memcg: rework usage of stats by soft limit

Instead of incrementing counter on each page in/out and comparing it with
constant, we set counter to constant, decrement counter on each page
in/out and compare it with zero.  We want to make comparing as fast as
possible.  On many RISC systems (probably not only RISC) comparing with
zero is more effective than comparing with a constant, since not every
constant can be immediate operand for compare instruction.

Also, I've renamed MEM_CGROUP_STAT_EVENTS to MEM_CGROUP_STAT_SOFTLIMIT,
since really it's not a generic counter.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Dan Malek <dan@embeddedalley.com>
Cc: Vladislav Buzov <vbuzov@embeddedalley.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Alexander Shishkin <virtuoso@slind.org>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5f8f93d..5a41d93 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -71,8 +71,9 @@ enum mem_cgroup_stat_index {
        MEM_CGROUP_STAT_FILE_MAPPED,  /* # of pages charged as file rss */
        MEM_CGROUP_STAT_PGPGIN_COUNT,   /* # of pages paged in */
        MEM_CGROUP_STAT_PGPGOUT_COUNT,  /* # of pages paged out */
-       MEM_CGROUP_STAT_EVENTS, /* sum of pagein + pageout for internal use */
        MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
+       MEM_CGROUP_STAT_SOFTLIMIT, /* decrements on each page in/out.
+                                       used by soft limit implementation */
 
        MEM_CGROUP_STAT_NSTATS,
 };
@@ -86,10 +87,10 @@ struct mem_cgroup_stat {
 };
 
 static inline void
-__mem_cgroup_stat_reset_safe(struct mem_cgroup_stat_cpu *stat,
-                               enum mem_cgroup_stat_index idx)
+__mem_cgroup_stat_set_safe(struct mem_cgroup_stat_cpu *stat,
+                               enum mem_cgroup_stat_index idx, s64 val)
 {
-       stat->count[idx] = 0;
+       stat->count[idx] = val;
 }
 
 static inline s64
@@ -411,9 +412,10 @@ static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem)
 
        cpu = get_cpu();
        cpustat = &mem->stat.cpustat[cpu];
-       val = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_EVENTS);
-       if (unlikely(val > SOFTLIMIT_EVENTS_THRESH)) {
-               __mem_cgroup_stat_reset_safe(cpustat, MEM_CGROUP_STAT_EVENTS);
+       val = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_SOFTLIMIT);
+       if (unlikely(val < 0)) {
+               __mem_cgroup_stat_set_safe(cpustat, MEM_CGROUP_STAT_SOFTLIMIT,
+                               SOFTLIMIT_EVENTS_THRESH);
                ret = true;
        }
        put_cpu();
@@ -546,7 +548,7 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
        else
                __mem_cgroup_stat_add_safe(cpustat,
                                MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
-       __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_EVENTS, 1);
+       __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_SOFTLIMIT, -1);
        put_cpu();
 }