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

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 37 insertions, 20 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f642a39f9eee..b510f284427a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -139,6 +139,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #endif
 #define TCP_RTO_MAX	((unsigned)(120*HZ))
 #define TCP_RTO_MIN	((unsigned)(HZ/5))
+#define TCP_TIMEOUT_MIN	(2U) /* Min timeout for TCP timers in jiffies */
 #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ))	/* RFC6298 2.1 initial RTO value	*/
 #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ))	/* RFC 1122 initial RTO value, now
 						 * used as a fallback RTO for the
@@ -150,8 +151,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes
 					                 * for local resources.
 					                 */
-#define TCP_REO_TIMEOUT_MIN	(2000) /* Min RACK reordering timeout in usec */
-
 #define TCP_KEEPALIVE_TIME	(120*60*HZ)	/* two hours */
 #define TCP_KEEPALIVE_PROBES	9		/* Max of 9 keepalive probes	*/
 #define TCP_KEEPALIVE_INTVL	(75*HZ)
@@ -257,7 +256,6 @@ extern int sysctl_tcp_rmem[3];
 extern int sysctl_tcp_app_win;
 extern int sysctl_tcp_adv_win_scale;
 extern int sysctl_tcp_frto;
-extern int sysctl_tcp_low_latency;
 extern int sysctl_tcp_nometrics_save;
 extern int sysctl_tcp_moderate_rcvbuf;
 extern int sysctl_tcp_tso_win_divisor;
@@ -352,8 +350,11 @@ int tcp_v4_rcv(struct sk_buff *skb);
 
 int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
 int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
+int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size);
 int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
 		 int flags);
+int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
+			size_t size, int flags);
 ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 		 size_t size, int flags);
 void tcp_release_cb(struct sock *sk);
@@ -363,7 +364,7 @@ void tcp_delack_timer_handler(struct sock *sk);
 int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb);
 void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
-			 const struct tcphdr *th, unsigned int len);
+			 const struct tcphdr *th);
 void tcp_rcv_space_adjust(struct sock *sk);
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
 void tcp_twsk_destructor(struct sock *sk);
@@ -796,6 +797,12 @@ struct tcp_skb_cb {
 			u16	tcp_gso_segs;
 			u16	tcp_gso_size;
 		};
+
+		/* Used to stash the receive timestamp while this skb is in the
+		 * out of order queue, as skb->tstamp is overwritten by the
+		 * rbnode.
+		 */
+		ktime_t		swtstamp;
 	};
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
@@ -812,7 +819,8 @@ struct tcp_skb_cb {
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
 	__u8		txstamp_ack:1,	/* Record TX timestamp for ack? */
 			eor:1,		/* Is skb MSG_EOR marked? */
-			unused:6;
+			has_rxtstamp:1,	/* SKB has a RX timestamp	*/
+			unused:5;
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
 	union {
 		struct {
@@ -849,6 +857,16 @@ static inline int tcp_v6_iif(const struct sk_buff *skb)
 
 	return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
 }
+
+/* TCP_SKB_CB reference means this can not be used from early demux */
+static inline int tcp_v6_sdif(const struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags))
+		return TCP_SKB_CB(skb)->header.h6.iif;
+#endif
+	return 0;
+}
 #endif
 
 /* TCP_SKB_CB reference means this can not be used from early demux */
@@ -862,6 +880,16 @@ static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
 	return false;
 }
 
+/* TCP_SKB_CB reference means this can not be used from early demux */
+static inline int tcp_v4_sdif(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+		return TCP_SKB_CB(skb)->header.h4.iif;
+#endif
+	return 0;
+}
+
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
  */
@@ -1243,17 +1271,6 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb)
 		__tcp_checksum_complete(skb);
 }
 
-/* Prequeue for VJ style copy to user, combined with checksumming. */
-
-static inline void tcp_prequeue_init(struct tcp_sock *tp)
-{
-	tp->ucopy.task = NULL;
-	tp->ucopy.len = 0;
-	tp->ucopy.memory = 0;
-	skb_queue_head_init(&tp->ucopy.prequeue);
-}
-
-bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb);
 int tcp_filter(struct sock *sk, struct sk_buff *skb);
 
@@ -1545,8 +1562,7 @@ int tcp_fastopen_reset_cipher(void *key, unsigned int len);
 void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
-			      struct tcp_fastopen_cookie *foc,
-			      struct dst_entry *dst);
+			      struct tcp_fastopen_cookie *foc);
 void tcp_fastopen_init_key_once(bool publish);
 bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
 			     struct tcp_fastopen_cookie *cookie);
@@ -1927,7 +1943,8 @@ static inline s64 tcp_rto_delta_us(const struct sock *sk)
 /*
  * Save and compile IPv4 options, return a pointer to it
  */
-static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
+static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net,
+							 struct sk_buff *skb)
 {
 	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	struct ip_options_rcu *dopt = NULL;
@@ -1936,7 +1953,7 @@ static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
 		int opt_size = sizeof(*dopt) + opt->optlen;
 
 		dopt = kmalloc(opt_size, GFP_ATOMIC);
-		if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) {
+		if (dopt && __ip_options_echo(net, &dopt->opt, skb, opt)) {
 			kfree(dopt);
 			dopt = NULL;
 		}