[patch 54/58] mm: fix Committed_AS underflow on large NR_CPUS environment

[Greg KH <gregkh@suse.de>]

[-- Attachment #1: committed_as-for-2.6.29.2.patch --]
[-- Type: text/plain, Size: 6932 bytes --]

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

------------------

From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>

commit 00a62ce91e554198ef28234c91c36f850f5a3bc9 upstream

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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 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(-)

--- a/fs/proc/meminfo.c
+++ b/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;
 
--- a/include/linux/mman.h
+++ b/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)
 {
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -84,7 +84,7 @@ 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
@@ -178,11 +178,7 @@ 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);
@@ -2477,6 +2473,10 @@ 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);
 	vm_area_cachep = kmem_cache_create("vm_area_struct",
 			sizeof(struct vm_area_struct), 0,
 			SLAB_PANIC, NULL);
--- a/mm/nommu.c
+++ b/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_create("vm_region_jar",
 					  sizeof(struct vm_region), 0,
 					  SLAB_PANIC, NULL);
@@ -1849,12 +1853,9 @@ 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);
 
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -514,49 +514,6 @@ 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
  */
@@ -577,7 +534,4 @@ 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
 }