linux-stable.git/drivers/gpu/drm/amd/amdkfd, branch linux-5.17.y

drm/amdkfd: Fix GWS queue count

2022-05-09T07:16:25+00:00

[ Upstream commit 7c6b6e18c890f30965b0589b0a57645e1dbccfde ]

dqm->gws_queue_count and pdd->qpd.mapped_gws_queue need to be updated
each time the queue gets evicted.

Fixes: b8020b0304c8 ("drm/amdkfd: Enable over-subscription with >1 GWS queue")
Signed-off-by: David Yat Sin 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdkfd: Check for potential null return of kmalloc_array()

2022-04-20T07:36:20+00:00

[ Upstream commit ebbb7bb9e80305820dc2328a371c1b35679f2667 ]

As the kmalloc_array() may return null, the 'event_waiters[i].wait' would lead to null-pointer dereference.
Therefore, it is better to check the return value of kmalloc_array() to avoid this confusion.

Signed-off-by: QintaoShen 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdkfd: Fix Incorrect VMIDs passed to HWS

2022-04-20T07:36:19+00:00

[ Upstream commit b7dfbd2e601f3fee545bc158feceba4f340fe7cf ]

Compute-only GPUs have more than 8 VMIDs allocated to KFD. Fix
this by passing correct number of VMIDs to HWS

v2: squash in warning fix (Alex)

Signed-off-by: Tushar Patel 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdkfd: Fix variable set but not used warning

2022-04-13T17:27:40+00:00

commit 90c44207cdd18091ac9aa7cab8a3e7b0ef00e847 upstream.

All warnings (new ones prefixed by >>):

   drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_svm.c: In function
'svm_range_deferred_list_work':
>> drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_svm.c:2067:22: warning:
variable 'p' set but not used [-Wunused-but-set-variable]
    2067 |  struct kfd_process *p;
         |

Fixes: 367c9b0f1b8750 ("drm/amdkfd: Ensure mm remain valid in svm deferred_list work")
Reported-by: kernel test robot 
Signed-off-by: Philip Yang 
Reviewed-By: Harish Kasiviswanathan 
Signed-off-by: Alex Deucher 
Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: Create file descriptor after client is added to smi_clients list

2022-04-13T17:27:39+00:00

commit e79a2398e1b2d47060474dca291542368183bc0f upstream.

This ensures userspace cannot prematurely clean-up the client before
it is fully initialised which has been proven to cause issues in the
past.

Cc: Felix Kuehling 
Cc: Alex Deucher 
Cc: "Christian König" 
Cc: "Pan, Xinhui" 
Cc: David Airlie 
Cc: Daniel Vetter 
Cc: amd-gfx@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Lee Jones 
Reviewed-by: Felix Kuehling 
Signed-off-by: Felix Kuehling 
Signed-off-by: Alex Deucher 
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: make CRAT table missing message informational only

2022-04-13T17:27:17+00:00

[ Upstream commit 9dff13f9edf755a15f6507874185a3290c1ae8bb ]

The driver has a fallback so make the message informational
rather than a warning. The driver has a fallback if the
Component Resource Association Table (CRAT) is missing, so
make this informational now.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1906
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdkfd: svm range restore work deadlock when process exit

2022-04-13T17:27:09+00:00

[ Upstream commit 6225bb3a88d22594aacea2485dc28ca12d596721 ]

kfd_process_notifier_release flush svm_range_restore_work
which calls svm_range_list_lock_and_flush_work to flush deferred_list
work, but if deferred_list work mmput release the last user, it will
call exit_mmap -> notifier_release, it is deadlock with below backtrace.

Move flush svm_range_restore_work to kfd_process_wq_release to avoid
deadlock. Then svm_range_restore_work take task->mm ref to avoid mm is
gone while validating and mapping ranges to GPU.

Workqueue: events svm_range_deferred_list_work [amdgpu]
Call Trace:
 wait_for_completion+0x94/0x100
 __flush_work+0x12a/0x1e0
 __cancel_work_timer+0x10e/0x190
 cancel_delayed_work_sync+0x13/0x20
 kfd_process_notifier_release+0x98/0x2a0 [amdgpu]
 __mmu_notifier_release+0x74/0x1f0
 exit_mmap+0x170/0x200
 mmput+0x5d/0x130
 svm_range_deferred_list_work+0x104/0x230 [amdgpu]
 process_one_work+0x220/0x3c0

Signed-off-by: Philip Yang 
Reported-by: Ruili Ji 
Tested-by: Ruili Ji 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdkfd: Ensure mm remain valid in svm deferred_list work

2022-04-13T17:27:09+00:00

[ Upstream commit 367c9b0f1b8750a704070e7ae85234d591290434 ]

svm_deferred_list work should continue to handle deferred_range_list
which maybe split to child range to avoid child range leak, and remove
ranges mmu interval notifier to avoid mm mm_count leak. So taking mm
reference when adding range to deferred list, to ensure mm is valid in
the scheduled deferred_list_work, and drop the mm referrence after range
is handled.

Signed-off-by: Philip Yang 
Reported-by: Ruili Ji 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdkfd: Don't take process mutex for svm ioctls

2022-04-13T17:27:09+00:00

[ Upstream commit ac7c48c0cce00d03b3c95fddcccb0a45257e33e3 ]

SVM ioctls take proper svms->lock to handle race conditions, don't need
take process mutex to serialize ioctls. This also fixes circular locking
warning:

WARNING: possible circular locking dependency detected

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock((work_completion)(&svms->deferred_list_work));
                                lock(&process->mutex);
                     lock((work_completion)(&svms->deferred_list_work));
   lock(&process->mutex);

   *** DEADLOCK ***

Signed-off-by: Philip Yang 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdkfd: enable heavy-weight TLB flush on Arcturus

2022-04-13T17:27:08+00:00

[ Upstream commit f61c40c0757a79bcf744314df606c2bc8ae6a729 ]

SDMA FW fixes the hang issue for adding heavy-weight TLB
flush on Arcturus, so we can enable it.

Signed-off-by: Eric Huang 
Acked-by: Alex Deucher 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin