diff options
author | David S. Miller <davem@davemloft.net> | 2015-09-26 16:08:27 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2015-09-26 16:08:27 -0700 |
commit | 4963ed48f2c20196d51a447ee87dc2815584fee4 (patch) | |
tree | a1902f466dafa00453889a4f1e66b00249ce0529 /net | |
parent | 4d54d86546f62c7c4a0fe3b36a64c5e3b98ce1a9 (diff) | |
parent | 518a7cb6980cd640c7f979d29021ad870f60d7d7 (diff) | |
download | linux-stable-4963ed48f2c20196d51a447ee87dc2815584fee4.tar.gz linux-stable-4963ed48f2c20196d51a447ee87dc2815584fee4.tar.bz2 linux-stable-4963ed48f2c20196d51a447ee87dc2815584fee4.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
net/ipv4/arp.c
The net/ipv4/arp.c conflict was one commit adding a new
local variable while another commit was deleting one.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
57 files changed, 778 insertions, 420 deletions
diff --git a/net/atm/clip.c b/net/atm/clip.c index 17e55dfecbe2..e07f551a863c 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -317,6 +317,9 @@ static int clip_constructor(struct neighbour *neigh) static int clip_encap(struct atm_vcc *vcc, int mode) { + if (!CLIP_VCC(vcc)) + return -EBADFD; + CLIP_VCC(vcc)->encap = mode; return 0; } diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 4d56e593faad..25644e1bc479 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2311,12 +2311,6 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) if (!conn) return 1; - chan = conn->smp; - if (!chan) { - BT_ERR("SMP security requested but not available"); - return 1; - } - if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED)) return 1; @@ -2330,6 +2324,12 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) if (smp_ltk_encrypt(conn, hcon->pending_sec_level)) return 0; + chan = conn->smp; + if (!chan) { + BT_ERR("SMP security requested but not available"); + return 1; + } + l2cap_chan_lock(chan); /* If SMP is already in progress ignore this request */ diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index b4d858a18eb6..03661d97463c 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1006,7 +1006,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); - len = sizeof(*ih); + len = skb_transport_offset(skb) + sizeof(*ih); for (i = 0; i < num; i++) { len += sizeof(*grec); @@ -1067,7 +1067,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, icmp6h = icmp6_hdr(skb); num = ntohs(icmp6h->icmp6_dataun.un_data16[1]); - len = sizeof(*icmp6h); + len = skb_transport_offset(skb) + sizeof(*icmp6h); for (i = 0; i < num; i++) { __be16 *nsrcs, _nsrcs; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 69a4d30a9ccf..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]...] */ 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..b9b0e3b5da49 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 +1352,16 @@ 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 now = CURRENT_TIME; + + con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2); + ceph_encode_timespec(&con->out_temp_keepalive2, &now); + con_out_kvec_add(con, sizeof(con->out_temp_keepalive2), + &con->out_temp_keepalive2); + } else { + con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive); + } con_flag_set(con, CON_FLAG_WRITE_PENDING); } @@ -1625,6 +1635,12 @@ 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 +2338,6 @@ 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 +2466,17 @@ 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 +2546,10 @@ 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 +2559,6 @@ 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 +2661,9 @@ 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 +2707,12 @@ 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 +2828,7 @@ 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 +3130,20 @@ 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/dev.c b/net/core/dev.c index 464c22b6261a..323c04edd779 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4723,6 +4723,8 @@ void napi_disable(struct napi_struct *n) while (test_and_set_bit(NAPI_STATE_SCHED, &n->state)) msleep(1); + while (test_and_set_bit(NAPI_STATE_NPSVC, &n->state)) + msleep(1); hrtimer_cancel(&n->timer); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index bf77e3639ce0..365de66436ac 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -631,15 +631,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, { int idx = 0; struct fib_rule *rule; + int err = 0; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; - if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWRULE, - NLM_F_MULTI, ops) < 0) + err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWRULE, + NLM_F_MULTI, ops); + if (err) break; skip: idx++; @@ -648,7 +650,7 @@ skip: cb->args[1] = idx; rules_ops_put(ops); - return skb->len; + return err; } static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) @@ -664,7 +666,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) if (ops == NULL) return -EAFNOSUPPORT; - return dump_rules(skb, cb, ops); + dump_rules(skb, cb, ops); + + return skb->len; } rcu_read_lock(); diff --git a/net/core/filter.c b/net/core/filter.c index 96bd962c292d..60e3fe7c59c0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -478,9 +478,9 @@ do_pass: bpf_src = BPF_X; } else { insn->dst_reg = BPF_REG_A; - insn->src_reg = BPF_REG_X; insn->imm = fp->k; bpf_src = BPF_SRC(fp->code); + insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0; } /* Common case where 'jump_false' is next insn. */ diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 49b599062af1..b4c530065106 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1478,6 +1478,15 @@ static int of_dev_node_match(struct device *dev, const void *data) return ret == 0 ? dev->of_node == data : ret; } +/* + * of_find_net_device_by_node - lookup the net device for the device node + * @np: OF device node + * + * Looks up the net_device structure corresponding with the device node. + * If successful, returns a pointer to the net_device with the embedded + * struct device refcount incremented by one, or NULL on failure. The + * refcount must be dropped when done with the net_device. + */ struct net_device *of_find_net_device_by_node(struct device_node *np) { struct device *dev; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 6aa3db8dfc3b..8bdada242a7d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -142,7 +142,7 @@ static void queue_process(struct work_struct *work) */ static int poll_one_napi(struct napi_struct *napi, int budget) { - int work; + int work = 0; /* net_rx_action's ->poll() invocations and our's are * synchronized by this test which is only made while @@ -151,7 +151,12 @@ static int poll_one_napi(struct napi_struct *napi, int budget) if (!test_bit(NAPI_STATE_SCHED, &napi->state)) return budget; - set_bit(NAPI_STATE_NPSVC, &napi->state); + /* If we set this bit but see that it has already been set, + * that indicates that napi has been disabled and we need + * to abort this operation + */ + if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) + goto out; work = napi->poll(napi, budget); WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll); @@ -159,6 +164,7 @@ static int poll_one_napi(struct napi_struct *napi, int budget) clear_bit(NAPI_STATE_NPSVC, &napi->state); +out: return budget - work; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e5452296ec2f..474a6da3b51a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3047,6 +3047,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) u32 portid = NETLINK_CB(cb->skb).portid; u32 seq = cb->nlh->nlmsg_seq; u32 filter_mask = 0; + int err; if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) { struct nlattr *extfilt; @@ -3067,20 +3068,25 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *br_dev = netdev_master_upper_dev_get(dev); if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { - if (idx >= cb->args[0] && - br_dev->netdev_ops->ndo_bridge_getlink( - skb, portid, seq, dev, filter_mask, - NLM_F_MULTI) < 0) - break; + if (idx >= cb->args[0]) { + err = br_dev->netdev_ops->ndo_bridge_getlink( + skb, portid, seq, dev, + filter_mask, NLM_F_MULTI); + if (err < 0 && err != -EOPNOTSUPP) + break; + } idx++; } if (ops->ndo_bridge_getlink) { - if (idx >= cb->args[0] && - ops->ndo_bridge_getlink(skb, portid, seq, dev, - filter_mask, - NLM_F_MULTI) < 0) - break; + if (idx >= cb->args[0]) { + err = ops->ndo_bridge_getlink(skb, portid, + seq, dev, + filter_mask, + NLM_F_MULTI); + if (err < 0 && err != -EOPNOTSUPP) + break; + } idx++; } } diff --git a/net/core/sock.c b/net/core/sock.c index ca2984afe16e..3307c02244d3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2740,10 +2740,8 @@ static void req_prot_cleanup(struct request_sock_ops *rsk_prot) return; kfree(rsk_prot->slab_name); rsk_prot->slab_name = NULL; - if (rsk_prot->slab) { - kmem_cache_destroy(rsk_prot->slab); - rsk_prot->slab = NULL; - } + kmem_cache_destroy(rsk_prot->slab); + rsk_prot->slab = NULL; } static int req_prot_init(const struct proto *prot) @@ -2828,10 +2826,8 @@ void proto_unregister(struct proto *prot) list_del(&prot->node); mutex_unlock(&proto_list_mutex); - if (prot->slab != NULL) { - kmem_cache_destroy(prot->slab); - prot->slab = NULL; - } + kmem_cache_destroy(prot->slab); + prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index bd9e718c2a20..3de0d0362d7f 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -398,12 +398,8 @@ out_err: void dccp_ackvec_exit(void) { - if (dccp_ackvec_slab != NULL) { - kmem_cache_destroy(dccp_ackvec_slab); - dccp_ackvec_slab = NULL; - } - if (dccp_ackvec_record_slab != NULL) { - kmem_cache_destroy(dccp_ackvec_record_slab); - dccp_ackvec_record_slab = NULL; - } + kmem_cache_destroy(dccp_ackvec_slab); + dccp_ackvec_slab = NULL; + kmem_cache_destroy(dccp_ackvec_record_slab); + dccp_ackvec_record_slab = NULL; } diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 83498975165f..90f77d08cc37 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -95,8 +95,7 @@ static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_f static void ccid_kmem_cache_destroy(struct kmem_cache *slab) { - if (slab != NULL) - kmem_cache_destroy(slab); + kmem_cache_destroy(slab); } static int __init ccid_activate(struct ccid_operations *ccid_ops) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 30addee2dd03..838f524cf11a 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -48,8 +48,6 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) tw->tw_ipv6only = sk->sk_ipv6only; } #endif - /* Linkage updates. */ - __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) @@ -60,6 +58,8 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) timeo = DCCP_TIMEWAIT_LEN; inet_twsk_schedule(tw, timeo); + /* Linkage updates. */ + __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 76e3800765f8..c59fa5d9c22c 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -634,6 +634,10 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd) port_index++; } kfree(pd->chip[i].rtable); + + /* Drop our reference to the MDIO bus device */ + if (pd->chip[i].host_dev) + put_device(pd->chip[i].host_dev); } kfree(pd->chip); } @@ -661,16 +665,22 @@ static int dsa_of_probe(struct device *dev) return -EPROBE_DEFER; ethernet = of_parse_phandle(np, "dsa,ethernet", 0); - if (!ethernet) - return -EINVAL; + if (!ethernet) { + ret = -EINVAL; + goto out_put_mdio; + } ethernet_dev = of_find_net_device_by_node(ethernet); - if (!ethernet_dev) - return -EPROBE_DEFER; + if (!ethernet_dev) { + ret = -EPROBE_DEFER; + goto out_put_mdio; + } pd = kzalloc(sizeof(*pd), GFP_KERNEL); - if (!pd) - return -ENOMEM; + if (!pd) { + ret = -ENOMEM; + goto out_put_ethernet; + } dev->platform_data = pd; pd->of_netdev = ethernet_dev; @@ -691,7 +701,9 @@ static int dsa_of_probe(struct device *dev) cd = &pd->chip[chip_index]; cd->of_node = child; - cd->host_dev = &mdio_bus->dev; + + /* When assigning the host device, increment its refcount */ + cd->host_dev = get_device(&mdio_bus->dev); sw_addr = of_get_property(child, "reg", NULL); if (!sw_addr) @@ -711,6 +723,12 @@ static int dsa_of_probe(struct device *dev) ret = -EPROBE_DEFER; goto out_free_chip; } + + /* Drop the mdio_bus device ref, replacing the host + * device with the mdio_bus_switch device, keeping + * the refcount from of_mdio_find_bus() above. + */ + put_device(cd->host_dev); cd->host_dev = &mdio_bus_switch->dev; } @@ -744,6 +762,10 @@ static int dsa_of_probe(struct device *dev) } } + /* The individual chips hold their own refcount on the mdio bus, + * so drop ours */ + put_device(&mdio_bus->dev); + return 0; out_free_chip: @@ -751,6 +773,10 @@ out_free_chip: out_free: kfree(pd); dev->platform_data = NULL; +out_put_ethernet: + put_device(ðernet_dev->dev); +out_put_mdio: + put_device(&mdio_bus->dev); return ret; } @@ -762,6 +788,7 @@ static void dsa_of_remove(struct device *dev) return; dsa_of_free_platform_data(pd); + put_device(&pd->of_netdev->dev); kfree(pd); } #else diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index d25efc93d8f1..b6ca0890d018 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -78,7 +78,7 @@ static int trailer_rcv(struct sk_buff *skb, struct net_device *dev, trailer = skb_tail_pointer(skb) - 4; if (trailer[0] != 0x80 || (trailer[1] & 0xf8) != 0x00 || - (trailer[3] & 0xef) != 0x00 || trailer[3] != 0x00) + (trailer[2] & 0xef) != 0x00 || trailer[3] != 0x00) goto out_drop; source_port = trailer[1] & 7; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 61ff5ea31283..01308e6e6127 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -113,6 +113,8 @@ #include <net/arp.h> #include <net/ax25.h> #include <net/netrom.h> +#include <net/dst_metadata.h> +#include <net/ip_tunnels.h> #include <linux/uaccess.h> @@ -296,7 +298,8 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, - const unsigned char *target_hw, struct sk_buff *oskb) + const unsigned char *target_hw, + struct dst_entry *dst) { struct sk_buff *skb; @@ -309,9 +312,7 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip, if (!skb) return; - if (oskb) - skb_dst_copy(skb, oskb); - + skb_dst_set(skb, dst); arp_xmit(skb); } @@ -333,6 +334,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); struct in_device *in_dev; + struct dst_entry *dst = NULL; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); @@ -381,9 +383,10 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } } + if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE)) + dst = dst_clone(skb_dst(skb)); arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, - dst_hw, dev->dev_addr, NULL, - dev->priv_flags & IFF_XMIT_DST_RELEASE ? NULL : skb); + dst_hw, dev->dev_addr, NULL, dst); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) @@ -654,6 +657,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) u16 dev_type = dev->type; int addr_type; struct neighbour *n; + struct dst_entry *reply_dst = NULL; bool is_garp = false; /* arp_rcv below verifies the ARP header and verifies the device @@ -754,13 +758,18 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) * cache. */ + if (arp->ar_op == htons(ARPOP_REQUEST) && skb_metadata_dst(skb)) + reply_dst = (struct dst_entry *) + iptunnel_metadata_reply(skb_metadata_dst(skb), + GFP_ATOMIC); + /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, - dev->dev_addr, sha); + arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, + sha, dev->dev_addr, sha, reply_dst); goto out; } @@ -779,9 +788,10 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, - dev, tip, sha, dev->dev_addr, - sha); + arp_send_dst(ARPOP_REPLY, ETH_P_ARP, + sip, dev, tip, sha, + dev->dev_addr, sha, + reply_dst); neigh_release(n); } } @@ -799,9 +809,10 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED || skb->pkt_type == PACKET_HOST || NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) { - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, - dev, tip, sha, dev->dev_addr, - sha); + arp_send_dst(ARPOP_REPLY, ETH_P_ARP, + sip, dev, tip, sha, + dev->dev_addr, sha, + reply_dst); } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 26d6ffb6d23c..6c2af797f2f9 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1426,7 +1426,7 @@ found: nh->nh_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) continue; - if (!(flp->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif) continue; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 79fe05befcae..e5eb8ac4089d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.flowi4_mark = mark; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; - fl4.flowi4_oif = vrf_master_ifindex(skb->dev) ? : skb->dev->ifindex; + fl4.flowi4_oif = vrf_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) @@ -461,7 +461,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; - fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev) ? : skb_in->dev->ifindex; + fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key(net, fl4); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index bac205136e1c..ba2f90d90cb5 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -685,20 +685,20 @@ void reqsk_queue_hash_req(struct request_sock_queue *queue, req->num_timeout = 0; req->sk = NULL; + setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req); + mod_timer_pinned(&req->rsk_timer, jiffies + timeout); + req->rsk_hash = hash; + /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ smp_wmb(); atomic_set(&req->rsk_refcnt, 2); - setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req); - req->rsk_hash = hash; spin_lock(&queue->syn_wait_lock); req->dl_next = lopt->syn_table[hash]; lopt->syn_table[hash] = req; spin_unlock(&queue->syn_wait_lock); - - mod_timer_pinned(&req->rsk_timer, jiffies + timeout); } EXPORT_SYMBOL(reqsk_queue_hash_req); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index ae22cc24fbe8..c67f9bd7699c 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -123,13 +123,15 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, /* * Step 2: Hash TW into tcp ehash chain. * Notes : - * - tw_refcnt is set to 3 because : + * - tw_refcnt is set to 4 because : * - We have one reference from bhash chain. * - We have one reference from ehash chain. + * - We have one reference from timer. + * - One reference for ourself (our caller will release it). * We can use atomic_set() because prior spin_lock()/spin_unlock() * committed into memory all tw fields. */ - atomic_set(&tw->tw_refcnt, 1 + 1 + 1); + atomic_set(&tw->tw_refcnt, 4); inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ @@ -217,7 +219,7 @@ void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL(inet_twsk_deschedule_put); -void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) +void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) { /* timeout := RTO * 3.5 * @@ -245,12 +247,14 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) */ tw->tw_kill = timeo <= 4*HZ; - if (!mod_timer_pinned(&tw->tw_timer, jiffies + timeo)) { - atomic_inc(&tw->tw_refcnt); + if (!rearm) { + BUG_ON(mod_timer_pinned(&tw->tw_timer, jiffies + timeo)); atomic_inc(&tw->tw_dr->tw_count); + } else { + mod_timer_pending(&tw->tw_timer, jiffies + timeo); } } -EXPORT_SYMBOL_GPL(inet_twsk_schedule); +EXPORT_SYMBOL_GPL(__inet_twsk_schedule); void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 29ed6c5a5185..84dce6a92f93 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -46,12 +46,13 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> +#include <net/dst_metadata.h> int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { - int pkt_len = skb->len; + int pkt_len = skb->len - skb_inner_network_offset(skb); struct iphdr *iph; int err; @@ -119,6 +120,33 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) } EXPORT_SYMBOL_GPL(iptunnel_pull_header); +struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, + gfp_t flags) +{ + struct metadata_dst *res; + struct ip_tunnel_info *dst, *src; + + if (!md || md->u.tun_info.mode & IP_TUNNEL_INFO_TX) + return NULL; + + res = metadata_dst_alloc(0, flags); + if (!res) + return NULL; + + dst = &res->u.tun_info; + src = &md->u.tun_info; + dst->key.tun_id = src->key.tun_id; + if (src->mode & IP_TUNNEL_INFO_IPV6) + memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src, + sizeof(struct in6_addr)); + else + dst->key.u.ipv4.dst = src->key.u.ipv4.src; + dst->mode = src->mode | IP_TUNNEL_INFO_TX; + + return res; +} +EXPORT_SYMBOL_GPL(iptunnel_metadata_reply); + struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool csum_help, int gso_type_mask) @@ -198,8 +226,6 @@ static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { [LWTUNNEL_IP_SRC] = { .type = NLA_U32 }, [LWTUNNEL_IP_TTL] = { .type = NLA_U8 }, [LWTUNNEL_IP_TOS] = { .type = NLA_U8 }, - [LWTUNNEL_IP_SPORT] = { .type = NLA_U16 }, - [LWTUNNEL_IP_DPORT] = { .type = NLA_U16 }, [LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 }, }; @@ -239,12 +265,6 @@ static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, if (tb[LWTUNNEL_IP_TOS]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); - if (tb[LWTUNNEL_IP_SPORT]) - tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP_SPORT]); - - if (tb[LWTUNNEL_IP_DPORT]) - tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP_DPORT]); - if (tb[LWTUNNEL_IP_FLAGS]) tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP_FLAGS]); @@ -266,8 +286,6 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, nla_put_be32(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || - nla_put_u16(skb, LWTUNNEL_IP_SPORT, tun_info->key.tp_src) || - nla_put_u16(skb, LWTUNNEL_IP_DPORT, tun_info->key.tp_dst) || nla_put_u16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; @@ -281,8 +299,6 @@ static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) + nla_total_size(4) /* LWTUNNEL_IP_SRC */ + nla_total_size(1) /* LWTUNNEL_IP_TOS */ + nla_total_size(1) /* LWTUNNEL_IP_TTL */ - + nla_total_size(2) /* LWTUNNEL_IP_SPORT */ - + nla_total_size(2) /* LWTUNNEL_IP_DPORT */ + nla_total_size(2); /* LWTUNNEL_IP_FLAGS */ } @@ -305,8 +321,6 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { [LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) }, [LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 }, [LWTUNNEL_IP6_TC] = { .type = NLA_U8 }, - [LWTUNNEL_IP6_SPORT] = { .type = NLA_U16 }, - [LWTUNNEL_IP6_DPORT] = { .type = NLA_U16 }, [LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 }, }; @@ -346,12 +360,6 @@ static int ip6_tun_build_state(struct net_device *dev, struct nlattr *attr, if (tb[LWTUNNEL_IP6_TC]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); - if (tb[LWTUNNEL_IP6_SPORT]) - tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP6_SPORT]); - - if (tb[LWTUNNEL_IP6_DPORT]) - tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP6_DPORT]); - if (tb[LWTUNNEL_IP6_FLAGS]) tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP6_FLAGS]); @@ -373,8 +381,6 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.ttl) || - nla_put_u16(skb, LWTUNNEL_IP6_SPORT, tun_info->key.tp_src) || - nla_put_u16(skb, LWTUNNEL_IP6_DPORT, tun_info->key.tp_dst) || nla_put_u16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; @@ -388,8 +394,6 @@ static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate) + nla_total_size(16) /* LWTUNNEL_IP6_SRC */ + nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */ + nla_total_size(1) /* LWTUNNEL_IP6_TC */ - + nla_total_size(2) /* LWTUNNEL_IP6_SPORT */ - + nla_total_size(2) /* LWTUNNEL_IP6_DPORT */ + nla_total_size(2); /* LWTUNNEL_IP6_FLAGS */ } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f7afcba8b1a1..6bab84503cd9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2036,6 +2036,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) struct fib_result res; struct rtable *rth; int orig_oif; + int err = -ENETUNREACH; res.tclassid = 0; res.fi = NULL; @@ -2144,7 +2145,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) goto make_route; } - if (fib_lookup(net, fl4, &res, 0)) { + err = fib_lookup(net, fl4, &res, 0); + if (err) { res.fi = NULL; res.table = NULL; if (fl4->flowi4_oif) { @@ -2172,7 +2174,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) res.type = RTN_UNICAST; goto make_route; } - rth = ERR_PTR(-ENETUNREACH); + rth = ERR_PTR(err); goto out; } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index c6ded6b2a79f..448c2615fece 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -154,14 +154,20 @@ static void bictcp_init(struct sock *sk) 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); + u32 now = tcp_time_stamp; + s32 delta; + + delta = now - tcp_sk(sk)->lsndtime; /* We were application limited (idle) for a while. * Shift epoch_start to keep cwnd growth to cubic curve. */ - if (ca->epoch_start && delta > 0) + if (ca->epoch_start && delta > 0) { ca->epoch_start += delta; + if (after(ca->epoch_start, now)) + ca->epoch_start = now; + } return; } } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e0a87c238882..e4fe62b6b106 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -162,9 +162,9 @@ kill_with_rst: if (tcp_death_row.sysctl_tw_recycle && tcptw->tw_ts_recent_stamp && tcp_tw_remember_stamp(tw)) - inet_twsk_schedule(tw, tw->tw_timeout); + inet_twsk_reschedule(tw, tw->tw_timeout); else - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return TCP_TW_ACK; } @@ -201,7 +201,7 @@ kill: return TCP_TW_SUCCESS; } } - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; @@ -251,7 +251,7 @@ kill: * Do not reschedule in the last case. */ if (paws_reject || th->ack) - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return tcp_timewait_check_oow_rate_limit( tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT); @@ -322,9 +322,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } while (0); #endif - /* Linkage updates. */ - __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); - /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) timeo = rto; @@ -338,6 +335,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } inet_twsk_schedule(tw, timeo); + /* Linkage updates. */ + __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 53ce6cf55598..9e53dd9bfcad 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2893,6 +2893,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); + skb_mstamp_get(&skb->skb_mstamp); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c0a15e7f359f..f7d1d5e19e95 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1024,7 +1024,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (netif_index_is_vrf(net, ipc.oif)) { flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, - (flow_flags | FLOWI_FLAG_VRFSRC), + (flow_flags | FLOWI_FLAG_VRFSRC | + FLOWI_FLAG_SKIP_NH_OIF), faddr, saddr, dport, inet->inet_sport); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 671011055ad5..0304d1680ca2 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -33,6 +33,8 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, if (saddr) fl4->saddr = saddr->a4; + fl4->flowi4_flags = FLOWI_FLAG_SKIP_NH_OIF; + rt = __ip_route_output_key(net, fl4); if (!IS_ERR(rt)) return &rt->dst; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 759d28ad16b7..c8380f1876f1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5132,13 +5132,12 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) rt = addrconf_get_prefix_route(&ifp->peer_addr, 128, ifp->idev->dev, 0, 0); - if (rt && ip6_del_rt(rt)) - dst_free(&rt->dst); + if (rt) + ip6_del_rt(rt); } dst_hold(&ifp->rt->dst); - if (ip6_del_rt(ifp->rt)) - dst_free(&ifp->rt->dst); + ip6_del_rt(ifp->rt); rt_genid_bump_ipv6(net); break; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 418d9823692b..7d2e0023c72d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -155,6 +155,11 @@ static void node_free(struct fib6_node *fn) kmem_cache_free(fib6_node_kmem, fn); } +static void rt6_rcu_free(struct rt6_info *rt) +{ + call_rcu(&rt->dst.rcu_head, dst_rcu_free); +} + static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) { int cpu; @@ -169,7 +174,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); pcpu_rt = *ppcpu_rt; if (pcpu_rt) { - dst_free(&pcpu_rt->dst); + rt6_rcu_free(pcpu_rt); *ppcpu_rt = NULL; } } @@ -181,7 +186,7 @@ static void rt6_release(struct rt6_info *rt) { if (atomic_dec_and_test(&rt->rt6i_ref)) { rt6_free_pcpu(rt); - dst_free(&rt->dst); + rt6_rcu_free(rt); } } @@ -846,7 +851,7 @@ add: *ins = rt; rt->rt6i_node = fn; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); + inet6_rt_notify(RTM_NEWROUTE, rt, info, 0); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { @@ -872,7 +877,7 @@ add: rt->rt6i_node = fn; rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); + inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; @@ -933,6 +938,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, int replace_required = 0; int sernum = fib6_new_sernum(info->nl_net); + if (WARN_ON_ONCE((rt->dst.flags & DST_NOCACHE) && + !atomic_read(&rt->dst.__refcnt))) + return -EINVAL; + if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) allow_create = 0; @@ -1025,6 +1034,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fib6_start_gc(info->nl_net, rt); if (!(rt->rt6i_flags & RTF_CACHE)) fib6_prune_clones(info->nl_net, pn); + rt->dst.flags &= ~DST_NOCACHE; } out: @@ -1049,7 +1059,8 @@ out: atomic_inc(&pn->leaf->rt6i_ref); } #endif - dst_free(&rt->dst); + if (!(rt->dst.flags & DST_NOCACHE)) + dst_free(&rt->dst); } return err; @@ -1060,7 +1071,8 @@ out: st_failure: if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) fib6_repair_tree(info->nl_net, fn); - dst_free(&rt->dst); + if (!(rt->dst.flags & DST_NOCACHE)) + dst_free(&rt->dst); return err; #endif } @@ -1410,7 +1422,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, fib6_purge_rt(rt, fn, net); - inet6_rt_notify(RTM_DELROUTE, rt, info); + inet6_rt_notify(RTM_DELROUTE, rt, info, 0); rt6_release(rt); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4038c694ec03..3c7b9310b33f 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -404,13 +404,13 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ipv6_tlv_tnl_enc_lim *tel; __u32 mtu; case ICMPV6_DEST_UNREACH: - net_warn_ratelimited("%s: Path to destination invalid or inactive!\n", - t->parms.name); + net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", + t->parms.name); break; case ICMPV6_TIME_EXCEED: if (code == ICMPV6_EXC_HOPLIMIT) { - net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", - t->parms.name); + net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", + t->parms.name); } break; case ICMPV6_PARAMPROB: @@ -421,12 +421,12 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (teli && teli == be32_to_cpu(info) - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { - net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", - t->parms.name); + net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", + t->parms.name); } } else { - net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n", - t->parms.name); + net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", + t->parms.name); } break; case ICMPV6_PKT_TOOBIG: @@ -634,20 +634,20 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, } if (!fl6->flowi6_mark) - dst = ip6_tnl_dst_check(tunnel); + dst = ip6_tnl_dst_get(tunnel); if (!dst) { - ndst = ip6_route_output(net, NULL, fl6); + dst = ip6_route_output(net, NULL, fl6); - if (ndst->error) + if (dst->error) goto tx_err_link_failure; - ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0); - if (IS_ERR(ndst)) { - err = PTR_ERR(ndst); - ndst = NULL; + dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; goto tx_err_link_failure; } - dst = ndst; + ndst = dst; } tdev = dst->dev; @@ -702,12 +702,9 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb = new_skb; } - if (fl6->flowi6_mark) { - skb_dst_set(skb, dst); - ndst = NULL; - } else { - skb_dst_set_noref(skb, dst); - } + if (!fl6->flowi6_mark && ndst) + ip6_tnl_dst_set(tunnel, ndst); + skb_dst_set(skb, dst); proto = NEXTHDR_GRE; if (encap_limit >= 0) { @@ -762,14 +759,12 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_set_inner_protocol(skb, protocol); ip6tunnel_xmit(NULL, skb, dev); - if (ndst) - ip6_tnl_dst_store(tunnel, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(ndst); + dst_release(dst); return err; } @@ -1223,6 +1218,9 @@ static const struct net_device_ops ip6gre_netdev_ops = { static void ip6gre_dev_free(struct net_device *dev) { + struct ip6_tnl *t = netdev_priv(dev); + + ip6_tnl_dst_destroy(t); free_percpu(dev->tstats); free_netdev(dev); } @@ -1245,9 +1243,10 @@ static void ip6gre_tunnel_setup(struct net_device *dev) netif_keep_dst(dev); } -static int ip6gre_tunnel_init(struct net_device *dev) +static int ip6gre_tunnel_init_common(struct net_device *dev) { struct ip6_tnl *tunnel; + int ret; tunnel = netdev_priv(dev); @@ -1255,16 +1254,37 @@ static int ip6gre_tunnel_init(struct net_device *dev) tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + ret = ip6_tnl_dst_init(tunnel); + if (ret) { + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; + } + + return 0; +} + +static int ip6gre_tunnel_init(struct net_device *dev) +{ + struct ip6_tnl *tunnel; + int ret; + + ret = ip6gre_tunnel_init_common(dev); + if (ret) + return ret; + + tunnel = netdev_priv(dev); + memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr)); if (ipv6_addr_any(&tunnel->parms.raddr)) dev->header_ops = &ip6gre_header_ops; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - return 0; } @@ -1460,19 +1480,16 @@ static void ip6gre_netlink_parms(struct nlattr *data[], static int ip6gre_tap_init(struct net_device *dev) { struct ip6_tnl *tunnel; + int ret; - tunnel = netdev_priv(dev); + ret = ip6gre_tunnel_init_common(dev); + if (ret) + return ret; - tunnel->dev = dev; - tunnel->net = dev_net(dev); - strcpy(tunnel->parms.name, dev->name); + tunnel = netdev_priv(dev); ip6gre_tnl_link_config(tunnel, 1); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 60c565309d0a..a598fe2c0849 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -600,20 +600,22 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr); + hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { int first_len = skb_pagelen(skb); struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || - skb_cloned(skb)) + skb_cloned(skb) || + skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || - skb_headroom(frag) < hlen) + skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr))) goto slow_path_clean; /* Partially cloned skb? */ @@ -630,8 +632,6 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, err = 0; offset = 0; - frag = skb_shinfo(skb)->frag_list; - skb_frag_list_init(skb); /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; @@ -639,8 +639,11 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, if (!tmp_hdr) { IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); - return -ENOMEM; + err = -ENOMEM; + goto fail; } + frag = skb_shinfo(skb)->frag_list; + skb_frag_list_init(skb); __skb_pull(skb, hlen); fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr)); @@ -737,7 +740,6 @@ slow_path: */ *prevhdr = NEXTHDR_FRAGMENT; - hroom = LL_RESERVED_SPACE(rt->dst.dev); troom = rt->dst.dev->needed_tailroom; /* diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b0ab420612bc..eabffbb89795 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -126,36 +126,92 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) * Locking : hash tables are protected by RCU and RTNL */ -struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) +static void ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst, + struct dst_entry *dst) { - struct dst_entry *dst = t->dst_cache; + write_seqlock_bh(&idst->lock); + dst_release(rcu_dereference_protected( + idst->dst, + lockdep_is_held(&idst->lock.lock))); + if (dst) { + dst_hold(dst); + idst->cookie = rt6_get_cookie((struct rt6_info *)dst); + } else { + idst->cookie = 0; + } + rcu_assign_pointer(idst->dst, dst); + write_sequnlock_bh(&idst->lock); +} + +struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t) +{ + struct ip6_tnl_dst *idst; + struct dst_entry *dst; + unsigned int seq; + u32 cookie; - if (dst && dst->obsolete && - !dst->ops->check(dst, t->dst_cookie)) { - t->dst_cache = NULL; + idst = raw_cpu_ptr(t->dst_cache); + + rcu_read_lock(); + do { + seq = read_seqbegin(&idst->lock); + dst = rcu_dereference(idst->dst); + cookie = idst->cookie; + } while (read_seqretry(&idst->lock, seq)); + + if (dst && !atomic_inc_not_zero(&dst->__refcnt)) + dst = NULL; + rcu_read_unlock(); + + if (dst && dst->obsolete && !dst->ops->check(dst, cookie)) { + ip6_tnl_per_cpu_dst_set(idst, NULL); dst_release(dst); - return NULL; + dst = NULL; } - return dst; } -EXPORT_SYMBOL_GPL(ip6_tnl_dst_check); +EXPORT_SYMBOL_GPL(ip6_tnl_dst_get); void ip6_tnl_dst_reset(struct ip6_tnl *t) { - dst_release(t->dst_cache); - t->dst_cache = NULL; + int i; + + for_each_possible_cpu(i) + ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), NULL); } EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); -void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) +void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst) +{ + ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), dst); + +} +EXPORT_SYMBOL_GPL(ip6_tnl_dst_set); + +void ip6_tnl_dst_destroy(struct ip6_tnl *t) { - struct rt6_info *rt = (struct rt6_info *) dst; - t->dst_cookie = rt6_get_cookie(rt); - dst_release(t->dst_cache); - t->dst_cache = dst; + if (!t->dst_cache) + return; + + ip6_tnl_dst_reset(t); + free_percpu(t->dst_cache); } -EXPORT_SYMBOL_GPL(ip6_tnl_dst_store); +EXPORT_SYMBOL_GPL(ip6_tnl_dst_destroy); + +int ip6_tnl_dst_init(struct ip6_tnl *t) +{ + int i; + + t->dst_cache = alloc_percpu(struct ip6_tnl_dst); + if (!t->dst_cache) + return -ENOMEM; + + for_each_possible_cpu(i) + seqlock_init(&per_cpu_ptr(t->dst_cache, i)->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(ip6_tnl_dst_init); /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses @@ -271,6 +327,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) static void ip6_dev_free(struct net_device *dev) { + struct ip6_tnl *t = netdev_priv(dev); + + ip6_tnl_dst_destroy(t); free_percpu(dev->tstats); free_netdev(dev); } @@ -510,14 +569,14 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, struct ipv6_tlv_tnl_enc_lim *tel; __u32 mtu; case ICMPV6_DEST_UNREACH: - net_warn_ratelimited("%s: Path to destination invalid or inactive!\n", - t->parms.name); + net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", + t->parms.name); rel_msg = 1; break; case ICMPV6_TIME_EXCEED: if ((*code) == ICMPV6_EXC_HOPLIMIT) { - net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", - t->parms.name); + net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } break; @@ -529,13 +588,13 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, if (teli && teli == *info - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { - net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", - t->parms.name); + net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } } else { - net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n", - t->parms.name); + net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", + t->parms.name); } break; case ICMPV6_PKT_TOOBIG: @@ -1010,23 +1069,23 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } else if (!fl6->flowi6_mark) - dst = ip6_tnl_dst_check(t); + dst = ip6_tnl_dst_get(t); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) goto tx_err_link_failure; if (!dst) { - ndst = ip6_route_output(net, NULL, fl6); + dst = ip6_route_output(net, NULL, fl6); - if (ndst->error) + if (dst->error) goto tx_err_link_failure; - ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0); - if (IS_ERR(ndst)) { - err = PTR_ERR(ndst); - ndst = NULL; + dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; goto tx_err_link_failure; } - dst = ndst; + ndst = dst; } tdev = dst->dev; @@ -1072,12 +1131,11 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, consume_skb(skb); skb = new_skb; } - if (fl6->flowi6_mark) { - skb_dst_set(skb, dst); - ndst = NULL; - } else { - skb_dst_set_noref(skb, dst); - } + + if (!fl6->flowi6_mark && ndst) + ip6_tnl_dst_set(t, ndst); + skb_dst_set(skb, dst); + skb->transport_header = skb->network_header; proto = fl6->flowi6_proto; @@ -1101,14 +1159,12 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; ip6tunnel_xmit(NULL, skb, dev); - if (ndst) - ip6_tnl_dst_store(t, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(ndst); + dst_release(dst); return err; } @@ -1573,12 +1629,21 @@ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); + int ret; t->dev = dev; t->net = dev_net(dev); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; + + ret = ip6_tnl_dst_init(t); + if (ret) { + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; + } + return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 118f8fa1a809..6fbf6fdde7e7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1298,8 +1298,7 @@ static void ip6_link_failure(struct sk_buff *skb) if (rt) { if (rt->rt6i_flags & RTF_CACHE) { dst_hold(&rt->dst); - if (ip6_del_rt(rt)) - dst_free(&rt->dst); + ip6_del_rt(rt); } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; } @@ -1862,9 +1861,11 @@ int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret) rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: + case RTN_UNREACHABLE: default: rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN - : -ENETUNREACH; + : (cfg->fc_type == RTN_UNREACHABLE) + ? -EHOSTUNREACH : -ENETUNREACH; rt->dst.output = ip6_pkt_discard_out; rt->dst.input = ip6_pkt_discard; break; @@ -2004,7 +2005,8 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) struct fib6_table *table; struct net *net = dev_net(rt->dst.dev); - if (rt == net->ipv6.ip6_null_entry) { + if (rt == net->ipv6.ip6_null_entry || + rt->dst.flags & DST_NOCACHE) { err = -ENOENT; goto out; } @@ -2491,6 +2493,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); + rt->dst.flags |= DST_NOCACHE; atomic_set(&rt->dst.__refcnt, 1); @@ -3279,7 +3282,8 @@ errout: return err; } -void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) +void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, + unsigned int nlm_flags) { struct sk_buff *skb; struct net *net = info->nl_net; @@ -3294,7 +3298,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, - event, info->portid, seq, 0, 0, 0); + event, info->portid, seq, 0, 0, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 17b1fe961c5d..7a77a1470f25 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2474,6 +2474,7 @@ static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, bss_conf->cqm_rssi_thold = rssi_thold; bss_conf->cqm_rssi_hyst = rssi_hyst; + sdata->u.mgd.last_cqm_event_signal = 0; /* tell the driver upon association, unless already associated */ if (sdata->u.mgd.associated && @@ -2518,15 +2519,17 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, continue; for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) { - if (~sdata->rc_rateidx_mcs_mask[i][j]) + if (~sdata->rc_rateidx_mcs_mask[i][j]) { sdata->rc_has_mcs_mask[i] = true; + break; + } + } - if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) + for (j = 0; j < NL80211_VHT_NSS_MAX; j++) { + if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) { sdata->rc_has_vht_mcs_mask[i] = true; - - if (sdata->rc_has_mcs_mask[i] && - sdata->rc_has_vht_mcs_mask[i]) break; + } } } diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 675d12c69e32..a5d41dfa9f05 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -107,12 +107,17 @@ EXPORT_SYMBOL(nf_log_register); void nf_log_unregister(struct nf_logger *logger) { + const struct nf_logger *log; int i; mutex_lock(&nf_log_mutex); - for (i = 0; i < NFPROTO_NUMPROTO; i++) - RCU_INIT_POINTER(loggers[i][logger->type], NULL); + for (i = 0; i < NFPROTO_NUMPROTO; i++) { + log = nft_log_dereference(loggers[i][logger->type]); + if (log == logger) + RCU_INIT_POINTER(loggers[i][logger->type], NULL); + } mutex_unlock(&nf_log_mutex); + synchronize_rcu(); } EXPORT_SYMBOL(nf_log_unregister); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 66def315eb56..9c8fab00164b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -619,6 +619,13 @@ struct nft_xt { static struct nft_expr_type nft_match_type; +static bool nft_match_cmp(const struct xt_match *match, + const char *name, u32 rev, u32 family) +{ + return strcmp(match->name, name) == 0 && match->revision == rev && + (match->family == NFPROTO_UNSPEC || match->family == family); +} + static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -626,7 +633,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, struct nft_xt *nft_match; struct xt_match *match; char *mt_name; - __u32 rev, family; + u32 rev, family; if (tb[NFTA_MATCH_NAME] == NULL || tb[NFTA_MATCH_REV] == NULL || @@ -641,8 +648,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, list_for_each_entry(nft_match, &nft_match_list, head) { struct xt_match *match = nft_match->ops.data; - if (strcmp(match->name, mt_name) == 0 && - match->revision == rev && match->family == family) { + if (nft_match_cmp(match, mt_name, rev, family)) { if (!try_module_get(match->me)) return ERR_PTR(-ENOENT); @@ -693,6 +699,13 @@ static LIST_HEAD(nft_target_list); static struct nft_expr_type nft_target_type; +static bool nft_target_cmp(const struct xt_target *tg, + const char *name, u32 rev, u32 family) +{ + return strcmp(tg->name, name) == 0 && tg->revision == rev && + (tg->family == NFPROTO_UNSPEC || tg->family == family); +} + static const struct nft_expr_ops * nft_target_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -700,7 +713,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, struct nft_xt *nft_target; struct xt_target *target; char *tg_name; - __u32 rev, family; + u32 rev, family; if (tb[NFTA_TARGET_NAME] == NULL || tb[NFTA_TARGET_REV] == NULL || @@ -715,8 +728,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, list_for_each_entry(nft_target, &nft_target_list, head) { struct xt_target *target = nft_target->ops.data; - if (strcmp(target->name, tg_name) == 0 && - target->revision == rev && target->family == family) { + if (nft_target_cmp(target, tg_name, rev, family)) { if (!try_module_get(target->me)) return ERR_PTR(-ENOENT); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 7f86d3b55060..8f060d7f9a0e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -125,6 +125,24 @@ static inline u32 netlink_group_mask(u32 group) return group ? 1 << (group - 1) : 0; } +static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, + gfp_t gfp_mask) +{ + unsigned int len = skb_end_offset(skb); + struct sk_buff *new; + + new = alloc_skb(len, gfp_mask); + if (new == NULL) + return NULL; + + NETLINK_CB(new).portid = NETLINK_CB(skb).portid; + NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; + NETLINK_CB(new).creds = NETLINK_CB(skb).creds; + + memcpy(skb_put(new, len), skb->data, len); + return new; +} + int netlink_add_tap(struct netlink_tap *nt) { if (unlikely(nt->dev->type != ARPHRD_NETLINK)) @@ -206,7 +224,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, int ret = -ENOMEM; dev_hold(dev); - nskb = skb_clone(skb, GFP_ATOMIC); + + if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head)) + nskb = netlink_to_full_skb(skb, GFP_ATOMIC); + else + nskb = skb_clone(skb, GFP_ATOMIC); if (nskb) { nskb->dev = dev; nskb->protocol = htons((u16) sk->sk_protocol); @@ -279,11 +301,6 @@ static void netlink_rcv_wake(struct sock *sk) } #ifdef CONFIG_NETLINK_MMAP -static bool netlink_skb_is_mmaped(const struct sk_buff *skb) -{ - return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED; -} - static bool netlink_rx_is_mmaped(struct sock *sk) { return nlk_sk(sk)->rx_ring.pg_vec != NULL; @@ -846,7 +863,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb) } #else /* CONFIG_NETLINK_MMAP */ -#define netlink_skb_is_mmaped(skb) false #define netlink_rx_is_mmaped(sk) false #define netlink_tx_is_mmaped(sk) false #define netlink_mmap sock_no_mmap @@ -1094,8 +1110,8 @@ static int netlink_insert(struct sock *sk, u32 portid) lock_sock(sk); - err = -EBUSY; - if (nlk_sk(sk)->portid) + err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY; + if (nlk_sk(sk)->bound) goto err; err = -ENOMEM; @@ -1115,10 +1131,14 @@ static int netlink_insert(struct sock *sk, u32 portid) err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; - nlk_sk(sk)->portid = 0; sock_put(sk); + goto err; } + /* We need to ensure that the socket is hashed and visible. */ + smp_wmb(); + nlk_sk(sk)->bound = portid; + err: release_sock(sk); return err; @@ -1503,6 +1523,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err; long unsigned int groups = nladdr->nl_groups; + bool bound; if (addr_len < sizeof(struct sockaddr_nl)) return -EINVAL; @@ -1519,9 +1540,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } - if (nlk->portid) + bound = nlk->bound; + if (bound) { + /* Ensure nlk->portid is up-to-date. */ + smp_rmb(); + if (nladdr->nl_pid != nlk->portid) return -EINVAL; + } if (nlk->netlink_bind && groups) { int group; @@ -1537,7 +1563,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, } } - if (!nlk->portid) { + /* No need for barriers here as we return to user-space without + * using any of the bound attributes. + */ + if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); @@ -1585,7 +1614,10 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; - if (!nlk->portid) + /* No need for barriers here as we return to user-space without + * using any of the bound attributes. + */ + if (!nlk->bound) err = netlink_autobind(sock); if (err == 0) { @@ -2426,10 +2458,13 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) dst_group = nlk->dst_group; } - if (!nlk->portid) { + if (!nlk->bound) { err = netlink_autobind(sock); if (err) goto out; + } else { + /* Ensure nlk is hashed and visible. */ + smp_rmb(); } /* It's a really convoluted way for userland to ask for mmaped diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 89008405d6b4..14437d9b1965 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -35,6 +35,7 @@ struct netlink_sock { unsigned long state; size_t max_recvmsg_len; wait_queue_head_t wait; + bool bound; bool cb_running; struct netlink_callback cb; struct mutex *cb_mutex; @@ -59,6 +60,15 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk) return container_of(sk, struct netlink_sock, sk); } +static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb) +{ +#ifdef CONFIG_NETLINK_MMAP + return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED; +#else + return false; +#endif /* CONFIG_NETLINK_MMAP */ +} + struct netlink_table { struct rhashtable hash; struct hlist_head mc_list; diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 2a071f470d57..d143aa9f6654 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -5,7 +5,8 @@ config OPENVSWITCH tristate "Open vSwitch" depends on INET - depends on (!NF_CONNTRACK || NF_CONNTRACK) + depends on !NF_CONNTRACK || \ + (NF_CONNTRACK && (!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6)) select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index aaf5cbd6d9ae..eb759e3a88ca 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -275,13 +275,15 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto) case NFPROTO_IPV6: { u8 nexthdr = ipv6_hdr(skb)->nexthdr; __be16 frag_off; + int ofs; - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), - &nexthdr, &frag_off); - if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { pr_debug("proto header not found\n"); return NF_ACCEPT; } + protoff = ofs; break; } default: diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 2913594c5123..a75828091e21 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -951,7 +951,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) if (error) goto err_kfree_flow; - ovs_flow_mask_key(&new_flow->key, &key, &mask); + ovs_flow_mask_key(&new_flow->key, &key, true, &mask); /* Extract flow identifier. */ error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], @@ -1079,7 +1079,7 @@ static struct sw_flow_actions *get_flow_actions(struct net *net, struct sw_flow_key masked_key; int error; - ovs_flow_mask_key(&masked_key, key, mask); + ovs_flow_mask_key(&masked_key, key, true, mask); error = ovs_nla_copy_actions(net, a, &masked_key, &acts, log); if (error) { OVS_NLERR(log, diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index c92d6a262bc5..5c030a4d7338 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -57,6 +57,7 @@ struct ovs_len_tbl { }; #define OVS_ATTR_NESTED -1 +#define OVS_ATTR_VARIABLE -2 static void update_range(struct sw_flow_match *match, size_t offset, size_t size, bool is_mask) @@ -304,6 +305,10 @@ size_t ovs_key_attr_size(void) + nla_total_size(28); /* OVS_KEY_ATTR_ND */ } +static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = { + [OVS_VXLAN_EXT_GBP] = { .len = sizeof(u32) }, +}; + static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = { [OVS_TUNNEL_KEY_ATTR_ID] = { .len = sizeof(u64) }, [OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = { .len = sizeof(u32) }, @@ -315,8 +320,9 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] [OVS_TUNNEL_KEY_ATTR_TP_SRC] = { .len = sizeof(u16) }, [OVS_TUNNEL_KEY_ATTR_TP_DST] = { .len = sizeof(u16) }, [OVS_TUNNEL_KEY_ATTR_OAM] = { .len = 0 }, - [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_NESTED }, - [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED }, + [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE }, + [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED, + .next = ovs_vxlan_ext_key_lens }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@ -349,6 +355,13 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) }, }; +static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) +{ + return expected_len == attr_len || + expected_len == OVS_ATTR_NESTED || + expected_len == OVS_ATTR_VARIABLE; +} + static bool is_all_zero(const u8 *fp, size_t size) { int i; @@ -388,7 +401,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, } expected_len = ovs_key_lens[type].len; - if (nla_len(nla) != expected_len && expected_len != OVS_ATTR_NESTED) { + if (!check_attr_len(nla_len(nla), expected_len)) { OVS_NLERR(log, "Key %d has unexpected len %d expected %d", type, nla_len(nla), expected_len); return -EINVAL; @@ -473,29 +486,50 @@ static int genev_tun_opt_from_nlattr(const struct nlattr *a, return 0; } -static const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = { - [OVS_VXLAN_EXT_GBP] = { .type = NLA_U32 }, -}; - -static int vxlan_tun_opt_from_nlattr(const struct nlattr *a, +static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) { - struct nlattr *tb[OVS_VXLAN_EXT_MAX+1]; + struct nlattr *a; + int rem; unsigned long opt_key_offset; struct vxlan_metadata opts; - int err; BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); - err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy); - if (err < 0) - return err; - memset(&opts, 0, sizeof(opts)); + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); - if (tb[OVS_VXLAN_EXT_GBP]) - opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]); + if (type > OVS_VXLAN_EXT_MAX) { + OVS_NLERR(log, "VXLAN extension %d out of range max %d", + type, OVS_VXLAN_EXT_MAX); + return -EINVAL; + } + + if (!check_attr_len(nla_len(a), + ovs_vxlan_ext_key_lens[type].len)) { + OVS_NLERR(log, "VXLAN extension %d has unexpected len %d expected %d", + type, nla_len(a), + ovs_vxlan_ext_key_lens[type].len); + return -EINVAL; + } + + switch (type) { + case OVS_VXLAN_EXT_GBP: + opts.gbp = nla_get_u32(a); + break; + default: + OVS_NLERR(log, "Unknown VXLAN extension attribute %d", + type); + return -EINVAL; + } + } + if (rem) { + OVS_NLERR(log, "VXLAN extension message has %d unknown bytes.", + rem); + return -EINVAL; + } if (!is_mask) SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false); @@ -528,8 +562,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, return -EINVAL; } - if (ovs_tunnel_key_lens[type].len != nla_len(a) && - ovs_tunnel_key_lens[type].len != OVS_ATTR_NESTED) { + if (!check_attr_len(nla_len(a), + ovs_tunnel_key_lens[type].len)) { OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d", type, nla_len(a), ovs_tunnel_key_lens[type].len); return -EINVAL; @@ -1052,10 +1086,13 @@ static void nlattr_set(struct nlattr *attr, u8 val, /* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { - if (tbl && tbl[nla_type(nla)].len == OVS_ATTR_NESTED) - nlattr_set(nla, val, tbl[nla_type(nla)].next); - else + if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) { + if (tbl[nla_type(nla)].next) + tbl = tbl[nla_type(nla)].next; + nlattr_set(nla, val, tbl); + } else { memset(nla_data(nla), val, nla_len(nla)); + } } } @@ -1922,8 +1959,7 @@ static int validate_set(const struct nlattr *a, key_len /= 2; if (key_type > OVS_KEY_ATTR_MAX || - (ovs_key_lens[key_type].len != key_len && - ovs_key_lens[key_type].len != OVS_ATTR_NESTED)) + !check_attr_len(key_len, ovs_key_lens[key_type].len)) return -EINVAL; if (masked && !validate_masked(nla_data(ovs_key), key_len)) diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index d22d8e948d0f..f2ea83ba4763 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -57,20 +57,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range) } void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, - const struct sw_flow_mask *mask) + bool full, const struct sw_flow_mask *mask) { - const long *m = (const long *)((const u8 *)&mask->key + - mask->range.start); - const long *s = (const long *)((const u8 *)src + - mask->range.start); - long *d = (long *)((u8 *)dst + mask->range.start); + int start = full ? 0 : mask->range.start; + int len = full ? sizeof *dst : range_n_bytes(&mask->range); + const long *m = (const long *)((const u8 *)&mask->key + start); + const long *s = (const long *)((const u8 *)src + start); + long *d = (long *)((u8 *)dst + start); int i; - /* The memory outside of the 'mask->range' are not set since - * further operations on 'dst' only uses contents within - * 'mask->range'. + /* If 'full' is true then all of 'dst' is fully initialized. Otherwise, + * if 'full' is false the memory outside of the 'mask->range' is left + * uninitialized. This can be used as an optimization when further + * operations on 'dst' only use contents within 'mask->range'. */ - for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long)) + for (i = 0; i < len; i += sizeof(long)) *d++ = *s++ & *m++; } @@ -475,7 +476,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, u32 hash; struct sw_flow_key masked_key; - ovs_flow_mask_key(&masked_key, unmasked, mask); + ovs_flow_mask_key(&masked_key, unmasked, false, mask); hash = flow_hash(&masked_key, &mask->range); head = find_bucket(ti, hash); hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) { diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 616eda10d955..2dd9900f533d 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -86,5 +86,5 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *, bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *); void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, - const struct sw_flow_mask *mask); + bool full, const struct sw_flow_mask *mask); #endif /* flow_table.h */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 7b8e39a22387..aa4b15c35884 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -230,6 +230,8 @@ struct packet_skb_cb { } sa; }; +#define vio_le() virtio_legacy_is_little_endian() + #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) #define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) @@ -2680,15 +2682,15 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && - (__virtio16_to_cpu(false, vnet_hdr.csum_start) + - __virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2 > - __virtio16_to_cpu(false, vnet_hdr.hdr_len))) - vnet_hdr.hdr_len = __cpu_to_virtio16(false, - __virtio16_to_cpu(false, vnet_hdr.csum_start) + - __virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2); + (__virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) + + __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2 > + __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len))) + vnet_hdr.hdr_len = __cpu_to_virtio16(vio_le(), + __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) + + __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2); err = -EINVAL; - if (__virtio16_to_cpu(false, vnet_hdr.hdr_len) > len) + if (__virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len) > len) goto out_unlock; if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) { @@ -2731,7 +2733,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, - __virtio16_to_cpu(false, vnet_hdr.hdr_len), + __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len), msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; @@ -2778,8 +2780,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (po->has_vnet_hdr) { if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { - u16 s = __virtio16_to_cpu(false, vnet_hdr.csum_start); - u16 o = __virtio16_to_cpu(false, vnet_hdr.csum_offset); + u16 s = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start); + u16 o = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset); if (!skb_partial_csum_set(skb, s, o)) { err = -EINVAL; goto out_free; @@ -2787,7 +2789,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) } skb_shinfo(skb)->gso_size = - __virtio16_to_cpu(false, vnet_hdr.gso_size); + __virtio16_to_cpu(vio_le(), vnet_hdr.gso_size); skb_shinfo(skb)->gso_type = gso_type; /* Header must be checked, and gso_segs computed. */ @@ -3161,9 +3163,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* This is a hint as to how much should be linear. */ vnet_hdr.hdr_len = - __cpu_to_virtio16(false, skb_headlen(skb)); + __cpu_to_virtio16(vio_le(), skb_headlen(skb)); vnet_hdr.gso_size = - __cpu_to_virtio16(false, sinfo->gso_size); + __cpu_to_virtio16(vio_le(), sinfo->gso_size); if (sinfo->gso_type & SKB_GSO_TCPV4) vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) @@ -3181,9 +3183,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (skb->ip_summed == CHECKSUM_PARTIAL) { vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - vnet_hdr.csum_start = __cpu_to_virtio16(false, + vnet_hdr.csum_start = __cpu_to_virtio16(vio_le(), skb_checksum_start_offset(skb)); - vnet_hdr.csum_offset = __cpu_to_virtio16(false, + vnet_hdr.csum_offset = __cpu_to_virtio16(vio_le(), skb->csum_offset); } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 715e01e5910a..f23a3b68bba6 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -33,7 +33,6 @@ struct fw_head { u32 mask; - bool mask_set; struct fw_filter __rcu *ht[HTSIZE]; struct rcu_head rcu; }; @@ -84,7 +83,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, } } } else { - /* old method */ + /* Old method: classify the packet using its skb mark. */ if (id && (TC_H_MAJ(id) == 0 || !(TC_H_MAJ(id ^ tp->q->handle)))) { res->classid = id; @@ -114,14 +113,9 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle) static int fw_init(struct tcf_proto *tp) { - struct fw_head *head; - - head = kzalloc(sizeof(struct fw_head), GFP_KERNEL); - if (head == NULL) - return -ENOBUFS; - - head->mask_set = false; - rcu_assign_pointer(tp->root, head); + /* We don't allocate fw_head here, because in the old method + * we don't need it at all. + */ return 0; } @@ -252,7 +246,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, int err; if (!opt) - return handle ? -EINVAL : 0; + return handle ? -EINVAL : 0; /* Succeed if it is old method. */ err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy); if (err < 0) @@ -302,11 +296,17 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, if (!handle) return -EINVAL; - if (!head->mask_set) { - head->mask = 0xFFFFFFFF; + if (!head) { + u32 mask = 0xFFFFFFFF; if (tb[TCA_FW_MASK]) - head->mask = nla_get_u32(tb[TCA_FW_MASK]); - head->mask_set = true; + mask = nla_get_u32(tb[TCA_FW_MASK]); + + head = kzalloc(sizeof(*head), GFP_KERNEL); + if (!head) + return -ENOBUFS; + head->mask = mask; + + rcu_assign_pointer(tp->root, head); } f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index b7143337e4fa..3d9ea9a48289 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1186,7 +1186,7 @@ static void sctp_v4_del_protocol(void) unregister_inetaddr_notifier(&sctp_inetaddr_notifier); } -static int __net_init sctp_net_init(struct net *net) +static int __net_init sctp_defaults_init(struct net *net) { int status; @@ -1279,12 +1279,6 @@ static int __net_init sctp_net_init(struct net *net) sctp_dbg_objcnt_init(net); - /* Initialize the control inode/socket for handling OOTB packets. */ - if ((status = sctp_ctl_sock_init(net))) { - pr_err("Failed to initialize the SCTP control sock\n"); - goto err_ctl_sock_init; - } - /* Initialize the local address list. */ INIT_LIST_HEAD(&net->sctp.local_addr_list); spin_lock_init(&net->sctp.local_addr_lock); @@ -1300,9 +1294,6 @@ static int __net_init sctp_net_init(struct net *net) return 0; -err_ctl_sock_init: - sctp_dbg_objcnt_exit(net); - sctp_proc_exit(net); err_init_proc: cleanup_sctp_mibs(net); err_init_mibs: @@ -1311,15 +1302,12 @@ err_sysctl_register: return status; } -static void __net_exit sctp_net_exit(struct net *net) +static void __net_exit sctp_defaults_exit(struct net *net) { /* Free the local address list */ sctp_free_addr_wq(net); sctp_free_local_addr_list(net); - /* Free the control endpoint. */ - inet_ctl_sock_destroy(net->sctp.ctl_sock); - sctp_dbg_objcnt_exit(net); sctp_proc_exit(net); @@ -1327,9 +1315,32 @@ static void __net_exit sctp_net_exit(struct net *net) sctp_sysctl_net_unregister(net); } -static struct pernet_operations sctp_net_ops = { - .init = sctp_net_init, - .exit = sctp_net_exit, +static struct pernet_operations sctp_defaults_ops = { + .init = sctp_defaults_init, + .exit = sctp_defaults_exit, +}; + +static int __net_init sctp_ctrlsock_init(struct net *net) +{ + int status; + + /* Initialize the control inode/socket for handling OOTB packets. */ + status = sctp_ctl_sock_init(net); + if (status) + pr_err("Failed to initialize the SCTP control sock\n"); + + return status; +} + +static void __net_init sctp_ctrlsock_exit(struct net *net) +{ + /* Free the control endpoint. */ + inet_ctl_sock_destroy(net->sctp.ctl_sock); +} + +static struct pernet_operations sctp_ctrlsock_ops = { + .init = sctp_ctrlsock_init, + .exit = sctp_ctrlsock_exit, }; /* Initialize the universe into something sensible. */ @@ -1462,8 +1473,11 @@ static __init int sctp_init(void) sctp_v4_pf_init(); sctp_v6_pf_init(); - status = sctp_v4_protosw_init(); + status = register_pernet_subsys(&sctp_defaults_ops); + if (status) + goto err_register_defaults; + status = sctp_v4_protosw_init(); if (status) goto err_protosw_init; @@ -1471,9 +1485,9 @@ static __init int sctp_init(void) if (status) goto err_v6_protosw_init; - status = register_pernet_subsys(&sctp_net_ops); + status = register_pernet_subsys(&sctp_ctrlsock_ops); if (status) - goto err_register_pernet_subsys; + goto err_register_ctrlsock; status = sctp_v4_add_protocol(); if (status) @@ -1489,12 +1503,14 @@ out: err_v6_add_protocol: sctp_v4_del_protocol(); err_add_protocol: - unregister_pernet_subsys(&sctp_net_ops); -err_register_pernet_subsys: + unregister_pernet_subsys(&sctp_ctrlsock_ops); +err_register_ctrlsock: sctp_v6_protosw_exit(); err_v6_protosw_init: sctp_v4_protosw_exit(); err_protosw_init: + unregister_pernet_subsys(&sctp_defaults_ops); +err_register_defaults: sctp_v4_pf_exit(); sctp_v6_pf_exit(); sctp_sysctl_unregister(); @@ -1527,12 +1543,14 @@ static __exit void sctp_exit(void) sctp_v6_del_protocol(); sctp_v4_del_protocol(); - unregister_pernet_subsys(&sctp_net_ops); + unregister_pernet_subsys(&sctp_ctrlsock_ops); /* Free protosw registrations */ sctp_v6_protosw_exit(); sctp_v4_protosw_exit(); + unregister_pernet_subsys(&sctp_defaults_ops); + /* Unregister with socket layer. */ sctp_v6_pf_exit(); sctp_v4_pf_exit(); diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b140c092d226..f14f24ee9983 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, 1, &k); + __wake_up_locked_key(wq, TASK_NORMAL, &k); spin_unlock_irqrestore(&wq->lock, flags); return ret; } @@ -1092,14 +1092,10 @@ void rpc_destroy_mempool(void) { rpciod_stop(); - if (rpc_buffer_mempool) - mempool_destroy(rpc_buffer_mempool); - if (rpc_task_mempool) - mempool_destroy(rpc_task_mempool); - if (rpc_task_slabp) - kmem_cache_destroy(rpc_task_slabp); - if (rpc_buffer_slabp) - kmem_cache_destroy(rpc_buffer_slabp); + mempool_destroy(rpc_buffer_mempool); + mempool_destroy(rpc_task_mempool); + kmem_cache_destroy(rpc_task_slabp); + kmem_cache_destroy(rpc_buffer_slabp); rpc_destroy_wait_queue(&delay_queue); } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index ab5dd621ae0c..2e98f4a243e5 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -614,6 +614,7 @@ static void xprt_autoclose(struct work_struct *work) clear_bit(XPRT_CLOSE_WAIT, &xprt->state); xprt->ops->close(xprt); xprt_release_write(xprt, NULL); + wake_up_bit(&xprt->state, XPRT_LOCKED); } /** @@ -723,6 +724,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) xprt->ops->release_xprt(xprt, NULL); out: spin_unlock_bh(&xprt->transport_lock); + wake_up_bit(&xprt->state, XPRT_LOCKED); } /** @@ -1394,6 +1396,10 @@ out: static void xprt_destroy(struct rpc_xprt *xprt) { dprintk("RPC: destroying transport %p\n", xprt); + + /* Exclude transport connect/disconnect handlers */ + wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE); + del_timer_sync(&xprt->timer); rpc_xprt_debugfs_unregister(xprt); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 7be90bc1a7c2..1a85e0ed0b48 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -777,7 +777,6 @@ static void xs_sock_mark_closed(struct rpc_xprt *xprt) xs_sock_reset_connection_flags(xprt); /* Mark transport as closed and wake up all pending tasks */ xprt_disconnect_done(xprt); - xprt_force_disconnect(xprt); } /** @@ -881,8 +880,11 @@ static void xs_xprt_free(struct rpc_xprt *xprt) */ static void xs_destroy(struct rpc_xprt *xprt) { + struct sock_xprt *transport = container_of(xprt, + struct sock_xprt, xprt); dprintk("RPC: xs_destroy xprt %p\n", xprt); + cancel_delayed_work_sync(&transport->connect_worker); xs_close(xprt); xs_xprt_free(xprt); module_put(THIS_MODULE); @@ -1435,6 +1437,7 @@ out: static void xs_tcp_state_change(struct sock *sk) { struct rpc_xprt *xprt; + struct sock_xprt *transport; read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) @@ -1446,13 +1449,12 @@ static void xs_tcp_state_change(struct sock *sk) sock_flag(sk, SOCK_ZAPPED), sk->sk_shutdown); + transport = container_of(xprt, struct sock_xprt, xprt); trace_rpc_socket_state_change(xprt, sk->sk_socket); switch (sk->sk_state) { case TCP_ESTABLISHED: spin_lock(&xprt->transport_lock); if (!xprt_test_and_set_connected(xprt)) { - struct sock_xprt *transport = container_of(xprt, - struct sock_xprt, xprt); /* Reset TCP record info */ transport->tcp_offset = 0; @@ -1461,6 +1463,8 @@ static void xs_tcp_state_change(struct sock *sk) transport->tcp_flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; xprt->connect_cookie++; + clear_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); + xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, -EAGAIN); } @@ -1496,6 +1500,9 @@ static void xs_tcp_state_change(struct sock *sk) smp_mb__after_atomic(); break; case TCP_CLOSE: + if (test_and_clear_bit(XPRT_SOCK_CONNECTING, + &transport->sock_state)) + xprt_clear_connecting(xprt); xs_sock_mark_closed(xprt); } out: @@ -2179,6 +2186,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* Tell the socket layer to start connecting... */ xprt->stat.connect_count++; xprt->stat.connect_start = jiffies; + set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); switch (ret) { case 0: @@ -2240,7 +2248,6 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EINPROGRESS: case -EALREADY: xprt_unlock_connect(xprt, transport); - xprt_clear_connecting(xprt); return; case -EINVAL: /* Happens, for instance, if the user specified a link diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 562c926a51cc..c5ac436235e0 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -539,6 +539,7 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) *err = -TIPC_ERR_NO_NAME; if (skb_linearize(skb)) return false; + msg = buf_msg(skb); if (msg_reroute_cnt(msg)) return false; dnode = addr_domain(net, msg_lookup_scope(msg)); |