Commit a0ed9c95 authored by Ramalingam C's avatar Ramalingam C

drm/i915/gt: Use XY_FAST_COLOR_BLT to clear obj on graphics ver 12+

Use faster XY_FAST_COLOR_BLT cmd on graphics version of 12 and more,
for clearing (Zero out) the pages of the newly allocated object.

XY_FAST_COLOR_BLT is faster than the older XY_COLOR_BLT.

v2:
  Typo fix at title [Thomas]
v3:
  XY_FAST_COLOR_BLT is used only for FLAT_CCS capable gen12+
Signed-off-by: default avatarRamalingam C <ramalingam.c@intel.com>
Signed-off-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: default avatarThomas Hellstrom <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220405150840.29351-3-ramalingam.c@intel.com
parent fd5803e5
...@@ -206,6 +206,11 @@ ...@@ -206,6 +206,11 @@
#define COLOR_BLT_CMD (2 << 29 | 0x40 << 22 | (5 - 2)) #define COLOR_BLT_CMD (2 << 29 | 0x40 << 22 | (5 - 2))
#define XY_COLOR_BLT_CMD (2 << 29 | 0x50 << 22) #define XY_COLOR_BLT_CMD (2 << 29 | 0x50 << 22)
#define XY_FAST_COLOR_BLT_CMD (2 << 29 | 0x44 << 22)
#define XY_FAST_COLOR_BLT_DEPTH_32 (2 << 19)
#define XY_FAST_COLOR_BLT_DW 16
#define XY_FAST_COLOR_BLT_MOCS_MASK GENMASK(27, 21)
#define XY_FAST_COLOR_BLT_MEM_TYPE_SHIFT 31
#define SRC_COPY_BLT_CMD (2 << 29 | 0x43 << 22) #define SRC_COPY_BLT_CMD (2 << 29 | 0x43 << 22)
#define GEN9_XY_FAST_COPY_BLT_CMD (2 << 29 | 0x42 << 22) #define GEN9_XY_FAST_COPY_BLT_CMD (2 << 29 | 0x42 << 22)
#define XY_SRC_COPY_BLT_CMD (2 << 29 | 0x53 << 22) #define XY_SRC_COPY_BLT_CMD (2 << 29 | 0x53 << 22)
......
...@@ -613,18 +613,51 @@ intel_context_migrate_copy(struct intel_context *ce, ...@@ -613,18 +613,51 @@ intel_context_migrate_copy(struct intel_context *ce,
return err; return err;
} }
static int emit_clear(struct i915_request *rq, u32 offset, int size, u32 value) static int emit_clear(struct i915_request *rq, u32 offset, int size,
u32 value, bool is_lmem)
{ {
const int ver = GRAPHICS_VER(rq->engine->i915); struct drm_i915_private *i915 = rq->engine->i915;
int mocs = rq->engine->gt->mocs.uc_index << 1;
const int ver = GRAPHICS_VER(i915);
int ring_sz;
u32 *cs; u32 *cs;
GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX); GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
cs = intel_ring_begin(rq, ver >= 8 ? 8 : 6); if (HAS_FLAT_CCS(i915) && ver >= 12)
ring_sz = XY_FAST_COLOR_BLT_DW;
else if (ver >= 8)
ring_sz = 8;
else
ring_sz = 6;
cs = intel_ring_begin(rq, ring_sz);
if (IS_ERR(cs)) if (IS_ERR(cs))
return PTR_ERR(cs); return PTR_ERR(cs);
if (ver >= 8) { if (HAS_FLAT_CCS(i915) && ver >= 12) {
*cs++ = XY_FAST_COLOR_BLT_CMD | XY_FAST_COLOR_BLT_DEPTH_32 |
(XY_FAST_COLOR_BLT_DW - 2);
*cs++ = FIELD_PREP(XY_FAST_COLOR_BLT_MOCS_MASK, mocs) |
(PAGE_SIZE - 1);
*cs++ = 0;
*cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
*cs++ = offset;
*cs++ = rq->engine->instance;
*cs++ = !is_lmem << XY_FAST_COLOR_BLT_MEM_TYPE_SHIFT;
/* BG7 */
*cs++ = value;
*cs++ = 0;
*cs++ = 0;
*cs++ = 0;
/* BG11 */
*cs++ = 0;
*cs++ = 0;
/* BG13 */
*cs++ = 0;
*cs++ = 0;
*cs++ = 0;
} else if (ver >= 8) {
*cs++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (7 - 2); *cs++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (7 - 2);
*cs++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE; *cs++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE;
*cs++ = 0; *cs++ = 0;
...@@ -707,7 +740,7 @@ intel_context_migrate_clear(struct intel_context *ce, ...@@ -707,7 +740,7 @@ intel_context_migrate_clear(struct intel_context *ce,
if (err) if (err)
goto out_rq; goto out_rq;
err = emit_clear(rq, offset, len, value); err = emit_clear(rq, offset, len, value, is_lmem);
/* Arbitration is re-enabled between requests. */ /* Arbitration is re-enabled between requests. */
out_rq: out_rq:
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment