intel-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH 04/14] drm/i915: Defer the unbind for a fence change until the next get_fence()
Date: Mon,  3 Dec 2012 11:49:02 +0000	[thread overview]
Message-ID: <1354535352-3506-5-git-send-email-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <1354535352-3506-1-git-send-email-chris@chris-wilson.co.uk>

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h        |    4 ++
 drivers/gpu/drm/i915/i915_gem.c        |   10 ++--
 drivers/gpu/drm/i915/i915_gem_tiling.c |   87 ++++++++------------------------
 3 files changed, 29 insertions(+), 72 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e2944e9..32cfe23 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1437,6 +1437,10 @@ int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev,
 		      uint32_t handle, uint64_t *offset);
 int i915_gem_dumb_destroy(struct drm_file *file_priv, struct drm_device *dev,
 			  uint32_t handle);
+
+uint32_t i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode);
+uint32_t i915_gem_get_gtt_alignment(struct drm_device *dev, uint32_t size, int tiling_mode);
+
 /**
  * Returns true if seq1 is later than seq2.
  */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f660f20..987227b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1437,7 +1437,7 @@ i915_gem_release_mmap(struct drm_i915_gem_object *obj)
 	obj->fault_mappable = false;
 }
 
-static uint32_t
+uint32_t
 i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode)
 {
 	uint32_t gtt_size;
@@ -1465,7 +1465,7 @@ i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode)
  * Return the required GTT alignment for an object, taking into account
  * potential fence register mapping.
  */
-static uint32_t
+uint32_t
 i915_gem_get_gtt_alignment(struct drm_device *dev,
 			   uint32_t size,
 			   int tiling_mode)
@@ -2484,13 +2484,13 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 
 	list_del(&obj->mm_list);
 	list_move_tail(&obj->gtt_list, &dev_priv->mm.unbound_list);
-	/* Avoid an unnecessary call to unbind on rebind. */
-	obj->map_and_fenceable = true;
 
 	drm_mm_put_block(obj->gtt_space);
 	obj->gtt_space = NULL;
 	obj->gtt_offset = 0;
 
+	obj->map_and_fenceable = false;
+
 	return 0;
 }
 
@@ -3689,8 +3689,6 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 
 	obj->fence_reg = I915_FENCE_REG_NONE;
 	obj->madv = I915_MADV_WILLNEED;
-	/* Avoid an unnecessary call to unbind on the first bind. */
-	obj->map_and_fenceable = true;
 
 	i915_gem_info_add_obj(obj->base.dev->dev_private, obj->base.size);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index cedbfd7..8e59bb5 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -252,47 +252,6 @@ i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode)
 	return true;
 }
 
-/* Is the current GTT allocation valid for the change in tiling? */
-static bool
-i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode)
-{
-	u32 size;
-
-	if (tiling_mode == I915_TILING_NONE)
-		return true;
-
-	if (INTEL_INFO(obj->base.dev)->gen >= 4)
-		return true;
-
-	if (INTEL_INFO(obj->base.dev)->gen == 3) {
-		if (obj->gtt_offset & ~I915_FENCE_START_MASK)
-			return false;
-	} else {
-		if (obj->gtt_offset & ~I830_FENCE_START_MASK)
-			return false;
-	}
-
-	/*
-	 * Previous chips need to be aligned to the size of the smallest
-	 * fence register that can contain the object.
-	 */
-	if (INTEL_INFO(obj->base.dev)->gen == 3)
-		size = 1024*1024;
-	else
-		size = 512*1024;
-
-	while (size < obj->base.size)
-		size <<= 1;
-
-	if (obj->gtt_space->size != size)
-		return false;
-
-	if (obj->gtt_offset & (size - 1))
-		return false;
-
-	return true;
-}
-
 /**
  * Sets the tiling mode of an object, returning the required swizzling of
  * bit 6 of addresses in the object.
@@ -365,33 +324,29 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		 * has to also include the unfenced register the GPU uses
 		 * whilst executing a fenced command for an untiled object.
 		 */
-
-		obj->map_and_fenceable =
-			obj->gtt_space == NULL ||
-			(obj->gtt_offset + obj->base.size <= dev_priv->mm.gtt_mappable_end &&
-			 i915_gem_object_fence_ok(obj, args->tiling_mode));
-
-		/* Rebind if we need a change of alignment */
-		if (!obj->map_and_fenceable) {
-			u32 unfenced_alignment =
-				i915_gem_get_unfenced_gtt_alignment(dev,
-								    obj->base.size,
-								    args->tiling_mode);
-			if (obj->gtt_offset & (unfenced_alignment - 1))
-				ret = i915_gem_object_unbind(obj);
+		obj->fence_dirty =
+			obj->fenced_gpu_access ||
+			obj->fence_reg != I915_FENCE_REG_NONE;
+
+		obj->tiling_mode = args->tiling_mode;
+		obj->stride = args->stride;
+
+		if (obj->gtt_space) {
+			unsigned fence_size = i915_gem_get_gtt_size(dev, obj->base.size, obj->tiling_mode);
+			unsigned fence_alignment = i915_gem_get_gtt_alignment(dev,
+									      obj->base.size,
+									      obj->tiling_mode);
+			bool fenceable =
+				obj->gtt_space->size == fence_size &&
+				(obj->gtt_space->start & (fence_alignment - 1)) == 0;
+			bool mappable =
+				obj->gtt_offset + obj->base.size <= dev_priv->mm.gtt_mappable_end;
+
+			obj->map_and_fenceable = mappable && fenceable;
 		}
 
-		if (ret == 0) {
-			obj->fence_dirty =
-				obj->fenced_gpu_access ||
-				obj->fence_reg != I915_FENCE_REG_NONE;
-
-			obj->tiling_mode = args->tiling_mode;
-			obj->stride = args->stride;
-
-			/* Force the fence to be reacquired for GTT access */
-			i915_gem_release_mmap(obj);
-		}
+		/* Force the fence to be reacquired for GTT access */
+		i915_gem_release_mmap(obj);
 	}
 	/* we have to maintain this existing ABI... */
 	args->stride = obj->stride;
-- 
1.7.10.4

  parent reply	other threads:[~2012-12-03 11:50 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-12-03 11:48 A bunch of random execbuffer patches Chris Wilson
2012-12-03 11:48 ` [PATCH 01/14] drm/i915: Move the get_pages assertions up to the right layer Chris Wilson
2012-12-03 11:49 ` [PATCH 02/14] drm/i915: Decouple the object from the unbound list before freeing pages Chris Wilson
2012-12-03 16:16   ` Daniel Vetter
2012-12-03 11:49 ` [PATCH 03/14] drm/i915: Bail if we attempt to allocate pages for a purged object Chris Wilson
2012-12-03 11:49 ` Chris Wilson [this message]
2012-12-03 11:49 ` [PATCH 05/14] drm/i915: Avoid forcing relocations through the mappable GTT or CPU Chris Wilson
2012-12-03 11:49 ` [PATCH 06/14] drm: Optionally create mm blocks from top-to-bottom Chris Wilson
2012-12-03 11:49 ` [PATCH 07/14] drm/i915: Preferentially allocate mappable GTT space to uncached bo Chris Wilson
2012-12-03 11:49 ` [PATCH 08/14] drm/i915: Tighten the checks for invalid relocation domains Chris Wilson
2012-12-03 11:49 ` [PATCH 09/14] drm/i915: Remove check for conflicting relocation write-domains Chris Wilson
2012-12-03 19:18   ` Daniel Vetter
2012-12-03 21:03     ` [PATCH] drm/i915: Reduce memory pressure during shrinker by preallocating swizzle pages Chris Wilson
2012-12-07  0:16       ` Daniel Vetter
2012-12-03 11:49 ` [PATCH 10/14] drm/i915: Take the handle idr spinlock once for looking up the exec objects Chris Wilson
2012-12-03 11:49 ` [PATCH 11/14] drm/i915: Move the execbuffer objects list from the stack into the tracker Chris Wilson
2012-12-03 11:49 ` [PATCH 12/14] drm/i915: Allow userspace to hint that the relocations were known Chris Wilson
2012-12-03 11:49 ` [PATCH 13/14] drm/i915: Use the reloc.handle as an index into the execbuffer array Chris Wilson
2012-12-03 11:49 ` [PATCH 14/14] drm/i915: Allow userspace to request an object at a specific offset 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=1354535352-3506-5-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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).