smc: support variable CLC proposal messages

According to RFC7609 [1] the CLC proposal message contains an area of
unknown length for future growth. Additionally it may contain up to
8 IPv6 prefixes. The current version of the SMC-code does not
understand CLC proposal messages using these variable length fields and,
thus, is incompatible with SMC implementations in other operating
systems.

This patch makes sure, SMC understands incoming CLC proposals
* with arbitrary length values for future growth
* with up to 8 IPv6 prefixes

[1] SMC-R Informational RFC: http://www.rfc-editor.org/info/rfc7609Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reviewed-by: Hans Wippel <hwippel@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/smc/af_smc.c

@@ -751,14 +751,16 @@ static void smc_listen_work(struct work_struct *work)
 {
 	struct smc_sock *new_smc = container_of(work, struct smc_sock,
 						smc_listen_work);
+	struct smc_clc_msg_proposal_prefix *pclc_prfx;
 	struct socket *newclcsock = new_smc->clcsock;
 	struct smc_sock *lsmc = new_smc->listen_smc;
 	struct smc_clc_msg_accept_confirm cclc;
 	int local_contact = SMC_REUSE_CONTACT;
 	struct sock *newsmcsk = &new_smc->sk;
-	struct smc_clc_msg_proposal pclc;
+	struct smc_clc_msg_proposal *pclc;
 	struct smc_ib_device *smcibdev;
 	struct sockaddr_in peeraddr;
+	u8 buf[SMC_CLC_MAX_LEN];
 	struct smc_link *link;
 	int reason_code = 0;
 	int rc = 0, len;
@@ -775,7 +777,7 @@ static void smc_listen_work(struct work_struct *work)
 	/* do inband token exchange -
 	 *wait for and receive SMC Proposal CLC message
 	 */
-	reason_code = smc_clc_wait_msg(new_smc, &pclc, sizeof(pclc),
+	reason_code = smc_clc_wait_msg(new_smc, &buf, sizeof(buf),
 				       SMC_CLC_PROPOSAL);
 	if (reason_code < 0)
 		goto out_err;
@@ -804,8 +806,11 @@ static void smc_listen_work(struct work_struct *work)
 		reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
 		goto decline_rdma;
 	}
-	if ((pclc.outgoing_subnet != subnet) ||
-	    (pclc.prefix_len != prefix_len)) {
+
+	pclc = (struct smc_clc_msg_proposal *)&buf;
+	pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+	if (pclc_prfx->outgoing_subnet != subnet ||
+	    pclc_prfx->prefix_len != prefix_len) {
 		reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
 		goto decline_rdma;
 	}
@@ -816,7 +821,7 @@ static void smc_listen_work(struct work_struct *work)
 	/* allocate connection / link group */
 	mutex_lock(&smc_create_lgr_pending);
 	local_contact = smc_conn_create(new_smc, peeraddr.sin_addr.s_addr,
-					smcibdev, ibport, &pclc.lcl, 0);
+					smcibdev, ibport, &pclc->lcl, 0);
 	if (local_contact < 0) {
 		rc = local_contact;
 		if (rc == -ENOMEM)

net/smc/smc_clc.c

@@ -22,6 +22,54 @@
 #include "smc_clc.h"
 #include "smc_ib.h"
 
+/* check if received message has a correct header length and contains valid
+ * heading and trailing eyecatchers
+ */
+static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm)
+{
+	struct smc_clc_msg_proposal_prefix *pclc_prfx;
+	struct smc_clc_msg_accept_confirm *clc;
+	struct smc_clc_msg_proposal *pclc;
+	struct smc_clc_msg_decline *dclc;
+	struct smc_clc_msg_trail *trl;
+
+	if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)))
+		return false;
+	switch (clcm->type) {
+	case SMC_CLC_PROPOSAL:
+		pclc = (struct smc_clc_msg_proposal *)clcm;
+		pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+		if (ntohs(pclc->hdr.length) !=
+			sizeof(*pclc) + ntohs(pclc->iparea_offset) +
+			sizeof(*pclc_prfx) +
+			pclc_prfx->ipv6_prefixes_cnt *
+				sizeof(struct smc_clc_ipv6_prefix) +
+			sizeof(*trl))
+			return false;
+		trl = (struct smc_clc_msg_trail *)
+			((u8 *)pclc + ntohs(pclc->hdr.length) - sizeof(*trl));
+		break;
+	case SMC_CLC_ACCEPT:
+	case SMC_CLC_CONFIRM:
+		clc = (struct smc_clc_msg_accept_confirm *)clcm;
+		if (ntohs(clc->hdr.length) != sizeof(*clc))
+			return false;
+		trl = &clc->trl;
+		break;
+	case SMC_CLC_DECLINE:
+		dclc = (struct smc_clc_msg_decline *)clcm;
+		if (ntohs(dclc->hdr.length) != sizeof(*dclc))
+			return false;
+		trl = &dclc->trl;
+		break;
+	default:
+		return false;
+	}
+	if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)))
+		return false;
+	return true;
+}
+
 /* Wait for data on the tcp-socket, analyze received data
  * Returns:
  * 0 if success and it was not a decline that we received.
@@ -72,9 +120,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	}
 	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)) ||
+	    (datlen > buflen) ||
 	    ((clcm->type != SMC_CLC_DECLINE) &&
 	     (clcm->type != expected_type))) {
 		smc->sk.sk_err = EPROTO;
@@ -89,7 +135,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	krflags = MSG_WAITALL;
 	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
 	len = kernel_recvmsg(smc->clcsock, &msg, &vec, 1, datlen, krflags);
-	if (len < datlen) {
+	if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
 		smc->sk.sk_err = EPROTO;
 		reason_code = -EPROTO;
 		goto out;
@@ -141,33 +187,43 @@ int smc_clc_send_proposal(struct smc_sock *smc,
 			  struct smc_ib_device *smcibdev,
 			  u8 ibport)
 {
+	struct smc_clc_msg_proposal_prefix pclc_prfx;
 	struct smc_clc_msg_proposal pclc;
+	struct smc_clc_msg_trail trl;
 	int reason_code = 0;
+	struct kvec vec[3];
 	struct msghdr msg;
-	struct kvec vec;
-	int len, rc;
+	int len, plen, rc;
 
 	/* send SMC Proposal CLC message */
+	plen = sizeof(pclc) + sizeof(pclc_prfx) + sizeof(trl);
 	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.length = htons(plen);
 	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], ETH_ALEN);
+	pclc.iparea_offset = htons(0);
 
+	memset(&pclc_prfx, 0, sizeof(pclc_prfx));
 	/* determine subnet and mask from internal TCP socket */
-	rc = smc_netinfo_by_tcpsk(smc->clcsock, &pclc.outgoing_subnet,
-				  &pclc.prefix_len);
+	rc = smc_netinfo_by_tcpsk(smc->clcsock, &pclc_prfx.outgoing_subnet,
+				  &pclc_prfx.prefix_len);
 	if (rc)
 		return SMC_CLC_DECL_CNFERR; /* configuration error */
-	memcpy(pclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	pclc_prfx.ipv6_prefixes_cnt = 0;
+	memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	memset(&msg, 0, sizeof(msg));
-	vec.iov_base = &pclc;
-	vec.iov_len = sizeof(pclc);
+	vec[0].iov_base = &pclc;
+	vec[0].iov_len = sizeof(pclc);
+	vec[1].iov_base = &pclc_prfx;
+	vec[1].iov_len = sizeof(pclc_prfx);
+	vec[2].iov_base = &trl;
+	vec[2].iov_len = sizeof(trl);
 	/* due to the few bytes needed for clc-handshake this cannot block */
-	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(pclc));
+	len = kernel_sendmsg(smc->clcsock, &msg, vec, 3, plen);
 	if (len < sizeof(pclc)) {
 		if (len >= 0) {
 			reason_code = -ENETUNREACH;

net/smc/smc_clc.h

@@ -62,17 +62,31 @@ struct smc_clc_msg_local {	/* header2 of clc messages */
 	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 */
+struct smc_clc_ipv6_prefix {
+	u8 prefix[4];
+	u8 prefix_len;
+} __packed;
+
+struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
 	__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_proposal {	/* clc proposal message sent by Linux */
+	struct smc_clc_msg_hdr hdr;
+	struct smc_clc_msg_local lcl;
+	__be16 iparea_offset;	/* offset to IP address information area */
+} __aligned(4);
+
+#define SMC_CLC_PROPOSAL_MAX_OFFSET	0x28
+#define SMC_CLC_PROPOSAL_MAX_PREFIX	(8 * sizeof(struct smc_clc_ipv6_prefix))
+#define SMC_CLC_MAX_LEN		(sizeof(struct smc_clc_msg_proposal) + \
+				 SMC_CLC_PROPOSAL_MAX_OFFSET + \
+				 SMC_CLC_PROPOSAL_MAX_PREFIX + \
+				 sizeof(struct smc_clc_msg_trail))
+
 struct smc_clc_msg_accept_confirm {	/* clc accept / confirm message */
 	struct smc_clc_msg_hdr hdr;
 	struct smc_clc_msg_local lcl;
@@ -102,6 +116,14 @@ struct smc_clc_msg_decline {	/* clc decline message */
 	struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */
 } __aligned(4);
 
+/* determine start of the prefix area within the proposal message */
+static inline struct smc_clc_msg_proposal_prefix *
+smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc)
+{
+	return (struct smc_clc_msg_proposal_prefix *)
+	       ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset));
+}
+
 struct smc_sock;
 struct smc_ib_device;