All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
To: intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	"Christian König" <christian.koenig@amd.com>
Subject: [RFC PATCH 4/5] drm/ttm: Document and optimize ttm_bo_pipeline_gutting()
Date: Thu, 20 May 2021 17:09:46 +0200	[thread overview]
Message-ID: <20210520150947.803891-5-thomas.hellstrom@linux.intel.com> (raw)
In-Reply-To: <20210520150947.803891-1-thomas.hellstrom@linux.intel.com>

If the bo is idle when calling ttm_bo_pipeline_gutting(), we unnecessarily
create a ghost object and push it out to delayed destroy.
Fix this by adding a path for idle, and document the function.

Also avoid having the bo end up in a bad state vulnerable to user-space
triggered kernel BUGs if the call to ttm_tt_create() fails.

Finally reuse ttm_bo_pipeline_gutting() in ttm_bo_evict().

Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c      | 20 +++++-----
 drivers/gpu/drm/ttm/ttm_bo_util.c | 63 ++++++++++++++++++++++++-------
 drivers/gpu/drm/ttm/ttm_tt.c      |  5 +++
 include/drm/ttm/ttm_tt.h          | 10 +++++
 4 files changed, 75 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index ca1b098b6a56..a8fa3375b8aa 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -501,10 +501,15 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 	bdev->funcs->evict_flags(bo, &placement);
 
 	if (!placement.num_placement && !placement.num_busy_placement) {
-		ttm_bo_wait(bo, false, false);
+		ret = ttm_bo_wait(bo, true, false);
+		if (ret)
+			return ret;
 
-		ttm_bo_cleanup_memtype_use(bo);
-		return ttm_tt_create(bo, false);
+		/*
+		 * Since we've already synced, this frees backing store
+		 * immediately.
+		 */
+		return ttm_bo_pipeline_gutting(bo);
 	}
 
 	ret = ttm_bo_mem_space(bo, &placement, &evict_mem, ctx);
@@ -974,13 +979,8 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	/*
 	 * Remove the backing store if no placement is given.
 	 */
-	if (!placement->num_placement && !placement->num_busy_placement) {
-		ret = ttm_bo_pipeline_gutting(bo);
-		if (ret)
-			return ret;
-
-		return ttm_tt_create(bo, false);
-	}
+	if (!placement->num_placement && !placement->num_busy_placement)
+		return ttm_bo_pipeline_gutting(bo);
 
 	/*
 	 * Check whether we need to move buffer.
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 919ee03f7eb3..1860e2e7563f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -479,7 +479,8 @@ static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
  */
 
 static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
-				      struct ttm_buffer_object **new_obj)
+				      struct ttm_buffer_object **new_obj,
+				      bool realloc_tt)
 {
 	struct ttm_transfer_obj *fbo;
 	int ret;
@@ -493,6 +494,17 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	ttm_bo_get(bo);
 	fbo->bo = bo;
 
+	if (realloc_tt) {
+		bo->ttm = NULL;
+		ret = ttm_tt_create(bo, true);
+		if (ret) {
+			bo->ttm = fbo->base.ttm;
+			kfree(fbo);
+			ttm_bo_put(bo);
+			return ret;
+		}
+	}
+
 	/**
 	 * Fix up members that we shouldn't copy directly:
 	 * TODO: Explicit member copy would probably be better here.
@@ -763,7 +775,7 @@ static int ttm_bo_move_to_ghost(struct ttm_buffer_object *bo,
 	dma_fence_put(bo->moving);
 	bo->moving = dma_fence_get(fence);
 
-	ret = ttm_buffer_object_transfer(bo, &ghost_obj);
+	ret = ttm_buffer_object_transfer(bo, &ghost_obj, false);
 	if (ret)
 		return ret;
 
@@ -836,26 +848,51 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_move_accel_cleanup);
 
+/**
+ * ttm_bo_pipeline_gutting - purge the contents of a bo
+ * @bo: The buffer object
+ *
+ * Purge the contents of a bo, async if the bo is not idle.
+ * After a successful call, the bo is left unpopulated in
+ * system placement. The function may wait uninterruptible
+ * for idle on OOM.
+ *
+ * Return: 0 if successful, negative error code on failure.
+ */
 int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 {
 	static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM };
 	struct ttm_buffer_object *ghost;
 	int ret;
 
-	ret = ttm_buffer_object_transfer(bo, &ghost);
-	if (ret)
-		return ret;
+	/* If already idle, no need for ghost object dance. */
+	ret = ttm_bo_wait(bo, false, true);
+	if (ret == -EBUSY) {
+		ret = ttm_buffer_object_transfer(bo, &ghost, true);
+		if (ret)
+			return ret;
 
-	ret = dma_resv_copy_fences(&ghost->base._resv, bo->base.resv);
-	/* Last resort, wait for the BO to be idle when we are OOM */
-	if (ret)
-		ttm_bo_wait(bo, false, false);
+		ret = dma_resv_copy_fences(&ghost->base._resv, bo->base.resv);
+		/* Last resort, wait for the BO to be idle when we are OOM */
+		if (ret)
+			ttm_bo_wait(bo, false, false);
 
-	ttm_resource_alloc(bo, &sys_mem, &bo->mem);
-	bo->ttm = NULL;
+		dma_resv_unlock(&ghost->base._resv);
+		ttm_bo_put(ghost);
+	} else {
+		if (!bo->ttm) {
+			ret = ttm_tt_create(bo, true);
+			if (ret)
+				return ret;
+		} else {
+			ttm_tt_unpopulate(bo->bdev, bo->ttm);
+			if (bo->type == ttm_bo_type_device)
+				ttm_tt_mark_for_clear(bo->ttm);
+		}
+		ttm_resource_free(bo, &bo->mem);
+	}
 
-	dma_resv_unlock(&ghost->base._resv);
-	ttm_bo_put(ghost);
+	ttm_resource_alloc(bo, &sys_mem, &bo->mem);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 539e0232cb3b..0b1053e93db2 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -134,6 +134,11 @@ void ttm_tt_destroy_common(struct ttm_device *bdev, struct ttm_tt *ttm)
 }
 EXPORT_SYMBOL(ttm_tt_destroy_common);
 
+void ttm_tt_mark_for_clear(struct ttm_tt *ttm)
+{
+	ttm->page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
+}
+
 void ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
 {
 	bdev->funcs->ttm_tt_destroy(bdev, ttm);
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 134d09ef7766..91552c83ac79 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -157,6 +157,16 @@ int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_oper
  */
 void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm);
 
+/**
+ * ttm_tt_mark_for_clear - Mark pages for clearing on populate.
+ *
+ * @ttm: Pointer to the ttm_tt structure
+ *
+ * Marks pages for clearing so that the next time the page vector is
+ * populated, the pages will be cleared.
+ */
+void ttm_tt_mark_for_clear(struct ttm_tt *ttm);
+
 void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages);
 
 #if IS_ENABLED(CONFIG_AGP)
-- 
2.31.1


WARNING: multiple messages have this Message-ID (diff)
From: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
To: intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	"Christian König" <christian.koenig@amd.com>
Subject: [Intel-gfx] [RFC PATCH 4/5] drm/ttm: Document and optimize ttm_bo_pipeline_gutting()
Date: Thu, 20 May 2021 17:09:46 +0200	[thread overview]
Message-ID: <20210520150947.803891-5-thomas.hellstrom@linux.intel.com> (raw)
In-Reply-To: <20210520150947.803891-1-thomas.hellstrom@linux.intel.com>

If the bo is idle when calling ttm_bo_pipeline_gutting(), we unnecessarily
create a ghost object and push it out to delayed destroy.
Fix this by adding a path for idle, and document the function.

Also avoid having the bo end up in a bad state vulnerable to user-space
triggered kernel BUGs if the call to ttm_tt_create() fails.

Finally reuse ttm_bo_pipeline_gutting() in ttm_bo_evict().

Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c      | 20 +++++-----
 drivers/gpu/drm/ttm/ttm_bo_util.c | 63 ++++++++++++++++++++++++-------
 drivers/gpu/drm/ttm/ttm_tt.c      |  5 +++
 include/drm/ttm/ttm_tt.h          | 10 +++++
 4 files changed, 75 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index ca1b098b6a56..a8fa3375b8aa 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -501,10 +501,15 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 	bdev->funcs->evict_flags(bo, &placement);
 
 	if (!placement.num_placement && !placement.num_busy_placement) {
-		ttm_bo_wait(bo, false, false);
+		ret = ttm_bo_wait(bo, true, false);
+		if (ret)
+			return ret;
 
-		ttm_bo_cleanup_memtype_use(bo);
-		return ttm_tt_create(bo, false);
+		/*
+		 * Since we've already synced, this frees backing store
+		 * immediately.
+		 */
+		return ttm_bo_pipeline_gutting(bo);
 	}
 
 	ret = ttm_bo_mem_space(bo, &placement, &evict_mem, ctx);
@@ -974,13 +979,8 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	/*
 	 * Remove the backing store if no placement is given.
 	 */
-	if (!placement->num_placement && !placement->num_busy_placement) {
-		ret = ttm_bo_pipeline_gutting(bo);
-		if (ret)
-			return ret;
-
-		return ttm_tt_create(bo, false);
-	}
+	if (!placement->num_placement && !placement->num_busy_placement)
+		return ttm_bo_pipeline_gutting(bo);
 
 	/*
 	 * Check whether we need to move buffer.
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 919ee03f7eb3..1860e2e7563f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -479,7 +479,8 @@ static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
  */
 
 static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
-				      struct ttm_buffer_object **new_obj)
+				      struct ttm_buffer_object **new_obj,
+				      bool realloc_tt)
 {
 	struct ttm_transfer_obj *fbo;
 	int ret;
@@ -493,6 +494,17 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	ttm_bo_get(bo);
 	fbo->bo = bo;
 
+	if (realloc_tt) {
+		bo->ttm = NULL;
+		ret = ttm_tt_create(bo, true);
+		if (ret) {
+			bo->ttm = fbo->base.ttm;
+			kfree(fbo);
+			ttm_bo_put(bo);
+			return ret;
+		}
+	}
+
 	/**
 	 * Fix up members that we shouldn't copy directly:
 	 * TODO: Explicit member copy would probably be better here.
@@ -763,7 +775,7 @@ static int ttm_bo_move_to_ghost(struct ttm_buffer_object *bo,
 	dma_fence_put(bo->moving);
 	bo->moving = dma_fence_get(fence);
 
-	ret = ttm_buffer_object_transfer(bo, &ghost_obj);
+	ret = ttm_buffer_object_transfer(bo, &ghost_obj, false);
 	if (ret)
 		return ret;
 
@@ -836,26 +848,51 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_move_accel_cleanup);
 
+/**
+ * ttm_bo_pipeline_gutting - purge the contents of a bo
+ * @bo: The buffer object
+ *
+ * Purge the contents of a bo, async if the bo is not idle.
+ * After a successful call, the bo is left unpopulated in
+ * system placement. The function may wait uninterruptible
+ * for idle on OOM.
+ *
+ * Return: 0 if successful, negative error code on failure.
+ */
 int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 {
 	static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM };
 	struct ttm_buffer_object *ghost;
 	int ret;
 
-	ret = ttm_buffer_object_transfer(bo, &ghost);
-	if (ret)
-		return ret;
+	/* If already idle, no need for ghost object dance. */
+	ret = ttm_bo_wait(bo, false, true);
+	if (ret == -EBUSY) {
+		ret = ttm_buffer_object_transfer(bo, &ghost, true);
+		if (ret)
+			return ret;
 
-	ret = dma_resv_copy_fences(&ghost->base._resv, bo->base.resv);
-	/* Last resort, wait for the BO to be idle when we are OOM */
-	if (ret)
-		ttm_bo_wait(bo, false, false);
+		ret = dma_resv_copy_fences(&ghost->base._resv, bo->base.resv);
+		/* Last resort, wait for the BO to be idle when we are OOM */
+		if (ret)
+			ttm_bo_wait(bo, false, false);
 
-	ttm_resource_alloc(bo, &sys_mem, &bo->mem);
-	bo->ttm = NULL;
+		dma_resv_unlock(&ghost->base._resv);
+		ttm_bo_put(ghost);
+	} else {
+		if (!bo->ttm) {
+			ret = ttm_tt_create(bo, true);
+			if (ret)
+				return ret;
+		} else {
+			ttm_tt_unpopulate(bo->bdev, bo->ttm);
+			if (bo->type == ttm_bo_type_device)
+				ttm_tt_mark_for_clear(bo->ttm);
+		}
+		ttm_resource_free(bo, &bo->mem);
+	}
 
-	dma_resv_unlock(&ghost->base._resv);
-	ttm_bo_put(ghost);
+	ttm_resource_alloc(bo, &sys_mem, &bo->mem);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 539e0232cb3b..0b1053e93db2 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -134,6 +134,11 @@ void ttm_tt_destroy_common(struct ttm_device *bdev, struct ttm_tt *ttm)
 }
 EXPORT_SYMBOL(ttm_tt_destroy_common);
 
+void ttm_tt_mark_for_clear(struct ttm_tt *ttm)
+{
+	ttm->page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
+}
+
 void ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
 {
 	bdev->funcs->ttm_tt_destroy(bdev, ttm);
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 134d09ef7766..91552c83ac79 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -157,6 +157,16 @@ int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_oper
  */
 void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm);
 
+/**
+ * ttm_tt_mark_for_clear - Mark pages for clearing on populate.
+ *
+ * @ttm: Pointer to the ttm_tt structure
+ *
+ * Marks pages for clearing so that the next time the page vector is
+ * populated, the pages will be cleared.
+ */
+void ttm_tt_mark_for_clear(struct ttm_tt *ttm);
+
 void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages);
 
 #if IS_ENABLED(CONFIG_AGP)
-- 
2.31.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2021-05-20 15:10 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-20 15:09 [RFC PATCH 0/5] Core TTM changes for i915 TTM enabling Thomas Hellström
2021-05-20 15:09 ` [Intel-gfx] " Thomas Hellström
2021-05-20 15:09 ` [RFC PATCH 1/5] drm/ttm: Add a generic TTM memcpy move for page-based iomem Thomas Hellström
2021-05-20 15:09   ` [Intel-gfx] " Thomas Hellström
2021-05-21  8:08   ` Christian König
2021-05-21  8:08     ` [Intel-gfx] " Christian König
2021-05-27  5:07   ` [drm/ttm] 0c13ca6d7f: WARNING:at_drivers/gpu/drm/drm_fb_helper.c:#drm_fb_helper_damage_work kernel test robot
2021-05-27  5:07     ` kernel test robot
2021-05-27  5:07     ` [Intel-gfx] " kernel test robot
2021-05-27  5:07     ` kernel test robot
2021-05-20 15:09 ` [RFC PATCH 2/5] drm, drm/i915: Move the memcpy_from_wc functionality to core drm Thomas Hellström
2021-05-20 15:09   ` [Intel-gfx] " Thomas Hellström
2021-05-20 15:09 ` [RFC PATCH 3/5] drm/ttm: Use drm_memcpy_from_wc for TTM bo moves Thomas Hellström
2021-05-20 15:09   ` [Intel-gfx] " Thomas Hellström
2021-05-21  8:10   ` Christian König
2021-05-21  8:10     ` [Intel-gfx] " Christian König
2021-05-21  8:30     ` Thomas Hellström
2021-05-21  8:30       ` [Intel-gfx] " Thomas Hellström
2021-05-20 15:09 ` Thomas Hellström [this message]
2021-05-20 15:09   ` [Intel-gfx] [RFC PATCH 4/5] drm/ttm: Document and optimize ttm_bo_pipeline_gutting() Thomas Hellström
2021-05-21  8:21   ` Christian König
2021-05-21  8:21     ` [Intel-gfx] " Christian König
2021-05-21  8:43     ` Thomas Hellström
2021-05-21  8:43       ` [Intel-gfx] " Thomas Hellström
2021-05-20 15:09 ` [RFC PATCH 5/5] drm/ttm, drm/amdgpu: Allow the driver some control over swapping Thomas Hellström
2021-05-20 15:09   ` [Intel-gfx] " Thomas Hellström
2021-05-20 15:17   ` Thomas Hellström
2021-05-20 15:17     ` [Intel-gfx] " Thomas Hellström
2021-05-20 15:20 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Core TTM changes for i915 TTM enabling Patchwork
2021-05-20 15:21 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-05-20 15:51 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-05-21 23:14 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210520150947.803891-5-thomas.hellstrom@linux.intel.com \
    --to=thomas.hellstrom@linux.intel.com \
    --cc=christian.koenig@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.