Dave Airlie [Thu, 4 Oct 2018 00:38:23 +0000 (10:38 +1000)]
Merge tag 'omapdrm-4.20-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tomba/linux into drm-next
omapdrm fixes and cleanups for 4.20
- fix memory barrier bug in DMM driver
- fix interrupt management in DMM driver
- partial workaround for errata i878
- fix use of freed memory
- some cleanups
Dave Airlie [Thu, 4 Oct 2018 00:19:33 +0000 (10:19 +1000)]
Merge branch 'vmwgfx-next' of git://people.freedesktop.org/~thomash/linux into drm-next
Mostly code reorganizations and optimizations for vmwgfx.
- Move TTM code that's only used by vmwgfx to vmwgfx
- Break out the vmwgfx buffer- and resource validation code to a separate source file
- Get rid of a number of atomic operations during command buffer validation.
Neil Armstrong [Fri, 28 Sep 2018 12:05:55 +0000 (14:05 +0200)]
drm/fb_helper: Allow leaking fbdev smem_start
Since "drm/fb: Stop leaking physical address", the default behaviour of
the DRM fbdev emulation is to set the smem_base to 0 and pass the new
FBINFO_HIDE_SMEM_START flag.
The main reason is to avoid leaking physical addresse to user-space, and
it follows a general move over the kernel code to avoid user-space to
manipulate physical addresses and then use some other mechanisms like
dma-buf to transfer physical buffer handles over multiple subsystems.
But, a lot of devices depends on closed sources binaries to enable
OpenGL hardware acceleration that uses this smem_start value to
pass physical addresses to out-of-tree modules in order to render
into these physical adresses. These should use dma-buf buffers allocated
from the DRM display device instead and stop relying on fbdev overallocation
to gather DMA memory (some HW vendors delivers GBM and Wayland capable
binaries, but older unsupported devices won't have these new binaries
and are doomed until an Open Source solution like Lima finalizes).
Since these devices heavily depends on this kind of software and because
the smem_start population was available for years, it's a breakage to
stop leaking smem_start without any alternative solutions.
This patch adds a Kconfig depending on the EXPERT config and an unsafe
kernel module parameter tainting the kernel when enabled.
A clear comment and Kconfig help text was added to clarify why and when
this patch should be reverted, but in the meantime it's a necessary
feature to keep.
Cc: Dave Airlie <airlied@gmail.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Noralf Trønnes <noralf@tronnes.org> Cc: Maxime Ripard <maxime.ripard@bootlin.com> Cc: Eric Anholt <eric@anholt.net> Cc: Lucas Stach <l.stach@pengutronix.de> Cc: Rob Clark <robdclark@gmail.com> Cc: Ben Skeggs <skeggsb@gmail.com> Cc: Christian König <christian.koenig@amd.com> Signed-off-by: Neil Armstrong <narmstrong@baylibre.com> Reviewed-by: Maxime Ripard <maxime.ripard@bootlin.com> Tested-by: Maxime Ripard <maxime.ripard@bootlin.com> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> Acked-by: Dave Airlie <airlied@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/1538136355-15383-1-git-send-email-narmstrong@baylibre.com
This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.
Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
drm/omap: Replace drm_gem_object_unreference_unlocked with put function
This patch unifies the naming of DRM functions for reference counting
of struct drm_gem_object. The resulting code is more aligned with the
rest of the Linux kernel interfaces.
Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
drm/omap: Replace drm_gem_object_{un/reference} with put,get functions
This patch unifies the naming of DRM functions for reference counting
of struct drm_gem_object. The resulting code is more aligned with the
rest of the Linux kernel interfaces.
Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
drm/omap: Substitute format_is_yuv() with format->is_yuv
drm_format_info table has a field 'is_yuv' to denote if the format
is yuv or not. The driver is expected to use this instead of
having a function for the same purpose.
Signed-off-by: Ayan Kumar halder <ayan.halder@arm.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Tomi Valkeinen [Wed, 26 Sep 2018 09:11:30 +0000 (12:11 +0300)]
drm/omap: partial workaround for DRA7xx DMM errata i878
Errata i878 says that MPU should not be used to access RAM and DMM at
the same time. As it's not possible to prevent MPU accessing RAM, we
need to access DMM via a proxy.
This patch changes DMM driver to access DMM registers via sDMA. Instead
of doing a normal readl/writel call to read/write a register, we use
sDMA to copy 4 bytes from/to the DMM registers.
This patch provides only a partial workaround for i878, as not only DMM
register reads/writes are affected, but also accesses to the DMM mapped
buffers (framebuffers, usually).
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Tomi Valkeinen [Wed, 26 Sep 2018 09:11:27 +0000 (12:11 +0300)]
drm/omap: fix memory barrier bug in DMM driver
A DMM timeout "timed out waiting for done" has been observed on DRA7
devices. The timeout happens rarely, and only when the system is under
heavy load.
Debugging showed that the timeout can be made to happen much more
frequently by optimizing the DMM driver, so that there's almost no code
between writing the last DMM descriptors to RAM, and writing to DMM
register which starts the DMM transaction.
The current theory is that a wmb() does not properly ensure that the
data written to RAM is observable by all the components in the system.
This DMM timeout has caused interesting (and rare) bugs as the error
handling was not functioning properly (the error handling has been fixed
in previous commits):
* If a DMM timeout happened when a GEM buffer was being pinned for
display on the screen, a timeout error would be shown, but the driver
would continue programming DSS HW with broken buffer, leading to
SYNCLOST floods and possible crashes.
* If a DMM timeout happened when other user (say, video decoder) was
pinning a GEM buffer, a timeout would be shown but if the user
handled the error properly, no other issues followed.
* If a DMM timeout happened when a GEM buffer was being released, the
driver does not even notice the error, leading to crashes or hang
later.
This patch adds wmb() and readl() calls after the last bit is written to
RAM, which should ensure that the execution proceeds only after the data
is actually in RAM, and thus observable by DMM.
The read-back should not be needed. Further study is required to understand
if DMM is somehow special case and read-back is ok, or if DRA7's memory
barriers do not work correctly.
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
drm/omap: remove set but not used variable 'frame_height'
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/gpu/drm/omapdrm/dss/dispc.c: In function 'dispc_ovl_setup_common':
drivers/gpu/drm/omapdrm/dss/dispc.c:2627:19: warning:
variable 'frame_height' set but not used [-Wunused-but-set-variable]
Thomas Hellstrom [Wed, 26 Sep 2018 14:32:40 +0000 (16:32 +0200)]
drm/vmwgfx: Make user resource lookups reference-free during validation
Make the process of looking up a user resource and adding it to the
validation list reference-free unless when it's actually added to the
validation list where a single reference is taken.
This saves two locked atomic operations per command stream buffer object
handle lookup, unless there is a lookup cache hit.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Thomas Hellstrom [Wed, 26 Sep 2018 14:29:49 +0000 (16:29 +0200)]
drm/vmwgfx: Don't refcount cotable lookups during command buffer validation
The typical pattern of these lookups are
-Lookup
-Put on validate list if not already there.
-Unreference
And since we are the exclusive user of the context during lookup time,
we can be sure that the resource will stay alive during the sequence.
So avoid taking a reference during lookup, and also avoid unreferencing
when done. There are two users outside of command buffer validation and
those are refcounted explicitly.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
The typical pattern of these lookups are
-Lookup
-Put on validate list if not already there.
-Unreference
And since we are the exclusive user of the context during lookup time,
we can be sure that the resource will stay alive during the sequence.
So avoid taking a reference during lookup, and also avoid unreferencing
when done.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Thomas Hellstrom [Wed, 26 Sep 2018 14:27:54 +0000 (16:27 +0200)]
drm/vmwgfx: Make buffer object lookups reference-free during validation
Make the process of looking up a buffer object and adding it to the
validation list reference-free unless when it's actually added to the
validation list where a single reference is taken.
This saves two locked atomic operations per command stream buffer object
handle lookup.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Thomas Hellstrom [Wed, 26 Sep 2018 13:59:20 +0000 (15:59 +0200)]
drm/vmwgfx: Adapt validation code for reference-free lookups
Adapt the validation code so that vmw_validation_add[res|bo] can be called
under an rcu read lock (non-sleeping) and with rcu-only protected resource-
or buffer object pointers.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Thomas Hellstrom [Wed, 26 Sep 2018 13:57:46 +0000 (15:57 +0200)]
drm/ttm: Export ttm_bo_get_unless_zero()
Export ttm_bo_get_unless_zero() to be used when looking up buffer
objects that are removed from the lookup structure in the destructor.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com> Reviewed-by: Christian König <christian.koenig@amd.com>
Dave Airlie [Thu, 27 Sep 2018 23:48:35 +0000 (09:48 +1000)]
Merge branch 'drm-next-4.20' of git://people.freedesktop.org/~agd5f/linux into drm-next
More new features and fixes for 4.20:
- Add dynamic powergating support for VCN on picasso
- Scheduler cleanup
- Vega20 support for KFD
- DC cleanups and bug fixes
Dave Airlie [Thu, 27 Sep 2018 23:37:51 +0000 (09:37 +1000)]
Merge tag 'drm-intel-next-2018-09-21' of git://anongit.freedesktop.org/drm/drm-intel into drm-next
Driver Changes:
- Bugzilla 107600: Fix stuttering video playback on MythTV on old hardware (Chris)
- Avoid black screen when using CSC coefficient matrix (Raviraj)
- Hammer PDs on Baytrail to make sure they reload (Chris)
- Capture some objects if unable to capture all, on error (Chris)
- Add W/A for 16 GB DIMMs on SKL+ (Mahesh)
- Only enable IPC for symmetric memory configurations on KBL+ (Mahesh)
- Assume pipe A to have maximum stride limits (Ville)
- Always update update OA contexts via context image (Tvrtko)
- Icelake enabling patches (Madhav, Dhinakaran)
- Add Icelake DMC firmware (Anusha)
- Fixes for CI found corner cases (Chris)
- Limit the backpressure for request allocation (Chris)
- Park GPU on module load so usage starts from known state (Chris)
- Flush tasklet when checking for idle (Chris)
- Use coherent write into the context image on BSW+ (Chris)
- Fix possible integer overflow for framebuffers that get aligned past 4GiB (Ville)
- Downgrade fence timeout from warn to notice and add debug hint (Chris)
- Fixes to multi function encoder code (Ville)
- Fix sprite plane check logic (Dan, Ville)
- PAGE_SIZE vs. I915_GTT_PAGE_SIZE fixes (Ville)
- Decode memory bandwidth and parameters for BXT and SKL+ (Mahesh)
- Overwrite BIOS set IPC value from KMS (Mahesh)
- Multiple pipe handling code cleanups/restructurings/optimizations (Ville)
- Spare low 4G address for non-48bit objects (Chris)
- Free context_setparam of struct_mutex (Chris)
- Delay updating ring register state on resume (Chris)
- Avoid unnecessarily copying overlay IOCTL parameters (Chris)
- Update GuC power domain states even without submission (Michal)
- Restore GuC preempt-context across S3/S4 (Chris)
- Add kernel selftest for rapid context switching (Chris)
- Keep runtime power management ref for live selftests (Chris)
- GEM code cleanups (Matt)
Dave Airlie [Thu, 27 Sep 2018 23:31:03 +0000 (09:31 +1000)]
Merge tag 'drm-misc-next-2018-09-27' of git://anongit.freedesktop.org/drm/drm-misc into drm-next
drm-misc-next for 4.20:
UAPI Changes:
- None
Cross-subsystem Changes:
- MAINTAINERS: Move udl, mxsfb, and fsl-dcu into drm-misc (Stefan, Sean)
Core Changes:
- syncobj: Check condition before returning timeout in schedule() (Chris)
Driver Changes:
- various: First wave of drm_fbdev_generic_setup() conversions (Noralf)
- bochs/virtio: More format byte-order improvements (Gerd)
- mxsfb: A couple fixes + add runtime pm support (Leonard)
- virtio: Add vmap support for prime objects (Ezequiel)
Cc: Stefan Agner <stefan@agner.ch> Cc: Sean Paul <sean@poorly.run> Cc: Noralf Trønnes <noralf@tronnes.org> Cc: Gerd Hoffman <kraxel@redhat.com> Cc: Leonard Crestez <leonard.crestez@nxp.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Ezequiel Garcia <ezequiel@collabora.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Sean Paul <sean@poorly.run> Link: https://patchwork.freedesktop.org/patch/msgid/20180927093950.GA180365@art_vandelay
drm/scheduler: remove timeout work_struct from drm_sched_job (v3)
having a delayed work item per job is redundant as we only need one
per scheduler to track the time out the currently executing job.
v2: the first element of the ring mirror list is the currently
executing job so we don't need a additional variable for it
v3: squash in fixes for v3d and etnaviv
Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com> Suggested-by: Christian König <christian.koenig@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/powerplay: Change id parameter type in pp_atomfwctrl_get_clk_information_by_clkid
Clang generates warnings when one enumerated type is implicitly
converted to another.
drivers/gpu/drm/amd/amdgpu/../powerplay/hwmgr/ppatomfwctrl.c:532:57:
warning: implicit conversion from enumeration type 'enum
atom_smu11_syspll0_clock_id' to different enumeration type 'BIOS_CLKID'
(aka 'enum atom_smu9_syspll0_clock_id') [-Wenum-conversion]
if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr,
SMU11_SYSPLL0_SOCCLK_ID, &frequency))
In this case, that is expected behavior. To make that clear to Clang
without explicitly casting these values, change id's type to uint8_t
in pp_atomfwctrl_get_clk_information_by_clkid so no conversion happens.
Reported-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Nathan Chancellor <natechancellor@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Mon, 18 Jun 2018 18:47:21 +0000 (14:47 -0400)]
drm/amdkfd: Remove the requirement for atomic Ops on vg20
Firmware have the workaround to replace the atomic Ops with read-modify-write on CP side.
User should not expect atomic Ops on system memory works normally if system didn't not
support it.
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-By: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Thomas Hellstrom [Wed, 26 Sep 2018 13:55:16 +0000 (15:55 +0200)]
drm/vmwgfx: Look up objects without taking a reference
Typically when we look up objects under the rcu lock, we take a reference
to make sure the returned object pointer is valid.
Now provide a function to look up an object and instead of taking a
reference to it, keep the rcu lock held when returning the object pointer.
This means that the object pointer is valid as long as the rcu lock is
held, but the object may be doomed (its refcount may be zero). Any
persistent usage of the object pointer outside of the rcu lock requires
a reference to be taken using kref_get_unless_zero().
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Thomas Hellstrom [Wed, 26 Sep 2018 13:50:13 +0000 (15:50 +0200)]
drm/vmwgfx: Make the object handles idr-generated
Instead of generating user-space object handles based on a, possibly
processed, hash of the kernel address of the object, use idr to generate
and lookup those handles. This might improve somewhat on security since
we loose all connections to the object's kernel address. Also idr is
designed to do just this.
As a todo-item, since user-space handles are now generated in sequence,
we can probably use a much simpler hash function to hash them.
Thomas Hellstrom [Wed, 26 Sep 2018 13:41:52 +0000 (15:41 +0200)]
drm/vmwgfx: Remove the resource avail field
This field was previously used to prevent a lookup of a resource before its
constructor had run to its end. This was mainly intended for an interface
that is now removed that allowed looking up a resource by its device id.
Currently all affected resources are added to the lookup mechanism (its
TTM prime object is initialized) late in the constructor where it's OK to
look up the resource.
This means we can change the device resource_lock to an ordinary spinlock
instead of an rwlock and remove a locking sequence during lookup.
Thomas Hellstrom [Wed, 26 Sep 2018 13:39:24 +0000 (15:39 +0200)]
drm/vmwgfx: Replace unconditional mutex unlocked warnings with lockdep counterpart
Replace instances of WARN_ON[_ONCE](!mutex_is_held()) with
lockdep_assert_held(). This makes sure the checking process actually
holds the mutex and also removes the checks from release builds
Thomas Hellstrom [Wed, 26 Sep 2018 13:36:52 +0000 (15:36 +0200)]
drm/vmwgfx: Use a validation context allocator for relocations and validations
A common trait of these objects are that they are allocated during the
command validation phase and freed after command submission. Furthermore
they are accessed by a single thread only. So provide a simple unprotected
stack-like allocator from which these objects can be allocated. Their
memory is freed with the validation context when the command submission
is done.
Note that the mm subsystem maintains a per-cpu cache of single pages to
make single page allocation and freeing efficient.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Thomas Hellstrom [Wed, 26 Sep 2018 13:28:55 +0000 (15:28 +0200)]
drm/vmwgfx: Adapt execbuf to the new validation api
Strip the old execbuf validation functionality and use the new API instead.
Also use the new API for a now removed execbuf function that was called
from the kms code.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Thomas Hellstrom [Wed, 26 Sep 2018 18:15:36 +0000 (20:15 +0200)]
drm/ttm, drm/vmwgfx: Move the lock- and object functionality to the vmwgfx driver
No other driver is using this functionality so move it out of TTM and
into the vmwgfx driver. Update includes and remove exports.
Also annotate to remove false static analyzer lock balance warnings.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Christian König <christian.koenig@amd.com>
During the 4.19 merge window for drm-misc, two patches critical to
supporting the display pipeline on the Allwinner R40 SoC were missed.
They were applied later but missed the merge window deadline. As a
result 4.19-rc1 kernel would crash on the R40 when it couldn't parse
the new device tree structure. We ended up removing support for the
R40 display pipeline for 4.19.
Since the missing patches are already merged for 4.20, we can now
revert the commit that removed support.
Alex Deucher [Wed, 26 Sep 2018 16:24:25 +0000 (11:24 -0500)]
drm/amdgpu/vcn: whitespace cleanup
Fix some indentation issues.
Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: James Zhu <James.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Alex Deucher [Wed, 26 Sep 2018 16:18:47 +0000 (11:18 -0500)]
drm/amdgpu/soc15: fix warnings in register macro
expects argument of type ‘unsigned int’ has type ‘long int’
Fixes: 52e211c1f04 ("drm/amdgpu:Add error message when register failed to reach expected value") Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: James Zhu <James.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Fri, 21 Sep 2018 18:47:45 +0000 (14:47 -0400)]
drm/amdgpu:Enable DPG mode on PCO
Add flag AMD_PG_SUPPORT_DPG to enable DPG mode on Picasso
Signed-off-by: James Zhu <James.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Fri, 21 Sep 2018 18:43:18 +0000 (14:43 -0400)]
drm/amdgpu:Add DPG pause mode support
Add functions to support VCN DPG pause mode.
Signed-off-by: James Zhu <James.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Mon, 10 Sep 2018 22:15:11 +0000 (18:15 -0400)]
drm/amdgpu:Add DPG pause state
Add DPG pause state to support VCN DPG mode.
Signed-off-by: James Zhu <James.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Fri, 21 Sep 2018 18:35:32 +0000 (14:35 -0400)]
drm/amdgpu:Add DPG mode support for vcn 1.0
Add DPG mode start/stop/mc_resume/clock_gating to
support vcn 1.0 DPG mode.
Signed-off-by: James Zhu <James.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Mon, 10 Sep 2018 20:00:36 +0000 (16:00 -0400)]
drm/amdgpu:Add DPG mode read/write macro
Some registers read/write needs program through SDRAM pool under
DPG mode.
Signed-off-by: James Zhu <James.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Mon, 10 Sep 2018 19:23:40 +0000 (15:23 -0400)]
drm/amdgpu:Add DPG support flag
Add DPG support flag for VCN DPG mode.
Signed-off-by: James Zhu <James.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Mon, 10 Sep 2018 18:58:16 +0000 (14:58 -0400)]
drm/amdgpu:Add new register offset/mask to support VCN DPG mode
New register offset/mask need to be added to support VCN DPG mode.
Signed-off-by: James Zhu <James.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Mon, 10 Sep 2018 18:06:08 +0000 (14:06 -0400)]
drm/amdgpu:Use register UVD_SCRATCH9 for VCN ring/ib test
Use register UVD_SCRATCH9 for VCN ring/ib test. Since those registers
can't be directly accessed under DPG(Dynamic Power Gate) mode.
Signed-off-by: James Zhu <James.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 17 Sep 2018 13:29:28 +0000 (15:29 +0200)]
drm/amdgpu: move more defines into amdgpu_irq.h
Everything that isn't related to the IH ring.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 17 Sep 2018 13:18:37 +0000 (15:18 +0200)]
drm/amdgpu: move more interrupt processing into amdgpu_irq.c
Add a callback to amdgpu_ih_process to remove most of the IV logic.
Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Only print the warning if there was actually some fence processed
from the SW fallback timer.
v2: Add return value to amdgpu_fence_process to let
amdgpu_fence_fallback know fences were actually
processed and then print the warning.
v3: Always return true if seq != last_seq
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Acked-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sun, 16 Sep 2018 18:13:21 +0000 (20:13 +0200)]
drm/amdgpu: cleanup amdgpu_ih.c
Cleanup amdgpu_ih.c to be able to handle multiple interrupt rings.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 17 Sep 2018 13:41:45 +0000 (15:41 +0200)]
drm/amdgpu: make function pointers mandatory
We always want those to be setup correctly.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 20 Sep 2018 11:26:18 +0000 (13:26 +0200)]
drm/amdgpu: drop extra newline in amdgpu_iv trace
That is superflous here.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
While the apg_end address is 0xffffffff, if add 1 with it, the value will be
overflow and roll back to 0. So when 0 is written to
mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, the system aperture is actually disabled. And
so any access to vram will trigger a page fault.
Raven2's HW issue only need increase the vram end address, and needn't do it on
the agp.
Signed-off-by: Huang Rui <ray.huang@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Cc: Marek Olšák <marek.olsak@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rex Zhu [Thu, 20 Sep 2018 09:06:22 +0000 (17:06 +0800)]
drm/amdgpu: Remove redundant code in gfx_v8_0.c
the CG related registers have been programed in golden setting
PG register default value is 0.
Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Hang Zhou <hang.zhou@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rex Zhu [Tue, 11 Sep 2018 02:33:38 +0000 (10:33 +0800)]
drm/amdgpu: Halt rlc/cp in rlc_safe_mode
before halt rlc/cp, need to
1. enter rlc safe mode
2. wait rlc/cp idle
Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Hang Zhou <hang.zhou@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rex Zhu [Tue, 28 Aug 2018 10:20:19 +0000 (18:20 +0800)]
drm/amdgpu: Refine function name
change function name gfx_v6/7/8/9_0_gpu_init to
gfx_v6/7/8/9_0_constants_init.
this function is just for init gfx constants such
as max pipes, render backends...
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Tue, 31 Oct 2017 17:32:53 +0000 (13:32 -0400)]
drm/amdkfd: Vega20 bring up on amdkfd side
Add Vega20 device IDs, device info and enable it in KFD.
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Shaoyun Liu [Tue, 6 Feb 2018 20:37:53 +0000 (15:37 -0500)]
drm/amdgpu: Add vega20 support on kfd probe
Add Vega20 support in amdgpu_amdkfd_device_probe.
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Shaoyun Liu [Tue, 13 Mar 2018 21:44:09 +0000 (17:44 -0400)]
drm/amd: Interface change to support 64 bit page_table_base
amdgpu_gpuvm_get_process_page_dir should return the page table address
in the format expected by the pm4_map_process packet for all ASIC
generations.
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Fri, 9 Feb 2018 21:29:14 +0000 (16:29 -0500)]
drm/amdkfd: Make the number of SDMA queues variable
Vega20 supports 8 SDMA queues per engine
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Emily Deng [Thu, 9 Aug 2018 07:05:31 +0000 (15:05 +0800)]
drm/amdgpu/sriov: Correct the setting about sdma doorbell offset of Vega10
Correct the format
For vega10 sriov, the sdma doorbell must be fixed as follow to keep the
same setting with host driver, or it will happen conflicts.
Signed-off-by: Emily Deng <Emily.Deng@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Shaoyun Liu [Fri, 23 Mar 2018 21:20:41 +0000 (16:20 -0500)]
drm/amdgpu: Doorbell assignment for 8 sdma user queue per engine
Change doorbell assignments to allow routing doorbells for 8 user
mode SDMA queues per engine.
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Jay Cornwall [Tue, 2 May 2017 22:39:37 +0000 (17:39 -0500)]
drm/amdkfd: Add wavefront context save state retrieval ioctl
Wavefront context save data is of interest to userspace clients for
debugging static wavefront state. The MQD contains two parameters
required to parse the control stack and the control stack itself
is kept in the MQD from gfx9 onwards.
Add an ioctl to fetch the context save area and control stack offsets
and to copy the control stack to a userspace address if it is kept in
the MQD.
Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Felix Kuehling [Tue, 21 Aug 2018 00:15:00 +0000 (20:15 -0400)]
drm/amdkfd: Report SDMA firmware version in the topology
Also save the version in struct kfd_dev so we only need to query
it once.
Signed-off-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Emily Deng [Thu, 14 Dec 2017 01:31:01 +0000 (09:31 +0800)]
drm/amdkfd: KFD doesn't support TONGA SRIOV
KFD module doesn't support TONGA SRIOV, if init KFD module in TONGA SRIOV
environment, it will let compute ring IB test fail.
Signed-off-by: Emily Deng <Emily.Deng@amd.com> Reviewed-by: Shaoyun.liu <Shaoyun.liu@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Eric Huang [Mon, 4 Jun 2018 19:22:24 +0000 (15:22 -0400)]
drm/amdkfd: reflect atomic support in IO link properties
Add the flags of properties according to Asic type and pcie
capabilities.
Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
James Zhu [Thu, 13 Sep 2018 20:55:44 +0000 (16:55 -0400)]
drm/amdgpu:No action when VCN PG state is unchanged
When VCN PG state is unchanged, it is unnecessary to reset power
gate state
Signed-off-by: James Zhu <James.Zhu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: Raise dispclk value for dce120 by 15%
[Why]
The DISPCLK value was previously requested to be 15% higher for all
ASICs that went through the dce110 bandwidth code path. As part of a
refactoring of dce_clocks and the dce110 set bandwidth codepath this
was removed for power saving considerations.
That change caused display corruption under certain hardware
configurations with Vega10.
[How]
The 15% DISPCLK increase is brought back but only on dce110 for now.
This is should be a temporary workaround until the root cause is sorted
out for why this occurs on Vega (or other ASICs, if reported).
Tested-by: Nick Sarnie <sarnex@gentoo.org> Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Reviewed-by: Harry Wentland <Harry.Wentland@amd.com> Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHY]
Previously night light forced a full update by
applying a transfer function update regardless of if it was changed.
This logic was removed,
Now gamma surface updates are only applied when there is also a plane
info update, this does not work in cases such as using the night light
slider.
[HOW]
When moving the night light slider we will perform a full update if
the gamma has changed and there is a surface, even when the surface
has not changed. Also get stream updates in setgamma prior to
update planes and stream.
Signed-off-by: SivapiriyanKumarasamy <sivapiriyan.kumarasamy@amd.com> Reviewed-by: Anthony Koo <Anthony.Koo@amd.com> Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Leo Li [Wed, 12 Sep 2018 14:58:09 +0000 (10:58 -0400)]
drm/amd/display: Remove mst_hotplug_work
[Why]
The work struct's schedule call was removed a while ago, making this
useless.
[How]
Remove it.
Signed-off-by: Leo Li <sunpeng.li@amd.com> Reviewed-by: David Francis <David.Francis@amd.com> Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: Guard against null stream dereference in do flip
[Why]
During suspend under some hardware configurations can result in a
series of atomic commits with a NULL stream status - which
causes a NULL pointer dereference. This should be guarded.
[How]
Exit early from the function - if we can't access the stream then
there isn't anything that can be done here.
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Reviewed-by: Harry Wentland <Harry.Wentland@amd.com> Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/display: program v_update and v_ready with proper field
[WHY]
There are two different variables used to calculate v_update and v_ready,
one for validation and the other for performance parameter calculation.
Before the variable for validation was used which caused underflow on
1080edp with vsr enabled
[HOW]
program v_update and v_ready with the variables for performance parameter
calculation
Signed-off-by: Su Sung Chung <su.chung@amd.com> Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com> Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
projects / linux.git / log