From: Ben Widawsky <ben@bwidawsk.net>
To: intel-gfx@lists.freedesktop.org
Cc: Ben Widawsky <ben@bwidawsk.net>
Subject: [PATCH 08/25] drm/i915: Ivybridge MI_ARB_ON_OFF context w/a
Date: Mon, 4 Jun 2012 14:42:48 -0700 [thread overview]
Message-ID: <1338846185-10571-9-git-send-email-ben@bwidawsk.net> (raw)
In-Reply-To: <1338846185-10571-1-git-send-email-ben@bwidawsk.net>
The workaround itself applies to gen7 only (according to the docs) and
as Eric Anholt points out shouldn't be required since we don't use HW
scheduling features, and therefore arbitration. Though since it is a
small, and simple addition, and we don't really understand the issue,
just do it.
FWIW, I eventually want to play with some of the arbitration stuff, and
I'd hate to forget about this.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
drivers/gpu/drm/i915/i915_gem_context.c | 12 +++++++++++-
drivers/gpu/drm/i915/i915_reg.h | 3 +++
2 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 388cf62..06e7264 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -331,10 +331,15 @@ mi_set_context(struct intel_ring_buffer *ring,
{
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(ring, 6);
if (ret)
return ret;
+ if (IS_GEN7(ring->dev))
+ intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_DISABLE);
+ else
+ intel_ring_emit(ring, MI_NOOP);
+
intel_ring_emit(ring, MI_NOOP);
intel_ring_emit(ring, MI_SET_CONTEXT);
intel_ring_emit(ring, new_context->obj->gtt_offset |
@@ -345,6 +350,11 @@ mi_set_context(struct intel_ring_buffer *ring,
/* w/a: MI_SET_CONTEXT must always be followed by MI_NOOP */
intel_ring_emit(ring, MI_NOOP);
+ if (IS_GEN7(ring->dev))
+ intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
+ else
+ intel_ring_emit(ring, MI_NOOP);
+
intel_ring_advance(ring);
return ret;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 66ed7e6..700e148 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -210,6 +210,9 @@
#define MI_DISPLAY_FLIP MI_INSTR(0x14, 2)
#define MI_DISPLAY_FLIP_I915 MI_INSTR(0x14, 1)
#define MI_DISPLAY_FLIP_PLANE(n) ((n) << 20)
+#define MI_ARB_ON_OFF MI_INSTR(0x08, 0)
+#define MI_ARB_ENABLE (1<<0)
+#define MI_ARB_DISABLE (0<<0)
#define MI_SET_CONTEXT MI_INSTR(0x18, 0)
#define MI_MM_SPACE_GTT (1<<8)
#define MI_MM_SPACE_PHYSICAL (0<<8)
--
1.7.10.2
next prev parent reply other threads:[~2012-06-04 21:45 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-06-04 21:42 [PATCH 00/25] i915 HW context support Ben Widawsky
2012-06-04 21:42 ` [PATCH 01/25] drm/i915: CXT_SIZE register offsets added Ben Widawsky
2012-06-04 21:42 ` [PATCH 02/25 v2] drm/i915: preliminary context support Ben Widawsky
2012-06-05 12:23 ` Ville Syrjälä
2012-06-05 16:30 ` Ben Widawsky
2012-06-04 21:42 ` [PATCH 03/25 v2] drm/i915: context basic create & destroy Ben Widawsky
2012-06-13 23:27 ` Ben Widawsky
2012-06-04 21:42 ` [PATCH 04/25] drm/i915: add context information to objects Ben Widawsky
2012-06-13 22:01 ` Daniel Vetter
2012-06-13 23:26 ` Ben Widawsky
2012-06-04 21:42 ` [PATCH 05/25] drm/i915: always bind context objects immediately Ben Widawsky
2012-06-04 21:42 ` [PATCH 06/25 v3] drm/i915: context switch implementation Ben Widawsky
2012-06-04 21:42 ` [PATCH 07/25] drm/i915: context trace events Ben Widawsky
2012-06-13 22:23 ` Daniel Vetter
2012-06-13 23:27 ` Ben Widawsky
2012-06-04 21:42 ` Ben Widawsky [this message]
2012-06-04 21:42 ` [PATCH 09/25] drm/i915: PIPE_CONTROL_TLB_INVALIDATE Ben Widawsky
2012-06-04 21:42 ` [PATCH 10/25 v2] drm/i915: possibly invalidate TLB before context switch Ben Widawsky
2012-06-04 21:42 ` [PATCH 11/25] drm/i915: use the default context Ben Widawsky
2012-06-04 21:42 ` [PATCH 12/25] drm/i915: add ccid to error state Ben Widawsky
2012-06-04 21:42 ` [PATCH 13/25 v3] drm/i915: switch to default context on idle Ben Widawsky
2012-06-04 21:42 ` [PATCH 14/25 v3] drm/i915/context: create & destroy ioctls Ben Widawsky
2012-06-04 21:42 ` [PATCH 15/25 v2] drm/i915/context: switch contexts with execbuf2 Ben Widawsky
2012-06-04 21:42 ` [PATCH 16/25] drm/i915: reset the GPU on context fini Ben Widawsky
2012-06-04 21:42 ` [PATCH 17/25] intel: wait render placeholder Ben Widawsky
2012-06-04 21:42 ` [PATCH 18/25] intel: Merge updated kernel header Ben Widawsky
2012-06-04 21:42 ` [PATCH 19/25] intel/context: Add drm_intel_context type Ben Widawsky
2012-06-04 21:43 ` [PATCH 20/25] intel/context: new execbuf interface for contexts Ben Widawsky
2012-06-04 21:43 ` [PATCH 21/25] intel: add decoding of MI_SET_CONTEXT Ben Widawsky
2012-06-04 21:43 ` [PATCH 22/25] context: libdrm wrappers Ben Widawsky
2012-06-04 21:43 ` [PATCH 23/25] context: update for new execbuf2 element Ben Widawsky
2012-06-04 21:43 ` [PATCH 24/25] contexts: basic test coverage Ben Widawsky
2012-06-13 23:30 ` Daniel Vetter
2012-06-14 3:13 ` [PATCH] " Ben Widawsky
2012-06-04 21:43 ` [PATCH 25/25] i965: hw context support Ben Widawsky
2012-06-04 23:01 ` Paul Berry
2012-06-04 23:10 ` [Intel-gfx] " Ben Widawsky
2012-06-05 5:53 ` [PATCH 00/25] i915 HW " Dave Airlie
2012-06-05 7:08 ` [Mesa-dev] " Kenneth Graunke
2012-06-05 16:32 ` Ben Widawsky
2012-06-05 23:37 ` Kenneth Graunke
2012-06-07 16:17 ` Ben Widawsky
2012-06-14 16:04 ` 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=1338846185-10571-9-git-send-email-ben@bwidawsk.net \
--to=ben@bwidawsk.net \
--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