Commit bb34bc2c authored by Ma Jun's avatar Ma Jun Committed by Alex Deucher
Browse files

drm/amdgpu: Fix the warning info in mode1 reset 

Fix the warning info below during mode1 reset.
[  +0.000004] Call Trace:
[  +0.000004]  <TASK>
[  +0.000006]  ? show_regs+0x6e/0x80
[  +0.000011]  ? __flush_work.isra.0+0x2e8/0x390
[  +0.000005]  ? __warn+0x91/0x150
[  +0.000009]  ? __flush_work.isra.0+0x2e8/0x390
[  +0.000006]  ? report_bug+0x19d/0x1b0
[  +0.000013]  ? handle_bug+0x46/0x80
[  +0.000012]  ? exc_invalid_op+0x1d/0x80
[  +0.000011]  ? asm_exc_invalid_op+0x1f/0x30
[  +0.000014]  ? __flush_work.isra.0+0x2e8/0x390
[  +0.000007]  ? __flush_work.isra.0+0x208/0x390
[  +0.000007]  ? _prb_read_valid+0x216/0x290
[  +0.000008]  __cancel_work_timer+0x11d/0x1a0
[  +0.000007]  ? try_to_grab_pending+0xe8/0x190
[  +0.000012]  cancel_work_sync+0x14/0x20
[  +0.000008]  amddrm_sched_stop+0x3c/0x1d0 [amd_sched]
[  +0.000032]  amdgpu_device_gpu_recover+0x29a/0xe90 [amdgpu]

This warning info was printed after applying the patch
"drm/sched: Convert drm scheduler to use a work queue rather than kthread".
The root cause is that amdgpu driver tries to use the uninitialized
work_struct in the struct drm_gpu_scheduler

v2:
 - Rename the function to amdgpu_ring_sched_ready and move it to
amdgpu_ring.c (Alex)
v3:
- Fix a few more checks based on Vitaly's patch (Alex)
v4:
- squash in fix noticed by Bert in
https://gitlab.freedesktop.org/drm/amd/-/issues/3139



Fixes: 11b3b9f4 ("drm/sched: Check scheduler ready before calling timeout handling")
Reviewed-by: default avatarAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: default avatarVitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: default avatarMa Jun <Jun.Ma2@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent faf51b20

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c

+1 −1
Original line number Diff line number Diff line
@@ -290,7 +290,7 @@ static int suspend_resume_compute_scheduler(struct amdgpu_device *adev, bool sus 
	for (i = 0; i < adev->gfx.num_compute_rings; i++) {

		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];



		if (!(ring && drm_sched_wqueue_ready(&ring->sched)))

		if (!amdgpu_ring_sched_ready(ring))

			continue;



		/* stop secheduler and drain ring. */

drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c

+4 −4
Original line number Diff line number Diff line
@@ -1678,7 +1678,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused) 
	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {

		struct amdgpu_ring *ring = adev->rings[i];



		if (!ring || !drm_sched_wqueue_ready(&ring->sched))

		if (!amdgpu_ring_sched_ready(ring))

			continue;

		drm_sched_wqueue_stop(&ring->sched);

	}
@@ -1694,7 +1694,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused) 
	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {

		struct amdgpu_ring *ring = adev->rings[i];



		if (!ring || !drm_sched_wqueue_ready(&ring->sched))

		if (!amdgpu_ring_sched_ready(ring))

			continue;

		drm_sched_wqueue_start(&ring->sched);

	}
@@ -1916,8 +1916,8 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val) 


	ring = adev->rings[val];



	if (!ring || !ring->funcs->preempt_ib ||

	    !drm_sched_wqueue_ready(&ring->sched))

	if (!amdgpu_ring_sched_ready(ring) ||

	    !ring->funcs->preempt_ib)

		return -EINVAL;



	/* the last preemption failed */

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

+6 −6
Original line number Diff line number Diff line
@@ -5021,7 +5021,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev) 
	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {

		struct amdgpu_ring *ring = adev->rings[i];



		if (!ring || !drm_sched_wqueue_ready(&ring->sched))

		if (!amdgpu_ring_sched_ready(ring))

			continue;



		spin_lock(&ring->sched.job_list_lock);
@@ -5160,7 +5160,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, 
	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {

		struct amdgpu_ring *ring = adev->rings[i];



		if (!ring || !drm_sched_wqueue_ready(&ring->sched))

		if (!amdgpu_ring_sched_ready(ring))

			continue;



		/* Clear job fence from fence drv to avoid force_completion
@@ -5627,7 +5627,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, 
		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {

			struct amdgpu_ring *ring = tmp_adev->rings[i];



			if (!ring || !drm_sched_wqueue_ready(&ring->sched))

			if (!amdgpu_ring_sched_ready(ring))

				continue;



			drm_sched_stop(&ring->sched, job ? &job->base : NULL);
@@ -5696,7 +5696,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, 
		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {

			struct amdgpu_ring *ring = tmp_adev->rings[i];



			if (!ring || !drm_sched_wqueue_ready(&ring->sched))

			if (!amdgpu_ring_sched_ready(ring))

				continue;



			drm_sched_start(&ring->sched, true);
@@ -6051,7 +6051,7 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta 
		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {

			struct amdgpu_ring *ring = adev->rings[i];



			if (!ring || !drm_sched_wqueue_ready(&ring->sched))

			if (!amdgpu_ring_sched_ready(ring))

				continue;



			drm_sched_stop(&ring->sched, NULL);
@@ -6179,7 +6179,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev) 
	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {

		struct amdgpu_ring *ring = adev->rings[i];



		if (!ring || !drm_sched_wqueue_ready(&ring->sched))

		if (!amdgpu_ring_sched_ready(ring))

			continue;



		drm_sched_start(&ring->sched, true);

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c

+12 −0
Original line number Diff line number Diff line
@@ -635,6 +635,7 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring) 
			      ring->name);



	ring->sched.ready = !r;



	return r;

}
@@ -717,3 +718,14 @@ void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring) 
	if (ring->is_sw_ring)

		amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_DE);

}



bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring)

{

	if (!ring)

		return false;



	if (ring->no_scheduler || !drm_sched_wqueue_ready(&ring->sched))

		return false;



	return true;

}

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h

+1 −1
Original line number Diff line number Diff line
@@ -450,5 +450,5 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, 
int amdgpu_ib_pool_init(struct amdgpu_device *adev);

void amdgpu_ib_pool_fini(struct amdgpu_device *adev);

int amdgpu_ib_ring_tests(struct amdgpu_device *adev);



bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring);

#endif