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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

1 files changed, 140 insertions, 14 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index b416a537bd0a..b5baeb9cb0fb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -247,12 +247,66 @@ static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
 static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
 	_sock_locks("k-clock-")
 };
+static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
+  "rlock-AF_UNSPEC", "rlock-AF_UNIX"     , "rlock-AF_INET"     ,
+  "rlock-AF_AX25"  , "rlock-AF_IPX"      , "rlock-AF_APPLETALK",
+  "rlock-AF_NETROM", "rlock-AF_BRIDGE"   , "rlock-AF_ATMPVC"   ,
+  "rlock-AF_X25"   , "rlock-AF_INET6"    , "rlock-AF_ROSE"     ,
+  "rlock-AF_DECnet", "rlock-AF_NETBEUI"  , "rlock-AF_SECURITY" ,
+  "rlock-AF_KEY"   , "rlock-AF_NETLINK"  , "rlock-AF_PACKET"   ,
+  "rlock-AF_ASH"   , "rlock-AF_ECONET"   , "rlock-AF_ATMSVC"   ,
+  "rlock-AF_RDS"   , "rlock-AF_SNA"      , "rlock-AF_IRDA"     ,
+  "rlock-AF_PPPOX" , "rlock-AF_WANPIPE"  , "rlock-AF_LLC"      ,
+  "rlock-27"       , "rlock-28"          , "rlock-AF_CAN"      ,
+  "rlock-AF_TIPC"  , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV"     ,
+  "rlock-AF_RXRPC" , "rlock-AF_ISDN"     , "rlock-AF_PHONET"   ,
+  "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG"      ,
+  "rlock-AF_NFC"   , "rlock-AF_VSOCK"    , "rlock-AF_KCM"      ,
+  "rlock-AF_QIPCRTR", "rlock-AF_SMC"     , "rlock-AF_MAX"
+};
+static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
+  "wlock-AF_UNSPEC", "wlock-AF_UNIX"     , "wlock-AF_INET"     ,
+  "wlock-AF_AX25"  , "wlock-AF_IPX"      , "wlock-AF_APPLETALK",
+  "wlock-AF_NETROM", "wlock-AF_BRIDGE"   , "wlock-AF_ATMPVC"   ,
+  "wlock-AF_X25"   , "wlock-AF_INET6"    , "wlock-AF_ROSE"     ,
+  "wlock-AF_DECnet", "wlock-AF_NETBEUI"  , "wlock-AF_SECURITY" ,
+  "wlock-AF_KEY"   , "wlock-AF_NETLINK"  , "wlock-AF_PACKET"   ,
+  "wlock-AF_ASH"   , "wlock-AF_ECONET"   , "wlock-AF_ATMSVC"   ,
+  "wlock-AF_RDS"   , "wlock-AF_SNA"      , "wlock-AF_IRDA"     ,
+  "wlock-AF_PPPOX" , "wlock-AF_WANPIPE"  , "wlock-AF_LLC"      ,
+  "wlock-27"       , "wlock-28"          , "wlock-AF_CAN"      ,
+  "wlock-AF_TIPC"  , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV"     ,
+  "wlock-AF_RXRPC" , "wlock-AF_ISDN"     , "wlock-AF_PHONET"   ,
+  "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG"      ,
+  "wlock-AF_NFC"   , "wlock-AF_VSOCK"    , "wlock-AF_KCM"      ,
+  "wlock-AF_QIPCRTR", "wlock-AF_SMC"     , "wlock-AF_MAX"
+};
+static const char *const af_family_elock_key_strings[AF_MAX+1] = {
+  "elock-AF_UNSPEC", "elock-AF_UNIX"     , "elock-AF_INET"     ,
+  "elock-AF_AX25"  , "elock-AF_IPX"      , "elock-AF_APPLETALK",
+  "elock-AF_NETROM", "elock-AF_BRIDGE"   , "elock-AF_ATMPVC"   ,
+  "elock-AF_X25"   , "elock-AF_INET6"    , "elock-AF_ROSE"     ,
+  "elock-AF_DECnet", "elock-AF_NETBEUI"  , "elock-AF_SECURITY" ,
+  "elock-AF_KEY"   , "elock-AF_NETLINK"  , "elock-AF_PACKET"   ,
+  "elock-AF_ASH"   , "elock-AF_ECONET"   , "elock-AF_ATMSVC"   ,
+  "elock-AF_RDS"   , "elock-AF_SNA"      , "elock-AF_IRDA"     ,
+  "elock-AF_PPPOX" , "elock-AF_WANPIPE"  , "elock-AF_LLC"      ,
+  "elock-27"       , "elock-28"          , "elock-AF_CAN"      ,
+  "elock-AF_TIPC"  , "elock-AF_BLUETOOTH", "elock-AF_IUCV"     ,
+  "elock-AF_RXRPC" , "elock-AF_ISDN"     , "elock-AF_PHONET"   ,
+  "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG"      ,
+  "elock-AF_NFC"   , "elock-AF_VSOCK"    , "elock-AF_KCM"      ,
+  "elock-AF_QIPCRTR", "elock-AF_SMC"     , "elock-AF_MAX"
+};
 
 /*
- * sk_callback_lock locking rules are per-address-family,
+ * sk_callback_lock and sk queues locking rules are per-address-family,
  * so split the lock classes by using a per-AF key:
  */
 static struct lock_class_key af_callback_keys[AF_MAX];
+static struct lock_class_key af_rlock_keys[AF_MAX];
+static struct lock_class_key af_wlock_keys[AF_MAX];
+static struct lock_class_key af_elock_keys[AF_MAX];
 static struct lock_class_key af_kern_callback_keys[AF_MAX];
 
 /* Take into consideration the size of the struct sk_buff overhead in the
@@ -1029,6 +1083,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 
 	union {
 		int val;
+		u64 val64;
 		struct linger ling;
 		struct timeval tm;
 	} v;
@@ -1259,6 +1314,40 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sk->sk_incoming_cpu;
 		break;
 
+	case SO_MEMINFO:
+	{
+		u32 meminfo[SK_MEMINFO_VARS];
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		sk_get_meminfo(sk, meminfo);
+
+		len = min_t(unsigned int, len, sizeof(meminfo));
+		if (copy_to_user(optval, &meminfo, len))
+			return -EFAULT;
+
+		goto lenout;
+	}
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	case SO_INCOMING_NAPI_ID:
+		v.val = READ_ONCE(sk->sk_napi_id);
+
+		/* aggregate non-NAPI IDs down to 0 */
+		if (v.val < MIN_NAPI_ID)
+			v.val = 0;
+
+		break;
+#endif
+
+	case SO_COOKIE:
+		lv = sizeof(u64);
+		if (len < lv)
+			return -EINVAL;
+		v.val64 = sock_gen_cookie(sk);
+		break;
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).
@@ -1483,6 +1572,27 @@ void sk_free(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_free);
 
+static void sk_init_common(struct sock *sk)
+{
+	skb_queue_head_init(&sk->sk_receive_queue);
+	skb_queue_head_init(&sk->sk_write_queue);
+	skb_queue_head_init(&sk->sk_error_queue);
+
+	rwlock_init(&sk->sk_callback_lock);
+	lockdep_set_class_and_name(&sk->sk_receive_queue.lock,
+			af_rlock_keys + sk->sk_family,
+			af_family_rlock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_write_queue.lock,
+			af_wlock_keys + sk->sk_family,
+			af_family_wlock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_error_queue.lock,
+			af_elock_keys + sk->sk_family,
+			af_family_elock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_callback_lock,
+			af_callback_keys + sk->sk_family,
+			af_family_clock_key_strings[sk->sk_family]);
+}
+
 /**
  *	sk_clone_lock - clone a socket, and lock its clone
  *	@sk: the socket to clone
@@ -1516,13 +1626,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		atomic_set(&newsk->sk_wmem_alloc, 1);
 		atomic_set(&newsk->sk_omem_alloc, 0);
-		skb_queue_head_init(&newsk->sk_receive_queue);
-		skb_queue_head_init(&newsk->sk_write_queue);
-
-		rwlock_init(&newsk->sk_callback_lock);
-		lockdep_set_class_and_name(&newsk->sk_callback_lock,
-				af_callback_keys + newsk->sk_family,
-				af_family_clock_key_strings[newsk->sk_family]);
+		sk_init_common(newsk);
 
 		newsk->sk_dst_cache	= NULL;
 		newsk->sk_dst_pending_confirm = 0;
@@ -1533,7 +1637,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 
 		sock_reset_flag(newsk, SOCK_DONE);
-		skb_queue_head_init(&newsk->sk_error_queue);
 
 		filter = rcu_dereference_protected(newsk->sk_filter, 1);
 		if (filter != NULL)
@@ -2466,10 +2569,7 @@ EXPORT_SYMBOL(sk_stop_timer);
 
 void sock_init_data(struct socket *sock, struct sock *sk)
 {
-	skb_queue_head_init(&sk->sk_receive_queue);
-	skb_queue_head_init(&sk->sk_write_queue);
-	skb_queue_head_init(&sk->sk_error_queue);
-
+	sk_init_common(sk);
 	sk->sk_send_head	=	NULL;
 
 	init_timer(&sk->sk_timer);
@@ -2521,7 +2621,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_rcvtimeo		=	MAX_SCHEDULE_TIMEOUT;
 	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;
 
-	sk->sk_stamp = ktime_set(-1L, 0);
+	sk->sk_stamp = SK_DEFAULT_STAMP;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id		=	0;
@@ -2802,6 +2902,21 @@ void sk_common_release(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_common_release);
 
+void sk_get_meminfo(const struct sock *sk, u32 *mem)
+{
+	memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
+
+	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
+	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
+	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
+	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+}
+
 #ifdef CONFIG_PROC_FS
 #define PROTO_INUSE_NR	64	/* should be enough for the first time */
 struct prot_inuse {
@@ -3142,3 +3257,14 @@ static int __init proto_init(void)
 subsys_initcall(proto_init);
 
 #endif /* PROC_FS */
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+bool sk_busy_loop_end(void *p, unsigned long start_time)
+{
+	struct sock *sk = p;
+
+	return !skb_queue_empty(&sk->sk_receive_queue) ||
+	       sk_busy_loop_timeout(sk, start_time);
+}
+EXPORT_SYMBOL(sk_busy_loop_end);
+#endif /* CONFIG_NET_RX_BUSY_POLL */