1 files changed, 152 insertions, 54 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index b23f174ab84c..5c5af9988f94 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -111,6 +111,8 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/user_namespace.h>
+#include <linux/jump_label.h>
+#include <linux/memcontrol.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -125,6 +127,7 @@
 #include <net/xfrm.h>
 #include <linux/ipsec.h>
 #include <net/cls_cgroup.h>
+#include <net/netprio_cgroup.h>
 
 #include <linux/filter.h>
 
@@ -134,6 +137,46 @@
 #include <net/tcp.h>
 #endif
 
+static DEFINE_MUTEX(proto_list_mutex);
+static LIST_HEAD(proto_list);
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+int mem_cgroup_sockets_init(struct cgroup *cgrp, 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(cgrp, 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(cgrp, ss);
+	mutex_unlock(&proto_list_mutex);
+	return ret;
+}
+
+void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	struct proto *proto;
+
+	mutex_lock(&proto_list_mutex);
+	list_for_each_entry_reverse(proto, &proto_list, node)
+		if (proto->destroy_cgroup)
+			proto->destroy_cgroup(cgrp, ss);
+	mutex_unlock(&proto_list_mutex);
+}
+#endif
+
 /*
  * Each address family might have different locking rules, so we have
  * one slock key per address family:
@@ -141,6 +184,9 @@
 static struct lock_class_key af_family_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
 
+struct jump_label_key memcg_socket_limit_enabled;
+EXPORT_SYMBOL(memcg_socket_limit_enabled);
+
 /*
  * Make lock validator output more readable. (we pre-construct these
  * strings build-time, so that runtime initialization of socket
@@ -221,10 +267,16 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
-#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP)
+#if defined(CONFIG_CGROUPS)
+#if !defined(CONFIG_NET_CLS_CGROUP)
 int net_cls_subsys_id = -1;
 EXPORT_SYMBOL_GPL(net_cls_subsys_id);
 #endif
+#if !defined(CONFIG_NETPRIO_CGROUP)
+int net_prio_subsys_id = -1;
+EXPORT_SYMBOL_GPL(net_prio_subsys_id);
+#endif
+#endif
 
 static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
 {
@@ -269,14 +321,14 @@ static void sock_warn_obsolete_bsdism(const char *name)
 	}
 }
 
-static void sock_disable_timestamp(struct sock *sk, int flag)
+#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
+
+static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
 {
-	if (sock_flag(sk, flag)) {
-		sock_reset_flag(sk, flag);
-		if (!sock_flag(sk, SOCK_TIMESTAMP) &&
-		    !sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) {
+	if (sk->sk_flags & flags) {
+		sk->sk_flags &= ~flags;
+		if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP))
 			net_disable_timestamp();
-		}
 	}
 }
 
@@ -678,7 +730,7 @@ set_rcvbuf:
 					      SOCK_TIMESTAMPING_RX_SOFTWARE);
 		else
 			sock_disable_timestamp(sk,
-					       SOCK_TIMESTAMPING_RX_SOFTWARE);
+					       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
 		sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE,
 				  val & SOF_TIMESTAMPING_SOFTWARE);
 		sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE,
@@ -736,6 +788,11 @@ set_rcvbuf:
 	case SO_RXQ_OVFL:
 		sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
 		break;
+
+	case SO_WIFI_STATUS:
+		sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
+		break;
+
 	default:
 		ret = -ENOPROTOOPT;
 		break;
@@ -957,6 +1014,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = !!sock_flag(sk, SOCK_RXQ_OVFL);
 		break;
 
+	case SO_WIFI_STATUS:
+		v.val = !!sock_flag(sk, SOCK_WIFI_STATUS);
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -1107,6 +1168,18 @@ void sock_update_classid(struct sock *sk)
 		sk->sk_classid = classid;
 }
 EXPORT_SYMBOL(sock_update_classid);
+
+void sock_update_netprioidx(struct sock *sk)
+{
+	struct cgroup_netprio_state *state;
+	if (in_interrupt())
+		return;
+	rcu_read_lock();
+	state = task_netprio_state(current);
+	sk->sk_cgrp_prioidx = state ? state->prioidx : 0;
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(sock_update_netprioidx);
 #endif
 
 /**
@@ -1134,6 +1207,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		atomic_set(&sk->sk_wmem_alloc, 1);
 
 		sock_update_classid(sk);
+		sock_update_netprioidx(sk);
 	}
 
 	return sk;
@@ -1154,8 +1228,7 @@ static void __sk_free(struct sock *sk)
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 	}
 
-	sock_disable_timestamp(sk, SOCK_TIMESTAMP);
-	sock_disable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE);
+	sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
 
 	if (atomic_read(&sk->sk_omem_alloc))
 		printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
@@ -1200,7 +1273,20 @@ void sk_release_kernel(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_release_kernel);
 
-struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
+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
+ *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ *
+ *	Caller must unlock socket even in error path (bh_unlock_sock(newsk))
+ */
+struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 {
 	struct sock *newsk;
 
@@ -1283,17 +1369,18 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 		sk_set_socket(newsk, NULL);
 		newsk->sk_wq = NULL;
 
+		sk_update_clone(sk, newsk);
+
 		if (newsk->sk_prot->sockets_allocated)
-			percpu_counter_inc(newsk->sk_prot->sockets_allocated);
+			sk_sockets_allocated_inc(newsk);
 
-		if (sock_flag(newsk, SOCK_TIMESTAMP) ||
-		    sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE))
+		if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
 			net_enable_timestamp();
 	}
 out:
 	return newsk;
 }
-EXPORT_SYMBOL_GPL(sk_clone);
+EXPORT_SYMBOL_GPL(sk_clone_lock);
 
 void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
@@ -1673,30 +1760,34 @@ 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 = atomic_long_add_return(amt, prot->memory_allocated);
+
+	allocated = sk_memory_allocated_add(sk, amt, &parent_status);
 
 	/* Under limit. */
-	if (allocated <= prot->sysctl_mem[0]) {
-		if (prot->memory_pressure && *prot->memory_pressure)
-			*prot->memory_pressure = 0;
+	if (parent_status == UNDER_LIMIT &&
+			allocated <= sk_prot_mem_limits(sk, 0)) {
+		sk_leave_memory_pressure(sk);
 		return 1;
 	}
 
-	/* Under pressure. */
-	if (allocated > prot->sysctl_mem[1])
-		if (prot->enter_memory_pressure)
-			prot->enter_memory_pressure(sk);
+	/* Under pressure. (we or our parents) */
+	if ((parent_status > SOFT_LIMIT) ||
+			allocated > sk_prot_mem_limits(sk, 1))
+		sk_enter_memory_pressure(sk);
 
-	/* Over hard limit. */
-	if (allocated > prot->sysctl_mem[2])
+	/* Over hard limit (we or our parents) */
+	if ((parent_status == OVER_LIMIT) ||
+			(allocated > sk_prot_mem_limits(sk, 2)))
 		goto suppress_allocation;
 
 	/* guarantee minimum buffer size under pressure */
 	if (kind == SK_MEM_RECV) {
 		if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
 			return 1;
+
 	} else { /* SK_MEM_SEND */
 		if (sk->sk_type == SOCK_STREAM) {
 			if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
@@ -1706,13 +1797,13 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 				return 1;
 	}
 
-	if (prot->memory_pressure) {
+	if (sk_has_memory_pressure(sk)) {
 		int alloc;
 
-		if (!*prot->memory_pressure)
+		if (!sk_under_memory_pressure(sk))
 			return 1;
-		alloc = percpu_counter_read_positive(prot->sockets_allocated);
-		if (prot->sysctl_mem[2] > alloc *
+		alloc = sk_sockets_allocated_read_positive(sk);
+		if (sk_prot_mem_limits(sk, 2) > alloc *
 		    sk_mem_pages(sk->sk_wmem_queued +
 				 atomic_read(&sk->sk_rmem_alloc) +
 				 sk->sk_forward_alloc))
@@ -1735,7 +1826,9 @@ suppress_allocation:
 
 	/* Alas. Undo changes. */
 	sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
-	atomic_long_sub(amt, prot->memory_allocated);
+
+	sk_memory_allocated_sub(sk, amt, parent_status);
+
 	return 0;
 }
 EXPORT_SYMBOL(__sk_mem_schedule);
@@ -1746,15 +1839,13 @@ EXPORT_SYMBOL(__sk_mem_schedule);
  */
 void __sk_mem_reclaim(struct sock *sk)
 {
-	struct proto *prot = sk->sk_prot;
-
-	atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT,
-		   prot->memory_allocated);
+	sk_memory_allocated_sub(sk,
+				sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, 0);
 	sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
 
-	if (prot->memory_pressure && *prot->memory_pressure &&
-	    (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0]))
-		*prot->memory_pressure = 0;
+	if (sk_under_memory_pressure(sk) &&
+	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
+		sk_leave_memory_pressure(sk);
 }
 EXPORT_SYMBOL(__sk_mem_reclaim);
 
@@ -2125,16 +2216,15 @@ EXPORT_SYMBOL(sock_get_timestampns);
 void sock_enable_timestamp(struct sock *sk, int flag)
 {
 	if (!sock_flag(sk, flag)) {
+		unsigned long previous_flags = sk->sk_flags;
+
 		sock_set_flag(sk, flag);
 		/*
 		 * we just set one of the two flags which require net
 		 * time stamping, but time stamping might have been on
 		 * already because of the other one
 		 */
-		if (!sock_flag(sk,
-				flag == SOCK_TIMESTAMP ?
-				SOCK_TIMESTAMPING_RX_SOFTWARE :
-				SOCK_TIMESTAMP))
+		if (!(previous_flags & SK_FLAGS_TIMESTAMP))
 			net_enable_timestamp();
 	}
 }
@@ -2246,9 +2336,6 @@ void sk_common_release(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_common_release);
 
-static DEFINE_RWLOCK(proto_list_lock);
-static LIST_HEAD(proto_list);
-
 #ifdef CONFIG_PROC_FS
 #define PROTO_INUSE_NR	64	/* should be enough for the first time */
 struct prot_inuse {
@@ -2397,10 +2484,10 @@ int proto_register(struct proto *prot, int alloc_slab)
 		}
 	}
 
-	write_lock(&proto_list_lock);
+	mutex_lock(&proto_list_mutex);
 	list_add(&prot->node, &proto_list);
 	assign_proto_idx(prot);
-	write_unlock(&proto_list_lock);
+	mutex_unlock(&proto_list_mutex);
 	return 0;
 
 out_free_timewait_sock_slab_name:
@@ -2423,10 +2510,10 @@ EXPORT_SYMBOL(proto_register);
 
 void proto_unregister(struct proto *prot)
 {
-	write_lock(&proto_list_lock);
+	mutex_lock(&proto_list_mutex);
 	release_proto_idx(prot);
 	list_del(&prot->node);
-	write_unlock(&proto_list_lock);
+	mutex_unlock(&proto_list_mutex);
 
 	if (prot->slab != NULL) {
 		kmem_cache_destroy(prot->slab);
@@ -2449,9 +2536,9 @@ EXPORT_SYMBOL(proto_unregister);
 
 #ifdef CONFIG_PROC_FS
 static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(proto_list_lock)
+	__acquires(proto_list_mutex)
 {
-	read_lock(&proto_list_lock);
+	mutex_lock(&proto_list_mutex);
 	return seq_list_start_head(&proto_list, *pos);
 }
 
@@ -2461,25 +2548,36 @@ static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 }
 
 static void proto_seq_stop(struct seq_file *seq, void *v)
-	__releases(proto_list_lock)
+	__releases(proto_list_mutex)
 {
-	read_unlock(&proto_list_lock);
+	mutex_unlock(&proto_list_mutex);
 }
 
 static char proto_method_implemented(const void *method)
 {
 	return method == NULL ? 'n' : 'y';
 }
+static long sock_prot_memory_allocated(struct proto *proto)
+{
+	return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L;
+}
+
+static char *sock_prot_memory_pressure(struct proto *proto)
+{
+	return proto->memory_pressure != NULL ?
+	proto_memory_pressure(proto) ? "yes" : "no" : "NI";
+}
 
 static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
 {
+
 	seq_printf(seq, "%-9s %4u %6d  %6ld   %-3s %6u   %-3s  %-10s "
 			"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
 		   proto->name,
 		   proto->obj_size,
 		   sock_prot_inuse_get(seq_file_net(seq), proto),
-		   proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L,
-		   proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI",
+		   sock_prot_memory_allocated(proto),
+		   sock_prot_memory_pressure(proto),
 		   proto->max_header,
 		   proto->slab == NULL ? "no" : "yes",
 		   module_name(proto->owner),