Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1958 commits)
  net: pack skb_shared_info more efficiently
  net_sched: red: split red_parms into parms and vars
  net_sched: sfq: extend limits
  cnic: Improve error recovery on bnx2x devices
  cnic: Re-init dev->stats_addr after chip reset
  net_sched: Bug in netem reordering
  bna: fix sparse warnings/errors
  bna: make ethtool_ops and strings const
  xgmac: cleanups
  net: make ethtool_ops const
  vmxnet3" make ethtool ops const
  xen-netback: make ops structs const
  virtio_net: Pass gfp flags when allocating rx buffers.
  ixgbe: FCoE: Add support for ndo_get_fcoe_hbainfo() call
  netdev: FCoE: Add new ndo_get_fcoe_hbainfo() call
  igb: reset PHY after recovering from PHY power down
  igb: add basic runtime PM support
  igb: Add support for byte queue limits.
  e1000: cleanup CE4100 MDIO registers access
  e1000: unmap ce4100_gbe_mdio_base_virt in e1000_remove
  ...

1 files changed, 97 insertions, 3 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b63f5f7dfa0..94da8ee9e2c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -50,6 +50,8 @@
 #include <linux/cpu.h>
 #include <linux/oom.h>
 #include "internal.h"
+#include <net/sock.h>
+#include <net/tcp_memcontrol.h>
 
 #include <asm/uaccess.h>
 
@@ -286,6 +288,10 @@ struct mem_cgroup {
 	 */
 	struct mem_cgroup_stat_cpu nocpu_base;
 	spinlock_t pcp_counter_lock;
+
+#ifdef CONFIG_INET
+	struct tcp_memcontrol tcp_mem;
+#endif
 };
 
 /* Stuffs for move charges at task migration. */
@@ -365,7 +371,58 @@ enum charge_type {
 
 static void mem_cgroup_get(struct mem_cgroup *memcg);
 static void mem_cgroup_put(struct mem_cgroup *memcg);
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+
+/* Writing them here to avoid exposing memcg's inner layout */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_INET
+#include <net/sock.h>
+#include <net/ip.h>
+
+static bool mem_cgroup_is_root(struct mem_cgroup *memcg);
+void sock_update_memcg(struct sock *sk)
+{
+	/* A socket spends its whole life in the same cgroup */
+	if (sk->sk_cgrp) {
+		WARN_ON(1);
+		return;
+	}
+	if (static_branch(&memcg_socket_limit_enabled)) {
+		struct mem_cgroup *memcg;
+
+		BUG_ON(!sk->sk_prot->proto_cgroup);
+
+		rcu_read_lock();
+		memcg = mem_cgroup_from_task(current);
+		if (!mem_cgroup_is_root(memcg)) {
+			mem_cgroup_get(memcg);
+			sk->sk_cgrp = sk->sk_prot->proto_cgroup(memcg);
+		}
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(sock_update_memcg);
+
+void sock_release_memcg(struct sock *sk)
+{
+	if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) {
+		struct mem_cgroup *memcg;
+		WARN_ON(!sk->sk_cgrp->memcg);
+		memcg = sk->sk_cgrp->memcg;
+		mem_cgroup_put(memcg);
+	}
+}
+
+struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
+{
+	if (!memcg || mem_cgroup_is_root(memcg))
+		return NULL;
+
+	return &memcg->tcp_mem.cg_proto;
+}
+EXPORT_SYMBOL(tcp_proto_cgroup);
+#endif /* CONFIG_INET */
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+
 static void drain_all_stock_async(struct mem_cgroup *memcg);
 
 static struct mem_cgroup_per_zone *
@@ -745,7 +802,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 	preempt_enable();
 }
 
-static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
+struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 {
 	return container_of(cgroup_subsys_state(cont,
 				mem_cgroup_subsys_id), struct mem_cgroup,
@@ -4612,6 +4669,36 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
 }
 #endif /* CONFIG_NUMA */
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+	/*
+	 * Part of this would be better living in a separate allocation
+	 * function, leaving us with just the cgroup tree population work.
+	 * We, however, depend on state such as network's proto_list that
+	 * is only initialized after cgroup creation. I found the less
+	 * cumbersome way to deal with it to defer it all to populate time
+	 */
+	return mem_cgroup_sockets_init(cont, ss);
+};
+
+static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
+				struct cgroup *cont)
+{
+	mem_cgroup_sockets_destroy(cont, ss);
+}
+#else
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+	return 0;
+}
+
+static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
+				struct cgroup *cont)
+{
+}
+#endif
+
 static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "usage_in_bytes",
@@ -4843,12 +4930,13 @@ static void mem_cgroup_put(struct mem_cgroup *memcg)
 /*
  * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
  */
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
 	if (!memcg->res.parent)
 		return NULL;
 	return mem_cgroup_from_res_counter(memcg->res.parent, res);
 }
+EXPORT_SYMBOL(parent_mem_cgroup);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 static void __init enable_swap_cgroup(void)
@@ -4964,6 +5052,8 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss,
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
+	kmem_cgroup_destroy(ss, cont);
+
 	mem_cgroup_put(memcg);
 }
 
@@ -4977,6 +5067,10 @@ static int mem_cgroup_populate(struct cgroup_subsys *ss,
 
 	if (!ret)
 		ret = register_memsw_files(cont, ss);
+
+	if (!ret)
+		ret = register_kmem_files(cont, ss);
+
 	return ret;
 }