All of lore.kernel.org
 help / color / mirror / Atom feed
From: Damien Lespiau <damien.lespiau@intel.com>
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH i-g-t 21/26] mediafill/skl: Start the gen9 media_fill from the gen8 version
Date: Fri, 26 Sep 2014 15:03:19 +0100	[thread overview]
Message-ID: <1411740204-25709-21-git-send-email-damien.lespiau@intel.com> (raw)
In-Reply-To: <1411740204-25709-1-git-send-email-damien.lespiau@intel.com>

From: Zhao Yakui <yakui.zhao@intel.com>

Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
---
 lib/Makefile.sources  |   1 +
 lib/media_fill.c      |  16 +++
 lib/media_fill.h      |   7 +
 lib/media_fill_gen9.c | 378 ++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 402 insertions(+)
 create mode 100644 lib/media_fill.c
 create mode 100644 lib/media_fill_gen9.c

diff --git a/lib/Makefile.sources b/lib/Makefile.sources
index 82e306d..eee145f 100644
--- a/lib/Makefile.sources
+++ b/lib/Makefile.sources
@@ -26,6 +26,7 @@ libintel_tools_la_SOURCES = 	\
 	media_fill_gen7.c       \
 	media_fill_gen8.c       \
 	media_fill_gen8lp.c     \
+	media_fill_gen9.c       \
 	gen7_media.h            \
 	gen8_media.h            \
 	rendercopy_i915.c	\
diff --git a/lib/media_fill.c b/lib/media_fill.c
new file mode 100644
index 0000000..1d212b8
--- /dev/null
+++ b/lib/media_fill.c
@@ -0,0 +1,16 @@
+#include "i830_reg.h"
+#include "media_fill.h"
+
+media_fillfunc_t get_media_fillfunc(int devid)
+{
+	media_fillfunc_t fill = NULL;
+
+	if (IS_GEN8(devid))
+		fill = gen8_media_fillfunc;
+	else if (IS_GEN7(devid))
+		fill = gen7_media_fillfunc;
+	else if (IS_GEN9(devid))
+		fill = gen9_media_fillfunc;
+
+	return fill;
+}
diff --git a/lib/media_fill.h b/lib/media_fill.h
index ca35aeb..226489c 100644
--- a/lib/media_fill.h
+++ b/lib/media_fill.h
@@ -25,4 +25,11 @@ gen8lp_media_fillfunc(struct intel_batchbuffer *batch,
 		unsigned width, unsigned height,
 		uint8_t color);
 
+void
+gen9_media_fillfunc(struct intel_batchbuffer *batch,
+                struct igt_buf *dst,
+                unsigned x, unsigned y,
+                unsigned width, unsigned height,
+                uint8_t color);
+
 #endif /* RENDE_MEDIA_FILL_H */
diff --git a/lib/media_fill_gen9.c b/lib/media_fill_gen9.c
new file mode 100644
index 0000000..98e2403
--- /dev/null
+++ b/lib/media_fill_gen9.c
@@ -0,0 +1,378 @@
+#include <intel_bufmgr.h>
+#include <i915_drm.h>
+
+#include "media_fill.h"
+#include "gen8_media.h"
+#include "intel_reg.h"
+
+#include <assert.h>
+
+#define ALIGN(x, y) (((x) + (y)-1) & ~((y)-1))
+
+static const uint32_t media_kernel[][4] = {
+	{ 0x00400001, 0x20202288, 0x00000020, 0x00000000 },
+	{ 0x00600001, 0x20800208, 0x008d0000, 0x00000000 },
+	{ 0x00200001, 0x20800208, 0x00450040, 0x00000000 },
+	{ 0x00000001, 0x20880608, 0x00000000, 0x000f000f },
+	{ 0x00800001, 0x20a00208, 0x00000020, 0x00000000 },
+	{ 0x00800001, 0x20e00208, 0x00000020, 0x00000000 },
+	{ 0x00800001, 0x21200208, 0x00000020, 0x00000000 },
+	{ 0x00800001, 0x21600208, 0x00000020, 0x00000000 },
+	{ 0x0c800031, 0x24000a40, 0x0e000080, 0x120a8000 },
+	{ 0x00600001, 0x2e000208, 0x008d0000, 0x00000000 },
+	{ 0x07800031, 0x20000a40, 0x0e000e00, 0x82000010 },
+};
+
+static uint32_t
+batch_used(struct intel_batchbuffer *batch)
+{
+	return batch->ptr - batch->buffer;
+}
+
+static uint32_t
+batch_align(struct intel_batchbuffer *batch, uint32_t align)
+{
+	uint32_t offset = batch_used(batch);
+	offset = ALIGN(offset, align);
+	batch->ptr = batch->buffer + offset;
+	return offset;
+}
+
+static void *
+batch_alloc(struct intel_batchbuffer *batch, uint32_t size, uint32_t align)
+{
+	uint32_t offset = batch_align(batch, align);
+	batch->ptr += size;
+	return memset(batch->buffer + offset, 0, size);
+}
+
+static uint32_t
+batch_offset(struct intel_batchbuffer *batch, void *ptr)
+{
+	return (uint8_t *)ptr - batch->buffer;
+}
+
+static uint32_t
+batch_copy(struct intel_batchbuffer *batch, const void *ptr, uint32_t size, uint32_t align)
+{
+	return batch_offset(batch, memcpy(batch_alloc(batch, size, align), ptr, size));
+}
+
+static void
+gen8_render_flush(struct intel_batchbuffer *batch, uint32_t batch_end)
+{
+	int ret;
+
+	ret = drm_intel_bo_subdata(batch->bo, 0, 4096, batch->buffer);
+	if (ret == 0)
+		ret = drm_intel_bo_mrb_exec(batch->bo, batch_end,
+					NULL, 0, 0, 0);
+	assert(ret == 0);
+}
+
+static uint32_t
+gen8_fill_curbe_buffer_data(struct intel_batchbuffer *batch,
+			uint8_t color)
+{
+	uint8_t *curbe_buffer;
+	uint32_t offset;
+
+	curbe_buffer = batch_alloc(batch, sizeof(uint32_t) * 8, 64);
+	offset = batch_offset(batch, curbe_buffer);
+	*curbe_buffer = color;
+
+	return offset;
+}
+
+static uint32_t
+gen8_fill_surface_state(struct intel_batchbuffer *batch,
+			struct igt_buf *buf,
+			uint32_t format,
+			int is_dst)
+{
+	struct gen8_surface_state *ss;
+	uint32_t write_domain, read_domain, offset;
+	int ret;
+
+	if (is_dst) {
+		write_domain = read_domain = I915_GEM_DOMAIN_RENDER;
+	} else {
+		write_domain = 0;
+		read_domain = I915_GEM_DOMAIN_SAMPLER;
+	}
+
+	ss = batch_alloc(batch, sizeof(*ss), 64);
+	offset = batch_offset(batch, ss);
+
+	ss->ss0.surface_type = GEN8_SURFACE_2D;
+	ss->ss0.surface_format = format;
+	ss->ss0.render_cache_read_write = 1;
+	ss->ss0.vertical_alignment = 1; /* align 4 */
+	ss->ss0.horizontal_alignment = 1; /* align 4 */
+
+	if (buf->tiling == I915_TILING_X)
+		ss->ss0.tiled_mode = 2;
+	else if (buf->tiling == I915_TILING_Y)
+		ss->ss0.tiled_mode = 3;
+
+	ss->ss8.base_addr = buf->bo->offset;
+
+	ret = drm_intel_bo_emit_reloc(batch->bo,
+				batch_offset(batch, ss) + 8 * 4,
+				buf->bo, 0,
+				read_domain, write_domain);
+	assert(ret == 0);
+
+	ss->ss2.height = igt_buf_height(buf) - 1;
+	ss->ss2.width  = igt_buf_width(buf) - 1;
+	ss->ss3.pitch  = buf->stride - 1;
+
+	ss->ss7.shader_chanel_select_r = 4;
+	ss->ss7.shader_chanel_select_g = 5;
+	ss->ss7.shader_chanel_select_b = 6;
+	ss->ss7.shader_chanel_select_a = 7;
+
+	return offset;
+}
+
+static uint32_t
+gen8_fill_binding_table(struct intel_batchbuffer *batch,
+			struct igt_buf *dst)
+{
+	uint32_t *binding_table, offset;
+
+	binding_table = batch_alloc(batch, 32, 64);
+	offset = batch_offset(batch, binding_table);
+
+	binding_table[0] = gen8_fill_surface_state(batch, dst, GEN8_SURFACEFORMAT_R8_UNORM, 1);
+
+	return offset;
+}
+
+static uint32_t
+gen8_fill_media_kernel(struct intel_batchbuffer *batch,
+		const uint32_t kernel[][4],
+		size_t size)
+{
+	uint32_t offset;
+
+	offset = batch_copy(batch, kernel, size, 64);
+
+	return offset;
+}
+
+static uint32_t
+gen8_fill_interface_descriptor(struct intel_batchbuffer *batch, struct igt_buf *dst)
+{
+	struct gen8_interface_descriptor_data *idd;
+	uint32_t offset;
+	uint32_t binding_table_offset, kernel_offset;
+
+	binding_table_offset = gen8_fill_binding_table(batch, dst);
+	kernel_offset = gen8_fill_media_kernel(batch, media_kernel, sizeof(media_kernel));
+
+	idd = batch_alloc(batch, sizeof(*idd), 64);
+	offset = batch_offset(batch, idd);
+
+	idd->desc0.kernel_start_pointer = (kernel_offset >> 6);
+
+	idd->desc2.single_program_flow = 1;
+	idd->desc2.floating_point_mode = GEN8_FLOATING_POINT_IEEE_754;
+
+	idd->desc3.sampler_count = 0;      /* 0 samplers used */
+	idd->desc3.sampler_state_pointer = 0;
+
+	idd->desc4.binding_table_entry_count = 0;
+	idd->desc4.binding_table_pointer = (binding_table_offset >> 5);
+
+	idd->desc5.constant_urb_entry_read_offset = 0;
+	idd->desc5.constant_urb_entry_read_length = 1; /* grf 1 */
+
+	return offset;
+}
+
+static void
+gen8_emit_state_base_address(struct intel_batchbuffer *batch)
+{
+	OUT_BATCH(GEN8_STATE_BASE_ADDRESS | (16 - 2));
+
+	/* general */
+	OUT_BATCH(0 | BASE_ADDRESS_MODIFY);
+	OUT_BATCH(0);
+
+	/* stateless data port */
+	OUT_BATCH(0 | BASE_ADDRESS_MODIFY);
+
+	/* surface */
+	OUT_RELOC(batch->bo, I915_GEM_DOMAIN_SAMPLER, 0, BASE_ADDRESS_MODIFY);
+	OUT_BATCH(0);
+
+	/* dynamic */
+	OUT_RELOC(batch->bo, I915_GEM_DOMAIN_RENDER | I915_GEM_DOMAIN_INSTRUCTION,
+		0, BASE_ADDRESS_MODIFY);
+	OUT_BATCH(0);
+
+	/* indirect */
+	OUT_BATCH(0);
+	OUT_BATCH(0);
+
+	/* instruction */
+	OUT_RELOC(batch->bo, I915_GEM_DOMAIN_INSTRUCTION, 0, BASE_ADDRESS_MODIFY);
+	OUT_BATCH(0);
+
+	/* general state buffer size */
+	OUT_BATCH(0xfffff000 | 1);
+	/* dynamic state buffer size */
+	OUT_BATCH(1 << 12 | 1);
+	/* indirect object buffer size */
+	OUT_BATCH(0xfffff000 | 1);
+	/* intruction buffer size, must set modify enable bit, otherwise it may result in GPU hang */
+	OUT_BATCH(1 << 12 | 1);
+}
+
+static void
+gen8_emit_vfe_state(struct intel_batchbuffer *batch)
+{
+	OUT_BATCH(GEN8_MEDIA_VFE_STATE | (9 - 2));
+
+	/* scratch buffer */
+	OUT_BATCH(0);
+	OUT_BATCH(0);
+
+	/* number of threads & urb entries */
+	OUT_BATCH(1 << 16 |
+		2 << 8);
+
+	OUT_BATCH(0);
+
+	/* urb entry size & curbe size */
+	OUT_BATCH(2 << 16 |
+		2);
+
+	/* scoreboard */
+	OUT_BATCH(0);
+	OUT_BATCH(0);
+	OUT_BATCH(0);
+}
+
+static void
+gen8_emit_curbe_load(struct intel_batchbuffer *batch, uint32_t curbe_buffer)
+{
+	OUT_BATCH(GEN8_MEDIA_CURBE_LOAD | (4 - 2));
+	OUT_BATCH(0);
+	/* curbe total data length */
+	OUT_BATCH(64);
+	/* curbe data start address, is relative to the dynamics base address */
+	OUT_BATCH(curbe_buffer);
+}
+
+static void
+gen8_emit_interface_descriptor_load(struct intel_batchbuffer *batch, uint32_t interface_descriptor)
+{
+	OUT_BATCH(GEN8_MEDIA_INTERFACE_DESCRIPTOR_LOAD | (4 - 2));
+	OUT_BATCH(0);
+	/* interface descriptor data length */
+	OUT_BATCH(sizeof(struct gen8_interface_descriptor_data));
+	/* interface descriptor address, is relative to the dynamics base address */
+	OUT_BATCH(interface_descriptor);
+}
+
+static void
+gen8_emit_media_state_flush(struct intel_batchbuffer *batch)
+{
+	OUT_BATCH(GEN8_MEDIA_STATE_FLUSH | (2 - 2));
+	OUT_BATCH(0);
+}
+
+static void
+gen8_emit_media_objects(struct intel_batchbuffer *batch,
+			unsigned x, unsigned y,
+			unsigned width, unsigned height)
+{
+	int i, j;
+
+	for (i = 0; i < width / 16; i++) {
+		for (j = 0; j < height / 16; j++) {
+			OUT_BATCH(GEN8_MEDIA_OBJECT | (8 - 2));
+
+			/* interface descriptor offset */
+			OUT_BATCH(0);
+
+			/* without indirect data */
+			OUT_BATCH(0);
+			OUT_BATCH(0);
+
+			/* scoreboard */
+			OUT_BATCH(0);
+			OUT_BATCH(0);
+
+			/* inline data (xoffset, yoffset) */
+			OUT_BATCH(x + i * 16);
+			OUT_BATCH(y + j * 16);
+			gen8_emit_media_state_flush(batch);
+		}
+	}
+}
+
+/*
+ * This sets up the media pipeline,
+ *
+ * +---------------+ <---- 4096
+ * |       ^       |
+ * |       |       |
+ * |    various    |
+ * |      state    |
+ * |       |       |
+ * |_______|_______| <---- 2048 + ?
+ * |       ^       |
+ * |       |       |
+ * |   batch       |
+ * |    commands   |
+ * |       |       |
+ * |       |       |
+ * +---------------+ <---- 0 + ?
+ *
+ */
+
+#define BATCH_STATE_SPLIT 2048
+
+void
+gen9_media_fillfunc(struct intel_batchbuffer *batch,
+		struct igt_buf *dst,
+		unsigned x, unsigned y,
+		unsigned width, unsigned height,
+		uint8_t color)
+{
+	uint32_t curbe_buffer, interface_descriptor;
+	uint32_t batch_end;
+
+	intel_batchbuffer_flush(batch);
+
+	/* setup states */
+	batch->ptr = &batch->buffer[BATCH_STATE_SPLIT];
+
+	curbe_buffer = gen8_fill_curbe_buffer_data(batch, color);
+	interface_descriptor = gen8_fill_interface_descriptor(batch, dst);
+	assert(batch->ptr < &batch->buffer[4095]);
+
+	/* media pipeline */
+	batch->ptr = batch->buffer;
+	OUT_BATCH(GEN8_PIPELINE_SELECT | PIPELINE_SELECT_MEDIA);
+	gen8_emit_state_base_address(batch);
+
+	gen8_emit_vfe_state(batch);
+
+	gen8_emit_curbe_load(batch, curbe_buffer);
+
+	gen8_emit_interface_descriptor_load(batch, interface_descriptor);
+
+	gen8_emit_media_objects(batch, x, y, width, height);
+
+	OUT_BATCH(MI_BATCH_BUFFER_END);
+
+	batch_end = batch_align(batch, 8);
+	assert(batch_end < BATCH_STATE_SPLIT);
+
+	gen8_render_flush(batch, batch_end);
+	intel_batchbuffer_reset(batch);
+}
-- 
1.8.3.1

  parent reply	other threads:[~2014-09-26 14:05 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-09-26 14:02 [PATCH i-g-t 01/26] skl: Add SKL PCI ids Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 02/26] skl: Add gen9 to intel_gen() Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 03/26] skl: initialize instdone bits for gen9 Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 04/26] list-workarounds/skl: Add Skylake to the list of valid platorms Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 05/26] rendercopy/skl: Start the gen9 rendercopy from the gen8 version Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 06/26] rendercopy/skl: Set the 3DSTATE_VF state Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 07/26] rendercopy/skl: Update 3DSTATE_SBE Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 08/26] rendercopy/skl: Pass the context to rendercopy function on SKL Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 09/26] rendercopy/skl: update instruction length Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 10/26] rendercopy/skl: Set Instruction Buffer size Modify Enable to 1 Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 11/26] rendercopy/skl: Fix the STATE_BASE_ADDRESS instruction length Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 12/26] rendercopy/skl: Fix the 3DSTATE_DS " Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 13/26] rendercopy/skl: Emit 3DSTATE_WM_HZ_OP Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 14/26] rendercopy/skl: Follow the spec to add the Pipeline selection mask Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 15/26] rendercopy/skl: Set the URB VS start address to 4 Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 16/26] assembler/skl: Add gen 9 to the -g option Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 17/26] assembler/skl: Redefine the cache agent type for some fixed functions Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 18/26] assembler/skl: update read(...) Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 19/26] assembler/skl: Add more cache agent for write(...) Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 20/26] assembler/skl: update the extdesc field for SEND instruction Damien Lespiau
2014-09-26 14:03 ` Damien Lespiau [this message]
2014-09-26 14:03 ` [PATCH i-g-t 22/26] mediafill/skl: follow the spec to update STATE_BASE_ADDRESS command Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 23/26] mediafill/skl: Follow the spec to add pipeline_select mask Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 24/26] mediafill/skl: Follow spec to configure FORCE_MEDIA_AWAKE in PIPELINE_SELECTION Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 25/26] mediafill/skl: Follow spec to configure media sampler DOP clock gating " Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 26/26] lib/skl: Return the render copy and media fill functions Damien Lespiau
2014-09-30 11:24 ` [PATCH i-g-t 01/26] skl: Add SKL PCI ids Damien Lespiau

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1411740204-25709-21-git-send-email-damien.lespiau@intel.com \
    --to=damien.lespiau@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.