Ville Syrjälä [Thu, 7 Feb 2019 20:21:43 +0000 (22:21 +0200)]
drm/i915: Turn off pipe gamma when it's not needed
The pipe internal precision is higher than what we currently program to
the degamma/gamma LUTs. We can get a higher quality image by bypassing
the LUTs when they're not needed. Let's do that.
Each plane has its own control bit for this, so we have to update
all active planes. The way we've done this we don't actually have
to run through the whole .check_plane() thing. And we actually
do the .color_check() after .check_plane() so we couldn't even do
that without shuffling the code around.
Additionally on pre-skl we have to update the primary plane regardless
of whether it's active or not on account of the primary plane gamma
enable bit also affecting the pipe bottom color.
v2: Drop the '.' from patch title (Uma)
Fix 'primayr' typo (Uma,Matt)
Rebase
Ville Syrjälä [Thu, 7 Feb 2019 20:21:42 +0000 (22:21 +0200)]
drm/i915: Track pipe csc enable in crtc state
Just like we did for pipe gamma, let's also track the pipe csc
state. The hardware only exists on ILK+, and currently we always
enable it on hsw+ and never on any other platforms. Just like
with pipe gamma, the primary plane control register is used
for the readout on pre-SKL, and the pipe bottom color register
on SKL+.
v2: Rebase
v3: Allow fastboot with csc_enable changes (Maarten)
Deal with HAS_GMCH
Ville Syrjälä [Thu, 7 Feb 2019 20:39:13 +0000 (22:39 +0200)]
drm/i915: Track pipe gamma enable/disable in crtc state
Track whether pipe gamma is enabled or disabled. For now we
stick to the current behaviour of always enabling gamma. But
we do get working state readout for this now. On SKL+ we use
the pipe bottom color as our hardware state. On pre-SKL we
read the state back from the primary plane control register.
That only really correct for g4x+, as older platforms never
gamma correct pipe bottom color. But doing the readout the
same way on all platforms is fine, and there is no other way
to do it really.
v2: Initialize val at declaration (Uma)
Drop the bogus skl scaler comment change (Uma)
Rebase
v3: Allow fastboot with gamma_enable changes (Maarten)
v4: Drop the PIPE_BOTTOM_COLOR write from
intel_update_pipe_config() again. It snuck back in
during the rebase
Ville Syrjälä [Thu, 7 Feb 2019 20:21:40 +0000 (22:21 +0200)]
drm/i915: Populate gamma_mode for all platforms
On pre-HSW gamma mode is configured via PIPECONF. The bits are
the same except shifted up, so we can reuse just store them in
crtc_state->gamma_mode in the HSW+ way, allowing us to share
some code later.
v2: Allow fastboot with gamma_mode changes (Maarten)
Add space around the '<<' in the reg macro
Deal with HAS_GMCH
drm/i915/psr: Execute the default PSR code path when setting i915_edp_psr_debug
Changing the i915_edp_psr_debug was enabling, disabling or switching
PSR version by directly calling intel_psr_disable_locked() and
intel_psr_enable_locked(), what is not the default PSR path that will
be executed by real users.
So lets force a fastset in the PSR CRTC to trigger a pipe update and
stress the default code path.
Recently a bug was found when switching from PSR2 to PSR1 while
enable_psr kernel parameter was set to the default parameter, this
changes fix it and also fixes the bug linked bellow were DRRS was
left enabled together with PSR when enabling PSR from debugfs.
v2: Handling missing case: disabled to PSR1
v3: Not duplicating the whole atomic state(Maarten)
v4: Adding back the missing call to intel_psr_irq_control(Dhinakaran)
Ramalingam C [Mon, 4 Feb 2019 15:44:40 +0000 (21:14 +0530)]
drm/i915: HDCP state handling in ddi_update_pipe
The downgrade of the fullmodeset into fastset
intel_encoder->update_pipe, in possible scenario, skips the En/Dis-able
DDI. Hence breaks the HDCP state change handling.
We also don't have any hdcp tests in CI, because the shard runs don't
have hdcp capable outputs :-/
So this change fixs it by handling the HDCP state change request at
intel_encoder->update_pipe too along with enable and disable of the DDI.
Fixes: d19f958db23c ("drm/i915: Enable fastset for non-boot modesets.")
v2:
Added commit id that broke the HDCP [Daniel]
Ville Syrjälä [Tue, 5 Feb 2019 16:08:41 +0000 (18:08 +0200)]
drm/i915: Move LUT programming to happen after vblank waits
The LUTs are single buffered so we should program them after
the double buffered pipe updates have been latched by the
hardware.
We'll also fix up the IPS vs. split gamma w/a to do the IPS
disable like everyone else. Note that this is currently dead
code as we don't use the split gamma mode on HSW, but that
will be fixed up shortly.
Ville Syrjälä [Tue, 5 Feb 2019 16:08:40 +0000 (18:08 +0200)]
drm/i915: Split color mgmt based on single vs. double buffered registers
Split the color management hooks along the single vs. double
buffered registers line. Of the currently programmed registers
GAMMA_MODE and the ilk+ pipe CSC are double buffered, the
LUTS and CHV CGM block are single buffered.
The double buffered register will be programmed during the
normal pipe update with evasion, and also during pipe enable
so that the settings will already be correct when the pipe
starts up before the planes are enabled.
The single buffered registers are currently programmed before
the vblank evade. Which is totally wrong, but we'll correct
that later.
v2: Add some docs to explain the two vfuncs (Matt,Uma)
Rebase
Ville Syrjälä [Tue, 5 Feb 2019 16:08:39 +0000 (18:08 +0200)]
drm/i915: Pull GAMMA_MODE write out from haswell_load_luts()
For bdw+ let's move the GAMMA_MODE write for the legacy LUT
mode into the .load_luts() funciton directly, rather than
relying on haswell_load_luts(). We'll be getting rid of
haswell_load_luts() entirely soon, and it's anyway cleaner
to have the GAMMA_MODE write in a single place.
Ville Syrjälä [Tue, 5 Feb 2019 16:08:36 +0000 (18:08 +0200)]
drm/i915: Split the gamma/csc enable bits from the plane_ctl() function
On g4x+ the pipe gamma enable bit for the primary plane affects
the pipe bottom color as well. The same for the pipe csc enable
bit on ilk+. Thus we must configure those bits correctly even
when the primary plane is disabled.
To make the feasible let's split those settings from the
plane_ctl() function into a seprate funciton that we can
call from the ->disable_plane() hook as well.
For consistency we'll do that on all the plane types. While
that has no real benefits at this time, it'll become useful
when we start to control the pipe gamma/csc enable bits
dynamically when we overhaul the color management code.
On pre-g4x there doesn't appear to be any way to gamma
correct the pipe bottom color, but sticking to the same
pattern doesn't hurt. And it'll still help us to do
crtc state readout correctly for the pipe gamma enable
bit for the color management overhaul.
An alternative apporach would be to still precompute these
bits into plane_state->ctl, but that would require that we
run through the plane check even when the plane isn't logically
enabled on any crtc. Currently that condition causes us to
short circuit the entire thing and not call ->check_plane().
There would also be some chicken and egg problems with
->check_plane() vs. crtc color state check that would
requite splitting certain things into multiple steps.
So all in all this seems like the easier route.
Ville Syrjälä [Wed, 6 Feb 2019 18:54:33 +0000 (20:54 +0200)]
drm/i915: Don't set update_wm_post on g4x+
update_wm_post is meant for pre-g4x only. Don't ever set
it on g4x+.
The only effect of a bogus update_wm_post on g4x+ could
be that we clear the legacy_cursor_update flag in
intel_atomic_commit(). Since legacy_cursor_update is
only set for legacy cursor updates (as the name suggests)
and we only set update_wm_post for a modeset the two
cases should never occur at the same time. But let's
be consistent in setting update_wm_post so we don't
end up confusing so many people.
Chris Wilson [Thu, 7 Feb 2019 07:18:22 +0000 (07:18 +0000)]
drm/i915: Hack and slash, throttle execbuffer hogs
Apply backpressure to hogs that emit requests faster than the GPU can
process them by waiting for their ring to be less than half-full before
proceeding with taking the struct_mutex.
This is a gross hack to apply throttling backpressure, the long term
goal is to remove the struct_mutex contention so that each client
naturally waits, preferably in an asynchronous, nonblocking fashion
(pipelined operations for the win), for their own resources and never
blocks another client within the driver at least. (Realtime priority
goals would extend to ensuring that resource contention favours high
priority clients as well.)
This patch only limits excessive request production and does not attempt
to throttle clients that block waiting for eviction (either global GTT or
system memory) or any other global resources, see above for the long term
goal.
No microbenchmarks are harmed (to the best of my knowledge).
Testcase: igt/gem_exec_schedule/pi-ringfull-* Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: John Harrison <John.C.Harrison@Intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190207071829.5574-1-chris@chris-wilson.co.uk
Lyude Paul [Tue, 29 Jan 2019 19:10:01 +0000 (14:10 -0500)]
drm/i915: Don't send hotplug in intel_dp_check_mst_status()
This hotplug also isn't needed: drm_dp_mst_topology_mgr_set_mst()
already sends a hotplug on its own from drm_dp_destroy_connector_work()
after destroying connectors in the MST topology.
Lyude Paul [Tue, 29 Jan 2019 19:10:00 +0000 (14:10 -0500)]
drm/i915: Don't send MST hotplugs during resume
We have a bad habit of calling drm_fb_helper_hotplug_event() far more
then we actually need to. MST appears to be one of these cases, where we
call drm_fb_helper_hotplug_event() if we fail to resume a connected MST
topology in intel_dp_mst_resume(). We don't actually need to do this at
all though since hotplug events are already sent from
drm_dp_connector_destroy_work() every time connectors are unregistered
from userspace's PoV. Additionally, extra calls to
drm_fb_helper_hotplug_event() also just mean more of a chance of doing a
connector probe somewhere we shouldn't.
So, don't send any hotplug events during resume if the MST topology
fails to come up. Just rely on the DP MST helpers to send them for us.
Lyude Paul [Tue, 29 Jan 2019 19:09:59 +0000 (14:09 -0500)]
drm/i915: Block fbdev HPD processing during suspend
When resuming, we check whether or not any previously connected
MST topologies are still present and if so, attempt to resume them. If
this fails, we disable said MST topologies and fire off a hotplug event
so that userspace knows to reprobe.
However, sending a hotplug event involves calling
drm_fb_helper_hotplug_event(), which in turn results in fbcon doing a
connector reprobe in the caller's thread - something we can't do at the
point in which i915 calls drm_dp_mst_topology_mgr_resume() since
hotplugging hasn't been fully initialized yet.
This currently causes some rather subtle but fatal issues. For example,
on my T480s the laptop dock connected to it usually disappears during a
suspend cycle, and comes back up a short while after the system has been
resumed. This guarantees pretty much every suspend and resume cycle,
drm_dp_mst_topology_mgr_set_mst(mgr, false); will be caused and in turn,
a connector hotplug will occur. Now it's Rute Goldberg time: when the
connector hotplug occurs, i915 reprobes /all/ of the connectors,
including eDP. However, eDP probing requires that we power on the panel
VDD which in turn, grabs a wakeref to the appropriate power domain on
the GPU (on my T480s, this is the PORT_DDI_A_IO domain). This is where
things start breaking, since this all happens before
intel_power_domains_enable() is called we end up leaking the wakeref
that was acquired and never releasing it later. Come next suspend/resume
cycle, this causes us to fail to shut down the GPU properly, which
causes it not to resume properly and die a horrible complicated death.
(as a note: this only happens when there's both an eDP panel and MST
topology connected which is removed mid-suspend. One or the other seems
to always be OK).
We could try to fix the VDD wakeref leak, but this doesn't seem like
it's worth it at all since we aren't able to handle hotplug detection
while resuming anyway. So, let's go with a more robust solution inspired
by nouveau: block fbdev from handling hotplug events until we resume
fbdev. This allows us to still send sysfs hotplug events to be handled
later by user space while we're resuming, while also preventing us from
actually processing any hotplug events we receive until it's safe.
This fixes the wakeref leak observed on the T480s and as such, also
fixes suspend/resume with MST topologies connected on this machine.
Changes since v2:
* Don't call drm_fb_helper_hotplug_event() under lock, do it after lock
(Chris Wilson)
* Don't call drm_fb_helper_hotplug_event() in
intel_fbdev_output_poll_changed() under lock (Chris Wilson)
* Always set ifbdev->hpd_waiting (Chris Wilson)
Signed-off-by: Lyude Paul <lyude@redhat.com> Fixes: 0e32b39ceed6 ("drm/i915: add DP 1.2 MST support (v0.7)") Cc: Todd Previte <tprevite@gmail.com> Cc: Dave Airlie <airlied@redhat.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Imre Deak <imre.deak@intel.com> Cc: intel-gfx@lists.freedesktop.org Cc: <stable@vger.kernel.org> # v3.17+ Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Link: https://patchwork.freedesktop.org/patch/msgid/20190129191001.442-2-lyude@redhat.com
Ville Syrjälä [Tue, 5 Feb 2019 20:50:55 +0000 (22:50 +0200)]
drm/i915: Bump skl+ wm blocks to 11 bits
On icl the plane watermark blocks field is 11 bits. Bump our define to
match so that readout won't ignore the extra bit. We can safely do this
for older platforms too since the unused bits are hardwired to zero.
Tvrtko Ursulin [Tue, 5 Feb 2019 13:03:53 +0000 (13:03 +0000)]
drm/i915/pmu: Fix enable count array size and bounds checking
Enable count array is supposed to have one counter for each possible
engine sampler. As such, array sizing and bounds checking is not correct
and would blow up the asserts if more samplers were added.
No ill-effect in the current code base but lets fix it for correctness.
At the same time tidy the assert for readability and robustness.
Ville Syrjälä [Mon, 4 Feb 2019 20:22:32 +0000 (22:22 +0200)]
drm/i915: W/A for underruns with WM1+ disabled on icl
Disabling WM1+ on ICL causes tons of underruns with
linear/X-tiled framebuffers. We can avoid this by flipping
on a chicken bit affecting the way the hw fill the FIFO.
This may not be the final solution but should hopefully
avoid some underruns in the meantime.
Ville Syrjälä [Tue, 5 Feb 2019 15:50:53 +0000 (17:50 +0200)]
drm/i915: Fix wm latency==0 disable on skl+
When adding the early latency==0 check back I neglected to
realize that we no longer have a way to return a failure
from the wm computation like we had in the past (since we
now calculate wms before ddb allocations). Also plane_en
being false doesn't actually indicate that the level is
invalid as it wil also happen when the plane is not
enabled.
skl_allocate_pipe_ddb() starts scanning from the maximum
watermark level and it stops as soon as it finds a level
that is deemed viable. The assumption being that if level
n+1 is valid then level n is valid as well. Thus if we
now disable any watermark level by zeroing its latency
the code will think that level to be actually valid
and won't confirm whether the actually enabled lower
watermark level(s) actually fit into the allotted ddb
space. This results in hilarious watermark values that
exceed the ddb allocation of the plane.
The way we must now indicate a failure is to assign an
unreasoanbly big value to min_ddb_alloc which will then
make skl_allocate_pipe_ddb() reject the entire level.
v2: Also do the same for the lines>31 case (Matt)
v3: Make 'blocks' u32 (Matt)
Chris Wilson [Tue, 5 Feb 2019 09:27:59 +0000 (09:27 +0000)]
drm/i915: Push clear_intel_crtc_state() onto the heap
clear_intel_crtc_state() uses the stack for saving a temporary copy of
certain bits of the inherited crtc_state before clearing the unwanted
bits. This pushes it over the stack limit for my little 32b Pineview,
so move the temporary allocation to the heap instead. As we now use a
zeroed struct, we can copy the whole extended state back to both
preserve what bits need to be preserved and zero the rest.
Ville Syrjälä [Mon, 4 Feb 2019 21:16:44 +0000 (23:16 +0200)]
drm/i915: Include register polling in reg_rw traces
We generally omit register polling from the i915_reg_rw tracepoint.
Understandable since polling could generate a lot of noise in the
trace. The downside is that the trace is incomplete. As a compromise
let's trace the final register value observed while polling. That
should be generally sufficient to observe what the code should be
doing next.
I suppose in some cases it might make sense to also trace the initial
register value, and maybe the number of times we polled. But that
would require a separate tracepoint so let's leave it for the future.
The other users of _NOTRACE() are i915_pmu and i2c bitbanging,
which I decided to leave alone.
Next we should do something to claw back the tracepoints for
planes and whatnot which were switched to _FW() a while back.
I guess just new macros for raw_rw+trace. The question is
what to call it?
drm/i915: do not return invalid pointers as a *dentry
When calling debugfs functions, they can now return error values if
something went wrong. If that happens, return a NULL as a *dentry to
the relay core instead of passing it an illegal pointer.
The relay core should be able to handle an illegal pointer, but add this
check to be safe.
Rodrigo Vivi [Mon, 4 Feb 2019 22:25:38 +0000 (14:25 -0800)]
drm/i915: Rename HAS_GMCH
First of all GMCH can be considered a feature by itself
since it is a chip present in some platforms that connects
the IA processor to memory and other components in PC.
Also with the introduction of display block at device info,
we got a redundant definition:
.display.has_gmch_display = 1,
So, let's clean up things a bit and use the standardized
way of has_feature on displays side.
No functional change and no manual interaction to generate
this patch.
It is only:
sed -si -e 's/has_gmch_display/has_gmch/g' \
-e 's/HAS_GMCH_DISPLAY/HAS_GMCH/g' drivers/gpu/drm/i915/*{c,h}
Chris Wilson [Tue, 5 Feb 2019 13:00:05 +0000 (13:00 +0000)]
drm/i915: Pull i915_gem_active into the i915_active family
Looking forward, we need to break the struct_mutex dependency on
i915_gem_active. In the meantime, external use of i915_gem_active is
quite beguiling, little do new users suspect that it implies a barrier
as each request it tracks must be ordered wrt the previous one. As one
of many, it can be used to track activity across multiple timelines, a
shared fence, which fits our unordered request submission much better. We
need to steer external users away from the singular, exclusive fence
imposed by i915_gem_active to i915_active instead. As part of that
process, we move i915_gem_active out of i915_request.c into
i915_active.c to start separating the two concepts, and rename it to
i915_active_request (both to tie it to the concept of tracking just one
request, and to give it a longer, less appealing name).
Chris Wilson [Tue, 5 Feb 2019 13:00:03 +0000 (13:00 +0000)]
drm/i915: Release the active tracker tree upon idling
As soon as we detect that the active tracker is idle and we prepare to
call the retire callback, release the storage for our tree of
per-timeline nodes. We expect these to be infrequently used and quick
to allocate, so there is little benefit in keeping the tree cached and
we would prefer to return the pages back to the system in a timely
fashion.
This also means that when we finalize the struct as a whole, we know as
the activity tracker must be idle, the tree has already been released.
Indeed we can reduce i915_active_fini() just to the assertions that there
is nothing to do.
Chris Wilson [Tue, 5 Feb 2019 13:00:02 +0000 (13:00 +0000)]
drm/i915: Generalise GPU activity tracking
We currently track GPU memory usage inside VMA, such that we never
release memory used by the GPU until after it has finished accessing it.
However, we may want to track other resources aside from VMA, or we may
want to split a VMA into multiple independent regions and track each
separately. For this purpose, generalise our request tracking (akin to
struct reservation_object) so that we can embed it into other objects.
Tvrtko Ursulin [Tue, 5 Feb 2019 09:50:31 +0000 (09:50 +0000)]
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only)
We want to allow userspace to reconfigure the subslice configuration on a
per context basis.
This is required for the functional requirement of shutting down non-VME
enabled sub-slices on Gen11 parts.
To do so, we expose a context parameter to allow adjustment of the RPCS
register stored within the context image (and currently not accessible via
LRI).
If the context is adjusted before first use or whilst idle, the adjustment
is for "free"; otherwise if the context is active we queue a request to do
so (using the kernel context), following all other activity by that
context, which is also marked as barrier for all following submission
against the same context.
Since the overhead of device re-configuration during context switching can
be significant, especially in multi-context workloads, we limit this new
uAPI to only support the Gen11 VME use case. In this use case either the
device is fully enabled, and exactly one slice and half of the subslices
are enabled.
/* Set VME configuration on a 1x6x8 part. */
sseu.slice_mask = 0x1;
sseu.subslice_mask = 0xe0;
gem_context_set_param(fd, &arg);
v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu()
(Lionel)
v3: Add ability to program this per engine (Chris)
v4: Move most get_sseu() into i915_gem_context.c (Lionel)
v5: Validate sseu configuration against the device's capabilities (Lionel)
v6: Change context powergating settings through MI_SDM on kernel context
(Chris)
v7: Synchronize the requests following a powergating setting change using
a global dependency (Chris)
Iterate timelines through dev_priv.gt.active_rings (Tvrtko)
Disable RPCS configuration setting for non capable users
(Lionel/Tvrtko)
v8: s/union intel_sseu/struct intel_sseu/ (Lionel)
s/dev_priv/i915/ (Tvrtko)
Change uapi class/instance fields to u16 (Tvrtko)
Bump mask fields to 64bits (Lionel)
Don't return EPERM when dynamic sseu is disabled (Tvrtko)
v9: Import context image into kernel context's ppgtt only when
reconfiguring powergated slice/subslices (Chris)
Use aliasing ppgtt when needed (Michel)
Tvrtko Ursulin:
v10:
* Update for upstream changes.
* Request submit needs a RPM reference.
* Reject on !FULL_PPGTT for simplicity.
* Pull out get/set param to helpers for readability and less indent.
* Use i915_request_await_dma_fence in add_global_barrier to skip waits
on the same timeline and avoid GEM_BUG_ON.
* No need to explicitly assign a NULL pointer to engine in legacy mode.
* No need to move gen8_make_rpcs up.
* Factored out global barrier as prep patch.
* Allow to only CAP_SYS_ADMIN if !Gen11.
v11:
* Remove engine vfunc in favour of local helper. (Chris Wilson)
* Stop retiring requests before updates since it is not needed
(Chris Wilson)
* Implement direct CPU update path for idle contexts. (Chris Wilson)
* Left side dependency needs only be on the same context timeline.
(Chris Wilson)
* It is sufficient to order the timeline. (Chris Wilson)
* Reject !RCS configuration attempts with -ENODEV for now.
v12:
* Rebase for make_rpcs.
v13:
* Centralize SSEU normalization to make_rpcs.
* Type width checking (uAPI <-> implementation).
* Gen11 restrictions uAPI checks.
* Gen11 subslice count differences handling.
Chris Wilson:
* args->size handling fixes.
* Update context image from GGTT.
* Postpone context image update to pinning.
* Use i915_gem_active_raw instead of last_request_on_engine.
v14:
* Add activity tracker on intel_context to fix the lifetime issues
and simplify the code. (Chris Wilson)
v15:
* Fix context pin leak if no space in ring by simplifying the
context pinning sequence.
v16:
* Rebase for context get/set param locking changes.
* Just -ENODEV on !Gen11. (Joonas)
v17:
* Fix one Gen11 subslice enablement rule.
* Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson)
v18:
* Update commit message. (Joonas)
* Restrict uAPI to VME use case. (Joonas)
v19:
* Rebase.
v20:
* Rebase for ce->active_tracker.
v21:
* Rebase for IS_GEN changes.
v22:
* Reserve uAPI for flags straight away. (Chris Wilson)
v23:
* Rebase for RUNTIME_INFO.
v24:
* Added some headline docs for the uapi usage. (Joonas/Chris)
v25:
* Renamed class/instance to engine_class/engine_instance to avoid clash
with C++ keyword. (Tony Ye)
v26:
* Rebased for runtime pm api changes.
v27:
* Rebased for intel_context_init.
* Wrap commit msg to 75.
v28:
(Chris Wilson)
* Use i915_gem_ggtt.
* Use i915_request_await_dma_fence to show a better example.
v29:
* i915_timeline_set_barrier can now fail. (Chris Wilson)
v30:
* Capture some acks.
v31:
* Drop the WARN_ON from use controllable paths. (Chris Wilson)
* Use overflows_type for all checks.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634
Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
Tvrtko Ursulin [Tue, 5 Feb 2019 09:50:30 +0000 (09:50 +0000)]
drm/i915: Add timeline barrier support
Timeline barrier allows serialization between different timelines.
After calling i915_timeline_set_barrier with a request, all following
submissions on this timeline will be set up as depending on this request,
or barrier. Once the barrier has been completed it automatically gets
cleared and things continue as normal.
This facility will be used by the upcoming context SSEU code.
v2:
* Assert barrier has been retired on timeline_fini. (Chris Wilson)
* Fix mock_timeline.
v3:
* Improved comment language. (Chris Wilson)
v4:
* Maintain ordering with previous barriers set on the timeline.
drm/i915/perf: lock powergating configuration to default when active
If some of the contexts submitting workloads to the GPU have been
configured to shutdown slices/subslices, we might loose the NOA
configurations written in the NOA muxes.
One possible solution to this problem is to reprogram the NOA muxes
when we switch to a new context. We initially tried this in the
workaround batchbuffer but some concerns where raised about the cost
of reprogramming at every context switch. This solution is also not
without consequences from the userspace point of view. Reprogramming
of the muxes can only happen once the powergating configuration has
changed (which happens after context switch). This means for a window
of time during the recording, counters recorded by the OA unit might
be invalid. This requires userspace dealing with OA reports to discard
the invalid values.
Minimizing the reprogramming could be implemented by tracking of the
last programmed configuration somewhere in GGTT and use MI_PREDICATE
to discard some of the programming commands, but the command streamer
would still have to parse all the MI_LRI instructions in the
workaround batchbuffer.
Another solution, which this change implements, is to simply disregard
the user requested configuration for the period of time when i915/perf
is active.
On most platforms there are no issues with this apart from a performance
penality for some media workloads that benefit from running on a partially
powergated GPU. We already prevent RC6 from affecting the programming so
it doesn't sound completely unreasonable to hold on powergating for the
same reason.
On Icelake however there would a functional problem if the slices not-
containing the VME block were left enabled with a running media workload
which explicitly disabled them. To avoid a GPU hang in this case, on
Icelake we lock the enablement to only slices which contain VME blocks.
Downside is that it means degraded GPU performance when OA is active but
there is no known alternative solution for this.
v2: Leave RPCS programming in intel_lrc.c (Lionel)
v3: Update for s/union intel_sseu/struct intel_sseu/ (Lionel)
More to_intel_context() (Tvrtko)
s/dev_priv/i915/ (Tvrtko)
Tvrtko Ursulin:
v4:
* Rebase for make_rpcs changes.
v5:
* Apply OA restriction from make_rpcs directly.
v6:
* Rebase for context image setup changes.
v7:
* Move stream assignment before metric enable.
drm/i915: Record the sseu configuration per-context & engine
We want to expose the ability to reconfigure the slices, subslice and
eu per context and per engine. To facilitate that, store the current
configuration on the context for each engine, which is initially set
to the device default upon creation.
v2: record sseu configuration per context & engine (Chris)
v3: introduce the i915_gem_context_sseu to store powergating
programming, sseu_dev_info has grown quite a bit (Lionel)
v4: rename i915_gem_sseu into intel_sseu (Chris)
use to_intel_context() (Chris)
v5: More to_intel_context() (Tvrtko)
Switch intel_sseu from union to struct (Tvrtko)
Move context default sseu in existing loop (Chris)
Chris Wilson [Mon, 4 Feb 2019 15:01:01 +0000 (15:01 +0000)]
drm/i915: Trim NEWCLIENT boosting
Limit the NEWCLIENT boost to only give its small priority boost to fresh
clients only that have no dependencies.
The idea for using NEWCLIENT boosting, commit b16c765122f9 ("drm/i915:
Priority boost for new clients"), is that short-lived streams are often
interactive and require lower latency -- and that by executing those
ahead of the long running hogs, the short-lived clients do little to
interfere with the system throughput by virtue of their short-lived
nature. However, we were only considering the client's own timeline for
determining whether or not it was a fresh stream. This allowed for
compositors to wake up before their vblank and bump all of its client
streams. However, in testing with media-bench this results in chaining
all cooperating contexts together preventing us from being able to
reorder contexts to reduce bubbles (pipeline stalls), overall increasing
latency, and reducing system throughput. The exact opposite of our
intent. The compromise of applying the NEWCLIENT boost to strictly fresh
clients (that do not wait upon anything else) should maintain the
"real-time response under load" characteristics of FQ_CODEL, without
locking together the long chains of dependencies across the system.
Chris Wilson [Mon, 4 Feb 2019 08:41:05 +0000 (08:41 +0000)]
drm/i915: Allow normal clients to always preempt idle priority clients
When first enabling preemption, we hesitated from making it a free-for-all
where every higher priority client would force a preempt-to-idle cycle
and take over from all lower priority clients. We hesitated because we
were uncertain just how well preemption would work in practice, whether
the preemption latency itself would detract from the latency gains for
higher priority tasks and whether it would work at all. Since
introducing preemption, we have been enabling it for more common tasks,
even giving normal clients a small preemptive boost when they first
start (to aide fairness and improve interactivity). Now lets take one
step further and give permission for all normal (priority:0) clients to
preempt any idle (priority:<0) task so that users running long compute
jobs do not overly impact other jobs (i.e. their desktop) and the system
remains responsive under such idle loads.
References: f6322eddaff7 ("drm/i915/preemption: Allow preemption between submission ports")
References: b16c765122f9 ("drm/i915: Priority boost for new clients") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Michal Wajdeczko <michal.wajdeczko@intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: "Bloomfield, Jon" <jon.bloomfield@intel.com> Cc: "Stead, Alan" <alan.stead@intel.com> Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190204084116.3013-1-chris@chris-wilson.co.uk
Hans de Goede [Tue, 29 Jan 2019 14:22:37 +0000 (15:22 +0100)]
drm/i915: Enable fastboot by default on VLV and CHV
We really want to have fastboot enabled by default to avoid an ugly
modeset during boot.
Currently we are enabling fastboot by default on gen9+ (Skylake and newer).
The intention is to enable it on older generations after it has seen more
testing on gen9+.
VLV and CHV devices are still being sold in stores today, as such it is
desirable to also enable fastboot by default on these now.
I've extensively tested fastboot=1 support on over 50 different
Bay- and Cherry-Trail devices. Testing DSI and eDP panels as well as
HDMI output (and even DP over Type-C on one device).
All 50 devices work fine with fastboot=1. On 2 devices their DSI panel
turns black as soon as the i915 driver loads when fastboot=0, so having
fastboot enabled is required for these 2 to work properly (for lack of
a better fix).
This restores the workaround that was reverted in c358514ba8da
("Revert "drm/i915/icl: WaEnableFloatBlendOptimization"").
The revert was due to the register write seemingly not sticking,
but the HW team has confirmed that this is because the
register is WO and that the workaround is indeed required.
Here the wa is added with a mask of 0 since the register is WO.
References: https://hsdes.intel.com/resource/1408134172
References: https://bugs.freedesktop.org/show_bug.cgi?id=107338 Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Signed-off-by: Talha Nassar <talha.nassar@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Link: https://patchwork.freedesktop.org/patch/msgid/1548983324-15344-4-git-send-email-talha.nassar@intel.com
Tvrtko Ursulin [Fri, 1 Feb 2019 01:08:42 +0000 (17:08 -0800)]
drm/i915: Move workaround infrastructure code up
Top comment in intel_workarounds.c says common code should come first so
lets respect that. Also, by moving the common code together opportunities
to reduce duplication will become more obvious.
Imre Deak [Mon, 28 Jan 2019 11:42:42 +0000 (13:42 +0200)]
drm/i915/icl: Add TypeC ports only if VBT is present
We can't safely probe Type C ports, whether they are a legacy or a
USB/Thunderbolt DP Alternate Type C port. This would require performing
the TypeC connect sequence - as described by the specification - but
that may have unwanted side-effects. These side-effects include at least
- without completeness - timeouts during AUX power well enabling and
subsequent PLL enabling errors.
To safely identify these ports we really need VBT, which has the proper
flag for this (ddi_vbt_port_info::supports_typec_usb, supports_tbt).
Based on the above disable Type C ports if we can't load VBT for some
reason.
v2:
- Notice that we disable TypeC ports completely and simplify accordingly
(Jose).
- Add code comment explaining why we disabled the ports. (Jani)
Cc: Jani Nikula <jani.nikula@intel.com> Cc: Paulo Zanoni <paulo.r.zanoni@intel.com> Cc: Jose Roberto de Souza <jose.souza@intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Imre Deak <imre.deak@intel.com> Reviewed-by: José Roberto de Souza <jose.souza@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190128114242.28666-1-imre.deak@intel.com
Ville Syrjälä [Wed, 30 Jan 2019 18:13:59 +0000 (20:13 +0200)]
drm/i915: Pick the first unused PLL once again
commit 5b0bd14dcc6b ("drm/i915/icl: keep track of unused pll while
looping") inadvertently (I presume) changed the code to pick the
last unused dpll rather than the first unused one like we did before.
While there should most likely be no harm in changing the order
let's change back just to avoid a change in the behaviour. At
least it might reduce the confusion when staring at logs (took
me a while to figure out why DPLL1 being picked over DPLL0
when the latter was most definitely available).
Matt Roper [Wed, 30 Jan 2019 18:10:22 +0000 (10:10 -0800)]
drm/i915: Apply LUT validation checks to platforms more accurately (v3)
Use of the new DRM_COLOR_LUT_NON_DECREASING test was a bit over-zealous;
it doesn't actually need to be applied to the degamma on "bdw-style"
platforms. Likewise, we overlooked the fact that CHV should have that
test applied to the gamma LUT as well as the degamma LUT.
Rather than adding more complicated platform checking to
intel_color_check(), let's just store the appropriate set of LUT
validation flags for each platform in the intel_device_info structure.
v2:
- Shuffle around LUT size tests so that the hardware-specific tests
won't be applied to legacy gamma tables. (Ville)
- Add a debug message so that it will be easier to understand why an
atomic transaction involving incorrectly-sized LUT's got rejected
by the driver.
v3:
- Switch size_t's to int's. (Ville)
Fixes: 85e2d61e4976 ("drm/i915: Validate userspace-provided color management LUT's (v4)")
References: https://lists.freedesktop.org/archives/intel-gfx/2019-January/187634.html Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Signed-off-by: Matt Roper <matthew.d.roper@intel.com> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190130181022.4291-1-matthew.d.roper@intel.com
Matt Roper [Wed, 30 Jan 2019 18:51:20 +0000 (10:51 -0800)]
drm/i915: Force background color to black for gen9+ (v2)
We don't yet allow userspace to control the CRTC background color, but
we should manually program the color to black to ensure the BIOS didn't
leave us with some other color. We should also set the pipe gamma and
pipe CSC bits so that the background color goes through the same color
management transformations that a plane with black pixels would.
v2: Rename register to SKL_BOTTOM_COLOR to more closely follow
bspec naming. (Ville)
Ville Syrjälä [Fri, 21 Dec 2018 17:14:34 +0000 (19:14 +0200)]
drm/i915: Drop the definite article in front of SAGV
The spec doesn't use a definite article in front of SAGV. The
rules regarding articles and initialisms are super fuzzy, but
at least to my ears it sounds much more natural to not have
the article. Perhaps because I tend to pronounce it as
"sag-vee" instead of spelling out the letters one at a time.
Actually I might still prefer to leave out the article if I
did spell them out.
Ville Syrjälä [Fri, 21 Dec 2018 17:14:33 +0000 (19:14 +0200)]
drm/i915: Pass dev_priv to skl_needs_memory_bw_wa()
skl_needs_memory_bw_wa() doesn't look at the passed in state at all.
Possibly it should, but for now let's make life simpler by just
passing in dev_priv.
Ville Syrjälä [Fri, 21 Dec 2018 17:14:32 +0000 (19:14 +0200)]
drm/i915: Account for minimum ddb allocation restrictions
On icl+ bspec tells us to calculate a separate minimum ddb
allocation from the blocks watermark. Both have to be checked
against the actual ddb allocation, but since we do things the
other way around we'll just calculat the minimum acceptable
ddb allocation by taking the maximum of the two values.
We'll also replace the memcmp() with a full trawl over the
the watermarks so that it'll ignore the min_ddb_alloc
because we can't directly read that out from the hw. I suppose
we could reconstruct it from the other values, but I was
too lazy to do that now.
Ville Syrjälä [Fri, 21 Dec 2018 17:14:31 +0000 (19:14 +0200)]
drm/i915: Fix > vs >= mismatch in watermark/ddb calculations
Bspec says we have to reject the watermark if it's >= the ddb
allocation. Fix the code to reject the == case as it should.
For transition watermarks we can just use >=, for the rest
we'll do +1 when calculating the minimum ddb allocation size.
Ville Syrjälä [Fri, 21 Dec 2018 17:14:30 +0000 (19:14 +0200)]
drm/i915: Fix bits vs. bytes mixup in dbuf block size computation
The spec used to say "8bpp" which someone took to mean 8 bytes per
pixel when in fact it was supposed to be 8 bits per pixel. The
spec has been updated to make it more clear now. Fix the code
to match.
Ville Syrjälä [Fri, 21 Dec 2018 17:14:29 +0000 (19:14 +0200)]
drm/i915: Reinstate an early latency==0 check for skl+
I thought we could remove all the early latency==0 checks
and rely on skl_wm_method{1,2}() checking for it. But
skl_compute_plane_wm() applies a bunch of workarounds to bump
up the latency before calling those guys so clearly it won't
end up doing the right thing. Also not sure if the calculations
based on the method1/2 results are safe agaisnt overflows so
it might not work all that well in any case. Let's put the
early check back.
Ville Syrjälä [Fri, 21 Dec 2018 17:14:28 +0000 (19:14 +0200)]
drm/i915: Don't ignore level 0 lines watermark for glk+
On glk+ the level 0 lines watermark actually matters. Do not ignore it.
And while at it let's change things so that we always program a
consistnet 0 to the register when the lines watermarks is ignored
by the hardware.
Lucas De Marchi [Fri, 25 Jan 2019 22:24:43 +0000 (14:24 -0800)]
drm/i915/icl: remove dpll from clk_sel
We should not pass DPLL_ID_ICL_DPLL0 or DPLL_ID_ICL_DPLL1 to this
function because the path is only taken for non-combophy ports. Let the
warning trigger if improper value is given.
While at it, rename the function to match the register name we are
trying to program.
Lucas De Marchi [Fri, 25 Jan 2019 22:24:41 +0000 (14:24 -0800)]
drm/i915/icl: use tc_port in MG_PLL macros
Fix the TODO leftover in the code by changing the argument in MG_PLL
macros. The MG_PLL ids used to access the register values can be
converted from tc_port rather than port.
All these registers can use the TC port to calculate the right offsets
because they are only available for TC ports. The range (PORT_C onwards)
may not be stable and change from platform to platform. So by using the
TC id directly we avoid having to check for the platform in the "leaf
functions" and thus passing dev_priv around.
The helper functions were also renamed to use "tc" as prefix to make
them more generic.
v2: Improve commit message and fix checkpatch warning (from Paulo)
Chris Wilson [Tue, 29 Jan 2019 20:52:30 +0000 (20:52 +0000)]
drm/i915: Drop fake breadcrumb irq
Missed breadcrumb detection is defunct due to the tight coupling with
dma_fence signaling and the myriad ways we may signal fences from
everywhere but from an interrupt, i.e. we frequently signal a fence
before we even see its interrupt. This means that even if we miss an
interrupt for a fence, it still is signaled before our breadcrumb
hangcheck fires, so simplify the breadcrumb hangchecking by moving it
into the GPU hangcheck and forgo fake interrupts.
Chris Wilson [Tue, 29 Jan 2019 20:52:29 +0000 (20:52 +0000)]
drm/i915: Replace global breadcrumbs with per-context interrupt tracking
A few years ago, see commit 688e6c725816 ("drm/i915: Slaughter the
thundering i915_wait_request herd"), the issue of handling multiple
clients waiting in parallel was brought to our attention. The
requirement was that every client should be woken immediately upon its
request being signaled, without incurring any cpu overhead.
To handle certain fragility of our hw meant that we could not do a
simple check inside the irq handler (some generations required almost
unbounded delays before we could be sure of seqno coherency) and so
request completion checking required delegation.
Before commit 688e6c725816, the solution was simple. Every client
waiting on a request would be woken on every interrupt and each would do
a heavyweight check to see if their request was complete. Commit 688e6c725816 introduced an rbtree so that only the earliest waiter on
the global timeline would woken, and would wake the next and so on.
(Along with various complications to handle requests being reordered
along the global timeline, and also a requirement for kthread to provide
a delegate for fence signaling that had no process context.)
The global rbtree depends on knowing the execution timeline (and global
seqno). Without knowing that order, we must instead check all contexts
queued to the HW to see which may have advanced. We trim that list by
only checking queued contexts that are being waited on, but still we
keep a list of all active contexts and their active signalers that we
inspect from inside the irq handler. By moving the waiters onto the fence
signal list, we can combine the client wakeup with the dma_fence
signaling (a dramatic reduction in complexity, but does require the HW
being coherent, the seqno must be visible from the cpu before the
interrupt is raised - we keep a timer backup just in case).
Having previously fixed all the issues with irq-seqno serialisation (by
inserting delays onto the GPU after each request instead of random delays
on the CPU after each interrupt), we can rely on the seqno state to
perfom direct wakeups from the interrupt handler. This allows us to
preserve our single context switch behaviour of the current routine,
with the only downside that we lose the RT priority sorting of wakeups.
In general, direct wakeup latency of multiple clients is about the same
(about 10% better in most cases) with a reduction in total CPU time spent
in the waiter (about 20-50% depending on gen). Average herd behaviour is
improved, but at the cost of not delegating wakeups on task_prio.
v2: Capture fence signaling state for error state and add comments to
warm even the most cold of hearts.
v3: Check if the request is still active before busywaiting
v4: Reduce the amount of pointer misdirection with list_for_each_safe
and using a local i915_request variable inside the loops
v5: Add a missing pluralisation to a purely informative selftest message.
Chris Wilson [Tue, 29 Jan 2019 20:52:28 +0000 (20:52 +0000)]
drm/i915: Remove the intel_engine_notify tracepoint
The global seqno is defunct and so we have no meaningful indicator of
forward progress for an engine. You need to listen to the request
signaling tracepoints instead.
Ville Syrjälä [Tue, 29 Jan 2019 14:19:13 +0000 (16:19 +0200)]
drm/i915/tv: Bypass the vertical filter if possible
Let's switch the pipe into interlaced mode and switch off
the TV encoder vertical filter if the pipe vdisplay
matches the TV YSIZE exactly.
While I didn't measure it I presume this might reduce
the power consumption a little bit, and the pixel rate
is halved as the pipe will now fetching in interlaced
mode rather than in progressive mode (effectively the
same difference as between IF-ID vs. PF-ID pfit modes
on more modern hardware) so a bit easier on the memory
bandwidth.
Ville Syrjälä [Tue, 29 Jan 2019 14:19:12 +0000 (16:19 +0200)]
drm/i915/tv: Fix adjusted_mode dotclock for interlaced modes
intel_tv_mode_to_mode() assumes the pipe will be in progressive
fetch mode, and thus when programming the pipe into interlaced
mode we have to halve the calculated dotclock to get the correct
field duration.
This becomes more important when we start to program the pipe
into interlaced mode on i965gm as we depend on the timestamps
to get accurate frame counter values. Withot halving the clock
our guesstimated frame counter would tick at twice the expected
speed.
Chris Wilson [Tue, 29 Jan 2019 18:54:52 +0000 (18:54 +0000)]
drm/i915/execlists: Suppress preempting self
In order to avoid preempting ourselves, we currently refuse to schedule
the tasklet if we reschedule an inflight context. However, this glosses
over a few issues such as what happens after a CS completion event and
we then preempt the newly executing context with itself, or if something
else causes a tasklet_schedule triggering the same evaluation to
preempt the active context with itself.
However, when we avoid preempting ELSP[0], we still retain the preemption
value as it may match a second preemption request within the same time period
that we need to resolve after the next CS event. However, since we only
store the maximum preemption priority seen, it may not match the
subsequent event and so we should double check whether or not we
actually do need to trigger a preempt-to-idle by comparing the top
priorities from each queue. Later, this gives us a hook for finer
control over deciding whether the preempt-to-idle is justified.
The sequence of events where we end up preempting for no avail is:
1. Queue requests/contexts A, B
2. Priority boost A; no preemption as it is executing, but keep hint
3. After CS switch, B is less than hint, force preempt-to-idle
4. Resubmit B after idling
v2: We can simplify a bunch of tests based on the knowledge that PI will
ensure that earlier requests along the same context will have the highest
priority.
v3: Demonstrate the stale preemption hint with a selftest
Chris Wilson [Tue, 29 Jan 2019 18:54:51 +0000 (18:54 +0000)]
drm/i915: Rename execlists->queue_priority to queue_priority_hint
After noticing that we trigger preemption events for currently executing
requests, as well as requests that complete before the preemption and
attempting to suppress those preemption events, it is wise to not
consider the queue_priority to be authoritative. As we only track the
maximum priority seen between dequeue passes, if the maximum priority
request is no longer available for dequeuing (it completed or is even
executing on another engine), we have no knowledge of the previous
queue_priority as it would require us to keep a full history of enqueued
requests -- but we already have that history in the priolists!
Rename the queue_priority to queue_priority_hint so that we do not
confuse it as being exactly the maximum priority in the queue, but merely
an indication that we have seen a new maximum priority value and as such
we should check whether it should preempt the currently running request.
v2: s/preempt_priority_hint/queue_priority_hint/ as preempt implies it
being only used for the singular task of preemption and not the wider
question of waking up due to a change in the queue.
Chris Wilson [Tue, 29 Jan 2019 18:54:50 +0000 (18:54 +0000)]
drm/i915: Identify active requests
To allow requests to forgo a common execution timeline, one question we
need to be able to answer is "is this request running?". To track
whether a request has started on HW, we can emit a breadcrumb at the
beginning of the request and check its timeline's HWSP to see if the
breadcrumb has advanced past the start of this request. (This is in
contrast to the global timeline where we need only ask if we are on the
global timeline and if the timeline has advanced past the end of the
previous request.)
There is still confusion from a preempted request, which has already
started but relinquished the HW to a high priority request. For the
common case, this discrepancy should be negligible. However, for
identification of hung requests, knowing which one was running at the
time of the hang will be much more important.
Chris Wilson [Tue, 29 Jan 2019 18:54:49 +0000 (18:54 +0000)]
drm/i915/selftests: Apply a subtest filter
In bringup on simulated HW even rudimentary tests are slow, and so many
may fail that we want to be able to filter out the noise to focus on the
specific problem. Even just the tests groups provided for igt is not
specific enough, and we would like to isolate one particular subtest
(and probably subsubtests!). For simplicity, allow the user to provide a
command line parameter such as
to restrict ourselves to only running on subtest. The exact name to use
is given during a normal run, highlighted as an error if it failed,
debug otherwise. The test group is optional, and then all subtests are
compared for an exact match with the filter (most subtests have unique
names). The filter can be negated, e.g. i915.st_filter=!igt_sync and
then all tests but those that match will be run. More than one match can
be supplied separated by a comma, e.g.
i915.st_filter=igt_vma_create,igt_vma_pin1
to only run those specified, or
i915.st_filter=!igt_vma_create,!igt_vma_pin1
to run all but those named. Mixing a blacklist and whitelist will only
execute those subtests matching the whitelist so long as they are
previously excluded in the blacklist.
Chris Wilson [Mon, 28 Jan 2019 18:18:12 +0000 (18:18 +0000)]
drm/i915: Track active timelines
Now that we pin timelines around use, we have a clearly defined lifetime
and convenient points at which we can track only the active timelines.
This allows us to reduce the list iteration to only consider those
active timelines and not all.
Chris Wilson [Mon, 28 Jan 2019 18:18:11 +0000 (18:18 +0000)]
drm/i915: Track the context's seqno in its own timeline HWSP
Now that we have allocated ourselves a cacheline to store a breadcrumb,
we can emit a write from the GPU into the timeline's HWSP of the
per-context seqno as we complete each request. This drops the mirroring
of the per-engine HWSP and allows each context to operate independently.
We do not need to unwind the per-context timeline, and so requests are
always consistent with the timeline breadcrumb, greatly simplifying the
completion checks as we no longer need to be concerned about the
global_seqno changing mid check.
One complication though is that we have to be wary that the request may
outlive the HWSP and so avoid touching the potentially danging pointer
after we have retired the fence. We also have to guard our access of the
HWSP with RCU, the release of the obj->mm.pages should already be RCU-safe.
At this point, we are emitting both per-context and global seqno and
still using the single per-engine execution timeline for resolving
interrupts.
Chris Wilson [Mon, 28 Jan 2019 18:18:10 +0000 (18:18 +0000)]
drm/i915: Share per-timeline HWSP using a slab suballocator
If we restrict ourselves to only using a cacheline for each timeline's
HWSP (we could go smaller, but want to avoid needless polluting
cachelines on different engines between different contexts), then we can
suballocate a single 4k page into 64 different timeline HWSP. By
treating each fresh allocation as a slab of 64 entries, we can keep it
around for the next 64 allocation attempts until we need to refresh the
slab cache.
John Harrison noted the issue of fragmentation leading to the same worst
case performance of one page per timeline as before, which can be
mitigated by adopting a freelist.
v2: Keep all partially allocated HWSP on a freelist
This is still without migration, so it is possible for the system to end
up with each timeline in its own page, but we ensure that no new
allocation would needless allocate a fresh page!
v3: Throw a selftest at the allocator to try and catch invalid cacheline
reuse.
Chris Wilson [Mon, 28 Jan 2019 18:18:09 +0000 (18:18 +0000)]
drm/i915: Allocate a status page for each timeline
Allocate a page for use as a status page by a group of timelines, as we
only need a dword of storage for each (rounded up to the cacheline for
safety) we can pack multiple timelines into the same page. Each timeline
will then be able to track its own HW seqno.
v2: Reuse the common per-engine HWSP for the solitary ringbuffer
timeline, so that we do not have to emit (using per-gen specialised
vfuncs) the breadcrumb into the distinct timeline HWSP and instead can
keep on using the common MI_STORE_DWORD_INDEX. However, to maintain the
sleight-of-hand for the global/per-context seqno switchover, we will
store both temporarily (and so use a custom offset for the shared timeline
HWSP until the switch over).
v3: Keep things simple and allocate a page for each timeline, page
sharing comes next.
v4: I was caught repeating the same MI_STORE_DWORD_IMM over and over
again in selftests.
v5: And caught red handed copying create timeline + check.
Chris Wilson [Mon, 28 Jan 2019 18:18:08 +0000 (18:18 +0000)]
drm/i915: Enlarge vma->pin_count
Previously we only accommodated having a vma pinned by a small number of
users, with the maximum being pinned for use by the display engine. As
such, we used a small bitfield only large enough to allow the vma to
be pinned twice (for back/front buffers) in each scanout plane. Keeping
the maximum permissible pin_count small allows us to quickly catch a
potential leak. However, as we want to split a 4096B page into 64
different cachelines and pin each cacheline for use by a different
timeline, we will exceed the current maximum permissible vma->pin_count
and so time has come to enlarge it.
Whilst we are here, try to pull together the similar bits:
Address/layout specification:
- bias, mappable, zone_4g: address limit specifiers
- fixed: address override, limits still apply though
- high: not strictly an address limit, but an address direction to search
Search controls:
- nonblock, nonfault, noevict
v2: Rewrite the guideline comment on bit consumption.
Chris Wilson [Mon, 28 Jan 2019 18:18:07 +0000 (18:18 +0000)]
drm/i915: Introduce concept of per-timeline (context) HWSP
Supplement the per-engine HWSP with a per-timeline HWSP. That is a
per-request pointer through which we can check a local seqno,
abstracting away the presumption of a global seqno. In this first step,
we point each request back into the engine's HWSP so everything
continues to work with the global timeline.
v2: s/i915_request_hwsp/hwsp_seqno/ to emphasis that this is the current
HW value and that we are accessing it via i915_request merely as a
convenience.
Chris Wilson [Mon, 28 Jan 2019 10:23:56 +0000 (10:23 +0000)]
drm/i915: Move list of timelines under its own lock
Currently, the list of timelines is serialised by the struct_mutex, but
to alleviate difficulties with using that mutex in future, move the
list management under its own dedicated mutex.
Chris Wilson [Mon, 28 Jan 2019 10:23:55 +0000 (10:23 +0000)]
drm/i915: Always allocate an object/vma for the HWSP
Currently we only allocate an object and vma if we are using a GGTT
virtual HWSP, and a plain struct page for a physical HWSP. For
convenience later on with global timelines, it will be useful to always
have the status page being tracked by a struct i915_vma. Make it so.
Chris Wilson [Mon, 28 Jan 2019 10:23:53 +0000 (10:23 +0000)]
drm/i915: Pull VM lists under the VM mutex.
A starting point to counter the pervasive struct_mutex. For the goal of
avoiding (or at least blocking under them!) global locks during user
request submission, a simple but important step is being able to manage
each clients GTT separately. For which, we want to replace using the
struct_mutex as the guard for all things GTT/VM and switch instead to a
specific mutex inside i915_address_space.
Chris Wilson [Mon, 28 Jan 2019 10:23:52 +0000 (10:23 +0000)]
drm/i915: Stop tracking MRU activity on VMA
Our goal is to remove struct_mutex and replace it with fine grained
locking. One of the thorny issues is our eviction logic for reclaiming
space for an execbuffer (or GTT mmaping, among a few other examples).
While eviction itself is easy to move under a per-VM mutex, performing
the activity tracking is less agreeable. One solution is not to do any
MRU tracking and do a simple coarse evaluation during eviction of
active/inactive, with a loose temporal ordering of last
insertion/evaluation. That keeps all the locking constrained to when we
are manipulating the VM itself, neatly avoiding the tricky handling of
possible recursive locking during execbuf and elsewhere.
Note that discarding the MRU (currently implemented as a pair of lists,
to avoid scanning the active list for a NONBLOCKING search) is unlikely
to impact upon our efficiency to reclaim VM space (where we think a LRU
model is best) as our current strategy is to use random idle replacement
first before doing a search, and over time the use of softpinned 48b
per-ppGTT is growing (thereby eliminating any need to perform any eviction
searches, in theory at least) with the remaining users being found on
much older devices (gen2-gen6).
v2: Changelog and commentary rewritten to elaborate on the duality of a
single list being both an inactive and active list.
v3: Consolidate bool parameters into a single set of flags; don't
comment on the duality of a single variable being a multiplicity of
bits.
Ville Syrjälä [Fri, 11 Jan 2019 17:49:50 +0000 (19:49 +0200)]
drm/i915: Try to sanitize bogus DPLL state left over by broken SNB BIOSen
Certain SNB machines (eg. ASUS K53SV) seem to have a broken BIOS
which misprograms the hardware badly when encountering a suitably
high resolution display. The programmed pipe timings are somewhat
bonkers and the DPLL is totally misprogrammed (P divider == 0).
That will result in atomic commit timeouts as apparently the pipe
is sufficiently stuck to not signal vblank interrupts.
IIRC something like this was also observed on some other SNB
machine years ago (might have been a Dell XPS 8300) but a BIOS
update cured it. Sadly looks like this was never fixed for the
ASUS K53SV as the latest BIOS (K53SV.320 11/11/2011) is still
broken.
The quickest way to deal with this seems to be to shut down
the pipe+ports+DPLL. Unfortunately doing this during the
normal sanitization phase isn't quite soon enough as we
already spew several WARNs about the bogus hardware state.
But it's better than hanging the boot for a few dozen seconds.
Since this is limited to a few old machines it doesn't seem
entirely worthwile to try and rework the readout+sanitization
code to handle it more gracefully.
v2: Fix potential NULL deref (kbuild test robot)
Constify has_bogus_dpll_config()
Cc: stable@vger.kernel.org # v4.20+ Cc: Daniel Kamil Kozar <dkk089@gmail.com> Reported-by: Daniel Kamil Kozar <dkk089@gmail.com> Tested-by: Daniel Kamil Kozar <dkk089@gmail.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109245 Fixes: 516a49cc1946 ("drm/i915: Fix assert_plane() warning on bootup with external display") Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190111174950.10681-1-ville.syrjala@linux.intel.com Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Ville Syrjälä [Fri, 25 Jan 2019 18:19:31 +0000 (20:19 +0200)]
drm/i915/tv: Use the scanline counter for timestamps on i965gm TV output
Just like the frame counter, the pixel counter also reads zero
all the time when the TV encoder is used. Fortunately the
scanline counter still works sufficiently well so let's use that
to correct the vblank timestamps. Otherwise the timestamps may
en up out of whack, and since we use them to guesstimate the
vblank counter value that may end up incorrect as well.
Ville Syrjälä [Fri, 25 Jan 2019 18:19:30 +0000 (20:19 +0200)]
drm/i915/tv: Fix return value for intel_tv_compute_config()
Ever since commit 204474a6b859 ("drm/i915: Pass down rc in
intel_encoder->compute_config()") we're supposed to return an
errno from .compute_config(). I failed to notice that when
pushing the TV encoder fixes which were written before said
commmit. Fix up the return value for the error case.