The patch titled
mm: fix Committed_AS underfolow on large NR_CPUS environment
has been added to the -mm tree. Its filename is
mm-fix-committed_as-underfolow-on-large-nr_cpus-environment.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: mm: fix Committed_AS underfolow on large NR_CPUS environment
From: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
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@xxxxxxxxxxxxxxxxxx>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Eric B Munson <ebmunson@xxxxxxxxxx>
Cc: Mel Gorman <mel@xxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Cc: <stable@xxxxxxxxxx> [All kernel versions]
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/proc/meminfo.c | 2 -
include/linux/mman.h | 9 ++------
mm/mmap.c | 12 +++++-----
mm/nommu.c | 13 ++++++-----
mm/swap.c | 46 -----------------------------------------
5 files changed, 17 insertions(+), 65 deletions(-)
diff -puN fs/proc/meminfo.c~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment fs/proc/meminfo.c
--- a/fs/proc/meminfo.c~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment
+++ a/fs/proc/meminfo.c
@@ -35,7 +35,7 @@ static int meminfo_proc_show(struct seq_
#define K(x) ((x) << (PAGE_SHIFT - 10))
si_meminfo(&i);
si_swapinfo(&i);
- committed = atomic_long_read(&vm_committed_space);
+ committed = percpu_counter_read_positive(&vm_committed_as);
allowed = ((totalram_pages - hugetlb_total_pages())
* sysctl_overcommit_ratio / 100) + total_swap_pages;
diff -puN include/linux/mman.h~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment include/linux/mman.h
--- a/include/linux/mman.h~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment
+++ a/include/linux/mman.h
@@ -12,21 +12,18 @@
#ifdef __KERNEL__
#include <linux/mm.h>
+#include <linux/percpu_counter.h>
#include <asm/atomic.h>
extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
-extern atomic_long_t vm_committed_space;
+extern struct percpu_counter vm_committed_as;
-#ifdef CONFIG_SMP
-extern void vm_acct_memory(long pages);
-#else
static inline void vm_acct_memory(long pages)
{
- atomic_long_add(pages, &vm_committed_space);
+ percpu_counter_add(&vm_committed_as, pages);
}
-#endif
static inline void vm_unacct_memory(long pages)
{
diff -puN mm/mmap.c~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment mm/mmap.c
--- a/mm/mmap.c~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment
+++ a/mm/mmap.c
@@ -85,7 +85,7 @@ EXPORT_SYMBOL(vm_get_page_prot);
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
-atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
+struct percpu_counter vm_committed_as;
/*
* Check that a process has enough memory to allocate a new virtual
@@ -179,11 +179,7 @@ int __vm_enough_memory(struct mm_struct
if (mm)
allowed -= mm->total_vm / 32;
- /*
- * cast `allowed' as a signed long because vm_committed_space
- * sometimes has a negative value
- */
- if (atomic_long_read(&vm_committed_space) < (long)allowed)
+ if (percpu_counter_read_positive(&vm_committed_as) < allowed)
return 0;
error:
vm_unacct_memory(pages);
@@ -2481,4 +2477,8 @@ void mm_drop_all_locks(struct mm_struct
*/
void __init mmap_init(void)
{
+ int ret;
+
+ ret = percpu_counter_init(&vm_committed_as, 0);
+ VM_BUG_ON(ret);
}
diff -puN mm/nommu.c~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment mm/nommu.c
--- a/mm/nommu.c~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment
+++ a/mm/nommu.c
@@ -62,7 +62,7 @@ void *high_memory;
struct page *mem_map;
unsigned long max_mapnr;
unsigned long num_physpages;
-atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
+struct percpu_counter vm_committed_as;
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
@@ -463,6 +463,10 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
*/
void __init mmap_init(void)
{
+ int ret;
+
+ ret = percpu_counter_init(&vm_committed_as, 0);
+ VM_BUG_ON(ret);
vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
}
@@ -1847,12 +1851,9 @@ int __vm_enough_memory(struct mm_struct
if (mm)
allowed -= mm->total_vm / 32;
- /*
- * cast `allowed' as a signed long because vm_committed_space
- * sometimes has a negative value
- */
- if (atomic_long_read(&vm_committed_space) < (long)allowed)
+ if (percpu_counter_read_positive(&vm_committed_as) < allowed)
return 0;
+
error:
vm_unacct_memory(pages);
diff -puN mm/swap.c~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment mm/swap.c
--- a/mm/swap.c~mm-fix-committed_as-underfolow-on-large-nr_cpus-environment
+++ a/mm/swap.c
@@ -491,49 +491,6 @@ unsigned pagevec_lookup_tag(struct pagev
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
}
_
Patches currently in -mm which might be from kosaki.motohiro@xxxxxxxxxxxxxx are
memcg-fix-mem_cgroup_shrink_usage.patch
mm-fix-committed_as-underfolow-on-large-nr_cpus-environment.patch
procfs-make-errno-values-consistent-when-open-pident-vs-exit2-race-occurs.patch
vmscan-low-order-lumpy-reclaim-also-should-use-pageout_io_sync.patch
page-allocator-replace-__alloc_pages_internal-with-__alloc_pages_nodemask.patch
page-allocator-do-not-sanity-check-order-in-the-fast-path.patch
page-allocator-do-not-sanity-check-order-in-the-fast-path-fix.patch
page-allocator-do-not-check-numa-node-id-when-the-caller-knows-the-node-is-valid.patch
page-allocator-check-only-once-if-the-zonelist-is-suitable-for-the-allocation.patch
page-allocator-break-up-the-allocator-entry-point-into-fast-and-slow-paths.patch
page-allocator-move-check-for-disabled-anti-fragmentation-out-of-fastpath.patch
page-allocator-calculate-the-preferred-zone-for-allocation-only-once.patch
page-allocator-calculate-the-preferred-zone-for-allocation-only-once-fix.patch
page-allocator-calculate-the-migratetype-for-allocation-only-once.patch
page-allocator-calculate-the-alloc_flags-for-allocation-only-once.patch
page-allocator-remove-a-branch-by-assuming-__gfp_high-==-alloc_high.patch
page-allocator-inline-__rmqueue_smallest.patch
page-allocator-inline-buffered_rmqueue.patch
page-allocator-inline-__rmqueue_fallback.patch
page-allocator-do-not-call-get_pageblock_migratetype-more-than-necessary.patch
page-allocator-do-not-disable-interrupts-in-free_page_mlock.patch
page-allocator-do-not-setup-zonelist-cache-when-there-is-only-one-node.patch
page-allocator-do-not-check-for-compound-pages-during-the-page-allocator-sanity-checks.patch
page-allocator-use-allocation-flags-as-an-index-to-the-zone-watermark.patch
page-allocator-update-nr_free_pages-only-as-necessary.patch
page-allocator-update-nr_free_pages-only-as-necessary-fix.patch
page-allocator-get-the-pageblock-migratetype-without-disabling-interrupts.patch
page-allocator-use-a-pre-calculated-value-instead-of-num_online_nodes-in-fast-paths.patch
page-allocator-slab-use-nr_online_nodes-to-check-for-a-numa-platform.patch
page-allocator-move-free_page_mlock-to-page_allocc.patch
getrusage-fill-ru_maxrss-value.patch
softirq-introduce-statistics-for-softirq.patch
proc-export-statistics-for-softirq-to-proc.patch
proc-update-document-for-proc-softirqs-and-proc-stat.patch
memcg-add-file-based-rss-accounting.patch
fs-symlink-write_begin-allocation-context-fix-reiser4-fix.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
