Merge tag 'amd-drm-next-5.10-2020-09-03' of git://people.freedesktop.org/~agd5f/linux into drm-next

amd-drm-next-5.10-2020-09-03:

amdgpu:
- RAS fixes
- Sienna Cichlid updates
- Navy Flounder updates
- DCE6 (SI) support in DC
- Enable plane rotation
- Rework pre-OS vram reservation handling during driver init
- Add standard interface to dump GPU metrics table from SMU
- Rework tiling and tmz state handling in atomic commits
- Pstate fixes
- Add voltage and power hwmon interfaces for renoir
- SW CTF fixes
- S/G display fix for Raven
- Print client strings for vmfaults for vega and newer
- Manual fan control fixes
- Display updates
- Reorg power management directory structure
- Misc bug fixes
- Misc code cleanups

amdkfd:
- Topology fixes
- Add SMI events for thermal throttling and GPU resets

radeon:
- switch from pci_* to dma_* for dma allocations
- PLL fix

Scheduler:
- Clean up priority levels

UAPI:
- amdgpu INFO IOCTL query update for TMZ state
  https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6049
- amdkfd SMI event interface updates
  https://github.com/RadeonOpenCompute/rocm_smi_lib/tree/therm_thrott

From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200903222921.4152-1-alexander.deucher@amd.com

1 files changed, 7 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 5fd67e1cc2a0..9c07014d9bd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -238,19 +238,15 @@ static void xgpu_ai_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 = AI_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)
-		adev->in_gpu_reset = true;
+	if (!down_read_trylock(&adev->reset_sem))
+		return;
+
+	atomic_set(&adev->in_gpu_reset, 1);
 
 	do {
 		if (xgpu_ai_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
@@ -261,14 +257,12 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	} while (timeout > 1);
 
 flr_done:
-	if (locked) {
-		adev->in_gpu_reset = false;
-		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)
-		&& adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT)
+		&& (amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
 		amdgpu_device_gpu_recover(adev, NULL);
 }