[Intel-gfx] [PATCH 186/190] drm/i915/cmdparser: Compare against the previous command descriptor

[Chris Wilson]

On the blitter (and in test code), we see long sequences of repeated
commands, e.g. XY_PIXEL_BLT, XY_SCANLINE_BLT, or XY_SRC_COPY. For these,
we can skip the hashtable lookup by remembering the previous command
descriptor and doing a straightforward compare of the command header.
The corollary is that we need to do one extra comparison before lookup
up new commands.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_cmd_parser.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 4fdcb19012e5..c0b034171b52 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -349,6 +349,9 @@ static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = {
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
 };
 
+static const struct drm_i915_cmd_descriptor noop_desc =
+	CMD(MI_NOOP, SMI, F, 1, S);
+
 #undef CMD
 #undef SMI
 #undef S3D
@@ -839,11 +842,14 @@ find_cmd_in_table(struct intel_engine_cs *ring,
 static const struct drm_i915_cmd_descriptor*
 find_cmd(struct intel_engine_cs *ring,
 	 u32 cmd_header,
+	 const struct drm_i915_cmd_descriptor *desc,
 	 struct drm_i915_cmd_descriptor *default_desc)
 {
-	const struct drm_i915_cmd_descriptor *desc;
 	u32 mask;
 
+	if (((cmd_header ^ desc->cmd.value) & desc->cmd.mask) == 0)
+		return desc;
+
 	desc = find_cmd_in_table(ring, cmd_header);
 	if (desc)
 		return desc;
@@ -852,10 +858,10 @@ find_cmd(struct intel_engine_cs *ring,
 	if (!mask)
 		return NULL;
 
-	BUG_ON(!default_desc);
-	default_desc->flags = CMD_DESC_SKIP;
+	default_desc->cmd.value = cmd_header;
+	default_desc->cmd.mask = 0xffff0000;
 	default_desc->length.mask = mask;
-
+	default_desc->flags = CMD_DESC_SKIP;
 	return default_desc;
 }
 
@@ -1080,7 +1086,8 @@ int i915_parse_cmds(struct intel_engine_cs *ring,
 		    bool is_master)
 {
 	u32 *cmd, *batch_end;
-	struct drm_i915_cmd_descriptor default_desc = { 0 };
+	struct drm_i915_cmd_descriptor default_desc = noop_desc;
+	const struct drm_i915_cmd_descriptor *desc = &default_desc;
 	bool oacontrol_set = false; /* OACONTROL tracking. See check_cmd() */
 	bool needs_clflush_after = false;
 	int ret = 0;
@@ -1100,13 +1107,12 @@ int i915_parse_cmds(struct intel_engine_cs *ring,
 	 */
 	batch_end = cmd + (batch_len / sizeof(*batch_end));
 	while (cmd < batch_end) {
-		const struct drm_i915_cmd_descriptor *desc;
 		u32 length;
 
 		if (*cmd == MI_BATCH_BUFFER_END)
 			break;
 
-		desc = find_cmd(ring, *cmd, &default_desc);
+		desc = find_cmd(ring, *cmd, desc, &default_desc);
 		if (!desc) {
 			DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n",
 					 *cmd);
-- 
2.7.0.rc3