[patch 03/32] x86-64: Always flush all pages in change_page_attr

[Chris Wright]

-stable review patch.  If anyone has any objections, please let us know.
---------------------

From: Andi Kleen <ak@xxxxxxx>

change_page_attr on x86-64 only flushed the TLB for pages that got
reverted. That's not correct: it has to be flushed in all cases.

This bug was added in some earlier changes.

Just flush all pages for now.

This could be done more efficiently, but for this late in the release
this seem to be the best fix.

Pointed out by Jan Beulich

Signed-off-by: Andi Kleen <ak@xxxxxxx>
Signed-off-by: Chris Wright <chrisw@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>
---
 arch/x86_64/mm/pageattr.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- linux-2.6.20.13.orig/arch/x86_64/mm/pageattr.c
+++ linux-2.6.20.13/arch/x86_64/mm/pageattr.c
@@ -81,8 +81,8 @@ static void flush_kernel_map(void *arg)
 		void *adr = page_address(pg);
 		if (cpu_has_clflush)
 			cache_flush_page(adr);
-		__flush_tlb_one(adr);
 	}
+	__flush_tlb_all();
 }
 
 static inline void flush_map(struct list_head *l)

-- 
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/