summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915
diff options
context:
space:
mode:
authorBen Widawsky <ben@bwidawsk.net>2014-06-30 20:53:35 +0400
committerDaniel Vetter <daniel.vetter@ffwll.ch>2014-07-08 00:10:10 +0400
commita1444b79fec2e95b705c5505c1f609306538dc49 (patch)
treed482d8ef2b59f5f2d1afa0cd2ee948cad0320515 /drivers/gpu/drm/i915
parent707d9cf9935cfba2d62dd80dc01dc5dc4530d4ca (diff)
downloadlinux-a1444b79fec2e95b705c5505c1f609306538dc49.tar.xz
drm/i915: Make semaphore updates more precise
With the ring mask we now have an easy way to know the number of rings in the system, and therefore can accurately predict the number of dwords to emit for semaphore signalling. This was not possible (easily) previously. There should be no functional impact, simply fewer instructions emitted. While we're here, simply do the round up to 2 instead of the fancier rounding we did before, which rounding up per mbox, ie 4. This also allows us to drop the unnecessary MI_NOOP, so not really 4, 3. v2: Use 3 dwords instead of 4 (Ville) Do the proper calculation to get the number of dwords to emit (Ville) Conditionally set .sync_to when semaphores are enabled (Ville) v3: Rebased on VCS2 Replace hweight_long with hweight32 (Ville) v4: Pull out the accidentally squashed hunk from the next patch after rebase (Daniel). v5: Fix conflict after rebase (Rodrigo) Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> (v1) Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Diffstat (limited to 'drivers/gpu/drm/i915')
-rw-r--r--drivers/gpu/drm/i915/intel_ringbuffer.c27
1 files changed, 9 insertions, 18 deletions
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 7ca1b946d8de..e9c8814bed36 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -679,23 +679,16 @@ static int gen6_signal(struct intel_engine_cs *signaller,
struct drm_device *dev = signaller->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *useless;
- int i, ret;
+ int i, ret, num_rings;
- /* NB: In order to be able to do semaphore MBOX updates for varying
- * number of rings, it's easiest if we round up each individual update
- * to a multiple of 2 (since ring updates must always be a multiple of
- * 2) even though the actual update only requires 3 dwords.
- */
-#define MBOX_UPDATE_DWORDS 4
- if (i915_semaphore_is_enabled(dev))
- num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS);
- else
- return intel_ring_begin(signaller, num_dwords);
+#define MBOX_UPDATE_DWORDS 3
+ num_rings = hweight32(INTEL_INFO(dev)->ring_mask);
+ num_dwords += round_up((num_rings-1) * MBOX_UPDATE_DWORDS, 2);
+#undef MBOX_UPDATE_DWORDS
ret = intel_ring_begin(signaller, num_dwords);
if (ret)
return ret;
-#undef MBOX_UPDATE_DWORDS
for_each_ring(useless, dev_priv, i) {
u32 mbox_reg = signaller->semaphore.mbox.signal[i];
@@ -703,15 +696,13 @@ static int gen6_signal(struct intel_engine_cs *signaller,
intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1));
intel_ring_emit(signaller, mbox_reg);
intel_ring_emit(signaller, signaller->outstanding_lazy_seqno);
- intel_ring_emit(signaller, MI_NOOP);
- } else {
- intel_ring_emit(signaller, MI_NOOP);
- intel_ring_emit(signaller, MI_NOOP);
- intel_ring_emit(signaller, MI_NOOP);
- intel_ring_emit(signaller, MI_NOOP);
}
}
+ /* If num_dwords was rounded, make sure the tail pointer is correct */
+ if (num_rings % 2 == 0)
+ intel_ring_emit(signaller, MI_NOOP);
+
return 0;
}