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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 72 insertions, 9 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index b3b75419eafe..433f45fc2d68 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -139,6 +139,7 @@ typedef __u64 __bitwise __addrpair;
  *	@skc_node: main hash linkage for various protocol lookup tables
  *	@skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
  *	@skc_tx_queue_mapping: tx queue number for this connection
+ *	@skc_rx_queue_mapping: rx queue number for this connection
  *	@skc_flags: place holder for sk_flags
  *		%SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		%SO_OOBINLINE settings, %SO_TIMESTAMPING settings
@@ -214,7 +215,10 @@ struct sock_common {
 		struct hlist_node	skc_node;
 		struct hlist_nulls_node skc_nulls_node;
 	};
-	int			skc_tx_queue_mapping;
+	unsigned short		skc_tx_queue_mapping;
+#ifdef CONFIG_XPS
+	unsigned short		skc_rx_queue_mapping;
+#endif
 	union {
 		int		skc_incoming_cpu;
 		u32		skc_rcv_wnd;
@@ -315,6 +319,9 @@ struct sock_common {
   *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
   *	@sk_reuseport_cb: reuseport group container
   *	@sk_rcu: used during RCU grace period
+  *	@sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
+  *	@sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+  *	@sk_txtime_unused: unused txtime flags
   */
 struct sock {
 	/*
@@ -326,6 +333,9 @@ struct sock {
 #define sk_nulls_node		__sk_common.skc_nulls_node
 #define sk_refcnt		__sk_common.skc_refcnt
 #define sk_tx_queue_mapping	__sk_common.skc_tx_queue_mapping
+#ifdef CONFIG_XPS
+#define sk_rx_queue_mapping	__sk_common.skc_rx_queue_mapping
+#endif
 
 #define sk_dontcopy_begin	__sk_common.skc_dontcopy_begin
 #define sk_dontcopy_end		__sk_common.skc_dontcopy_end
@@ -468,6 +478,12 @@ struct sock {
 	u8			sk_shutdown;
 	u32			sk_tskey;
 	atomic_t		sk_zckey;
+
+	u8			sk_clockid;
+	u8			sk_txtime_deadline_mode : 1,
+				sk_txtime_report_errors : 1,
+				sk_txtime_unused : 6;
+
 	struct socket		*sk_socket;
 	void			*sk_user_data;
 #ifdef CONFIG_SECURITY
@@ -783,6 +799,7 @@ enum sock_flags {
 	SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
 	SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
+	SOCK_TXTIME,
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -1578,10 +1595,17 @@ void sock_kzfree_s(struct sock *sk, void *mem, int size);
 void sk_send_sigurg(struct sock *sk);
 
 struct sockcm_cookie {
+	u64 transmit_time;
 	u32 mark;
 	u16 tsflags;
 };
 
+static inline void sockcm_init(struct sockcm_cookie *sockc,
+			       const struct sock *sk)
+{
+	*sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags };
+}
+
 int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
 		     struct sockcm_cookie *sockc);
 int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
@@ -1681,19 +1705,58 @@ static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 
 static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
 {
+	/* sk_tx_queue_mapping accept only upto a 16-bit value */
+	if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX))
+		return;
 	sk->sk_tx_queue_mapping = tx_queue;
 }
 
+#define NO_QUEUE_MAPPING	USHRT_MAX
+
 static inline void sk_tx_queue_clear(struct sock *sk)
 {
-	sk->sk_tx_queue_mapping = -1;
+	sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING;
 }
 
 static inline int sk_tx_queue_get(const struct sock *sk)
 {
-	return sk ? sk->sk_tx_queue_mapping : -1;
+	if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING)
+		return sk->sk_tx_queue_mapping;
+
+	return -1;
 }
 
+static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb)
+{
+#ifdef CONFIG_XPS
+	if (skb_rx_queue_recorded(skb)) {
+		u16 rx_queue = skb_get_rx_queue(skb);
+
+		if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING))
+			return;
+
+		sk->sk_rx_queue_mapping = rx_queue;
+	}
+#endif
+}
+
+static inline void sk_rx_queue_clear(struct sock *sk)
+{
+#ifdef CONFIG_XPS
+	sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING;
+#endif
+}
+
+#ifdef CONFIG_XPS
+static inline int sk_rx_queue_get(const struct sock *sk)
+{
+	if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING)
+		return sk->sk_rx_queue_mapping;
+
+	return -1;
+}
+#endif
+
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
 	sk_tx_queue_clear(sk);
@@ -1725,7 +1788,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 {
 	WARN_ON(parent->sk);
 	write_lock_bh(&sk->sk_callback_lock);
-	sk->sk_wq = parent->wq;
+	rcu_assign_pointer(sk->sk_wq, parent->wq);
 	parent->sk = sk;
 	sk_set_socket(sk, parent);
 	sk->sk_uid = SOCK_INODE(parent)->i_uid;
@@ -1994,16 +2057,16 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq)
 /**
  * sock_poll_wait - place memory barrier behind the poll_wait call.
  * @filp:           file
- * @wait_address:   socket wait queue
  * @p:              poll_table
  *
  * See the comments in the wq_has_sleeper function.
  */
-static inline void sock_poll_wait(struct file *filp,
-		wait_queue_head_t *wait_address, poll_table *p)
+static inline void sock_poll_wait(struct file *filp, poll_table *p)
 {
-	if (!poll_does_not_wait(p) && wait_address) {
-		poll_wait(filp, wait_address, p);
+	struct socket *sock = filp->private_data;
+
+	if (!poll_does_not_wait(p)) {
+		poll_wait(filp, &sock->wq->wait, p);
 		/* We need to be sure we are in sync with the
 		 * socket flags modification.
 		 *