AGP fix race condition between unmapping and freeing pages

With Andi's clflush fixup, we were getting hangs on server exit, flushing the
mappings after freeing each page helped.

This showed up a race condition where the pages after being freed could be
reused before the agp mappings had been flushed.  Flushing after each single
page is a bad thing for future drm work, so make the page destroy a two pass
unmapping all the pages, flushing the mappings, and then destroying the pages.

Signed-off-by: Dave Airlie <airlied@linux.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 4 insertions, 2 deletions

diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c
index 141ca176c397..d87961993ccf 100644
--- a/drivers/char/agp/intel-agp.c
+++ b/drivers/char/agp/intel-agp.c
@@ -400,9 +400,11 @@ static void intel_i810_free_by_type(struct agp_memory *curr)
                 if (curr->page_count == 4)
                         i8xx_destroy_pages(gart_to_virt(curr->memory[0]));
                 else {
-                        agp_bridge->driver->agp_destroy_page(
-                                 gart_to_virt(curr->memory[0]));
+                        agp_bridge->driver->agp_destroy_page(gart_to_virt(curr->memory[0]),
+                                                             AGP_PAGE_DESTROY_UNMAP);
                         global_flush_tlb();
+                        agp_bridge->driver->agp_destroy_page(gart_to_virt(curr->memory[0]),
+                                                             AGP_PAGE_DESTROY_FREE);
                 }
                 agp_free_page_array(curr);
         }