When filling the ring to align the emit pointer to the next cacheline,
use memset64() rather than open-coding it. As we know that we always
have an even number of dwords, we can replace the dword loop with the
qword equivalent.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/intel_ringbuffer.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index c68ac605b8a9..07a9a2b4beb7 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1717,22 +1717,24 @@ u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords)
/* Align the ring tail to a cacheline boundary */
int intel_ring_cacheline_align(struct i915_request *rq)
{
- int num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32);
- u32 *cs;
+ int num_dwords;
+ void *cs;
+ num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32);
if (num_dwords == 0)
return 0;
- num_dwords = CACHELINE_BYTES / sizeof(u32) - num_dwords;
+ num_dwords = CACHELINE_DWORDS - num_dwords;
+ GEM_BUG_ON(num_dwords & 1);
+
cs = intel_ring_begin(rq, num_dwords);
if (IS_ERR(cs))
return PTR_ERR(cs);
- while (num_dwords--)
- *cs++ = MI_NOOP;
-
+ memset64(cs, 0, num_dwords/2);
intel_ring_advance(rq, cs);
+ GEM_BUG_ON(rq->ring->emit & CACHELINE_BYTES);
return 0;
}
--
2.17.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
