diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f619e24fc3bb..e78bc98ab229 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -947,6 +947,8 @@ unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item); bool memcg_stat_item_valid(int idx); bool memcg_vm_event_item_valid(enum vm_event_item idx); unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); +unsigned long lruvec_page_state_monotonic(struct lruvec *lruvec, + enum node_stat_item idx); unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx); @@ -1399,6 +1401,12 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); } +static inline unsigned long lruvec_page_state_monotonic(struct lruvec *lruvec, + enum node_stat_item idx) +{ + return node_page_state_monotonic(lruvec_pgdat(lruvec), idx); +} + static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 3c9c266cf782..fb8c76289e02 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -194,6 +194,19 @@ unsigned long global_node_page_state_pages(enum node_stat_item item) return x; } +/* + * Non-clamping variant of global_node_page_state() intended for callers that + * snapshot a monotonically-incremented counter and subtract two samples. + * Returns the raw wrapping value so that unsigned modular subtraction stays + * correct across a signed-long overflow (a real hazard on 32-bit) that the + * clamp in global_node_page_state() would otherwise turn into a huge spurious + * delta. Do NOT use for non-monotonic page-count reads. + */ +static inline unsigned long global_node_page_state_monotonic(enum node_stat_item item) +{ + return (unsigned long)atomic_long_read(&vm_node_stat[item]); +} + static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); @@ -259,11 +272,14 @@ extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); +extern unsigned long node_page_state_monotonic(struct pglist_data *pgdat, + enum node_stat_item item); extern void fold_vm_numa_events(void); #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) #define node_page_state_pages(node, item) global_node_page_state_pages(item) +#define node_page_state_monotonic(node, item) global_node_page_state_monotonic(item) static inline void fold_vm_numa_events(void) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ec92cb40156d..d804f8d07581 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -508,6 +508,42 @@ unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) return x; } +/** + * lruvec_page_state_monotonic - non-clamping lruvec stat read for delta sampling + * @lruvec: the LRU vector to read from + * @idx: the node_stat_item to read + * + * Returns the raw state[idx] value cast to unsigned long, skipping the + * clamp-negative-to-zero step in lruvec_page_state(). Intended for callers + * that snapshot a monotonically-incremented counter and subtract two + * samples: unsigned modular arithmetic then yields the correct delta across + * a signed-long wraparound (a real hazard on 32-bit) that the clamp would + * otherwise turn into a huge spurious delta. + * + * Do NOT use for non-monotonic page-count reads where a transient negative + * reading from per-CPU delta skew must present as zero. + * + * XXX: This helper (and its node/global peers) exists because some + * monotonically-incremented event counters are stored in + * enum node_stat_item. + */ +unsigned long lruvec_page_state_monotonic(struct lruvec *lruvec, + enum node_stat_item idx) +{ + struct mem_cgroup_per_node *pn; + int i; + + if (mem_cgroup_disabled()) + return node_page_state_monotonic(lruvec_pgdat(lruvec), idx); + + i = memcg_stats_index(idx); + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) + return 0; + + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + return (unsigned long)READ_ONCE(pn->lruvec_stats->state[i]); +} + unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { diff --git a/mm/vmstat.c b/mm/vmstat.c index 3b5cb1031f72..507118474c03 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1025,6 +1025,17 @@ unsigned long node_page_state(struct pglist_data *pgdat, return node_page_state_pages(pgdat, item); } + +/* + * Non-clamping variant of node_page_state() intended for callers that + * snapshot a monotonically-incremented counter and subtract two samples. + * See global_node_page_state_monotonic() for the rationale. + */ +unsigned long node_page_state_monotonic(struct pglist_data *pgdat, + enum node_stat_item item) +{ + return (unsigned long)atomic_long_read(&pgdat->vm_stat[item]); +} #endif /*