Files
android_kernel_xiaomi_sm8450/include/linux/vmstat.h
Jaewon Kim 1f318a9b0d mm/vmscan: count layzfree pages and fix nr_isolated_* mismatch
Fix an nr_isolate_* mismatch problem between cma and dirty lazyfree pages.

If try_to_unmap_one is used for reclaim and it detects a dirty lazyfree
page, then the lazyfree page is changed to a normal anon page having
SwapBacked by commit 802a3a92ad ("mm: reclaim MADV_FREE pages").  Even
with the change, reclaim context correctly counts isolated files because
it uses is_file_lru to distinguish file.  And the change to anon is not
happened if try_to_unmap_one is used for migration.  So migration context
like compaction also correctly counts isolated files even though it uses
page_is_file_lru insted of is_file_lru.  Recently page_is_file_cache was
renamed to page_is_file_lru by commit 9de4f22a60 ("mm: code cleanup for
MADV_FREE").

But the nr_isolate_* mismatch problem happens on cma alloc.  There is
reclaim_clean_pages_from_list which is being used only by cma.  It was
introduced by commit 02c6de8d75 ("mm: cma: discard clean pages during
contiguous allocation instead of migration") to reclaim clean file pages
without migration.  The cma alloc uses both reclaim_clean_pages_from_list
and migrate_pages, and it uses page_is_file_lru to count isolated files.
If there are dirty lazyfree pages allocated from cma memory region, the
pages are counted as isolated file at the beginging but are counted as
isolated anon after finished.

Mem-Info:
Node 0 active_anon:3045904kB inactive_anon:611448kB active_file:14892kB inactive_file:205636kB unevictable:10416kB isolated(anon):0kB isolated(file):37664kB mapped:630216kB dirty:384kB writeback:0kB shmem:42576kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no

Like log above, there were too much isolated files, 37664kB, which
triggers too_many_isolated in reclaim even when there is no actually
isolated file in system wide.  It could be reproducible by running two
programs, writing on MADV_FREE page and doing cma alloc, respectively.
Although isolated anon is 0, I found that the internal value of isolated
anon was the negative value of isolated file.

Fix this by compensating the isolated count for both LRU lists.  Count
non-discarded lazyfree pages in shrink_page_list, then compensate the
counted number in reclaim_clean_pages_from_list.

Reported-by: Yong-Taek Lee <ytk.lee@samsung.com>
Suggested-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Jaewon Kim <jaewon31.kim@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Shaohua Li <shli@fb.com>
Link: http://lkml.kernel.org/r/20200426011718.30246-1-jaewon31.kim@samsung.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-03 20:09:47 -07:00

436 lines
12 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_VMSTAT_H
#define _LINUX_VMSTAT_H
#include <linux/types.h>
#include <linux/percpu.h>
#include <linux/mmzone.h>
#include <linux/vm_event_item.h>
#include <linux/atomic.h>
#include <linux/static_key.h>
extern int sysctl_stat_interval;
#ifdef CONFIG_NUMA
#define ENABLE_NUMA_STAT 1
#define DISABLE_NUMA_STAT 0
extern int sysctl_vm_numa_stat;
DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key);
extern int sysctl_vm_numa_stat_handler(struct ctl_table *table,
int write, void __user *buffer, size_t *length, loff_t *ppos);
#endif
struct reclaim_stat {
unsigned nr_dirty;
unsigned nr_unqueued_dirty;
unsigned nr_congested;
unsigned nr_writeback;
unsigned nr_immediate;
unsigned nr_activate[2];
unsigned nr_ref_keep;
unsigned nr_unmap_fail;
unsigned nr_lazyfree_fail;
};
enum writeback_stat_item {
NR_DIRTY_THRESHOLD,
NR_DIRTY_BG_THRESHOLD,
NR_VM_WRITEBACK_STAT_ITEMS,
};
#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);
/*
* vm counters are allowed to be racy. Use raw_cpu_ops to avoid the
* local_irq_disable overhead.
*/
static inline void __count_vm_event(enum vm_event_item item)
{
raw_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)
{
raw_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 */
#ifdef CONFIG_DEBUG_TLBFLUSH
#define count_vm_tlb_event(x) count_vm_event(x)
#define count_vm_tlb_events(x, y) count_vm_events(x, y)
#else
#define count_vm_tlb_event(x) do {} while (0)
#define count_vm_tlb_events(x, y) do { (void)(y); } while (0)
#endif
#ifdef CONFIG_DEBUG_VM_VMACACHE
#define count_vm_vmacache_event(x) count_vm_event(x)
#else
#define count_vm_vmacache_event(x) do {} while (0)
#endif
#define __count_zid_vm_events(item, zid, delta) \
__count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
/*
* Zone and node-based page accounting with per cpu differentials.
*/
extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS];
extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS];
#ifdef CONFIG_NUMA
static inline void zone_numa_state_add(long x, struct zone *zone,
enum numa_stat_item item)
{
atomic_long_add(x, &zone->vm_numa_stat[item]);
atomic_long_add(x, &vm_numa_stat[item]);
}
static inline unsigned long global_numa_state(enum numa_stat_item item)
{
long x = atomic_long_read(&vm_numa_stat[item]);
return x;
}
static inline unsigned long zone_numa_state_snapshot(struct zone *zone,
enum numa_stat_item item)
{
long x = atomic_long_read(&zone->vm_numa_stat[item]);
int cpu;
for_each_online_cpu(cpu)
x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item];
return x;
}
#endif /* CONFIG_NUMA */
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_zone_stat[item]);
}
static inline void node_page_state_add(long x, struct pglist_data *pgdat,
enum node_stat_item item)
{
atomic_long_add(x, &pgdat->vm_stat[item]);
atomic_long_add(x, &vm_node_stat[item]);
}
static inline unsigned long global_zone_page_state(enum zone_stat_item item)
{
long x = atomic_long_read(&vm_zone_stat[item]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
static inline unsigned long global_node_page_state(enum node_stat_item item)
{
long x = atomic_long_read(&vm_node_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;
}
#ifdef CONFIG_NUMA
extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item);
extern unsigned long sum_zone_node_page_state(int node,
enum zone_stat_item item);
extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item);
extern unsigned long node_page_state(struct pglist_data *pgdat,
enum node_stat_item item);
#else
#define sum_zone_node_page_state(node, item) global_zone_page_state(item)
#define node_page_state(node, item) global_node_page_state(item)
#endif /* CONFIG_NUMA */
#ifdef CONFIG_SMP
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 __dec_zone_page_state(struct page *, enum zone_stat_item);
void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long);
void __inc_node_page_state(struct page *, enum node_stat_item);
void __dec_node_page_state(struct page *, enum node_stat_item);
void mod_zone_page_state(struct zone *, enum zone_stat_item, long);
void inc_zone_page_state(struct page *, enum zone_stat_item);
void dec_zone_page_state(struct page *, enum zone_stat_item);
void mod_node_page_state(struct pglist_data *, enum node_stat_item, long);
void inc_node_page_state(struct page *, enum node_stat_item);
void dec_node_page_state(struct page *, enum node_stat_item);
extern void inc_node_state(struct pglist_data *, enum node_stat_item);
extern void __inc_zone_state(struct zone *, enum zone_stat_item);
extern void __inc_node_state(struct pglist_data *, enum node_stat_item);
extern void dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_node_state(struct pglist_data *, enum node_stat_item);
void quiet_vmstat(void);
void cpu_vm_stats_fold(int cpu);
void refresh_zone_stat_thresholds(void);
struct ctl_table;
int vmstat_refresh(struct ctl_table *, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
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, long delta)
{
zone_page_state_add(delta, zone, item);
}
static inline void __mod_node_page_state(struct pglist_data *pgdat,
enum node_stat_item item, int delta)
{
node_page_state_add(delta, pgdat, 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_zone_stat[item]);
}
static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
atomic_long_inc(&pgdat->vm_stat[item]);
atomic_long_inc(&vm_node_stat[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_zone_stat[item]);
}
static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
atomic_long_dec(&pgdat->vm_stat[item]);
atomic_long_dec(&vm_node_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 __inc_node_page_state(struct page *page,
enum node_stat_item item)
{
__inc_node_state(page_pgdat(page), item);
}
static inline void __dec_zone_page_state(struct page *page,
enum zone_stat_item item)
{
__dec_zone_state(page_zone(page), item);
}
static inline void __dec_node_page_state(struct page *page,
enum node_stat_item item)
{
__dec_node_state(page_pgdat(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 inc_node_page_state __inc_node_page_state
#define dec_node_page_state __dec_node_page_state
#define mod_node_page_state __mod_node_page_state
#define inc_zone_state __inc_zone_state
#define inc_node_state __inc_node_state
#define dec_zone_state __dec_zone_state
#define set_pgdat_percpu_threshold(pgdat, callback) { }
static inline void refresh_zone_stat_thresholds(void) { }
static inline void cpu_vm_stats_fold(int cpu) { }
static inline void quiet_vmstat(void) { }
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[];
static inline const char *zone_stat_name(enum zone_stat_item item)
{
return vmstat_text[item];
}
#ifdef CONFIG_NUMA
static inline const char *numa_stat_name(enum numa_stat_item item)
{
return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
item];
}
#endif /* CONFIG_NUMA */
static inline const char *node_stat_name(enum node_stat_item item)
{
return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
NR_VM_NUMA_STAT_ITEMS +
item];
}
static inline const char *lru_list_name(enum lru_list lru)
{
return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
}
static inline const char *writeback_stat_name(enum writeback_stat_item item)
{
return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
NR_VM_NUMA_STAT_ITEMS +
NR_VM_NODE_STAT_ITEMS +
item];
}
#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)
static inline const char *vm_event_name(enum vm_event_item item)
{
return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
NR_VM_NUMA_STAT_ITEMS +
NR_VM_NODE_STAT_ITEMS +
NR_VM_WRITEBACK_STAT_ITEMS +
item];
}
#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */
#endif /* _LINUX_VMSTAT_H */