From: Greg Thelen <gthelen@xxxxxxxxxx>
Subject: memcg: make mem_cgroup_read_stat() unsigned
mem_cgroup_read_stat() returns a page count by summing per cpu page
counters. The summing is racy wrt. updates, so a transient negative sum
is possible. Callers don't want negative values:
- mem_cgroup_wb_stats() doesn't want negative nr_dirty or
nr_writeback. This could confuse dirty throttling.
- oom reports and memory.stat shouldn't show confusing negative usage.
- tree_usage() already avoids negatives.
Avoid returning negative page counts from mem_cgroup_read_stat() and
convert it to unsigned.
[akpm@xxxxxxxxxxxxxxxxxxxx: fix old typo while we're in there]
Signed-off-by: Greg Thelen <gthelen@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> [4.2+]
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 30 ++++++++++++++++++------------
1 file changed, 18 insertions(+), 12 deletions(-)
diff -puN mm/memcontrol.c~memcg-make-mem_cgroup_read_stat-unsigned mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-make-mem_cgroup_read_stat-unsigned
+++ a/mm/memcontrol.c
@@ -644,12 +644,14 @@ mem_cgroup_largest_soft_limit_node(struc
}
/*
+ * Return page count for single (non recursive) @memcg.
+ *
* Implementation Note: reading percpu statistics for memcg.
*
* Both of vmstat[] and percpu_counter has threshold and do periodic
* synchronization to implement "quick" read. There are trade-off between
* reading cost and precision of value. Then, we may have a chance to implement
- * a periodic synchronizion of counter in memcg's counter.
+ * a periodic synchronization of counter in memcg's counter.
*
* But this _read() function is used for user interface now. The user accounts
* memory usage by memory cgroup and he _always_ requires exact value because
@@ -659,17 +661,24 @@ mem_cgroup_largest_soft_limit_node(struc
*
* If there are kernel internal actions which can make use of some not-exact
* value, and reading all cpu value can be performance bottleneck in some
- * common workload, threashold and synchonization as vmstat[] should be
+ * common workload, threshold and synchronization as vmstat[] should be
* implemented.
*/
-static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
- enum mem_cgroup_stat_index idx)
+static unsigned long
+mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx)
{
long val = 0;
int cpu;
+ /* Per-cpu values can be negative, use a signed accumulator */
for_each_possible_cpu(cpu)
val += per_cpu(memcg->stat->count[idx], cpu);
+ /*
+ * Summing races with updates, so val may be negative. Avoid exposing
+ * transient negative values.
+ */
+ if (val < 0)
+ val = 0;
return val;
}
@@ -1254,7 +1263,7 @@ void mem_cgroup_print_oom_info(struct me
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
- pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+ pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
K(mem_cgroup_read_stat(iter, i)));
}
@@ -2819,14 +2828,11 @@ static unsigned long tree_stat(struct me
enum mem_cgroup_stat_index idx)
{
struct mem_cgroup *iter;
- long val = 0;
+ unsigned long val = 0;
- /* Per-cpu values can be negative, use a signed accumulator */
for_each_mem_cgroup_tree(iter, memcg)
val += mem_cgroup_read_stat(iter, idx);
- if (val < 0) /* race ? */
- val = 0;
return val;
}
@@ -3169,7 +3175,7 @@ static int memcg_stat_show(struct seq_fi
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
- seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
+ seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i],
mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
}
@@ -3194,13 +3200,13 @@ static int memcg_stat_show(struct seq_fi
(u64)memsw * PAGE_SIZE);
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
- long long val = 0;
+ unsigned long long val = 0;
if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
for_each_mem_cgroup_tree(mi, memcg)
val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
- seq_printf(m, "total_%s %lld\n", mem_cgroup_stat_names[i], val);
+ seq_printf(m, "total_%s %llu\n", mem_cgroup_stat_names[i], val);
}
for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
_
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html