bybrooklyn/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-04-18 14:53:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: revert "fix system hang issue during GPU reset"

Browse Source 
The whole approach wasn't thought through till the end.

We already had a reset lock like this in the past and it caused the same problems like this one.

Completely revert the patch for now and add individual trylock protection to the hardware access functions as necessary.

This reverts commit df9c8d1aa2.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Christian König
2020-08-12 17:48:26 +02:00
committed by Alex Deucher
parent 05f39286ce
commit f1403342eb
39 changed files with 184 additions and 469 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
View File

@@ -259,16 +259,20 @@ 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 reset_sem to allow "amdgpu_job_timedout"
* 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.
*/
down_read(&adev->reset_sem);
locked = mutex_trylock(&adev->lock_reset);
if (locked)
adev->in_gpu_reset = true;
do {
if (xgpu_nv_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
goto flr_done;
@@ -278,7 +282,10 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
} while (timeout > 1);
flr_done:
up_read(&adev->reset_sem);
if (locked) {
adev->in_gpu_reset = false;
mutex_unlock(&adev->lock_reset);
}
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)