i965: Completely annotate the batch bo when aub dumping.

Previously, when the environment variable INTEL_DEBUG=aub was set,
mesa would simply instruct DRM to start dumping data to an .aub file,
but we would not provide DRM with any information about the format of
the data in various buffers.  As a result, a lot of the data in the
generate .aub file would be unannotated, making further data analysis
difficult.

This patch causes the entire contents of each batch buffer to be
annotated using the data in brw->state_batch_list (which was
previously used only to annotate the output of INTEL_DEBUG=bat).  This
includes data that was allocated by brw_state_batch, such as binding
tables, surface and sampler states, depth/stencil state, and so on.

The new annotation mechanism requires DRM version 2.4.34.

Reviewed-by: Eric Anholt <[email protected]>

6 files changed, 117 insertions, 27 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_context.h b/src/mesa/drivers/dri/i965/brw_context.h
index a7684166949..251893f8a04 100644
--- a/src/mesa/drivers/dri/i965/brw_context.h
+++ b/src/mesa/drivers/dri/i965/brw_context.h
@@ -193,33 +193,71 @@ struct brw_state_flags {
    GLuint cache;
 };
 
+#define AUB_TRACE_TYPE_MASK		0x0000ff00
+#define AUB_TRACE_TYPE_NOTYPE		(0 << 8)
+#define AUB_TRACE_TYPE_BATCH		(1 << 8)
+#define AUB_TRACE_TYPE_VERTEX_BUFFER	(5 << 8)
+#define AUB_TRACE_TYPE_2D_MAP		(6 << 8)
+#define AUB_TRACE_TYPE_CUBE_MAP		(7 << 8)
+#define AUB_TRACE_TYPE_VOLUME_MAP	(9 << 8)
+#define AUB_TRACE_TYPE_1D_MAP		(10 << 8)
+#define AUB_TRACE_TYPE_CONSTANT_BUFFER	(11 << 8)
+#define AUB_TRACE_TYPE_CONSTANT_URB	(12 << 8)
+#define AUB_TRACE_TYPE_INDEX_BUFFER	(13 << 8)
+#define AUB_TRACE_TYPE_GENERAL		(14 << 8)
+#define AUB_TRACE_TYPE_SURFACE		(15 << 8)
+
+/**
+ * state_struct_type enum values are encoded with the top 16 bits representing
+ * the type to be delivered to the .aub file, and the bottom 16 bits
+ * representing the subtype.  This macro performs the encoding.
+ */
+#define ENCODE_SS_TYPE(type, subtype) (((type) << 16) | (subtype))
+
 enum state_struct_type {
-   AUB_TRACE_VS_STATE =			1,
-   AUB_TRACE_GS_STATE =			2,
-   AUB_TRACE_CLIP_STATE =		3,
-   AUB_TRACE_SF_STATE =			4,
-   AUB_TRACE_WM_STATE =			5,
-   AUB_TRACE_CC_STATE =			6,
-   AUB_TRACE_CLIP_VP_STATE =		7,
-   AUB_TRACE_SF_VP_STATE =		8,
-   AUB_TRACE_CC_VP_STATE =		0x9,
-   AUB_TRACE_SAMPLER_STATE =		0xa,
-   AUB_TRACE_KERNEL_INSTRUCTIONS =	0xb,
-   AUB_TRACE_SCRATCH_SPACE =		0xc,
-   AUB_TRACE_SAMPLER_DEFAULT_COLOR =    0xd,
-
-   AUB_TRACE_SCISSOR_STATE =		0x15,
-   AUB_TRACE_BLEND_STATE =		0x16,
-   AUB_TRACE_DEPTH_STENCIL_STATE =	0x17,
-
-   /* Not written to .aub files the same way the structures above are. */
-   AUB_TRACE_NO_TYPE =			0x100,
-   AUB_TRACE_BINDING_TABLE =		0x101,
-   AUB_TRACE_SURFACE_STATE =		0x102,
-   AUB_TRACE_VS_CONSTANTS =		0x103,
-   AUB_TRACE_WM_CONSTANTS =		0x104,
+   AUB_TRACE_VS_STATE =			ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 1),
+   AUB_TRACE_GS_STATE =			ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 2),
+   AUB_TRACE_CLIP_STATE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 3),
+   AUB_TRACE_SF_STATE =			ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 4),
+   AUB_TRACE_WM_STATE =			ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 5),
+   AUB_TRACE_CC_STATE =			ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 6),
+   AUB_TRACE_CLIP_VP_STATE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 7),
+   AUB_TRACE_SF_VP_STATE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 8),
+   AUB_TRACE_CC_VP_STATE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 0x9),
+   AUB_TRACE_SAMPLER_STATE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 0xa),
+   AUB_TRACE_KERNEL_INSTRUCTIONS =	ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 0xb),
+   AUB_TRACE_SCRATCH_SPACE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 0xc),
+   AUB_TRACE_SAMPLER_DEFAULT_COLOR =    ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 0xd),
+
+   AUB_TRACE_SCISSOR_STATE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 0x15),
+   AUB_TRACE_BLEND_STATE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 0x16),
+   AUB_TRACE_DEPTH_STENCIL_STATE =	ENCODE_SS_TYPE(AUB_TRACE_TYPE_GENERAL, 0x17),
+
+   AUB_TRACE_VERTEX_BUFFER =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_VERTEX_BUFFER, 0),
+   AUB_TRACE_BINDING_TABLE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_SURFACE, 0x100),
+   AUB_TRACE_SURFACE_STATE =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_SURFACE, 0x200),
+   AUB_TRACE_VS_CONSTANTS =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_CONSTANT_BUFFER, 0),
+   AUB_TRACE_WM_CONSTANTS =		ENCODE_SS_TYPE(AUB_TRACE_TYPE_CONSTANT_BUFFER, 1),
 };
 
+/**
+ * Decode a state_struct_type value to determine the type that should be
+ * stored in the .aub file.
+ */
+static inline uint32_t AUB_TRACE_TYPE(enum state_struct_type ss_type)
+{
+   return (ss_type & 0xFFFF0000) >> 16;
+}
+
+/**
+ * Decode a state_struct_type value to determine the subtype that should be
+ * stored in the .aub file.
+ */
+static inline uint32_t AUB_TRACE_SUBTYPE(enum state_struct_type ss_type)
+{
+   return ss_type & 0xFFFF;
+}
+
 /** Subclass of Mesa vertex program */
 struct brw_vertex_program {
    struct gl_vertex_program program;
@@ -1040,6 +1078,7 @@ void brw_emit_query_end(struct brw_context *brw);
  * brw_state_dump.c
  */
 void brw_debug_batch(struct intel_context *intel);
+void brw_annotate_aub(struct intel_context *intel);
 
 /*======================================================================
  * brw_tex.c
diff --git a/src/mesa/drivers/dri/i965/brw_state_batch.c b/src/mesa/drivers/dri/i965/brw_state_batch.c
index 81d034ce822..84683511066 100644
--- a/src/mesa/drivers/dri/i965/brw_state_batch.c
+++ b/src/mesa/drivers/dri/i965/brw_state_batch.c
@@ -57,6 +57,52 @@ brw_track_state_batch(struct brw_context *brw,
 }
 
 /**
+ * Convenience function to populate a single drm_intel_aub_annotation data
+ * structure.
+ */
+static inline void
+make_annotation(drm_intel_aub_annotation *annotation, uint32_t type,
+                uint32_t subtype, uint32_t ending_offset)
+{
+   annotation->type = type;
+   annotation->subtype = subtype;
+   annotation->ending_offset = ending_offset;
+}
+
+/**
+ * Generate a set of aub file annotations for the current batch buffer, and
+ * deliver them to DRM.
+ *
+ * The "used" section of the batch buffer (the portion containing batch
+ * commands) is annotated with AUB_TRACE_TYPE_BATCH.  The remainder of the
+ * batch buffer (which contains data structures pointed to by batch commands)
+ * is annotated according to the type of each data structure.
+ */
+void
+brw_annotate_aub(struct intel_context *intel)
+{
+   struct brw_context *brw = brw_context(&intel->ctx);
+
+   unsigned annotation_count = 2 * brw->state_batch_count + 1;
+   drm_intel_aub_annotation annotations[annotation_count];
+   int a = 0;
+   make_annotation(&annotations[a++], AUB_TRACE_TYPE_BATCH, 0,
+                   4*intel->batch.used);
+   for (int i = brw->state_batch_count; i-- > 0; ) {
+      uint32_t type = brw->state_batch_list[i].type;
+      uint32_t start_offset = brw->state_batch_list[i].offset;
+      uint32_t end_offset = start_offset + brw->state_batch_list[i].size;
+      make_annotation(&annotations[a++], AUB_TRACE_TYPE_NOTYPE, 0,
+                      start_offset);
+      make_annotation(&annotations[a++], AUB_TRACE_TYPE(type),
+                      AUB_TRACE_SUBTYPE(type), end_offset);
+   }
+   assert(a == annotation_count);
+   drm_intel_bufmgr_gem_set_aub_annotations(intel->batch.bo, annotations,
+                                            annotation_count);
+}
+
+/**
  * Allocates a block of space in the batchbuffer for indirect state.
  *
  * We don't want to allocate separate BOs for every bit of indirect
@@ -95,7 +141,7 @@ brw_state_batch(struct brw_context *brw,
 
    batch->state_batch_offset = offset;
 
-   if (unlikely(INTEL_DEBUG & DEBUG_BATCH))
+   if (unlikely(INTEL_DEBUG & (DEBUG_BATCH | DEBUG_AUB)))
       brw_track_state_batch(brw, type, offset, size);
 
    *out_offset = offset;
diff --git a/src/mesa/drivers/dri/i965/brw_vtbl.c b/src/mesa/drivers/dri/i965/brw_vtbl.c
index 733193425d3..d05b602ab8e 100644
--- a/src/mesa/drivers/dri/i965/brw_vtbl.c
+++ b/src/mesa/drivers/dri/i965/brw_vtbl.c
@@ -234,6 +234,7 @@ void brwInitVtbl( struct brw_context *brw )
    brw->intel.vtbl.destroy = brw_destroy_context;
    brw->intel.vtbl.update_draw_buffer = brw_update_draw_buffer;
    brw->intel.vtbl.debug_batch = brw_debug_batch;
+   brw->intel.vtbl.annotate_aub = brw_annotate_aub;
    brw->intel.vtbl.render_target_supported = brw_render_target_supported;
    brw->intel.vtbl.is_hiz_depth_format = brw_is_hiz_depth_format;
 
diff --git a/src/mesa/drivers/dri/i965/gen6_blorp.cpp b/src/mesa/drivers/dri/i965/gen6_blorp.cpp
index 6db8f40c33b..8eed9dca01e 100644
--- a/src/mesa/drivers/dri/i965/gen6_blorp.cpp
+++ b/src/mesa/drivers/dri/i965/gen6_blorp.cpp
@@ -183,7 +183,7 @@ gen6_blorp_emit_vertices(struct brw_context *brw,
          /* v2 */ 0, 0, 0, 0,     params->x0, params->y0, 0, 1,
       };
 
-      vertex_data = (float *) brw_state_batch(brw, AUB_TRACE_NO_TYPE,
+      vertex_data = (float *) brw_state_batch(brw, AUB_TRACE_VERTEX_BUFFER,
                                               GEN6_BLORP_VBO_SIZE, 32,
                                               &vertex_offset);
       memcpy(vertex_data, vertices, GEN6_BLORP_VBO_SIZE);
diff --git a/src/mesa/drivers/dri/intel/intel_batchbuffer.c b/src/mesa/drivers/dri/intel/intel_batchbuffer.c
index d10e00867eb..76a69f7c88d 100644
--- a/src/mesa/drivers/dri/intel/intel_batchbuffer.c
+++ b/src/mesa/drivers/dri/intel/intel_batchbuffer.c
@@ -185,9 +185,12 @@ do_flush_locked(struct intel_context *intel)
       if (batch->needs_sol_reset)
 	 flags |= I915_EXEC_GEN7_SOL_RESET;
 
-      if (ret == 0)
+      if (ret == 0) {
+         if (unlikely(INTEL_DEBUG & DEBUG_AUB) && intel->vtbl.annotate_aub)
+            intel->vtbl.annotate_aub(intel);
 	 ret = drm_intel_bo_mrb_exec(batch->bo, 4*batch->used, NULL, 0, 0,
 				     flags);
+      }
    }
 
    if (unlikely(INTEL_DEBUG & DEBUG_BATCH))
diff --git a/src/mesa/drivers/dri/intel/intel_context.h b/src/mesa/drivers/dri/intel/intel_context.h
index 065f1d6d01a..d064f37c9c5 100644
--- a/src/mesa/drivers/dri/intel/intel_context.h
+++ b/src/mesa/drivers/dri/intel/intel_context.h
@@ -177,6 +177,7 @@ struct intel_context
       void (*assert_not_dirty) (struct intel_context *intel);
 
       void (*debug_batch)(struct intel_context *intel);
+      void (*annotate_aub)(struct intel_context *intel);
       bool (*render_target_supported)(struct intel_context *intel,
 				      struct gl_renderbuffer *rb);