Commit a1444b79 authored by Ben Widawsky's avatar Ben Widawsky Committed by Daniel Vetter

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: default avatarRodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> (v1)
Signed-off-by: default avatarBen Widawsky <ben@bwidawsk.net>
Signed-off-by: default avatarRodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: default avatarDaniel Vetter <daniel.vetter@ffwll.ch>
parent 707d9cf9
...@@ -679,23 +679,16 @@ static int gen6_signal(struct intel_engine_cs *signaller, ...@@ -679,23 +679,16 @@ static int gen6_signal(struct intel_engine_cs *signaller,
struct drm_device *dev = signaller->dev; struct drm_device *dev = signaller->dev;
struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *useless; 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 #define MBOX_UPDATE_DWORDS 3
* number of rings, it's easiest if we round up each individual update num_rings = hweight32(INTEL_INFO(dev)->ring_mask);
* to a multiple of 2 (since ring updates must always be a multiple of num_dwords += round_up((num_rings-1) * MBOX_UPDATE_DWORDS, 2);
* 2) even though the actual update only requires 3 dwords. #undef MBOX_UPDATE_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);
ret = intel_ring_begin(signaller, num_dwords); ret = intel_ring_begin(signaller, num_dwords);
if (ret) if (ret)
return ret; return ret;
#undef MBOX_UPDATE_DWORDS
for_each_ring(useless, dev_priv, i) { for_each_ring(useless, dev_priv, i) {
u32 mbox_reg = signaller->semaphore.mbox.signal[i]; u32 mbox_reg = signaller->semaphore.mbox.signal[i];
...@@ -703,15 +696,13 @@ static int gen6_signal(struct intel_engine_cs *signaller, ...@@ -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, MI_LOAD_REGISTER_IMM(1));
intel_ring_emit(signaller, mbox_reg); intel_ring_emit(signaller, mbox_reg);
intel_ring_emit(signaller, signaller->outstanding_lazy_seqno); 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; return 0;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment