i965: Add support for GL_ARB_buffer_storage.

It turns out we can allow COHERENT storage/mappings all the time,
regardless of LLC vs non-LLC.  It just means never using temporary
mappings to avoid GPU stalls, and on non-LLC we have to use the GTT intead
of CPU mappings.  If we were to use CPU maps on non-LLC (which might be
useful if apps end up using buffer_storage on PBO reads, to avoid WC read
slowness), those would be PERSISTENT but not COHERENT, but doing that
would require us driving the clflushes from userspace somehow.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

3 files changed, 9 insertions, 3 deletions

diff --git a/docs/GL3.txt b/docs/GL3.txt
index 9758dcca24e..b7e4c876499 100644
--- a/docs/GL3.txt
+++ b/docs/GL3.txt
@@ -170,7 +170,7 @@ GL 4.4:
 
   GLSL 4.4                                             not started
   GL_MAX_VERTEX_ATTRIB_STRIDE                          not started
-  GL_ARB_buffer_storage                                DONE (r300, r600, radeonsi)
+  GL_ARB_buffer_storage                                DONE (i965, r300, r600, radeonsi)
   GL_ARB_clear_texture                                 not started
   GL_ARB_enhanced_layouts                              not started
   GL_ARB_multi_bind                                    started (Fredrik Höglund)
diff --git a/src/mesa/drivers/dri/i965/intel_buffer_objects.c b/src/mesa/drivers/dri/i965/intel_buffer_objects.c
index 260308a80a2..96dacde04fb 100644
--- a/src/mesa/drivers/dri/i965/intel_buffer_objects.c
+++ b/src/mesa/drivers/dri/i965/intel_buffer_objects.c
@@ -401,8 +401,12 @@ intel_bufferobj_map_range(struct gl_context * ctx,
     * doesn't require the current contents of that range, make a new
     * BO, and we'll copy what they put in there out at unmap or
     * FlushRange time.
+    *
+    * That is, unless they're looking for a persistent mapping -- we would
+    * need to do blits in the MemoryBarrier call, and it's easier to just do a
+    * GPU stall and do a mapping.
     */
-   if (!(access & GL_MAP_UNSYNCHRONIZED_BIT) &&
+   if (!(access & (GL_MAP_UNSYNCHRONIZED_BIT | GL_MAP_PERSISTENT_BIT)) &&
        (access & GL_MAP_INVALIDATE_RANGE_BIT) &&
        drm_intel_bo_busy(intel_obj->buffer)) {
       /* Ensure that the base alignment of the allocation meets the alignment
@@ -429,7 +433,8 @@ intel_bufferobj_map_range(struct gl_context * ctx,
 
    if (access & GL_MAP_UNSYNCHRONIZED_BIT)
       drm_intel_gem_bo_map_unsynchronized(intel_obj->buffer);
-   else if (!brw->has_llc && !(access & GL_MAP_READ_BIT)) {
+   else if (!brw->has_llc && (!(access & GL_MAP_READ_BIT) ||
+                              (access & GL_MAP_PERSISTENT_BIT))) {
       drm_intel_gem_bo_map_gtt(intel_obj->buffer);
       intel_bufferobj_mark_inactive(intel_obj);
    } else {
diff --git a/src/mesa/drivers/dri/i965/intel_extensions.c b/src/mesa/drivers/dri/i965/intel_extensions.c
index 5094c2b1aed..2a6875836cf 100644
--- a/src/mesa/drivers/dri/i965/intel_extensions.c
+++ b/src/mesa/drivers/dri/i965/intel_extensions.c
@@ -162,6 +162,7 @@ intelInitExtensions(struct gl_context *ctx)
 
    assert(brw->gen >= 4);
 
+   ctx->Extensions.ARB_buffer_storage = true;
    ctx->Extensions.ARB_depth_buffer_float = true;
    ctx->Extensions.ARB_depth_clamp = true;
    ctx->Extensions.ARB_depth_texture = true;