linux/net/smc/smc_clc.c

605 lines
18 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* 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, 2018
*
* Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com>
*/
#include <linux/in.h>
#include <linux/inetdevice.h>
#include <linux/if_ether.h>
sched/headers: Move task_struct::signal and task_struct::sighand types and accessors into <linux/sched/signal.h> task_struct::signal and task_struct::sighand are pointers, which would normally make it straightforward to not define those types in sched.h. That is not so, because the types are accompanied by a myriad of APIs (macros and inline functions) that dereference them. Split the types and the APIs out of sched.h and move them into a new header, <linux/sched/signal.h>. With this change sched.h does not know about 'struct signal' and 'struct sighand' anymore, trying to put accessors into sched.h as a test fails the following way: ./include/linux/sched.h: In function ‘test_signal_types’: ./include/linux/sched.h:2461:18: error: dereferencing pointer to incomplete type ‘struct signal_struct’ ^ This reduces the size and complexity of sched.h significantly. Update all headers and .c code that relied on getting the signal handling functionality from <linux/sched.h> to include <linux/sched/signal.h>. The list of affected files in the preparatory patch was partly generated by grepping for the APIs, and partly by doing coverage build testing, both all[yes|mod|def|no]config builds on 64-bit and 32-bit x86, and an array of cross-architecture builds. Nevertheless some (trivial) build breakage is still expected related to rare Kconfig combinations and in-flight patches to various kernel code, but most of it should be handled by this patch. Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-02-02 15:35:14 +08:00
#include <linux/sched/signal.h>
#include <net/addrconf.h>
#include <net/sock.h>
#include <net/tcp.h>
#include "smc.h"
#include "smc_core.h"
#include "smc_clc.h"
#include "smc_ib.h"
#include "smc_ism.h"
#define SMCR_CLC_ACCEPT_CONFIRM_LEN 68
#define SMCD_CLC_ACCEPT_CONFIRM_LEN 48
#define SMC_CLC_RECV_BUF_LEN 100
/* eye catcher "SMCR" EBCDIC for CLC messages */
static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'};
/* eye catcher "SMCD" EBCDIC for CLC messages */
static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'};
/* 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, bool check_trl)
{
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)) &&
memcmp(clcm->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_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:
if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D)
return false;
clc = (struct smc_clc_msg_accept_confirm *)clcm;
if ((clcm->path == SMC_TYPE_R &&
ntohs(clc->hdr.length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) ||
(clcm->path == SMC_TYPE_D &&
ntohs(clc->hdr.length) != SMCD_CLC_ACCEPT_CONFIRM_LEN))
return false;
trl = (struct smc_clc_msg_trail *)
((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*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 (check_trl &&
memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) &&
memcmp(trl->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)))
return false;
return true;
}
/* find ipv4 addr on device and get the prefix len, fill CLC proposal msg */
static int smc_clc_prfx_set4_rcu(struct dst_entry *dst, __be32 ipv4,
struct smc_clc_msg_proposal_prefix *prop)
{
struct in_device *in_dev = __in_dev_get_rcu(dst->dev);
const struct in_ifaddr *ifa;
if (!in_dev)
return -ENODEV;
in_dev_for_each_ifa_rcu(ifa, in_dev) {
if (!inet_ifa_match(ipv4, ifa))
continue;
prop->prefix_len = inet_mask_len(ifa->ifa_mask);
prop->outgoing_subnet = ifa->ifa_address & ifa->ifa_mask;
/* prop->ipv6_prefixes_cnt = 0; already done by memset before */
return 0;
}
return -ENOENT;
}
/* fill CLC proposal msg with ipv6 prefixes from device */
static int smc_clc_prfx_set6_rcu(struct dst_entry *dst,
struct smc_clc_msg_proposal_prefix *prop,
struct smc_clc_ipv6_prefix *ipv6_prfx)
{
#if IS_ENABLED(CONFIG_IPV6)
struct inet6_dev *in6_dev = __in6_dev_get(dst->dev);
struct inet6_ifaddr *ifa;
int cnt = 0;
if (!in6_dev)
return -ENODEV;
/* use a maximum of 8 IPv6 prefixes from device */
list_for_each_entry(ifa, &in6_dev->addr_list, if_list) {
if (ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)
continue;
ipv6_addr_prefix(&ipv6_prfx[cnt].prefix,
&ifa->addr, ifa->prefix_len);
ipv6_prfx[cnt].prefix_len = ifa->prefix_len;
cnt++;
if (cnt == SMC_CLC_MAX_V6_PREFIX)
break;
}
prop->ipv6_prefixes_cnt = cnt;
if (cnt)
return 0;
#endif
return -ENOENT;
}
/* retrieve and set prefixes in CLC proposal msg */
static int smc_clc_prfx_set(struct socket *clcsock,
struct smc_clc_msg_proposal_prefix *prop,
struct smc_clc_ipv6_prefix *ipv6_prfx)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
struct sockaddr_storage addrs;
struct sockaddr_in6 *addr6;
struct sockaddr_in *addr;
int rc = -ENOENT;
if (!dst) {
rc = -ENOTCONN;
goto out;
}
if (!dst->dev) {
rc = -ENODEV;
goto out_rel;
}
/* get address to which the internal TCP socket is bound */
kernel_getsockname(clcsock, (struct sockaddr *)&addrs);
/* analyze IP specific data of net_device belonging to TCP socket */
addr6 = (struct sockaddr_in6 *)&addrs;
rcu_read_lock();
if (addrs.ss_family == PF_INET) {
/* IPv4 */
addr = (struct sockaddr_in *)&addrs;
rc = smc_clc_prfx_set4_rcu(dst, addr->sin_addr.s_addr, prop);
} else if (ipv6_addr_v4mapped(&addr6->sin6_addr)) {
/* mapped IPv4 address - peer is IPv4 only */
rc = smc_clc_prfx_set4_rcu(dst, addr6->sin6_addr.s6_addr32[3],
prop);
} else {
/* IPv6 */
rc = smc_clc_prfx_set6_rcu(dst, prop, ipv6_prfx);
}
rcu_read_unlock();
out_rel:
dst_release(dst);
out:
return rc;
}
/* match ipv4 addrs of dev against addr in CLC proposal */
static int smc_clc_prfx_match4_rcu(struct net_device *dev,
struct smc_clc_msg_proposal_prefix *prop)
{
struct in_device *in_dev = __in_dev_get_rcu(dev);
const struct in_ifaddr *ifa;
if (!in_dev)
return -ENODEV;
in_dev_for_each_ifa_rcu(ifa, in_dev) {
if (prop->prefix_len == inet_mask_len(ifa->ifa_mask) &&
inet_ifa_match(prop->outgoing_subnet, ifa))
return 0;
}
return -ENOENT;
}
/* match ipv6 addrs of dev against addrs in CLC proposal */
static int smc_clc_prfx_match6_rcu(struct net_device *dev,
struct smc_clc_msg_proposal_prefix *prop)
{
#if IS_ENABLED(CONFIG_IPV6)
struct inet6_dev *in6_dev = __in6_dev_get(dev);
struct smc_clc_ipv6_prefix *ipv6_prfx;
struct inet6_ifaddr *ifa;
int i, max;
if (!in6_dev)
return -ENODEV;
/* ipv6 prefix list starts behind smc_clc_msg_proposal_prefix */
ipv6_prfx = (struct smc_clc_ipv6_prefix *)((u8 *)prop + sizeof(*prop));
max = min_t(u8, prop->ipv6_prefixes_cnt, SMC_CLC_MAX_V6_PREFIX);
list_for_each_entry(ifa, &in6_dev->addr_list, if_list) {
if (ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)
continue;
for (i = 0; i < max; i++) {
if (ifa->prefix_len == ipv6_prfx[i].prefix_len &&
ipv6_prefix_equal(&ifa->addr, &ipv6_prfx[i].prefix,
ifa->prefix_len))
return 0;
}
}
#endif
return -ENOENT;
}
/* check if proposed prefixes match one of our device prefixes */
int smc_clc_prfx_match(struct socket *clcsock,
struct smc_clc_msg_proposal_prefix *prop)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
int rc;
if (!dst) {
rc = -ENOTCONN;
goto out;
}
if (!dst->dev) {
rc = -ENODEV;
goto out_rel;
}
rcu_read_lock();
if (!prop->ipv6_prefixes_cnt)
rc = smc_clc_prfx_match4_rcu(dst->dev, prop);
else
rc = smc_clc_prfx_match6_rcu(dst->dev, prop);
rcu_read_unlock();
out_rel:
dst_release(dst);
out:
return rc;
}
/* 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, unsigned long timeout)
{
long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo;
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 = {buf, buflen};
int len, datlen, recvlen;
bool check_trl = true;
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
*/
/*
* Caller must make sure that buflen is no less than
* sizeof(struct smc_clc_msg_hdr)
*/
krflags = MSG_PEEK | MSG_WAITALL;
clc_sk->sk_rcvtimeo = timeout;
iov_iter_kvec(&msg.msg_iter, READ, &vec, 1,
sizeof(struct smc_clc_msg_hdr));
len = sock_recvmsg(smc->clcsock, &msg, 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;
if (clc_sk->sk_err == EAGAIN &&
expected_type == SMC_CLC_DECLINE)
clc_sk->sk_err = 0; /* reset for fallback usage */
else
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) {
if (len != -EAGAIN || expected_type != SMC_CLC_DECLINE)
smc->sk.sk_err = -len;
reason_code = len;
goto out;
}
datlen = ntohs(clcm->length);
if ((len < sizeof(struct smc_clc_msg_hdr)) ||
(clcm->version < SMC_V1) ||
((clcm->type != SMC_CLC_DECLINE) &&
(clcm->type != expected_type))) {
smc->sk.sk_err = EPROTO;
reason_code = -EPROTO;
goto out;
}
if (clcm->type == SMC_CLC_PROPOSAL && clcm->path == SMC_TYPE_N)
reason_code = SMC_CLC_DECL_VERSMISMAT; /* just V2 offered */
/* receive the complete CLC message */
memset(&msg, 0, sizeof(struct msghdr));
if (datlen > buflen) {
check_trl = false;
recvlen = buflen;
} else {
recvlen = datlen;
}
iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, recvlen);
krflags = MSG_WAITALL;
len = sock_recvmsg(smc->clcsock, &msg, krflags);
if (len < recvlen || !smc_clc_msg_hdr_valid(clcm, check_trl)) {
smc->sk.sk_err = EPROTO;
reason_code = -EPROTO;
goto out;
}
datlen -= len;
while (datlen) {
u8 tmp[SMC_CLC_RECV_BUF_LEN];
vec.iov_base = &tmp;
vec.iov_len = SMC_CLC_RECV_BUF_LEN;
/* receive remaining proposal message */
recvlen = datlen > SMC_CLC_RECV_BUF_LEN ?
SMC_CLC_RECV_BUF_LEN : datlen;
iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, recvlen);
len = sock_recvmsg(smc->clcsock, &msg, krflags);
datlen -= len;
}
if (clcm->type == SMC_CLC_DECLINE) {
struct smc_clc_msg_decline *dclc;
dclc = (struct smc_clc_msg_decline *)clcm;
reason_code = SMC_CLC_DECL_PEERDECL;
smc->peer_diagnosis = ntohl(dclc->peer_diagnosis);
if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
smc->conn.lgr->sync_err = 1;
smc_lgr_terminate_sched(smc->conn.lgr);
}
}
out:
clc_sk->sk_rcvtimeo = rcvtimeo;
return reason_code;
}
/* send CLC DECLINE message across internal TCP socket */
int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
{
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_V1;
dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
if ((!smc->conn.lgr || !smc->conn.lgr->is_smcd) &&
smc_ib_is_valid_local_systemid())
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 < 0 || len < sizeof(struct smc_clc_msg_decline))
len = -EPROTO;
return len > 0 ? 0 : len;
}
/* send CLC PROPOSAL message across internal TCP socket */
int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
struct smc_init_info *ini)
{
struct smc_clc_msg_proposal_prefix *pclc_prfx;
struct smc_clc_msg_proposal *pclc_base;
struct smc_clc_msg_proposal_area *pclc;
struct smc_clc_ipv6_prefix *ipv6_prfx;
struct smc_clc_msg_smcd *pclc_smcd;
struct smc_clc_msg_trail *trl;
int len, i, plen, rc;
int reason_code = 0;
struct kvec vec[5];
struct msghdr msg;
pclc = kzalloc(sizeof(*pclc), GFP_KERNEL);
if (!pclc)
return -ENOMEM;
pclc_base = &pclc->pclc_base;
pclc_smcd = &pclc->pclc_smcd;
pclc_prfx = &pclc->pclc_prfx;
ipv6_prfx = pclc->pclc_prfx_ipv6;
trl = &pclc->pclc_trl;
/* retrieve ip prefixes for CLC proposal msg */
rc = smc_clc_prfx_set(smc->clcsock, pclc_prfx, ipv6_prfx);
if (rc) {
kfree(pclc);
return SMC_CLC_DECL_CNFERR; /* configuration error */
}
/* send SMC Proposal CLC message */
plen = sizeof(*pclc_base) + sizeof(*pclc_prfx) +
(pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0])) +
sizeof(*trl);
memcpy(pclc_base->hdr.eyecatcher, SMC_EYECATCHER,
sizeof(SMC_EYECATCHER));
pclc_base->hdr.type = SMC_CLC_PROPOSAL;
pclc_base->hdr.version = SMC_V1; /* SMC version */
pclc_base->hdr.path = smc_type;
if (smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B) {
/* add SMC-R specifics */
memcpy(pclc_base->lcl.id_for_peer, local_systemid,
sizeof(local_systemid));
memcpy(pclc_base->lcl.gid, ini->ib_gid, SMC_GID_SIZE);
memcpy(pclc_base->lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1],
ETH_ALEN);
pclc_base->iparea_offset = htons(0);
}
if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
/* add SMC-D specifics */
plen += sizeof(*pclc_smcd);
pclc_base->iparea_offset = htons(sizeof(*pclc_smcd));
pclc_smcd->gid = ini->ism_dev->local_gid;
}
pclc_base->hdr.length = htons(plen);
memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
memset(&msg, 0, sizeof(msg));
i = 0;
vec[i].iov_base = pclc_base;
vec[i++].iov_len = sizeof(*pclc_base);
if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
vec[i].iov_base = pclc_smcd;
vec[i++].iov_len = sizeof(*pclc_smcd);
}
vec[i].iov_base = pclc_prfx;
vec[i++].iov_len = sizeof(*pclc_prfx);
if (pclc_prfx->ipv6_prefixes_cnt > 0) {
vec[i].iov_base = ipv6_prfx;
vec[i++].iov_len = pclc_prfx->ipv6_prefixes_cnt *
sizeof(ipv6_prfx[0]);
}
vec[i].iov_base = trl;
vec[i++].iov_len = sizeof(*trl);
/* due to the few bytes needed for clc-handshake this cannot block */
len = kernel_sendmsg(smc->clcsock, &msg, vec, i, plen);
if (len < 0) {
smc->sk.sk_err = smc->clcsock->sk->sk_err;
reason_code = -smc->sk.sk_err;
} else if (len < ntohs(pclc_base->hdr.length)) {
reason_code = -ENETUNREACH;
smc->sk.sk_err = -reason_code;
}
kfree(pclc);
return reason_code;
}
/* build and send CLC CONFIRM / ACCEPT message */
static int smc_clc_send_confirm_accept(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *clc,
int first_contact)
{
struct smc_connection *conn = &smc->conn;
struct msghdr msg;
struct kvec vec;
/* send SMC Confirm CLC msg */
clc->hdr.version = SMC_V1; /* SMC version */
if (first_contact)
clc->hdr.flag = 1;
if (conn->lgr->is_smcd) {
/* SMC-D specific settings */
memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER,
sizeof(SMCD_EYECATCHER));
clc->hdr.path = SMC_TYPE_D;
clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
clc->d0.gid = conn->lgr->smcd->local_gid;
clc->d0.token = conn->rmb_desc->token;
clc->d0.dmbe_size = conn->rmbe_size_short;
clc->d0.dmbe_idx = 0;
memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
memcpy(clc->d0.smcd_trl.eyecatcher, SMCD_EYECATCHER,
sizeof(SMCD_EYECATCHER));
} else {
struct smc_link *link = conn->lnk;
/* SMC-R specific settings */
link = conn->lnk;
memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER,
sizeof(SMC_EYECATCHER));
clc->hdr.path = SMC_TYPE_R;
clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
memcpy(clc->r0.lcl.id_for_peer, local_systemid,
sizeof(local_systemid));
memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE);
memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
ETH_ALEN);
hton24(clc->r0.qpn, link->roce_qp->qp_num);
clc->r0.rmb_rkey =
htonl(conn->rmb_desc->mr_rx[link->link_idx]->rkey);
clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
clc->r0.rmbe_alert_token = htonl(conn->alert_token_local);
switch (clc->hdr.type) {
case SMC_CLC_ACCEPT:
clc->r0.qp_mtu = link->path_mtu;
break;
case SMC_CLC_CONFIRM:
clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu);
break;
}
clc->r0.rmbe_size = conn->rmbe_size_short;
clc->r0.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
(conn->rmb_desc->sgt[link->link_idx].sgl));
hton24(clc->r0.psn, link->psn_initial);
memcpy(clc->r0.smcr_trl.eyecatcher, SMC_EYECATCHER,
sizeof(SMC_EYECATCHER));
}
memset(&msg, 0, sizeof(msg));
vec.iov_base = clc;
vec.iov_len = ntohs(clc->hdr.length);
return kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
ntohs(clc->hdr.length));
}
/* 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;
int len;
/* send SMC Confirm CLC msg */
memset(&cclc, 0, sizeof(cclc));
cclc.hdr.type = SMC_CLC_CONFIRM;
len = smc_clc_send_confirm_accept(smc, &cclc, 0);
if (len < ntohs(cclc.hdr.length)) {
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, bool srv_first_contact)
{
struct smc_clc_msg_accept_confirm aclc;
int len;
memset(&aclc, 0, sizeof(aclc));
aclc.hdr.type = SMC_CLC_ACCEPT;
len = smc_clc_send_confirm_accept(new_smc, &aclc, srv_first_contact);
if (len < ntohs(aclc.hdr.length))
len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
return len > 0 ? 0 : len;
}