Skip to contentSkip to conversation

drm/amdgpu: Fix the warning info in mode1 reset

PATCH In review Ma Jun 3 participants 3 messages Jan 5, 2024 – Jan 23, 2024

Subsystems (2)
lore
Share & tools
lore

Ma Jun

author
#0 lore raw

PATCH v2 1/1 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)

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  6 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c   | 14 +++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h   |  2 +-
 3 files changed, 17 insertions(+), 5 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3 -3
index 4b1d5f42249f..d0d82e69b034 100644
@@ -5700,7 +5700,7 @@ 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);
@@ -5776,7 +5776,7 @@ 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);
@@ -6265,7 +6265,7 @@ 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 +13 -1
index 41266bc99345..9555d5532d8e 100644
@@ -636,7 +636,8 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring)
 		DRM_DEV_DEBUG(adev->dev, "ring test on %s succeeded\n",
 			      ring->name);
 
-	ring->sched.ready = !r;
+	if (!ring->no_scheduler)
+		ring->sched.ready = !r;
 	return r;
 }
 
@@ -719,3 +720,14 @@ 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
index bbb53720a018..fe1a61eb6e4c 100644
@@ -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
Signature · 1 line
2.34.1
#1 lore raw

ping...

Quoted 108 lines · Ma Jun

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)

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  6 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c   | 14 +++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h   |  2 +-
 3 files changed, 17 insertions(+), 5 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3 -3
index 4b1d5f42249f..d0d82e69b034 100644
@@ -5700,7 +5700,7 @@ 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);
@@ -5776,7 +5776,7 @@ 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);
@@ -6265,7 +6265,7 @@ 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 +13 -1
index 41266bc99345..9555d5532d8e 100644
@@ -636,7 +636,8 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring)
 		DRM_DEV_DEBUG(adev->dev, "ring test on %s succeeded\n",
 			      ring->name);
 
-	ring->sched.ready = !r;
+	if (!ring->no_scheduler)
+		ring->sched.ready = !r;
 	return r;
 }
 
@@ -719,3 +720,14 @@ 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
index bbb53720a018..fe1a61eb6e4c 100644
@@ -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
Reviewed-by on v2 1/1
#2 lore raw
In reply to Ma Jun
Quoted 21 lines · Ma Jun

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]
Quoted 6 lines

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

Quoted 85 lines

v2:
- Rename the function to amdgpu_ring_sched_ready and move it to
amdgpu_ring.c (Alex)

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  6 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c   | 14 +++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h   |  2 +-
 3 files changed, 17 insertions(+), 5 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3 -3
index 4b1d5f42249f..d0d82e69b034 100644
@@ -5700,7 +5700,7 @@ 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);
@@ -5776,7 +5776,7 @@ 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);
@@ -6265,7 +6265,7 @@ 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 +13 -1
index 41266bc99345..9555d5532d8e 100644
@@ -636,7 +636,8 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring)
                DRM_DEV_DEBUG(adev->dev, "ring test on %s succeeded\n",
                              ring->name);
 
-       ring->sched.ready = !r;
+       if (!ring->no_scheduler)
+               ring->sched.ready = !r;
        return r;
 }
 
@@ -719,3 +720,14 @@ 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 -2
index bbb53720a018..fe1a61eb6e4c 100644
@@ -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
--

2.34.1