Intel-GFX Archive on lore.kernel.org
 help / color / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH 05/29] drm/i915: Only pwrite through the GTT if there is space in the aperture
Date: Sat, 11 Aug 2012 15:41:04 +0100
Message-ID: <1344696088-24760-6-git-send-email-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <1344696088-24760-1-git-send-email-chris@chris-wilson.co.uk>

Avoid stalling and waiting for the GPU by checking to see if there is
sufficient inactive space in the aperture for us to bind the buffer
prior to writing through the GTT. If there is inadequate space we will
have to stall waiting for the GPU, and incur overheads moving objects
about. Instead, only incur the clflush overhead on the target object by
writing through shmem.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h            |    6 ++++--
 drivers/gpu/drm/i915/i915_gem.c            |   29 +++++++++++++++-------------
 drivers/gpu/drm/i915/i915_gem_context.c    |    4 ++--
 drivers/gpu/drm/i915/i915_gem_evict.c      |    6 +++++-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |    2 +-
 drivers/gpu/drm/i915/intel_overlay.c       |    2 +-
 drivers/gpu/drm/i915/intel_pm.c            |    2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.c    |    6 +++---
 8 files changed, 33 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e252947..78eed86 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1307,7 +1307,8 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 void i915_gem_free_object(struct drm_gem_object *obj);
 int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj,
 				     uint32_t alignment,
-				     bool map_and_fenceable);
+				     bool map_and_fenceable,
+				     bool nonblocking);
 void i915_gem_object_unpin(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_object_unbind(struct drm_i915_gem_object *obj);
 void i915_gem_release_mmap(struct drm_i915_gem_object *obj);
@@ -1454,7 +1455,8 @@ void i915_gem_init_global_gtt(struct drm_device *dev,
 int __must_check i915_gem_evict_something(struct drm_device *dev, int min_size,
 					  unsigned alignment,
 					  unsigned cache_level,
-					  bool mappable);
+					  bool mappable,
+					  bool nonblock);
 int i915_gem_evict_everything(struct drm_device *dev);
 
 /* i915_gem_stolen.c */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0e0fc1e..b16b5ff 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -41,7 +41,8 @@ static void i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *o
 static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj);
 static __must_check int i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 						    unsigned alignment,
-						    bool map_and_fenceable);
+						    bool map_and_fenceable,
+						    bool nonblocking);
 static int i915_gem_phys_pwrite(struct drm_device *dev,
 				struct drm_i915_gem_object *obj,
 				struct drm_i915_gem_pwrite *args,
@@ -609,7 +610,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 	char __user *user_data;
 	int page_offset, page_length, ret;
 
-	ret = i915_gem_object_pin(obj, 0, true);
+	ret = i915_gem_object_pin(obj, 0, true, true);
 	if (ret)
 		goto out;
 
@@ -925,10 +926,8 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	if (obj->gtt_space &&
-	    obj->cache_level == I915_CACHE_NONE &&
+	if (obj->cache_level == I915_CACHE_NONE &&
 	    obj->tiling_mode == I915_TILING_NONE &&
-	    obj->map_and_fenceable &&
 	    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
 		ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file);
 		/* Note that the gtt paths might fail with non-page-backed user
@@ -936,7 +935,7 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		 * textures). Fallback to the shmem path in that case. */
 	}
 
-	if (ret == -EFAULT)
+	if (ret == -EFAULT || ret == -ENOSPC)
 		ret = i915_gem_shmem_pwrite(dev, obj, args, file);
 
 out:
@@ -1115,7 +1114,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 			goto unlock;
 	}
 	if (!obj->gtt_space) {
-		ret = i915_gem_object_bind_to_gtt(obj, 0, true);
+		ret = i915_gem_object_bind_to_gtt(obj, 0, true, false);
 		if (ret)
 			goto unlock;
 
@@ -2771,7 +2770,8 @@ static void i915_gem_verify_gtt(struct drm_device *dev)
 static int
 i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 			    unsigned alignment,
-			    bool map_and_fenceable)
+			    bool map_and_fenceable,
+			    bool nonblocking)
 {
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
@@ -2847,7 +2847,8 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 	if (obj->gtt_space == NULL) {
 		ret = i915_gem_evict_something(dev, size, alignment,
 					       obj->cache_level,
-					       map_and_fenceable);
+					       map_and_fenceable,
+					       nonblocking);
 		if (ret)
 			return ret;
 
@@ -3187,7 +3188,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 * (e.g. libkms for the bootup splash), we have to ensure that we
 	 * always use map_and_fenceable for all scanout buffers.
 	 */
-	ret = i915_gem_object_pin(obj, alignment, true);
+	ret = i915_gem_object_pin(obj, alignment, true, false);
 	if (ret)
 		return ret;
 
@@ -3324,7 +3325,8 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
 int
 i915_gem_object_pin(struct drm_i915_gem_object *obj,
 		    uint32_t alignment,
-		    bool map_and_fenceable)
+		    bool map_and_fenceable,
+		    bool nonblocking)
 {
 	int ret;
 
@@ -3348,7 +3350,8 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 
 	if (obj->gtt_space == NULL) {
 		ret = i915_gem_object_bind_to_gtt(obj, alignment,
-						  map_and_fenceable);
+						  map_and_fenceable,
+						  nonblocking);
 		if (ret)
 			return ret;
 	}
@@ -3406,7 +3409,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 	obj->user_pin_count++;
 	obj->pin_filp = file;
 	if (obj->user_pin_count == 1) {
-		ret = i915_gem_object_pin(obj, args->alignment, true);
+		ret = i915_gem_object_pin(obj, args->alignment, true, false);
 		if (ret)
 			goto out;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index f5c721b..184753e 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -228,7 +228,7 @@ static int create_default_context(struct drm_i915_private *dev_priv)
 	 * default context.
 	 */
 	dev_priv->ring[RCS].default_context = ctx;
-	ret = i915_gem_object_pin(ctx->obj, CONTEXT_ALIGN, false);
+	ret = i915_gem_object_pin(ctx->obj, CONTEXT_ALIGN, false, false);
 	if (ret)
 		goto err_destroy;
 
@@ -379,7 +379,7 @@ static int do_switch(struct i915_hw_context *to)
 	if (from_obj == to->obj)
 		return 0;
 
-	ret = i915_gem_object_pin(to->obj, CONTEXT_ALIGN, false);
+	ret = i915_gem_object_pin(to->obj, CONTEXT_ALIGN, false, false);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 74635da..a2d8acd 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -45,7 +45,7 @@ mark_free(struct drm_i915_gem_object *obj, struct list_head *unwind)
 int
 i915_gem_evict_something(struct drm_device *dev, int min_size,
 			 unsigned alignment, unsigned cache_level,
-			 bool mappable)
+			 bool mappable, bool nonblocking)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct list_head eviction_list, unwind_list;
@@ -92,12 +92,16 @@ i915_gem_evict_something(struct drm_device *dev, int min_size,
 			goto found;
 	}
 
+	if (nonblocking)
+		goto none;
+
 	/* Now merge in the soon-to-be-expired objects... */
 	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
 		if (mark_free(obj, &unwind_list))
 			goto found;
 	}
 
+none:
 	/* Nothing found, clean up and bail out! */
 	while (!list_empty(&unwind_list)) {
 		obj = list_first_entry(&unwind_list,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 50b07a1..dbb003d 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -354,7 +354,7 @@ pin_and_fence_object(struct drm_i915_gem_object *obj,
 		obj->tiling_mode != I915_TILING_NONE;
 	need_mappable = need_fence || need_reloc_mappable(obj);
 
-	ret = i915_gem_object_pin(obj, entry->alignment, need_mappable);
+	ret = i915_gem_object_pin(obj, entry->alignment, need_mappable, false);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 830d0dd..7a98459 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -1439,7 +1439,7 @@ void intel_setup_overlay(struct drm_device *dev)
 		}
 		overlay->flip_addr = reg_bo->phys_obj->handle->busaddr;
 	} else {
-		ret = i915_gem_object_pin(reg_bo, PAGE_SIZE, true);
+		ret = i915_gem_object_pin(reg_bo, PAGE_SIZE, true, false);
 		if (ret) {
 			DRM_ERROR("failed to pin overlay register bo\n");
 			goto out_free_bo;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d64dffb..3021c18 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2138,7 +2138,7 @@ intel_alloc_context_page(struct drm_device *dev)
 		return NULL;
 	}
 
-	ret = i915_gem_object_pin(ctx, 4096, true);
+	ret = i915_gem_object_pin(ctx, 4096, true, false);
 	if (ret) {
 		DRM_ERROR("failed to pin power context: %d\n", ret);
 		goto err_unref;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 95144b1..80d8791 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -379,7 +379,7 @@ init_pipe_control(struct intel_ring_buffer *ring)
 
 	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
 
-	ret = i915_gem_object_pin(obj, 4096, true);
+	ret = i915_gem_object_pin(obj, 4096, true, false);
 	if (ret)
 		goto err_unref;
 
@@ -967,7 +967,7 @@ static int init_status_page(struct intel_ring_buffer *ring)
 
 	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
 
-	ret = i915_gem_object_pin(obj, 4096, true);
+	ret = i915_gem_object_pin(obj, 4096, true, false);
 	if (ret != 0) {
 		goto err_unref;
 	}
@@ -1024,7 +1024,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 
 	ring->obj = obj;
 
-	ret = i915_gem_object_pin(obj, PAGE_SIZE, true);
+	ret = i915_gem_object_pin(obj, PAGE_SIZE, true, false);
 	if (ret)
 		goto err_unref;
 
-- 
1.7.10.4

  parent reply index

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-08-11 14:40 Stolen pages, with a little surprise Chris Wilson
2012-08-11 14:41 ` [PATCH 01/29] drm/i915: Track unbound pages Chris Wilson
2012-08-20  9:00   ` [PATCH 1/2] drm/i915: move functions around Daniel Vetter
2012-08-20  9:00     ` [PATCH 2/2] drm/i915: Track unbound pages Daniel Vetter
2012-08-20  9:23       ` [PATCH] Add some sanity checks to unbound tracking Chris Wilson
2012-08-20  9:36       ` [PATCH 2/2] drm/i915: Track unbound pages Chris Wilson
2012-08-20  9:42         ` Daniel Vetter
2012-08-11 14:41 ` [PATCH 02/29] drm/i915: Show (count, size) of purgeable objects in i915_gem_objects Chris Wilson
2012-08-20  9:04   ` Daniel Vetter
2012-08-20  9:17     ` Chris Wilson
2012-08-11 14:41 ` [PATCH 03/29] drm/i915: Show pin count in debugfs Chris Wilson
2012-08-11 14:41 ` [PATCH 04/29] drm/i915: Try harder to allocate an mmap_offset Chris Wilson
2012-08-20  9:37   ` Daniel Vetter
2012-08-20 11:31     ` Chris Wilson
2012-08-11 14:41 ` Chris Wilson [this message]
2012-08-11 14:41 ` [PATCH 06/29] drm/i915: Protect private gem objects from truncate (such as imported dmabuf) Chris Wilson
2012-08-11 14:41 ` [PATCH 07/29] drm/i915: Extract general object init routine Chris Wilson
2012-08-24  0:05   ` Daniel Vetter
2012-08-11 14:41 ` [PATCH 08/29] drm/i915: Introduce drm_i915_gem_object_ops Chris Wilson
2012-08-20 19:35   ` Daniel Vetter
2012-08-11 14:41 ` [PATCH 09/29] drm/i915: Pin backing pages whilst exporting through a dmabuf vmap Chris Wilson
2012-08-11 14:41 ` [PATCH 10/29] drm/i915: Pin backing pages for pwrite Chris Wilson
2012-08-11 14:41 ` [PATCH 11/29] drm/i915: Pin backing pages for pread Chris Wilson
2012-08-11 14:41 ` [PATCH 12/29] drm/i915: Replace the array of pages with a scatterlist Chris Wilson
2012-08-11 14:41 ` [PATCH 13/29] drm/i915: Convert the dmabuf object to use the new i915_gem_object_ops Chris Wilson
2012-08-11 14:41 ` [PATCH 14/29] drm: Introduce drm_mm_create_block() Chris Wilson
2012-08-11 14:41 ` [PATCH 15/29] drm/i915: Fix detection of stolen base for gen2 Chris Wilson
2012-08-11 14:41 ` [PATCH 16/29] drm/i915: Fix location of stolen memory register for SandyBridge+ Chris Wilson
2012-08-20 19:38   ` Daniel Vetter
2012-08-22 15:54     ` Chris Wilson
2012-08-11 14:41 ` [PATCH 17/29] drm/i915: Avoid clearing preallocated regions from the GTT Chris Wilson
2012-08-11 14:41 ` [PATCH 18/29] drm/i915: Delay allocation of stolen space for FBC Chris Wilson
2012-08-20 19:51   ` Daniel Vetter
2012-08-22 15:51     ` Chris Wilson
2012-08-11 14:41 ` [PATCH 19/29] drm/i915: Allow objects to be created with no backing pages, but stolen space Chris Wilson
2012-08-11 14:41 ` [PATCH 20/29] drm/i915: Differentiate between prime and stolen objects Chris Wilson
2012-08-11 14:41 ` [PATCH 21/29] drm/i915: Support readback of stolen objects upon error Chris Wilson
2012-08-11 14:41 ` [PATCH 22/29] drm/i915: Handle stolen objects in pwrite Chris Wilson
2012-08-20 19:56   ` Daniel Vetter
2012-08-22 15:47     ` Chris Wilson
2012-08-30 15:09     ` Chris Wilson
2012-08-11 14:41 ` [PATCH 23/29] drm/i915: Handle stolen objects for pread Chris Wilson
2012-08-11 14:41 ` [PATCH 24/29] drm/i915: Introduce i915_gem_object_create_stolen() Chris Wilson
2012-08-11 14:41 ` [PATCH 25/29] drm/i915: Allocate fbcon from stolen memory Chris Wilson
2012-08-11 14:41 ` [PATCH 26/29] drm/i915: Allocate ringbuffers " Chris Wilson
2012-08-11 14:41 ` [PATCH 27/29] drm/i915: Allocate overlay registers " Chris Wilson
2012-08-20 21:17   ` Daniel Vetter
2012-08-22 15:45     ` Chris Wilson
2012-08-22 16:26       ` Daniel Vetter
2012-08-11 14:41 ` [PATCH 28/29] drm/i915: Use a slab for object allocation Chris Wilson
2012-08-11 14:41 ` [PATCH 29/29] drm/i915: Introduce mapping of user pages into video memory (userptr) ioctl Chris Wilson

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=1344696088-24760-6-git-send-email-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --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

Intel-GFX Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/intel-gfx/0 intel-gfx/git/0.git
	git clone --mirror https://lore.kernel.org/intel-gfx/1 intel-gfx/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 intel-gfx intel-gfx/ https://lore.kernel.org/intel-gfx \
		intel-gfx@lists.freedesktop.org
	public-inbox-index intel-gfx

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.freedesktop.lists.intel-gfx


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git