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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 24 insertions, 44 deletions

diff --git a/net/smc/smc.h b/net/smc/smc.h
index e4829a2f46ba..51ae1f10d81a 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -114,11 +114,17 @@ struct smc_host_cdc_msg {		/* Connection Data Control message */
 	u8				reserved[18];
 } __aligned(8);
 
+enum smc_urg_state {
+	SMC_URG_VALID,			/* data present */
+	SMC_URG_NOTYET,			/* data pending */
+	SMC_URG_READ			/* data was already read */
+};
+
 struct smc_connection {
 	struct rb_node		alert_node;
 	struct smc_link_group	*lgr;		/* link group of connection */
 	u32			alert_token_local; /* unique conn. id */
-	u8			peer_conn_idx;	/* from tcp handshake */
+	u8			peer_rmbe_idx;	/* from tcp handshake */
 	int			peer_rmbe_size;	/* size of peer rx buffer */
 	atomic_t		peer_rmbe_space;/* remaining free bytes in peer
 						 * rmbe
@@ -126,9 +132,7 @@ struct smc_connection {
 	int			rtoken_idx;	/* idx to peer RMB rkey/addr */
 
 	struct smc_buf_desc	*sndbuf_desc;	/* send buffer descriptor */
-	int			sndbuf_size;	/* sndbuf size <== sock wmem */
 	struct smc_buf_desc	*rmb_desc;	/* RMBE descriptor */
-	int			rmbe_size;	/* RMBE size <== sock rmem */
 	int			rmbe_size_short;/* compressed notation */
 	int			rmbe_update_limit;
 						/* lower limit for consumer
@@ -153,6 +157,7 @@ struct smc_connection {
 	u16			tx_cdc_seq;	/* sequence # for CDC send */
 	spinlock_t		send_lock;	/* protect wr_sends */
 	struct delayed_work	tx_work;	/* retry of smc_cdc_msg_send */
+	u32			tx_off;		/* base offset in peer rmb */
 
 	struct smc_host_cdc_msg	local_rx_ctrl;	/* filled during event_handl.
 						 * .prod cf. TCP rcv_nxt
@@ -161,9 +166,21 @@ struct smc_connection {
 	union smc_host_cursor	rx_curs_confirmed; /* confirmed to peer
 						    * source of snd_una ?
 						    */
+	union smc_host_cursor	urg_curs;	/* points at urgent byte */
+	enum smc_urg_state	urg_state;
+	bool			urg_tx_pend;	/* urgent data staged */
+	bool			urg_rx_skip_pend;
+						/* indicate urgent oob data
+						 * read, but previous regular
+						 * data still pending
+						 */
+	char			urg_rx_byte;	/* urgent byte */
 	atomic_t		bytes_to_rcv;	/* arrived data,
 						 * not yet received
 						 */
+	atomic_t		splice_pending;	/* number of spliced bytes
+						 * pending processing
+						 */
 #ifndef KERNEL_HAS_ATOMIC64
 	spinlock_t		acurs_lock;	/* protect cursors */
 #endif
@@ -180,6 +197,10 @@ struct smc_sock {				/* smc sock container */
 	struct list_head	accept_q;	/* sockets to be accepted */
 	spinlock_t		accept_q_lock;	/* protects accept_q */
 	bool			use_fallback;	/* fallback to tcp */
+	int			sockopt_defer_accept;
+						/* sockopt TCP_DEFER_ACCEPT
+						 * value
+						 */
 	u8			wait_close_tx_prepared : 1;
 						/* shutdown wr or close
 						 * started, waiting for unsent
@@ -214,41 +235,6 @@ static inline u32 ntoh24(u8 *net)
 	return be32_to_cpu(t);
 }
 
-#define SMC_BUF_MIN_SIZE 16384		/* minimum size of an RMB */
-
-#define SMC_RMBE_SIZES	16	/* number of distinct sizes for an RMBE */
-/* theoretically, the RFC states that largest size would be 512K,
- * i.e. compressed 5 and thus 6 sizes (0..5), despite
- * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15)
- */
-
-/* convert the RMB size into the compressed notation - minimum 16K.
- * In contrast to plain ilog2, this rounds towards the next power of 2,
- * so the socket application gets at least its desired sndbuf / rcvbuf size.
- */
-static inline u8 smc_compress_bufsize(int size)
-{
-	u8 compressed;
-
-	if (size <= SMC_BUF_MIN_SIZE)
-		return 0;
-
-	size = (size - 1) >> 14;
-	compressed = ilog2(size) + 1;
-	if (compressed >= SMC_RMBE_SIZES)
-		compressed = SMC_RMBE_SIZES - 1;
-	return compressed;
-}
-
-/* convert the RMB size from compressed notation into integer */
-static inline int smc_uncompress_bufsize(u8 compressed)
-{
-	u32 size;
-
-	size = 0x00000001 << (((int)compressed) + 14);
-	return (int)size;
-}
-
 #ifdef CONFIG_XFRM
 static inline bool using_ipsec(struct smc_sock *smc)
 {
@@ -262,12 +248,6 @@ static inline bool using_ipsec(struct smc_sock *smc)
 }
 #endif
 
-struct smc_clc_msg_local;
-
-void smc_conn_free(struct smc_connection *conn);
-int smc_conn_create(struct smc_sock *smc,
-		    struct smc_ib_device *smcibdev, u8 ibport,
-		    struct smc_clc_msg_local *lcl, int srv_first_contact);
 struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock);
 void smc_close_non_accepted(struct sock *sk);