From c12176d3368b9b36ae484d323d41e94be26f9b65 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 5 Nov 2015 18:50:29 -0800 Subject: memcg: fix thresholds for 32b architectures. Commit 424cdc141380 ("memcg: convert threshold to bytes") has fixed a regression introduced by 3e32cb2e0a12 ("mm: memcontrol: lockless page counters") where thresholds were silently converted to use page units rather than bytes when interpreting the user input. The fix is not complete, though, as properly pointed out by Ben Hutchings during stable backport review. The page count is converted to bytes but unsigned long is used to hold the value which would be obviously not sufficient for 32b systems with more than 4G thresholds. The same applies to usage as taken from mem_cgroup_usage which might overflow. Let's remove this bytes vs. pages internal tracking differences and handle thresholds in page units internally. Chage mem_cgroup_usage() to return the value in page units and revert 424cdc141380 because this should be sufficient for the consistent handling. mem_cgroup_read_u64 as the only users of mem_cgroup_usage outside of the threshold handling code is converted to give the proper in bytes result. It is doing that already for page_counter output so this is more consistent as well. The value presented to the userspace is still in bytes units. Fixes: 424cdc141380 ("memcg: convert threshold to bytes") Fixes: 3e32cb2e0a12 ("mm: memcontrol: lockless page counters") Signed-off-by: Michal Hocko Reported-by: Ben Hutchings Reviewed-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: From: Michal Hocko Subject: memcg-fix-thresholds-for-32b-architectures-fix Cc: Ben Hutchings Cc: Vladimir Davydov Cc: Johannes Weiner From: Andrew Morton Subject: memcg-fix-thresholds-for-32b-architectures-fix-fix don't attempt to inline mem_cgroup_usage() The compiler ignores the inline anwyay. And __always_inlining it adds 600 bytes of goop to the .o file. Cc: Ben Hutchings Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d47de73d7c36..38765d8e7e18 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2801,9 +2801,9 @@ static unsigned long tree_stat(struct mem_cgroup *memcg, return val; } -static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) +static inline unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) { - u64 val; + unsigned long val; if (mem_cgroup_is_root(memcg)) { val = tree_stat(memcg, MEM_CGROUP_STAT_CACHE); @@ -2816,7 +2816,7 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) else val = page_counter_read(&memcg->memsw); } - return val << PAGE_SHIFT; + return val; } enum { @@ -2850,9 +2850,9 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, switch (MEMFILE_ATTR(cft->private)) { case RES_USAGE: if (counter == &memcg->memory) - return mem_cgroup_usage(memcg, false); + return (u64)mem_cgroup_usage(memcg, false) * PAGE_SIZE; if (counter == &memcg->memsw) - return mem_cgroup_usage(memcg, true); + return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE; return (u64)page_counter_read(counter) * PAGE_SIZE; case RES_LIMIT: return (u64)counter->limit * PAGE_SIZE; @@ -3352,7 +3352,6 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, ret = page_counter_memparse(args, "-1", &threshold); if (ret) return ret; - threshold <<= PAGE_SHIFT; mutex_lock(&memcg->thresholds_lock); -- cgit v1.2.3-58-ga151