percpu_counters(): use cpu notifiers

per-cpu counters presently must iterate over all possible CPUs in the
exhaustive percpu_counter_sum().

But it can be much better to only iterate over the presently-online CPUs.  To
do this, we must arrange for an offlined CPU's count to be spilled into the
counter's central count.

We can do this for all percpu_counters in the machine by linking them into a
single global list and walking that list at CPU_DEAD time.

(I hope.  Might have race windows in which the percpu_counter_sum() count is
inaccurate?)

Cc: Gautham R Shenoy <ego@in.ibm.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 6 insertions, 12 deletions

diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index f5aa593ccf32..3d9f70972cdf 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -8,6 +8,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/smp.h>
+#include <linux/list.h>
 #include <linux/threads.h>
 #include <linux/percpu.h>
 #include <linux/types.h>
@@ -17,6 +18,9 @@
 struct percpu_counter {
         spinlock_t lock;
         s64 count;
+#ifdef CONFIG_HOTPLUG_CPU
+        struct list_head list;  /* All percpu_counters are on a list */
+#endif
         s32 *counters;
 };
 
@@ -26,18 +30,8 @@ struct percpu_counter {
 #define FBC_BATCH       (NR_CPUS*4)
 #endif
 
-static inline void percpu_counter_init(struct percpu_counter *fbc, s64 amount)
-{
-        spin_lock_init(&fbc->lock);
-        fbc->count = amount;
-        fbc->counters = alloc_percpu(s32);
-}
-
-static inline void percpu_counter_destroy(struct percpu_counter *fbc)
-{
-        free_percpu(fbc->counters);
-}
-
+void percpu_counter_init(struct percpu_counter *fbc, s64 amount);
+void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_mod(struct percpu_counter *fbc, s32 amount);
 s64 percpu_counter_sum(struct percpu_counter *fbc);