Currently, the last object in the execlist is the always the batch.
However, when building the batch buffer we often know the batch object
first and if we can use the first slot in the execlist we can emit
relocation instructions relative to it immediately and avoid a separate
pass to adjust the relocations to point to the last execlist slot.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_drv.c | 1 +
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 5 ++++-
include/uapi/drm/i915_drm.h | 8 +++++++-
3 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c04bd1058562..4868586722e7 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -354,6 +354,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
case I915_PARAM_HAS_EXEC_FENCE:
case I915_PARAM_HAS_EXEC_FENCE_DMABUF:
case I915_PARAM_HAS_EXEC_CAPTURE:
+ case I915_PARAM_HAS_EXEC_BATCH_FIRST:
/* For the time being all of these are always true;
* if some supported hardware does not have one of these
* features this value needs to be provided from
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 8582a96b0e9b..dbb53281ddb1 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -555,7 +555,10 @@ ht_head(const struct i915_gem_context *ctx, u32 handle)
static int eb_batch_index(const struct i915_execbuffer *eb)
{
- return eb->args->buffer_count - 1;
+ if (eb->args->flags & I915_EXEC_BATCH_FIRST)
+ return 0;
+ else
+ return eb->args->buffer_count - 1;
}
static int eb_select_context(struct i915_execbuffer *eb)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 9eda849df680..8923af8e81c0 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -424,6 +424,11 @@ typedef struct drm_i915_irq_wait {
*/
#define I915_PARAM_HAS_EXEC_CAPTURE 46
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying the batch buffer
+ * as the first execobject as opposed to the last. See I915_EXEC_BATCH_FIRST.
+ */
+#define I915_PARAM_HAS_EXEC_BATCH_FIRST 47
+
typedef struct drm_i915_getparam {
__s32 param;
/*
@@ -922,7 +927,8 @@ struct drm_i915_gem_execbuffer2 {
*/
#define I915_EXEC_FENCE_ANY (1<<19)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ANY<<1))
+#define I915_EXEC_BATCH_FIRST (1<<19)
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1))
#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff)
#define i915_execbuffer2_set_context_id(eb2, context) \
--
2.11.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
