From: Daniel Vetter <daniel.vetter@ffwll.ch>
To: Intel Graphics Development <intel-gfx@lists.freedesktop.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Subject: [PATCH 3/5] drm/i915: implement SNB workaround for lazy global gtt
Date: Wed, 15 Feb 2012 23:50:23 +0100 [thread overview]
Message-ID: <1329346225-14795-4-git-send-email-daniel.vetter@ffwll.ch> (raw)
In-Reply-To: <1329346225-14795-1-git-send-email-daniel.vetter@ffwll.ch>
PIPE_CONTROL on snb needs global gtt mappings in place to workaround a
hw gotcha. No other commands need such a workaround. Luckily we can
detect a PIPE_CONTROL commands easily because they have a write_domain
= I915_GEM_DOMAIN_INSTRUCTION (and nothing else has that).
v2: Binding the target of such a reloc into the global gtt actually
works instead of binding the source, which is rather pointless ...
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 15 ++++++++++++++-
1 files changed, 14 insertions(+), 1 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 81687af..f8cabf2 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -273,6 +273,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
{
struct drm_device *dev = obj->base.dev;
struct drm_gem_object *target_obj;
+ struct drm_i915_gem_object *target_i915_obj;
uint32_t target_offset;
int ret = -EINVAL;
@@ -281,7 +282,8 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
if (unlikely(target_obj == NULL))
return -ENOENT;
- target_offset = to_intel_bo(target_obj)->gtt_offset;
+ target_i915_obj = to_intel_bo(target_obj);
+ target_offset = target_i915_obj->gtt_offset;
/* The target buffer should have appeared before us in the
* exec_object list, so it should have a GTT space bound by now.
@@ -383,6 +385,17 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
io_mapping_unmap_atomic(reloc_page);
}
+ /* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
+ * pipe_control writes because the gpu doesn't properly redirect them
+ * through the ppgtt for non_secure batchbuffers. */
+ if (unlikely(IS_GEN6(dev) &&
+ reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
+ !target_i915_obj->has_global_gtt_mapping)) {
+ i915_gem_gtt_bind_object(target_i915_obj,
+ target_i915_obj->cache_level);
+ target_i915_obj->has_global_gtt_mapping = 1;
+ }
+
/* and update the user's relocation entry */
reloc->presumed_offset = target_offset;
--
1.7.9
next prev parent reply other threads:[~2012-02-15 22:50 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-02-15 22:50 [PATCH 0/5] aliasing ppgtt, advanced things Daniel Vetter
2012-02-15 22:50 ` [PATCH 1/5] drm/i915: split out dma mapping from global gtt bind/unbind functions Daniel Vetter
2012-02-15 22:50 ` [PATCH 2/5] drm/i915: bind objects to the global gtt only when needed Daniel Vetter
2012-02-15 22:50 ` Daniel Vetter [this message]
2012-02-15 23:10 ` [PATCH 3/5] drm/i915: implement SNB workaround for lazy global gtt Chris Wilson
2012-02-15 23:25 ` Daniel Vetter
2012-03-20 20:57 ` Daniel Vetter
2012-02-15 22:50 ` [PATCH 4/5] drm/i915: enable lazy global-gtt binding Daniel Vetter
2012-02-15 22:50 ` [PATCH 5/5] drm/i915: add HAS_ALIASING_PPGTT parameter for userspace Daniel Vetter
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=1329346225-14795-4-git-send-email-daniel.vetter@ffwll.ch \
--to=daniel.vetter@ffwll.ch \
--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