smc_clc.c 8.5 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12
/*
 *  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>
13
#include <linux/if_ether.h>
14 15
#include <linux/sched/signal.h>

16 17 18 19
#include <net/sock.h>
#include <net/tcp.h>

#include "smc.h"
20
#include "smc_core.h"
21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
#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;
	}
96
	if (clcm->type == SMC_CLC_DECLINE) {
97
		reason_code = SMC_CLC_DECL_REPLY;
98 99 100 101 102
		if (ntohl(((struct smc_clc_msg_decline *)buf)->peer_diagnosis)
			== SMC_CLC_DECL_SYNCERR)
			smc->conn.lgr->sync_err = true;
	}

103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
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);
157
	memcpy(&pclc.lcl.mac, &smcibdev->mac[ibport - 1], ETH_ALEN);
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185

	/* 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)
{
186
	struct smc_connection *conn = &smc->conn;
187
	struct smc_clc_msg_accept_confirm cclc;
188
	struct smc_link *link;
189 190 191 192 193
	int reason_code = 0;
	struct msghdr msg;
	struct kvec vec;
	int len;

194
	link = &conn->lgr->lnk[SMC_SINGLE_LINK];
195 196 197 198 199 200 201
	/* 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));
202 203
	memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
	       SMC_GID_SIZE);
204
	memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
205
	hton24(cclc.qpn, link->roce_qp->qp_num);
206
	cclc.rmb_rkey =
207
		htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
208
	cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */
209 210
	cclc.rmbe_alert_token = htonl(conn->alert_token_local);
	cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
211 212 213
	cclc.rmbe_size = conn->rmbe_size_short;
	cclc.rmb_dma_addr =
		cpu_to_be64((u64)conn->rmb_desc->dma_addr[SMC_SINGLE_LINK]);
214
	hton24(cclc.psn, link->psn_initial);
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234

	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 */
235
int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
236
{
237
	struct smc_connection *conn = &new_smc->conn;
238
	struct smc_clc_msg_accept_confirm aclc;
239
	struct smc_link *link;
240 241 242 243 244
	struct msghdr msg;
	struct kvec vec;
	int rc = 0;
	int len;

245
	link = &conn->lgr->lnk[SMC_SINGLE_LINK];
246 247 248 249 250
	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 */
251 252
	if (srv_first_contact)
		aclc.hdr.flag = 1;
253
	memcpy(aclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
254 255
	memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
	       SMC_GID_SIZE);
256
	memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
257
	hton24(aclc.qpn, link->roce_qp->qp_num);
258
	aclc.rmb_rkey =
259
		htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
260
	aclc.conn_idx = 1;			/* as long as 1 RMB = 1 RMBE */
261 262
	aclc.rmbe_alert_token = htonl(conn->alert_token_local);
	aclc.qp_mtu = link->path_mtu;
U
Ursula Braun 已提交
263 264 265
	aclc.rmbe_size = conn->rmbe_size_short,
	aclc.rmb_dma_addr =
		cpu_to_be64((u64)conn->rmb_desc->dma_addr[SMC_SINGLE_LINK]);
266
	hton24(aclc.psn, link->psn_initial);
267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
	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;
}