summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2021-02-25 17:16:47 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2021-02-26 09:41:00 -0800
commit2bbd00aef0671bfe3c2ca5ba67097246257de125 (patch)
treeb6a5214b96f727e7fe029365855d9d729ca5d57a
parenta052d4d13d88c2073d1339d9dce02cba7b4dc609 (diff)
mm: vmstat: fix NOHZ wakeups for node stat changes
On NOHZ, the periodic vmstat flushers on each CPU can go to sleep and won't wake up until stat changes are detected in the per-cpu deltas of the zone vmstat counters. In commit 75ef71840539 ("mm, vmstat: add infrastructure for per-node vmstats") per-node counters were introduced, and subsequently most stats were moved from the zone to the node level. However, the node counters weren't added to the NOHZ wakeup detection. In theory this can cause per-cpu errors to remain in the user-reported stats indefinitely. In practice this only affects a handful of sub counters (file_mapped, dirty and writeback e.g.) because other page state changes at the node level likely involve a change at the zone level as well (alloc and free, lru ops). Also, nobody has complained. Fix it up for completeness: wake up vmstat refreshing on node changes. Also remove the BUILD_BUG_ONs that assert counter size; we haven't relied on it since we added sizeof() to the range calculation in commit 13c9aaf7fa01 ("mm/vmstat.c: fix NUMA statistics updates"). Link: https://lkml.kernel.org/r/20210202184342.118513-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/vmstat.c15
1 files changed, 9 insertions, 6 deletions
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6cdf789ced5e..0b0fc3b77789 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1894,16 +1894,12 @@ static void vmstat_update(struct work_struct *w)
*/
static bool need_update(int cpu)
{
+ pg_data_t *last_pgdat = NULL;
struct zone *zone;
for_each_populated_zone(zone) {
struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu);
-
- BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1);
-#ifdef CONFIG_NUMA
- BUILD_BUG_ON(sizeof(p->vm_numa_stat_diff[0]) != 2);
-#endif
-
+ struct per_cpu_nodestat *n;
/*
* The fast way of checking if there are any vmstat diffs.
*/
@@ -1915,6 +1911,13 @@ static bool need_update(int cpu)
sizeof(p->vm_numa_stat_diff[0])))
return true;
#endif
+ if (last_pgdat == zone->zone_pgdat)
+ continue;
+ last_pgdat = zone->zone_pgdat;
+ n = per_cpu_ptr(zone->zone_pgdat->per_cpu_nodestats, cpu);
+ if (memchr_inv(n->vm_node_stat_diff, 0, NR_VM_NODE_STAT_ITEMS *
+ sizeof(n->vm_node_stat_diff[0])))
+ return true;
}
return false;
}