linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c, branch v5.8

drm/amdgpu: don't do soft recovery if gpu_recovery=0

2020-07-09T18:42:49+00:00

It's impossible to debug shader hangs with soft recovery.

Signed-off-by: Marek Olšák 
Reviewed-by: Alex Deucher 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher 
Cc: stable@vger.kernel.org

drm/amdgpu: remove set but not used variable 'priority'

2020-04-23T19:06:41+00:00

drivers/gpu/drm/amd/amdgpu/amdgpu_job.c: In function amdgpu_job_submit:
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c:148:26: warning: variable priority set but not used [-Wunused-but-set-variable]

commit 33abcb1f5a17 ("drm/amdgpu: set compute queue priority at mqd_init")
left behind this, remove it.

Reviewed-by: Christian König 
Signed-off-by: YueHaibing 
Signed-off-by: Alex Deucher

drm/amdgpu: restrict debugfs register access under SR-IOV

2020-04-13T16:01:04+00:00

Under bare metal, there is no more else to take
care of the GPU register access through MMIO.
Under Virtualization, to access GPU register is
implemented through KIQ during run-time due to
world-switch.

Therefore, under SR-IOV user can only access
debugfs to r/w GPU registers when meets all
three conditions below.
- amdgpu_gpu_recovery=0
- TDR happened
- in_gpu_reset=0

v2: merge amdgpu_virt_can_access_debugfs() into
    amdgpu_virt_enable_access_debugfs()

v3: drop ret variable in amdgpu_virt_enable_access_debugfs()
    and directly return result

Signed-off-by: Yintian Tao 
Acked-by: Alex Deucher 
Signed-off-by: Alex Deucher

drm/amdgpu: implement more ib pools (v2)

2020-04-01T18:44:44+00:00

We have three ib pools, they are normal, VM, direct pools.

Any jobs which schedule IBs without dependence on gpu scheduler should
use DIRECT pool.

Any jobs schedule direct VM update IBs should use VM pool.

Any other jobs use NORMAL pool.

v2: squash in coding style fix

Signed-off-by: xinhui pan 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher

drm/amdgpu: set compute queue priority at mqd_init

2020-03-09T17:51:24+00:00

We were changing compute ring priority while rings were being used
before every job submission which is not recommended. This patch
sets compute queue priority at mqd initialization for gfx8, gfx9 and
gfx10.

Policy: make queue 0 of each pipe as high priority compute queue

High/normal priority compute sched lists are generated from set of high/normal
priority compute queues. At context creation, entity of compute queue
get a sched list from high or normal priority depending on ctx->priority

Signed-off-by: Nirmoy Das 
Acked-by: Alex Deucher 
Acked-by: Christian König 
Signed-off-by: Alex Deucher

drm/amdgpu: drop amdgpu_job.owner

2020-01-16T18:35:10+00:00

Entirely unused.

Signed-off-by: Christian König 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdgpu: explicitely sync to VM updates v2

2019-12-09T22:02:07+00:00

Allows us to reduce the overhead while syncing to fences a bit.

v2: also drop adev parameter from the functions

Signed-off-by: Christian König 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdgpu: If amdgpu_ib_schedule fails return back the error.

2019-10-25T20:50:11+00:00

Use ERR_PTR to return back the error happened during amdgpu_ib_schedule.

Signed-off-by: Andrey Grodzovsky 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher

drm/amdgpu: Avoid HW GPU reset for RAS.

2019-09-13T22:41:05+00:00

Problem:
Under certain conditions, when some IP bocks take a RAS error,
we can get into a situation where a GPU reset is not possible
due to issues in RAS in SMU/PSP.

Temporary fix until proper solution in PSP/SMU is ready:
When uncorrectable error happens the DF will unconditionally
broadcast error event packets to all its clients/slave upon
receiving fatal error event and freeze all its outbound queues,
err_event_athub interrupt  will be triggered.
In such case and we use this interrupt
to issue GPU reset. THe GPU reset code is modified for such case to avoid HW
reset, only stops schedulers, deatches all in progress and not yet scheduled
job's fences, set error code on them and signals.
Also reject any new incoming job submissions from user space.
All this is done to notify the applications of the problem.

v2:
Extract amdgpu_amdkfd_pre/post_reset from amdgpu_device_lock/unlock_adev
Move amdgpu_job_stop_all_jobs_on_sched to amdgpu_job.c
Remove print param from amdgpu_ras_query_error_count

v3:
Update based on prevoius bug fixing patch to properly call amdgpu_amdkfd_pre_reset
for other XGMI hive memebers.

Signed-off-by: Andrey Grodzovsky 
Acked-by: Felix Kuehling 
Reviewed-by: Hawking Zhang 
Signed-off-by: Alex Deucher

Merge tag 'drm-misc-next-2019-06-14' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

2019-06-14T09:44:24+00:00

drm-misc-next for v5.3:

UAPI Changes:

Cross-subsystem Changes:
- Add code to signal all dma-fences when freed with pending signals.
- Annotate reservation object access in CONFIG_DEBUG_MUTEXES

Core Changes:
- Assorted documentation fixes.
- Use irqsave/restore spinlock to add crc entry.
- Move code around to drm_client, for internal modeset clients.
- Make drm_crtc.h and drm_debugfs.h self-contained.
- Remove drm_fb_helper_connector.
- Add bootsplash to todo.
- Fix lock ordering in pan_display_legacy.
- Support pinning buffers to current location in gem-vram.
- Remove the now unused locking functions from gem-vram.
- Remove the now unused kmap-object argument from vram helpers.
- Stop checking return value of debugfs_create.
- Add atomic encoder enable/disable helpers.
- pass drm_atomic_state to atomic connector check.
- Add atomic support for bridge enable/disable.
- Add self refresh helpers to core.

Driver Changes:
- Add extra delay to make MTP SDM845 work.
- Small fixes to virtio, vkms, sii902x, sii9234, ast, mcde, analogix, rockchip.
- Add zpos and ?BGR8888 support to meson.
- More removals of drm_os_linux and drmP headers for amd, radeon, sti, r128, r128, savage, sis.
- Allow synopsis to unwedge the i2c hdmi bus.
- Add orientation quirks for GPD panels.
- Edid cleanups and fixing handling for edid < 1.2.
- Add runtime pm to stm.
- Handle s/r in dw-hdmi.
- Add hooks for power on/off to dsi for stm.
- Remove virtio dirty tracking code, done in drm core.
- Rework BO handling in ast and mgag200.

Tiny conflict in drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c,
needed #include  to make it compile.

Signed-off-by: Daniel Vetter 
From: Maarten Lankhorst 
Link: https://patchwork.freedesktop.org/patch/msgid/0e01de30-9797-853c-732f-4a5bd6e61445@linux.intel.com