mm: memcontrol: lockless page counters

Memory is internally accounted in bytes, using spinlock-protected 64-bit
counters, even though the smallest accounting delta is a page.  The
counter interface is also convoluted and does too many things.

Introduce a new lockless word-sized page counter API, then change all
memory accounting over to it.  The translation from and to bytes then only
happens when interfacing with userspace.

The removed locking overhead is noticable when scaling beyond the per-cpu
charge caches - on a 4-socket machine with 144-threads, the following test
shows the performance differences of 288 memcgs concurrently running a
page fault benchmark:

vanilla:

   18631648.500498      task-clock (msec)         #  140.643 CPUs utilized            ( +-  0.33% )
         1,380,638      context-switches          #    0.074 K/sec                    ( +-  0.75% )
            24,390      cpu-migrations            #    0.001 K/sec                    ( +-  8.44% )
     1,843,305,768      page-faults               #    0.099 M/sec                    ( +-  0.00% )
50,134,994,088,218      cycles                    #    2.691 GHz                      ( +-  0.33% )
   <not supported>      stalled-cycles-frontend
   <not supported>      stalled-cycles-backend
 8,049,712,224,651      instructions              #    0.16  insns per cycle          ( +-  0.04% )
 1,586,970,584,979      branches                  #   85.176 M/sec                    ( +-  0.05% )
     1,724,989,949      branch-misses             #    0.11% of all branches          ( +-  0.48% )

     132.474343877 seconds time elapsed                                          ( +-  0.21% )

lockless:

   12195979.037525      task-clock (msec)         #  133.480 CPUs utilized            ( +-  0.18% )
           832,850      context-switches          #    0.068 K/sec                    ( +-  0.54% )
            15,624      cpu-migrations            #    0.001 K/sec                    ( +- 10.17% )
     1,843,304,774      page-faults               #    0.151 M/sec                    ( +-  0.00% )
32,811,216,801,141      cycles                    #    2.690 GHz                      ( +-  0.18% )
   <not supported>      stalled-cycles-frontend
   <not supported>      stalled-cycles-backend
 9,999,265,091,727      instructions              #    0.30  insns per cycle          ( +-  0.10% )
 2,076,759,325,203      branches                  #  170.282 M/sec                    ( +-  0.12% )
     1,656,917,214      branch-misses             #    0.08% of all branches          ( +-  0.55% )

      91.369330729 seconds time elapsed                                          ( +-  0.45% )

On top of improved scalability, this also gets rid of the icky long long
types in the very heart of memcg, which is great for 32 bit and also makes
the code a lot more readable.

Notable differences between the old and new API:

- res_counter_charge() and res_counter_charge_nofail() become
  page_counter_try_charge() and page_counter_charge() resp. to match
  the more common kernel naming scheme of try_do()/do()

- res_counter_uncharge_until() is only ever used to cancel a local
  counter and never to uncharge bigger segments of a hierarchy, so
  it's replaced by the simpler page_counter_cancel()

- res_counter_set_limit() is replaced by page_counter_limit(), which
  expects its callers to serialize against themselves

- res_counter_memparse_write_strategy() is replaced by
  page_counter_limit(), which rounds down to the nearest page size -
  rather than up.  This is more reasonable for explicitely requested
  hard upper limits.

- to keep charging light-weight, page_counter_try_charge() charges
  speculatively, only to roll back if the result exceeds the limit.
  Because of this, a failing bigger charge can temporarily lock out
  smaller charges that would otherwise succeed.  The error is bounded
  to the difference between the smallest and the biggest possible
  charge size, so for memcg, this means that a failing THP charge can
  send base page charges into reclaim upto 2MB (4MB) before the limit
  would have been reached.  This should be acceptable.

[akpm@linux-foundation.org: add includes for WARN_ON_ONCE and memparse]
[akpm@linux-foundation.org: add includes for WARN_ON_ONCE, memparse, strncmp, and PAGE_SIZE]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 62 insertions, 20 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6b75640ef5ab..ea007615e8f9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -447,9 +447,8 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
 	/*
 	 * __GFP_NOFAIL allocations will move on even if charging is not
 	 * possible. Therefore we don't even try, and have this allocation
-	 * unaccounted. We could in theory charge it with
-	 * res_counter_charge_nofail, but we hope those allocations are rare,
-	 * and won't be worth the trouble.
+	 * unaccounted. We could in theory charge it forcibly, but we hope
+	 * those allocations are rare, and won't be worth the trouble.
 	 */
 	if (gfp & __GFP_NOFAIL)
 		return true;
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
new file mode 100644
index 000000000000..7cce3be99ff3
--- /dev/null
+++ b/include/linux/page_counter.h
@@ -0,0 +1,51 @@
+#ifndef _LINUX_PAGE_COUNTER_H
+#define _LINUX_PAGE_COUNTER_H
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <asm/page.h>
+
+struct page_counter {
+	atomic_long_t count;
+	unsigned long limit;
+	struct page_counter *parent;
+
+	/* legacy */
+	unsigned long watermark;
+	unsigned long failcnt;
+};
+
+#if BITS_PER_LONG == 32
+#define PAGE_COUNTER_MAX LONG_MAX
+#else
+#define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE)
+#endif
+
+static inline void page_counter_init(struct page_counter *counter,
+				     struct page_counter *parent)
+{
+	atomic_long_set(&counter->count, 0);
+	counter->limit = PAGE_COUNTER_MAX;
+	counter->parent = parent;
+}
+
+static inline unsigned long page_counter_read(struct page_counter *counter)
+{
+	return atomic_long_read(&counter->count);
+}
+
+int page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
+void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_try_charge(struct page_counter *counter,
+			    unsigned long nr_pages,
+			    struct page_counter **fail);
+int page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_limit(struct page_counter *counter, unsigned long limit);
+int page_counter_memparse(const char *buf, unsigned long *nr_pages);
+
+static inline void page_counter_reset_watermark(struct page_counter *counter)
+{
+	counter->watermark = page_counter_read(counter);
+}
+
+#endif /* _LINUX_PAGE_COUNTER_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index e6f235ebf6c9..7ff44e062a38 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -54,8 +54,8 @@
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/page_counter.h>
 #include <linux/memcontrol.h>
-#include <linux/res_counter.h>
 #include <linux/static_key.h>
 #include <linux/aio.h>
 #include <linux/sched.h>
@@ -1062,7 +1062,7 @@ enum cg_proto_flags {
 };
 
 struct cg_proto {
-	struct res_counter	memory_allocated;	/* Current allocated memory. */
+	struct page_counter	memory_allocated;	/* Current allocated memory. */
 	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
 	int			memory_pressure;
 	long			sysctl_mem[3];
@@ -1214,34 +1214,26 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
 					      unsigned long amt,
 					      int *parent_status)
 {
-	struct res_counter *fail;
-	int ret;
+	page_counter_charge(&prot->memory_allocated, amt);
 
-	ret = res_counter_charge_nofail(&prot->memory_allocated,
-					amt << PAGE_SHIFT, &fail);
-	if (ret < 0)
+	if (page_counter_read(&prot->memory_allocated) >
+	    prot->memory_allocated.limit)
 		*parent_status = OVER_LIMIT;
 }
 
 static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
 					      unsigned long amt)
 {
-	res_counter_uncharge(&prot->memory_allocated, amt << PAGE_SHIFT);
-}
-
-static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
-{
-	u64 ret;
-	ret = res_counter_read_u64(&prot->memory_allocated, RES_USAGE);
-	return ret >> PAGE_SHIFT;
+	page_counter_uncharge(&prot->memory_allocated, amt);
 }
 
 static inline long
 sk_memory_allocated(const struct sock *sk)
 {
 	struct proto *prot = sk->sk_prot;
+
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 
 	return atomic_long_read(prot->memory_allocated);
 }
@@ -1255,7 +1247,7 @@ sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
 		memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
 		/* update the root cgroup regardless */
 		atomic_long_add_return(amt, prot->memory_allocated);
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 	}
 
 	return atomic_long_add_return(amt, prot->memory_allocated);