diff options
| author | Roman Gushchin <guro@fb.com> | 2020-10-01 13:07:49 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-02 09:13:41 -0700 |
| commit | be458311cdbb5d94820ffc4e40c5906085c0a507 (patch) | |
| tree | ced755d5f88226d5aea7a14a38864b23656b94a7 | |
| parent | 472e5b056f000a778abb41f1e443de58eb259783 (diff) | |
mm: memcg/slab: fix slab statistics in !SMP configuration
Since commit ea426c2a7de8 ("mm: memcg: prepare for byte-sized vmstat
items") the write side of slab counters accepts a value in bytes and
converts it to pages. It happens in __mod_node_page_state().
However a non-SMP version of __mod_node_page_state() doesn't perform
this conversion. It leads to incorrect (unrealistically high) slab
counters values. Fix this by adding a similar conversion to the non-SMP
version of __mod_node_page_state().
Signed-off-by: Roman Gushchin <guro@fb.com>
Reported-and-tested-by: Bastian Bittorf <bb@npl.de>
Fixes: ea426c2a7de8 ("mm: memcg: prepare for byte-sized vmstat items")
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
| -rw-r--r-- | include/linux/vmstat.h | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 91220ace31da..7557c1070fd7 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -312,6 +312,11 @@ static inline void __mod_zone_page_state(struct zone *zone, static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { + if (vmstat_item_in_bytes(item)) { + VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); + delta >>= PAGE_SHIFT; + } + node_page_state_add(delta, pgdat, item); } |