[Intel-gfx] [CI] drm/i915: Prefer memset64() when filling the iomap

[Chris Wilson]

As the ringbuffer may exist inside stolen memory, our access to it may
be via the GTT iomap. This implies we may only have WC access for which
the conventional memset() substitution of rep stos performs very badly,
so switch to the rep mov[dq] variants when available.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at intel.com>
Cc: Matthew Auld <matthew.auld at intel.com>
Reviewed-by: Matthew Auld <matthew.auld at intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 72d6167c519a..04d9d9a946a7 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1693,17 +1693,18 @@ u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords)
 		need_wrap &= ~1;
 		GEM_BUG_ON(need_wrap > ring->space);
 		GEM_BUG_ON(ring->emit + need_wrap > ring->size);
+		GEM_BUG_ON(!IS_ALIGNED(need_wrap, sizeof(u64)));
 
 		/* Fill the tail with MI_NOOP */
-		memset(ring->vaddr + ring->emit, 0, need_wrap);
-		ring->emit = 0;
+		memset64(ring->vaddr + ring->emit, 0, need_wrap / sizeof(u64));
 		ring->space -= need_wrap;
+		ring->emit = 0;
 	}
 
 	GEM_BUG_ON(ring->emit > ring->size - bytes);
 	GEM_BUG_ON(ring->space < bytes);
 	cs = ring->vaddr + ring->emit;
-	GEM_DEBUG_EXEC(memset(cs, POISON_INUSE, bytes));
+	GEM_DEBUG_EXEC(memset32(cs, POISON_INUSE, bytes / sizeof(*cs)));
 	ring->emit += bytes;
 	ring->space -= bytes;
 
-- 
2.16.2