[PATCH 3/5] drm/amdgpu:use new gpu recover routine

Monk Liu Monk.Liu at amd.com
Tue Oct 24 08:42:12 UTC 2017


retire gpu_reset and sriov_gpu_reset and use new implemented
amdgpu_gpu_recover

Change-Id: Ib1de998eaffe7ed2bdd398a4f1b4ca62f9abf2a6
Signed-off-by: Monk Liu <Monk.Liu at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |   2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 307 +----------------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c  |  10 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c    |   2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c    |   5 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h   |   1 -
 drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c      |   2 +-
 drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c      |   2 +-
 8 files changed, 19 insertions(+), 312 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 003668f..335df11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1844,7 +1844,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_psp_check_fw_loading_status(adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i))
 
 /* Common functions */
-int amdgpu_gpu_reset(struct amdgpu_device *adev);
+int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job* job);
 bool amdgpu_need_backup(struct amdgpu_device *adev);
 void amdgpu_pci_config_reset(struct amdgpu_device *adev);
 bool amdgpu_need_post(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 1f1b92e..ee306c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2818,304 +2818,6 @@ static int amdgpu_recover_vram_from_shadow(struct amdgpu_device *adev,
 	return r;
 }
 
-/**
- * amdgpu_sriov_gpu_reset - reset the asic
- *
- * @adev: amdgpu device pointer
- * @job: which job trigger hang
- *
- * Attempt the reset the GPU if it has hung (all asics).
- * for SRIOV case.
- * Returns 0 for success or an error on failure.
- */
-int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job)
-{
-	int i, j, r = 0;
-	int resched;
-	struct amdgpu_bo *bo, *tmp;
-	struct amdgpu_ring *ring;
-	struct dma_fence *fence = NULL, *next = NULL;
-
-	mutex_lock(&adev->virt.lock_reset);
-	atomic_inc(&adev->gpu_reset_counter);
-	adev->in_sriov_reset = true;
-
-	/* block TTM */
-	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
-
-	/* we start from the ring trigger GPU hang */
-	j = job ? job->ring->idx : 0;
-
-	/* block scheduler */
-	for (i = j; i < j + AMDGPU_MAX_RINGS; ++i) {
-		ring = adev->rings[i % AMDGPU_MAX_RINGS];
-		if (!ring || !ring->sched.thread)
-			continue;
-
-		kthread_park(ring->sched.thread);
-
-		if (job && j != i)
-			continue;
-
-		/* here give the last chance to check if job removed from mirror-list
-		 * since we already pay some time on kthread_park */
-		if (job && list_empty(&job->base.node)) {
-			kthread_unpark(ring->sched.thread);
-			goto give_up_reset;
-		}
-
-		if (amd_sched_invalidate_job(&job->base, amdgpu_job_hang_limit))
-			amd_sched_job_kickout(&job->base);
-
-		/* only do job_reset on the hang ring if @job not NULL */
-		amd_sched_hw_job_reset(&ring->sched, NULL);
-
-		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
-		amdgpu_fence_driver_force_completion(ring);
-	}
-
-	/* request to take full control of GPU before re-initialization  */
-	if (job)
-		amdgpu_virt_reset_gpu(adev);
-	else
-		amdgpu_virt_request_full_gpu(adev, true);
-
-
-	/* Resume IP prior to SMC */
-	amdgpu_sriov_reinit_early(adev);
-
-	/* we need recover gart prior to run SMC/CP/SDMA resume */
-	amdgpu_ttm_recover_gart(adev);
-
-	/* now we are okay to resume SMC/CP/SDMA */
-	amdgpu_sriov_reinit_late(adev);
-
-	amdgpu_irq_gpu_reset_resume_helper(adev);
-
-	if (amdgpu_ib_ring_tests(adev))
-		dev_err(adev->dev, "[GPU_RESET] ib ring test failed (%d).\n", r);
-
-	/* release full control of GPU after ib test */
-	amdgpu_virt_release_full_gpu(adev, true);
-
-	DRM_INFO("recover vram bo from shadow\n");
-
-	ring = adev->mman.buffer_funcs_ring;
-	mutex_lock(&adev->shadow_list_lock);
-	list_for_each_entry_safe(bo, tmp, &adev->shadow_list, shadow_list) {
-		next = NULL;
-		amdgpu_recover_vram_from_shadow(adev, ring, bo, &next);
-		if (fence) {
-			r = dma_fence_wait(fence, false);
-			if (r) {
-				WARN(r, "recovery from shadow isn't completed\n");
-				break;
-			}
-		}
-
-		dma_fence_put(fence);
-		fence = next;
-	}
-	mutex_unlock(&adev->shadow_list_lock);
-
-	if (fence) {
-		r = dma_fence_wait(fence, false);
-		if (r)
-			WARN(r, "recovery from shadow isn't completed\n");
-	}
-	dma_fence_put(fence);
-
-	for (i = j; i < j + AMDGPU_MAX_RINGS; ++i) {
-		ring = adev->rings[i % AMDGPU_MAX_RINGS];
-		if (!ring || !ring->sched.thread)
-			continue;
-
-		if (job && j != i) {
-			kthread_unpark(ring->sched.thread);
-			continue;
-		}
-
-		amd_sched_job_recovery(&ring->sched);
-		kthread_unpark(ring->sched.thread);
-	}
-
-	drm_helper_resume_force_mode(adev->ddev);
-give_up_reset:
-	ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);
-	if (r) {
-		/* bad news, how to tell it to userspace ? */
-		dev_info(adev->dev, "GPU reset failed\n");
-	} else {
-		dev_info(adev->dev, "GPU reset successed!\n");
-	}
-
-	adev->in_sriov_reset = false;
-	mutex_unlock(&adev->virt.lock_reset);
-	return r;
-}
-
-/**
- * amdgpu_gpu_reset - reset the asic
- *
- * @adev: amdgpu device pointer
- *
- * Attempt the reset the GPU if it has hung (all asics).
- * Returns 0 for success or an error on failure.
- */
-int amdgpu_gpu_reset(struct amdgpu_device *adev)
-{
-	struct drm_atomic_state *state = NULL;
-	int i, r;
-	int resched;
-	bool need_full_reset, vram_lost = false;
-
-	if (!amdgpu_check_soft_reset(adev)) {
-		DRM_INFO("No hardware hang detected. Did some blocks stall?\n");
-		return 0;
-	}
-
-	atomic_inc(&adev->gpu_reset_counter);
-
-	/* block TTM */
-	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
-	/* store modesetting */
-	if (amdgpu_device_has_dc_support(adev))
-		state = drm_atomic_helper_suspend(adev->ddev);
-
-	/* block scheduler */
-	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
-		struct amdgpu_ring *ring = adev->rings[i];
-
-		if (!ring || !ring->sched.thread)
-			continue;
-		kthread_park(ring->sched.thread);
-		amd_sched_hw_job_reset(&ring->sched, NULL);
-		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
-		amdgpu_fence_driver_force_completion(ring);
-	}
-
-	need_full_reset = amdgpu_need_full_reset(adev);
-
-	if (!need_full_reset) {
-		amdgpu_pre_soft_reset(adev);
-		r = amdgpu_soft_reset(adev);
-		amdgpu_post_soft_reset(adev);
-		if (r || amdgpu_check_soft_reset(adev)) {
-			DRM_INFO("soft reset failed, will fallback to full reset!\n");
-			need_full_reset = true;
-		}
-	}
-
-	if (need_full_reset) {
-		r = amdgpu_suspend(adev);
-
-retry:
-		amdgpu_atombios_scratch_regs_save(adev);
-		r = amdgpu_asic_reset(adev);
-		amdgpu_atombios_scratch_regs_restore(adev);
-		/* post card */
-		amdgpu_atom_asic_init(adev->mode_info.atom_context);
-
-		if (!r) {
-			dev_info(adev->dev, "GPU reset succeeded, trying to resume\n");
-			r = amdgpu_resume_phase1(adev);
-			if (r)
-				goto out;
-			vram_lost = amdgpu_check_vram_lost(adev);
-			if (vram_lost) {
-				DRM_ERROR("VRAM is lost!\n");
-				atomic_inc(&adev->vram_lost_counter);
-			}
-			r = amdgpu_ttm_recover_gart(adev);
-			if (r)
-				goto out;
-			r = amdgpu_resume_phase2(adev);
-			if (r)
-				goto out;
-			if (vram_lost)
-				amdgpu_fill_reset_magic(adev);
-		}
-	}
-out:
-	if (!r) {
-		amdgpu_irq_gpu_reset_resume_helper(adev);
-		r = amdgpu_ib_ring_tests(adev);
-		if (r) {
-			dev_err(adev->dev, "ib ring test failed (%d).\n", r);
-			r = amdgpu_suspend(adev);
-			need_full_reset = true;
-			goto retry;
-		}
-		/**
-		 * recovery vm page tables, since we cannot depend on VRAM is
-		 * consistent after gpu full reset.
-		 */
-		if (need_full_reset && amdgpu_need_backup(adev)) {
-			struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
-			struct amdgpu_bo *bo, *tmp;
-			struct dma_fence *fence = NULL, *next = NULL;
-
-			DRM_INFO("recover vram bo from shadow\n");
-			mutex_lock(&adev->shadow_list_lock);
-			list_for_each_entry_safe(bo, tmp, &adev->shadow_list, shadow_list) {
-				next = NULL;
-				amdgpu_recover_vram_from_shadow(adev, ring, bo, &next);
-				if (fence) {
-					r = dma_fence_wait(fence, false);
-					if (r) {
-						WARN(r, "recovery from shadow isn't completed\n");
-						break;
-					}
-				}
-
-				dma_fence_put(fence);
-				fence = next;
-			}
-			mutex_unlock(&adev->shadow_list_lock);
-			if (fence) {
-				r = dma_fence_wait(fence, false);
-				if (r)
-					WARN(r, "recovery from shadow isn't completed\n");
-			}
-			dma_fence_put(fence);
-		}
-		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
-			struct amdgpu_ring *ring = adev->rings[i];
-
-			if (!ring || !ring->sched.thread)
-				continue;
-
-			amd_sched_job_recovery(&ring->sched);
-			kthread_unpark(ring->sched.thread);
-		}
-	} else {
-		dev_err(adev->dev, "asic resume failed (%d).\n", r);
-		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
-			if (adev->rings[i] && adev->rings[i]->sched.thread) {
-				kthread_unpark(adev->rings[i]->sched.thread);
-			}
-		}
-	}
-
-	if (amdgpu_device_has_dc_support(adev)) {
-		r = drm_atomic_helper_resume(adev->ddev, state);
-		amdgpu_dm_display_resume(adev);
-	} else
-		drm_helper_resume_force_mode(adev->ddev);
-
-	ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);
-	if (r) {
-		/* bad news, how to tell it to userspace ? */
-		dev_info(adev->dev, "GPU reset failed\n");
-	}
-	else {
-		dev_info(adev->dev, "GPU reset successed!\n");
-	}
-
-	amdgpu_vf_error_trans_all(adev);
-	return r;
-}
-
 static int amdgpu_reset(struct amdgpu_device *adev, uint64_t* reset_flags)
 {
 	int r;
@@ -3239,6 +2941,15 @@ static int amdgpu_reset_sriov(struct amdgpu_device *adev, uint64_t *reset_flags,
 	return r;
 }
 
+/**
+ * amdgpu_gpu_recover - reset the asic and recover scheduler
+ *
+ * @adev: amdgpu device pointer
+ * @job: which job trigger hang
+ *
+ * Attempt to reset the GPU if it has hung (all asics).
+ * Returns 0 for success or an error on failure.
+ */
 int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job)
 {
 	struct drm_atomic_state *state = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index f43319c..e64d93f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -694,25 +694,25 @@ static int amdgpu_debugfs_fence_info(struct seq_file *m, void *data)
 }
 
 /**
- * amdgpu_debugfs_gpu_reset - manually trigger a gpu reset
+ * amdgpu_debugfs_gpu_recover - manually trigger a gpu reset & recover
  *
  * Manually trigger a gpu reset at the next fence wait.
  */
-static int amdgpu_debugfs_gpu_reset(struct seq_file *m, void *data)
+static int amdgpu_debugfs_gpu_recover(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 
-	seq_printf(m, "gpu reset\n");
-	amdgpu_gpu_reset(adev);
+	seq_printf(m, "gpu recover\n");
+	amdgpu_gpu_recover(adev, NULL);
 
 	return 0;
 }
 
 static const struct drm_info_list amdgpu_debugfs_fence_list[] = {
 	{"amdgpu_fence_info", &amdgpu_debugfs_fence_info, 0, NULL},
-	{"amdgpu_gpu_reset", &amdgpu_debugfs_gpu_reset, 0, NULL}
+	{"amdgpu_gpu_recover", &amdgpu_debugfs_gpu_recover, 0, NULL}
 };
 
 static const struct drm_info_list amdgpu_debugfs_fence_list_sriov[] = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 47c5ce9..9c2f87c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -88,7 +88,7 @@ static void amdgpu_irq_reset_work_func(struct work_struct *work)
 						  reset_work);
 
 	if (!amdgpu_sriov_vf(adev))
-		amdgpu_gpu_reset(adev);
+		amdgpu_gpu_recover(adev, NULL);
 }
 
 /* Disable *all* interrupts */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index a094a92..dfc6518 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -37,10 +37,7 @@ static void amdgpu_job_timedout(struct amd_sched_job *s_job)
 		  atomic_read(&job->ring->fence_drv.last_seq),
 		  job->ring->fence_drv.sync_seq);
 
-	if (amdgpu_sriov_vf(job->adev))
-		amdgpu_sriov_gpu_reset(job->adev, job);
-	else
-		amdgpu_gpu_reset(job->adev);
+	amdgpu_gpu_recover(job->adev, job);
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index b89d37f..3a661aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -285,7 +285,6 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);
 int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init);
 int amdgpu_virt_release_full_gpu(struct amdgpu_device *adev, bool init);
 int amdgpu_virt_reset_gpu(struct amdgpu_device *adev);
-int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job);
 int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev);
 void amdgpu_virt_free_mm_table(struct amdgpu_device *adev);
 int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index b4906d2..f8522a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -254,7 +254,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	}
 
 	/* Trigger recovery due to world switch failure */
-	amdgpu_sriov_gpu_reset(adev, NULL);
+	amdgpu_gpu_recover(adev, NULL);
 }
 
 static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index c25a831..dae6d3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
@@ -514,7 +514,7 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
 	}
 
 	/* Trigger recovery due to world switch failure */
-	amdgpu_sriov_gpu_reset(adev, NULL);
+	amdgpu_gpu_recover(adev, NULL);
 }
 
 static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,
-- 
2.7.4



More information about the amd-gfx mailing list