[igt-dev] [PATCH i-g-t 0/4] tests/i915: Enable XY_FAST_COPY_BLT for gen12+

[igt-dev] [PATCH i-g-t 0/4] tests/i915: Enable XY_FAST_COPY_BLT for gen12+

[Vikas Srivastava]

Test case uses legacy command XY_SRC_COPY_BLT_CMD which
is not supported on newer platforms. Modify test
to use XY_FAST_COPY_BLT.

Arjun Melkaveri (1):
  tests/i915/gem_linear_blits: Enable XY_FAST_COPY_BLT copy instruction

Vikas Srivastava (3):
  tests/i915/gem_caching: Enable XY_FAST_COPY_BLT for MTL
  lib/intel_batchbuffer: Enable XY_FAST_COPY_BLT support for
    api_intel_bb
  tests/i915/gem_userptr_blits: Enable XY_FAST_COPY_BLT command for
    gen12+

 lib/intel_batchbuffer.c        |  57 +++++++++++-------
 tests/i915/gem_caching.c       |  25 +++++---
 tests/i915/gem_linear_blits.c  |  68 ++++++++++++++--------
 tests/i915/gem_userptr_blits.c | 102 ++++++++++++++++++++-------------
 4 files changed, 162 insertions(+), 90 deletions(-)

-- 
2.25.1

[igt-dev] [PATCH i-g-t 1/4 v3] tests/i915/gem_linear_blits: Enable XY_FAST_COPY_BLT copy instruction

[Vikas Srivastava]

From: Arjun Melkaveri <arjun.melkaveri@intel.com>

Test case uses legacy command XY_SRC_COPY_BLT_CMD which is
not supported on newer platforms. Modify test to
use XY_FAST_COPY_BLT.

Signed-off-by: Arjun Melkaveri <arjun.melkaveri@intel.com>
Co-developed-by: Vikas Srivastava <vikas.srivastava@intel.com>
Signed-off-by: Vikas Srivastava <vikas.srivastava@intel.com>
Cc: Karolina Stolarek <karolina.stolarek@intel.com>
---
 tests/i915/gem_linear_blits.c | 68 +++++++++++++++++++++++------------
 1 file changed, 45 insertions(+), 23 deletions(-)

diff --git a/tests/i915/gem_linear_blits.c b/tests/i915/gem_linear_blits.c
index fac25095f5..17fbbd3710 100644
--- a/tests/i915/gem_linear_blits.c
+++ b/tests/i915/gem_linear_blits.c
@@ -48,6 +48,7 @@
 #include "i915/gem_create.h"
 #include "igt.h"
 #include "igt_types.h"
+#include "i915/i915_blt.h"
 
 IGT_TEST_DESCRIPTION("Test doing many blits with a working set larger than the"
 		     " aperture size.");
@@ -67,6 +68,7 @@ static void copy(int fd, uint64_t ahnd, uint32_t dst, uint32_t src,
 	struct drm_i915_gem_relocation_entry reloc[2];
 	struct drm_i915_gem_exec_object2 obj[3];
 	struct drm_i915_gem_execbuffer2 exec;
+	static uint32_t devid;
 	int i = 0;
 
 	memset(obj, 0, sizeof(obj));
@@ -83,29 +85,49 @@ static void copy(int fd, uint64_t ahnd, uint32_t dst, uint32_t src,
 	obj[2].offset = CANONICAL(obj[2].offset);
 	obj[2].flags = EXEC_OBJECT_SUPPORTS_48B_ADDRESS;
 
-	batch[i++] = XY_SRC_COPY_BLT_CMD |
-		  XY_SRC_COPY_BLT_WRITE_ALPHA |
-		  XY_SRC_COPY_BLT_WRITE_RGB;
-	if (intel_gen(intel_get_drm_devid(fd)) >= 8)
-		batch[i - 1] |= 8;
-	else
-		batch[i - 1] |= 6;
-
-	batch[i++] = (3 << 24) | /* 32 bits */
-		  (0xcc << 16) | /* copy ROP */
-		  WIDTH*4;
-	batch[i++] = 0; /* dst x1,y1 */
-	batch[i++] = (HEIGHT << 16) | WIDTH; /* dst x2,y2 */
-	batch[i++] = obj[0].offset;
-	if (intel_gen(intel_get_drm_devid(fd)) >= 8)
-		batch[i++] = obj[0].offset >> 32;
-	batch[i++] = 0; /* src x1,y1 */
-	batch[i++] = WIDTH*4;
-	batch[i++] = obj[1].offset;
-	if (intel_gen(intel_get_drm_devid(fd)) >= 8)
-		batch[i++] = obj[1].offset >> 32;
-	batch[i++] = MI_BATCH_BUFFER_END;
-	batch[i++] = MI_NOOP;
+	devid = intel_get_drm_devid(fd);
+
+
+	if (blt_has_xy_src_copy(fd)) {
+		batch[i++] = XY_SRC_COPY_BLT_CMD |
+			     XY_SRC_COPY_BLT_WRITE_ALPHA |
+			     XY_SRC_COPY_BLT_WRITE_RGB;
+		if (intel_gen(intel_get_drm_devid(fd)) >= 8)
+			batch[i - 1] |= 8;
+		else
+			batch[i - 1] |= 6;
+
+		batch[i++] = (3 << 24) | /* 32 bits */
+			  (0xcc << 16) | /* copy ROP */
+			  WIDTH * 4;
+		batch[i++] = 0; /* dst x1,y1 */
+		batch[i++] = (HEIGHT << 16) | WIDTH; /* dst x2,y2 */
+		batch[i++] = obj[0].offset;
+		if (intel_gen(devid) >= 8)
+			batch[i++] = obj[0].offset >> 32;
+		batch[i++] = 0; /* src x1,y1 */
+		batch[i++] = WIDTH * 4;
+		batch[i++] = obj[1].offset;
+		if (intel_gen(devid) >= 8)
+			batch[i++] = obj[1].offset >> 32;
+		batch[i++] = MI_BATCH_BUFFER_END;
+		batch[i++] = MI_NOOP;
+	} else if (blt_has_fast_copy(fd)) {
+		batch[i++] = XY_FAST_COPY_BLT;
+		batch[i++] = XY_FAST_COPY_COLOR_DEPTH_32 | WIDTH * 4;
+		batch[i++] = 0; /* dst x1,y1 */
+		batch[i++] = (HEIGHT << 16) | WIDTH; /* dst x2,y2 */
+		batch[i++] = obj[0].offset; /* dst address lower bits */
+		batch[i++] = obj[0].offset >> 32; /* dst address upper bits */
+		batch[i++] = 0; /* src x1,y1 */
+		batch[i++] = WIDTH * 4; /* src pitch */
+		batch[i++] = obj[1].offset; /* src address lower bits */
+		batch[i++] = obj[1].offset >> 32; /* src address upper bits */
+		batch[i++] = MI_BATCH_BUFFER_END;
+		batch[i++] = MI_NOOP;
+	} else {
+		igt_assert_f(0, "No supported blit command found\n");
+	}
 
 	gem_write(fd, obj[2].handle, 0, batch, i * sizeof(batch[0]));
 
-- 
2.25.1

[igt-dev] [PATCH i-g-t 2/4 v3] tests/i915/gem_caching: Enable XY_FAST_COPY_BLT for MTL

[Vikas Srivastava]

Test case uses legacy command XY_SRC_COPY_BLT_CMD which
is not supported on newer platforms. Modify test to
use XY_FAST_COPY_BLT.

Signed-off-by: Vikas Srivastava <vikas.srivastava@intel.com>
Cc: Karolina Stolarek <karolina.stolarek@intel.com>
---
 tests/i915/gem_caching.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/tests/i915/gem_caching.c b/tests/i915/gem_caching.c
index eb0170abca..3783dc2b33 100644
--- a/tests/i915/gem_caching.c
+++ b/tests/i915/gem_caching.c
@@ -39,6 +39,7 @@
 
 #include "i915/gem.h"
 #include "igt.h"
+#include "i915/i915_blt.h"
 
 IGT_TEST_DESCRIPTION("Test snoop consistency when touching partial"
 		     " cachelines.");
@@ -82,15 +83,23 @@ copy_bo(struct intel_bb *ibb, struct intel_buf *src, struct intel_buf *dst)
 	intel_bb_add_intel_buf(ibb, src, false);
 	intel_bb_add_intel_buf(ibb, dst, true);
 
-	intel_bb_out(ibb,
-		     XY_SRC_COPY_BLT_CMD |
-		     XY_SRC_COPY_BLT_WRITE_ALPHA |
-		     XY_SRC_COPY_BLT_WRITE_RGB |
-		     (6 + 2 * has_64b_reloc));
+	if (blt_has_xy_src_copy(ibb->i915)) {
+		intel_bb_out(ibb,
+			     XY_SRC_COPY_BLT_CMD |
+			     XY_SRC_COPY_BLT_WRITE_ALPHA |
+			     XY_SRC_COPY_BLT_WRITE_RGB |
+			     (6 + 2 * has_64b_reloc));
+
+		intel_bb_out(ibb, (3 << 24) | /* 32 bits */
+			     (0xcc << 16) | /* copy ROP */
+			     4096);
+	} else if (blt_has_fast_copy(ibb->i915)) {
+		intel_bb_out(ibb, XY_FAST_COPY_BLT);
+		intel_bb_out(ibb, XY_FAST_COPY_COLOR_DEPTH_32 | 4096);
+	} else {
+		igt_assert_f(0, "No supported blit command found\n");
+	}
 
-	intel_bb_out(ibb, (3 << 24) | /* 32 bits */
-		     (0xcc << 16) | /* copy ROP */
-		     4096);
 	intel_bb_out(ibb, 0 << 16 | 0);
 	intel_bb_out(ibb, (BO_SIZE/4096) << 16 | 1024);
 	intel_bb_emit_reloc_fenced(ibb, dst->handle,
-- 
2.25.1

[igt-dev] [PATCH i-g-t 3/4i v3] lib/intel_batchbuffer: Enable XY_FAST_COPY_BLT support for api_intel_bb

[Vikas Srivastava]

Test case uses legacy command XY_SRC_COPY_BLT_CMD which is
not supported on newer platforms. Modify test to use
XY_FAST_COPY_BLT.

Signed-off-by: Vikas Srivastava <vikas.srivastava@intel.com>
Cc: Karolina Stolarek <karolina.stolarek@intel.com>
---
 lib/intel_batchbuffer.c | 57 ++++++++++++++++++++++++++---------------
 1 file changed, 37 insertions(+), 20 deletions(-)

diff --git a/lib/intel_batchbuffer.c b/lib/intel_batchbuffer.c
index 40e444ad9b..a4eb4c2bbc 100644
--- a/lib/intel_batchbuffer.c
+++ b/lib/intel_batchbuffer.c
@@ -2409,11 +2409,16 @@ uint32_t intel_bb_copy_data(struct intel_bb *ibb,
  */
 void intel_bb_blit_start(struct intel_bb *ibb, uint32_t flags)
 {
-	intel_bb_out(ibb, XY_SRC_COPY_BLT_CMD |
-		     XY_SRC_COPY_BLT_WRITE_ALPHA |
-		     XY_SRC_COPY_BLT_WRITE_RGB |
-		     flags |
-		     (6 + 2 * (ibb->gen >= 8)));
+	if (blt_has_xy_src_copy(ibb->i915))
+		intel_bb_out(ibb, XY_SRC_COPY_BLT_CMD |
+			     XY_SRC_COPY_BLT_WRITE_ALPHA |
+			     XY_SRC_COPY_BLT_WRITE_RGB |
+			     flags |
+			     (6 + 2 * (ibb->gen >= 8)));
+	else if (blt_has_fast_copy(ibb->i915))
+		intel_bb_out(ibb, XY_FAST_COPY_BLT | flags);
+	else
+		igt_assert_f(0, "No supported blit command found\n");
 }
 
 /*
@@ -2451,12 +2456,20 @@ void intel_bb_emit_blt_copy(struct intel_bb *ibb,
 
 	if (gen >= 4 && src->tiling != I915_TILING_NONE) {
 		src_pitch /= 4;
-		cmd_bits |= XY_SRC_COPY_BLT_SRC_TILED;
+		if (blt_has_xy_src_copy(ibb->i915))
+			cmd_bits |= XY_SRC_COPY_BLT_SRC_TILED;
+		else if (blt_has_fast_copy(ibb->i915))
+			cmd_bits |= fast_copy_dword0(src->tiling, dst->tiling);
+		else
+			igt_assert_f(0, "No supported blit command found\n");
 	}
 
 	if (gen >= 4 && dst->tiling != I915_TILING_NONE) {
 		dst_pitch /= 4;
-		cmd_bits |= XY_SRC_COPY_BLT_DST_TILED;
+		if (blt_has_xy_src_copy(ibb->i915))
+			cmd_bits |= XY_SRC_COPY_BLT_DST_TILED;
+		else
+			cmd_bits |= fast_copy_dword0(src->tiling, dst->tiling);
 	}
 
 	CHECK_RANGE(src_x1); CHECK_RANGE(src_y1);
@@ -2467,19 +2480,23 @@ void intel_bb_emit_blt_copy(struct intel_bb *ibb,
 	CHECK_RANGE(src_pitch); CHECK_RANGE(dst_pitch);
 
 	br13_bits = 0;
-	switch (bpp) {
-	case 8:
-		break;
-	case 16:		/* supporting only RGB565, not ARGB1555 */
-		br13_bits |= 1 << 24;
-		break;
-	case 32:
-		br13_bits |= 3 << 24;
-		cmd_bits |= (XY_SRC_COPY_BLT_WRITE_ALPHA |
-			     XY_SRC_COPY_BLT_WRITE_RGB);
-		break;
-	default:
-		igt_fail(IGT_EXIT_FAILURE);
+	if (blt_has_xy_src_copy(ibb->i915)) {
+		switch (bpp) {
+		case 8:
+			break;
+		case 16:		/* supporting only RGB565, not ARGB1555 */
+			br13_bits |= 1 << 24;
+			break;
+		case 32:
+			br13_bits |= 3 << 24;
+			cmd_bits |= (XY_SRC_COPY_BLT_WRITE_ALPHA |
+				     XY_SRC_COPY_BLT_WRITE_RGB);
+			break;
+		default:
+			igt_fail(IGT_EXIT_FAILURE);
+		}
+	} else {
+		br13_bits = fast_copy_dword1(ibb->i915, src->tiling, dst->tiling, bpp);
 	}
 
 	if ((src->tiling | dst->tiling) >= I915_TILING_Y) {
-- 
2.25.1

[igt-dev] [PATCH i-g-t 4/4 v3] tests/i915/gem_userptr_blits: Enable XY_FAST_COPY_BLT command for gen12+

[Vikas Srivastava]

Test case uses legacy command XY_SRC_COPY_BLT_CMD which is
not supported on newer platforms. Modify test
to use XY_FAST_COPY_BLT.

Signed-off-by: Vikas Srivastava <vikas.srivastava@intel.com>
Cc: Karolina Stolarek <karolina.stolarek@intel.com>
---
 tests/i915/gem_userptr_blits.c | 102 ++++++++++++++++++++-------------
 1 file changed, 63 insertions(+), 39 deletions(-)

diff --git a/tests/i915/gem_userptr_blits.c b/tests/i915/gem_userptr_blits.c
index 07a453229a..3a1a81e456 100644
--- a/tests/i915/gem_userptr_blits.c
+++ b/tests/i915/gem_userptr_blits.c
@@ -66,6 +66,7 @@
 #include "sw_sync.h"
 
 #include "eviction_common.c"
+#include "i915/i915_blt.h"
 
 #ifndef PAGE_SIZE
 #define PAGE_SIZE 4096
@@ -99,6 +100,7 @@ static int copy(int fd, uint32_t dst, uint32_t src)
 	struct drm_i915_gem_relocation_entry reloc[2];
 	struct drm_i915_gem_exec_object2 obj[3];
 	struct drm_i915_gem_execbuffer2 exec;
+	static uint32_t devid;
 	uint32_t handle;
 	int ret, i=0;
 	uint64_t dst_offset, src_offset, bb_offset;
@@ -108,29 +110,49 @@ static int copy(int fd, uint32_t dst, uint32_t src)
 	dst_offset = bb_offset + 4096;
 	src_offset = dst_offset + WIDTH * HEIGHT * sizeof(uint32_t) * (src != dst);
 
-	batch[i++] = XY_SRC_COPY_BLT_CMD |
-		  XY_SRC_COPY_BLT_WRITE_ALPHA |
-		  XY_SRC_COPY_BLT_WRITE_RGB;
-	if (intel_gen(intel_get_drm_devid(fd)) >= 8)
-		batch[i - 1] |= 8;
-	else
-		batch[i - 1] |= 6;
-
-	batch[i++] = (3 << 24) | /* 32 bits */
-		  (0xcc << 16) | /* copy ROP */
-		  WIDTH*4;
-	batch[i++] = 0; /* dst x1,y1 */
-	batch[i++] = (HEIGHT << 16) | WIDTH; /* dst x2,y2 */
-	batch[i++] = dst_offset; /* dst reloc */
-	if (intel_gen(intel_get_drm_devid(fd)) >= 8)
-		batch[i++] = dst_offset >> 32;
-	batch[i++] = 0; /* src x1,y1 */
-	batch[i++] = WIDTH*4;
-	batch[i++] = src_offset; /* src reloc */
-	if (intel_gen(intel_get_drm_devid(fd)) >= 8)
-		batch[i++] = src_offset >> 32;
-	batch[i++] = MI_BATCH_BUFFER_END;
-	batch[i++] = MI_NOOP;
+	devid = intel_get_drm_devid(fd);
+
+	if (blt_has_xy_src_copy(fd)) {
+		batch[i++] = XY_SRC_COPY_BLT_CMD |
+			     XY_SRC_COPY_BLT_WRITE_ALPHA |
+			     XY_SRC_COPY_BLT_WRITE_RGB;
+
+		if (intel_gen(devid) >= 8)
+			batch[i - 1] |= 8;
+		else
+			batch[i - 1] |= 6;
+
+		batch[i++] = (3 << 24) | /* 32 bits */
+			  (0xcc << 16) | /* copy ROP */
+			  WIDTH * 4;
+		batch[i++] = 0; /* dst x1,y1 */
+		batch[i++] = (HEIGHT << 16) | WIDTH; /* dst x2,y2 */
+		batch[i++] = lower_32_bits(dst_offset); /* dst reloc*/
+		if (intel_gen(devid) >= 8)
+			batch[i++] = upper_32_bits(CANONICAL(dst_offset));
+		batch[i++] = 0; /* src x1,y1 */
+		batch[i++] = WIDTH * 4;
+		batch[i++] = lower_32_bits(src_offset); /* src reloc */
+		if (intel_gen(devid) >= 8)
+			batch[i++] = upper_32_bits(CANONICAL(src_offset));
+		batch[i++] = MI_BATCH_BUFFER_END;
+		batch[i++] = MI_NOOP;
+	} else if (blt_has_fast_copy(fd)) {
+		batch[i++] = XY_FAST_COPY_BLT;
+		batch[i++] = XY_FAST_COPY_COLOR_DEPTH_32 | WIDTH * 4;
+		batch[i++] = 0;/* dst x1,y1 */
+		batch[i++] = (HEIGHT << 16) | WIDTH;/* dst x2,y2 */
+		batch[i++] = lower_32_bits(dst_offset); /* dst address */
+		batch[i++] = upper_32_bits(CANONICAL(dst_offset));
+		batch[i++] = 0;/* src x1,y1 */
+		batch[i++] = WIDTH * 4;/* src pitch */
+		batch[i++] = lower_32_bits(src_offset); /* src address */
+		batch[i++] = upper_32_bits(CANONICAL(src_offset));
+		batch[i++] = MI_BATCH_BUFFER_END;
+		batch[i++] = MI_NOOP;
+	} else {
+		igt_assert_f(0, "No supported blit command found\n");
+	}
 
 	handle = gem_create(fd, 4096);
 	gem_write(fd, handle, 0, batch, sizeof(batch));
@@ -254,20 +276,7 @@ blit(int fd, uint32_t dst, uint32_t src, uint32_t *all_bo, int n_bo)
 	reloc[1].read_domains = I915_GEM_DOMAIN_RENDER;
 	reloc[1].write_domain = 0;
 
-	if (intel_graphics_ver(devid) >= IP_VER(12, 60)) {
-		batch[i++] = XY_FAST_COPY_BLT;
-		batch[i++] = XY_FAST_COPY_COLOR_DEPTH_32 | WIDTH*4;
-		batch[i++] = 0; /* dst x1,y1 */
-		batch[i++] = (HEIGHT << 16) | WIDTH; /* dst x2,y2 */
-		batch[i++] = lower_32_bits(dst_offset); /* dst address */
-		batch[i++] = upper_32_bits(CANONICAL(dst_offset));
-		batch[i++] = 0; /* src x1,y1 */
-		batch[i++] = WIDTH*4; /* src pitch */
-		batch[i++] = lower_32_bits(src_offset); /* src address */
-		batch[i++] = upper_32_bits(CANONICAL(src_offset));
-		batch[i++] = MI_BATCH_BUFFER_END;
-		batch[i++] = MI_NOOP;
-	} else {
+	if (blt_has_xy_src_copy(fd)) {
 		batch[i++] = XY_SRC_COPY_BLT_CMD |
 			     XY_SRC_COPY_BLT_WRITE_ALPHA |
 			     XY_SRC_COPY_BLT_WRITE_RGB;
@@ -277,19 +286,34 @@ blit(int fd, uint32_t dst, uint32_t src, uint32_t *all_bo, int n_bo)
 			batch[i - 1] |= 6;
 		batch[i++] = (3 << 24) | /* 32 bits */
 			     (0xcc << 16) | /* copy ROP */
-			     WIDTH*4;
+			     WIDTH * 4;
 		batch[i++] = 0; /* dst x1,y1 */
 		batch[i++] = (HEIGHT << 16) | WIDTH; /* dst x2,y2 */
 		batch[i++] = lower_32_bits(dst_offset);
 		if (intel_gen(devid) >= 8)
 			batch[i++] = upper_32_bits(CANONICAL(dst_offset));
 		batch[i++] = 0; /* src x1,y1 */
-		batch[i++] = WIDTH*4;
+		batch[i++] = WIDTH * 4;
 		batch[i++] = lower_32_bits(src_offset);
 		if (intel_gen(devid) >= 8)
 			batch[i++] = upper_32_bits(CANONICAL(src_offset));
 		batch[i++] = MI_BATCH_BUFFER_END;
 		batch[i++] = MI_NOOP;
+	} else if (blt_has_fast_copy(fd)) {
+		batch[i++] = XY_FAST_COPY_BLT;
+		batch[i++] = XY_FAST_COPY_COLOR_DEPTH_32 | WIDTH * 4;
+		batch[i++] = 0; /* dst x1,y1 */
+		batch[i++] = (HEIGHT << 16) | WIDTH; /* dst x2,y2 */
+		batch[i++] = lower_32_bits(dst_offset); /* dst address */
+		batch[i++] = upper_32_bits(CANONICAL(dst_offset));
+		batch[i++] = 0; /* src x1,y1 */
+		batch[i++] = WIDTH * 4; /* src pitch */
+		batch[i++] = lower_32_bits(src_offset); /* src address */
+		batch[i++] = upper_32_bits(CANONICAL(src_offset));
+		batch[i++] = MI_BATCH_BUFFER_END;
+		batch[i++] = MI_NOOP;
+	} else {
+		igt_assert_f(0, "No supported blit command found\n");
 	}
 
 	gem_write(fd, handle, 0, batch, sizeof(batch));
-- 
2.25.1