drm/i915: Emit to ringbuffer directly

This removes the usage of intel_ring_emit in favour of
directly writing to the ring buffer.

intel_ring_emit was preventing the compiler for optimising
fetch and increment of the current ring buffer pointer and
therefore generating very verbose code for every write.

It had no useful purpose since all ringbuffer operations
are started and ended with intel_ring_begin and
intel_ring_advance respectively, with no bail out in the
middle possible, so it is fine to increment the tail in
intel_ring_begin and let the code manage the pointer
itself.

Useless instruction removal amounts to approximately
two and half kilobytes of saved text on my build.

Not sure if this has any measurable performance
implications but executing a ton of useless instructions
on fast paths cannot be good.

v2:
 * Change return from intel_ring_begin to error pointer by
   popular demand.
 * Move tail increment to intel_ring_advance to enable some
   error checking.

v3:
 * Move tail advance back into intel_ring_begin.
 * Rebase and tidy.

v4:
 * Complete rebase after a few months since v3.

v5:
 * Remove unecessary cast and fix !debug compile. (Chris Wilson)

v6:
 * Make intel_ring_offset take request as well.
 * Fix recording of request postfix plus a sprinkle of asserts.
   (Chris Wilson)

v7:
 * Use intel_ring_offset to get the postfix. (Chris Wilson)
 * Convert GVT code as well.

v8:
 * Rename *out++ to *cs++.

v9:
 * Fix GVT out to cs conversion in GVT.

v10:
 * Rebase for new intel_ring_begin in selftests.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170214113242.29241-1-tvrtko.ursulin@linux.intel.com

1 files changed, 19 insertions, 21 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 111b7f8c617a..da0846fe2ad6 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1336,25 +1336,25 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 static int
 i915_reset_gen7_sol_offsets(struct drm_i915_gem_request *req)
 {
-	struct intel_ring *ring = req->ring;
-	int ret, i;
+	u32 *cs;
+	int i;
 
 	if (!IS_GEN7(req->i915) || req->engine->id != RCS) {
 		DRM_DEBUG("sol reset is gen7/rcs only\n");
 		return -EINVAL;
 	}
 
-	ret = intel_ring_begin(req, 4 * 3);
-	if (ret)
-		return ret;
+	cs = intel_ring_begin(req, 4 * 3);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
 
 	for (i = 0; i < 4; i++) {
-		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit_reg(ring, GEN7_SO_WRITE_OFFSET(i));
-		intel_ring_emit(ring, 0);
+		*cs++ = MI_LOAD_REGISTER_IMM(1);
+		*cs++ = i915_mmio_reg_offset(GEN7_SO_WRITE_OFFSET(i));
+		*cs++ = 0;
 	}
 
-	intel_ring_advance(ring);
+	intel_ring_advance(req, cs);
 
 	return 0;
 }
@@ -1415,7 +1415,7 @@ execbuf_submit(struct i915_execbuffer_params *params,
 	struct drm_i915_private *dev_priv = params->request->i915;
 	u64 exec_start, exec_len;
 	int instp_mode;
-	u32 instp_mask;
+	u32 instp_mask, *cs;
 	int ret;
 
 	ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
@@ -1461,17 +1461,15 @@ execbuf_submit(struct i915_execbuffer_params *params,
 
 	if (params->engine->id == RCS &&
 	    instp_mode != dev_priv->relative_constants_mode) {
-		struct intel_ring *ring = params->request->ring;
-
-		ret = intel_ring_begin(params->request, 4);
-		if (ret)
-			return ret;
-
-		intel_ring_emit(ring, MI_NOOP);
-		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit_reg(ring, INSTPM);
-		intel_ring_emit(ring, instp_mask << 16 | instp_mode);
-		intel_ring_advance(ring);
+		cs = intel_ring_begin(params->request, 4);
+		if (IS_ERR(cs))
+			return PTR_ERR(cs);
+
+		*cs++ = MI_NOOP;
+		*cs++ = MI_LOAD_REGISTER_IMM(1);
+		*cs++ = i915_mmio_reg_offset(INSTPM);
+		*cs++ = instp_mask << 16 | instp_mode;
+		intel_ring_advance(params->request, cs);
 
 		dev_priv->relative_constants_mode = instp_mode;
 	}