Merge branch 'akpm' (patches from Andrew)

Merge first patch-bomb from Andrew Morton:

 - A few hotfixes which missed 4.4 becasue I was asleep.  cc'ed to
   -stable

 - A few misc fixes

 - OCFS2 updates

 - Part of MM.  Including pretty large changes to page-flags handling
   and to thp management which have been buffered up for 2-3 cycles now.

  I have a lot of MM material this time.

[ It turns out the THP part wasn't quite ready, so that got dropped from
  this series  - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (117 commits)
  zsmalloc: reorganize struct size_class to pack 4 bytes hole
  mm/zbud.c: use list_last_entry() instead of list_tail_entry()
  zram/zcomp: do not zero out zcomp private pages
  zram: pass gfp from zcomp frontend to backend
  zram: try vmalloc() after kmalloc()
  zram/zcomp: use GFP_NOIO to allocate streams
  mm: add tracepoint for scanning pages
  drivers/base/memory.c: fix kernel warning during memory hotplug on ppc64
  mm/page_isolation: use macro to judge the alignment
  mm: fix noisy sparse warning in LIBCFS_ALLOC_PRE()
  mm: rework virtual memory accounting
  include/linux/memblock.h: fix ordering of 'flags' argument in comments
  mm: move lru_to_page to mm_inline.h
  Documentation/filesystems: describe the shared memory usage/accounting
  memory-hotplug: don't BUG() in register_memory_resource()
  hugetlb: make mm and fs code explicitly non-modular
  mm/swapfile.c: use list_for_each_entry_safe in free_swap_count_continuations
  mm: /proc/pid/clear_refs: no need to clear VM_SOFTDIRTY in clear_soft_dirty_pmd()
  mm: make sure isolate_lru_page() is never called for tail page
  vmstat: make vmstat_updater deferrable again and shut down on idle
  ...

8 files changed, 59 insertions, 136 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 51270238e269..6c1c8bc93412 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -195,44 +195,6 @@ bool sk_net_capable(const struct sock *sk, int cap)
 }
 EXPORT_SYMBOL(sk_net_capable);
 
-
-#ifdef CONFIG_MEMCG_KMEM
-int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
-{
-	struct proto *proto;
-	int ret = 0;
-
-	mutex_lock(&proto_list_mutex);
-	list_for_each_entry(proto, &proto_list, node) {
-		if (proto->init_cgroup) {
-			ret = proto->init_cgroup(memcg, ss);
-			if (ret)
-				goto out;
-		}
-	}
-
-	mutex_unlock(&proto_list_mutex);
-	return ret;
-out:
-	list_for_each_entry_continue_reverse(proto, &proto_list, node)
-		if (proto->destroy_cgroup)
-			proto->destroy_cgroup(memcg);
-	mutex_unlock(&proto_list_mutex);
-	return ret;
-}
-
-void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
-{
-	struct proto *proto;
-
-	mutex_lock(&proto_list_mutex);
-	list_for_each_entry_reverse(proto, &proto_list, node)
-		if (proto->destroy_cgroup)
-			proto->destroy_cgroup(memcg);
-	mutex_unlock(&proto_list_mutex);
-}
-#endif
-
 /*
  * Each address family might have different locking rules, so we have
  * one slock key per address family:
@@ -240,11 +202,6 @@ void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
 static struct lock_class_key af_family_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
 
-#if defined(CONFIG_MEMCG_KMEM)
-struct static_key memcg_socket_limit_enabled;
-EXPORT_SYMBOL(memcg_socket_limit_enabled);
-#endif
-
 /*
  * Make lock validator output more readable. (we pre-construct these
  * strings build-time, so that runtime initialization of socket
@@ -1507,12 +1464,6 @@ void sk_free(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_free);
 
-static void sk_update_clone(const struct sock *sk, struct sock *newsk)
-{
-	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		sock_update_memcg(newsk);
-}
-
 /**
  *	sk_clone_lock - clone a socket, and lock its clone
  *	@sk: the socket to clone
@@ -1607,7 +1558,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		sk_set_socket(newsk, NULL);
 		newsk->sk_wq = NULL;
 
-		sk_update_clone(sk, newsk);
+		if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+			sock_update_memcg(newsk);
 
 		if (newsk->sk_prot->sockets_allocated)
 			sk_sockets_allocated_inc(newsk);
@@ -2089,27 +2041,27 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 	struct proto *prot = sk->sk_prot;
 	int amt = sk_mem_pages(size);
 	long allocated;
-	int parent_status = UNDER_LIMIT;
 
 	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
 
-	allocated = sk_memory_allocated_add(sk, amt, &parent_status);
+	allocated = sk_memory_allocated_add(sk, amt);
+
+	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
+	    !mem_cgroup_charge_skmem(sk->sk_memcg, amt))
+		goto suppress_allocation;
 
 	/* Under limit. */
-	if (parent_status == UNDER_LIMIT &&
-			allocated <= sk_prot_mem_limits(sk, 0)) {
+	if (allocated <= sk_prot_mem_limits(sk, 0)) {
 		sk_leave_memory_pressure(sk);
 		return 1;
 	}
 
-	/* Under pressure. (we or our parents) */
-	if ((parent_status > SOFT_LIMIT) ||
-			allocated > sk_prot_mem_limits(sk, 1))
+	/* Under pressure. */
+	if (allocated > sk_prot_mem_limits(sk, 1))
 		sk_enter_memory_pressure(sk);
 
-	/* Over hard limit (we or our parents) */
-	if ((parent_status == OVER_LIMIT) ||
-			(allocated > sk_prot_mem_limits(sk, 2)))
+	/* Over hard limit. */
+	if (allocated > sk_prot_mem_limits(sk, 2))
 		goto suppress_allocation;
 
 	/* guarantee minimum buffer size under pressure */
@@ -2158,6 +2110,9 @@ suppress_allocation:
 
 	sk_memory_allocated_sub(sk, amt);
 
+	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+		mem_cgroup_uncharge_skmem(sk->sk_memcg, amt);
+
 	return 0;
 }
 EXPORT_SYMBOL(__sk_mem_schedule);
@@ -2173,6 +2128,9 @@ void __sk_mem_reclaim(struct sock *sk, int amount)
 	sk_memory_allocated_sub(sk, amount);
 	sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
 
+	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+		mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);
+
 	if (sk_under_memory_pressure(sk) &&
 	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
 		sk_leave_memory_pressure(sk);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7bb1b091efd1..fd17eec93525 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -422,7 +422,8 @@ void tcp_init_sock(struct sock *sk)
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
 	local_bh_disable();
-	sock_update_memcg(sk);
+	if (mem_cgroup_sockets_enabled)
+		sock_update_memcg(sk);
 	sk_sockets_allocated_inc(sk);
 	local_bh_enable();
 }
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 65947c1f4733..c7d1fb50f381 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1818,7 +1818,9 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	tcp_saved_syn_free(tp);
 
 	sk_sockets_allocated_dec(sk);
-	sock_release_memcg(sk);
+
+	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+		sock_release_memcg(sk);
 }
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
 
@@ -2342,11 +2344,6 @@ struct proto tcp_prot = {
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
 #endif
-#ifdef CONFIG_MEMCG_KMEM
-	.init_cgroup		= tcp_init_cgroup,
-	.destroy_cgroup		= tcp_destroy_cgroup,
-	.proto_cgroup		= tcp_proto_cgroup,
-#endif
 	.diag_destroy		= tcp_abort,
 };
 EXPORT_SYMBOL(tcp_prot);
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 2379c1b4efb2..18bc7f745e9c 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -8,75 +8,49 @@
 
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
+	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct page_counter *counter_parent = NULL;
 	/*
 	 * The root cgroup does not use page_counters, but rather,
 	 * rely on the data already collected by the network
 	 * subsystem
 	 */
-	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)
+	if (memcg == root_mem_cgroup)
 		return 0;
 
-	cg_proto->sysctl_mem[0] = sysctl_tcp_mem[0];
-	cg_proto->sysctl_mem[1] = sysctl_tcp_mem[1];
-	cg_proto->sysctl_mem[2] = sysctl_tcp_mem[2];
-	cg_proto->memory_pressure = 0;
-	cg_proto->memcg = memcg;
+	memcg->tcp_mem.memory_pressure = 0;
 
-	parent_cg = tcp_prot.proto_cgroup(parent);
-	if (parent_cg)
-		counter_parent = &parent_cg->memory_allocated;
+	if (parent)
+		counter_parent = &parent->tcp_mem.memory_allocated;
 
-	page_counter_init(&cg_proto->memory_allocated, counter_parent);
-	percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL);
+	page_counter_init(&memcg->tcp_mem.memory_allocated, counter_parent);
 
 	return 0;
 }
-EXPORT_SYMBOL(tcp_init_cgroup);
 
 void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 {
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
+	if (memcg == root_mem_cgroup)
 		return;
 
-	percpu_counter_destroy(&cg_proto->sockets_allocated);
-
-	if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags))
-		static_key_slow_dec(&memcg_socket_limit_enabled);
-
+	if (memcg->tcp_mem.active)
+		static_branch_dec(&memcg_sockets_enabled_key);
 }
-EXPORT_SYMBOL(tcp_destroy_cgroup);
 
 static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
 {
-	struct cg_proto *cg_proto;
-	int i;
 	int ret;
 
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
+	if (memcg == root_mem_cgroup)
 		return -EINVAL;
 
-	ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages);
+	ret = page_counter_limit(&memcg->tcp_mem.memory_allocated, nr_pages);
 	if (ret)
 		return ret;
 
-	for (i = 0; i < 3; i++)
-		cg_proto->sysctl_mem[i] = min_t(long, nr_pages,
-						sysctl_tcp_mem[i]);
-
-	if (nr_pages == PAGE_COUNTER_MAX)
-		clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
-	else {
+	if (!memcg->tcp_mem.active) {
 		/*
-		 * The active bit needs to be written after the static_key
+		 * The active flag needs to be written after the static_key
 		 * update. This is what guarantees that the socket activation
 		 * function is the last one to run. See sock_update_memcg() for
 		 * details, and note that we don't mark any socket as belonging
@@ -90,14 +64,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
 		 * We never race with the readers in sock_update_memcg(),
 		 * because when this value change, the code to process it is not
 		 * patched in yet.
-		 *
-		 * The activated bit is used to guarantee that no two writers
-		 * will do the update in the same memcg. Without that, we can't
-		 * properly shutdown the static key.
 		 */
-		if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags))
-			static_key_slow_inc(&memcg_socket_limit_enabled);
-		set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
+		static_branch_inc(&memcg_sockets_enabled_key);
+		memcg->tcp_mem.active = true;
 	}
 
 	return 0;
@@ -141,32 +110,32 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 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:
-		if (!cg_proto)
-			return PAGE_COUNTER_MAX;
-		val = cg_proto->memory_allocated.limit;
+		if (memcg == root_mem_cgroup)
+			val = PAGE_COUNTER_MAX;
+		else
+			val = memcg->tcp_mem.memory_allocated.limit;
 		val *= PAGE_SIZE;
 		break;
 	case RES_USAGE:
-		if (!cg_proto)
+		if (memcg == root_mem_cgroup)
 			val = atomic_long_read(&tcp_memory_allocated);
 		else
-			val = page_counter_read(&cg_proto->memory_allocated);
+			val = page_counter_read(&memcg->tcp_mem.memory_allocated);
 		val *= PAGE_SIZE;
 		break;
 	case RES_FAILCNT:
-		if (!cg_proto)
+		if (memcg == root_mem_cgroup)
 			return 0;
-		val = cg_proto->memory_allocated.failcnt;
+		val = memcg->tcp_mem.memory_allocated.failcnt;
 		break;
 	case RES_MAX_USAGE:
-		if (!cg_proto)
+		if (memcg == root_mem_cgroup)
 			return 0;
-		val = cg_proto->memory_allocated.watermark;
+		val = memcg->tcp_mem.memory_allocated.watermark;
 		val *= PAGE_SIZE;
 		break;
 	default:
@@ -179,19 +148,17 @@ static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg;
-	struct cg_proto *cg_proto;
 
 	memcg = mem_cgroup_from_css(of_css(of));
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
+	if (memcg == root_mem_cgroup)
 		return nbytes;
 
 	switch (of_cft(of)->private) {
 	case RES_MAX_USAGE:
-		page_counter_reset_watermark(&cg_proto->memory_allocated);
+		page_counter_reset_watermark(&memcg->tcp_mem.memory_allocated);
 		break;
 	case RES_FAILCNT:
-		cg_proto->memory_allocated.failcnt = 0;
+		memcg->tcp_mem.memory_allocated.failcnt = 0;
 		break;
 	}
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 412a920fe0ec..fda379cd600d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2813,13 +2813,16 @@ begin_fwd:
  */
 void sk_forced_mem_schedule(struct sock *sk, int size)
 {
-	int amt, status;
+	int amt;
 
 	if (size <= sk->sk_forward_alloc)
 		return;
 	amt = sk_mem_pages(size);
 	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
-	sk_memory_allocated_add(sk, amt, &status);
+	sk_memory_allocated_add(sk, amt);
+
+	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
+		mem_cgroup_charge_skmem(sk->sk_memcg, amt);
 }
 
 /* Send a FIN. The caller locks the socket for us.
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index db9f1c318afc..4ad8edb46f7c 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1889,9 +1889,6 @@ struct proto tcpv6_prot = {
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
 #endif
-#ifdef CONFIG_MEMCG_KMEM
-	.proto_cgroup		= tcp_proto_cgroup,
-#endif
 	.clear_sk		= tcp_v6_clear_sk,
 	.diag_destroy		= tcp_abort,
 };
diff --git a/net/socket.c b/net/socket.c
index 91c2de6f5020..c044d1e8508c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -294,7 +294,7 @@ static int init_inodecache(void)
 					      0,
 					      (SLAB_HWCACHE_ALIGN |
 					       SLAB_RECLAIM_ACCOUNT |
-					       SLAB_MEM_SPREAD),
+					       SLAB_MEM_SPREAD | SLAB_ACCOUNT),
 					      init_once);
 	if (sock_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index d81186d34558..14f45bf0410c 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1500,7 +1500,7 @@ int register_rpc_pipefs(void)
 	rpc_inode_cachep = kmem_cache_create("rpc_inode_cache",
 				sizeof(struct rpc_inode),
 				0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 				init_once);
 	if (!rpc_inode_cachep)
 		return -ENOMEM;