mm/vmstat: fix overflow in mod_zone_page_state()

mod_zone_page_state() takes a "delta" integer argument.  delta contains
the number of pages that should be added or subtracted from a struct
zone's vm_stat field.

If a zone is larger than 8TB this will cause overflows.  E.g.  for a
zone with a size slightly larger than 8TB the line

    mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);

in mm/page_alloc.c:free_area_init_core() will result in a negative
result for the NR_ALLOC_BATCH entry within the zone's vm_stat, since 8TB
contain 0x8xxxxxxx pages which will be sign extended to a negative
value.

Fix this by changing the delta argument to long type.

This could fix an early boot problem seen on s390, where we have a 9TB
system with only one node.  ZONE_DMA contains 2GB and ZONE_NORMAL the
rest.  The system is trying to allocate a GFP_DMA page but ZONE_DMA is
completely empty, so it tries to reclaim pages in an endless loop.

This was seen on a heavily patched 3.10 kernel.  One possible
explaination seem to be the overflows caused by mod_zone_page_state().
Unfortunately I did not have the chance to verify that this patch
actually fixes the problem, since I don't have access to the system
right now.  However the overflow problem does exist anyway.

Given the description that a system with slightly less than 8TB does
work, this seems to be a candidate for the observed problem.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Heiko Carstens 2015-12-29 14:54:32 -08:00 committed by Linus Torvalds
parent cc28d6d80f
commit 6cdb18ad98
2 changed files with 8 additions and 8 deletions

View File

@ -176,11 +176,11 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
#define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d)) #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
#ifdef CONFIG_SMP #ifdef CONFIG_SMP
void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int); void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long);
void __inc_zone_page_state(struct page *, enum zone_stat_item); void __inc_zone_page_state(struct page *, enum zone_stat_item);
void __dec_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item);
void mod_zone_page_state(struct zone *, enum zone_stat_item, int); void mod_zone_page_state(struct zone *, enum zone_stat_item, long);
void inc_zone_page_state(struct page *, enum zone_stat_item); void inc_zone_page_state(struct page *, enum zone_stat_item);
void dec_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item);
@ -205,7 +205,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
* The functions directly modify the zone and global counters. * The functions directly modify the zone and global counters.
*/ */
static inline void __mod_zone_page_state(struct zone *zone, static inline void __mod_zone_page_state(struct zone *zone,
enum zone_stat_item item, int delta) enum zone_stat_item item, long delta)
{ {
zone_page_state_add(delta, zone, item); zone_page_state_add(delta, zone, item);
} }

View File

@ -219,7 +219,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
* particular counter cannot be updated from interrupt context. * particular counter cannot be updated from interrupt context.
*/ */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
int delta) long delta)
{ {
struct per_cpu_pageset __percpu *pcp = zone->pageset; struct per_cpu_pageset __percpu *pcp = zone->pageset;
s8 __percpu *p = pcp->vm_stat_diff + item; s8 __percpu *p = pcp->vm_stat_diff + item;
@ -318,8 +318,8 @@ EXPORT_SYMBOL(__dec_zone_page_state);
* 1 Overstepping half of threshold * 1 Overstepping half of threshold
* -1 Overstepping minus half of threshold * -1 Overstepping minus half of threshold
*/ */
static inline void mod_state(struct zone *zone, static inline void mod_state(struct zone *zone, enum zone_stat_item item,
enum zone_stat_item item, int delta, int overstep_mode) long delta, int overstep_mode)
{ {
struct per_cpu_pageset __percpu *pcp = zone->pageset; struct per_cpu_pageset __percpu *pcp = zone->pageset;
s8 __percpu *p = pcp->vm_stat_diff + item; s8 __percpu *p = pcp->vm_stat_diff + item;
@ -357,7 +357,7 @@ static inline void mod_state(struct zone *zone,
} }
void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
int delta) long delta)
{ {
mod_state(zone, item, delta, 0); mod_state(zone, item, delta, 0);
} }
@ -384,7 +384,7 @@ EXPORT_SYMBOL(dec_zone_page_state);
* Use interrupt disable to serialize counter updates * Use interrupt disable to serialize counter updates
*/ */
void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
int delta) long delta)
{ {
unsigned long flags; unsigned long flags;