smc: CLC handshake (incl. preparation steps)

* CLC (Connection Layer Control) handshake
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/smc/Makefile

 obj-$(CONFIG_SMC)	+= smc.o
-smc-y := af_smc.o smc_pnet.o smc_ib.o
+smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o

net/smc/smc.h

@@ -28,6 +28,12 @@ enum smc_state {		/* possible states of an SMC socket */
 struct smc_sock {				/* smc sock container */
 	struct sock		sk;
 	struct socket		*clcsock;	/* internal tcp socket */
+	struct sockaddr		*addr;		/* inet connect address */
+	struct smc_sock		*listen_smc;	/* listen parent */
+	struct work_struct	tcp_listen_work;/* handle tcp socket accepts */
+	struct work_struct	smc_listen_work;/* prepare new accept socket */
+	struct list_head	accept_q;	/* sockets to be accepted */
+	spinlock_t		accept_q_lock;	/* protects accept_q */
 	bool			use_fallback;	/* fallback to tcp */
 };
 
@@ -40,4 +46,20 @@ static inline struct smc_sock *smc_sk(const struct sock *sk)
 
 extern u8	local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */
 
+#ifdef CONFIG_XFRM
+static inline bool using_ipsec(struct smc_sock *smc)
+{
+	return (smc->clcsock->sk->sk_policy[0] ||
+		smc->clcsock->sk->sk_policy[1]) ? 1 : 0;
+}
+#else
+static inline bool using_ipsec(struct smc_sock *smc)
+{
+	return 0;
+}
+#endif
+
+int smc_netinfo_by_tcpsk(struct socket *clcsock, __be32 *subnet,
+			 u8 *prefix_len);
+
 #endif	/* __SMC_H */

net/smc/smc_clc.c

+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  CLC (connection layer control) handshake over initial TCP socket to
+ *  prepare for RDMA traffic
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/in.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+
+#include "smc.h"
+#include "smc_clc.h"
+#include "smc_ib.h"
+
+/* Wait for data on the tcp-socket, analyze received data
+ * Returns:
+ * 0 if success and it was not a decline that we received.
+ * SMC_CLC_DECL_REPLY if decline received for fallback w/o another decl send.
+ * clcsock error, -EINTR, -ECONNRESET, -EPROTO otherwise.
+ */
+int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
+		     u8 expected_type)
+{
+	struct sock *clc_sk = smc->clcsock->sk;
+	struct smc_clc_msg_hdr *clcm = buf;
+	struct msghdr msg = {NULL, 0};
+	int reason_code = 0;
+	struct kvec vec;
+	int len, datlen;
+	int krflags;
+
+	/* peek the first few bytes to determine length of data to receive
+	 * so we don't consume any subsequent CLC message or payload data
+	 * in the TCP byte stream
+	 */
+	vec.iov_base = buf;
+	vec.iov_len = buflen;
+	krflags = MSG_PEEK | MSG_WAITALL;
+	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
+	len = kernel_recvmsg(smc->clcsock, &msg, &vec, 1,
+			     sizeof(struct smc_clc_msg_hdr), krflags);
+	if (signal_pending(current)) {
+		reason_code = -EINTR;
+		clc_sk->sk_err = EINTR;
+		smc->sk.sk_err = EINTR;
+		goto out;
+	}
+	if (clc_sk->sk_err) {
+		reason_code = -clc_sk->sk_err;
+		smc->sk.sk_err = clc_sk->sk_err;
+		goto out;
+	}
+	if (!len) { /* peer has performed orderly shutdown */
+		smc->sk.sk_err = ECONNRESET;
+		reason_code = -ECONNRESET;
+		goto out;
+	}
+	if (len < 0) {
+		smc->sk.sk_err = -len;
+		reason_code = len;
+		goto out;
+	}
+	datlen = ntohs(clcm->length);
+	if ((len < sizeof(struct smc_clc_msg_hdr)) ||
+	    (datlen < sizeof(struct smc_clc_msg_decline)) ||
+	    (datlen > sizeof(struct smc_clc_msg_accept_confirm)) ||
+	    memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) ||
+	    ((clcm->type != SMC_CLC_DECLINE) &&
+	     (clcm->type != expected_type))) {
+		smc->sk.sk_err = EPROTO;
+		reason_code = -EPROTO;
+		goto out;
+	}
+
+	/* receive the complete CLC message */
+	vec.iov_base = buf;
+	vec.iov_len = buflen;
+	memset(&msg, 0, sizeof(struct msghdr));
+	krflags = MSG_WAITALL;
+	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
+	len = kernel_recvmsg(smc->clcsock, &msg, &vec, 1, datlen, krflags);
+	if (len < datlen) {
+		smc->sk.sk_err = EPROTO;
+		reason_code = -EPROTO;
+		goto out;
+	}
+	if (clcm->type == SMC_CLC_DECLINE)
+		reason_code = SMC_CLC_DECL_REPLY;
+out:
+	return reason_code;
+}
+
+/* send CLC DECLINE message across internal TCP socket */
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
+			 u8 out_of_sync)
+{
+	struct smc_clc_msg_decline dclc;
+	struct msghdr msg;
+	struct kvec vec;
+	int len;
+
+	memset(&dclc, 0, sizeof(dclc));
+	memcpy(dclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	dclc.hdr.type = SMC_CLC_DECLINE;
+	dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
+	dclc.hdr.version = SMC_CLC_V1;
+	dclc.hdr.flag = out_of_sync ? 1 : 0;
+	memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid));
+	dclc.peer_diagnosis = htonl(peer_diag_info);
+	memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+
+	memset(&msg, 0, sizeof(msg));
+	vec.iov_base = &dclc;
+	vec.iov_len = sizeof(struct smc_clc_msg_decline);
+	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
+			     sizeof(struct smc_clc_msg_decline));
+	if (len < sizeof(struct smc_clc_msg_decline))
+		smc->sk.sk_err = EPROTO;
+	if (len < 0)
+		smc->sk.sk_err = -len;
+	return len;
+}
+
+/* send CLC PROPOSAL message across internal TCP socket */
+int smc_clc_send_proposal(struct smc_sock *smc,
+			  struct smc_ib_device *smcibdev,
+			  u8 ibport)
+{
+	struct smc_clc_msg_proposal pclc;
+	int reason_code = 0;
+	struct msghdr msg;
+	struct kvec vec;
+	int len, rc;
+
+	/* send SMC Proposal CLC message */
+	memset(&pclc, 0, sizeof(pclc));
+	memcpy(pclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	pclc.hdr.type = SMC_CLC_PROPOSAL;
+	pclc.hdr.length = htons(sizeof(pclc));
+	pclc.hdr.version = SMC_CLC_V1;		/* SMC version */
+	memcpy(pclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
+	memcpy(&pclc.lcl.gid, &smcibdev->gid[ibport - 1], SMC_GID_SIZE);
+	memcpy(&pclc.lcl.mac, &smcibdev->mac[ibport - 1],
+	       sizeof(smcibdev->mac[ibport - 1]));
+
+	/* determine subnet and mask from internal TCP socket */
+	rc = smc_netinfo_by_tcpsk(smc->clcsock, &pclc.outgoing_subnet,
+				  &pclc.prefix_len);
+	if (rc)
+		return SMC_CLC_DECL_CNFERR; /* configuration error */
+	memcpy(pclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	memset(&msg, 0, sizeof(msg));
+	vec.iov_base = &pclc;
+	vec.iov_len = sizeof(pclc);
+	/* due to the few bytes needed for clc-handshake this cannot block */
+	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(pclc));
+	if (len < sizeof(pclc)) {
+		if (len >= 0) {
+			reason_code = -ENETUNREACH;
+			smc->sk.sk_err = -reason_code;
+		} else {
+			smc->sk.sk_err = smc->clcsock->sk->sk_err;
+			reason_code = -smc->sk.sk_err;
+		}
+	}
+
+	return reason_code;
+}
+
+/* send CLC CONFIRM message across internal TCP socket */
+int smc_clc_send_confirm(struct smc_sock *smc)
+{
+	struct smc_clc_msg_accept_confirm cclc;
+	int reason_code = 0;
+	struct msghdr msg;
+	struct kvec vec;
+	int len;
+
+	/* send SMC Confirm CLC msg */
+	memset(&cclc, 0, sizeof(cclc));
+	memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	cclc.hdr.type = SMC_CLC_CONFIRM;
+	cclc.hdr.length = htons(sizeof(cclc));
+	cclc.hdr.version = SMC_CLC_V1;		/* SMC version */
+	memcpy(cclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
+
+	/* tbd in follow-on patch: fill in link-related values */
+
+	/* tbd in follow-on patch: fill in rmb-related values */
+
+	cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */
+
+	memcpy(cclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+
+	memset(&msg, 0, sizeof(msg));
+	vec.iov_base = &cclc;
+	vec.iov_len = sizeof(cclc);
+	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(cclc));
+	if (len < sizeof(cclc)) {
+		if (len >= 0) {
+			reason_code = -ENETUNREACH;
+			smc->sk.sk_err = -reason_code;
+		} else {
+			smc->sk.sk_err = smc->clcsock->sk->sk_err;
+			reason_code = -smc->sk.sk_err;
+		}
+	}
+	return reason_code;
+}
+
+/* send CLC ACCEPT message across internal TCP socket */
+int smc_clc_send_accept(struct smc_sock *new_smc)
+{
+	struct smc_clc_msg_accept_confirm aclc;
+	struct msghdr msg;
+	struct kvec vec;
+	int rc = 0;
+	int len;
+
+	memset(&aclc, 0, sizeof(aclc));
+	memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	aclc.hdr.type = SMC_CLC_ACCEPT;
+	aclc.hdr.length = htons(sizeof(aclc));
+	aclc.hdr.version = SMC_CLC_V1;		/* SMC version */
+	memcpy(aclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
+
+	/* tbd in follow-on patch: fill in link-related values */
+
+	/* tbd in follow-on patch: fill in rmb-related values */
+
+	aclc.conn_idx = 1;			/* as long as 1 RMB = 1 RMBE */
+	memcpy(aclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+
+	memset(&msg, 0, sizeof(msg));
+	vec.iov_base = &aclc;
+	vec.iov_len = sizeof(aclc);
+	len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1, sizeof(aclc));
+	if (len < sizeof(aclc)) {
+		if (len >= 0)
+			new_smc->sk.sk_err = EPROTO;
+		else
+			new_smc->sk.sk_err = new_smc->clcsock->sk->sk_err;
+		rc = sock_error(&new_smc->sk);
+	}
+
+	return rc;
+}

net/smc/smc_clc.h

+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  CLC (connection layer control) handshake over initial TCP socket to
+ *  prepare for RDMA traffic
+ *
+ *  Copyright IBM Corp. 2016
+ *
+ *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#ifndef _SMC_CLC_H
+#define _SMC_CLC_H
+
+#include <rdma/ib_verbs.h>
+
+#include "smc.h"
+
+#define SMC_CLC_PROPOSAL	0x01
+#define SMC_CLC_ACCEPT		0x02
+#define SMC_CLC_CONFIRM		0x03
+#define SMC_CLC_DECLINE		0x04
+
+/* eye catcher "SMCR" EBCDIC for CLC messages */
+static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'};
+
+#define SMC_CLC_V1		0x1		/* SMC version                */
+#define CLC_WAIT_TIME		(6 * HZ)	/* max. wait time on clcsock  */
+#define SMC_CLC_DECL_MEM	0x01010000  /* insufficient memory resources  */
+#define SMC_CLC_DECL_TIMEOUT	0x02000000  /* timeout                        */
+#define SMC_CLC_DECL_CNFERR	0x03000000  /* configuration error            */
+#define SMC_CLC_DECL_IPSEC	0x03030000  /* IPsec usage                    */
+#define SMC_CLC_DECL_SYNCERR	0x04000000  /* synchronization error          */
+#define SMC_CLC_DECL_REPLY	0x06000000  /* reply to a received decline    */
+#define SMC_CLC_DECL_INTERR	0x99990000  /* internal error                 */
+
+struct smc_clc_msg_hdr {	/* header1 of clc messages */
+	u8 eyecatcher[4];	/* eye catcher */
+	u8 type;		/* proposal / accept / confirm / decline */
+	__be16 length;
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8 version : 4,
+	   flag    : 1,
+	   rsvd	   : 3;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 rsvd    : 3,
+	   flag    : 1,
+	   version : 4;
+#endif
+} __packed;			/* format defined in RFC7609 */
+
+struct smc_clc_msg_trail {	/* trailer of clc messages */
+	u8 eyecatcher[4];
+};
+
+struct smc_clc_msg_local {	/* header2 of clc messages */
+	u8 id_for_peer[SMC_SYSTEMID_LEN]; /* unique system id */
+	u8 gid[16];		/* gid of ib_device port */
+	u8 mac[6];		/* mac of ib_device port */
+};
+
+struct smc_clc_msg_proposal {	/* clc proposal message */
+	struct smc_clc_msg_hdr hdr;
+	struct smc_clc_msg_local lcl;
+	__be16 iparea_offset;	/* offset to IP address information area */
+	__be32 outgoing_subnet;	/* subnet mask */
+	u8 prefix_len;		/* number of significant bits in mask */
+	u8 reserved[2];
+	u8 ipv6_prefixes_cnt;	/* number of IPv6 prefixes in prefix array */
+	struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */
+} __aligned(4);
+
+struct smc_clc_msg_accept_confirm {	/* clc accept / confirm message */
+	struct smc_clc_msg_hdr hdr;
+	struct smc_clc_msg_local lcl;
+	u8 qpn[3];		/* QP number */
+	__be32 rmb_rkey;	/* RMB rkey */
+	u8 conn_idx;		/* Connection index, which RMBE in RMB */
+	__be32 rmbe_alert_token;/* unique connection id */
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8 rmbe_size : 4,	/* RMBE buf size (compressed notation) */
+	   qp_mtu   : 4;	/* QP mtu */
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 qp_mtu   : 4,
+	   rmbe_size : 4;
+#endif
+	u8 reserved;
+	__be64 rmb_dma_addr;	/* RMB virtual address */
+	u8 reserved2;
+	u8 psn[3];		/* initial packet sequence number */
+	struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */
+} __packed;			/* format defined in RFC7609 */
+
+struct smc_clc_msg_decline {	/* clc decline message */
+	struct smc_clc_msg_hdr hdr;
+	u8 id_for_peer[SMC_SYSTEMID_LEN]; /* sender peer_id */
+	__be32 peer_diagnosis;	/* diagnosis information */
+	u8 reserved2[4];
+	struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */
+} __aligned(4);
+
+struct smc_sock;
+struct smc_ib_device;
+
+int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
+		     u8 expected_type);
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
+			 u8 out_of_sync);
+int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev,
+			  u8 ibport);
+int smc_clc_send_confirm(struct smc_sock *smc);
+int smc_clc_send_accept(struct smc_sock *smc);
+
+#endif