[PATCH 06/11] drm/amdgpu: pass ttm process to buffer object

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Change-Id: Ifb0dc95db6a358cf7f76e2a99f94c58637ad6ee6
Signed-off-by: Chunming Zhou <david1.zhou at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |   3 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c     |   2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c    |  17 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 170 ++++++++++++++++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h |   6 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    |   1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c     |   1 +
 7 files changed, 187 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 4b66585a8638..f398a566f57b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -443,7 +443,8 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 			     int alignment, u32 initial_domain,
 			     u64 flags, enum ttm_bo_type type,
 			     struct reservation_object *resv,
-			     struct drm_gem_object **obj);
+			     struct drm_gem_object **obj,
+			     struct ttm_process *process);
 
 int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 			    struct drm_device *dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index ff89e84b34ce..1cee2125f570 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -146,7 +146,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 				       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 				       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
 				       AMDGPU_GEM_CREATE_VRAM_CLEARED,
-				       true, NULL, &gobj);
+				       true, NULL, &gobj, &adev->kernel_process);
 	if (ret) {
 		pr_err("failed to allocate framebuffer (%d)\n", aligned_size);
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 37b19ce97699..d5cbdc810aba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -45,7 +45,8 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 			     int alignment, u32 initial_domain,
 			     u64 flags, enum ttm_bo_type type,
 			     struct reservation_object *resv,
-			     struct drm_gem_object **obj)
+			     struct drm_gem_object **obj,
+			     struct ttm_process *process)
 {
 	struct amdgpu_bo *bo;
 	int r;
@@ -56,8 +57,8 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 		alignment = PAGE_SIZE;
 	}
 
-	r = amdgpu_bo_create(adev, size, alignment, initial_domain,
-			     flags, type, resv, &bo);
+	r = amdgpu_bo_create1(adev, size, alignment, initial_domain,
+			      flags, type, resv, &bo, process);
 	if (r) {
 		DRM_DEBUG("Failed to allocate GEM object (%ld, %d, %u, %d)\n",
 			  size, initial_domain, alignment, r);
@@ -243,7 +244,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 
 	r = amdgpu_gem_object_create(adev, size, args->in.alignment,
 				     (u32)(0xffffffff & args->in.domains),
-				     flags, false, resv, &gobj);
+				     flags, false, resv, &gobj, &vm->ttm_vm);
 	if (!r) {
 		abo = gem_to_amdgpu_bo(gobj);
 		abo->tbo.process = &vm->ttm_vm;
@@ -273,6 +274,8 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 {
 	struct ttm_operation_ctx ctx = { true, false };
 	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	struct amdgpu_vm *vm = &fpriv->vm;
 	struct drm_amdgpu_gem_userptr *args = data;
 	struct drm_gem_object *gobj;
 	struct amdgpu_bo *bo;
@@ -297,7 +300,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 
 	/* create a gem object to contain this object in */
 	r = amdgpu_gem_object_create(adev, args->size, 0, AMDGPU_GEM_DOMAIN_CPU,
-				     0, 0, NULL, &gobj);
+				     0, 0, NULL, &gobj, &vm->ttm_vm);
 	if (r)
 		return r;
 
@@ -735,6 +738,8 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 			    struct drm_mode_create_dumb *args)
 {
 	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
+	struct amdgpu_vm *vm = &fpriv->vm;
 	struct drm_gem_object *gobj;
 	uint32_t handle;
 	int r;
@@ -747,7 +752,7 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 	r = amdgpu_gem_object_create(adev, args->size, 0,
 				     AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-				     false, NULL, &gobj);
+				     false, NULL, &gobj, &vm->ttm_vm);
 	if (r)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index e911db2d1945..7bb6ee777067 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -421,6 +421,11 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size,
 		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
 #endif
 
+	if (type == ttm_bo_type_kernel) {
+		bo->tbo.priority = 1;
+		bo->tbo.process = &adev->kernel_process;
+	}
+
 	bo->tbo.bdev = &adev->mman.bdev;
 	amdgpu_ttm_placement_from_domain(bo, domains);
 	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
@@ -447,11 +452,6 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size,
 	else
 		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, 0);
 
-	if (type == ttm_bo_type_kernel) {
-		bo->tbo.priority = 1;
-		bo->tbo.process = &adev->kernel_process;
-	}
-
 	if (flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
 	    bo->tbo.mem.placement & TTM_PL_FLAG_VRAM) {
 		struct dma_fence *fence;
@@ -538,6 +538,166 @@ int amdgpu_bo_create(struct amdgpu_device *adev, unsigned long size,
 
 	return r;
 }
+static int amdgpu_bo_do_create1(struct amdgpu_device *adev, unsigned long size,
+				int byte_align, u32 domain,
+				u64 flags, enum ttm_bo_type type,
+				struct reservation_object *resv,
+				struct amdgpu_bo **bo_ptr,
+				struct ttm_process *process)
+{
+	struct ttm_operation_ctx ctx = {
+		.interruptible = (type != ttm_bo_type_kernel),
+		.no_wait_gpu = false,
+		.resv = resv,
+		.flags = TTM_OPT_FLAG_ALLOW_RES_EVICT
+	};
+	struct amdgpu_bo *bo;
+	unsigned long page_align;
+	size_t acc_size;
+	u32 domains, preferred_domains, allowed_domains;
+	int r;
+
+	page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
+	size = ALIGN(size, PAGE_SIZE);
+
+	if (!amdgpu_bo_validate_size(adev, size, domain))
+		return -ENOMEM;
+
+	*bo_ptr = NULL;
+
+	acc_size = ttm_bo_dma_acc_size(&adev->mman.bdev, size,
+				       sizeof(struct amdgpu_bo));
+
+	preferred_domains = domain & (AMDGPU_GEM_DOMAIN_VRAM |
+				      AMDGPU_GEM_DOMAIN_GTT |
+				      AMDGPU_GEM_DOMAIN_CPU |
+				      AMDGPU_GEM_DOMAIN_GDS |
+				      AMDGPU_GEM_DOMAIN_GWS |
+				      AMDGPU_GEM_DOMAIN_OA);
+	allowed_domains = preferred_domains;
+	if (type != ttm_bo_type_kernel &&
+	    allowed_domains == AMDGPU_GEM_DOMAIN_VRAM)
+		allowed_domains |= AMDGPU_GEM_DOMAIN_GTT;
+	domains = preferred_domains;
+retry:
+	bo = kzalloc(sizeof(struct amdgpu_bo), GFP_KERNEL);
+	if (bo == NULL)
+		return -ENOMEM;
+	drm_gem_private_object_init(adev->ddev, &bo->gem_base, size);
+	INIT_LIST_HEAD(&bo->shadow_list);
+	INIT_LIST_HEAD(&bo->va);
+	bo->preferred_domains = preferred_domains;
+	bo->allowed_domains = allowed_domains;
+
+	bo->flags = flags;
+
+#ifdef CONFIG_X86_32
+	/* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
+	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
+	 */
+	bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+#elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
+	/* Don't try to enable write-combining when it can't work, or things
+	 * may be slow
+	 * See https://bugs.freedesktop.org/show_bug.cgi?id=88758
+	 */
+
+#ifndef CONFIG_COMPILE_TEST
+#warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
+	 thanks to write-combining
+#endif
+
+	if (bo->flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
+		DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
+			      "better performance thanks to write-combining\n");
+	bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+#else
+	/* For architectures that don't support WC memory,
+	 * mask out the WC flag from the BO
+	 */
+	if (!drm_arch_can_wc_memory())
+		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+#endif
+
+	if (type == ttm_bo_type_kernel)
+		bo->tbo.priority = 1;
+	bo->tbo.process = process;
+
+	bo->tbo.bdev = &adev->mman.bdev;
+	amdgpu_ttm_placement_from_domain(bo, domains);
+	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type,
+				 &bo->placement, page_align, &ctx, acc_size,
+				 NULL, resv, &amdgpu_ttm_bo_destroy);
+	if (unlikely(r && r != -ERESTARTSYS) && type == ttm_bo_type_device &&
+	    !(flags & AMDGPU_GEM_CREATE_NO_FALLBACK)) {
+		if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) {
+			flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+			goto retry;
+		} else if (domains != allowed_domains) {
+			domains = allowed_domains;
+			goto retry;
+		}
+	}
+	if (unlikely(r))
+		return r;
+
+	if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
+	    bo->tbo.mem.mem_type == TTM_PL_VRAM &&
+	    bo->tbo.mem.start < adev->gmc.visible_vram_size >> PAGE_SHIFT)
+		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved,
+					     ctx.bytes_moved);
+	else
+		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, 0);
+
+	if (flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
+	    bo->tbo.mem.placement & TTM_PL_FLAG_VRAM) {
+		struct dma_fence *fence;
+
+		r = amdgpu_fill_buffer(bo, 0, bo->tbo.resv, &fence);
+		if (unlikely(r))
+			goto fail_unreserve;
+
+		amdgpu_bo_fence(bo, fence, false);
+		dma_fence_put(bo->tbo.moving);
+		bo->tbo.moving = dma_fence_get(fence);
+		dma_fence_put(fence);
+	}
+	if (!resv)
+		amdgpu_bo_unreserve(bo);
+	*bo_ptr = bo;
+
+	trace_amdgpu_bo_create(bo);
+
+	/* Treat CPU_ACCESS_REQUIRED only as a hint if given by UMD */
+	if (type == ttm_bo_type_device)
+		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+
+	return 0;
+
+fail_unreserve:
+	if (!resv)
+		ww_mutex_unlock(&bo->tbo.resv->lock);
+	amdgpu_bo_unref(&bo);
+	return r;
+}
+
+
+int amdgpu_bo_create1(struct amdgpu_device *adev, unsigned long size,
+		      int byte_align, u32 domain,
+		      u64 flags, enum ttm_bo_type type,
+		      struct reservation_object *resv,
+		      struct amdgpu_bo **bo_ptr, struct ttm_process *process)
+{
+	uint64_t parent_flags = flags & ~AMDGPU_GEM_CREATE_SHADOW;
+	int r;
+
+	r = amdgpu_bo_do_create1(adev, size, byte_align, domain,
+				 parent_flags, type, resv, bo_ptr, process);
+	if (r)
+		return r;
+	return r;
+}
+
 
 int amdgpu_bo_backup_to_shadow(struct amdgpu_device *adev,
 			       struct amdgpu_ring *ring,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 546f77cb7882..d4191f0424d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -208,6 +208,12 @@ int amdgpu_bo_create(struct amdgpu_device *adev, unsigned long size,
 		     u64 flags, enum ttm_bo_type type,
 		     struct reservation_object *resv,
 		     struct amdgpu_bo **bo_ptr);
+int amdgpu_bo_create1(struct amdgpu_device *adev, unsigned long size,
+		      int byte_align, u32 domain,
+		      u64 flags, enum ttm_bo_type type,
+		      struct reservation_object *resv,
+		      struct amdgpu_bo **bo_ptr, struct ttm_process *process);
+
 int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 			      unsigned long size, int align,
 			      u32 domain, struct amdgpu_bo **bo_ptr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 4c9e10505e2d..591db2df1685 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1535,6 +1535,7 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
 		return;
 
 	amdgpu_ttm_debugfs_fini(adev);
+	ttm_process_fini(&adev->kernel_process, &adev->mman.bdev);
 	amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, NULL);
 	amdgpu_ttm_fw_reserve_vram_fini(adev);
 	if (adev->mman.aper_base_kaddr)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 6ef449ea8d07..3a54b236fd42 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2612,6 +2612,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		amdgpu_vm_free_mapping(adev, vm, mapping, NULL);
 	}
 
+	ttm_process_fini(&vm->ttm_vm, &adev->mman.bdev);
 	root = amdgpu_bo_ref(vm->root.base.bo);
 	r = amdgpu_bo_reserve(root, true);
 	if (r) {
-- 
2.14.1



[Index of Archives]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux