diff options
Diffstat (limited to 'net')
66 files changed, 1097 insertions, 749 deletions
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 37a78d20c0f6..ba1210253f5e 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -94,8 +94,6 @@ struct p9_trans_rdma { struct ib_pd *pd; struct ib_qp *qp; struct ib_cq *cq; - struct ib_mr *dma_mr; - u32 lkey; long timeout; int sq_depth; struct semaphore sq_sem; @@ -382,9 +380,6 @@ static void rdma_destroy_trans(struct p9_trans_rdma *rdma) if (!rdma) return; - if (rdma->dma_mr && !IS_ERR(rdma->dma_mr)) - ib_dereg_mr(rdma->dma_mr); - if (rdma->qp && !IS_ERR(rdma->qp)) ib_destroy_qp(rdma->qp); @@ -415,7 +410,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c) sge.addr = c->busa; sge.length = client->msize; - sge.lkey = rdma->lkey; + sge.lkey = rdma->pd->local_dma_lkey; wr.next = NULL; c->wc_op = IB_WC_RECV; @@ -506,7 +501,7 @@ dont_need_post_recv: sge.addr = c->busa; sge.length = c->req->tc->size; - sge.lkey = rdma->lkey; + sge.lkey = rdma->pd->local_dma_lkey; wr.next = NULL; c->wc_op = IB_WC_SEND; @@ -647,7 +642,6 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) struct p9_trans_rdma *rdma; struct rdma_conn_param conn_param; struct ib_qp_init_attr qp_attr; - struct ib_device_attr devattr; struct ib_cq_init_attr cq_attr = {}; /* Parse the transport specific mount options */ @@ -700,11 +694,6 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) if (err || (rdma->state != P9_RDMA_ROUTE_RESOLVED)) goto error; - /* Query the device attributes */ - err = ib_query_device(rdma->cm_id->device, &devattr); - if (err) - goto error; - /* Create the Completion Queue */ cq_attr.cqe = opts.sq_depth + opts.rq_depth + 1; rdma->cq = ib_create_cq(rdma->cm_id->device, cq_comp_handler, @@ -719,17 +708,6 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) if (IS_ERR(rdma->pd)) goto error; - /* Cache the DMA lkey in the transport */ - rdma->dma_mr = NULL; - if (devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) - rdma->lkey = rdma->cm_id->device->local_dma_lkey; - else { - rdma->dma_mr = ib_get_dma_mr(rdma->pd, IB_ACCESS_LOCAL_WRITE); - if (IS_ERR(rdma->dma_mr)) - goto error; - rdma->lkey = rdma->dma_mr->lkey; - } - /* Create the Queue Pair */ memset(&qp_attr, 0, sizeof qp_attr); qp_attr.event_handler = qp_event_handler; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index af5e187553fd..ea748c93a07f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -16,7 +16,6 @@ #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> -#include <net/switchdev.h> #include <uapi/linux/if_bridge.h> #include "br_private.h" diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 3cd8cc9e804b..5f5a02b49a99 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -117,10 +117,11 @@ out_filt: return err; } -static void __vlan_vid_del(struct net_device *dev, struct net_bridge *br, - u16 vid) +static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, + u16 vid) { const struct net_device_ops *ops = dev->netdev_ops; + int err = 0; /* If driver uses VLAN ndo ops, use 8021q to delete vid * on device, otherwise try switchdev ops to delete vid. @@ -137,8 +138,12 @@ static void __vlan_vid_del(struct net_device *dev, struct net_bridge *br, }, }; - switchdev_port_obj_del(dev, &vlan_obj); + err = switchdev_port_obj_del(dev, &vlan_obj); + if (err == -EOPNOTSUPP) + err = 0; } + + return err; } static int __vlan_del(struct net_port_vlans *v, u16 vid) @@ -151,7 +156,11 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid) if (v->port_idx) { struct net_bridge_port *p = v->parent.port; - __vlan_vid_del(p->dev, p->br, vid); + int err; + + err = __vlan_vid_del(p->dev, p->br, vid); + if (err) + return err; } clear_bit(vid, v->vlan_bitmap); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index f30329f72641..54a00d66509e 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -357,6 +357,7 @@ ceph_parse_options(char *options, const char *dev_name, opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; + opt->monc_ping_timeout = CEPH_MONC_PING_TIMEOUT_DEFAULT; /* get mon ip(s) */ /* ip1[:port1][,ip2[:port2]...] */ @@ -517,8 +518,11 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client) struct ceph_options *opt = client->options; size_t pos = m->count; - if (opt->name) - seq_printf(m, "name=%s,", opt->name); + if (opt->name) { + seq_puts(m, "name="); + seq_escape(m, opt->name, ", \t\n\\"); + seq_putc(m, ','); + } if (opt->key) seq_puts(m, "secret=<hidden>,"); diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 790fe89d90c0..4440edcce0d6 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -79,10 +79,6 @@ int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *inkey) return 0; } - - -#define AES_KEY_SIZE 16 - static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void) { return crypto_alloc_blkcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index e3be1d22a247..525f454f7531 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -163,6 +163,7 @@ static struct kmem_cache *ceph_msg_data_cache; static char tag_msg = CEPH_MSGR_TAG_MSG; static char tag_ack = CEPH_MSGR_TAG_ACK; static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE; +static char tag_keepalive2 = CEPH_MSGR_TAG_KEEPALIVE2; #ifdef CONFIG_LOCKDEP static struct lock_class_key socket_class; @@ -176,7 +177,7 @@ static struct lock_class_key socket_class; static void queue_con(struct ceph_connection *con); static void cancel_con(struct ceph_connection *con); -static void con_work(struct work_struct *); +static void ceph_con_workfn(struct work_struct *); static void con_fault(struct ceph_connection *con); /* @@ -276,22 +277,22 @@ static void _ceph_msgr_exit(void) ceph_msgr_wq = NULL; } - ceph_msgr_slab_exit(); - BUG_ON(zero_page == NULL); page_cache_release(zero_page); zero_page = NULL; + + ceph_msgr_slab_exit(); } int ceph_msgr_init(void) { + if (ceph_msgr_slab_init()) + return -ENOMEM; + BUG_ON(zero_page != NULL); zero_page = ZERO_PAGE(0); page_cache_get(zero_page); - if (ceph_msgr_slab_init()) - return -ENOMEM; - /* * The number of active work items is limited by the number of * connections, so leave @max_active at default. @@ -749,7 +750,7 @@ void ceph_con_init(struct ceph_connection *con, void *private, mutex_init(&con->mutex); INIT_LIST_HEAD(&con->out_queue); INIT_LIST_HEAD(&con->out_sent); - INIT_DELAYED_WORK(&con->work, con_work); + INIT_DELAYED_WORK(&con->work, ceph_con_workfn); con->state = CON_STATE_CLOSED; } @@ -1351,7 +1352,15 @@ static void prepare_write_keepalive(struct ceph_connection *con) { dout("prepare_write_keepalive %p\n", con); con_out_kvec_reset(con); - con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive); + if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) { + struct timespec ts = CURRENT_TIME; + struct ceph_timespec ceph_ts; + ceph_encode_timespec(&ceph_ts, &ts); + con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2); + con_out_kvec_add(con, sizeof(ceph_ts), &ceph_ts); + } else { + con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive); + } con_flag_set(con, CON_FLAG_WRITE_PENDING); } @@ -1625,6 +1634,12 @@ static void prepare_read_tag(struct ceph_connection *con) con->in_tag = CEPH_MSGR_TAG_READY; } +static void prepare_read_keepalive_ack(struct ceph_connection *con) +{ + dout("prepare_read_keepalive_ack %p\n", con); + con->in_base_pos = 0; +} + /* * Prepare to read a message. */ @@ -2322,13 +2337,6 @@ static int read_partial_message(struct ceph_connection *con) return ret; BUG_ON(!con->in_msg ^ skip); - if (con->in_msg && data_len > con->in_msg->data_length) { - pr_warn("%s skipping long message (%u > %zd)\n", - __func__, data_len, con->in_msg->data_length); - ceph_msg_put(con->in_msg); - con->in_msg = NULL; - skip = 1; - } if (skip) { /* skip this message */ dout("alloc_msg said skip message\n"); @@ -2457,6 +2465,17 @@ static void process_message(struct ceph_connection *con) mutex_lock(&con->mutex); } +static int read_keepalive_ack(struct ceph_connection *con) +{ + struct ceph_timespec ceph_ts; + size_t size = sizeof(ceph_ts); + int ret = read_partial(con, size, size, &ceph_ts); + if (ret <= 0) + return ret; + ceph_decode_timespec(&con->last_keepalive_ack, &ceph_ts); + prepare_read_tag(con); + return 1; +} /* * Write something to the socket. Called in a worker thread when the @@ -2526,6 +2545,10 @@ more_kvec: do_next: if (con->state == CON_STATE_OPEN) { + if (con_flag_test_and_clear(con, CON_FLAG_KEEPALIVE_PENDING)) { + prepare_write_keepalive(con); + goto more; + } /* is anything else pending? */ if (!list_empty(&con->out_queue)) { prepare_write_message(con); @@ -2535,10 +2558,6 @@ do_next: prepare_write_ack(con); goto more; } - if (con_flag_test_and_clear(con, CON_FLAG_KEEPALIVE_PENDING)) { - prepare_write_keepalive(con); - goto more; - } } /* Nothing to do! */ @@ -2641,6 +2660,9 @@ more: case CEPH_MSGR_TAG_ACK: prepare_read_ack(con); break; + case CEPH_MSGR_TAG_KEEPALIVE2_ACK: + prepare_read_keepalive_ack(con); + break; case CEPH_MSGR_TAG_CLOSE: con_close_socket(con); con->state = CON_STATE_CLOSED; @@ -2684,6 +2706,12 @@ more: process_ack(con); goto more; } + if (con->in_tag == CEPH_MSGR_TAG_KEEPALIVE2_ACK) { + ret = read_keepalive_ack(con); + if (ret <= 0) + goto out; + goto more; + } out: dout("try_read done on %p ret %d\n", con, ret); @@ -2799,7 +2827,7 @@ static void con_fault_finish(struct ceph_connection *con) /* * Do some work on a connection. Drop a connection ref when we're done. */ -static void con_work(struct work_struct *work) +static void ceph_con_workfn(struct work_struct *work) { struct ceph_connection *con = container_of(work, struct ceph_connection, work.work); @@ -3101,6 +3129,20 @@ void ceph_con_keepalive(struct ceph_connection *con) } EXPORT_SYMBOL(ceph_con_keepalive); +bool ceph_con_keepalive_expired(struct ceph_connection *con, + unsigned long interval) +{ + if (interval > 0 && + (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2)) { + struct timespec now = CURRENT_TIME; + struct timespec ts; + jiffies_to_timespec(interval, &ts); + ts = timespec_add(con->last_keepalive_ack, ts); + return timespec_compare(&now, &ts) >= 0; + } + return false; +} + static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type) { struct ceph_msg_data *data; diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 9d6ff1215928..edda01626a45 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -149,6 +149,10 @@ static int __open_session(struct ceph_mon_client *monc) CEPH_ENTITY_TYPE_MON, monc->cur_mon, &monc->monmap->mon_inst[monc->cur_mon].addr); + /* send an initial keepalive to ensure our timestamp is + * valid by the time we are in an OPENED state */ + ceph_con_keepalive(&monc->con); + /* initiatiate authentication handshake */ ret = ceph_auth_build_hello(monc->auth, monc->m_auth->front.iov_base, @@ -170,14 +174,19 @@ static bool __sub_expired(struct ceph_mon_client *monc) */ static void __schedule_delayed(struct ceph_mon_client *monc) { - unsigned int delay; + struct ceph_options *opt = monc->client->options; + unsigned long delay; - if (monc->cur_mon < 0 || __sub_expired(monc)) + if (monc->cur_mon < 0 || __sub_expired(monc)) { delay = 10 * HZ; - else + } else { delay = 20 * HZ; - dout("__schedule_delayed after %u\n", delay); - schedule_delayed_work(&monc->delayed_work, delay); + if (opt->monc_ping_timeout > 0) + delay = min(delay, opt->monc_ping_timeout / 3); + } + dout("__schedule_delayed after %lu\n", delay); + schedule_delayed_work(&monc->delayed_work, + round_jiffies_relative(delay)); } /* @@ -743,11 +752,23 @@ static void delayed_work(struct work_struct *work) __close_session(monc); __open_session(monc); /* continue hunting */ } else { - ceph_con_keepalive(&monc->con); + struct ceph_options *opt = monc->client->options; + int is_auth = ceph_auth_is_authenticated(monc->auth); + if (ceph_con_keepalive_expired(&monc->con, + opt->monc_ping_timeout)) { + dout("monc keepalive timeout\n"); + is_auth = 0; + __close_session(monc); + monc->hunting = true; + __open_session(monc); + } - __validate_auth(monc); + if (!monc->hunting) { + ceph_con_keepalive(&monc->con); + __validate_auth(monc); + } - if (ceph_auth_is_authenticated(monc->auth)) + if (is_auth) __send_subscribe(monc); } __schedule_delayed(monc); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 50033677c0fa..80b94e37c94a 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2817,8 +2817,9 @@ out: } /* - * lookup and return message for incoming reply. set up reply message - * pages. + * Lookup and return message for incoming reply. Don't try to do + * anything about a larger than preallocated data portion of the + * message at the moment - for now, just skip the message. */ static struct ceph_msg *get_reply(struct ceph_connection *con, struct ceph_msg_header *hdr, @@ -2836,10 +2837,10 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); if (!req) { - *skip = 1; + pr_warn("%s osd%d tid %llu unknown, skipping\n", + __func__, osd->o_osd, tid); m = NULL; - dout("get_reply unknown tid %llu from osd%d\n", tid, - osd->o_osd); + *skip = 1; goto out; } @@ -2849,10 +2850,9 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, ceph_msg_revoke_incoming(req->r_reply); if (front_len > req->r_reply->front_alloc_len) { - pr_warn("get_reply front %d > preallocated %d (%u#%llu)\n", - front_len, req->r_reply->front_alloc_len, - (unsigned int)con->peer_name.type, - le64_to_cpu(con->peer_name.num)); + pr_warn("%s osd%d tid %llu front %d > preallocated %d\n", + __func__, osd->o_osd, req->r_tid, front_len, + req->r_reply->front_alloc_len); m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS, false); if (!m) @@ -2860,37 +2860,22 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, ceph_msg_put(req->r_reply); req->r_reply = m; } - m = ceph_msg_get(req->r_reply); - - if (data_len > 0) { - struct ceph_osd_data *osd_data; - /* - * XXX This is assuming there is only one op containing - * XXX page data. Probably OK for reads, but this - * XXX ought to be done more generally. - */ - osd_data = osd_req_op_extent_osd_data(req, 0); - if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) { - if (osd_data->pages && - unlikely(osd_data->length < data_len)) { - - pr_warn("tid %lld reply has %d bytes we had only %llu bytes ready\n", - tid, data_len, osd_data->length); - *skip = 1; - ceph_msg_put(m); - m = NULL; - goto out; - } - } + if (data_len > req->r_reply->data_length) { + pr_warn("%s osd%d tid %llu data %d > preallocated %zu, skipping\n", + __func__, osd->o_osd, req->r_tid, data_len, + req->r_reply->data_length); + m = NULL; + *skip = 1; + goto out; } - *skip = 0; + + m = ceph_msg_get(req->r_reply); dout("get_reply tid %lld %p\n", tid, m); out: mutex_unlock(&osdc->request_mutex); return m; - } static struct ceph_msg *alloc_msg(struct ceph_connection *con, diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 4a3125836b64..7d8f581d9f1f 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1300,7 +1300,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, ceph_decode_addr(&addr); pr_info("osd%d up\n", osd); BUG_ON(osd >= map->max_osd); - map->osd_state[osd] |= CEPH_OSD_UP; + map->osd_state[osd] |= CEPH_OSD_UP | CEPH_OSD_EXISTS; map->osd_addr[osd] = addr; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index ae8306e7c56f..bf77e3639ce0 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -44,7 +44,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, } EXPORT_SYMBOL(fib_default_rule_add); -u32 fib_default_rule_pref(struct fib_rules_ops *ops) +static u32 fib_default_rule_pref(struct fib_rules_ops *ops) { struct list_head *pos; struct fib_rule *rule; @@ -60,7 +60,6 @@ u32 fib_default_rule_pref(struct fib_rules_ops *ops) return 0; } -EXPORT_SYMBOL(fib_default_rule_pref); static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, @@ -299,8 +298,8 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) } rule->fr_net = net; - if (tb[FRA_PRIORITY]) - rule->pref = nla_get_u32(tb[FRA_PRIORITY]); + rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) + : fib_default_rule_pref(ops); if (tb[FRA_IIFNAME]) { struct net_device *dev; @@ -350,9 +349,6 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) else rule->suppress_ifgroup = -1; - if (!tb[FRA_PRIORITY] && ops->default_pref) - rule->pref = ops->default_pref(ops); - err = -EINVAL; if (tb[FRA_GOTO]) { if (rule->action != FR_ACT_GOTO) diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 9d66a0f72f90..295bbd6a56f2 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -229,7 +229,6 @@ static const struct fib_rules_ops __net_initconst dn_fib_rules_ops_template = { .configure = dn_fib_rule_configure, .compare = dn_fib_rule_compare, .fill = dn_fib_rule_fill, - .default_pref = fib_default_rule_pref, .flush_cache = dn_fib_rule_flush_cache, .nlgroup = RTNLGRP_DECnet_RULE, .policy = dn_fib_rule_policy, diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 18123d50f576..f2bda9e89c61 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -318,7 +318,6 @@ static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .delete = fib4_rule_delete, .compare = fib4_rule_compare, .fill = fib4_rule_fill, - .default_pref = fib_default_rule_pref, .nlmsg_payload = fib4_rule_nlmsg_payload, .flush_cache = fib4_rule_flush_cache, .nlgroup = RTNLGRP_IPV4_RULE, diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3a2c0162c3ba..866ee89f5254 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -233,7 +233,6 @@ static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = { .match = ipmr_rule_match, .configure = ipmr_rule_configure, .compare = ipmr_rule_compare, - .default_pref = fib_default_rule_pref, .fill = ipmr_rule_fill, .nlgroup = RTNLGRP_IPV4_RULE, .policy = ipmr_rule_policy, diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 28011fb1f4a2..c6ded6b2a79f 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -151,6 +151,21 @@ static void bictcp_init(struct sock *sk) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } +static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) +{ + if (event == CA_EVENT_TX_START) { + s32 delta = tcp_time_stamp - tcp_sk(sk)->lsndtime; + struct bictcp *ca = inet_csk_ca(sk); + + /* We were application limited (idle) for a while. + * Shift epoch_start to keep cwnd growth to cubic curve. + */ + if (ca->epoch_start && delta > 0) + ca->epoch_start += delta; + return; + } +} + /* calculate the cubic root of x using a table lookup followed by one * Newton-Raphson iteration. * Avg err ~= 0.195% @@ -450,6 +465,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .cong_avoid = bictcp_cong_avoid, .set_state = bictcp_state, .undo_cwnd = bictcp_undo_cwnd, + .cwnd_event = bictcp_cwnd_event, .pkts_acked = bictcp_acked, .owner = THIS_MODULE, .name = "cubic", diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1188e4fcf23b..f9a8a12b62ee 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -164,6 +164,9 @@ static void tcp_event_data_sent(struct tcp_sock *tp, struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_time_stamp; + if (tcp_packets_in_flight(tp) == 0) + tcp_ca_event(sk, CA_EVENT_TX_START); + tp->lsndtime = now; /* If it is a reply for ato after last received @@ -940,9 +943,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, &md5); tcp_header_size = tcp_options_size + sizeof(struct tcphdr); - if (tcp_packets_in_flight(tp) == 0) - tcp_ca_event(sk, CA_EVENT_TX_START); - /* if no packet is in qdisc/device queue, then allow XPS to select * another queue. We can be called from tcp_tsq_handler() * which holds one reference to sk_wmem_alloc. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 99c0f2b843f0..030fefdc9aed 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1943,37 +1943,6 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) __ipv6_dev_ac_dec(ifp->idev, &addr); } -static int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) -{ - if (dev->addr_len != ETH_ALEN) - return -1; - memcpy(eui, dev->dev_addr, 3); - memcpy(eui + 5, dev->dev_addr + 3, 3); - - /* - * The zSeries OSA network cards can be shared among various - * OS instances, but the OSA cards have only one MAC address. - * This leads to duplicate address conflicts in conjunction - * with IPv6 if more than one instance uses the same card. - * - * The driver for these cards can deliver a unique 16-bit - * identifier for each instance sharing the same card. It is - * placed instead of 0xFFFE in the interface identifier. The - * "u" bit of the interface identifier is not inverted in this - * case. Hence the resulting interface identifier has local - * scope according to RFC2373. - */ - if (dev->dev_id) { - eui[3] = (dev->dev_id >> 8) & 0xFF; - eui[4] = dev->dev_id & 0xFF; - } else { - eui[3] = 0xFF; - eui[4] = 0xFE; - eui[0] ^= 2; - } - return 0; -} - static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev) { if (dev->addr_len != IEEE802154_ADDR_LEN) diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 2367a16eae58..9f777ec59a59 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -258,11 +258,6 @@ nla_put_failure: return -ENOBUFS; } -static u32 fib6_rule_default_pref(struct fib_rules_ops *ops) -{ - return 0x3FFF; -} - static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(16) /* dst */ @@ -279,7 +274,6 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .configure = fib6_rule_configure, .compare = fib6_rule_compare, .fill = fib6_rule_fill, - .default_pref = fib6_rule_default_pref, .nlmsg_payload = fib6_rule_nlmsg_payload, .nlgroup = RTNLGRP_IPV6_RULE, .policy = fib6_rule_policy, diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 74ceb73c1c9a..0e004cc42a22 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -217,7 +217,6 @@ static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = { .match = ip6mr_rule_match, .configure = ip6mr_rule_configure, .compare = ip6mr_rule_compare, - .default_pref = fib_default_rule_pref, .fill = ip6mr_rule_fill, .nlgroup = RTNLGRP_IPV6_RULE, .policy = ip6mr_rule_policy, @@ -550,7 +549,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) if (it->cache == &mrt->mfc6_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == mrt->mfc6_cache_array) + else if (it->cache == &mrt->mfc6_cache_array[it->ct]) read_unlock(&mrt_lock); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f45cac6f8356..53617d715188 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1748,7 +1748,7 @@ static int ip6_convert_metrics(struct mx6_config *mxc, return -EINVAL; } -int ip6_route_add(struct fib6_config *cfg) +int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret) { int err; struct net *net = cfg->fc_nlinfo.nl_net; @@ -1756,7 +1756,6 @@ int ip6_route_add(struct fib6_config *cfg) struct net_device *dev = NULL; struct inet6_dev *idev = NULL; struct fib6_table *table; - struct mx6_config mxc = { .mx = NULL, }; int addr_type; if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) @@ -1981,6 +1980,32 @@ install_route: cfg->fc_nlinfo.nl_net = dev_net(dev); + *rt_ret = rt; + + return 0; +out: + if (dev) + dev_put(dev); + if (idev) + in6_dev_put(idev); + if (rt) + dst_free(&rt->dst); + + *rt_ret = NULL; + + return err; +} + +int ip6_route_add(struct fib6_config *cfg) +{ + struct mx6_config mxc = { .mx = NULL, }; + struct rt6_info *rt = NULL; + int err; + + err = ip6_route_info_create(cfg, &rt); + if (err) + goto out; + err = ip6_convert_metrics(&mxc, cfg); if (err) goto out; @@ -1988,14 +2013,12 @@ install_route: err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc); kfree(mxc.mx); + return err; out: - if (dev) - dev_put(dev); - if (idev) - in6_dev_put(idev); if (rt) dst_free(&rt->dst); + return err; } @@ -2776,19 +2799,78 @@ errout: return err; } -static int ip6_route_multipath(struct fib6_config *cfg, int add) +struct rt6_nh { + struct rt6_info *rt6_info; + struct fib6_config r_cfg; + struct mx6_config mxc; + struct list_head next; +}; + +static void ip6_print_replace_route_err(struct list_head *rt6_nh_list) +{ + struct rt6_nh *nh; + + list_for_each_entry(nh, rt6_nh_list, next) { + pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6 nexthop %pI6 ifi %d\n", + &nh->r_cfg.fc_dst, &nh->r_cfg.fc_gateway, + nh->r_cfg.fc_ifindex); + } +} + +static int ip6_route_info_append(struct list_head *rt6_nh_list, + struct rt6_info *rt, struct fib6_config *r_cfg) +{ + struct rt6_nh *nh; + struct rt6_info *rtnh; + int err = -EEXIST; + + list_for_each_entry(nh, rt6_nh_list, next) { + /* check if rt6_info already exists */ + rtnh = nh->rt6_info; + + if (rtnh->dst.dev == rt->dst.dev && + rtnh->rt6i_idev == rt->rt6i_idev && + ipv6_addr_equal(&rtnh->rt6i_gateway, + &rt->rt6i_gateway)) + return err; + } + + nh = kzalloc(sizeof(*nh), GFP_KERNEL); + if (!nh) + return -ENOMEM; + nh->rt6_info = rt; + err = ip6_convert_metrics(&nh->mxc, r_cfg); + if (err) { + kfree(nh); + return err; + } + memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); + list_add_tail(&nh->next, rt6_nh_list); + + return 0; +} + +static int ip6_route_multipath_add(struct fib6_config *cfg) { struct fib6_config r_cfg; struct rtnexthop *rtnh; + struct rt6_info *rt; + struct rt6_nh *err_nh; + struct rt6_nh *nh, *nh_safe; int remaining; int attrlen; - int err = 0, last_err = 0; + int err = 1; + int nhn = 0; + int replace = (cfg->fc_nlinfo.nlh && + (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE)); + LIST_HEAD(rt6_nh_list); remaining = cfg->fc_mp_len; -beginning: rtnh = (struct rtnexthop *)cfg->fc_mp; - /* Parse a Multipath Entry */ + /* Parse a Multipath Entry and build a list (rt6_nh_list) of + * rt6_info structs per nexthop + */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) @@ -2808,22 +2890,32 @@ beginning: if (nla) r_cfg.fc_encap_type = nla_get_u16(nla); } - err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg); + + err = ip6_route_info_create(&r_cfg, &rt); + if (err) + goto cleanup; + + err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); if (err) { - last_err = err; - /* If we are trying to remove a route, do not stop the - * loop when ip6_route_del() fails (because next hop is - * already gone), we should try to remove all next hops. - */ - if (add) { - /* If add fails, we should try to delete all - * next hops that have been already added. - */ - add = 0; - remaining = cfg->fc_mp_len - remaining; - goto beginning; - } + dst_free(&rt->dst); + goto cleanup; + } + + rtnh = rtnh_next(rtnh, &remaining); + } + + err_nh = NULL; + list_for_each_entry(nh, &rt6_nh_list, next) { + err = __ip6_ins_rt(nh->rt6_info, &cfg->fc_nlinfo, &nh->mxc); + /* nh->rt6_info is used or freed at this point, reset to NULL*/ + nh->rt6_info = NULL; + if (err) { + if (replace && nhn) + ip6_print_replace_route_err(&rt6_nh_list); + err_nh = nh; + goto add_errout; } + /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, * we have already failed to add the first nexthop: @@ -2833,6 +2925,62 @@ beginning: */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + nhn++; + } + + goto cleanup; + +add_errout: + /* Delete routes that were already added */ + list_for_each_entry(nh, &rt6_nh_list, next) { + if (err_nh == nh) + break; + ip6_route_del(&nh->r_cfg); + } + +cleanup: + list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { + if (nh->rt6_info) + dst_free(&nh->rt6_info->dst); + kfree(nh->mxc.mx); + list_del(&nh->next); + kfree(nh); + } + + return err; +} + +static int ip6_route_multipath_del(struct fib6_config *cfg) +{ + struct fib6_config r_cfg; + struct rtnexthop *rtnh; + int remaining; + int attrlen; + int err = 1, last_err = 0; + + remaining = cfg->fc_mp_len; + rtnh = (struct rtnexthop *)cfg->fc_mp; + + /* Parse a Multipath Entry */ + while (rtnh_ok(rtnh, remaining)) { + memcpy(&r_cfg, cfg, sizeof(*cfg)); + if (rtnh->rtnh_ifindex) + r_cfg.fc_ifindex = rtnh->rtnh_ifindex; + + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + if (nla) { + nla_memcpy(&r_cfg.fc_gateway, nla, 16); + r_cfg.fc_flags |= RTF_GATEWAY; + } + } + err = ip6_route_del(&r_cfg); + if (err) + last_err = err; + rtnh = rtnh_next(rtnh, &remaining); } @@ -2849,7 +2997,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) return err; if (cfg.fc_mp) - return ip6_route_multipath(&cfg, 0); + return ip6_route_multipath_del(&cfg); else return ip6_route_del(&cfg); } @@ -2864,7 +3012,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) return err; if (cfg.fc_mp) - return ip6_route_multipath(&cfg, 1); + return ip6_route_multipath_add(&cfg); else return ip6_route_add(&cfg); } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 685ec13ed7c2..17b1fe961c5d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2468,6 +2468,10 @@ static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, rssi_hyst == bss_conf->cqm_rssi_hyst) return 0; + if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER && + !(sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) + return -EOPNOTSUPP; + bss_conf->cqm_rssi_thold = rssi_thold; bss_conf->cqm_rssi_hyst = rssi_hyst; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 705ef1d040ed..cd7e55e08a23 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4267,6 +4267,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband; struct cfg80211_chan_def chandef; int ret; + u32 i; + bool have_80mhz; sband = local->hw.wiphy->bands[cbss->channel->band]; @@ -4317,6 +4319,20 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } } + /* Allow VHT if at least one channel on the sband supports 80 MHz */ + have_80mhz = false; + for (i = 0; i < sband->n_channels; i++) { + if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED | + IEEE80211_CHAN_NO_80MHZ)) + continue; + + have_80mhz = true; + break; + } + + if (!have_80mhz) + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, cbss->channel, ht_cap, ht_oper, vht_oper, diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 9857693b91ec..9ce8883d5f44 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -716,7 +716,7 @@ static bool rate_control_cap_mask(struct ieee80211_sub_if_data *sdata, /* Filter out rates that the STA does not support */ *mask &= sta->supp_rates[sband->band]; - for (i = 0; i < sizeof(mcs_mask); i++) + for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) mcs_mask[i] &= sta->ht_cap.mcs.rx_mask[i]; sta_vht_cap = sta->vht_cap.vht_mcs.rx_mcs_map; diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index aee701a5649e..4e202d0679b2 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -1249,6 +1249,58 @@ static void iee80211_tdls_recalc_chanctx(struct ieee80211_sub_if_data *sdata) mutex_unlock(&local->chanctx_mtx); } +static int iee80211_tdls_have_ht_peers(struct ieee80211_sub_if_data *sdata) +{ + struct sta_info *sta; + bool result = false; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { + if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || + !test_sta_flag(sta, WLAN_STA_AUTHORIZED) || + !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH) || + !sta->sta.ht_cap.ht_supported) + continue; + result = true; + break; + } + rcu_read_unlock(); + + return result; +} + +static void +iee80211_tdls_recalc_ht_protection(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + bool tdls_ht; + u16 protection = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED | + IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT | + IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT; + u16 opmode; + + /* Nothing to do if the BSS connection uses HT */ + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) + return; + + tdls_ht = (sta && sta->sta.ht_cap.ht_supported) || + iee80211_tdls_have_ht_peers(sdata); + + opmode = sdata->vif.bss_conf.ht_operation_mode; + + if (tdls_ht) + opmode |= protection; + else + opmode &= ~protection; + + if (opmode == sdata->vif.bss_conf.ht_operation_mode) + return; + + sdata->vif.bss_conf.ht_operation_mode = opmode; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_HT); +} + int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, enum nl80211_tdls_operation oper) { @@ -1274,6 +1326,10 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, return -ENOTSUPP; } + /* protect possible bss_conf changes and avoid concurrency in + * ieee80211_bss_info_change_notify() + */ + sdata_lock(sdata); mutex_lock(&local->mtx); tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer); @@ -1287,16 +1343,18 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, iee80211_tdls_recalc_chanctx(sdata); - rcu_read_lock(); + mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, peer); if (!sta) { - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); ret = -ENOLINK; break; } + iee80211_tdls_recalc_ht_protection(sdata, sta); + set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); WARN_ON_ONCE(is_zero_ether_addr(sdata->u.mgd.tdls_peer) || !ether_addr_equal(sdata->u.mgd.tdls_peer, peer)); @@ -1318,6 +1376,11 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, ieee80211_flush_queues(local, sdata, false); ret = sta_info_destroy_addr(sdata, peer); + + mutex_lock(&local->sta_mtx); + iee80211_tdls_recalc_ht_protection(sdata, NULL); + mutex_unlock(&local->sta_mtx); + iee80211_tdls_recalc_chanctx(sdata); break; default: @@ -1335,6 +1398,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, &sdata->u.mgd.request_smps_work); mutex_unlock(&local->mtx); + sdata_unlock(sdata); return ret; } diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 834ccdbc74be..ff1c798921a6 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -120,6 +120,7 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_vht_cap *vht_cap = &sta->sta.vht_cap; struct ieee80211_sta_vht_cap own_cap; u32 cap_info, i; + bool have_80mhz; memset(vht_cap, 0, sizeof(*vht_cap)); @@ -129,6 +130,20 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, if (!vht_cap_ie || !sband->vht_cap.vht_supported) return; + /* Allow VHT if at least one channel on the sband supports 80 MHz */ + have_80mhz = false; + for (i = 0; i < sband->n_channels; i++) { + if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED | + IEEE80211_CHAN_NO_80MHZ)) + continue; + + have_80mhz = true; + break; + } + + if (!have_80mhz) + return; + /* * A VHT STA must support 40 MHz, but if we verify that here * then we break a few things - some APs (e.g. Netgear R6300v2 diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index afe905c208af..691b54fcaf2a 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -152,9 +152,13 @@ htable_bits(u32 hashsize) #define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) #ifdef IP_SET_HASH_WITH_NET0 +/* cidr from 0 to SET_HOST_MASK() value and c = cidr + 1 */ #define NLEN(family) (SET_HOST_MASK(family) + 1) +#define CIDR_POS(c) ((c) - 1) #else +/* cidr from 1 to SET_HOST_MASK() value and c = cidr + 1 */ #define NLEN(family) SET_HOST_MASK(family) +#define CIDR_POS(c) ((c) - 2) #endif #else @@ -305,7 +309,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n) } else if (h->nets[i].cidr[n] < cidr) { j = i; } else if (h->nets[i].cidr[n] == cidr) { - h->nets[cidr - 1].nets[n]++; + h->nets[CIDR_POS(cidr)].nets[n]++; return; } } @@ -314,7 +318,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n) h->nets[i].cidr[n] = h->nets[i - 1].cidr[n]; } h->nets[i].cidr[n] = cidr; - h->nets[cidr - 1].nets[n] = 1; + h->nets[CIDR_POS(cidr)].nets[n] = 1; } static void @@ -325,8 +329,8 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n) for (i = 0; i < nets_length; i++) { if (h->nets[i].cidr[n] != cidr) continue; - h->nets[cidr - 1].nets[n]--; - if (h->nets[cidr - 1].nets[n] > 0) + h->nets[CIDR_POS(cidr)].nets[n]--; + if (h->nets[CIDR_POS(cidr)].nets[n] > 0) return; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 3c862c0a76d1..a93dfebffa81 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -131,6 +131,13 @@ hash_netnet4_data_next(struct hash_netnet4_elem *next, #define HOST_MASK 32 #include "ip_set_hash_gen.h" +static void +hash_netnet4_init(struct hash_netnet4_elem *e) +{ + e->cidr[0] = HOST_MASK; + e->cidr[1] = HOST_MASK; +} + static int hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -160,7 +167,7 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], { const struct hash_netnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netnet4_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; + struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, last; u32 ip2 = 0, ip2_from = 0, ip2_to = 0, last2; @@ -169,6 +176,7 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + hash_netnet4_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; @@ -357,6 +365,13 @@ hash_netnet6_data_next(struct hash_netnet4_elem *next, #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" +static void +hash_netnet6_init(struct hash_netnet6_elem *e) +{ + e->cidr[0] = HOST_MASK; + e->cidr[1] = HOST_MASK; +} + static int hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -385,13 +400,14 @@ hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netnet6_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; + struct hash_netnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + hash_netnet6_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 0c68734f5cc4..9a14c237830f 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -142,6 +142,13 @@ hash_netportnet4_data_next(struct hash_netportnet4_elem *next, #define HOST_MASK 32 #include "ip_set_hash_gen.h" +static void +hash_netportnet4_init(struct hash_netportnet4_elem *e) +{ + e->cidr[0] = HOST_MASK; + e->cidr[1] = HOST_MASK; +} + static int hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -175,7 +182,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], { const struct hash_netportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netportnet4_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; + struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, ip_last, p = 0, port, port_to; u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2; @@ -185,6 +192,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + hash_netportnet4_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || @@ -412,6 +420,13 @@ hash_netportnet6_data_next(struct hash_netportnet4_elem *next, #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" +static void +hash_netportnet6_init(struct hash_netportnet6_elem *e) +{ + e->cidr[0] = HOST_MASK; + e->cidr[1] = HOST_MASK; +} + static int hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -445,7 +460,7 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], { const struct hash_netportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netportnet6_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; + struct hash_netportnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; @@ -454,6 +469,7 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + hash_netportnet6_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index eedf0495f11f..c09d6c7198f6 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -313,12 +313,13 @@ out_free: } EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc); -static void nf_ct_tmpl_free(struct nf_conn *tmpl) +void nf_ct_tmpl_free(struct nf_conn *tmpl) { nf_ct_ext_destroy(tmpl); nf_ct_ext_free(tmpl); kfree(tmpl); } +EXPORT_SYMBOL_GPL(nf_ct_tmpl_free); static void destroy_conntrack(struct nf_conntrack *nfct) diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 888b9558415e..c8a4a48bced9 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -380,7 +380,7 @@ static int __net_init synproxy_net_init(struct net *net) err3: free_percpu(snet->stats); err2: - nf_conntrack_free(ct); + nf_ct_tmpl_free(ct); err1: return err; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 0c0e8ecf02ab..70277b11f742 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -444,6 +444,7 @@ done: static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); + u_int16_t res_id; int msglen; if (nlh->nlmsg_len < NLMSG_HDRLEN || @@ -468,7 +469,12 @@ static void nfnetlink_rcv(struct sk_buff *skb) nfgenmsg = nlmsg_data(nlh); skb_pull(skb, msglen); - nfnetlink_rcv_batch(skb, nlh, nfgenmsg->res_id); + /* Work around old nft using host byte order */ + if (nfgenmsg->res_id == NFNL_SUBSYS_NFTABLES) + res_id = NFNL_SUBSYS_NFTABLES; + else + res_id = ntohs(nfgenmsg->res_id); + nfnetlink_rcv_batch(skb, nlh, res_id); } else { netlink_rcv_skb(skb, &nfnetlink_rcv_msg); } diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 685cc6a17163..a5cd6d90b78b 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -301,7 +301,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, __be32 **packet_id_ptr) { size_t size; - size_t data_len = 0, cap_len = 0; + size_t data_len = 0, cap_len = 0, rem_len = 0; unsigned int hlen = 0; struct sk_buff *skb; struct nlattr *nla; @@ -360,6 +360,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; cap_len = entskb->len; + rem_len = data_len - hlen; break; } @@ -377,7 +378,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, size += nla_total_size(seclen); } - skb = nfnetlink_alloc_skb(net, size, queue->peer_portid, + skb = __netlink_alloc_skb(net->nfnl, size, rem_len, queue->peer_portid, GFP_ATOMIC); if (!skb) { skb_tx_error(entskb); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 8e524898ccea..faf32d888198 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -255,7 +255,7 @@ out: return 0; err3: - nf_conntrack_free(ct); + nf_ct_tmpl_free(ct); err2: nf_ct_l3proto_module_put(par->family); err1: diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 50889be1517d..7f86d3b55060 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -674,12 +674,19 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock, mask = datagram_poll(file, sock, wait); - spin_lock_bh(&sk->sk_receive_queue.lock); - if (nlk->rx_ring.pg_vec) { - if (netlink_has_valid_frame(&nlk->rx_ring)) - mask |= POLLIN | POLLRDNORM; + /* We could already have received frames in the normal receive + * queue, that will show up as NL_MMAP_STATUS_COPY in the ring, + * so if mask contains pollin/etc already, there's no point + * walking the ring. + */ + if ((mask & (POLLIN | POLLRDNORM)) != (POLLIN | POLLRDNORM)) { + spin_lock_bh(&sk->sk_receive_queue.lock); + if (nlk->rx_ring.pg_vec) { + if (netlink_has_valid_frame(&nlk->rx_ring)) + mask |= POLLIN | POLLRDNORM; + } + spin_unlock_bh(&sk->sk_receive_queue.lock); } - spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (nlk->tx_ring.pg_vec) { @@ -1837,15 +1844,16 @@ retry: } EXPORT_SYMBOL(netlink_unicast); -struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, - u32 dst_portid, gfp_t gfp_mask) +struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size, + unsigned int ldiff, u32 dst_portid, + gfp_t gfp_mask) { #ifdef CONFIG_NETLINK_MMAP + unsigned int maxlen, linear_size; struct sock *sk = NULL; struct sk_buff *skb; struct netlink_ring *ring; struct nl_mmap_hdr *hdr; - unsigned int maxlen; sk = netlink_getsockbyportid(ssk, dst_portid); if (IS_ERR(sk)) @@ -1856,7 +1864,11 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, if (ring->pg_vec == NULL) goto out_put; - if (ring->frame_size - NL_MMAP_HDRLEN < size) + /* We need to account the full linear size needed as a ring + * slot cannot have non-linear parts. + */ + linear_size = size + ldiff; + if (ring->frame_size - NL_MMAP_HDRLEN < linear_size) goto out_put; skb = alloc_skb_head(gfp_mask); @@ -1870,13 +1882,14 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, /* check again under lock */ maxlen = ring->frame_size - NL_MMAP_HDRLEN; - if (maxlen < size) + if (maxlen < linear_size) goto out_free; netlink_forward_ring(ring); hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); if (hdr == NULL) goto err2; + netlink_ring_setup_skb(skb, sk, ring, hdr); netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED); atomic_inc(&ring->pending); @@ -1902,7 +1915,7 @@ out: #endif return alloc_skb(size, gfp_mask); } -EXPORT_SYMBOL_GPL(netlink_alloc_skb); +EXPORT_SYMBOL_GPL(__netlink_alloc_skb); int netlink_has_listeners(struct sock *sk, unsigned int group) { diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index af7cdef42066..2a071f470d57 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -5,6 +5,7 @@ config OPENVSWITCH tristate "Open vSwitch" depends on INET + depends on (!NF_CONNTRACK || NF_CONNTRACK) select LIBCRC32C select MPLS select NET_MPLS_GSO @@ -31,17 +32,6 @@ config OPENVSWITCH If unsure, say N. -config OPENVSWITCH_CONNTRACK - bool "Open vSwitch conntrack action support" - depends on OPENVSWITCH - depends on NF_CONNTRACK - default OPENVSWITCH - ---help--- - If you say Y here, then Open vSwitch module will be able to pass - packets through conntrack. - - Say N to exclude this support and reduce the binary size. - config OPENVSWITCH_GRE tristate "Open vSwitch GRE tunneling support" depends on OPENVSWITCH diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile index 5b5913b06f54..60f809085b92 100644 --- a/net/openvswitch/Makefile +++ b/net/openvswitch/Makefile @@ -15,7 +15,9 @@ openvswitch-y := \ vport-internal_dev.o \ vport-netdev.o -openvswitch-$(CONFIG_OPENVSWITCH_CONNTRACK) += conntrack.o +ifneq ($(CONFIG_NF_CONNTRACK),) +openvswitch-y += conntrack.o +endif obj-$(CONFIG_OPENVSWITCH_VXLAN)+= vport-vxlan.o obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 3cb30667a7dc..43f5dd7a5577 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -19,7 +19,7 @@ struct ovs_conntrack_info; enum ovs_key_attr; -#if defined(CONFIG_OPENVSWITCH_CONNTRACK) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) void ovs_ct_init(struct net *); void ovs_ct_exit(struct net *); bool ovs_ct_verify(struct net *, enum ovs_key_attr attr); @@ -82,5 +82,5 @@ static inline int ovs_ct_put_key(const struct sw_flow_key *key, } static inline void ovs_ct_free_action(const struct nlattr *a) { } -#endif +#endif /* CONFIG_NF_CONNTRACK */ #endif /* ovs_conntrack.h */ diff --git a/net/rds/connection.c b/net/rds/connection.c index a50e652eb269..49adeef8090c 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -70,7 +70,8 @@ static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr) } while (0) /* rcu read lock must be held or the connection spinlock */ -static struct rds_connection *rds_conn_lookup(struct hlist_head *head, +static struct rds_connection *rds_conn_lookup(struct net *net, + struct hlist_head *head, __be32 laddr, __be32 faddr, struct rds_transport *trans) { @@ -78,7 +79,7 @@ static struct rds_connection *rds_conn_lookup(struct hlist_head *head, hlist_for_each_entry_rcu(conn, head, c_hash_node) { if (conn->c_faddr == faddr && conn->c_laddr == laddr && - conn->c_trans == trans) { + conn->c_trans == trans && net == rds_conn_net(conn)) { ret = conn; break; } @@ -132,7 +133,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP) goto new_conn; rcu_read_lock(); - conn = rds_conn_lookup(head, laddr, faddr, trans); + conn = rds_conn_lookup(net, head, laddr, faddr, trans); if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && laddr == faddr && !is_outgoing) { /* This is a looped back IB connection, and we're @@ -189,6 +190,12 @@ new_conn: } } + if (trans == NULL) { + kmem_cache_free(rds_conn_slab, conn); + conn = ERR_PTR(-ENODEV); + goto out; + } + conn->c_trans = trans; ret = trans->conn_alloc(conn, gfp); @@ -239,7 +246,7 @@ new_conn: if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP) found = NULL; else - found = rds_conn_lookup(head, laddr, faddr, trans); + found = rds_conn_lookup(net, head, laddr, faddr, trans); if (found) { trans->conn_free(conn->c_transport_data); kmem_cache_free(rds_conn_slab, conn); diff --git a/net/rds/ib.c b/net/rds/ib.c index d020fade312c..2d3f2ab475df 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -99,8 +99,6 @@ static void rds_ib_dev_free(struct work_struct *work) if (rds_ibdev->mr_pool) rds_ib_destroy_mr_pool(rds_ibdev->mr_pool); - if (rds_ibdev->mr) - ib_dereg_mr(rds_ibdev->mr); if (rds_ibdev->pd) ib_dealloc_pd(rds_ibdev->pd); @@ -164,12 +162,6 @@ static void rds_ib_add_one(struct ib_device *device) goto put_dev; } - rds_ibdev->mr = ib_get_dma_mr(rds_ibdev->pd, IB_ACCESS_LOCAL_WRITE); - if (IS_ERR(rds_ibdev->mr)) { - rds_ibdev->mr = NULL; - goto put_dev; - } - rds_ibdev->mr_pool = rds_ib_create_mr_pool(rds_ibdev); if (IS_ERR(rds_ibdev->mr_pool)) { rds_ibdev->mr_pool = NULL; @@ -230,11 +222,10 @@ struct rds_ib_device *rds_ib_get_client_data(struct ib_device *device) * * This can be called at any time and can be racing with any other RDS path. */ -static void rds_ib_remove_one(struct ib_device *device) +static void rds_ib_remove_one(struct ib_device *device, void *client_data) { - struct rds_ib_device *rds_ibdev; + struct rds_ib_device *rds_ibdev = client_data; - rds_ibdev = ib_get_client_data(device, &rds_ib_client); if (!rds_ibdev) return; diff --git a/net/rds/ib.h b/net/rds/ib.h index 9fc95e38659a..aae60fda77f6 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -100,7 +100,6 @@ struct rds_ib_connection { /* alphabet soup, IBTA style */ struct rdma_cm_id *i_cm_id; struct ib_pd *i_pd; - struct ib_mr *i_mr; struct ib_cq *i_send_cq; struct ib_cq *i_recv_cq; @@ -173,7 +172,6 @@ struct rds_ib_device { struct list_head conn_list; struct ib_device *dev; struct ib_pd *pd; - struct ib_mr *mr; struct rds_ib_mr_pool *mr_pool; unsigned int fmr_max_remaps; unsigned int max_fmrs; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index d150bb4aa3cb..9043f5c04787 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -269,7 +269,6 @@ static int rds_ib_setup_qp(struct rds_connection *conn) /* Protection domain and memory range */ ic->i_pd = rds_ibdev->pd; - ic->i_mr = rds_ibdev->mr; cq_attr.cqe = ic->i_send_ring.w_nr + 1; ic->i_send_cq = ib_create_cq(dev, rds_ib_send_cq_comp_handler, @@ -375,7 +374,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) rds_ib_recv_init_ack(ic); - rdsdebug("conn %p pd %p mr %p cq %p %p\n", conn, ic->i_pd, ic->i_mr, + rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd, ic->i_send_cq, ic->i_recv_cq); out: @@ -682,7 +681,6 @@ void rds_ib_conn_shutdown(struct rds_connection *conn) ic->i_cm_id = NULL; ic->i_pd = NULL; - ic->i_mr = NULL; ic->i_send_cq = NULL; ic->i_recv_cq = NULL; ic->i_send_hdrs = NULL; diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 6bbe62060060..f43831e4186a 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -62,12 +62,12 @@ void rds_ib_recv_init_ring(struct rds_ib_connection *ic) sge = &recv->r_sge[0]; sge->addr = ic->i_recv_hdrs_dma + (i * sizeof(struct rds_header)); sge->length = sizeof(struct rds_header); - sge->lkey = ic->i_mr->lkey; + sge->lkey = ic->i_pd->local_dma_lkey; sge = &recv->r_sge[1]; sge->addr = 0; sge->length = RDS_FRAG_SIZE; - sge->lkey = ic->i_mr->lkey; + sge->lkey = ic->i_pd->local_dma_lkey; } } @@ -564,7 +564,7 @@ void rds_ib_recv_init_ack(struct rds_ib_connection *ic) sge->addr = ic->i_ack_dma; sge->length = sizeof(struct rds_header); - sge->lkey = ic->i_mr->lkey; + sge->lkey = ic->i_pd->local_dma_lkey; wr->sg_list = sge; wr->num_sge = 1; diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index c576ebeb4115..4e88047086b6 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -202,9 +202,9 @@ void rds_ib_send_init_ring(struct rds_ib_connection *ic) sge = &send->s_sge[0]; sge->addr = ic->i_send_hdrs_dma + (i * sizeof(struct rds_header)); sge->length = sizeof(struct rds_header); - sge->lkey = ic->i_mr->lkey; + sge->lkey = ic->i_pd->local_dma_lkey; - send->s_sge[1].lkey = ic->i_mr->lkey; + send->s_sge[1].lkey = ic->i_pd->local_dma_lkey; } } @@ -818,7 +818,7 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op) /* Convert our struct scatterlist to struct ib_sge */ send->s_sge[0].addr = ib_sg_dma_address(ic->i_cm_id->device, op->op_sg); send->s_sge[0].length = ib_sg_dma_len(ic->i_cm_id->device, op->op_sg); - send->s_sge[0].lkey = ic->i_mr->lkey; + send->s_sge[0].lkey = ic->i_pd->local_dma_lkey; rdsdebug("rva %Lx rpa %Lx len %u\n", op->op_remote_addr, send->s_sge[0].addr, send->s_sge[0].length); @@ -932,7 +932,7 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) send->s_sge[j].addr = ib_sg_dma_address(ic->i_cm_id->device, scat); send->s_sge[j].length = len; - send->s_sge[j].lkey = ic->i_mr->lkey; + send->s_sge[j].lkey = ic->i_pd->local_dma_lkey; sent += len; rdsdebug("ic %p sent %d remote_addr %llu\n", ic, sent, remote_addr); diff --git a/net/rds/iw.c b/net/rds/iw.c index 5d5a9d258658..3df0295c6659 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -125,12 +125,11 @@ free_attr: kfree(dev_attr); } -static void rds_iw_remove_one(struct ib_device *device) +static void rds_iw_remove_one(struct ib_device *device, void *client_data) { - struct rds_iw_device *rds_iwdev; + struct rds_iw_device *rds_iwdev = client_data; struct rds_iw_cm_id *i_cm_id, *next; - rds_iwdev = ib_get_client_data(device, &rds_iw_client); if (!rds_iwdev) return; @@ -149,10 +148,7 @@ static void rds_iw_remove_one(struct ib_device *device) if (rds_iwdev->mr) ib_dereg_mr(rds_iwdev->mr); - while (ib_dealloc_pd(rds_iwdev->pd)) { - rdsdebug("Failed to dealloc pd %p\n", rds_iwdev->pd); - msleep(1); - } + ib_dealloc_pd(rds_iwdev->pd); list_del(&rds_iwdev->list); kfree(rds_iwdev); diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index dba8d0864f18..6a8fbd6e69e7 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -667,11 +667,12 @@ static int rds_iw_init_fastreg(struct rds_iw_mr_pool *pool, struct ib_mr *mr; int err; - mr = ib_alloc_fast_reg_mr(rds_iwdev->pd, pool->max_message_size); + mr = ib_alloc_mr(rds_iwdev->pd, IB_MR_TYPE_MEM_REG, + pool->max_message_size); if (IS_ERR(mr)) { err = PTR_ERR(mr); - printk(KERN_WARNING "RDS/IW: ib_alloc_fast_reg_mr failed (err=%d)\n", err); + printk(KERN_WARNING "RDS/IW: ib_alloc_mr failed (err=%d)\n", err); return err; } diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 334fe98c5084..86152ec3b887 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -153,9 +153,10 @@ void rds_iw_send_init_ring(struct rds_iw_connection *ic) sge->length = sizeof(struct rds_header); sge->lkey = 0; - send->s_mr = ib_alloc_fast_reg_mr(ic->i_pd, fastreg_message_size); + send->s_mr = ib_alloc_mr(ic->i_pd, IB_MR_TYPE_MEM_REG, + fastreg_message_size); if (IS_ERR(send->s_mr)) { - printk(KERN_WARNING "RDS/IW: ib_alloc_fast_reg_mr failed\n"); + printk(KERN_WARNING "RDS/IW: ib_alloc_mr failed\n"); break; } diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f12149a29cb1..b41e9ea2ffff 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -341,7 +341,15 @@ static void __rfkill_switch_all(const enum rfkill_type type, bool blocked) { struct rfkill *rfkill; - rfkill_global_states[type].cur = blocked; + if (type == RFKILL_TYPE_ALL) { + int i; + + for (i = 0; i < NUM_RFKILL_TYPES; i++) + rfkill_global_states[i].cur = blocked; + } else { + rfkill_global_states[type].cur = blocked; + } + list_for_each_entry(rfkill, &rfkill_list, node) { if (rfkill->type != type && type != RFKILL_TYPE_ALL) continue; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 4345790ad326..b7143337e4fa 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -506,14 +506,22 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, if (IS_ERR(rt)) continue; + if (!dst) + dst = &rt->dst; + /* Ensure the src address belongs to the output * interface. */ odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr, false); - if (!odev || odev->ifindex != fl4->flowi4_oif) + if (!odev || odev->ifindex != fl4->flowi4_oif) { + if (&rt->dst != dst) + dst_release(&rt->dst); continue; + } + if (dst != &rt->dst) + dst_release(dst); dst = &rt->dst; break; } diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 4feda2d0a833..548240dd15fc 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -23,7 +23,7 @@ struct unx_cred { }; #define uc_uid uc_base.cr_uid -#define UNX_WRITESLACK (21 + (UNX_MAXNODENAME >> 2)) +#define UNX_WRITESLACK (21 + XDR_QUADLEN(UNX_MAXNODENAME)) #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2928afffbb81..4a2340a54401 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -44,7 +44,7 @@ static void cache_revisit_request(struct cache_head *item); static void cache_init(struct cache_head *h) { time_t now = seconds_since_boot(); - h->next = NULL; + INIT_HLIST_NODE(&h->cache_list); h->flags = 0; kref_init(&h->ref); h->expiry_time = now + CACHE_NEW_EXPIRY; @@ -54,15 +54,14 @@ static void cache_init(struct cache_head *h) struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, struct cache_head *key, int hash) { - struct cache_head **head, **hp; - struct cache_head *new = NULL, *freeme = NULL; + struct cache_head *new = NULL, *freeme = NULL, *tmp = NULL; + struct hlist_head *head; head = &detail->hash_table[hash]; read_lock(&detail->hash_lock); - for (hp=head; *hp != NULL ; hp = &(*hp)->next) { - struct cache_head *tmp = *hp; + hlist_for_each_entry(tmp, head, cache_list) { if (detail->match(tmp, key)) { if (cache_is_expired(detail, tmp)) /* This entry is expired, we will discard it. */ @@ -88,12 +87,10 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, write_lock(&detail->hash_lock); /* check if entry appeared while we slept */ - for (hp=head; *hp != NULL ; hp = &(*hp)->next) { - struct cache_head *tmp = *hp; + hlist_for_each_entry(tmp, head, cache_list) { if (detail->match(tmp, key)) { if (cache_is_expired(detail, tmp)) { - *hp = tmp->next; - tmp->next = NULL; + hlist_del_init(&tmp->cache_list); detail->entries --; freeme = tmp; break; @@ -104,8 +101,8 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, return tmp; } } - new->next = *head; - *head = new; + + hlist_add_head(&new->cache_list, head); detail->entries++; cache_get(new); write_unlock(&detail->hash_lock); @@ -143,7 +140,6 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, * If 'old' is not VALID, we update it directly, * otherwise we need to replace it */ - struct cache_head **head; struct cache_head *tmp; if (!test_bit(CACHE_VALID, &old->flags)) { @@ -168,15 +164,13 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, } cache_init(tmp); detail->init(tmp, old); - head = &detail->hash_table[hash]; write_lock(&detail->hash_lock); if (test_bit(CACHE_NEGATIVE, &new->flags)) set_bit(CACHE_NEGATIVE, &tmp->flags); else detail->update(tmp, new); - tmp->next = *head; - *head = tmp; + hlist_add_head(&tmp->cache_list, &detail->hash_table[hash]); detail->entries++; cache_get(tmp); cache_fresh_locked(tmp, new->expiry_time); @@ -416,28 +410,29 @@ static int cache_clean(void) /* find a non-empty bucket in the table */ while (current_detail && current_index < current_detail->hash_size && - current_detail->hash_table[current_index] == NULL) + hlist_empty(¤t_detail->hash_table[current_index])) current_index++; /* find a cleanable entry in the bucket and clean it, or set to next bucket */ if (current_detail && current_index < current_detail->hash_size) { - struct cache_head *ch, **cp; + struct cache_head *ch = NULL; struct cache_detail *d; + struct hlist_head *head; + struct hlist_node *tmp; write_lock(¤t_detail->hash_lock); /* Ok, now to clean this strand */ - cp = & current_detail->hash_table[current_index]; - for (ch = *cp ; ch ; cp = & ch->next, ch = *cp) { + head = ¤t_detail->hash_table[current_index]; + hlist_for_each_entry_safe(ch, tmp, head, cache_list) { if (current_detail->nextcheck > ch->expiry_time) current_detail->nextcheck = ch->expiry_time+1; if (!cache_is_expired(current_detail, ch)) continue; - *cp = ch->next; - ch->next = NULL; + hlist_del_init(&ch->cache_list); current_detail->entries--; rv = 1; break; @@ -1270,18 +1265,13 @@ EXPORT_SYMBOL_GPL(qword_get); * get a header, then pass each real item in the cache */ -struct handle { - struct cache_detail *cd; -}; - -static void *c_start(struct seq_file *m, loff_t *pos) +void *cache_seq_start(struct seq_file *m, loff_t *pos) __acquires(cd->hash_lock) { loff_t n = *pos; unsigned int hash, entry; struct cache_head *ch; - struct cache_detail *cd = ((struct handle*)m->private)->cd; - + struct cache_detail *cd = m->private; read_lock(&cd->hash_lock); if (!n--) @@ -1289,7 +1279,7 @@ static void *c_start(struct seq_file *m, loff_t *pos) hash = n >> 32; entry = n & ((1LL<<32) - 1); - for (ch=cd->hash_table[hash]; ch; ch=ch->next) + hlist_for_each_entry(ch, &cd->hash_table[hash], cache_list) if (!entry--) return ch; n &= ~((1LL<<32) - 1); @@ -1297,51 +1287,57 @@ static void *c_start(struct seq_file *m, loff_t *pos) hash++; n += 1LL<<32; } while(hash < cd->hash_size && - cd->hash_table[hash]==NULL); + hlist_empty(&cd->hash_table[hash])); if (hash >= cd->hash_size) return NULL; *pos = n+1; - return cd->hash_table[hash]; + return hlist_entry_safe(cd->hash_table[hash].first, + struct cache_head, cache_list); } +EXPORT_SYMBOL_GPL(cache_seq_start); -static void *c_next(struct seq_file *m, void *p, loff_t *pos) +void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) { struct cache_head *ch = p; int hash = (*pos >> 32); - struct cache_detail *cd = ((struct handle*)m->private)->cd; + struct cache_detail *cd = m->private; if (p == SEQ_START_TOKEN) hash = 0; - else if (ch->next == NULL) { + else if (ch->cache_list.next == NULL) { hash++; *pos += 1LL<<32; } else { ++*pos; - return ch->next; + return hlist_entry_safe(ch->cache_list.next, + struct cache_head, cache_list); } *pos &= ~((1LL<<32) - 1); while (hash < cd->hash_size && - cd->hash_table[hash] == NULL) { + hlist_empty(&cd->hash_table[hash])) { hash++; *pos += 1LL<<32; } if (hash >= cd->hash_size) return NULL; ++*pos; - return cd->hash_table[hash]; + return hlist_entry_safe(cd->hash_table[hash].first, + struct cache_head, cache_list); } +EXPORT_SYMBOL_GPL(cache_seq_next); -static void c_stop(struct seq_file *m, void *p) +void cache_seq_stop(struct seq_file *m, void *p) __releases(cd->hash_lock) { - struct cache_detail *cd = ((struct handle*)m->private)->cd; + struct cache_detail *cd = m->private; read_unlock(&cd->hash_lock); } +EXPORT_SYMBOL_GPL(cache_seq_stop); static int c_show(struct seq_file *m, void *p) { struct cache_head *cp = p; - struct cache_detail *cd = ((struct handle*)m->private)->cd; + struct cache_detail *cd = m->private; if (p == SEQ_START_TOKEN) return cd->cache_show(m, cd, NULL); @@ -1364,33 +1360,36 @@ static int c_show(struct seq_file *m, void *p) } static const struct seq_operations cache_content_op = { - .start = c_start, - .next = c_next, - .stop = c_stop, + .start = cache_seq_start, + .next = cache_seq_next, + .stop = cache_seq_stop, .show = c_show, }; static int content_open(struct inode *inode, struct file *file, struct cache_detail *cd) { - struct handle *han; + struct seq_file *seq; + int err; if (!cd || !try_module_get(cd->owner)) return -EACCES; - han = __seq_open_private(file, &cache_content_op, sizeof(*han)); - if (han == NULL) { + + err = seq_open(file, &cache_content_op); + if (err) { module_put(cd->owner); - return -ENOMEM; + return err; } - han->cd = cd; + seq = file->private_data; + seq->private = cd; return 0; } static int content_release(struct inode *inode, struct file *file, struct cache_detail *cd) { - int ret = seq_release_private(inode, file); + int ret = seq_release(inode, file); module_put(cd->owner); return ret; } @@ -1665,17 +1664,21 @@ EXPORT_SYMBOL_GPL(cache_unregister_net); struct cache_detail *cache_create_net(struct cache_detail *tmpl, struct net *net) { struct cache_detail *cd; + int i; cd = kmemdup(tmpl, sizeof(struct cache_detail), GFP_KERNEL); if (cd == NULL) return ERR_PTR(-ENOMEM); - cd->hash_table = kzalloc(cd->hash_size * sizeof(struct cache_head *), + cd->hash_table = kzalloc(cd->hash_size * sizeof(struct hlist_head), GFP_KERNEL); if (cd->hash_table == NULL) { kfree(cd); return ERR_PTR(-ENOMEM); } + + for (i = 0; i < cd->hash_size; i++) + INIT_HLIST_HEAD(&cd->hash_table[i]); cd->net = net; return cd; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 337ca851a350..b140c092d226 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -297,7 +297,7 @@ static int rpc_complete_task(struct rpc_task *task) clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate); ret = atomic_dec_and_test(&task->tk_count); if (waitqueue_active(wq)) - __wake_up_locked_key(wq, TASK_NORMAL, &k); + __wake_up_locked_key(wq, TASK_NORMAL, 1, &k); spin_unlock_irqrestore(&wq->lock, flags); return ret; } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 5a16d8d8c831..a8f579df14d8 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -34,36 +34,19 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net); -#define svc_serv_is_pooled(serv) ((serv)->sv_function) +#define svc_serv_is_pooled(serv) ((serv)->sv_ops->svo_function) -/* - * Mode for mapping cpus to pools. - */ -enum { - SVC_POOL_AUTO = -1, /* choose one of the others */ - SVC_POOL_GLOBAL, /* no mapping, just a single global pool - * (legacy & UP mode) */ - SVC_POOL_PERCPU, /* one pool per cpu */ - SVC_POOL_PERNODE /* one pool per numa node */ -}; #define SVC_POOL_DEFAULT SVC_POOL_GLOBAL /* * Structure for mapping cpus to pools and vice versa. * Setup once during sunrpc initialisation. */ -static struct svc_pool_map { - int count; /* How many svc_servs use us */ - int mode; /* Note: int not enum to avoid - * warnings about "enumeration value - * not handled in switch" */ - unsigned int npools; - unsigned int *pool_to; /* maps pool id to cpu or node */ - unsigned int *to_pool; /* maps cpu or node to pool id */ -} svc_pool_map = { - .count = 0, +struct svc_pool_map svc_pool_map = { .mode = SVC_POOL_DEFAULT }; +EXPORT_SYMBOL_GPL(svc_pool_map); + static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */ static int @@ -236,7 +219,7 @@ svc_pool_map_init_pernode(struct svc_pool_map *m) * vice versa). Initialise the map if we're the first user. * Returns the number of pools. */ -static unsigned int +unsigned int svc_pool_map_get(void) { struct svc_pool_map *m = &svc_pool_map; @@ -271,7 +254,7 @@ svc_pool_map_get(void) mutex_unlock(&svc_pool_map_mutex); return m->npools; } - +EXPORT_SYMBOL_GPL(svc_pool_map_get); /* * Drop a reference to the global map of cpus to pools. @@ -280,7 +263,7 @@ svc_pool_map_get(void) * mode using the pool_mode module option without * rebooting or re-loading sunrpc.ko. */ -static void +void svc_pool_map_put(void) { struct svc_pool_map *m = &svc_pool_map; @@ -297,7 +280,7 @@ svc_pool_map_put(void) mutex_unlock(&svc_pool_map_mutex); } - +EXPORT_SYMBOL_GPL(svc_pool_map_put); static int svc_pool_map_get_node(unsigned int pidx) { @@ -423,7 +406,7 @@ EXPORT_SYMBOL_GPL(svc_bind); */ static struct svc_serv * __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, - void (*shutdown)(struct svc_serv *serv, struct net *net)) + struct svc_serv_ops *ops) { struct svc_serv *serv; unsigned int vers; @@ -440,7 +423,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, bufsize = RPCSVC_MAXPAYLOAD; serv->sv_max_payload = bufsize? bufsize : 4096; serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE); - serv->sv_shutdown = shutdown; + serv->sv_ops = ops; xdrsize = 0; while (prog) { prog->pg_lovers = prog->pg_nvers-1; @@ -486,26 +469,22 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, struct svc_serv * svc_create(struct svc_program *prog, unsigned int bufsize, - void (*shutdown)(struct svc_serv *serv, struct net *net)) + struct svc_serv_ops *ops) { - return __svc_create(prog, bufsize, /*npools*/1, shutdown); + return __svc_create(prog, bufsize, /*npools*/1, ops); } EXPORT_SYMBOL_GPL(svc_create); struct svc_serv * svc_create_pooled(struct svc_program *prog, unsigned int bufsize, - void (*shutdown)(struct svc_serv *serv, struct net *net), - svc_thread_fn func, struct module *mod) + struct svc_serv_ops *ops) { struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); - serv = __svc_create(prog, bufsize, npools, shutdown); + serv = __svc_create(prog, bufsize, npools, ops); if (!serv) goto out_err; - - serv->sv_function = func; - serv->sv_module = mod; return serv; out_err: svc_pool_map_put(); @@ -517,8 +496,8 @@ void svc_shutdown_net(struct svc_serv *serv, struct net *net) { svc_close_net(serv, net); - if (serv->sv_shutdown) - serv->sv_shutdown(serv, net); + if (serv->sv_ops->svo_shutdown) + serv->sv_ops->svo_shutdown(serv, net); } EXPORT_SYMBOL_GPL(svc_shutdown_net); @@ -604,40 +583,52 @@ svc_release_buffer(struct svc_rqst *rqstp) } struct svc_rqst * -svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) +svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; rqstp = kzalloc_node(sizeof(*rqstp), GFP_KERNEL, node); if (!rqstp) - goto out_enomem; + return rqstp; - serv->sv_nrthreads++; __set_bit(RQ_BUSY, &rqstp->rq_flags); spin_lock_init(&rqstp->rq_lock); rqstp->rq_server = serv; rqstp->rq_pool = pool; - spin_lock_bh(&pool->sp_lock); - pool->sp_nrthreads++; - list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads); - spin_unlock_bh(&pool->sp_lock); rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_argp) - goto out_thread; + goto out_enomem; rqstp->rq_resp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_resp) - goto out_thread; + goto out_enomem; if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node)) - goto out_thread; + goto out_enomem; return rqstp; -out_thread: - svc_exit_thread(rqstp); out_enomem: - return ERR_PTR(-ENOMEM); + svc_rqst_free(rqstp); + return NULL; +} +EXPORT_SYMBOL_GPL(svc_rqst_alloc); + +struct svc_rqst * +svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) +{ + struct svc_rqst *rqstp; + + rqstp = svc_rqst_alloc(serv, pool, node); + if (!rqstp) + return ERR_PTR(-ENOMEM); + + serv->sv_nrthreads++; + spin_lock_bh(&pool->sp_lock); + pool->sp_nrthreads++; + list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads); + spin_unlock_bh(&pool->sp_lock); + return rqstp; } EXPORT_SYMBOL_GPL(svc_prepare_thread); @@ -739,12 +730,12 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) break; } - __module_get(serv->sv_module); - task = kthread_create_on_node(serv->sv_function, rqstp, + __module_get(serv->sv_ops->svo_module); + task = kthread_create_on_node(serv->sv_ops->svo_function, rqstp, node, "%s", serv->sv_name); if (IS_ERR(task)) { error = PTR_ERR(task); - module_put(serv->sv_module); + module_put(serv->sv_ops->svo_module); svc_exit_thread(rqstp); break; } @@ -772,15 +763,21 @@ EXPORT_SYMBOL_GPL(svc_set_num_threads); * mutex" for the service. */ void -svc_exit_thread(struct svc_rqst *rqstp) +svc_rqst_free(struct svc_rqst *rqstp) { - struct svc_serv *serv = rqstp->rq_server; - struct svc_pool *pool = rqstp->rq_pool; - svc_release_buffer(rqstp); kfree(rqstp->rq_resp); kfree(rqstp->rq_argp); kfree(rqstp->rq_auth_data); + kfree_rcu(rqstp, rq_rcu_head); +} +EXPORT_SYMBOL_GPL(svc_rqst_free); + +void +svc_exit_thread(struct svc_rqst *rqstp) +{ + struct svc_serv *serv = rqstp->rq_server; + struct svc_pool *pool = rqstp->rq_pool; spin_lock_bh(&pool->sp_lock); pool->sp_nrthreads--; @@ -788,7 +785,7 @@ svc_exit_thread(struct svc_rqst *rqstp) list_del_rcu(&rqstp->rq_all); spin_unlock_bh(&pool->sp_lock); - kfree_rcu(rqstp, rq_rcu_head); + svc_rqst_free(rqstp); /* Release the server */ if (serv) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 163ac45c3639..a6cbb2104667 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -24,7 +24,6 @@ static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); static void svc_age_temp_xprts(unsigned long closure); static void svc_delete_xprt(struct svc_xprt *xprt); -static void svc_xprt_do_enqueue(struct svc_xprt *xprt); /* apparently the "standard" is that clients close * idle connections after 5 minutes, servers after @@ -225,12 +224,12 @@ static void svc_xprt_received(struct svc_xprt *xprt) } /* As soon as we clear busy, the xprt could be closed and - * 'put', so we need a reference to call svc_xprt_do_enqueue with: + * 'put', so we need a reference to call svc_enqueue_xprt with: */ svc_xprt_get(xprt); smp_mb__before_atomic(); clear_bit(XPT_BUSY, &xprt->xpt_flags); - svc_xprt_do_enqueue(xprt); + xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt); svc_xprt_put(xprt); } @@ -320,7 +319,7 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt) return false; } -static void svc_xprt_do_enqueue(struct svc_xprt *xprt) +void svc_xprt_do_enqueue(struct svc_xprt *xprt) { struct svc_pool *pool; struct svc_rqst *rqstp = NULL; @@ -402,6 +401,7 @@ redo_search: out: trace_svc_xprt_do_enqueue(xprt, rqstp); } +EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); /* * Queue up a transport with data pending. If there are idle nfsd @@ -412,7 +412,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) { if (test_bit(XPT_BUSY, &xprt->xpt_flags)) return; - svc_xprt_do_enqueue(xprt); + xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt); } EXPORT_SYMBOL_GPL(svc_xprt_enqueue); diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index f1e8dafbd507..cb25c89da623 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -39,6 +39,25 @@ static int fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_create_data_internal *cdata) { + struct ib_device_attr *devattr = &ia->ri_devattr; + struct ib_mr *mr; + + /* Obtain an lkey to use for the regbufs, which are + * protected from remote access. + */ + if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) { + ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; + } else { + mr = ib_get_dma_mr(ia->ri_pd, IB_ACCESS_LOCAL_WRITE); + if (IS_ERR(mr)) { + pr_err("%s: ib_get_dma_mr for failed with %lX\n", + __func__, PTR_ERR(mr)); + return -ENOMEM; + } + ia->ri_dma_lkey = ia->ri_dma_mr->lkey; + ia->ri_dma_mr = mr; + } + return 0; } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 04ea914201b2..d6653f5d0830 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -117,7 +117,7 @@ __frwr_recovery_worker(struct work_struct *work) if (ib_dereg_mr(r->r.frmr.fr_mr)) goto out_fail; - r->r.frmr.fr_mr = ib_alloc_fast_reg_mr(pd, depth); + r->r.frmr.fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); if (IS_ERR(r->r.frmr.fr_mr)) goto out_fail; @@ -148,7 +148,7 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, struct rpcrdma_frmr *f = &r->r.frmr; int rc; - f->fr_mr = ib_alloc_fast_reg_mr(pd, depth); + f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); if (IS_ERR(f->fr_mr)) goto out_mr_err; f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth); @@ -158,7 +158,7 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, out_mr_err: rc = PTR_ERR(f->fr_mr); - dprintk("RPC: %s: ib_alloc_fast_reg_mr status %i\n", + dprintk("RPC: %s: ib_alloc_mr status %i\n", __func__, rc); return rc; @@ -189,6 +189,11 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct ib_device_attr *devattr = &ia->ri_devattr; int depth, delta; + /* Obtain an lkey to use for the regbufs, which are + * protected from remote access. + */ + ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; + ia->ri_max_frmr_depth = min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, devattr->max_fast_reg_page_list_len); diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c index 41985d07fdb7..72cf8b15bbb4 100644 --- a/net/sunrpc/xprtrdma/physical_ops.c +++ b/net/sunrpc/xprtrdma/physical_ops.c @@ -23,6 +23,29 @@ static int physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_create_data_internal *cdata) { + struct ib_device_attr *devattr = &ia->ri_devattr; + struct ib_mr *mr; + + /* Obtain an rkey to use for RPC data payloads. + */ + mr = ib_get_dma_mr(ia->ri_pd, + IB_ACCESS_LOCAL_WRITE | + IB_ACCESS_REMOTE_WRITE | + IB_ACCESS_REMOTE_READ); + if (IS_ERR(mr)) { + pr_err("%s: ib_get_dma_mr for failed with %lX\n", + __func__, PTR_ERR(mr)); + return -ENOMEM; + } + ia->ri_dma_mr = mr; + + /* Obtain an lkey to use for regbufs. + */ + if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) + ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; + else + ia->ri_dma_lkey = ia->ri_dma_mr->lkey; + return 0; } @@ -51,7 +74,7 @@ physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, struct rpcrdma_ia *ia = &r_xprt->rx_ia; rpcrdma_map_one(ia->ri_device, seg, rpcrdma_data_dir(writing)); - seg->mr_rkey = ia->ri_bind_mem->rkey; + seg->mr_rkey = ia->ri_dma_mr->rkey; seg->mr_base = seg->mr_dma; seg->mr_nsegs = 1; return 1; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 84ea37daef36..bc8bd6577467 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -71,6 +71,67 @@ static const char transfertypes[][12] = { }; #endif +/* The client can send a request inline as long as the RPCRDMA header + * plus the RPC call fit under the transport's inline limit. If the + * combined call message size exceeds that limit, the client must use + * the read chunk list for this operation. + */ +static bool rpcrdma_args_inline(struct rpc_rqst *rqst) +{ + unsigned int callsize = RPCRDMA_HDRLEN_MIN + rqst->rq_snd_buf.len; + + return callsize <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst); +} + +/* The client can't know how large the actual reply will be. Thus it + * plans for the largest possible reply for that particular ULP + * operation. If the maximum combined reply message size exceeds that + * limit, the client must provide a write list or a reply chunk for + * this request. + */ +static bool rpcrdma_results_inline(struct rpc_rqst *rqst) +{ + unsigned int repsize = RPCRDMA_HDRLEN_MIN + rqst->rq_rcv_buf.buflen; + + return repsize <= RPCRDMA_INLINE_READ_THRESHOLD(rqst); +} + +static int +rpcrdma_tail_pullup(struct xdr_buf *buf) +{ + size_t tlen = buf->tail[0].iov_len; + size_t skip = tlen & 3; + + /* Do not include the tail if it is only an XDR pad */ + if (tlen < 4) + return 0; + + /* xdr_write_pages() adds a pad at the beginning of the tail + * if the content in "buf->pages" is unaligned. Force the + * tail's actual content to land at the next XDR position + * after the head instead. + */ + if (skip) { + unsigned char *src, *dst; + unsigned int count; + + src = buf->tail[0].iov_base; + dst = buf->head[0].iov_base; + dst += buf->head[0].iov_len; + + src += skip; + tlen -= skip; + + dprintk("RPC: %s: skip=%zu, memmove(%p, %p, %zu)\n", + __func__, skip, dst, src, tlen); + + for (count = tlen; count; count--) + *dst++ = *src++; + } + + return tlen; +} + /* * Chunk assembly from upper layer xdr_buf. * @@ -122,6 +183,10 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, if (len && n == nsegs) return -EIO; + /* When encoding the read list, the tail is always sent inline */ + if (type == rpcrdma_readch) + return n; + if (xdrbuf->tail[0].iov_len) { /* the rpcrdma protocol allows us to omit any trailing * xdr pad bytes, saving the server an RDMA operation. */ @@ -297,8 +362,7 @@ out: * pre-registered memory buffer for this request. For small amounts * of data, this is efficient. The cutoff value is tunable. */ -static int -rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) +static void rpcrdma_inline_pullup(struct rpc_rqst *rqst) { int i, npages, curlen; int copy_len; @@ -310,16 +374,9 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) destp = rqst->rq_svec[0].iov_base; curlen = rqst->rq_svec[0].iov_len; destp += curlen; - /* - * Do optional padding where it makes sense. Alignment of write - * payload can help the server, if our setting is accurate. - */ - pad -= (curlen + 36/*sizeof(struct rpcrdma_msg_padded)*/); - if (pad < 0 || rqst->rq_slen - curlen < RPCRDMA_INLINE_PAD_THRESH) - pad = 0; /* don't pad this request */ - dprintk("RPC: %s: pad %d destp 0x%p len %d hdrlen %d\n", - __func__, pad, destp, rqst->rq_slen, curlen); + dprintk("RPC: %s: destp 0x%p len %d hdrlen %d\n", + __func__, destp, rqst->rq_slen, curlen); copy_len = rqst->rq_snd_buf.page_len; @@ -355,7 +412,6 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) page_base = 0; } /* header now contains entire send message */ - return pad; } /* @@ -380,7 +436,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); struct rpcrdma_req *req = rpcr_to_rdmar(rqst); char *base; - size_t rpclen, padlen; + size_t rpclen; ssize_t hdrlen; enum rpcrdma_chunktype rtype, wtype; struct rpcrdma_msg *headerp; @@ -402,28 +458,15 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) /* * Chunks needed for results? * + * o Read ops return data as write chunk(s), header as inline. * o If the expected result is under the inline threshold, all ops - * return as inline (but see later). + * return as inline. * o Large non-read ops return as a single reply chunk. - * o Large read ops return data as write chunk(s), header as inline. - * - * Note: the NFS code sending down multiple result segments implies - * the op is one of read, readdir[plus], readlink or NFSv4 getacl. - */ - - /* - * This code can handle read chunks, write chunks OR reply - * chunks -- only one type. If the request is too big to fit - * inline, then we will choose read chunks. If the request is - * a READ, then use write chunks to separate the file data - * into pages; otherwise use reply chunks. */ - if (rqst->rq_rcv_buf.buflen <= RPCRDMA_INLINE_READ_THRESHOLD(rqst)) - wtype = rpcrdma_noch; - else if (rqst->rq_rcv_buf.page_len == 0) - wtype = rpcrdma_replych; - else if (rqst->rq_rcv_buf.flags & XDRBUF_READ) + if (rqst->rq_rcv_buf.flags & XDRBUF_READ) wtype = rpcrdma_writech; + else if (rpcrdma_results_inline(rqst)) + wtype = rpcrdma_noch; else wtype = rpcrdma_replych; @@ -432,21 +475,25 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * * o If the total request is under the inline threshold, all ops * are sent as inline. - * o Large non-write ops are sent with the entire message as a - * single read chunk (protocol 0-position special case). * o Large write ops transmit data as read chunk(s), header as * inline. + * o Large non-write ops are sent with the entire message as a + * single read chunk (protocol 0-position special case). * - * Note: the NFS code sending down multiple argument segments - * implies the op is a write. - * TBD check NFSv4 setacl + * This assumes that the upper layer does not present a request + * that both has a data payload, and whose non-data arguments + * by themselves are larger than the inline threshold. */ - if (rqst->rq_snd_buf.len <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst)) + if (rpcrdma_args_inline(rqst)) { rtype = rpcrdma_noch; - else if (rqst->rq_snd_buf.page_len == 0) - rtype = rpcrdma_areadch; - else + } else if (rqst->rq_snd_buf.flags & XDRBUF_WRITE) { rtype = rpcrdma_readch; + } else { + r_xprt->rx_stats.nomsg_call_count++; + headerp->rm_type = htonl(RDMA_NOMSG); + rtype = rpcrdma_areadch; + rpclen = 0; + } /* The following simplification is not true forever */ if (rtype != rpcrdma_noch && wtype == rpcrdma_replych) @@ -458,7 +505,6 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) } hdrlen = RPCRDMA_HDRLEN_MIN; - padlen = 0; /* * Pull up any extra send data into the preregistered buffer. @@ -467,45 +513,15 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) */ if (rtype == rpcrdma_noch) { - padlen = rpcrdma_inline_pullup(rqst, - RPCRDMA_INLINE_PAD_VALUE(rqst)); - - if (padlen) { - headerp->rm_type = rdma_msgp; - headerp->rm_body.rm_padded.rm_align = - cpu_to_be32(RPCRDMA_INLINE_PAD_VALUE(rqst)); - headerp->rm_body.rm_padded.rm_thresh = - cpu_to_be32(RPCRDMA_INLINE_PAD_THRESH); - headerp->rm_body.rm_padded.rm_pempty[0] = xdr_zero; - headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero; - headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero; - hdrlen += 2 * sizeof(u32); /* extra words in padhdr */ - if (wtype != rpcrdma_noch) { - dprintk("RPC: %s: invalid chunk list\n", - __func__); - return -EIO; - } - } else { - headerp->rm_body.rm_nochunks.rm_empty[0] = xdr_zero; - headerp->rm_body.rm_nochunks.rm_empty[1] = xdr_zero; - headerp->rm_body.rm_nochunks.rm_empty[2] = xdr_zero; - /* new length after pullup */ - rpclen = rqst->rq_svec[0].iov_len; - /* - * Currently we try to not actually use read inline. - * Reply chunks have the desirable property that - * they land, packed, directly in the target buffers - * without headers, so they require no fixup. The - * additional RDMA Write op sends the same amount - * of data, streams on-the-wire and adds no overhead - * on receive. Therefore, we request a reply chunk - * for non-writes wherever feasible and efficient. - */ - if (wtype == rpcrdma_noch) - wtype = rpcrdma_replych; - } - } + rpcrdma_inline_pullup(rqst); + headerp->rm_body.rm_nochunks.rm_empty[0] = xdr_zero; + headerp->rm_body.rm_nochunks.rm_empty[1] = xdr_zero; + headerp->rm_body.rm_nochunks.rm_empty[2] = xdr_zero; + /* new length after pullup */ + rpclen = rqst->rq_svec[0].iov_len; + } else if (rtype == rpcrdma_readch) + rpclen += rpcrdma_tail_pullup(&rqst->rq_snd_buf); if (rtype != rpcrdma_noch) { hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf, headerp, rtype); @@ -518,9 +534,9 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) if (hdrlen < 0) return hdrlen; - dprintk("RPC: %s: %s: hdrlen %zd rpclen %zd padlen %zd" + dprintk("RPC: %s: %s: hdrlen %zd rpclen %zd" " headerp 0x%p base 0x%p lkey 0x%x\n", - __func__, transfertypes[wtype], hdrlen, rpclen, padlen, + __func__, transfertypes[wtype], hdrlen, rpclen, headerp, base, rdmab_lkey(req->rl_rdmabuf)); /* @@ -534,26 +550,15 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) req->rl_send_iov[0].length = hdrlen; req->rl_send_iov[0].lkey = rdmab_lkey(req->rl_rdmabuf); + req->rl_niovs = 1; + if (rtype == rpcrdma_areadch) + return 0; + req->rl_send_iov[1].addr = rdmab_addr(req->rl_sendbuf); req->rl_send_iov[1].length = rpclen; req->rl_send_iov[1].lkey = rdmab_lkey(req->rl_sendbuf); req->rl_niovs = 2; - - if (padlen) { - struct rpcrdma_ep *ep = &r_xprt->rx_ep; - - req->rl_send_iov[2].addr = rdmab_addr(ep->rep_padbuf); - req->rl_send_iov[2].length = padlen; - req->rl_send_iov[2].lkey = rdmab_lkey(ep->rep_padbuf); - - req->rl_send_iov[3].addr = req->rl_send_iov[1].addr + rpclen; - req->rl_send_iov[3].length = rqst->rq_slen - rpclen; - req->rl_send_iov[3].lkey = rdmab_lkey(req->rl_sendbuf); - - req->rl_niovs = 4; - } - return 0; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 2e1348bde325..cb5174284074 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -115,15 +115,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.tail[0].iov_len = 0; } -static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count) -{ - if (!rdma_cap_read_multi_sge(xprt->sc_cm_id->device, - xprt->sc_cm_id->port_num)) - return 1; - else - return min_t(int, sge_count, xprt->sc_max_sge); -} - /* Issue an RDMA_READ using the local lkey to map the data sink */ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, @@ -144,8 +135,7 @@ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, ctxt->direction = DMA_FROM_DEVICE; ctxt->read_hdr = head; - pages_needed = - min_t(int, pages_needed, rdma_read_max_sge(xprt, pages_needed)); + pages_needed = min_t(int, pages_needed, xprt->sc_max_sge_rd); read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); for (pno = 0; pno < pages_needed; pno++) { diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index d25cd430f9ff..1dfae8317065 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -136,6 +136,79 @@ static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt, return dma_addr; } +/* Returns the address of the first read chunk or <nul> if no read chunk + * is present + */ +struct rpcrdma_read_chunk * +svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp) +{ + struct rpcrdma_read_chunk *ch = + (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; + + if (ch->rc_discrim == xdr_zero) + return NULL; + return ch; +} + +/* Returns the address of the first read write array element or <nul> + * if no write array list is present + */ +static struct rpcrdma_write_array * +svc_rdma_get_write_array(struct rpcrdma_msg *rmsgp) +{ + if (rmsgp->rm_body.rm_chunks[0] != xdr_zero || + rmsgp->rm_body.rm_chunks[1] == xdr_zero) + return NULL; + return (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[1]; +} + +/* Returns the address of the first reply array element or <nul> if no + * reply array is present + */ +static struct rpcrdma_write_array * +svc_rdma_get_reply_array(struct rpcrdma_msg *rmsgp) +{ + struct rpcrdma_read_chunk *rch; + struct rpcrdma_write_array *wr_ary; + struct rpcrdma_write_array *rp_ary; + + /* XXX: Need to fix when reply chunk may occur with read list + * and/or write list. + */ + if (rmsgp->rm_body.rm_chunks[0] != xdr_zero || + rmsgp->rm_body.rm_chunks[1] != xdr_zero) + return NULL; + + rch = svc_rdma_get_read_chunk(rmsgp); + if (rch) { + while (rch->rc_discrim != xdr_zero) + rch++; + + /* The reply chunk follows an empty write array located + * at 'rc_position' here. The reply array is at rc_target. + */ + rp_ary = (struct rpcrdma_write_array *)&rch->rc_target; + goto found_it; + } + + wr_ary = svc_rdma_get_write_array(rmsgp); + if (wr_ary) { + int chunk = be32_to_cpu(wr_ary->wc_nchunks); + + rp_ary = (struct rpcrdma_write_array *) + &wr_ary->wc_array[chunk].wc_target.rs_length; + goto found_it; + } + + /* No read list, no write list */ + rp_ary = (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[2]; + + found_it: + if (rp_ary->wc_discrim == xdr_zero) + return NULL; + return rp_ary; +} + /* Assumptions: * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE */ @@ -384,6 +457,7 @@ static int send_reply(struct svcxprt_rdma *rdma, int byte_count) { struct ib_send_wr send_wr; + u32 xdr_off; int sge_no; int sge_bytes; int page_no; @@ -418,8 +492,8 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->direction = DMA_TO_DEVICE; /* Map the payload indicated by 'byte_count' */ + xdr_off = 0; for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) { - int xdr_off = 0; sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count); byte_count -= sge_bytes; ctxt->sge[sge_no].addr = @@ -457,6 +531,13 @@ static int send_reply(struct svcxprt_rdma *rdma, } rqstp->rq_next_page = rqstp->rq_respages + 1; + /* The loop above bumps sc_dma_used for each sge. The + * xdr_buf.tail gets a separate sge, but resides in the + * same page as xdr_buf.head. Don't count it twice. + */ + if (sge_no > ctxt->count) + atomic_dec(&rdma->sc_dma_used); + if (sge_no > rdma->sc_max_sge) { pr_err("svcrdma: Too many sges (%d)\n", sge_no); goto err; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 6b36279e4288..fcc3eb80c265 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -91,7 +91,7 @@ struct svc_xprt_class svc_rdma_class = { .xcl_name = "rdma", .xcl_owner = THIS_MODULE, .xcl_ops = &svc_rdma_ops, - .xcl_max_payload = RPCRDMA_MAXPAYLOAD, + .xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA, .xcl_ident = XPRT_TRANSPORT_RDMA, }; @@ -659,6 +659,7 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id, if (xprt) { set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); + svc_xprt_put(xprt); } break; default: @@ -733,17 +734,19 @@ static struct svc_rdma_fastreg_mr *rdma_alloc_frmr(struct svcxprt_rdma *xprt) struct ib_mr *mr; struct ib_fast_reg_page_list *pl; struct svc_rdma_fastreg_mr *frmr; + u32 num_sg; frmr = kmalloc(sizeof(*frmr), GFP_KERNEL); if (!frmr) goto err; - mr = ib_alloc_fast_reg_mr(xprt->sc_pd, RPCSVC_MAXPAGES); + num_sg = min_t(u32, RPCSVC_MAXPAGES, xprt->sc_frmr_pg_list_len); + mr = ib_alloc_mr(xprt->sc_pd, IB_MR_TYPE_MEM_REG, num_sg); if (IS_ERR(mr)) goto err_free_frmr; pl = ib_alloc_fast_reg_page_list(xprt->sc_cm_id->device, - RPCSVC_MAXPAGES); + num_sg); if (IS_ERR(pl)) goto err_free_mr; @@ -872,6 +875,8 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) * capabilities of this particular device */ newxprt->sc_max_sge = min((size_t)devattr.max_sge, (size_t)RPCSVC_MAXPAGES); + newxprt->sc_max_sge_rd = min_t(size_t, devattr.max_sge_rd, + RPCSVC_MAXPAGES); newxprt->sc_max_requests = min((size_t)devattr.max_qp_wr, (size_t)svcrdma_max_requests); newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_max_requests; @@ -1046,6 +1051,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) " remote_ip : %pI4\n" " remote_port : %d\n" " max_sge : %d\n" + " max_sge_rd : %d\n" " sq_depth : %d\n" " max_requests : %d\n" " ord : %d\n", @@ -1059,6 +1065,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) ntohs(((struct sockaddr_in *)&newxprt->sc_cm_id-> route.addr.dst_addr)->sin_port), newxprt->sc_max_sge, + newxprt->sc_max_sge_rd, newxprt->sc_sq_depth, newxprt->sc_max_requests, newxprt->sc_ord); @@ -1201,40 +1208,6 @@ static int svc_rdma_secure_port(struct svc_rqst *rqstp) return 1; } -/* - * Attempt to register the kvec representing the RPC memory with the - * device. - * - * Returns: - * NULL : The device does not support fastreg or there were no more - * fastreg mr. - * frmr : The kvec register request was successfully posted. - * <0 : An error was encountered attempting to register the kvec. - */ -int svc_rdma_fastreg(struct svcxprt_rdma *xprt, - struct svc_rdma_fastreg_mr *frmr) -{ - struct ib_send_wr fastreg_wr; - u8 key; - - /* Bump the key */ - key = (u8)(frmr->mr->lkey & 0x000000FF); - ib_update_fast_reg_key(frmr->mr, ++key); - - /* Prepare FASTREG WR */ - memset(&fastreg_wr, 0, sizeof fastreg_wr); - fastreg_wr.opcode = IB_WR_FAST_REG_MR; - fastreg_wr.send_flags = IB_SEND_SIGNALED; - fastreg_wr.wr.fast_reg.iova_start = (unsigned long)frmr->kva; - fastreg_wr.wr.fast_reg.page_list = frmr->page_list; - fastreg_wr.wr.fast_reg.page_list_len = frmr->page_list_len; - fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT; - fastreg_wr.wr.fast_reg.length = frmr->map_len; - fastreg_wr.wr.fast_reg.access_flags = frmr->access_flags; - fastreg_wr.wr.fast_reg.rkey = frmr->mr->lkey; - return svc_rdma_send(xprt, &fastreg_wr); -} - int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) { struct ib_send_wr *bad_wr, *n_wr; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 680f888a9ddd..64443eb754ad 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -175,10 +175,8 @@ xprt_rdma_format_addresses6(struct rpc_xprt *xprt, struct sockaddr *sap) } static void -xprt_rdma_format_addresses(struct rpc_xprt *xprt) +xprt_rdma_format_addresses(struct rpc_xprt *xprt, struct sockaddr *sap) { - struct sockaddr *sap = (struct sockaddr *) - &rpcx_to_rdmad(xprt).addr; char buf[128]; switch (sap->sa_family) { @@ -302,7 +300,7 @@ xprt_setup_rdma(struct xprt_create *args) struct rpc_xprt *xprt; struct rpcrdma_xprt *new_xprt; struct rpcrdma_ep *new_ep; - struct sockaddr_in *sin; + struct sockaddr *sap; int rc; if (args->addrlen > sizeof(xprt->addr)) { @@ -333,26 +331,20 @@ xprt_setup_rdma(struct xprt_create *args) * Set up RDMA-specific connect data. */ - /* Put server RDMA address in local cdata */ - memcpy(&cdata.addr, args->dstaddr, args->addrlen); + sap = (struct sockaddr *)&cdata.addr; + memcpy(sap, args->dstaddr, args->addrlen); /* Ensure xprt->addr holds valid server TCP (not RDMA) * address, for any side protocols which peek at it */ xprt->prot = IPPROTO_TCP; xprt->addrlen = args->addrlen; - memcpy(&xprt->addr, &cdata.addr, xprt->addrlen); + memcpy(&xprt->addr, sap, xprt->addrlen); - sin = (struct sockaddr_in *)&cdata.addr; - if (ntohs(sin->sin_port) != 0) + if (rpc_get_port(sap)) xprt_set_bound(xprt); - dprintk("RPC: %s: %pI4:%u\n", - __func__, &sin->sin_addr.s_addr, ntohs(sin->sin_port)); - - /* Set max requests */ cdata.max_requests = xprt->max_reqs; - /* Set some length limits */ cdata.rsize = RPCRDMA_MAX_SEGS * PAGE_SIZE; /* RDMA write max */ cdata.wsize = RPCRDMA_MAX_SEGS * PAGE_SIZE; /* RDMA read max */ @@ -375,8 +367,7 @@ xprt_setup_rdma(struct xprt_create *args) new_xprt = rpcx_to_rdmax(xprt); - rc = rpcrdma_ia_open(new_xprt, (struct sockaddr *) &cdata.addr, - xprt_rdma_memreg_strategy); + rc = rpcrdma_ia_open(new_xprt, sap, xprt_rdma_memreg_strategy); if (rc) goto out1; @@ -409,7 +400,7 @@ xprt_setup_rdma(struct xprt_create *args) INIT_DELAYED_WORK(&new_xprt->rx_connect_worker, xprt_rdma_connect_worker); - xprt_rdma_format_addresses(xprt); + xprt_rdma_format_addresses(xprt, sap); xprt->max_payload = new_xprt->rx_ia.ri_ops->ro_maxpages(new_xprt); if (xprt->max_payload == 0) goto out4; @@ -420,6 +411,9 @@ xprt_setup_rdma(struct xprt_create *args) if (!try_module_get(THIS_MODULE)) goto out4; + dprintk("RPC: %s: %s:%s\n", __func__, + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); return xprt; out4: @@ -653,31 +647,30 @@ static void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) if (xprt_connected(xprt)) idle_time = (long)(jiffies - xprt->last_used) / HZ; - seq_printf(seq, - "\txprt:\trdma %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu " - "%lu %lu %lu %Lu %Lu %Lu %Lu %lu %lu %lu\n", - - 0, /* need a local port? */ - xprt->stat.bind_count, - xprt->stat.connect_count, - xprt->stat.connect_time, - idle_time, - xprt->stat.sends, - xprt->stat.recvs, - xprt->stat.bad_xids, - xprt->stat.req_u, - xprt->stat.bklog_u, - - r_xprt->rx_stats.read_chunk_count, - r_xprt->rx_stats.write_chunk_count, - r_xprt->rx_stats.reply_chunk_count, - r_xprt->rx_stats.total_rdma_request, - r_xprt->rx_stats.total_rdma_reply, - r_xprt->rx_stats.pullup_copy_count, - r_xprt->rx_stats.fixup_copy_count, - r_xprt->rx_stats.hardway_register_count, - r_xprt->rx_stats.failed_marshal_count, - r_xprt->rx_stats.bad_reply_count); + seq_puts(seq, "\txprt:\trdma "); + seq_printf(seq, "%u %lu %lu %lu %ld %lu %lu %lu %llu %llu ", + 0, /* need a local port? */ + xprt->stat.bind_count, + xprt->stat.connect_count, + xprt->stat.connect_time, + idle_time, + xprt->stat.sends, + xprt->stat.recvs, + xprt->stat.bad_xids, + xprt->stat.req_u, + xprt->stat.bklog_u); + seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu\n", + r_xprt->rx_stats.read_chunk_count, + r_xprt->rx_stats.write_chunk_count, + r_xprt->rx_stats.reply_chunk_count, + r_xprt->rx_stats.total_rdma_request, + r_xprt->rx_stats.total_rdma_reply, + r_xprt->rx_stats.pullup_copy_count, + r_xprt->rx_stats.fixup_copy_count, + r_xprt->rx_stats.hardway_register_count, + r_xprt->rx_stats.failed_marshal_count, + r_xprt->rx_stats.bad_reply_count, + r_xprt->rx_stats.nomsg_call_count); } static int diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 891c4ede2c20..682996779970 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -52,6 +52,7 @@ #include <linux/prefetch.h> #include <linux/sunrpc/addr.h> #include <asm/bitops.h> +#include <linux/module.h> /* try_module_get()/module_put() */ #include "xprt_rdma.h" @@ -414,6 +415,14 @@ connected: return 0; } +static void rpcrdma_destroy_id(struct rdma_cm_id *id) +{ + if (id) { + module_put(id->device->owner); + rdma_destroy_id(id); + } +} + static struct rdma_cm_id * rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia, struct sockaddr *addr) @@ -440,6 +449,17 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, } wait_for_completion_interruptible_timeout(&ia->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT) + 1); + + /* FIXME: + * Until xprtrdma supports DEVICE_REMOVAL, the provider must + * be pinned while there are active NFS/RDMA mounts to prevent + * hangs and crashes at umount time. + */ + if (!ia->ri_async_rc && !try_module_get(id->device->owner)) { + dprintk("RPC: %s: Failed to get device module\n", + __func__); + ia->ri_async_rc = -ENODEV; + } rc = ia->ri_async_rc; if (rc) goto out; @@ -449,16 +469,17 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, if (rc) { dprintk("RPC: %s: rdma_resolve_route() failed %i\n", __func__, rc); - goto out; + goto put; } wait_for_completion_interruptible_timeout(&ia->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT) + 1); rc = ia->ri_async_rc; if (rc) - goto out; + goto put; return id; - +put: + module_put(id->device->owner); out: rdma_destroy_id(id); return ERR_PTR(rc); @@ -493,9 +514,11 @@ rpcrdma_clean_cq(struct ib_cq *cq) int rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) { - int rc, mem_priv; struct rpcrdma_ia *ia = &xprt->rx_ia; struct ib_device_attr *devattr = &ia->ri_devattr; + int rc; + + ia->ri_dma_mr = NULL; ia->ri_id = rpcrdma_create_id(xprt, ia, addr); if (IS_ERR(ia->ri_id)) { @@ -519,11 +542,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) goto out3; } - if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) { - ia->ri_have_dma_lkey = 1; - ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; - } - if (memreg == RPCRDMA_FRMR) { /* Requires both frmr reg and local dma lkey */ if (((devattr->device_cap_flags & @@ -539,42 +557,19 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) if (!ia->ri_device->alloc_fmr) { dprintk("RPC: %s: MTHCAFMR registration " "not supported by HCA\n", __func__); - memreg = RPCRDMA_ALLPHYSICAL; + goto out3; } } - /* - * Optionally obtain an underlying physical identity mapping in - * order to do a memory window-based bind. This base registration - * is protected from remote access - that is enabled only by binding - * for the specific bytes targeted during each RPC operation, and - * revoked after the corresponding completion similar to a storage - * adapter. - */ switch (memreg) { case RPCRDMA_FRMR: ia->ri_ops = &rpcrdma_frwr_memreg_ops; break; case RPCRDMA_ALLPHYSICAL: ia->ri_ops = &rpcrdma_physical_memreg_ops; - mem_priv = IB_ACCESS_LOCAL_WRITE | - IB_ACCESS_REMOTE_WRITE | - IB_ACCESS_REMOTE_READ; - goto register_setup; + break; case RPCRDMA_MTHCAFMR: ia->ri_ops = &rpcrdma_fmr_memreg_ops; - if (ia->ri_have_dma_lkey) - break; - mem_priv = IB_ACCESS_LOCAL_WRITE; - register_setup: - ia->ri_bind_mem = ib_get_dma_mr(ia->ri_pd, mem_priv); - if (IS_ERR(ia->ri_bind_mem)) { - printk(KERN_ALERT "%s: ib_get_dma_mr for " - "phys register failed with %lX\n", - __func__, PTR_ERR(ia->ri_bind_mem)); - rc = -ENOMEM; - goto out3; - } break; default: printk(KERN_ERR "RPC: Unsupported memory " @@ -592,7 +587,7 @@ out3: ib_dealloc_pd(ia->ri_pd); ia->ri_pd = NULL; out2: - rdma_destroy_id(ia->ri_id); + rpcrdma_destroy_id(ia->ri_id); ia->ri_id = NULL; out1: return rc; @@ -606,25 +601,17 @@ out1: void rpcrdma_ia_close(struct rpcrdma_ia *ia) { - int rc; - dprintk("RPC: %s: entering\n", __func__); - if (ia->ri_bind_mem != NULL) { - rc = ib_dereg_mr(ia->ri_bind_mem); - dprintk("RPC: %s: ib_dereg_mr returned %i\n", - __func__, rc); - } - if (ia->ri_id != NULL && !IS_ERR(ia->ri_id)) { if (ia->ri_id->qp) rdma_destroy_qp(ia->ri_id); - rdma_destroy_id(ia->ri_id); + rpcrdma_destroy_id(ia->ri_id); ia->ri_id = NULL; } /* If the pd is still busy, xprtrdma missed freeing a resource */ if (ia->ri_pd && !IS_ERR(ia->ri_pd)) - WARN_ON(ib_dealloc_pd(ia->ri_pd)); + ib_dealloc_pd(ia->ri_pd); } /* @@ -639,6 +626,12 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, struct ib_cq_init_attr cq_attr = {}; int rc, err; + if (devattr->max_sge < RPCRDMA_MAX_IOVS) { + dprintk("RPC: %s: insufficient sge's available\n", + __func__); + return -ENOMEM; + } + /* check provider's send/recv wr limits */ if (cdata->max_requests > devattr->max_qp_wr) cdata->max_requests = devattr->max_qp_wr; @@ -651,21 +644,13 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, if (rc) return rc; ep->rep_attr.cap.max_recv_wr = cdata->max_requests; - ep->rep_attr.cap.max_send_sge = (cdata->padding ? 4 : 2); + ep->rep_attr.cap.max_send_sge = RPCRDMA_MAX_IOVS; ep->rep_attr.cap.max_recv_sge = 1; ep->rep_attr.cap.max_inline_data = 0; ep->rep_attr.sq_sig_type = IB_SIGNAL_REQ_WR; ep->rep_attr.qp_type = IB_QPT_RC; ep->rep_attr.port_num = ~0; - if (cdata->padding) { - ep->rep_padbuf = rpcrdma_alloc_regbuf(ia, cdata->padding, - GFP_KERNEL); - if (IS_ERR(ep->rep_padbuf)) - return PTR_ERR(ep->rep_padbuf); - } else - ep->rep_padbuf = NULL; - dprintk("RPC: %s: requested max: dtos: send %d recv %d; " "iovs: send %d recv %d\n", __func__, @@ -748,7 +733,8 @@ out2: dprintk("RPC: %s: ib_destroy_cq returned %i\n", __func__, err); out1: - rpcrdma_free_regbuf(ia, ep->rep_padbuf); + if (ia->ri_dma_mr) + ib_dereg_mr(ia->ri_dma_mr); return rc; } @@ -775,8 +761,6 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) ia->ri_id->qp = NULL; } - rpcrdma_free_regbuf(ia, ep->rep_padbuf); - rpcrdma_clean_cq(ep->rep_attr.recv_cq); rc = ib_destroy_cq(ep->rep_attr.recv_cq); if (rc) @@ -788,6 +772,12 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) if (rc) dprintk("RPC: %s: ib_destroy_cq returned %i\n", __func__, rc); + + if (ia->ri_dma_mr) { + rc = ib_dereg_mr(ia->ri_dma_mr); + dprintk("RPC: %s: ib_dereg_mr returned %i\n", + __func__, rc); + } } /* @@ -825,7 +815,7 @@ retry: if (ia->ri_device != id->device) { printk("RPC: %s: can't reconnect on " "different device!\n", __func__); - rdma_destroy_id(id); + rpcrdma_destroy_id(id); rc = -ENETUNREACH; goto out; } @@ -834,7 +824,7 @@ retry: if (rc) { dprintk("RPC: %s: rdma_create_qp failed %i\n", __func__, rc); - rdma_destroy_id(id); + rpcrdma_destroy_id(id); rc = -ENETUNREACH; goto out; } @@ -845,7 +835,7 @@ retry: write_unlock(&ia->ri_qplock); rdma_destroy_qp(old); - rdma_destroy_id(old); + rpcrdma_destroy_id(old); } else { dprintk("RPC: %s: connecting...\n", __func__); rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr); @@ -1229,75 +1219,6 @@ rpcrdma_mapping_error(struct rpcrdma_mr_seg *seg) (unsigned long long)seg->mr_dma, seg->mr_dmalen); } -static int -rpcrdma_register_internal(struct rpcrdma_ia *ia, void *va, int len, - struct ib_mr **mrp, struct ib_sge *iov) -{ - struct ib_phys_buf ipb; - struct ib_mr *mr; - int rc; - - /* - * All memory passed here was kmalloc'ed, therefore phys-contiguous. - */ - iov->addr = ib_dma_map_single(ia->ri_device, - va, len, DMA_BIDIRECTIONAL); - if (ib_dma_mapping_error(ia->ri_device, iov->addr)) - return -ENOMEM; - - iov->length = len; - - if (ia->ri_have_dma_lkey) { - *mrp = NULL; - iov->lkey = ia->ri_dma_lkey; - return 0; - } else if (ia->ri_bind_mem != NULL) { - *mrp = NULL; - iov->lkey = ia->ri_bind_mem->lkey; - return 0; - } - - ipb.addr = iov->addr; - ipb.size = iov->length; - mr = ib_reg_phys_mr(ia->ri_pd, &ipb, 1, - IB_ACCESS_LOCAL_WRITE, &iov->addr); - - dprintk("RPC: %s: phys convert: 0x%llx " - "registered 0x%llx length %d\n", - __func__, (unsigned long long)ipb.addr, - (unsigned long long)iov->addr, len); - - if (IS_ERR(mr)) { - *mrp = NULL; - rc = PTR_ERR(mr); - dprintk("RPC: %s: failed with %i\n", __func__, rc); - } else { - *mrp = mr; - iov->lkey = mr->lkey; - rc = 0; - } - - return rc; -} - -static int -rpcrdma_deregister_internal(struct rpcrdma_ia *ia, - struct ib_mr *mr, struct ib_sge *iov) -{ - int rc; - - ib_dma_unmap_single(ia->ri_device, - iov->addr, iov->length, DMA_BIDIRECTIONAL); - - if (NULL == mr) - return 0; - - rc = ib_dereg_mr(mr); - if (rc) - dprintk("RPC: %s: ib_dereg_mr failed %i\n", __func__, rc); - return rc; -} - /** * rpcrdma_alloc_regbuf - kmalloc and register memory for SEND/RECV buffers * @ia: controlling rpcrdma_ia @@ -1317,26 +1238,29 @@ struct rpcrdma_regbuf * rpcrdma_alloc_regbuf(struct rpcrdma_ia *ia, size_t size, gfp_t flags) { struct rpcrdma_regbuf *rb; - int rc; + struct ib_sge *iov; - rc = -ENOMEM; rb = kmalloc(sizeof(*rb) + size, flags); if (rb == NULL) goto out; - rb->rg_size = size; - rb->rg_owner = NULL; - rc = rpcrdma_register_internal(ia, rb->rg_base, size, - &rb->rg_mr, &rb->rg_iov); - if (rc) + iov = &rb->rg_iov; + iov->addr = ib_dma_map_single(ia->ri_device, + (void *)rb->rg_base, size, + DMA_BIDIRECTIONAL); + if (ib_dma_mapping_error(ia->ri_device, iov->addr)) goto out_free; + iov->length = size; + iov->lkey = ia->ri_dma_lkey; + rb->rg_size = size; + rb->rg_owner = NULL; return rb; out_free: kfree(rb); out: - return ERR_PTR(rc); + return ERR_PTR(-ENOMEM); } /** @@ -1347,10 +1271,15 @@ out: void rpcrdma_free_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb) { - if (rb) { - rpcrdma_deregister_internal(ia, rb->rg_mr, &rb->rg_iov); - kfree(rb); - } + struct ib_sge *iov; + + if (!rb) + return; + + iov = &rb->rg_iov; + ib_dma_unmap_single(ia->ri_device, + iov->addr, iov->length, DMA_BIDIRECTIONAL); + kfree(rb); } /* @@ -1363,9 +1292,11 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_req *req) { + struct ib_device *device = ia->ri_device; struct ib_send_wr send_wr, *send_wr_fail; struct rpcrdma_rep *rep = req->rl_reply; - int rc; + struct ib_sge *iov = req->rl_send_iov; + int i, rc; if (rep) { rc = rpcrdma_ep_post_recv(ia, ep, rep); @@ -1376,22 +1307,15 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, send_wr.next = NULL; send_wr.wr_id = RPCRDMA_IGNORE_COMPLETION; - send_wr.sg_list = req->rl_send_iov; + send_wr.sg_list = iov; send_wr.num_sge = req->rl_niovs; send_wr.opcode = IB_WR_SEND; - if (send_wr.num_sge == 4) /* no need to sync any pad (constant) */ - ib_dma_sync_single_for_device(ia->ri_device, - req->rl_send_iov[3].addr, - req->rl_send_iov[3].length, - DMA_TO_DEVICE); - ib_dma_sync_single_for_device(ia->ri_device, - req->rl_send_iov[1].addr, - req->rl_send_iov[1].length, - DMA_TO_DEVICE); - ib_dma_sync_single_for_device(ia->ri_device, - req->rl_send_iov[0].addr, - req->rl_send_iov[0].length, - DMA_TO_DEVICE); + + for (i = 0; i < send_wr.num_sge; i++) + ib_dma_sync_single_for_device(device, iov[i].addr, + iov[i].length, DMA_TO_DEVICE); + dprintk("RPC: %s: posting %d s/g entries\n", + __func__, send_wr.num_sge); if (DECR_CQCOUNT(ep) > 0) send_wr.send_flags = 0; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index f49dd8b38122..02512221b8bc 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -51,7 +51,6 @@ #include <linux/sunrpc/clnt.h> /* rpc_xprt */ #include <linux/sunrpc/rpc_rdma.h> /* RPC/RDMA protocol */ #include <linux/sunrpc/xprtrdma.h> /* xprt parameters */ -#include <linux/sunrpc/svc.h> /* RPCSVC_MAXPAYLOAD */ #define RDMA_RESOLVE_TIMEOUT (5000) /* 5 seconds */ #define RDMA_CONNECT_RETRY_MAX (2) /* retries if no listener backlog */ @@ -65,9 +64,8 @@ struct rpcrdma_ia { struct ib_device *ri_device; struct rdma_cm_id *ri_id; struct ib_pd *ri_pd; - struct ib_mr *ri_bind_mem; + struct ib_mr *ri_dma_mr; u32 ri_dma_lkey; - int ri_have_dma_lkey; struct completion ri_done; int ri_async_rc; unsigned int ri_max_frmr_depth; @@ -89,7 +87,6 @@ struct rpcrdma_ep { int rep_connected; struct ib_qp_init_attr rep_attr; wait_queue_head_t rep_connect_wait; - struct rpcrdma_regbuf *rep_padbuf; struct rdma_conn_param rep_remote_cma; struct sockaddr_storage rep_remote_addr; struct delayed_work rep_connect_worker; @@ -119,7 +116,6 @@ struct rpcrdma_ep { struct rpcrdma_regbuf { size_t rg_size; struct rpcrdma_req *rg_owner; - struct ib_mr *rg_mr; struct ib_sge rg_iov; __be32 rg_base[0] __attribute__ ((aligned(256))); }; @@ -165,8 +161,7 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb) * struct rpcrdma_buffer. N is the max number of outstanding requests. */ -/* temporary static scatter/gather max */ -#define RPCRDMA_MAX_DATA_SEGS (64) /* max scatter/gather */ +#define RPCRDMA_MAX_DATA_SEGS ((1 * 1024 * 1024) / PAGE_SIZE) #define RPCRDMA_MAX_SEGS (RPCRDMA_MAX_DATA_SEGS + 2) /* head+tail = 2 */ struct rpcrdma_buffer; @@ -258,16 +253,18 @@ struct rpcrdma_mr_seg { /* chunk descriptors */ char *mr_offset; /* kva if no page, else offset */ }; +#define RPCRDMA_MAX_IOVS (2) + struct rpcrdma_req { - unsigned int rl_niovs; /* 0, 2 or 4 */ - unsigned int rl_nchunks; /* non-zero if chunks */ - unsigned int rl_connect_cookie; /* retry detection */ - struct rpcrdma_buffer *rl_buffer; /* home base for this structure */ + unsigned int rl_niovs; + unsigned int rl_nchunks; + unsigned int rl_connect_cookie; + struct rpcrdma_buffer *rl_buffer; struct rpcrdma_rep *rl_reply;/* holder for reply buffer */ - struct ib_sge rl_send_iov[4]; /* for active requests */ - struct rpcrdma_regbuf *rl_rdmabuf; - struct rpcrdma_regbuf *rl_sendbuf; - struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; + struct ib_sge rl_send_iov[RPCRDMA_MAX_IOVS]; + struct rpcrdma_regbuf *rl_rdmabuf; + struct rpcrdma_regbuf *rl_sendbuf; + struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; }; static inline struct rpcrdma_req * @@ -342,6 +339,7 @@ struct rpcrdma_stats { unsigned long hardway_register_count; unsigned long failed_marshal_count; unsigned long bad_reply_count; + unsigned long nomsg_call_count; }; /* diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0030376327b7..7be90bc1a7c2 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -822,6 +822,8 @@ static void xs_reset_transport(struct sock_xprt *transport) if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); + kernel_sock_shutdown(sock, SHUT_RDWR); + write_lock_bh(&sk->sk_callback_lock); transport->inet = NULL; transport->sock = NULL; @@ -829,6 +831,7 @@ static void xs_reset_transport(struct sock_xprt *transport) sk->sk_user_data = NULL; xs_restore_old_callbacks(transport, sk); + xprt_clear_connected(xprt); write_unlock_bh(&sk->sk_callback_lock); xs_sock_reset_connection_flags(xprt); @@ -1866,7 +1869,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_data_ready = xs_local_data_ready; sk->sk_write_space = xs_udp_write_space; sk->sk_error_report = xs_error_report; - sk->sk_allocation = GFP_ATOMIC; + sk->sk_allocation = GFP_NOIO; xprt_clear_connected(xprt); @@ -2051,7 +2054,7 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_user_data = xprt; sk->sk_data_ready = xs_udp_data_ready; sk->sk_write_space = xs_udp_write_space; - sk->sk_allocation = GFP_ATOMIC; + sk->sk_allocation = GFP_NOIO; xprt_set_connected(xprt); @@ -2153,7 +2156,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; sk->sk_error_report = xs_error_report; - sk->sk_allocation = GFP_ATOMIC; + sk->sk_allocation = GFP_NOIO; /* socket options */ sock_reset_flag(sk, SOCK_LINGER); @@ -2279,13 +2282,14 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); - /* Start by resetting any existing state */ - xs_reset_transport(transport); - - if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) { + if (transport->sock != NULL) { dprintk("RPC: xs_connect delayed xprt %p for %lu " "seconds\n", xprt, xprt->reestablish_timeout / HZ); + + /* Start by resetting any existing state */ + xs_reset_transport(transport); + queue_delayed_work(rpciod_workqueue, &transport->connect_worker, xprt->reestablish_timeout); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 16c1c43980a1..fda38f830a10 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -853,12 +853,8 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .cb = cb, .idx = idx, }; - int err; - - err = switchdev_port_obj_dump(dev, &dump.obj); - if (err) - return err; + switchdev_port_obj_dump(dev, &dump.obj); return dump.idx; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 8b010c976b2f..41042de3ae9b 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -170,6 +170,30 @@ static void bclink_retransmit_pkt(struct tipc_net *tn, u32 after, u32 to) } /** + * bclink_prepare_wakeup - prepare users for wakeup after congestion + * @bcl: broadcast link + * @resultq: queue for users which can be woken up + * Move a number of waiting users, as permitted by available space in + * the send queue, from link wait queue to specified queue for wakeup + */ +static void bclink_prepare_wakeup(struct tipc_link *bcl, struct sk_buff_head *resultq) +{ + int pnd[TIPC_SYSTEM_IMPORTANCE + 1] = {0,}; + int imp, lim; + struct sk_buff *skb, *tmp; + + skb_queue_walk_safe(&bcl->wakeupq, skb, tmp) { + imp = TIPC_SKB_CB(skb)->chain_imp; + lim = bcl->window + bcl->backlog[imp].limit; + pnd[imp] += TIPC_SKB_CB(skb)->chain_sz; + if ((pnd[imp] + bcl->backlog[imp].len) >= lim) + continue; + skb_unlink(skb, &bcl->wakeupq); + skb_queue_tail(resultq, skb); + } +} + +/** * tipc_bclink_wakeup_users - wake up pending users * * Called with no locks taken @@ -177,8 +201,12 @@ static void bclink_retransmit_pkt(struct tipc_net *tn, u32 after, u32 to) void tipc_bclink_wakeup_users(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *bcl = tn->bcl; + struct sk_buff_head resultq; - tipc_sk_rcv(net, &tn->bclink->link.wakeupq); + skb_queue_head_init(&resultq); + bclink_prepare_wakeup(bcl, &resultq); + tipc_sk_rcv(net, &resultq); } /** diff --git a/net/wireless/reg.c b/net/wireless/reg.c index b144485946f2..2510b231451e 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2625,7 +2625,7 @@ static void restore_regulatory_settings(bool reset_user) * settings, user regulatory settings takes precedence. */ if (is_an_alpha2(alpha2)) - regulatory_hint_user(user_alpha2, NL80211_USER_REG_HINT_USER); + regulatory_hint_user(alpha2, NL80211_USER_REG_HINT_USER); spin_lock(®_requests_lock); list_splice_tail_init(&tmp_reg_req_list, ®_requests_list); |