1 files changed, 80 insertions, 71 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 79532540201..15635074570 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -156,7 +156,7 @@ typedef __u64 __bitwise __addrpair;
  */
 struct sock_common {
 	/* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned
-	 * address on 64bit arches : cf INET_MATCH() and INET_TW_MATCH()
+	 * address on 64bit arches : cf INET_MATCH()
 	 */
 	union {
 		__addrpair	skc_addrpair;
@@ -191,6 +191,12 @@ struct sock_common {
 #ifdef CONFIG_NET_NS
 	struct net	 	*skc_net;
 #endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+	struct in6_addr		skc_v6_daddr;
+	struct in6_addr		skc_v6_rcv_saddr;
+#endif
+
 	/*
 	 * fields between dontcopy_begin/dontcopy_end
 	 * are not copied in sock_copy()
@@ -237,7 +243,8 @@ struct cg_proto;
   *	@sk_sndbuf: size of send buffer in bytes
   *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
   *		   %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
-  *	@sk_no_check: %SO_NO_CHECK setting, whether or not checkup packets
+  *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
+  *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
   *	@sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
   *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
@@ -301,6 +308,8 @@ struct sock {
 #define sk_dontcopy_end		__sk_common.skc_dontcopy_end
 #define sk_hash			__sk_common.skc_hash
 #define sk_portpair		__sk_common.skc_portpair
+#define sk_num			__sk_common.skc_num
+#define sk_dport		__sk_common.skc_dport
 #define sk_addrpair		__sk_common.skc_addrpair
 #define sk_daddr		__sk_common.skc_daddr
 #define sk_rcv_saddr		__sk_common.skc_rcv_saddr
@@ -312,6 +321,9 @@ struct sock {
 #define sk_bind_node		__sk_common.skc_bind_node
 #define sk_prot			__sk_common.skc_prot
 #define sk_net			__sk_common.skc_net
+#define sk_v6_daddr		__sk_common.skc_v6_daddr
+#define sk_v6_rcv_saddr	__sk_common.skc_v6_rcv_saddr
+
 	socket_lock_t		sk_lock;
 	struct sk_buff_head	sk_receive_queue;
 	/*
@@ -360,7 +372,8 @@ struct sock {
 	struct sk_buff_head	sk_write_queue;
 	kmemcheck_bitfield_begin(flags);
 	unsigned int		sk_shutdown  : 2,
-				sk_no_check  : 2,
+				sk_no_check_tx : 1,
+				sk_no_check_rx : 1,
 				sk_userlocks : 4,
 				sk_protocol  : 8,
 				sk_type      : 16;
@@ -384,7 +397,7 @@ struct sock {
 	unsigned short		sk_ack_backlog;
 	unsigned short		sk_max_ack_backlog;
 	__u32			sk_priority;
-#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 	__u32			sk_cgrp_prioidx;
 #endif
 	struct pid		*sk_peer_pid;
@@ -407,7 +420,7 @@ struct sock {
 	u32			sk_classid;
 	struct cg_proto		*sk_cgrp;
 	void			(*sk_state_change)(struct sock *sk);
-	void			(*sk_data_ready)(struct sock *sk, int bytes);
+	void			(*sk_data_ready)(struct sock *sk);
 	void			(*sk_write_space)(struct sock *sk);
 	void			(*sk_error_report)(struct sock *sk);
 	int			(*sk_backlog_rcv)(struct sock *sk,
@@ -809,37 +822,51 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 	return sk->sk_backlog_rcv(sk, skb);
 }
 
-static inline void sock_rps_record_flow(const struct sock *sk)
+static inline void sock_rps_record_flow_hash(__u32 hash)
 {
 #ifdef CONFIG_RPS
 	struct rps_sock_flow_table *sock_flow_table;
 
 	rcu_read_lock();
 	sock_flow_table = rcu_dereference(rps_sock_flow_table);
-	rps_record_sock_flow(sock_flow_table, sk->sk_rxhash);
+	rps_record_sock_flow(sock_flow_table, hash);
 	rcu_read_unlock();
 #endif
 }
 
-static inline void sock_rps_reset_flow(const struct sock *sk)
+static inline void sock_rps_reset_flow_hash(__u32 hash)
 {
 #ifdef CONFIG_RPS
 	struct rps_sock_flow_table *sock_flow_table;
 
 	rcu_read_lock();
 	sock_flow_table = rcu_dereference(rps_sock_flow_table);
-	rps_reset_sock_flow(sock_flow_table, sk->sk_rxhash);
+	rps_reset_sock_flow(sock_flow_table, hash);
 	rcu_read_unlock();
 #endif
 }
 
+static inline void sock_rps_record_flow(const struct sock *sk)
+{
+#ifdef CONFIG_RPS
+	sock_rps_record_flow_hash(sk->sk_rxhash);
+#endif
+}
+
+static inline void sock_rps_reset_flow(const struct sock *sk)
+{
+#ifdef CONFIG_RPS
+	sock_rps_reset_flow_hash(sk->sk_rxhash);
+#endif
+}
+
 static inline void sock_rps_save_rxhash(struct sock *sk,
 					const struct sk_buff *skb)
 {
 #ifdef CONFIG_RPS
-	if (unlikely(sk->sk_rxhash != skb->rxhash)) {
+	if (unlikely(sk->sk_rxhash != skb->hash)) {
 		sock_rps_reset_flow(sk);
-		sk->sk_rxhash = skb->rxhash;
+		sk->sk_rxhash = skb->hash;
 	}
 #endif
 }
@@ -1024,11 +1051,10 @@ enum cg_proto_flags {
 };
 
 struct cg_proto {
-	void			(*enter_memory_pressure)(struct sock *sk);
-	struct res_counter	*memory_allocated;	/* Current allocated memory. */
-	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
-	int			*memory_pressure;
-	long			*sysctl_mem;
+	struct res_counter	memory_allocated;	/* Current allocated memory. */
+	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
+	int			memory_pressure;
+	long			sysctl_mem[3];
 	unsigned long		flags;
 	/*
 	 * memcg field is used to find which memcg we belong directly
@@ -1124,7 +1150,7 @@ static inline bool sk_under_memory_pressure(const struct sock *sk)
 		return false;
 
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		return !!*sk->sk_cgrp->memory_pressure;
+		return !!sk->sk_cgrp->memory_pressure;
 
 	return !!*sk->sk_prot->memory_pressure;
 }
@@ -1144,8 +1170,7 @@ static inline void sk_leave_memory_pressure(struct sock *sk)
 		struct proto *prot = sk->sk_prot;
 
 		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
-			if (*cg_proto->memory_pressure)
-				*cg_proto->memory_pressure = 0;
+			cg_proto->memory_pressure = 0;
 	}
 
 }
@@ -1160,7 +1185,7 @@ static inline void sk_enter_memory_pressure(struct sock *sk)
 		struct proto *prot = sk->sk_prot;
 
 		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
-			cg_proto->enter_memory_pressure(sk);
+			cg_proto->memory_pressure = 1;
 	}
 
 	sk->sk_prot->enter_memory_pressure(sk);
@@ -1181,7 +1206,7 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
 	struct res_counter *fail;
 	int ret;
 
-	ret = res_counter_charge_nofail(prot->memory_allocated,
+	ret = res_counter_charge_nofail(&prot->memory_allocated,
 					amt << PAGE_SHIFT, &fail);
 	if (ret < 0)
 		*parent_status = OVER_LIMIT;
@@ -1190,13 +1215,13 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
 static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
 					      unsigned long amt)
 {
-	res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT);
+	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);
+	ret = res_counter_read_u64(&prot->memory_allocated, RES_USAGE);
 	return ret >> PAGE_SHIFT;
 }
 
@@ -1244,7 +1269,7 @@ static inline void sk_sockets_allocated_dec(struct sock *sk)
 		struct cg_proto *cg_proto = sk->sk_cgrp;
 
 		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
-			percpu_counter_dec(cg_proto->sockets_allocated);
+			percpu_counter_dec(&cg_proto->sockets_allocated);
 	}
 
 	percpu_counter_dec(prot->sockets_allocated);
@@ -1258,7 +1283,7 @@ static inline void sk_sockets_allocated_inc(struct sock *sk)
 		struct cg_proto *cg_proto = sk->sk_cgrp;
 
 		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
-			percpu_counter_inc(cg_proto->sockets_allocated);
+			percpu_counter_inc(&cg_proto->sockets_allocated);
 	}
 
 	percpu_counter_inc(prot->sockets_allocated);
@@ -1270,7 +1295,7 @@ sk_sockets_allocated_read_positive(struct sock *sk)
 	struct proto *prot = sk->sk_prot;
 
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		return percpu_counter_read_positive(sk->sk_cgrp->sockets_allocated);
+		return percpu_counter_read_positive(&sk->sk_cgrp->sockets_allocated);
 
 	return percpu_counter_read_positive(prot->sockets_allocated);
 }
@@ -1465,6 +1490,11 @@ static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
  */
 #define sock_owned_by_user(sk)	((sk)->sk_lock.owned)
 
+static inline void sock_release_ownership(struct sock *sk)
+{
+	sk->sk_lock.owned = 0;
+}
+
 /*
  * Macro so as to not evaluate some arguments when
  * lockdep is not enabled.
@@ -1526,8 +1556,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
 
 struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
 			     gfp_t priority);
-struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
-			     gfp_t priority);
 void sock_wfree(struct sk_buff *skb);
 void skb_orphan_partial(struct sk_buff *skb);
 void sock_rfree(struct sk_buff *skb);
@@ -1595,35 +1623,6 @@ void sk_common_release(struct sock *sk);
 /* Initialise core socket variables */
 void sock_init_data(struct socket *sock, struct sock *sk);
 
-void sk_filter_release_rcu(struct rcu_head *rcu);
-
-/**
- *	sk_filter_release - release a socket filter
- *	@fp: filter to remove
- *
- *	Remove a filter from a socket and release its resources.
- */
-
-static inline void sk_filter_release(struct sk_filter *fp)
-{
-	if (atomic_dec_and_test(&fp->refcnt))
-		call_rcu(&fp->rcu, sk_filter_release_rcu);
-}
-
-static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
-{
-	unsigned int size = sk_filter_len(fp);
-
-	atomic_sub(size, &sk->sk_omem_alloc);
-	sk_filter_release(fp);
-}
-
-static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
-{
-	atomic_inc(&fp->refcnt);
-	atomic_add(sk_filter_len(fp), &sk->sk_omem_alloc);
-}
-
 /*
  * Socket reference counting postulates.
  *
@@ -1655,6 +1654,10 @@ static inline void sock_put(struct sock *sk)
 	if (atomic_dec_and_test(&sk->sk_refcnt))
 		sk_free(sk);
 }
+/* Generic version of sock_put(), dealing with all sockets
+ * (TCP_TIMEWAIT, ESTABLISHED...)
+ */
+void sock_gen_put(struct sock *sk);
 
 int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested);
 
@@ -1727,14 +1730,12 @@ sk_dst_get(struct sock *sk)
 
 	rcu_read_lock();
 	dst = rcu_dereference(sk->sk_dst_cache);
-	if (dst)
-		dst_hold(dst);
+	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+		dst = NULL;
 	rcu_read_unlock();
 	return dst;
 }
 
-void sk_reset_txq(struct sock *sk);
-
 static inline void dst_negative_advice(struct sock *sk)
 {
 	struct dst_entry *ndst, *dst = __sk_dst_get(sk);
@@ -1744,7 +1745,7 @@ static inline void dst_negative_advice(struct sock *sk)
 
 		if (ndst != dst) {
 			rcu_assign_pointer(sk->sk_dst_cache, ndst);
-			sk_reset_txq(sk);
+			sk_tx_queue_clear(sk);
 		}
 	}
 }
@@ -1767,9 +1768,11 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
 static inline void
 sk_dst_set(struct sock *sk, struct dst_entry *dst)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_set(sk, dst);
-	spin_unlock(&sk->sk_dst_lock);
+	struct dst_entry *old_dst;
+
+	sk_tx_queue_clear(sk);
+	old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
+	dst_release(old_dst);
 }
 
 static inline void
@@ -1781,9 +1784,7 @@ __sk_dst_reset(struct sock *sk)
 static inline void
 sk_dst_reset(struct sock *sk)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_reset(sk);
-	spin_unlock(&sk->sk_dst_lock);
+	sk_dst_set(sk, NULL);
 }
 
 struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
@@ -2165,7 +2166,6 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 {
 #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL)			| \
 			   (1UL << SOCK_RCVTSTAMP)			| \
-			   (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)	| \
 			   (1UL << SOCK_TIMESTAMPING_SOFTWARE)		| \
 			   (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE)	| \
 			   (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE))
@@ -2231,8 +2231,12 @@ void sock_net_set(struct sock *sk, struct net *net)
  */
 static inline void sk_change_net(struct sock *sk, struct net *net)
 {
-	put_net(sock_net(sk));
-	sock_net_set(sk, hold_net(net));
+	struct net *current_net = sock_net(sk);
+
+	if (!net_eq(current_net, net)) {
+		put_net(current_net);
+		sock_net_set(sk, hold_net(net));
+	}
 }
 
 static inline struct sock *skb_steal_sock(struct sk_buff *skb)
@@ -2253,6 +2257,11 @@ int sock_get_timestampns(struct sock *, struct timespec __user *);
 int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
 		       int type);
 
+bool sk_ns_capable(const struct sock *sk,
+		   struct user_namespace *user_ns, int cap);
+bool sk_capable(const struct sock *sk, int cap);
+bool sk_net_capable(const struct sock *sk, int cap);
+
 /*
  *	Enable debug/info messages
  */