drm/i915/cmdparser: Limit clflush to active cachelines

We only need to clflush those cachelines that we have validated to be
read by the GPU. Userspace typically fills the batch length in
correctly, the exceptions tend to be explicit tests within igt.

v2: Use ptr_mask_bits() to make Mika happy
v3: cmd is not advanced on MI_BBE, so make sure to include an extra
dword in the clflush.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170310115518.13832-1-chris@chris-wilson.co.uk

1 files changed, 14 insertions, 11 deletions

diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 21b1cd917d81..7af100f84410 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1279,11 +1279,17 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 	 * space. Parsing should be faster in some cases this way.
 	 */
 	batch_end = cmd + (batch_len / sizeof(*batch_end));
-	while (cmd < batch_end) {
+	do {
 		u32 length;
 
-		if (*cmd == MI_BATCH_BUFFER_END)
+		if (*cmd == MI_BATCH_BUFFER_END) {
+			if (needs_clflush_after) {
+				void *ptr = ptr_mask_bits(shadow_batch_obj->mm.mapping);
+				drm_clflush_virt_range(ptr,
+						       (void *)(cmd + 1) - ptr);
+			}
 			break;
+		}
 
 		desc = find_cmd(engine, *cmd, desc, &default_desc);
 		if (!desc) {
@@ -1323,17 +1329,14 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 		}
 
 		cmd += length;
-	}
-
-	if (cmd >= batch_end) {
-		DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
-		ret = -EINVAL;
-	}
+		if  (cmd >= batch_end) {
+			DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
+			ret = -EINVAL;
+			break;
+		}
+	} while (1);
 
-	if (ret == 0 && needs_clflush_after)
-		drm_clflush_virt_range(shadow_batch_obj->mm.mapping, batch_len);
 	i915_gem_object_unpin_map(shadow_batch_obj);
-
 	return ret;
 }