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

Pull networking updates from David Miller:
 "Highlights:

   1) Support TX_RING in AF_PACKET TPACKET_V3 mode, from Sowmini
      Varadhan.

   2) Simplify classifier state on sk_buff in order to shrink it a bit.
      From Willem de Bruijn.

   3) Introduce SIPHASH and it's usage for secure sequence numbers and
      syncookies. From Jason A. Donenfeld.

   4) Reduce CPU usage for ICMP replies we are going to limit or
      suppress, from Jesper Dangaard Brouer.

   5) Introduce Shared Memory Communications socket layer, from Ursula
      Braun.

   6) Add RACK loss detection and allow it to actually trigger fast
      recovery instead of just assisting after other algorithms have
      triggered it. From Yuchung Cheng.

   7) Add xmit_more and BQL support to mvneta driver, from Simon Guinot.

   8) skb_cow_data avoidance in esp4 and esp6, from Steffen Klassert.

   9) Export MPLS packet stats via netlink, from Robert Shearman.

  10) Significantly improve inet port bind conflict handling, especially
      when an application is restarted and changes it's setting of
      reuseport. From Josef Bacik.

  11) Implement TX batching in vhost_net, from Jason Wang.

  12) Extend the dummy device so that VF (virtual function) features,
      such as configuration, can be more easily tested. From Phil
      Sutter.

  13) Avoid two atomic ops per page on x86 in bnx2x driver, from Eric
      Dumazet.

  14) Add new bpf MAP, implementing a longest prefix match trie. From
      Daniel Mack.

  15) Packet sample offloading support in mlxsw driver, from Yotam Gigi.

  16) Add new aquantia driver, from David VomLehn.

  17) Add bpf tracepoints, from Daniel Borkmann.

  18) Add support for port mirroring to b53 and bcm_sf2 drivers, from
      Florian Fainelli.

  19) Remove custom busy polling in many drivers, it is done in the core
      networking since 4.5 times. From Eric Dumazet.

  20) Support XDP adjust_head in virtio_net, from John Fastabend.

  21) Fix several major holes in neighbour entry confirmation, from
      Julian Anastasov.

  22) Add XDP support to bnxt_en driver, from Michael Chan.

  23) VXLAN offloads for enic driver, from Govindarajulu Varadarajan.

  24) Add IPVTAP driver (IP-VLAN based tap driver) from Sainath Grandhi.

  25) Support GRO in IPSEC protocols, from Steffen Klassert"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1764 commits)
  Revert "ath10k: Search SMBIOS for OEM board file extension"
  net: socket: fix recvmmsg not returning error from sock_error
  bnxt_en: use eth_hw_addr_random()
  bpf: fix unlocking of jited image when module ronx not set
  arch: add ARCH_HAS_SET_MEMORY config
  net: napi_watchdog() can use napi_schedule_irqoff()
  tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"
  net/hsr: use eth_hw_addr_random()
  net: mvpp2: enable building on 64-bit platforms
  net: mvpp2: switch to build_skb() in the RX path
  net: mvpp2: simplify MVPP2_PRS_RI_* definitions
  net: mvpp2: fix indentation of MVPP2_EXT_GLOBAL_CTRL_DEFAULT
  net: mvpp2: remove unused register definitions
  net: mvpp2: simplify mvpp2_bm_bufs_add()
  net: mvpp2: drop useless fields in mvpp2_bm_pool and related code
  net: mvpp2: remove unused 'tx_skb' field of 'struct mvpp2_tx_queue'
  net: mvpp2: release reference to txq_cpu[] entry after unmapping
  net: mvpp2: handle too large value in mvpp2_rx_time_coal_set()
  net: mvpp2: handle too large value handling in mvpp2_rx_pkts_coal_set()
  net: mvpp2: remove useless arguments in mvpp2_rx_{pkts, time}_coal_set
  ...

1 files changed, 87 insertions, 53 deletions

diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h
index 0f9265cb2a96..47c03ca5c404 100644
--- a/include/uapi/linux/rds.h
+++ b/include/uapi/linux/rds.h
@@ -35,6 +35,7 @@
 #define _LINUX_RDS_H
 
 #include <linux/types.h>
+#include <linux/socket.h>		/* For __kernel_sockaddr_storage. */
 
 #define RDS_IB_ABI_VERSION		0x301
 
@@ -52,6 +53,13 @@
 #define RDS_GET_MR_FOR_DEST		7
 #define SO_RDS_TRANSPORT		8
 
+/* Socket option to tap receive path latency
+ *	SO_RDS: SO_RDS_MSG_RXPATH_LATENCY
+ *	Format used struct rds_rx_trace_so
+ */
+#define SO_RDS_MSG_RXPATH_LATENCY	10
+
+
 /* supported values for SO_RDS_TRANSPORT */
 #define	RDS_TRANS_IB	0
 #define	RDS_TRANS_IWARP	1
@@ -77,6 +85,12 @@
  *	the same as for the GET_MR setsockopt.
  * RDS_CMSG_RDMA_STATUS (recvmsg)
  *	Returns the status of a completed RDMA operation.
+ * RDS_CMSG_RXPATH_LATENCY(recvmsg)
+ *	Returns rds message latencies in various stages of receive
+ *	path in nS. Its set per socket using SO_RDS_MSG_RXPATH_LATENCY
+ *	socket option. Legitimate points are defined in
+ *	enum rds_message_rxpath_latency. More points can be added in
+ *	future. CSMG format is struct rds_cmsg_rx_trace.
  */
 #define RDS_CMSG_RDMA_ARGS		1
 #define RDS_CMSG_RDMA_DEST		2
@@ -87,6 +101,7 @@
 #define RDS_CMSG_ATOMIC_CSWP		7
 #define RDS_CMSG_MASKED_ATOMIC_FADD	8
 #define RDS_CMSG_MASKED_ATOMIC_CSWP	9
+#define RDS_CMSG_RXPATH_LATENCY		11
 
 #define RDS_INFO_FIRST			10000
 #define RDS_INFO_COUNTERS		10000
@@ -103,8 +118,8 @@
 #define RDS_INFO_LAST			10010
 
 struct rds_info_counter {
-	uint8_t	name[32];
-	uint64_t	value;
+	__u8	name[32];
+	__u64	value;
 } __attribute__((packed));
 
 #define RDS_INFO_CONNECTION_FLAG_SENDING	0x01
@@ -114,35 +129,35 @@ struct rds_info_counter {
 #define TRANSNAMSIZ	16
 
 struct rds_info_connection {
-	uint64_t	next_tx_seq;
-	uint64_t	next_rx_seq;
+	__u64		next_tx_seq;
+	__u64		next_rx_seq;
 	__be32		laddr;
 	__be32		faddr;
-	uint8_t	transport[TRANSNAMSIZ];		/* null term ascii */
-	uint8_t	flags;
+	__u8		transport[TRANSNAMSIZ];		/* null term ascii */
+	__u8		flags;
 } __attribute__((packed));
 
 #define RDS_INFO_MESSAGE_FLAG_ACK               0x01
 #define RDS_INFO_MESSAGE_FLAG_FAST_ACK          0x02
 
 struct rds_info_message {
-	uint64_t	seq;
-	uint32_t	len;
+	__u64		seq;
+	__u32		len;
 	__be32		laddr;
 	__be32		faddr;
 	__be16		lport;
 	__be16		fport;
-	uint8_t	flags;
+	__u8		flags;
 } __attribute__((packed));
 
 struct rds_info_socket {
-	uint32_t	sndbuf;
+	__u32		sndbuf;
 	__be32		bound_addr;
 	__be32		connected_addr;
 	__be16		bound_port;
 	__be16		connected_port;
-	uint32_t	rcvbuf;
-	uint64_t	inum;
+	__u32		rcvbuf;
+	__u64		inum;
 } __attribute__((packed));
 
 struct rds_info_tcp_socket {
@@ -150,25 +165,44 @@ struct rds_info_tcp_socket {
 	__be16          local_port;
 	__be32          peer_addr;
 	__be16          peer_port;
-	uint64_t       hdr_rem;
-	uint64_t       data_rem;
-	uint32_t       last_sent_nxt;
-	uint32_t       last_expected_una;
-	uint32_t       last_seen_una;
+	__u64           hdr_rem;
+	__u64           data_rem;
+	__u32           last_sent_nxt;
+	__u32           last_expected_una;
+	__u32           last_seen_una;
 } __attribute__((packed));
 
 #define RDS_IB_GID_LEN	16
 struct rds_info_rdma_connection {
 	__be32		src_addr;
 	__be32		dst_addr;
-	uint8_t		src_gid[RDS_IB_GID_LEN];
-	uint8_t		dst_gid[RDS_IB_GID_LEN];
-
-	uint32_t	max_send_wr;
-	uint32_t	max_recv_wr;
-	uint32_t	max_send_sge;
-	uint32_t	rdma_mr_max;
-	uint32_t	rdma_mr_size;
+	__u8		src_gid[RDS_IB_GID_LEN];
+	__u8		dst_gid[RDS_IB_GID_LEN];
+
+	__u32		max_send_wr;
+	__u32		max_recv_wr;
+	__u32		max_send_sge;
+	__u32		rdma_mr_max;
+	__u32		rdma_mr_size;
+};
+
+/* RDS message Receive Path Latency points */
+enum rds_message_rxpath_latency {
+	RDS_MSG_RX_HDR_TO_DGRAM_START = 0,
+	RDS_MSG_RX_DGRAM_REASSEMBLE,
+	RDS_MSG_RX_DGRAM_DELIVERED,
+	RDS_MSG_RX_DGRAM_TRACE_MAX
+};
+
+struct rds_rx_trace_so {
+	u8 rx_traces;
+	u8 rx_trace_pos[RDS_MSG_RX_DGRAM_TRACE_MAX];
+};
+
+struct rds_cmsg_rx_trace {
+	u8 rx_traces;
+	u8 rx_trace_pos[RDS_MSG_RX_DGRAM_TRACE_MAX];
+	u64 rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX];
 };
 
 /*
@@ -209,70 +243,70 @@ struct rds_info_rdma_connection {
  * (so that the application does not have to worry about
  * alignment).
  */
-typedef uint64_t	rds_rdma_cookie_t;
+typedef __u64		rds_rdma_cookie_t;
 
 struct rds_iovec {
-	uint64_t	addr;
-	uint64_t	bytes;
+	__u64		addr;
+	__u64		bytes;
 };
 
 struct rds_get_mr_args {
 	struct rds_iovec vec;
-	uint64_t	cookie_addr;
-	uint64_t	flags;
+	__u64		cookie_addr;
+	__u64		flags;
 };
 
 struct rds_get_mr_for_dest_args {
-	struct sockaddr_storage	dest_addr;
+	struct __kernel_sockaddr_storage dest_addr;
 	struct rds_iovec 	vec;
-	uint64_t		cookie_addr;
-	uint64_t		flags;
+	__u64			cookie_addr;
+	__u64			flags;
 };
 
 struct rds_free_mr_args {
 	rds_rdma_cookie_t cookie;
-	uint64_t	flags;
+	__u64		flags;
 };
 
 struct rds_rdma_args {
 	rds_rdma_cookie_t cookie;
 	struct rds_iovec remote_vec;
-	uint64_t	local_vec_addr;
-	uint64_t	nr_local;
-	uint64_t	flags;
-	uint64_t	user_token;
+	__u64		local_vec_addr;
+	__u64		nr_local;
+	__u64		flags;
+	__u64		user_token;
 };
 
 struct rds_atomic_args {
 	rds_rdma_cookie_t cookie;
-	uint64_t 	local_addr;
-	uint64_t 	remote_addr;
+	__u64		local_addr;
+	__u64		remote_addr;
 	union {
 		struct {
-			uint64_t	compare;
-			uint64_t	swap;
+			__u64		compare;
+			__u64		swap;
 		} cswp;
 		struct {
-			uint64_t	add;
+			__u64		add;
 		} fadd;
 		struct {
-			uint64_t	compare;
-			uint64_t	swap;
-			uint64_t	compare_mask;
-			uint64_t	swap_mask;
+			__u64		compare;
+			__u64		swap;
+			__u64		compare_mask;
+			__u64		swap_mask;
 		} m_cswp;
 		struct {
-			uint64_t	add;
-			uint64_t	nocarry_mask;
+			__u64		add;
+			__u64		nocarry_mask;
 		} m_fadd;
 	};
-	uint64_t	flags;
-	uint64_t	user_token;
+	__u64		flags;
+	__u64		user_token;
 };
 
 struct rds_rdma_notify {
-	uint64_t	user_token;
-	int32_t		status;
+	__u64		user_token;
+	__s32		status;
 };
 
 #define RDS_RDMA_SUCCESS	0