vbo: cache/memoize the result of vbo_get_minmax_indices (v3)

Some games developers are unaware that an index buffer in a VBO still needs
to be read by the CPU if some varying data comes from a user pointer (unless
glDrawRangeElements and friends are used). This is particularly bad when
they tell us that the index buffer should live in VRAM.

This cache helps, e.g. lifting This War Of Mine (a particularly bad
offender) from under 10fps to slightly over 20fps on a Carrizo.

Note that there is nothing prohibiting a user from rendering from multiple
threads simultaneously with the same index buffer, hence the locking. (The
internal buffer map taken for the buffer still leads to a race, but at least
the locks are a move in the right direction.)

v2: disable the cache on USAGE_TEXTURE_BUFFER as well (Chris Forbes)

v3:
- use bool instead of GLboolean for MinMaxCacheDirty (Ian Romanick)
- replace the sticky USAGE_PERSISTENT_WRITE_MAP bit by a direct
  AccessFlags check

Reviewed-by: Chris Forbes <[email protected]> (v2)
Reviewed-by: Marek Olšák <[email protected]>

2 files changed, 15 insertions, 1 deletions

diff --git a/src/mesa/main/bufferobj.c b/src/mesa/main/bufferobj.c
index 2fcad6501ae..3d93cf826b2 100644
--- a/src/mesa/main/bufferobj.c
+++ b/src/mesa/main/bufferobj.c
@@ -458,6 +458,7 @@ _mesa_delete_buffer_object(struct gl_context *ctx,
 {
    (void) ctx;
 
+   vbo_delete_minmax_cache(bufObj);
    _mesa_align_free(bufObj->Data);
 
    /* assign strange values here to help w/ debugging */
@@ -1528,6 +1529,7 @@ _mesa_buffer_storage(struct gl_context *ctx, struct gl_buffer_object *bufObj,
 
    bufObj->Written = GL_TRUE;
    bufObj->Immutable = GL_TRUE;
+   bufObj->MinMaxCacheDirty = true;
 
    assert(ctx->Driver.BufferData);
    if (!ctx->Driver.BufferData(ctx, target, size, data, GL_DYNAMIC_DRAW,
@@ -1641,6 +1643,7 @@ _mesa_buffer_data(struct gl_context *ctx, struct gl_buffer_object *bufObj,
    FLUSH_VERTICES(ctx, _NEW_BUFFER_OBJECT);
 
    bufObj->Written = GL_TRUE;
+   bufObj->MinMaxCacheDirty = true;
 
 #ifdef VBO_DEBUG
    printf("glBufferDataARB(%u, sz %ld, from %p, usage 0x%x)\n",
@@ -1753,6 +1756,7 @@ _mesa_buffer_sub_data(struct gl_context *ctx, struct gl_buffer_object *bufObj,
    }
 
    bufObj->Written = GL_TRUE;
+   bufObj->MinMaxCacheDirty = true;
 
    assert(ctx->Driver.BufferSubData);
    ctx->Driver.BufferSubData(ctx, offset, size, data, bufObj);
@@ -1872,6 +1876,8 @@ _mesa_clear_buffer_sub_data(struct gl_context *ctx,
    if (size == 0)
       return;
 
+   bufObj->MinMaxCacheDirty = true;
+
    if (data == NULL) {
       /* clear to zeros, per the spec */
       ctx->Driver.ClearBufferSubData(ctx, offset, size,
@@ -2285,6 +2291,8 @@ _mesa_copy_buffer_sub_data(struct gl_context *ctx,
       }
    }
 
+   dst->MinMaxCacheDirty = true;
+
    ctx->Driver.CopyBufferSubData(ctx, src, dst, readOffset, writeOffset, size);
 }
 
@@ -2489,8 +2497,10 @@ _mesa_map_buffer_range(struct gl_context *ctx,
       assert(bufObj->Mappings[MAP_USER].AccessFlags == access);
    }
 
-   if (access & GL_MAP_WRITE_BIT)
+   if (access & GL_MAP_WRITE_BIT) {
       bufObj->Written = GL_TRUE;
+      bufObj->MinMaxCacheDirty = true;
+   }
 
 #ifdef VBO_DEBUG
    if (strstr(func, "Range") == NULL) { /* If not MapRange */
diff --git a/src/mesa/main/mtypes.h b/src/mesa/main/mtypes.h
index 4446d94b407..28aa781790b 100644
--- a/src/mesa/main/mtypes.h
+++ b/src/mesa/main/mtypes.h
@@ -1282,6 +1282,10 @@ struct gl_buffer_object
    GLuint NumMapBufferWriteCalls;
 
    struct gl_buffer_mapping Mappings[MAP_COUNT];
+
+   /** Memoization of min/max index computations for static index buffers */
+   struct hash_table *MinMaxCache;
+   bool MinMaxCacheDirty;
 };