x86: work around PAGE_KERNEL_WC not getting WC in iomap_atomic_prot_pfn.

In the absence of PAT, PAGE_KERNEL_WC ends up mapping to a memory type that
gets UC behavior even in the presence of a WC MTRR covering the area in
question.  By swapping to PAGE_KERNEL_UC_MINUS, we can get the actual
behavior the caller wanted (WC if you can manage it, UC otherwise).

This recovers the 40% performance improvement of using WC in the DRM
to upload vertex data.

Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index d0151d8ce452329ca8c4b042658437a48731f397..ca53224fc56c8eeb1c57feccdccf93e09c25b2cb 100644 (file)
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -17,6 +17,7 @@
  */
 
 #include <asm/iomap.h>
+#include <asm/pat.h>
 #include <linux/module.h>
 
 /* Map 'pfn' using fixed map 'type' and protections 'prot'
@@ -29,6 +30,15 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 
        pagefault_disable();
 
+       /*
+        * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS.
+        * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the
+        * MTRR is UC or WC.  UC_MINUS gets the real intention, of the
+        * user, which is "WC if the MTRR is WC, UC if you can't do that."
+        */
+       if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
+               prot = PAGE_KERNEL_UC_MINUS;
+
        idx = type + KM_TYPE_NR*smp_processor_id();
        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
        set_pte(kmap_pte-idx, pfn_pte(pfn, prot));