Skip to contentSkip to conversation

shadow page table support

PATCH New Chunming Zhou 1 participant 15 messages Jul 27, 2016 1 message not in the archive

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

cover shadow page table support

Since we cannot make sure VRAM is safe after gpu reset, page table backup is neccessary, shadow page table is sense way to recovery page talbe when gpu reset happens.
We need to allocate GTT bo as the shadow of VRAM bo when creating page table, and make them same. After gpu reset, we will need to use SDMA to copy GTT bo content to VRAM bo, then page table will be recoveried.

Chunming Zhou (14):
drm/amdgpu: irq resume should be immediately after gpu resume drm/amdgpu: add shadow bo support
drm/amdgpu: set shadow flag for pd/pt bo
drm/amdgpu: update shadow pt bo while update pt drm/amdgpu: update pd shadow while updating pd drm/amdgpu: implement amdgpu_vm_recover_page_table_from_shadow drm/amdgpu: link all vm clients
drm/amdgpu: add vm_list_lock
drm/amd: add block entity function
drm/amd: abstract entity wait idle
drm/amdgpu: recover page tables after gpu reset drm/amd: wait neccessary dependency before running job drm/amdgpu: add vm recover pt fence
drm/amdgpu: add backup condition for shadow page table

 drivers/gpu/drm/amd/amdgpu/amdgpu.h           |  15 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c        |   6 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    |  35 ++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c       |   5 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c    |  36 ++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c        | 216 ++++++++++++++++++++++----
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.c |  37 ++++-
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.h |   5 +
 include/uapi/drm/amdgpu_drm.h                 |   2 +
 9 files changed, 323 insertions(+), 34 deletions(-)
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

A message that is not in the archive (sent off-list or not yet received): 1469601498-17747-1-git-send-email-David1.Zhou-5C7GfCeVMHo@public.gmane.org

#2 lore raw

PATCH 1/14 drm/amdgpu: irq resume should be immediately after gpu resume

Change-Id Icf64bf5964f0ef66c239ab0679d51275cc272699
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1 -1
index eab931a..449ea00 100644
@@ -2143,6 +2143,7 @@ retry:
 		amdgpu_atombios_scratch_regs_restore(adev);
 	}
 	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);
@@ -2177,7 +2178,6 @@ retry:
 		/* bad news, how to tell it to userspace ? */
 		dev_info(adev->dev, "GPU reset failed\n");
 	}
-	amdgpu_irq_gpu_reset_resume_helper(adev);
 
 	return r;
 }
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#3 lore raw

PATCH 2/14 drm/amdgpu: add shadow bo support

In reply to a message not in the archive

shadow bo is the shadow of a bo, which is always in GTT, which can be used to backup the original bo.

Change-Id Ia27d4225c47ff41d3053eb691276e29fb2d64026
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 36 +++++++++++++++++++++++++++---
 include/uapi/drm/amdgpu_drm.h              |  2 ++
 3 files changed, 36 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +1 -0
index b7d9e66..7b4a0cf 100644
@@ -500,6 +500,7 @@ struct amdgpu_bo {
 	struct amdgpu_device		*adev;
 	struct drm_gem_object		gem_base;
 	struct amdgpu_bo		*parent;
+	struct amdgpu_bo		*shadow;
 
 	struct ttm_bo_kmap_obj		dma_buf_vmap;
 	struct amdgpu_mn		*mn;
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +33 -3
index 67de19c..6e59b4e 100644
@@ -356,6 +356,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 {
 	struct ttm_placement placement = {0};
 	struct ttm_place placements[AMDGPU_GEM_DOMAIN_MAX + 1];
+	int r;
 
 	memset(&placements, 0,
 	       (AMDGPU_GEM_DOMAIN_MAX + 1) * sizeof(struct ttm_place));
@@ -363,9 +364,32 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	amdgpu_ttm_placement_init(adev, &placement,
 				  placements, domain, flags);
 
-	return amdgpu_bo_create_restricted(adev, size, byte_align, kernel,
-					   domain, flags, sg, &placement,
-					   resv, bo_ptr);
+	r = amdgpu_bo_create_restricted(adev, size, byte_align, kernel,
+					domain, flags, sg, &placement,
+					resv, bo_ptr);
+	if (r)
+		return r;
+
+	if (flags & AMDGPU_GEM_CREATE_SHADOW) {
+		memset(&placements, 0,
+		       (AMDGPU_GEM_DOMAIN_MAX + 1) * sizeof(struct ttm_place));
+
+		amdgpu_ttm_placement_init(adev, &placement,
+					  placements, AMDGPU_GEM_DOMAIN_GTT,
+					  AMDGPU_GEM_CREATE_CPU_GTT_USWC);
+
+		r = amdgpu_bo_create_restricted(adev, size, byte_align, kernel,
+						AMDGPU_GEM_DOMAIN_GTT,
+						AMDGPU_GEM_CREATE_CPU_GTT_USWC,
+						NULL, &placement,
+						(*bo_ptr)->tbo.resv,
+						&(*bo_ptr)->shadow);
+		if (r)
+			amdgpu_bo_unref(bo_ptr);
+	} else
+		(*bo_ptr)->shadow = NULL;
+
+	return 0;
 }
 
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
@@ -422,6 +446,12 @@ void amdgpu_bo_unref(struct amdgpu_bo **bo)
 
 	if ((*bo) == NULL)
 		return;
+	if ((*bo)->flags & AMDGPU_GEM_CREATE_SHADOW) {
+		tbo = &((*bo)->shadow->tbo);
+		ttm_bo_unref(&tbo);
+		if (tbo == NULL)
+			(*bo)->shadow = NULL;
+	}
 
 	tbo = &((*bo)->tbo);
 	ttm_bo_unref(&tbo);
include/uapi/drm/amdgpu_drm.h +2 -0
index 946f238..2d756d9 100644
@@ -75,6 +75,8 @@
 #define AMDGPU_GEM_CREATE_NO_CPU_ACCESS		(1 << 1)
 /* Flag that USWC attributes should be used for GTT */
 #define AMDGPU_GEM_CREATE_CPU_GTT_USWC		(1 << 2)
+/* Flag that create shadow bo(GTT) while allocating vram bo */
+#define AMDGPU_GEM_CREATE_SHADOW		(1 << 3)
 
 struct drm_amdgpu_gem_create_in  {
 	/** the requested memory size */
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#4 lore raw

PATCH 3/14 drm/amdgpu: set shadow flag for pd/pt bo

In reply to a message not in the archive

the pd/pt shadow bo will be used to backup page table, when gpu reset happens, we can restore the page table by them.

Change-Id I31eeb581f203d1db0654a48745ef4e64ed40ed9b
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h    |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 16 +++++++++++++---
 2 files changed, 15 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +2 -0
index 7b4a0cf..4b3c6d2 100644
@@ -869,6 +869,8 @@ struct amdgpu_ring {
 struct amdgpu_vm_pt {
 	struct amdgpu_bo_list_entry	entry;
 	uint64_t			addr;
+	struct amdgpu_bo_list_entry	entry_shadow;
+	uint64_t			addr_shadow;
 };
 
 struct amdgpu_vm {
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +13 -3
index 38c80ea..aedd1cb 100644
@@ -1331,9 +1331,10 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = saddr; pt_idx <= eaddr; ++pt_idx) {
 		struct reservation_object *resv = vm->page_directory->tbo.resv;
-		struct amdgpu_bo_list_entry *entry;
+		struct amdgpu_bo_list_entry *entry, *entry_shadow;
 		struct amdgpu_bo *pt;
 
+		entry_shadow = &vm->page_tables[pt_idx].entry_shadow;
 		entry = &vm->page_tables[pt_idx].entry;
 		if (entry->robj)
 			continue;
@@ -1341,7 +1342,8 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		r = amdgpu_bo_create(adev, AMDGPU_VM_PTE_COUNT * 8,
 				     AMDGPU_GPU_PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_VRAM,
-				     AMDGPU_GEM_CREATE_NO_CPU_ACCESS,
+				     AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
+				     AMDGPU_GEM_CREATE_SHADOW,
 				     NULL, resv, &pt);
 		if (r)
 			goto error_free;
@@ -1363,6 +1365,13 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		entry->tv.shared = true;
 		entry->user_pages = NULL;
 		vm->page_tables[pt_idx].addr = 0;
+
+		entry_shadow->robj = pt->shadow;
+		entry_shadow->priority = 0;
+		entry_shadow->tv.bo = &entry_shadow->robj->tbo;
+		entry_shadow->tv.shared = true;
+		entry_shadow->user_pages = NULL;
+		vm->page_tables[pt_idx].addr_shadow = 0;
 	}
 
 	return 0;
@@ -1540,7 +1549,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	r = amdgpu_bo_create(adev, pd_size, align, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
-			     AMDGPU_GEM_CREATE_NO_CPU_ACCESS,
+			     AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
+			     AMDGPU_GEM_CREATE_SHADOW,
 			     NULL, NULL, &vm->page_directory);
 	if (r)
 		goto error_free_sched_entity;
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#5 lore raw

PATCH 4/14 drm/amdgpu: update shadow pt bo while update pt

In reply to a message not in the archive
Change-Id I8245cdad490d2a0b8cf4b9320e53e14db0b6add4
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +12 -4
index aedd1cb..e7a400d 100644
@@ -651,6 +651,7 @@ int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
 		if (vm->page_tables[pt_idx].addr == pt)
 			continue;
 		vm->page_tables[pt_idx].addr = pt;
+		vm->page_tables[pt_idx].addr_shadow = pt;
 
 		pde = pd_addr + pt_idx * 8;
 		if (((last_pde + 8 * count) != pde) ||
@@ -801,7 +802,7 @@ static void amdgpu_vm_update_ptes(struct amdgpu_device *adev,
 					*vm_update_params,
 				  struct amdgpu_vm *vm,
 				  uint64_t start, uint64_t end,
-				  uint64_t dst, uint32_t flags)
+				  uint64_t dst, uint32_t flags, bool shadow)
 {
 	const uint64_t mask = AMDGPU_VM_PTE_COUNT - 1;
 
@@ -815,7 +816,8 @@ static void amdgpu_vm_update_ptes(struct amdgpu_device *adev,
 	/* initialize the variables */
 	addr = start;
 	pt_idx = addr >> amdgpu_vm_block_size;
-	pt = vm->page_tables[pt_idx].entry.robj;
+	pt = shadow ? vm->page_tables[pt_idx].entry_shadow.robj :
+		vm->page_tables[pt_idx].entry.robj;
 
 	if ((addr & ~mask) == (end & ~mask))
 		nptes = end - addr;
@@ -834,7 +836,8 @@ static void amdgpu_vm_update_ptes(struct amdgpu_device *adev,
 	/* walk over the address space and update the page tables */
 	while (addr < end) {
 		pt_idx = addr >> amdgpu_vm_block_size;
-		pt = vm->page_tables[pt_idx].entry.robj;
+		pt = shadow ? vm->page_tables[pt_idx].entry_shadow.robj :
+			vm->page_tables[pt_idx].entry.robj;
 
 		if ((addr & ~mask) == (end & ~mask))
 			nptes = end - addr;
@@ -941,6 +944,8 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 		/* two extra commands for begin/end of fragment */
 		ndw += 2 * 10;
 	}
+	/* double ndw, since need to update shadow pt bo as well */
+	ndw *= 2;
 
 	r = amdgpu_job_alloc_with_ib(adev, ndw * 4, &job);
 	if (r)
@@ -960,9 +965,12 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	r = reservation_object_reserve_shared(vm->page_directory->tbo.resv);
 	if (r)
 		goto error_free;
+	/* update shadow pt bo */
+	amdgpu_vm_update_ptes(adev, &vm_update_params, vm, start,
+			      last + 1, addr, flags, true);
 
 	amdgpu_vm_update_ptes(adev, &vm_update_params, vm, start,
-			      last + 1, addr, flags);
+			      last + 1, addr, flags, false);
 
 	amdgpu_ring_pad_ib(ring, vm_update_params.ib);
 	WARN_ON(vm_update_params.ib->length_dw > ndw);
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#6 lore raw

PATCH 5/14 drm/amdgpu: update pd shadow while updating pd

In reply to a message not in the archive
Change-Id Icafa90a6625ea7b5ab3e360ba0d73544cda251b0
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h    |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 68 +++++++++++++++++++++++-----------
 2 files changed, 48 insertions(+), 21 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +1 -0
index 4b3c6d2..a7951aa 100644
@@ -891,6 +891,7 @@ struct amdgpu_vm {
 
 	/* contains the page directory */
 	struct amdgpu_bo	*page_directory;
+	struct amdgpu_bo_list_entry	pd_entry_shadow;
 	unsigned		max_pde_used;
 	struct fence		*page_directory_fence;
 	uint64_t		last_eviction_counter;
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +47 -21

105 lines not on this page · raw message

Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#7 lore raw

PATCH 6/14 drm/amdgpu: implement amdgpu_vm_recover_page_table_from_shadow

In reply to a message not in the archive
Change-Id I9957e726576289448911f5fb2ff7bcb9311a1906
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h    |  2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 77 ++++++++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +2 -0
index a7951aa..1f941c4a 100644
@@ -1000,6 +1000,8 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
 		       uint64_t addr);
 void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 		      struct amdgpu_bo_va *bo_va);
+int amdgpu_vm_recover_page_table_from_shadow(struct amdgpu_device *adev,
+					     struct amdgpu_vm *vm);
 
 /*
  * context related structures
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +77 -0

83 lines not on this page · raw message

Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#8 lore raw

PATCH 7/14 drm/amdgpu: link all vm clients

In reply to a message not in the archive

Add vm client to list tail when creating it, move to head while submit to scheduler.

Change-Id I0625092f918853303a5ee97ea2eac87fb790ed69
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        | 6 ++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c     | 4 ++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c     | 3 +++
 4 files changed, 15 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +6 -0
index 1f941c4a..7e93d34 100644
@@ -889,6 +889,9 @@ struct amdgpu_vm {
 	/* BO mappings freed, but not yet updated in the PT */
 	struct list_head	freed;
 
+	/* vm itself list */
+	struct list_head	list;
+
 	/* contains the page directory */
 	struct amdgpu_bo	*page_directory;
 	struct amdgpu_bo_list_entry	pd_entry_shadow;
@@ -2160,6 +2163,9 @@ struct amdgpu_device {
 	struct kfd_dev          *kfd;
 
 	struct amdgpu_virtualization virtualization;
+
+	/* link all vm clients */
+	struct list_head		vm_list;
 };
 
 bool amdgpu_device_is_px(struct drm_device *dev);
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +4 -0
index 45d5227..d19838b 100644
@@ -835,7 +835,10 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			    union drm_amdgpu_cs *cs)
 {
+	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_ring *ring = p->job->ring;
+	struct amdgpu_device *adev = ring->adev;
 	struct amd_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
 	struct amdgpu_job *job;
 	int r;
@@ -858,6 +861,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	trace_amdgpu_cs_ioctl(job);
 	amd_sched_entity_push_job(&job->base);
+	list_move(&vm->list, &adev->vm_list);
 
 	return 0;
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2 -0
index 449ea00..877afb5 100644
@@ -1559,6 +1559,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	spin_lock_init(&adev->gc_cac_idx_lock);
 	spin_lock_init(&adev->audio_endpt_idx_lock);
 
+	INIT_LIST_HEAD(&adev->vm_list);
+
 	adev->rmmio_base = pci_resource_start(adev->pdev, 5);
 	adev->rmmio_size = pci_resource_len(adev->pdev, 5);
 	adev->rmmio = ioremap(adev->rmmio_base, adev->rmmio_size);
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +3 -0
index 4f95dc4..35d939b 100644
@@ -1628,6 +1628,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	INIT_LIST_HEAD(&vm->invalidated);
 	INIT_LIST_HEAD(&vm->cleared);
 	INIT_LIST_HEAD(&vm->freed);
+	INIT_LIST_HEAD(&vm->list);
 
 	pd_size = amdgpu_vm_directory_size(adev);
 	pd_entries = amdgpu_vm_num_pdes(adev);
@@ -1675,6 +1676,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	vm->pd_entry_shadow.tv.bo = &vm->page_directory->shadow->tbo;
 	vm->pd_entry_shadow.tv.shared = true;
 	vm->pd_entry_shadow.user_pages = NULL;
+	list_add_tail(&vm->list, &adev->vm_list);
 
 	return 0;
 
@@ -1702,6 +1704,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	struct amdgpu_bo_va_mapping *mapping, *tmp;
 	int i;
 
+	list_del(&vm->list);
 	amd_sched_entity_fini(vm->entity.sched, &vm->entity);
 
 	if (!RB_EMPTY_ROOT(&vm->va)) {
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#9 lore raw

PATCH 8/14 drm/amdgpu: add vm_list_lock

In reply to a message not in the archive

To lock adev->vm_list.

Change-Id I74d309eca9c22d190dd4072c69d26fa7fdea8884
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        | 1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c     | 2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c     | 4 ++++
 4 files changed, 8 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +1 -0
index 7e93d34..357d56a6 100644
@@ -2166,6 +2166,7 @@ struct amdgpu_device {
 
 	/* link all vm clients */
 	struct list_head		vm_list;
+	spinlock_t			vm_list_lock;
 };
 
 bool amdgpu_device_is_px(struct drm_device *dev);
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +2 -0
index d19838b..29c10f4 100644
@@ -861,7 +861,9 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	trace_amdgpu_cs_ioctl(job);
 	amd_sched_entity_push_job(&job->base);
+	spin_lock(&adev->vm_list_lock);
 	list_move(&vm->list, &adev->vm_list);
+	spin_unlock(&adev->vm_list_lock);
 
 	return 0;
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1 -0
index 877afb5..de782ae 100644
@@ -1560,6 +1560,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	spin_lock_init(&adev->audio_endpt_idx_lock);
 
 	INIT_LIST_HEAD(&adev->vm_list);
+	spin_lock_init(&adev->vm_list_lock);
 
 	adev->rmmio_base = pci_resource_start(adev->pdev, 5);
 	adev->rmmio_size = pci_resource_len(adev->pdev, 5);
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +4 -0
index 35d939b..1cb2e71 100644
@@ -1676,7 +1676,9 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	vm->pd_entry_shadow.tv.bo = &vm->page_directory->shadow->tbo;
 	vm->pd_entry_shadow.tv.shared = true;
 	vm->pd_entry_shadow.user_pages = NULL;
+	spin_lock(&adev->vm_list_lock);
 	list_add_tail(&vm->list, &adev->vm_list);
+	spin_unlock(&adev->vm_list_lock);
 
 	return 0;
 
@@ -1704,7 +1706,9 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	struct amdgpu_bo_va_mapping *mapping, *tmp;
 	int i;
 
+	spin_lock(&adev->vm_list_lock);
 	list_del(&vm->list);
+	spin_unlock(&adev->vm_list_lock);
 	amd_sched_entity_fini(vm->entity.sched, &vm->entity);
 
 	if (!RB_EMPTY_ROOT(&vm->va)) {
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#10 lore raw

PATCH 9/14 drm/amd: add block entity function

In reply to a message not in the archive
Change-Id Ia0378640962eef362569e0bbe090aea1ca083a55
---
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 24 ++++++++++++++++++++++++
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.h |  3 +++
 2 files changed, 27 insertions(+)
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +24 -0
index f96aa82..71b5f1a 100644
@@ -110,6 +110,26 @@ amd_sched_rq_select_entity(struct amd_sched_rq *rq)
 }
 
 /**
+ * block all entity of this run queue
+ *
+ * @rq		The run queue to check.
+ *
+ */
+int amd_sched_rq_block_entity(struct amd_sched_rq *rq, bool block)
+{
+	struct amd_sched_entity *entity;
+
+	spin_lock(&rq->lock);
+
+	list_for_each_entry(entity, &rq->entities, list)
+		entity->block = block;
+
+	spin_unlock(&rq->lock);
+
+	return 0;
+}
+
+/**
  * Init a context entity used by scheduler when submit to HW ring.
  *
  * @sched	The pointer to the scheduler
@@ -134,6 +154,7 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 	INIT_LIST_HEAD(&entity->list);
 	entity->rq = rq;
 	entity->sched = sched;
+	entity->block = false;
 
 	spin_lock_init(&entity->queue_lock);
 	r = kfifo_alloc(&entity->job_queue, jobs * sizeof(void *), GFP_KERNEL);
@@ -186,6 +207,9 @@ static bool amd_sched_entity_is_idle(struct amd_sched_entity *entity)
  */
 static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity)
 {
+	if (entity->block)
+		return false;
+
 	if (kfifo_is_empty(&entity->job_queue))
 		return false;
 
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +3 -0
index 7cbbbfb..a1c0073 100644
@@ -52,6 +52,8 @@ struct amd_sched_entity {
 
 	struct fence			*dependency;
 	struct fence_cb			cb;
+
+	bool                            block;
 };
 
 /**
@@ -155,4 +157,5 @@ int amd_sched_job_init(struct amd_sched_job *job,
 		       void *owner);
 void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched);
 void amd_sched_job_recovery(struct amd_gpu_scheduler *sched);
+int amd_sched_rq_block_entity(struct amd_sched_rq *rq, bool block);
 #endif
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#11 lore raw

PATCH 10/14 drm/amd: abstract entity wait idle

In reply to a message not in the archive
Change-Id I51307ed2fe76de7430f69e70cb859e21cbe236b3
---
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 8 +++++++-
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 2 ++
 2 files changed, 9 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +7 -1
index 71b5f1a..33640ca 100644
@@ -219,6 +219,12 @@ static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity)
 	return true;
 }
 
+void amd_sched_entity_wait_idle(struct amd_gpu_scheduler *sched,
+				struct amd_sched_entity *entity)
+{
+	wait_event(sched->job_scheduled, amd_sched_entity_is_idle(entity));
+}
+
 /**
  * Destroy a context entity
  *
@@ -239,7 +245,7 @@ void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 	 * The client will not queue more IBs during this fini, consume existing
 	 * queued IBs
 	*/
-	wait_event(sched->job_scheduled, amd_sched_entity_is_idle(entity));
+	amd_sched_entity_wait_idle(sched, entity);
 
 	amd_sched_rq_remove_entity(rq, entity);
 	kfifo_free(&entity->job_queue);
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +2 -0
index a1c0073..a133fb7 100644
@@ -146,6 +146,8 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 			   struct amd_sched_entity *entity);
 void amd_sched_entity_push_job(struct amd_sched_job *sched_job);
+void amd_sched_entity_wait_idle(struct amd_gpu_scheduler *sched,
+				struct amd_sched_entity *entity);
 
 struct amd_sched_fence *amd_sched_fence_create(
 	struct amd_sched_entity *s_entity, void *owner);
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#12 lore raw

PATCH 11/14 drm/amdgpu: recover page tables after gpu reset

In reply to a message not in the archive
Change-Id I963598ba6eb44bc8620d70e026c0175d1a1de120
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +29 -1
index de782ae..e5fde84 100644
@@ -2146,18 +2146,46 @@ retry:
 		amdgpu_atombios_scratch_regs_restore(adev);
 	}
 	if (!r) {
+		struct amdgpu_ring *buffer_ring = adev->mman.buffer_funcs_ring;
+
 		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 no problem
+		 * after gpu full reset.
+		 */
+		if (need_full_reset && !(adev->flags & AMD_IS_APU)) {
+			struct amdgpu_vm *vm, *tmp;
+
+			DRM_INFO("recover page table from shadow\n");
+			amd_sched_rq_block_entity(
+				&buffer_ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL], true);
+			kthread_unpark(buffer_ring->sched.thread);
+			spin_lock(&adev->vm_list_lock);
+			list_for_each_entry_safe(vm, tmp, &adev->vm_list, list) {
+				spin_unlock(&adev->vm_list_lock);
+				amdgpu_vm_recover_page_table_from_shadow(adev, vm);
+				spin_lock(&adev->vm_list_lock);
+			}
+			spin_unlock(&adev->vm_list_lock);
+			amd_sched_rq_block_entity(
+				&buffer_ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL], false);
+			amd_sched_entity_wait_idle(&buffer_ring->sched, &adev->mman.entity);
+		}
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = adev->rings[i];
 			if (!ring)
 				continue;
+
+			DRM_INFO("ring:%d recover jobs\n", ring->idx);
+			if ((ring == buffer_ring) && need_full_reset)
+				kthread_park(buffer_ring->sched.thread);
 			amd_sched_job_recovery(&ring->sched);
 			kthread_unpark(ring->sched.thread);
 		}
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#13 lore raw

PATCH 12/14 drm/amd: wait neccessary dependency before running job

In reply to a message not in the archive
Change-Id Ibcc3558c2330caad1a2edb9902b3f21bd950d19f
---
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +4 -1
index 33640ca..1e824f4 100644
@@ -442,9 +442,12 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)
 
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct amd_sched_fence *s_fence = s_job->s_fence;
-		struct fence *fence;
+		struct fence *fence, *dependency;
 
 		spin_unlock(&sched->job_list_lock);
+		while ((dependency = sched->ops->dependency(s_job)))
+		       fence_wait(dependency, false);
+
 		fence = sched->ops->run_job(s_job);
 		atomic_inc(&sched->hw_rq_count);
 		if (fence) {
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#14 lore raw

PATCH 13/14 drm/amdgpu: add vm recover pt fence

In reply to a message not in the archive

Before every job runs, we must make sure which's vm is recoverred completely.

Change-Id Ibe77a3c8f8206def280543fbb4195ad2ab9772e0
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c |  5 +++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c  | 21 +++++++++++++++------
 3 files changed, 22 insertions(+), 6 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +2 -0
index 357d56a6..43beefb 100644
@@ -913,6 +913,8 @@ struct amdgpu_vm {
 
 	/* client id */
 	u64                     client_id;
+
+	struct fence            *recover_pt_fence;
 };
 
 struct amdgpu_vm_id {
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +5 -0
index 6674d40..248e479 100644
@@ -152,6 +152,10 @@ static struct fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
 		fence = amdgpu_sync_get_fence(&job->sync);
 	}
 
+	if (fence == NULL && vm && vm->recover_pt_fence &&
+	    !fence_is_signaled(vm->recover_pt_fence))
+		fence = vm->recover_pt_fence;
+
 	return fence;
 }
 
@@ -170,6 +174,7 @@ static struct fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 	BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
 	trace_amdgpu_sched_run_job(job);
+
 	r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs,
 			       job->sync.last_vm_update, job, &fence);
 	if (r)
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +15 -6
index 1cb2e71..b0bf0aa 100644
@@ -703,11 +703,11 @@ error_free:
 static int amdgpu_vm_recover_bo_from_shadow(struct amdgpu_device *adev,
 					    struct amdgpu_bo *bo,
 					    struct amdgpu_bo *bo_shadow,
-					    struct reservation_object *resv)
+					    struct reservation_object *resv,
+					    struct fence **fence)
 
 {
 	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
-	struct fence *fence;
 	int r;
 	uint64_t vram_addr, gtt_addr;
 
@@ -727,9 +727,9 @@ static int amdgpu_vm_recover_bo_from_shadow(struct amdgpu_device *adev,
 		goto err3;
 
 	r = amdgpu_copy_buffer(ring, gtt_addr, vram_addr,
-			       amdgpu_bo_size(bo), resv, &fence);
+			       amdgpu_bo_size(bo), resv, fence);
 	if (!r)
-		amdgpu_bo_fence(bo, fence, true);
+		amdgpu_bo_fence(bo, *fence, true);
 
 err3:
 	amdgpu_bo_unpin(bo_shadow);
@@ -743,6 +743,7 @@ err1:
 int amdgpu_vm_recover_page_table_from_shadow(struct amdgpu_device *adev,
 					     struct amdgpu_vm *vm)
 {
+	struct fence *fence;
 	uint64_t pt_idx;
 	int r;
 
@@ -753,11 +754,14 @@ int amdgpu_vm_recover_page_table_from_shadow(struct amdgpu_device *adev,
 
 	r = amdgpu_vm_recover_bo_from_shadow(adev, vm->page_directory,
 					     vm->page_directory->shadow,
-					     NULL);
+					     NULL, &fence);
 	if (r) {
 		DRM_ERROR("recover page table failed!\n");
 		goto err;
 	}
+	fence_put(vm->recover_pt_fence);
+	vm->recover_pt_fence = fence_get(fence);
+	fence_put(fence);
 
 	for (pt_idx = 0; pt_idx <= vm->max_pde_used; ++pt_idx) {
 		struct amdgpu_bo *bo = vm->page_tables[pt_idx].entry.robj;
@@ -766,11 +770,14 @@ int amdgpu_vm_recover_page_table_from_shadow(struct amdgpu_device *adev,
 		if (!bo || !bo_shadow)
 			continue;
 		r = amdgpu_vm_recover_bo_from_shadow(adev, bo, bo_shadow,
-						     NULL);
+						     NULL, &fence);
 		if (r) {
 			DRM_ERROR("recover page table failed!\n");
 			goto err;
 		}
+		fence_put(vm->recover_pt_fence);
+		vm->recover_pt_fence = fence_get(fence);
+		fence_put(fence);
 	}
 
 err:
@@ -1629,6 +1636,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	INIT_LIST_HEAD(&vm->cleared);
 	INIT_LIST_HEAD(&vm->freed);
 	INIT_LIST_HEAD(&vm->list);
+	vm->recover_pt_fence = NULL;
 
 	pd_size = amdgpu_vm_directory_size(adev);
 	pd_entries = amdgpu_vm_num_pdes(adev);
@@ -1730,6 +1738,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	amdgpu_bo_unref(&vm->page_directory);
 	fence_put(vm->page_directory_fence);
+	fence_put(vm->recover_pt_fence);
 }
 
 /**
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
#15 lore raw

PATCH 14/14 drm/amdgpu: add backup condition for shadow page table

In reply to a message not in the archive
Change-Id I5a8c0f4c1e9b65d2310ccb0f669b478884072a11
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 71 +++++++++++++++++++++++-----------
 1 file changed, 48 insertions(+), 23 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +48 -23
index b0bf0aa..141ccf4 100644
@@ -112,6 +112,14 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 	list_add(&entry->tv.head, validated);
 }
 
+static bool amdgpu_vm_need_backup(struct amdgpu_device *adev)
+{
+	if (adev->flags & AMD_IS_APU)
+		return false;
+
+	return amdgpu_lockup_timeout > 0 ? true : false;
+}
+
 /**
  * amdgpu_vm_get_bos - add the vm BOs to a duplicates list
  *
@@ -140,13 +148,18 @@ void amdgpu_vm_get_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		struct amdgpu_bo_list_entry *entry = &vm->page_tables[i].entry;
 		struct amdgpu_bo_list_entry *entry_shadow = &vm->page_tables[i].entry_shadow;
 
-		if (!entry->robj || !entry_shadow->robj)
+		if (!entry->robj)
+			continue;
+
+		if (amdgpu_vm_need_backup(adev) && !entry_shadow->robj)
 			continue;
 
 		list_add(&entry->tv.head, duplicates);
-		list_add(&entry_shadow->tv.head, duplicates);
+		if (amdgpu_vm_need_backup(adev))
+			list_add(&entry_shadow->tv.head, duplicates);
 	}
-	list_add(&vm->pd_entry_shadow.tv.head, duplicates);
+	if (amdgpu_vm_need_backup(adev))
+		list_add(&vm->pd_entry_shadow.tv.head, duplicates);
 }
 
 /**
@@ -747,6 +760,8 @@ int amdgpu_vm_recover_page_table_from_shadow(struct amdgpu_device *adev,
 	uint64_t pt_idx;
 	int r;
 
+	if (!amdgpu_vm_need_backup(adev))
+		return 0;
 	/* bo and shadow use same resv, so reverve one time */
 	r = amdgpu_bo_reserve(vm->page_directory, false);
 	if (unlikely(r != 0))
@@ -801,9 +816,12 @@ int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
 {
 	int r;
 
-	r = amdgpu_vm_update_pd_or_shadow(adev, vm, true);
-	if (r)
-		return r;
+	if (amdgpu_vm_need_backup(adev)) {
+		r = amdgpu_vm_update_pd_or_shadow(adev, vm, true);
+		if (r)
+			return r;
+	}
+
 	return amdgpu_vm_update_pd_or_shadow(adev, vm, false);
 }
 
@@ -1069,10 +1087,11 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	r = reservation_object_reserve_shared(vm->page_directory->tbo.resv);
 	if (r)
 		goto error_free;
-	/* update shadow pt bo */
-	amdgpu_vm_update_ptes(adev, &vm_update_params, vm, start,
-			      last + 1, addr, flags, true);
-
+	if (amdgpu_vm_need_backup(adev)) {
+		/* update shadow pt bo */
+		amdgpu_vm_update_ptes(adev, &vm_update_params, vm, start,
+				      last + 1, addr, flags, true);
+	}
 	amdgpu_vm_update_ptes(adev, &vm_update_params, vm, start,
 			      last + 1, addr, flags, false);
 
@@ -1455,7 +1474,8 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 				     AMDGPU_GPU_PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
-				     AMDGPU_GEM_CREATE_SHADOW,
+				     (amdgpu_vm_need_backup(adev) ?
+				      AMDGPU_GEM_CREATE_SHADOW : 0),
 				     NULL, resv, &pt);
 		if (r)
 			goto error_free;
@@ -1478,12 +1498,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		entry->user_pages = NULL;
 		vm->page_tables[pt_idx].addr = 0;
 
-		entry_shadow->robj = pt->shadow;
-		entry_shadow->priority = 0;
-		entry_shadow->tv.bo = &entry_shadow->robj->tbo;
-		entry_shadow->tv.shared = true;
-		entry_shadow->user_pages = NULL;
-		vm->page_tables[pt_idx].addr_shadow = 0;
+		if (amdgpu_vm_need_backup(adev)) {
+			entry_shadow->robj = pt->shadow;
+			entry_shadow->priority = 0;
+			entry_shadow->tv.bo = &entry_shadow->robj->tbo;
+			entry_shadow->tv.shared = true;
+			entry_shadow->user_pages = NULL;
+			vm->page_tables[pt_idx].addr_shadow = 0;
+		}
 	}
 
 	return 0;
@@ -1664,7 +1686,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	r = amdgpu_bo_create(adev, pd_size, align, true,
 			     AMDGPU_GEM_DOMAIN_VRAM,
 			     AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
-			     AMDGPU_GEM_CREATE_SHADOW,
+			     (amdgpu_vm_need_backup(adev) ?
+			      AMDGPU_GEM_CREATE_SHADOW : 0),
 			     NULL, NULL, &vm->page_directory);
 	if (r)
 		goto error_free_sched_entity;
@@ -1679,11 +1702,13 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		goto error_free_page_directory;
 	vm->last_eviction_counter = atomic64_read(&adev->num_evictions);
 
-	vm->pd_entry_shadow.robj = vm->page_directory->shadow;
-	vm->pd_entry_shadow.priority = 0;
-	vm->pd_entry_shadow.tv.bo = &vm->page_directory->shadow->tbo;
-	vm->pd_entry_shadow.tv.shared = true;
-	vm->pd_entry_shadow.user_pages = NULL;
+	if (amdgpu_vm_need_backup(adev)) {
+		vm->pd_entry_shadow.robj = vm->page_directory->shadow;
+		vm->pd_entry_shadow.priority = 0;
+		vm->pd_entry_shadow.tv.bo = &vm->page_directory->shadow->tbo;
+		vm->pd_entry_shadow.tv.shared = true;
+		vm->pd_entry_shadow.user_pages = NULL;
+	}
 	spin_lock(&adev->vm_list_lock);
 	list_add_tail(&vm->list, &adev->vm_list);
 	spin_unlock(&adev->vm_list_lock);
Signature · 6 lines
1.9.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx