From 00a62ce91e554198ef28234c91c36f850f5a3bc9 Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Thu, 30 Apr 2009 15:08:51 -0700
Subject: mm: fix Committed_AS underflow on large NR_CPUS environment
The Committed_AS field can underflow in certain situations:
> # while true; do cat /proc/meminfo | grep _AS; sleep 1; done | uniq -c
> 1 Committed_AS: 18446744073709323392 kB
> 11 Committed_AS: 18446744073709455488 kB
> 6 Committed_AS: 35136 kB
> 5 Committed_AS: 18446744073709454400 kB
> 7 Committed_AS: 35904 kB
> 3 Committed_AS: 18446744073709453248 kB
> 2 Committed_AS: 34752 kB
> 9 Committed_AS: 18446744073709453248 kB
> 8 Committed_AS: 34752 kB
> 3 Committed_AS: 18446744073709320960 kB
> 7 Committed_AS: 18446744073709454080 kB
> 3 Committed_AS: 18446744073709320960 kB
> 5 Committed_AS: 18446744073709454080 kB
> 6 Committed_AS: 18446744073709320960 kB
Because NR_CPUS can be greater than 1000 and meminfo_proc_show() does
not check for underflow.
But NR_CPUS proportional isn't good calculation. In general,
possibility of lock contention is proportional to the number of online
cpus, not theorical maximum cpus (NR_CPUS).
The current kernel has generic percpu-counter stuff. using it is right
way. it makes code simplify and percpu_counter_read_positive() don't
make underflow issue.
Reported-by: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Eric B Munson <ebmunson@us.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: <stable@kernel.org> [All kernel versions]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
mm/swap.c | 46 ----------------------------------------------
1 file changed, 46 deletions(-)
(limited to 'mm/swap.c')
diff --git a/mm/swap.c b/mm/swap.c
index bede23c..cb29ae5 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -491,49 +491,6 @@ unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
EXPORT_SYMBOL(pagevec_lookup_tag);
-#ifdef CONFIG_SMP
-/*
- * We tolerate a little inaccuracy to avoid ping-ponging the counter between
- * CPUs
- */
-#define ACCT_THRESHOLD max(16, NR_CPUS * 2)
-
-static DEFINE_PER_CPU(long, committed_space);
-
-void vm_acct_memory(long pages)
-{
- long *local;
-
- preempt_disable();
- local = &__get_cpu_var(committed_space);
- *local += pages;
- if (*local > ACCT_THRESHOLD || *local < -ACCT_THRESHOLD) {
- atomic_long_add(*local, &vm_committed_space);
- *local = 0;
- }
- preempt_enable();
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-/* Drop the CPU's cached committed space back into the central pool. */
-static int cpu_swap_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
-{
- long *committed;
-
- committed = &per_cpu(committed_space, (long)hcpu);
- if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
- atomic_long_add(*committed, &vm_committed_space);
- *committed = 0;
- drain_cpu_pagevecs((long)hcpu);
- }
- return NOTIFY_OK;
-}
-#endif /* CONFIG_HOTPLUG_CPU */
-#endif /* CONFIG_SMP */
-
/*
* Perform any setup for the swap system
*/
@@ -554,7 +511,4 @@ void __init swap_setup(void)
* Right now other parts of the system means that we
* _really_ don't want to cluster much more
*/
-#ifdef CONFIG_HOTPLUG_CPU
- hotcpu_notifier(cpu_swap_callback, 0);
-#endif
}
--
cgit v1.1