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>

1 files changed, 44 insertions, 43 deletions

diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 1d191357bf88..272327134a1b 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -9,13 +9,13 @@
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	/*
-	 * The root cgroup does not use res_counters, but rather,
+	 * The root cgroup does not use page_counters, but rather,
 	 * rely on the data already collected by the network
 	 * subsystem
 	 */
-	struct res_counter *res_parent = NULL;
-	struct cg_proto *cg_proto, *parent_cg;
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct page_counter *counter_parent = NULL;
+	struct cg_proto *cg_proto, *parent_cg;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
@@ -29,9 +29,9 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 
 	parent_cg = tcp_prot.proto_cgroup(parent);
 	if (parent_cg)
-		res_parent = &parent_cg->memory_allocated;
+		counter_parent = &parent_cg->memory_allocated;
 
-	res_counter_init(&cg_proto->memory_allocated, res_parent);
+	page_counter_init(&cg_proto->memory_allocated, counter_parent);
 	percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL);
 
 	return 0;
@@ -50,7 +50,7 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
-static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
+static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
 {
 	struct cg_proto *cg_proto;
 	int i;
@@ -60,20 +60,17 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	if (!cg_proto)
 		return -EINVAL;
 
-	if (val > RES_COUNTER_MAX)
-		val = RES_COUNTER_MAX;
-
-	ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
+	ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages);
 	if (ret)
 		return ret;
 
 	for (i = 0; i < 3; i++)
-		cg_proto->sysctl_mem[i] = min_t(long, val >> PAGE_SHIFT,
+		cg_proto->sysctl_mem[i] = min_t(long, nr_pages,
 						sysctl_tcp_mem[i]);
 
-	if (val == RES_COUNTER_MAX)
+	if (nr_pages == PAGE_COUNTER_MAX)
 		clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
-	else if (val != RES_COUNTER_MAX) {
+	else {
 		/*
 		 * The active bit needs to be written after the static_key
 		 * update. This is what guarantees that the socket activation
@@ -102,11 +99,20 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	return 0;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+};
+
+static DEFINE_MUTEX(tcp_limit_mutex);
+
 static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	unsigned long long val;
+	unsigned long nr_pages;
 	int ret = 0;
 
 	buf = strstrip(buf);
@@ -114,10 +120,12 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = res_counter_memparse_write_strategy(buf, &val);
+		ret = page_counter_memparse(buf, &nr_pages);
 		if (ret)
 			break;
-		ret = tcp_update_limit(memcg, val);
+		mutex_lock(&tcp_limit_mutex);
+		ret = tcp_update_limit(memcg, nr_pages);
+		mutex_unlock(&tcp_limit_mutex);
 		break;
 	default:
 		ret = -EINVAL;
@@ -126,43 +134,36 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	return ret ?: nbytes;
 }
 
-static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return default_val;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, type);
-}
-
-static u64 tcp_read_usage(struct mem_cgroup *memcg)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, RES_USAGE);
-}
-
 static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg);
 	u64 val;
 
 	switch (cft->private) {
 	case RES_LIMIT:
-		val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX);
+		if (!cg_proto)
+			return PAGE_COUNTER_MAX;
+		val = cg_proto->memory_allocated.limit;
+		val *= PAGE_SIZE;
 		break;
 	case RES_USAGE:
-		val = tcp_read_usage(memcg);
+		if (!cg_proto)
+			val = atomic_long_read(&tcp_memory_allocated);
+		else
+			val = page_counter_read(&cg_proto->memory_allocated);
+		val *= PAGE_SIZE;
 		break;
 	case RES_FAILCNT:
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.failcnt;
+		break;
 	case RES_MAX_USAGE:
-		val = tcp_read_stat(memcg, cft->private, 0);
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.watermark;
+		val *= PAGE_SIZE;
 		break;
 	default:
 		BUG();
@@ -183,10 +184,10 @@ static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
 
 	switch (of_cft(of)->private) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&cg_proto->memory_allocated);
+		page_counter_reset_watermark(&cg_proto->memory_allocated);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&cg_proto->memory_allocated);
+		cg_proto->memory_allocated.failcnt = 0;
 		break;
 	}