lruvec_page_state(), node_page_state(), and global_node_page_state() all clamp negative reads to zero on CONFIG_SMP so that a transient per-CPU delta skew presents as zero pages rather than as a garbage unsigned value. This is the right behaviour for non-monotonic page-count readers. It is however incorrect for callers that snapshot a monotonically- incremented event counter and compute a delta from two samples. Once the underlying signed long wraps past LONG_MAX, the clamped read drops to zero while the previously-recorded snapshot still holds the pre-wrap value; the unsigned subtraction then underflows into a ~2^31 spurious delta for 32-bit architecture and corrupts the caller's accumulator. Add non-clamping siblings that return the underlying state value cast to unsigned long: global_node_page_state_monotonic() node_page_state_monotonic() lruvec_page_state_monotonic() With both samples read via the _monotonic variant, unsigned modular subtraction stays correct across a signed-long wraparound as long as the true growth between two samples fits in unsigned long (< 2^32 on 32-bit, < 2^64 on 64-bit); the 32-bit bound is the practically-reachable one that motivates this helper. The variants are only safe for monotonically-incremented counters. Non-monotonic page-count readers must keep using the existing clamped helpers so transient negative reads still present as zero. This is a prerequisite for the following patch which replaces the producer-side anon_cost/file_cost accumulators with a read-side accumulator in prepare_scan_control() that samples monotonic per-LRU vmstat counters (PGROTATE_*, PGRECLAIM_PAGEOUT_*, WORKINGSET_RESTORE_*) via lruvec_page_state_monotonic() and folds the unsigned modular delta into a per-lruvec cost_accum[]. Acked-by: Johannes Weiner Signed-off-by: Usama Arif --- include/linux/memcontrol.h | 8 ++++++++ include/linux/vmstat.h | 16 ++++++++++++++++ mm/memcontrol.c | 36 ++++++++++++++++++++++++++++++++++++ mm/vmstat.c | 11 +++++++++++ 4 files changed, 71 insertions(+) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e1f46a0016fc..b40bc4f6fe4a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -931,6 +931,8 @@ 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); @@ -1378,6 +1380,12 @@ 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 56cd4af08232..b4a357c5f7e0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -502,6 +502,42 @@ 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 we place + * monotonically-incremented event counters (PGROTATE_*, PGRECLAIM_PAGEOUT_*) + * into 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 f534972f517d..c4364f0eb08a 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1024,6 +1024,17 @@ 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 /* -- 2.53.0-Meta