Fix race in the accessed/dirty bit handlers

From: Christoph Lameter <clameter_at_engr.sgi.com>
Date: 2006-03-08 14:05:32
A pte may be zapped by the swapper, exiting process, unmapping or page
migration while the accessed or dirty bit handers are about to run. In that
case the accessed bit or dirty is set on an zeroed pte which leads the VM to
conclude that this is a swap pte. This may lead to

- Messages from the vm like

swap_free: Bad swap file entry 4000000000000000

- Processes being aborted

swap_dup: Bad swap file entry 4000000000000000
VM: killing process ....

Page migration is particular suitable for the creation of this race since
it needs to remove and restore page table entries.

The fix here is to check for the present bit and simply not update
the pte if the page is not present anymore. If the page is not present
then the fault handler should run next which will take care of the problem
by bringing the page back and then mark the page dirty or move it onto the
active list.

Signed-off-by: Christoph Lameter <clameter@sgi.com>

Index: linux-2.6.16-rc5-mm3/arch/ia64/kernel/ivt.S
===================================================================
--- linux-2.6.16-rc5-mm3.orig/arch/ia64/kernel/ivt.S	2006-03-07 09:17:22.000000000 -0800
+++ linux-2.6.16-rc5-mm3/arch/ia64/kernel/ivt.S	2006-03-07 18:53:11.000000000 -0800
@@ -561,11 +561,12 @@ ENTRY(dirty_bit)
 	;;					// avoid RAW on r18
 	mov ar.ccv=r18				// set compare value for cmpxchg
 	or r25=_PAGE_D|_PAGE_A,r18		// set the dirty and accessed bits
+	tbit.z p7,p6 = r18,_PAGE_P_BIT		// Check present bit
 	;;
-	cmpxchg8.acq r26=[r17],r25,ar.ccv
+(p6)	cmpxchg8.acq r26=[r17],r25,ar.ccv	// Only update if page is present
 	mov r24=PAGE_SHIFT<<2
 	;;
-	cmp.eq p6,p7=r26,r18
+(p6)	cmp.eq p6,p7=r26,r18			// Only compare if page is present
 	;;
 (p6)	itc.d r25				// install updated PTE
 	;;
@@ -626,11 +627,12 @@ ENTRY(iaccess_bit)
 	;;
 	mov ar.ccv=r18				// set compare value for cmpxchg
 	or r25=_PAGE_A,r18			// set the accessed bit
+	tbit.z p7,p6 = r18,_PAGE_P_BIT	 	// Check present bit
 	;;
-	cmpxchg8.acq r26=[r17],r25,ar.ccv
+(p6)	cmpxchg8.acq r26=[r17],r25,ar.ccv	// Only if page present
 	mov r24=PAGE_SHIFT<<2
 	;;
-	cmp.eq p6,p7=r26,r18
+(p6)	cmp.eq p6,p7=r26,r18			// Only if page present
 	;;
 (p6)	itc.i r25				// install updated PTE
 	;;
@@ -680,11 +682,12 @@ ENTRY(daccess_bit)
 	;;					// avoid RAW on r18
 	mov ar.ccv=r18				// set compare value for cmpxchg
 	or r25=_PAGE_A,r18			// set the dirty bit
+	tbit.z p7,p6 = r18,_PAGE_P_BIT		// Check present bit
 	;;
-	cmpxchg8.acq r26=[r17],r25,ar.ccv
+(p6)	cmpxchg8.acq r26=[r17],r25,ar.ccv	// Only if page is present
 	mov r24=PAGE_SHIFT<<2
 	;;
-	cmp.eq p6,p7=r26,r18
+(p6)	cmp.eq p6,p7=r26,r18			// Only if page is present
 	;;
 (p6)	itc.d r25				// install updated PTE
 	/*
-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Received on Wed Mar 08 14:06:48 2006

This archive was generated by hypermail 2.1.8 : 2006-03-08 14:06:58 EST