* Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2012, 2015, Intel Corporation.
+ * Copyright (c) 2012, 2016, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
kib_tx_t *tx;
kib_tx_poolset_t *tps;
- tps = net->ibn_tx_ps[lnet_cpt_of_nid(target)];
+ tps = net->ibn_tx_ps[lnet_cpt_of_nid(target, ni)];
node = kiblnd_pool_alloc_node(&tps->tps_poolset);
if (node == NULL)
return NULL;
LASSERT(tx->tx_queued);
/* We rely on this for QP sizing */
LASSERT(tx->tx_nwrq > 0);
+ LASSERT(tx->tx_nwrq <= 1 + conn->ibc_max_frags);
LASSERT(credit == 0 || credit == 1);
LASSERT(conn->ibc_outstanding_credits >= 0);
LASSERT (type == IBLND_MSG_GET_DONE ||
type == IBLND_MSG_PUT_DONE);
- if (kiblnd_rd_size(srcrd) > conn->ibc_max_frags << PAGE_SHIFT) {
- CERROR("RDMA is too large for peer %s (%d), src size: %d dst size: %d\n",
- libcfs_nid2str(conn->ibc_peer->ibp_nid),
- conn->ibc_max_frags << PAGE_SHIFT,
- kiblnd_rd_size(srcrd), kiblnd_rd_size(dstrd));
- GOTO(too_big, rc = -EMSGSIZE);
- }
-
srcidx = dstidx = 0;
while (resid > 0) {
break;
}
- if (tx->tx_nwrq >= IBLND_MAX_RDMA_FRAGS) {
+ if (tx->tx_nwrq >= conn->ibc_max_frags) {
CERROR("RDMA has too many fragments for peer %s (%d), "
"src idx/frags: %d/%d dst idx/frags: %d/%d\n",
libcfs_nid2str(conn->ibc_peer->ibp_nid),
- IBLND_MAX_RDMA_FRAGS,
+ conn->ibc_max_frags,
srcidx, srcrd->rd_nfrags,
dstidx, dstrd->rd_nfrags);
rc = -EMSGSIZE;
wrq++;
sge++;
}
-too_big:
+
if (rc < 0) /* no RDMA if completing with failure */
tx->tx_nwrq = 0;
* connected */
read_lock_irqsave(g_lock, flags);
- peer = kiblnd_find_peer_locked(nid);
+ peer = kiblnd_find_peer_locked(ni, nid);
if (peer != NULL && !list_empty(&peer->ibp_conns)) {
/* Found a peer with an established connection */
conn = kiblnd_get_conn_locked(peer);
/* Re-try with a write lock */
write_lock(g_lock);
- peer = kiblnd_find_peer_locked(nid);
+ peer = kiblnd_find_peer_locked(ni, nid);
if (peer != NULL) {
if (list_empty(&peer->ibp_conns)) {
/* found a peer, but it's still connecting... */
write_lock_irqsave(g_lock, flags);
- peer2 = kiblnd_find_peer_locked(nid);
+ peer2 = kiblnd_find_peer_locked(ni, nid);
if (peer2 != NULL) {
if (list_empty(&peer2->ibp_conns)) {
/* found a peer, but it's still connecting... */
kib_rej_t rej;
int version = IBLND_MSG_VERSION;
unsigned long flags;
- int max_frags;
int rc;
struct sockaddr_in *peer_addr;
LASSERT (!in_interrupt());
__u32 ip = ntohl(peer_addr->sin_addr.s_addr);
CERROR("Peer's port (%pI4h:%hu) is not privileged\n",
&ip, ntohs(peer_addr->sin_port));
- goto failed;
- }
+ goto failed;
+ }
- if (priv_nob < offsetof(kib_msg_t, ibm_type)) {
- CERROR("Short connection request\n");
- goto failed;
- }
+ if (priv_nob < offsetof(kib_msg_t, ibm_type)) {
+ CERROR("Short connection request\n");
+ goto failed;
+ }
- /* Future protocol version compatibility support! If the
- * o2iblnd-specific protocol changes, or when LNET unifies
- * protocols over all LNDs, the initial connection will
- * negotiate a protocol version. I trap this here to avoid
- * console errors; the reject tells the peer which protocol I
- * speak. */
- if (reqmsg->ibm_magic == LNET_PROTO_MAGIC ||
- reqmsg->ibm_magic == __swab32(LNET_PROTO_MAGIC))
- goto failed;
- if (reqmsg->ibm_magic == IBLND_MSG_MAGIC &&
- reqmsg->ibm_version != IBLND_MSG_VERSION &&
- reqmsg->ibm_version != IBLND_MSG_VERSION_1)
- goto failed;
- if (reqmsg->ibm_magic == __swab32(IBLND_MSG_MAGIC) &&
- reqmsg->ibm_version != __swab16(IBLND_MSG_VERSION) &&
- reqmsg->ibm_version != __swab16(IBLND_MSG_VERSION_1))
- goto failed;
+ /* Future protocol version compatibility support! If the
+ * o2iblnd-specific protocol changes, or when LNET unifies
+ * protocols over all LNDs, the initial connection will
+ * negotiate a protocol version. I trap this here to avoid
+ * console errors; the reject tells the peer which protocol I
+ * speak. */
+ if (reqmsg->ibm_magic == LNET_PROTO_MAGIC ||
+ reqmsg->ibm_magic == __swab32(LNET_PROTO_MAGIC))
+ goto failed;
+ if (reqmsg->ibm_magic == IBLND_MSG_MAGIC &&
+ reqmsg->ibm_version != IBLND_MSG_VERSION &&
+ reqmsg->ibm_version != IBLND_MSG_VERSION_1)
+ goto failed;
+ if (reqmsg->ibm_magic == __swab32(IBLND_MSG_MAGIC) &&
+ reqmsg->ibm_version != __swab16(IBLND_MSG_VERSION) &&
+ reqmsg->ibm_version != __swab16(IBLND_MSG_VERSION_1))
+ goto failed;
- rc = kiblnd_unpack_msg(reqmsg, priv_nob);
- if (rc != 0) {
- CERROR("Can't parse connection request: %d\n", rc);
- goto failed;
- }
+ rc = kiblnd_unpack_msg(reqmsg, priv_nob);
+ if (rc != 0) {
+ CERROR("Can't parse connection request: %d\n", rc);
+ goto failed;
+ }
- nid = reqmsg->ibm_srcnid;
- ni = lnet_net2ni(LNET_NIDNET(reqmsg->ibm_dstnid));
+ nid = reqmsg->ibm_srcnid;
+ ni = lnet_nid2ni_addref(reqmsg->ibm_dstnid);
- if (ni != NULL) {
- net = (kib_net_t *)ni->ni_data;
- rej.ibr_incarnation = net->ibn_incarnation;
- }
+ if (ni != NULL) {
+ net = (kib_net_t *)ni->ni_data;
+ rej.ibr_incarnation = net->ibn_incarnation;
+ }
- if (ni == NULL || /* no matching net */
- ni->ni_nid != reqmsg->ibm_dstnid || /* right NET, wrong NID! */
- net->ibn_dev != ibdev) { /* wrong device */
+ if (ni == NULL || /* no matching net */
+ ni->ni_nid != reqmsg->ibm_dstnid || /* right NET, wrong NID! */
+ net->ibn_dev != ibdev) { /* wrong device */
CERROR("Can't accept conn from %s on %s (%s:%d:%pI4h): "
- "bad dst nid %s\n", libcfs_nid2str(nid),
- ni == NULL ? "NA" : libcfs_nid2str(ni->ni_nid),
- ibdev->ibd_ifname, ibdev->ibd_nnets,
+ "bad dst nid %s\n", libcfs_nid2str(nid),
+ ni == NULL ? "NA" : libcfs_nid2str(ni->ni_nid),
+ ibdev->ibd_ifname, ibdev->ibd_nnets,
&ibdev->ibd_ifip,
- libcfs_nid2str(reqmsg->ibm_dstnid));
+ libcfs_nid2str(reqmsg->ibm_dstnid));
- goto failed;
- }
+ goto failed;
+ }
/* check time stamp as soon as possible */
- if (reqmsg->ibm_dststamp != 0 &&
- reqmsg->ibm_dststamp != net->ibn_incarnation) {
- CWARN("Stale connection request\n");
- rej.ibr_why = IBLND_REJECT_CONN_STALE;
- goto failed;
- }
+ if (reqmsg->ibm_dststamp != 0 &&
+ reqmsg->ibm_dststamp != net->ibn_incarnation) {
+ CWARN("Stale connection request\n");
+ rej.ibr_why = IBLND_REJECT_CONN_STALE;
+ goto failed;
+ }
- /* I can accept peer's version */
- version = reqmsg->ibm_version;
+ /* I can accept peer's version */
+ version = reqmsg->ibm_version;
- if (reqmsg->ibm_type != IBLND_MSG_CONNREQ) {
- CERROR("Unexpected connreq msg type: %x from %s\n",
- reqmsg->ibm_type, libcfs_nid2str(nid));
- goto failed;
- }
+ if (reqmsg->ibm_type != IBLND_MSG_CONNREQ) {
+ CERROR("Unexpected connreq msg type: %x from %s\n",
+ reqmsg->ibm_type, libcfs_nid2str(nid));
+ goto failed;
+ }
if (reqmsg->ibm_u.connparams.ibcp_queue_depth >
kiblnd_msg_queue_size(version, ni)) {
goto failed;
}
- max_frags = reqmsg->ibm_u.connparams.ibcp_max_frags >> IBLND_FRAG_SHIFT;
- if (max_frags > kiblnd_rdma_frags(version, ni)) {
+ if (reqmsg->ibm_u.connparams.ibcp_max_frags >
+ kiblnd_rdma_frags(version, ni)) {
CWARN("Can't accept conn from %s (version %x): "
- "max message size %d is too large (%d wanted)\n",
- libcfs_nid2str(nid), version, max_frags,
+ "max_frags %d too large (%d wanted)\n",
+ libcfs_nid2str(nid), version,
+ reqmsg->ibm_u.connparams.ibcp_max_frags,
kiblnd_rdma_frags(version, ni));
if (version >= IBLND_MSG_VERSION)
rej.ibr_why = IBLND_REJECT_RDMA_FRAGS;
goto failed;
- } else if ((max_frags < kiblnd_rdma_frags(version, ni)) &&
+ } else if (reqmsg->ibm_u.connparams.ibcp_max_frags <
+ kiblnd_rdma_frags(version, ni) &&
net->ibn_fmr_ps == NULL) {
CWARN("Can't accept conn from %s (version %x): "
- "max message size %d incompatible without FMR pool "
+ "max_frags %d incompatible without FMR pool "
"(%d wanted)\n",
- libcfs_nid2str(nid), version, max_frags,
+ libcfs_nid2str(nid), version,
+ reqmsg->ibm_u.connparams.ibcp_max_frags,
kiblnd_rdma_frags(version, ni));
if (version == IBLND_MSG_VERSION)
}
/* We have validated the peer's parameters so use those */
- peer->ibp_max_frags = max_frags;
+ peer->ibp_max_frags = reqmsg->ibm_u.connparams.ibcp_max_frags;
peer->ibp_queue_depth = reqmsg->ibm_u.connparams.ibcp_queue_depth;
write_lock_irqsave(g_lock, flags);
- peer2 = kiblnd_find_peer_locked(nid);
+ peer2 = kiblnd_find_peer_locked(ni, nid);
if (peer2 != NULL) {
if (peer2->ibp_version == 0) {
peer2->ibp_version = version;
kiblnd_init_msg(ackmsg, IBLND_MSG_CONNACK,
sizeof(ackmsg->ibm_u.connparams));
ackmsg->ibm_u.connparams.ibcp_queue_depth = conn->ibc_queue_depth;
- ackmsg->ibm_u.connparams.ibcp_max_frags = conn->ibc_max_frags << IBLND_FRAG_SHIFT;
+ ackmsg->ibm_u.connparams.ibcp_max_frags = conn->ibc_max_frags;
ackmsg->ibm_u.connparams.ibcp_max_msg_size = IBLND_MSG_SIZE;
kiblnd_pack_msg(ni, ackmsg, version, 0, nid, reqmsg->ibm_srcstamp);
if (cp) {
msg_size = cp->ibcp_max_msg_size;
- frag_num = cp->ibcp_max_frags << IBLND_FRAG_SHIFT;
+ frag_num = cp->ibcp_max_frags;
queue_dep = cp->ibcp_queue_depth;
}
break;
case IBLND_REJECT_RDMA_FRAGS: {
- struct lnet_ioctl_config_lnd_tunables *tunables;
+ struct lnet_ioctl_config_o2iblnd_tunables *tunables;
if (!cp) {
reason = "can't negotiate max frags";
goto out;
}
- tunables = peer->ibp_ni->ni_lnd_tunables;
- if (!tunables->lt_tun_u.lt_o2ib.lnd_map_on_demand) {
+ tunables = &peer->ibp_ni->ni_lnd_tunables.lnd_tun_u.lnd_o2ib;
+ if (!tunables->lnd_map_on_demand) {
reason = "map_on_demand must be enabled";
goto out;
}
goto failed;
}
- if ((msg->ibm_u.connparams.ibcp_max_frags >> IBLND_FRAG_SHIFT) >
+ if (msg->ibm_u.connparams.ibcp_max_frags >
conn->ibc_max_frags) {
CERROR("%s has incompatible max_frags %d (<=%d wanted)\n",
libcfs_nid2str(peer->ibp_nid),
- msg->ibm_u.connparams.ibcp_max_frags >> IBLND_FRAG_SHIFT,
+ msg->ibm_u.connparams.ibcp_max_frags,
conn->ibc_max_frags);
rc = -EPROTO;
goto failed;
conn->ibc_credits = msg->ibm_u.connparams.ibcp_queue_depth;
conn->ibc_reserved_credits = msg->ibm_u.connparams.ibcp_queue_depth;
conn->ibc_queue_depth = msg->ibm_u.connparams.ibcp_queue_depth;
- conn->ibc_max_frags = msg->ibm_u.connparams.ibcp_max_frags >> IBLND_FRAG_SHIFT;
+ conn->ibc_max_frags = msg->ibm_u.connparams.ibcp_max_frags;
LASSERT(conn->ibc_credits + conn->ibc_reserved_credits +
IBLND_OOB_MSGS(ver) <= IBLND_RX_MSGS(conn));
memset(msg, 0, sizeof(*msg));
kiblnd_init_msg(msg, IBLND_MSG_CONNREQ, sizeof(msg->ibm_u.connparams));
msg->ibm_u.connparams.ibcp_queue_depth = conn->ibc_queue_depth;
- msg->ibm_u.connparams.ibcp_max_frags = conn->ibc_max_frags << IBLND_FRAG_SHIFT;
+ msg->ibm_u.connparams.ibcp_max_frags = conn->ibc_max_frags;
msg->ibm_u.connparams.ibcp_max_msg_size = IBLND_MSG_SIZE;
kiblnd_pack_msg(peer->ibp_ni, msg, version,
}
while (reconn < KIB_RECONN_BREAK) {
- if (kiblnd_data.kib_reconn_sec != get_seconds()) {
- kiblnd_data.kib_reconn_sec = get_seconds();
+ if (kiblnd_data.kib_reconn_sec !=
+ ktime_get_real_seconds()) {
+ kiblnd_data.kib_reconn_sec = ktime_get_real_seconds();
list_splice_init(&kiblnd_data.kib_reconn_wait,
&kiblnd_data.kib_reconn_list);
}
rc = cfs_cpt_bind(lnet_cpt_table(), sched->ibs_cpt);
if (rc != 0) {
- CWARN("Failed to bind on CPT %d, please verify whether "
- "all CPUs are healthy and reload modules if necessary, "
- "otherwise your system might under risk of low "
- "performance\n", sched->ibs_cpt);
+ CWARN("Unable to bind on CPU partition %d, please verify "
+ "whether all CPUs are healthy and reload modules if "
+ "necessary, otherwise your system might under risk of "
+ "low performance\n", sched->ibs_cpt);
}
spin_lock_irqsave(&sched->ibs_lock, flags);