linux_dsm_epyc7002/include/linux/vmstat.h
Lisa Du 6e543d5780 mm: vmscan: fix do_try_to_free_pages() livelock
This patch is based on KOSAKI's work and I add a little more description,
please refer https://lkml.org/lkml/2012/6/14/74.

Currently, I found system can enter a state that there are lots of free
pages in a zone but only order-0 and order-1 pages which means the zone is
heavily fragmented, then high order allocation could make direct reclaim
path's long stall(ex, 60 seconds) especially in no swap and no compaciton
enviroment.  This problem happened on v3.4, but it seems issue still lives
in current tree, the reason is do_try_to_free_pages enter live lock:

kswapd will go to sleep if the zones have been fully scanned and are still
not balanced.  As kswapd thinks there's little point trying all over again
to avoid infinite loop.  Instead it changes order from high-order to
0-order because kswapd think order-0 is the most important.  Look at
73ce02e9 in detail.  If watermarks are ok, kswapd will go back to sleep
and may leave zone->all_unreclaimable =3D 0.  It assume high-order users
can still perform direct reclaim if they wish.

Direct reclaim continue to reclaim for a high order which is not a
COSTLY_ORDER without oom-killer until kswapd turn on
zone->all_unreclaimble= .  This is because to avoid too early oom-kill.
So it means direct_reclaim depends on kswapd to break this loop.

In worst case, direct-reclaim may continue to page reclaim forever when
kswapd sleeps forever until someone like watchdog detect and finally kill
the process.  As described in:
http://thread.gmane.org/gmane.linux.kernel.mm/103737

We can't turn on zone->all_unreclaimable from direct reclaim path because
direct reclaim path don't take any lock and this way is racy.  Thus this
patch removes zone->all_unreclaimable field completely and recalculates
zone reclaimable state every time.

Note: we can't take the idea that direct-reclaim see zone->pages_scanned
directly and kswapd continue to use zone->all_unreclaimable.  Because, it
is racy.  commit 929bea7c71 (vmscan: all_unreclaimable() use
zone->all_unreclaimable as a name) describes the detail.

[akpm@linux-foundation.org: uninline zone_reclaimable_pages() and zone_reclaimable()]
Cc: Aaditya Kumar <aaditya.kumar.30@gmail.com>
Cc: Ying Han <yinghan@google.com>
Cc: Nick Piggin <npiggin@gmail.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Bob Liu <lliubbo@gmail.com>
Cc: Neil Zhang <zhangwm@marvell.com>
Cc: Russell King - ARM Linux <linux@arm.linux.org.uk>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Lisa Du <cldu@marvell.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 15:58:01 -07:00

274 lines
7.2 KiB
C

#ifndef _LINUX_VMSTAT_H
#define _LINUX_VMSTAT_H
#include <linux/types.h>
#include <linux/percpu.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/vm_event_item.h>
#include <linux/atomic.h>
extern int sysctl_stat_interval;
#ifdef CONFIG_VM_EVENT_COUNTERS
/*
* Light weight per cpu counter implementation.
*
* Counters should only be incremented and no critical kernel component
* should rely on the counter values.
*
* Counters are handled completely inline. On many platforms the code
* generated will simply be the increment of a global address.
*/
struct vm_event_state {
unsigned long event[NR_VM_EVENT_ITEMS];
};
DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
static inline void __count_vm_event(enum vm_event_item item)
{
__this_cpu_inc(vm_event_states.event[item]);
}
static inline void count_vm_event(enum vm_event_item item)
{
this_cpu_inc(vm_event_states.event[item]);
}
static inline void __count_vm_events(enum vm_event_item item, long delta)
{
__this_cpu_add(vm_event_states.event[item], delta);
}
static inline void count_vm_events(enum vm_event_item item, long delta)
{
this_cpu_add(vm_event_states.event[item], delta);
}
extern void all_vm_events(unsigned long *);
extern void vm_events_fold_cpu(int cpu);
#else
/* Disable counters */
static inline void count_vm_event(enum vm_event_item item)
{
}
static inline void count_vm_events(enum vm_event_item item, long delta)
{
}
static inline void __count_vm_event(enum vm_event_item item)
{
}
static inline void __count_vm_events(enum vm_event_item item, long delta)
{
}
static inline void all_vm_events(unsigned long *ret)
{
}
static inline void vm_events_fold_cpu(int cpu)
{
}
#endif /* CONFIG_VM_EVENT_COUNTERS */
#ifdef CONFIG_NUMA_BALANCING
#define count_vm_numa_event(x) count_vm_event(x)
#define count_vm_numa_events(x, y) count_vm_events(x, y)
#else
#define count_vm_numa_event(x) do {} while (0)
#define count_vm_numa_events(x, y) do { (void)(y); } while (0)
#endif /* CONFIG_NUMA_BALANCING */
#define __count_zone_vm_events(item, zone, delta) \
__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
zone_idx(zone), delta)
/*
* Zone based page accounting with per cpu differentials.
*/
extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
static inline void zone_page_state_add(long x, struct zone *zone,
enum zone_stat_item item)
{
atomic_long_add(x, &zone->vm_stat[item]);
atomic_long_add(x, &vm_stat[item]);
}
static inline unsigned long global_page_state(enum zone_stat_item item)
{
long x = atomic_long_read(&vm_stat[item]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
static inline unsigned long zone_page_state(struct zone *zone,
enum zone_stat_item item)
{
long x = atomic_long_read(&zone->vm_stat[item]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
/*
* More accurate version that also considers the currently pending
* deltas. For that we need to loop over all cpus to find the current
* deltas. There is no synchronization so the result cannot be
* exactly accurate either.
*/
static inline unsigned long zone_page_state_snapshot(struct zone *zone,
enum zone_stat_item item)
{
long x = atomic_long_read(&zone->vm_stat[item]);
#ifdef CONFIG_SMP
int cpu;
for_each_online_cpu(cpu)
x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item];
if (x < 0)
x = 0;
#endif
return x;
}
extern unsigned long global_reclaimable_pages(void);
#ifdef CONFIG_NUMA
/*
* Determine the per node value of a stat item. This function
* is called frequently in a NUMA machine, so try to be as
* frugal as possible.
*/
static inline unsigned long node_page_state(int node,
enum zone_stat_item item)
{
struct zone *zones = NODE_DATA(node)->node_zones;
return
#ifdef CONFIG_ZONE_DMA
zone_page_state(&zones[ZONE_DMA], item) +
#endif
#ifdef CONFIG_ZONE_DMA32
zone_page_state(&zones[ZONE_DMA32], item) +
#endif
#ifdef CONFIG_HIGHMEM
zone_page_state(&zones[ZONE_HIGHMEM], item) +
#endif
zone_page_state(&zones[ZONE_NORMAL], item) +
zone_page_state(&zones[ZONE_MOVABLE], item);
}
extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
#else
#define node_page_state(node, item) global_page_state(item)
#define zone_statistics(_zl, _z, gfp) do { } while (0)
#endif /* CONFIG_NUMA */
#define add_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))
extern void inc_zone_state(struct zone *, enum zone_stat_item);
#ifdef CONFIG_SMP
void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
void __inc_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 inc_zone_page_state(struct page *, enum zone_stat_item);
void dec_zone_page_state(struct page *, enum zone_stat_item);
extern void inc_zone_state(struct zone *, enum zone_stat_item);
extern void __inc_zone_state(struct zone *, enum zone_stat_item);
extern void dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
void cpu_vm_stats_fold(int cpu);
void refresh_zone_stat_thresholds(void);
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
int calculate_pressure_threshold(struct zone *zone);
int calculate_normal_threshold(struct zone *zone);
void set_pgdat_percpu_threshold(pg_data_t *pgdat,
int (*calculate_pressure)(struct zone *));
#else /* CONFIG_SMP */
/*
* We do not maintain differentials in a single processor configuration.
* The functions directly modify the zone and global counters.
*/
static inline void __mod_zone_page_state(struct zone *zone,
enum zone_stat_item item, int delta)
{
zone_page_state_add(delta, zone, item);
}
static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
{
atomic_long_inc(&zone->vm_stat[item]);
atomic_long_inc(&vm_stat[item]);
}
static inline void __inc_zone_page_state(struct page *page,
enum zone_stat_item item)
{
__inc_zone_state(page_zone(page), item);
}
static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
{
atomic_long_dec(&zone->vm_stat[item]);
atomic_long_dec(&vm_stat[item]);
}
static inline void __dec_zone_page_state(struct page *page,
enum zone_stat_item item)
{
__dec_zone_state(page_zone(page), item);
}
/*
* We only use atomic operations to update counters. So there is no need to
* disable interrupts.
*/
#define inc_zone_page_state __inc_zone_page_state
#define dec_zone_page_state __dec_zone_page_state
#define mod_zone_page_state __mod_zone_page_state
#define set_pgdat_percpu_threshold(pgdat, callback) { }
static inline void refresh_cpu_vm_stats(int cpu) { }
static inline void refresh_zone_stat_thresholds(void) { }
static inline void cpu_vm_stats_fold(int cpu) { }
static inline void drain_zonestat(struct zone *zone,
struct per_cpu_pageset *pset) { }
#endif /* CONFIG_SMP */
static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages,
int migratetype)
{
__mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages);
if (is_migrate_cma(migratetype))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages);
}
extern const char * const vmstat_text[];
#endif /* _LINUX_VMSTAT_H */