drm/amdgpu: use a dummy owner for sysfs triggered cleaner shaders v4

Otherwise triggering sysfs multiple times without other submissions in
between only runs the shader once.

v2: add some comment
v

drm/amdgpu: use a dummy owner for sysfs triggered cleaner shaders v4

Otherwise triggering sysfs multiple times without other submissions in
between only runs the shader once.

v2: add some comment
v3: re-add missing cast
v4: squash in semicolon fix

Signed-off-by: Christian König <[email protected]>
Reviewed-by: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
(cherry picked from commit 8b2ae7d492675e8af8902f103364bef59382b935)

show more ...

drm/amdgpu: stop reserving VMIDs to enforce isolation

That was quite troublesome for gang submit. Completely drop this
approach and enforce the isolation separately.

Signed-off-by: Christian König

drm/amdgpu: stop reserving VMIDs to enforce isolation

That was quite troublesome for gang submit. Completely drop this
approach and enforce the isolation separately.

Signed-off-by: Christian König <[email protected]>
Acked-by: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/gfx: adjust workload profile handling

No need to make the workload profile setup dependent
on the results of cancelling the delayed work thread.
We have all of the necessary checking in p

drm/amdgpu/gfx: adjust workload profile handling

No need to make the workload profile setup dependent
on the results of cancelling the delayed work thread.
We have all of the necessary checking in place for the
workload profile reference counting, so separate the
two. As it is now, we can theoretically end up with
the call from begin_use happening while the worker
thread is executing which would result in the profile
not getting set for that submission. It should not
affect the reference counting.

v2: bail early if the the profile is already active (Lijo)

Reviewed-by: Lijo Lazar <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/gfx: fix ref counting for ring based profile handling

We need to make sure the workload profile ref counts are
balanced. This isn't currently the case because we can
increment the count

drm/amdgpu/gfx: fix ref counting for ring based profile handling

We need to make sure the workload profile ref counts are
balanced. This isn't currently the case because we can
increment the count on submissions, but the decrement may
be delayed as work comes in. Track when we enable the
workload profile so the references are balanced.

v2: switch to a mutex and active flag
v3: fix mutex init

Fixes: 8fdb3958e396 ("drm/amdgpu/gfx: add ring helpers for setting workload profile")
Cc: Yang Wang <[email protected]>
Cc: Kenneth Feng <[email protected]>
Tested-by: Kenneth Feng <[email protected]>
Reviewed-by: Kenneth Feng <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/gfx: delete stray tabs

These lines are indented one tab too far. Delete the extra tabs.

Reviewed-by: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Dan Carpenter <da

drm/amdgpu/gfx: delete stray tabs

These lines are indented one tab too far. Delete the extra tabs.

Reviewed-by: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Dan Carpenter <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/mes: keep enforce isolation up to date

Re-send the mes message on resume to make sure the
mes state is up to date.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")

drm/amdgpu/mes: keep enforce isolation up to date

Re-send the mes message on resume to make sure the
mes state is up to date.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")
Acked-by: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: Shaoyun Liu <[email protected]>
Cc: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
(cherry picked from commit 27b791514789844e80da990c456c2465325e0851)

show more ...

drm/amdgpu/gfx: only call mes for enforce isolation if supported

This should not be called on chips without MES so check if
MES is enabled and if the cleaner shader is supported.

Fixes: 8521e3c5f05

drm/amdgpu/gfx: only call mes for enforce isolation if supported

This should not be called on chips without MES so check if
MES is enabled and if the cleaner shader is supported.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")
Reviewed-by: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: Shaoyun Liu <[email protected]>
Cc: Srinivasan Shanmugam <[email protected]>
(cherry picked from commit 80513e389765c8f9543b26d8fa4bbdf0e59ff8bc)

show more ...

drm/amdgpu/mes: keep enforce isolation up to date

Re-send the mes message on resume to make sure the
mes state is up to date.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")

drm/amdgpu/mes: keep enforce isolation up to date

Re-send the mes message on resume to make sure the
mes state is up to date.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")
Acked-by: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: Shaoyun Liu <[email protected]>
Cc: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/gfx: only call mes for enforce isolation if supported

This should not be called on chips without MES so check if
MES is enabled and if the cleaner shader is supported.

Fixes: 8521e3c5f05

drm/amdgpu/gfx: only call mes for enforce isolation if supported

This should not be called on chips without MES so check if
MES is enabled and if the cleaner shader is supported.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")
Reviewed-by: Srinivasan Shanmugam <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: Shaoyun Liu <[email protected]>
Cc: Srinivasan Shanmugam <[email protected]>

show more ...

drm/amdgpu/gfx: add amdgpu_gfx_off_ctrl_immediate()

Same as amdgpu_gfx_off_ctrl(), but without the delay
for gfxoff disallow.

Reviewed-by: Lijo Lazar <[email protected]>
Suggested-by: Błażej Szczy

drm/amdgpu/gfx: add amdgpu_gfx_off_ctrl_immediate()

Same as amdgpu_gfx_off_ctrl(), but without the delay
for gfxoff disallow.

Reviewed-by: Lijo Lazar <[email protected]>
Suggested-by: Błażej Szczygieł <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu/gfx: add ring helpers for setting workload profile

Add helpers to switch the workload profile dynamically when
commands are submitted. This allows us to switch to
the FULLSCREEN3D or COM

drm/amdgpu/gfx: add ring helpers for setting workload profile

Add helpers to switch the workload profile dynamically when
commands are submitted. This allows us to switch to
the FULLSCREEN3D or COMPUTE profile when work is submitted.
Add a delayed work handler to delay switching out of the
selected profile if additional work comes in. This works
the same as the VIDEO profile for VCN. This lets dynamically
enable workload profiles on the fly and then move back
to the default when there is no work.

Reviewed-by: Lijo Lazar <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: Fix Circular Locking Dependency in AMDGPU GFX Isolation

This commit addresses a circular locking dependency issue within the GFX
isolation mechanism. The problem was identified by a warn

drm/amdgpu: Fix Circular Locking Dependency in AMDGPU GFX Isolation

This commit addresses a circular locking dependency issue within the GFX
isolation mechanism. The problem was identified by a warning indicating
a potential deadlock due to inconsistent lock acquisition order.

- The `amdgpu_gfx_enforce_isolation_ring_begin_use` and
`amdgpu_gfx_enforce_isolation_ring_end_use` functions previously
acquired `enforce_isolation_mutex` and called `amdgpu_gfx_kfd_sch_ctrl`,
leading to potential deadlocks. ie., If `amdgpu_gfx_kfd_sch_ctrl` is
called while `enforce_isolation_mutex` is held, and
`amdgpu_gfx_enforce_isolation_handler` is called while `kfd_sch_mutex` is
held, it can create a circular dependency.

By ensuring consistent lock usage, this fix resolves the issue:

[ 606.297333] ======================================================
[ 606.297343] WARNING: possible circular locking dependency detected
[ 606.297353] 6.10.0-amd-mlkd-610-311224-lof #19 Tainted: G OE
[ 606.297365] ------------------------------------------------------
[ 606.297375] kworker/u96:3/3825 is trying to acquire lock:
[ 606.297385] ffff9aa64e431cb8 ((work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work)){+.+.}-{0:0}, at: __flush_work+0x232/0x610
[ 606.297413]
but task is already holding lock:
[ 606.297423] ffff9aa64e432338 (&adev->gfx.kfd_sch_mutex){+.+.}-{3:3}, at: amdgpu_gfx_kfd_sch_ctrl+0x51/0x4d0 [amdgpu]
[ 606.297725]
which lock already depends on the new lock.

[ 606.297738]
the existing dependency chain (in reverse order) is:
[ 606.297749]
-> #2 (&adev->gfx.kfd_sch_mutex){+.+.}-{3:3}:
[ 606.297765] __mutex_lock+0x85/0x930
[ 606.297776] mutex_lock_nested+0x1b/0x30
[ 606.297786] amdgpu_gfx_kfd_sch_ctrl+0x51/0x4d0 [amdgpu]
[ 606.298007] amdgpu_gfx_enforce_isolation_ring_begin_use+0x2a4/0x5d0 [amdgpu]
[ 606.298225] amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[ 606.298412] amdgpu_ib_schedule+0x176/0x8a0 [amdgpu]
[ 606.298603] amdgpu_job_run+0xac/0x1e0 [amdgpu]
[ 606.298866] drm_sched_run_job_work+0x24f/0x430 [gpu_sched]
[ 606.298880] process_one_work+0x21e/0x680
[ 606.298890] worker_thread+0x190/0x350
[ 606.298899] kthread+0xe7/0x120
[ 606.298908] ret_from_fork+0x3c/0x60
[ 606.298919] ret_from_fork_asm+0x1a/0x30
[ 606.298929]
-> #1 (&adev->enforce_isolation_mutex){+.+.}-{3:3}:
[ 606.298947] __mutex_lock+0x85/0x930
[ 606.298956] mutex_lock_nested+0x1b/0x30
[ 606.298966] amdgpu_gfx_enforce_isolation_handler+0x87/0x370 [amdgpu]
[ 606.299190] process_one_work+0x21e/0x680
[ 606.299199] worker_thread+0x190/0x350
[ 606.299208] kthread+0xe7/0x120
[ 606.299217] ret_from_fork+0x3c/0x60
[ 606.299227] ret_from_fork_asm+0x1a/0x30
[ 606.299236]
-> #0 ((work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work)){+.+.}-{0:0}:
[ 606.299257] __lock_acquire+0x16f9/0x2810
[ 606.299267] lock_acquire+0xd1/0x300
[ 606.299276] __flush_work+0x250/0x610
[ 606.299286] cancel_delayed_work_sync+0x71/0x80
[ 606.299296] amdgpu_gfx_kfd_sch_ctrl+0x287/0x4d0 [amdgpu]
[ 606.299509] amdgpu_gfx_enforce_isolation_ring_begin_use+0x2a4/0x5d0 [amdgpu]
[ 606.299723] amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[ 606.299909] amdgpu_ib_schedule+0x176/0x8a0 [amdgpu]
[ 606.300101] amdgpu_job_run+0xac/0x1e0 [amdgpu]
[ 606.300355] drm_sched_run_job_work+0x24f/0x430 [gpu_sched]
[ 606.300369] process_one_work+0x21e/0x680
[ 606.300378] worker_thread+0x190/0x350
[ 606.300387] kthread+0xe7/0x120
[ 606.300396] ret_from_fork+0x3c/0x60
[ 606.300406] ret_from_fork_asm+0x1a/0x30
[ 606.300416]
other info that might help us debug this:

[ 606.300428] Chain exists of:
(work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work) --> &adev->enforce_isolation_mutex --> &adev->gfx.kfd_sch_mutex

[ 606.300458] Possible unsafe locking scenario:

[ 606.300468] CPU0 CPU1
[ 606.300476] ---- ----
[ 606.300484] lock(&adev->gfx.kfd_sch_mutex);
[ 606.300494] lock(&adev->enforce_isolation_mutex);
[ 606.300508] lock(&adev->gfx.kfd_sch_mutex);
[ 606.300521] lock((work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work));
[ 606.300536]
*** DEADLOCK ***

[ 606.300546] 5 locks held by kworker/u96:3/3825:
[ 606.300555] #0: ffff9aa5aa1f5d58 ((wq_completion)comp_1.1.0){+.+.}-{0:0}, at: process_one_work+0x3f5/0x680
[ 606.300577] #1: ffffaa53c3c97e40 ((work_completion)(&sched->work_run_job)){+.+.}-{0:0}, at: process_one_work+0x1d6/0x680
[ 606.300600] #2: ffff9aa64e463c98 (&adev->enforce_isolation_mutex){+.+.}-{3:3}, at: amdgpu_gfx_enforce_isolation_ring_begin_use+0x1c3/0x5d0 [amdgpu]
[ 606.300837] #3: ffff9aa64e432338 (&adev->gfx.kfd_sch_mutex){+.+.}-{3:3}, at: amdgpu_gfx_kfd_sch_ctrl+0x51/0x4d0 [amdgpu]
[ 606.301062] #4: ffffffff8c1a5660 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x70/0x610
[ 606.301083]
stack backtrace:
[ 606.301092] CPU: 14 PID: 3825 Comm: kworker/u96:3 Tainted: G OE 6.10.0-amd-mlkd-610-311224-lof #19
[ 606.301109] Hardware name: Gigabyte Technology Co., Ltd. X570S GAMING X/X570S GAMING X, BIOS F7 03/22/2024
[ 606.301124] Workqueue: comp_1.1.0 drm_sched_run_job_work [gpu_sched]
[ 606.301140] Call Trace:
[ 606.301146] <TASK>
[ 606.301154] dump_stack_lvl+0x9b/0xf0
[ 606.301166] dump_stack+0x10/0x20
[ 606.301175] print_circular_bug+0x26c/0x340
[ 606.301187] check_noncircular+0x157/0x170
[ 606.301197] ? register_lock_class+0x48/0x490
[ 606.301213] __lock_acquire+0x16f9/0x2810
[ 606.301230] lock_acquire+0xd1/0x300
[ 606.301239] ? __flush_work+0x232/0x610
[ 606.301250] ? srso_alias_return_thunk+0x5/0xfbef5
[ 606.301261] ? mark_held_locks+0x54/0x90
[ 606.301274] ? __flush_work+0x232/0x610
[ 606.301284] __flush_work+0x250/0x610
[ 606.301293] ? __flush_work+0x232/0x610
[ 606.301305] ? __pfx_wq_barrier_func+0x10/0x10
[ 606.301318] ? mark_held_locks+0x54/0x90
[ 606.301331] ? srso_alias_return_thunk+0x5/0xfbef5
[ 606.301345] cancel_delayed_work_sync+0x71/0x80
[ 606.301356] amdgpu_gfx_kfd_sch_ctrl+0x287/0x4d0 [amdgpu]
[ 606.301661] amdgpu_gfx_enforce_isolation_ring_begin_use+0x2a4/0x5d0 [amdgpu]
[ 606.302050] ? srso_alias_return_thunk+0x5/0xfbef5
[ 606.302069] amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[ 606.302452] amdgpu_ib_schedule+0x176/0x8a0 [amdgpu]
[ 606.302862] ? drm_sched_entity_error+0x82/0x190 [gpu_sched]
[ 606.302890] amdgpu_job_run+0xac/0x1e0 [amdgpu]
[ 606.303366] drm_sched_run_job_work+0x24f/0x430 [gpu_sched]
[ 606.303388] process_one_work+0x21e/0x680
[ 606.303409] worker_thread+0x190/0x350
[ 606.303424] ? __pfx_worker_thread+0x10/0x10
[ 606.303437] kthread+0xe7/0x120
[ 606.303449] ? __pfx_kthread+0x10/0x10
[ 606.303463] ret_from_fork+0x3c/0x60
[ 606.303476] ? __pfx_kthread+0x10/0x10
[ 606.303489] ret_from_fork_asm+0x1a/0x30
[ 606.303512] </TASK>

v2: Refactor lock handling to resolve circular dependency (Alex)

- Introduced a `sched_work` flag to defer the call to
`amdgpu_gfx_kfd_sch_ctrl` until after releasing
`enforce_isolation_mutex`.
- This change ensures that `amdgpu_gfx_kfd_sch_ctrl` is called outside
the critical section, preventing the circular dependency and deadlock.
- The `sched_work` flag is set within the mutex-protected section if
conditions are met, and the actual function call is made afterward.
- This approach ensures consistent lock acquisition order.

Fixes: afefd6f24502 ("drm/amdgpu: Implement Enforce Isolation Handler for KGD/KFD serialization")
Cc: Christian König <[email protected]>
Cc: Alex Deucher <[email protected]>
Signed-off-by: Srinivasan Shanmugam <[email protected]>
Suggested-by: Alex Deucher <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
(cherry picked from commit 0b6b2dd38336d5fd49214f0e4e6495e658e3ab44)
Cc: [email protected]

show more ...

drm/amdgpu: Fix Circular Locking Dependency in AMDGPU GFX Isolation

This commit addresses a circular locking dependency issue within the GFX
isolation mechanism. The problem was identified by a warn

drm/amdgpu: Fix Circular Locking Dependency in AMDGPU GFX Isolation

This commit addresses a circular locking dependency issue within the GFX
isolation mechanism. The problem was identified by a warning indicating
a potential deadlock due to inconsistent lock acquisition order.

- The `amdgpu_gfx_enforce_isolation_ring_begin_use` and
`amdgpu_gfx_enforce_isolation_ring_end_use` functions previously
acquired `enforce_isolation_mutex` and called `amdgpu_gfx_kfd_sch_ctrl`,
leading to potential deadlocks. ie., If `amdgpu_gfx_kfd_sch_ctrl` is
called while `enforce_isolation_mutex` is held, and
`amdgpu_gfx_enforce_isolation_handler` is called while `kfd_sch_mutex` is
held, it can create a circular dependency.

By ensuring consistent lock usage, this fix resolves the issue:

[ 606.297333] ======================================================
[ 606.297343] WARNING: possible circular locking dependency detected
[ 606.297353] 6.10.0-amd-mlkd-610-311224-lof #19 Tainted: G OE
[ 606.297365] ------------------------------------------------------
[ 606.297375] kworker/u96:3/3825 is trying to acquire lock:
[ 606.297385] ffff9aa64e431cb8 ((work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work)){+.+.}-{0:0}, at: __flush_work+0x232/0x610
[ 606.297413]
but task is already holding lock:
[ 606.297423] ffff9aa64e432338 (&adev->gfx.kfd_sch_mutex){+.+.}-{3:3}, at: amdgpu_gfx_kfd_sch_ctrl+0x51/0x4d0 [amdgpu]
[ 606.297725]
which lock already depends on the new lock.

[ 606.297738]
the existing dependency chain (in reverse order) is:
[ 606.297749]
-> #2 (&adev->gfx.kfd_sch_mutex){+.+.}-{3:3}:
[ 606.297765] __mutex_lock+0x85/0x930
[ 606.297776] mutex_lock_nested+0x1b/0x30
[ 606.297786] amdgpu_gfx_kfd_sch_ctrl+0x51/0x4d0 [amdgpu]
[ 606.298007] amdgpu_gfx_enforce_isolation_ring_begin_use+0x2a4/0x5d0 [amdgpu]
[ 606.298225] amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[ 606.298412] amdgpu_ib_schedule+0x176/0x8a0 [amdgpu]
[ 606.298603] amdgpu_job_run+0xac/0x1e0 [amdgpu]
[ 606.298866] drm_sched_run_job_work+0x24f/0x430 [gpu_sched]
[ 606.298880] process_one_work+0x21e/0x680
[ 606.298890] worker_thread+0x190/0x350
[ 606.298899] kthread+0xe7/0x120
[ 606.298908] ret_from_fork+0x3c/0x60
[ 606.298919] ret_from_fork_asm+0x1a/0x30
[ 606.298929]
-> #1 (&adev->enforce_isolation_mutex){+.+.}-{3:3}:
[ 606.298947] __mutex_lock+0x85/0x930
[ 606.298956] mutex_lock_nested+0x1b/0x30
[ 606.298966] amdgpu_gfx_enforce_isolation_handler+0x87/0x370 [amdgpu]
[ 606.299190] process_one_work+0x21e/0x680
[ 606.299199] worker_thread+0x190/0x350
[ 606.299208] kthread+0xe7/0x120
[ 606.299217] ret_from_fork+0x3c/0x60
[ 606.299227] ret_from_fork_asm+0x1a/0x30
[ 606.299236]
-> #0 ((work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work)){+.+.}-{0:0}:
[ 606.299257] __lock_acquire+0x16f9/0x2810
[ 606.299267] lock_acquire+0xd1/0x300
[ 606.299276] __flush_work+0x250/0x610
[ 606.299286] cancel_delayed_work_sync+0x71/0x80
[ 606.299296] amdgpu_gfx_kfd_sch_ctrl+0x287/0x4d0 [amdgpu]
[ 606.299509] amdgpu_gfx_enforce_isolation_ring_begin_use+0x2a4/0x5d0 [amdgpu]
[ 606.299723] amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[ 606.299909] amdgpu_ib_schedule+0x176/0x8a0 [amdgpu]
[ 606.300101] amdgpu_job_run+0xac/0x1e0 [amdgpu]
[ 606.300355] drm_sched_run_job_work+0x24f/0x430 [gpu_sched]
[ 606.300369] process_one_work+0x21e/0x680
[ 606.300378] worker_thread+0x190/0x350
[ 606.300387] kthread+0xe7/0x120
[ 606.300396] ret_from_fork+0x3c/0x60
[ 606.300406] ret_from_fork_asm+0x1a/0x30
[ 606.300416]
other info that might help us debug this:

[ 606.300428] Chain exists of:
(work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work) --> &adev->enforce_isolation_mutex --> &adev->gfx.kfd_sch_mutex

[ 606.300458] Possible unsafe locking scenario:

[ 606.300468] CPU0 CPU1
[ 606.300476] ---- ----
[ 606.300484] lock(&adev->gfx.kfd_sch_mutex);
[ 606.300494] lock(&adev->enforce_isolation_mutex);
[ 606.300508] lock(&adev->gfx.kfd_sch_mutex);
[ 606.300521] lock((work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work));
[ 606.300536]
*** DEADLOCK ***

[ 606.300546] 5 locks held by kworker/u96:3/3825:
[ 606.300555] #0: ffff9aa5aa1f5d58 ((wq_completion)comp_1.1.0){+.+.}-{0:0}, at: process_one_work+0x3f5/0x680
[ 606.300577] #1: ffffaa53c3c97e40 ((work_completion)(&sched->work_run_job)){+.+.}-{0:0}, at: process_one_work+0x1d6/0x680
[ 606.300600] #2: ffff9aa64e463c98 (&adev->enforce_isolation_mutex){+.+.}-{3:3}, at: amdgpu_gfx_enforce_isolation_ring_begin_use+0x1c3/0x5d0 [amdgpu]
[ 606.300837] #3: ffff9aa64e432338 (&adev->gfx.kfd_sch_mutex){+.+.}-{3:3}, at: amdgpu_gfx_kfd_sch_ctrl+0x51/0x4d0 [amdgpu]
[ 606.301062] #4: ffffffff8c1a5660 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x70/0x610
[ 606.301083]
stack backtrace:
[ 606.301092] CPU: 14 PID: 3825 Comm: kworker/u96:3 Tainted: G OE 6.10.0-amd-mlkd-610-311224-lof #19
[ 606.301109] Hardware name: Gigabyte Technology Co., Ltd. X570S GAMING X/X570S GAMING X, BIOS F7 03/22/2024
[ 606.301124] Workqueue: comp_1.1.0 drm_sched_run_job_work [gpu_sched]
[ 606.301140] Call Trace:
[ 606.301146] <TASK>
[ 606.301154] dump_stack_lvl+0x9b/0xf0
[ 606.301166] dump_stack+0x10/0x20
[ 606.301175] print_circular_bug+0x26c/0x340
[ 606.301187] check_noncircular+0x157/0x170
[ 606.301197] ? register_lock_class+0x48/0x490
[ 606.301213] __lock_acquire+0x16f9/0x2810
[ 606.301230] lock_acquire+0xd1/0x300
[ 606.301239] ? __flush_work+0x232/0x610
[ 606.301250] ? srso_alias_return_thunk+0x5/0xfbef5
[ 606.301261] ? mark_held_locks+0x54/0x90
[ 606.301274] ? __flush_work+0x232/0x610
[ 606.301284] __flush_work+0x250/0x610
[ 606.301293] ? __flush_work+0x232/0x610
[ 606.301305] ? __pfx_wq_barrier_func+0x10/0x10
[ 606.301318] ? mark_held_locks+0x54/0x90
[ 606.301331] ? srso_alias_return_thunk+0x5/0xfbef5
[ 606.301345] cancel_delayed_work_sync+0x71/0x80
[ 606.301356] amdgpu_gfx_kfd_sch_ctrl+0x287/0x4d0 [amdgpu]
[ 606.301661] amdgpu_gfx_enforce_isolation_ring_begin_use+0x2a4/0x5d0 [amdgpu]
[ 606.302050] ? srso_alias_return_thunk+0x5/0xfbef5
[ 606.302069] amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[ 606.302452] amdgpu_ib_schedule+0x176/0x8a0 [amdgpu]
[ 606.302862] ? drm_sched_entity_error+0x82/0x190 [gpu_sched]
[ 606.302890] amdgpu_job_run+0xac/0x1e0 [amdgpu]
[ 606.303366] drm_sched_run_job_work+0x24f/0x430 [gpu_sched]
[ 606.303388] process_one_work+0x21e/0x680
[ 606.303409] worker_thread+0x190/0x350
[ 606.303424] ? __pfx_worker_thread+0x10/0x10
[ 606.303437] kthread+0xe7/0x120
[ 606.303449] ? __pfx_kthread+0x10/0x10
[ 606.303463] ret_from_fork+0x3c/0x60
[ 606.303476] ? __pfx_kthread+0x10/0x10
[ 606.303489] ret_from_fork_asm+0x1a/0x30
[ 606.303512] </TASK>

v2: Refactor lock handling to resolve circular dependency (Alex)

- Introduced a `sched_work` flag to defer the call to
`amdgpu_gfx_kfd_sch_ctrl` until after releasing
`enforce_isolation_mutex`.
- This change ensures that `amdgpu_gfx_kfd_sch_ctrl` is called outside
the critical section, preventing the circular dependency and deadlock.
- The `sched_work` flag is set within the mutex-protected section if
conditions are met, and the actual function call is made afterward.
- This approach ensures consistent lock acquisition order.

Fixes: afefd6f24502 ("drm/amdgpu: Implement Enforce Isolation Handler for KGD/KFD serialization")
Cc: Christian König <[email protected]>
Cc: Alex Deucher <[email protected]>
Signed-off-by: Srinivasan Shanmugam <[email protected]>
Suggested-by: Alex Deucher <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: partially revert "reduce reset time"

This partially reverts commit 194eb174cbe4fe2b3376ac30acca2dc8c8beca00.

This commit introduced a new state variable into adev without even
remotely

drm/amdgpu: partially revert "reduce reset time"

This partially reverts commit 194eb174cbe4fe2b3376ac30acca2dc8c8beca00.

This commit introduced a new state variable into adev without even
remotely worrying about CPU barriers.

Since we already have the amdgpu_in_reset() function exactly for this
use case partially revert that.

Signed-off-by: Christian König <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: Fix potential integer overflow in scheduler mask calculations

The use of 1 << i in scheduler mask calculations can result in an
unintentional integer overflow due to the expression being

drm/amdgpu: Fix potential integer overflow in scheduler mask calculations

The use of 1 << i in scheduler mask calculations can result in an
unintentional integer overflow due to the expression being
evaluated as a 32-bit signed integer.

This patch replaces 1 << i with 1ULL << i to ensure the operation
is performed as a 64-bit unsigned integer, preventing overflow

Discovered in coverity scan, CID 1636393, 1636175, 1636007, 1635853

Fixes: c5c63d9cb5d3 ("drm/amdgpu: add amdgpu_gfx_sched_mask and amdgpu_compute_sched_mask debugfs")
Signed-off-by: Karol Przybylski <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amd/amdgpu: Add Annotations to Process Isolation functions

This update adds explanations to key functions that manage how the
Kernel Fusion Driver (KFD) and Kernel Graphics Driver (KGD) share th

drm/amd/amdgpu: Add Annotations to Process Isolation functions

This update adds explanations to key functions that manage how the
Kernel Fusion Driver (KFD) and Kernel Graphics Driver (KGD) share the
GPU.

amdgpu_gfx_enforce_isolation_wait_for_kfd: Controls the waiting period
for KFD to ensure it takes turns with KGD in using the GPU. It uses a
mutex to safely manage shared data, like timing and state, and tracks
when KFD starts and stops waiting.

amdgpu_gfx_enforce_isolation_ring_begin_use: Ensures KFD has enough time
to run before new tasks are submitted to the GPU ring. It uses a mutex
to synchronize access and may adjust the KFD scheduler.

amdgpu_gfx_enforce_isolation_ring_end_use: Handles cleanup and state
updates when finishing the use of a GPU ring. It may also adjust the KFD
scheduler, using a mutex to manage shared data access.

Cc: Christian König <[email protected]>
Cc: Alex Deucher <[email protected]>
Signed-off-by: Srinivasan Shanmugam <[email protected]>
Suggested-by: Alex Deucher <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amd/amdgpu: Add Descriptions to Process Isolation and Cleaner Shader Sysfs Functions

This update adds explanations to key functions related to process
isolation and cleaner shader execution sysf

drm/amd/amdgpu: Add Descriptions to Process Isolation and Cleaner Shader Sysfs Functions

This update adds explanations to key functions related to process
isolation and cleaner shader execution sysfs interfaces.

- `amdgpu_gfx_set_run_cleaner_shader`: Describes how to manually run a
cleaner shader, which clears the Local Data Store (LDS) and General
Purpose Registers (GPRs) to ensure data isolation between GPU workloads.

- `amdgpu_gfx_get_enforce_isolation`: Describes how to query the current
settings of the 'enforce_isolation' feature for each GPU partition.

- `amdgpu_gfx_set_enforce_isolation`: Describes how to enable or disable
process isolation for GPU partitions through the sysfs interface.

Cc: Christian König <[email protected]>
Cc: Alex Deucher <[email protected]>
Signed-off-by: Srinivasan Shanmugam <[email protected]>
Suggested-by: Alex Deucher <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amd/pm: add inst to dpm_set_powergating_by_smu

Add an instance parameter to amdgpu_dpm_set_powergating_by_smu() function,
and use the instance to call set_powergating_by_smu().

v2: remove dupli

drm/amd/pm: add inst to dpm_set_powergating_by_smu

Add an instance parameter to amdgpu_dpm_set_powergating_by_smu() function,
and use the instance to call set_powergating_by_smu().

v2: remove duplicated functions.

remove for-loop in amdgpu_dpm_set_powergating_by_smu(), and temporarily
move it to amdgpu_dpm_enable_vcn(), in order to keep the exact same logic
as before, until further separation in next patch.

v3: drop SI logic in amdgpu_dpm_enable_vcn().

Signed-off-by: Boyuan Zhang <[email protected]>
Acked-by: Christian König <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: Fix sysfs warning when hotplugging

Fix the similar warning when hotplugging:

[ 155.585721] kernfs: can not remove 'enforce_isolation', no directory
[ 155.592201] WARNING: CPU: 3 PID:

drm/amdgpu: Fix sysfs warning when hotplugging

Fix the similar warning when hotplugging:

[ 155.585721] kernfs: can not remove 'enforce_isolation', no directory
[ 155.592201] WARNING: CPU: 3 PID: 6960 at fs/kernfs/dir.c:1683 kernfs_remove_by_name_ns+0xb9/0xc0
[ 155.601145] Modules linked in: xt_MASQUERADE xt_comment nft_compat veth bridge stp llc overlay nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables nfnetlink qrtr intel_rapl_msr amd_atl intel_rapl_common amd64_edac edac_mce_amd amdgpu kvm_amd kvm ipmi_ssif amdxcp rapl drm_exec gpu_sched drm_buddy i2c_algo_bit drm_suballoc_helper drm_ttm_helper ttm pcspkr drm_display_helper acpi_cpufreq drm_kms_helper video wmi k10temp i2c_piix4 acpi_ipmi ipmi_si drm zram ip_tables loop squashfs dm_multipath crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel sha512_ssse3 sha256_ssse3 sha1_ssse3 sp5100_tco ixgbe rfkill ccp dca sunrpc be2iscsi bnx2i cnic uio cxgb4i cxgb4 tls cxgb3i cxgb3 mdio libcxgbi libcxgb qla4xxx iscsi_boot_sysfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ipmi_devintf ipmi_msghandler fuse
[ 155.685224] systemd-journald[1354]: Compressed data object 957 -> 524 using ZSTD
[ 155.685687] CPU: 3 PID: 6960 Comm: amd_pci_unplug Not tainted 6.10.0-1148853.1.zuul.164395107d6642bdb451071313e9378d #1
[ 155.704149] Hardware name: TYAN B8021G88V2HR-2T/S8021GM2NR-2T, BIOS V1.03.B10 04/01/2019
[ 155.712383] RIP: 0010:kernfs_remove_by_name_ns+0xb9/0xc0
[ 155.717805] Code: a0 00 48 89 ef e8 37 96 c7 ff 5b b8 fe ff ff ff 5d 41 5c 41 5d e9 f7 96 a0 00 0f 0b eb ab 48 c7 c7 48 ba 7e 8f e8 f7 66 bf ff <0f> 0b eb dc 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90
[ 155.736766] RSP: 0018:ffffb1685d7a3e20 EFLAGS: 00010296
[ 155.742108] RAX: 0000000000000038 RBX: ffff929e94c80000 RCX: 0000000000000000
[ 155.749363] RDX: ffff928e1efaf200 RSI: ffff928e1efa18c0 RDI: ffff928e1efa18c0
[ 155.756612] RBP: 0000000000000008 R08: 0000000000000000 R09: 0000000000000003
[ 155.763855] R10: ffffb1685d7a3cd8 R11: ffffffff8fb3e1c8 R12: ffffffffc1ef5341
[ 155.771104] R13: ffff929e94cc5530 R14: 0000000000000000 R15: 0000000000000000
[ 155.778357] FS: 00007fd9dd8d9c40(0000) GS:ffff928e1ef80000(0000) knlGS:0000000000000000
[ 155.786594] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 155.792450] CR2: 0000561245ceee38 CR3: 0000000113018000 CR4: 00000000003506f0
[ 155.799702] Call Trace:
[ 155.802254] <TASK>
[ 155.804460] ? __warn+0x80/0x120
[ 155.807798] ? kernfs_remove_by_name_ns+0xb9/0xc0
[ 155.812617] ? report_bug+0x164/0x190
[ 155.816393] ? handle_bug+0x3c/0x80
[ 155.819994] ? exc_invalid_op+0x17/0x70
[ 155.823939] ? asm_exc_invalid_op+0x1a/0x20
[ 155.828235] ? kernfs_remove_by_name_ns+0xb9/0xc0
[ 155.833058] amdgpu_gfx_sysfs_fini+0x59/0xd0 [amdgpu]
[ 155.838637] gfx_v9_0_sw_fini+0x123/0x1c0 [amdgpu]
[ 155.843887] amdgpu_device_fini_sw+0xbc/0x3e0 [amdgpu]
[ 155.849432] amdgpu_driver_release_kms+0x16/0x30 [amdgpu]
[ 155.855235] drm_dev_put.part.0+0x3c/0x60 [drm]
[ 155.859914] drm_release+0x8b/0xc0 [drm]
[ 155.863978] __fput+0xf1/0x2c0
[ 155.867141] __x64_sys_close+0x3c/0x80
[ 155.870998] do_syscall_64+0x64/0x170

V2: Add details in comments (Tim)

Signed-off-by: Jesse Zhang <[email protected]>
Reported-by: Andy Dong <[email protected]>
Reviewed-by: Tim Huang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amd/amdgpu: limit single process inside MES

This is for MES to limit only one process for the user queues

Signed-off-by: Shaoyun Liu <[email protected]>
Reviewed-by: Alex Deucher <alexander.d

drm/amd/amdgpu: limit single process inside MES

This is for MES to limit only one process for the user queues

Signed-off-by: Shaoyun Liu <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: Implement virt req_ras_err_count

Enable RAS late init if VF RAS Telemetry is supported.

When enabled, the VF can use this interface to query total
RAS error counts from the host.

The

drm/amdgpu: Implement virt req_ras_err_count

Enable RAS late init if VF RAS Telemetry is supported.

When enabled, the VF can use this interface to query total
RAS error counts from the host.

The VF FB access may abruptly end due to a fatal error,
therefore the VF must cache and sanitize the input.

The Host allows 15 Telemetry messages every 60 seconds, afterwhich
the host will ignore any more in-coming telemetry messages. The VF will
rate limit its msg calling to once every 5 seconds (12 times in 60 seconds).
While the VF is rate limited, it will continue to report the last
good cached data.

v2: Flip generate report & update statistics order for VF

Signed-off-by: Victor Skvortsov <[email protected]>
Acked-by: Tao Zhou <[email protected]>
Reviewed-by: Zhigang Luo <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: Avoid kcq disable during reset

Reset sequence indicates that hardware already ran into a bad state.
Avoid sending unmap queue request to reset KCQ. This will also cover RAS
error scenari

drm/amdgpu: Avoid kcq disable during reset

Reset sequence indicates that hardware already ran into a bad state.
Avoid sending unmap queue request to reset KCQ. This will also cover RAS
error scenarios which need a reset to recover, hence remove the check.

Signed-off-by: Lijo Lazar <[email protected]>
Reviewed-by: Le Ma <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: Fix map/unmap queue logic

In current logic, it calls ring_alloc followed by a ring_test. ring_test
in turn will call another ring_alloc. This is illegal usage as a
ring_alloc is expected

drm/amdgpu: Fix map/unmap queue logic

In current logic, it calls ring_alloc followed by a ring_test. ring_test
in turn will call another ring_alloc. This is illegal usage as a
ring_alloc is expected to be closed properly with a ring_commit. Change
to commit the map/unmap queue packet first followed by a ring_test. Add a
comment about the usage of ring_test.

Also, reorder the current pre-condition checks of job hang or kiq ring
scheduler not ready. Without them being met, it is not useful to attempt
ring or memory allocations.

Fixes tag refers to the original patch which introduced this issue which
then got carried over into newer code.

Signed-off-by: Lijo Lazar <[email protected]>
Reviewed-by: Le Ma <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Fixes: 6c10b5cc4eaa ("drm/amdgpu: Remove duplicate code in gfx_v8_0.c")

show more ...

drm/amdgpu: Add sysfs interface for gc reset mask

Add two sysfs interfaces for gfx and compute:
gfx_reset_mask
compute_reset_mask

These interfaces are read-only and show the resets supported by the

drm/amdgpu: Add sysfs interface for gc reset mask

Add two sysfs interfaces for gfx and compute:
gfx_reset_mask
compute_reset_mask

These interfaces are read-only and show the resets supported by the IP.
For example, full adapter reset (mode1/mode2/BACO/etc),
soft reset, queue reset, and pipe reset.

V2: the sysfs node returns a text string instead of some flags (Christian)
v3: add a generic helper which takes the ring as parameter
and print the strings in the order they are applied (Christian)

check amdgpu_gpu_recovery before creating sysfs file itself,
and initialize supported_reset_types in IP version files (Lijo)
v4: Fixing uninitialized variables (Tim)

Signed-off-by: Jesse Zhang <[email protected]>
Suggested-by: Alex Deucher <[email protected]>
Reviewed-by: Tim Huang <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...

drm/amdgpu: Group gfx sysfs functions

Make amdgpu_gfx_sysfs_init/fini functions as common entry points for all
gfx related sysfs nodes.

Signed-off-by: Lijo Lazar <[email protected]>
Reviewed-by: A

drm/amdgpu: Group gfx sysfs functions

Make amdgpu_gfx_sysfs_init/fini functions as common entry points for all
gfx related sysfs nodes.

Signed-off-by: Lijo Lazar <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

show more ...