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

Pull networking fixes from David Miller:
 "A lot of Thanksgiving turkey leftovers accumulated, here goes:

   1) Fix bluetooth l2cap_chan object leak, from Johan Hedberg.

   2) IDs for some new iwlwifi chips, from Oren Givon.

   3) Fix rtlwifi lockups on boot, from Larry Finger.

   4) Fix memory leak in fm10k, from Stephen Hemminger.

   5) We have a route leak in the ipv6 tunnel infrastructure, fix from
      Paolo Abeni.

   6) Fix buffer pointer handling in arm64 bpf JIT,f rom Zi Shen Lim.

   7) Wrong lockdep annotations in tcp md5 support, fix from Eric
      Dumazet.

   8) Work around some middle boxes which prevent proper handling of TCP
      Fast Open, from Yuchung Cheng.

   9) TCP repair can do huge kmalloc() requests, build paged SKBs
      instead.  From Eric Dumazet.

  10) Fix msg_controllen overflow in scm_detach_fds, from Daniel
      Borkmann.

  11) Fix device leaks on ipmr table destruction in ipv4 and ipv6, from
      Nikolay Aleksandrov.

  12) Fix use after free in epoll with AF_UNIX sockets, from Rainer
      Weikusat.

  13) Fix double free in VRF code, from Nikolay Aleksandrov.

  14) Fix skb leaks on socket receive queue in tipc, from Ying Xue.

  15) Fix ifup/ifdown crach in xgene driver, from Iyappan Subramanian.

  16) Fix clearing of persistent array maps in bpf, from Daniel
      Borkmann.

  17) In TCP, for the cross-SYN case, we don't initialize tp->copied_seq
      early enough.  From Eric Dumazet.

  18) Fix out of bounds accesses in bpf array implementation when
      updating elements, from Daniel Borkmann.

  19) Fill gaps in RCU protection of np->opt in ipv6 stack, from Eric
      Dumazet.

  20) When dumping proxy neigh entries, we have to accomodate NULL
      device pointers properly, from Konstantin Khlebnikov.

  21) SCTP doesn't release all ipv6 socket resources properly, fix from
      Eric Dumazet.

  22) Prevent underflows of sch->q.qlen for multiqueue packet
      schedulers, also from Eric Dumazet.

  23) Fix MAC and unicast list handling in bnxt_en driver, from Jeffrey
      Huang and Michael Chan.

  24) Don't actively scan radar channels, from Antonio Quartulli"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (110 commits)
  net: phy: reset only targeted phy
  bnxt_en: Setup uc_list mac filters after resetting the chip.
  bnxt_en: enforce proper storing of MAC address
  bnxt_en: Fixed incorrect implementation of ndo_set_mac_address
  net: lpc_eth: remove irq > NR_IRQS check from probe()
  net_sched: fix qdisc_tree_decrease_qlen() races
  openvswitch: fix hangup on vxlan/gre/geneve device deletion
  ipv4: igmp: Allow removing groups from a removed interface
  ipv6: sctp: implement sctp_v6_destroy_sock()
  arm64: bpf: add 'store immediate' instruction
  ipv6: kill sk_dst_lock
  ipv6: sctp: add rcu protection around np->opt
  net/neighbour: fix crash at dumping device-agnostic proxy entries
  sctp: use GFP_USER for user-controlled kmalloc
  sctp: convert sack_needed and sack_generation to bits
  ipv6: add complete rcu protection around np->opt
  bpf: fix allocation warnings in bpf maps and integer overflow
  mvebu: dts: enable IP checksum with jumbo frames for Armada 38x on Port0
  net: mvneta: enable setting custom TX IP checksum limit
  net: mvneta: fix error path for building skb
  ...

13 files changed, 84 insertions, 41 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index de464e6683b6..83d1926c61e4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -40,6 +40,7 @@ struct bpf_map {
 	struct user_struct *user;
 	const struct bpf_map_ops *ops;
 	struct work_struct work;
+	atomic_t usercnt;
 };
 
 struct bpf_map_type_list {
@@ -167,8 +168,10 @@ struct bpf_prog *bpf_prog_get(u32 ufd);
 void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_put_rcu(struct bpf_prog *prog);
 
-struct bpf_map *bpf_map_get(u32 ufd);
+struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
+void bpf_map_inc(struct bpf_map *map, bool uref);
+void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 
 extern int sysctl_unprivileged_bpf_disabled;
diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h
index cc92268af89a..6ac3cad9aef1 100644
--- a/include/linux/dns_resolver.h
+++ b/include/linux/dns_resolver.h
@@ -27,7 +27,7 @@
 #ifdef __KERNEL__
 
 extern int dns_query(const char *type, const char *name, size_t namelen,
-		     const char *options, char **_result, time_t *_expiry);
+		     const char *options, char **_result, time64_t *_expiry);
 
 #endif /* KERNEL */
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 0ef2a97ccdb5..402753bccafa 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -227,7 +227,7 @@ struct ipv6_pinfo {
 	struct ipv6_ac_socklist	*ipv6_ac_list;
 	struct ipv6_fl_socklist __rcu *ipv6_fl_list;
 
-	struct ipv6_txoptions	*opt;
+	struct ipv6_txoptions __rcu	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
 	struct inet6_cork	cork;
diff --git a/include/linux/net.h b/include/linux/net.h
index 70ac5e28e6b7..0b4ac7da583a 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -34,8 +34,12 @@ struct inode;
 struct file;
 struct net;
 
-#define SOCK_ASYNC_NOSPACE	0
-#define SOCK_ASYNC_WAITDATA	1
+/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located
+ * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected.
+ * Eventually all flags will be in sk->sk_wq_flags.
+ */
+#define SOCKWQ_ASYNC_NOSPACE	0
+#define SOCKWQ_ASYNC_WAITDATA	1
 #define SOCK_NOSPACE		2
 #define SOCK_PASSCRED		3
 #define SOCK_PASSSEC		4
@@ -89,6 +93,7 @@ struct socket_wq {
 	/* Note: wait MUST be first field of socket_wq */
 	wait_queue_head_t	wait;
 	struct fasync_struct	*fasync_list;
+	unsigned long		flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */
 	struct rcu_head		rcu;
 } ____cacheline_aligned_in_smp;
 
@@ -96,7 +101,7 @@ struct socket_wq {
  *  struct socket - general BSD socket
  *  @state: socket state (%SS_CONNECTED, etc)
  *  @type: socket type (%SOCK_STREAM, etc)
- *  @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
+ *  @flags: socket flags (%SOCK_NOSPACE, etc)
  *  @ops: protocol specific socket operations
  *  @file: File back pointer for gc
  *  @sk: internal networking protocol agnostic socket representation
@@ -202,7 +207,7 @@ enum {
 	SOCK_WAKE_URG,
 };
 
-int sock_wake_async(struct socket *sk, int how, int band);
+int sock_wake_async(struct socket_wq *sk_wq, int how, int band);
 int sock_register(const struct net_proto_family *fam);
 void sock_unregister(int family);
 int __sock_create(struct net *net, int family, int type, int proto,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 67bfac1abfc1..3b5d134e945a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1398,7 +1398,8 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length
+ *	@hard_header_len: Hardware header length, which means that this is the
+ *			  minimum size of a packet.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index b36d837c701e..2a91a0561a47 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -62,6 +62,7 @@ struct unix_sock {
 #define UNIX_GC_CANDIDATE	0
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
+	wait_queue_t		peer_wake;
 };
 
 static inline struct unix_sock *unix_sk(const struct sock *sk)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 2bfb2ad2fab1..877f682989b8 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -133,27 +133,18 @@ void rt6_clean_tohost(struct net *net, struct in6_addr *gateway);
 /*
  *	Store a destination cache entry in a socket
  */
-static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst,
-				   const struct in6_addr *daddr,
-				   const struct in6_addr *saddr)
+static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
+				 const struct in6_addr *daddr,
+				 const struct in6_addr *saddr)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct rt6_info *rt = (struct rt6_info *) dst;
 
+	np->dst_cookie = rt6_get_cookie((struct rt6_info *)dst);
 	sk_setup_caps(sk, dst);
 	np->daddr_cache = daddr;
 #ifdef CONFIG_IPV6_SUBTREES
 	np->saddr_cache = saddr;
 #endif
-	np->dst_cookie = rt6_get_cookie(rt);
-}
-
-static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
-				 struct in6_addr *daddr, struct in6_addr *saddr)
-{
-	spin_lock(&sk->sk_dst_lock);
-	__ip6_dst_store(sk, dst, daddr, saddr);
-	spin_unlock(&sk->sk_dst_lock);
 }
 
 static inline bool ipv6_unicast_destination(const struct sk_buff *skb)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index e1a10b0ac0b0..9a5c9f013784 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock;
  */
 
 struct ipv6_txoptions {
+	atomic_t		refcnt;
 	/* Length of this structure */
 	int			tot_len;
 
@@ -217,7 +218,7 @@ struct ipv6_txoptions {
 	struct ipv6_opt_hdr	*dst0opt;
 	struct ipv6_rt_hdr	*srcrt;	/* Routing Header */
 	struct ipv6_opt_hdr	*dst1opt;
-
+	struct rcu_head		rcu;
 	/* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
 };
 
@@ -252,6 +253,24 @@ struct ipv6_fl_socklist {
 	struct rcu_head			rcu;
 };
 
+static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
+{
+	struct ipv6_txoptions *opt;
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt && !atomic_inc_not_zero(&opt->refcnt))
+		opt = NULL;
+	rcu_read_unlock();
+	return opt;
+}
+
+static inline void txopt_put(struct ipv6_txoptions *opt)
+{
+	if (opt && atomic_dec_and_test(&opt->refcnt))
+		kfree_rcu(opt, rcu);
+}
+
 struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
 struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 					 struct ip6_flowlabel *fl,
@@ -490,6 +509,7 @@ struct ip6_create_arg {
 	u32 user;
 	const struct in6_addr *src;
 	const struct in6_addr *dst;
+	int iif;
 	u8 ecn;
 };
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 82045fca388b..760bc4d5a2cf 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2003,8 +2003,10 @@ enum ieee80211_hw_flags {
  *	it shouldn't be set.
  *
  * @max_tx_aggregation_subframes: maximum number of subframes in an
- *	aggregate an HT driver will transmit, used by the peer as a
- *	hint to size its reorder buffer.
+ *	aggregate an HT driver will transmit. Though ADDBA will advertise
+ *	a constant value of 64 as some older APs can crash if the window
+ *	size is smaller (an example is LinkSys WRT120N with FW v1.0.07
+ *	build 002 Jun 18 2012).
  *
  * @offchannel_tx_hw_queue: HW queue ID to use for offchannel TX
  *	(if %IEEE80211_HW_QUEUE_CONTROL is set)
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index bf3937431030..2d8edaad29cb 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -181,8 +181,7 @@ void ndisc_cleanup(void);
 int ndisc_rcv(struct sk_buff *skb);
 
 void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
-		   const struct in6_addr *daddr, const struct in6_addr *saddr,
-		   struct sk_buff *oskb);
+		   const struct in6_addr *daddr, const struct in6_addr *saddr);
 
 void ndisc_send_rs(struct net_device *dev,
 		   const struct in6_addr *saddr, const struct in6_addr *daddr);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 4c79ce8c1f92..b2a8e6338576 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -61,6 +61,9 @@ struct Qdisc {
 				      */
 #define TCQ_F_WARN_NONWC	(1 << 16)
 #define TCQ_F_CPUSTATS		0x20 /* run using percpu statistics */
+#define TCQ_F_NOPARENT		0x40 /* root of its hierarchy :
+				      * qdisc_tree_decrease_qlen() should stop.
+				      */
 	u32			limit;
 	const struct Qdisc_ops	*ops;
 	struct qdisc_size_table	__rcu *stab;
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 495c87e367b3..7bbb71081aeb 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -775,10 +775,10 @@ struct sctp_transport {
 		hb_sent:1,
 
 		/* Is the Path MTU update pending on this tranport */
-		pmtu_pending:1;
+		pmtu_pending:1,
 
-	/* Has this transport moved the ctsn since we last sacked */
-	__u32 sack_generation;
+		/* Has this transport moved the ctsn since we last sacked */
+		sack_generation:1;
 	u32 dst_cookie;
 
 	struct flowi fl;
@@ -1482,19 +1482,19 @@ struct sctp_association {
 			prsctp_capable:1,   /* Can peer do PR-SCTP? */
 			auth_capable:1;     /* Is peer doing SCTP-AUTH? */
 
-		/* Ack State   : This flag indicates if the next received
+		/* sack_needed : This flag indicates if the next received
 		 *             : packet is to be responded to with a
-		 *             : SACK. This is initializedto 0.  When a packet
-		 *             : is received it is incremented. If this value
+		 *             : SACK. This is initialized to 0.  When a packet
+		 *             : is received sack_cnt is incremented. If this value
 		 *             : reaches 2 or more, a SACK is sent and the
 		 *             : value is reset to 0. Note: This is used only
 		 *             : when no DATA chunks are received out of
 		 *             : order.  When DATA chunks are out of order,
 		 *             : SACK's are not delayed (see Section 6).
 		 */
-		__u8    sack_needed;     /* Do we need to sack the peer? */
+		__u8    sack_needed:1,     /* Do we need to sack the peer? */
+			sack_generation:1;
 		__u32	sack_cnt;
-		__u32	sack_generation;
 
 		__u32   adaptation_ind;	 /* Adaptation Code point. */
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 7f89e4ba18d1..52d27ee924f4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -254,7 +254,6 @@ struct cg_proto;
   *	@sk_wq: sock wait queue and async head
   *	@sk_rx_dst: receive input route used by early demux
   *	@sk_dst_cache: destination cache
-  *	@sk_dst_lock: destination cache lock
   *	@sk_policy: flow policy
   *	@sk_receive_queue: incoming packets
   *	@sk_wmem_alloc: transmit queue bytes committed
@@ -384,14 +383,16 @@ struct sock {
 	int			sk_rcvbuf;
 
 	struct sk_filter __rcu	*sk_filter;
-	struct socket_wq __rcu	*sk_wq;
-
+	union {
+		struct socket_wq __rcu	*sk_wq;
+		struct socket_wq	*sk_wq_raw;
+	};
 #ifdef CONFIG_XFRM
 	struct xfrm_policy	*sk_policy[2];
 #endif
 	struct dst_entry	*sk_rx_dst;
 	struct dst_entry __rcu	*sk_dst_cache;
-	spinlock_t		sk_dst_lock;
+	/* Note: 32bit hole on 64bit arches */
 	atomic_t		sk_wmem_alloc;
 	atomic_t		sk_omem_alloc;
 	int			sk_sndbuf;
@@ -2005,10 +2006,27 @@ static inline unsigned long sock_wspace(struct sock *sk)
 	return amt;
 }
 
-static inline void sk_wake_async(struct sock *sk, int how, int band)
+/* Note:
+ *  We use sk->sk_wq_raw, from contexts knowing this
+ *  pointer is not NULL and cannot disappear/change.
+ */
+static inline void sk_set_bit(int nr, struct sock *sk)
 {
-	if (sock_flag(sk, SOCK_FASYNC))
-		sock_wake_async(sk->sk_socket, how, band);
+	set_bit(nr, &sk->sk_wq_raw->flags);
+}
+
+static inline void sk_clear_bit(int nr, struct sock *sk)
+{
+	clear_bit(nr, &sk->sk_wq_raw->flags);
+}
+
+static inline void sk_wake_async(const struct sock *sk, int how, int band)
+{
+	if (sock_flag(sk, SOCK_FASYNC)) {
+		rcu_read_lock();
+		sock_wake_async(rcu_dereference(sk->sk_wq), how, band);
+		rcu_read_unlock();
+	}
 }
 
 /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might