diff options
| author | Dennis Li <Dennis.Li@amd.com> | 2020-08-20 05:06:32 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2020-08-24 19:23:48 +0300 |
| commit | 6049db43d6dd9cbb9d7f897839d15b0bc600e23c (patch) | |
| tree | ada04bea31c2af434811ffdcc34471859a603925 /drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | |
| parent | 66b8a9c0a747b9d05509d480f5054a65ac327515 (diff) | |
| download | linux-6049db43d6dd9cbb9d7f897839d15b0bc600e23c.tar.xz | |
drm/amdgpu: change reset lock from mutex to rw_semaphore
clients don't need reset-lock for synchronization when no
GPU recovery.
v2:
change to return the return value of down_read_killable.
v3:
if GPU recovery begin, VF ignore FLR notification.
Reviewed-by: Monk Liu <monk.liu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 18 |
1 files changed, 6 insertions, 12 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 3cb10ab943a6..9c23abf9b140 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -259,19 +259,15 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, flr_work); struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt); int timeout = NV_MAILBOX_POLL_FLR_TIMEDOUT; - int locked; /* block amdgpu_gpu_recover till msg FLR COMPLETE received, * otherwise the mailbox msg will be ruined/reseted by * the VF FLR. - * - * we can unlock the lock_reset to allow "amdgpu_job_timedout" - * to run gpu_recover() after FLR_NOTIFICATION_CMPL received - * which means host side had finished this VF's FLR. */ - locked = mutex_trylock(&adev->lock_reset); - if (locked) - atomic_set(&adev->in_gpu_reset, 1); + if (!down_read_trylock(&adev->reset_sem)) + return; + + atomic_set(&adev->in_gpu_reset, 1); do { if (xgpu_nv_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL) @@ -282,10 +278,8 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) } while (timeout > 1); flr_done: - if (locked) { - atomic_set(&adev->in_gpu_reset, 0); - mutex_unlock(&adev->lock_reset); - } + atomic_set(&adev->in_gpu_reset, 0); + up_read(&adev->reset_sem); /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) |