[Mesa-dev] [PATCH] [RFC] i965: Rewrite the HiZ op (v2)
Chad Versace
chad.versace at linux.intel.com
Sat Feb 4 10:10:33 PST 2012
==== RFC notes ====
This patch needs to land in 8.0, so please share your comments. You can
find this on my hiz-kill-meta-op-v12 branch.
The patch is complete for gen6, and everything I test seems to work well.
It introduces no Piglit delta; it fixes the remaining oglc failures in bug
43327; it fixes bug 44927. Nexuiz and Citybench like it.
You may notice that /*TODO: gen7*/ is sprinkled about. And there's a few
/*TODO: comment me*/'s too. I'm still working on that. But I wanted to
get the patch out now, early, so that you can comment.
v2: Incorporate Ken's comments. This largely meant removing the shaders
and removing some unneeded packets.
What follows is the real commit message.
==== Summary ====
This HiZ op was implemented as a meta-op. This patch reimplements it by
constructing and emitting a special batch. This fixes several known bugs,
and likely a lot of undiscovered ones too.
==== Why the HiZ meta-op needed to die ====
The HiZ op was implemented as a meta-op, which caused lots of trouble. All
other meta-ops occur as a result of some GL call (for example, glClear and
glGenerateMipmap), but the HiZ meta-op was special. It was called in
places that Mesa (in particular, the vbo and swrast modules) did not
expect---and were not prepared for---state changes to occur (for example:
glDraw; glCallList; within glBegin/End blocks; and within
swrast_prepare_render as a result of intel_miptree_map).
In an attempt to work around these unexpected state changes, I added two
hooks in i965:
- A hook for glDraw, located in brw_predraw_resolve_buffers (which is
called in the glDraw path). This hook detected if a predraw resolve
meta-op had occurred, and would hackishly repropagate some GL state
if necessary. This ensured that the meta-op state changes would not
intefere with the vbo module's subsequent execution of glDraw.
- A hook for glBegin, implemented by brwPrepareExecBegin. This hook
resolved all buffers before entering
a glBegin/End block, thus preventing an infinitely recurring call to
vbo_exec_FlushVertices. The vbo module called vbo_exec_FlushVertices to
flush its vertex queue in response to GL state changes.
Unfortunately, these hooks were not sufficient. The meta-op state changes
still interacted badly with glPopAttrib (as discovered in bug 44927) and
with swrast rendering (as discovered by debugging gen6's swrast fallback
for glBitmap). I expect there are more undiscovered bugs. Rather than play
whack-a-mole in a minefield, the sane approach is to replace the HiZ
meta-op with something safer.
==== How it was killed ====
This patch consists of several logical components:
1. Rewrite the HiZ op by replacing gen6_resolve_slice with
gen6_hiz_exec. The new function does not call a meta-op, but instead
manually constructs and emits a batch to "draw" the HiZ op's
rectangle primitive. The new function alters no GL state.
2. Add fields to brw_context::hiz for the new HiZ op.
3. Rewrite gen6_hiz_init, and invoke it in the eglMakeCurrent codepath.
4. Kill all dead HiZ code:
- the function gen6_resolve_slice
- the dirty flag BRW_NEW_HIZ
- the dead fields in brw_context::hiz
- the state packet manipulation triggered by the now removed
brw_context::hiz::op
- the meta-op workaround in brw_predraw_resolve_buffers (discussed above)
- the meta-op workaround brwPrepareExecBegin (discussed above)
TODO: write gen7 variant for gen6_hiz_exec
TODO: test egypt
Note: This is a candidate for the 8.0 branch.
CC: Eric Anholt <eric at anholt.net>
CC: Kenneth Graunke <kenneth at whitecape.org>
CC: Paul Berry <stereotype441 at gmail.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=43327
Reported-by: xunx.fang at intel.com
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=44927
Reported-by: chao.a.chen at intel.com
Signed-off-by: Chad Versace <chad.versace at linux.intel.com>
---
src/mesa/drivers/dri/i965/brw_context.c | 55 --
src/mesa/drivers/dri/i965/brw_context.h | 40 +-
src/mesa/drivers/dri/i965/brw_draw.c | 47 +--
src/mesa/drivers/dri/i965/brw_state_upload.c | 1 -
src/mesa/drivers/dri/i965/brw_vtbl.c | 2 +
src/mesa/drivers/dri/i965/gen6_clip_state.c | 20 +-
src/mesa/drivers/dri/i965/gen6_depthstencil.c | 9 +-
src/mesa/drivers/dri/i965/gen6_hiz.c | 883 ++++++++++++++++--------
src/mesa/drivers/dri/i965/gen6_sf_state.c | 16 +-
src/mesa/drivers/dri/i965/gen6_vs_state.c | 13 +
src/mesa/drivers/dri/i965/gen6_wm_state.c | 20 +-
src/mesa/drivers/dri/i965/gen7_clip_state.c | 20 +-
src/mesa/drivers/dri/i965/gen7_sf_state.c | 19 +-
src/mesa/drivers/dri/i965/gen7_wm_state.c | 18 -
src/mesa/drivers/dri/intel/intel_batchbuffer.c | 27 +
src/mesa/drivers/dri/intel/intel_batchbuffer.h | 1 +
16 files changed, 676 insertions(+), 515 deletions(-)
create mode 100644 src/mesa/drivers/dri/i965/junk
diff --git a/src/mesa/drivers/dri/i965/brw_context.c b/src/mesa/drivers/dri/i965/brw_context.c
index 1ab6310..65de260 100644
--- a/src/mesa/drivers/dri/i965/brw_context.c
+++ b/src/mesa/drivers/dri/i965/brw_context.c
@@ -41,8 +41,6 @@
#include "brw_draw.h"
#include "brw_state.h"
-#include "gen6_hiz.h"
-
#include "intel_fbo.h"
#include "intel_mipmap_tree.h"
#include "intel_regions.h"
@@ -57,58 +55,6 @@
* Mesa's Driver Functions
***************************************/
-/**
- * \brief Prepare for entry into glBegin/glEnd block.
- *
- * Resolve buffers before entering a glBegin/glEnd block. This is
- * necessary to prevent recursive calls to FLUSH_VERTICES.
- *
- * This resolves the depth buffer of each enabled depth texture and the HiZ
- * buffer of the attached depth renderbuffer.
- *
- * Details
- * -------
- * When vertices are queued during a glBegin/glEnd block, those vertices must
- * be drawn before any rendering state changes. To ensure this, Mesa calls
- * FLUSH_VERTICES as a prehook to such state changes. Therefore,
- * FLUSH_VERTICES itself cannot change rendering state without falling into a
- * recursive trap.
- *
- * This precludes meta-ops, namely buffer resolves, from occurring while any
- * vertices are queued. To prevent that situation, we resolve some buffers on
- * entering a glBegin/glEnd
- *
- * \see brwCleanupExecEnd()
- */
-static void brwPrepareExecBegin(struct gl_context *ctx)
-{
- struct brw_context *brw = brw_context(ctx);
- struct intel_context *intel = &brw->intel;
- struct intel_renderbuffer *draw_irb;
- struct intel_texture_object *tex_obj;
-
- if (!intel->has_hiz) {
- /* The context uses no feature that requires buffer resolves. */
- return;
- }
-
- /* Resolve each enabled texture. */
- for (int i = 0; i < ctx->Const.MaxTextureImageUnits; i++) {
- if (!ctx->Texture.Unit[i]._ReallyEnabled)
- continue;
- tex_obj = intel_texture_object(ctx->Texture.Unit[i]._Current);
- if (!tex_obj || !tex_obj->mt)
- continue;
- intel_miptree_all_slices_resolve_depth(intel, tex_obj->mt);
- }
-
- /* Resolve the attached depth buffer. */
- draw_irb = intel_get_renderbuffer(ctx->DrawBuffer, BUFFER_DEPTH);
- if (draw_irb) {
- intel_renderbuffer_resolve_hiz(intel, draw_irb);
- }
-}
-
static void brwInitDriverFunctions(struct intel_screen *screen,
struct dd_function_table *functions)
{
@@ -117,7 +63,6 @@ static void brwInitDriverFunctions(struct intel_screen *screen,
brwInitFragProgFuncs( functions );
brw_init_queryobj_functions(functions);
- functions->PrepareExecBegin = brwPrepareExecBegin;
functions->BeginTransformFeedback = brw_begin_transform_feedback;
if (screen->gen >= 7)
diff --git a/src/mesa/drivers/dri/i965/brw_context.h b/src/mesa/drivers/dri/i965/brw_context.h
index c027bef..72e5059 100644
--- a/src/mesa/drivers/dri/i965/brw_context.h
+++ b/src/mesa/drivers/dri/i965/brw_context.h
@@ -119,6 +119,10 @@
#define BRW_MAX_CURBE (32*16)
struct brw_context;
+struct brw_instruction;
+struct brw_vs_prog_key;
+struct brw_wm_prog_key;
+struct brw_wm_prog_data;
enum brw_state_id {
BRW_STATE_URB_FENCE,
@@ -144,7 +148,6 @@ enum brw_state_id {
BRW_STATE_VS_CONSTBUF,
BRW_STATE_PROGRAM_CACHE,
BRW_STATE_STATE_BASE_ADDRESS,
- BRW_STATE_HIZ,
BRW_STATE_SOL_INDICES,
};
@@ -174,7 +177,6 @@ enum brw_state_id {
#define BRW_NEW_VS_CONSTBUF (1 << BRW_STATE_VS_CONSTBUF)
#define BRW_NEW_PROGRAM_CACHE (1 << BRW_STATE_PROGRAM_CACHE)
#define BRW_NEW_STATE_BASE_ADDRESS (1 << BRW_STATE_STATE_BASE_ADDRESS)
-#define BRW_NEW_HIZ (1 << BRW_STATE_HIZ)
#define BRW_NEW_SOL_INDICES (1 << BRW_STATE_SOL_INDICES)
struct brw_state_flags {
@@ -950,38 +952,18 @@ struct brw_context
int state_batch_count;
/**
- * \brief State needed to execute HiZ meta-ops
+ * \brief State needed to execute HiZ ops.
*
- * All fields except \c op are initialized by gen6_hiz_init().
+ * \see gen6_hiz_init()
+ * \see gen6_hiz_exec()
*/
struct brw_hiz_state {
- /**
- * \brief Indicates which HiZ operation is in progress.
+ /** \brief VBO for rectangle primitive.
*
- * See the following sections of the Sandy Bridge PRM, Volume 1, Part2:
- * - 7.5.3.1 Depth Buffer Clear
- * - 7.5.3.2 Depth Buffer Resolve
- * - 7.5.3.3 Hierarchical Depth Buffer Resolve
+ * Rather than using glGenBuffers(), we allocate the VBO directly
+ * through drm.
*/
- enum brw_hiz_op {
- BRW_HIZ_OP_NONE = 0,
- BRW_HIZ_OP_DEPTH_CLEAR,
- BRW_HIZ_OP_DEPTH_RESOLVE,
- BRW_HIZ_OP_HIZ_RESOLVE,
- } op;
-
- /** \brief Shader state */
- struct {
- GLuint program;
- GLuint position_vbo;
- GLint position_location;
- } shader;
-
- /** \brief VAO for the rectangle primitive's vertices. */
- GLuint vao;
-
- GLuint fbo;
- struct gl_renderbuffer *depth_rb;
+ drm_intel_bo *vertex_bo;
} hiz;
struct brw_sol_state {
diff --git a/src/mesa/drivers/dri/i965/brw_draw.c b/src/mesa/drivers/dri/i965/brw_draw.c
index f50fffd..e919f3e 100644
--- a/src/mesa/drivers/dri/i965/brw_draw.c
+++ b/src/mesa/drivers/dri/i965/brw_draw.c
@@ -126,12 +126,7 @@ static void gen6_set_prim(struct brw_context *brw,
DBG("PRIM: %s\n", _mesa_lookup_enum_by_nr(prim->mode));
- if (brw->hiz.op) {
- assert(prim->mode == GL_TRIANGLES);
- hw_prim = _3DPRIM_RECTLIST;
- } else {
- hw_prim = prim_to_hw_prim[prim->mode];
- }
+ hw_prim = prim_to_hw_prim[prim->mode];
if (hw_prim != brw->primitive) {
brw->primitive = hw_prim;
@@ -307,17 +302,11 @@ brw_predraw_resolve_buffers(struct brw_context *brw)
struct intel_context *intel = &brw->intel;
struct intel_renderbuffer *depth_irb;
struct intel_texture_object *tex_obj;
- bool did_resolve = false;
-
- /* Avoid recursive HiZ op. */
- if (brw->hiz.op) {
- return;
- }
/* Resolve the depth buffer's HiZ buffer. */
depth_irb = intel_get_renderbuffer(ctx->DrawBuffer, BUFFER_DEPTH);
if (depth_irb && depth_irb->mt) {
- did_resolve |= intel_renderbuffer_resolve_hiz(intel, depth_irb);
+ intel_renderbuffer_resolve_hiz(intel, depth_irb);
}
/* Resolve depth buffer of each enabled depth texture. */
@@ -327,33 +316,7 @@ brw_predraw_resolve_buffers(struct brw_context *brw)
tex_obj = intel_texture_object(ctx->Texture.Unit[i]._Current);
if (!tex_obj || !tex_obj->mt)
continue;
- did_resolve |= intel_miptree_all_slices_resolve_depth(intel, tex_obj->mt);
- }
-
- if (did_resolve) {
- /* Call vbo_bind_array() to synchronize the vbo module's vertex
- * attributes to the gl_context's.
- *
- * Details
- * -------
- * The vbo module tracks vertex attributes separately from the
- * gl_context. Specifically, the vbo module maintins vertex attributes
- * in vbo_exec_context::array::inputs, which is synchronized with
- * gl_context::Array::ArrayObj::VertexAttrib by vbo_bind_array().
- * vbo_draw_arrays() calls vbo_bind_array() to perform the
- * synchronization before calling the real draw call,
- * vbo_context::draw_arrays.
- *
- * At this point (after performing a resolve meta-op but before calling
- * vbo_bind_array), the gl_context's vertex attributes have been
- * restored to their original state (that is, their state before the
- * meta-op began), but the vbo module's vertex attribute are those used
- * in the last meta-op. Therefore we must manually synchronize the two with
- * vbo_bind_array() before continuing with the original draw command.
- */
- _mesa_update_state(ctx);
- vbo_bind_arrays(ctx);
- _mesa_update_state(ctx);
+ intel_miptree_all_slices_resolve_depth(intel, tex_obj->mt);
}
}
@@ -372,9 +335,7 @@ static void brw_postdraw_set_buffers_need_resolve(struct brw_context *brw)
struct intel_renderbuffer *depth_irb =
intel_get_renderbuffer(fb, BUFFER_DEPTH);
- if (depth_irb &&
- ctx->Depth.Mask &&
- !brw->hiz.op) {
+ if (depth_irb && ctx->Depth.Mask) {
intel_renderbuffer_set_needs_depth_resolve(depth_irb);
}
}
diff --git a/src/mesa/drivers/dri/i965/brw_state_upload.c b/src/mesa/drivers/dri/i965/brw_state_upload.c
index d071f87..f5e6fdc 100644
--- a/src/mesa/drivers/dri/i965/brw_state_upload.c
+++ b/src/mesa/drivers/dri/i965/brw_state_upload.c
@@ -372,7 +372,6 @@ static struct dirty_bit_map brw_bits[] = {
DEFINE_BIT(BRW_NEW_GS_BINDING_TABLE),
DEFINE_BIT(BRW_NEW_PS_BINDING_TABLE),
DEFINE_BIT(BRW_NEW_STATE_BASE_ADDRESS),
- DEFINE_BIT(BRW_NEW_HIZ),
{0, 0, 0}
};
diff --git a/src/mesa/drivers/dri/i965/brw_vtbl.c b/src/mesa/drivers/dri/i965/brw_vtbl.c
index be975d1..a24b44d 100644
--- a/src/mesa/drivers/dri/i965/brw_vtbl.c
+++ b/src/mesa/drivers/dri/i965/brw_vtbl.c
@@ -70,9 +70,11 @@ static void brw_destroy_context( struct intel_context *intel )
brw_destroy_state(brw);
brw_draw_destroy( brw );
+
ralloc_free(brw->wm.compile_data);
dri_bo_release(&brw->curbe.curbe_bo);
+ dri_bo_release(&brw->hiz.vertex_bo);
dri_bo_release(&brw->vs.const_bo);
dri_bo_release(&brw->wm.const_bo);
diff --git a/src/mesa/drivers/dri/i965/gen6_clip_state.c b/src/mesa/drivers/dri/i965/gen6_clip_state.c
index d2a5f75..b3bb8ae 100644
--- a/src/mesa/drivers/dri/i965/gen6_clip_state.c
+++ b/src/mesa/drivers/dri/i965/gen6_clip_state.c
@@ -67,23 +67,6 @@ upload_clip_state(struct brw_context *brw)
GEN6_CLIP_NON_PERSPECTIVE_BARYCENTRIC_ENABLE;
}
- if (brw->hiz.op) {
- /* HiZ operations emit a rectangle primitive, which requires clipping to
- * be disabled. From page 10 of the Sandy Bridge PRM Volume 2 Part 1
- * Section 1.3 3D Primitives Overview:
- * RECTLIST:
- * Either the CLIP unit should be DISABLED, or the CLIP unit's Clip
- * Mode should be set to a value other than CLIPMODE_NORMAL.
- */
- BEGIN_BATCH(4);
- OUT_BATCH(_3DSTATE_CLIP << 16 | (4 - 2));
- OUT_BATCH(0);
- OUT_BATCH(0);
- OUT_BATCH(0);
- ADVANCE_BATCH();
- return;
- }
-
if (!ctx->Transform.DepthClamp)
depth_clamp = GEN6_CLIP_Z_TEST;
@@ -124,8 +107,7 @@ const struct brw_tracked_state gen6_clip_state = {
.dirty = {
.mesa = _NEW_TRANSFORM | _NEW_LIGHT,
.brw = (BRW_NEW_CONTEXT |
- BRW_NEW_FRAGMENT_PROGRAM |
- BRW_NEW_HIZ),
+ BRW_NEW_FRAGMENT_PROGRAM),
.cache = 0
},
.emit = upload_clip_state,
diff --git a/src/mesa/drivers/dri/i965/gen6_depthstencil.c b/src/mesa/drivers/dri/i965/gen6_depthstencil.c
index d9f686a..4ea517f 100644
--- a/src/mesa/drivers/dri/i965/gen6_depthstencil.c
+++ b/src/mesa/drivers/dri/i965/gen6_depthstencil.c
@@ -82,11 +82,7 @@ gen6_upload_depth_stencil_state(struct brw_context *brw)
}
/* _NEW_DEPTH */
- if ((ctx->Depth.Test || brw->hiz.op) && depth_irb) {
- assert(brw->hiz.op != BRW_HIZ_OP_DEPTH_RESOLVE || ctx->Depth.Test);
- assert(brw->hiz.op != BRW_HIZ_OP_HIZ_RESOLVE || !ctx->Depth.Test);
- assert(brw->hiz.op != BRW_HIZ_OP_DEPTH_CLEAR || !ctx->Depth.Test);
-
+ if (ctx->Depth.Test && depth_irb) {
ds->ds2.depth_test_enable = ctx->Depth.Test;
ds->ds2.depth_test_func = intel_translate_compare_func(ctx->Depth.Func);
ds->ds2.depth_write_enable = ctx->Depth.Mask;
@@ -98,8 +94,7 @@ gen6_upload_depth_stencil_state(struct brw_context *brw)
const struct brw_tracked_state gen6_depth_stencil_state = {
.dirty = {
.mesa = _NEW_DEPTH | _NEW_STENCIL | _NEW_BUFFERS,
- .brw = (BRW_NEW_BATCH |
- BRW_NEW_HIZ),
+ .brw = BRW_NEW_BATCH,
.cache = 0,
},
.emit = gen6_upload_depth_stencil_state,
diff --git a/src/mesa/drivers/dri/i965/gen6_hiz.c b/src/mesa/drivers/dri/i965/gen6_hiz.c
index d7698ed..3638000 100644
--- a/src/mesa/drivers/dri/i965/gen6_hiz.c
+++ b/src/mesa/drivers/dri/i965/gen6_hiz.c
@@ -25,324 +25,653 @@
#include <assert.h>
-#include "mesa/drivers/common/meta.h"
-
-#include "mesa/main/arrayobj.h"
-#include "mesa/main/bufferobj.h"
-#include "mesa/main/depth.h"
-#include "mesa/main/enable.h"
-#include "mesa/main/fbobject.h"
-#include "mesa/main/framebuffer.h"
-#include "mesa/main/get.h"
-#include "mesa/main/renderbuffer.h"
+#include "glsl/ralloc.h"
+
#include "mesa/main/shaderapi.h"
-#include "mesa/main/varray.h"
+#include "mesa/main/shaderobj.h"
+#include "intel_batchbuffer.h"
#include "intel_fbo.h"
#include "intel_mipmap_tree.h"
-#include "intel_regions.h"
-#include "intel_tex.h"
#include "brw_context.h"
#include "brw_defines.h"
+#include "brw_state.h"
+#include "brw_vs.h"
+#include "brw_wm.h"
-static const uint32_t gen6_hiz_meta_save =
-
- /* Disable alpha, depth, and stencil test.
- *
- * See the following sections of the Sandy Bridge PRM, Volume 1, Part2:
- * - 7.5.3.1 Depth Buffer Clear
- * - 7.5.3.2 Depth Buffer Resolve
- * - 7.5.3.3 Hierarchical Depth Buffer Resolve
- */
- MESA_META_ALPHA_TEST |
- MESA_META_DEPTH_TEST |
- MESA_META_STENCIL_TEST |
-
- /* Disable viewport mapping.
- *
- * From page 11 of the Sandy Bridge PRM, Volume 2, Part 1, Section 1.3
- * 3D Primitives Overview:
- * RECTLIST:
- * Viewport Mapping must be DISABLED (as is typical with the use of
- * screen- space coordinates).
- *
- * We must also manually disable 3DSTATE_SF.Viewport_Transform_Enable.
- */
- MESA_META_VIEWPORT |
-
- /* Disable clipping.
- *
- * From page 11 of the Sandy Bridge PRM, Volume 2, Part 1, Section 1.3
- * 3D Primitives Overview:
- * Either the CLIP unit should be DISABLED, or the CLIP unit’s Clip
- * Mode should be set to a value other than CLIPMODE_NORMAL.
- */
- MESA_META_CLIP |
-
- /* Render a solid rectangle (set 3DSTATE_SF.FrontFace_Fill_Mode).
- *
- * From page 249 of the Sandy Bridge PRM, Volume 2, Part 1, Section
- * 6.4.1.1 3DSTATE_SF, FrontFace_Fill_Mode:
- * SOLID: Any triangle or rectangle object found to be front-facing
- * is rendered as a solid object. This setting is required when
- * (rendering rectangle (RECTLIST) objects.
- * Also see field BackFace_Fill_Mode.
- *
- * Note: MESA_META_RASTERIZAION also disables culling, but that is
- * irrelevant. See 3DSTATE_SF.Cull_Mode.
- */
- MESA_META_RASTERIZATION |
-
- /* Each HiZ operation uses a vertex shader and VAO. */
- MESA_META_SHADER |
- MESA_META_VERTEX |
-
- /* Disable scissoring.
- *
- * Scissoring is disabled for resolves because a resolve operation
- * should resolve the entire buffer. Scissoring is disabled for depth
- * clears because, if we are performing a partial depth clear, then we
- * specify the clear region with the RECTLIST vertices.
- */
- MESA_META_SCISSOR |
-
- MESA_META_SELECT_FEEDBACK;
+/**
+ * For an overview of the HiZ operations, see the following sections of the
+ * Sandy Bridge PRM, Volume 1, Part2:
+ * - 7.5.3.1 Depth Buffer Clear
+ * - 7.5.3.2 Depth Buffer Resolve
+ * - 7.5.3.3 Hierarchical Depth Buffer Resolve
+ */
+enum gen6_hiz_op {
+ GEN6_HIZ_OP_DEPTH_CLEAR,
+ GEN6_HIZ_OP_DEPTH_RESOLVE,
+ GEN6_HIZ_OP_HIZ_RESOLVE,
+};
-static void
-gen6_hiz_get_framebuffer_enum(struct gl_context *ctx,
- GLenum *bind_enum,
- GLenum *get_enum)
-{
- if (ctx->Extensions.EXT_framebuffer_blit && ctx->API == API_OPENGL) {
- /* Different buffers may be bound to GL_DRAW_FRAMEBUFFER and
- * GL_READ_FRAMEBUFFER. Take care to not disrupt the read buffer.
- */
- *bind_enum = GL_DRAW_FRAMEBUFFER;
- *get_enum = GL_DRAW_FRAMEBUFFER_BINDING;
- } else {
- /* The enums GL_DRAW_FRAMEBUFFER and GL_READ_FRAMEBUFFER do not exist.
- * The bound framebuffer is both the read and draw buffer.
- */
- *bind_enum = GL_FRAMEBUFFER;
- *get_enum = GL_FRAMEBUFFER_BINDING;
- }
-}
+/**
+ * \name Constants for HiZ VBO
+ * \{
+ *
+ * \see brw_context::hiz::vertex_bo
+ */
+#define GEN6_HIZ_NUM_VERTICES 3
+#define GEN6_HIZ_NUM_VERTEX_COMPONENTS 4
+#define GEN6_HIZ_VBO_SIZE (GEN6_HIZ_NUM_VERTICES \
+ * GEN6_HIZ_NUM_VERTEX_COMPONENTS \
+ * sizeof(float))
+/** \} */
/**
- * Initialize static data needed for HiZ operations.
+ * \brief Initialize data needed for the HiZ op.
+ *
+ * This called when executing the first HiZ op.
+ * \see brw_context::hiz
*/
static void
gen6_hiz_init(struct brw_context *brw)
{
struct gl_context *ctx = &brw->intel.ctx;
+ struct intel_context *intel = &brw->intel;
struct brw_hiz_state *hiz = &brw->hiz;
- GLenum fb_bind_enum, fb_get_enum;
- if (hiz->fbo != 0)
- return;
-
- gen6_hiz_get_framebuffer_enum(ctx, &fb_bind_enum, &fb_get_enum);
+ hiz->vertex_bo = drm_intel_bo_alloc(intel->bufmgr, "bufferobj",
+ GEN6_HIZ_VBO_SIZE, /* size */
+ 64); /* alignment */
- /* Create depthbuffer.
- *
- * Until glRenderbufferStorage is called, the renderbuffer hash table
- * maps the renderbuffer name to a dummy renderbuffer. We need the
- * renderbuffer to be registered in the hash table so that framebuffer
- * validation succeeds, so we hackishly allocate storage then immediately
- * discard it.
- */
- GLuint depth_rb_name;
- _mesa_GenRenderbuffersEXT(1, &depth_rb_name);
- _mesa_BindRenderbufferEXT(GL_RENDERBUFFER, depth_rb_name);
- _mesa_RenderbufferStorageEXT(GL_RENDERBUFFER, GL_DEPTH_COMPONENT, 32, 32);
- _mesa_reference_renderbuffer(&hiz->depth_rb,
- _mesa_lookup_renderbuffer(ctx, depth_rb_name));
- intel_miptree_release(&((struct intel_renderbuffer*) hiz->depth_rb)->mt);
-
- /* Setup FBO. */
- _mesa_GenFramebuffersEXT(1, &hiz->fbo);
- _mesa_BindFramebufferEXT(fb_bind_enum, hiz->fbo);
- _mesa_FramebufferRenderbufferEXT(fb_bind_enum,
- GL_DEPTH_ATTACHMENT,
- GL_RENDERBUFFER,
- hiz->depth_rb->Name);
-
- /* Compile vertex shader. */
- const char *vs_source =
- "attribute vec4 position;\n"
- "void main()\n"
- "{\n"
- " gl_Position = position;\n"
- "}\n";
- GLuint vs = _mesa_CreateShaderObjectARB(GL_VERTEX_SHADER);
- _mesa_ShaderSourceARB(vs, 1, &vs_source, NULL);
- _mesa_CompileShaderARB(vs);
-
- /* Compile fragment shader. */
- const char *fs_source = "void main() {}";
- GLuint fs = _mesa_CreateShaderObjectARB(GL_FRAGMENT_SHADER);
- _mesa_ShaderSourceARB(fs, 1, &fs_source, NULL);
- _mesa_CompileShaderARB(fs);
-
- /* Link and use program. */
- hiz->shader.program = _mesa_CreateProgramObjectARB();
- _mesa_AttachShader(hiz->shader.program, vs);
- _mesa_AttachShader(hiz->shader.program, fs);
- _mesa_LinkProgramARB(hiz->shader.program);
- _mesa_UseProgramObjectARB(hiz->shader.program);
-
- /* Create and bind VAO. */
- _mesa_GenVertexArrays(1, &hiz->vao);
- _mesa_BindVertexArray(hiz->vao);
-
- /* Setup VBO for 'position'. */
- hiz->shader.position_location =
- _mesa_GetAttribLocationARB(hiz->shader.program, "position");
- _mesa_GenBuffersARB(1, &hiz->shader.position_vbo);
- _mesa_BindBufferARB(GL_ARRAY_BUFFER_ARB, hiz->shader.position_vbo);
- _mesa_VertexAttribPointerARB(hiz->shader.position_location,
- 2, /*components*/
- GL_FLOAT,
- GL_FALSE, /*normalized?*/
- 0, /*stride*/
- NULL);
- _mesa_EnableVertexAttribArrayARB(hiz->shader.position_location);
-
- /* Cleanup. */
- _mesa_DeleteShader(vs);
- _mesa_DeleteShader(fs);
+ if (!hiz->vertex_bo)
+ _mesa_error(ctx, GL_OUT_OF_MEMORY, "failed to allocate internal VBO");
}
/**
- * Wrap \c brw->hiz.depth_rb around a miptree.
+ * \brief Execute a HiZ op on a miptree slice.
*
- * \see gen6_hiz_teardown_depth_buffer()
- */
-static void
-gen6_hiz_setup_depth_buffer(struct brw_context *brw,
- struct intel_mipmap_tree *mt,
- unsigned int level,
- unsigned int layer)
-{
- struct gl_renderbuffer *rb = brw->hiz.depth_rb;
- struct intel_renderbuffer *irb = intel_renderbuffer(rb);
-
- rb->Format = mt->format;
- rb->_BaseFormat = _mesa_get_format_base_format(rb->Format);
- rb->InternalFormat = rb->_BaseFormat;
- rb->Width = mt->level[level].width;
- rb->Height = mt->level[level].height;
-
- irb->mt_level = level;
- irb->mt_layer = layer;
-
- intel_miptree_reference(&irb->mt, mt);
- intel_renderbuffer_set_draw_offset(irb);
-}
-
-/**
- * Release the region from \c brw->hiz.depth_rb.
+ * To execute the HiZ op, this function manually constructs and emits a batch
+ * to "draw" the HiZ op's rectangle primitive. The batchbuffer is flushed
+ * before constructing and after emitting the batch.
*
- * \see gen6_hiz_setup_depth_buffer()
+ * This function alters no GL state.
+ *
+ * For an overview of HiZ ops, see the following sections of the Sandy Bridge
+ * PRM, Volume 1, Part2:
+ * - 7.5.3.1 Depth Buffer Clear
+ * - 7.5.3.2 Depth Buffer Resolve
+ * - 7.5.3.3 Hierarchical Depth Buffer Resolve
*/
static void
-gen6_hiz_teardown_depth_buffer(struct gl_renderbuffer *rb)
-{
- struct intel_renderbuffer *irb = intel_renderbuffer(rb);
- intel_miptree_release(&irb->mt);
-}
-
-static void
-gen6_resolve_slice(struct intel_context *intel,
- struct intel_mipmap_tree *mt,
- unsigned int level,
- unsigned int layer,
- enum brw_hiz_op op)
+gen6_hiz_exec(struct intel_context *intel,
+ struct intel_mipmap_tree *mt,
+ unsigned int level,
+ unsigned int layer,
+ enum gen6_hiz_op op)
{
struct gl_context *ctx = &intel->ctx;
struct brw_context *brw = brw_context(ctx);
struct brw_hiz_state *hiz = &brw->hiz;
- GLenum fb_bind_enum, fb_get_enum;
-
- /* Do not recurse. */
- assert(!brw->hiz.op);
+ assert(op != GEN6_HIZ_OP_DEPTH_CLEAR); /* Not implemented yet. */
assert(mt->hiz_mt != NULL);
- assert(level >= mt->first_level);
- assert(level <= mt->last_level);
- assert(layer < mt->level[level].depth);
-
- gen6_hiz_get_framebuffer_enum(ctx, &fb_bind_enum, &fb_get_enum);
-
- /* Save state. */
- GLint save_drawbuffer;
- GLint save_renderbuffer;
- _mesa_meta_begin(ctx, gen6_hiz_meta_save);
- _mesa_GetIntegerv(fb_get_enum, &save_drawbuffer);
- _mesa_GetIntegerv(GL_RENDERBUFFER_BINDING, &save_renderbuffer);
-
- /* Initialize context data for HiZ operations. */
- gen6_hiz_init(brw);
-
- /* Set depth state. */
- if (!ctx->Depth.Mask) {
- /* This sets 3DSTATE_WM.Depth_Buffer_Write_Enable. */
- _mesa_DepthMask(GL_TRUE);
- }
- if (op == BRW_HIZ_OP_DEPTH_RESOLVE) {
- _mesa_set_enable(ctx, GL_DEPTH_TEST, GL_TRUE);
- _mesa_DepthFunc(GL_NEVER);
- }
+ intel_miptree_check_level_layer(mt, level, layer);
- /* Setup FBO. */
- gen6_hiz_setup_depth_buffer(brw, mt, level, layer);
- _mesa_BindFramebufferEXT(fb_bind_enum, hiz->fbo);
+ if (hiz->vertex_bo == NULL)
+ gen6_hiz_init(brw);
+ if (hiz->vertex_bo == NULL) {
+ /* Ouch. Give up. */
+ return;
+ }
- /* A rectangle primitive (3DPRIM_RECTLIST) consists of only three vertices.
- * The vertices reside in screen space with DirectX coordinates (this is,
- * (0, 0) is the upper left corner).
+ /* Setup VBO for the rectangle primitive..
+ *
+ * A rectangle primitive (3DPRIM_RECTLIST) consists of only three
+ * vertices. The vertices reside in screen space with DirectX coordinates
+ * (that is, (0, 0) is the upper left corner).
*
* v2 ------ implied
* | |
* | |
* v0 ----- v1
+ *
+ * Since the VS is disabled, the clipper loads each vertex directly from
+ * the VBO. As the clipper loads each vertex, perspective division occurs.
+ * This requires that we explicity provide the vertex's w component. (This
+ * requirement was discovered by observing the simulator).
+ */
+ {
+ const int width = mt->level[level].width;
+ const int height = mt->level[level].height;
+ const float vertices[GEN6_HIZ_VBO_SIZE] = {
+ 0, height, 0, 1, /* v0 */
+ width, height, 0, 1, /* v1 */
+ 0, 0, 0, 1, /* v2 */
+ };
+
+ drm_intel_bo_subdata(hiz->vertex_bo, 0, GEN6_HIZ_VBO_SIZE, vertices);
+ }
+
+ /* To ensure that the batch contains only the resolve, flush the batch
+ * before beginning and after finishing emitting the resolve packets.
+ *
+ * Ideally, we would not need to flush for the resolve op. But, I suspect
+ * that it's unsafe for CMD_PIPELINE_SELECT to occur multiple times in
+ * a single batch, and there is no safe way to ensure that other than by
+ * fencing the resolve with flushes. Ideally, we would just detect if
+ * a batch is in progress and do the right thing, but that would require
+ * the ability to safely manipulate brw_context::state::dirty::brw outside
+ * of brw_state_init().
+ */
+ intel_flush(ctx);
+
+ /* Emit the following packets:
+ * CMD_PIPELINE_SELECT
+ * 3DSTATE_MULTISAMPLE
+ * 3DSTATE_SAMPLE_MASK
+ * 3DSTATE_GS_SVB_INDEX
+ * CMD_STATE_SIP
+ * CMD_VF_STATISTICS
+ */
+ brw_invariant_state.emit(brw);
+
+ /* CMD_STATE_BASE_ADDRESS
+ *
+ * From the Sandy Bridge PRM, Volume 1, Part 1, Table STATE_BASE_ADDRESS:
+ *
+ * The following commands must be reissued following any change to the
+ * base addresses:
+ * 3DSTATE_CC_POINTERS
+ * 3DSTATE_BINDING_TABLE_POINTERS
+ * 3DSTATE_SAMPLER_STATE_POINTERS
+ * 3DSTATE_VIEWPORT_STATE_POINTERS
+ * MEDIA_STATE_POINTERS
+ */
+ {
+ BEGIN_BATCH(10);
+ OUT_BATCH(CMD_STATE_BASE_ADDRESS << 16 | (10 - 2));
+ OUT_BATCH(1); /* GeneralStateBaseAddressModifyEnable */
+ /* SurfaceStateBaseAddress */
+ OUT_RELOC(intel->batch.bo, I915_GEM_DOMAIN_SAMPLER, 0, 1);
+ /* DynamicStateBaseAddress */
+ OUT_RELOC(intel->batch.bo, (I915_GEM_DOMAIN_RENDER |
+ I915_GEM_DOMAIN_INSTRUCTION), 0, 1);
+ OUT_BATCH(1); /* IndirectObjectBaseAddress */
+ OUT_BATCH(1); /* InstructionBaseAddress */
+ OUT_BATCH(1); /* GeneralStateUpperBound */
+ OUT_BATCH(1); /* DynamicStateUpperBound */
+ OUT_BATCH(1); /* IndirectObjectUpperBound*/
+ OUT_BATCH(1); /* InstructionAccessUpperBound */
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_VIEWPORT_STATE_POINTERS
+ *
+ * Viewport mapping is disabled for the HiZ op, so it's safe to
+ * set all viewport state pointers to null.
+ *
+ * From page 11 of the Sandy Bridge PRM, Volume 2, Part 1, Section 1.3
+ * 3D Primitives Overview:
+ * RECTLIST:
+ * Viewport Mapping must be DISABLED (as is typical with the use of
+ * screen- space coordinates).
+ */
+ {
+ BEGIN_BATCH(4);
+ OUT_BATCH(_3DSTATE_VIEWPORT_STATE_POINTERS << 16 | (4 - 2) |
+ GEN6_CC_VIEWPORT_MODIFY |
+ GEN6_SF_VIEWPORT_MODIFY |
+ GEN6_CLIP_VIEWPORT_MODIFY);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_URB
+ *
+ * Assign the entire URB to the VS.
+ *
+ * A warning appears in the Sandybridge PRM Volume 2 Part 1 Section 1.4.7
+ * 3DSTATE_URB, but here we can safely ignore it:
+ * Because of URB corruption caused by allocating a previous GS unit
+ * URB entry to the VS unit, software is required to send a “GS NULL
+ * Fence” (Send URB fence with VS URB size == 1 and GS URB size == 0)
+ * plus a dummy DRAW call before any case where VS will be taking over
+ * GS URB space.
+ * We can ignore it because this batch contains only one draw call.
+ *
+ * TODO: Explain why max vs entries must be set. Quote spec.
+ */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ BEGIN_BATCH(3);
+ OUT_BATCH(_3DSTATE_URB << 16 | (3 - 2));
+ OUT_BATCH(brw->urb.max_vs_entries << GEN6_URB_VS_ENTRIES_SHIFT);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* DEPTH_STENCIL_STATE
+ *
+ * The offset is relative CMD_STATE_BASE_ADDRESS.DynamicStateBaseAddress.
+ */
+ uint32_t depthstencil_offset;
+ {
+ assert(intel->gen == 6);
+
+ struct gen6_depth_stencil_state *state;
+ state = brw_state_batch(brw, AUB_TRACE_DEPTH_STENCIL_STATE,
+ sizeof(*state), 64,
+ &depthstencil_offset);
+ memset(state, 0, sizeof(*state));
+
+ /* See the following sections of the Sandy Bridge PRM, Volume 1, Part2:
+ * - 7.5.3.1 Depth Buffer Clear
+ * - 7.5.3.2 Depth Buffer Resolve
+ * - 7.5.3.3 Hierarchical Depth Buffer Resolve
+ */
+ state->ds2.depth_write_enable = 1;
+ if (op == GEN6_HIZ_OP_DEPTH_RESOLVE) {
+ state->ds2.depth_test_enable = 1;
+ state->ds2.depth_test_func = COMPAREFUNC_NEVER;
+ }
+ }
+
+ /* 3DSTATE_CC_STATE_POINTERS
+ *
+ * The HiZ op doesn't use BLEND_STATE or COLOR_CALC_STATE.
+ */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+ BEGIN_BATCH(4);
+ OUT_BATCH(_3DSTATE_CC_STATE_POINTERS << 16 | (4 - 2));
+ OUT_BATCH(1); /* BLEND_STATE offset */
+ OUT_BATCH(depthstencil_offset | 1); /* DEPTH_STENCIL_STATE offset */
+ OUT_BATCH(1); /* COLOR_CALC_STATE offset */
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_VS
+ *
+ * Disable vertex shader.
+ */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ intel_emit_vs_enable_flush(intel);
+
+ BEGIN_BATCH(6);
+ OUT_BATCH(_3DSTATE_VS << 16 | (6 - 2));
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_GS
+ *
+ * Disable the geometry shader.
+ */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ BEGIN_BATCH(7);
+ OUT_BATCH(_3DSTATE_GS << 16 | (7 - 2));
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_CLIP
+ *
+ * Disable the clipper.
+ *
+ * The HiZ op emits a rectangle primitive, which requires clipping to
+ * be disabled. From page 10 of the Sandy Bridge PRM Volume 2 Part 1
+ * Section 1.3 "3D Primitives Overview":
+ * RECTLIST:
+ * Either the CLIP unit should be DISABLED, or the CLIP unit's Clip
+ * Mode should be set to a value other than CLIPMODE_NORMAL.
+ */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ BEGIN_BATCH(4);
+ OUT_BATCH(_3DSTATE_CLIP << 16 | (4 - 2));
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_SF
+ *
+ * Disable ViewportTransformEnable (dw2.1)
+ *
+ * From the SandyBridge PRM, Volume 2, Part 1, Section 1.3, "3D
+ * Primitives Overview":
+ * RECTLIST: Viewport Mapping must be DISABLED (as is typical with the
+ * use of screen- space coordinates).
+ *
+ * A solid rectangle must be rendered, so set FrontFaceFillMode (dw2.4:3)
+ * and BackFaceFillMode (dw2.5:6) to SOLID(0).
+ *
+ * From the Sandy Bridge PRM, Volume 2, Part 1, Section
+ * 6.4.1.1 3DSTATE_SF, Field FrontFaceFillMode:
+ * SOLID: Any triangle or rectangle object found to be front-facing
+ * is rendered as a solid object. This setting is required when
+ * (rendering rectangle (RECTLIST) objects.
*/
- const int width = hiz->depth_rb->Width;
- const int height = hiz->depth_rb->Height;
- const GLfloat positions[] = {
- 0, height,
- width, height,
- 0, 0,
- };
-
- /* Setup program and vertex attributes. */
- _mesa_UseProgramObjectARB(hiz->shader.program);
- _mesa_BindVertexArray(hiz->vao);
- _mesa_BindBufferARB(GL_ARRAY_BUFFER, hiz->shader.position_vbo);
- _mesa_BufferDataARB(GL_ARRAY_BUFFER_ARB, sizeof(positions), positions,
- GL_DYNAMIC_DRAW_ARB);
-
- /* Execute the HiZ operation. */
- brw->hiz.op = op;
- brw->state.dirty.brw |= BRW_NEW_HIZ;
- _mesa_DrawArrays(GL_TRIANGLES, 0, 3);
- brw->state.dirty.brw |= BRW_NEW_HIZ;
- brw->hiz.op = BRW_HIZ_OP_NONE;
-
- /* Restore state.
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ BEGIN_BATCH(20);
+ OUT_BATCH(_3DSTATE_SF << 16 | (20 - 2));
+ OUT_BATCH((1 - 1) << GEN6_SF_NUM_OUTPUTS_SHIFT | /* only position */
+ 1 << GEN6_SF_URB_ENTRY_READ_LENGTH_SHIFT |
+ 1 << GEN6_SF_URB_ENTRY_READ_OFFSET_SHIFT);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_CONSTANT_PS
*
- * The order in which state is restored is significant. The draw buffer
- * used for the HiZ op has no stencil buffer, and glStencilFunc() clamps
- * the stencil reference value to the range allowed by the draw buffer's
- * number of stencil bits. So, the draw buffer binding must be restored
- * before the stencil state, or else the stencil ref will be clamped to 0.
+ * Disable the push constant buffer.
*/
- gen6_hiz_teardown_depth_buffer(hiz->depth_rb);
- _mesa_BindRenderbufferEXT(GL_RENDERBUFFER, save_renderbuffer);
- _mesa_BindFramebufferEXT(fb_bind_enum, save_drawbuffer);
- _mesa_meta_end(ctx);
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ BEGIN_BATCH(5);
+ OUT_BATCH(_3DSTATE_CONSTANT_PS << 16 | (5 - 2));
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_WM
+ *
+ * Disable thread dispatch (dw5.19) and enable the HiZ op.
+ */
+ {
+ uint32_t dw4 = 0;
+
+ switch (op) {
+ case GEN6_HIZ_OP_DEPTH_CLEAR:
+ assert(!"not implemented");
+ dw4 |= GEN6_WM_DEPTH_CLEAR;
+ break;
+ case GEN6_HIZ_OP_DEPTH_RESOLVE:
+ dw4 |= GEN6_WM_DEPTH_RESOLVE;
+ break;
+ case GEN6_HIZ_OP_HIZ_RESOLVE:
+ dw4 |= GEN6_WM_HIERARCHICAL_DEPTH_RESOLVE;
+ break;
+ default:
+ assert(0);
+ break;
+ }
+
+ /* Even though thread dispatch disabled, max threads (dw5.25) must be
+ * nonzero to prevent the GPU from hanging.
+ */
+ uint32_t dw5 = (brw->max_wm_threads - 1) << GEN6_WM_MAX_THREADS_SHIFT;
+
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ BEGIN_BATCH(9);
+ OUT_BATCH(_3DSTATE_WM << 16 | (9 - 2));
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ OUT_BATCH(dw4);
+ OUT_BATCH(dw5);
+ OUT_BATCH((1 - 1) << GEN6_WM_NUM_SF_OUTPUTS_SHIFT); /* only position */
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_SCISSOR_STATE_POINTERS
+ *
+ * The HiZ op does not use scissoring, so set the state pointer to null.
+ */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ BEGIN_BATCH(2);
+ OUT_BATCH(_3DSTATE_SCISSOR_STATE_POINTERS << 16 | (2 - 2));
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_BINDING_TABLE_POINTERS */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ gen6_binding_table_pointers.emit(brw);
+ }
+
+ /* 3DSTATE_DEPTH_BUFFER */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ uint32_t width = mt->level[level].width;
+ uint32_t height = mt->level[level].height;
+
+ uint32_t tile_x;
+ uint32_t tile_y;
+ uint32_t offset;
+ {
+ /* Construct a dummy renderbuffer just to extract tile offsets. */
+ struct intel_renderbuffer rb;
+ rb.mt = mt;
+ rb.mt_level = level;
+ rb.mt_layer = layer;
+ intel_renderbuffer_set_draw_offset(&rb);
+ offset = intel_renderbuffer_tile_offsets(&rb, &tile_x, &tile_y);
+ }
+
+ uint32_t format;
+ switch (mt->format) {
+ case MESA_FORMAT_Z16: format = BRW_DEPTHFORMAT_D16_UNORM; break;
+ case MESA_FORMAT_Z32_FLOAT: format = BRW_DEPTHFORMAT_D32_FLOAT; break;
+ case MESA_FORMAT_X8_Z24: format = BRW_DEPTHFORMAT_D24_UNORM_X8_UINT; break;
+ default: assert(0); break;
+ }
+
+ intel_emit_post_sync_nonzero_flush(intel);
+ intel_emit_depth_stall_flushes(intel);
+
+ BEGIN_BATCH(7);
+ OUT_BATCH(_3DSTATE_DEPTH_BUFFER << 16 | (7 - 2));
+ OUT_BATCH(((mt->region->pitch * mt->region->cpp) - 1) |
+ format << 18 |
+ 1 << 21 | /* separate stencil enable */
+ 1 << 22 | /* hiz enable */
+ BRW_TILEWALK_YMAJOR << 26 |
+ 1 << 27 | /* y-tiled */
+ BRW_SURFACE_2D << 29);
+ OUT_RELOC(mt->region->bo,
+ I915_GEM_DOMAIN_RENDER, I915_GEM_DOMAIN_RENDER,
+ offset);
+ OUT_BATCH(BRW_SURFACE_MIPMAPLAYOUT_BELOW << 1 |
+ (width + tile_x - 1) << 6 |
+ (height + tile_y - 1) << 19);
+ OUT_BATCH(0);
+ OUT_BATCH(tile_x |
+ tile_y << 16);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_HIER_DEPTH_BUFFER */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ struct intel_region *hiz_region = mt->hiz_mt->region;
+
+ BEGIN_BATCH(3);
+ OUT_BATCH((_3DSTATE_HIER_DEPTH_BUFFER << 16) | (3 - 2));
+ OUT_BATCH(hiz_region->pitch * hiz_region->cpp - 1);
+ OUT_RELOC(hiz_region->bo,
+ I915_GEM_DOMAIN_RENDER, I915_GEM_DOMAIN_RENDER,
+ 0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_STENCIL_BUFFER */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ BEGIN_BATCH(3);
+ OUT_BATCH((_3DSTATE_STENCIL_BUFFER << 16) | (3 - 2));
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_CLEAR_PARAMS
+ *
+ * From the Sandybridge PRM, Volume 2, Part 1, Section 3DSTATE_CLEAR_PARAMS:
+ * 3DSTATE_CLEAR_PARAMS packet must follow the DEPTH_BUFFER_STATE packet
+ * when HiZ is enabled and the DEPTH_BUFFER_STATE changes.
+ */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ intel_emit_post_sync_nonzero_flush(intel);
+ BEGIN_BATCH(2);
+ OUT_BATCH(_3DSTATE_CLEAR_PARAMS << 16 | (2 - 2));
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_DRAWING_RECTANGLE */
+ {
+ BEGIN_BATCH(4);
+ OUT_BATCH(_3DSTATE_DRAWING_RECTANGLE << 16 | (4 - 2));
+ OUT_BATCH(0);
+ OUT_BATCH(((mt->level[level].width - 1) & 0xffff) |
+ ((mt->level[level].height - 1) << 16));
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_VERTEX_BUFFERS */
+ {
+ const int num_buffers = 1;
+ const int batch_length = 1 + 4 * num_buffers;
+
+ uint32_t dw0 = GEN6_VB0_ACCESS_VERTEXDATA |
+ (GEN6_HIZ_NUM_VERTEX_COMPONENTS * sizeof(float)) << BRW_VB0_PITCH_SHIFT;
+ if (intel->gen >= 7)
+ dw0 |= GEN7_VB0_ADDRESS_MODIFYENABLE;
+
+ BEGIN_BATCH(batch_length);
+ OUT_BATCH((_3DSTATE_VERTEX_BUFFERS << 16) | (batch_length - 2));
+ OUT_BATCH(dw0);
+ OUT_RELOC(hiz->vertex_bo, I915_GEM_DOMAIN_VERTEX, 0, 0);
+ OUT_RELOC(hiz->vertex_bo, I915_GEM_DOMAIN_VERTEX, 0, hiz->vertex_bo->size - 1);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* 3DSTATE_VERTEX_ELEMENTS
+ *
+ * TODO: Explain WTF is happening here.
+ */
+ {
+ const int num_elements = 2;
+ const int batch_length = 1 + 2 * num_elements;
+
+ BEGIN_BATCH(batch_length);
+ OUT_BATCH((_3DSTATE_VERTEX_ELEMENTS << 16) | (batch_length - 2));
+ OUT_BATCH(0 << GEN6_VE0_INDEX_SHIFT |
+ GEN6_VE0_VALID |
+ BRW_SURFACEFORMAT_R32G32B32A32_FLOAT << BRW_VE0_FORMAT_SHIFT |
+ 0 << BRW_VE0_SRC_OFFSET_SHIFT |
+ 0 << BRW_VE1_DST_OFFSET_SHIFT);
+ OUT_BATCH(BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_0_SHIFT |
+ BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_1_SHIFT |
+ BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_2_SHIFT |
+ BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_3_SHIFT);
+ OUT_BATCH(0 << GEN6_VE0_INDEX_SHIFT |
+ GEN6_VE0_VALID |
+ BRW_SURFACEFORMAT_R32G32B32A32_FLOAT << BRW_VE0_FORMAT_SHIFT |
+ 0 << BRW_VE0_SRC_OFFSET_SHIFT |
+ 0 << BRW_VE1_DST_OFFSET_SHIFT);
+ OUT_BATCH(BRW_VE1_COMPONENT_STORE_SRC << BRW_VE1_COMPONENT_0_SHIFT |
+ BRW_VE1_COMPONENT_STORE_SRC << BRW_VE1_COMPONENT_1_SHIFT |
+ BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_2_SHIFT |
+ BRW_VE1_COMPONENT_STORE_1_FLT << BRW_VE1_COMPONENT_3_SHIFT);
+ ADVANCE_BATCH();
+ }
+
+ /* CMD_3D_PRIM */
+ {
+ /* TODO(chad): gen7 */
+ assert(intel->gen == 6);
+
+ BEGIN_BATCH(6);
+ OUT_BATCH(CMD_3D_PRIM << 16 | (6 - 2) |
+ _3DPRIM_RECTLIST << GEN4_3DPRIM_TOPOLOGY_TYPE_SHIFT |
+ GEN4_3DPRIM_VERTEXBUFFER_ACCESS_SEQUENTIAL);
+ OUT_BATCH(GEN6_HIZ_NUM_VERTICES); /* vertex count per instance */
+ OUT_BATCH(0);
+ OUT_BATCH(1); /* instance count */
+ OUT_BATCH(0);
+ OUT_BATCH(0);
+ ADVANCE_BATCH();
+ }
+
+ /* See comments above at first invocation of intel_flush(). */
+ intel_flush(ctx);
+
+ /* Be safe. */
+ brw->state.dirty.brw = ~0;
+ brw->state.dirty.cache = ~0;
}
void
@@ -351,7 +680,7 @@ gen6_resolve_hiz_slice(struct intel_context *intel,
uint32_t level,
uint32_t layer)
{
- gen6_resolve_slice(intel, mt, level, layer, BRW_HIZ_OP_HIZ_RESOLVE);
+ gen6_hiz_exec(intel, mt, level, layer, GEN6_HIZ_OP_HIZ_RESOLVE);
}
@@ -361,5 +690,5 @@ gen6_resolve_depth_slice(struct intel_context *intel,
uint32_t level,
uint32_t layer)
{
- gen6_resolve_slice(intel, mt, level, layer, BRW_HIZ_OP_DEPTH_RESOLVE);
+ gen6_hiz_exec(intel, mt, level, layer, GEN6_HIZ_OP_DEPTH_RESOLVE);
}
diff --git a/src/mesa/drivers/dri/i965/gen6_sf_state.c b/src/mesa/drivers/dri/i965/gen6_sf_state.c
index 163b54c..07b8e6d 100644
--- a/src/mesa/drivers/dri/i965/gen6_sf_state.c
+++ b/src/mesa/drivers/dri/i965/gen6_sf_state.c
@@ -149,17 +149,8 @@ upload_sf_state(struct brw_context *brw)
urb_entry_read_length << GEN6_SF_URB_ENTRY_READ_LENGTH_SHIFT |
urb_entry_read_offset << GEN6_SF_URB_ENTRY_READ_OFFSET_SHIFT;
- dw2 = GEN6_SF_STATISTICS_ENABLE;
-
- /* Enable viewport transform only if no HiZ operation is progress
- *
- * From page 11 of the SandyBridge PRM, Volume 2, Part 1, Section 1.3, "3D
- * Primitives Overview":
- * RECTLIST: Viewport Mapping must be DISABLED (as is typical with the
- * use of screen- space coordinates).
- */
- if (!brw->hiz.op)
- dw2 |= GEN6_SF_VIEWPORT_TRANSFORM_ENABLE;
+ dw2 = GEN6_SF_STATISTICS_ENABLE |
+ GEN6_SF_VIEWPORT_TRANSFORM_ENABLE;
dw3 = 0;
dw4 = 0;
@@ -354,8 +345,7 @@ const struct brw_tracked_state gen6_sf_state = {
_NEW_POINT |
_NEW_TRANSFORM),
.brw = (BRW_NEW_CONTEXT |
- BRW_NEW_FRAGMENT_PROGRAM |
- BRW_NEW_HIZ),
+ BRW_NEW_FRAGMENT_PROGRAM),
.cache = CACHE_NEW_VS_PROG
},
.emit = upload_sf_state,
diff --git a/src/mesa/drivers/dri/i965/gen6_vs_state.c b/src/mesa/drivers/dri/i965/gen6_vs_state.c
index 63efaa4..c481ac6 100644
--- a/src/mesa/drivers/dri/i965/gen6_vs_state.c
+++ b/src/mesa/drivers/dri/i965/gen6_vs_state.c
@@ -164,6 +164,19 @@ upload_vs_state(struct brw_context *brw)
if (intel->ctx.Shader.CurrentVertexProgram == NULL)
floating_point_mode = GEN6_VS_FLOATING_POINT_MODE_ALT;
+ if (intel->gen == 6) {
+ BEGIN_BATCH(4);
+ OUT_BATCH(_3DSTATE_PIPE_CONTROL);
+ OUT_BATCH(PIPE_CONTROL_CS_STALL |
+ PIPE_CONTROL_WRITE_IMMEDIATE);
+ OUT_RELOC(intel->batch.workaround_bo,
+ I915_GEM_DOMAIN_INSTRUCTION, I915_GEM_DOMAIN_INSTRUCTION, 0);
+ OUT_BATCH(0); /* write data */
+ ADVANCE_BATCH();
+ }
+
+ intel_emit_vs_enable_flush(intel);
+
BEGIN_BATCH(6);
OUT_BATCH(_3DSTATE_VS << 16 | (6 - 2));
OUT_BATCH(brw->vs.prog_offset);
diff --git a/src/mesa/drivers/dri/i965/gen6_wm_state.c b/src/mesa/drivers/dri/i965/gen6_wm_state.c
index 3669811..205e648 100644
--- a/src/mesa/drivers/dri/i965/gen6_wm_state.c
+++ b/src/mesa/drivers/dri/i965/gen6_wm_state.c
@@ -149,23 +149,6 @@ upload_wm_state(struct brw_context *brw)
dw4 |= (brw->wm.prog_data->first_curbe_grf_16 <<
GEN6_WM_DISPATCH_START_GRF_SHIFT_2);
- switch (brw->hiz.op) {
- case BRW_HIZ_OP_NONE:
- break;
- case BRW_HIZ_OP_DEPTH_CLEAR:
- dw4 |= GEN6_WM_DEPTH_CLEAR;
- break;
- case BRW_HIZ_OP_DEPTH_RESOLVE:
- dw4 |= GEN6_WM_DEPTH_RESOLVE;
- break;
- case BRW_HIZ_OP_HIZ_RESOLVE:
- dw4 |= GEN6_WM_HIERARCHICAL_DEPTH_RESOLVE;
- break;
- default:
- assert(0);
- break;
- }
-
dw5 |= (brw->max_wm_threads - 1) << GEN6_WM_MAX_THREADS_SHIFT;
/* CACHE_NEW_WM_PROG */
@@ -233,8 +216,7 @@ const struct brw_tracked_state gen6_wm_state = {
_NEW_PROGRAM_CONSTANTS |
_NEW_POLYGON),
.brw = (BRW_NEW_FRAGMENT_PROGRAM |
- BRW_NEW_BATCH |
- BRW_NEW_HIZ),
+ BRW_NEW_BATCH),
.cache = (CACHE_NEW_SAMPLER |
CACHE_NEW_WM_PROG)
},
diff --git a/src/mesa/drivers/dri/i965/gen7_clip_state.c b/src/mesa/drivers/dri/i965/gen7_clip_state.c
index 9be3ce9..c32cd98 100644
--- a/src/mesa/drivers/dri/i965/gen7_clip_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_clip_state.c
@@ -39,23 +39,6 @@ upload_clip_state(struct brw_context *brw)
/* BRW_NEW_FRAGMENT_PROGRAM */
const struct gl_fragment_program *fprog = brw->fragment_program;
- if (brw->hiz.op) {
- /* HiZ operations emit a rectangle primitive, which requires clipping to
- * be disabled. From page 10 of the Sandy Bridge PRM Volume 2 Part 1
- * Section 1.3 3D Primitives Overview:
- * RECTLIST:
- * Either the CLIP unit should be DISABLED, or the CLIP unit's Clip
- * Mode should be set to a value other than CLIPMODE_NORMAL.
- */
- BEGIN_BATCH(4);
- OUT_BATCH(_3DSTATE_CLIP << 16 | (4 - 2));
- OUT_BATCH(0);
- OUT_BATCH(0);
- OUT_BATCH(0);
- ADVANCE_BATCH();
- return;
- }
-
/* _NEW_BUFFERS */
bool render_to_fbo = brw->intel.ctx.DrawBuffer->Name != 0;
@@ -133,8 +116,7 @@ const struct brw_tracked_state gen7_clip_state = {
_NEW_LIGHT |
_NEW_TRANSFORM),
.brw = (BRW_NEW_CONTEXT |
- BRW_NEW_FRAGMENT_PROGRAM |
- BRW_NEW_HIZ),
+ BRW_NEW_FRAGMENT_PROGRAM),
.cache = 0
},
.emit = upload_clip_state,
diff --git a/src/mesa/drivers/dri/i965/gen7_sf_state.c b/src/mesa/drivers/dri/i965/gen7_sf_state.c
index da7ef81..b215af2 100644
--- a/src/mesa/drivers/dri/i965/gen7_sf_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_sf_state.c
@@ -149,8 +149,7 @@ const struct brw_tracked_state gen7_sbe_state = {
_NEW_PROGRAM |
_NEW_TRANSFORM),
.brw = (BRW_NEW_CONTEXT |
- BRW_NEW_FRAGMENT_PROGRAM |
- BRW_NEW_HIZ),
+ BRW_NEW_FRAGMENT_PROGRAM),
.cache = CACHE_NEW_VS_PROG
},
.emit = upload_sbe_state,
@@ -166,17 +165,8 @@ upload_sf_state(struct brw_context *brw)
/* _NEW_BUFFERS */
bool render_to_fbo = brw->intel.ctx.DrawBuffer->Name != 0;
- dw1 = GEN6_SF_STATISTICS_ENABLE;
-
- /* Enable viewport transform only if no HiZ operation is progress
- *
- * From page 11 of the SandyBridge PRM, Volume 2, Part 1, Section 1.3, "3D
- * Primitives Overview":
- * RECTLIST: Viewport Mapping must be DISABLED (as is typical with the
- * use of screen- space coordinates).
- */
- if (!brw->hiz.op)
- dw1 |= GEN6_SF_VIEWPORT_TRANSFORM_ENABLE;
+ dw1 = GEN6_SF_STATISTICS_ENABLE |
+ GEN6_SF_VIEWPORT_TRANSFORM_ENABLE;
/* _NEW_BUFFERS */
dw1 |= (brw_depthbuffer_format(brw) << GEN7_SF_DEPTH_BUFFER_SURFACE_FORMAT_SHIFT);
@@ -310,8 +300,7 @@ const struct brw_tracked_state gen7_sf_state = {
_NEW_SCISSOR |
_NEW_BUFFERS |
_NEW_POINT),
- .brw = (BRW_NEW_CONTEXT |
- BRW_NEW_HIZ),
+ .brw = BRW_NEW_CONTEXT,
.cache = CACHE_NEW_VS_PROG
},
.emit = upload_sf_state,
diff --git a/src/mesa/drivers/dri/i965/gen7_wm_state.c b/src/mesa/drivers/dri/i965/gen7_wm_state.c
index 32222f9..870590f 100644
--- a/src/mesa/drivers/dri/i965/gen7_wm_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_wm_state.c
@@ -49,23 +49,6 @@ upload_wm_state(struct brw_context *brw)
dw1 |= GEN7_WM_LINE_AA_WIDTH_1_0;
dw1 |= GEN7_WM_LINE_END_CAP_AA_WIDTH_0_5;
- switch (brw->hiz.op) {
- case BRW_HIZ_OP_NONE:
- break;
- case BRW_HIZ_OP_DEPTH_CLEAR:
- dw1 |= GEN7_WM_DEPTH_CLEAR;
- break;
- case BRW_HIZ_OP_DEPTH_RESOLVE:
- dw1 |= GEN7_WM_DEPTH_RESOLVE;
- break;
- case BRW_HIZ_OP_HIZ_RESOLVE:
- dw1 |= GEN7_WM_HIERARCHICAL_DEPTH_RESOLVE;
- break;
- default:
- assert(0);
- break;
- }
-
/* _NEW_LINE */
if (ctx->Line.StippleFlag)
dw1 |= GEN7_WM_LINE_STIPPLE_ENABLE;
@@ -106,7 +89,6 @@ const struct brw_tracked_state gen7_wm_state = {
.mesa = (_NEW_LINE | _NEW_LIGHT | _NEW_POLYGON |
_NEW_COLOR | _NEW_BUFFERS),
.brw = (BRW_NEW_FRAGMENT_PROGRAM |
- BRW_NEW_HIZ |
BRW_NEW_BATCH),
.cache = 0,
},
diff --git a/src/mesa/drivers/dri/i965/junk b/src/mesa/drivers/dri/i965/junk
new file mode 100644
index 0000000..e69de29
diff --git a/src/mesa/drivers/dri/intel/intel_batchbuffer.c b/src/mesa/drivers/dri/intel/intel_batchbuffer.c
index f4bc6b2..e0c3879 100644
--- a/src/mesa/drivers/dri/intel/intel_batchbuffer.c
+++ b/src/mesa/drivers/dri/intel/intel_batchbuffer.c
@@ -361,6 +361,33 @@ emit:
item->header = intel->batch.emit;
}
+
+/**
+ * \brief This flush must occur before toggling 3DSTATE_VS.VsFunctionEnable.
+ *
+ * From the BSpec, Volume 2a, Part 3 "Vertex Shader", Section
+ * 3DSTATE_VS, Field "VS Function Enable":
+ * A pipeline flush must be programmed prior to a 3DSTATE_VS command
+ * that causes the VS Function Enable to toggle. Pipeline flush can
+ * be executed by sending a PIPE_CONTROL command with CS stall bit
+ * set and a post sync operation.
+ */
+void
+intel_emit_vs_enable_flush(struct intel_context *intel)
+{
+ if (intel->gen != 6)
+ return;
+
+ BEGIN_BATCH(4);
+ OUT_BATCH(_3DSTATE_PIPE_CONTROL);
+ OUT_BATCH(PIPE_CONTROL_CS_STALL |
+ PIPE_CONTROL_WRITE_IMMEDIATE);
+ OUT_RELOC(intel->batch.workaround_bo,
+ I915_GEM_DOMAIN_INSTRUCTION, I915_GEM_DOMAIN_INSTRUCTION, 0);
+ OUT_BATCH(0); /* write data */
+ ADVANCE_BATCH();
+}
+
/**
* Restriction [DevSNB, DevIVB]:
*
diff --git a/src/mesa/drivers/dri/intel/intel_batchbuffer.h b/src/mesa/drivers/dri/intel/intel_batchbuffer.h
index e5e5bd4..f010cc4 100644
--- a/src/mesa/drivers/dri/intel/intel_batchbuffer.h
+++ b/src/mesa/drivers/dri/intel/intel_batchbuffer.h
@@ -40,6 +40,7 @@ bool intel_batchbuffer_emit_reloc_fenced(struct intel_context *intel,
uint32_t read_domains,
uint32_t write_domain,
uint32_t offset);
+void intel_emit_vs_enable_flush(struct intel_context *intel);
void intel_batchbuffer_emit_mi_flush(struct intel_context *intel);
void intel_emit_post_sync_nonzero_flush(struct intel_context *intel);
void intel_emit_depth_stall_flushes(struct intel_context *intel);
--
1.7.7.5
More information about the mesa-dev
mailing list