drm/i915: Use memset64() to align the ring with MI_NOOP

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.

v2: s/0/MI_NOOP<<32 | MI_NOOP/
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180425123718.16366-1-chris@chris-wilson.co.uk

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, (u64)MI_NOOP << 32 | MI_NOOP, num_dwords / 2);
 	intel_ring_advance(rq, cs);
 
+	GEM_BUG_ON(rq->ring->emit & (CACHELINE_BYTES - 1));
 	return 0;
 }