MSRValue": "0x023C000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000010 ",
+ "MSRValue": "0x043C000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020020 ",
+ "MSRValue": "0x2000020020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0020 ",
+ "MSRValue": "0x20003C0020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000020 ",
+ "MSRValue": "0x0084000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000020 ",
+ "MSRValue": "0x0104000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000020 ",
+ "MSRValue": "0x0204000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000020 ",
+ "MSRValue": "0x0404000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000020 ",
+ "MSRValue": "0x1004000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000020 ",
+ "MSRValue": "0x2004000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000020 ",
+ "MSRValue": "0x3F84000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000020 ",
+ "MSRValue": "0x00BC000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000020 ",
+ "MSRValue": "0x013C000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000020 ",
+ "MSRValue": "0x023C000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000020 ",
+ "MSRValue": "0x043C000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020040 ",
+ "MSRValue": "0x2000020040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0040 ",
+ "MSRValue": "0x20003C0040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000040 ",
+ "MSRValue": "0x0084000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000040 ",
+ "MSRValue": "0x0104000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000040 ",
+ "MSRValue": "0x0204000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000040 ",
+ "MSRValue": "0x0404000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000040 ",
+ "MSRValue": "0x1004000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000040 ",
+ "MSRValue": "0x2004000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000040 ",
+ "MSRValue": "0x3F84000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000040 ",
+ "MSRValue": "0x00BC000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000040 ",
+ "MSRValue": "0x013C000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000040 ",
+ "MSRValue": "0x023C000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000040 ",
+ "MSRValue": "0x043C000040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020080 ",
+ "MSRValue": "0x2000020080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0080 ",
+ "MSRValue": "0x20003C0080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000080 ",
+ "MSRValue": "0x0084000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000080 ",
+ "MSRValue": "0x0104000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000080 ",
+ "MSRValue": "0x0204000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000080 ",
+ "MSRValue": "0x0404000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000080 ",
+ "MSRValue": "0x1004000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000080 ",
+ "MSRValue": "0x2004000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000080 ",
+ "MSRValue": "0x3F84000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000080 ",
+ "MSRValue": "0x00BC000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000080 ",
+ "MSRValue": "0x013C000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000080 ",
+ "MSRValue": "0x023C000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000080 ",
+ "MSRValue": "0x043C000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020100 ",
+ "MSRValue": "0x2000020100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0100 ",
+ "MSRValue": "0x20003C0100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000100 ",
+ "MSRValue": "0x0084000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000100 ",
+ "MSRValue": "0x0104000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000100 ",
+ "MSRValue": "0x0204000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000100 ",
+ "MSRValue": "0x0404000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000100 ",
+ "MSRValue": "0x1004000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000100 ",
+ "MSRValue": "0x2004000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000100 ",
+ "MSRValue": "0x3F84000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000100 ",
+ "MSRValue": "0x00BC000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000100 ",
+ "MSRValue": "0x013C000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000100 ",
+ "MSRValue": "0x023C000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000100 ",
+ "MSRValue": "0x043C000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020200 ",
+ "MSRValue": "0x2000020200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0200 ",
+ "MSRValue": "0x20003C0200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000200 ",
+ "MSRValue": "0x0084000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000200 ",
+ "MSRValue": "0x0104000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000200 ",
+ "MSRValue": "0x0204000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000200 ",
+ "MSRValue": "0x0404000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000200 ",
+ "MSRValue": "0x1004000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000200 ",
+ "MSRValue": "0x2004000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000200 ",
+ "MSRValue": "0x3F84000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000200 ",
+ "MSRValue": "0x00BC000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000200 ",
+ "MSRValue": "0x013C000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000200 ",
+ "MSRValue": "0x023C000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000200 ",
+ "MSRValue": "0x043C000200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000028000 ",
+ "MSRValue": "0x2000028000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c8000 ",
+ "MSRValue": "0x20003C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084008000 ",
+ "MSRValue": "0x0084008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104008000 ",
+ "MSRValue": "0x0104008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204008000 ",
+ "MSRValue": "0x0204008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404008000 ",
+ "MSRValue": "0x0404008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004008000 ",
+ "MSRValue": "0x1004008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004008000 ",
+ "MSRValue": "0x2004008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84008000 ",
+ "MSRValue": "0x3F84008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts any other requests that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc008000 ",
+ "MSRValue": "0x00BC008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts any other requests that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c008000 ",
+ "MSRValue": "0x013C008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts any other requests that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c008000 ",
+ "MSRValue": "0x023C008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts any other requests that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c008000 ",
+ "MSRValue": "0x043C008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "OTHER & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020090 ",
+ "MSRValue": "0x2000020090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0090 ",
+ "MSRValue": "0x20003C0090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000090 ",
+ "MSRValue": "0x0084000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000090 ",
+ "MSRValue": "0x0104000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000090 ",
+ "MSRValue": "0x0204000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000090 ",
+ "MSRValue": "0x0404000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000090 ",
+ "MSRValue": "0x1004000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000090 ",
+ "MSRValue": "0x2004000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000090 ",
+ "MSRValue": "0x3F84000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000090 ",
+ "MSRValue": "0x00BC000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000090 ",
+ "MSRValue": "0x013C000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000090 ",
+ "MSRValue": "0x023C000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000090 ",
+ "MSRValue": "0x043C000090",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020120 ",
+ "MSRValue": "0x2000020120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0120 ",
+ "MSRValue": "0x20003C0120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000120 ",
+ "MSRValue": "0x0084000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000120 ",
+ "MSRValue": "0x0104000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000120 ",
+ "MSRValue": "0x0204000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000120 ",
+ "MSRValue": "0x0404000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000120 ",
+ "MSRValue": "0x1004000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000120 ",
+ "MSRValue": "0x2004000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000120 ",
+ "MSRValue": "0x3F84000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000120 ",
+ "MSRValue": "0x00BC000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000120 ",
+ "MSRValue": "0x013C000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000120 ",
+ "MSRValue": "0x023C000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000120 ",
+ "MSRValue": "0x043C000120",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020240 ",
+ "MSRValue": "0x2000020240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0240 ",
+ "MSRValue": "0x20003C0240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000240 ",
+ "MSRValue": "0x0084000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000240 ",
+ "MSRValue": "0x0104000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000240 ",
+ "MSRValue": "0x0204000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000240 ",
+ "MSRValue": "0x0404000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000240 ",
+ "MSRValue": "0x1004000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000240 ",
+ "MSRValue": "0x2004000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000240 ",
+ "MSRValue": "0x3F84000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000240 ",
+ "MSRValue": "0x00BC000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000240 ",
+ "MSRValue": "0x013C000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000240 ",
+ "MSRValue": "0x023C000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch code reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000240 ",
+ "MSRValue": "0x043C000240",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all prefetch code reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020091 ",
+ "MSRValue": "0x2000020091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0091 ",
+ "MSRValue": "0x20003C0091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000091 ",
+ "MSRValue": "0x0084000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000091 ",
+ "MSRValue": "0x0104000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000091 ",
+ "MSRValue": "0x0204000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000091 ",
+ "MSRValue": "0x0404000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000091 ",
+ "MSRValue": "0x1004000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000091 ",
+ "MSRValue": "0x2004000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000091 ",
+ "MSRValue": "0x3F84000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000091 ",
+ "MSRValue": "0x00BC000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000091 ",
+ "MSRValue": "0x013C000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000091 ",
+ "MSRValue": "0x023C000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000091 ",
+ "MSRValue": "0x043C000091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand & prefetch data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2000020122 ",
+ "MSRValue": "0x2000020122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x20003c0122 ",
+ "MSRValue": "0x20003C0122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address.",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000122 ",
+ "MSRValue": "0x0084000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000122 ",
+ "MSRValue": "0x0104000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000122 ",
+ "MSRValue": "0x0204000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000122 ",
+ "MSRValue": "0x0404000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000122 ",
+ "MSRValue": "0x1004000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x2004000122 ",
+ "MSRValue": "0x2004000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f84000122 ",
+ "MSRValue": "0x3F84000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000122 ",
+ "MSRValue": "0x00BC000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information.",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000122 ",
+ "MSRValue": "0x013C000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000122 ",
+ "MSRValue": "0x023C000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response.",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000122 ",
+ "MSRValue": "0x043C000122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts all demand & prefetch RFOs",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
}
[
{
"PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
- "EventCode": "0x00",
"Counter": "Fixed counter 0",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
},
{
"PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.THREAD",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"AnyThread": "1",
},
{
"PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
- "EventCode": "0x00",
"Counter": "Fixed counter 2",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+ "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
"EventCode": "0x87",
"Counter": "0,1,2,3",
"UMask": "0x1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.",
- "EventCode": "0xA2",
+ "PublicDescription": "This event counts resource-related stall cycles.",
+ "EventCode": "0xa2",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "RESOURCE_STALLS.ANY",
"CounterHTOff": "2"
},
{
+ "PublicDescription": "Number of Uops delivered by the LSD.",
"EventCode": "0xA8",
"Counter": "0,1,2,3",
"UMask": "0x1",
"CounterHTOff": "1"
},
{
- "PublicDescription": "This event counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
"EventCode": "0xC0",
"Counter": "0,1,2,3",
"UMask": "0x2",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "PEBS": "1",
"EventCode": "0xC1",
"Counter": "0,1,2,3",
"UMask": "0x40",
"EventName": "OTHER_ASSISTS.ANY_WB_ASSIST",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"Data_LA": "1"
},
{
- "PublicDescription": "This event counts cycles without actually retired uops.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts cycles without actually retired uops.",
"EventCode": "0xC2",
"Invert": "1",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "UOPS_RETIRED.STALL_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles without actually retired uops.",
+ "BriefDescription": "Cycles no executable uops retired (Precise Event)",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
+ "PEBS": "1",
+ "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to PEBS uops retired event.",
"EventCode": "0xC2",
"Invert": "1",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "UOPS_RETIRED.TOTAL_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles with less than 10 actually retired uops.",
+ "BriefDescription": "Number of cycles using always true condition applied to PEBS uops retired event.",
"CounterMask": "10",
"CounterHTOff": "0,1,2,3"
},
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts not taken branch instructions retired.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "BR_INST_RETIRED.NOT_TAKEN",
"SampleAfterValue": "400009",
- "BriefDescription": "Not taken branch instructions retired.",
+ "BriefDescription": "Counts all not taken macro branch instructions retired. (Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts far branch instructions retired.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x40",
"Errata": "BDW98",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
"SampleAfterValue": "100007",
- "BriefDescription": "Far branch instructions retired.",
+ "BriefDescription": "Counts the number of far branch instructions retired.(Precise Event)",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"SampleAfterValue": "100003",
"L1_Hit_Indication": "1",
"CounterHTOff": "0,1,2,3"
[
{
- "EventCode": "0x00",
"UMask": "0x1",
"BriefDescription": "Instructions retired from execution.",
"Counter": "Fixed counter 0",
"CounterHTOff": "Fixed counter 0"
},
{
- "EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when the thread is not in halt state",
"Counter": "Fixed counter 1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
"Counter": "Fixed counter 1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"UMask": "0x3",
"BriefDescription": "Reference cycles when the core is not in halt state.",
"Counter": "Fixed counter 2",
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"Counter": "0,1,2,3",
"EventName": "ILD_STALL.LCP",
- "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+ "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Instruction per taken branch",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "IpTB"
+ },
+ {
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Branch instructions per taken branch. ",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "BpTB"
+ },
+ {
"MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
- "MetricGroup": "Frontend",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+ "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+ "MetricGroup": "Instruction_Type;L1_Bound",
+ "MetricName": "IpL"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+ "BriefDescription": "Instructions per Store",
+ "MetricGroup": "Instruction_Type;Store_Bound",
+ "MetricName": "IpS"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Instructions per Branch",
+ "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+ "MetricName": "IpB"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "BriefDescription": "Instruction per (near) call",
+ "MetricGroup": "Branches",
+ "MetricName": "IpCall"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS",
+ "MetricName": "FLOPc"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS_SMT",
+ "MetricName": "FLOPc_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
- "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
- "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
- "MetricGroup": "Unknown_Branches",
- "MetricName": "BAClear_Cost"
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "Branch_Misprediction_Cost"
+ },
+ {
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts_SMT",
+ "MetricName": "Branch_Misprediction_Cost_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "IpMispredict"
},
{
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
- "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
- "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * cycles )",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
- "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (2*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles))",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
- "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricGroup": "TLB_SMT",
+ "MetricName": "Page_Walks_Utilization_SMT"
+ },
+ {
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L1MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI"
+ },
+ {
+ "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2HPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L3MPKI"
+ },
+ {
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
+ "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
+ "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )",
+ "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+ "MetricGroup": "Memory_Lat",
+ "MetricName": "DRAM_Read_Latency"
+ },
+ {
+ "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@",
+ "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_Parallel_Reads"
+ },
+ {
+ "MetricExpr": "cbox_0@event\\=0x0@",
+ "BriefDescription": "Socket actual clocks when any core is active on that socket",
+ "MetricGroup": "",
+ "MetricName": "Socket_CLKS"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
},
{
"EventCode": "0x24",
- "UMask": "0x41",
+ "UMask": "0xc1",
"BriefDescription": "Demand Data Read requests that hit L2 cache",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
- "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+ "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x24",
- "UMask": "0x42",
+ "UMask": "0xc2",
"BriefDescription": "RFO requests that hit L2 cache.",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.RFO_HIT",
},
{
"EventCode": "0x24",
- "UMask": "0x44",
+ "UMask": "0xc4",
"BriefDescription": "L2 cache hits when fetching instructions, code reads.",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.CODE_RD_HIT",
},
{
"EventCode": "0x24",
- "UMask": "0x50",
+ "UMask": "0xd0",
"BriefDescription": "L2 prefetch requests that hit L2 cache",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.L2_PF_HIT",
{
"EventCode": "0xD0",
"UMask": "0x11",
- "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops that miss the STLB.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+ "PublicDescription": "This event counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD0",
"UMask": "0x12",
- "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)",
+ "BriefDescription": "Retired store uops that miss the STLB.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+ "PublicDescription": "This event counts store uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
"SampleAfterValue": "100003",
"L1_Hit_Indication": "1",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xD0",
"UMask": "0x21",
- "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops with locked access.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
"Errata": "BDM35",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with locked access retired to the architected path.",
+ "PublicDescription": "This event counts load uops with locked access retired to the architected path.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD0",
"UMask": "0x41",
- "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops that split across a cacheline boundary.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD0",
"UMask": "0x42",
- "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
+ "BriefDescription": "Retired store uops that split across a cacheline boundary.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"SampleAfterValue": "100003",
"L1_Hit_Indication": "1",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xD0",
"UMask": "0x81",
- "BriefDescription": "All retired load uops. (Precise Event - PEBS)",
+ "BriefDescription": "All retired load uops.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
+ "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD0",
"UMask": "0x82",
- "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
+ "BriefDescription": "All retired store uops.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.ALL_STORES",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
+ "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
"SampleAfterValue": "2000003",
"L1_Hit_Indication": "1",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xD1",
"UMask": "0x1",
- "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data source were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
+ "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD1",
"UMask": "0x2",
- "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
"Errata": "BDM35",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.",
+ "PublicDescription": "This event counts retired load uops which data sources were hits in the mid-level (L2) cache.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD1",
"UMask": "0x4",
- "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
"Errata": "BDM100",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
+ "PublicDescription": "This event counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
"SampleAfterValue": "50021",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD1",
"UMask": "0x8",
- "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.",
+ "BriefDescription": "Retired load uops misses in L1 cache as data sources.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
+ "PublicDescription": "This event counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD1",
"UMask": "0x10",
- "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.",
+ "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
+ "PublicDescription": "This event counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
"SampleAfterValue": "50021",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD1",
"UMask": "0x20",
- "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).",
+ "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
{
"EventCode": "0xD1",
"UMask": "0x40",
- "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
+ "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD2",
"UMask": "0x1",
- "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS",
"Errata": "BDM100",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
+ "PublicDescription": "This event counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
"SampleAfterValue": "20011",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD2",
"UMask": "0x2",
- "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
"Errata": "BDM100",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
+ "PublicDescription": "This event counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
"SampleAfterValue": "20011",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD2",
"UMask": "0x4",
- "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
"Errata": "BDM100",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
+ "PublicDescription": "This event counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
"SampleAfterValue": "20011",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD2",
"UMask": "0x8",
- "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)",
+ "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE",
"Errata": "BDM100",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
+ "PublicDescription": "This event counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD3",
"UMask": "0x1",
+ "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
"Errata": "BDE70, BDM100",
- "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
+ "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD3",
"UMask": "0x4",
- "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)",
+ "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
{
"EventCode": "0xD3",
"UMask": "0x10",
- "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)",
+ "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
{
"EventCode": "0xD3",
"UMask": "0x20",
- "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)",
+ "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all requests that hit in the L3",
- "MSRValue": "0x3f803c8fff",
+ "BriefDescription": "Counts all requests hit in the L3",
+ "MSRValue": "0x3F803C8FFF",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all requests hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c07f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C07F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c07f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C07F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c0244",
+ "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C0244",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c0122",
+ "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C0122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c0122",
+ "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C0122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c0091",
+ "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C0091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c0091",
+ "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C0091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3",
- "MSRValue": "0x3f803c0200",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
+ "MSRValue": "0x3F803C0200",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3",
- "MSRValue": "0x3f803c0100",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
+ "MSRValue": "0x3F803C0100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c0002",
+ "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C0002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3",
- "MSRValue": "0x3f803c0002",
+ "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3",
+ "MSRValue": "0x3F803C0002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
}
{
"EventCode": "0xC7",
"UMask": "0x3",
- "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "2000003",
{
"EventCode": "0xC7",
"UMask": "0x4",
- "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
{
"EventCode": "0xC7",
"UMask": "0x8",
- "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
{
"EventCode": "0xC7",
"UMask": "0x10",
- "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"SampleAfterValue": "2000003",
{
"EventCode": "0xC7",
"UMask": "0x15",
- "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+ "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
"SampleAfterValue": "2000006",
{
"EventCode": "0xc7",
"UMask": "0x20",
- "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"SampleAfterValue": "2000003",
{
"EventCode": "0xC7",
"UMask": "0x2a",
- "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+ "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.SINGLE",
"SampleAfterValue": "2000005",
{
"EventCode": "0xC7",
"UMask": "0x3c",
- "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.PACKED",
"SampleAfterValue": "2000004",
{
"EventCode": "0xc8",
"UMask": "0x4",
- "BriefDescription": "Number of times HLE abort was triggered (PEBS)",
+ "BriefDescription": "Number of times HLE abort was triggered",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "HLE_RETIRED.ABORTED",
- "PublicDescription": "Number of times HLE abort was triggered (PEBS).",
+ "PublicDescription": "Number of times HLE abort was triggered.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xc9",
"UMask": "0x4",
- "BriefDescription": "Number of times RTM abort was triggered (PEBS)",
+ "BriefDescription": "Number of times RTM abort was triggered",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "RTM_RETIRED.ABORTED",
- "PublicDescription": "Number of times RTM abort was triggered (PEBS).",
+ "PublicDescription": "Number of times RTM abort was triggered .",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 4",
+ "BriefDescription": "Randomly selected loads with latency value being above 4",
"PEBS": "2",
"MSRValue": "0x4",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
- "PublicDescription": "This event counts loads with latency value being above four.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above four.",
"TakenAlone": "1",
"SampleAfterValue": "100003",
"CounterHTOff": "3"
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 8",
+ "BriefDescription": "Randomly selected loads with latency value being above 8",
"PEBS": "2",
"MSRValue": "0x8",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
- "PublicDescription": "This event counts loads with latency value being above eight.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above eight.",
"TakenAlone": "1",
"SampleAfterValue": "50021",
"CounterHTOff": "3"
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 16",
+ "BriefDescription": "Randomly selected loads with latency value being above 16",
"PEBS": "2",
"MSRValue": "0x10",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
- "PublicDescription": "This event counts loads with latency value being above 16.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 16.",
"TakenAlone": "1",
"SampleAfterValue": "20011",
"CounterHTOff": "3"
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 32",
+ "BriefDescription": "Randomly selected loads with latency value being above 32",
"PEBS": "2",
"MSRValue": "0x20",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
- "PublicDescription": "This event counts loads with latency value being above 32.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 32.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "3"
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 64",
+ "BriefDescription": "Randomly selected loads with latency value being above 64",
"PEBS": "2",
"MSRValue": "0x40",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
- "PublicDescription": "This event counts loads with latency value being above 64.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 64.",
"TakenAlone": "1",
"SampleAfterValue": "2003",
"CounterHTOff": "3"
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 128",
+ "BriefDescription": "Randomly selected loads with latency value being above 128",
"PEBS": "2",
"MSRValue": "0x80",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
- "PublicDescription": "This event counts loads with latency value being above 128.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 128.",
"TakenAlone": "1",
"SampleAfterValue": "1009",
"CounterHTOff": "3"
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 256",
+ "BriefDescription": "Randomly selected loads with latency value being above 256",
"PEBS": "2",
"MSRValue": "0x100",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
- "PublicDescription": "This event counts loads with latency value being above 256.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 256.",
"TakenAlone": "1",
"SampleAfterValue": "503",
"CounterHTOff": "3"
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 512",
+ "BriefDescription": "Randomly selected loads with latency value being above 512",
"PEBS": "2",
"MSRValue": "0x200",
"Counter": "3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"Errata": "BDM100, BDM35",
- "PublicDescription": "This event counts loads with latency value being above 512.",
+ "PublicDescription": "Counts randomly selected loads with latency value being above 512.",
"TakenAlone": "1",
"SampleAfterValue": "101",
"CounterHTOff": "3"
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all requests that miss in the L3",
- "MSRValue": "0x3fbfc08fff",
+ "BriefDescription": "Counts all requests miss in the L3",
+ "MSRValue": "0x3FBFC08FFF",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all requests miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache",
- "MSRValue": "0x087fc007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
+ "MSRValue": "0x087FC007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache",
- "MSRValue": "0x103fc007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
+ "MSRValue": "0x103FC007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram",
- "MSRValue": "0x063bc007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
+ "MSRValue": "0x063BC007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram",
- "MSRValue": "0x06040007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
+ "MSRValue": "0x06040007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3",
- "MSRValue": "0x3fbfc007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
+ "MSRValue": "0x3FBFC007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
"MSRValue": "0x0604000244",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3",
- "MSRValue": "0x3fbfc00244",
+ "BriefDescription": "Counts all demand & prefetch code reads miss in the L3",
+ "MSRValue": "0x3FBFC00244",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch code reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
"MSRValue": "0x0604000122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3",
- "MSRValue": "0x3fbfc00122",
+ "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3",
+ "MSRValue": "0x3FBFC00122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache",
- "MSRValue": "0x087fc00091",
+ "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
+ "MSRValue": "0x087FC00091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache",
- "MSRValue": "0x103fc00091",
+ "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
+ "MSRValue": "0x103FC00091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram",
- "MSRValue": "0x063bc00091",
+ "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
+ "MSRValue": "0x063BC00091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
"MSRValue": "0x0604000091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3",
- "MSRValue": "0x3fbfc00091",
+ "BriefDescription": "Counts all demand & prefetch data reads miss in the L3",
+ "MSRValue": "0x3FBFC00091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3",
- "MSRValue": "0x3fbfc00200",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
+ "MSRValue": "0x3FBFC00200",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3",
- "MSRValue": "0x3fbfc00100",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
+ "MSRValue": "0x3FBFC00100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache",
- "MSRValue": "0x103fc00002",
+ "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
+ "MSRValue": "0x103FC00002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
- "MSRValue": "0x3fbfc00002",
+ "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3",
+ "MSRValue": "0x3FBFC00002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
}
[
{
- "EventCode": "0x00",
"UMask": "0x1",
"BriefDescription": "Instructions retired from execution.",
"Counter": "Fixed counter 0",
"CounterHTOff": "Fixed counter 0"
},
{
- "EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when the thread is not in halt state",
"Counter": "Fixed counter 1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
"Counter": "Fixed counter 1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"UMask": "0x3",
"BriefDescription": "Reference cycles when the core is not in halt state.",
"Counter": "Fixed counter 2",
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"Counter": "0,1,2,3",
"EventName": "ILD_STALL.LCP",
- "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+ "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA2",
+ "EventCode": "0xa2",
"UMask": "0x1",
"BriefDescription": "Resource-related stall cycles",
"Counter": "0,1,2,3",
"EventName": "RESOURCE_STALLS.ANY",
- "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.",
+ "PublicDescription": "This event counts resource-related stall cycles.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC2",
"UMask": "0x1",
- "BriefDescription": "Actually retired uops. (Precise Event - PEBS)",
+ "BriefDescription": "Actually retired uops.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "UOPS_RETIRED.ALL",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
+ "PublicDescription": "This event counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC2",
"UMask": "0x2",
- "BriefDescription": "Retirement slots used. (Precise Event - PEBS)",
+ "BriefDescription": "Retirement slots used.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "UOPS_RETIRED.RETIRE_SLOTS",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of retirement slots used.",
+ "PublicDescription": "This event counts the number of retirement slots used.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x1",
- "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)",
+ "BriefDescription": "Conditional branch instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.CONDITIONAL",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.",
+ "PublicDescription": "This event counts conditional branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x2",
- "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)",
+ "BriefDescription": "Direct and indirect near call instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NEAR_CALL",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.",
+ "PublicDescription": "This event counts both direct and indirect near call instructions retired.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x2",
- "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)",
+ "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect macro near call instructions retired (captured in ring 3).",
+ "PublicDescription": "This event counts both direct and indirect macro near call instructions retired (captured in ring 3).",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x8",
- "BriefDescription": "Return instructions retired. (Precise Event - PEBS)",
+ "BriefDescription": "Return instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NEAR_RETURN",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.",
+ "PublicDescription": "This event counts return instructions retired.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x20",
- "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)",
+ "BriefDescription": "Taken branch instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NEAR_TAKEN",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.",
+ "PublicDescription": "This event counts taken branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC5",
"UMask": "0x1",
- "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)",
+ "BriefDescription": "Mispredicted conditional branch instructions retired.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.CONDITIONAL",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.",
+ "PublicDescription": "This event counts mispredicted conditional branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC5",
"UMask": "0x8",
- "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)",
+ "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.RET",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted return instructions retired.",
+ "PublicDescription": "This event counts mispredicted return instructions retired.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC5",
"UMask": "0x20",
- "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
+ "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
- "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
+ "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
- "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
- "MetricGroup": "Frontend",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Instruction per taken branch",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "IpTB"
+ },
+ {
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Branch instructions per taken branch. ",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "BpTB"
+ },
+ {
+ "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+ "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+ "MetricGroup": "Instruction_Type;L1_Bound",
+ "MetricName": "IpL"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+ "BriefDescription": "Instructions per Store",
+ "MetricGroup": "Instruction_Type;Store_Bound",
+ "MetricName": "IpS"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Instructions per Branch",
+ "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+ "MetricName": "IpB"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "BriefDescription": "Instruction per (near) call",
+ "MetricGroup": "Branches",
+ "MetricName": "IpCall"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS",
+ "MetricName": "FLOPc"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS_SMT",
+ "MetricName": "FLOPc_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
- "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
- "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
- "MetricGroup": "Unknown_Branches",
- "MetricName": "BAClear_Cost"
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "Branch_Misprediction_Cost"
+ },
+ {
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts_SMT",
+ "MetricName": "Branch_Misprediction_Cost_SMT"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "IpMispredict"
+ },
+ {
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
- "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
- "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
+ "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
- "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
- "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricGroup": "TLB_SMT",
+ "MetricName": "Page_Walks_Utilization_SMT"
+ },
+ {
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Access_BW"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L1MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI"
+ },
+ {
+ "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2HPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L3MPKI"
+ },
+ {
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
+ "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
+ "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
+ "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+ "MetricGroup": "Memory_Lat",
+ "MetricName": "DRAM_Read_Latency"
+ },
+ {
+ "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
+ "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_Parallel_Reads"
+ },
+ {
+ "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 1 == 1 else 0 else 0",
+ "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
+ "MetricGroup": "Memory_Lat",
+ "MetricName": "MEM_PMM_Read_Latency"
+ },
+ {
+ "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0",
+ "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "PMM_Read_BW"
+ },
+ {
+ "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0",
+ "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "PMM_Write_BW"
+ },
+ {
+ "MetricExpr": "cha_0@event\\=0x0@",
+ "BriefDescription": "Socket actual clocks when any core is active on that socket",
+ "MetricGroup": "",
+ "MetricName": "Socket_CLKS"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
"UMask": "0x21",
"EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
"SampleAfterValue": "200003",
- "BriefDescription": "Locked load uops retired (Precise event capable)"
+ "BriefDescription": "Locked load uops retired (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x41",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
+ "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x42",
"EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
"SampleAfterValue": "200003",
- "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
+ "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x43",
"EventName": "MEM_UOPS_RETIRED.SPLIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
+ "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x81",
"EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired (Precise event capable)"
+ "BriefDescription": "Load uops retired (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x82",
"EventName": "MEM_UOPS_RETIRED.ALL_STORES",
"SampleAfterValue": "200003",
- "BriefDescription": "Store uops retired (Precise event capable)"
+ "BriefDescription": "Store uops retired (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x83",
"EventName": "MEM_UOPS_RETIRED.ALL",
"SampleAfterValue": "200003",
- "BriefDescription": "Memory uops retired (Precise event capable)"
+ "BriefDescription": "Memory uops retired (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)"
+ "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x2",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
+ "BriefDescription": "Load uops retired that hit L2 (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x8",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
+ "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x10",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that missed L2 (Precise event capable)"
+ "BriefDescription": "Load uops retired that missed L2 (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x20",
"EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
"SampleAfterValue": "200003",
- "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)"
+ "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x40",
"EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Loads retired that hit WCB (Precise event capable)"
+ "BriefDescription": "Loads retired that hit WCB (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x80",
"EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Loads retired that came from DRAM (Precise event capable)"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x40000032b7 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
+ "BriefDescription": "Loads retired that came from DRAM (Precise event capable)",
+ "Data_LA": "1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x36000032b7 ",
+ "MSRValue": "0x36000032b7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.ANY",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x10000032b7 ",
+ "MSRValue": "0x10000032b7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HITM_OTHER_CORE",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x04000032b7 ",
+ "MSRValue": "0x04000032b7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x02000032b7 ",
+ "MSRValue": "0x02000032b7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x00000432b7 ",
+ "MSRValue": "0x00000432b7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT",
"BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that hit the L2 cache.",
"Offcore": "1"
},
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x00000132b7 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000000022 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
- },
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000022 ",
+ "MSRValue": "0x3600000022",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.ANY",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000022 ",
+ "MSRValue": "0x1000000022",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HITM_OTHER_CORE",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000022 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0200000022 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000040022 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that hit the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000010022 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000003091",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x3600003091",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.ANY",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x1000003091",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0400003091",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0200003091",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000043091",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads (demand & prefetch) that hit the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000013091",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000003010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x3600003010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.ANY",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x1000003010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0400003010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0200003010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module. ",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000043010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_HIT",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that hit the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000013010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000008000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x3600008000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.ANY",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x1000008000 ",
+ "MSRValue": "0x0400000022",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0400008000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0200008000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module. ",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts requests to the uncore subsystem that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000048000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts requests to the uncore subsystem that hit the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts requests to the uncore subsystem that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000018000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts requests to the uncore subsystem that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000004800 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x3600004800 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.ANY",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x1000004800 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0400004800 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0200004800 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000044800 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_HIT",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that hit the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000014800 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000004000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x3600004000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.ANY",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x1000004000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0400004000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0200004000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000044000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_HIT",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that hit the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000014000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000002000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x3600002000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.ANY",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x1000002000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0400002000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0200002000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000042000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that hit the L2 cache.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000012000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000001000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.OUTSTANDING",
- "MSRIndex": "0x1a6",
+ "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+ "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600001000 ",
+ "MSRValue": "0x0200000022",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.ANY",
+ "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache.",
+ "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000001000 ",
+ "MSRValue": "0x0000040022",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HITM_OTHER_CORE",
+ "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+ "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that hit the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400001000 ",
+ "MSRValue": "0x3600003091",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+ "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.ANY",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+ "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200001000 ",
+ "MSRValue": "0x1000003091",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+ "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache lines requests by software prefetch instructions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000041000 ",
+ "MSRValue": "0x0400003091",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_HIT",
+ "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache lines requests by software prefetch instructions that hit the L2 cache.",
+ "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000011000 ",
+ "MSRValue": "0x0200003091",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.ANY_RESPONSE",
+ "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem.",
+ "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x4000000800 ",
+ "MSRValue": "0x0000043091",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.OUTSTANDING",
- "MSRIndex": "0x1a6",
+ "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT",
+ "MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+ "BriefDescription": "Counts data reads (demand & prefetch) that hit the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000800 ",
+ "MSRValue": "0x3600003010",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.ANY",
+ "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.ANY",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache.",
+ "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000800 ",
+ "MSRValue": "0x1000003010",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
+ "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+ "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000800 ",
+ "MSRValue": "0x0400003010",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+ "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+ "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000800 ",
+ "MSRValue": "0x0200003010",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+ "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040800 ",
+ "MSRValue": "0x0000043010",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_HIT",
+ "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_HIT",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that hit the L2 cache.",
+ "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that hit the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000010800 ",
+ "MSRValue": "0x1000008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE",
+ "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem.",
+ "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x4000000400 ",
+ "MSRValue": "0x0400008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
- "MSRIndex": "0x1a6",
+ "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+ "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000400 ",
+ "MSRValue": "0x0200008000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.ANY",
+ "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache.",
+ "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts requests to the uncore subsystem that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000400 ",
+ "MSRValue": "0x0000048000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HITM_OTHER_CORE",
+ "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+ "BriefDescription": "Counts requests to the uncore subsystem that hit the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts requests to the uncore subsystem that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000400 ",
+ "MSRValue": "0x0000018000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+ "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+ "BriefDescription": "Counts requests to the uncore subsystem that have any transaction responses from the uncore subsystem.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000400 ",
+ "MSRValue": "0x3600004800",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+ "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.ANY",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts bus lock and split lock requests that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040400 ",
+ "MSRValue": "0x0000044800",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT",
+ "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_HIT",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts bus lock and split lock requests that hit the L2 cache.",
+ "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that hit the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts bus lock and split lock requests that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000010400 ",
+ "MSRValue": "0x3600004000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE",
+ "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.ANY",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts bus lock and split lock requests that have any transaction responses from the uncore subsystem.",
+ "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x4000000200 ",
+ "MSRValue": "0x1000004000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.OUTSTANDING",
- "MSRIndex": "0x1a6",
+ "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
+ "MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+ "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000200 ",
+ "MSRValue": "0x0400004000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.ANY",
+ "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache.",
+ "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000200 ",
+ "MSRValue": "0x0200004000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HITM_OTHER_CORE",
+ "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+ "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000200 ",
+ "MSRValue": "0x0000044000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+ "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_HIT",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+ "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that hit the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000200 ",
+ "MSRValue": "0x3600002000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+ "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.ANY",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040200 ",
+ "MSRValue": "0x1000002000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_HIT",
+ "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache.",
+ "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000010200 ",
+ "MSRValue": "0x0400002000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.ANY_RESPONSE",
+ "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem.",
+ "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x4000000100 ",
+ "MSRValue": "0x0200002000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.OUTSTANDING",
- "MSRIndex": "0x1a6",
+ "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+ "MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+ "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000100 ",
+ "MSRValue": "0x0000042000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.ANY",
+ "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache.",
+ "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that hit the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000100 ",
+ "MSRValue": "0x3600001000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HITM_OTHER_CORE",
+ "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.ANY",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+ "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000100 ",
+ "MSRValue": "0x1000001000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+ "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+ "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000100 ",
+ "MSRValue": "0x0400001000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+ "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040100 ",
+ "MSRValue": "0x0200001000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT",
+ "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache.",
+ "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts data cache lines requests by software prefetch instructions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000010100 ",
+ "MSRValue": "0x0000041000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE",
+ "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_HIT",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem.",
+ "BriefDescription": "Counts data cache lines requests by software prefetch instructions that hit the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x4000000080 ",
+ "MSRValue": "0x3600000800",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING",
- "MSRIndex": "0x1a6",
+ "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.ANY",
+ "MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+ "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000080 ",
+ "MSRValue": "0x1000000800",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.ANY",
+ "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache.",
+ "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000080 ",
+ "MSRValue": "0x0400000800",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HITM_OTHER_CORE",
+ "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+ "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000080 ",
+ "MSRValue": "0x0200000800",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+ "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+ "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000080 ",
+ "MSRValue": "0x0000040800",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+ "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_HIT",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that hit the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts bus lock and split lock requests that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040080 ",
+ "MSRValue": "0x0000010400",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT",
+ "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache.",
+ "BriefDescription": "Counts bus lock and split lock requests that have any transaction responses from the uncore subsystem.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000010080 ",
+ "MSRValue": "0x3600000100",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE",
+ "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.ANY",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem.",
+ "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+ "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x4000000020 ",
+ "MSRValue": "0x3600000080",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.OUTSTANDING",
- "MSRIndex": "0x1a6",
+ "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.ANY",
+ "MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+ "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000020 ",
+ "MSRValue": "0x3600000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.ANY",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000020 ",
+ "MSRValue": "0x1000000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HITM_OTHER_CORE",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000020 ",
+ "MSRValue": "0x0400000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000020 ",
+ "MSRValue": "0x0200000020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040020 ",
+ "MSRValue": "0x0000040020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT",
"BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that hit the L2 cache.",
"Offcore": "1"
},
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000010020 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000000010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
- },
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000010 ",
+ "MSRValue": "0x3600000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.ANY",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000010 ",
+ "MSRValue": "0x1000000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HITM_OTHER_CORE",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000010 ",
+ "MSRValue": "0x0400000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000010 ",
+ "MSRValue": "0x0200000010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040010 ",
+ "MSRValue": "0x0000040010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_HIT",
"BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that hit the L2 cache.",
"Offcore": "1"
},
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000010010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x4000000008 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.COREWB.OUTSTANDING",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
- "Offcore": "1"
- },
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000008 ",
+ "MSRValue": "0x3600000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.ANY",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000008 ",
+ "MSRValue": "0x1000000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HITM_OTHER_CORE",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000008 ",
+ "MSRValue": "0x0400000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000008 ",
+ "MSRValue": "0x0200000008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040008 ",
+ "MSRValue": "0x0000040008",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.COREWB.L2_HIT",
"BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that hit the L2 cache.",
"Offcore": "1"
},
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000010008 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x4000000004 ",
+ "MSRValue": "0x4000000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000004 ",
+ "MSRValue": "0x3600000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.ANY",
"BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache.",
"Offcore": "1"
},
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x1000000004 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
- "Offcore": "1"
- },
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000004 ",
+ "MSRValue": "0x0400000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000004 ",
+ "MSRValue": "0x0200000004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040004 ",
+ "MSRValue": "0x0000040004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT",
"BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that hit the L2 cache.",
"Offcore": "1"
},
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000010004 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x4000000002 ",
+ "MSRValue": "0x4000000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000002 ",
+ "MSRValue": "0x3600000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.ANY",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000002 ",
+ "MSRValue": "0x1000000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HITM_OTHER_CORE",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000002 ",
+ "MSRValue": "0x0400000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000002 ",
+ "MSRValue": "0x0200000002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040002 ",
+ "MSRValue": "0x0000040002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT",
"BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that hit the L2 cache.",
"Offcore": "1"
},
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000010002 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
- },
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand cacheable data reads of full cache lines that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x4000000001 ",
+ "MSRValue": "0x4000000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x3600000001 ",
+ "MSRValue": "0x3600000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.ANY",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x1000000001 ",
+ "MSRValue": "0x1000000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HITM_OTHER_CORE",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0400000001 ",
+ "MSRValue": "0x0400000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0200000001 ",
+ "MSRValue": "0x0200000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
"EventCode": "0xB7",
- "MSRValue": "0x0000040001 ",
+ "MSRValue": "0x0000040001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT",
"SampleAfterValue": "100007",
"BriefDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache.",
"Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x0000010001 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem.",
- "Offcore": "1"
}
]
\ No newline at end of file
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"SampleAfterValue": "200003",
"BriefDescription": "Machine clears due to memory ordering issue"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x20000032b7 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000022 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000003091",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000003010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000008000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000004800 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000004000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000002000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000001000 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000800 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000400 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000200 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000100 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000080 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000020 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000010 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000008 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000004 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000002 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
- },
- {
- "CollectPEBSRecord": "1",
- "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
- "EventCode": "0xB7",
- "MSRValue": "0x2000000001 ",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.NON_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address.",
- "Offcore": "1"
}
]
\ No newline at end of file
[
{
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.",
- "EventCode": "0x00",
"Counter": "Fixed counter 0",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
},
{
"PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.",
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.CORE",
},
{
"PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.",
- "EventCode": "0x00",
"Counter": "Fixed counter 2",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
+ "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x1",
"UMask": "0x11",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)"
+ "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x12",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
"SampleAfterValue": "200003",
- "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)"
+ "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"UMask": "0x13",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
"SampleAfterValue": "200003",
- "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)"
+ "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)",
+ "Data_LA": "1"
}
]
\ No newline at end of file
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
"SampleAfterValue": "200003",
- "BriefDescription": "Locked load uops retired (Precise event capable)"
+ "BriefDescription": "Locked load uops retired (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
+ "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
"SampleAfterValue": "200003",
- "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
+ "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
+ "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired (Precise event capable)"
+ "BriefDescription": "Load uops retired (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.ALL_STORES",
"SampleAfterValue": "200003",
- "BriefDescription": "Store uops retired (Precise event capable)"
+ "BriefDescription": "Store uops retired (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.ALL",
"SampleAfterValue": "200003",
- "BriefDescription": "Memory uops retired (Precise event capable)"
+ "BriefDescription": "Memory uops retired (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)"
+ "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
+ "BriefDescription": "Load uops retired that hit L2 (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
+ "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that missed L2 (Precise event capable)"
+ "BriefDescription": "Load uops retired that missed L2 (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
"SampleAfterValue": "200003",
- "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)"
+ "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Loads retired that hit WCB (Precise event capable)"
+ "BriefDescription": "Loads retired that hit WCB (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
"SampleAfterValue": "200003",
- "BriefDescription": "Loads retired that came from DRAM (Precise event capable)"
+ "BriefDescription": "Loads retired that came from DRAM (Precise event capable)",
+ "Data_LA": "1"
},
{
"CollectPEBSRecord": "1",
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PDIR_COUNTER": "na",
"MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+ "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.",
"Offcore": "1"
},
{
"PEBS": "2",
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. You cannot collect a PEBs record for this event.",
- "EventCode": "0x00",
"Counter": "Fixed counter 0",
"UMask": "0x1",
"PEBScounters": "32",
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. This event uses fixed counter 1. You cannot collect a PEBs record for this event.",
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"PEBScounters": "33",
{
"CollectPEBSRecord": "1",
"PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. This event uses fixed counter 2. You cannot collect a PEBs record for this event.",
- "EventCode": "0x00",
"Counter": "Fixed counter 2",
"UMask": "0x3",
"PEBScounters": "34",
},
{
"CollectPEBSRecord": "1",
- "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
+ "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification. Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
"SampleAfterValue": "200003",
- "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)"
+ "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
"SampleAfterValue": "200003",
- "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)"
+ "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
+ "Data_LA": "1"
},
{
"PEBS": "2",
"PEBScounters": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
"SampleAfterValue": "200003",
- "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)"
+ "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)",
+ "Data_LA": "1"
}
]
\ No newline at end of file
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Demand data read requests that hit L2 cache.",
+ "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x41",
+ "UMask": "0xc1",
"Errata": "HSD78",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
"SampleAfterValue": "200003",
"PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.",
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x42",
+ "UMask": "0xc2",
"EventName": "L2_RQSTS.RFO_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "RFO requests that hit L2 cache",
"PublicDescription": "Number of instruction fetches that hit the L2 cache.",
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x44",
+ "UMask": "0xc4",
"EventName": "L2_RQSTS.CODE_RD_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "L2 cache hits when fetching instructions, code reads.",
"PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.",
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x50",
+ "UMask": "0xd0",
"EventName": "L2_RQSTS.L2_PF_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "L2 prefetch requests that hit L2 cache",
"Errata": "HSD29, HSD25, HSM26, HSM30",
"EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
"SampleAfterValue": "20011",
- "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ",
+ "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
"CounterHTOff": "0,1,2,3",
"Data_LA": "1"
},
"Errata": "HSD29, HSD25, HSM26, HSM30",
"EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
"SampleAfterValue": "20011",
- "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ",
+ "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
"CounterHTOff": "0,1,2,3",
"Data_LA": "1"
},
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "",
"EventCode": "0xf4",
"Counter": "0,1,2,3",
"UMask": "0x10",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all requests hit in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c8fff",
+ "MSRValue": "0x3F803C8FFF",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_HIT.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all requests that hit in the L3",
+ "BriefDescription": "Counts all requests hit in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c07f7",
+ "MSRValue": "0x10003C07F7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "BriefDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c07f7",
+ "MSRValue": "0x04003C07F7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "BriefDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0244",
+ "MSRValue": "0x04003C0244",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0122",
+ "MSRValue": "0x10003C0122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0122",
+ "MSRValue": "0x04003C0122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0091",
+ "MSRValue": "0x10003C0091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0091",
+ "MSRValue": "0x04003C0091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0200",
+ "MSRValue": "0x3F803C0200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0100",
+ "MSRValue": "0x3F803C0100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0080",
+ "MSRValue": "0x3F803C0080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0040",
+ "MSRValue": "0x3F803C0040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0020",
+ "MSRValue": "0x3F803C0020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3f803c0010",
+ "MSRValue": "0x3F803C0010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0004",
+ "MSRValue": "0x10003C0004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0004",
+ "MSRValue": "0x04003C0004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0002",
+ "MSRValue": "0x10003C0002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0002",
+ "MSRValue": "0x04003C0002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10003c0001",
+ "MSRValue": "0x10003C0001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04003c0001",
+ "MSRValue": "0x04003C0001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
}
[
{
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xC1",
"Counter": "0,1,2,3",
"UMask": "0x8",
"Errata": "HSD56, HSM57",
"EventName": "OTHER_ASSISTS.AVX_TO_SSE",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
+ "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xC1",
"Counter": "0,1,2,3",
"UMask": "0x10",
"Errata": "HSD56, HSM57",
"EventName": "OTHER_ASSISTS.SSE_TO_AVX",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
+ "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Number of X87 FP assists due to output values.",
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "FP_ASSIST.X87_OUTPUT",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of X87 assists due to output value.",
+ "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Number of X87 FP assists due to input values.",
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "FP_ASSIST.X87_INPUT",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of X87 assists due to input value.",
+ "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Number of SIMD FP assists due to output values.",
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x8",
"EventName": "FP_ASSIST.SIMD_OUTPUT",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of SIMD FP assists due to Output values",
+ "BriefDescription": "SSE* FP micro-code assist when output value is invalid.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Number of SIMD FP assists due to input values.",
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "FP_ASSIST.SIMD_INPUT",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of SIMD FP assists due to input values",
+ "BriefDescription": "Any input SSE* FP Assist",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Cycles with any input/output SSE* or FP assists.",
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xCA",
"Counter": "0,1,2,3",
"UMask": "0x1e",
"EventName": "FP_ASSIST.ANY",
"SampleAfterValue": "100003",
- "BriefDescription": "Cycles with any input/output SSE or FP assist",
+ "BriefDescription": "Counts any FP_ASSIST umask was incrementing",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
}
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Instruction per taken branch",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "IpTB"
+ },
+ {
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Branch instructions per taken branch. ",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "BpTB"
+ },
+ {
"MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
- "MetricGroup": "Frontend",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+ "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+ "MetricGroup": "Instruction_Type;L1_Bound",
+ "MetricName": "IpL"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+ "BriefDescription": "Instructions per Store",
+ "MetricGroup": "Instruction_Type;Store_Bound",
+ "MetricName": "IpS"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Instructions per Branch",
+ "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+ "MetricName": "IpB"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "BriefDescription": "Instruction per (near) call",
+ "MetricGroup": "Branches",
+ "MetricName": "IpCall"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
- "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
- "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
- "MetricGroup": "Unknown_Branches",
- "MetricName": "BAClear_Cost"
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "IpMispredict"
},
{
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
- "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
- "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
- "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
- "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricGroup": "TLB_SMT",
+ "MetricName": "Page_Walks_Utilization_SMT"
+ },
+ {
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L1MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2HPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L3MPKI"
+ },
+ {
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"SampleAfterValue": "100003",
- "BriefDescription": "Loads with latency value being above 4.",
+ "BriefDescription": "Randomly selected loads with latency value being above 4.",
"TakenAlone": "1",
"CounterHTOff": "3"
},
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"SampleAfterValue": "50021",
- "BriefDescription": "Loads with latency value being above 8.",
+ "BriefDescription": "Randomly selected loads with latency value being above 8.",
"TakenAlone": "1",
"CounterHTOff": "3"
},
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"SampleAfterValue": "20011",
- "BriefDescription": "Loads with latency value being above 16.",
+ "BriefDescription": "Randomly selected loads with latency value being above 16.",
"TakenAlone": "1",
"CounterHTOff": "3"
},
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"SampleAfterValue": "100003",
- "BriefDescription": "Loads with latency value being above 32.",
+ "BriefDescription": "Randomly selected loads with latency value being above 32.",
"TakenAlone": "1",
"CounterHTOff": "3"
},
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"SampleAfterValue": "2003",
- "BriefDescription": "Loads with latency value being above 64.",
+ "BriefDescription": "Randomly selected loads with latency value being above 64.",
"TakenAlone": "1",
"CounterHTOff": "3"
},
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"SampleAfterValue": "1009",
- "BriefDescription": "Loads with latency value being above 128.",
+ "BriefDescription": "Randomly selected loads with latency value being above 128.",
"TakenAlone": "1",
"CounterHTOff": "3"
},
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"SampleAfterValue": "503",
- "BriefDescription": "Loads with latency value being above 256.",
+ "BriefDescription": "Randomly selected loads with latency value being above 256.",
"TakenAlone": "1",
"CounterHTOff": "3"
},
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"SampleAfterValue": "101",
- "BriefDescription": "Loads with latency value being above 512.",
+ "BriefDescription": "Randomly selected loads with latency value being above 512.",
"TakenAlone": "1",
"CounterHTOff": "3"
},
{
- "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all requests miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc08fff",
+ "MSRValue": "0x3FFFC08FFF",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all requests that miss in the L3",
+ "BriefDescription": "Counts all requests miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "miss the L3 and the data is returned from local dram",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01004007f7",
+ "MSRValue": "0x01004007F7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.LOCAL_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "miss the L3 and the data is returned from local dram",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc007f7",
+ "MSRValue": "0x3FFFC007F7",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3",
+ "BriefDescription": "miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
"EventCode": "0xB7, 0xBB",
"MSRValue": "0x0100400244",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.LOCAL_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch code reads miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00244",
+ "MSRValue": "0x3FFFC00244",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3",
+ "BriefDescription": "Counts all demand & prefetch code reads miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
"EventCode": "0xB7, 0xBB",
"MSRValue": "0x0100400122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.LOCAL_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00122",
+ "MSRValue": "0x3FFFC00122",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3",
+ "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
"EventCode": "0xB7, 0xBB",
"MSRValue": "0x0100400091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.LOCAL_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00091",
+ "MSRValue": "0x3FFFC00091",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3",
+ "BriefDescription": "Counts all demand & prefetch data reads miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00200",
+ "MSRValue": "0x3FFFC00200",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00100",
+ "MSRValue": "0x3FFFC00100",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00080",
+ "MSRValue": "0x3FFFC00080",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00040",
+ "MSRValue": "0x3FFFC00040",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00020",
+ "MSRValue": "0x3FFFC00020",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00010",
+ "MSRValue": "0x3FFFC00010",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
"EventCode": "0xB7, 0xBB",
"MSRValue": "0x0100400004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.LOCAL_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00004",
+ "MSRValue": "0x3FFFC00004",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand code reads that miss in the L3",
+ "BriefDescription": "Counts all demand code reads miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
"EventCode": "0xB7, 0xBB",
"MSRValue": "0x0100400002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.LOCAL_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00002",
+ "MSRValue": "0x3FFFC00002",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
+ "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
"EventCode": "0xB7, 0xBB",
"MSRValue": "0x0100400001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.LOCAL_DRAM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads miss in the L3",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fffc00001",
+ "MSRValue": "0x3FFFC00001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that miss in the L3",
+ "BriefDescription": "Counts demand data reads miss in the L3",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
}
[
{
"PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
- "EventCode": "0x00",
"Counter": "Fixed counter 0",
"UMask": "0x1",
"Errata": "HSD140, HSD143",
},
{
"PublicDescription": "This event counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.",
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.THREAD",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"AnyThread": "1",
},
{
"PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state.",
- "EventCode": "0x00",
"Counter": "Fixed counter 2",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"CounterHTOff": "1"
},
{
- "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
"EventCode": "0xC0",
"Counter": "0,1,2,3",
"UMask": "0x2",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.",
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xC1",
"Counter": "0,1,2,3",
"UMask": "0x40",
"EventName": "OTHER_ASSISTS.ANY_WB_ASSIST",
"SampleAfterValue": "100003",
- "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"Data_LA": "1"
},
{
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xC2",
"Invert": "1",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "UOPS_RETIRED.STALL_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles without actually retired uops.",
+ "BriefDescription": "Cycles no executable uops retired",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
},
{
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xC2",
"Invert": "1",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "UOPS_RETIRED.TOTAL_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles with less than 10 actually retired uops.",
+ "BriefDescription": "Number of cycles using always true condition applied to PEBS uops retired event.",
"CounterMask": "10",
"CounterHTOff": "0,1,2,3"
},
{
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xC2",
"Invert": "1",
"Counter": "0,1,2,3",
"AnyThread": "1",
"EventName": "UOPS_RETIRED.CORE_STALL_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles without actually retired uops.",
+ "BriefDescription": "Cycles no executable uops retired on core",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3"
},
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Counts the number of not taken branch instructions retired.",
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x10",
"EventName": "BR_INST_RETIRED.NOT_TAKEN",
"SampleAfterValue": "400009",
- "BriefDescription": "Not taken branch instructions retired.",
+ "BriefDescription": "Counts all not taken macro branch instructions retired.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Number of far branches retired.",
+ "PEBS": "1",
+ "PublicDescription": "",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x40",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
"SampleAfterValue": "100003",
- "BriefDescription": "Far branch instructions retired.",
+ "BriefDescription": "Counts the number of far branch instructions retired.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
},
{
"EventCode": "0x24",
- "UMask": "0x41",
+ "UMask": "0xc1",
"BriefDescription": "Demand Data Read requests that hit L2 cache",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
"Errata": "HSD78",
- "PublicDescription": "Demand data read requests that hit L2 cache.",
+ "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x24",
- "UMask": "0x42",
+ "UMask": "0xc2",
"BriefDescription": "RFO requests that hit L2 cache",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.RFO_HIT",
},
{
"EventCode": "0x24",
- "UMask": "0x44",
+ "UMask": "0xc4",
"BriefDescription": "L2 cache hits when fetching instructions, code reads.",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.CODE_RD_HIT",
},
{
"EventCode": "0x24",
- "UMask": "0x50",
+ "UMask": "0xd0",
"BriefDescription": "L2 prefetch requests that hit L2 cache",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.L2_PF_HIT",
{
"EventCode": "0xD0",
"UMask": "0x11",
- "BriefDescription": "Retired load uops that miss the STLB. (precise Event)",
+ "BriefDescription": "Retired load uops that miss the STLB.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
{
"EventCode": "0xD0",
"UMask": "0x12",
- "BriefDescription": "Retired store uops that miss the STLB. (precise Event)",
+ "BriefDescription": "Retired store uops that miss the STLB.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
{
"EventCode": "0xD0",
"UMask": "0x21",
- "BriefDescription": "Retired load uops with locked access. (precise Event)",
+ "BriefDescription": "Retired load uops with locked access.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
{
"EventCode": "0xD0",
"UMask": "0x41",
- "BriefDescription": "Retired load uops that split across a cacheline boundary. (precise Event)",
+ "BriefDescription": "Retired load uops that split across a cacheline boundary.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
"Errata": "HSD29, HSM30",
- "PublicDescription": "This event counts load uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD0",
"UMask": "0x42",
- "BriefDescription": "Retired store uops that split across a cacheline boundary. (precise Event)",
+ "BriefDescription": "Retired store uops that split across a cacheline boundary.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
"Errata": "HSD29, HSM30",
"L1_Hit_Indication": "1",
- "PublicDescription": "This event counts store uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD0",
"UMask": "0x81",
- "BriefDescription": "All retired load uops. (precise Event)",
+ "BriefDescription": "All retired load uops.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
{
"EventCode": "0xD0",
"UMask": "0x82",
- "BriefDescription": "All retired store uops. (precise Event)",
+ "BriefDescription": "All retired store uops.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.ALL_STORES",
"Errata": "HSD29, HSM30",
"L1_Hit_Indication": "1",
- "PublicDescription": "This event counts all store uops retired. This is a precise event.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD1",
"UMask": "0x4",
- "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
+ "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
"Errata": "HSD74, HSD29, HSD25, HSM26, HSM30",
- "PublicDescription": "This event counts retired load uops in which data sources were data hits in the L3 cache without snoops required. This does not include hardware prefetches. This is a precise event.",
+ "PublicDescription": "Retired load uops with L3 cache hits as data sources.",
"SampleAfterValue": "50021",
"CounterHTOff": "0,1,2,3"
},
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
"Errata": "HSM30",
- "PublicDescription": "This event counts retired load uops in which data sources missed in the L1 cache. This does not include hardware prefetches. This is a precise event.",
+ "PublicDescription": "Retired load uops missed L1 cache as data sources.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD1",
"UMask": "0x10",
- "BriefDescription": "Retired load uops with L2 cache misses as data sources.",
+ "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
"Errata": "HSD29, HSM30",
+ "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.",
"SampleAfterValue": "50021",
"CounterHTOff": "0,1,2,3"
},
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_RETIRED.L3_MISS",
"Errata": "HSD74, HSD29, HSD25, HSM26, HSM30",
+ "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD2",
"UMask": "0x2",
- "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ",
+ "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
"Errata": "HSD29, HSD25, HSM26, HSM30",
- "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HIT in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
"SampleAfterValue": "20011",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD2",
"UMask": "0x4",
- "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ",
+ "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
"Errata": "HSD29, HSD25, HSM26, HSM30",
- "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HITM (hit modified) in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
"SampleAfterValue": "20011",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD3",
"UMask": "0x1",
+ "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
"Errata": "HSD74, HSD29, HSD25, HSM30",
- "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
+ "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xD3",
"UMask": "0x4",
- "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)",
+ "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
{
"EventCode": "0xD3",
"UMask": "0x10",
- "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)",
+ "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
{
"EventCode": "0xD3",
"UMask": "0x20",
- "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)",
+ "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache",
"Data_LA": "1",
"PEBS": "1",
"Counter": "0,1,2,3",
"BriefDescription": "Split locks in SQ",
"Counter": "0,1,2,3",
"EventName": "SQ_MISC.SPLIT_LOCK",
- "PublicDescription": "",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c0001",
+ "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C0001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c0001",
+ "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C0001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c0002",
+ "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C0002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c0002",
+ "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C0002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c0004",
+ "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C0004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c0004",
+ "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C0004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3",
- "MSRValue": "0x3f803c0010",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
+ "MSRValue": "0x3F803C0010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3",
- "MSRValue": "0x3f803c0020",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
+ "MSRValue": "0x3F803C0020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3",
- "MSRValue": "0x3f803c0040",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
+ "MSRValue": "0x3F803C0040",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3",
- "MSRValue": "0x3f803c0080",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
+ "MSRValue": "0x3F803C0080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3",
- "MSRValue": "0x3f803c0100",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
+ "MSRValue": "0x3F803C0100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3",
- "MSRValue": "0x3f803c0200",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
+ "MSRValue": "0x3F803C0200",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c0091",
+ "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C0091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c0091",
+ "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C0091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c0122",
+ "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C0122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c0122",
+ "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C0122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c0244",
+ "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C0244",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
- "MSRValue": "0x04003c07f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+ "MSRValue": "0x04003C07F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
- "MSRValue": "0x10003c07f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+ "MSRValue": "0x10003C07F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all requests that hit in the L3",
- "MSRValue": "0x3f803c8fff",
+ "BriefDescription": "Counts all requests hit in the L3",
+ "MSRValue": "0x3F803C8FFF",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all requests hit in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
}
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Instruction per taken branch",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "IpTB"
+ },
+ {
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Branch instructions per taken branch. ",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "BpTB"
+ },
+ {
"MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
- "MetricGroup": "Frontend",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+ "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+ "MetricGroup": "Instruction_Type;L1_Bound",
+ "MetricName": "IpL"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+ "BriefDescription": "Instructions per Store",
+ "MetricGroup": "Instruction_Type;Store_Bound",
+ "MetricName": "IpS"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Instructions per Branch",
+ "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+ "MetricName": "IpB"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "BriefDescription": "Instruction per (near) call",
+ "MetricGroup": "Branches",
+ "MetricName": "IpCall"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
- "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
- "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
- "MetricGroup": "Unknown_Branches",
- "MetricName": "BAClear_Cost"
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "IpMispredict"
},
{
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
- "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
- "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
- "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
- "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricGroup": "TLB_SMT",
+ "MetricName": "Page_Walks_Utilization_SMT"
+ },
+ {
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L1MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2HPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L3MPKI"
+ },
+ {
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
+ "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )",
+ "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+ "MetricGroup": "Memory_Lat",
+ "MetricName": "DRAM_Read_Latency"
+ },
+ {
+ "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@",
+ "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_Parallel_Reads"
+ },
+ {
+ "MetricExpr": "cbox_0@event\\=0x0@",
+ "BriefDescription": "Socket actual clocks when any core is active on that socket",
+ "MetricGroup": "",
+ "MetricName": "Socket_CLKS"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 4.",
+ "BriefDescription": "Randomly selected loads with latency value being above 4.",
"PEBS": "2",
"MSRValue": "0x4",
"Counter": "3",
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 8.",
+ "BriefDescription": "Randomly selected loads with latency value being above 8.",
"PEBS": "2",
"MSRValue": "0x8",
"Counter": "3",
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 16.",
+ "BriefDescription": "Randomly selected loads with latency value being above 16.",
"PEBS": "2",
"MSRValue": "0x10",
"Counter": "3",
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 32.",
+ "BriefDescription": "Randomly selected loads with latency value being above 32.",
"PEBS": "2",
"MSRValue": "0x20",
"Counter": "3",
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 64.",
+ "BriefDescription": "Randomly selected loads with latency value being above 64.",
"PEBS": "2",
"MSRValue": "0x40",
"Counter": "3",
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 128.",
+ "BriefDescription": "Randomly selected loads with latency value being above 128.",
"PEBS": "2",
"MSRValue": "0x80",
"Counter": "3",
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 256.",
+ "BriefDescription": "Randomly selected loads with latency value being above 256.",
"PEBS": "2",
"MSRValue": "0x100",
"Counter": "3",
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Loads with latency value being above 512.",
+ "BriefDescription": "Randomly selected loads with latency value being above 512.",
"PEBS": "2",
"MSRValue": "0x200",
"Counter": "3",
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that miss in the L3",
- "MSRValue": "0x3fbfc00001",
+ "BriefDescription": "Counts demand data reads miss in the L3",
+ "MSRValue": "0x3FBFC00001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
"MSRValue": "0x0600400001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
- "MSRValue": "0x3fbfc00002",
+ "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3",
+ "MSRValue": "0x3FBFC00002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
"MSRValue": "0x0600400002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache",
- "MSRValue": "0x103fc00002",
+ "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
+ "MSRValue": "0x103FC00002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that miss in the L3",
- "MSRValue": "0x3fbfc00004",
+ "BriefDescription": "Counts all demand code reads miss in the L3",
+ "MSRValue": "0x3FBFC00004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
"MSRValue": "0x0600400004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3",
- "MSRValue": "0x3fbfc00010",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
+ "MSRValue": "0x3FBFC00010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3",
- "MSRValue": "0x3fbfc00020",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
+ "MSRValue": "0x3FBFC00020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3",
- "MSRValue": "0x3fbfc00040",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
+ "MSRValue": "0x3FBFC00040",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3",
- "MSRValue": "0x3fbfc00080",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
+ "MSRValue": "0x3FBFC00080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3",
- "MSRValue": "0x3fbfc00100",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
+ "MSRValue": "0x3FBFC00100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3",
- "MSRValue": "0x3fbfc00200",
+ "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
+ "MSRValue": "0x3FBFC00200",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3",
- "MSRValue": "0x3fbfc00091",
+ "BriefDescription": "Counts all demand & prefetch data reads miss in the L3",
+ "MSRValue": "0x3FBFC00091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
"MSRValue": "0x0600400091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram",
- "MSRValue": "0x063f800091",
+ "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
+ "MSRValue": "0x063F800091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache",
- "MSRValue": "0x103fc00091",
+ "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
+ "MSRValue": "0x103FC00091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache",
- "MSRValue": "0x083fc00091",
+ "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
+ "MSRValue": "0x083FC00091",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3",
- "MSRValue": "0x3fbfc00122",
+ "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3",
+ "MSRValue": "0x3FBFC00122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
"MSRValue": "0x0600400122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3",
- "MSRValue": "0x3fbfc00244",
+ "BriefDescription": "Counts all demand & prefetch code reads miss in the L3",
+ "MSRValue": "0x3FBFC00244",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch code reads miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram",
+ "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
"MSRValue": "0x0600400244",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3",
- "MSRValue": "0x3fbfc007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
+ "MSRValue": "0x3FBFC007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram",
- "MSRValue": "0x06004007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
+ "MSRValue": "0x06004007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram",
- "MSRValue": "0x063f8007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
+ "MSRValue": "0x063F8007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache",
- "MSRValue": "0x103fc007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
+ "MSRValue": "0x103FC007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache",
- "MSRValue": "0x083fc007f7",
+ "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
+ "MSRValue": "0x083FC007F7",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all requests that miss in the L3",
- "MSRValue": "0x3fbfc08fff",
+ "BriefDescription": "Counts all requests miss in the L3",
+ "MSRValue": "0x3FBFC08FFF",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts all requests miss in the L3",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
}
[
{
- "EventCode": "0x00",
"UMask": "0x1",
"BriefDescription": "Instructions retired from execution.",
"Counter": "Fixed counter 0",
"CounterHTOff": "Fixed counter 0"
},
{
- "EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when the thread is not in halt state.",
"Counter": "Fixed counter 1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
"Counter": "Fixed counter 1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"UMask": "0x3",
"BriefDescription": "Reference cycles when the core is not in halt state.",
"Counter": "Fixed counter 2",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "UOPS_RETIRED.ALL",
+ "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+ "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 uops or 4 instructions could retire each cycle.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.CONDITIONAL",
+ "PublicDescription": "Counts the number of conditional branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NEAR_RETURN",
+ "PublicDescription": "Counts the number of near return instructions retired.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+ "PublicDescription": "Number of near taken branches retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+ "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address ",
+ "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand data reads ",
+ "BriefDescription": "Counts all demand data reads",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand rfo's ",
+ "BriefDescription": "Counts all demand rfo's",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all demand & prefetch prefetch RFOs ",
+ "BriefDescription": "Counts all demand & prefetch prefetch RFOs",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.ALL_READS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts all data/code/rfo references (demand & prefetch) ",
+ "BriefDescription": "Counts all data/code/rfo references (demand & prefetch)",
"CounterHTOff": "0,1,2,3"
}
]
\ No newline at end of file
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
- "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
- "MetricGroup": "Frontend",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Instruction per taken branch",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "IpTB"
+ },
+ {
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Branch instructions per taken branch. ",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "BpTB"
+ },
+ {
+ "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+ "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+ "MetricGroup": "Instruction_Type;L1_Bound",
+ "MetricName": "IpL"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+ "BriefDescription": "Instructions per Store",
+ "MetricGroup": "Instruction_Type;Store_Bound",
+ "MetricName": "IpS"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Instructions per Branch",
+ "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+ "MetricName": "IpB"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "BriefDescription": "Instruction per (near) call",
+ "MetricGroup": "Branches",
+ "MetricName": "IpCall"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS",
+ "MetricName": "FLOPc"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS_SMT",
+ "MetricName": "FLOPc_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
- "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
- "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
- "MetricGroup": "Unknown_Branches",
- "MetricName": "BAClear_Cost"
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "IpMispredict"
},
{
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
- "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
- "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
- "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
- "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricGroup": "TLB_SMT",
+ "MetricName": "Page_Walks_Utilization_SMT"
+ },
+ {
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L1MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2HPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L3MPKI"
+ },
+ {
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
+ "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
[
{
- "EventCode": "0x00",
"Counter": "Fixed counter 0",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
"CounterHTOff": "Fixed counter 0"
},
{
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.THREAD",
},
{
"PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"AnyThread": "1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"Counter": "Fixed counter 2",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
- "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
- "MetricGroup": "Frontend",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Instruction per taken branch",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "IpTB"
+ },
+ {
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Branch instructions per taken branch. ",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "BpTB"
+ },
+ {
+ "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+ "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+ "MetricGroup": "Instruction_Type;L1_Bound",
+ "MetricName": "IpL"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+ "BriefDescription": "Instructions per Store",
+ "MetricGroup": "Instruction_Type;Store_Bound",
+ "MetricName": "IpS"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Instructions per Branch",
+ "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+ "MetricName": "IpB"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "BriefDescription": "Instruction per (near) call",
+ "MetricGroup": "Branches",
+ "MetricName": "IpCall"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS",
+ "MetricName": "FLOPc"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS_SMT",
+ "MetricName": "FLOPc_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
- "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
- "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
- "MetricGroup": "Unknown_Branches",
- "MetricName": "BAClear_Cost"
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "IpMispredict"
},
{
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
- "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
- "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
- "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
- "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricGroup": "TLB_SMT",
+ "MetricName": "Page_Walks_Utilization_SMT"
+ },
+ {
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L1MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2HPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L3MPKI"
+ },
+ {
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
+ "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
+ "MetricExpr": "cbox_0@event\\=0x0@",
+ "BriefDescription": "Socket actual clocks when any core is active on that socket",
+ "MetricGroup": "",
+ "MetricName": "Socket_CLKS"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
[
{
- "EventCode": "0x00",
"Counter": "Fixed counter 0",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
"CounterHTOff": "Fixed counter 0"
},
{
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.THREAD",
},
{
"PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"AnyThread": "1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"Counter": "Fixed counter 2",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
},
{
"PEBS": "1",
- "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x41",
},
{
"PEBS": "1",
- "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x42",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier. ",
+ "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.",
"EventCode": "0x51",
"Counter": "0,1,2,3",
"UMask": "0x1",
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
- "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
- "MetricGroup": "Frontend",
+ "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS",
+ "MetricName": "FLOPc"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS_SMT",
+ "MetricName": "FLOPc_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
+ "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
+ "MetricExpr": "cbox_0@event\\=0x0@",
+ "BriefDescription": "Socket actual clocks when any core is active on that socket",
+ "MetricGroup": "",
+ "MetricName": "Socket_CLKS"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
[
{
- "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ",
- "EventCode": "0x00",
+ "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.",
"Counter": "Fixed counter 1",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
"CounterHTOff": "Fixed counter 1"
},
{
- "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
- "EventCode": "0x00",
+ "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
"Counter": "Fixed counter 2",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.THREAD",
"CounterHTOff": "Fixed counter 2"
},
{
- "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
- "EventCode": "0x00",
+ "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
"Counter": "Fixed counter 3",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
+ "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x2",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x00",
"Counter": "Fixed counter 2",
"UMask": "0x2",
"AnyThread": "1",
"BriefDescription": "Counts the number of L2 cache misses"
},
{
- "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses. ",
+ "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.",
"EventCode": "0x86",
"Counter": "0,1",
"UMask": "0x4",
"EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES",
"SampleAfterValue": "200003",
- "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses. "
+ "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses."
},
{
- "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted. ",
+ "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted.",
"EventCode": "0x04",
"Counter": "0,1",
"UMask": "0x1",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000070 ",
+ "MSRValue": "0x4000000070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400070 ",
+ "MSRValue": "0x1000400070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400070 ",
+ "MSRValue": "0x0800400070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080070 ",
+ "MSRValue": "0x1000080070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080070 ",
+ "MSRValue": "0x0800080070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010070 ",
+ "MSRValue": "0x0000010070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x40000032f7 ",
+ "MSRValue": "0x40000032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x10004032f7 ",
+ "MSRValue": "0x10004032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x08004032f7 ",
+ "MSRValue": "0x08004032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x10000832f7 ",
+ "MSRValue": "0x10000832f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x08000832f7 ",
+ "MSRValue": "0x08000832f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x00000132f7 ",
+ "MSRValue": "0x00000132f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000044 ",
+ "MSRValue": "0x4000000044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400044 ",
+ "MSRValue": "0x1000400044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400044 ",
+ "MSRValue": "0x0800400044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080044 ",
+ "MSRValue": "0x1000080044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080044 ",
+ "MSRValue": "0x0800080044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010044 ",
+ "MSRValue": "0x0000010044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000022 ",
+ "MSRValue": "0x4000000022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400022 ",
+ "MSRValue": "0x1000400022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400022 ",
+ "MSRValue": "0x0800400022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080022 ",
+ "MSRValue": "0x1000080022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080022 ",
+ "MSRValue": "0x0800080022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010022 ",
+ "MSRValue": "0x0000010022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000003091 ",
+ "MSRValue": "0x4000003091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000403091 ",
+ "MSRValue": "0x1000403091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800403091 ",
+ "MSRValue": "0x0800403091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000083091 ",
+ "MSRValue": "0x1000083091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800083091 ",
+ "MSRValue": "0x0800083091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000013091 ",
+ "MSRValue": "0x0000013091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000008000 ",
+ "MSRValue": "0x4000008000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000408000 ",
+ "MSRValue": "0x1000408000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800408000 ",
+ "MSRValue": "0x0800408000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000088000 ",
+ "MSRValue": "0x1000088000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800088000 ",
+ "MSRValue": "0x0800088000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000018000 ",
+ "MSRValue": "0x0000018000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000014800 ",
+ "MSRValue": "0x0000014800",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000014000 ",
+ "MSRValue": "0x0000014000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000002000 ",
+ "MSRValue": "0x4000002000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000402000 ",
+ "MSRValue": "0x1000402000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800402000 ",
+ "MSRValue": "0x0800402000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000082000 ",
+ "MSRValue": "0x1000082000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800082000 ",
+ "MSRValue": "0x0800082000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000012000 ",
+ "MSRValue": "0x0000012000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000001000 ",
+ "MSRValue": "0x4000001000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000401000 ",
+ "MSRValue": "0x1000401000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800401000 ",
+ "MSRValue": "0x0800401000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000081000 ",
+ "MSRValue": "0x1000081000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800081000 ",
+ "MSRValue": "0x0800081000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000011000 ",
+ "MSRValue": "0x0000011000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010800 ",
+ "MSRValue": "0x0000010800",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000400 ",
+ "MSRValue": "0x4000000400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400400 ",
+ "MSRValue": "0x1000400400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400400 ",
+ "MSRValue": "0x0800400400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080400 ",
+ "MSRValue": "0x1000080400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080400 ",
+ "MSRValue": "0x0800080400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010400 ",
+ "MSRValue": "0x0000010400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000200 ",
+ "MSRValue": "0x4000000200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400200 ",
+ "MSRValue": "0x1000400200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400200 ",
+ "MSRValue": "0x0800400200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080200 ",
+ "MSRValue": "0x1000080200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080200 ",
+ "MSRValue": "0x0800080200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010200 ",
+ "MSRValue": "0x0000010200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400100 ",
+ "MSRValue": "0x1000400100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400100 ",
+ "MSRValue": "0x0800400100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080100 ",
+ "MSRValue": "0x1000080100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080100 ",
+ "MSRValue": "0x0800080100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010100 ",
+ "MSRValue": "0x0000010100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000080 ",
+ "MSRValue": "0x4000000080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400080 ",
+ "MSRValue": "0x1000400080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400080 ",
+ "MSRValue": "0x0800400080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080080 ",
+ "MSRValue": "0x1000080080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080080 ",
+ "MSRValue": "0x0800080080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010080 ",
+ "MSRValue": "0x0000010080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000040 ",
+ "MSRValue": "0x4000000040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400040 ",
+ "MSRValue": "0x1000400040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400040 ",
+ "MSRValue": "0x0800400040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080040 ",
+ "MSRValue": "0x1000080040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080040 ",
+ "MSRValue": "0x0800080040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010040 ",
+ "MSRValue": "0x0000010040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400020 ",
+ "MSRValue": "0x1000400020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400020 ",
+ "MSRValue": "0x0800400020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080020 ",
+ "MSRValue": "0x1000080020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080020 ",
+ "MSRValue": "0x0800080020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000020020 ",
+ "MSRValue": "0x0000020020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010020 ",
+ "MSRValue": "0x0000010020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000004 ",
+ "MSRValue": "0x4000000004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400004 ",
+ "MSRValue": "0x1000400004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400004 ",
+ "MSRValue": "0x0800400004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080004 ",
+ "MSRValue": "0x1000080004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080004 ",
+ "MSRValue": "0x0800080004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010004 ",
+ "MSRValue": "0x0000010004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000002 ",
+ "MSRValue": "0x4000000002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400002 ",
+ "MSRValue": "0x1000400002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400002 ",
+ "MSRValue": "0x0800400002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080002 ",
+ "MSRValue": "0x1000080002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080002 ",
+ "MSRValue": "0x0800080002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010002 ",
+ "MSRValue": "0x0000010002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x4000000001 ",
+ "MSRValue": "0x4000000001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000400001 ",
+ "MSRValue": "0x1000400001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800400001 ",
+ "MSRValue": "0x0800400001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_E_F",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1000080001 ",
+ "MSRValue": "0x1000080001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0800080001 ",
+ "MSRValue": "0x0800080001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_E_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0000010001 ",
+ "MSRValue": "0x0000010001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000001 ",
+ "MSRValue": "0x0002000001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000002 ",
+ "MSRValue": "0x0002000002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000004 ",
+ "MSRValue": "0x0002000004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000020 ",
+ "MSRValue": "0x0002000020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000080 ",
+ "MSRValue": "0x0002000080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000100 ",
+ "MSRValue": "0x0002000100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000200 ",
+ "MSRValue": "0x0002000200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000400 ",
+ "MSRValue": "0x0002000400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002001000 ",
+ "MSRValue": "0x0002001000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002002000 ",
+ "MSRValue": "0x0002002000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002008000 ",
+ "MSRValue": "0x0002008000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002003091 ",
+ "MSRValue": "0x0002003091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000022 ",
+ "MSRValue": "0x0002000022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000044 ",
+ "MSRValue": "0x0002000044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x00020032f7 ",
+ "MSRValue": "0x00020032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0002000070 ",
+ "MSRValue": "0x0002000070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_M",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state ",
+ "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000001 ",
+ "MSRValue": "0x0004000001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000002 ",
+ "MSRValue": "0x0004000002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000004 ",
+ "MSRValue": "0x0004000004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000020 ",
+ "MSRValue": "0x0004000020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000040 ",
+ "MSRValue": "0x0004000040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000080 ",
+ "MSRValue": "0x0004000080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000100 ",
+ "MSRValue": "0x0004000100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000200 ",
+ "MSRValue": "0x0004000200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000400 ",
+ "MSRValue": "0x0004000400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004001000 ",
+ "MSRValue": "0x0004001000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004002000 ",
+ "MSRValue": "0x0004002000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004008000 ",
+ "MSRValue": "0x0004008000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004003091 ",
+ "MSRValue": "0x0004003091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000022 ",
+ "MSRValue": "0x0004000022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000044 ",
+ "MSRValue": "0x0004000044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x00040032f7 ",
+ "MSRValue": "0x00040032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0004000070 ",
+ "MSRValue": "0x0004000070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_E",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state ",
+ "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000001 ",
+ "MSRValue": "0x0008000001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000002 ",
+ "MSRValue": "0x0008000002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000004 ",
+ "MSRValue": "0x0008000004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000020 ",
+ "MSRValue": "0x0008000020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000080 ",
+ "MSRValue": "0x0008000080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000100 ",
+ "MSRValue": "0x0008000100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000200 ",
+ "MSRValue": "0x0008000200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000400 ",
+ "MSRValue": "0x0008000400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008001000 ",
+ "MSRValue": "0x0008001000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008002000 ",
+ "MSRValue": "0x0008002000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008008000 ",
+ "MSRValue": "0x0008008000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008003091 ",
+ "MSRValue": "0x0008003091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000022 ",
+ "MSRValue": "0x0008000022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0008000044 ",
+ "MSRValue": "0x0008000044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x00080032f7 ",
+ "MSRValue": "0x00080032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_S",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in S state ",
+ "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in S state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000001 ",
+ "MSRValue": "0x0010000001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000002 ",
+ "MSRValue": "0x0010000002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000004 ",
+ "MSRValue": "0x0010000004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000020 ",
+ "MSRValue": "0x0010000020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000040 ",
+ "MSRValue": "0x0010000040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000080 ",
+ "MSRValue": "0x0010000080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000100 ",
+ "MSRValue": "0x0010000100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000200 ",
+ "MSRValue": "0x0010000200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000400 ",
+ "MSRValue": "0x0010000400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010001000 ",
+ "MSRValue": "0x0010001000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010002000 ",
+ "MSRValue": "0x0010002000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010008000 ",
+ "MSRValue": "0x0010008000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010003091 ",
+ "MSRValue": "0x0010003091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000022 ",
+ "MSRValue": "0x0010000022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000044 ",
+ "MSRValue": "0x0010000044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x00100032f7 ",
+ "MSRValue": "0x00100032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0010000070 ",
+ "MSRValue": "0x0010000070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_F",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state ",
+ "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180002 ",
+ "MSRValue": "0x1800180002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180004 ",
+ "MSRValue": "0x1800180004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180020 ",
+ "MSRValue": "0x1800180020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180040 ",
+ "MSRValue": "0x1800180040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180080 ",
+ "MSRValue": "0x1800180080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180100 ",
+ "MSRValue": "0x1800180100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180200 ",
+ "MSRValue": "0x1800180200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180400 ",
+ "MSRValue": "0x1800180400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800181000 ",
+ "MSRValue": "0x1800181000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800182000 ",
+ "MSRValue": "0x1800182000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800188000 ",
+ "MSRValue": "0x1800188000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800183091 ",
+ "MSRValue": "0x1800183091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180022 ",
+ "MSRValue": "0x1800180022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180044 ",
+ "MSRValue": "0x1800180044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x18001832f7 ",
+ "MSRValue": "0x18001832f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800180070 ",
+ "MSRValue": "0x1800180070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800400002 ",
+ "MSRValue": "0x1800400002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800400004 ",
+ "MSRValue": "0x1800400004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800400040 ",
+ "MSRValue": "0x1800400040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800400080 ",
+ "MSRValue": "0x1800400080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800400100 ",
+ "MSRValue": "0x1800400100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800400400 ",
+ "MSRValue": "0x1800400400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800401000 ",
+ "MSRValue": "0x1800401000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800402000 ",
+ "MSRValue": "0x1800402000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800408000 ",
+ "MSRValue": "0x1800408000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800403091 ",
+ "MSRValue": "0x1800403091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800400022 ",
+ "MSRValue": "0x1800400022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800400044 ",
+ "MSRValue": "0x1800400044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x18004032f7 ",
+ "MSRValue": "0x18004032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x1800400070 ",
+ "MSRValue": "0x1800400070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400070 ",
+ "MSRValue": "0x0100400070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200070 ",
+ "MSRValue": "0x0080200070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000070 ",
+ "MSRValue": "0x0101000070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800070 ",
+ "MSRValue": "0x0080800070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x01004032f7 ",
+ "MSRValue": "0x01004032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts any Read request that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x00802032f7 ",
+ "MSRValue": "0x00802032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x01010032f7 ",
+ "MSRValue": "0x01010032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts any Read request that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x00808032f7 ",
+ "MSRValue": "0x00808032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400044 ",
+ "MSRValue": "0x0100400044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200044 ",
+ "MSRValue": "0x0080200044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000044 ",
+ "MSRValue": "0x0101000044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800044 ",
+ "MSRValue": "0x0080800044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400022 ",
+ "MSRValue": "0x0100400022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200022 ",
+ "MSRValue": "0x0080200022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000022 ",
+ "MSRValue": "0x0101000022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts Demand cacheable data write requests that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800022 ",
+ "MSRValue": "0x0080800022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100403091 ",
+ "MSRValue": "0x0100403091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080203091 ",
+ "MSRValue": "0x0080203091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101003091 ",
+ "MSRValue": "0x0101003091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080803091 ",
+ "MSRValue": "0x0080803091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100408000 ",
+ "MSRValue": "0x0100408000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080208000 ",
+ "MSRValue": "0x0080208000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101008000 ",
+ "MSRValue": "0x0101008000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts any request that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080808000 ",
+ "MSRValue": "0x0080808000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100402000 ",
+ "MSRValue": "0x0100402000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080202000 ",
+ "MSRValue": "0x0080202000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101002000 ",
+ "MSRValue": "0x0101002000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080802000 ",
+ "MSRValue": "0x0080802000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100401000 ",
+ "MSRValue": "0x0100401000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080201000 ",
+ "MSRValue": "0x0080201000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101001000 ",
+ "MSRValue": "0x0101001000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080801000 ",
+ "MSRValue": "0x0080801000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400400 ",
+ "MSRValue": "0x0100400400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200400 ",
+ "MSRValue": "0x0080200400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000400 ",
+ "MSRValue": "0x0101000400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800400 ",
+ "MSRValue": "0x0080800400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400200 ",
+ "MSRValue": "0x0100400200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200200 ",
+ "MSRValue": "0x0080200200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000200 ",
+ "MSRValue": "0x0101000200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800200 ",
+ "MSRValue": "0x0080800200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400100 ",
+ "MSRValue": "0x0100400100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_FAR",
"MSRIndex": "0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200100 ",
+ "MSRValue": "0x0080200100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000100 ",
+ "MSRValue": "0x0101000100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_FAR",
"MSRIndex": "0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800100 ",
+ "MSRValue": "0x0080800100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x2000020080 ",
+ "MSRValue": "0x2000020080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.NON_DRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400080 ",
+ "MSRValue": "0x0100400080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200080 ",
+ "MSRValue": "0x0080200080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000080 ",
+ "MSRValue": "0x0101000080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800080 ",
+ "MSRValue": "0x0080800080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400040 ",
+ "MSRValue": "0x0100400040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200040 ",
+ "MSRValue": "0x0080200040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000040 ",
+ "MSRValue": "0x0101000040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800040 ",
+ "MSRValue": "0x0080800040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x2000020020 ",
+ "MSRValue": "0x2000020020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.NON_DRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400020 ",
+ "MSRValue": "0x0100400020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200020 ",
+ "MSRValue": "0x0080200020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000020 ",
+ "MSRValue": "0x0101000020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800020 ",
+ "MSRValue": "0x0080800020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400004 ",
+ "MSRValue": "0x0100400004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200004 ",
+ "MSRValue": "0x0080200004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000004 ",
+ "MSRValue": "0x0101000004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800004 ",
+ "MSRValue": "0x0080800004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400002 ",
+ "MSRValue": "0x0100400002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200002 ",
+ "MSRValue": "0x0080200002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000002 ",
+ "MSRValue": "0x0101000002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800002 ",
+ "MSRValue": "0x0080800002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0100400001 ",
+ "MSRValue": "0x0100400001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080200001 ",
+ "MSRValue": "0x0080200001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0101000001 ",
+ "MSRValue": "0x0101000001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_FAR",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far. ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far.",
"Offcore": "1"
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0080800001 ",
+ "MSRValue": "0x0080800001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_NEAR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600001 ",
+ "MSRValue": "0x0180600001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600002 ",
+ "MSRValue": "0x0180600002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600004 ",
+ "MSRValue": "0x0180600004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600020 ",
+ "MSRValue": "0x0180600020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600080 ",
+ "MSRValue": "0x0180600080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600100 ",
+ "MSRValue": "0x0180600100",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600200 ",
+ "MSRValue": "0x0180600200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600400 ",
+ "MSRValue": "0x0180600400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180601000 ",
+ "MSRValue": "0x0180601000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180608000 ",
+ "MSRValue": "0x0180608000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180603091 ",
+ "MSRValue": "0x0180603091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600022 ",
+ "MSRValue": "0x0180600022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600044 ",
+ "MSRValue": "0x0180600044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x01806032f7 ",
+ "MSRValue": "0x01806032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0180600070 ",
+ "MSRValue": "0x0180600070",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800001 ",
+ "MSRValue": "0x0181800001",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800002 ",
+ "MSRValue": "0x0181800002",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800004 ",
+ "MSRValue": "0x0181800004",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800020 ",
+ "MSRValue": "0x0181800020",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800040 ",
+ "MSRValue": "0x0181800040",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800080 ",
+ "MSRValue": "0x0181800080",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800200 ",
+ "MSRValue": "0x0181800200",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800400 ",
+ "MSRValue": "0x0181800400",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181801000 ",
+ "MSRValue": "0x0181801000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181802000 ",
+ "MSRValue": "0x0181802000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181808000 ",
+ "MSRValue": "0x0181808000",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181803091 ",
+ "MSRValue": "0x0181803091",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800022 ",
+ "MSRValue": "0x0181800022",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x0181800044 ",
+ "MSRValue": "0x0181800044",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR",
},
{
"EventCode": "0xB7",
- "MSRValue": "0x01818032f7 ",
+ "MSRValue": "0x01818032f7",
"Counter": "0,1",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.ANY_READ.DDR",
"BriefDescription": "Counts the number of micro-ops retired that are from the complex flows issued by the micro-sequencer (MS)."
},
{
- "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists. ",
+ "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists.",
"EventCode": "0xC2",
"Counter": "0,1",
"UMask": "0x10",
"UMask": "0x20",
"EventName": "NO_ALLOC_CYCLES.RAT_STALL",
"SampleAfterValue": "200003",
- "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted. "
+ "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted."
},
{
"PublicDescription": "This event counts the number of core cycles when no uops are allocated, the instruction queue is empty and the alloc pipe is stalled waiting for instructions to be fetched.",
"UMask": "0x1f",
"EventName": "RS_FULL_STALL.ALL",
"SampleAfterValue": "200003",
- "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full. "
+ "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full."
},
{
"EventCode": "0xC0",
"UMask": "0x1",
"EventName": "CYCLES_DIV_BUSY.ALL",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles the number of core cycles when divider is busy. Does not imply a stall waiting for the divider. "
+ "BriefDescription": "Cycles the number of core cycles when divider is busy. Does not imply a stall waiting for the divider."
},
{
"PublicDescription": "This event counts the number of instructions that retire. For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires. The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps.",
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
"BriefDescription": "Counts the number of unhalted reference clock cycles"
},
{
- "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter\r\n",
- "EventCode": "0x00",
+ "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter",
"Counter": "Fixed counter 2",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.THREAD",
"BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles"
},
{
- "EventCode": "0x00",
"Counter": "Fixed counter 3",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"UMask": "0x1",
"EventName": "RECYCLEQ.LD_BLOCK_ST_FORWARD",
"SampleAfterValue": "200003",
- "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store ",
+ "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store",
"Data_LA": "1"
},
{
"EdgeDetect": "1"
},
{
- "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress. ",
+ "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress.",
"EventCode": "0x05",
"Counter": "0,1",
"UMask": "0x2",
[
{
- "PEBS": "1",
- "EventCode": "0xD0",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x11",
- "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
- "SampleAfterValue": "100003",
- "BriefDescription": "Retired load uops that miss the STLB.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x1",
+ "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Demand Data Read requests that hit L2 cache.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xD0",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x12",
- "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
- "SampleAfterValue": "100003",
- "BriefDescription": "Retired store uops that miss the STLB.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x3",
+ "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Demand Data Read requests.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xD0",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x21",
- "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
- "SampleAfterValue": "100007",
- "BriefDescription": "Retired load uops with locked access.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x4",
+ "EventName": "L2_RQSTS.RFO_HIT",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "RFO requests that hit L2 cache.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
- "EventCode": "0xD0",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x41",
- "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
- "SampleAfterValue": "100003",
- "BriefDescription": "Retired load uops that split across a cacheline boundary.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x8",
+ "EventName": "L2_RQSTS.RFO_MISS",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "RFO requests that miss L2 cache.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
- "EventCode": "0xD0",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x42",
- "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
- "SampleAfterValue": "100003",
- "BriefDescription": "Retired store uops that split across a cacheline boundary.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0xc",
+ "EventName": "L2_RQSTS.ALL_RFO",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "RFO requests to L2 cache.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "PublicDescription": "This event counts the number of load uops retired",
- "EventCode": "0xD0",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x81",
- "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
- "SampleAfterValue": "2000003",
- "BriefDescription": "All retired load uops.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x10",
+ "EventName": "L2_RQSTS.CODE_RD_HIT",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "PublicDescription": "This event counts the number of store uops retired.",
- "EventCode": "0xD0",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x82",
- "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
- "SampleAfterValue": "2000003",
- "BriefDescription": "All retired store uops.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x20",
+ "EventName": "L2_RQSTS.CODE_RD_MISS",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "L2 cache misses when fetching instructions.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xD1",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x30",
+ "EventName": "L2_RQSTS.ALL_CODE_RD",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "L2 code requests.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xD1",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
- "SampleAfterValue": "100003",
- "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x40",
+ "EventName": "L2_RQSTS.PF_HIT",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required.",
- "EventCode": "0xD1",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT",
- "SampleAfterValue": "50021",
- "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x80",
+ "EventName": "L2_RQSTS.PF_MISS",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xD1",
+ "EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x40",
- "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
- "SampleAfterValue": "100003",
- "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0xc0",
+ "EventName": "L2_RQSTS.ALL_PF",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Requests from L2 hardware prefetchers.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xD2",
+ "EventCode": "0x27",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS",
- "SampleAfterValue": "20011",
- "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "PEBS": "1",
- "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a non-modified state.",
- "EventCode": "0xD2",
- "Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT",
- "SampleAfterValue": "20011",
- "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.",
- "CounterHTOff": "0,1,2,3"
+ "EventName": "L2_STORE_LOCK_RQSTS.MISS",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "RFOs that miss cache lines.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2.",
- "EventCode": "0xD2",
+ "EventCode": "0x27",
"Counter": "0,1,2,3",
"UMask": "0x4",
- "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM",
- "SampleAfterValue": "20011",
- "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.",
- "CounterHTOff": "0,1,2,3"
+ "EventName": "L2_STORE_LOCK_RQSTS.HIT_E",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "RFOs that hit cache lines in E state.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xD2",
+ "EventCode": "0x27",
"Counter": "0,1,2,3",
"UMask": "0x8",
- "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE",
- "SampleAfterValue": "100003",
- "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.",
- "CounterHTOff": "0,1,2,3"
+ "EventName": "L2_STORE_LOCK_RQSTS.HIT_M",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "RFOs that hit cache lines in M state.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "PublicDescription": "This event counts retired demand loads that missed the last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops.",
- "EventCode": "0xD4",
+ "EventCode": "0x27",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS",
- "SampleAfterValue": "100007",
- "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load.",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0xf",
+ "EventName": "L2_STORE_LOCK_RQSTS.ALL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "RFOs that access cache lines in any state.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier. ",
- "EventCode": "0x51",
+ "EventCode": "0x28",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "L1D.REPLACEMENT",
- "SampleAfterValue": "2000003",
- "BriefDescription": "L1D data line replacements.",
+ "EventName": "L2_L1D_WB_RQSTS.MISS",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x51",
+ "EventCode": "0x28",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "EventName": "L1D.ALLOCATED_IN_M",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Allocated L1D data cache lines in M state.",
+ "EventName": "L2_L1D_WB_RQSTS.HIT_S",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x51",
+ "EventCode": "0x28",
"Counter": "0,1,2,3",
"UMask": "0x4",
- "EventName": "L1D.EVICTION",
- "SampleAfterValue": "2000003",
- "BriefDescription": "L1D data cache lines in M state evicted due to replacement.",
+ "EventName": "L2_L1D_WB_RQSTS.HIT_E",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x51",
+ "EventCode": "0x28",
"Counter": "0,1,2,3",
"UMask": "0x8",
- "EventName": "L1D.ALL_M_REPLACEMENT",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.",
+ "EventName": "L2_L1D_WB_RQSTS.HIT_M",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0x28",
+ "Counter": "0,1,2,3",
+ "UMask": "0xf",
+ "EventName": "L2_L1D_WB_RQSTS.ALL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0x2E",
+ "Counter": "0,1,2,3",
+ "UMask": "0x41",
+ "EventName": "LONGEST_LAT_CACHE.MISS",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Core-originated cacheable demand requests missed LLC.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0x2E",
+ "Counter": "0,1,2,3",
+ "UMask": "0x4f",
+ "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "2"
},
{
- "EventCode": "0x63",
+ "EventCode": "0x48",
+ "Counter": "2",
+ "UMask": "0x1",
+ "AnyThread": "1",
+ "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+ "CounterMask": "1",
+ "CounterHTOff": "2"
+ },
+ {
+ "EventCode": "0x48",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION",
+ "EventName": "L1D_PEND_MISS.FB_FULL",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when L1D is locked.",
+ "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+ "CounterMask": "1",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.",
+ "EventCode": "0x51",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "L1D.REPLACEMENT",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "L1D data line replacements.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0x51",
+ "Counter": "0,1,2,3",
+ "UMask": "0x2",
+ "EventName": "L1D.ALLOCATED_IN_M",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Allocated L1D data cache lines in M state.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0x51",
+ "Counter": "0,1,2,3",
+ "UMask": "0x4",
+ "EventName": "L1D.EVICTION",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "L1D data cache lines in M state evicted due to replacement.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0x51",
+ "Counter": "0,1,2,3",
+ "UMask": "0x8",
+ "EventName": "L1D.ALL_M_REPLACEMENT",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0x60",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+ "CounterMask": "6",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"EventCode": "0x60",
"Counter": "0,1,2,3",
"BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0x60",
+ "Counter": "0,1,2,3",
+ "UMask": "0x4",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
+ "CounterMask": "1",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"EventCode": "0x60",
"Counter": "0,1,2,3",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0x63",
+ "Counter": "0,1,2,3",
+ "UMask": "0x2",
+ "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles when L1D is locked.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"EventCode": "0xB0",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x24",
+ "EventCode": "0xBF",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
- "SampleAfterValue": "200003",
- "BriefDescription": "Demand Data Read requests that hit L2 cache.",
+ "UMask": "0x5",
+ "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x24",
+ "PEBS": "1",
+ "EventCode": "0xD0",
"Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "L2_RQSTS.RFO_HIT",
- "SampleAfterValue": "200003",
- "BriefDescription": "RFO requests that hit L2 cache.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x11",
+ "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x24",
+ "PEBS": "1",
+ "EventCode": "0xD0",
"Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "L2_RQSTS.RFO_MISS",
- "SampleAfterValue": "200003",
- "BriefDescription": "RFO requests that miss L2 cache.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x12",
+ "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PEBS": "1",
+ "EventCode": "0xD0",
+ "Counter": "0,1,2,3",
+ "UMask": "0x21",
+ "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x24",
+ "PEBS": "1",
+ "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)",
+ "EventCode": "0xD0",
"Counter": "0,1,2,3",
- "UMask": "0x10",
- "EventName": "L2_RQSTS.CODE_RD_HIT",
- "SampleAfterValue": "200003",
- "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x41",
+ "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x24",
+ "PEBS": "1",
+ "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)",
+ "EventCode": "0xD0",
"Counter": "0,1,2,3",
- "UMask": "0x20",
- "EventName": "L2_RQSTS.CODE_RD_MISS",
- "SampleAfterValue": "200003",
- "BriefDescription": "L2 cache misses when fetching instructions.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x42",
+ "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x24",
+ "PEBS": "1",
+ "PublicDescription": "This event counts the number of load uops retired (Precise Event)",
+ "EventCode": "0xD0",
"Counter": "0,1,2,3",
- "UMask": "0x40",
- "EventName": "L2_RQSTS.PF_HIT",
- "SampleAfterValue": "200003",
- "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x81",
+ "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "All retired load uops. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x24",
+ "PEBS": "1",
+ "PublicDescription": "This event counts the number of store uops retired. (Precise Event - PEBS)",
+ "EventCode": "0xD0",
"Counter": "0,1,2,3",
- "UMask": "0x80",
- "EventName": "L2_RQSTS.PF_MISS",
- "SampleAfterValue": "200003",
- "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x82",
+ "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "All retired store uops. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x27",
+ "PEBS": "1",
+ "EventCode": "0xD1",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "L2_STORE_LOCK_RQSTS.MISS",
- "SampleAfterValue": "200003",
- "BriefDescription": "RFOs that miss cache lines.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x27",
+ "PEBS": "1",
+ "EventCode": "0xD1",
"Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "L2_STORE_LOCK_RQSTS.HIT_E",
- "SampleAfterValue": "200003",
- "BriefDescription": "RFOs that hit cache lines in E state.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x2",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x27",
+ "PEBS": "1",
+ "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required. (Precise Event - PEBS)",
+ "EventCode": "0xD1",
"Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "L2_STORE_LOCK_RQSTS.HIT_M",
- "SampleAfterValue": "200003",
- "BriefDescription": "RFOs that hit cache lines in M state.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x4",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT",
+ "SampleAfterValue": "50021",
+ "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x27",
+ "PEBS": "1",
+ "EventCode": "0xD1",
"Counter": "0,1,2,3",
- "UMask": "0xf",
- "EventName": "L2_STORE_LOCK_RQSTS.ALL",
- "SampleAfterValue": "200003",
- "BriefDescription": "RFOs that access cache lines in any state.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x40",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x28",
+ "PEBS": "1",
+ "EventCode": "0xD2",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "L2_L1D_WB_RQSTS.MISS",
- "SampleAfterValue": "200003",
- "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS",
+ "SampleAfterValue": "20011",
+ "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x28",
+ "PEBS": "1",
+ "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a non-modified state. (Precise Event - PEBS)",
+ "EventCode": "0xD2",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "EventName": "L2_L1D_WB_RQSTS.HIT_S",
- "SampleAfterValue": "200003",
- "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT",
+ "SampleAfterValue": "20011",
+ "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x28",
+ "PEBS": "1",
+ "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2. (Precise Event - PEBS)",
+ "EventCode": "0xD2",
"Counter": "0,1,2,3",
"UMask": "0x4",
- "EventName": "L2_L1D_WB_RQSTS.HIT_E",
- "SampleAfterValue": "200003",
- "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM",
+ "SampleAfterValue": "20011",
+ "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x28",
+ "PEBS": "1",
+ "EventCode": "0xD2",
"Counter": "0,1,2,3",
"UMask": "0x8",
- "EventName": "L2_L1D_WB_RQSTS.HIT_M",
- "SampleAfterValue": "200003",
- "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x28",
+ "PEBS": "1",
+ "PublicDescription": "This event counts retired demand loads that missed the last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops. (Precise Event - PEBS)",
+ "EventCode": "0xD4",
"Counter": "0,1,2,3",
- "UMask": "0xf",
- "EventName": "L2_L1D_WB_RQSTS.ALL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x2",
+ "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xF0",
"BriefDescription": "Dirty L2 cache lines filling the L2.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
- {
- "EventCode": "0x2E",
- "Counter": "0,1,2,3",
- "UMask": "0x41",
- "EventName": "LONGEST_LAT_CACHE.MISS",
- "SampleAfterValue": "100003",
- "BriefDescription": "Core-originated cacheable demand requests missed LLC.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x2E",
- "Counter": "0,1,2,3",
- "UMask": "0x4f",
- "EventName": "LONGEST_LAT_CACHE.REFERENCE",
- "SampleAfterValue": "100003",
- "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
{
"EventCode": "0xF4",
"Counter": "0,1,2,3",
"BriefDescription": "Split locks in SQ.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
- {
- "EventCode": "0x24",
- "Counter": "0,1,2,3",
- "UMask": "0x3",
- "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
- "SampleAfterValue": "200003",
- "BriefDescription": "Demand Data Read requests.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x24",
- "Counter": "0,1,2,3",
- "UMask": "0xc",
- "EventName": "L2_RQSTS.ALL_RFO",
- "SampleAfterValue": "200003",
- "BriefDescription": "RFO requests to L2 cache.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x24",
- "Counter": "0,1,2,3",
- "UMask": "0x30",
- "EventName": "L2_RQSTS.ALL_CODE_RD",
- "SampleAfterValue": "200003",
- "BriefDescription": "L2 code requests.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x24",
- "Counter": "0,1,2,3",
- "UMask": "0xc0",
- "EventName": "L2_RQSTS.ALL_PF",
- "SampleAfterValue": "200003",
- "BriefDescription": "Requests from L2 hardware prefetchers.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xBF",
- "Counter": "0,1,2,3",
- "UMask": "0x5",
- "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES",
- "SampleAfterValue": "100003",
- "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.",
- "CounterMask": "1",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x60",
- "Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
- "CounterMask": "1",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x60",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
- "CounterMask": "6",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x48",
- "Counter": "2",
- "UMask": "0x1",
- "AnyThread": "1",
- "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
- "CounterMask": "1",
- "CounterHTOff": "2"
- },
- {
- "EventCode": "0x48",
- "Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "L1D_PEND_MISS.FB_FULL",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
- "CounterMask": "1",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
{
"EventCode": "0xB7, 0xBB",
"MSRValue": "0x10003c0244",
"EventName": "OFFCORE_RESPONSE.DATA_IN.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE",
+ "BriefDescription": "REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT_M.HITM",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM",
+ "BriefDescription": "REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.PF_IFETCH.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE",
+ "BriefDescription": "REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE",
+ "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE",
+ "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE",
"CounterHTOff": "0,1,2,3"
}
]
\ No newline at end of file
[
- {
- "EventCode": "0xC1",
- "Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "OTHER_ASSISTS.AVX_STORE",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xC1",
- "Counter": "0,1,2,3",
- "UMask": "0x10",
- "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xC1",
- "Counter": "0,1,2,3",
- "UMask": "0x20",
- "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xCA",
- "Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "FP_ASSIST.X87_OUTPUT",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of X87 assists due to output value.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xCA",
- "Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "FP_ASSIST.X87_INPUT",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of X87 assists due to input value.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xCA",
- "Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "FP_ASSIST.SIMD_OUTPUT",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of SIMD FP assists due to Output values.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xCA",
- "Counter": "0,1,2,3",
- "UMask": "0x10",
- "EventName": "FP_ASSIST.SIMD_INPUT",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of SIMD FP assists due to input values.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
{
"EventCode": "0x10",
"Counter": "0,1,2,3",
"BriefDescription": "Number of AVX-256 Computational FP double precision uops issued this cycle.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0xC1",
+ "Counter": "0,1,2,3",
+ "UMask": "0x8",
+ "EventName": "OTHER_ASSISTS.AVX_STORE",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xC1",
+ "Counter": "0,1,2,3",
+ "UMask": "0x10",
+ "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xC1",
+ "Counter": "0,1,2,3",
+ "UMask": "0x20",
+ "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xCA",
+ "Counter": "0,1,2,3",
+ "UMask": "0x2",
+ "EventName": "FP_ASSIST.X87_OUTPUT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of X87 assists due to output value.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xCA",
+ "Counter": "0,1,2,3",
+ "UMask": "0x4",
+ "EventName": "FP_ASSIST.X87_INPUT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of X87 assists due to input value.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xCA",
+ "Counter": "0,1,2,3",
+ "UMask": "0x8",
+ "EventName": "FP_ASSIST.SIMD_OUTPUT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of SIMD FP assists due to Output values.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xCA",
+ "Counter": "0,1,2,3",
+ "UMask": "0x10",
+ "EventName": "FP_ASSIST.SIMD_INPUT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of SIMD FP assists due to input values.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"EventCode": "0xCA",
"Counter": "0,1,2,3",
[
- {
- "EventCode": "0x80",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "ICACHE.HIT",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.",
- "EventCode": "0x80",
- "Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "ICACHE.MISSES",
- "SampleAfterValue": "200003",
- "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "IDQ.DSB_UOPS",
+ "UMask": "0x4",
+ "EventName": "IDQ.MITE_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+ "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x10",
- "EventName": "IDQ.MS_DSB_UOPS",
+ "UMask": "0x8",
+ "EventName": "IDQ.DSB_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x20",
- "EventName": "IDQ.MS_MITE_UOPS",
+ "UMask": "0x8",
+ "EventName": "IDQ.DSB_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+ "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x30",
- "EventName": "IDQ.MS_UOPS",
+ "UMask": "0x10",
+ "EventName": "IDQ.MS_DSB_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+ "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more information.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x30",
- "EventName": "IDQ.MS_CYCLES",
+ "UMask": "0x10",
+ "EventName": "IDQ.MS_DSB_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+ "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled. In the ideal case 4 uops can be delivered each cycle. The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them. This event is used in determining the front-end bound category of the top-down pipeline slots characterization.",
- "EventCode": "0x9C",
+ "EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+ "UMask": "0x10",
+ "EdgeDetect": "1",
+ "EventName": "IDQ.MS_DSB_OCCUR",
"SampleAfterValue": "2000003",
- "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .",
- "CounterHTOff": "0,1,2,3"
+ "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
+ "CounterMask": "1",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x9C",
+ "EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+ "UMask": "0x18",
+ "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
+ "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.",
"CounterMask": "4",
- "CounterHTOff": "0,1,2,3"
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x9C",
+ "EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+ "UMask": "0x18",
+ "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
- "CounterMask": "3",
- "CounterHTOff": "0,1,2,3"
+ "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.",
+ "CounterMask": "1",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xAB",
+ "EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "DSB2MITE_SWITCHES.COUNT",
+ "UMask": "0x20",
+ "EventName": "IDQ.MS_MITE_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.",
+ "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline. It excludes cycles when the back-end cannot accept new micro-ops. The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.",
- "EventCode": "0xAB",
+ "EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
+ "UMask": "0x24",
+ "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
+ "BriefDescription": "Cycles MITE is delivering 4 Uops.",
+ "CounterMask": "4",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xAC",
+ "EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "DSB_FILL.OTHER_CANCEL",
+ "UMask": "0x24",
+ "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.",
+ "BriefDescription": "Cycles MITE is delivering any Uop.",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xAC",
+ "EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "DSB_FILL.EXCEED_DSB_LINES",
+ "UMask": "0x30",
+ "EventName": "IDQ.MS_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.",
+ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance. See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more information.",
"EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "IDQ.MITE_CYCLES",
+ "UMask": "0x30",
+ "EventName": "IDQ.MS_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+ "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "IDQ.DSB_CYCLES",
+ "UMask": "0x30",
+ "EdgeDetect": "1",
+ "EventName": "IDQ.MS_SWITCHES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
+ "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"Counter": "0,1,2,3",
- "UMask": "0x10",
- "EventName": "IDQ.MS_DSB_CYCLES",
+ "UMask": "0x3c",
+ "EventName": "IDQ.MITE_ALL_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
- "CounterMask": "1",
+ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x79",
+ "EventCode": "0x80",
"Counter": "0,1,2,3",
- "UMask": "0x10",
- "EdgeDetect": "1",
- "EventName": "IDQ.MS_DSB_OCCUR",
+ "UMask": "0x1",
+ "EventName": "ICACHE.HIT",
"SampleAfterValue": "2000003",
- "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
- "CounterMask": "1",
+ "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.",
+ "EventCode": "0x80",
+ "Counter": "0,1,2,3",
+ "UMask": "0x2",
+ "EventName": "ICACHE.MISSES",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled. In the ideal case 4 uops can be delivered each cycle. The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them. This event is used in determining the front-end bound category of the top-down pipeline slots characterization.",
+ "EventCode": "0x9C",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "EventCode": "0x9C",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
+ "CounterMask": "4",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "EventCode": "0x9C",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
+ "CounterMask": "3",
+ "CounterHTOff": "0,1,2,3"
+ },
{
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x79",
- "Counter": "0,1,2,3",
- "UMask": "0x18",
- "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.",
- "CounterMask": "4",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x79",
+ "EventCode": "0x9C",
+ "Invert": "1",
"Counter": "0,1,2,3",
- "UMask": "0x18",
- "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+ "UMask": "0x1",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.",
+ "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"CounterMask": "1",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x79",
+ "EventCode": "0xAB",
"Counter": "0,1,2,3",
- "UMask": "0x24",
- "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
+ "UMask": "0x1",
+ "EventName": "DSB2MITE_SWITCHES.COUNT",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles MITE is delivering 4 Uops.",
- "CounterMask": "4",
+ "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x79",
+ "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline. It excludes cycles when the back-end cannot accept new micro-ops. The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.",
+ "EventCode": "0xAB",
"Counter": "0,1,2,3",
- "UMask": "0x24",
- "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+ "UMask": "0x2",
+ "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles MITE is delivering any Uop.",
- "CounterMask": "1",
+ "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xAC",
"Counter": "0,1,2,3",
- "UMask": "0xa",
- "EventName": "DSB_FILL.ALL_CANCEL",
+ "UMask": "0x2",
+ "EventName": "DSB_FILL.OTHER_CANCEL",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.",
+ "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x9C",
- "Invert": "1",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
- "CounterMask": "1",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "EventCode": "0x79",
+ "EventCode": "0xAC",
"Counter": "0,1,2,3",
- "UMask": "0x3c",
- "EventName": "IDQ.MITE_ALL_UOPS",
+ "UMask": "0x8",
+ "EventName": "DSB_FILL.EXCEED_DSB_LINES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.",
+ "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x79",
+ "EventCode": "0xAC",
"Counter": "0,1,2,3",
- "UMask": "0x30",
- "EdgeDetect": "1",
- "EventName": "IDQ.MS_SWITCHES",
+ "UMask": "0xa",
+ "EventName": "DSB_FILL.ALL_CANCEL",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
- "CounterMask": "1",
+ "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
}
]
\ No newline at end of file
[
+ {
+ "EventCode": "0x05",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "MISALIGN_MEM_REF.LOADS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0x05",
+ "Counter": "0,1,2,3",
+ "UMask": "0x2",
+ "EventName": "MISALIGN_MEM_REF.STORES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xBE",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "PAGE_WALKS.LLC_MISS",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from memory disambiguation, external snoops, or cross SMT-HW-thread snoop (stores) hitting load buffers. Machine clears can have a significant performance impact if they are happening frequently.",
"EventCode": "0xC3",
"TakenAlone": "1",
"CounterHTOff": "3"
},
- {
- "EventCode": "0xBE",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "PAGE_WALKS.LLC_MISS",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x05",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "MISALIGN_MEM_REF.LOADS",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x05",
- "Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "MISALIGN_MEM_REF.STORES",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
{
"EventCode": "0xB7, 0xBB",
"MSRValue": "0x300400244",
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.LLC_MISS_LOCAL.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+ "BriefDescription": "REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.DATA_IN_SOCKET.LLC_MISS_LOCAL.ANY_LLC_HIT",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT",
+ "BriefDescription": "REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.DEMAND_IFETCH.LLC_MISS_LOCAL.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+ "BriefDescription": "REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.PF_DATA_RD.LLC_MISS_LOCAL.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+ "BriefDescription": "REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.PF_IFETCH.LLC_MISS_LOCAL.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+ "BriefDescription": "REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.LLC_MISS_LOCAL.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+ "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
"CounterHTOff": "0,1,2,3"
},
{
"EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.LLC_MISS_LOCAL.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+ "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
"CounterHTOff": "0,1,2,3"
}
]
\ No newline at end of file
"BriefDescription": "Valid instructions written to IQ per cycle.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0x4E",
+ "Counter": "0,1,2,3",
+ "UMask": "0x2",
+ "EventName": "HW_PRE_REQ.DL1_MISS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"EventCode": "0x5C",
"Counter": "0,1,2,3",
"BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
- {
- "EventCode": "0x4E",
- "Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "HW_PRE_REQ.DL1_MISS",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
{
"EventCode": "0x63",
"Counter": "0,1,2,3",
[
{
- "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ",
- "EventCode": "0x00",
- "Counter": "Fixed counter 1",
+ "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
+ "Counter": "Fixed counter 2",
+ "UMask": "0x3",
+ "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Reference cycles when the core is not in halt state.",
+ "CounterHTOff": "Fixed counter 2"
+ },
+ {
+ "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.",
+ "Counter": "Fixed counter 0",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
"SampleAfterValue": "2000003",
"BriefDescription": "Instructions retired from execution.",
- "CounterHTOff": "Fixed counter 1"
+ "CounterHTOff": "Fixed counter 0"
},
{
- "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
- "EventCode": "0x00",
- "Counter": "Fixed counter 2",
+ "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
+ "Counter": "Fixed counter 1",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.THREAD",
"SampleAfterValue": "2000003",
"BriefDescription": "Core cycles when the thread is not in halt state.",
- "CounterHTOff": "Fixed counter 2"
+ "CounterHTOff": "Fixed counter 1"
},
{
- "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
- "EventCode": "0x00",
- "Counter": "Fixed counter 3",
- "UMask": "0x3",
- "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+ "Counter": "Fixed counter 1",
+ "UMask": "0x2",
+ "AnyThread": "1",
+ "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
"SampleAfterValue": "2000003",
- "BriefDescription": "Reference cycles when the core is not in halt state.",
- "CounterHTOff": "Fixed counter 3"
+ "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+ "CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x88",
+ "EventCode": "0x03",
"Counter": "0,1,2,3",
- "UMask": "0x41",
- "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Not taken macro-conditional branches.",
+ "UMask": "0x1",
+ "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
+ "EventCode": "0x03",
"Counter": "0,1,2,3",
- "UMask": "0x81",
- "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired macro-conditional branches.",
+ "UMask": "0x2",
+ "EventName": "LD_BLOCKS.STORE_FORWARD",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "EventCode": "0x03",
"Counter": "0,1,2,3",
- "UMask": "0x82",
- "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.",
+ "UMask": "0x8",
+ "EventName": "LD_BLOCKS.NO_SR",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "EventCode": "0x03",
"Counter": "0,1,2,3",
- "UMask": "0x84",
- "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.",
+ "UMask": "0x10",
+ "EventName": "LD_BLOCKS.ALL_BLOCK",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K. This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline. The enhanced address check typically has a performance penalty of 5 cycles.",
+ "EventCode": "0x07",
"Counter": "0,1,2,3",
- "UMask": "0x88",
- "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.",
+ "UMask": "0x1",
+ "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "False dependencies in MOB due to partial compare.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "EventCode": "0x07",
"Counter": "0,1,2,3",
- "UMask": "0x90",
- "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired direct near calls.",
+ "UMask": "0x8",
+ "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "EventCode": "0x0D",
"Counter": "0,1,2,3",
- "UMask": "0xa0",
- "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired indirect calls.",
+ "UMask": "0x3",
+ "EventName": "INT_MISC.RECOVERY_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "EventCode": "0x0D",
"Counter": "0,1,2,3",
- "UMask": "0xc1",
- "EventName": "BR_INST_EXEC.ALL_CONDITIONAL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Speculative and retired macro-conditional branches.",
+ "UMask": "0x3",
+ "EdgeDetect": "1",
+ "EventName": "INT_MISC.RECOVERY_STALLS_COUNT",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "EventCode": "0x0D",
"Counter": "0,1,2,3",
- "UMask": "0xc2",
- "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP",
- "SampleAfterValue": "200003",
- "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.",
+ "UMask": "0x3",
+ "AnyThread": "1",
+ "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "EventCode": "0x0D",
"Counter": "0,1,2,3",
- "UMask": "0xc4",
- "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
- "SampleAfterValue": "200003",
- "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.",
+ "UMask": "0x40",
+ "EventName": "INT_MISC.RAT_STALL_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.",
+ "EventCode": "0x0E",
"Counter": "0,1,2,3",
- "UMask": "0xc8",
- "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN",
- "SampleAfterValue": "200003",
- "BriefDescription": "Speculative and retired indirect return branches.",
+ "UMask": "0x1",
+ "EventName": "UOPS_ISSUED.ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "EventCode": "0x0E",
+ "Invert": "1",
"Counter": "0,1,2,3",
- "UMask": "0xd0",
- "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Speculative and retired direct near calls.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x1",
+ "EventName": "UOPS_ISSUED.STALL_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
+ "CounterMask": "1",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x89",
+ "EventCode": "0x0E",
+ "Invert": "1",
"Counter": "0,1,2,3",
- "UMask": "0x41",
- "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x1",
+ "AnyThread": "1",
+ "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
+ "CounterMask": "1",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x89",
+ "EventCode": "0x14",
"Counter": "0,1,2,3",
- "UMask": "0x81",
- "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.",
+ "UMask": "0x1",
+ "EventName": "ARITH.FPU_DIV_ACTIVE",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles when divider is busy executing divide operations.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x89",
+ "PublicDescription": "This event counts the number of the divide operations executed.",
+ "EventCode": "0x14",
"Counter": "0,1,2,3",
- "UMask": "0x84",
- "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.",
+ "UMask": "0x1",
+ "EdgeDetect": "1",
+ "EventName": "ARITH.FPU_DIV",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Divide operations executed.",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x89",
+ "EventCode": "0x3C",
"Counter": "0,1,2,3",
- "UMask": "0x88",
- "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.",
+ "UMask": "0x0",
+ "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Thread cycles when thread is not in halt state.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x89",
+ "EventCode": "0x3C",
"Counter": "0,1,2,3",
- "UMask": "0x90",
- "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired mispredicted direct near calls.",
+ "UMask": "0x0",
+ "AnyThread": "1",
+ "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x89",
+ "EventCode": "0x3C",
"Counter": "0,1,2,3",
- "UMask": "0xa0",
- "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
+ "UMask": "0x1",
+ "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x89",
+ "EventCode": "0x3C",
"Counter": "0,1,2,3",
- "UMask": "0xc1",
- "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
+ "UMask": "0x1",
+ "AnyThread": "1",
+ "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x89",
+ "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+ "EventCode": "0x3C",
"Counter": "0,1,2,3",
- "UMask": "0xc4",
- "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
- "SampleAfterValue": "200003",
- "BriefDescription": "Mispredicted indirect branches excluding calls and returns.",
+ "UMask": "0x1",
+ "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x89",
+ "EventCode": "0x3C",
"Counter": "0,1,2,3",
- "UMask": "0xd0",
- "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL",
- "SampleAfterValue": "200003",
- "BriefDescription": "Speculative and retired mispredicted direct near calls.",
+ "UMask": "0x1",
+ "AnyThread": "1",
+ "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"Counter": "0,1,2,3",
- "UMask": "0x0",
- "EventName": "CPU_CLK_UNHALTED.THREAD_P",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Thread cycles when thread is not in halt state.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xA8",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "LSD.UOPS",
+ "UMask": "0x2",
+ "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of Uops delivered by the LSD.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0xA8",
+ "EventCode": "0x3C",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "LSD.CYCLES_ACTIVE",
+ "UMask": "0x2",
+ "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
- "CounterMask": "1",
+ "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x87",
+ "EventCode": "0x4C",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "ILD_STALL.LCP",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
+ "EventName": "LOAD_HIT_PRE.SW_PF",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x87",
+ "EventCode": "0x4C",
"Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "ILD_STALL.IQ_FULL",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Stall cycles because IQ is full.",
+ "UMask": "0x2",
+ "EventName": "LOAD_HIT_PRE.HW_PF",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x0D",
+ "EventCode": "0x59",
"Counter": "0,1,2,3",
- "UMask": "0x40",
- "EventName": "INT_MISC.RAT_STALL_CYCLES",
+ "UMask": "0x20",
+ "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.",
+ "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual.",
"EventCode": "0x59",
"Counter": "0,1,2,3",
"UMask": "0x20",
- "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP",
+ "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.",
+ "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.",
+ "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.",
"EventCode": "0x59",
"Counter": "0,1,2,3",
"UMask": "0x40",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA2",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "RESOURCE_STALLS.ANY",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Resource-related stall cycles.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xA2",
- "Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "RESOURCE_STALLS.LB",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Counts the cycles of stall due to lack of load buffers.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xA2",
- "Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "RESOURCE_STALLS.RS",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles stalled due to no eligible RS entry available.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xA2",
+ "EventCode": "0x5B",
"Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "RESOURCE_STALLS.SB",
+ "UMask": "0xc",
+ "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
+ "BriefDescription": "Cycles with either free list is empty.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA2",
+ "EventCode": "0x5B",
"Counter": "0,1,2,3",
- "UMask": "0x10",
- "EventName": "RESOURCE_STALLS.ROB",
+ "UMask": "0xf",
+ "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles stalled due to re-order buffer full.",
+ "BriefDescription": "Resource stalls2 control structures full for physical registers.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.",
- "EventCode": "0x0E",
+ "EventCode": "0x5B",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "UOPS_ISSUED.ANY",
+ "UMask": "0x4f",
+ "EventName": "RESOURCE_STALLS2.OOO_RSRC",
"SampleAfterValue": "2000003",
- "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).",
+ "BriefDescription": "Resource stalls out of order resources full.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x0E",
- "Invert": "1",
+ "EventCode": "0x5E",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "UOPS_ISSUED.STALL_CYCLES",
+ "EventName": "RS_EVENTS.EMPTY_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
- "CounterMask": "1",
- "CounterHTOff": "0,1,2,3"
+ "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x0E",
+ "EventCode": "0x5E",
"Invert": "1",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "AnyThread": "1",
- "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
+ "EdgeDetect": "1",
+ "EventName": "RS_EVENTS.EMPTY_END",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
+ "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
"CounterMask": "1",
- "CounterHTOff": "0,1,2,3"
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x5E",
+ "EventCode": "0x87",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "RS_EVENTS.EMPTY_CYCLES",
+ "EventName": "ILD_STALL.LCP",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+ "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xCC",
+ "EventCode": "0x87",
"Counter": "0,1,2,3",
- "UMask": "0x20",
- "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+ "UMask": "0x4",
+ "EventName": "ILD_STALL.IQ_FULL",
"SampleAfterValue": "2000003",
- "BriefDescription": "Count cases of saving new LBR.",
+ "BriefDescription": "Stall cycles because IQ is full.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear. Machine clears can have a significant performance impact if they are happening frequently.",
- "EventCode": "0xC3",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "MACHINE_CLEARS.SMC",
- "SampleAfterValue": "100003",
- "BriefDescription": "Self-modifying code (SMC) detected.",
+ "UMask": "0x41",
+ "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Not taken macro-conditional branches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.",
- "EventCode": "0xC3",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x20",
- "EventName": "MACHINE_CLEARS.MASKMOV",
- "SampleAfterValue": "100003",
- "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.",
+ "UMask": "0x81",
+ "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired macro-conditional branches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xC0",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x0",
- "EventName": "INST_RETIRED.ANY_P",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Number of instructions retired. General Counter - architectural event.",
+ "UMask": "0x82",
+ "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "PublicDescription": "This event counts the number of micro-ops retired.",
- "EventCode": "0xC2",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "UOPS_RETIRED.ALL",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Actually retired uops.",
+ "UMask": "0x84",
+ "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle. This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization.",
- "EventCode": "0xC2",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Retirement slots used.",
+ "UMask": "0x88",
+ "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xC2",
- "Invert": "1",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "UOPS_RETIRED.STALL_CYCLES",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles without actually retired uops.",
- "CounterMask": "1",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x90",
+ "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired direct near calls.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xC2",
- "Invert": "1",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles with less than 10 actually retired uops.",
- "CounterMask": "10",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0xa0",
+ "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired indirect calls.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xC4",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "BR_INST_RETIRED.CONDITIONAL",
- "SampleAfterValue": "400009",
- "BriefDescription": "Conditional branch instructions retired.",
+ "UMask": "0xc1",
+ "EventName": "BR_INST_EXEC.ALL_CONDITIONAL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Speculative and retired macro-conditional branches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xC4",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "BR_INST_RETIRED.NEAR_CALL",
- "SampleAfterValue": "100007",
- "BriefDescription": "Direct and indirect near call instructions retired.",
+ "UMask": "0xc2",
+ "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xC4",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x0",
- "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
- "SampleAfterValue": "400009",
- "BriefDescription": "All (macro) branch instructions retired.",
+ "UMask": "0xc4",
+ "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xC4",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "BR_INST_RETIRED.NEAR_RETURN",
- "SampleAfterValue": "100007",
- "BriefDescription": "Return instructions retired.",
+ "UMask": "0xc8",
+ "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Speculative and retired indirect return branches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xC4",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x10",
- "EventName": "BR_INST_RETIRED.NOT_TAKEN",
- "SampleAfterValue": "400009",
- "BriefDescription": "Not taken branch instructions retired.",
+ "UMask": "0xd0",
+ "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Speculative and retired direct near calls.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xC4",
+ "EventCode": "0x88",
"Counter": "0,1,2,3",
- "UMask": "0x20",
- "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
- "SampleAfterValue": "400009",
- "BriefDescription": "Taken branch instructions retired.",
+ "UMask": "0xff",
+ "EventName": "BR_INST_EXEC.ALL_BRANCHES",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Speculative and retired branches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xC4",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x40",
- "EventName": "BR_INST_RETIRED.FAR_BRANCH",
- "SampleAfterValue": "100007",
- "BriefDescription": "Far branch instructions retired.",
+ "UMask": "0x41",
+ "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "2",
- "EventCode": "0xC4",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
- "SampleAfterValue": "400009",
- "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0x81",
+ "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xC5",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "BR_MISP_RETIRED.CONDITIONAL",
- "SampleAfterValue": "400009",
- "BriefDescription": "Mispredicted conditional branch instructions retired.",
+ "UMask": "0x84",
+ "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xC5",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "BR_MISP_RETIRED.NEAR_CALL",
- "SampleAfterValue": "100007",
- "BriefDescription": "Direct and indirect mispredicted near call instructions retired.",
+ "UMask": "0x88",
+ "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xC5",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x0",
- "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
- "SampleAfterValue": "400009",
- "BriefDescription": "All mispredicted macro branch instructions retired.",
+ "UMask": "0x90",
+ "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired mispredicted direct near calls.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xC5",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x10",
- "EventName": "BR_MISP_RETIRED.NOT_TAKEN",
- "SampleAfterValue": "400009",
- "BriefDescription": "Mispredicted not taken branch instructions retired.",
+ "UMask": "0xa0",
+ "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "1",
- "EventCode": "0xC5",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x20",
- "EventName": "BR_MISP_RETIRED.TAKEN",
- "SampleAfterValue": "400009",
- "BriefDescription": "Mispredicted taken branch instructions retired.",
+ "UMask": "0xc1",
+ "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PEBS": "2",
- "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)",
- "EventCode": "0xC5",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
- "SampleAfterValue": "400009",
- "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).",
- "CounterHTOff": "0,1,2,3"
+ "UMask": "0xc4",
+ "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Mispredicted indirect branches excluding calls and returns.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xC1",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED",
- "SampleAfterValue": "100003",
- "BriefDescription": "Retired instructions experiencing ITLB misses.",
+ "UMask": "0xd0",
+ "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Speculative and retired mispredicted direct near calls.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x14",
+ "EventCode": "0x89",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "ARITH.FPU_DIV_ACTIVE",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles when divider is busy executing divide operations.",
+ "UMask": "0xff",
+ "EventName": "BR_MISP_EXEC.ALL_BRANCHES",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts the number of the divide operations executed.",
- "EventCode": "0x14",
+ "EventCode": "0xA1",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EdgeDetect": "1",
- "EventName": "ARITH.FPU_DIV",
- "SampleAfterValue": "100003",
- "BriefDescription": "Divide operations executed.",
- "CounterMask": "1",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles per thread when uops are dispatched to port 0.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xB1",
+ "EventCode": "0xA1",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "UOPS_DISPATCHED.THREAD",
+ "AnyThread": "1",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Uops dispatched per thread.",
+ "BriefDescription": "Cycles per core when uops are dispatched to port 0.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xB1",
+ "EventCode": "0xA1",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "EventName": "UOPS_DISPATCHED.CORE",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
"SampleAfterValue": "2000003",
- "BriefDescription": "Uops dispatched from any thread.",
+ "BriefDescription": "Cycles per thread when uops are dispatched to port 1.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+ "UMask": "0x2",
+ "AnyThread": "1",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per thread when uops are dispatched to port 0.",
+ "BriefDescription": "Cycles per core when uops are dispatched to port 1.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+ "UMask": "0xc",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per thread when uops are dispatched to port 1.",
+ "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"Counter": "0,1,2,3",
- "UMask": "0x40",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+ "UMask": "0xc",
+ "AnyThread": "1",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per thread when uops are dispatched to port 4.",
+ "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xA1",
"Counter": "0,1,2,3",
- "UMask": "0x80",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+ "UMask": "0x30",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per thread when uops are dispatched to port 5.",
+ "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA3",
+ "EventCode": "0xA1",
"Counter": "0,1,2,3",
- "UMask": "0x4",
- "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH",
+ "UMask": "0x30",
+ "AnyThread": "1",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.",
- "CounterMask": "4",
- "CounterHTOff": "0,1,2,3"
+ "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA3",
- "Counter": "2",
- "UMask": "0x2",
- "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+ "EventCode": "0xA1",
+ "Counter": "0,1,2,3",
+ "UMask": "0x40",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
"SampleAfterValue": "2000003",
- "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
- "CounterMask": "2",
- "CounterHTOff": "2"
+ "BriefDescription": "Cycles per thread when uops are dispatched to port 4.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA3",
+ "EventCode": "0xA1",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING",
+ "UMask": "0x40",
+ "AnyThread": "1",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.",
- "CounterMask": "1",
+ "BriefDescription": "Cycles per core when uops are dispatched to port 4.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA3",
- "Counter": "2",
- "UMask": "0x6",
- "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING",
+ "EventCode": "0xA1",
+ "Counter": "0,1,2,3",
+ "UMask": "0x80",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
"SampleAfterValue": "2000003",
- "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
- "CounterMask": "6",
- "CounterHTOff": "2"
+ "BriefDescription": "Cycles per thread when uops are dispatched to port 5.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA3",
+ "EventCode": "0xA1",
"Counter": "0,1,2,3",
- "UMask": "0x5",
- "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING",
+ "UMask": "0x80",
+ "AnyThread": "1",
+ "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.",
- "CounterMask": "5",
- "CounterHTOff": "0,1,2,3"
+ "BriefDescription": "Cycles per core when uops are dispatched to port 5.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x4C",
+ "EventCode": "0xA2",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "LOAD_HIT_PRE.SW_PF",
- "SampleAfterValue": "100003",
- "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.",
+ "EventName": "RESOURCE_STALLS.ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Resource-related stall cycles.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x4C",
+ "EventCode": "0xA2",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "EventName": "LOAD_HIT_PRE.HW_PF",
- "SampleAfterValue": "100003",
- "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.",
+ "EventName": "RESOURCE_STALLS.LB",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Counts the cycles of stall due to lack of load buffers.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x03",
+ "EventCode": "0xA2",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "LD_BLOCKS.DATA_UNKNOWN",
- "SampleAfterValue": "100003",
- "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.",
+ "UMask": "0x4",
+ "EventName": "RESOURCE_STALLS.RS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles stalled due to no eligible RS entry available.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
- "EventCode": "0x03",
+ "EventCode": "0xA2",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "LD_BLOCKS.STORE_FORWARD",
- "SampleAfterValue": "100003",
- "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.",
+ "UMask": "0x8",
+ "EventName": "RESOURCE_STALLS.SB",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x03",
+ "EventCode": "0xA2",
"Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "LD_BLOCKS.NO_SR",
- "SampleAfterValue": "100003",
- "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+ "UMask": "0xa",
+ "EventName": "RESOURCE_STALLS.LB_SB",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Resource stalls due to load or store buffers all being in use.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x03",
+ "EventCode": "0xA2",
+ "Counter": "0,1,2,3",
+ "UMask": "0xe",
+ "EventName": "RESOURCE_STALLS.MEM_RS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xA2",
"Counter": "0,1,2,3",
"UMask": "0x10",
- "EventName": "LD_BLOCKS.ALL_BLOCK",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).",
+ "EventName": "RESOURCE_STALLS.ROB",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles stalled due to re-order buffer full.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K. This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline. The enhanced address check typically has a performance penalty of 5 cycles.",
- "EventCode": "0x07",
+ "EventCode": "0xA2",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
- "SampleAfterValue": "100003",
- "BriefDescription": "False dependencies in MOB due to partial compare.",
+ "UMask": "0xf0",
+ "EventName": "RESOURCE_STALLS.OOO_RSRC",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x07",
+ "EventCode": "0xA3",
"Counter": "0,1,2,3",
- "UMask": "0x8",
- "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK",
- "SampleAfterValue": "100003",
- "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.",
+ "UMask": "0x1",
+ "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xB6",
+ "EventCode": "0xA3",
+ "Counter": "2",
+ "UMask": "0x2",
+ "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
+ "CounterMask": "2",
+ "CounterHTOff": "2"
+ },
+ {
+ "EventCode": "0xA3",
+ "Counter": "0,1,2,3",
+ "UMask": "0x4",
+ "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.",
+ "CounterMask": "4",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "EventCode": "0xA3",
+ "Counter": "0,1,2,3",
+ "UMask": "0x5",
+ "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.",
+ "CounterMask": "5",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "EventCode": "0xA3",
+ "Counter": "2",
+ "UMask": "0x6",
+ "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
+ "CounterMask": "6",
+ "CounterHTOff": "2"
+ },
+ {
+ "EventCode": "0xA8",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "AGU_BYPASS_CANCEL.COUNT",
- "SampleAfterValue": "100003",
- "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.",
+ "EventName": "LSD.UOPS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of Uops delivered by the LSD.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x3C",
+ "EventCode": "0xA8",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
+ "EventName": "LSD.CYCLES_ACTIVE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
+ "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x3C",
+ "EventCode": "0xA8",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
+ "UMask": "0x1",
+ "EventName": "LSD.CYCLES_4_UOPS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.",
- "CounterHTOff": "0,1,2,3"
+ "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+ "CounterMask": "4",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA1",
+ "EventCode": "0xB1",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "AnyThread": "1",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
+ "EventName": "UOPS_DISPATCHED.THREAD",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per core when uops are dispatched to port 0.",
+ "BriefDescription": "Uops dispatched per thread.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA1",
+ "EventCode": "0xB1",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "AnyThread": "1",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
+ "EventName": "UOPS_DISPATCHED.CORE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per core when uops are dispatched to port 1.",
+ "BriefDescription": "Uops dispatched from any thread.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA1",
+ "EventCode": "0xB1",
"Counter": "0,1,2,3",
- "UMask": "0x40",
- "AnyThread": "1",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
+ "UMask": "0x2",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per core when uops are dispatched to port 4.",
+ "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+ "CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA1",
+ "EventCode": "0xB1",
"Counter": "0,1,2,3",
- "UMask": "0x80",
- "AnyThread": "1",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
+ "UMask": "0x2",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per core when uops are dispatched to port 5.",
+ "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+ "CounterMask": "2",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA1",
+ "EventCode": "0xB1",
"Counter": "0,1,2,3",
- "UMask": "0xc",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+ "UMask": "0x2",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.",
+ "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+ "CounterMask": "3",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA1",
+ "EventCode": "0xB1",
"Counter": "0,1,2,3",
- "UMask": "0x30",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+ "UMask": "0x2",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.",
+ "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+ "CounterMask": "4",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA1",
+ "EventCode": "0xB1",
+ "Invert": "1",
"Counter": "0,1,2,3",
- "UMask": "0xc",
- "AnyThread": "1",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
+ "UMask": "0x2",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.",
+ "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA1",
+ "EventCode": "0xB6",
"Counter": "0,1,2,3",
- "UMask": "0x30",
- "AnyThread": "1",
- "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
+ "UMask": "0x1",
+ "EventName": "AGU_BYPASS_CANCEL.COUNT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xC0",
+ "Counter": "0,1,2,3",
+ "UMask": "0x0",
+ "EventName": "INST_RETIRED.ANY_P",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
+ "BriefDescription": "Number of instructions retired. General Counter - architectural event.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "1"
},
{
- "EventCode": "0x5B",
+ "EventCode": "0xC1",
"Counter": "0,1,2,3",
- "UMask": "0xf",
- "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Resource stalls2 control structures full for physical registers.",
+ "UMask": "0x2",
+ "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Retired instructions experiencing ITLB misses.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x5B",
+ "PEBS": "1",
+ "PublicDescription": "This event counts the number of micro-ops retired. (Precise Event)",
+ "EventCode": "0xC2",
"Counter": "0,1,2,3",
- "UMask": "0xc",
- "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY",
+ "UMask": "0x1",
+ "EventName": "UOPS_RETIRED.ALL",
"SampleAfterValue": "2000003",
- "BriefDescription": "Cycles with either free list is empty.",
+ "BriefDescription": "Actually retired uops. (Precise Event - PEBS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA2",
+ "EventCode": "0xC2",
+ "Invert": "1",
"Counter": "0,1,2,3",
- "UMask": "0xe",
- "EventName": "RESOURCE_STALLS.MEM_RS",
+ "UMask": "0x1",
+ "EventName": "UOPS_RETIRED.STALL_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "BriefDescription": "Cycles without actually retired uops.",
+ "CounterMask": "1",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0xA2",
+ "EventCode": "0xC2",
+ "Invert": "1",
"Counter": "0,1,2,3",
- "UMask": "0xf0",
- "EventName": "RESOURCE_STALLS.OOO_RSRC",
+ "UMask": "0x1",
+ "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x5B",
- "Counter": "0,1,2,3",
- "UMask": "0x4f",
- "EventName": "RESOURCE_STALLS2.OOO_RSRC",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Resource stalls out of order resources full.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xA2",
- "Counter": "0,1,2,3",
- "UMask": "0xa",
- "EventName": "RESOURCE_STALLS.LB_SB",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Resource stalls due to load or store buffers all being in use.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "BriefDescription": "Cycles with less than 10 actually retired uops.",
+ "CounterMask": "10",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x0D",
+ "EventCode": "0xC2",
+ "Invert": "1",
"Counter": "0,1,2,3",
- "UMask": "0x3",
- "EventName": "INT_MISC.RECOVERY_CYCLES",
+ "UMask": "0x1",
+ "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
+ "BriefDescription": "Cycles without actually retired uops.",
"CounterMask": "1",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel? 64 and IA-32 Architectures Optimization Reference Manual.",
- "EventCode": "0x59",
+ "PEBS": "1",
+ "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle. This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization. (Precise Event - PEBS)",
+ "EventCode": "0xC2",
"Counter": "0,1,2,3",
- "UMask": "0x20",
- "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES",
+ "UMask": "0x2",
+ "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.",
- "CounterMask": "1",
+ "BriefDescription": "Retirement slots used. (Precise Event - PEBS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x0D",
+ "EventCode": "0xc3",
"Counter": "0,1,2,3",
- "UMask": "0x3",
+ "UMask": "0x1",
"EdgeDetect": "1",
- "EventName": "INT_MISC.RECOVERY_STALLS_COUNT",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
+ "EventName": "MACHINE_CLEARS.COUNT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of machine clears (nukes) of any type.",
"CounterMask": "1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xE6",
+ "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear. Machine clears can have a significant performance impact if they are happening frequently.",
+ "EventCode": "0xC3",
"Counter": "0,1,2,3",
- "UMask": "0x1f",
- "EventName": "BACLEARS.ANY",
+ "UMask": "0x4",
+ "EventName": "MACHINE_CLEARS.SMC",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
+ "BriefDescription": "Self-modifying code (SMC) detected.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x88",
+ "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.",
+ "EventCode": "0xC3",
"Counter": "0,1,2,3",
- "UMask": "0xff",
- "EventName": "BR_INST_EXEC.ALL_BRANCHES",
- "SampleAfterValue": "200003",
- "BriefDescription": "Speculative and retired branches.",
+ "UMask": "0x20",
+ "EventName": "MACHINE_CLEARS.MASKMOV",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x89",
+ "EventCode": "0xC4",
"Counter": "0,1,2,3",
- "UMask": "0xff",
- "EventName": "BR_MISP_EXEC.ALL_BRANCHES",
- "SampleAfterValue": "200003",
- "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
+ "UMask": "0x0",
+ "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "All (macro) branch instructions retired.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xC2",
- "Invert": "1",
+ "PEBS": "1",
+ "EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles without actually retired uops.",
- "CounterMask": "1",
- "CounterHTOff": "0,1,2,3"
+ "EventName": "BR_INST_RETIRED.CONDITIONAL",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA8",
+ "PEBS": "1",
+ "EventCode": "0xC4",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "LSD.CYCLES_4_UOPS",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
- "CounterMask": "4",
+ "UMask": "0x2",
+ "EventName": "BR_INST_RETIRED.NEAR_CALL",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xc3",
+ "PEBS": "1",
+ "EventCode": "0xC4",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EdgeDetect": "1",
- "EventName": "MACHINE_CLEARS.COUNT",
- "SampleAfterValue": "100003",
- "BriefDescription": "Number of machine clears (nukes) of any type.",
- "CounterMask": "1",
+ "UMask": "0x2",
+ "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x5E",
- "Invert": "1",
+ "PEBS": "2",
+ "EventCode": "0xC4",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EdgeDetect": "1",
- "EventName": "RS_EVENTS.EMPTY_END",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
- "CounterMask": "1",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x4",
+ "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0x00",
- "Counter": "Fixed counter 2",
- "UMask": "0x2",
- "AnyThread": "1",
- "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
- "CounterHTOff": "Fixed counter 2"
+ "PEBS": "1",
+ "EventCode": "0xC4",
+ "Counter": "0,1,2,3",
+ "UMask": "0x8",
+ "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Return instructions retired. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x3C",
+ "EventCode": "0xC4",
"Counter": "0,1,2,3",
- "UMask": "0x0",
- "AnyThread": "1",
- "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+ "UMask": "0x10",
+ "EventName": "BR_INST_RETIRED.NOT_TAKEN",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Not taken branch instructions retired.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x3C",
+ "PEBS": "1",
+ "EventCode": "0xC4",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "AnyThread": "1",
- "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+ "UMask": "0x20",
+ "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x0D",
+ "EventCode": "0xC4",
"Counter": "0,1,2,3",
- "UMask": "0x3",
- "AnyThread": "1",
- "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
- "CounterMask": "1",
+ "UMask": "0x40",
+ "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Far branch instructions retired.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xB1",
+ "EventCode": "0xC5",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
- "CounterMask": "1",
+ "UMask": "0x0",
+ "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "All mispredicted macro branch instructions retired.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xB1",
+ "PEBS": "1",
+ "EventCode": "0xC5",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
- "CounterMask": "2",
+ "UMask": "0x1",
+ "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xB1",
+ "PEBS": "1",
+ "EventCode": "0xC5",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
- "CounterMask": "3",
+ "EventName": "BR_MISP_RETIRED.NEAR_CALL",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Direct and indirect mispredicted near call instructions retired. (Precise Event - PEBS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xB1",
+ "PEBS": "2",
+ "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)",
+ "EventCode": "0xC5",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
- "CounterMask": "4",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
+ "UMask": "0x4",
+ "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).",
+ "CounterHTOff": "0,1,2,3"
},
{
- "EventCode": "0xB1",
- "Invert": "1",
+ "PEBS": "1",
+ "EventCode": "0xC5",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+ "UMask": "0x10",
+ "EventName": "BR_MISP_RETIRED.NOT_TAKEN",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Mispredicted not taken branch instructions retired.(Precise Event - PEBS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
- "EventCode": "0x3C",
+ "PEBS": "1",
+ "EventCode": "0xC5",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
+ "UMask": "0x20",
+ "EventName": "BR_MISP_RETIRED.TAKEN",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Mispredicted taken branch instructions retired. (Precise Event - PEBS).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x3C",
+ "EventCode": "0xCC",
"Counter": "0,1,2,3",
- "UMask": "0x1",
- "AnyThread": "1",
- "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+ "UMask": "0x20",
+ "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
"SampleAfterValue": "2000003",
- "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+ "BriefDescription": "Count cases of saving new LBR.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x3C",
+ "EventCode": "0xE6",
"Counter": "0,1,2,3",
- "UMask": "0x2",
- "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+ "UMask": "0x1f",
+ "EventName": "BACLEARS.ANY",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
}
]
\ No newline at end of file
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
- "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
- "MetricGroup": "Frontend",
+ "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS",
+ "MetricName": "FLOPc"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS_SMT",
+ "MetricName": "FLOPc_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
+ "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
[
{
- "EventCode": "0xAE",
- "Counter": "0,1,2,3",
- "UMask": "0x1",
- "EventName": "ITLB.ITLB_FLUSH",
- "SampleAfterValue": "100007",
- "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x4F",
- "Counter": "0,1,2,3",
- "UMask": "0x10",
- "EventName": "EPT.WALK_CYCLES",
- "SampleAfterValue": "2000003",
- "BriefDescription": "Cycle count for an Extended Page table walk. The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0x85",
+ "EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
+ "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
"SampleAfterValue": "100003",
- "BriefDescription": "Misses at all ITLB levels that cause page walks.",
+ "BriefDescription": "Load misses in all DTLB levels that cause page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x85",
+ "EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "EventName": "ITLB_MISSES.WALK_COMPLETED",
+ "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
- "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
+ "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.",
- "EventCode": "0x85",
+ "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
+ "EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x4",
- "EventName": "ITLB_MISSES.WALK_DURATION",
+ "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when PMH is busy with page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x85",
+ "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.",
+ "EventCode": "0x08",
"Counter": "0,1,2,3",
"UMask": "0x10",
- "EventName": "ITLB_MISSES.STLB_HIT",
+ "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
- "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
+ "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x08",
+ "EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+ "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
"SampleAfterValue": "100003",
- "BriefDescription": "Load misses in all DTLB levels that cause page walks.",
+ "BriefDescription": "Store misses in all DTLB levels that cause page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x08",
+ "EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+ "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
- "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.",
+ "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
- "EventCode": "0x08",
+ "EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x4",
- "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
+ "EventName": "DTLB_STORE_MISSES.WALK_DURATION",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when PMH is busy with page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.",
- "EventCode": "0x08",
+ "EventCode": "0x49",
"Counter": "0,1,2,3",
"UMask": "0x10",
- "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+ "EventName": "DTLB_STORE_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
- "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
+ "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x49",
+ "EventCode": "0x4F",
+ "Counter": "0,1,2,3",
+ "UMask": "0x10",
+ "EventName": "EPT.WALK_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycle count for an Extended Page table walk. The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
+ "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
"SampleAfterValue": "100003",
- "BriefDescription": "Store misses in all DTLB levels that cause page walks.",
+ "BriefDescription": "Misses at all ITLB levels that cause page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x49",
+ "EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x2",
- "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+ "EventName": "ITLB_MISSES.WALK_COMPLETED",
"SampleAfterValue": "100003",
- "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
+ "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x49",
+ "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.",
+ "EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x4",
- "EventName": "DTLB_STORE_MISSES.WALK_DURATION",
+ "EventName": "ITLB_MISSES.WALK_DURATION",
"SampleAfterValue": "2000003",
"BriefDescription": "Cycles when PMH is busy with page walks.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x49",
+ "EventCode": "0x85",
"Counter": "0,1,2,3",
"UMask": "0x10",
- "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+ "EventName": "ITLB_MISSES.STLB_HIT",
"SampleAfterValue": "100003",
- "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
+ "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
+ {
+ "EventCode": "0xAE",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "ITLB.ITLB_FLUSH",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"BriefDescription": "L2 cache request misses"
},
{
- "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss. Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events. \r\n",
+ "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss. Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.",
"EventCode": "0x86",
"Counter": "0,1",
"UMask": "0x4",
--- /dev/null
+[
+ {
+ "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss. Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
+ "EventCode": "0x86",
+ "Counter": "0,1",
+ "UMask": "0x2",
+ "EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Cycles code-fetch stalled due to an outstanding ITLB miss."
+ },
+ {
+ "PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes. This will include cycles due to an ITLB miss, ICache miss and other events.",
+ "EventCode": "0x86",
+ "Counter": "0,1",
+ "UMask": "0x3f",
+ "EventName": "FETCH_STALL.ALL",
+ "SampleAfterValue": "200003",
+ "BriefDescription": "Cycles code-fetch stalled due to any reason."
+ }
+]
\ No newline at end of file
"UMask": "0x4",
"EventName": "NO_ALLOC_CYCLES.MISPREDICTS",
"SampleAfterValue": "200003",
- "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire. After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted "
+ "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire. After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted"
},
{
"EventCode": "0xCA",
},
{
"PublicDescription": "This event counts the number of instructions that retire. For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires. The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps. Background: Modern microprocessors employ extensive pipelining and speculative techniques. Since sometimes an instruction is started but never completed, the notion of \"retirement\" is introduced. A retired instruction is one that commits its states. Or stated differently, an instruction might be abandoned at some point. No instruction is truly finished until it retires. This counter measures the number of completed instructions. The fixed event is INST_RETIRED.ANY and the programmable event is INST_RETIRED.ANY_P.",
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
},
{
"PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. In systems with a constant core frequency, this event can give you a measurement of the elapsed time while the core was not in halt state by dividing the event count by the core frequency. This event is architecturally defined and is a designated fixed counter. CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time. CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.",
- "EventCode": "0x00",
"Counter": "Fixed counter 2",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.CORE",
},
{
"PublicDescription": "Counts the number of reference cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. Divide this event count by core frequency to determine the elapsed time while the core was not in halt state. Divide this event count by core frequency to determine the elapsed time while the core was not in halt state. This event is architecturally defined and is a designated fixed counter. CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time. CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time. The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.",
- "EventCode": "0x00",
"Counter": "Fixed counter 3",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.",
+ "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x41",
+ "UMask": "0xc1",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "Demand Data Read requests that hit L2 cache",
"PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x42",
+ "UMask": "0xc2",
"EventName": "L2_RQSTS.RFO_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "RFO requests that hit L2 cache",
"PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
"EventCode": "0x24",
"Counter": "0,1,2,3",
- "UMask": "0x44",
+ "UMask": "0xc4",
"EventName": "L2_RQSTS.CODE_RD_HIT",
"SampleAfterValue": "200003",
"BriefDescription": "L2 cache hits when fetching instructions, code reads.",
},
{
"PEBS": "1",
- "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n",
+ "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
"EventCode": "0xD1",
"Counter": "0,1,2,3",
"UMask": "0x1",
},
{
"PEBS": "1",
- "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n",
+ "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
"EventCode": "0xD1",
"Counter": "0,1,2,3",
"UMask": "0x40",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
+ "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
"EventCode": "0xF2",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "L2_LINES_OUT.USELESS_PREF",
"SampleAfterValue": "200003",
- "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+ "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fc0400001 ",
+ "MSRValue": "0x3FC0408000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & ANY_SNOOP",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000400001 ",
+ "MSRValue": "0x1000408000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HITM",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400400001 ",
+ "MSRValue": "0x0400408000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200400001 ",
+ "MSRValue": "0x0200408000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_MISS",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100400001 ",
+ "MSRValue": "0x0100408000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080400001 ",
+ "MSRValue": "0x0080408000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NONE",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fc01c0001 ",
+ "MSRValue": "0x0040408000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_HIT & ANY_SNOOP",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x10001c0001 ",
+ "MSRValue": "0x3FC01C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x04001c0001 ",
+ "MSRValue": "0x10001C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x02001c0001 ",
+ "MSRValue": "0x04001C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x01001c0001 ",
+ "MSRValue": "0x02001C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00801c0001 ",
+ "MSRValue": "0x01001C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_NONE",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fc0020001 ",
+ "MSRValue": "0x00801C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1000020001 ",
+ "MSRValue": "0x00401C8000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0400020001 ",
+ "MSRValue": "0x3FC0108000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0200020001 ",
+ "MSRValue": "0x1000108000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0100020001 ",
+ "MSRValue": "0x0400108000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts any other requests",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0080020001 ",
+ "MSRValue": "0x0200108000",
"Counter": "0,1,2,3",
"UMask": "0x1",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100108000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080108000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040108000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0088000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000088000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400088000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200088000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100088000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080088000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040088000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0048000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000048000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400048000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200048000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100048000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080048000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040048000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0028000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000028000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400028000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200028000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100028000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080028000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040028000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests have any response type.",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0000018000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests have any response type.",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC01C0004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x10001C0004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x04001C0004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x02001C0004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x01001C0004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x00801C0004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x00401C0004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0100004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000100004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400100004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200100004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100100004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080100004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040100004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0080004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000080004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400080004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200080004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100080004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080080004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040080004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0040004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000040004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400040004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200040004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100040004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080040004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040040004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0020004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000020004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400020004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200020004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100020004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080020004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040020004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0000010004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC01C0002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x10001C0002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x04001C0002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x02001C0002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x01001C0002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x00801C0002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x00401C0002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0100002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000100002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400100002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200100002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100100002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080100002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040100002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0080002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000080002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400080002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200080002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100080002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080080002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040080002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0040002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000040002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400040002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200040002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100040002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080040002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040040002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0020002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000020002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400020002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200020002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100020002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080020002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040020002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0000010002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC01C0001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x10001C0001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x04001C0001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x02001C0001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x01001C0001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x00801C0001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x00401C0001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0100001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000100001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400100001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200100001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100100001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080100001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040100001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0080001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000080001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400080001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200080001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100080001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080080001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040080001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0040001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000040001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400040001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200040001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100040001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080040001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040040001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC0020001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1000020001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0400020001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0200020001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0100020001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0080020001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0040020001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads have any response type.",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0000010001 ",
+ "MSRValue": "0x0000010001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts demand data reads that have any response type.",
+ "BriefDescription": "Counts demand data reads have any response type.",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
}
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.",
+ "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.",
"EventCode": "0x9C",
"Counter": "0,1,2,3",
"UMask": "0x1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+ "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
"EventCode": "0xAB",
"Counter": "0,1,2,3",
"UMask": "0x2",
},
{
"PEBS": "1",
- "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n",
+ "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"EventCode": "0xC6",
"MSRValue": "0x11",
"Counter": "0,1,2,3",
},
{
"PEBS": "1",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
"EventCode": "0xC6",
"MSRValue": "0x400806",
"Counter": "0,1,2,3",
},
{
"PEBS": "1",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
"EventCode": "0xC6",
"MSRValue": "0x401006",
"Counter": "0,1,2,3",
},
{
"PEBS": "1",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
"EventCode": "0xC6",
"MSRValue": "0x402006",
"Counter": "0,1,2,3",
},
{
"PEBS": "1",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
"EventCode": "0xC6",
"MSRValue": "0x100206",
"Counter": "0,1,2,3",
"UMask": "0x4",
"EventName": "HLE_RETIRED.ABORTED",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ",
+ "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
"EventCode": "0xC8",
"Counter": "0,1,2,3",
"UMask": "0x20",
"UMask": "0x4",
"EventName": "RTM_RETIRED.ABORTED",
"SampleAfterValue": "2000003",
- "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ",
+ "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
},
{
"PEBS": "2",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
"EventCode": "0xCD",
"MSRValue": "0x4",
"Counter": "0,1,2,3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"SampleAfterValue": "100003",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"TakenAlone": "1",
"CounterHTOff": "0,1,2,3"
},
{
"PEBS": "2",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
"EventCode": "0xCD",
"MSRValue": "0x8",
"Counter": "0,1,2,3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"SampleAfterValue": "50021",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"TakenAlone": "1",
"CounterHTOff": "0,1,2,3"
},
{
"PEBS": "2",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
"EventCode": "0xCD",
"MSRValue": "0x10",
"Counter": "0,1,2,3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"SampleAfterValue": "20011",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"TakenAlone": "1",
"CounterHTOff": "0,1,2,3"
},
{
"PEBS": "2",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
"EventCode": "0xCD",
"MSRValue": "0x20",
"Counter": "0,1,2,3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"TakenAlone": "1",
"CounterHTOff": "0,1,2,3"
},
{
"PEBS": "2",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.",
"EventCode": "0xCD",
"MSRValue": "0x40",
"Counter": "0,1,2,3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"SampleAfterValue": "2003",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
"TakenAlone": "1",
"CounterHTOff": "0,1,2,3"
},
{
"PEBS": "2",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.",
"EventCode": "0xCD",
"MSRValue": "0x80",
"Counter": "0,1,2,3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"SampleAfterValue": "1009",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
"TakenAlone": "1",
"CounterHTOff": "0,1,2,3"
},
{
"PEBS": "2",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.",
"EventCode": "0xCD",
"MSRValue": "0x100",
"Counter": "0,1,2,3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"SampleAfterValue": "503",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
"TakenAlone": "1",
"CounterHTOff": "0,1,2,3"
},
{
"PEBS": "2",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
"EventCode": "0xCD",
"MSRValue": "0x200",
"Counter": "0,1,2,3",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"SampleAfterValue": "101",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"TakenAlone": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts any other requests",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3ffc000001 ",
+ "MSRValue": "0x3FFC408000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x203C408000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x103C408000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x043C408000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x023C408000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x013C408000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x00BC408000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x007C408000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC4008000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2004008000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1004008000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0404008000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0204008000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0104008000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0084008000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0044008000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000408000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x20001C8000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000108000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000088000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000048000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts any other requests",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000028000",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts any other requests",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FFC400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x203C400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x103C400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x043C400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x023C400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x013C400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x00BC400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x007C400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC4000004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2004000004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1004000004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0404000004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0204000004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0104000004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0084000004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0044000004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000400004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x20001C0004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000100004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000080004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000040004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000020004",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FFC400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x203C400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x103C400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x043C400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x023C400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x013C400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x00BC400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x007C400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FC4000002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2004000002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1004000002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0404000002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0204000002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0104000002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0084000002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0044000002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000400002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x20001C0002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000100002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000080002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000040002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts all demand data writes (RFOs)",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000020002",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x3FFC400001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS & ANY_SNOOP",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x103c000001 ",
+ "MSRValue": "0x203C400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x103C400001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HITM",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x043c000001 ",
+ "MSRValue": "0x043C400001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x023c000001 ",
+ "MSRValue": "0x023C400001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_MISS",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x013c000001 ",
+ "MSRValue": "0x013C400001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x00bc000001 ",
+ "MSRValue": "0x00BC400001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x007C400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NONE",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x3fc4000001 ",
+ "MSRValue": "0x3FC4000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x1004000001 ",
+ "MSRValue": "0x2004000001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x1004000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0404000001 ",
+ "MSRValue": "0x0404000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0204000001 ",
+ "MSRValue": "0x0204000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0104000001 ",
+ "MSRValue": "0x0104000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
},
{
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "PublicDescription": "Counts demand data reads",
"EventCode": "0xB7, 0xBB",
- "MSRValue": "0x0084000001 ",
+ "MSRValue": "0x0084000001",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
- "MSRIndex": "0x1a6,0x1a7",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x0044000001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000400001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x20001C0001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000100001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000080001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000040001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts demand data reads",
+ "Offcore": "1",
+ "CounterHTOff": "0,1,2,3"
+ },
+ {
+ "PublicDescription": "Counts demand data reads",
+ "EventCode": "0xB7, 0xBB",
+ "MSRValue": "0x2000020001",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
+ "MSRIndex": "0x1a6, 0x1a7",
"SampleAfterValue": "100003",
- "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+ "BriefDescription": "Counts demand data reads",
"Offcore": "1",
"CounterHTOff": "0,1,2,3"
}
[
{
"PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
- "EventCode": "0x00",
"Counter": "Fixed counter 0",
"UMask": "0x1",
"EventName": "INST_RETIRED.ANY",
},
{
"PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"EventName": "CPU_CLK_UNHALTED.THREAD",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"Counter": "Fixed counter 1",
"UMask": "0x2",
"AnyThread": "1",
},
{
"PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
- "EventCode": "0x00",
"Counter": "Fixed counter 2",
"UMask": "0x3",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
+ "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
"EventCode": "0x0E",
"Counter": "0,1,2,3",
"UMask": "0x2",
"BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.",
+ "EventCode": "0x59",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
"EventCode": "0x5E",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
- "EventCode": "0xA2",
+ "PublicDescription": "Counts resource-related stall cycles.",
+ "EventCode": "0xa2",
"Counter": "0,1,2,3",
"UMask": "0x1",
"EventName": "RESOURCE_STALLS.ANY",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+ "PublicDescription": "This event counts cycles without actually retired uops.",
"EventCode": "0xC2",
"Invert": "1",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "PublicDescription": "Number of machine clears (nukes) of any type.",
"EventCode": "0xC3",
"Counter": "0,1,2,3",
"UMask": "0x1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+ "PEBS": "1",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
"EventCode": "0xC4",
"Counter": "0,1,2,3",
"UMask": "0x10",
"Errata": "SKL091",
"EventName": "BR_INST_RETIRED.NOT_TAKEN",
"SampleAfterValue": "400009",
- "BriefDescription": "Not taken branch instructions retired.",
+ "BriefDescription": "Counts all not taken macro branch instructions retired.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"UMask": "0x20",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
"SampleAfterValue": "400009",
- "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ",
+ "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"BriefDescription": "Increments whenever there is an update to the LBR array.",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0xCC",
+ "Counter": "0,1,2,3",
+ "UMask": "0x40",
+ "EventName": "ROB_MISC_EVENTS.PAUSE_INST",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
"EventCode": "0xE6",
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
- "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
- "MetricGroup": "Frontend",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Instruction per taken branch",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "IpTB"
+ },
+ {
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Branch instructions per taken branch. ",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "BpTB"
+ },
+ {
+ "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+ "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+ "MetricGroup": "Instruction_Type;L1_Bound",
+ "MetricName": "IpL"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+ "BriefDescription": "Instructions per Store",
+ "MetricGroup": "Instruction_Type;Store_Bound",
+ "MetricName": "IpS"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Instructions per Branch",
+ "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+ "MetricName": "IpB"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "BriefDescription": "Instruction per (near) call",
+ "MetricGroup": "Branches",
+ "MetricName": "IpCall"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS",
+ "MetricName": "FLOPc"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS_SMT",
+ "MetricName": "FLOPc_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
- "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
- "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
- "MetricGroup": "Unknown_Branches",
- "MetricName": "BAClear_Cost"
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "Branch_Misprediction_Cost"
},
{
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts_SMT",
+ "MetricName": "Branch_Misprediction_Cost_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "IpMispredict"
+ },
+ {
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
- "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
- "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
+ "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
- "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
- "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricGroup": "TLB_SMT",
+ "MetricName": "Page_Walks_Utilization_SMT"
+ },
+ {
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Access_BW"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L1MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI"
+ },
+ {
+ "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2HPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L3MPKI"
+ },
+ {
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
+ "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
+ "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,thresh\\=1@",
+ "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_Parallel_Reads"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
},
{
"EventCode": "0x24",
- "UMask": "0x41",
+ "UMask": "0xc1",
"BriefDescription": "Demand Data Read requests that hit L2 cache",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
- "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.",
+ "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x24",
- "UMask": "0x42",
+ "UMask": "0xc2",
"BriefDescription": "RFO requests that hit L2 cache",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.RFO_HIT",
},
{
"EventCode": "0x24",
- "UMask": "0x44",
+ "UMask": "0xc4",
"BriefDescription": "L2 cache hits when fetching instructions, code reads.",
"Counter": "0,1,2,3",
"EventName": "L2_RQSTS.CODE_RD_HIT",
"BriefDescription": "Core-originated cacheable demand requests missed L3",
"Counter": "0,1,2,3",
"EventName": "LONGEST_LAT_CACHE.MISS",
+ "Errata": "SKL057",
"PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"BriefDescription": "Core-originated cacheable demand requests that refer to L3",
"Counter": "0,1,2,3",
"EventName": "LONGEST_LAT_CACHE.REFERENCE",
- "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.",
+ "Errata": "SKL057",
+ "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x48",
"UMask": "0x1",
- "BriefDescription": "L1D miss outstandings duration in cycles",
+ "BriefDescription": "Cycles with L1D load Misses outstanding.",
"Counter": "0,1,2,3",
- "EventName": "L1D_PEND_MISS.PENDING",
- "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+ "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+ "CounterMask": "1",
+ "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x48",
"UMask": "0x1",
- "BriefDescription": "Cycles with L1D load Misses outstanding.",
+ "BriefDescription": "L1D miss outstandings duration in cycles",
"Counter": "0,1,2,3",
- "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
- "CounterMask": "1",
- "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+ "EventName": "L1D_PEND_MISS.PENDING",
+ "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x60",
"UMask": "0x1",
- "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
+ "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
- "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+ "CounterMask": "1",
+ "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x60",
"UMask": "0x1",
- "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+ "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
- "CounterMask": "1",
- "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
+ "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x60",
"UMask": "0x8",
- "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+ "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
- "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+ "CounterMask": "1",
+ "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x60",
"UMask": "0x8",
- "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+ "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
- "CounterMask": "1",
- "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+ "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_RETIRED.L1_HIT",
- "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n",
+ "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_LOAD_RETIRED.FB_HIT",
- "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n",
+ "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
"BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.",
"Counter": "0,1,2,3",
"EventName": "L2_LINES_OUT.SILENT",
+ "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped",
"Counter": "0,1,2,3",
"EventName": "L2_LINES_OUT.NON_SILENT",
- "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped.",
+ "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xF2",
"UMask": "0x4",
- "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+ "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
+ "Deprecated": "1",
"Counter": "0,1,2,3",
"EventName": "L2_LINES_OUT.USELESS_PREF",
- "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
+ "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
"SampleAfterValue": "200003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that have any response type.",
- "MSRValue": "0x0000010001 ",
+ "BriefDescription": "Counts demand data reads have any response type.",
+ "MSRValue": "0x0000010001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0001 ",
+ "BriefDescription": "Counts demand data reads TBD TBD",
+ "MSRValue": "0x01003C0001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0001 ",
+ "BriefDescription": "Counts demand data reads TBD TBD",
+ "MSRValue": "0x04003C0001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0001 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0001 ",
+ "BriefDescription": "Counts demand data reads TBD TBD",
+ "MSRValue": "0x10003C0001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that hit in the L3.",
- "MSRValue": "0x3f803c0001 ",
+ "BriefDescription": "Counts demand data reads TBD TBD",
+ "MSRValue": "0x3F803C0001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.",
- "MSRValue": "0x0000010002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
+ "MSRValue": "0x0000010002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+ "MSRValue": "0x01003C0002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+ "MSRValue": "0x04003C0002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0002 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+ "MSRValue": "0x10003C0002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.",
- "MSRValue": "0x3f803c0002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+ "MSRValue": "0x3F803C0002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that have any response type.",
- "MSRValue": "0x0000010004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+ "MSRValue": "0x0000010004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+ "MSRValue": "0x01003C0004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+ "MSRValue": "0x04003C0004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0004 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+ "MSRValue": "0x10003C0004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that hit in the L3.",
- "MSRValue": "0x3f803c0004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+ "MSRValue": "0x3F803C0004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.",
- "MSRValue": "0x0000010010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
+ "MSRValue": "0x0000010010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+ "MSRValue": "0x01003C0010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+ "MSRValue": "0x04003C0010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0010 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+ "MSRValue": "0x10003C0010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.",
- "MSRValue": "0x3f803c0010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+ "MSRValue": "0x3F803C0010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.",
- "MSRValue": "0x0000010020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
+ "MSRValue": "0x0000010020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+ "MSRValue": "0x01003C0020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+ "MSRValue": "0x04003C0020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0020 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+ "MSRValue": "0x10003C0020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.",
- "MSRValue": "0x3f803c0020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+ "MSRValue": "0x3F803C0020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.",
- "MSRValue": "0x0000010080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
+ "MSRValue": "0x0000010080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+ "MSRValue": "0x01003C0080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+ "MSRValue": "0x04003C0080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0080 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+ "MSRValue": "0x10003C0080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.",
- "MSRValue": "0x3f803c0080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+ "MSRValue": "0x3F803C0080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.",
- "MSRValue": "0x0000010100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
+ "MSRValue": "0x0000010100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+ "MSRValue": "0x01003C0100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+ "MSRValue": "0x04003C0100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+ "MSRValue": "0x10003C0100",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+ "MSRValue": "0x3F803C0100",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.",
- "MSRValue": "0x3f803c0100 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.",
+ "MSRValue": "0x0000010400",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.",
- "MSRValue": "0x0000010400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+ "MSRValue": "0x01003C0400",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+ "MSRValue": "0x04003C0400",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+ "MSRValue": "0x10003C0400",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "PF_L1D_AND_SW & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+ "MSRValue": "0x3F803C0400",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0400 ",
+ "BriefDescription": "TBD have any response type.",
+ "MSRValue": "0x0000010490",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.",
- "MSRValue": "0x3f803c0400 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x01003C0490",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts any other requests that have any response type.",
- "MSRValue": "0x0000018000 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x04003C0490",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c8000 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x10003C0490",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c8000 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x3F803C0490",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "OTHER & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c8000 ",
+ "BriefDescription": "TBD have any response type.",
+ "MSRValue": "0x0000010120",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c8000 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x01003C0120",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts any other requests that hit in the L3.",
- "MSRValue": "0x3f803c8000 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x04003C0120",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that have any response type.",
- "MSRValue": "0x0000010490 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x10003C0120",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0490 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x3F803C0120",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0490 ",
+ "BriefDescription": "TBD have any response type.",
+ "MSRValue": "0x0000010491",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0490 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x01003C0491",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0490 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x04003C0491",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that hit in the L3.",
- "MSRValue": "0x3f803c0490 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x10003C0491",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that have any response type.",
- "MSRValue": "0x0000010120 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x3F803C0491",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0120 ",
+ "BriefDescription": "TBD have any response type.",
+ "MSRValue": "0x0000010122",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD have any response type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0120 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x01003C0122",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0120 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x04003C0122",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0120 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x10003C0122",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that hit in the L3.",
- "MSRValue": "0x3f803c0120 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x3F803C0122",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that have any response type.",
- "MSRValue": "0x0000010491 ",
+ "BriefDescription": "Counts demand data reads",
+ "MSRValue": "0x08007C0001",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "Counts demand data reads",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0491 ",
+ "BriefDescription": "Counts all demand data writes (RFOs)",
+ "MSRValue": "0x08007C0002",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "Counts all demand data writes (RFOs)",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0491 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+ "MSRValue": "0x08007C0004",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0491 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
+ "MSRValue": "0x08007C0010",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0491 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
+ "MSRValue": "0x08007C0020",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.",
- "MSRValue": "0x3f803c0491 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
+ "MSRValue": "0x08007C0080",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.",
- "MSRValue": "0x0000010122 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
+ "MSRValue": "0x08007C0100",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
- "MSRValue": "0x01003c0122 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests",
+ "MSRValue": "0x08007C0400",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x04003c0122 ",
+ "BriefDescription": "TBD",
+ "MSRValue": "0x08007C0490",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
- "MSRValue": "0x08003c0122 ",
+ "BriefDescription": "TBD",
+ "MSRValue": "0x08007C0120",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
- "MSRValue": "0x10003c0122 ",
+ "BriefDescription": "TBD",
+ "MSRValue": "0x08007C0491",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.",
- "MSRValue": "0x3f803c0122 ",
+ "BriefDescription": "TBD",
+ "MSRValue": "0x08007C0122",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "PublicDescription": "TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
}
"BriefDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8)",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
- "PublicDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"BriefDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16)",
"Counter": "0,1,2,3",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
- "PublicDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
[
- {
- "EventCode": "0x79",
- "UMask": "0x4",
- "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
- "Counter": "0,1,2,3",
- "EventName": "IDQ.MITE_UOPS",
- "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
- "SampleAfterValue": "2000003",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
{
"EventCode": "0x79",
"UMask": "0x4",
},
{
"EventCode": "0x79",
- "UMask": "0x8",
- "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+ "UMask": "0x4",
+ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
- "EventName": "IDQ.DSB_UOPS",
- "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+ "EventName": "IDQ.MITE_UOPS",
+ "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0x79",
+ "UMask": "0x8",
+ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+ "Counter": "0,1,2,3",
+ "EventName": "IDQ.DSB_UOPS",
+ "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+ "SampleAfterValue": "2000003",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"EventCode": "0x79",
"UMask": "0x10",
{
"EventCode": "0x79",
"UMask": "0x18",
- "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
+ "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3",
- "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
- "CounterMask": "4",
- "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+ "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+ "CounterMask": "1",
+ "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x18",
- "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
+ "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"Counter": "0,1,2,3",
- "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
- "CounterMask": "1",
- "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+ "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
+ "CounterMask": "4",
+ "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x24",
- "BriefDescription": "Cycles MITE is delivering 4 Uops",
+ "BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
- "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
- "CounterMask": "4",
- "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+ "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+ "CounterMask": "1",
+ "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x79",
"UMask": "0x24",
- "BriefDescription": "Cycles MITE is delivering any Uop",
+ "BriefDescription": "Cycles MITE is delivering 4 Uops",
"Counter": "0,1,2,3",
- "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
- "CounterMask": "1",
- "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+ "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
+ "CounterMask": "4",
+ "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EdgeDetect": "1",
"EventCode": "0x79",
"UMask": "0x30",
- "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
+ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
"Counter": "0,1,2,3",
- "EventName": "IDQ.MS_SWITCHES",
- "CounterMask": "1",
- "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+ "EventName": "IDQ.MS_UOPS",
+ "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "EdgeDetect": "1",
"EventCode": "0x79",
"UMask": "0x30",
- "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+ "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
"Counter": "0,1,2,3",
- "EventName": "IDQ.MS_UOPS",
- "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
+ "EventName": "IDQ.MS_SWITCHES",
+ "CounterMask": "1",
+ "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "Invert": "1",
"EventCode": "0x9C",
"UMask": "0x1",
- "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
+ "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
"Counter": "0,1,2,3",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
- "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
+ "CounterMask": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x9C",
"UMask": "0x1",
- "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+ "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
"Counter": "0,1,2,3",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
- "CounterMask": "4",
- "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
+ "CounterMask": "1",
+ "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x9C",
"UMask": "0x1",
- "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+ "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
"Counter": "0,1,2,3",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
- "CounterMask": "3",
- "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
+ "CounterMask": "2",
+ "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x9C",
"UMask": "0x1",
- "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
+ "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
"Counter": "0,1,2,3",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
- "CounterMask": "2",
- "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+ "CounterMask": "3",
+ "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x9C",
"UMask": "0x1",
- "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
+ "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
"Counter": "0,1,2,3",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
- "CounterMask": "1",
- "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+ "CounterMask": "4",
+ "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "Invert": "1",
"EventCode": "0x9C",
"UMask": "0x1",
- "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
+ "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
"Counter": "0,1,2,3",
- "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
- "CounterMask": "1",
+ "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+ "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
- "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+ "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x11",
+ "MSRValue": "0x400406",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.DSB_MISS",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
- "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x12",
+ "MSRValue": "0x200206",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.L1I_MISS",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x13",
+ "MSRValue": "0x400206",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.L2_MISS",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.",
+ "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x14",
+ "MSRValue": "0x15",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.ITLB_MISS",
+ "EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
- "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+ "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.",
+ "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x15",
+ "MSRValue": "0x14",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.STLB_MISS",
+ "EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
- "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+ "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x400206",
+ "MSRValue": "0x13",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
+ "EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x200206",
+ "MSRValue": "0x12",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
+ "EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x400406",
+ "MSRValue": "0x11",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
+ "EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
+ "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x400806",
+ "MSRValue": "0x300206",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
"MSRIndex": "0x3F7",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x401006",
+ "MSRValue": "0x100206",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x402006",
+ "MSRValue": "0x420006",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x404006",
+ "MSRValue": "0x410006",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x410006",
+ "MSRValue": "0x404006",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"TakenAlone": "1",
"SampleAfterValue": "100007",
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x420006",
+ "MSRValue": "0x402006",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.",
"PEBS": "1",
- "MSRValue": "0x100206",
+ "MSRValue": "0x401006",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
- "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0xC6",
"UMask": "0x1",
- "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
"PEBS": "1",
- "MSRValue": "0x300206",
+ "MSRValue": "0x400806",
"Counter": "0,1,2,3",
- "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
"TakenAlone": "1",
"SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
{
"EventCode": "0x60",
"UMask": "0x10",
- "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+ "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
- "CounterMask": "1",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
+ "CounterMask": "6",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x60",
"UMask": "0x10",
- "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
+ "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
"Counter": "0,1,2,3",
- "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
- "CounterMask": "6",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
+ "CounterMask": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC8",
"UMask": "0x4",
- "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ",
+ "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "HLE_RETIRED.ABORTED",
"BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
"Counter": "0,1,2,3",
"EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
+ "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC9",
"UMask": "0x4",
- "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ",
+ "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "RTM_RETIRED.ABORTED",
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"PEBS": "2",
- "MSRValue": "0x4",
+ "MSRValue": "0x200",
"Counter": "0,1,2,3",
- "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
"TakenAlone": "1",
- "SampleAfterValue": "100003",
+ "SampleAfterValue": "101",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
"PEBS": "2",
- "MSRValue": "0x8",
+ "MSRValue": "0x100",
"Counter": "0,1,2,3",
- "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.",
"TakenAlone": "1",
- "SampleAfterValue": "50021",
+ "SampleAfterValue": "503",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
"PEBS": "2",
- "MSRValue": "0x10",
+ "MSRValue": "0x80",
"Counter": "0,1,2,3",
- "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.",
"TakenAlone": "1",
- "SampleAfterValue": "20011",
+ "SampleAfterValue": "1009",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
"PEBS": "2",
- "MSRValue": "0x20",
+ "MSRValue": "0x40",
"Counter": "0,1,2,3",
- "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.",
"TakenAlone": "1",
- "SampleAfterValue": "100007",
+ "SampleAfterValue": "2003",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"PEBS": "2",
- "MSRValue": "0x40",
+ "MSRValue": "0x20",
"Counter": "0,1,2,3",
- "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
"TakenAlone": "1",
- "SampleAfterValue": "2003",
+ "SampleAfterValue": "100007",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"PEBS": "2",
- "MSRValue": "0x80",
+ "MSRValue": "0x10",
"Counter": "0,1,2,3",
- "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
"TakenAlone": "1",
- "SampleAfterValue": "1009",
+ "SampleAfterValue": "20011",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"PEBS": "2",
- "MSRValue": "0x100",
+ "MSRValue": "0x8",
"Counter": "0,1,2,3",
- "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
"TakenAlone": "1",
- "SampleAfterValue": "503",
+ "SampleAfterValue": "50021",
"CounterHTOff": "0,1,2,3"
},
{
"EventCode": "0xCD",
"UMask": "0x1",
- "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.",
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"PEBS": "2",
- "MSRValue": "0x200",
+ "MSRValue": "0x4",
"Counter": "0,1,2,3",
- "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
- "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
"TakenAlone": "1",
- "SampleAfterValue": "101",
+ "SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
{
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that miss in the L3.",
- "MSRValue": "0x3fbc000001 ",
+ "BriefDescription": "Counts demand data reads TBD TBD",
+ "MSRValue": "0x3FBC000001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00001 ",
+ "BriefDescription": "Counts demand data reads TBD",
+ "MSRValue": "0x083FC00001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00001 ",
+ "BriefDescription": "Counts demand data reads TBD",
+ "MSRValue": "0x103FC00001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00001 ",
+ "BriefDescription": "Counts demand data reads TBD",
+ "MSRValue": "0x063FC00001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800001 ",
+ "BriefDescription": "Counts demand data reads TBD",
+ "MSRValue": "0x063B800001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000001 ",
+ "BriefDescription": "Counts demand data reads TBD",
+ "MSRValue": "0x0604000001",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.",
- "MSRValue": "0x3fbc000002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+ "MSRValue": "0x3FBC000002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+ "MSRValue": "0x083FC00002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+ "MSRValue": "0x103FC00002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+ "MSRValue": "0x063FC00002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+ "MSRValue": "0x063B800002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000002 ",
+ "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+ "MSRValue": "0x0604000002",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all demand data writes (RFOs) TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that miss in the L3.",
- "MSRValue": "0x3fbc000004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+ "MSRValue": "0x3FBC000004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+ "MSRValue": "0x083FC00004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+ "MSRValue": "0x103FC00004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+ "MSRValue": "0x063FC00004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+ "MSRValue": "0x063B800004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000004 ",
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+ "MSRValue": "0x0604000004",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.",
- "MSRValue": "0x3fbc000010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+ "MSRValue": "0x3FBC000010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+ "MSRValue": "0x083FC00010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+ "MSRValue": "0x103FC00010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+ "MSRValue": "0x063FC00010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+ "MSRValue": "0x063B800010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000010 ",
+ "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+ "MSRValue": "0x0604000010",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.",
- "MSRValue": "0x3fbc000020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+ "MSRValue": "0x3FBC000020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+ "MSRValue": "0x083FC00020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+ "MSRValue": "0x103FC00020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+ "MSRValue": "0x063FC00020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+ "MSRValue": "0x063B800020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000020 ",
+ "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+ "MSRValue": "0x0604000020",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.",
- "MSRValue": "0x3fbc000080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+ "MSRValue": "0x3FBC000080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+ "MSRValue": "0x083FC00080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+ "MSRValue": "0x103FC00080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+ "MSRValue": "0x063FC00080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+ "MSRValue": "0x063B800080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000080 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+ "MSRValue": "0x0604000080",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.",
- "MSRValue": "0x3fbc000100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+ "MSRValue": "0x3FBC000100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+ "MSRValue": "0x083FC00100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+ "MSRValue": "0x103FC00100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+ "MSRValue": "0x063FC00100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+ "MSRValue": "0x063B800100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000100 ",
+ "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+ "MSRValue": "0x0604000100",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.",
- "MSRValue": "0x3fbc000400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+ "MSRValue": "0x3FBC000400",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+ "MSRValue": "0x083FC00400",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+ "MSRValue": "0x103FC00400",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+ "MSRValue": "0x063FC00400",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+ "MSRValue": "0x063B800400",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000400 ",
+ "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+ "MSRValue": "0x0604000400",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts any other requests that miss in the L3.",
- "MSRValue": "0x3fbc008000 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc08000 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc08000 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc08000 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b808000 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
- "SampleAfterValue": "100003",
- "CounterHTOff": "0,1,2,3"
- },
- {
- "Offcore": "1",
- "EventCode": "0xB7, 0xBB",
- "UMask": "0x1",
- "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604008000 ",
- "Counter": "0,1,2,3",
- "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that miss in the L3.",
- "MSRValue": "0x3fbc000490 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x3FBC000490",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00490 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x083FC00490",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00490 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x103FC00490",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00490 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x063FC00490",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800490 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x063B800490",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000490 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x0604000490",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that miss in the L3.",
- "MSRValue": "0x3fbc000120 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x3FBC000120",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00120 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x083FC00120",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00120 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x103FC00120",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00120 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x063FC00120",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800120 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x063B800120",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000120 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x0604000120",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.",
- "MSRValue": "0x3fbc000491 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x3FBC000491",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00491 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x083FC00491",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00491 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x103FC00491",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00491 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x063FC00491",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800491 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x063B800491",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000491 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x0604000491",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.",
- "MSRValue": "0x3fbc000122 ",
+ "BriefDescription": "TBD TBD TBD",
+ "MSRValue": "0x3FBC000122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
- "MSRValue": "0x083fc00122 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x083FC00122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
- "MSRValue": "0x103fc00122 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x103FC00122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
- "MSRValue": "0x063fc00122 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x063FC00122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.",
- "MSRValue": "0x063b800122 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x063B800122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"Offcore": "1",
"EventCode": "0xB7, 0xBB",
"UMask": "0x1",
- "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.",
- "MSRValue": "0x0604000122 ",
+ "BriefDescription": "TBD TBD",
+ "MSRValue": "0x0604000122",
"Counter": "0,1,2,3",
"EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
- "MSRIndex": "0x1a6,0x1a7",
- "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+ "MSRIndex": "0x1a6, 0x1a7",
+ "PublicDescription": "TBD TBD",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
}
[
{
- "EventCode": "0x00",
"UMask": "0x1",
"BriefDescription": "Instructions retired from execution.",
"Counter": "Fixed counter 0",
"CounterHTOff": "Fixed counter 0"
},
{
- "EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when the thread is not in halt state",
"Counter": "Fixed counter 1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"UMask": "0x2",
"BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
"Counter": "Fixed counter 1",
"CounterHTOff": "Fixed counter 1"
},
{
- "EventCode": "0x00",
"UMask": "0x3",
"BriefDescription": "Reference cycles when the core is not in halt state.",
"Counter": "Fixed counter 2",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "Invert": "1",
"EventCode": "0x0E",
"UMask": "0x1",
- "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
+ "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
"Counter": "0,1,2,3",
- "EventName": "UOPS_ISSUED.ANY",
- "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+ "EventName": "UOPS_ISSUED.STALL_CYCLES",
+ "CounterMask": "1",
+ "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "Invert": "1",
"EventCode": "0x0E",
"UMask": "0x1",
- "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+ "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
"Counter": "0,1,2,3",
- "EventName": "UOPS_ISSUED.STALL_CYCLES",
- "CounterMask": "1",
- "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+ "EventName": "UOPS_ISSUED.ANY",
+ "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
"Counter": "0,1,2,3",
"EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
- "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
+ "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x1",
- "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
+ "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
"Counter": "0,1,2,3",
- "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+ "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+ "AnyThread": "1",
"SampleAfterValue": "2503",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0x3C",
"UMask": "0x1",
- "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+ "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
"Counter": "0,1,2,3",
- "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
- "AnyThread": "1",
+ "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
"SampleAfterValue": "2503",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0x5E",
+ "EventCode": "0x59",
"UMask": "0x1",
- "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
+ "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.",
"Counter": "0,1,2,3",
- "EventName": "RS_EVENTS.EMPTY_CYCLES",
- "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+ "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD",
+ "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0x5E",
+ "UMask": "0x1",
+ "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
+ "Counter": "0,1,2,3",
+ "EventName": "RS_EVENTS.EMPTY_CYCLES",
+ "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+ "SampleAfterValue": "2000003",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"EventCode": "0x87",
"UMask": "0x1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA2",
+ "EventCode": "0xa2",
"UMask": "0x1",
"BriefDescription": "Resource-related stall cycles",
"Counter": "0,1,2,3",
"EventName": "RESOURCE_STALLS.ANY",
- "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+ "PublicDescription": "Counts resource-related stall cycles.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0xA8",
+ "UMask": "0x1",
+ "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+ "Counter": "0,1,2,3",
+ "EventName": "LSD.CYCLES_4_UOPS",
+ "CounterMask": "4",
+ "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
+ "SampleAfterValue": "2000003",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"EventCode": "0xA8",
"UMask": "0x1",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "EventCode": "0xA8",
+ "EventCode": "0xB1",
"UMask": "0x1",
- "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+ "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
"Counter": "0,1,2,3",
- "EventName": "LSD.CYCLES_4_UOPS",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
"CounterMask": "4",
- "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
+ "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x1",
- "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
+ "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
"Counter": "0,1,2,3",
- "EventName": "UOPS_EXECUTED.THREAD",
- "PublicDescription": "Number of uops to be executed per-thread each cycle.",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+ "CounterMask": "3",
+ "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "Invert": "1",
"EventCode": "0xB1",
"UMask": "0x1",
- "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+ "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
"Counter": "0,1,2,3",
- "EventName": "UOPS_EXECUTED.STALL_CYCLES",
- "CounterMask": "1",
- "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+ "CounterMask": "2",
+ "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "Invert": "1",
"EventCode": "0xB1",
"UMask": "0x1",
- "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
- "Counter": "0,1,2,3",
- "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
- "CounterMask": "2",
- "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
- "SampleAfterValue": "2000003",
- "CounterHTOff": "0,1,2,3,4,5,6,7"
- },
- {
- "EventCode": "0xB1",
- "UMask": "0x1",
- "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+ "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
"Counter": "0,1,2,3",
- "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
- "CounterMask": "3",
- "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+ "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+ "CounterMask": "1",
+ "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x1",
- "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+ "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
"Counter": "0,1,2,3",
- "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
- "CounterMask": "4",
- "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+ "EventName": "UOPS_EXECUTED.THREAD",
+ "PublicDescription": "Number of uops to be executed per-thread each cycle.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "Invert": "1",
"EventCode": "0xB1",
"UMask": "0x2",
- "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+ "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
"Counter": "0,1,2,3",
- "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
"CounterMask": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
{
"EventCode": "0xB1",
"UMask": "0x2",
- "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+ "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
"Counter": "0,1,2,3",
- "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
- "CounterMask": "2",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+ "CounterMask": "4",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xB1",
"UMask": "0x2",
- "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+ "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
"Counter": "0,1,2,3",
- "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
- "CounterMask": "4",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+ "CounterMask": "2",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "Invert": "1",
"EventCode": "0xB1",
"UMask": "0x2",
- "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+ "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
"Counter": "0,1,2,3",
- "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
"CounterMask": "1",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
+ "Invert": "1",
"EventCode": "0xC2",
"UMask": "0x2",
- "BriefDescription": "Retirement slots used.",
+ "BriefDescription": "Cycles with less than 10 actually retired uops.",
"Counter": "0,1,2,3",
- "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
- "PublicDescription": "Counts the retirement slots used.",
+ "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+ "CounterMask": "10",
+ "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"Counter": "0,1,2,3",
"EventName": "UOPS_RETIRED.STALL_CYCLES",
"CounterMask": "1",
- "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+ "PublicDescription": "This event counts cycles without actually retired uops.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "Invert": "1",
"EventCode": "0xC2",
"UMask": "0x2",
- "BriefDescription": "Cycles with less than 10 actually retired uops.",
+ "BriefDescription": "Retirement slots used.",
"Counter": "0,1,2,3",
- "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
- "CounterMask": "10",
- "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
+ "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+ "PublicDescription": "Counts the retirement slots used.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"Counter": "0,1,2,3",
"EventName": "MACHINE_CLEARS.COUNT",
"CounterMask": "1",
+ "PublicDescription": "Number of machine clears (nukes) of any type.",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC4",
"UMask": "0x10",
- "BriefDescription": "Not taken branch instructions retired.",
+ "BriefDescription": "Counts all not taken macro branch instructions retired.",
+ "PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_INST_RETIRED.NOT_TAKEN",
"Errata": "SKL091",
- "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
"SampleAfterValue": "400009",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
"EventCode": "0xC5",
"UMask": "0x20",
- "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ",
+ "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
+ {
+ "EventCode": "0xCC",
+ "UMask": "0x40",
+ "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.",
+ "Counter": "0,1,2,3",
+ "EventName": "ROB_MISC_EVENTS.PAUSE_INST",
+ "SampleAfterValue": "2000003",
+ "CounterHTOff": "0,1,2,3,4,5,6,7"
+ },
{
"EventCode": "0xE6",
"UMask": "0x1",
[
{
- "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Frontend_Bound"
+ },
+ {
+ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Frontend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Bad_Speculation"
+ },
+ {
+ "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Bad_Speculation_SMT"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Backend_Bound"
+ },
+ {
+ "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Backend_Bound_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricGroup": "TopdownL1",
+ "MetricName": "Retiring"
+ },
+ {
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+ "MetricGroup": "TopdownL1_SMT",
+ "MetricName": "Retiring_SMT"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
"MetricGroup": "TopDownL1",
"MetricName": "IPC"
},
{
- "BriefDescription": "Uops Per Instruction",
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
- "MetricGroup": "Pipeline",
+ "BriefDescription": "Uops Per Instruction",
+ "MetricGroup": "Pipeline;Retiring",
"MetricName": "UPI"
},
{
- "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
- "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
- "MetricGroup": "Frontend",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Instruction per taken branch",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "IpTB"
+ },
+ {
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "BriefDescription": "Branch instructions per taken branch. ",
+ "MetricGroup": "Branches;PGO",
+ "MetricName": "BpTB"
+ },
+ {
+ "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+ "MetricGroup": "PGO",
"MetricName": "IFetch_Line_Utilization"
},
{
- "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
- "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
- "MetricGroup": "DSB; Frontend_Bandwidth",
+ "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))",
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricGroup": "DSB;Frontend_Bandwidth",
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "BriefDescription": "Cycles Per Instruction (threaded)",
"MetricGroup": "Pipeline;Summary",
"MetricName": "CPI"
},
{
- "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
"MetricGroup": "Summary",
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricExpr": "4 * cycles",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
{
- "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Total issue-pipeline slots (per core)",
+ "MetricGroup": "TopDownL1_SMT",
+ "MetricName": "SLOTS_SMT"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+ "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+ "MetricGroup": "Instruction_Type;L1_Bound",
+ "MetricName": "IpL"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+ "BriefDescription": "Instructions per Store",
+ "MetricGroup": "Instruction_Type;Store_Bound",
+ "MetricName": "IpS"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Instructions per Branch",
+ "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+ "MetricName": "IpB"
+ },
+ {
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "BriefDescription": "Instruction per (near) call",
+ "MetricGroup": "Branches",
+ "MetricName": "IpCall"
+ },
+ {
"MetricExpr": "INST_RETIRED.ANY",
+ "BriefDescription": "Total number of retired Instructions",
"MetricGroup": "Summary",
"MetricName": "Instructions"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / cycles",
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC_SMT"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS",
+ "MetricName": "FLOPc"
+ },
+ {
+ "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricGroup": "FLOPS_SMT",
+ "MetricName": "FLOPc_SMT"
+ },
+ {
+ "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
- "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
"MetricGroup": "Pipeline;Ports_Utilization",
"MetricName": "ILP"
},
{
- "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
- "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
- "MetricGroup": "Unknown_Branches",
- "MetricName": "BAClear_Cost"
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "Branch_Misprediction_Cost"
+ },
+ {
+ "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+ "MetricGroup": "Branch_Mispredicts_SMT",
+ "MetricName": "Branch_Misprediction_Cost_SMT"
},
{
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+ "MetricGroup": "Branch_Mispredicts",
+ "MetricName": "IpMispredict"
+ },
+ {
+ "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
"BriefDescription": "Core actual clocks when any thread is active on the physical core",
- "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "SMT",
"MetricName": "CORE_CLKS"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
{
- "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
- "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
"MetricGroup": "Memory_Bound;Memory_BW",
"MetricName": "MLP"
},
{
+ "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
"BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
- "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
"MetricGroup": "TLB",
"MetricName": "Page_Walks_Utilization"
},
{
- "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricGroup": "TLB_SMT",
+ "MetricName": "Page_Walks_Utilization_SMT"
+ },
+ {
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "L3_Cache_Access_BW"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L1MPKI"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI"
+ },
+ {
+ "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2MPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L2HPKI_All"
+ },
+ {
+ "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricGroup": "Cache_Misses;",
+ "MetricName": "L3MPKI"
+ },
+ {
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "BriefDescription": "Average CPU Utilization",
"MetricGroup": "Summary",
"MetricName": "CPU_Utilization"
},
{
+ "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},
{
- "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricGroup": "Power",
"MetricName": "Turbo_Utilization"
},
{
- "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
"MetricGroup": "SMT;Summary",
"MetricName": "SMT_2T_Utilization"
},
{
- "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
"MetricGroup": "Summary",
"MetricName": "Kernel_Utilization"
},
{
- "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_BW_Use"
+ },
+ {
+ "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
+ "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+ "MetricGroup": "Memory_Lat",
+ "MetricName": "DRAM_Read_Latency"
+ },
+ {
+ "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
+ "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "DRAM_Parallel_Reads"
+ },
+ {
+ "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 0 == 1 else 0 else 0",
+ "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
+ "MetricGroup": "Memory_Lat",
+ "MetricName": "MEM_PMM_Read_Latency"
+ },
+ {
+ "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
+ "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "PMM_Read_BW"
+ },
+ {
+ "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
+ "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
+ "MetricGroup": "Memory_BW",
+ "MetricName": "PMM_Write_BW"
+ },
+ {
+ "MetricExpr": "cha_0@event\\=0x0@",
+ "BriefDescription": "Socket actual clocks when any core is active on that socket",
+ "MetricGroup": "",
+ "MetricName": "Socket_CLKS"
+ },
+ {
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per core",
"MetricName": "C3_Core_Residency"
},
{
- "BriefDescription": "C6 residency percent per core",
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per core",
"MetricName": "C6_Core_Residency"
},
{
- "BriefDescription": "C7 residency percent per core",
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per core",
"MetricName": "C7_Core_Residency"
},
{
- "BriefDescription": "C2 residency percent per package",
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C2 residency percent per package",
"MetricName": "C2_Pkg_Residency"
},
{
- "BriefDescription": "C3 residency percent per package",
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C3 residency percent per package",
"MetricName": "C3_Pkg_Residency"
},
{
- "BriefDescription": "C6 residency percent per package",
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C6 residency percent per package",
"MetricName": "C6_Pkg_Residency"
},
{
- "BriefDescription": "C7 residency percent per package",
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
"MetricGroup": "Power",
+ "BriefDescription": "C7 residency percent per package",
"MetricName": "C7_Pkg_Residency"
}
]
'return_id,'
'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
'parent_call_path_id,'
- 'parent_id'
+ 'calls.parent_id'
' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
do_query(query, 'CREATE VIEW samples_view AS '
// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
#include "trace/beauty/beauty.h"
-#include <uapi/linux/fs.h>
static size_t renameat2__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
{
--- /dev/null
+access
+acct
+add_key
+chdir
+chmod
+chown
+chroot
+creat
+delete_module
+execve
+execveat
+faccessat
+fchmodat
+fchownat
+fgetxattr
+finit_module
+fremovexattr
+fsetxattr
+futimesat
+getxattr
+inotify_add_watch
+lchown
+lgetxattr
+link
+linkat
+listxattr
+llistxattr
+lremovexattr
+lsetxattr
+lstat
+memfd_create
+mkdir
+mkdirat
+mknod
+mknodat
+mq_open
+mq_timedsend
+mq_unlink
+name_to_handle_at
+newfstatat
+open
+openat
+pivot_root
+pwrite64
+quotactl
+readlink
+readlinkat
+removexattr
+rename
+renameat
+renameat2
+request_key
+rmdir
+setxattr
+stat
+statfs
+statx
+swapoff
+swapon
+symlink
+symlinkat
+truncate
+unlink
+unlinkat
+utimensat
if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
return -1;
- pr_debug("%s: handling sym %s addr %lx len %lx\n", __func__,
- sym->name, sym->start, sym->end - sym->start);
+ pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+ sym->name, sym->start, sym->end - sym->start);
memset(tpath, 0, sizeof(tpath));
perf_exe(tpath, sizeof(tpath));
info_linear = info_node->info_linear;
sub_id = dso->bpf_prog.sub_id;
- info.buffer = (void *)(info_linear->info.jited_prog_insns);
+ info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
info.buffer_length = info_linear->info.jited_prog_len;
if (info_linear->info.nr_line_info)
const char *srcline;
u64 addr;
- addr = pc + ((u64 *)(info_linear->info.jited_ksyms))[sub_id];
+ addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
count = disassemble(pc, &info);
if (prog_linfo)
#include "asm/bug.h"
#include "debug.h"
#include <unistd.h>
-#include <asm/unistd.h>
#include <sys/syscall.h>
static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
if (!etmq->packet)
goto out_free;
- if (etm->synth_opts.last_branch || etm->sample_branches) {
- etmq->prev_packet = zalloc(szp);
- if (!etmq->prev_packet)
- goto out_free;
- }
+ etmq->prev_packet = zalloc(szp);
+ if (!etmq->prev_packet)
+ goto out_free;
if (etm->synth_opts.last_branch) {
size_t sz = sizeof(struct branch_stack);
* PREV_PACKET is a branch.
*/
if (etm->synth_opts.last_branch &&
- etmq->prev_packet &&
etmq->prev_packet->sample_type == CS_ETM_RANGE &&
etmq->prev_packet->last_instr_taken_branch)
cs_etm__update_last_branch_rb(etmq);
etmq->period_instructions = instrs_over;
}
- if (etm->sample_branches && etmq->prev_packet) {
+ if (etm->sample_branches) {
bool generate_sample = false;
/* Generate sample for tracing on packet */
struct cs_etm_auxtrace *etm = etmq->etm;
struct cs_etm_packet *tmp;
- if (!etmq->prev_packet)
- return 0;
-
/* Handle start tracing packet */
if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
goto swap_packet;
if (flags & TEP_FIELD_IS_DYNAMIC) {
unsigned long long tmp_val;
- tmp_val = tep_read_number(fmtf->event->pevent,
+ tmp_val = tep_read_number(fmtf->event->tep,
data + offset, len);
offset = tmp_val;
len = offset >> 16;
unsigned long long value_int;
value_int = tep_read_number(
- fmtf->event->pevent,
+ fmtf->event->tep,
data + offset + i * len, len);
if (!(flags & TEP_FIELD_IS_SIGNED))
else if (prog_id > node->info_linear->info.id)
n = n->rb_right;
else
- break;
+ goto out;
}
+ node = NULL;
+out:
up_read(&env->bpf_progs.lock);
return node;
}
else if (btf_id > node->id)
n = n->rb_right;
else
- break;
+ goto out;
}
+ node = NULL;
+out:
up_read(&env->bpf_progs.lock);
return node;
}
#include <stdio.h>
#include <linux/kernel.h>
#include <linux/bpf.h>
+#include <linux/perf_event.h>
#include "../perf.h"
#include "build-id.h"
*/
int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
unsigned int auxtrace_pages,
- bool auxtrace_overwrite, int nr_cblocks, int affinity)
+ bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush)
{
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
* Its value is decided by evsel's write_backward.
* So &mp should not be passed through const pointer.
*/
- struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity };
+ struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush };
if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
{
- return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS);
+ return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1);
}
int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
{
struct perf_evlist *evlist = arg;
bool draining = false;
- int i;
+ int i, done = 0;
+
+ while (!done) {
+ bool got_data = false;
- while (draining || !(evlist->thread.done)) {
- if (draining)
- draining = false;
- else if (evlist->thread.done)
+ if (evlist->thread.done)
draining = true;
if (!draining)
pr_warning("cannot locate proper evsel for the side band event\n");
perf_mmap__consume(map);
+ got_data = true;
}
perf_mmap__read_done(map);
}
+
+ if (draining && !got_data)
+ break;
}
return NULL;
}
int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
unsigned int auxtrace_pages,
- bool auxtrace_overwrite, int nr_cblocks, int affinity);
+ bool auxtrace_overwrite, int nr_cblocks,
+ int affinity, int flush);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
void perf_evlist__munmap(struct perf_evlist *evlist);
return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
}
+static int perf_evsel__tool_name(char *bf, size_t size)
+{
+ int ret = scnprintf(bf, size, "duration_time");
+ return ret;
+}
+
const char *perf_evsel__name(struct perf_evsel *evsel)
{
char bf[128];
break;
case PERF_TYPE_SOFTWARE:
- perf_evsel__sw_name(evsel, bf, sizeof(bf));
+ if (evsel->tool_event)
+ perf_evsel__tool_name(bf, sizeof(bf));
+ else
+ perf_evsel__sw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_TRACEPOINT:
if (data->user_regs.abi) {
u64 mask = evsel->attr.sample_regs_user;
- sz = hweight_long(mask) * sizeof(u64);
+ sz = hweight64(mask) * sizeof(u64);
OVERFLOW_CHECK(array, sz, max_size);
data->user_regs.mask = mask;
data->user_regs.regs = (u64 *)array;
if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
u64 mask = evsel->attr.sample_regs_intr;
- sz = hweight_long(mask) * sizeof(u64);
+ sz = hweight64(mask) * sizeof(u64);
OVERFLOW_CHECK(array, sz, max_size);
data->intr_regs.mask = mask;
data->intr_regs.regs = (u64 *)array;
if (type & PERF_SAMPLE_REGS_USER) {
if (sample->user_regs.abi) {
result += sizeof(u64);
- sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+ sz = hweight64(sample->user_regs.mask) * sizeof(u64);
result += sz;
} else {
result += sizeof(u64);
if (type & PERF_SAMPLE_REGS_INTR) {
if (sample->intr_regs.abi) {
result += sizeof(u64);
- sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+ sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
result += sz;
} else {
result += sizeof(u64);
if (type & PERF_SAMPLE_REGS_USER) {
if (sample->user_regs.abi) {
*array++ = sample->user_regs.abi;
- sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+ sz = hweight64(sample->user_regs.mask) * sizeof(u64);
memcpy(array, sample->user_regs.regs, sz);
array = (void *)array + sz;
} else {
if (type & PERF_SAMPLE_REGS_INTR) {
if (sample->intr_regs.abi) {
*array++ = sample->intr_regs.abi;
- sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+ sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
memcpy(array, sample->intr_regs.regs, sz);
array = (void *)array + sz;
} else {
typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data);
+enum perf_tool_event {
+ PERF_TOOL_NONE = 0,
+ PERF_TOOL_DURATION_TIME = 1,
+};
+
/** struct perf_evsel - event selector
*
* @evlist - evlist this evsel is in, if it is in one.
unsigned int sample_size;
int id_pos;
int is_pos;
+ enum perf_tool_event tool_event;
bool uniquified_name;
bool snapshot;
bool supported;
perf_env__insert_bpf_prog_info(env, info_node);
}
+ up_write(&env->bpf_progs.lock);
return 0;
out:
free(info_linear);
static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
{
struct perf_env *env = &ff->ph->env;
+ struct btf_node *node = NULL;
u32 count, i;
+ int err = -1;
if (ff->ph->needs_swap) {
pr_warning("interpreting btf from systems with endianity is not yet supported\n");
down_write(&env->bpf_progs.lock);
for (i = 0; i < count; ++i) {
- struct btf_node *node;
u32 id, data_size;
if (do_read_u32(ff, &id))
- return -1;
+ goto out;
if (do_read_u32(ff, &data_size))
- return -1;
+ goto out;
node = malloc(sizeof(struct btf_node) + data_size);
if (!node)
- return -1;
+ goto out;
node->id = id;
node->data_size = data_size;
- if (__do_read(ff, node->data, data_size)) {
- free(node);
- return -1;
- }
+ if (__do_read(ff, node->data, data_size))
+ goto out;
perf_env__insert_btf(env, node);
+ node = NULL;
}
+ err = 0;
+out:
up_write(&env->bpf_progs.lock);
- return 0;
+ free(node);
+ return err;
}
struct feature_ops {
return kmap && kmap->name[0];
}
+bool __map__is_bpf_prog(const struct map *map)
+{
+ const char *name;
+
+ if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+ return true;
+
+ /*
+ * If PERF_RECORD_BPF_EVENT is not included, the dso will not have
+ * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can
+ * guess the type based on name.
+ */
+ name = map->dso->short_name;
+ return name && (strstr(name, "bpf_prog_") == name);
+}
+
bool map__has_symbols(const struct map *map)
{
return dso__has_symbols(map->dso);
rc = strcmp(m->dso->short_name, map->dso->short_name);
if (rc < 0)
p = &(*p)->rb_left;
- else if (rc > 0)
- p = &(*p)->rb_right;
else
- return;
+ p = &(*p)->rb_right;
}
rb_link_node(&map->rb_node_name, parent, p);
rb_insert_color(&map->rb_node_name, &maps->names);
bool __map__is_kernel(const struct map *map);
bool __map__is_extra_kernel_map(const struct map *map);
+bool __map__is_bpf_prog(const struct map *map);
static inline bool __map__is_kmodule(const struct map *map)
{
- return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
+ return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
+ !__map__is_bpf_prog(map);
}
bool map__has_symbols(const struct map *map);
perf_mmap__setup_affinity_mask(map, mp);
+ map->flush = mp->flush;
+
if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
&mp->auxtrace_mp, map->base, fd))
return -1;
md->start = md->overwrite ? head : old;
md->end = md->overwrite ? old : head;
- if (md->start == md->end)
+ if ((md->end - md->start) < md->flush)
return -EAGAIN;
size = md->end - md->start;
} aio;
#endif
cpu_set_t affinity_mask;
+ u64 flush;
};
/*
};
struct mmap_params {
- int prot, mask, nr_cblocks, affinity;
+ int prot, mask, nr_cblocks, affinity, flush;
struct auxtrace_mmap_params auxtrace_mp;
};
__add_event(struct list_head *list, int *idx,
struct perf_event_attr *attr,
char *name, struct perf_pmu *pmu,
- struct list_head *config_terms, bool auto_merge_stats)
+ struct list_head *config_terms, bool auto_merge_stats,
+ const char *cpu_list)
{
struct perf_evsel *evsel;
- struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
+ struct cpu_map *cpus = pmu ? pmu->cpus :
+ cpu_list ? cpu_map__new(cpu_list) : NULL;
event_attr_init(attr);
struct perf_event_attr *attr, char *name,
struct list_head *config_terms)
{
- return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM;
+ return __add_event(list, idx, attr, name, NULL, config_terms, false, NULL) ? 0 : -ENOMEM;
+}
+
+static int add_event_tool(struct list_head *list, int *idx,
+ enum perf_tool_event tool_event)
+{
+ struct perf_evsel *evsel;
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_DUMMY,
+ };
+
+ evsel = __add_event(list, idx, &attr, NULL, NULL, NULL, false, "0");
+ if (!evsel)
+ return -ENOMEM;
+ evsel->tool_event = tool_event;
+ if (tool_event == PERF_TOOL_DURATION_TIME)
+ evsel->unit = strdup("ns");
+ return 0;
}
static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
get_config_name(head_config), &config_terms);
}
+int parse_events_add_tool(struct parse_events_state *parse_state,
+ struct list_head *list,
+ enum perf_tool_event tool_event)
+{
+ return add_event_tool(list, &parse_state->idx, tool_event);
+}
+
int parse_events_add_pmu(struct parse_events_state *parse_state,
struct list_head *list, char *name,
struct list_head *head_config,
if (!head_config) {
attr.type = pmu->type;
- evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
+ evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL,
+ auto_merge_stats, NULL);
if (evsel) {
evsel->pmu_name = name;
evsel->use_uncore_alias = use_uncore_alias;
evsel = __add_event(list, &parse_state->idx, &attr,
get_config_name(head_config), pmu,
- &config_terms, auto_merge_stats);
+ &config_terms, auto_merge_stats, NULL);
if (evsel) {
evsel->unit = info.unit;
evsel->scale = info.scale;
return evt_num;
}
+static void print_tool_event(const char *name, const char *event_glob,
+ bool name_only)
+{
+ if (event_glob && !strglobmatch(name, event_glob))
+ return;
+ if (name_only)
+ printf("%s ", name);
+ else
+ printf(" %-50s [%s]\n", name, "Tool event");
+
+}
+
+void print_tool_events(const char *event_glob, bool name_only)
+{
+ print_tool_event("duration_time", event_glob, name_only);
+ if (pager_in_use())
+ printf("\n");
+}
+
void print_symbol_events(const char *event_glob, unsigned type,
struct event_symbol *syms, unsigned max,
bool name_only)
print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
event_symbols_sw, PERF_COUNT_SW_MAX, name_only);
+ print_tool_events(event_glob, name_only);
print_hwcache_events(event_glob, name_only);
struct list_head *list,
u32 type, u64 config,
struct list_head *head_config);
+enum perf_tool_event;
+int parse_events_add_tool(struct parse_events_state *parse_state,
+ struct list_head *list,
+ enum perf_tool_event tool_event);
int parse_events_add_cache(struct list_head *list, int *idx,
char *type, char *op_result1, char *op_result2,
struct parse_events_error *error,
void print_symbol_events(const char *event_glob, unsigned type,
struct event_symbol *syms, unsigned max,
bool name_only);
+void print_tool_events(const char *event_glob, bool name_only);
void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
bool name_only);
int print_hwcache_events(const char *event_glob, bool name_only);
#include "../perf.h"
#include "parse-events.h"
#include "parse-events-bison.h"
+#include "evsel.h"
char *parse_events_get_text(yyscan_t yyscanner);
YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
}
+static int tool(yyscan_t scanner, enum perf_tool_event event)
+{
+ YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+ yylval->num = event;
+ return PE_VALUE_SYM_TOOL;
+}
+
static int term(yyscan_t scanner, int type)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
-duration_time { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+duration_time { return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
/*
#include <linux/types.h>
#include "util.h"
#include "pmu.h"
+#include "evsel.h"
#include "debug.h"
#include "parse-events.h"
#include "parse-events-bison.h"
%token PE_START_EVENTS PE_START_TERMS
%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
+%token PE_VALUE_SYM_TOOL
%token PE_EVENT_NAME
%token PE_NAME
%token PE_BPF_OBJECT PE_BPF_SOURCE
%type <num> PE_VALUE
%type <num> PE_VALUE_SYM_HW
%type <num> PE_VALUE_SYM_SW
+%type <num> PE_VALUE_SYM_TOOL
%type <num> PE_RAW
%type <num> PE_TERM
%type <str> PE_NAME
ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL));
$$ = list;
}
+|
+PE_VALUE_SYM_TOOL sep_slash_slash_dc
+{
+ struct list_head *list;
+
+ ALLOC_LIST(list);
+ ABORT_ON(parse_events_add_tool(_parse_state, list, $1));
+ $$ = list;
+}
event_legacy_cache:
PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
static PyObject*
tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
{
- struct tep_handle *pevent = field->event->pevent;
+ struct tep_handle *pevent = field->event->tep;
void *data = pe->sample.raw_data;
PyObject *ret = NULL;
unsigned long long val;
ns = nsecs - s * NSEC_PER_SEC;
scripting_context->event_data = data;
- scripting_context->pevent = evsel->tp_format->pevent;
+ scripting_context->pevent = evsel->tp_format->tep;
ENTER;
SAVETMPS;
ns = nsecs - s * NSEC_PER_SEC;
scripting_context->event_data = data;
- scripting_context->pevent = evsel->tp_format->pevent;
+ scripting_context->pevent = evsel->tp_format->tep;
context = _PyCapsule_New(scripting_context, NULL, NULL);
size = event->header.size;
+ skip = -EINVAL;
+
if (size < sizeof(struct perf_event_header) ||
(skip = rd->process(session, event, file_pos)) < 0) {
- pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+ pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n",
file_offset + head, event->header.size,
- event->header.type);
- err = -EINVAL;
+ event->header.type, strerror(-skip));
+ err = skip;
goto out;
}
#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
-static bool is_duration_time(struct perf_evsel *evsel)
-{
- return !strcmp(evsel->name, "duration_time");
-}
-
static void print_running(struct perf_stat_config *config,
u64 run, u64 ena)
{
ad.id = id = config->aggr_map->map[s];
first = true;
evlist__for_each_entry(evlist, counter) {
- if (is_duration_time(counter))
- continue;
-
ad.val = ad.ena = ad.run = 0;
ad.nr = 0;
if (!collect_data(config, counter, aggr_cb, &ad))
if (prefix)
fputs(prefix, config->output);
evlist__for_each_entry(evlist, counter) {
- if (is_duration_time(counter))
- continue;
if (first) {
aggr_printout(config, counter, cpu, 0);
first = false;
/* Print metrics headers only */
evlist__for_each_entry(evlist, counter) {
- if (is_duration_time(counter))
- continue;
os.evsel = counter;
out.ctx = &os;
out.print_metric = print_metric_header;
break;
case AGGR_THREAD:
evlist__for_each_entry(evlist, counter) {
- if (is_duration_time(counter))
- continue;
print_aggr_thread(config, _target, counter, prefix);
}
break;
case AGGR_GLOBAL:
evlist__for_each_entry(evlist, counter) {
- if (is_duration_time(counter))
- continue;
print_counter_aggr(config, counter, prefix);
}
if (metric_only)
print_no_aggr_metric(config, evlist, prefix);
else {
evlist__for_each_entry(evlist, counter) {
- if (is_duration_time(counter))
- continue;
print_counter(config, counter, prefix);
}
}
unsigned long long read_size(struct tep_event *event, void *ptr, int size)
{
- return tep_read_number(event->pevent, ptr, size);
+ return tep_read_number(event->tep, ptr, size);
}
void event_format__fprintf(struct tep_event *event,
tep_set_flag(pevent, TEP_NSEC_OUTPUT);
tep_set_file_bigendian(pevent, file_bigendian);
- tep_set_host_bigendian(pevent, host_bigendian);
+ tep_set_local_bigendian(pevent, host_bigendian);
if (do_read(buf, 1) < 0)
goto out;
static int trace_event__init2(void)
{
- int be = tep_host_bigendian();
+ int be = tep_is_bigendian();
struct tep_handle *pevent;
if (trace_event__init(&tevent))
pevent = tevent.pevent;
tep_set_flag(pevent, TEP_NSEC_OUTPUT);
tep_set_file_bigendian(pevent, be);
- tep_set_host_bigendian(pevent, be);
+ tep_set_local_bigendian(pevent, be);
tevent_initialized = true;
return 0;
}
struct nfit_test_sec {
u8 state;
u8 ext_state;
+ u8 old_state;
u8 passphrase[32];
u8 master_passphrase[32];
u64 overwrite_end_time;
static struct gen_pool *nfit_pool;
+static const char zero_key[NVDIMM_PASSPHRASE_LEN];
+
static struct nfit_test *to_nfit_test(struct device *dev)
{
struct platform_device *pdev = to_platform_device(dev);
struct device *dev = &t->pdev.dev;
struct nfit_test_sec *sec = &dimm_sec_info[dimm];
- if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED) ||
- (sec->state & ND_INTEL_SEC_STATE_FROZEN)) {
+ if (sec->state & ND_INTEL_SEC_STATE_FROZEN) {
nd_cmd->status = ND_INTEL_STATUS_INVALID_STATE;
dev_dbg(dev, "secure erase: wrong security state\n");
} else if (memcmp(nd_cmd->passphrase, sec->passphrase,
nd_cmd->status = ND_INTEL_STATUS_INVALID_PASS;
dev_dbg(dev, "secure erase: wrong passphrase\n");
} else {
+ if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED)
+ && (memcmp(nd_cmd->passphrase, zero_key,
+ ND_INTEL_PASSPHRASE_SIZE) != 0)) {
+ dev_dbg(dev, "invalid zero key\n");
+ return 0;
+ }
memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
memset(sec->master_passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
sec->state = 0;
return 0;
}
- memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
+ sec->old_state = sec->state;
sec->state = ND_INTEL_SEC_STATE_OVERWRITE;
dev_dbg(dev, "overwrite progressing.\n");
sec->overwrite_end_time = get_jiffies_64() + 5 * HZ;
if (time_is_before_jiffies64(sec->overwrite_end_time)) {
sec->overwrite_end_time = 0;
- sec->state = 0;
+ sec->state = sec->old_state;
+ sec->old_state = 0;
sec->ext_state = ND_INTEL_SEC_ESTATE_ENABLED;
dev_dbg(dev, "overwrite is complete\n");
} else
.prog_type = BPF_PROG_TYPE_XDP,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
+{
+ "calls: ptr null check in subprog",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .fixup_map_hash_48b = { 3 },
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
+ .retval = 0,
+},
{
"calls: two calls with args",
.insns = {
.errstr = "invalid access to packet",
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
+{
+ "direct packet access: test29 (reg > pkt_end in subprog)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
ALL_TESTS="
rif_set_addr_test
+ rif_vrf_set_addr_test
rif_inherit_bridge_addr_test
rif_non_inherit_bridge_addr_test
vlan_interface_deletion_test
ip link set dev $swp1 addr $swp1_mac
}
+rif_vrf_set_addr_test()
+{
+ # Test that it is possible to set an IP address on a VRF upper despite
+ # its random MAC address.
+ RET=0
+
+ ip link add name vrf-test type vrf table 10
+ ip link set dev $swp1 master vrf-test
+
+ ip -4 address add 192.0.2.1/24 dev vrf-test
+ check_err $? "failed to set IPv4 address on VRF"
+ ip -6 address add 2001:db8:1::1/64 dev vrf-test
+ check_err $? "failed to set IPv6 address on VRF"
+
+ log_test "RIF - setting IP address on VRF"
+
+ ip link del dev vrf-test
+}
+
rif_inherit_bridge_addr_test()
{
RET=0
+include ../../../../scripts/Kbuild.include
+
all:
top_srcdir = ../../../..
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
+TEST_GEN_PROGS_x86_64 += x86_64/smm_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
-LDFLAGS += -pthread -no-pie
+
+no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
+ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
+
+LDFLAGS += -pthread $(no-pie-option)
# After inclusion, $(OUTPUT) is defined and
# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
#endif
max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1;
guest_page_size = (1ul << guest_page_shift);
- /* 1G of guest page sized pages */
- guest_num_pages = (1ul << (30 - guest_page_shift));
+ /*
+ * A little more than 1G of guest page sized pages. Cover the
+ * case where the size is not aligned to 64 pages.
+ */
+ guest_num_pages = (1ul << (30 - guest_page_shift)) + 3;
host_page_size = getpagesize();
host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
!!((guest_num_pages * guest_page_size) % host_page_size);
kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
#ifdef USE_CLEAR_DIRTY_LOG
kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
- DIV_ROUND_UP(host_num_pages, 64) * 64);
+ host_num_pages);
#endif
vm_dirty_log_verify(bmap);
iteration++;
#define MSR_IA32_APICBASE_ENABLE (1<<11)
#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
+#define APIC_BASE_MSR 0x800
+#define X2APIC_ENABLE (1UL << 10)
+#define APIC_ICR 0x300
+#define APIC_DEST_SELF 0x40000
+#define APIC_DEST_ALLINC 0x80000
+#define APIC_DEST_ALLBUT 0xC0000
+#define APIC_ICR_RR_MASK 0x30000
+#define APIC_ICR_RR_INVALID 0x00000
+#define APIC_ICR_RR_INPROG 0x10000
+#define APIC_ICR_RR_VALID 0x20000
+#define APIC_INT_LEVELTRIG 0x08000
+#define APIC_INT_ASSERT 0x04000
+#define APIC_ICR_BUSY 0x01000
+#define APIC_DEST_LOGICAL 0x00800
+#define APIC_DEST_PHYSICAL 0x00000
+#define APIC_DM_FIXED 0x00000
+#define APIC_DM_FIXED_MASK 0x00700
+#define APIC_DM_LOWEST 0x00100
+#define APIC_DM_SMI 0x00200
+#define APIC_DM_REMRD 0x00300
+#define APIC_DM_NMI 0x00400
+#define APIC_DM_INIT 0x00500
+#define APIC_DM_STARTUP 0x00600
+#define APIC_DM_EXTINT 0x00700
+#define APIC_VECTOR_MASK 0x000FF
+#define APIC_ICR2 0x310
+
#define MSR_IA32_TSCDEADLINE 0x000006e0
#define MSR_IA32_UCODE_WRITE 0x00000079
if (vm->kvm_fd < 0)
exit(KSFT_SKIP);
+ if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
+ fprintf(stderr, "immediate_exit not available, skipping test\n");
+ exit(KSFT_SKIP);
+ }
+
vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, type);
TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
"rc: %i errno: %i", vm->fd, errno);
nested_size, sizeof(state->nested_));
}
+ /*
+ * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
+ * guest state is consistent only after userspace re-enters the
+ * kernel with KVM_RUN. Complete IO prior to migrating state
+ * to a new VM.
+ */
+ vcpu_run_complete_io(vm, vcpuid);
+
nmsrs = kvm_get_num_msrs(vm);
list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
list->nmsrs = nmsrs;
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int r;
- if (state->nested.size) {
- r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
- r);
- }
-
r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
r);
r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
r);
+
+ if (state->nested.size) {
+ r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
+ r);
+ }
}
stage, run->exit_reason,
exit_reason_str(run->exit_reason));
- memset(®s1, 0, sizeof(regs1));
- vcpu_regs_get(vm, VCPU_ID, ®s1);
switch (get_ucall(vm, VCPU_ID, &uc)) {
case UCALL_ABORT:
TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
stage, (ulong)uc.args[1]);
state = vcpu_save_state(vm, VCPU_ID);
+ memset(®s1, 0, sizeof(regs1));
+ vcpu_regs_get(vm, VCPU_ID, ®s1);
+
kvm_vm_release(vm);
/* Restore state in a new VM. */
free(hv_cpuid_entries);
- vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+ rv = _vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+ if (rv) {
+ fprintf(stderr,
+ "Enlightened VMCS is unsupported, skip related test\n");
+ goto vm_free;
+ }
hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
if (!hv_cpuid_entries)
free(hv_cpuid_entries);
+vm_free:
kvm_vm_free(vm);
return 0;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * Tests for SMM.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+
+#include "vmx.h"
+
+#define VCPU_ID 1
+
+#define PAGE_SIZE 4096
+
+#define SMRAM_SIZE 65536
+#define SMRAM_MEMSLOT ((1 << 16) | 1)
+#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE)
+#define SMRAM_GPA 0x1000000
+#define SMRAM_STAGE 0xfe
+
+#define STR(x) #x
+#define XSTR(s) STR(s)
+
+#define SYNC_PORT 0xe
+#define DONE 0xff
+
+/*
+ * This is compiled as normal 64-bit code, however, SMI handler is executed
+ * in real-address mode. To stay simple we're limiting ourselves to a mode
+ * independent subset of asm here.
+ * SMI handler always report back fixed stage SMRAM_STAGE.
+ */
+uint8_t smi_handler[] = {
+ 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */
+ 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */
+ 0x0f, 0xaa, /* rsm */
+};
+
+void sync_with_host(uint64_t phase)
+{
+ asm volatile("in $" XSTR(SYNC_PORT)", %%al \n"
+ : : "a" (phase));
+}
+
+void self_smi(void)
+{
+ wrmsr(APIC_BASE_MSR + (APIC_ICR >> 4),
+ APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+ uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
+
+ sync_with_host(1);
+
+ wrmsr(MSR_IA32_APICBASE, apicbase | X2APIC_ENABLE);
+
+ sync_with_host(2);
+
+ self_smi();
+
+ sync_with_host(4);
+
+ if (vmx_pages) {
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+
+ sync_with_host(5);
+
+ self_smi();
+
+ sync_with_host(7);
+ }
+
+ sync_with_host(DONE);
+}
+
+int main(int argc, char *argv[])
+{
+ struct vmx_pages *vmx_pages = NULL;
+ vm_vaddr_t vmx_pages_gva = 0;
+
+ struct kvm_regs regs;
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct kvm_x86_state *state;
+ int stage, stage_reported;
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+ run = vcpu_state(vm, VCPU_ID);
+
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA,
+ SMRAM_MEMSLOT, SMRAM_PAGES, 0);
+ TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT)
+ == SMRAM_GPA, "could not allocate guest physical addresses?");
+
+ memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE);
+ memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler,
+ sizeof(smi_handler));
+
+ vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA);
+
+ if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
+ vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+ vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+ } else {
+ printf("will skip SMM test with VMX enabled\n");
+ vcpu_args_set(vm, VCPU_ID, 1, 0);
+ }
+
+ for (stage = 1;; stage++) {
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Stage %d: unexpected exit reason: %u (%s),\n",
+ stage, run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ memset(®s, 0, sizeof(regs));
+ vcpu_regs_get(vm, VCPU_ID, ®s);
+
+ stage_reported = regs.rax & 0xff;
+
+ if (stage_reported == DONE)
+ goto done;
+
+ TEST_ASSERT(stage_reported == stage ||
+ stage_reported == SMRAM_STAGE,
+ "Unexpected stage: #%x, got %x",
+ stage, stage_reported);
+
+ state = vcpu_save_state(vm, VCPU_ID);
+ kvm_vm_release(vm);
+ kvm_vm_restart(vm, O_RDWR);
+ vm_vcpu_add(vm, VCPU_ID, 0, 0);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+ vcpu_load_state(vm, VCPU_ID, state);
+ run = vcpu_state(vm, VCPU_ID);
+ free(state);
+ }
+
+done:
+ kvm_vm_free(vm);
+}
struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
- if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
- fprintf(stderr, "immediate_exit not available, skipping test\n");
- exit(KSFT_SKIP);
- }
-
/* Create VM */
vm = vm_create_default(VCPU_ID, 0, guest_code);
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
stage, (ulong)uc.args[1]);
- /*
- * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
- * guest state is consistent only after userspace re-enters the
- * kernel with KVM_RUN. Complete IO prior to migrating state
- * to a new VM.
- */
- vcpu_run_complete_io(vm, VCPU_ID);
-
+ state = vcpu_save_state(vm, VCPU_ID);
memset(®s1, 0, sizeof(regs1));
vcpu_regs_get(vm, VCPU_ID, ®s1);
- state = vcpu_save_state(vm, VCPU_ID);
kvm_vm_release(vm);
/* Restore state in a new VM. */
nsuccess=$((nsuccess+1))
printf "\n TEST: %-50s [ OK ]\n" "${msg}"
else
+ ret=1
nfail=$((nfail+1))
printf "\n TEST: %-50s [FAIL]\n" "${msg}"
if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
fib_check_iproute_support "ipproto" "ipproto"
if [ $? -eq 0 ]; then
- match="ipproto icmp"
- fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match"
+ match="ipproto ipv6-icmp"
+ fib_rule6_test_match_n_redirect "$match" "$match" "ipproto ipv6-icmp match"
fi
}
run_fibrule_tests
cleanup
+if [ "$TESTS" != "none" ]; then
+ printf "\nTests passed: %3d\n" ${nsuccess}
+ printf "Tests failed: %3d\n" ${nfail}
+fi
+
exit $ret
return $rc
}
+check_expected()
+{
+ local out="$1"
+ local expected="$2"
+ local rc=0
+
+ [ "${out}" = "${expected}" ] && return 0
+
+ if [ -z "${out}" ]; then
+ if [ "$VERBOSE" = "1" ]; then
+ printf "\nNo route entry found\n"
+ printf "Expected:\n"
+ printf " ${expected}\n"
+ fi
+ return 1
+ fi
+
+ # tricky way to convert output to 1-line without ip's
+ # messy '\'; this drops all extra white space
+ out=$(echo ${out})
+ if [ "${out}" != "${expected}" ]; then
+ rc=1
+ if [ "${VERBOSE}" = "1" ]; then
+ printf " Unexpected route entry. Have:\n"
+ printf " ${out}\n"
+ printf " Expected:\n"
+ printf " ${expected}\n\n"
+ fi
+ fi
+
+ return $rc
+}
+
# add route for a prefix, flushing any existing routes first
# expected to be the first step of a test
add_route6()
pfx=$1
out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
- [ "${out}" = "${expected}" ] && return 0
-
- if [ -z "${out}" ]; then
- if [ "$VERBOSE" = "1" ]; then
- printf "\nNo route entry found\n"
- printf "Expected:\n"
- printf " ${expected}\n"
- fi
- return 1
- fi
-
- # tricky way to convert output to 1-line without ip's
- # messy '\'; this drops all extra white space
- out=$(echo ${out})
- if [ "${out}" != "${expected}" ]; then
- rc=1
- if [ "${VERBOSE}" = "1" ]; then
- printf " Unexpected route entry. Have:\n"
- printf " ${out}\n"
- printf " Expected:\n"
- printf " ${expected}\n\n"
- fi
- fi
-
- return $rc
+ check_expected "${out}" "${expected}"
}
route_cleanup()
ip -netns ns2 addr add 172.16.103.2/24 dev veth4
ip -netns ns2 addr add 172.16.104.1/24 dev dummy1
- set +ex
+ set +e
}
# assumption is that basic add of a single path route works
run_cmd "$IP li set dev dummy2 down"
rc=$?
if [ $rc -eq 0 ]; then
- check_route6 ""
+ out=$($IP -6 ro ls match 2001:db8:104::/64)
+ check_expected "${out}" ""
rc=$?
fi
log_test $rc 0 "Prefix route removed on link down"
local pfx
local expected="$1"
local out
- local rc=0
set -- $expected
pfx=$1
[ "${pfx}" = "unreachable" ] && pfx=$2
out=$($IP ro ls match ${pfx})
- [ "${out}" = "${expected}" ] && return 0
-
- if [ -z "${out}" ]; then
- if [ "$VERBOSE" = "1" ]; then
- printf "\nNo route entry found\n"
- printf "Expected:\n"
- printf " ${expected}\n"
- fi
- return 1
- fi
-
- # tricky way to convert output to 1-line without ip's
- # messy '\'; this drops all extra white space
- out=$(echo ${out})
- if [ "${out}" != "${expected}" ]; then
- rc=1
- if [ "${VERBOSE}" = "1" ]; then
- printf " Unexpected route entry. Have:\n"
- printf " ${out}\n"
- printf " Expected:\n"
- printf " ${expected}\n\n"
- fi
- fi
-
- return $rc
+ check_expected "${out}" "${expected}"
}
# assumption is that basic add of a single path route works
run_cmd "$IP li set dev dummy2 down"
rc=$?
if [ $rc -eq 0 ]; then
- check_route ""
+ out=$($IP ro ls match 172.16.104.0/24)
+ check_expected "${out}" ""
rc=$?
fi
log_test $rc 0 "Prefix route removed on link down"
exit 0
fi
+ret=0
echo "--------------------"
echo "running psock_fanout test"
echo "--------------------"
./in_netns.sh ./psock_fanout
if [ $? -ne 0 ]; then
echo "[FAIL]"
+ ret=1
else
echo "[PASS]"
fi
./in_netns.sh ./psock_tpacket
if [ $? -ne 0 ]; then
echo "[FAIL]"
+ ret=1
else
echo "[PASS]"
fi
./in_netns.sh ./txring_overwrite
if [ $? -ne 0 ]; then
echo "[FAIL]"
+ ret=1
else
echo "[PASS]"
fi
+exit $ret
./socket
if [ $? -ne 0 ]; then
echo "[FAIL]"
+ exit 1
else
echo "[PASS]"
fi
-
# SPDX-License-Identifier: GPL-2.0
# Makefile for netfilter selftests
-TEST_PROGS := nft_trans_stress.sh nft_nat.sh
+TEST_PROGS := nft_trans_stress.sh nft_nat.sh conntrack_icmp_related.sh
include ../lib.mk
--- /dev/null
+#!/bin/bash
+#
+# check that ICMP df-needed/pkttoobig icmp are set are set as related
+# state
+#
+# Setup is:
+#
+# nsclient1 -> nsrouter1 -> nsrouter2 -> nsclient2
+# MTU 1500, except for nsrouter2 <-> nsclient2 link (1280).
+# ping nsclient2 from nsclient1, checking that conntrack did set RELATED
+# 'fragmentation needed' icmp packet.
+#
+# In addition, nsrouter1 will perform IP masquerading, i.e. also
+# check the icmp errors are propagated to the correct host as per
+# nat of "established" icmp-echo "connection".
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without nft tool"
+ exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+cleanup() {
+ for i in 1 2;do ip netns del nsclient$i;done
+ for i in 1 2;do ip netns del nsrouter$i;done
+}
+
+ipv4() {
+ echo -n 192.168.$1.2
+}
+
+ipv6 () {
+ echo -n dead:$1::2
+}
+
+check_counter()
+{
+ ns=$1
+ name=$2
+ expect=$3
+ local lret=0
+
+ cnt=$(ip netns exec $ns nft list counter inet filter "$name" | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ echo "ERROR: counter $name in $ns has unexpected value (expected $expect)" 1>&2
+ ip netns exec $ns nft list counter inet filter "$name" 1>&2
+ lret=1
+ fi
+
+ return $lret
+}
+
+check_unknown()
+{
+ expect="packets 0 bytes 0"
+ for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do
+ check_counter $n "unknown" "$expect"
+ if [ $? -ne 0 ] ;then
+ return 1
+ fi
+ done
+
+ return 0
+}
+
+for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do
+ ip netns add $n
+ ip -net $n link set lo up
+done
+
+DEV=veth0
+ip link add $DEV netns nsclient1 type veth peer name eth1 netns nsrouter1
+DEV=veth0
+ip link add $DEV netns nsclient2 type veth peer name eth1 netns nsrouter2
+
+DEV=veth0
+ip link add $DEV netns nsrouter1 type veth peer name eth2 netns nsrouter2
+
+DEV=veth0
+for i in 1 2; do
+ ip -net nsclient$i link set $DEV up
+ ip -net nsclient$i addr add $(ipv4 $i)/24 dev $DEV
+ ip -net nsclient$i addr add $(ipv6 $i)/64 dev $DEV
+done
+
+ip -net nsrouter1 link set eth1 up
+ip -net nsrouter1 link set veth0 up
+
+ip -net nsrouter2 link set eth1 up
+ip -net nsrouter2 link set eth2 up
+
+ip -net nsclient1 route add default via 192.168.1.1
+ip -net nsclient1 -6 route add default via dead:1::1
+
+ip -net nsclient2 route add default via 192.168.2.1
+ip -net nsclient2 route add default via dead:2::1
+
+i=3
+ip -net nsrouter1 addr add 192.168.1.1/24 dev eth1
+ip -net nsrouter1 addr add 192.168.3.1/24 dev veth0
+ip -net nsrouter1 addr add dead:1::1/64 dev eth1
+ip -net nsrouter1 addr add dead:3::1/64 dev veth0
+ip -net nsrouter1 route add default via 192.168.3.10
+ip -net nsrouter1 -6 route add default via dead:3::10
+
+ip -net nsrouter2 addr add 192.168.2.1/24 dev eth1
+ip -net nsrouter2 addr add 192.168.3.10/24 dev eth2
+ip -net nsrouter2 addr add dead:2::1/64 dev eth1
+ip -net nsrouter2 addr add dead:3::10/64 dev eth2
+ip -net nsrouter2 route add default via 192.168.3.1
+ip -net nsrouter2 route add default via dead:3::1
+
+sleep 2
+for i in 4 6; do
+ ip netns exec nsrouter1 sysctl -q net.ipv$i.conf.all.forwarding=1
+ ip netns exec nsrouter2 sysctl -q net.ipv$i.conf.all.forwarding=1
+done
+
+for netns in nsrouter1 nsrouter2; do
+ip netns exec $netns nft -f - <<EOF
+table inet filter {
+ counter unknown { }
+ counter related { }
+ chain forward {
+ type filter hook forward priority 0; policy accept;
+ meta l4proto icmpv6 icmpv6 type "packet-too-big" ct state "related" counter name "related" accept
+ meta l4proto icmp icmp type "destination-unreachable" ct state "related" counter name "related" accept
+ meta l4proto { icmp, icmpv6 } ct state new,established accept
+ counter name "unknown" drop
+ }
+}
+EOF
+done
+
+ip netns exec nsclient1 nft -f - <<EOF
+table inet filter {
+ counter unknown { }
+ counter related { }
+ chain input {
+ type filter hook input priority 0; policy accept;
+ meta l4proto { icmp, icmpv6 } ct state established,untracked accept
+
+ meta l4proto { icmp, icmpv6 } ct state "related" counter name "related" accept
+ counter name "unknown" drop
+ }
+}
+EOF
+
+ip netns exec nsclient2 nft -f - <<EOF
+table inet filter {
+ counter unknown { }
+ counter new { }
+ counter established { }
+
+ chain input {
+ type filter hook input priority 0; policy accept;
+ meta l4proto { icmp, icmpv6 } ct state established,untracked accept
+
+ meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" accept
+ meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" accept
+ counter name "unknown" drop
+ }
+ chain output {
+ type filter hook output priority 0; policy accept;
+ meta l4proto { icmp, icmpv6 } ct state established,untracked accept
+
+ meta l4proto { icmp, icmpv6 } ct state "new" counter name "new"
+ meta l4proto { icmp, icmpv6 } ct state "established" counter name "established"
+ counter name "unknown" drop
+ }
+}
+EOF
+
+
+# make sure NAT core rewrites adress of icmp error if nat is used according to
+# conntrack nat information (icmp error will be directed at nsrouter1 address,
+# but it needs to be routed to nsclient1 address).
+ip netns exec nsrouter1 nft -f - <<EOF
+table ip nat {
+ chain postrouting {
+ type nat hook postrouting priority 0; policy accept;
+ ip protocol icmp oifname "veth0" counter masquerade
+ }
+}
+table ip6 nat {
+ chain postrouting {
+ type nat hook postrouting priority 0; policy accept;
+ ip6 nexthdr icmpv6 oifname "veth0" counter masquerade
+ }
+}
+EOF
+
+ip netns exec nsrouter2 ip link set eth1 mtu 1280
+ip netns exec nsclient2 ip link set veth0 mtu 1280
+sleep 1
+
+ip netns exec nsclient1 ping -c 1 -s 1000 -q -M do 192.168.2.2 >/dev/null
+if [ $? -ne 0 ]; then
+ echo "ERROR: netns ip routing/connectivity broken" 1>&2
+ cleanup
+ exit 1
+fi
+ip netns exec nsclient1 ping6 -q -c 1 -s 1000 dead:2::2 >/dev/null
+if [ $? -ne 0 ]; then
+ echo "ERROR: netns ipv6 routing/connectivity broken" 1>&2
+ cleanup
+ exit 1
+fi
+
+check_unknown
+if [ $? -ne 0 ]; then
+ ret=1
+fi
+
+expect="packets 0 bytes 0"
+for netns in nsrouter1 nsrouter2 nsclient1;do
+ check_counter "$netns" "related" "$expect"
+ if [ $? -ne 0 ]; then
+ ret=1
+ fi
+done
+
+expect="packets 2 bytes 2076"
+check_counter nsclient2 "new" "$expect"
+if [ $? -ne 0 ]; then
+ ret=1
+fi
+
+ip netns exec nsclient1 ping -q -c 1 -s 1300 -M do 192.168.2.2 > /dev/null
+if [ $? -eq 0 ]; then
+ echo "ERROR: ping should have failed with PMTU too big error" 1>&2
+ ret=1
+fi
+
+# nsrouter2 should have generated the icmp error, so
+# related counter should be 0 (its in forward).
+expect="packets 0 bytes 0"
+check_counter "nsrouter2" "related" "$expect"
+if [ $? -ne 0 ]; then
+ ret=1
+fi
+
+# but nsrouter1 should have seen it, same for nsclient1.
+expect="packets 1 bytes 576"
+for netns in nsrouter1 nsclient1;do
+ check_counter "$netns" "related" "$expect"
+ if [ $? -ne 0 ]; then
+ ret=1
+ fi
+done
+
+ip netns exec nsclient1 ping6 -c 1 -s 1300 dead:2::2 > /dev/null
+if [ $? -eq 0 ]; then
+ echo "ERROR: ping6 should have failed with PMTU too big error" 1>&2
+ ret=1
+fi
+
+expect="packets 2 bytes 1856"
+for netns in nsrouter1 nsclient1;do
+ check_counter "$netns" "related" "$expect"
+ if [ $? -ne 0 ]; then
+ ret=1
+ fi
+done
+
+if [ $ret -eq 0 ];then
+ echo "PASS: icmp mtu error had RELATED state"
+else
+ echo "ERROR: icmp error RELATED state test has failed"
+fi
+
+cleanup
+exit $ret
test_masquerade6()
{
+ local natflags=$1
local lret=0
ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
table ip6 nat {
chain postrouting {
type nat hook postrouting priority 0; policy accept;
- meta oif veth0 masquerade
+ meta oif veth0 masquerade $natflags
}
}
EOF
ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
if [ $? -ne 0 ] ; then
- echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading"
+ echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags"
lret=1
fi
fi
done
+ ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)"
+ lret=1
+ fi
+
ip netns exec ns0 nft flush chain ip6 nat postrouting
if [ $? -ne 0 ]; then
echo "ERROR: Could not flush ip6 nat postrouting" 1>&2
lret=1
fi
- test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2"
+ test $lret -eq 0 && echo "PASS: IPv6 masquerade $natflags for ns2"
return $lret
}
test_masquerade()
{
+ local natflags=$1
local lret=0
ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
if [ $? -ne 0 ] ; then
- echo "ERROR: canot ping ns1 from ns2"
+ echo "ERROR: cannot ping ns1 from ns2 $natflags"
lret=1
fi
table ip nat {
chain postrouting {
type nat hook postrouting priority 0; policy accept;
- meta oif veth0 masquerade
+ meta oif veth0 masquerade $natflags
}
}
EOF
ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
if [ $? -ne 0 ] ; then
- echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading"
+ echo "ERROR: cannot ping ns1 from ns2 with active ip masquere $natflags"
lret=1
fi
fi
done
+ ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)"
+ lret=1
+ fi
+
ip netns exec ns0 nft flush chain ip nat postrouting
if [ $? -ne 0 ]; then
echo "ERROR: Could not flush nat postrouting" 1>&2
lret=1
fi
- test $lret -eq 0 && echo "PASS: IP masquerade for ns2"
+ test $lret -eq 0 && echo "PASS: IP masquerade $natflags for ns2"
return $lret
}
test_local_dnat6
reset_counters
-test_masquerade
-test_masquerade6
+test_masquerade ""
+test_masquerade6 ""
+
+reset_counters
+test_masquerade "fully-random"
+test_masquerade6 "fully-random"
reset_counters
test_redirect
ph.p_offset = 0;
ph.p_vaddr = VADDR;
ph.p_paddr = 0;
- ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload);
- ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload);
+ ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len;
+ ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len;
ph.p_align = 4096;
fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_EXCL|O_TMPFILE, 0700);
int main(void)
{
- const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE);
-#ifdef __arm__
- unsigned long va = 2 * PAGE_SIZE;
-#else
- unsigned long va = 0;
-#endif
+ const int PAGE_SIZE = sysconf(_SC_PAGESIZE);
+ const unsigned long va_max = 1UL << 32;
+ unsigned long va;
void *p;
int fd;
unsigned long a, b;
if (fd == -1)
return 1;
- p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
- if (p == MAP_FAILED) {
- if (errno == EPERM)
- return 4;
+ for (va = 0; va < va_max; va += PAGE_SIZE) {
+ p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
+ if (p == (void *)va)
+ break;
+ }
+ if (va == va_max) {
+ fprintf(stderr, "error: mmap doesn't like you\n");
return 1;
}
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Extract the number of CPUs expected from the specified Kconfig-file
# fragment by checking CONFIG_SMP and CONFIG_NR_CPUS. If the specified
#
# Usage: configNR_CPUS.sh config-frag
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2013
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
cf=$1
if test ! -r $cf
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# config_override.sh base override
#
# that conflict with any in override, concatenating what remains and
# sending the result to standard output.
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2017
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
base=$1
if test -r $base
#!/bin/bash
-# Usage: configcheck.sh .config .config-template
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
+# SPDX-License-Identifier: GPL-2.0+
#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
+# Usage: configcheck.sh .config .config-template
#
# Copyright (C) IBM Corporation, 2011
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
T=${TMPDIR-/tmp}/abat-chk-config.sh.$$
trap 'rm -rf $T' 0
cat $1 > $T/.config
cat $2 | sed -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' |
+grep -v '^CONFIG_INITRAMFS_SOURCE' |
awk '
{
print "if grep -q \"" $0 "\" < '"$T/.config"'";
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Usage: configinit.sh config-spec-file build-output-dir results-dir
#
# for example, "O=/tmp/foo". If this argument is omitted, the .config
# file will be generated directly in the current directory.
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2013
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
T=${TMPDIR-/tmp}/configinit.sh.$$
trap 'rm -rf $T' 0
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Get an estimate of how CPU-hoggy to be.
#
# Usage: cpus2use.sh
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2013
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
idlecpus=`mpstat | tail -1 | \
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Shell functions for the rest of the scripts.
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2013
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
# bootparam_hotplug_cpu bootparam-string
#
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Alternate sleeping and spinning on randomly selected CPUs. The purpose
# of this script is to inflict random OS jitter on a concurrently running
# sleepmax: Maximum microseconds to sleep, defaults to one second.
# spinmax: Maximum microseconds to spin, defaults to one millisecond.
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2016
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
me=$(($1 * 1000))
duration=$2
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Build a kvm-ready Linux kernel from the tree in the current directory.
#
# Usage: kvm-build.sh config-template build-dir resdir
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2011
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
config_template=${1}
if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template"
#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
#
# Invoke a text editor on all console.log files for all runs with diagnostics,
# that is, on all such files having a console.log.diags counterpart.
#
# The "directory" above should end with the date/time directory, for example,
# "tools/testing/selftests/rcutorture/res/2018.02.25-14:27:27".
+#
+# Copyright (C) IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
rundir="${1}"
if test -z "$rundir" -o ! -d "$rundir"
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Analyze a given results directory for locktorture progress.
#
# Usage: kvm-recheck-lock.sh resdir
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2014
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
i="$1"
if test -d "$i" -a -r "$i"
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Analyze a given results directory for rcutorture progress.
#
# Usage: kvm-recheck-rcu.sh resdir
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2014
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
i="$1"
if test -d "$i" -a -r "$i"
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Analyze a given results directory for rcuperf performance measurements,
# looking for ftrace data. Exits with 0 if data was found, analyzed, and
#
# Usage: kvm-recheck-rcuperf-ftrace.sh resdir
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2016
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
i="$1"
. functions.sh
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Analyze a given results directory for rcuperf performance measurements.
#
# Usage: kvm-recheck-rcuperf.sh resdir
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2016
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
i="$1"
if test -d "$i" -a -r "$i"
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Given the results directories for previous KVM-based torture runs,
# check the build and console output for errors. Given a directory
#
# Usage: kvm-recheck.sh resdir ...
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2011
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
. functions.sh
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Run a kvm-based test of the specified tree on the specified configs.
# Fully automated run and error checking, no graphics console.
#
# More sophisticated argument parsing is clearly needed.
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2011
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
T=${TMPDIR-/tmp}/kvm-test-1-run.sh.$$
trap 'rm -rf $T' 0
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Run a series of tests under KVM. By default, this series is specified
# by the relevant CFLIST file, but can be overridden by the --configs
#
# Usage: kvm.sh [ options ]
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2011
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
scriptname=$0
args="$*"
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Create an initrd directory if one does not already exist.
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2013
#
# Author: Connor Shu <Connor.Shu@ibm.com>
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Check the build output from an rcutorture run for goodness.
# The "file" is a pathname on the local system, and "title" is
#
# Usage: parse-build.sh file title
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2011
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
F=$1
title=$2
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Check the console output from an rcutorture run for oopses.
# The "file" is a pathname on the local system, and "title" is
#
# Usage: parse-console.sh file title
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2011
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
T=${TMPDIR-/tmp}/parse-console.sh.$$
file="$1"
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Kernel-version-dependent shell functions for the rest of the scripts.
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2014
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
# locktorture_param_onoff bootparam-string config-file
#
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Kernel-version-dependent shell functions for the rest of the scripts.
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2013
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
# rcutorture_param_n_barrier_cbs bootparam-string
#
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
#
# Torture-suite-dependent shell functions for the rest of the scripts.
#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
# Copyright (C) IBM Corporation, 2015
#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
# per_version_boot_params bootparam-string config-file seconds
#
SECCOMP_FILTER_FLAG_LOG,
SECCOMP_FILTER_FLAG_SPEC_ALLOW,
SECCOMP_FILTER_FLAG_NEW_LISTENER };
- unsigned int flag, all_flags;
+ unsigned int exclusive[] = {
+ SECCOMP_FILTER_FLAG_TSYNC,
+ SECCOMP_FILTER_FLAG_NEW_LISTENER };
+ unsigned int flag, all_flags, exclusive_mask;
int i;
long ret;
- /* Test detection of known-good filter flags */
+ /* Test detection of individual known-good filter flags */
for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
int bits = 0;
all_flags |= flag;
}
- /* Test detection of all known-good filter flags */
- ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL);
- EXPECT_EQ(-1, ret);
- EXPECT_EQ(EFAULT, errno) {
- TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
- all_flags);
+ /*
+ * Test detection of all known-good filter flags combined. But
+ * for the exclusive flags we need to mask them out and try them
+ * individually for the "all flags" testing.
+ */
+ exclusive_mask = 0;
+ for (i = 0; i < ARRAY_SIZE(exclusive); i++)
+ exclusive_mask |= exclusive[i];
+ for (i = 0; i < ARRAY_SIZE(exclusive); i++) {
+ flag = all_flags & ~exclusive_mask;
+ flag |= exclusive[i];
+
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EFAULT, errno) {
+ TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
+ flag);
+ }
}
- /* Test detection of an unknown filter flag */
+ /* Test detection of an unknown filter flags, without exclusives. */
flag = -1;
+ flag &= ~exclusive_mask;
ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
EXPECT_EQ(-1, ret);
EXPECT_EQ(EINVAL, errno) {
{
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+ /*
+ * Update the timer output so that it is likely to match the
+ * state we're about to restore. If the timer expires between
+ * this point and the register restoration, we'll take the
+ * interrupt anyway.
+ */
+ kvm_timer_update_irq(vcpu, kvm_timer_should_fire(vtimer), vtimer);
+
/*
* When using a userspace irqchip with the architected timers and a
* host interrupt controller that doesn't support an active state, we
int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
{
struct arch_timer_context *timer;
- bool level;
switch (regid) {
case KVM_REG_ARM_TIMER_CTL:
return -1;
}
- level = kvm_timer_should_fire(timer);
- kvm_timer_update_irq(vcpu, level, timer);
- timer_emulate(timer);
-
return 0;
}
switch (treg) {
case TIMER_REG_TVAL:
- val = kvm_phys_timer_read() - timer->cntvoff - timer->cnt_cval;
+ val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff;
break;
case TIMER_REG_CTL:
{
switch (treg) {
case TIMER_REG_TVAL:
- timer->cnt_cval = val - kvm_phys_timer_read() - timer->cntvoff;
+ timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + val;
break;
case TIMER_REG_CTL:
static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
const struct kvm_vcpu_init *init)
{
- unsigned int i;
+ unsigned int i, ret;
int phys_target = kvm_target_cpu();
if (init->target != phys_target)
vcpu->arch.target = phys_target;
/* Now we know what it is, we can reset it. */
- return kvm_reset_vcpu(vcpu);
-}
+ ret = kvm_reset_vcpu(vcpu);
+ if (ret) {
+ vcpu->arch.target = -1;
+ bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
+ }
+ return ret;
+}
static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
struct kvm_vcpu_init *init)
* Only PMD_SIZE transparent hugepages(THP) are
* currently supported. This code will need to be
* updated to support other THP sizes.
+ *
+ * Make sure the host VA and the guest IPA are sufficiently
+ * aligned and that the block is contained within the memslot.
*/
- if (transparent_hugepage_adjust(&pfn, &fault_ipa))
+ if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
+ transparent_hugepage_adjust(&pfn, &fault_ipa))
vma_pagesize = PMD_SIZE;
}
vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS;
+ if (was_enabled && !vgic_cpu->lpis_enabled)
+ vgic_flush_pending_lpis(vcpu);
+
if (!was_enabled && vgic_cpu->lpis_enabled)
vgic_enable_lpis(vcpu);
}
kfree(irq);
}
+void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_irq *irq, *tmp;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags);
+
+ list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) {
+ if (irq->intid >= VGIC_MIN_LPI) {
+ raw_spin_lock(&irq->irq_lock);
+ list_del(&irq->ap_list);
+ irq->vcpu = NULL;
+ raw_spin_unlock(&irq->irq_lock);
+ vgic_put_irq(vcpu->kvm, irq);
+ }
+ }
+
+ raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags);
+}
+
void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending)
{
WARN_ON(irq_set_irqchip_state(irq->host_irq,
bool vgic_has_its(struct kvm *kvm);
int kvm_vgic_register_its_device(void);
void vgic_enable_lpis(struct kvm_vcpu *vcpu);
+void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu);
int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi);
int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr);
int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
{
struct kvm_kernel_irq_routing_entry *ei;
int r;
+ u32 gsi = array_index_nospec(ue->gsi, KVM_MAX_IRQ_ROUTES);
/*
* Do not allow GSI to be mapped to the same irqchip more than once.
* Allow only one to one mapping between GSI and non-irqchip routing.
*/
- hlist_for_each_entry(ei, &rt->map[ue->gsi], link)
+ hlist_for_each_entry(ei, &rt->map[gsi], link)
if (ei->type != KVM_IRQ_ROUTING_IRQCHIP ||
ue->type != KVM_IRQ_ROUTING_IRQCHIP ||
ue->u.irqchip.irqchip == ei->irqchip.irqchip)
return -EINVAL;
- e->gsi = ue->gsi;
+ e->gsi = gsi;
e->type = ue->type;
r = kvm_set_routing_entry(kvm, e, ue);
if (r)
if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
return -EINVAL;
- if ((log->first_page & 63) || (log->num_pages & 63))
+ if (log->first_page & 63)
return -EINVAL;
slots = __kvm_memslots(kvm, as_id);
n = kvm_dirty_bitmap_bytes(memslot);
if (log->first_page > memslot->npages ||
- log->num_pages > memslot->npages - log->first_page)
- return -EINVAL;
+ log->num_pages > memslot->npages - log->first_page ||
+ (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63)))
+ return -EINVAL;
*flush = false;
dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
struct kvm_device_ops *ops = NULL;
struct kvm_device *dev;
bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+ int type;
int ret;
if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
return -ENODEV;
- ops = kvm_device_ops_table[cd->type];
+ type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table));
+ ops = kvm_device_ops_table[type];
if (ops == NULL)
return -ENODEV;
dev->kvm = kvm;
mutex_lock(&kvm->lock);
- ret = ops->create(dev, cd->type);
+ ret = ops->create(dev, type);
if (ret < 0) {
mutex_unlock(&kvm->lock);
kfree(dev);
projects / linux.git / commitdiff