diff options
Diffstat (limited to 'net')
158 files changed, 3738 insertions, 2730 deletions
diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c index 99bb22aea346..68c80f3c9add 100644 --- a/net/6lowpan/iphc.c +++ b/net/6lowpan/iphc.c @@ -148,6 +148,11 @@ (((a)->s6_addr16[6]) == 0) && \ (((a)->s6_addr[14]) == 0)) +#define lowpan_is_linklocal_zero_padded(a) \ + (!(hdr->saddr.s6_addr[1] & 0x3f) && \ + !hdr->saddr.s6_addr16[1] && \ + !hdr->saddr.s6_addr32[1]) + #define LOWPAN_IPHC_CID_DCI(cid) (cid & 0x0f) #define LOWPAN_IPHC_CID_SCI(cid) ((cid & 0xf0) >> 4) @@ -1101,7 +1106,8 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev, true); iphc1 |= LOWPAN_IPHC_SAC; } else { - if (ipv6_saddr_type & IPV6_ADDR_LINKLOCAL) { + if (ipv6_saddr_type & IPV6_ADDR_LINKLOCAL && + lowpan_is_linklocal_zero_padded(hdr->saddr)) { iphc1 |= lowpan_compress_addr_64(&hc_ptr, &hdr->saddr, saddr, true); @@ -1135,7 +1141,8 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev, false); iphc1 |= LOWPAN_IPHC_DAC; } else { - if (ipv6_daddr_type & IPV6_ADDR_LINKLOCAL) { + if (ipv6_daddr_type & IPV6_ADDR_LINKLOCAL && + lowpan_is_linklocal_zero_padded(hdr->daddr)) { iphc1 |= lowpan_compress_addr_64(&hc_ptr, &hdr->daddr, daddr, false); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index c162af5d16bf..d4b3dd5413be 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4727,6 +4727,19 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u32 flags; u8 *ptr, real_len; + switch (type) { + case LE_ADV_IND: + case LE_ADV_DIRECT_IND: + case LE_ADV_SCAN_IND: + case LE_ADV_NONCONN_IND: + case LE_ADV_SCAN_RSP: + break; + default: + BT_ERR_RATELIMITED("Unknown advetising packet type: 0x%02x", + type); + return; + } + /* Find the end of the data in case the report contains padded zero * bytes at the end causing an invalid length value. * diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 6e125d76df0d..c045b3c54768 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -1065,6 +1065,9 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) if (instance_flags & MGMT_ADV_FLAG_LIMITED_DISCOV) flags |= LE_AD_LIMITED; + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) + flags |= LE_AD_NO_BREDR; + if (flags || (instance_flags & MGMT_ADV_FLAG_MANAGED_FLAGS)) { /* If a discovery flag wasn't provided, simply use the global * settings. @@ -1072,9 +1075,6 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) if (!flags) flags |= mgmt_get_adv_discov_flags(hdev); - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) - flags |= LE_AD_NO_BREDR; - /* If flags would still be empty, then there is no need to * include the "Flags" AD field". */ diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index e4cae72895a7..388ee8b59145 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -778,7 +778,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, } if (sec.level < BT_SECURITY_LOW || - sec.level > BT_SECURITY_HIGH) { + sec.level > BT_SECURITY_FIPS) { err = -EINVAL; break; } diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index e23449094188..9cb7044d0801 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -582,7 +582,7 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) int err; err = switchdev_port_attr_set(br->dev, &attr); - if (err) + if (err && err != -EOPNOTSUPP) return err; br->ageing_time = t; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 67b2e27999aa..8570bc7744c2 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1521,6 +1521,8 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; + tmp.name[sizeof(tmp.name) - 1] = '\0'; + t = find_table_lock(net, tmp.name, &ret, &ebt_mutex); if (!t) return ret; @@ -2332,6 +2334,8 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; + tmp.name[sizeof(tmp.name) - 1] = '\0'; + t = find_table_lock(net, tmp.name, &ret, &ebt_mutex); if (!t) return ret; diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index adc8d7221dbb..77f7e7a9ebe1 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -40,7 +40,8 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, /* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT) * or the bridge port (NF_BRIDGE PREROUTING). */ -static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, +static void nft_reject_br_send_v4_tcp_reset(struct net *net, + struct sk_buff *oldskb, const struct net_device *dev, int hook) { @@ -48,7 +49,6 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, struct iphdr *niph; const struct tcphdr *oth; struct tcphdr _oth; - struct net *net = sock_net(oldskb->sk); if (!nft_bridge_iphdr_validate(oldskb)) return; @@ -75,7 +75,8 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, br_deliver(br_port_get_rcu(dev), nskb); } -static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, +static void nft_reject_br_send_v4_unreach(struct net *net, + struct sk_buff *oldskb, const struct net_device *dev, int hook, u8 code) { @@ -86,7 +87,6 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, void *payload; __wsum csum; u8 proto; - struct net *net = sock_net(oldskb->sk); if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb)) return; @@ -273,17 +273,17 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, case htons(ETH_P_IP): switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, - pkt->hook, + nft_reject_br_send_v4_unreach(pkt->net, pkt->skb, + pkt->in, pkt->hook, priv->icmp_code); break; case NFT_REJECT_TCP_RST: - nft_reject_br_send_v4_tcp_reset(pkt->skb, pkt->in, - pkt->hook); + nft_reject_br_send_v4_tcp_reset(pkt->net, pkt->skb, + pkt->in, pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: - nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, - pkt->hook, + nft_reject_br_send_v4_unreach(pkt->net, pkt->skb, + pkt->in, pkt->hook, nft_reject_icmp_code(priv->icmp_code)); break; } diff --git a/net/can/raw.c b/net/can/raw.c index 2e67b1423cd3..972c187d40ab 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -755,7 +755,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err < 0) goto free_skb; - sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); + sock_tx_timestamp(sk, sk->sk_tsflags, &skb_shinfo(skb)->tx_flags); skb->dev = dev; skb->sk = sk; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index bcbec33c6a14..dcc18c6f7cf9 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -361,7 +361,6 @@ 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]...] */ @@ -686,6 +685,9 @@ int __ceph_open_session(struct ceph_client *client, unsigned long started) return client->auth_err; } + pr_info("client%llu fsid %pU\n", ceph_client_id(client), &client->fsid); + ceph_debugfs_client_init(client); + return 0; } EXPORT_SYMBOL(__ceph_open_session); diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 593dc2eabcc8..b902fbc7863e 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -112,15 +112,20 @@ static int monc_show(struct seq_file *s, void *p) struct ceph_mon_generic_request *req; struct ceph_mon_client *monc = &client->monc; struct rb_node *rp; + int i; mutex_lock(&monc->mutex); - if (monc->have_mdsmap) - seq_printf(s, "have mdsmap %u\n", (unsigned int)monc->have_mdsmap); - if (monc->have_osdmap) - seq_printf(s, "have osdmap %u\n", (unsigned int)monc->have_osdmap); - if (monc->want_next_osdmap) - seq_printf(s, "want next osdmap\n"); + for (i = 0; i < ARRAY_SIZE(monc->subs); i++) { + seq_printf(s, "have %s %u", ceph_sub_str[i], + monc->subs[i].have); + if (monc->subs[i].want) + seq_printf(s, " want %llu%s", + le64_to_cpu(monc->subs[i].item.start), + (monc->subs[i].item.flags & + CEPH_SUBSCRIBE_ONETIME ? "" : "+")); + seq_putc(s, '\n'); + } for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) { __u16 op; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9382619a405b..a5502898ea33 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -235,18 +235,12 @@ static struct workqueue_struct *ceph_msgr_wq; static int ceph_msgr_slab_init(void) { BUG_ON(ceph_msg_cache); - ceph_msg_cache = kmem_cache_create("ceph_msg", - sizeof (struct ceph_msg), - __alignof__(struct ceph_msg), 0, NULL); - + ceph_msg_cache = KMEM_CACHE(ceph_msg, 0); if (!ceph_msg_cache) return -ENOMEM; BUG_ON(ceph_msg_data_cache); - ceph_msg_data_cache = kmem_cache_create("ceph_msg_data", - sizeof (struct ceph_msg_data), - __alignof__(struct ceph_msg_data), - 0, NULL); + ceph_msg_data_cache = KMEM_CACHE(ceph_msg_data, 0); if (ceph_msg_data_cache) return 0; @@ -275,7 +269,7 @@ static void _ceph_msgr_exit(void) } BUG_ON(zero_page == NULL); - page_cache_release(zero_page); + put_page(zero_page); zero_page = NULL; ceph_msgr_slab_exit(); @@ -288,7 +282,7 @@ int ceph_msgr_init(void) BUG_ON(zero_page != NULL); zero_page = ZERO_PAGE(0); - page_cache_get(zero_page); + get_page(zero_page); /* * The number of active work items is limited by the number of @@ -1221,25 +1215,19 @@ static void prepare_message_data(struct ceph_msg *msg, u32 data_len) static void prepare_write_message_footer(struct ceph_connection *con) { struct ceph_msg *m = con->out_msg; - int v = con->out_kvec_left; m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE; dout("prepare_write_message_footer %p\n", con); - con->out_kvec[v].iov_base = &m->footer; + con_out_kvec_add(con, sizeof_footer(con), &m->footer); if (con->peer_features & CEPH_FEATURE_MSG_AUTH) { if (con->ops->sign_message) con->ops->sign_message(m); else m->footer.sig = 0; - con->out_kvec[v].iov_len = sizeof(m->footer); - con->out_kvec_bytes += sizeof(m->footer); } else { m->old_footer.flags = m->footer.flags; - con->out_kvec[v].iov_len = sizeof(m->old_footer); - con->out_kvec_bytes += sizeof(m->old_footer); } - con->out_kvec_left++; con->out_more = m->more_to_follow; con->out_msg_done = true; } @@ -1614,7 +1602,7 @@ static int write_partial_skip(struct ceph_connection *con) dout("%s %p %d left\n", __func__, con, con->out_skip); while (con->out_skip > 0) { - size_t size = min(con->out_skip, (int) PAGE_CACHE_SIZE); + size_t size = min(con->out_skip, (int) PAGE_SIZE); ret = ceph_tcp_sendpage(con->sock, zero_page, 0, size, true); if (ret <= 0) @@ -2409,11 +2397,7 @@ static int read_partial_message(struct ceph_connection *con) } /* footer */ - if (need_sign) - size = sizeof(m->footer); - else - size = sizeof(m->old_footer); - + size = sizeof_footer(con); end += size; ret = read_partial(con, end, size, &m->footer); if (ret <= 0) @@ -3089,10 +3073,7 @@ void ceph_msg_revoke(struct ceph_msg *msg) con->out_skip += con_out_kvec_skip(con); } else { BUG_ON(!msg->data_length); - if (con->peer_features & CEPH_FEATURE_MSG_AUTH) - con->out_skip += sizeof(msg->footer); - else - con->out_skip += sizeof(msg->old_footer); + con->out_skip += sizeof_footer(con); } /* data, middle, front */ if (msg->data_length) diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index de85dddc3dc0..cf638c009cfa 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -122,51 +122,91 @@ static void __close_session(struct ceph_mon_client *monc) ceph_msg_revoke(monc->m_subscribe); ceph_msg_revoke_incoming(monc->m_subscribe_ack); ceph_con_close(&monc->con); - monc->cur_mon = -1; + monc->pending_auth = 0; ceph_auth_reset(monc->auth); } /* - * Open a session with a (new) monitor. + * Pick a new monitor at random and set cur_mon. If we are repicking + * (i.e. cur_mon is already set), be sure to pick a different one. */ -static int __open_session(struct ceph_mon_client *monc) +static void pick_new_mon(struct ceph_mon_client *monc) { - char r; - int ret; + int old_mon = monc->cur_mon; - if (monc->cur_mon < 0) { - get_random_bytes(&r, 1); - monc->cur_mon = r % monc->monmap->num_mon; - dout("open_session num=%d r=%d -> mon%d\n", - monc->monmap->num_mon, r, monc->cur_mon); - monc->sub_sent = 0; - monc->sub_renew_after = jiffies; /* i.e., expired */ - monc->want_next_osdmap = !!monc->want_next_osdmap; - - dout("open_session mon%d opening\n", monc->cur_mon); - ceph_con_open(&monc->con, - 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, - monc->m_auth->front_alloc_len); - __send_prepared_auth_request(monc, ret); + BUG_ON(monc->monmap->num_mon < 1); + + if (monc->monmap->num_mon == 1) { + monc->cur_mon = 0; } else { - dout("open_session mon%d already open\n", monc->cur_mon); + int max = monc->monmap->num_mon; + int o = -1; + int n; + + if (monc->cur_mon >= 0) { + if (monc->cur_mon < monc->monmap->num_mon) + o = monc->cur_mon; + if (o >= 0) + max--; + } + + n = prandom_u32() % max; + if (o >= 0 && n >= o) + n++; + + monc->cur_mon = n; } - return 0; + + dout("%s mon%d -> mon%d out of %d mons\n", __func__, old_mon, + monc->cur_mon, monc->monmap->num_mon); +} + +/* + * Open a session with a new monitor. + */ +static void __open_session(struct ceph_mon_client *monc) +{ + int ret; + + pick_new_mon(monc); + + monc->hunting = true; + if (monc->had_a_connection) { + monc->hunt_mult *= CEPH_MONC_HUNT_BACKOFF; + if (monc->hunt_mult > CEPH_MONC_HUNT_MAX_MULT) + monc->hunt_mult = CEPH_MONC_HUNT_MAX_MULT; + } + + monc->sub_renew_after = jiffies; /* i.e., expired */ + monc->sub_renew_sent = 0; + + dout("%s opening mon%d\n", __func__, monc->cur_mon); + ceph_con_open(&monc->con, 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); + + /* initiate authentication handshake */ + ret = ceph_auth_build_hello(monc->auth, + monc->m_auth->front.iov_base, + monc->m_auth->front_alloc_len); + BUG_ON(ret <= 0); + __send_prepared_auth_request(monc, ret); } -static bool __sub_expired(struct ceph_mon_client *monc) +static void reopen_session(struct ceph_mon_client *monc) { - return time_after_eq(jiffies, monc->sub_renew_after); + if (!monc->hunting) + pr_info("mon%d %s session lost, hunting for new mon\n", + monc->cur_mon, ceph_pr_addr(&monc->con.peer_addr.in_addr)); + + __close_session(monc); + __open_session(monc); } /* @@ -174,74 +214,70 @@ static bool __sub_expired(struct ceph_mon_client *monc) */ static void __schedule_delayed(struct ceph_mon_client *monc) { - struct ceph_options *opt = monc->client->options; unsigned long delay; - if (monc->cur_mon < 0 || __sub_expired(monc)) { - delay = 10 * HZ; - } else { - delay = 20 * HZ; - if (opt->monc_ping_timeout > 0) - delay = min(delay, opt->monc_ping_timeout / 3); - } + if (monc->hunting) + delay = CEPH_MONC_HUNT_INTERVAL * monc->hunt_mult; + else + delay = CEPH_MONC_PING_INTERVAL; + dout("__schedule_delayed after %lu\n", delay); - schedule_delayed_work(&monc->delayed_work, - round_jiffies_relative(delay)); + mod_delayed_work(system_wq, &monc->delayed_work, + round_jiffies_relative(delay)); } +const char *ceph_sub_str[] = { + [CEPH_SUB_MDSMAP] = "mdsmap", + [CEPH_SUB_MONMAP] = "monmap", + [CEPH_SUB_OSDMAP] = "osdmap", +}; + /* - * Send subscribe request for mdsmap and/or osdmap. + * Send subscribe request for one or more maps, according to + * monc->subs. */ static void __send_subscribe(struct ceph_mon_client *monc) { - dout("__send_subscribe sub_sent=%u exp=%u want_osd=%d\n", - (unsigned int)monc->sub_sent, __sub_expired(monc), - monc->want_next_osdmap); - if ((__sub_expired(monc) && !monc->sub_sent) || - monc->want_next_osdmap == 1) { - struct ceph_msg *msg = monc->m_subscribe; - struct ceph_mon_subscribe_item *i; - void *p, *end; - int num; - - p = msg->front.iov_base; - end = p + msg->front_alloc_len; - - num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap; - ceph_encode_32(&p, num); - - if (monc->want_next_osdmap) { - dout("__send_subscribe to 'osdmap' %u\n", - (unsigned int)monc->have_osdmap); - ceph_encode_string(&p, end, "osdmap", 6); - i = p; - i->have = cpu_to_le64(monc->have_osdmap); - i->onetime = 1; - p += sizeof(*i); - monc->want_next_osdmap = 2; /* requested */ - } - if (monc->want_mdsmap) { - dout("__send_subscribe to 'mdsmap' %u+\n", - (unsigned int)monc->have_mdsmap); - ceph_encode_string(&p, end, "mdsmap", 6); - i = p; - i->have = cpu_to_le64(monc->have_mdsmap); - i->onetime = 0; - p += sizeof(*i); - } - ceph_encode_string(&p, end, "monmap", 6); - i = p; - i->have = 0; - i->onetime = 0; - p += sizeof(*i); - - msg->front.iov_len = p - msg->front.iov_base; - msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); - ceph_msg_revoke(msg); - ceph_con_send(&monc->con, ceph_msg_get(msg)); - - monc->sub_sent = jiffies | 1; /* never 0 */ + struct ceph_msg *msg = monc->m_subscribe; + void *p = msg->front.iov_base; + void *const end = p + msg->front_alloc_len; + int num = 0; + int i; + + dout("%s sent %lu\n", __func__, monc->sub_renew_sent); + + BUG_ON(monc->cur_mon < 0); + + if (!monc->sub_renew_sent) + monc->sub_renew_sent = jiffies | 1; /* never 0 */ + + msg->hdr.version = cpu_to_le16(2); + + for (i = 0; i < ARRAY_SIZE(monc->subs); i++) { + if (monc->subs[i].want) + num++; } + BUG_ON(num < 1); /* monmap sub is always there */ + ceph_encode_32(&p, num); + for (i = 0; i < ARRAY_SIZE(monc->subs); i++) { + const char *s = ceph_sub_str[i]; + + if (!monc->subs[i].want) + continue; + + dout("%s %s start %llu flags 0x%x\n", __func__, s, + le64_to_cpu(monc->subs[i].item.start), + monc->subs[i].item.flags); + ceph_encode_string(&p, end, s, strlen(s)); + memcpy(p, &monc->subs[i].item, sizeof(monc->subs[i].item)); + p += sizeof(monc->subs[i].item); + } + + BUG_ON(p != (end - 35 - (ARRAY_SIZE(monc->subs) - num) * 19)); + msg->front.iov_len = p - msg->front.iov_base; + msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); + ceph_msg_revoke(msg); + ceph_con_send(&monc->con, ceph_msg_get(msg)); } static void handle_subscribe_ack(struct ceph_mon_client *monc, @@ -255,15 +291,16 @@ static void handle_subscribe_ack(struct ceph_mon_client *monc, seconds = le32_to_cpu(h->duration); mutex_lock(&monc->mutex); - if (monc->hunting) { - pr_info("mon%d %s session established\n", - monc->cur_mon, - ceph_pr_addr(&monc->con.peer_addr.in_addr)); - monc->hunting = false; + if (monc->sub_renew_sent) { + monc->sub_renew_after = monc->sub_renew_sent + + (seconds >> 1) * HZ - 1; + dout("%s sent %lu duration %d renew after %lu\n", __func__, + monc->sub_renew_sent, seconds, monc->sub_renew_after); + monc->sub_renew_sent = 0; + } else { + dout("%s sent %lu renew after %lu, ignoring\n", __func__, + monc->sub_renew_sent, monc->sub_renew_after); } - dout("handle_subscribe_ack after %d seconds\n", seconds); - monc->sub_renew_after = monc->sub_sent + (seconds >> 1)*HZ - 1; - monc->sub_sent = 0; mutex_unlock(&monc->mutex); return; bad: @@ -272,36 +309,82 @@ bad: } /* - * Keep track of which maps we have + * Register interest in a map + * + * @sub: one of CEPH_SUB_* + * @epoch: X for "every map since X", or 0 for "just the latest" */ -int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 got) +static bool __ceph_monc_want_map(struct ceph_mon_client *monc, int sub, + u32 epoch, bool continuous) +{ + __le64 start = cpu_to_le64(epoch); + u8 flags = !continuous ? CEPH_SUBSCRIBE_ONETIME : 0; + + dout("%s %s epoch %u continuous %d\n", __func__, ceph_sub_str[sub], + epoch, continuous); + + if (monc->subs[sub].want && + monc->subs[sub].item.start == start && + monc->subs[sub].item.flags == flags) + return false; + + monc->subs[sub].item.start = start; + monc->subs[sub].item.flags = flags; + monc->subs[sub].want = true; + + return true; +} + +bool ceph_monc_want_map(struct ceph_mon_client *monc, int sub, u32 epoch, + bool continuous) { + bool need_request; + mutex_lock(&monc->mutex); - monc->have_mdsmap = got; + need_request = __ceph_monc_want_map(monc, sub, epoch, continuous); mutex_unlock(&monc->mutex); - return 0; + + return need_request; } -EXPORT_SYMBOL(ceph_monc_got_mdsmap); +EXPORT_SYMBOL(ceph_monc_want_map); -int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 got) +/* + * Keep track of which maps we have + * + * @sub: one of CEPH_SUB_* + */ +static void __ceph_monc_got_map(struct ceph_mon_client *monc, int sub, + u32 epoch) +{ + dout("%s %s epoch %u\n", __func__, ceph_sub_str[sub], epoch); + + if (monc->subs[sub].want) { + if (monc->subs[sub].item.flags & CEPH_SUBSCRIBE_ONETIME) + monc->subs[sub].want = false; + else + monc->subs[sub].item.start = cpu_to_le64(epoch + 1); + } + + monc->subs[sub].have = epoch; +} + +void ceph_monc_got_map(struct ceph_mon_client *monc, int sub, u32 epoch) { mutex_lock(&monc->mutex); - monc->have_osdmap = got; - monc->want_next_osdmap = 0; + __ceph_monc_got_map(monc, sub, epoch); mutex_unlock(&monc->mutex); - return 0; } +EXPORT_SYMBOL(ceph_monc_got_map); /* * Register interest in the next osdmap */ void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc) { - dout("request_next_osdmap have %u\n", monc->have_osdmap); + dout("%s have %u\n", __func__, monc->subs[CEPH_SUB_OSDMAP].have); mutex_lock(&monc->mutex); - if (!monc->want_next_osdmap) - monc->want_next_osdmap = 1; - if (monc->want_next_osdmap < 2) + if (__ceph_monc_want_map(monc, CEPH_SUB_OSDMAP, + monc->subs[CEPH_SUB_OSDMAP].have + 1, false)) __send_subscribe(monc); mutex_unlock(&monc->mutex); } @@ -320,15 +403,15 @@ int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch, long ret; mutex_lock(&monc->mutex); - while (monc->have_osdmap < epoch) { + while (monc->subs[CEPH_SUB_OSDMAP].have < epoch) { mutex_unlock(&monc->mutex); if (timeout && time_after_eq(jiffies, started + timeout)) return -ETIMEDOUT; ret = wait_event_interruptible_timeout(monc->client->auth_wq, - monc->have_osdmap >= epoch, - ceph_timeout_jiffies(timeout)); + monc->subs[CEPH_SUB_OSDMAP].have >= epoch, + ceph_timeout_jiffies(timeout)); if (ret < 0) return ret; @@ -341,11 +424,14 @@ int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch, EXPORT_SYMBOL(ceph_monc_wait_osdmap); /* - * + * Open a session with a random monitor. Request monmap and osdmap, + * which are waited upon in __ceph_open_session(). */ int ceph_monc_open_session(struct ceph_mon_client *monc) { mutex_lock(&monc->mutex); + __ceph_monc_want_map(monc, CEPH_SUB_MONMAP, 0, true); + __ceph_monc_want_map(monc, CEPH_SUB_OSDMAP, 0, false); __open_session(monc); __schedule_delayed(monc); mutex_unlock(&monc->mutex); @@ -353,29 +439,15 @@ int ceph_monc_open_session(struct ceph_mon_client *monc) } EXPORT_SYMBOL(ceph_monc_open_session); -/* - * We require the fsid and global_id in order to initialize our - * debugfs dir. - */ -static bool have_debugfs_info(struct ceph_mon_client *monc) -{ - dout("have_debugfs_info fsid %d globalid %lld\n", - (int)monc->client->have_fsid, monc->auth->global_id); - return monc->client->have_fsid && monc->auth->global_id > 0; -} - static void ceph_monc_handle_map(struct ceph_mon_client *monc, struct ceph_msg *msg) { struct ceph_client *client = monc->client; struct ceph_monmap *monmap = NULL, *old = monc->monmap; void *p, *end; - int had_debugfs_info, init_debugfs = 0; mutex_lock(&monc->mutex); - had_debugfs_info = have_debugfs_info(monc); - dout("handle_monmap\n"); p = msg->front.iov_base; end = p + msg->front.iov_len; @@ -395,29 +467,11 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, client->monc.monmap = monmap; kfree(old); - if (!client->have_fsid) { - client->have_fsid = true; - if (!had_debugfs_info && have_debugfs_info(monc)) { - pr_info("client%lld fsid %pU\n", - ceph_client_id(monc->client), - &monc->client->fsid); - init_debugfs = 1; - } - mutex_unlock(&monc->mutex); - - if (init_debugfs) { - /* - * do debugfs initialization without mutex to avoid - * creating a locking dependency - */ - ceph_debugfs_client_init(monc->client); - } + __ceph_monc_got_map(monc, CEPH_SUB_MONMAP, monc->monmap->epoch); + client->have_fsid = true; - goto out_unlocked; - } out: mutex_unlock(&monc->mutex); -out_unlocked: wake_up_all(&client->auth_wq); } @@ -745,18 +799,15 @@ static void delayed_work(struct work_struct *work) dout("monc delayed_work\n"); mutex_lock(&monc->mutex); if (monc->hunting) { - __close_session(monc); - __open_session(monc); /* continue hunting */ + dout("%s continuing hunt\n", __func__); + reopen_session(monc); } else { - 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)) { + CEPH_MONC_PING_TIMEOUT)) { dout("monc keepalive timeout\n"); is_auth = 0; - __close_session(monc); - monc->hunting = true; - __open_session(monc); + reopen_session(monc); } if (!monc->hunting) { @@ -764,8 +815,14 @@ static void delayed_work(struct work_struct *work) __validate_auth(monc); } - if (is_auth) - __send_subscribe(monc); + if (is_auth) { + unsigned long now = jiffies; + + dout("%s renew subs? now %lu renew after %lu\n", + __func__, now, monc->sub_renew_after); + if (time_after_eq(now, monc->sub_renew_after)) + __send_subscribe(monc); + } } __schedule_delayed(monc); mutex_unlock(&monc->mutex); @@ -852,18 +909,14 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) &monc->client->msgr); monc->cur_mon = -1; - monc->hunting = true; - monc->sub_renew_after = jiffies; - monc->sub_sent = 0; + monc->had_a_connection = false; + monc->hunt_mult = 1; INIT_DELAYED_WORK(&monc->delayed_work, delayed_work); monc->generic_request_tree = RB_ROOT; monc->num_generic_requests = 0; monc->last_tid = 0; - monc->have_mdsmap = 0; - monc->have_osdmap = 0; - monc->want_next_osdmap = 1; return 0; out_auth_reply: @@ -888,7 +941,7 @@ void ceph_monc_stop(struct ceph_mon_client *monc) mutex_lock(&monc->mutex); __close_session(monc); - + monc->cur_mon = -1; mutex_unlock(&monc->mutex); /* @@ -910,26 +963,40 @@ void ceph_monc_stop(struct ceph_mon_client *monc) } EXPORT_SYMBOL(ceph_monc_stop); +static void finish_hunting(struct ceph_mon_client *monc) +{ + if (monc->hunting) { + dout("%s found mon%d\n", __func__, monc->cur_mon); + monc->hunting = false; + monc->had_a_connection = true; + monc->hunt_mult /= 2; /* reduce by 50% */ + if (monc->hunt_mult < 1) + monc->hunt_mult = 1; + } +} + static void handle_auth_reply(struct ceph_mon_client *monc, struct ceph_msg *msg) { int ret; int was_auth = 0; - int had_debugfs_info, init_debugfs = 0; mutex_lock(&monc->mutex); - had_debugfs_info = have_debugfs_info(monc); was_auth = ceph_auth_is_authenticated(monc->auth); monc->pending_auth = 0; ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base, msg->front.iov_len, monc->m_auth->front.iov_base, monc->m_auth->front_alloc_len); + if (ret > 0) { + __send_prepared_auth_request(monc, ret); + goto out; + } + + finish_hunting(monc); + if (ret < 0) { monc->client->auth_err = ret; - wake_up_all(&monc->client->auth_wq); - } else if (ret > 0) { - __send_prepared_auth_request(monc, ret); } else if (!was_auth && ceph_auth_is_authenticated(monc->auth)) { dout("authenticated, starting session\n"); @@ -939,23 +1006,15 @@ static void handle_auth_reply(struct ceph_mon_client *monc, __send_subscribe(monc); __resend_generic_request(monc); - } - if (!had_debugfs_info && have_debugfs_info(monc)) { - pr_info("client%lld fsid %pU\n", - ceph_client_id(monc->client), - &monc->client->fsid); - init_debugfs = 1; + pr_info("mon%d %s session established\n", monc->cur_mon, + ceph_pr_addr(&monc->con.peer_addr.in_addr)); } - mutex_unlock(&monc->mutex); - if (init_debugfs) { - /* - * do debugfs initialization without mutex to avoid - * creating a locking dependency - */ - ceph_debugfs_client_init(monc->client); - } +out: + mutex_unlock(&monc->mutex); + if (monc->client->auth_err < 0) + wake_up_all(&monc->client->auth_wq); } static int __validate_auth(struct ceph_mon_client *monc) @@ -1096,29 +1155,17 @@ static void mon_fault(struct ceph_connection *con) { struct ceph_mon_client *monc = con->private; - if (!monc) - return; - - dout("mon_fault\n"); mutex_lock(&monc->mutex); - if (!con->private) - goto out; - - if (!monc->hunting) - pr_info("mon%d %s session lost, " - "hunting for new mon\n", monc->cur_mon, - ceph_pr_addr(&monc->con.peer_addr.in_addr)); - - __close_session(monc); - if (!monc->hunting) { - /* start hunting */ - monc->hunting = true; - __open_session(monc); - } else { - /* already hunting, let's wait a bit */ - __schedule_delayed(monc); + dout("%s mon%d\n", __func__, monc->cur_mon); + if (monc->cur_mon >= 0) { + if (!monc->hunting) { + dout("%s hunting for new mon\n", __func__); + reopen_session(monc); + __schedule_delayed(monc); + } else { + dout("%s already hunting\n", __func__); + } } -out: mutex_unlock(&monc->mutex); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 5bc053778fed..32355d9d0103 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -338,9 +338,10 @@ static void ceph_osdc_release_request(struct kref *kref) ceph_put_snap_context(req->r_snapc); if (req->r_mempool) mempool_free(req, req->r_osdc->req_mempool); - else + else if (req->r_num_ops <= CEPH_OSD_SLAB_OPS) kmem_cache_free(ceph_osd_request_cache, req); - + else + kfree(req); } void ceph_osdc_get_request(struct ceph_osd_request *req) @@ -369,28 +370,22 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_msg *msg; size_t msg_size; - BUILD_BUG_ON(CEPH_OSD_MAX_OP > U16_MAX); - BUG_ON(num_ops > CEPH_OSD_MAX_OP); - - msg_size = 4 + 4 + 8 + 8 + 4+8; - msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */ - msg_size += 1 + 8 + 4 + 4; /* pg_t */ - msg_size += 4 + CEPH_MAX_OID_NAME_LEN; /* oid */ - msg_size += 2 + num_ops*sizeof(struct ceph_osd_op); - msg_size += 8; /* snapid */ - msg_size += 8; /* snap_seq */ - msg_size += 8 * (snapc ? snapc->num_snaps : 0); /* snaps */ - msg_size += 4; - if (use_mempool) { + BUG_ON(num_ops > CEPH_OSD_SLAB_OPS); req = mempool_alloc(osdc->req_mempool, gfp_flags); - memset(req, 0, sizeof(*req)); + } else if (num_ops <= CEPH_OSD_SLAB_OPS) { + req = kmem_cache_alloc(ceph_osd_request_cache, gfp_flags); } else { - req = kmem_cache_zalloc(ceph_osd_request_cache, gfp_flags); + BUG_ON(num_ops > CEPH_OSD_MAX_OPS); + req = kmalloc(sizeof(*req) + num_ops * sizeof(req->r_ops[0]), + gfp_flags); } - if (req == NULL) + if (unlikely(!req)) return NULL; + /* req only, each op is zeroed in _osd_req_op_init() */ + memset(req, 0, sizeof(*req)); + req->r_osdc = osdc; req->r_mempool = use_mempool; req->r_num_ops = num_ops; @@ -408,18 +403,36 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, req->r_base_oloc.pool = -1; req->r_target_oloc.pool = -1; + msg_size = OSD_OPREPLY_FRONT_LEN; + if (num_ops > CEPH_OSD_SLAB_OPS) { + /* ceph_osd_op and rval */ + msg_size += (num_ops - CEPH_OSD_SLAB_OPS) * + (sizeof(struct ceph_osd_op) + 4); + } + /* create reply message */ if (use_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0); else - msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, - OSD_OPREPLY_FRONT_LEN, gfp_flags, true); + msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, msg_size, + gfp_flags, true); if (!msg) { ceph_osdc_put_request(req); return NULL; } req->r_reply = msg; + msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */ + msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */ + msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */ + msg_size += 1 + 8 + 4 + 4; /* pgid */ + msg_size += 4 + CEPH_MAX_OID_NAME_LEN; /* oid */ + msg_size += 2 + num_ops * sizeof(struct ceph_osd_op); + msg_size += 8; /* snapid */ + msg_size += 8; /* snap_seq */ + msg_size += 4 + 8 * (snapc ? snapc->num_snaps : 0); /* snaps */ + msg_size += 4; /* retry_attempt */ + /* create request message; allow space for oid */ if (use_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op, 0); @@ -498,7 +511,7 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req, if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL) payload_len += length; - op->payload_len = payload_len; + op->indata_len = payload_len; } EXPORT_SYMBOL(osd_req_op_extent_init); @@ -517,10 +530,32 @@ void osd_req_op_extent_update(struct ceph_osd_request *osd_req, BUG_ON(length > previous); op->extent.length = length; - op->payload_len -= previous - length; + op->indata_len -= previous - length; } EXPORT_SYMBOL(osd_req_op_extent_update); +void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req, + unsigned int which, u64 offset_inc) +{ + struct ceph_osd_req_op *op, *prev_op; + + BUG_ON(which + 1 >= osd_req->r_num_ops); + + prev_op = &osd_req->r_ops[which]; + op = _osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags); + /* dup previous one */ + op->indata_len = prev_op->indata_len; + op->outdata_len = prev_op->outdata_len; + op->extent = prev_op->extent; + /* adjust offset */ + op->extent.offset += offset_inc; + op->extent.length -= offset_inc; + + if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL) + op->indata_len -= offset_inc; +} +EXPORT_SYMBOL(osd_req_op_extent_dup_last); + void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *class, const char *method) { @@ -554,7 +589,7 @@ void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, op->cls.argc = 0; /* currently unused */ - op->payload_len = payload_len; + op->indata_len = payload_len; } EXPORT_SYMBOL(osd_req_op_cls_init); @@ -587,7 +622,7 @@ int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, op->xattr.cmp_mode = cmp_mode; ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist); - op->payload_len = payload_len; + op->indata_len = payload_len; return 0; } EXPORT_SYMBOL(osd_req_op_xattr_init); @@ -707,7 +742,7 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, BUG_ON(osd_data->type == CEPH_OSD_DATA_TYPE_NONE); dst->cls.indata_len = cpu_to_le32(data_length); ceph_osdc_msg_data_add(req->r_request, osd_data); - src->payload_len += data_length; + src->indata_len += data_length; request_data_len += data_length; } osd_data = &src->cls.response_data; @@ -750,7 +785,7 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, dst->op = cpu_to_le16(src->op); dst->flags = cpu_to_le32(src->flags); - dst->payload_len = cpu_to_le32(src->payload_len); + dst->payload_len = cpu_to_le32(src->indata_len); return request_data_len; } @@ -1810,7 +1845,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) ceph_decode_need(&p, end, 4, bad_put); numops = ceph_decode_32(&p); - if (numops > CEPH_OSD_MAX_OP) + if (numops > CEPH_OSD_MAX_OPS) goto bad_put; if (numops != req->r_num_ops) goto bad_put; @@ -1821,7 +1856,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) int len; len = le32_to_cpu(op->payload_len); - req->r_reply_op_len[i] = len; + req->r_ops[i].outdata_len = len; dout(" op %d has %d bytes\n", i, len); payload_len += len; p += sizeof(*op); @@ -1836,7 +1871,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) ceph_decode_need(&p, end, 4 + numops * 4, bad_put); retry_attempt = ceph_decode_32(&p); for (i = 0; i < numops; i++) - req->r_reply_op_result[i] = ceph_decode_32(&p); + req->r_ops[i].rval = ceph_decode_32(&p); if (le16_to_cpu(msg->hdr.version) >= 6) { p += 8 + 4; /* skip replay_version */ @@ -2187,7 +2222,8 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) goto bad; done: downgrade_write(&osdc->map_sem); - ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch); + ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP, + osdc->osdmap->epoch); /* * subscribe to subsequent osdmap updates if full to ensure @@ -2646,8 +2682,8 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) round_jiffies_relative(osdc->client->options->osd_idle_ttl)); err = -ENOMEM; - osdc->req_mempool = mempool_create_kmalloc_pool(10, - sizeof(struct ceph_osd_request)); + osdc->req_mempool = mempool_create_slab_pool(10, + ceph_osd_request_cache); if (!osdc->req_mempool) goto out; @@ -2782,11 +2818,12 @@ EXPORT_SYMBOL(ceph_osdc_writepages); int ceph_osdc_setup(void) { + size_t size = sizeof(struct ceph_osd_request) + + CEPH_OSD_SLAB_OPS * sizeof(struct ceph_osd_req_op); + BUG_ON(ceph_osd_request_cache); - ceph_osd_request_cache = kmem_cache_create("ceph_osd_request", - sizeof (struct ceph_osd_request), - __alignof__(struct ceph_osd_request), - 0, NULL); + ceph_osd_request_cache = kmem_cache_create("ceph_osd_request", size, + 0, 0, NULL); return ceph_osd_request_cache ? 0 : -ENOMEM; } diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c index c7c220a736e5..6864007e64fc 100644 --- a/net/ceph/pagelist.c +++ b/net/ceph/pagelist.c @@ -56,7 +56,7 @@ int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len) size_t bit = pl->room; int ret; - memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), + memcpy(pl->mapped_tail + (pl->length & ~PAGE_MASK), buf, bit); pl->length += bit; pl->room -= bit; @@ -67,7 +67,7 @@ int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len) return ret; } - memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len); + memcpy(pl->mapped_tail + (pl->length & ~PAGE_MASK), buf, len); pl->length += len; pl->room -= len; return 0; diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index 10297f7a89ba..00d2601407c5 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -95,19 +95,19 @@ int ceph_copy_user_to_page_vector(struct page **pages, loff_t off, size_t len) { int i = 0; - int po = off & ~PAGE_CACHE_MASK; + int po = off & ~PAGE_MASK; int left = len; int l, bad; while (left > 0) { - l = min_t(int, PAGE_CACHE_SIZE-po, left); + l = min_t(int, PAGE_SIZE-po, left); bad = copy_from_user(page_address(pages[i]) + po, data, l); if (bad == l) return -EFAULT; data += l - bad; left -= l - bad; po += l - bad; - if (po == PAGE_CACHE_SIZE) { + if (po == PAGE_SIZE) { po = 0; i++; } @@ -121,17 +121,17 @@ void ceph_copy_to_page_vector(struct page **pages, loff_t off, size_t len) { int i = 0; - size_t po = off & ~PAGE_CACHE_MASK; + size_t po = off & ~PAGE_MASK; size_t left = len; while (left > 0) { - size_t l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + size_t l = min_t(size_t, PAGE_SIZE-po, left); memcpy(page_address(pages[i]) + po, data, l); data += l; left -= l; po += l; - if (po == PAGE_CACHE_SIZE) { + if (po == PAGE_SIZE) { po = 0; i++; } @@ -144,17 +144,17 @@ void ceph_copy_from_page_vector(struct page **pages, loff_t off, size_t len) { int i = 0; - size_t po = off & ~PAGE_CACHE_MASK; + size_t po = off & ~PAGE_MASK; size_t left = len; while (left > 0) { - size_t l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + size_t l = min_t(size_t, PAGE_SIZE-po, left); memcpy(data, page_address(pages[i]) + po, l); data += l; left -= l; po += l; - if (po == PAGE_CACHE_SIZE) { + if (po == PAGE_SIZE) { po = 0; i++; } @@ -168,25 +168,25 @@ EXPORT_SYMBOL(ceph_copy_from_page_vector); */ void ceph_zero_page_vector_range(int off, int len, struct page **pages) { - int i = off >> PAGE_CACHE_SHIFT; + int i = off >> PAGE_SHIFT; - off &= ~PAGE_CACHE_MASK; + off &= ~PAGE_MASK; dout("zero_page_vector_page %u~%u\n", off, len); /* leading partial page? */ if (off) { - int end = min((int)PAGE_CACHE_SIZE, off + len); + int end = min((int)PAGE_SIZE, off + len); dout("zeroing %d %p head from %d\n", i, pages[i], (int)off); zero_user_segment(pages[i], off, end); len -= (end - off); i++; } - while (len >= PAGE_CACHE_SIZE) { + while (len >= PAGE_SIZE) { dout("zeroing %d %p len=%d\n", i, pages[i], len); - zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE); - len -= PAGE_CACHE_SIZE; + zero_user_segment(pages[i], 0, PAGE_SIZE); + len -= PAGE_SIZE; i++; } /* trailing partial page? */ diff --git a/net/core/datagram.c b/net/core/datagram.c index fa9dc6450b08..b7de71f8d5d3 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -301,16 +301,19 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(skb_free_datagram); -void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) +void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) { bool slow; if (likely(atomic_read(&skb->users) == 1)) smp_rmb(); - else if (likely(!atomic_dec_and_test(&skb->users))) + else if (likely(!atomic_dec_and_test(&skb->users))) { + sk_peek_offset_bwd(sk, len); return; + } slow = lock_sock_fast(sk); + sk_peek_offset_bwd(sk, len); skb_orphan(skb); sk_mem_reclaim_partial(sk); unlock_sock_fast(sk, slow); @@ -318,7 +321,7 @@ void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) /* skb is now orphaned, can be freed outside of locked section */ __kfree_skb(skb); } -EXPORT_SYMBOL(skb_free_datagram_locked); +EXPORT_SYMBOL(__skb_free_datagram_locked); /** * skb_kill_datagram - Free a datagram skbuff forcibly diff --git a/net/core/dev.c b/net/core/dev.c index b9bcbe77d913..d51343a821ed 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4439,6 +4439,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; NAPI_GRO_CB(skb)->encap_mark = 0; + NAPI_GRO_CB(skb)->is_fou = 0; NAPI_GRO_CB(skb)->gro_remcsum_start = 0; /* Setup for GRO checksum validation */ @@ -4663,6 +4664,8 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) if (unlikely(skb_gro_header_hard(skb, hlen))) { eth = skb_gro_header_slow(skb, hlen, 0); if (unlikely(!eth)) { + net_warn_ratelimited("%s: dropping impossible skb from %s\n", + __func__, napi->dev->name); napi_reuse_skb(napi, skb); return NULL; } diff --git a/net/core/devlink.c b/net/core/devlink.c index 590fa561cb7f..b84cf0df4a0e 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -119,7 +119,8 @@ static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, return devlink_port_get_from_attrs(devlink, info->attrs); } -#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) +#define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0) +#define DEVLINK_NL_FLAG_NEED_PORT BIT(1) static int devlink_nl_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) @@ -132,8 +133,9 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops, mutex_unlock(&devlink_mutex); return PTR_ERR(devlink); } - info->user_ptr[0] = devlink; - if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) { + info->user_ptr[0] = devlink; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { struct devlink_port *devlink_port; mutex_lock(&devlink_port_mutex); @@ -143,7 +145,7 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops, mutex_unlock(&devlink_mutex); return PTR_ERR(devlink_port); } - info->user_ptr[1] = devlink_port; + info->user_ptr[0] = devlink_port; } return 0; } @@ -356,8 +358,8 @@ out: static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, struct genl_info *info) { - struct devlink *devlink = info->user_ptr[0]; - struct devlink_port *devlink_port = info->user_ptr[1]; + struct devlink_port *devlink_port = info->user_ptr[0]; + struct devlink *devlink = devlink_port->devlink; struct sk_buff *msg; int err; @@ -436,8 +438,8 @@ static int devlink_port_type_set(struct devlink *devlink, static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info) { - struct devlink *devlink = info->user_ptr[0]; - struct devlink_port *devlink_port = info->user_ptr[1]; + struct devlink_port *devlink_port = info->user_ptr[0]; + struct devlink *devlink = devlink_port->devlink; int err; if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { @@ -511,6 +513,7 @@ static const struct genl_ops devlink_nl_ops[] = { .doit = devlink_nl_cmd_get_doit, .dumpit = devlink_nl_cmd_get_dumpit, .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, { @@ -533,12 +536,14 @@ static const struct genl_ops devlink_nl_ops[] = { .doit = devlink_nl_cmd_port_split_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_PORT_UNSPLIT, .doit = devlink_nl_cmd_port_unsplit_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, }; @@ -630,7 +635,6 @@ int devlink_port_register(struct devlink *devlink, } devlink_port->devlink = devlink; devlink_port->index = port_index; - devlink_port->type = DEVLINK_PORT_TYPE_NOTSET; devlink_port->registered = true; list_add_tail(&devlink_port->list, &devlink->port_list); mutex_unlock(&devlink_port_mutex); diff --git a/net/core/filter.c b/net/core/filter.c index b7177d01ecb0..e8486ba601ea 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1166,7 +1166,7 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) } old_fp = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) @@ -1764,6 +1764,7 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { case offsetof(struct bpf_tunnel_key, tunnel_label): + case offsetof(struct bpf_tunnel_key, tunnel_ext): goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have @@ -1849,6 +1850,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { case offsetof(struct bpf_tunnel_key, tunnel_label): + case offsetof(struct bpf_tunnel_key, tunnel_ext): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. @@ -1861,7 +1863,8 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return -EINVAL; } } - if (unlikely(!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label)) + if (unlikely((!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label) || + from->tunnel_ext)) return -EINVAL; skb_dst_drop(skb); @@ -2256,7 +2259,7 @@ int sk_detach_filter(struct sock *sk) return -EPERM; filter = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + lockdep_sock_is_held(sk)); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); @@ -2276,7 +2279,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, lock_sock(sk); filter = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + lockdep_sock_is_held(sk)); if (!filter) goto out; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f2066772d0f3..a75f7e94b445 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -909,6 +909,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } diff --git a/net/core/sock.c b/net/core/sock.c index b67b9aedb230..e16a5db853c6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -221,7 +221,8 @@ static const char *const af_family_key_strings[AF_MAX+1] = { "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , - "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_MAX" + "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" , + "sk_lock-AF_MAX" }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , @@ -237,7 +238,8 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , - "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_MAX" + "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" , + "slock-AF_MAX" }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , @@ -253,7 +255,8 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , - "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_MAX" + "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" , + "clock-AF_MAX" }; /* @@ -402,9 +405,8 @@ static void sock_disable_timestamp(struct sock *sk, unsigned long flags) } -int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int err; unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; @@ -414,10 +416,6 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return -ENOMEM; } - err = sk_filter(sk, skb); - if (err) - return err; - if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; @@ -440,6 +438,18 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk->sk_data_ready(sk); return 0; } +EXPORT_SYMBOL(__sock_queue_rcv_skb); + +int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + int err; + + err = sk_filter(sk, skb); + if (err) + return err; + + return __sock_queue_rcv_skb(sk, skb); +} EXPORT_SYMBOL(sock_queue_rcv_skb); int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) @@ -832,7 +842,8 @@ set_rcvbuf: !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { - if (sk->sk_state != TCP_ESTABLISHED) { + if ((1 << sk->sk_state) & + (TCPF_CLOSE | TCPF_LISTEN)) { ret = -EINVAL; break; } @@ -1418,8 +1429,12 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, } EXPORT_SYMBOL(sk_alloc); -void sk_destruct(struct sock *sk) +/* Sockets having SOCK_RCU_FREE will call this function after one RCU + * grace period. This is the case for UDP sockets and TCP listeners. + */ +static void __sk_destruct(struct rcu_head *head) { + struct sock *sk = container_of(head, struct sock, sk_rcu); struct sk_filter *filter; if (sk->sk_destruct) @@ -1448,6 +1463,14 @@ void sk_destruct(struct sock *sk) sk_prot_free(sk->sk_prot_creator, sk); } +void sk_destruct(struct sock *sk) +{ + if (sock_flag(sk, SOCK_RCU_FREE)) + call_rcu(&sk->sk_rcu, __sk_destruct); + else + __sk_destruct(&sk->sk_rcu); +} + static void __sk_free(struct sock *sk) { if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt)) @@ -1512,6 +1535,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_dst_cache = NULL; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; + atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; @@ -1866,27 +1890,51 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, } EXPORT_SYMBOL(sock_alloc_send_skb); +int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, + struct sockcm_cookie *sockc) +{ + u32 tsflags; + + switch (cmsg->cmsg_type) { + case SO_MARK: + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + sockc->mark = *(u32 *)CMSG_DATA(cmsg); + break; + case SO_TIMESTAMPING: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + + tsflags = *(u32 *)CMSG_DATA(cmsg); + if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK) + return -EINVAL; + + sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; + sockc->tsflags |= tsflags; + break; + default: + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL(__sock_cmsg_send); + int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc) { struct cmsghdr *cmsg; + int ret; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_SOCKET) continue; - switch (cmsg->cmsg_type) { - case SO_MARK: - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) - return -EPERM; - if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) - return -EINVAL; - sockc->mark = *(u32 *)CMSG_DATA(cmsg); - break; - default: - return -EINVAL; - } + ret = __sock_cmsg_send(sk, msg, cmsg, sockc); + if (ret) + return ret; } return 0; } @@ -2142,6 +2190,15 @@ void __sk_mem_reclaim(struct sock *sk, int amount) } EXPORT_SYMBOL(__sk_mem_reclaim); +int sk_set_peek_off(struct sock *sk, int val) +{ + if (val < 0) + return -EINVAL; + + sk->sk_peek_off = val; + return 0; +} +EXPORT_SYMBOL_GPL(sk_set_peek_off); /* * Set of default routines for initialising struct proto_ops when @@ -2429,11 +2486,6 @@ EXPORT_SYMBOL(lock_sock_nested); void release_sock(struct sock *sk) { - /* - * The sk_lock has mutex_unlock() semantics: - */ - mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); - spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index a996ce8c8fb2..ca9e35bbe13c 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -67,6 +67,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); return nla_put(skb, attrtype, sizeof(mem), &mem); } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 9c67a961ba53..f6d183f8f332 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -62,7 +62,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) nexthop = daddr = usin->sin_addr.s_addr; inet_opt = rcu_dereference_protected(inet->inet_opt, - sock_owned_by_user(sk)); + lockdep_sock_is_held(sk)); if (inet_opt != NULL && inet_opt->opt.srr) { if (daddr == 0) return -EINVAL; @@ -764,6 +764,7 @@ static int dccp_v4_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; const struct iphdr *iph; + bool refcounted; struct sock *sk; int min_cov; @@ -801,7 +802,7 @@ static int dccp_v4_rcv(struct sk_buff *skb) lookup: sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), - dh->dccph_sport, dh->dccph_dport); + dh->dccph_sport, dh->dccph_dport, &refcounted); if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); @@ -830,6 +831,7 @@ lookup: goto lookup; } sock_hold(sk); + refcounted = true; nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); @@ -886,7 +888,8 @@ discard_it: return 0; discard_and_relse: - sock_put(sk); + if (refcounted) + sock_put(sk); goto discard_it; } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 4663a01d5039..8ceb3cebcad4 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -642,6 +642,7 @@ discard: static int dccp_v6_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; + bool refcounted; struct sock *sk; int min_cov; @@ -670,7 +671,7 @@ static int dccp_v6_rcv(struct sk_buff *skb) lookup: sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), dh->dccph_sport, dh->dccph_dport, - inet6_iif(skb)); + inet6_iif(skb), &refcounted); if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); @@ -699,6 +700,7 @@ lookup: goto lookup; } sock_hold(sk); + refcounted = true; nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); @@ -752,7 +754,8 @@ discard_it: return 0; discard_and_relse: - sock_put(sk); + if (refcounted) + sock_put(sk); goto discard_it; } @@ -865,7 +868,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.fl6_sport = inet->inet_sport; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); dst = ip6_dst_lookup_flow(sk, &fl6, final_p); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a575f0350d5a..2dae0d064359 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -104,8 +104,8 @@ static int dsa_slave_open(struct net_device *dev) goto clear_promisc; } - if (ds->drv->port_stp_update) - ds->drv->port_stp_update(ds, p->port, stp_state); + if (ds->drv->port_stp_state_set) + ds->drv->port_stp_state_set(ds, p->port, stp_state); if (p->phy) phy_start(p->phy); @@ -147,8 +147,8 @@ static int dsa_slave_close(struct net_device *dev) if (ds->drv->port_disable) ds->drv->port_disable(ds, p->port, p->phy); - if (ds->drv->port_stp_update) - ds->drv->port_stp_update(ds, p->port, BR_STATE_DISABLED); + if (ds->drv->port_stp_state_set) + ds->drv->port_stp_state_set(ds, p->port, BR_STATE_DISABLED); return 0; } @@ -207,21 +207,16 @@ static int dsa_slave_port_vlan_add(struct net_device *dev, { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - int err; if (switchdev_trans_ph_prepare(trans)) { if (!ds->drv->port_vlan_prepare || !ds->drv->port_vlan_add) return -EOPNOTSUPP; - err = ds->drv->port_vlan_prepare(ds, p->port, vlan, trans); - if (err) - return err; - } else { - err = ds->drv->port_vlan_add(ds, p->port, vlan, trans); - if (err) - return err; + return ds->drv->port_vlan_prepare(ds, p->port, vlan, trans); } + ds->drv->port_vlan_add(ds, p->port, vlan, trans); + return 0; } @@ -256,17 +251,17 @@ static int dsa_slave_port_fdb_add(struct net_device *dev, { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - int ret; - if (!ds->drv->port_fdb_prepare || !ds->drv->port_fdb_add) - return -EOPNOTSUPP; + if (switchdev_trans_ph_prepare(trans)) { + if (!ds->drv->port_fdb_prepare || !ds->drv->port_fdb_add) + return -EOPNOTSUPP; - if (switchdev_trans_ph_prepare(trans)) - ret = ds->drv->port_fdb_prepare(ds, p->port, fdb, trans); - else - ret = ds->drv->port_fdb_add(ds, p->port, fdb, trans); + return ds->drv->port_fdb_prepare(ds, p->port, fdb, trans); + } - return ret; + ds->drv->port_fdb_add(ds, p->port, fdb, trans); + + return 0; } static int dsa_slave_port_fdb_del(struct net_device *dev, @@ -305,16 +300,19 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EOPNOTSUPP; } -static int dsa_slave_stp_update(struct net_device *dev, u8 state) +static int dsa_slave_stp_state_set(struct net_device *dev, + const struct switchdev_attr *attr, + struct switchdev_trans *trans) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - int ret = -EOPNOTSUPP; - if (ds->drv->port_stp_update) - ret = ds->drv->port_stp_update(ds, p->port, state); + if (switchdev_trans_ph_prepare(trans)) + return ds->drv->port_stp_state_set ? 0 : -EOPNOTSUPP; - return ret; + ds->drv->port_stp_state_set(ds, p->port, attr->u.stp_state); + + return 0; } static int dsa_slave_vlan_filtering(struct net_device *dev, @@ -339,17 +337,11 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->parent; int ret; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: - if (switchdev_trans_ph_prepare(trans)) - ret = ds->drv->port_stp_update ? 0 : -EOPNOTSUPP; - else - ret = ds->drv->port_stp_update(ds, p->port, - attr->u.stp_state); + ret = dsa_slave_stp_state_set(dev, attr, trans); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: ret = dsa_slave_vlan_filtering(dev, attr, trans); @@ -468,7 +460,8 @@ static void dsa_slave_bridge_port_leave(struct net_device *dev) /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, * so allow it to be in BR_STATE_FORWARDING to be kept functional */ - dsa_slave_stp_update(dev, BR_STATE_FORWARDING); + if (ds->drv->port_stp_state_set) + ds->drv->port_stp_state_set(ds, p->port, BR_STATE_FORWARDING); } static int dsa_slave_port_attr_get(struct net_device *dev, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9e481992dbae..8217cd22f921 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -948,6 +948,7 @@ const struct proto_ops inet_dgram_ops = { .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, + .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, @@ -1106,7 +1107,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) struct ip_options_rcu *inet_opt; inet_opt = rcu_dereference_protected(inet->inet_opt, - sock_owned_by_user(sk)); + lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index bdb2a07ec363..40d6b87713a1 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1933,7 +1933,8 @@ int cipso_v4_sock_setattr(struct sock *sk, sk_inet = inet_sk(sk); - old = rcu_dereference_protected(sk_inet->inet_opt, sock_owned_by_user(sk)); + old = rcu_dereference_protected(sk_inet->inet_opt, + lockdep_sock_is_held(sk)); if (sk_inet->is_icsk) { sk_conn = inet_csk(sk); if (old) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index d97268e8ff10..ab64d9f2eef9 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1559,21 +1559,45 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags) } #ifdef CONFIG_IP_ROUTE_MULTIPATH +static bool fib_good_nh(const struct fib_nh *nh) +{ + int state = NUD_REACHABLE; + + if (nh->nh_scope == RT_SCOPE_LINK) { + struct neighbour *n; + + rcu_read_lock_bh(); + + n = __ipv4_neigh_lookup_noref(nh->nh_dev, nh->nh_gw); + if (n) + state = n->nud_state; + + rcu_read_unlock_bh(); + } + + return !!(state & NUD_VALID); +} void fib_select_multipath(struct fib_result *res, int hash) { struct fib_info *fi = res->fi; + struct net *net = fi->fib_net; + bool first = false; for_nexthops(fi) { if (hash > atomic_read(&nh->nh_upper_bound)) continue; - res->nh_sel = nhsel; - return; + if (!net->ipv4.sysctl_fib_multipath_use_neigh || + fib_good_nh(nh)) { + res->nh_sel = nhsel; + return; + } + if (!first) { + res->nh_sel = nhsel; + first = true; + } } endfor_nexthops(fi); - - /* Race condition: route has just become dead. */ - res->nh_sel = 0; } #endif diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index a0586b4a197d..d039f8fff57f 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -22,7 +22,6 @@ struct fou { u8 flags; __be16 port; u16 type; - struct udp_offload udp_offloads; struct list_head list; struct rcu_head rcu; }; @@ -186,15 +185,26 @@ drop: return 0; } -static struct sk_buff **fou_gro_receive(struct sk_buff **head, - struct sk_buff *skb, - struct udp_offload *uoff) +static struct sk_buff **fou_gro_receive(struct sock *sk, + struct sk_buff **head, + struct sk_buff *skb) { const struct net_offload *ops; struct sk_buff **pp = NULL; - u8 proto = NAPI_GRO_CB(skb)->proto; + u8 proto = fou_from_sock(sk)->protocol; const struct net_offload **offloads; + /* We can clear the encap_mark for FOU as we are essentially doing + * one of two possible things. We are either adding an L4 tunnel + * header to the outer L3 tunnel header, or we are are simply + * treating the GRE tunnel header as though it is a UDP protocol + * specific header such as VXLAN or GENEVE. + */ + NAPI_GRO_CB(skb)->encap_mark = 0; + + /* Flag this frame as already having an outer encap header */ + NAPI_GRO_CB(skb)->is_fou = 1; + rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); @@ -209,11 +219,11 @@ out_unlock: return pp; } -static int fou_gro_complete(struct sk_buff *skb, int nhoff, - struct udp_offload *uoff) +static int fou_gro_complete(struct sock *sk, struct sk_buff *skb, + int nhoff) { const struct net_offload *ops; - u8 proto = NAPI_GRO_CB(skb)->proto; + u8 proto = fou_from_sock(sk)->protocol; int err = -ENOSYS; const struct net_offload **offloads; @@ -256,9 +266,9 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, return guehdr; } -static struct sk_buff **gue_gro_receive(struct sk_buff **head, - struct sk_buff *skb, - struct udp_offload *uoff) +static struct sk_buff **gue_gro_receive(struct sock *sk, + struct sk_buff **head, + struct sk_buff *skb) { const struct net_offload **offloads; const struct net_offload *ops; @@ -269,7 +279,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, void *data; u16 doffset = 0; int flush = 1; - struct fou *fou = container_of(uoff, struct fou, udp_offloads); + struct fou *fou = fou_from_sock(sk); struct gro_remcsum grc; skb_gro_remcsum_init(&grc); @@ -352,6 +362,17 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, } } + /* We can clear the encap_mark for GUE as we are essentially doing + * one of two possible things. We are either adding an L4 tunnel + * header to the outer L3 tunnel header, or we are are simply + * treating the GRE tunnel header as though it is a UDP protocol + * specific header such as VXLAN or GENEVE. + */ + NAPI_GRO_CB(skb)->encap_mark = 0; + + /* Flag this frame as already having an outer encap header */ + NAPI_GRO_CB(skb)->is_fou = 1; + rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[guehdr->proto_ctype]); @@ -370,8 +391,7 @@ out: return pp; } -static int gue_gro_complete(struct sk_buff *skb, int nhoff, - struct udp_offload *uoff) +static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { const struct net_offload **offloads; struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff); @@ -419,10 +439,7 @@ static int fou_add_to_port_list(struct net *net, struct fou *fou) static void fou_release(struct fou *fou) { struct socket *sock = fou->sock; - struct sock *sk = sock->sk; - if (sk->sk_family == AF_INET) - udp_del_offload(&fou->udp_offloads); list_del(&fou->list); udp_tunnel_sock_release(sock); @@ -432,11 +449,9 @@ static void fou_release(struct fou *fou) static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg) { udp_sk(sk)->encap_rcv = fou_udp_recv; - fou->protocol = cfg->protocol; - fou->udp_offloads.callbacks.gro_receive = fou_gro_receive; - fou->udp_offloads.callbacks.gro_complete = fou_gro_complete; - fou->udp_offloads.port = cfg->udp_config.local_udp_port; - fou->udp_offloads.ipproto = cfg->protocol; + udp_sk(sk)->gro_receive = fou_gro_receive; + udp_sk(sk)->gro_complete = fou_gro_complete; + fou_from_sock(sk)->protocol = cfg->protocol; return 0; } @@ -444,9 +459,8 @@ static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg) static int gue_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg) { udp_sk(sk)->encap_rcv = gue_udp_recv; - fou->udp_offloads.callbacks.gro_receive = gue_gro_receive; - fou->udp_offloads.callbacks.gro_complete = gue_gro_complete; - fou->udp_offloads.port = cfg->udp_config.local_udp_port; + udp_sk(sk)->gro_receive = gue_gro_receive; + udp_sk(sk)->gro_complete = gue_gro_complete; return 0; } @@ -505,12 +519,6 @@ static int fou_create(struct net *net, struct fou_cfg *cfg, sk->sk_allocation = GFP_ATOMIC; - if (cfg->udp_config.family == AF_INET) { - err = udp_add_offload(net, &fou->udp_offloads); - if (err) - goto error; - } - err = fou_add_to_port_list(net, fou); if (err) goto error; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index c47539d04b88..6a5bd4317866 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -150,6 +150,14 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0) goto out; + /* We can only support GRE_CSUM if we can track the location of + * the GRE header. In the case of FOU/GUE we cannot because the + * outer UDP header displaces the GRE header leaving us in a state + * of limbo. + */ + if ((greh->flags & GRE_CSUM) && NAPI_GRO_CB(skb)->is_fou) + goto out; + type = greh->protocol; rcu_read_lock(); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index bc5196ea1bdf..ab69da2d2a77 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -661,6 +661,9 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); newsk->sk_write_space = sk_stream_write_space; + /* listeners have SOCK_RCU_FREE, not the children */ + sock_reset_flag(newsk, SOCK_RCU_FREE); + newsk->sk_mark = inet_rsk(req)->ir_mark; atomic64_set(&newsk->sk_cookie, atomic64_read(&inet_rsk(req)->ir_cookie)); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 5fdb02f5598e..bd591eb81ec9 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -356,6 +356,7 @@ struct sock *inet_diag_find_one_icsk(struct net *net, { struct sock *sk; + rcu_read_lock(); if (req->sdiag_family == AF_INET) sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], @@ -376,9 +377,11 @@ struct sock *inet_diag_find_one_icsk(struct net *net, req->id.idiag_if); } #endif - else + else { + rcu_read_unlock(); return ERR_PTR(-EINVAL); - + } + rcu_read_unlock(); if (!sk) return ERR_PTR(-ENOENT); @@ -772,13 +775,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; - struct hlist_nulls_node *node; struct sock *sk; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock_bh(&ilb->lock); - sk_nulls_for_each(sk, node, &ilb->head) { + sk_for_each(sk, &ilb->head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index bc68eced0105..fcadb670f50b 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -198,13 +198,13 @@ static inline int compute_score(struct sock *sk, struct net *net, } /* - * Don't inline this cruft. Here are some nice properties to exploit here. The - * BSD API does not allow a listening sock to specify the remote port nor the + * Here are some nice properties to exploit here. The BSD API + * does not allow a listening sock to specify the remote port nor the * remote address for the connection. So always assume those are both * wildcarded during the search since they can never be otherwise. */ - +/* called with rcu_read_lock() : No refcount taken on the socket */ struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, @@ -212,38 +212,27 @@ struct sock *__inet_lookup_listener(struct net *net, const __be32 daddr, const unsigned short hnum, const int dif) { - struct sock *sk, *result; - struct hlist_nulls_node *node; unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; - int score, hiscore, matches = 0, reuseport = 0; - bool select_ok = true; + int score, hiscore = 0, matches = 0, reuseport = 0; + struct sock *sk, *result = NULL; u32 phash = 0; - rcu_read_lock(); -begin: - result = NULL; - hiscore = 0; - sk_nulls_for_each_rcu(sk, node, &ilb->head) { + sk_for_each_rcu(sk, &ilb->head) { score = compute_score(sk, net, hnum, daddr, dif); if (score > hiscore) { - result = sk; - hiscore = score; reuseport = sk->sk_reuseport; if (reuseport) { phash = inet_ehashfn(net, daddr, hnum, saddr, sport); - if (select_ok) { - struct sock *sk2; - sk2 = reuseport_select_sock(sk, phash, - skb, doff); - if (sk2) { - result = sk2; - goto found; - } - } + result = reuseport_select_sock(sk, phash, + skb, doff); + if (result) + return result; matches = 1; } + result = sk; + hiscore = score; } else if (score == hiscore && reuseport) { matches++; if (reciprocal_scale(phash, matches) == 0) @@ -251,25 +240,6 @@ begin: phash = next_pseudo_random32(phash); } } - /* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE) - goto begin; - if (result) { -found: - if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) - result = NULL; - else if (unlikely(compute_score(result, net, hnum, daddr, - dif) < hiscore)) { - sock_put(result); - select_ok = false; - goto begin; - } - } - rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(__inet_lookup_listener); @@ -312,7 +282,6 @@ struct sock *__inet_lookup_established(struct net *net, unsigned int slot = hash & hashinfo->ehash_mask; struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; - rcu_read_lock(); begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_hash != hash) @@ -339,7 +308,6 @@ begin: out: sk = NULL; found: - rcu_read_unlock(); return sk; } EXPORT_SYMBOL_GPL(__inet_lookup_established); @@ -471,10 +439,9 @@ static int inet_reuseport_add_sock(struct sock *sk, bool match_wildcard)) { struct sock *sk2; - struct hlist_nulls_node *node; kuid_t uid = sock_i_uid(sk); - sk_nulls_for_each_rcu(sk2, node, &ilb->head) { + sk_for_each_rcu(sk2, &ilb->head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -512,7 +479,8 @@ int __inet_hash(struct sock *sk, struct sock *osk, if (err) goto unlock; } - __sk_nulls_add_node_rcu(sk, &ilb->head); + hlist_add_head_rcu(&sk->sk_node, &ilb->head); + sock_set_flag(sk, SOCK_RCU_FREE); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); unlock: spin_unlock(&ilb->lock); @@ -539,20 +507,25 @@ void inet_unhash(struct sock *sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; spinlock_t *lock; + bool listener = false; int done; if (sk_unhashed(sk)) return; - if (sk->sk_state == TCP_LISTEN) + if (sk->sk_state == TCP_LISTEN) { lock = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)].lock; - else + listener = true; + } else { lock = inet_ehash_lockp(hashinfo, sk->sk_hash); - + } spin_lock_bh(lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - done = __sk_nulls_del_node_init_rcu(sk); + if (listener) + done = __sk_del_node_init(sk); + else + done = __sk_nulls_del_node_init_rcu(sk); if (done) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock_bh(lock); @@ -688,9 +661,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].head, - i + LISTENING_NULLS_BASE); - } + INIT_HLIST_HEAD(&h->listening_hash[i].head); + } } EXPORT_SYMBOL_GPL(inet_hashinfo_init); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 31936d387cfd..af5d1f38217f 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -862,9 +862,16 @@ static void __gre_tunnel_init(struct net_device *dev) dev->hw_features |= GRE_FEATURES; if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) { - /* TCP offload with GRE SEQ is not supported. */ - dev->features |= NETIF_F_GSO_SOFTWARE; - dev->hw_features |= NETIF_F_GSO_SOFTWARE; + /* TCP offload with GRE SEQ is not supported, nor + * can we support 2 levels of outer headers requiring + * an update. + */ + if (!(tunnel->parms.o_flags & TUNNEL_CSUM) || + (tunnel->encap.type == TUNNEL_ENCAP_NONE)) { + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + } + /* Can use a lockless transmit, unless we generate * output sequences */ diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 035ad645a8d9..89b5f3bd6694 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -219,11 +219,12 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, } EXPORT_SYMBOL(ip_cmsg_recv_offset); -int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, +int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6) { int err, val; struct cmsghdr *cmsg; + struct net *net = sock_net(sk); for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -244,6 +245,12 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, continue; } #endif + if (cmsg->cmsg_level == SOL_SOCKET) { + if (__sock_cmsg_send(sk, msg, cmsg, &ipc->sockc)) + return -EINVAL; + continue; + } + if (cmsg->cmsg_level != SOL_IP) continue; switch (cmsg->cmsg_type) { @@ -635,7 +642,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, if (err) break; old = rcu_dereference_protected(inet->inet_opt, - sock_owned_by_user(sk)); + lockdep_sock_is_held(sk)); if (inet->is_icsk) { struct inet_connection_sock *icsk = inet_csk(sk); #if IS_ENABLED(CONFIG_IPV6) @@ -1295,7 +1302,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, struct ip_options_rcu *inet_opt; inet_opt = rcu_dereference_protected(inet->inet_opt, - sock_owned_by_user(sk)); + lockdep_sock_is_held(sk)); opt->optlen = 0; if (inet_opt) memcpy(optbuf, &inet_opt->opt, diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 02dd990af542..43445df61efd 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -86,15 +86,15 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, } EXPORT_SYMBOL_GPL(iptunnel_xmit); -int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, - bool xnet) +int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len, + __be16 inner_proto, bool raw_proto, bool xnet) { if (unlikely(!pskb_may_pull(skb, hdr_len))) return -ENOMEM; skb_pull_rcsum(skb, hdr_len); - if (inner_proto == htons(ETH_P_TEB)) { + if (!raw_proto && inner_proto == htons(ETH_P_TEB)) { struct ethhdr *eh; if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) @@ -117,7 +117,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, return iptunnel_pull_offloads(skb); } -EXPORT_SYMBOL_GPL(iptunnel_pull_header); +EXPORT_SYMBOL_GPL(__iptunnel_pull_header); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags) @@ -247,10 +247,10 @@ static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP_ID]); if (tb[LWTUNNEL_IP_DST]) - tun_info->key.u.ipv4.dst = nla_get_be32(tb[LWTUNNEL_IP_DST]); + tun_info->key.u.ipv4.dst = nla_get_in_addr(tb[LWTUNNEL_IP_DST]); if (tb[LWTUNNEL_IP_SRC]) - tun_info->key.u.ipv4.src = nla_get_be32(tb[LWTUNNEL_IP_SRC]); + tun_info->key.u.ipv4.src = nla_get_in_addr(tb[LWTUNNEL_IP_SRC]); if (tb[LWTUNNEL_IP_TTL]) tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP_TTL]); @@ -275,8 +275,8 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); if (nla_put_be64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id) || - nla_put_be32(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) || - nla_put_be32(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || + nla_put_in_addr(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) || + nla_put_in_addr(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_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags)) @@ -372,8 +372,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id) || nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) || 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_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) || + nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) || nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index bf081927e06b..4133b0f513af 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -359,11 +359,12 @@ unsigned int arpt_do_table(struct sk_buff *skb, } /* All zeroes == unconditional rule. */ -static inline bool unconditional(const struct arpt_arp *arp) +static inline bool unconditional(const struct arpt_entry *e) { static const struct arpt_arp uncond; - return memcmp(arp, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct arpt_entry) && + memcmp(&e->arp, &uncond, sizeof(uncond)) == 0; } /* Figures out from what hook each rule can be called: returns 0 if @@ -402,11 +403,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo, |= ((1 << hook) | (1 << NF_ARP_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct arpt_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && unconditional(&e->arp)) || - visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -474,14 +474,12 @@ next: return 1; } -static inline int check_entry(const struct arpt_entry *e, const char *name) +static inline int check_entry(const struct arpt_entry *e) { const struct xt_entry_target *t; - if (!arp_checkentry(&e->arp)) { - duprintf("arp_tables: arp check failed %p %s.\n", e, name); + if (!arp_checkentry(&e->arp)) return -EINVAL; - } if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) return -EINVAL; @@ -522,10 +520,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size) struct xt_target *target; int ret; - ret = check_entry(e, name); - if (ret) - return ret; - e->counters.pcnt = xt_percpu_counter_alloc(); if (IS_ERR_VALUE(e->counters.pcnt)) return -ENOMEM; @@ -557,7 +551,7 @@ static bool check_underflow(const struct arpt_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->arp)) + if (!unconditional(e)) return false; t = arpt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -576,9 +570,11 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || - (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { + (unsigned char *)e + sizeof(struct arpt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -590,6 +586,10 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, return -EINVAL; } + err = check_entry(e); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_ARP_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -598,9 +598,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; @@ -969,6 +969,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, sizeof(struct arpt_get_entries) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR_OR_NULL(t)) { @@ -1233,7 +1234,8 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } @@ -1246,7 +1248,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, } /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct arpt_entry *)e, name); + ret = check_entry((struct arpt_entry *)e); if (ret) return ret; @@ -1662,6 +1664,7 @@ static int compat_get_entries(struct net *net, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(NFPROTO_ARP); t = xt_find_table_lock(net, NFPROTO_ARP, get.name); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e53f8d6f326d..631c100a1338 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline bool unconditional(const struct ipt_ip *ip) +static inline bool unconditional(const struct ipt_entry *e) { static const struct ipt_ip uncond; - return memcmp(ip, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct ipt_entry) && + memcmp(&e->ip, &uncond, sizeof(uncond)) == 0; #undef FWINV } @@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ipt_entry) && + if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && - t->verdict < 0 && - unconditional(&s->ip)) { + t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] @@ -476,11 +476,10 @@ mark_source_chains(const struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ipt_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && unconditional(&e->ip)) || - visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -569,14 +568,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net) } static int -check_entry(const struct ipt_entry *e, const char *name) +check_entry(const struct ipt_entry *e) { const struct xt_entry_target *t; - if (!ip_checkentry(&e->ip)) { - duprintf("ip check failed %p %s.\n", e, name); + if (!ip_checkentry(&e->ip)) return -EINVAL; - } if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) @@ -666,10 +663,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; - ret = check_entry(e, name); - if (ret) - return ret; - e->counters.pcnt = xt_percpu_counter_alloc(); if (IS_ERR_VALUE(e->counters.pcnt)) return -ENOMEM; @@ -721,7 +714,7 @@ static bool check_underflow(const struct ipt_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->ip)) + if (!unconditional(e)) return false; t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -741,9 +734,11 @@ check_entry_size_and_hooks(struct ipt_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || - (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { + (unsigned char *)e + sizeof(struct ipt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -755,6 +750,10 @@ check_entry_size_and_hooks(struct ipt_entry *e, return -EINVAL; } + err = check_entry(e); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -763,9 +762,9 @@ check_entry_size_and_hooks(struct ipt_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; @@ -1157,6 +1156,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR_OR_NULL(t)) { @@ -1493,7 +1493,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } @@ -1506,7 +1507,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, } /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct ipt_entry *)e, name); + ret = check_entry((struct ipt_entry *)e); if (ret) return ret; @@ -1935,6 +1936,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 7b8fbb352877..db5b87509446 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -18,10 +18,10 @@ #include <net/netfilter/nf_conntrack_synproxy.h> static struct iphdr * -synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr) +synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr, + __be32 daddr) { struct iphdr *iph; - struct net *net = sock_net(skb->sk); skb_reset_network_header(skb); iph = (struct iphdr *)skb_put(skb, sizeof(*iph)); @@ -40,14 +40,12 @@ synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr) } static void -synproxy_send_tcp(const struct synproxy_net *snet, +synproxy_send_tcp(struct net *net, const struct sk_buff *skb, struct sk_buff *nskb, struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, struct iphdr *niph, struct tcphdr *nth, unsigned int tcp_hdr_size) { - struct net *net = nf_ct_net(snet->tmpl); - nth->check = ~tcp_v4_check(tcp_hdr_size, niph->saddr, niph->daddr, 0); nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (unsigned char *)nth - nskb->head; @@ -72,7 +70,7 @@ free_nskb: } static void -synproxy_send_client_synack(const struct synproxy_net *snet, +synproxy_send_client_synack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { @@ -91,7 +89,7 @@ synproxy_send_client_synack(const struct synproxy_net *snet, return; skb_reserve(nskb, MAX_TCP_HEADER); - niph = synproxy_build_ip(nskb, iph->daddr, iph->saddr); + niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); @@ -109,15 +107,16 @@ synproxy_send_client_synack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + synproxy_send_tcp(net, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } static void -synproxy_send_server_syn(const struct synproxy_net *snet, +synproxy_send_server_syn(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts, u32 recv_seq) { + struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *nskb; struct iphdr *iph, *niph; struct tcphdr *nth; @@ -132,7 +131,7 @@ synproxy_send_server_syn(const struct synproxy_net *snet, return; skb_reserve(nskb, MAX_TCP_HEADER); - niph = synproxy_build_ip(nskb, iph->saddr, iph->daddr); + niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); @@ -153,12 +152,12 @@ synproxy_send_server_syn(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(snet, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, + synproxy_send_tcp(net, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, niph, nth, tcp_hdr_size); } static void -synproxy_send_server_ack(const struct synproxy_net *snet, +synproxy_send_server_ack(struct net *net, const struct ip_ct_tcp *state, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) @@ -177,7 +176,7 @@ synproxy_send_server_ack(const struct synproxy_net *snet, return; skb_reserve(nskb, MAX_TCP_HEADER); - niph = synproxy_build_ip(nskb, iph->daddr, iph->saddr); + niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); @@ -193,11 +192,11 @@ synproxy_send_server_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(snet, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); + synproxy_send_tcp(net, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); } static void -synproxy_send_client_ack(const struct synproxy_net *snet, +synproxy_send_client_ack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { @@ -215,7 +214,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet, return; skb_reserve(nskb, MAX_TCP_HEADER); - niph = synproxy_build_ip(nskb, iph->saddr, iph->daddr); + niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); @@ -231,15 +230,16 @@ synproxy_send_client_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + synproxy_send_tcp(net, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } static bool -synproxy_recv_client_ack(const struct synproxy_net *snet, +synproxy_recv_client_ack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq) { + struct synproxy_net *snet = synproxy_pernet(net); int mss; mss = __cookie_v4_check(ip_hdr(skb), th, ntohl(th->ack_seq) - 1); @@ -255,7 +255,7 @@ synproxy_recv_client_ack(const struct synproxy_net *snet, if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_check_timestamp_cookie(opts); - synproxy_send_server_syn(snet, skb, th, opts, recv_seq); + synproxy_send_server_syn(net, skb, th, opts, recv_seq); return true; } @@ -263,7 +263,8 @@ static unsigned int synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_synproxy_info *info = par->targinfo; - struct synproxy_net *snet = synproxy_pernet(par->net); + struct net *net = par->net; + struct synproxy_net *snet = synproxy_pernet(net); struct synproxy_options opts = {}; struct tcphdr *th, _th; @@ -292,12 +293,12 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) XT_SYNPROXY_OPT_SACK_PERM | XT_SYNPROXY_OPT_ECN); - synproxy_send_client_synack(snet, skb, th, &opts); + synproxy_send_client_synack(net, skb, th, &opts); return NF_DROP; } else if (th->ack && !(th->fin || th->rst || th->syn)) { /* ACK from client */ - synproxy_recv_client_ack(snet, skb, th, &opts, ntohl(th->seq)); + synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq)); return NF_DROP; } @@ -308,7 +309,8 @@ static unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs) { - struct synproxy_net *snet = synproxy_pernet(nhs->net); + struct net *net = nhs->net; + struct synproxy_net *snet = synproxy_pernet(net); enum ip_conntrack_info ctinfo; struct nf_conn *ct; struct nf_conn_synproxy *synproxy; @@ -365,7 +367,7 @@ static unsigned int ipv4_synproxy_hook(void *priv, * therefore we need to add 1 to make the SYN sequence * number match the one of first SYN. */ - if (synproxy_recv_client_ack(snet, skb, th, &opts, + if (synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq) + 1)) this_cpu_inc(snet->stats->cookie_retrans); @@ -391,12 +393,12 @@ static unsigned int ipv4_synproxy_hook(void *priv, XT_SYNPROXY_OPT_SACK_PERM); swap(opts.tsval, opts.tsecr); - synproxy_send_server_ack(snet, state, skb, th, &opts); + synproxy_send_server_ack(net, state, skb, th, &opts); nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq)); swap(opts.tsval, opts.tsecr); - synproxy_send_client_ack(snet, skb, th, &opts); + synproxy_send_client_ack(net, skb, th, &opts); consume_skb(skb); return NF_STOLEN; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index cf9700b1a106..66ddcb60519a 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -737,6 +737,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* no remote port */ } + ipc.sockc.tsflags = sk->sk_tsflags; ipc.addr = inet->inet_saddr; ipc.opt = NULL; ipc.oif = sk->sk_bound_dev_if; @@ -744,10 +745,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.ttl = 0; ipc.tos = -1; - sock_tx_timestamp(sk, &ipc.tx_flags); - if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); + err = ip_cmsg_send(sk, msg, &ipc, false); if (unlikely(err)) { kfree(ipc.opt); return err; @@ -768,6 +767,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } + sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); + saddr = ipc.addr; ipc.addr = faddr = daddr; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8d22de74080c..438f50c1a676 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -339,8 +339,8 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, struct msghdr *msg, size_t length, - struct rtable **rtp, - unsigned int flags) + struct rtable **rtp, unsigned int flags, + const struct sockcm_cookie *sockc) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); @@ -379,7 +379,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->ip_summed = CHECKSUM_NONE; - sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); + sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); skb->transport_header = skb->network_header; err = -EFAULT; @@ -540,6 +540,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) daddr = inet->inet_daddr; } + ipc.sockc.tsflags = sk->sk_tsflags; ipc.addr = inet->inet_saddr; ipc.opt = NULL; ipc.tx_flags = 0; @@ -548,7 +549,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { - err = ip_cmsg_send(net, msg, &ipc, false); + err = ip_cmsg_send(sk, msg, &ipc, false); if (unlikely(err)) { kfree(ipc.opt); goto out; @@ -638,10 +639,10 @@ back_from_confirm: if (inet->hdrincl) err = raw_send_hdrinc(sk, &fl4, msg, len, - &rt, msg->msg_flags); + &rt, msg->msg_flags, &ipc.sockc); else { - sock_tx_timestamp(sk, &ipc.tx_flags); + sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); if (!ipc.addr) ipc.addr = fl4.daddr; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1e1fe6086dd9..bb0419582b8d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -960,6 +960,17 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_IP_ROUTE_MULTIPATH + { + .procname = "fib_multipath_use_neigh", + .data = &init_net.ipv4.sysctl_fib_multipath_use_neigh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 08b8b960a8ed..4d73858991af 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -428,14 +428,16 @@ void tcp_init_sock(struct sock *sk) } EXPORT_SYMBOL(tcp_init_sock); -static void tcp_tx_timestamp(struct sock *sk, struct sk_buff *skb) +static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb) { - if (sk->sk_tsflags) { + if (sk->sk_tsflags || tsflags) { struct skb_shared_info *shinfo = skb_shinfo(skb); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); - sock_tx_timestamp(sk, &shinfo->tx_flags); + sock_tx_timestamp(sk, tsflags, &shinfo->tx_flags); if (shinfo->tx_flags & SKBTX_ANY_TSTAMP) shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; + tcb->txstamp_ack = !!(shinfo->tx_flags & SKBTX_ACK_TSTAMP); } } @@ -957,7 +959,7 @@ new_segment: offset += copy; size -= copy; if (!size) { - tcp_tx_timestamp(sk, skb); + tcp_tx_timestamp(sk, sk->sk_tsflags, skb); goto out; } @@ -1077,6 +1079,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; + struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; bool sg; @@ -1119,6 +1122,15 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) /* 'common' sending to sendq */ } + sockc.tsflags = sk->sk_tsflags; + if (msg->msg_controllen) { + err = sock_cmsg_send(sk, msg, &sockc); + if (unlikely(err)) { + err = -EINVAL; + goto out_err; + } + } + /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -1237,7 +1249,7 @@ new_segment: copied += copy; if (!msg_data_left(msg)) { - tcp_tx_timestamp(sk, skb); + tcp_tx_timestamp(sk, sockc.tsflags, skb); goto out; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e6e65f79ade8..983f04c11177 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2252,16 +2252,6 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) } } -/* CWND moderation, preventing bursts due to too big ACKs - * in dubious situations. - */ -static inline void tcp_moderate_cwnd(struct tcp_sock *tp) -{ - tp->snd_cwnd = min(tp->snd_cwnd, - tcp_packets_in_flight(tp) + tcp_max_burst(tp)); - tp->snd_cwnd_stamp = tcp_time_stamp; -} - static bool tcp_tsopt_ecr_before(const struct tcp_sock *tp, u32 when) { return tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && @@ -2410,7 +2400,6 @@ static bool tcp_try_undo_recovery(struct sock *sk) /* Hold old state until something *above* high_seq * is ACKed. For Reno it is MUST to prevent false * fast retransmits (RFC2582). SACK TCP is safe. */ - tcp_moderate_cwnd(tp); if (!tcp_any_retrans_done(sk)) tp->retrans_stamp = 0; return true; @@ -3093,7 +3082,7 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, const struct skb_shared_info *shinfo; /* Avoid cache line misses to get skb_shinfo() and shinfo->tx_flags */ - if (likely(!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK))) + if (likely(!TCP_SKB_CB(skb)->txstamp_ack)) return; shinfo = skb_shinfo(skb); @@ -4318,6 +4307,12 @@ static bool tcp_try_coalesce(struct sock *sk, return true; } +static void tcp_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + __kfree_skb(skb); +} + /* This one checks to see if we can put data from the * out_of_order queue into the receive_queue. */ @@ -4342,7 +4337,7 @@ static void tcp_ofo_queue(struct sock *sk) __skb_unlink(skb, &tp->out_of_order_queue); if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { SOCK_DEBUG(sk, "ofo packet was already received\n"); - __kfree_skb(skb); + tcp_drop(sk, skb); continue; } SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n", @@ -4394,7 +4389,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP); - __kfree_skb(skb); + tcp_drop(sk, skb); return; } @@ -4458,7 +4453,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { /* All the bits are present. Drop. */ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb); + tcp_drop(sk, skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); goto add_sack; @@ -4497,7 +4492,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb1); + tcp_drop(sk, skb1); } add_sack: @@ -4580,12 +4575,13 @@ err: static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - int eaten = -1; bool fragstolen = false; + int eaten = -1; - if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) - goto drop; - + if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { + __kfree_skb(skb); + return; + } skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); @@ -4667,7 +4663,7 @@ out_of_window: tcp_enter_quickack_mode(sk); inet_csk_schedule_ack(sk); drop: - __kfree_skb(skb); + tcp_drop(sk, skb); return; } @@ -5244,7 +5240,7 @@ syn_challenge: return true; discard: - __kfree_skb(skb); + tcp_drop(sk, skb); return false; } @@ -5462,7 +5458,7 @@ csum_error: TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS); discard: - __kfree_skb(skb); + tcp_drop(sk, skb); } EXPORT_SYMBOL(tcp_rcv_established); @@ -5693,7 +5689,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, TCP_DELACK_MAX, TCP_RTO_MAX); discard: - __kfree_skb(skb); + tcp_drop(sk, skb); return 0; } else { tcp_send_ack(sk); @@ -6054,7 +6050,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (!queued) { discard: - __kfree_skb(skb); + tcp_drop(sk, skb); } return 0; } @@ -6343,8 +6339,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie); - if (want_cookie) - goto drop_and_free; + if (want_cookie) { + reqsk_free(req); + return 0; + } } reqsk_put(req); return 0; @@ -6354,7 +6352,7 @@ drop_and_release: drop_and_free: reqsk_free(req); drop: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); + tcp_listendrop(sk); return 0; } EXPORT_SYMBOL(tcp_conn_request); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ad450509029b..f4f2a0a3849d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -157,7 +157,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) nexthop = daddr = usin->sin_addr.s_addr; inet_opt = rcu_dereference_protected(inet->inet_opt, - sock_owned_by_user(sk)); + lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) { if (!daddr) return -EINVAL; @@ -329,7 +329,7 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort) * errors returned from accept(). */ inet_csk_reqsk_queue_drop(req->rsk_listener, req); - NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS); + tcp_listendrop(req->rsk_listener); } reqsk_put(req); } @@ -628,6 +628,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); #ifdef CONFIG_TCP_MD5SIG + rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); if (sk && sk_fullsock(sk)) { key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *) @@ -646,16 +647,18 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) ntohs(th->source), inet_iif(skb)); /* don't send rst if it can't find key */ if (!sk1) - return; - rcu_read_lock(); + goto out; + key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *) &ip_hdr(skb)->saddr, AF_INET); if (!key) - goto release_sk1; + goto out; + genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) - goto release_sk1; + goto out; + } if (key) { @@ -698,11 +701,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); #ifdef CONFIG_TCP_MD5SIG -release_sk1: - if (sk1) { - rcu_read_unlock(); - sock_put(sk1); - } +out: + rcu_read_unlock(); #endif } @@ -882,8 +882,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, - sock_owned_by_user(sk) || - lockdep_is_held((spinlock_t *)&sk->sk_lock.slock)); + lockdep_sock_is_held(sk)); if (!md5sig) return NULL; #if IS_ENABLED(CONFIG_IPV6) @@ -928,8 +927,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, } md5sig = rcu_dereference_protected(tp->md5sig_info, - sock_owned_by_user(sk) || - lockdep_is_held(&sk->sk_lock.slock)); + lockdep_sock_is_held(sk)); if (!md5sig) { md5sig = kmalloc(sizeof(*md5sig), gfp); if (!md5sig) @@ -1246,7 +1244,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) &tcp_request_sock_ipv4_ops, sk, skb); drop: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); + tcp_listendrop(sk); return 0; } EXPORT_SYMBOL(tcp_v4_conn_request); @@ -1348,7 +1346,7 @@ exit_overflow: exit_nonewsk: dst_release(dst); exit: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); + tcp_listendrop(sk); return NULL; put_and_exit: inet_csk_prepare_forced_close(newsk); @@ -1538,11 +1536,12 @@ EXPORT_SYMBOL(tcp_prequeue); int tcp_v4_rcv(struct sk_buff *skb) { + struct net *net = dev_net(skb->dev); const struct iphdr *iph; const struct tcphdr *th; + bool refcounted; struct sock *sk; int ret; - struct net *net = dev_net(skb->dev); if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -1588,7 +1587,7 @@ int tcp_v4_rcv(struct sk_buff *skb) lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, - th->dest); + th->dest, &refcounted); if (!sk) goto no_tcp_socket; @@ -1609,7 +1608,11 @@ process: inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + /* We own a reference on the listener, increase it again + * as we might lose it too soon. + */ sock_hold(sk); + refcounted = true; nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); @@ -1665,7 +1668,8 @@ process: bh_unlock_sock(sk); put_and_return: - sock_put(sk); + if (refcounted) + sock_put(sk); return ret; @@ -1688,7 +1692,9 @@ discard_it: return 0; discard_and_relse: - sock_put(sk); + sk_drops_add(sk, skb); + if (refcounted) + sock_put(sk); goto discard_it; do_time_wait: @@ -1712,6 +1718,7 @@ do_time_wait: if (sk2) { inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; + refcounted = false; goto process; } /* Fall through to ACK */ @@ -1845,17 +1852,17 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock); */ static void *listening_get_next(struct seq_file *seq, void *cur) { - struct inet_connection_sock *icsk; - struct hlist_nulls_node *node; - struct sock *sk = cur; - struct inet_listen_hashbucket *ilb; struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); + struct inet_listen_hashbucket *ilb; + struct inet_connection_sock *icsk; + struct sock *sk = cur; if (!sk) { +get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock_bh(&ilb->lock); - sk = sk_nulls_head(&ilb->head); + sk = sk_head(&ilb->head); st->offset = 0; goto get_sk; } @@ -1863,28 +1870,20 @@ static void *listening_get_next(struct seq_file *seq, void *cur) ++st->num; ++st->offset; - sk = sk_nulls_next(sk); + sk = sk_next(sk); get_sk: - sk_nulls_for_each_from(sk, node) { + sk_for_each_from(sk) { if (!net_eq(sock_net(sk), net)) continue; - if (sk->sk_family == st->family) { - cur = sk; - goto out; - } + if (sk->sk_family == st->family) + return sk; icsk = inet_csk(sk); } spin_unlock_bh(&ilb->lock); st->offset = 0; - if (++st->bucket < INET_LHTABLE_SIZE) { - ilb = &tcp_hashinfo.listening_hash[st->bucket]; - spin_lock_bh(&ilb->lock); - sk = sk_nulls_head(&ilb->head); - goto get_sk; - } - cur = NULL; -out: - return cur; + if (++st->bucket < INET_LHTABLE_SIZE) + goto get_head; + return NULL; } static void *listening_get_idx(struct seq_file *seq, loff_t *pos) @@ -2383,6 +2382,7 @@ static int __net_init tcp_sk_init(struct net *net) IPPROTO_TCP, net); if (res) goto fail; + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index acb366dd61e6..4c53e7c86586 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -704,7 +704,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) { /* Out of window: send ACK and drop. */ - if (!(flg & TCP_FLAG_RST)) + if (!(flg & TCP_FLAG_RST) && + !tcp_oow_rate_limited(sock_net(sk), skb, + LINUX_MIB_TCPACKSKIPPEDSYNRECV, + &tcp_rsk(req)->last_oow_ack_time)) req->rsk_ops->send_ack(sk, skb, req); if (paws_reject) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 08eed5e16df0..3563788d064f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -143,10 +143,9 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, unsigned int log) { struct sock *sk2; - struct hlist_nulls_node *node; kuid_t uid = sock_i_uid(sk); - sk_nulls_for_each(sk2, node, &hslot->head) { + sk_for_each(sk2, &hslot->head) { if (net_eq(sock_net(sk2), net) && sk2 != sk && (bitmap || udp_sk(sk2)->udp_port_hash == num) && @@ -177,12 +176,11 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, bool match_wildcard)) { struct sock *sk2; - struct hlist_nulls_node *node; kuid_t uid = sock_i_uid(sk); int res = 0; spin_lock(&hslot2->lock); - udp_portaddr_for_each_entry(sk2, node, &hslot2->head) { + udp_portaddr_for_each_entry(sk2, &hslot2->head) { if (net_eq(sock_net(sk2), net) && sk2 != sk && (udp_sk(sk2)->udp_port_hash == num) && @@ -207,11 +205,10 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot, bool match_wildcard)) { struct net *net = sock_net(sk); - struct hlist_nulls_node *node; kuid_t uid = sock_i_uid(sk); struct sock *sk2; - sk_nulls_for_each(sk2, node, &hslot->head) { + sk_for_each(sk2, &hslot->head) { if (net_eq(sock_net(sk2), net) && sk2 != sk && sk2->sk_family == sk->sk_family && @@ -333,17 +330,18 @@ found: goto fail_unlock; } - sk_nulls_add_node_rcu(sk, &hslot->head); + sk_add_node_rcu(sk, &hslot->head); hslot->count++; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); spin_lock(&hslot2->lock); - hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, &hslot2->head); hslot2->count++; spin_unlock(&hslot2->lock); } + sock_set_flag(sk, SOCK_RCU_FREE); error = 0; fail_unlock: spin_unlock_bh(&hslot->lock); @@ -497,37 +495,27 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct sk_buff *skb) { struct sock *sk, *result; - struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; - bool select_ok = true; u32 hash = 0; -begin: result = NULL; badness = 0; - udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { score = compute_score2(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { - result = sk; - badness = score; reuseport = sk->sk_reuseport; if (reuseport) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - if (select_ok) { - struct sock *sk2; - - sk2 = reuseport_select_sock(sk, hash, skb, + result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - select_ok = false; - goto found; - } - } + if (result) + return result; matches = 1; } + badness = score; + result = sk; } else if (score == badness && reuseport) { matches++; if (reciprocal_scale(hash, matches) == 0) @@ -535,23 +523,6 @@ begin: hash = next_pseudo_random32(hash); } } - /* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != slot2) - goto begin; - if (result) { -found: - if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) - result = NULL; - else if (unlikely(compute_score2(result, net, saddr, sport, - daddr, hnum, dif) < badness)) { - sock_put(result); - goto begin; - } - } return result; } @@ -563,15 +534,12 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, int dif, struct udp_table *udptable, struct sk_buff *skb) { struct sock *sk, *result; - struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; - bool select_ok = true; u32 hash = 0; - rcu_read_lock(); if (hslot->count > 10) { hash2 = udp4_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; @@ -593,35 +561,27 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, htonl(INADDR_ANY), hnum, dif, hslot2, slot2, skb); } - rcu_read_unlock(); return result; } begin: result = NULL; badness = 0; - sk_nulls_for_each_rcu(sk, node, &hslot->head) { + sk_for_each_rcu(sk, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { - result = sk; - badness = score; reuseport = sk->sk_reuseport; if (reuseport) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - if (select_ok) { - struct sock *sk2; - - sk2 = reuseport_select_sock(sk, hash, skb, + result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - select_ok = false; - goto found; - } - } + if (result) + return result; matches = 1; } + result = sk; + badness = score; } else if (score == badness && reuseport) { matches++; if (reciprocal_scale(hash, matches) == 0) @@ -629,25 +589,6 @@ begin: hash = next_pseudo_random32(hash); } } - /* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != slot) - goto begin; - - if (result) { -found: - if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) - result = NULL; - else if (unlikely(compute_score(result, net, saddr, hnum, sport, - daddr, dport, dif) < badness)) { - sock_put(result); - goto begin; - } - } - rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(__udp4_lib_lookup); @@ -663,13 +604,37 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, udptable, skb); } +struct sock *udp4_lib_lookup_skb(struct sk_buff *skb, + __be16 sport, __be16 dport) +{ + const struct iphdr *iph = ip_hdr(skb); + const struct net_device *dev = + skb_dst(skb) ? skb_dst(skb)->dev : skb->dev; + + return __udp4_lib_lookup(dev_net(dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + &udp_table, skb); +} +EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb); + +/* Must be called under rcu_read_lock(). + * Does increment socket refcount. + */ +#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \ + IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { - return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, - &udp_table, NULL); + struct sock *sk; + + sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, + dif, &udp_table, NULL); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + return sk; } EXPORT_SYMBOL_GPL(udp4_lib_lookup); +#endif static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, __be16 loc_port, __be32 loc_addr, @@ -771,7 +736,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) sk->sk_err = err; sk->sk_error_report(sk); out: - sock_put(sk); + return; } void udp_err(struct sk_buff *skb, u32 info) @@ -1027,15 +992,13 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) */ connected = 1; } - ipc.addr = inet->inet_saddr; + ipc.sockc.tsflags = sk->sk_tsflags; + ipc.addr = inet->inet_saddr; ipc.oif = sk->sk_bound_dev_if; - sock_tx_timestamp(sk, &ipc.tx_flags); - if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc, - sk->sk_family == AF_INET6); + err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); if (unlikely(err)) { kfree(ipc.opt); return err; @@ -1060,6 +1023,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) saddr = ipc.addr; ipc.addr = faddr = daddr; + sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); + if (ipc.opt && ipc.opt->opt.srr) { if (!daddr) return -EINVAL; @@ -1342,7 +1307,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; unsigned int ulen, copied; - int peeked, off = 0; + int peeked, peeking, off; int err; int is_udplite = IS_UDPLITE(sk); bool checksum_valid = false; @@ -1352,15 +1317,16 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, return ip_recv_error(sk, msg, len, addr_len); try_again: + peeking = off = sk_peek_offset(sk, flags); skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), &peeked, &off, &err); if (!skb) - goto out; + return err; - ulen = skb->len - sizeof(struct udphdr); + ulen = skb->len; copied = len; - if (copied > ulen) - copied = ulen; + if (copied > ulen - off) + copied = ulen - off; else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; @@ -1370,18 +1336,16 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov || peeking) { checksum_valid = !udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } if (checksum_valid || skb_csum_unnecessary(skb)) - err = skb_copy_datagram_msg(skb, sizeof(struct udphdr), - msg, copied); + err = skb_copy_datagram_msg(skb, off, msg, copied); else { - err = skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr), - msg); + err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_err; @@ -1394,7 +1358,8 @@ try_again: UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } - goto out_free; + skb_free_datagram_locked(sk, skb); + return err; } if (!peeked) @@ -1418,9 +1383,7 @@ try_again: if (flags & MSG_TRUNC) err = ulen; -out_free: - skb_free_datagram_locked(sk, skb); -out: + __skb_free_datagram_locked(sk, skb, peeking ? -err : err); return err; csum_copy_err: @@ -1474,13 +1437,13 @@ void udp_lib_unhash(struct sock *sk) spin_lock_bh(&hslot->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - if (sk_nulls_del_node_init_rcu(sk)) { + if (sk_del_node_init_rcu(sk)) { hslot->count--; inet_sk(sk)->inet_num = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_lock(&hslot2->lock); - hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); hslot2->count--; spin_unlock(&hslot2->lock); } @@ -1513,12 +1476,12 @@ void udp_lib_rehash(struct sock *sk, u16 newhash) if (hslot2 != nhslot2) { spin_lock(&hslot2->lock); - hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); hslot2->count--; spin_unlock(&hslot2->lock); spin_lock(&nhslot2->lock); - hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, &nhslot2->head); nhslot2->count++; spin_unlock(&nhslot2->lock); @@ -1548,7 +1511,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk_incoming_cpu_update(sk); } - rc = sock_queue_rcv_skb(sk, skb); + rc = __sock_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); @@ -1664,10 +1627,14 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } } - if (rcu_access_pointer(sk->sk_filter) && - udp_lib_checksum_complete(skb)) - goto csum_error; + if (rcu_access_pointer(sk->sk_filter)) { + if (udp_lib_checksum_complete(skb)) + goto csum_error; + if (sk_filter(sk, skb)) + goto drop; + } + udp_csum_pull_header(skb); if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); @@ -1697,35 +1664,6 @@ drop: return -1; } -static void flush_stack(struct sock **stack, unsigned int count, - struct sk_buff *skb, unsigned int final) -{ - unsigned int i; - struct sk_buff *skb1 = NULL; - struct sock *sk; - - for (i = 0; i < count; i++) { - sk = stack[i]; - if (likely(!skb1)) - skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); - - if (!skb1) { - atomic_inc(&sk->sk_drops); - UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, - IS_UDPLITE(sk)); - UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, - IS_UDPLITE(sk)); - } - - if (skb1 && udp_queue_rcv_skb(sk, skb1) <= 0) - skb1 = NULL; - - sock_put(sk); - } - if (unlikely(skb1)) - kfree_skb(skb1); -} - /* For TCP sockets, sk_rx_dst is protected by socket lock * For UDP, we use xchg() to guard against concurrent changes. */ @@ -1749,14 +1687,14 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udp_table *udptable, int proto) { - struct sock *sk, *stack[256 / sizeof(struct sock *)]; - struct hlist_nulls_node *node; + struct sock *sk, *first = NULL; unsigned short hnum = ntohs(uh->dest); struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); - int dif = skb->dev->ifindex; - unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node); unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); - bool inner_flushed = false; + unsigned int offset = offsetof(typeof(*sk), sk_node); + int dif = skb->dev->ifindex; + struct hlist_node *node; + struct sk_buff *nskb; if (use_hash2) { hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & @@ -1767,23 +1705,28 @@ start_lookup: offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } - spin_lock(&hslot->lock); - sk_nulls_for_each_entry_offset(sk, node, &hslot->head, offset) { - if (__udp_is_mcast_sock(net, sk, - uh->dest, daddr, - uh->source, saddr, - dif, hnum)) { - if (unlikely(count == ARRAY_SIZE(stack))) { - flush_stack(stack, count, skb, ~0); - inner_flushed = true; - count = 0; - } - stack[count++] = sk; - sock_hold(sk); + sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { + if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr, + uh->source, saddr, dif, hnum)) + continue; + + if (!first) { + first = sk; + continue; } - } + nskb = skb_clone(skb, GFP_ATOMIC); - spin_unlock(&hslot->lock); + if (unlikely(!nskb)) { + atomic_inc(&sk->sk_drops); + UDP_INC_STATS_BH(net, UDP_MIB_RCVBUFERRORS, + IS_UDPLITE(sk)); + UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + continue; + } + if (udp_queue_rcv_skb(sk, nskb) > 0) + consume_skb(nskb); + } /* Also lookup *:port if we are using hash2 and haven't done so yet. */ if (use_hash2 && hash2 != hash2_any) { @@ -1791,16 +1734,13 @@ start_lookup: goto start_lookup; } - /* - * do the slow work with no lock held - */ - if (count) { - flush_stack(stack, count, skb, count - 1); + if (first) { + if (udp_queue_rcv_skb(first, skb) > 0) + consume_skb(skb); } else { - if (!inner_flushed) - UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, - proto == IPPROTO_UDPLITE); - consume_skb(skb); + kfree_skb(skb); + UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, + proto == IPPROTO_UDPLITE); } return 0; } @@ -1897,7 +1837,6 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, inet_compute_pseudo); ret = udp_queue_rcv_skb(sk, skb); - sock_put(sk); /* a return value > 0 means to resubmit the input, but * it wants the return to be -protocol, or 0 @@ -1958,49 +1897,24 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, int dif) { struct sock *sk, *result; - struct hlist_nulls_node *node; unsigned short hnum = ntohs(loc_port); - unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask); + unsigned int slot = udp_hashfn(net, hnum, udp_table.mask); struct udp_hslot *hslot = &udp_table.hash[slot]; /* Do not bother scanning a too big list */ if (hslot->count > 10) return NULL; - rcu_read_lock(); -begin: - count = 0; result = NULL; - sk_nulls_for_each_rcu(sk, node, &hslot->head) { - if (__udp_is_mcast_sock(net, sk, - loc_port, loc_addr, - rmt_port, rmt_addr, - dif, hnum)) { + sk_for_each_rcu(sk, &hslot->head) { + if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr, + rmt_port, rmt_addr, dif, hnum)) { + if (result) + return NULL; result = sk; - ++count; - } - } - /* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != slot) - goto begin; - - if (result) { - if (count != 1 || - unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) - result = NULL; - else if (unlikely(!__udp_is_mcast_sock(net, result, - loc_port, loc_addr, - rmt_port, rmt_addr, - dif, hnum))) { - sock_put(result); - result = NULL; } } - rcu_read_unlock(); + return result; } @@ -2013,37 +1927,22 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, __be16 rmt_port, __be32 rmt_addr, int dif) { - struct sock *sk, *result; - struct hlist_nulls_node *node; unsigned short hnum = ntohs(loc_port); unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum); unsigned int slot2 = hash2 & udp_table.mask; struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum); + struct sock *sk; - rcu_read_lock(); - result = NULL; - udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { - if (INET_MATCH(sk, net, acookie, - rmt_addr, loc_addr, ports, dif)) - result = sk; + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { + if (INET_MATCH(sk, net, acookie, rmt_addr, + loc_addr, ports, dif)) + return sk; /* Only check first socket in chain */ break; } - - if (result) { - if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) - result = NULL; - else if (unlikely(!INET_MATCH(sk, net, acookie, - rmt_addr, loc_addr, - ports, dif))) { - sock_put(result); - result = NULL; - } - } - rcu_read_unlock(); - return result; + return NULL; } void udp_v4_early_demux(struct sk_buff *skb) @@ -2051,7 +1950,7 @@ void udp_v4_early_demux(struct sk_buff *skb) struct net *net = dev_net(skb->dev); const struct iphdr *iph; const struct udphdr *uh; - struct sock *sk; + struct sock *sk = NULL; struct dst_entry *dst; int dif = skb->dev->ifindex; int ours; @@ -2083,11 +1982,9 @@ void udp_v4_early_demux(struct sk_buff *skb) } else if (skb->pkt_type == PACKET_HOST) { sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif); - } else { - return; } - if (!sk) + if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2)) return; skb->sk = sk; @@ -2387,14 +2284,13 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) for (state->bucket = start; state->bucket <= state->udp_table->mask; ++state->bucket) { - struct hlist_nulls_node *node; struct udp_hslot *hslot = &state->udp_table->hash[state->bucket]; - if (hlist_nulls_empty(&hslot->head)) + if (hlist_empty(&hslot->head)) continue; spin_lock_bh(&hslot->lock); - sk_nulls_for_each(sk, node, &hslot->head) { + sk_for_each(sk, &hslot->head) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == state->family) @@ -2413,7 +2309,7 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) struct net *net = seq_file_net(seq); do { - sk = sk_nulls_next(sk); + sk = sk_next(sk); } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family)); if (!sk) { @@ -2622,12 +2518,12 @@ void __init udp_table_init(struct udp_table *table, const char *name) table->hash2 = table->hash + (table->mask + 1); for (i = 0; i <= table->mask; i++) { - INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); + INIT_HLIST_HEAD(&table->hash[i].head); table->hash[i].count = 0; spin_lock_init(&table->hash[i].lock); } for (i = 0; i <= table->mask; i++) { - INIT_HLIST_NULLS_HEAD(&table->hash2[i].head, i); + INIT_HLIST_HEAD(&table->hash2[i].head); table->hash2[i].count = 0; spin_lock_init(&table->hash2[i].lock); } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index df1966f3b6ec..3d5ccf4b1412 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -36,10 +36,11 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { int err = -EINVAL; - struct sock *sk; + struct sock *sk = NULL; struct sk_buff *rep; struct net *net = sock_net(in_skb->sk); + rcu_read_lock(); if (req->sdiag_family == AF_INET) sk = __udp4_lib_lookup(net, req->id.idiag_src[0], req->id.idiag_sport, @@ -54,9 +55,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, req->id.idiag_dport, req->id.idiag_if, tbl, NULL); #endif - else - goto out_nosk; - + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + rcu_read_unlock(); err = -ENOENT; if (!sk) goto out_nosk; @@ -96,24 +97,23 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, struct nlattr *bc) { - int num, s_num, slot, s_slot; struct net *net = sock_net(skb->sk); + int num, s_num, slot, s_slot; s_slot = cb->args[0]; num = s_num = cb->args[1]; for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) { - struct sock *sk; - struct hlist_nulls_node *node; struct udp_hslot *hslot = &table->hash[slot]; + struct sock *sk; num = 0; - if (hlist_nulls_empty(&hslot->head)) + if (hlist_empty(&hslot->head)) continue; spin_lock_bh(&hslot->lock); - sk_nulls_for_each(sk, node, &hslot->head) { + sk_for_each(sk, &hslot->head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 0ed2dafb7cc4..6230cf4b0d2d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -14,18 +14,6 @@ #include <net/udp.h> #include <net/protocol.h> -static DEFINE_SPINLOCK(udp_offload_lock); -static struct udp_offload_priv __rcu *udp_offload_base __read_mostly; - -#define udp_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&udp_offload_lock)) - -struct udp_offload_priv { - struct udp_offload *offload; - possible_net_t net; - struct rcu_head rcu; - struct udp_offload_priv __rcu *next; -}; - static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, @@ -179,6 +167,7 @@ out_unlock: return segs; } +EXPORT_SYMBOL(skb_udp_tunnel_segment); static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, netdev_features_t features) @@ -253,64 +242,14 @@ out: return segs; } -int udp_add_offload(struct net *net, struct udp_offload *uo) -{ - struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_ATOMIC); - - if (!new_offload) - return -ENOMEM; - - write_pnet(&new_offload->net, net); - new_offload->offload = uo; - - spin_lock(&udp_offload_lock); - new_offload->next = udp_offload_base; - rcu_assign_pointer(udp_offload_base, new_offload); - spin_unlock(&udp_offload_lock); - - return 0; -} -EXPORT_SYMBOL(udp_add_offload); - -static void udp_offload_free_routine(struct rcu_head *head) -{ - struct udp_offload_priv *ou_priv = container_of(head, struct udp_offload_priv, rcu); - kfree(ou_priv); -} - -void udp_del_offload(struct udp_offload *uo) -{ - struct udp_offload_priv __rcu **head = &udp_offload_base; - struct udp_offload_priv *uo_priv; - - spin_lock(&udp_offload_lock); - - uo_priv = udp_deref_protected(*head); - for (; uo_priv != NULL; - uo_priv = udp_deref_protected(*head)) { - if (uo_priv->offload == uo) { - rcu_assign_pointer(*head, - udp_deref_protected(uo_priv->next)); - goto unlock; - } - head = &uo_priv->next; - } - pr_warn("udp_del_offload: didn't find offload for port %d\n", ntohs(uo->port)); -unlock: - spin_unlock(&udp_offload_lock); - if (uo_priv) - call_rcu(&uo_priv->rcu, udp_offload_free_routine); -} -EXPORT_SYMBOL(udp_del_offload); - struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, - struct udphdr *uh) + struct udphdr *uh, udp_lookup_t lookup) { - struct udp_offload_priv *uo_priv; struct sk_buff *p, **pp = NULL; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; + struct sock *sk; if (NAPI_GRO_CB(skb)->encap_mark || (skb->ip_summed != CHECKSUM_PARTIAL && @@ -322,13 +261,10 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, NAPI_GRO_CB(skb)->encap_mark = 1; rcu_read_lock(); - uo_priv = rcu_dereference(udp_offload_base); - for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) { - if (net_eq(read_pnet(&uo_priv->net), dev_net(skb->dev)) && - uo_priv->offload->port == uh->dest && - uo_priv->offload->callbacks.gro_receive) - goto unflush; - } + sk = (*lookup)(skb, uh->source, uh->dest); + + if (sk && udp_sk(sk)->gro_receive) + goto unflush; goto out_unlock; unflush: @@ -352,9 +288,7 @@ unflush: skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); - NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto; - pp = uo_priv->offload->callbacks.gro_receive(head, skb, - uo_priv->offload); + pp = udp_sk(sk)->gro_receive(sk, head, skb); out_unlock: rcu_read_unlock(); @@ -362,6 +296,7 @@ out: NAPI_GRO_CB(skb)->flush |= flush; return pp; } +EXPORT_SYMBOL(udp_gro_receive); static struct sk_buff **udp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) @@ -383,39 +318,28 @@ static struct sk_buff **udp4_gro_receive(struct sk_buff **head, inet_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; - return udp_gro_receive(head, skb, uh); + return udp_gro_receive(head, skb, uh, udp4_lib_lookup_skb); flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } -int udp_gro_complete(struct sk_buff *skb, int nhoff) +int udp_gro_complete(struct sk_buff *skb, int nhoff, + udp_lookup_t lookup) { - struct udp_offload_priv *uo_priv; __be16 newlen = htons(skb->len - nhoff); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); int err = -ENOSYS; + struct sock *sk; uh->len = newlen; rcu_read_lock(); - - uo_priv = rcu_dereference(udp_offload_base); - for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) { - if (net_eq(read_pnet(&uo_priv->net), dev_net(skb->dev)) && - uo_priv->offload->port == uh->dest && - uo_priv->offload->callbacks.gro_complete) - break; - } - - if (uo_priv) { - NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto; - err = uo_priv->offload->callbacks.gro_complete(skb, - nhoff + sizeof(struct udphdr), - uo_priv->offload); - } - + sk = (*lookup)(skb, uh->source, uh->dest); + if (sk && udp_sk(sk)->gro_complete) + err = udp_sk(sk)->gro_complete(sk, skb, + nhoff + sizeof(struct udphdr)); rcu_read_unlock(); if (skb->remcsum_offload) @@ -426,6 +350,7 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff) return err; } +EXPORT_SYMBOL(udp_gro_complete); static int udp4_gro_complete(struct sk_buff *skb, int nhoff) { @@ -440,7 +365,7 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; } - return udp_gro_complete(skb, nhoff); + return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } static const struct net_offload udpv4_offload = { diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 96599d1a1318..47f12c73d959 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -69,6 +69,8 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, udp_sk(sk)->encap_type = cfg->encap_type; udp_sk(sk)->encap_rcv = cfg->encap_rcv; udp_sk(sk)->encap_destroy = cfg->encap_destroy; + udp_sk(sk)->gro_receive = cfg->gro_receive; + udp_sk(sk)->gro_complete = cfg->gro_complete; udp_tunnel_encap_enable(sock); } diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 2fbd90bf8d33..5e9d6bf4aaca 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -8,9 +8,10 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ addrlabel.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ - exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o + exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \ + udp_offload.o -ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o +ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b11c37cfd67c..bfa86f040c16 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -64,6 +64,8 @@ #include <asm/uaccess.h> #include <linux/mroute6.h> +#include "ip6_offload.h" + MODULE_AUTHOR("Cast of dozens"); MODULE_DESCRIPTION("IPv6 protocol stack for Linux"); MODULE_LICENSE("GPL"); @@ -561,6 +563,7 @@ const struct proto_ops inet6_dgram_ops = { .recvmsg = inet_recvmsg, /* ok */ .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, + .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, @@ -958,6 +961,10 @@ static int __init inet6_init(void) if (err) goto udplitev6_fail; + err = udpv6_offload_init(); + if (err) + goto udpv6_offload_fail; + err = tcpv6_init(); if (err) goto tcpv6_fail; @@ -987,6 +994,8 @@ pingv6_fail: ipv6_packet_fail: tcpv6_exit(); tcpv6_fail: + udpv6_offload_exit(); +udpv6_offload_fail: udplitev6_exit(); udplitev6_fail: udpv6_exit(); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 428162155280..a73d70119fcd 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -685,7 +685,8 @@ EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg, struct flowi6 *fl6, struct ipv6_txoptions *opt, - int *hlimit, int *tclass, int *dontfrag) + int *hlimit, int *tclass, int *dontfrag, + struct sockcm_cookie *sockc) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; @@ -702,6 +703,12 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, goto exit_f; } + if (cmsg->cmsg_level == SOL_SOCKET) { + if (__sock_cmsg_send(sk, msg, cmsg, sockc)) + return -EINVAL; + continue; + } + if (cmsg->cmsg_level != SOL_IPV6) continue; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 0a37ddc7af51..6b573ebe49de 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -400,6 +400,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; + struct sockcm_cookie sockc_unused = {0}; int iif = 0; int addr_type = 0; int len; @@ -527,7 +528,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl6, (struct rt6_info *)dst, - MSG_DONTWAIT, np->dontfrag); + MSG_DONTWAIT, np->dontfrag, &sockc_unused); if (err) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); @@ -566,6 +567,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) int hlimit; u8 tclass; u32 mark = IP6_REPLY_MARK(net, skb->mark); + struct sockcm_cookie sockc_unused = {0}; saddr = &ipv6_hdr(skb)->daddr; @@ -617,7 +619,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl6, (struct rt6_info *)dst, MSG_DONTWAIT, - np->dontfrag); + np->dontfrag, &sockc_unused); if (err) { ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 295ca29a23c3..0b03533453e4 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -501,7 +501,8 @@ static int ila_nl_dump_start(struct netlink_callback *cb) struct ila_net *ilan = net_generic(net, ila_net_id); struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args; - return rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter); + return rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter, + GFP_KERNEL); } static int ila_nl_dump_done(struct netlink_callback *cb) diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 70f2628be6fa..f1678388fb0d 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -69,7 +69,6 @@ struct sock *__inet6_lookup_established(struct net *net, struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; - rcu_read_lock(); begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_hash != hash) @@ -90,7 +89,6 @@ begin: out: sk = NULL; found: - rcu_read_unlock(); return sk; } EXPORT_SYMBOL(__inet6_lookup_established); @@ -122,6 +120,7 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } +/* called with rcu_read_lock() */ struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, @@ -129,39 +128,27 @@ struct sock *inet6_lookup_listener(struct net *net, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif) { - struct sock *sk; - const struct hlist_nulls_node *node; - struct sock *result; - int score, hiscore, matches = 0, reuseport = 0; - bool select_ok = true; - u32 phash = 0; unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; + int score, hiscore = 0, matches = 0, reuseport = 0; + struct sock *sk, *result = NULL; + u32 phash = 0; - rcu_read_lock(); -begin: - result = NULL; - hiscore = 0; - sk_nulls_for_each(sk, node, &ilb->head) { + sk_for_each(sk, &ilb->head) { score = compute_score(sk, net, hnum, daddr, dif); if (score > hiscore) { - hiscore = score; - result = sk; reuseport = sk->sk_reuseport; if (reuseport) { phash = inet6_ehashfn(net, daddr, hnum, saddr, sport); - if (select_ok) { - struct sock *sk2; - sk2 = reuseport_select_sock(sk, phash, - skb, doff); - if (sk2) { - result = sk2; - goto found; - } - } + result = reuseport_select_sock(sk, phash, + skb, doff); + if (result) + return result; matches = 1; } + result = sk; + hiscore = score; } else if (score == hiscore && reuseport) { matches++; if (reciprocal_scale(phash, matches) == 0) @@ -169,25 +156,6 @@ begin: phash = next_pseudo_random32(phash); } } - /* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE) - goto begin; - if (result) { -found: - if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) - result = NULL; - else if (unlikely(compute_score(result, net, hnum, daddr, - dif) < hiscore)) { - sock_put(result); - select_ok = false; - goto begin; - } - } - rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(inet6_lookup_listener); @@ -199,12 +167,12 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, const int dif) { struct sock *sk; + bool refcounted; - local_bh_disable(); sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, - ntohs(dport), dif); - local_bh_enable(); - + ntohs(dport), dif, &refcounted); + if (sk && !refcounted && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; return sk; } EXPORT_SYMBOL_GPL(inet6_lookup); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index dc2db4f7b182..35d3ddc328f8 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -372,6 +372,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, if (olen > 0) { struct msghdr msg; struct flowi6 flowi6; + struct sockcm_cookie sockc_junk; int junk; err = -ENOMEM; @@ -390,7 +391,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, memset(&flowi6, 0, sizeof(flowi6)); err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, - &junk, &junk, &junk); + &junk, &junk, &junk, &sockc_junk); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 82e9f3076028..204af2219471 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -325,8 +325,6 @@ static int __init ipv6_offload_init(void) if (tcpv6_offload_init() < 0) pr_crit("%s: Cannot add TCP protocol offload\n", __func__); - if (udp_offload_init() < 0) - pr_crit("%s: Cannot add UDP protocol offload\n", __func__); if (ipv6_exthdrs_offload_init() < 0) pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); diff --git a/net/ipv6/ip6_offload.h b/net/ipv6/ip6_offload.h index 2e155c651b35..96b40e41ac53 100644 --- a/net/ipv6/ip6_offload.h +++ b/net/ipv6/ip6_offload.h @@ -12,7 +12,8 @@ #define __ip6_offload_h int ipv6_exthdrs_offload_init(void); -int udp_offload_init(void); +int udpv6_offload_init(void); +int udpv6_offload_exit(void); int tcpv6_offload_init(void); #endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 9428345d3a07..171518e3ca21 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1090,8 +1090,8 @@ static inline int ip6_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, - int transhdrlen, int mtu, unsigned int flags, - const struct flowi6 *fl6) + int exthdrlen, int transhdrlen, int mtu, + unsigned int flags, const struct flowi6 *fl6) { struct sk_buff *skb; @@ -1116,7 +1116,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb_put(skb, fragheaderlen + transhdrlen); /* initialize network header pointer */ - skb_reset_network_header(skb); + skb_set_network_header(skb, exthdrlen); /* initialize protocol header pointer */ skb->transport_header = skb->network_header + fragheaderlen; @@ -1258,7 +1258,8 @@ static int __ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - unsigned int flags, int dontfrag) + unsigned int flags, int dontfrag, + const struct sockcm_cookie *sockc) { struct sk_buff *skb, *skb_prev = NULL; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu; @@ -1329,7 +1330,7 @@ emsgsize: csummode = CHECKSUM_PARTIAL; if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { - sock_tx_timestamp(sk, &tx_flags); + sock_tx_timestamp(sk, sockc->tsflags, &tx_flags); if (tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) tskey = sk->sk_tskey++; @@ -1358,7 +1359,7 @@ emsgsize: (rt->dst.dev->features & NETIF_F_UFO) && (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, - hh_len, fragheaderlen, + hh_len, fragheaderlen, exthdrlen, transhdrlen, mtu, flags, fl6); if (err) goto error; @@ -1565,7 +1566,8 @@ int ip6_append_data(struct sock *sk, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6, - struct rt6_info *rt, unsigned int flags, int dontfrag) + struct rt6_info *rt, unsigned int flags, int dontfrag, + const struct sockcm_cookie *sockc) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -1593,7 +1595,8 @@ int ip6_append_data(struct sock *sk, return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base, &np->cork, sk_page_frag(sk), getfrag, - from, length, transhdrlen, flags, dontfrag); + from, length, transhdrlen, flags, dontfrag, + sockc); } EXPORT_SYMBOL_GPL(ip6_append_data); @@ -1752,7 +1755,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, - int dontfrag) + int dontfrag, const struct sockcm_cookie *sockc) { struct inet_cork_full cork; struct inet6_cork v6_cork; @@ -1779,7 +1782,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, - flags, dontfrag); + flags, dontfrag, sockc); if (err) { __ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork); return ERR_PTR(err); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index eb2ac4bb09ce..1f20345cbc97 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -252,12 +252,12 @@ static int ip6_tnl_create2(struct net_device *dev) t = netdev_priv(dev); + dev->rtnl_link_ops = &ip6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); - dev->rtnl_link_ops = &ip6_link_ops; dev_hold(dev); ip6_tnl_link(ip6n, t); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4449ad1f8114..4ff4b29894eb 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -407,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) break; - opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + opt = rcu_dereference_protected(np->opt, + lockdep_sock_is_held(sk)); opt = ipv6_renew_options(sk, opt, optname, (struct ipv6_opt_hdr __user *)optval, optlen); @@ -471,6 +472,7 @@ sticky_done: struct ipv6_txoptions *opt = NULL; struct msghdr msg; struct flowi6 fl6; + struct sockcm_cookie sockc_junk; int junk; memset(&fl6, 0, sizeof(fl6)); @@ -503,7 +505,7 @@ sticky_done: msg.msg_control = (void *)(opt+1); retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, - &junk, &junk); + &junk, &junk, &sockc_junk); if (retv) goto done; update: @@ -1123,7 +1125,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, struct ipv6_txoptions *opt; lock_sock(sk); - opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + opt = rcu_dereference_protected(np->opt, + lockdep_sock_is_held(sk)); len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len); release_sock(sk); /* check if ipv6_getsockopt_sticky() returns err code */ diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 84f9baf7aee8..86b67b70b626 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -198,11 +198,12 @@ get_entry(const void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline bool unconditional(const struct ip6t_ip6 *ipv6) +static inline bool unconditional(const struct ip6t_entry *e) { static const struct ip6t_ip6 uncond; - return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct ip6t_entry) && + memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0; } static inline const struct xt_entry_target * @@ -258,11 +259,10 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ip6t_entry) && + if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && - t->verdict < 0 && - unconditional(&s->ipv6)) { + t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] @@ -488,11 +488,10 @@ mark_source_chains(const struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ip6t_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && - unconditional(&e->ipv6)) || visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -581,14 +580,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net) } static int -check_entry(const struct ip6t_entry *e, const char *name) +check_entry(const struct ip6t_entry *e) { const struct xt_entry_target *t; - if (!ip6_checkentry(&e->ipv6)) { - duprintf("ip_tables: ip check failed %p %s.\n", e, name); + if (!ip6_checkentry(&e->ipv6)) return -EINVAL; - } if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) @@ -679,10 +676,6 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; - ret = check_entry(e, name); - if (ret) - return ret; - e->counters.pcnt = xt_percpu_counter_alloc(); if (IS_ERR_VALUE(e->counters.pcnt)) return -ENOMEM; @@ -733,7 +726,7 @@ static bool check_underflow(const struct ip6t_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->ipv6)) + if (!unconditional(e)) return false; t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -753,9 +746,11 @@ check_entry_size_and_hooks(struct ip6t_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || - (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { + (unsigned char *)e + sizeof(struct ip6t_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -767,6 +762,10 @@ check_entry_size_and_hooks(struct ip6t_entry *e, return -EINVAL; } + err = check_entry(e); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -775,9 +774,9 @@ check_entry_size_and_hooks(struct ip6t_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; @@ -1169,6 +1168,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR_OR_NULL(t)) { @@ -1505,7 +1505,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } @@ -1518,7 +1519,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, } /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct ip6t_entry *)e, name); + ret = check_entry((struct ip6t_entry *)e); if (ret) return ret; @@ -1944,6 +1945,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index c382db7a2e73..da1cff79e447 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -62,6 +62,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct dst_entry *dst; struct rt6_info *rt; struct pingfakehdr pfh; + struct sockcm_cookie junk = {0}; pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); @@ -144,7 +145,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) err = ip6_append_data(sk, ping_getfrag, &pfh, len, 0, hlimit, np->tclass, NULL, &fl6, rt, - MSG_DONTWAIT, np->dontfrag); + MSG_DONTWAIT, np->dontfrag, &junk); if (err) { ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index fa59dd7a427e..b07ce21983aa 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -745,6 +745,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct dst_entry *dst = NULL; struct raw6_frag_vec rfv; struct flowi6 fl6; + struct sockcm_cookie sockc; int addr_len = msg->msg_namelen; int hlimit = -1; int tclass = -1; @@ -821,13 +822,15 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (fl6.flowi6_oif == 0) fl6.flowi6_oif = sk->sk_bound_dev_if; + sockc.tsflags = sk->sk_tsflags; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + &hlimit, &tclass, &dontfrag, + &sockc); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -897,7 +900,7 @@ back_from_confirm: lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info *)dst, - msg->msg_flags, dontfrag); + msg->msg_flags, dontfrag, &sockc); if (err) ip6_flush_pending_frames(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 711d209f9124..0e621bc1ae11 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -234,7 +234,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; - opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); @@ -858,6 +858,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) return; #ifdef CONFIG_TCP_MD5SIG + rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); if (sk && sk_fullsock(sk)) { key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr); @@ -875,16 +876,15 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) th->source, &ipv6h->daddr, ntohs(th->source), tcp_v6_iif(skb)); if (!sk1) - return; + goto out; - rcu_read_lock(); key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr); if (!key) - goto release_sk1; + goto out; genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) - goto release_sk1; + goto out; } #endif @@ -898,11 +898,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); #ifdef CONFIG_TCP_MD5SIG -release_sk1: - if (sk1) { - rcu_read_unlock(); - sock_put(sk1); - } +out: + rcu_read_unlock(); #endif } @@ -967,7 +964,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) &tcp_request_sock_ipv6_ops, sk, skb); drop: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); + tcp_listendrop(sk); return 0; /* don't send reset */ } @@ -1172,7 +1169,7 @@ out_overflow: out_nonewsk: dst_release(dst); out: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); + tcp_listendrop(sk); return NULL; } @@ -1351,6 +1348,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) { const struct tcphdr *th; const struct ipv6hdr *hdr; + bool refcounted; struct sock *sk; int ret; struct net *net = dev_net(skb->dev); @@ -1381,7 +1379,8 @@ static int tcp_v6_rcv(struct sk_buff *skb) lookup: sk = __inet6_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), - th->source, th->dest, inet6_iif(skb)); + th->source, th->dest, inet6_iif(skb), + &refcounted); if (!sk) goto no_tcp_socket; @@ -1404,6 +1403,7 @@ process: goto lookup; } sock_hold(sk); + refcounted = true; nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); @@ -1460,7 +1460,8 @@ process: bh_unlock_sock(sk); put_and_return: - sock_put(sk); + if (refcounted) + sock_put(sk); return ret ? -1 : 0; no_tcp_socket: @@ -1483,7 +1484,9 @@ discard_it: return 0; discard_and_relse: - sock_put(sk); + sk_drops_add(sk, skb); + if (refcounted) + sock_put(sk); goto discard_it; do_time_wait: @@ -1514,6 +1517,7 @@ do_time_wait: inet_twsk_deschedule_put(tw); sk = sk2; tcp_v6_restore_cb(skb); + refcounted = false; goto process; } /* Fall through to ACK */ diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fd25e447a5fa..a050b70b9101 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -213,37 +213,28 @@ static struct sock *udp6_lib_lookup2(struct net *net, struct sk_buff *skb) { struct sock *sk, *result; - struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; - bool select_ok = true; u32 hash = 0; -begin: result = NULL; badness = -1; - udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { score = compute_score2(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { - result = sk; - badness = score; reuseport = sk->sk_reuseport; if (reuseport) { hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - if (select_ok) { - struct sock *sk2; - sk2 = reuseport_select_sock(sk, hash, skb, + result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - select_ok = false; - goto found; - } - } + if (result) + return result; matches = 1; } + result = sk; + badness = score; } else if (score == badness && reuseport) { matches++; if (reciprocal_scale(hash, matches) == 0) @@ -251,27 +242,10 @@ begin: hash = next_pseudo_random32(hash); } } - /* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != slot2) - goto begin; - - if (result) { -found: - if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) - result = NULL; - else if (unlikely(compute_score2(result, net, saddr, sport, - daddr, hnum, dif) < badness)) { - sock_put(result); - goto begin; - } - } return result; } +/* rcu_read_lock() must be held */ struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, @@ -279,15 +253,12 @@ struct sock *__udp6_lib_lookup(struct net *net, struct sk_buff *skb) { struct sock *sk, *result; - struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; - bool select_ok = true; u32 hash = 0; - rcu_read_lock(); if (hslot->count > 10) { hash2 = udp6_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; @@ -309,34 +280,26 @@ struct sock *__udp6_lib_lookup(struct net *net, &in6addr_any, hnum, dif, hslot2, slot2, skb); } - rcu_read_unlock(); return result; } begin: result = NULL; badness = -1; - sk_nulls_for_each_rcu(sk, node, &hslot->head) { + sk_for_each_rcu(sk, &hslot->head) { score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif); if (score > badness) { - result = sk; - badness = score; reuseport = sk->sk_reuseport; if (reuseport) { hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - if (select_ok) { - struct sock *sk2; - - sk2 = reuseport_select_sock(sk, hash, skb, + result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - select_ok = false; - goto found; - } - } + if (result) + return result; matches = 1; } + result = sk; + badness = score; } else if (score == badness && reuseport) { matches++; if (reciprocal_scale(hash, matches) == 0) @@ -344,25 +307,6 @@ begin: hash = next_pseudo_random32(hash); } } - /* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != slot) - goto begin; - - if (result) { -found: - if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) - result = NULL; - else if (unlikely(compute_score(result, net, hnum, saddr, sport, - daddr, dport, dif) < badness)) { - sock_put(result); - goto begin; - } - } - rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(__udp6_lib_lookup); @@ -382,12 +326,37 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, udptable, skb); } +struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, + __be16 sport, __be16 dport) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + const struct net_device *dev = + skb_dst(skb) ? skb_dst(skb)->dev : skb->dev; + + return __udp6_lib_lookup(dev_net(dev), &iph->saddr, sport, + &iph->daddr, dport, inet6_iif(skb), + &udp_table, skb); +} +EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb); + +/* Must be called under rcu_read_lock(). + * Does increment socket refcount. + */ +#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \ + IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { - return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL); + struct sock *sk; + + sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, + dif, &udp_table, NULL); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + return sk; } EXPORT_SYMBOL_GPL(udp6_lib_lookup); +#endif /* * This should be easy, if there is something there we @@ -401,7 +370,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; unsigned int ulen, copied; - int peeked, off = 0; + int peeked, peeking, off; int err; int is_udplite = IS_UDPLITE(sk); bool checksum_valid = false; @@ -415,15 +384,16 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: + peeking = off = sk_peek_offset(sk, flags); skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), &peeked, &off, &err); if (!skb) - goto out; + return err; - ulen = skb->len - sizeof(struct udphdr); + ulen = skb->len; copied = len; - if (copied > ulen) - copied = ulen; + if (copied > ulen - off) + copied = ulen - off; else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; @@ -435,17 +405,16 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov || peeking) { checksum_valid = !udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } if (checksum_valid || skb_csum_unnecessary(skb)) - err = skb_copy_datagram_msg(skb, sizeof(struct udphdr), - msg, copied); + err = skb_copy_datagram_msg(skb, off, msg, copied); else { - err = skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr), msg); + err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_err; } @@ -462,7 +431,8 @@ try_again: UDP_MIB_INERRORS, is_udplite); } - goto out_free; + skb_free_datagram_locked(sk, skb); + return err; } if (!peeked) { if (is_udp4) @@ -510,9 +480,7 @@ try_again: if (flags & MSG_TRUNC) err = ulen; -out_free: - skb_free_datagram_locked(sk, skb); -out: + __skb_free_datagram_locked(sk, skb, peeking ? -err : err); return err; csum_copy_err: @@ -585,7 +553,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk->sk_err = err; sk->sk_error_report(sk); out: - sock_put(sk); + return; } static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) @@ -598,7 +566,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk_incoming_cpu_update(sk); } - rc = sock_queue_rcv_skb(sk, skb); + rc = __sock_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); @@ -692,8 +660,11 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (rcu_access_pointer(sk->sk_filter)) { if (udp_lib_checksum_complete(skb)) goto csum_error; + if (sk_filter(sk, skb)) + goto drop; } + udp_csum_pull_header(skb); if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); @@ -747,33 +718,6 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, return true; } -static void flush_stack(struct sock **stack, unsigned int count, - struct sk_buff *skb, unsigned int final) -{ - struct sk_buff *skb1 = NULL; - struct sock *sk; - unsigned int i; - - for (i = 0; i < count; i++) { - sk = stack[i]; - if (likely(!skb1)) - skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); - if (!skb1) { - atomic_inc(&sk->sk_drops); - UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, - IS_UDPLITE(sk)); - UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, - IS_UDPLITE(sk)); - } - - if (skb1 && udpv6_queue_rcv_skb(sk, skb1) <= 0) - skb1 = NULL; - sock_put(sk); - } - if (unlikely(skb1)) - kfree_skb(skb1); -} - static void udp6_csum_zero_error(struct sk_buff *skb) { /* RFC 2460 section 8.1 says that we SHOULD log @@ -792,15 +736,15 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, struct udp_table *udptable, int proto) { - struct sock *sk, *stack[256 / sizeof(struct sock *)]; + struct sock *sk, *first = NULL; const struct udphdr *uh = udp_hdr(skb); - struct hlist_nulls_node *node; unsigned short hnum = ntohs(uh->dest); struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); - int dif = inet6_iif(skb); - unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node); + unsigned int offset = offsetof(typeof(*sk), sk_node); unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); - bool inner_flushed = false; + int dif = inet6_iif(skb); + struct hlist_node *node; + struct sk_buff *nskb; if (use_hash2) { hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) & @@ -811,27 +755,32 @@ start_lookup: offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } - spin_lock(&hslot->lock); - sk_nulls_for_each_entry_offset(sk, node, &hslot->head, offset) { - if (__udp_v6_is_mcast_sock(net, sk, - uh->dest, daddr, - uh->source, saddr, - dif, hnum) && - /* If zero checksum and no_check is not on for - * the socket then skip it. - */ - (uh->check || udp_sk(sk)->no_check6_rx)) { - if (unlikely(count == ARRAY_SIZE(stack))) { - flush_stack(stack, count, skb, ~0); - inner_flushed = true; - count = 0; - } - stack[count++] = sk; - sock_hold(sk); + sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { + if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr, + uh->source, saddr, dif, hnum)) + continue; + /* If zero checksum and no_check is not on for + * the socket then skip it. + */ + if (!uh->check && !udp_sk(sk)->no_check6_rx) + continue; + if (!first) { + first = sk; + continue; + } + nskb = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!nskb)) { + atomic_inc(&sk->sk_drops); + UDP6_INC_STATS_BH(net, UDP_MIB_RCVBUFERRORS, + IS_UDPLITE(sk)); + UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + continue; } - } - spin_unlock(&hslot->lock); + if (udpv6_queue_rcv_skb(sk, nskb) > 0) + consume_skb(nskb); + } /* Also lookup *:port if we are using hash2 and haven't done so yet. */ if (use_hash2 && hash2 != hash2_any) { @@ -839,13 +788,13 @@ start_lookup: goto start_lookup; } - if (count) { - flush_stack(stack, count, skb, count - 1); + if (first) { + if (udpv6_queue_rcv_skb(first, skb) > 0) + consume_skb(skb); } else { - if (!inner_flushed) - UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, - proto == IPPROTO_UDPLITE); - consume_skb(skb); + kfree_skb(skb); + UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, + proto == IPPROTO_UDPLITE); } return 0; } @@ -853,10 +802,10 @@ start_lookup: int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { + const struct in6_addr *saddr, *daddr; struct net *net = dev_net(skb->dev); - struct sock *sk; struct udphdr *uh; - const struct in6_addr *saddr, *daddr; + struct sock *sk; u32 ulen = 0; if (!pskb_may_pull(skb, sizeof(struct udphdr))) @@ -910,7 +859,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int ret; if (!uh->check && !udp_sk(sk)->no_check6_rx) { - sock_put(sk); udp6_csum_zero_error(skb); goto csum_error; } @@ -920,7 +868,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ip6_compute_pseudo); ret = udpv6_queue_rcv_skb(sk, skb); - sock_put(sk); /* a return value > 0 means to resubmit the input */ if (ret > 0) @@ -1128,6 +1075,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int connected = 0; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); + struct sockcm_cookie sockc; /* destination address check */ if (sin6) { @@ -1247,6 +1195,7 @@ do_udp_sendmsg: fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; fl6.flowi6_mark = sk->sk_mark; + sockc.tsflags = sk->sk_tsflags; if (msg->msg_controllen) { opt = &opt_space; @@ -1254,7 +1203,8 @@ do_udp_sendmsg: opt->tot_len = sizeof(*opt); err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + &hlimit, &tclass, &dontfrag, + &sockc); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1321,7 +1271,7 @@ back_from_confirm: skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), hlimit, tclass, opt, &fl6, (struct rt6_info *)dst, - msg->msg_flags, dontfrag); + msg->msg_flags, dontfrag, &sockc); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) err = udp_v6_send_skb(skb, &fl6); @@ -1348,7 +1298,8 @@ do_append_data: err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), hlimit, tclass, opt, &fl6, (struct rt6_info *)dst, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag); + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag, + &sockc); if (err) udp_v6_flush_pending_frames(sk); else if (!corkreq) diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 2b0fbe6929e8..5429f6bcf047 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -153,7 +153,7 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head, skip: NAPI_GRO_CB(skb)->is_ipv6 = 1; - return udp_gro_receive(head, skb, uh); + return udp_gro_receive(head, skb, uh, udp6_lib_lookup_skb); flush: NAPI_GRO_CB(skb)->flush = 1; @@ -173,7 +173,7 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; } - return udp_gro_complete(skb, nhoff); + return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } static const struct net_offload udpv6_offload = { @@ -184,7 +184,12 @@ static const struct net_offload udpv6_offload = { }, }; -int __init udp_offload_init(void) +int udpv6_offload_init(void) { return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); } + +int udpv6_offload_exit(void) +{ + return inet6_del_offload(&udpv6_offload, IPPROTO_UDP); +} diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index ec22078b0914..42de4ccd159f 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -123,12 +123,11 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; int length; - /* Point to L2TP header */ - optr = ptr = skb->data; - if (!pskb_may_pull(skb, 4)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; session_id = ntohl(*((__be32 *) ptr)); ptr += 4; @@ -156,6 +155,9 @@ static int l2tp_ip_recv(struct sk_buff *skb) if (!pskb_may_pull(skb, length)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; + ptr += 4; pr_debug("%s: ip recv\n", tunnel->name); print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 6b54ff3ff4cb..46e07267e503 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -136,12 +136,11 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; int length; - /* Point to L2TP header */ - optr = ptr = skb->data; - if (!pskb_may_pull(skb, 4)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; session_id = ntohl(*((__be32 *) ptr)); ptr += 4; @@ -169,6 +168,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb) if (!pskb_may_pull(skb, length)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; + ptr += 4; pr_debug("%s: ip recv\n", tunnel->name); print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } @@ -492,6 +494,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct flowi6 fl6; + struct sockcm_cookie sockc_unused = {0}; int addr_len = msg->msg_namelen; int hlimit = -1; int tclass = -1; @@ -562,9 +565,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); - if (err < 0) { + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag, + &sockc_unused); + if (err < 0) { fl6_sock_release(flowlabel); return err; } @@ -625,7 +629,7 @@ back_from_confirm: err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, hlimit, tclass, opt, &fl6, (struct rt6_info *)dst, - msg->msg_flags, dontfrag); + msg->msg_flags, dontfrag, &sockc_unused); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 4932e9f243a2..42fa81031dfa 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -935,6 +935,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, size_t len) { struct tid_ampdu_tx *tid_tx; + struct ieee80211_txq *txq; u16 capab, tid; u8 buf_size; bool amsdu; @@ -945,6 +946,10 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; buf_size = min(buf_size, local->hw.max_tx_aggregation_subframes); + txq = sta->sta.txq[tid]; + if (!amsdu && txq) + set_bit(IEEE80211_TXQ_NO_AMSDU, &to_txq_info(txq)->flags); + mutex_lock(&sta->ampdu_mlme.mtx); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index fe1704c4e8fb..fc4730b938d0 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -65,11 +65,13 @@ static int ieee80211_change_iface(struct wiphy *wiphy, return ret; if (type == NL80211_IFTYPE_AP_VLAN && - params && params->use_4addr == 0) + params && params->use_4addr == 0) { RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); - else if (type == NL80211_IFTYPE_STATION && - params && params->use_4addr >= 0) + ieee80211_check_fast_rx_iface(sdata); + } else if (type == NL80211_IFTYPE_STATION && + params && params->use_4addr >= 0) { sdata->u.mgd.use_4addr = params->use_4addr; + } if (sdata->vif.type == NL80211_IFTYPE_MONITOR && flags) { struct ieee80211_local *local = sdata->local; @@ -732,6 +734,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.beacon_int = params->beacon_interval; sdata->vif.bss_conf.dtim_period = params->dtim_period; sdata->vif.bss_conf.enable_beacon = true; + sdata->vif.bss_conf.allow_p2p_go_ps = sdata->vif.p2p; sdata->vif.bss_conf.ssid_len = params->ssid_len; if (params->ssid_len) @@ -1202,6 +1205,9 @@ static int sta_apply_parameters(struct ieee80211_local *local, params->opmode_notif, band); } + if (params->support_p2p_ps >= 0) + sta->sta.support_p2p_ps = params->support_p2p_ps; + if (ieee80211_vif_is_mesh(&sdata->vif)) sta_apply_mesh_params(local, sta, params); @@ -1363,6 +1369,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, rcu_assign_pointer(vlansdata->u.vlan.sta, sta); new_4addr = true; + __ieee80211_check_fast_rx_iface(vlansdata); } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && @@ -1499,7 +1506,7 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, memset(pinfo, 0, sizeof(*pinfo)); - pinfo->generation = mesh_paths_generation; + pinfo->generation = mpath->sdata->u.mesh.mesh_paths_generation; pinfo->filled = MPATH_INFO_FRAME_QLEN | MPATH_INFO_SN | @@ -1577,7 +1584,7 @@ static void mpp_set_pinfo(struct mesh_path *mpath, u8 *mpp, memset(pinfo, 0, sizeof(*pinfo)); memcpy(mpp, mpath->mpp, ETH_ALEN); - pinfo->generation = mpp_paths_generation; + pinfo->generation = mpath->sdata->u.mesh.mpp_paths_generation; } static int ieee80211_get_mpp(struct wiphy *wiphy, struct net_device *dev, @@ -1885,6 +1892,7 @@ static int ieee80211_change_bss(struct wiphy *wiphy, sdata->flags |= IEEE80211_SDATA_DONT_BRIDGE_PACKETS; else sdata->flags &= ~IEEE80211_SDATA_DONT_BRIDGE_PACKETS; + ieee80211_check_fast_rx_iface(sdata); } if (params->ht_opmode >= 0) { diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 283981108ca8..74142d07ad31 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -343,8 +343,10 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, const struct cfg80211_chan_def *chandef) { - if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) + if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) { + ieee80211_recalc_chanctx_min_def(local, ctx); return; + } WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef)); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 4ab5c522ceee..b251b2f7f8dd 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -127,6 +127,9 @@ static const char *hw_flag_names[] = { FLAG(BEACON_TX_STATUS), FLAG(NEEDS_UNIQUE_STA_ADDR), FLAG(SUPPORTS_REORDERING_BUFFER), + FLAG(USES_RSS), + FLAG(TX_AMSDU), + FLAG(TX_FRAG_LIST), #undef FLAG }; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index a39512f09f9e..33dfcbc2bf9c 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -3,6 +3,7 @@ * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright(c) 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -51,31 +52,54 @@ static const struct file_operations sta_ ##name## _ops = { \ STA_FILE(aid, sta.aid, D); +static const char * const sta_flag_names[] = { +#define FLAG(F) [WLAN_STA_##F] = #F + FLAG(AUTH), + FLAG(ASSOC), + FLAG(PS_STA), + FLAG(AUTHORIZED), + FLAG(SHORT_PREAMBLE), + FLAG(WDS), + FLAG(CLEAR_PS_FILT), + FLAG(MFP), + FLAG(BLOCK_BA), + FLAG(PS_DRIVER), + FLAG(PSPOLL), + FLAG(TDLS_PEER), + FLAG(TDLS_PEER_AUTH), + FLAG(TDLS_INITIATOR), + FLAG(TDLS_CHAN_SWITCH), + FLAG(TDLS_OFF_CHANNEL), + FLAG(TDLS_WIDER_BW), + FLAG(UAPSD), + FLAG(SP), + FLAG(4ADDR_EVENT), + FLAG(INSERTED), + FLAG(RATE_CONTROL), + FLAG(TOFFSET_KNOWN), + FLAG(MPSP_OWNER), + FLAG(MPSP_RECIPIENT), + FLAG(PS_DELIVER), +#undef FLAG +}; + static ssize_t sta_flags_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - char buf[121]; + char buf[16 * NUM_WLAN_STA_FLAGS], *pos = buf; + char *end = buf + sizeof(buf) - 1; struct sta_info *sta = file->private_data; + unsigned int flg; + + BUILD_BUG_ON(ARRAY_SIZE(sta_flag_names) != NUM_WLAN_STA_FLAGS); + + for (flg = 0; flg < NUM_WLAN_STA_FLAGS; flg++) { + if (test_sta_flag(sta, flg)) + pos += scnprintf(pos, end - pos, "%s\n", + sta_flag_names[flg]); + } -#define TEST(flg) \ - test_sta_flag(sta, WLAN_STA_##flg) ? #flg "\n" : "" - - int res = scnprintf(buf, sizeof(buf), - "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", - TEST(AUTH), TEST(ASSOC), TEST(PS_STA), - TEST(PS_DRIVER), TEST(AUTHORIZED), - TEST(SHORT_PREAMBLE), - sta->sta.wme ? "WME\n" : "", - TEST(WDS), TEST(CLEAR_PS_FILT), - TEST(MFP), TEST(BLOCK_BA), TEST(PSPOLL), - TEST(UAPSD), TEST(SP), TEST(TDLS_PEER), - TEST(TDLS_PEER_AUTH), TEST(TDLS_INITIATOR), - TEST(TDLS_CHAN_SWITCH), TEST(TDLS_OFF_CHANNEL), - TEST(4ADDR_EVENT), TEST(INSERTED), - TEST(RATE_CONTROL), TEST(TOFFSET_KNOWN), - TEST(MPSP_OWNER), TEST(MPSP_RECIPIENT)); -#undef TEST - return simple_read_from_buffer(userbuf, count, ppos, buf, res); + return simple_read_from_buffer(userbuf, count, ppos, buf, strlen(buf)); } STA_OPS(flags); @@ -151,11 +175,12 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, static ssize_t sta_agg_status_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { - char _buf[12] = {}, *buf = _buf; + char _buf[25] = {}, *buf = _buf; struct sta_info *sta = file->private_data; bool start, tx; unsigned long tid; - int ret; + char *pos; + int ret, timeout = 5000; if (count > sizeof(_buf)) return -EINVAL; @@ -164,37 +189,48 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu return -EFAULT; buf[sizeof(_buf) - 1] = '\0'; + pos = buf; + buf = strsep(&pos, " "); + if (!buf) + return -EINVAL; - if (strncmp(buf, "tx ", 3) == 0) { - buf += 3; + if (!strcmp(buf, "tx")) tx = true; - } else if (strncmp(buf, "rx ", 3) == 0) { - buf += 3; + else if (!strcmp(buf, "rx")) tx = false; - } else + else return -EINVAL; - if (strncmp(buf, "start ", 6) == 0) { - buf += 6; + buf = strsep(&pos, " "); + if (!buf) + return -EINVAL; + if (!strcmp(buf, "start")) { start = true; if (!tx) return -EINVAL; - } else if (strncmp(buf, "stop ", 5) == 0) { - buf += 5; + } else if (!strcmp(buf, "stop")) { start = false; - } else + } else { return -EINVAL; + } - ret = kstrtoul(buf, 0, &tid); - if (ret) - return ret; + buf = strsep(&pos, " "); + if (!buf) + return -EINVAL; + if (sscanf(buf, "timeout=%d", &timeout) == 1) { + buf = strsep(&pos, " "); + if (!buf || !tx || !start) + return -EINVAL; + } - if (tid >= IEEE80211_NUM_TIDS) + ret = kstrtoul(buf, 0, &tid); + if (ret || tid >= IEEE80211_NUM_TIDS) return -EINVAL; if (tx) { if (start) - ret = ieee80211_start_tx_ba_session(&sta->sta, tid, 5000); + ret = ieee80211_start_tx_ba_session(&sta->sta, tid, + timeout); else ret = ieee80211_stop_tx_ba_session(&sta->sta, tid); } else { @@ -322,14 +358,14 @@ STA_OPS(vht_capa); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ - sta->debugfs.dir, sta, &sta_ ##name## _ops); + sta->debugfs_dir, sta, &sta_ ##name## _ops); #define DEBUGFS_ADD_COUNTER(name, field) \ if (sizeof(sta->field) == sizeof(u32)) \ - debugfs_create_u32(#name, 0400, sta->debugfs.dir, \ + debugfs_create_u32(#name, 0400, sta->debugfs_dir, \ (u32 *) &sta->field); \ else \ - debugfs_create_u64(#name, 0400, sta->debugfs.dir, \ + debugfs_create_u64(#name, 0400, sta->debugfs_dir, \ (u64 *) &sta->field); void ieee80211_sta_debugfs_add(struct sta_info *sta) @@ -339,8 +375,6 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) struct dentry *stations_dir = sta->sdata->debugfs.subdir_stations; u8 mac[3*ETH_ALEN]; - sta->debugfs.add_has_run = true; - if (!stations_dir) return; @@ -355,8 +389,8 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) * destroyed quickly enough the old station's debugfs * dir might still be around. */ - sta->debugfs.dir = debugfs_create_dir(mac, stations_dir); - if (!sta->debugfs.dir) + sta->debugfs_dir = debugfs_create_dir(mac, stations_dir); + if (!sta->debugfs_dir) return; DEBUGFS_ADD(flags); @@ -372,14 +406,14 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) if (sizeof(sta->driver_buffered_tids) == sizeof(u32)) debugfs_create_x32("driver_buffered_tids", 0400, - sta->debugfs.dir, + sta->debugfs_dir, (u32 *)&sta->driver_buffered_tids); else debugfs_create_x64("driver_buffered_tids", 0400, - sta->debugfs.dir, + sta->debugfs_dir, (u64 *)&sta->driver_buffered_tids); - drv_sta_add_debugfs(local, sdata, &sta->sta, sta->debugfs.dir); + drv_sta_add_debugfs(local, sdata, &sta->sta, sta->debugfs_dir); } void ieee80211_sta_debugfs_remove(struct sta_info *sta) @@ -387,7 +421,7 @@ void ieee80211_sta_debugfs_remove(struct sta_info *sta) struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; - drv_sta_remove_debugfs(local, sdata, &sta->sta, sta->debugfs.dir); - debugfs_remove_recursive(sta->debugfs.dir); - sta->debugfs.dir = NULL; + drv_sta_remove_debugfs(local, sdata, &sta->sta, sta->debugfs_dir); + debugfs_remove_recursive(sta->debugfs_dir); + sta->debugfs_dir = NULL; } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 18b0d65baff0..184473c257eb 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1,3 +1,8 @@ +/* +* Portions of this file +* Copyright(c) 2016 Intel Deutschland GmbH +*/ + #ifndef __MAC80211_DRIVER_OPS #define __MAC80211_DRIVER_OPS @@ -29,6 +34,16 @@ static inline void drv_tx(struct ieee80211_local *local, local->ops->tx(&local->hw, control, skb); } +static inline void drv_sync_rx_queues(struct ieee80211_local *local, + struct sta_info *sta) +{ + if (local->ops->sync_rx_queues) { + trace_drv_sync_rx_queues(local, sta->sdata, &sta->sta); + local->ops->sync_rx_queues(&local->hw); + trace_drv_return_void(local); + } +} + static inline void drv_get_et_strings(struct ieee80211_sub_if_data *sdata, u32 sset, u8 *data) { diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index fc3238376b39..c6d4b75eb60b 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -649,8 +649,6 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, const u8 *bssid, return NULL; } - sta->rx_stats.last_rx = jiffies; - /* make sure mandatory rates are always added */ sband = local->hw.wiphy->bands[band]; sta->sta.supp_rates[band] = supp_rates | @@ -670,10 +668,11 @@ static int ieee80211_sta_active_ibss(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); list_for_each_entry_rcu(sta, &local->sta_list, list) { + unsigned long last_active = ieee80211_sta_last_active(sta); + if (sta->sdata == sdata && - time_after(sta->rx_stats.last_rx + - IEEE80211_IBSS_MERGE_INTERVAL, - jiffies)) { + time_is_after_jiffies(last_active + + IEEE80211_IBSS_MERGE_INTERVAL)) { active++; break; } @@ -1236,8 +1235,6 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata, if (!sta) return; - sta->rx_stats.last_rx = jiffies; - /* make sure mandatory rates are always added */ sband = local->hw.wiphy->bands[band]; sta->sta.supp_rates[band] = supp_rates | @@ -1259,11 +1256,13 @@ static void ieee80211_ibss_sta_expire(struct ieee80211_sub_if_data *sdata) mutex_lock(&local->sta_mtx); list_for_each_entry_safe(sta, tmp, &local->sta_list, list) { + unsigned long last_active = ieee80211_sta_last_active(sta); + if (sdata != sta->sdata) continue; - if (time_after(jiffies, sta->rx_stats.last_rx + exp_time) || - (time_after(jiffies, sta->rx_stats.last_rx + exp_rsn) && + if (time_is_before_jiffies(last_active + exp_time) || + (time_is_before_jiffies(last_active + exp_rsn) && sta->sta_state != IEEE80211_STA_AUTHORIZED)) { sta_dbg(sta->sdata, "expiring inactive %sSTA %pM\n", sta->sta_state != IEEE80211_STA_AUTHORIZED ? diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 804575ff7af5..8857b01b82d0 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -696,6 +696,11 @@ struct ieee80211_if_mesh { /* offset from skb->data while building IE */ int meshconf_offset; + + struct mesh_table *mesh_paths; + struct mesh_table *mpp_paths; /* Store paths for MPP&MAP */ + int mesh_paths_generation; + int mpp_paths_generation; }; #ifdef CONFIG_MAC80211_MESH @@ -797,6 +802,7 @@ struct mac80211_qos_map { enum txq_info_flags { IEEE80211_TXQ_STOP, IEEE80211_TXQ_AMPDU, + IEEE80211_TXQ_NO_AMSDU, }; struct txq_info { @@ -1489,6 +1495,11 @@ u64 ieee80211_mgmt_tx_cookie(struct ieee80211_local *local); int ieee80211_attach_ack_skb(struct ieee80211_local *local, struct sk_buff *skb, u64 *cookie, gfp_t gfp); +void ieee80211_check_fast_rx(struct sta_info *sta); +void __ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata); +void ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata); +void ieee80211_clear_fast_rx(struct sta_info *sta); + /* STA code */ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata); int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, @@ -1719,6 +1730,10 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta); enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta); void ieee80211_sta_set_rx_nss(struct sta_info *sta); +enum ieee80211_sta_rx_bandwidth +ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width); +enum nl80211_chan_width ieee80211_sta_cap_chan_bw(struct sta_info *sta); +void ieee80211_sta_set_rx_nss(struct sta_info *sta); void ieee80211_process_mu_groups(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt); u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 453b4e741780..097ece8b5c02 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1093,7 +1093,7 @@ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata) sdata->fragment_next = 0; if (ieee80211_vif_is_mesh(&sdata->vif)) - mesh_rmc_free(sdata); + ieee80211_mesh_teardown_sdata(sdata); } static void ieee80211_uninit(struct net_device *dev) diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 3df7b0392d30..edd6f2945f69 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -338,6 +338,7 @@ static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, } else { rcu_assign_pointer(sta->gtk[idx], new); } + ieee80211_check_fast_rx(sta); } else { defunikey = old && old == key_mtx_dereference(sdata->local, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 8190bf27ebff..33c80de61eca 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -558,6 +558,8 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, if (!ops->set_key) wiphy->flags |= WIPHY_FLAG_IBSS_RSN; + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_RRM); + wiphy->bss_priv_size = sizeof(struct ieee80211_bss); local = wiphy_priv(wiphy); @@ -854,7 +856,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) /* Only HW csum features are currently compatible with mac80211 */ feature_whitelist = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | - NETIF_F_GSO_SOFTWARE; + NETIF_F_GSO_SOFTWARE | NETIF_F_RXCSUM; if (WARN_ON(hw->netdev_features & ~feature_whitelist)) return -EINVAL; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index d32cefcb63b0..dcc1facc807c 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -25,7 +25,6 @@ bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt) void ieee80211s_init(void) { - mesh_pathtbl_init(); mesh_allocated = 1; rm_cache = kmem_cache_create("mesh_rmc", sizeof(struct rmc_entry), 0, 0, NULL); @@ -35,7 +34,6 @@ void ieee80211s_stop(void) { if (!mesh_allocated) return; - mesh_pathtbl_unregister(); kmem_cache_destroy(rm_cache); } @@ -176,22 +174,23 @@ int mesh_rmc_init(struct ieee80211_sub_if_data *sdata) return -ENOMEM; sdata->u.mesh.rmc->idx_mask = RMC_BUCKETS - 1; for (i = 0; i < RMC_BUCKETS; i++) - INIT_LIST_HEAD(&sdata->u.mesh.rmc->bucket[i]); + INIT_HLIST_HEAD(&sdata->u.mesh.rmc->bucket[i]); return 0; } void mesh_rmc_free(struct ieee80211_sub_if_data *sdata) { struct mesh_rmc *rmc = sdata->u.mesh.rmc; - struct rmc_entry *p, *n; + struct rmc_entry *p; + struct hlist_node *n; int i; if (!sdata->u.mesh.rmc) return; for (i = 0; i < RMC_BUCKETS; i++) { - list_for_each_entry_safe(p, n, &rmc->bucket[i], list) { - list_del(&p->list); + hlist_for_each_entry_safe(p, n, &rmc->bucket[i], list) { + hlist_del(&p->list); kmem_cache_free(rm_cache, p); } } @@ -220,16 +219,20 @@ int mesh_rmc_check(struct ieee80211_sub_if_data *sdata, u32 seqnum = 0; int entries = 0; u8 idx; - struct rmc_entry *p, *n; + struct rmc_entry *p; + struct hlist_node *n; + + if (!rmc) + return -1; /* Don't care about endianness since only match matters */ memcpy(&seqnum, &mesh_hdr->seqnum, sizeof(mesh_hdr->seqnum)); idx = le32_to_cpu(mesh_hdr->seqnum) & rmc->idx_mask; - list_for_each_entry_safe(p, n, &rmc->bucket[idx], list) { + hlist_for_each_entry_safe(p, n, &rmc->bucket[idx], list) { ++entries; if (time_after(jiffies, p->exp_time) || entries == RMC_QUEUE_MAX_LEN) { - list_del(&p->list); + hlist_del(&p->list); kmem_cache_free(rm_cache, p); --entries; } else if ((seqnum == p->seqnum) && ether_addr_equal(sa, p->sa)) @@ -243,7 +246,7 @@ int mesh_rmc_check(struct ieee80211_sub_if_data *sdata, p->seqnum = seqnum; p->exp_time = jiffies + RMC_TIMEOUT; memcpy(p->sa, sa, ETH_ALEN); - list_add(&p->list, &rmc->bucket[idx]); + hlist_add_head(&p->list, &rmc->bucket[idx]); return 0; } @@ -1348,12 +1351,6 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata) ifmsh->last_preq + msecs_to_jiffies(ifmsh->mshcfg.dot11MeshHWMPpreqMinInterval))) mesh_path_start_discovery(sdata); - if (test_and_clear_bit(MESH_WORK_GROW_MPATH_TABLE, &ifmsh->wrkq_flags)) - mesh_mpath_table_grow(); - - if (test_and_clear_bit(MESH_WORK_GROW_MPP_TABLE, &ifmsh->wrkq_flags)) - mesh_mpp_table_grow(); - if (test_and_clear_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags)) ieee80211_mesh_housekeeping(sdata); @@ -1388,6 +1385,9 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) /* Allocate all mesh structures when creating the first mesh interface. */ if (!mesh_allocated) ieee80211s_init(); + + mesh_pathtbl_init(sdata); + setup_timer(&ifmsh->mesh_path_timer, ieee80211_mesh_path_timer, (unsigned long) sdata); @@ -1402,3 +1402,9 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) sdata->vif.bss_conf.bssid = zero_addr; } + +void ieee80211_mesh_teardown_sdata(struct ieee80211_sub_if_data *sdata) +{ + mesh_rmc_free(sdata); + mesh_pathtbl_unregister(sdata); +} diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 87c017a3b1ce..26b9ccbe1fce 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -21,8 +21,6 @@ /** * enum mesh_path_flags - mac80211 mesh path flags * - * - * * @MESH_PATH_ACTIVE: the mesh path can be used for forwarding * @MESH_PATH_RESOLVING: the discovery process is running for this mesh path * @MESH_PATH_SN_VALID: the mesh path contains a valid destination sequence @@ -32,6 +30,8 @@ * @MESH_PATH_RESOLVED: the mesh path can has been resolved * @MESH_PATH_REQ_QUEUED: there is an unsent path request for this destination * already queued up, waiting for the discovery process to start. + * @MESH_PATH_DELETED: the mesh path has been deleted and should no longer + * be used * * MESH_PATH_RESOLVED is used by the mesh path timer to * decide when to stop or cancel the mesh path discovery. @@ -43,6 +43,7 @@ enum mesh_path_flags { MESH_PATH_FIXED = BIT(3), MESH_PATH_RESOLVED = BIT(4), MESH_PATH_REQ_QUEUED = BIT(5), + MESH_PATH_DELETED = BIT(6), }; /** @@ -51,10 +52,6 @@ enum mesh_path_flags { * * * @MESH_WORK_HOUSEKEEPING: run the periodic mesh housekeeping tasks - * @MESH_WORK_GROW_MPATH_TABLE: the mesh path table is full and needs - * to grow. - * @MESH_WORK_GROW_MPP_TABLE: the mesh portals table is full and needs to - * grow * @MESH_WORK_ROOT: the mesh root station needs to send a frame * @MESH_WORK_DRIFT_ADJUST: time to compensate for clock drift relative to other * mesh nodes @@ -62,8 +59,6 @@ enum mesh_path_flags { */ enum mesh_deferred_task_flags { MESH_WORK_HOUSEKEEPING, - MESH_WORK_GROW_MPATH_TABLE, - MESH_WORK_GROW_MPP_TABLE, MESH_WORK_ROOT, MESH_WORK_DRIFT_ADJUST, MESH_WORK_MBSS_CHANGED, @@ -73,12 +68,16 @@ enum mesh_deferred_task_flags { * struct mesh_path - mac80211 mesh path structure * * @dst: mesh path destination mac address + * @mpp: mesh proxy mac address + * @rhash: rhashtable list pointer + * @gate_list: list pointer for known gates list * @sdata: mesh subif * @next_hop: mesh neighbor to which frames for this destination will be * forwarded * @timer: mesh path discovery timer * @frame_queue: pending queue for frames sent to this destination while the * path is unresolved + * @rcu: rcu head for freeing mesh path * @sn: target sequence number * @metric: current metric to this destination * @hop_count: hops to destination @@ -97,14 +96,16 @@ enum mesh_deferred_task_flags { * @is_gate: the destination station of this path is a mesh gate * * - * The combination of dst and sdata is unique in the mesh path table. Since the - * next_hop STA is only protected by RCU as well, deleting the STA must also - * remove/substitute the mesh_path structure and wait until that is no longer - * reachable before destroying the STA completely. + * The dst address is unique in the mesh path table. Since the mesh_path is + * protected by RCU, deleting the next_hop STA must remove / substitute the + * mesh_path structure and wait until that is no longer reachable before + * destroying the STA completely. */ struct mesh_path { u8 dst[ETH_ALEN]; u8 mpp[ETH_ALEN]; /* used for MPP or MAP */ + struct rhash_head rhash; + struct hlist_node gate_list; struct ieee80211_sub_if_data *sdata; struct sta_info __rcu *next_hop; struct timer_list timer; @@ -128,34 +129,17 @@ struct mesh_path { /** * struct mesh_table * - * @hash_buckets: array of hash buckets of the table - * @hashwlock: array of locks to protect write operations, one per bucket - * @hash_mask: 2^size_order - 1, used to compute hash idx - * @hash_rnd: random value used for hash computations - * @entries: number of entries in the table - * @free_node: function to free nodes of the table - * @copy_node: function to copy nodes of the table - * @size_order: determines size of the table, there will be 2^size_order hash - * buckets * @known_gates: list of known mesh gates and their mpaths by the station. The * gate's mpath may or may not be resolved and active. - * - * rcu_head: RCU head to free the table + * @gates_lock: protects updates to known_gates + * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr + * @entries: number of entries in the table */ struct mesh_table { - /* Number of buckets will be 2^N */ - struct hlist_head *hash_buckets; - spinlock_t *hashwlock; /* One per bucket, for add/del */ - unsigned int hash_mask; /* (2^size_order) - 1 */ - __u32 hash_rnd; /* Used for hash generation */ - atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ - void (*free_node) (struct hlist_node *p, bool free_leafs); - int (*copy_node) (struct hlist_node *p, struct mesh_table *newtbl); - int size_order; - struct hlist_head *known_gates; + struct hlist_head known_gates; spinlock_t gates_lock; - - struct rcu_head rcu_head; + struct rhashtable rhead; + atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ }; /* Recent multicast cache */ @@ -170,20 +154,21 @@ struct mesh_table { * @seqnum: mesh sequence number of the frame * @exp_time: expiration time of the entry, in jiffies * @sa: source address of the frame + * @list: hashtable list pointer * * The Recent Multicast Cache keeps track of the latest multicast frames that * have been received by a mesh interface and discards received multicast frames * that are found in the cache. */ struct rmc_entry { - struct list_head list; - u32 seqnum; + struct hlist_node list; unsigned long exp_time; + u32 seqnum; u8 sa[ETH_ALEN]; }; struct mesh_rmc { - struct list_head bucket[RMC_BUCKETS]; + struct hlist_head bucket[RMC_BUCKETS]; u32 idx_mask; }; @@ -234,6 +219,7 @@ void ieee80211s_init(void); void ieee80211s_update_metric(struct ieee80211_local *local, struct sta_info *sta, struct sk_buff *skb); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); +void ieee80211_mesh_teardown_sdata(struct ieee80211_sub_if_data *sdata); int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh); @@ -299,9 +285,6 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, void mesh_sta_cleanup(struct sta_info *sta); /* Private interfaces */ -/* Mesh tables */ -void mesh_mpath_table_grow(void); -void mesh_mpp_table_grow(void); /* Mesh paths */ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, u8 ttl, const u8 *target, u32 target_sn, @@ -309,8 +292,8 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta); void mesh_path_flush_pending(struct mesh_path *mpath); void mesh_path_tx_pending(struct mesh_path *mpath); -int mesh_pathtbl_init(void); -void mesh_pathtbl_unregister(void); +int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); +void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata); int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_path_timer(unsigned long data); void mesh_path_flush_by_nexthop(struct sta_info *sta); @@ -319,8 +302,6 @@ void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata); bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt); -extern int mesh_paths_generation; -extern int mpp_paths_generation; #ifdef CONFIG_MAC80211_MESH static inline diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 5b6aec1a0630..8f9c3bde835f 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -530,7 +530,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, const u8 *target_addr, *orig_addr; const u8 *da; u8 target_flags, ttl, flags; - u32 orig_sn, target_sn, lifetime, target_metric; + u32 orig_sn, target_sn, lifetime, target_metric = 0; bool reply = false; bool forward = true; bool root_is_gate; @@ -1012,6 +1012,10 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) goto enddiscovery; spin_lock_bh(&mpath->state_lock); + if (mpath->flags & MESH_PATH_DELETED) { + spin_unlock_bh(&mpath->state_lock); + goto enddiscovery; + } mpath->flags &= ~MESH_PATH_REQ_QUEUED; if (preq_node->flags & PREQ_Q_F_START) { if (mpath->flags & MESH_PATH_RESOLVING) { diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 2ba7aa56b11c..6db2ddfa0695 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -18,11 +18,22 @@ #include "ieee80211_i.h" #include "mesh.h" -/* There will be initially 2^INIT_PATHS_SIZE_ORDER buckets */ -#define INIT_PATHS_SIZE_ORDER 2 +static void mesh_path_free_rcu(struct mesh_table *tbl, struct mesh_path *mpath); -/* Keep the mean chain length below this constant */ -#define MEAN_CHAIN_LEN 2 +static u32 mesh_table_hash(const void *addr, u32 len, u32 seed) +{ + /* Use last four bytes of hw addr as hash index */ + return jhash_1word(*(u32 *)(addr+2), seed); +} + +static const struct rhashtable_params mesh_rht_params = { + .nelem_hint = 2, + .automatic_shrinking = true, + .key_len = ETH_ALEN, + .key_offset = offsetof(struct mesh_path, dst), + .head_offset = offsetof(struct mesh_path, rhash), + .hashfn = mesh_table_hash, +}; static inline bool mpath_expired(struct mesh_path *mpath) { @@ -31,173 +42,36 @@ static inline bool mpath_expired(struct mesh_path *mpath) !(mpath->flags & MESH_PATH_FIXED); } -struct mpath_node { - struct hlist_node list; - struct rcu_head rcu; - /* This indirection allows two different tables to point to the same - * mesh_path structure, useful when resizing - */ - struct mesh_path *mpath; -}; - -static struct mesh_table __rcu *mesh_paths; -static struct mesh_table __rcu *mpp_paths; /* Store paths for MPP&MAP */ - -int mesh_paths_generation; -int mpp_paths_generation; - -/* This lock will have the grow table function as writer and add / delete nodes - * as readers. RCU provides sufficient protection only when reading the table - * (i.e. doing lookups). Adding or adding or removing nodes requires we take - * the read lock or we risk operating on an old table. The write lock is only - * needed when modifying the number of buckets a table. - */ -static DEFINE_RWLOCK(pathtbl_resize_lock); - - -static inline struct mesh_table *resize_dereference_paths( - struct mesh_table __rcu *table) +static void mesh_path_rht_free(void *ptr, void *tblptr) { - return rcu_dereference_protected(table, - lockdep_is_held(&pathtbl_resize_lock)); -} + struct mesh_path *mpath = ptr; + struct mesh_table *tbl = tblptr; -static inline struct mesh_table *resize_dereference_mesh_paths(void) -{ - return resize_dereference_paths(mesh_paths); + mesh_path_free_rcu(tbl, mpath); } -static inline struct mesh_table *resize_dereference_mpp_paths(void) +static struct mesh_table *mesh_table_alloc(void) { - return resize_dereference_paths(mpp_paths); -} - -/* - * CAREFUL -- "tbl" must not be an expression, - * in particular not an rcu_dereference(), since - * it's used twice. So it is illegal to do - * for_each_mesh_entry(rcu_dereference(...), ...) - */ -#define for_each_mesh_entry(tbl, node, i) \ - for (i = 0; i <= tbl->hash_mask; i++) \ - hlist_for_each_entry_rcu(node, &tbl->hash_buckets[i], list) - - -static struct mesh_table *mesh_table_alloc(int size_order) -{ - int i; struct mesh_table *newtbl; newtbl = kmalloc(sizeof(struct mesh_table), GFP_ATOMIC); if (!newtbl) return NULL; - newtbl->hash_buckets = kzalloc(sizeof(struct hlist_head) * - (1 << size_order), GFP_ATOMIC); - - if (!newtbl->hash_buckets) { - kfree(newtbl); - return NULL; - } - - newtbl->hashwlock = kmalloc(sizeof(spinlock_t) * - (1 << size_order), GFP_ATOMIC); - if (!newtbl->hashwlock) { - kfree(newtbl->hash_buckets); - kfree(newtbl); - return NULL; - } - - newtbl->size_order = size_order; - newtbl->hash_mask = (1 << size_order) - 1; + INIT_HLIST_HEAD(&newtbl->known_gates); atomic_set(&newtbl->entries, 0); - get_random_bytes(&newtbl->hash_rnd, - sizeof(newtbl->hash_rnd)); - for (i = 0; i <= newtbl->hash_mask; i++) - spin_lock_init(&newtbl->hashwlock[i]); spin_lock_init(&newtbl->gates_lock); return newtbl; } -static void __mesh_table_free(struct mesh_table *tbl) +static void mesh_table_free(struct mesh_table *tbl) { - kfree(tbl->hash_buckets); - kfree(tbl->hashwlock); + rhashtable_free_and_destroy(&tbl->rhead, + mesh_path_rht_free, tbl); kfree(tbl); } -static void mesh_table_free(struct mesh_table *tbl, bool free_leafs) -{ - struct hlist_head *mesh_hash; - struct hlist_node *p, *q; - struct mpath_node *gate; - int i; - - mesh_hash = tbl->hash_buckets; - for (i = 0; i <= tbl->hash_mask; i++) { - spin_lock_bh(&tbl->hashwlock[i]); - hlist_for_each_safe(p, q, &mesh_hash[i]) { - tbl->free_node(p, free_leafs); - atomic_dec(&tbl->entries); - } - spin_unlock_bh(&tbl->hashwlock[i]); - } - if (free_leafs) { - spin_lock_bh(&tbl->gates_lock); - hlist_for_each_entry_safe(gate, q, - tbl->known_gates, list) { - hlist_del(&gate->list); - kfree(gate); - } - kfree(tbl->known_gates); - spin_unlock_bh(&tbl->gates_lock); - } - - __mesh_table_free(tbl); -} - -static int mesh_table_grow(struct mesh_table *oldtbl, - struct mesh_table *newtbl) -{ - struct hlist_head *oldhash; - struct hlist_node *p, *q; - int i; - - if (atomic_read(&oldtbl->entries) - < MEAN_CHAIN_LEN * (oldtbl->hash_mask + 1)) - return -EAGAIN; - - newtbl->free_node = oldtbl->free_node; - newtbl->copy_node = oldtbl->copy_node; - newtbl->known_gates = oldtbl->known_gates; - atomic_set(&newtbl->entries, atomic_read(&oldtbl->entries)); - - oldhash = oldtbl->hash_buckets; - for (i = 0; i <= oldtbl->hash_mask; i++) - hlist_for_each(p, &oldhash[i]) - if (oldtbl->copy_node(p, newtbl) < 0) - goto errcopy; - - return 0; - -errcopy: - for (i = 0; i <= newtbl->hash_mask; i++) { - hlist_for_each_safe(p, q, &newtbl->hash_buckets[i]) - oldtbl->free_node(p, 0); - } - return -ENOMEM; -} - -static u32 mesh_table_hash(const u8 *addr, struct ieee80211_sub_if_data *sdata, - struct mesh_table *tbl) -{ - /* Use last four bytes of hw addr and interface index as hash index */ - return jhash_2words(*(u32 *)(addr+2), sdata->dev->ifindex, - tbl->hash_rnd) & tbl->hash_mask; -} - - /** * * mesh_path_assign_nexthop - update mesh path next hop @@ -340,23 +214,15 @@ static struct mesh_path *mpath_lookup(struct mesh_table *tbl, const u8 *dst, struct ieee80211_sub_if_data *sdata) { struct mesh_path *mpath; - struct hlist_head *bucket; - struct mpath_node *node; - - bucket = &tbl->hash_buckets[mesh_table_hash(dst, sdata, tbl)]; - hlist_for_each_entry_rcu(node, bucket, list) { - mpath = node->mpath; - if (mpath->sdata == sdata && - ether_addr_equal(dst, mpath->dst)) { - if (mpath_expired(mpath)) { - spin_lock_bh(&mpath->state_lock); - mpath->flags &= ~MESH_PATH_ACTIVE; - spin_unlock_bh(&mpath->state_lock); - } - return mpath; - } + + mpath = rhashtable_lookup_fast(&tbl->rhead, dst, mesh_rht_params); + + if (mpath && mpath_expired(mpath)) { + spin_lock_bh(&mpath->state_lock); + mpath->flags &= ~MESH_PATH_ACTIVE; + spin_unlock_bh(&mpath->state_lock); } - return NULL; + return mpath; } /** @@ -371,15 +237,52 @@ static struct mesh_path *mpath_lookup(struct mesh_table *tbl, const u8 *dst, struct mesh_path * mesh_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) { - return mpath_lookup(rcu_dereference(mesh_paths), dst, sdata); + return mpath_lookup(sdata->u.mesh.mesh_paths, dst, sdata); } struct mesh_path * mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) { - return mpath_lookup(rcu_dereference(mpp_paths), dst, sdata); + return mpath_lookup(sdata->u.mesh.mpp_paths, dst, sdata); } +static struct mesh_path * +__mesh_path_lookup_by_idx(struct mesh_table *tbl, int idx) +{ + int i = 0, ret; + struct mesh_path *mpath = NULL; + struct rhashtable_iter iter; + + ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); + if (ret) + return NULL; + + ret = rhashtable_walk_start(&iter); + if (ret && ret != -EAGAIN) + goto err; + + while ((mpath = rhashtable_walk_next(&iter))) { + if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) + continue; + if (IS_ERR(mpath)) + break; + if (i++ == idx) + break; + } +err: + rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); + + if (IS_ERR(mpath) || !mpath) + return NULL; + + if (mpath_expired(mpath)) { + spin_lock_bh(&mpath->state_lock); + mpath->flags &= ~MESH_PATH_ACTIVE; + spin_unlock_bh(&mpath->state_lock); + } + return mpath; +} /** * mesh_path_lookup_by_idx - look up a path in the mesh path table by its index @@ -393,25 +296,7 @@ mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) struct mesh_path * mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { - struct mesh_table *tbl = rcu_dereference(mesh_paths); - struct mpath_node *node; - int i; - int j = 0; - - for_each_mesh_entry(tbl, node, i) { - if (sdata && node->mpath->sdata != sdata) - continue; - if (j++ == idx) { - if (mpath_expired(node->mpath)) { - spin_lock_bh(&node->mpath->state_lock); - node->mpath->flags &= ~MESH_PATH_ACTIVE; - spin_unlock_bh(&node->mpath->state_lock); - } - return node->mpath; - } - } - - return NULL; + return __mesh_path_lookup_by_idx(sdata->u.mesh.mesh_paths, idx); } /** @@ -426,19 +311,7 @@ mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) struct mesh_path * mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { - struct mesh_table *tbl = rcu_dereference(mpp_paths); - struct mpath_node *node; - int i; - int j = 0; - - for_each_mesh_entry(tbl, node, i) { - if (sdata && node->mpath->sdata != sdata) - continue; - if (j++ == idx) - return node->mpath; - } - - return NULL; + return __mesh_path_lookup_by_idx(sdata->u.mesh.mpp_paths, idx); } /** @@ -448,30 +321,26 @@ mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) int mesh_path_add_gate(struct mesh_path *mpath) { struct mesh_table *tbl; - struct mpath_node *gate, *new_gate; int err; rcu_read_lock(); - tbl = rcu_dereference(mesh_paths); - - hlist_for_each_entry_rcu(gate, tbl->known_gates, list) - if (gate->mpath == mpath) { - err = -EEXIST; - goto err_rcu; - } + tbl = mpath->sdata->u.mesh.mesh_paths; - new_gate = kzalloc(sizeof(struct mpath_node), GFP_ATOMIC); - if (!new_gate) { - err = -ENOMEM; + spin_lock_bh(&mpath->state_lock); + if (mpath->is_gate) { + err = -EEXIST; + spin_unlock_bh(&mpath->state_lock); goto err_rcu; } - mpath->is_gate = true; mpath->sdata->u.mesh.num_gates++; - new_gate->mpath = mpath; - spin_lock_bh(&tbl->gates_lock); - hlist_add_head_rcu(&new_gate->list, tbl->known_gates); - spin_unlock_bh(&tbl->gates_lock); + + spin_lock(&tbl->gates_lock); + hlist_add_head_rcu(&mpath->gate_list, &tbl->known_gates); + spin_unlock(&tbl->gates_lock); + + spin_unlock_bh(&mpath->state_lock); + mpath_dbg(mpath->sdata, "Mesh path: Recorded new gate: %pM. %d known gates\n", mpath->dst, mpath->sdata->u.mesh.num_gates); @@ -485,28 +354,22 @@ err_rcu: * mesh_gate_del - remove a mesh gate from the list of known gates * @tbl: table which holds our list of known gates * @mpath: gate mpath - * - * Locking: must be called inside rcu_read_lock() section */ static void mesh_gate_del(struct mesh_table *tbl, struct mesh_path *mpath) { - struct mpath_node *gate; - struct hlist_node *q; + lockdep_assert_held(&mpath->state_lock); + if (!mpath->is_gate) + return; - hlist_for_each_entry_safe(gate, q, tbl->known_gates, list) { - if (gate->mpath != mpath) - continue; - spin_lock_bh(&tbl->gates_lock); - hlist_del_rcu(&gate->list); - kfree_rcu(gate, rcu); - spin_unlock_bh(&tbl->gates_lock); - mpath->sdata->u.mesh.num_gates--; - mpath->is_gate = false; - mpath_dbg(mpath->sdata, - "Mesh path: Deleted gate: %pM. %d known gates\n", - mpath->dst, mpath->sdata->u.mesh.num_gates); - break; - } + mpath->is_gate = false; + spin_lock_bh(&tbl->gates_lock); + hlist_del_rcu(&mpath->gate_list); + mpath->sdata->u.mesh.num_gates--; + spin_unlock_bh(&tbl->gates_lock); + + mpath_dbg(mpath->sdata, + "Mesh path: Deleted gate: %pM. %d known gates\n", + mpath->dst, mpath->sdata->u.mesh.num_gates); } /** @@ -518,6 +381,31 @@ int mesh_gate_num(struct ieee80211_sub_if_data *sdata) return sdata->u.mesh.num_gates; } +static +struct mesh_path *mesh_path_new(struct ieee80211_sub_if_data *sdata, + const u8 *dst, gfp_t gfp_flags) +{ + struct mesh_path *new_mpath; + + new_mpath = kzalloc(sizeof(struct mesh_path), gfp_flags); + if (!new_mpath) + return NULL; + + memcpy(new_mpath->dst, dst, ETH_ALEN); + eth_broadcast_addr(new_mpath->rann_snd_addr); + new_mpath->is_root = false; + new_mpath->sdata = sdata; + new_mpath->flags = 0; + skb_queue_head_init(&new_mpath->frame_queue); + new_mpath->timer.data = (unsigned long) new_mpath; + new_mpath->timer.function = mesh_path_timer; + new_mpath->exp_time = jiffies; + spin_lock_init(&new_mpath->state_lock); + init_timer(&new_mpath->timer); + + return new_mpath; +} + /** * mesh_path_add - allocate and add a new path to the mesh path table * @dst: destination address of the path (ETH_ALEN length) @@ -530,15 +418,9 @@ int mesh_gate_num(struct ieee80211_sub_if_data *sdata) struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst) { - struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - struct ieee80211_local *local = sdata->local; struct mesh_table *tbl; struct mesh_path *mpath, *new_mpath; - struct mpath_node *node, *new_node; - struct hlist_head *bucket; - int grow = 0; - int err; - u32 hash_idx; + int ret; if (ether_addr_equal(dst, sdata->vif.addr)) /* never add ourselves as neighbours */ @@ -550,129 +432,44 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, if (atomic_add_unless(&sdata->u.mesh.mpaths, 1, MESH_MAX_MPATHS) == 0) return ERR_PTR(-ENOSPC); - read_lock_bh(&pathtbl_resize_lock); - tbl = resize_dereference_mesh_paths(); - - hash_idx = mesh_table_hash(dst, sdata, tbl); - bucket = &tbl->hash_buckets[hash_idx]; - - spin_lock(&tbl->hashwlock[hash_idx]); - - hlist_for_each_entry(node, bucket, list) { - mpath = node->mpath; - if (mpath->sdata == sdata && - ether_addr_equal(dst, mpath->dst)) - goto found; - } - - err = -ENOMEM; - new_mpath = kzalloc(sizeof(struct mesh_path), GFP_ATOMIC); + new_mpath = mesh_path_new(sdata, dst, GFP_ATOMIC); if (!new_mpath) - goto err_path_alloc; - - new_node = kmalloc(sizeof(struct mpath_node), GFP_ATOMIC); - if (!new_node) - goto err_node_alloc; - - memcpy(new_mpath->dst, dst, ETH_ALEN); - eth_broadcast_addr(new_mpath->rann_snd_addr); - new_mpath->is_root = false; - new_mpath->sdata = sdata; - new_mpath->flags = 0; - skb_queue_head_init(&new_mpath->frame_queue); - new_node->mpath = new_mpath; - new_mpath->timer.data = (unsigned long) new_mpath; - new_mpath->timer.function = mesh_path_timer; - new_mpath->exp_time = jiffies; - spin_lock_init(&new_mpath->state_lock); - init_timer(&new_mpath->timer); - - hlist_add_head_rcu(&new_node->list, bucket); - if (atomic_inc_return(&tbl->entries) >= - MEAN_CHAIN_LEN * (tbl->hash_mask + 1)) - grow = 1; - - mesh_paths_generation++; - - if (grow) { - set_bit(MESH_WORK_GROW_MPATH_TABLE, &ifmsh->wrkq_flags); - ieee80211_queue_work(&local->hw, &sdata->work); - } - mpath = new_mpath; -found: - spin_unlock(&tbl->hashwlock[hash_idx]); - read_unlock_bh(&pathtbl_resize_lock); - return mpath; + return ERR_PTR(-ENOMEM); -err_node_alloc: - kfree(new_mpath); -err_path_alloc: - atomic_dec(&sdata->u.mesh.mpaths); - spin_unlock(&tbl->hashwlock[hash_idx]); - read_unlock_bh(&pathtbl_resize_lock); - return ERR_PTR(err); -} + tbl = sdata->u.mesh.mesh_paths; + do { + ret = rhashtable_lookup_insert_fast(&tbl->rhead, + &new_mpath->rhash, + mesh_rht_params); -static void mesh_table_free_rcu(struct rcu_head *rcu) -{ - struct mesh_table *tbl = container_of(rcu, struct mesh_table, rcu_head); + if (ret == -EEXIST) + mpath = rhashtable_lookup_fast(&tbl->rhead, + dst, + mesh_rht_params); - mesh_table_free(tbl, false); -} + } while (unlikely(ret == -EEXIST && !mpath)); -void mesh_mpath_table_grow(void) -{ - struct mesh_table *oldtbl, *newtbl; - - write_lock_bh(&pathtbl_resize_lock); - oldtbl = resize_dereference_mesh_paths(); - newtbl = mesh_table_alloc(oldtbl->size_order + 1); - if (!newtbl) - goto out; - if (mesh_table_grow(oldtbl, newtbl) < 0) { - __mesh_table_free(newtbl); - goto out; - } - rcu_assign_pointer(mesh_paths, newtbl); - - call_rcu(&oldtbl->rcu_head, mesh_table_free_rcu); - - out: - write_unlock_bh(&pathtbl_resize_lock); -} + if (ret && ret != -EEXIST) + return ERR_PTR(ret); -void mesh_mpp_table_grow(void) -{ - struct mesh_table *oldtbl, *newtbl; - - write_lock_bh(&pathtbl_resize_lock); - oldtbl = resize_dereference_mpp_paths(); - newtbl = mesh_table_alloc(oldtbl->size_order + 1); - if (!newtbl) - goto out; - if (mesh_table_grow(oldtbl, newtbl) < 0) { - __mesh_table_free(newtbl); - goto out; + /* At this point either new_mpath was added, or we found a + * matching entry already in the table; in the latter case + * free the unnecessary new entry. + */ + if (ret == -EEXIST) { + kfree(new_mpath); + new_mpath = mpath; } - rcu_assign_pointer(mpp_paths, newtbl); - call_rcu(&oldtbl->rcu_head, mesh_table_free_rcu); - - out: - write_unlock_bh(&pathtbl_resize_lock); + sdata->u.mesh.mesh_paths_generation++; + return new_mpath; } int mpp_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst, const u8 *mpp) { - struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - struct ieee80211_local *local = sdata->local; struct mesh_table *tbl; - struct mesh_path *mpath, *new_mpath; - struct mpath_node *node, *new_node; - struct hlist_head *bucket; - int grow = 0; - int err = 0; - u32 hash_idx; + struct mesh_path *new_mpath; + int ret; if (ether_addr_equal(dst, sdata->vif.addr)) /* never add ourselves as neighbours */ @@ -681,65 +478,19 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, if (is_multicast_ether_addr(dst)) return -ENOTSUPP; - err = -ENOMEM; - new_mpath = kzalloc(sizeof(struct mesh_path), GFP_ATOMIC); - if (!new_mpath) - goto err_path_alloc; + new_mpath = mesh_path_new(sdata, dst, GFP_ATOMIC); - new_node = kmalloc(sizeof(struct mpath_node), GFP_ATOMIC); - if (!new_node) - goto err_node_alloc; + if (!new_mpath) + return -ENOMEM; - read_lock_bh(&pathtbl_resize_lock); - memcpy(new_mpath->dst, dst, ETH_ALEN); memcpy(new_mpath->mpp, mpp, ETH_ALEN); - new_mpath->sdata = sdata; - new_mpath->flags = 0; - skb_queue_head_init(&new_mpath->frame_queue); - new_node->mpath = new_mpath; - init_timer(&new_mpath->timer); - new_mpath->exp_time = jiffies; - spin_lock_init(&new_mpath->state_lock); - - tbl = resize_dereference_mpp_paths(); + tbl = sdata->u.mesh.mpp_paths; + ret = rhashtable_lookup_insert_fast(&tbl->rhead, + &new_mpath->rhash, + mesh_rht_params); - hash_idx = mesh_table_hash(dst, sdata, tbl); - bucket = &tbl->hash_buckets[hash_idx]; - - spin_lock(&tbl->hashwlock[hash_idx]); - - err = -EEXIST; - hlist_for_each_entry(node, bucket, list) { - mpath = node->mpath; - if (mpath->sdata == sdata && - ether_addr_equal(dst, mpath->dst)) - goto err_exists; - } - - hlist_add_head_rcu(&new_node->list, bucket); - if (atomic_inc_return(&tbl->entries) >= - MEAN_CHAIN_LEN * (tbl->hash_mask + 1)) - grow = 1; - - spin_unlock(&tbl->hashwlock[hash_idx]); - read_unlock_bh(&pathtbl_resize_lock); - - mpp_paths_generation++; - - if (grow) { - set_bit(MESH_WORK_GROW_MPP_TABLE, &ifmsh->wrkq_flags); - ieee80211_queue_work(&local->hw, &sdata->work); - } - return 0; - -err_exists: - spin_unlock(&tbl->hashwlock[hash_idx]); - read_unlock_bh(&pathtbl_resize_lock); - kfree(new_node); -err_node_alloc: - kfree(new_mpath); -err_path_alloc: - return err; + sdata->u.mesh.mpp_paths_generation++; + return ret; } @@ -753,17 +504,26 @@ err_path_alloc: */ void mesh_plink_broken(struct sta_info *sta) { - struct mesh_table *tbl; + struct ieee80211_sub_if_data *sdata = sta->sdata; + struct mesh_table *tbl = sdata->u.mesh.mesh_paths; static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; - struct mpath_node *node; - struct ieee80211_sub_if_data *sdata = sta->sdata; - int i; + struct rhashtable_iter iter; + int ret; - rcu_read_lock(); - tbl = rcu_dereference(mesh_paths); - for_each_mesh_entry(tbl, node, i) { - mpath = node->mpath; + ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); + if (ret) + return; + + ret = rhashtable_walk_start(&iter); + if (ret && ret != -EAGAIN) + goto out; + + while ((mpath = rhashtable_walk_next(&iter))) { + if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) + continue; + if (IS_ERR(mpath)) + break; if (rcu_access_pointer(mpath->next_hop) == sta && mpath->flags & MESH_PATH_ACTIVE && !(mpath->flags & MESH_PATH_FIXED)) { @@ -777,33 +537,30 @@ void mesh_plink_broken(struct sta_info *sta) WLAN_REASON_MESH_PATH_DEST_UNREACHABLE, bcast); } } - rcu_read_unlock(); +out: + rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); } -static void mesh_path_node_reclaim(struct rcu_head *rp) +static void mesh_path_free_rcu(struct mesh_table *tbl, + struct mesh_path *mpath) { - struct mpath_node *node = container_of(rp, struct mpath_node, rcu); + struct ieee80211_sub_if_data *sdata = mpath->sdata; - del_timer_sync(&node->mpath->timer); - kfree(node->mpath); - kfree(node); + spin_lock_bh(&mpath->state_lock); + mpath->flags |= MESH_PATH_RESOLVING | MESH_PATH_DELETED; + mesh_gate_del(tbl, mpath); + spin_unlock_bh(&mpath->state_lock); + del_timer_sync(&mpath->timer); + atomic_dec(&sdata->u.mesh.mpaths); + atomic_dec(&tbl->entries); + kfree_rcu(mpath, rcu); } -/* needs to be called with the corresponding hashwlock taken */ -static void __mesh_path_del(struct mesh_table *tbl, struct mpath_node *node) +static void __mesh_path_del(struct mesh_table *tbl, struct mesh_path *mpath) { - struct mesh_path *mpath = node->mpath; - struct ieee80211_sub_if_data *sdata = node->mpath->sdata; - - spin_lock(&mpath->state_lock); - mpath->flags |= MESH_PATH_RESOLVING; - if (mpath->is_gate) - mesh_gate_del(tbl, mpath); - hlist_del_rcu(&node->list); - call_rcu(&node->rcu, mesh_path_node_reclaim); - spin_unlock(&mpath->state_lock); - atomic_dec(&sdata->u.mesh.mpaths); - atomic_dec(&tbl->entries); + rhashtable_remove_fast(&tbl->rhead, &mpath->rhash, mesh_rht_params); + mesh_path_free_rcu(tbl, mpath); } /** @@ -819,65 +576,88 @@ static void __mesh_path_del(struct mesh_table *tbl, struct mpath_node *node) */ void mesh_path_flush_by_nexthop(struct sta_info *sta) { - struct mesh_table *tbl; + struct ieee80211_sub_if_data *sdata = sta->sdata; + struct mesh_table *tbl = sdata->u.mesh.mesh_paths; struct mesh_path *mpath; - struct mpath_node *node; - int i; + struct rhashtable_iter iter; + int ret; - rcu_read_lock(); - read_lock_bh(&pathtbl_resize_lock); - tbl = resize_dereference_mesh_paths(); - for_each_mesh_entry(tbl, node, i) { - mpath = node->mpath; - if (rcu_access_pointer(mpath->next_hop) == sta) { - spin_lock(&tbl->hashwlock[i]); - __mesh_path_del(tbl, node); - spin_unlock(&tbl->hashwlock[i]); - } + ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); + if (ret) + return; + + ret = rhashtable_walk_start(&iter); + if (ret && ret != -EAGAIN) + goto out; + + while ((mpath = rhashtable_walk_next(&iter))) { + if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) + continue; + if (IS_ERR(mpath)) + break; + + if (rcu_access_pointer(mpath->next_hop) == sta) + __mesh_path_del(tbl, mpath); } - read_unlock_bh(&pathtbl_resize_lock); - rcu_read_unlock(); +out: + rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); } static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, const u8 *proxy) { - struct mesh_table *tbl; - struct mesh_path *mpp; - struct mpath_node *node; - int i; + struct mesh_table *tbl = sdata->u.mesh.mpp_paths; + struct mesh_path *mpath; + struct rhashtable_iter iter; + int ret; - rcu_read_lock(); - read_lock_bh(&pathtbl_resize_lock); - tbl = resize_dereference_mpp_paths(); - for_each_mesh_entry(tbl, node, i) { - mpp = node->mpath; - if (ether_addr_equal(mpp->mpp, proxy)) { - spin_lock(&tbl->hashwlock[i]); - __mesh_path_del(tbl, node); - spin_unlock(&tbl->hashwlock[i]); - } + ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); + if (ret) + return; + + ret = rhashtable_walk_start(&iter); + if (ret && ret != -EAGAIN) + goto out; + + while ((mpath = rhashtable_walk_next(&iter))) { + if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) + continue; + if (IS_ERR(mpath)) + break; + + if (ether_addr_equal(mpath->mpp, proxy)) + __mesh_path_del(tbl, mpath); } - read_unlock_bh(&pathtbl_resize_lock); - rcu_read_unlock(); +out: + rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); } -static void table_flush_by_iface(struct mesh_table *tbl, - struct ieee80211_sub_if_data *sdata) +static void table_flush_by_iface(struct mesh_table *tbl) { struct mesh_path *mpath; - struct mpath_node *node; - int i; + struct rhashtable_iter iter; + int ret; + + ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); + if (ret) + return; + + ret = rhashtable_walk_start(&iter); + if (ret && ret != -EAGAIN) + goto out; - WARN_ON(!rcu_read_lock_held()); - for_each_mesh_entry(tbl, node, i) { - mpath = node->mpath; - if (mpath->sdata != sdata) + while ((mpath = rhashtable_walk_next(&iter))) { + if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) continue; - spin_lock_bh(&tbl->hashwlock[i]); - __mesh_path_del(tbl, node); - spin_unlock_bh(&tbl->hashwlock[i]); + if (IS_ERR(mpath)) + break; + __mesh_path_del(tbl, mpath); } +out: + rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); } /** @@ -890,16 +670,8 @@ static void table_flush_by_iface(struct mesh_table *tbl, */ void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) { - struct mesh_table *tbl; - - rcu_read_lock(); - read_lock_bh(&pathtbl_resize_lock); - tbl = resize_dereference_mesh_paths(); - table_flush_by_iface(tbl, sdata); - tbl = resize_dereference_mpp_paths(); - table_flush_by_iface(tbl, sdata); - read_unlock_bh(&pathtbl_resize_lock); - rcu_read_unlock(); + table_flush_by_iface(sdata->u.mesh.mesh_paths); + table_flush_by_iface(sdata->u.mesh.mpp_paths); } /** @@ -911,37 +683,25 @@ void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) * * Returns: 0 if successful */ -static int table_path_del(struct mesh_table __rcu *rcu_tbl, +static int table_path_del(struct mesh_table *tbl, struct ieee80211_sub_if_data *sdata, const u8 *addr) { - struct mesh_table *tbl; struct mesh_path *mpath; - struct mpath_node *node; - struct hlist_head *bucket; - int hash_idx; - int err = 0; - - tbl = resize_dereference_paths(rcu_tbl); - hash_idx = mesh_table_hash(addr, sdata, tbl); - bucket = &tbl->hash_buckets[hash_idx]; - - spin_lock(&tbl->hashwlock[hash_idx]); - hlist_for_each_entry(node, bucket, list) { - mpath = node->mpath; - if (mpath->sdata == sdata && - ether_addr_equal(addr, mpath->dst)) { - __mesh_path_del(tbl, node); - goto enddel; - } + + rcu_read_lock(); + mpath = rhashtable_lookup_fast(&tbl->rhead, addr, mesh_rht_params); + if (!mpath) { + rcu_read_unlock(); + return -ENXIO; } - err = -ENXIO; -enddel: - spin_unlock(&tbl->hashwlock[hash_idx]); - return err; + __mesh_path_del(tbl, mpath); + rcu_read_unlock(); + return 0; } + /** * mesh_path_del - delete a mesh path from the table * @@ -952,36 +712,13 @@ enddel: */ int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr) { - int err = 0; + int err; /* flush relevant mpp entries first */ mpp_flush_by_proxy(sdata, addr); - read_lock_bh(&pathtbl_resize_lock); - err = table_path_del(mesh_paths, sdata, addr); - mesh_paths_generation++; - read_unlock_bh(&pathtbl_resize_lock); - - return err; -} - -/** - * mpp_path_del - delete a mesh proxy path from the table - * - * @addr: addr address (ETH_ALEN length) - * @sdata: local subif - * - * Returns: 0 if successful - */ -static int mpp_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr) -{ - int err = 0; - - read_lock_bh(&pathtbl_resize_lock); - err = table_path_del(mpp_paths, sdata, addr); - mpp_paths_generation++; - read_unlock_bh(&pathtbl_resize_lock); - + err = table_path_del(sdata->u.mesh.mesh_paths, sdata, addr); + sdata->u.mesh.mesh_paths_generation++; return err; } @@ -1015,39 +752,30 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) struct ieee80211_sub_if_data *sdata = mpath->sdata; struct mesh_table *tbl; struct mesh_path *from_mpath = mpath; - struct mpath_node *gate = NULL; + struct mesh_path *gate; bool copy = false; - struct hlist_head *known_gates; - - rcu_read_lock(); - tbl = rcu_dereference(mesh_paths); - known_gates = tbl->known_gates; - rcu_read_unlock(); - if (!known_gates) - return -EHOSTUNREACH; + tbl = sdata->u.mesh.mesh_paths; - hlist_for_each_entry_rcu(gate, known_gates, list) { - if (gate->mpath->sdata != sdata) - continue; - - if (gate->mpath->flags & MESH_PATH_ACTIVE) { - mpath_dbg(sdata, "Forwarding to %pM\n", gate->mpath->dst); - mesh_path_move_to_queue(gate->mpath, from_mpath, copy); - from_mpath = gate->mpath; + rcu_read_lock(); + hlist_for_each_entry_rcu(gate, &tbl->known_gates, gate_list) { + if (gate->flags & MESH_PATH_ACTIVE) { + mpath_dbg(sdata, "Forwarding to %pM\n", gate->dst); + mesh_path_move_to_queue(gate, from_mpath, copy); + from_mpath = gate; copy = true; } else { mpath_dbg(sdata, "Not forwarding to %pM (flags %#x)\n", - gate->mpath->dst, gate->mpath->flags); + gate->dst, gate->flags); } } - hlist_for_each_entry_rcu(gate, known_gates, list) - if (gate->mpath->sdata == sdata) { - mpath_dbg(sdata, "Sending to %pM\n", gate->mpath->dst); - mesh_path_tx_pending(gate->mpath); - } + hlist_for_each_entry_rcu(gate, &tbl->known_gates, gate_list) { + mpath_dbg(sdata, "Sending to %pM\n", gate->dst); + mesh_path_tx_pending(gate); + } + rcu_read_unlock(); return (from_mpath == mpath) ? -EHOSTUNREACH : 0; } @@ -1104,118 +832,73 @@ void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop) mesh_path_tx_pending(mpath); } -static void mesh_path_node_free(struct hlist_node *p, bool free_leafs) -{ - struct mesh_path *mpath; - struct mpath_node *node = hlist_entry(p, struct mpath_node, list); - mpath = node->mpath; - hlist_del_rcu(p); - if (free_leafs) { - del_timer_sync(&mpath->timer); - kfree(mpath); - } - kfree(node); -} - -static int mesh_path_node_copy(struct hlist_node *p, struct mesh_table *newtbl) -{ - struct mesh_path *mpath; - struct mpath_node *node, *new_node; - u32 hash_idx; - - new_node = kmalloc(sizeof(struct mpath_node), GFP_ATOMIC); - if (new_node == NULL) - return -ENOMEM; - - node = hlist_entry(p, struct mpath_node, list); - mpath = node->mpath; - new_node->mpath = mpath; - hash_idx = mesh_table_hash(mpath->dst, mpath->sdata, newtbl); - hlist_add_head(&new_node->list, - &newtbl->hash_buckets[hash_idx]); - return 0; -} - -int mesh_pathtbl_init(void) +int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) { struct mesh_table *tbl_path, *tbl_mpp; int ret; - tbl_path = mesh_table_alloc(INIT_PATHS_SIZE_ORDER); + tbl_path = mesh_table_alloc(); if (!tbl_path) return -ENOMEM; - tbl_path->free_node = &mesh_path_node_free; - tbl_path->copy_node = &mesh_path_node_copy; - tbl_path->known_gates = kzalloc(sizeof(struct hlist_head), GFP_ATOMIC); - if (!tbl_path->known_gates) { - ret = -ENOMEM; - goto free_path; - } - INIT_HLIST_HEAD(tbl_path->known_gates); - - tbl_mpp = mesh_table_alloc(INIT_PATHS_SIZE_ORDER); + tbl_mpp = mesh_table_alloc(); if (!tbl_mpp) { ret = -ENOMEM; goto free_path; } - tbl_mpp->free_node = &mesh_path_node_free; - tbl_mpp->copy_node = &mesh_path_node_copy; - tbl_mpp->known_gates = kzalloc(sizeof(struct hlist_head), GFP_ATOMIC); - if (!tbl_mpp->known_gates) { - ret = -ENOMEM; - goto free_mpp; - } - INIT_HLIST_HEAD(tbl_mpp->known_gates); - /* Need no locking since this is during init */ - RCU_INIT_POINTER(mesh_paths, tbl_path); - RCU_INIT_POINTER(mpp_paths, tbl_mpp); + rhashtable_init(&tbl_path->rhead, &mesh_rht_params); + rhashtable_init(&tbl_mpp->rhead, &mesh_rht_params); + + sdata->u.mesh.mesh_paths = tbl_path; + sdata->u.mesh.mpp_paths = tbl_mpp; return 0; -free_mpp: - mesh_table_free(tbl_mpp, true); free_path: - mesh_table_free(tbl_path, true); + mesh_table_free(tbl_path); return ret; } -void mesh_path_expire(struct ieee80211_sub_if_data *sdata) +static +void mesh_path_tbl_expire(struct ieee80211_sub_if_data *sdata, + struct mesh_table *tbl) { - struct mesh_table *tbl; struct mesh_path *mpath; - struct mpath_node *node; - int i; + struct rhashtable_iter iter; + int ret; - rcu_read_lock(); - tbl = rcu_dereference(mesh_paths); - for_each_mesh_entry(tbl, node, i) { - if (node->mpath->sdata != sdata) + ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_KERNEL); + if (ret) + return; + + ret = rhashtable_walk_start(&iter); + if (ret && ret != -EAGAIN) + goto out; + + while ((mpath = rhashtable_walk_next(&iter))) { + if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) continue; - mpath = node->mpath; + if (IS_ERR(mpath)) + break; if ((!(mpath->flags & MESH_PATH_RESOLVING)) && (!(mpath->flags & MESH_PATH_FIXED)) && time_after(jiffies, mpath->exp_time + MESH_PATH_EXPIRE)) - mesh_path_del(mpath->sdata, mpath->dst); - } - - tbl = rcu_dereference(mpp_paths); - for_each_mesh_entry(tbl, node, i) { - if (node->mpath->sdata != sdata) - continue; - mpath = node->mpath; - if ((!(mpath->flags & MESH_PATH_FIXED)) && - time_after(jiffies, mpath->exp_time + MESH_PATH_EXPIRE)) - mpp_path_del(mpath->sdata, mpath->dst); + __mesh_path_del(tbl, mpath); } +out: + rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); +} - rcu_read_unlock(); +void mesh_path_expire(struct ieee80211_sub_if_data *sdata) +{ + mesh_path_tbl_expire(sdata, sdata->u.mesh.mesh_paths); + mesh_path_tbl_expire(sdata, sdata->u.mesh.mpp_paths); } -void mesh_pathtbl_unregister(void) +void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata) { - /* no need for locking during exit path */ - mesh_table_free(rcu_dereference_protected(mesh_paths, 1), true); - mesh_table_free(rcu_dereference_protected(mpp_paths, 1), true); + mesh_table_free(sdata->u.mesh.mesh_paths); + mesh_table_free(sdata->u.mesh.mpp_paths); } diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index a07e93c21c9e..563bea050383 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -61,7 +61,7 @@ static bool rssi_threshold_check(struct ieee80211_sub_if_data *sdata, s32 rssi_threshold = sdata->u.mesh.mshcfg.rssi_threshold; return rssi_threshold == 0 || (sta && - (s8)-ewma_signal_read(&sta->rx_stats.avg_signal) > + (s8)-ewma_signal_read(&sta->rx_stats_avg.signal) > rssi_threshold); } @@ -331,7 +331,9 @@ free: * * @sta: mesh peer link to deactivate * - * All mesh paths with this peer as next hop will be flushed + * Mesh paths with this peer as next hop should be flushed + * by the caller outside of plink_lock. + * * Returns beacon changed flag if the beacon content changed. * * Locking: the caller must hold sta->mesh->plink_lock @@ -346,7 +348,6 @@ static u32 __mesh_plink_deactivate(struct sta_info *sta) if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) changed = mesh_plink_dec_estab_count(sdata); sta->mesh->plink_state = NL80211_PLINK_BLOCKED; - mesh_path_flush_by_nexthop(sta); ieee80211_mps_sta_status_update(sta); changed |= ieee80211_mps_set_sta_local_pm(sta, @@ -374,6 +375,7 @@ u32 mesh_plink_deactivate(struct sta_info *sta) sta->sta.addr, sta->mesh->llid, sta->mesh->plid, sta->mesh->reason); spin_unlock_bh(&sta->mesh->plink_lock); + mesh_path_flush_by_nexthop(sta); return changed; } @@ -748,6 +750,7 @@ u32 mesh_plink_block(struct sta_info *sta) changed = __mesh_plink_deactivate(sta); sta->mesh->plink_state = NL80211_PLINK_BLOCKED; spin_unlock_bh(&sta->mesh->plink_lock); + mesh_path_flush_by_nexthop(sta); return changed; } @@ -797,6 +800,7 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, struct mesh_config *mshcfg = &sdata->u.mesh.mshcfg; enum ieee80211_self_protected_actioncode action = 0; u32 changed = 0; + bool flush = false; mpl_dbg(sdata, "peer %pM in state %s got event %s\n", sta->sta.addr, mplstates[sta->mesh->plink_state], mplevents[event]); @@ -885,6 +889,7 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, changed |= mesh_set_short_slot_time(sdata); mesh_plink_close(sdata, sta, event); action = WLAN_SP_MESH_PEERING_CLOSE; + flush = true; break; case OPN_ACPT: action = WLAN_SP_MESH_PEERING_CONFIRM; @@ -916,6 +921,8 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, break; } spin_unlock_bh(&sta->mesh->plink_lock); + if (flush) + mesh_path_flush_by_nexthop(sta); if (action) { mesh_plink_frame_tx(sdata, sta, action, sta->sta.addr, sta->mesh->llid, sta->mesh->plid, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 281b8d6e5109..d3c75ac8a029 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -122,15 +122,16 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - if (unlikely(!sdata->u.mgd.associated)) + if (unlikely(!ifmgd->associated)) return; - ifmgd->probe_send_count = 0; + if (ifmgd->probe_send_count) + ifmgd->probe_send_count = 0; if (ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR)) return; - mod_timer(&sdata->u.mgd.conn_mon_timer, + mod_timer(&ifmgd->conn_mon_timer, round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); } @@ -2216,6 +2217,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) const u8 *ssid; u8 *dst = ifmgd->associated->bssid; u8 unicast_limit = max(1, max_probe_tries - 3); + struct sta_info *sta; /* * Try sending broadcast probe requests for the last three @@ -2234,6 +2236,14 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) */ ifmgd->probe_send_count++; + if (dst) { + mutex_lock(&sdata->local->sta_mtx); + sta = sta_info_get(sdata, dst); + if (!WARN_ON(!sta)) + ieee80211_check_fast_rx(sta); + mutex_unlock(&sdata->local->sta_mtx); + } + if (ieee80211_hw_check(&sdata->local->hw, REPORTS_TX_ACK_STATUS)) { ifmgd->nullfunc_failed = false; ieee80211_send_nullfunc(sdata->local, sdata, false); diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c index 0be0aadfc559..88e6ebbbe24f 100644 --- a/net/mac80211/ocb.c +++ b/net/mac80211/ocb.c @@ -75,8 +75,6 @@ void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata, if (!sta) return; - sta->rx_stats.last_rx = jiffies; - /* Add only mandatory rates for now */ sband = local->hw.wiphy->bands[band]; sta->sta.supp_rates[band] = diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 624fe5b81615..8d3260785b94 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -96,9 +96,9 @@ static inline void rate_control_add_sta_debugfs(struct sta_info *sta) { #ifdef CONFIG_MAC80211_DEBUGFS struct rate_control_ref *ref = sta->rate_ctrl; - if (ref && sta->debugfs.dir && ref->ops->add_sta_debugfs) + if (ref && sta->debugfs_dir && ref->ops->add_sta_debugfs) ref->ops->add_sta_debugfs(ref->priv, sta->rate_ctrl_priv, - sta->debugfs.dir); + sta->debugfs_dir); #endif } diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 370d677b547b..d77a9a842338 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -883,6 +883,59 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, ratetbl->rate[offset].flags = flags; } +static inline int +minstrel_ht_get_prob_ewma(struct minstrel_ht_sta *mi, int rate) +{ + int group = rate / MCS_GROUP_RATES; + rate %= MCS_GROUP_RATES; + return mi->groups[group].rates[rate].prob_ewma; +} + +static int +minstrel_ht_get_max_amsdu_len(struct minstrel_ht_sta *mi) +{ + int group = mi->max_prob_rate / MCS_GROUP_RATES; + const struct mcs_group *g = &minstrel_mcs_groups[group]; + int rate = mi->max_prob_rate % MCS_GROUP_RATES; + + /* Disable A-MSDU if max_prob_rate is bad */ + if (mi->groups[group].rates[rate].prob_ewma < MINSTREL_FRAC(50, 100)) + return 1; + + /* If the rate is slower than single-stream MCS1, make A-MSDU limit small */ + if (g->duration[rate] > MCS_DURATION(1, 0, 52)) + return 500; + + /* + * If the rate is slower than single-stream MCS4, limit A-MSDU to usual + * data packet size + */ + if (g->duration[rate] > MCS_DURATION(1, 0, 104)) + return 1600; + + /* + * If the rate is slower than single-stream MCS7, or if the max throughput + * rate success probability is less than 75%, limit A-MSDU to twice the usual + * data packet size + */ + if (g->duration[rate] > MCS_DURATION(1, 0, 260) || + (minstrel_ht_get_prob_ewma(mi, mi->max_tp_rate[0]) < + MINSTREL_FRAC(75, 100))) + return 3200; + + /* + * HT A-MPDU limits maximum MPDU size under BA agreement to 4095 bytes. + * Since aggregation sessions are started/stopped without txq flush, use + * the limit here to avoid the complexity of having to de-aggregate + * packets in the queue. + */ + if (!mi->sta->vht_cap.vht_supported) + return IEEE80211_MAX_MPDU_LEN_HT_BA; + + /* unlimited */ + return 0; +} + static void minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { @@ -907,6 +960,7 @@ minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_prob_rate); } + mi->sta->max_rc_amsdu_len = minstrel_ht_get_max_amsdu_len(mi); rates->rate[i].idx = -1; rate_control_set_rates(mp->hw, mi->sta, rates); } @@ -924,6 +978,7 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) struct minstrel_rate_stats *mrs; struct minstrel_mcs_group_data *mg; unsigned int sample_dur, sample_group, cur_max_tp_streams; + int tp_rate1, tp_rate2; int sample_idx = 0; if (mi->sample_wait > 0) { @@ -945,14 +1000,22 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) mrs = &mg->rates[sample_idx]; sample_idx += sample_group * MCS_GROUP_RATES; + /* Set tp_rate1, tp_rate2 to the highest / second highest max_tp_rate */ + if (minstrel_get_duration(mi->max_tp_rate[0]) > + minstrel_get_duration(mi->max_tp_rate[1])) { + tp_rate1 = mi->max_tp_rate[1]; + tp_rate2 = mi->max_tp_rate[0]; + } else { + tp_rate1 = mi->max_tp_rate[0]; + tp_rate2 = mi->max_tp_rate[1]; + } + /* * Sampling might add some overhead (RTS, no aggregation) - * to the frame. Hence, don't use sampling for the currently - * used rates. + * to the frame. Hence, don't use sampling for the highest currently + * used highest throughput or probability rate. */ - if (sample_idx == mi->max_tp_rate[0] || - sample_idx == mi->max_tp_rate[1] || - sample_idx == mi->max_prob_rate) + if (sample_idx == mi->max_tp_rate[0] || sample_idx == mi->max_prob_rate) return -1; /* @@ -967,10 +1030,10 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) * if the link is working perfectly. */ - cur_max_tp_streams = minstrel_mcs_groups[mi->max_tp_rate[0] / + cur_max_tp_streams = minstrel_mcs_groups[tp_rate1 / MCS_GROUP_RATES].streams; sample_dur = minstrel_get_duration(sample_idx); - if (sample_dur >= minstrel_get_duration(mi->max_tp_rate[1]) && + if (sample_dur >= minstrel_get_duration(tp_rate2) && (cur_max_tp_streams - 1 < minstrel_mcs_groups[sample_group].streams || sample_dur >= minstrel_get_duration(mi->max_prob_rate))) { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index dc27becb9b71..c2b659e9a9f9 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -722,8 +722,8 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) return -1; } -static int iwl80211_get_cs_keyid(const struct ieee80211_cipher_scheme *cs, - struct sk_buff *skb) +static int ieee80211_get_cs_keyid(const struct ieee80211_cipher_scheme *cs, + struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; __le16 fc; @@ -1421,16 +1421,9 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { sta->rx_stats.last_rx = jiffies; if (ieee80211_is_data(hdr->frame_control) && - !is_multicast_ether_addr(hdr->addr1)) { - sta->rx_stats.last_rate_idx = - status->rate_idx; - sta->rx_stats.last_rate_flag = - status->flag; - sta->rx_stats.last_rate_vht_flag = - status->vht_flag; - sta->rx_stats.last_rate_vht_nss = - status->vht_nss; - } + !is_multicast_ether_addr(hdr->addr1)) + sta->rx_stats.last_rate = + sta_stats_encode_rate(status); } } else if (rx->sdata->vif.type == NL80211_IFTYPE_OCB) { sta->rx_stats.last_rx = jiffies; @@ -1440,22 +1433,22 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) * match the current local configuration when processed. */ sta->rx_stats.last_rx = jiffies; - if (ieee80211_is_data(hdr->frame_control)) { - sta->rx_stats.last_rate_idx = status->rate_idx; - sta->rx_stats.last_rate_flag = status->flag; - sta->rx_stats.last_rate_vht_flag = status->vht_flag; - sta->rx_stats.last_rate_vht_nss = status->vht_nss; - } + if (ieee80211_is_data(hdr->frame_control)) + sta->rx_stats.last_rate = sta_stats_encode_rate(status); } if (rx->sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_sta_rx_notify(rx->sdata, hdr); sta->rx_stats.fragments++; + + u64_stats_update_begin(&rx->sta->rx_stats.syncp); sta->rx_stats.bytes += rx->skb->len; + u64_stats_update_end(&rx->sta->rx_stats.syncp); + if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) { sta->rx_stats.last_signal = status->signal; - ewma_signal_add(&sta->rx_stats.avg_signal, -status->signal); + ewma_signal_add(&sta->rx_stats_avg.signal, -status->signal); } if (status->chains) { @@ -1467,7 +1460,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) continue; sta->rx_stats.chain_signal_last[i] = signal; - ewma_signal_add(&sta->rx_stats.chain_signal_avg[i], + ewma_signal_add(&sta->rx_stats_avg.chain_signal[i], -signal); } } @@ -1586,7 +1579,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) if (ieee80211_has_protected(fc) && rx->sta->cipher_scheme) { cs = rx->sta->cipher_scheme; - keyid = iwl80211_get_cs_keyid(cs, rx->skb); + keyid = ieee80211_get_cs_keyid(cs, rx->skb); if (unlikely(keyid < 0)) return RX_DROP_UNUSABLE; } @@ -1670,7 +1663,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) hdrlen = ieee80211_hdrlen(fc); if (cs) { - keyidx = iwl80211_get_cs_keyid(cs, rx->skb); + keyidx = ieee80211_get_cs_keyid(cs, rx->skb); if (unlikely(keyidx < 0)) return RX_DROP_UNUSABLE; @@ -2129,6 +2122,17 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) ieee80211_rx_stats(dev, skb->len); + if (rx->sta) { + /* The seqno index has the same property as needed + * for the rx_msdu field, i.e. it is IEEE80211_NUM_TIDS + * for non-QoS-data frames. Here we know it's a data + * frame, so count MSDUs. + */ + u64_stats_update_begin(&rx->sta->rx_stats.syncp); + rx->sta->rx_stats.msdu[rx->seqno_idx]++; + u64_stats_update_end(&rx->sta->rx_stats.syncp); + } + if ((sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && !(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) && @@ -2415,15 +2419,6 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) return RX_DROP_MONITOR; - if (rx->sta) { - /* The seqno index has the same property as needed - * for the rx_msdu field, i.e. it is IEEE80211_NUM_TIDS - * for non-QoS-data frames. Here we know it's a data - * frame, so count MSDUs. - */ - rx->sta->rx_stats.msdu[rx->seqno_idx]++; - } - /* * Send unexpected-4addr-frame event to hostapd. For older versions, * also drop the frame to cooked monitor interfaces. @@ -2474,14 +2469,14 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) rx->skb->dev = dev; - if (local->ps_sdata && local->hw.conf.dynamic_ps_timeout > 0 && + if (!ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS) && + local->ps_sdata && local->hw.conf.dynamic_ps_timeout > 0 && !is_multicast_ether_addr( ((struct ethhdr *)rx->skb->data)->h_dest) && (!local->scanning && - !test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state))) { - mod_timer(&local->dynamic_ps_timer, jiffies + - msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout)); - } + !test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state))) + mod_timer(&local->dynamic_ps_timer, jiffies + + msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout)); ieee80211_deliver_skb(rx); @@ -3201,7 +3196,7 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx, res = rxh(rx); \ if (res != RX_CONTINUE) \ goto rxh_next; \ - } while (0); + } while (0) /* Lock here to avoid hitting all of the data used in the RX * path (e.g. key data, station data, ...) concurrently when @@ -3219,30 +3214,30 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx, */ rx->skb = skb; - CALL_RXH(ieee80211_rx_h_check_more_data) - CALL_RXH(ieee80211_rx_h_uapsd_and_pspoll) - CALL_RXH(ieee80211_rx_h_sta_process) - CALL_RXH(ieee80211_rx_h_decrypt) - CALL_RXH(ieee80211_rx_h_defragment) - CALL_RXH(ieee80211_rx_h_michael_mic_verify) + CALL_RXH(ieee80211_rx_h_check_more_data); + CALL_RXH(ieee80211_rx_h_uapsd_and_pspoll); + CALL_RXH(ieee80211_rx_h_sta_process); + CALL_RXH(ieee80211_rx_h_decrypt); + CALL_RXH(ieee80211_rx_h_defragment); + CALL_RXH(ieee80211_rx_h_michael_mic_verify); /* must be after MMIC verify so header is counted in MPDU mic */ #ifdef CONFIG_MAC80211_MESH if (ieee80211_vif_is_mesh(&rx->sdata->vif)) CALL_RXH(ieee80211_rx_h_mesh_fwding); #endif - CALL_RXH(ieee80211_rx_h_amsdu) - CALL_RXH(ieee80211_rx_h_data) + CALL_RXH(ieee80211_rx_h_amsdu); + CALL_RXH(ieee80211_rx_h_data); /* special treatment -- needs the queue */ res = ieee80211_rx_h_ctrl(rx, frames); if (res != RX_CONTINUE) goto rxh_next; - CALL_RXH(ieee80211_rx_h_mgmt_check) - CALL_RXH(ieee80211_rx_h_action) - CALL_RXH(ieee80211_rx_h_userspace_mgmt) - CALL_RXH(ieee80211_rx_h_action_return) - CALL_RXH(ieee80211_rx_h_mgmt) + CALL_RXH(ieee80211_rx_h_mgmt_check); + CALL_RXH(ieee80211_rx_h_action); + CALL_RXH(ieee80211_rx_h_userspace_mgmt); + CALL_RXH(ieee80211_rx_h_action_return); + CALL_RXH(ieee80211_rx_h_mgmt); rxh_next: ieee80211_rx_handlers_result(rx, res); @@ -3265,10 +3260,10 @@ static void ieee80211_invoke_rx_handlers(struct ieee80211_rx_data *rx) res = rxh(rx); \ if (res != RX_CONTINUE) \ goto rxh_next; \ - } while (0); + } while (0) - CALL_RXH(ieee80211_rx_h_check_dup) - CALL_RXH(ieee80211_rx_h_check) + CALL_RXH(ieee80211_rx_h_check_dup); + CALL_RXH(ieee80211_rx_h_check); ieee80211_rx_reorder_ampdu(rx, &reorder_release); @@ -3513,6 +3508,351 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) return false; } +void ieee80211_check_fast_rx(struct sta_info *sta) +{ + struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_local *local = sdata->local; + struct ieee80211_key *key; + struct ieee80211_fast_rx fastrx = { + .dev = sdata->dev, + .vif_type = sdata->vif.type, + .control_port_protocol = sdata->control_port_protocol, + }, *old, *new = NULL; + bool assign = false; + + /* use sparse to check that we don't return without updating */ + __acquire(check_fast_rx); + + BUILD_BUG_ON(sizeof(fastrx.rfc1042_hdr) != sizeof(rfc1042_header)); + BUILD_BUG_ON(sizeof(fastrx.rfc1042_hdr) != ETH_ALEN); + ether_addr_copy(fastrx.rfc1042_hdr, rfc1042_header); + ether_addr_copy(fastrx.vif_addr, sdata->vif.addr); + + fastrx.uses_rss = ieee80211_hw_check(&local->hw, USES_RSS); + + /* fast-rx doesn't do reordering */ + if (ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION) && + !ieee80211_hw_check(&local->hw, SUPPORTS_REORDERING_BUFFER)) + goto clear; + + switch (sdata->vif.type) { + case NL80211_IFTYPE_STATION: + /* 4-addr is harder to deal with, later maybe */ + if (sdata->u.mgd.use_4addr) + goto clear; + /* software powersave is a huge mess, avoid all of it */ + if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK)) + goto clear; + if (ieee80211_hw_check(&local->hw, SUPPORTS_PS) && + !ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS)) + goto clear; + if (sta->sta.tdls) { + fastrx.da_offs = offsetof(struct ieee80211_hdr, addr1); + fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr2); + fastrx.expected_ds_bits = 0; + } else { + fastrx.sta_notify = sdata->u.mgd.probe_send_count > 0; + fastrx.da_offs = offsetof(struct ieee80211_hdr, addr1); + fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr3); + fastrx.expected_ds_bits = + cpu_to_le16(IEEE80211_FCTL_FROMDS); + } + break; + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_AP: + /* parallel-rx requires this, at least with calls to + * ieee80211_sta_ps_transition() + */ + if (!ieee80211_hw_check(&local->hw, AP_LINK_PS)) + goto clear; + fastrx.da_offs = offsetof(struct ieee80211_hdr, addr3); + fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr2); + fastrx.expected_ds_bits = cpu_to_le16(IEEE80211_FCTL_TODS); + + fastrx.internal_forward = + !(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) && + (sdata->vif.type != NL80211_IFTYPE_AP_VLAN || + !sdata->u.vlan.sta); + break; + default: + goto clear; + } + + if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + goto clear; + + rcu_read_lock(); + key = rcu_dereference(sta->ptk[sta->ptk_idx]); + if (key) { + switch (key->conf.cipher) { + case WLAN_CIPHER_SUITE_TKIP: + /* we don't want to deal with MMIC in fast-rx */ + goto clear_rcu; + case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + break; + default: + /* we also don't want to deal with WEP or cipher scheme + * since those require looking up the key idx in the + * frame, rather than assuming the PTK is used + * (we need to revisit this once we implement the real + * PTK index, which is now valid in the spec, but we + * haven't implemented that part yet) + */ + goto clear_rcu; + } + + fastrx.key = true; + fastrx.icv_len = key->conf.icv_len; + } + + assign = true; + clear_rcu: + rcu_read_unlock(); + clear: + __release(check_fast_rx); + + if (assign) + new = kmemdup(&fastrx, sizeof(fastrx), GFP_KERNEL); + + spin_lock_bh(&sta->lock); + old = rcu_dereference_protected(sta->fast_rx, true); + rcu_assign_pointer(sta->fast_rx, new); + spin_unlock_bh(&sta->lock); + + if (old) + kfree_rcu(old, rcu_head); +} + +void ieee80211_clear_fast_rx(struct sta_info *sta) +{ + struct ieee80211_fast_rx *old; + + spin_lock_bh(&sta->lock); + old = rcu_dereference_protected(sta->fast_rx, true); + RCU_INIT_POINTER(sta->fast_rx, NULL); + spin_unlock_bh(&sta->lock); + + if (old) + kfree_rcu(old, rcu_head); +} + +void __ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + lockdep_assert_held(&local->sta_mtx); + + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (sdata != sta->sdata && + (!sta->sdata->bss || sta->sdata->bss != sdata->bss)) + continue; + ieee80211_check_fast_rx(sta); + } +} + +void ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + + mutex_lock(&local->sta_mtx); + __ieee80211_check_fast_rx_iface(sdata); + mutex_unlock(&local->sta_mtx); +} + +static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, + struct ieee80211_fast_rx *fast_rx) +{ + struct sk_buff *skb = rx->skb; + struct ieee80211_hdr *hdr = (void *)skb->data; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + struct sta_info *sta = rx->sta; + int orig_len = skb->len; + int snap_offs = ieee80211_hdrlen(hdr->frame_control); + struct { + u8 snap[sizeof(rfc1042_header)]; + __be16 proto; + } *payload __aligned(2); + struct { + u8 da[ETH_ALEN]; + u8 sa[ETH_ALEN]; + } addrs __aligned(2); + struct ieee80211_sta_rx_stats *stats = &sta->rx_stats; + + if (fast_rx->uses_rss) + stats = this_cpu_ptr(sta->pcpu_rx_stats); + + /* for parallel-rx, we need to have DUP_VALIDATED, otherwise we write + * to a common data structure; drivers can implement that per queue + * but we don't have that information in mac80211 + */ + if (!(status->flag & RX_FLAG_DUP_VALIDATED)) + return false; + +#define FAST_RX_CRYPT_FLAGS (RX_FLAG_PN_VALIDATED | RX_FLAG_DECRYPTED) + + /* If using encryption, we also need to have: + * - PN_VALIDATED: similar, but the implementation is tricky + * - DECRYPTED: necessary for PN_VALIDATED + */ + if (fast_rx->key && + (status->flag & FAST_RX_CRYPT_FLAGS) != FAST_RX_CRYPT_FLAGS) + return false; + + /* we don't deal with A-MSDU deaggregation here */ + if (status->rx_flags & IEEE80211_RX_AMSDU) + return false; + + if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) + return false; + + if (unlikely(ieee80211_is_frag(hdr))) + return false; + + /* Since our interface address cannot be multicast, this + * implicitly also rejects multicast frames without the + * explicit check. + * + * We shouldn't get any *data* frames not addressed to us + * (AP mode will accept multicast *management* frames), but + * punting here will make it go through the full checks in + * ieee80211_accept_frame(). + */ + if (!ether_addr_equal(fast_rx->vif_addr, hdr->addr1)) + return false; + + if ((hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_FROMDS | + IEEE80211_FCTL_TODS)) != + fast_rx->expected_ds_bits) + goto drop; + + /* assign the key to drop unencrypted frames (later) + * and strip the IV/MIC if necessary + */ + if (fast_rx->key && !(status->flag & RX_FLAG_IV_STRIPPED)) { + /* GCMP header length is the same */ + snap_offs += IEEE80211_CCMP_HDR_LEN; + } + + if (!pskb_may_pull(skb, snap_offs + sizeof(*payload))) + goto drop; + payload = (void *)(skb->data + snap_offs); + + if (!ether_addr_equal(payload->snap, fast_rx->rfc1042_hdr)) + return false; + + /* Don't handle these here since they require special code. + * Accept AARP and IPX even though they should come with a + * bridge-tunnel header - but if we get them this way then + * there's little point in discarding them. + */ + if (unlikely(payload->proto == cpu_to_be16(ETH_P_TDLS) || + payload->proto == fast_rx->control_port_protocol)) + return false; + + /* after this point, don't punt to the slowpath! */ + + if (rx->key && !(status->flag & RX_FLAG_MIC_STRIPPED) && + pskb_trim(skb, skb->len - fast_rx->icv_len)) + goto drop; + + if (unlikely(fast_rx->sta_notify)) { + ieee80211_sta_rx_notify(rx->sdata, hdr); + fast_rx->sta_notify = false; + } + + /* statistics part of ieee80211_rx_h_sta_process() */ + stats->last_rx = jiffies; + stats->last_rate = sta_stats_encode_rate(status); + + stats->fragments++; + + if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) { + stats->last_signal = status->signal; + if (!fast_rx->uses_rss) + ewma_signal_add(&sta->rx_stats_avg.signal, + -status->signal); + } + + if (status->chains) { + int i; + + stats->chains = status->chains; + for (i = 0; i < ARRAY_SIZE(status->chain_signal); i++) { + int signal = status->chain_signal[i]; + + if (!(status->chains & BIT(i))) + continue; + + stats->chain_signal_last[i] = signal; + if (!fast_rx->uses_rss) + ewma_signal_add(&sta->rx_stats_avg.chain_signal[i], + -signal); + } + } + /* end of statistics */ + + if (rx->key && !ieee80211_has_protected(hdr->frame_control)) + goto drop; + + /* do the header conversion - first grab the addresses */ + ether_addr_copy(addrs.da, skb->data + fast_rx->da_offs); + ether_addr_copy(addrs.sa, skb->data + fast_rx->sa_offs); + /* remove the SNAP but leave the ethertype */ + skb_pull(skb, snap_offs + sizeof(rfc1042_header)); + /* push the addresses in front */ + memcpy(skb_push(skb, sizeof(addrs)), &addrs, sizeof(addrs)); + + skb->dev = fast_rx->dev; + + ieee80211_rx_stats(fast_rx->dev, skb->len); + + /* The seqno index has the same property as needed + * for the rx_msdu field, i.e. it is IEEE80211_NUM_TIDS + * for non-QoS-data frames. Here we know it's a data + * frame, so count MSDUs. + */ + u64_stats_update_begin(&stats->syncp); + stats->msdu[rx->seqno_idx]++; + stats->bytes += orig_len; + u64_stats_update_end(&stats->syncp); + + if (fast_rx->internal_forward) { + struct sta_info *dsta = sta_info_get(rx->sdata, skb->data); + + if (dsta) { + /* + * Send to wireless media and increase priority by 256 + * to keep the received priority instead of + * reclassifying the frame (see cfg80211_classify8021d). + */ + skb->priority += 256; + skb->protocol = htons(ETH_P_802_3); + skb_reset_network_header(skb); + skb_reset_mac_header(skb); + dev_queue_xmit(skb); + return true; + } + } + + /* deliver to local stack */ + skb->protocol = eth_type_trans(skb, fast_rx->dev); + memset(skb->cb, 0, sizeof(skb->cb)); + if (rx->napi) + napi_gro_receive(rx->napi, skb); + else + netif_receive_skb(skb); + + return true; + drop: + dev_kfree_skb(skb); + stats->dropped++; + return true; +} + /* * This function returns whether or not the SKB * was destined for RX processing or not, which, @@ -3527,6 +3867,21 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, rx->skb = skb; + /* See if we can do fast-rx; if we have to copy we already lost, + * so punt in that case. We should never have to deliver a data + * frame to multiple interfaces anyway. + * + * We skip the ieee80211_accept_frame() call and do the necessary + * checking inside ieee80211_invoke_fast_rx(). + */ + if (consume && rx->sta) { + struct ieee80211_fast_rx *fast_rx; + + fast_rx = rcu_dereference(rx->sta->fast_rx); + if (fast_rx && ieee80211_invoke_fast_rx(rx, fast_rx)) + return true; + } + if (!ieee80211_accept_frame(rx)) return false; @@ -3552,6 +3907,7 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, * be called with rcu_read_lock protection. */ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, + struct ieee80211_sta *pubsta, struct sk_buff *skb, struct napi_struct *napi) { @@ -3561,7 +3917,6 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, __le16 fc; struct ieee80211_rx_data rx; struct ieee80211_sub_if_data *prev; - struct sta_info *sta, *prev_sta; struct rhash_head *tmp; int err = 0; @@ -3597,7 +3952,14 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, ieee80211_is_beacon(hdr->frame_control))) ieee80211_scan_rx(local, skb); - if (ieee80211_is_data(fc)) { + if (pubsta) { + rx.sta = container_of(pubsta, struct sta_info, sta); + rx.sdata = rx.sta->sdata; + if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) + return; + goto out; + } else if (ieee80211_is_data(fc)) { + struct sta_info *sta, *prev_sta; const struct bucket_table *tbl; prev_sta = NULL; @@ -3671,8 +4033,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, * This is the receive path handler. It is called by a low level driver when an * 802.11 MPDU is received from the hardware. */ -void ieee80211_rx_napi(struct ieee80211_hw *hw, struct sk_buff *skb, - struct napi_struct *napi) +void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, + struct sk_buff *skb, struct napi_struct *napi) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_rate *rate = NULL; @@ -3771,7 +4133,8 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct sk_buff *skb, ieee80211_tpt_led_trig_rx(local, ((struct ieee80211_hdr *)skb->data)->frame_control, skb->len); - __ieee80211_rx_handle_packet(hw, skb, napi); + + __ieee80211_rx_handle_packet(hw, pubsta, skb, napi); rcu_read_unlock(); diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index ae980ce8daff..41aa728e5468 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -66,7 +66,9 @@ ieee80211_bss_info_update(struct ieee80211_local *local, struct cfg80211_bss *cbss; struct ieee80211_bss *bss; int clen, srlen; - struct cfg80211_inform_bss bss_meta = {}; + struct cfg80211_inform_bss bss_meta = { + .boottime_ns = rx_status->boottime_ns, + }; bool signal_valid; if (ieee80211_hw_check(&local->hw, SIGNAL_DBM)) @@ -303,6 +305,7 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr); ether_addr_copy(local->hw_scan_req->req.mac_addr_mask, req->mac_addr_mask); + ether_addr_copy(local->hw_scan_req->req.bssid, req->bssid); return true; } @@ -497,7 +500,7 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, for (i = 0; i < scan_req->n_ssids; i++) ieee80211_send_probe_req( - sdata, local->scan_addr, NULL, + sdata, local->scan_addr, scan_req->bssid, scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len, scan_req->ie, scan_req->ie_len, scan_req->rates[band], false, @@ -562,6 +565,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, req->n_channels * sizeof(req->channels[0]); local->hw_scan_req->req.ie = ies; local->hw_scan_req->req.flags = req->flags; + eth_broadcast_addr(local->hw_scan_req->req.bssid); local->hw_scan_band = 0; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index d20bab5c146c..5ccfdbd406bd 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2,7 +2,7 @@ * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2015 Intel Deutschland GmbH + * Copyright (C) 2015 - 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -67,6 +67,7 @@ static const struct rhashtable_params sta_rht_params = { .nelem_hint = 3, /* start small */ + .insecure_elasticity = true, /* Disable chain-length checks. */ .automatic_shrinking = true, .head_offset = offsetof(struct sta_info, hash_node), .key_offset = offsetof(struct sta_info, addr), @@ -254,15 +255,16 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) #ifdef CONFIG_MAC80211_MESH kfree(sta->mesh); #endif + free_percpu(sta->pcpu_rx_stats); kfree(sta); } /* Caller must hold local->sta_mtx */ -static void sta_info_hash_add(struct ieee80211_local *local, - struct sta_info *sta) +static int sta_info_hash_add(struct ieee80211_local *local, + struct sta_info *sta) { - rhashtable_insert_fast(&local->sta_hash, &sta->hash_node, - sta_rht_params); + return rhashtable_insert_fast(&local->sta_hash, &sta->hash_node, + sta_rht_params); } static void sta_deliver_ps_frames(struct work_struct *wk) @@ -311,6 +313,13 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, if (!sta) return NULL; + if (ieee80211_hw_check(hw, USES_RSS)) { + sta->pcpu_rx_stats = + alloc_percpu(struct ieee80211_sta_rx_stats); + if (!sta->pcpu_rx_stats) + goto free; + } + spin_lock_init(&sta->lock); spin_lock_init(&sta->ps_lock); INIT_WORK(&sta->drv_deliver_wk, sta_deliver_ps_frames); @@ -335,15 +344,17 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->sdata = sdata; sta->rx_stats.last_rx = jiffies; + u64_stats_init(&sta->rx_stats.syncp); + sta->sta_state = IEEE80211_STA_NONE; /* Mark TID as unreserved */ sta->reserved_tid = IEEE80211_TID_UNRESERVED; sta->last_connected = ktime_get_seconds(); - ewma_signal_init(&sta->rx_stats.avg_signal); - for (i = 0; i < ARRAY_SIZE(sta->rx_stats.chain_signal_avg); i++) - ewma_signal_init(&sta->rx_stats.chain_signal_avg[i]); + ewma_signal_init(&sta->rx_stats_avg.signal); + for (i = 0; i < ARRAY_SIZE(sta->rx_stats_avg.chain_signal); i++) + ewma_signal_init(&sta->rx_stats_avg.chain_signal[i]); if (local->ops->wake_tx_queue) { void *txq_data; @@ -406,6 +417,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, } } + sta->sta.max_rc_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_BA; + sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); return sta; @@ -524,7 +537,9 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) set_sta_flag(sta, WLAN_STA_BLOCK_BA); /* make the station visible */ - sta_info_hash_add(local, sta); + err = sta_info_hash_add(local, sta); + if (err) + goto out_drop_sta; list_add_tail_rcu(&sta->list, &local->sta_list); @@ -557,6 +572,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) out_remove: sta_info_hash_del(local, sta); list_del_rcu(&sta->list); + out_drop_sta: local->num_sta--; synchronize_net(); __cleanup_single_sta(sta); @@ -875,6 +891,13 @@ static int __must_check __sta_info_destroy_part1(struct sta_info *sta) set_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_DESTROY_STA); + /* + * Before removing the station from the driver there might be pending + * rx frames on RSS queues sent prior to the disassociation - wait for + * all such frames to be processed. + */ + drv_sync_rx_queues(local, sta); + ret = sta_info_hash_del(local, sta); if (WARN_ON(ret)) return ret; @@ -1087,10 +1110,12 @@ void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, mutex_lock(&local->sta_mtx); list_for_each_entry_safe(sta, tmp, &local->sta_list, list) { + unsigned long last_active = ieee80211_sta_last_active(sta); + if (sdata != sta->sdata) continue; - if (time_after(jiffies, sta->rx_stats.last_rx + exp_time)) { + if (time_is_before_jiffies(last_active + exp_time)) { sta_dbg(sta->sdata, "expiring inactive STA %pM\n", sta->sta.addr); @@ -1760,6 +1785,31 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(ieee80211_sta_set_buffered); +static void +ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + bool allow_p2p_go_ps = sdata->vif.p2p; + struct sta_info *sta; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (sdata != sta->sdata || + !test_sta_flag(sta, WLAN_STA_ASSOC)) + continue; + if (!sta->sta.support_p2p_ps) { + allow_p2p_go_ps = false; + break; + } + } + rcu_read_unlock(); + + if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) { + sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_P2P_PS); + } +} + int sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state) { @@ -1821,12 +1871,16 @@ int sta_info_move_state(struct sta_info *sta, } else if (sta->sta_state == IEEE80211_STA_ASSOC) { clear_bit(WLAN_STA_ASSOC, &sta->_flags); ieee80211_recalc_min_chandef(sta->sdata); + if (!sta->sta.support_p2p_ps) + ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); } break; case IEEE80211_STA_ASSOC: if (sta->sta_state == IEEE80211_STA_AUTH) { set_bit(WLAN_STA_ASSOC, &sta->_flags); ieee80211_recalc_min_chandef(sta->sdata); + if (!sta->sta.support_p2p_ps) + ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); } else if (sta->sta_state == IEEE80211_STA_AUTHORIZED) { if (sta->sdata->vif.type == NL80211_IFTYPE_AP || (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && @@ -1834,6 +1888,7 @@ int sta_info_move_state(struct sta_info *sta, atomic_dec(&sta->sdata->bss->num_mcast_sta); clear_bit(WLAN_STA_AUTHORIZED, &sta->_flags); ieee80211_clear_fast_xmit(sta); + ieee80211_clear_fast_rx(sta); } break; case IEEE80211_STA_AUTHORIZED: @@ -1844,6 +1899,7 @@ int sta_info_move_state(struct sta_info *sta, atomic_inc(&sta->sdata->bss->num_mcast_sta); set_bit(WLAN_STA_AUTHORIZED, &sta->_flags); ieee80211_check_fast_xmit(sta); + ieee80211_check_fast_rx(sta); } break; default: @@ -1890,43 +1946,117 @@ u8 sta_info_tx_streams(struct sta_info *sta) >> IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT) + 1; } -static void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) +static struct ieee80211_sta_rx_stats * +sta_get_last_rx_stats(struct sta_info *sta) { - rinfo->flags = 0; - - if (sta->rx_stats.last_rate_flag & RX_FLAG_HT) { - rinfo->flags |= RATE_INFO_FLAGS_MCS; - rinfo->mcs = sta->rx_stats.last_rate_idx; - } else if (sta->rx_stats.last_rate_flag & RX_FLAG_VHT) { - rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS; - rinfo->nss = sta->rx_stats.last_rate_vht_nss; - rinfo->mcs = sta->rx_stats.last_rate_idx; - } else { + struct ieee80211_sta_rx_stats *stats = &sta->rx_stats; + struct ieee80211_local *local = sta->local; + int cpu; + + if (!ieee80211_hw_check(&local->hw, USES_RSS)) + return stats; + + for_each_possible_cpu(cpu) { + struct ieee80211_sta_rx_stats *cpustats; + + cpustats = per_cpu_ptr(sta->pcpu_rx_stats, cpu); + + if (time_after(cpustats->last_rx, stats->last_rx)) + stats = cpustats; + } + + return stats; +} + +static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, + struct rate_info *rinfo) +{ + rinfo->bw = (rate & STA_STATS_RATE_BW_MASK) >> + STA_STATS_RATE_BW_SHIFT; + + if (rate & STA_STATS_RATE_VHT) { + rinfo->flags = RATE_INFO_FLAGS_VHT_MCS; + rinfo->mcs = rate & 0xf; + rinfo->nss = (rate & 0xf0) >> 4; + } else if (rate & STA_STATS_RATE_HT) { + rinfo->flags = RATE_INFO_FLAGS_MCS; + rinfo->mcs = rate & 0xff; + } else if (rate & STA_STATS_RATE_LEGACY) { struct ieee80211_supported_band *sband; - int shift = ieee80211_vif_get_shift(&sta->sdata->vif); u16 brate; - - sband = sta->local->hw.wiphy->bands[ - ieee80211_get_sdata_band(sta->sdata)]; - brate = sband->bitrates[sta->rx_stats.last_rate_idx].bitrate; + unsigned int shift; + + sband = local->hw.wiphy->bands[(rate >> 4) & 0xf]; + brate = sband->bitrates[rate & 0xf].bitrate; + if (rinfo->bw == RATE_INFO_BW_5) + shift = 2; + else if (rinfo->bw == RATE_INFO_BW_10) + shift = 1; + else + shift = 0; rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift); } - if (sta->rx_stats.last_rate_flag & RX_FLAG_SHORT_GI) + if (rate & STA_STATS_RATE_SGI) rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; +} + +static void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) +{ + u16 rate = ACCESS_ONCE(sta_get_last_rx_stats(sta)->last_rate); - if (sta->rx_stats.last_rate_flag & RX_FLAG_5MHZ) - rinfo->bw = RATE_INFO_BW_5; - else if (sta->rx_stats.last_rate_flag & RX_FLAG_10MHZ) - rinfo->bw = RATE_INFO_BW_10; - else if (sta->rx_stats.last_rate_flag & RX_FLAG_40MHZ) - rinfo->bw = RATE_INFO_BW_40; - else if (sta->rx_stats.last_rate_vht_flag & RX_VHT_FLAG_80MHZ) - rinfo->bw = RATE_INFO_BW_80; - else if (sta->rx_stats.last_rate_vht_flag & RX_VHT_FLAG_160MHZ) - rinfo->bw = RATE_INFO_BW_160; + if (rate == STA_STATS_RATE_INVALID) + rinfo->flags = 0; else - rinfo->bw = RATE_INFO_BW_20; + sta_stats_decode_rate(sta->local, rate, rinfo); +} + +static void sta_set_tidstats(struct sta_info *sta, + struct cfg80211_tid_stats *tidstats, + int tid) +{ + struct ieee80211_local *local = sta->local; + + if (!(tidstats->filled & BIT(NL80211_TID_STATS_RX_MSDU))) { + unsigned int start; + + do { + start = u64_stats_fetch_begin(&sta->rx_stats.syncp); + tidstats->rx_msdu = sta->rx_stats.msdu[tid]; + } while (u64_stats_fetch_retry(&sta->rx_stats.syncp, start)); + + tidstats->filled |= BIT(NL80211_TID_STATS_RX_MSDU); + } + + if (!(tidstats->filled & BIT(NL80211_TID_STATS_TX_MSDU))) { + tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU); + tidstats->tx_msdu = sta->tx_stats.msdu[tid]; + } + + if (!(tidstats->filled & BIT(NL80211_TID_STATS_TX_MSDU_RETRIES)) && + ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { + tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU_RETRIES); + tidstats->tx_msdu_retries = sta->status_stats.msdu_retries[tid]; + } + + if (!(tidstats->filled & BIT(NL80211_TID_STATS_TX_MSDU_FAILED)) && + ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { + tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU_FAILED); + tidstats->tx_msdu_failed = sta->status_stats.msdu_failed[tid]; + } +} + +static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats) +{ + unsigned int start; + u64 value; + + do { + start = u64_stats_fetch_begin(&rxstats->syncp); + value = rxstats->bytes; + } while (u64_stats_fetch_retry(&rxstats->syncp, start)); + + return value; } void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) @@ -1935,7 +2065,10 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) struct ieee80211_local *local = sdata->local; struct rate_control_ref *ref = NULL; u32 thr = 0; - int i, ac; + int i, ac, cpu; + struct ieee80211_sta_rx_stats *last_rxstats; + + last_rxstats = sta_get_last_rx_stats(sta); if (test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) ref = local->rate_ctrl; @@ -1964,7 +2097,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->connected_time = ktime_get_seconds() - sta->last_connected; sinfo->inactive_time = - jiffies_to_msecs(jiffies - sta->rx_stats.last_rx); + jiffies_to_msecs(jiffies - ieee80211_sta_last_active(sta)); if (!(sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES64) | BIT(NL80211_STA_INFO_TX_BYTES)))) { @@ -1983,12 +2116,30 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) if (!(sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES64) | BIT(NL80211_STA_INFO_RX_BYTES)))) { - sinfo->rx_bytes = sta->rx_stats.bytes; + sinfo->rx_bytes += sta_get_stats_bytes(&sta->rx_stats); + + if (sta->pcpu_rx_stats) { + for_each_possible_cpu(cpu) { + struct ieee80211_sta_rx_stats *cpurxs; + + cpurxs = per_cpu_ptr(sta->pcpu_rx_stats, cpu); + sinfo->rx_bytes += sta_get_stats_bytes(cpurxs); + } + } + sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64); } if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_PACKETS))) { sinfo->rx_packets = sta->rx_stats.packets; + if (sta->pcpu_rx_stats) { + for_each_possible_cpu(cpu) { + struct ieee80211_sta_rx_stats *cpurxs; + + cpurxs = per_cpu_ptr(sta->pcpu_rx_stats, cpu); + sinfo->rx_packets += cpurxs->packets; + } + } sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS); } @@ -2003,6 +2154,14 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) } sinfo->rx_dropped_misc = sta->rx_stats.dropped; + if (sta->pcpu_rx_stats) { + for_each_possible_cpu(cpu) { + struct ieee80211_sta_rx_stats *cpurxs; + + cpurxs = per_cpu_ptr(sta->pcpu_rx_stats, cpu); + sinfo->rx_packets += cpurxs->dropped; + } + } if (sdata->vif.type == NL80211_IFTYPE_STATION && !(sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)) { @@ -2014,29 +2173,36 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) if (ieee80211_hw_check(&sta->local->hw, SIGNAL_DBM) || ieee80211_hw_check(&sta->local->hw, SIGNAL_UNSPEC)) { if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL))) { - sinfo->signal = (s8)sta->rx_stats.last_signal; + sinfo->signal = (s8)last_rxstats->last_signal; sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL); } - if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))) { + if (!sta->pcpu_rx_stats && + !(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))) { sinfo->signal_avg = - -ewma_signal_read(&sta->rx_stats.avg_signal); + -ewma_signal_read(&sta->rx_stats_avg.signal); sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG); } } - if (sta->rx_stats.chains && + /* for the average - if pcpu_rx_stats isn't set - rxstats must point to + * the sta->rx_stats struct, so the check here is fine with and without + * pcpu statistics + */ + if (last_rxstats->chains && !(sinfo->filled & (BIT(NL80211_STA_INFO_CHAIN_SIGNAL) | BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) { - sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL) | - BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG); + sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL); + if (!sta->pcpu_rx_stats) + sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG); + + sinfo->chains = last_rxstats->chains; - sinfo->chains = sta->rx_stats.chains; for (i = 0; i < ARRAY_SIZE(sinfo->chain_signal); i++) { sinfo->chain_signal[i] = - sta->rx_stats.chain_signal_last[i]; + last_rxstats->chain_signal_last[i]; sinfo->chain_signal_avg[i] = - -ewma_signal_read(&sta->rx_stats.chain_signal_avg[i]); + -ewma_signal_read(&sta->rx_stats_avg.chain_signal[i]); } } @@ -2055,33 +2221,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { struct cfg80211_tid_stats *tidstats = &sinfo->pertid[i]; - if (!(tidstats->filled & BIT(NL80211_TID_STATS_RX_MSDU))) { - tidstats->filled |= BIT(NL80211_TID_STATS_RX_MSDU); - tidstats->rx_msdu = sta->rx_stats.msdu[i]; - } - - if (!(tidstats->filled & BIT(NL80211_TID_STATS_TX_MSDU))) { - tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU); - tidstats->tx_msdu = sta->tx_stats.msdu[i]; - } - - if (!(tidstats->filled & - BIT(NL80211_TID_STATS_TX_MSDU_RETRIES)) && - ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { - tidstats->filled |= - BIT(NL80211_TID_STATS_TX_MSDU_RETRIES); - tidstats->tx_msdu_retries = - sta->status_stats.msdu_retries[i]; - } - - if (!(tidstats->filled & - BIT(NL80211_TID_STATS_TX_MSDU_FAILED)) && - ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { - tidstats->filled |= - BIT(NL80211_TID_STATS_TX_MSDU_FAILED); - tidstats->tx_msdu_failed = - sta->status_stats.msdu_failed[i]; - } + sta_set_tidstats(sta, tidstats, i); } if (ieee80211_vif_is_mesh(&sdata->vif)) { @@ -2150,3 +2290,12 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->expected_throughput = thr; } } + +unsigned long ieee80211_sta_last_active(struct sta_info *sta) +{ + struct ieee80211_sta_rx_stats *stats = sta_get_last_rx_stats(sta); + + if (time_after(stats->last_rx, sta->status_stats.last_ack)) + return stats->last_rx; + return sta->status_stats.last_ack; +} diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 053f5c4fa495..c8b8ccc370eb 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -1,7 +1,7 @@ /* * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright(c) 2015 Intel Deutschland GmbH + * Copyright(c) 2015-2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -18,6 +18,7 @@ #include <linux/average.h> #include <linux/etherdevice.h> #include <linux/rhashtable.h> +#include <linux/u64_stats_sync.h> #include "key.h" /** @@ -69,6 +70,8 @@ * @WLAN_STA_MPSP_RECIPIENT: local STA is recipient of a MPSP. * @WLAN_STA_PS_DELIVER: station woke up, but we're still blocking TX * until pending frames are delivered + * + * @NUM_WLAN_STA_FLAGS: number of defined flags */ enum ieee80211_sta_info_flags { WLAN_STA_AUTH, @@ -97,6 +100,8 @@ enum ieee80211_sta_info_flags { WLAN_STA_MPSP_OWNER, WLAN_STA_MPSP_RECIPIENT, WLAN_STA_PS_DELIVER, + + NUM_WLAN_STA_FLAGS, }; #define ADDBA_RESP_INTERVAL HZ @@ -281,6 +286,40 @@ struct ieee80211_fast_tx { }; /** + * struct ieee80211_fast_rx - RX fastpath information + * @dev: netdevice for reporting the SKB + * @vif_type: (P2P-less) interface type of the original sdata (sdata->vif.type) + * @vif_addr: interface address + * @rfc1042_hdr: copy of the RFC 1042 SNAP header (to have in cache) + * @control_port_protocol: control port protocol copied from sdata + * @expected_ds_bits: from/to DS bits expected + * @icv_len: length of the MIC if present + * @key: bool indicating encryption is expected (key is set) + * @sta_notify: notify the MLME code (once) + * @internal_forward: forward froms internally on AP/VLAN type interfaces + * @uses_rss: copy of USES_RSS hw flag + * @da_offs: offset of the DA in the header (for header conversion) + * @sa_offs: offset of the SA in the header (for header conversion) + * @rcu_head: RCU head for freeing this structure + */ +struct ieee80211_fast_rx { + struct net_device *dev; + enum nl80211_iftype vif_type; + u8 vif_addr[ETH_ALEN] __aligned(2); + u8 rfc1042_hdr[6] __aligned(2); + __be16 control_port_protocol; + __le16 expected_ds_bits; + u8 icv_len; + u8 key:1, + sta_notify:1, + internal_forward:1, + uses_rss:1; + u8 da_offs, sa_offs; + + struct rcu_head rcu_head; +}; + +/** * struct mesh_sta - mesh STA information * @plink_lock: serialize access to plink fields * @llid: Local link ID @@ -330,6 +369,21 @@ struct mesh_sta { DECLARE_EWMA(signal, 1024, 8) +struct ieee80211_sta_rx_stats { + unsigned long packets; + unsigned long last_rx; + unsigned long num_duplicates; + unsigned long fragments; + unsigned long dropped; + int last_signal; + u8 chains; + s8 chain_signal_last[IEEE80211_MAX_CHAINS]; + u16 last_rate; + struct u64_stats_sync syncp; + u64 bytes; + u64 msdu[IEEE80211_NUM_TIDS + 1]; +}; + /** * struct sta_info - STA information * @@ -371,13 +425,12 @@ DECLARE_EWMA(signal, 1024, 8) * @ampdu_mlme: A-MPDU state machine state * @timer_to_tid: identity mapping to ID timers * @mesh: mesh STA information - * @debugfs: debug filesystem info + * @debugfs_dir: debug filesystem directory dentry * @dead: set to true when sta is unlinked * @removed: set to true when sta is being removed from sta_list * @uploaded: set to true when sta is uploaded to the driver * @sta: station information we share with the driver * @sta_state: duplicates information about station state (for debug) - * @beacon_loss_count: number of times beacon loss has triggered * @rcu_head: RCU head used for freeing this station struct * @cur_max_bandwidth: maximum bandwidth to use for TX to the station, * taken from HT/VHT capabilities or VHT operating mode notification @@ -386,10 +439,13 @@ DECLARE_EWMA(signal, 1024, 8) * @cipher_scheme: optional cipher scheme for this station * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED) * @fast_tx: TX fastpath information + * @fast_rx: RX fastpath information * @tdls_chandef: a TDLS peer can have a wider chandef that is compatible to * the BSS one. * @tx_stats: TX statistics * @rx_stats: RX statistics + * @pcpu_rx_stats: per-CPU RX statistics, assigned only if the driver needs + * this (by advertising the USES_RSS hw flag) * @status_stats: TX status statistics */ struct sta_info { @@ -409,6 +465,8 @@ struct sta_info { spinlock_t lock; struct ieee80211_fast_tx __rcu *fast_tx; + struct ieee80211_fast_rx __rcu *fast_rx; + struct ieee80211_sta_rx_stats __percpu *pcpu_rx_stats; #ifdef CONFIG_MAC80211_MESH struct mesh_sta *mesh; @@ -438,24 +496,11 @@ struct sta_info { long last_connected; /* Updated from RX path only, no locking requirements */ + struct ieee80211_sta_rx_stats rx_stats; struct { - unsigned long packets; - u64 bytes; - unsigned long last_rx; - unsigned long num_duplicates; - unsigned long fragments; - unsigned long dropped; - int last_signal; - struct ewma_signal avg_signal; - u8 chains; - s8 chain_signal_last[IEEE80211_MAX_CHAINS]; - struct ewma_signal chain_signal_avg[IEEE80211_MAX_CHAINS]; - int last_rate_idx; - u32 last_rate_flag; - u32 last_rate_vht_flag; - u8 last_rate_vht_nss; - u64 msdu[IEEE80211_NUM_TIDS + 1]; - } rx_stats; + struct ewma_signal signal; + struct ewma_signal chain_signal[IEEE80211_MAX_CHAINS]; + } rx_stats_avg; /* Plus 1 for non-QoS frames */ __le16 last_seq_ctrl[IEEE80211_NUM_TIDS + 1]; @@ -468,6 +513,7 @@ struct sta_info { unsigned long last_tdls_pkt_time; u64 msdu_retries[IEEE80211_NUM_TIDS + 1]; u64 msdu_failed[IEEE80211_NUM_TIDS + 1]; + unsigned long last_ack; } status_stats; /* Updated from TX path only, no locking requirements */ @@ -486,10 +532,7 @@ struct sta_info { u8 timer_to_tid[IEEE80211_NUM_TIDS]; #ifdef CONFIG_MAC80211_DEBUGFS - struct sta_info_debugfsdentries { - struct dentry *dir; - bool add_has_run; - } debugfs; + struct dentry *debugfs_dir; #endif enum ieee80211_sta_rx_bandwidth cur_max_bandwidth; @@ -677,4 +720,44 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta); void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta); void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta); +unsigned long ieee80211_sta_last_active(struct sta_info *sta); + +#define STA_STATS_RATE_INVALID 0 +#define STA_STATS_RATE_VHT 0x8000 +#define STA_STATS_RATE_HT 0x4000 +#define STA_STATS_RATE_LEGACY 0x2000 +#define STA_STATS_RATE_SGI 0x1000 +#define STA_STATS_RATE_BW_SHIFT 9 +#define STA_STATS_RATE_BW_MASK (0x7 << STA_STATS_RATE_BW_SHIFT) + +static inline u16 sta_stats_encode_rate(struct ieee80211_rx_status *s) +{ + u16 r = s->rate_idx; + + if (s->vht_flag & RX_VHT_FLAG_80MHZ) + r |= RATE_INFO_BW_80 << STA_STATS_RATE_BW_SHIFT; + else if (s->vht_flag & RX_VHT_FLAG_160MHZ) + r |= RATE_INFO_BW_160 << STA_STATS_RATE_BW_SHIFT; + else if (s->flag & RX_FLAG_40MHZ) + r |= RATE_INFO_BW_40 << STA_STATS_RATE_BW_SHIFT; + else if (s->flag & RX_FLAG_10MHZ) + r |= RATE_INFO_BW_10 << STA_STATS_RATE_BW_SHIFT; + else if (s->flag & RX_FLAG_5MHZ) + r |= RATE_INFO_BW_5 << STA_STATS_RATE_BW_SHIFT; + else + r |= RATE_INFO_BW_20 << STA_STATS_RATE_BW_SHIFT; + + if (s->flag & RX_FLAG_SHORT_GI) + r |= STA_STATS_RATE_SGI; + + if (s->flag & RX_FLAG_VHT) + r |= STA_STATS_RATE_VHT | (s->vht_nss << 4); + else if (s->flag & RX_FLAG_HT) + r |= STA_STATS_RATE_HT; + else + r |= STA_STATS_RATE_LEGACY | (s->band << 4); + + return r; +} + #endif /* STA_INFO_H */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 8b1b2ea03eb5..c6d5c724e032 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -188,7 +188,7 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) struct ieee80211_sub_if_data *sdata = sta->sdata; if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) - sta->rx_stats.last_rx = jiffies; + sta->status_stats.last_ack = jiffies; if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *) skb->data; @@ -647,7 +647,7 @@ void ieee80211_tx_status_noskb(struct ieee80211_hw *hw, sta->status_stats.retry_count += retry_count; if (acked) { - sta->rx_stats.last_rx = jiffies; + sta->status_stats.last_ack = jiffies; if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index c9eeb3f12808..a29ea813b7d5 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -4,7 +4,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2014, Intel Corporation * Copyright 2014 Intel Mobile Communications GmbH - * Copyright 2015 Intel Deutschland GmbH + * Copyright 2015 - 2016 Intel Deutschland GmbH * * This file is GPLv2 as found in COPYING. */ @@ -15,6 +15,7 @@ #include <linux/rtnetlink.h> #include "ieee80211_i.h" #include "driver-ops.h" +#include "rate.h" /* give usermode some time for retries in setting up the TDLS session */ #define TDLS_PEER_SETUP_TIMEOUT (15 * HZ) @@ -302,7 +303,7 @@ ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata, /* IEEE802.11ac-2013 Table E-4 */ u16 centers_80mhz[] = { 5210, 5290, 5530, 5610, 5690, 5775 }; struct cfg80211_chan_def uc = sta->tdls_chandef; - enum nl80211_chan_width max_width = ieee80211_get_sta_bw(&sta->sta); + enum nl80211_chan_width max_width = ieee80211_sta_cap_chan_bw(sta); int i; /* only support upgrading non-narrow channels up to 80Mhz */ @@ -313,7 +314,7 @@ ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata, if (max_width > NL80211_CHAN_WIDTH_80) max_width = NL80211_CHAN_WIDTH_80; - if (uc.width == max_width) + if (uc.width >= max_width) return; /* * Channel usage constrains in the IEEE802.11ac-2013 specification only @@ -324,6 +325,7 @@ ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata, for (i = 0; i < ARRAY_SIZE(centers_80mhz); i++) if (abs(uc.chan->center_freq - centers_80mhz[i]) <= 30) { uc.center_freq1 = centers_80mhz[i]; + uc.center_freq2 = 0; uc.width = NL80211_CHAN_WIDTH_80; break; } @@ -332,7 +334,7 @@ ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata, return; /* proceed to downgrade the chandef until usable or the same */ - while (uc.width > max_width && + while (uc.width > max_width || !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc, sdata->wdev.iftype)) ieee80211_chandef_downgrade(&uc); @@ -1242,18 +1244,44 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, return ret; } -static void iee80211_tdls_recalc_chanctx(struct ieee80211_sub_if_data *sdata) +static void iee80211_tdls_recalc_chanctx(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta) { struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *ctx; + enum nl80211_chan_width width; + struct ieee80211_supported_band *sband; mutex_lock(&local->chanctx_mtx); conf = rcu_dereference_protected(sdata->vif.chanctx_conf, lockdep_is_held(&local->chanctx_mtx)); if (conf) { + width = conf->def.width; + sband = local->hw.wiphy->bands[conf->def.chan->band]; ctx = container_of(conf, struct ieee80211_chanctx, conf); ieee80211_recalc_chanctx_chantype(local, ctx); + + /* if width changed and a peer is given, update its BW */ + if (width != conf->def.width && sta && + test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) { + enum ieee80211_sta_rx_bandwidth bw; + + bw = ieee80211_chan_width_to_rx_bw(conf->def.width); + bw = min(bw, ieee80211_sta_cap_rx_bw(sta)); + if (bw != sta->sta.bandwidth) { + sta->sta.bandwidth = bw; + rate_control_rate_update(local, sband, sta, + IEEE80211_RC_BW_CHANGED); + /* + * if a TDLS peer BW was updated, we need to + * recalc the chandef width again, to get the + * correct chanctx min_def + */ + ieee80211_recalc_chanctx_chantype(local, ctx); + } + } + } mutex_unlock(&local->chanctx_mtx); } @@ -1350,8 +1378,6 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, break; } - iee80211_tdls_recalc_chanctx(sdata); - mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, peer); if (!sta) { @@ -1360,6 +1386,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, break; } + iee80211_tdls_recalc_chanctx(sdata, sta); iee80211_tdls_recalc_ht_protection(sdata, sta); set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); @@ -1390,7 +1417,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, iee80211_tdls_recalc_ht_protection(sdata, NULL); mutex_unlock(&local->sta_mtx); - iee80211_tdls_recalc_chanctx(sdata); + iee80211_tdls_recalc_chanctx(sdata, NULL); break; default: ret = -ENOTSUPP; diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 2b0a17ee907a..8c3b7ae103bc 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -1,3 +1,8 @@ +/* +* Portions of this file +* Copyright(c) 2016 Intel Deutschland GmbH +*/ + #if !defined(__MAC80211_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) #define __MAC80211_DRIVER_TRACE @@ -899,6 +904,13 @@ DEFINE_EVENT(sta_event, drv_sta_pre_rcu_remove, TP_ARGS(local, sdata, sta) ); +DEFINE_EVENT(sta_event, drv_sync_rx_queues, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta), + TP_ARGS(local, sdata, sta) +); + DEFINE_EVENT(sta_event, drv_sta_rate_tbl_update, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 62ad5321257d..e04d850726c5 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1116,11 +1116,15 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, reset_agg_timer = true; } else { queued = true; + if (info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER) { + clear_sta_flag(tx->sta, WLAN_STA_SP); + ps_dbg(tx->sta->sdata, + "STA %pM aid %d: SP frame queued, close the SP w/o telling the peer\n", + tx->sta->sta.addr, tx->sta->sta.aid); + } info->control.vif = &tx->sdata->vif; info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; - info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS | - IEEE80211_TX_CTL_NO_PS_BUFFER | - IEEE80211_TX_STATUS_EOSP; + info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; __skb_queue_tail(&tid_tx->pending, skb); if (skb_queue_len(&tid_tx->pending) > STA_MAX_TX_BUFFER) purge_skb = __skb_dequeue(&tid_tx->pending); @@ -1247,7 +1251,8 @@ static void ieee80211_drv_tx(struct ieee80211_local *local, struct txq_info *txqi; u8 ac; - if (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE) + if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) || + (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) goto tx_normal; if (!ieee80211_is_data(hdr->frame_control)) @@ -1324,6 +1329,10 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, out: spin_unlock_bh(&txqi->queue.lock); + if (skb && skb_has_frag_list(skb) && + !ieee80211_hw_check(&local->hw, TX_FRAG_LIST)) + skb_linearize(skb); + return skb; } EXPORT_SYMBOL(ieee80211_tx_dequeue); @@ -1691,7 +1700,9 @@ static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, bool rate_found = false; u8 rate_retries = 0; u16 rate_flags = 0; - u8 mcs_known, mcs_flags; + u8 mcs_known, mcs_flags, mcs_bw; + u16 vht_known; + u8 vht_mcs = 0, vht_nss = 0; int i; info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | @@ -1767,11 +1778,38 @@ static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, mcs_flags & IEEE80211_RADIOTAP_MCS_SGI) rate_flags |= IEEE80211_TX_RC_SHORT_GI; + mcs_bw = mcs_flags & IEEE80211_RADIOTAP_MCS_BW_MASK; if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_BW && - mcs_flags & IEEE80211_RADIOTAP_MCS_BW_40) + mcs_bw == IEEE80211_RADIOTAP_MCS_BW_40) rate_flags |= IEEE80211_TX_RC_40_MHZ_WIDTH; break; + case IEEE80211_RADIOTAP_VHT: + vht_known = get_unaligned_le16(iterator.this_arg); + rate_found = true; + + rate_flags = IEEE80211_TX_RC_VHT_MCS; + if ((vht_known & IEEE80211_RADIOTAP_VHT_KNOWN_GI) && + (iterator.this_arg[2] & + IEEE80211_RADIOTAP_VHT_FLAG_SGI)) + rate_flags |= IEEE80211_TX_RC_SHORT_GI; + if (vht_known & + IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH) { + if (iterator.this_arg[3] == 1) + rate_flags |= + IEEE80211_TX_RC_40_MHZ_WIDTH; + else if (iterator.this_arg[3] == 4) + rate_flags |= + IEEE80211_TX_RC_80_MHZ_WIDTH; + else if (iterator.this_arg[3] == 11) + rate_flags |= + IEEE80211_TX_RC_160_MHZ_WIDTH; + } + + vht_mcs = iterator.this_arg[4] >> 4; + vht_nss = iterator.this_arg[4] & 0xF; + break; + /* * Please update the file * Documentation/networking/mac80211-injection.txt @@ -1797,6 +1835,9 @@ static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, if (rate_flags & IEEE80211_TX_RC_MCS) { info->control.rates[0].idx = rate; + } else if (rate_flags & IEEE80211_TX_RC_VHT_MCS) { + ieee80211_rate_set_vht(info->control.rates, vht_mcs, + vht_nss); } else { for (i = 0; i < sband->n_bitrates; i++) { if (rate * 5 != sband->bitrates[i].bitrate) @@ -1807,6 +1848,9 @@ static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, } } + if (info->control.rates[0].idx < 0) + info->control.flags &= ~IEEE80211_TX_CTRL_RATE_INJECT; + info->control.rates[0].flags = rate_flags; info->control.rates[0].count = min_t(u8, rate_retries + 1, local->hw.max_rate_tries); @@ -2181,7 +2225,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, } if (mppath && mpath) - mesh_path_del(mpath->sdata, mpath->dst); + mesh_path_del(sdata, mpath->dst); } /* @@ -2767,6 +2811,154 @@ void ieee80211_clear_fast_xmit(struct sta_info *sta) kfree_rcu(fast_tx, rcu_head); } +static bool ieee80211_amsdu_realloc_pad(struct ieee80211_local *local, + struct sk_buff *skb, int headroom, + int *subframe_len) +{ + int amsdu_len = *subframe_len + sizeof(struct ethhdr); + int padding = (4 - amsdu_len) & 3; + + if (skb_headroom(skb) < headroom || skb_tailroom(skb) < padding) { + I802_DEBUG_INC(local->tx_expand_skb_head); + + if (pskb_expand_head(skb, headroom, padding, GFP_ATOMIC)) { + wiphy_debug(local->hw.wiphy, + "failed to reallocate TX buffer\n"); + return false; + } + } + + if (padding) { + *subframe_len += padding; + memset(skb_put(skb, padding), 0, padding); + } + + return true; +} + +static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata, + struct ieee80211_fast_tx *fast_tx, + struct sk_buff *skb) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr; + struct ethhdr amsdu_hdr; + int hdr_len = fast_tx->hdr_len - sizeof(rfc1042_header); + int subframe_len = skb->len - hdr_len; + void *data; + u8 *qc; + + if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) + return false; + + if (info->control.flags & IEEE80211_TX_CTRL_AMSDU) + return true; + + if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(amsdu_hdr), + &subframe_len)) + return false; + + amsdu_hdr.h_proto = cpu_to_be16(subframe_len); + memcpy(amsdu_hdr.h_source, skb->data + fast_tx->sa_offs, ETH_ALEN); + memcpy(amsdu_hdr.h_dest, skb->data + fast_tx->da_offs, ETH_ALEN); + + data = skb_push(skb, sizeof(amsdu_hdr)); + memmove(data, data + sizeof(amsdu_hdr), hdr_len); + memcpy(data + hdr_len, &amsdu_hdr, sizeof(amsdu_hdr)); + + hdr = data; + qc = ieee80211_get_qos_ctl(hdr); + *qc |= IEEE80211_QOS_CTL_A_MSDU_PRESENT; + + info->control.flags |= IEEE80211_TX_CTRL_AMSDU; + + return true; +} + +static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct ieee80211_fast_tx *fast_tx, + struct sk_buff *skb) +{ + struct ieee80211_local *local = sdata->local; + u8 tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; + struct ieee80211_txq *txq = sta->sta.txq[tid]; + struct txq_info *txqi; + struct sk_buff **frag_tail, *head; + int subframe_len = skb->len - ETH_ALEN; + u8 max_subframes = sta->sta.max_amsdu_subframes; + int max_frags = local->hw.max_tx_fragments; + int max_amsdu_len = sta->sta.max_amsdu_len; + __be16 len; + void *data; + bool ret = false; + int n = 1, nfrags; + + if (!ieee80211_hw_check(&local->hw, TX_AMSDU)) + return false; + + if (!txq) + return false; + + txqi = to_txq_info(txq); + if (test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags)) + return false; + + if (sta->sta.max_rc_amsdu_len) + max_amsdu_len = min_t(int, max_amsdu_len, + sta->sta.max_rc_amsdu_len); + + spin_lock_bh(&txqi->queue.lock); + + head = skb_peek_tail(&txqi->queue); + if (!head) + goto out; + + if (skb->len + head->len > max_amsdu_len) + goto out; + + if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) + goto out; + + nfrags = 1 + skb_shinfo(skb)->nr_frags; + nfrags += 1 + skb_shinfo(head)->nr_frags; + frag_tail = &skb_shinfo(head)->frag_list; + while (*frag_tail) { + nfrags += 1 + skb_shinfo(*frag_tail)->nr_frags; + frag_tail = &(*frag_tail)->next; + n++; + } + + if (max_subframes && n > max_subframes) + goto out; + + if (max_frags && nfrags > max_frags) + goto out; + + if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) + 2, + &subframe_len)) + goto out; + + ret = true; + data = skb_push(skb, ETH_ALEN + 2); + memmove(data, data + ETH_ALEN + 2, 2 * ETH_ALEN); + + data += 2 * ETH_ALEN; + len = cpu_to_be16(subframe_len); + memcpy(data, &len, 2); + memcpy(data + 2, rfc1042_header, sizeof(rfc1042_header)); + + head->len += skb->len; + head->data_len += skb->len; + *frag_tail = skb; + +out: + spin_unlock_bh(&txqi->queue.lock); + + return ret; +} + static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, struct net_device *dev, struct sta_info *sta, struct ieee80211_fast_tx *fast_tx, @@ -2821,6 +3013,10 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, ieee80211_tx_stats(dev, skb->len + extra_head); + if ((hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) && + ieee80211_amsdu_aggregate(sdata, sta, fast_tx, skb)) + return true; + /* will not be crypto-handled beyond what we do here, so use false * as the may-encrypt argument for the resize to not account for * more room than we already have in 'extra_head' diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 7390de4946a9..0319d6d4f863 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2724,8 +2724,9 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, rate = cfg80211_calculate_bitrate(&ri); if (WARN_ONCE(!rate, - "Invalid bitrate: flags=0x%x, idx=%d, vht_nss=%d\n", - status->flag, status->rate_idx, status->vht_nss)) + "Invalid bitrate: flags=0x%llx, idx=%d, vht_nss=%d\n", + (unsigned long long)status->flag, status->rate_idx, + status->vht_nss)) return 0; /* rewind from end of MPDU */ diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 89e04d55aa18..e590e2ef9eaf 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -319,7 +319,30 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta) return IEEE80211_STA_RX_BW_80; } -static enum ieee80211_sta_rx_bandwidth +enum nl80211_chan_width ieee80211_sta_cap_chan_bw(struct sta_info *sta) +{ + struct ieee80211_sta_vht_cap *vht_cap = &sta->sta.vht_cap; + u32 cap_width; + + if (!vht_cap->vht_supported) { + if (!sta->sta.ht_cap.ht_supported) + return NL80211_CHAN_WIDTH_20_NOHT; + + return sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? + NL80211_CHAN_WIDTH_40 : NL80211_CHAN_WIDTH_20; + } + + cap_width = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; + + if (cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ) + return NL80211_CHAN_WIDTH_160; + else if (cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + return NL80211_CHAN_WIDTH_80P80; + + return NL80211_CHAN_WIDTH_80; +} + +enum ieee80211_sta_rx_bandwidth ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width) { switch (width) { @@ -347,10 +370,7 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) bw = ieee80211_sta_cap_rx_bw(sta); bw = min(bw, sta->cur_max_bandwidth); - - /* do not cap the BW of TDLS WIDER_BW peers by the bss */ - if (!test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) - bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width)); + bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width)); return bw; } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 18848258adde..7e4f2652bca7 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -504,18 +504,20 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, !ieee80211_is_robust_mgmt_frame(skb)) return RX_CONTINUE; - data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len; - if (!rx->sta || data_len < 0) - return RX_DROP_UNUSABLE; - if (status->flag & RX_FLAG_DECRYPTED) { if (!pskb_may_pull(rx->skb, hdrlen + IEEE80211_CCMP_HDR_LEN)) return RX_DROP_UNUSABLE; + if (status->flag & RX_FLAG_MIC_STRIPPED) + mic_len = 0; } else { if (skb_linearize(rx->skb)) return RX_DROP_UNUSABLE; } + data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len; + if (!rx->sta || data_len < 0) + return RX_DROP_UNUSABLE; + if (!(status->flag & RX_FLAG_PN_VALIDATED)) { ccmp_hdr2pn(pn, skb->data + hdrlen); @@ -720,8 +722,7 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); u8 pn[IEEE80211_GCMP_PN_LEN]; - int data_len; - int queue; + int data_len, queue, mic_len = IEEE80211_GCMP_MIC_LEN; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -729,19 +730,20 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) !ieee80211_is_robust_mgmt_frame(skb)) return RX_CONTINUE; - data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN - - IEEE80211_GCMP_MIC_LEN; - if (!rx->sta || data_len < 0) - return RX_DROP_UNUSABLE; - if (status->flag & RX_FLAG_DECRYPTED) { if (!pskb_may_pull(rx->skb, hdrlen + IEEE80211_GCMP_HDR_LEN)) return RX_DROP_UNUSABLE; + if (status->flag & RX_FLAG_MIC_STRIPPED) + mic_len = 0; } else { if (skb_linearize(rx->skb)) return RX_DROP_UNUSABLE; } + data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN - mic_len; + if (!rx->sta || data_len < 0) + return RX_DROP_UNUSABLE; + if (!(status->flag & RX_FLAG_PN_VALIDATED)) { gcmp_hdr2pn(pn, skb->data + hdrlen); @@ -772,7 +774,7 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) } /* Remove GCMP header and MIC */ - if (pskb_trim(skb, skb->len - IEEE80211_GCMP_MIC_LEN)) + if (pskb_trim(skb, skb->len - mic_len)) return RX_DROP_UNUSABLE; memmove(skb->data + IEEE80211_GCMP_HDR_LEN, skb->data, hdrlen); skb_pull(skb, IEEE80211_GCMP_HDR_LEN); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index b18c5ed42d95..0b80a7140cc4 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -543,6 +543,9 @@ static struct net_device *find_outdev(struct net *net, if (!dev) return ERR_PTR(-ENODEV); + if (IS_ERR(dev)) + return dev; + /* The caller is holding rtnl anyways, so release the dev reference */ dev_put(dev); diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index b0bc475f641e..2e8e7e5fb4a6 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -95,7 +95,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) if (!nested) goto nla_put_failure; if (mtype_do_head(skb, map) || - nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 7e6568cad494..a748b0c2c981 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -497,6 +497,26 @@ __ip_set_put(struct ip_set *set) write_unlock_bh(&ip_set_ref_lock); } +/* set->ref can be swapped out by ip_set_swap, netlink events (like dump) need + * a separate reference counter + */ +static inline void +__ip_set_get_netlink(struct ip_set *set) +{ + write_lock_bh(&ip_set_ref_lock); + set->ref_netlink++; + write_unlock_bh(&ip_set_ref_lock); +} + +static inline void +__ip_set_put_netlink(struct ip_set *set) +{ + write_lock_bh(&ip_set_ref_lock); + BUG_ON(set->ref_netlink == 0); + set->ref_netlink--; + write_unlock_bh(&ip_set_ref_lock); +} + /* Add, del and test set entries from kernel. * * The set behind the index must exist and must be referenced @@ -1002,7 +1022,7 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); - if (s && s->ref) { + if (s && (s->ref || s->ref_netlink)) { ret = -IPSET_ERR_BUSY; goto out; } @@ -1024,7 +1044,7 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, if (!s) { ret = -ENOENT; goto out; - } else if (s->ref) { + } else if (s->ref || s->ref_netlink) { ret = -IPSET_ERR_BUSY; goto out; } @@ -1171,6 +1191,9 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, from->family == to->family)) return -IPSET_ERR_TYPE_MISMATCH; + if (from->ref_netlink || to->ref_netlink) + return -EBUSY; + strncpy(from_name, from->name, IPSET_MAXNAMELEN); strncpy(from->name, to->name, IPSET_MAXNAMELEN); strncpy(to->name, from_name, IPSET_MAXNAMELEN); @@ -1206,7 +1229,7 @@ ip_set_dump_done(struct netlink_callback *cb) if (set->variant->uref) set->variant->uref(set, cb, false); pr_debug("release set %s\n", set->name); - __ip_set_put_byindex(inst, index); + __ip_set_put_netlink(set); } return 0; } @@ -1328,7 +1351,7 @@ dump_last: if (!cb->args[IPSET_CB_ARG0]) { /* Start listing: make sure set won't be destroyed */ pr_debug("reference set\n"); - set->ref++; + set->ref_netlink++; } write_unlock_bh(&ip_set_ref_lock); nlh = start_msg(skb, NETLINK_CB(cb->skb).portid, @@ -1396,7 +1419,7 @@ release_refcount: if (set->variant->uref) set->variant->uref(set, cb, false); pr_debug("release set %s\n", set->name); - __ip_set_put_byindex(inst, index); + __ip_set_put_netlink(set); cb->args[IPSET_CB_ARG0] = 0; } out: diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index e5336ab36d67..d32fd6b036bf 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -1082,7 +1082,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask)) goto nla_put_failure; #endif - if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 24c6c1962aea..a2a89e4e0a14 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -458,7 +458,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) if (!nested) goto nla_put_failure; if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) || - nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + n * set->dsize))) goto nla_put_failure; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5bebe78b9bbd..aa93877ab6e2 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -640,7 +640,12 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, /* nfnetlink_unicast will either free the nskb or add it to a socket */ err = nfnetlink_unicast(nskb, net, queue->peer_portid, MSG_DONTWAIT); if (err < 0) { - queue->queue_user_dropped++; + if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { + failopen = 1; + err = 0; + } else { + queue->queue_user_dropped++; + } goto err_out_unlock; } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 3f9d45d3d9b7..6fa016564f90 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -192,7 +192,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); int err; - err = rhashtable_walk_init(&priv->ht, &hti); + err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); iter->err = err; if (err) return; @@ -248,7 +248,7 @@ static void nft_hash_gc(struct work_struct *work) priv = container_of(work, struct nft_hash, gc_work.work); set = nft_set_container_of(priv); - err = rhashtable_walk_init(&priv->ht, &hti); + err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); if (err) goto schedule; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 49d14ecad444..b10ade272b50 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -120,9 +120,9 @@ xt_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff, { switch (protocol) { case IPPROTO_TCP: - return __inet_lookup(net, &tcp_hashinfo, skb, doff, - saddr, sport, daddr, dport, - in->ifindex); + return inet_lookup(net, &tcp_hashinfo, skb, doff, + saddr, sport, daddr, dport, + in->ifindex); case IPPROTO_UDP: return udp4_lib_lookup(net, saddr, sport, daddr, dport, in->ifindex); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 215fc08c02ab..0f16bf635480 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2343,7 +2343,8 @@ static int netlink_walk_start(struct nl_seq_iter *iter) { int err; - err = rhashtable_walk_init(&nl_table[iter->link].hash, &iter->hti); + err = rhashtable_walk_init(&nl_table[iter->link].hash, &iter->hti, + GFP_KERNEL); if (err) { iter->link = MAX_LINKS; return err; diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 234a73344c6e..ce947292ae77 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -7,7 +7,9 @@ config OPENVSWITCH depends on INET depends on !NF_CONNTRACK || \ (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ - (!NF_NAT || NF_NAT))) + (!NF_NAT || NF_NAT) && \ + (!NF_NAT_IPV4 || NF_NAT_IPV4) && \ + (!NF_NAT_IPV6 || NF_NAT_IPV6))) select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index dc5eb29fe7d6..1b9d286756be 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -535,14 +535,15 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, switch (ctinfo) { case IP_CT_RELATED: case IP_CT_RELATED_REPLY: - if (skb->protocol == htons(ETH_P_IP) && + if (IS_ENABLED(CONFIG_NF_NAT_IPV4) && + skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, hooknum)) err = NF_DROP; goto push; -#if IS_ENABLED(CONFIG_NF_NAT_IPV6) - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) && + skb->protocol == htons(ETH_P_IPV6)) { __be16 frag_off; u8 nexthdr = ipv6_hdr(skb)->nexthdr; int hdrlen = ipv6_skip_exthdr(skb, @@ -557,7 +558,6 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, err = NF_DROP; goto push; } -#endif } /* Non-ICMP, fall thru to initialize if needed. */ case IP_CT_NEW: @@ -664,11 +664,12 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, /* Determine NAT type. * Check if the NAT type can be deduced from the tracked connection. - * Make sure expected traffic is NATted only when committing. + * Make sure new expected connections (IP_CT_RELATED) are NATted only + * when committing. */ if (info->nat & OVS_CT_NAT && ctinfo != IP_CT_NEW && ct->status & IPS_NAT_MASK && - (!(ct->status & IPS_EXPECTED_BIT) || info->commit)) { + (ctinfo != IP_CT_RELATED || info->commit)) { /* NAT an established or related connection like before. */ if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) /* This is the REPLY direction for a connection @@ -968,7 +969,8 @@ static int parse_nat(const struct nlattr *attr, break; case OVS_NAT_ATTR_IP_MIN: - nla_memcpy(&info->range.min_addr, a, nla_len(a)); + nla_memcpy(&info->range.min_addr, a, + sizeof(info->range.min_addr)); info->range.flags |= NF_NAT_RANGE_MAP_IPS; break; @@ -1238,7 +1240,8 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, } if (info->range.flags & NF_NAT_RANGE_MAP_IPS) { - if (info->family == NFPROTO_IPV4) { + if (IS_ENABLED(CONFIG_NF_NAT_IPV4) && + info->family == NFPROTO_IPV4) { if (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MIN, info->range.min_addr.ip) || (info->range.max_addr.ip @@ -1246,8 +1249,8 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MAX, info->range.max_addr.ip)))) return false; -#if IS_ENABLED(CONFIG_NF_NAT_IPV6) - } else if (info->family == NFPROTO_IPV6) { + } else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) && + info->family == NFPROTO_IPV6) { if (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MIN, &info->range.min_addr.in6) || (memcmp(&info->range.max_addr.in6, @@ -1256,7 +1259,6 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MAX, &info->range.max_addr.in6)))) return false; -#endif } else { return false; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 1ecfa710ca98..81a4c0574d73 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1837,6 +1837,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; + struct sockcm_cookie sockc; __be16 proto = 0; int err; int extra_len = 0; @@ -1925,12 +1926,21 @@ retry: goto out_unlock; } + sockc.tsflags = 0; + if (msg->msg_controllen) { + err = sock_cmsg_send(sk, msg, &sockc); + if (unlikely(err)) { + err = -EINVAL; + goto out_unlock; + } + } + skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); + sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -2486,7 +2496,8 @@ static int packet_snd_vnet_gso(struct sk_buff *skb, static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, - __be16 proto, unsigned char *addr, int hlen, int copylen) + __be16 proto, unsigned char *addr, int hlen, int copylen, + const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; int to_write, offset, len, nr_frags, len_max; @@ -2500,7 +2511,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->dev = dev; skb->priority = po->sk.sk_priority; skb->mark = po->sk.sk_mark; - sock_tx_timestamp(&po->sk, &skb_shinfo(skb)->tx_flags); + sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); skb_shinfo(skb)->destructor_arg = ph.raw; skb_reserve(skb, hlen); @@ -2624,6 +2635,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) struct sk_buff *skb; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; + struct sockcm_cookie sockc; __be16 proto; int err, reserve = 0; void *ph; @@ -2655,6 +2667,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); } + sockc.tsflags = 0; + if (msg->msg_controllen) { + err = sock_cmsg_send(&po->sk, msg, &sockc); + if (unlikely(err)) + goto out; + } + err = -ENXIO; if (unlikely(dev == NULL)) goto out; @@ -2712,7 +2731,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, - addr, hlen, copylen); + addr, hlen, copylen, &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !po->has_vnet_hdr && @@ -2851,6 +2870,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; + sockc.tsflags = 0; sockc.mark = sk->sk_mark; if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); @@ -2908,7 +2928,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } - sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); + sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { @@ -4151,7 +4171,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, /* Opening a Tx-ring is NOT supported in TPACKET_V3 */ if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) { - WARN(1, "Tx-ring is not supported.\n"); + net_warn_ratelimited("Tx-ring is not supported.\n"); goto out; } diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 977fb86065b7..abc8cc805e8d 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -796,7 +796,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn, addr = kmap_atomic(sg_page(&frag->f_sg)); - src = addr + frag_off; + src = addr + frag->f_sg.offset + frag_off; dst = (void *)map->m_page_addrs[map_page] + map_off; for (k = 0; k < to_copy; k += 8) { /* Record ports that became uncongested, ie diff --git a/net/rds/page.c b/net/rds/page.c index 616f21f4e7d7..e2b5a5832d3d 100644 --- a/net/rds/page.c +++ b/net/rds/page.c @@ -135,8 +135,8 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes, if (rem->r_offset != 0) rds_stats_inc(s_page_remainder_hit); - rem->r_offset += bytes; - if (rem->r_offset == PAGE_SIZE) { + rem->r_offset += ALIGN(bytes, 8); + if (rem->r_offset >= PAGE_SIZE) { __free_page(rem->r_page); rem->r_page = NULL; } diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 03f26e3a6f48..884027f62783 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1141,6 +1141,7 @@ static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, { struct rfkill *rfkill; struct rfkill_event ev; + int ret; /* we don't need the 'hard' variable but accept it */ if (count < RFKILL_EVENT_SIZE_V1 - 1) @@ -1155,29 +1156,36 @@ static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, if (copy_from_user(&ev, buf, count)) return -EFAULT; - if (ev.op != RFKILL_OP_CHANGE && ev.op != RFKILL_OP_CHANGE_ALL) - return -EINVAL; - if (ev.type >= NUM_RFKILL_TYPES) return -EINVAL; mutex_lock(&rfkill_global_mutex); - if (ev.op == RFKILL_OP_CHANGE_ALL) + switch (ev.op) { + case RFKILL_OP_CHANGE_ALL: rfkill_update_global_state(ev.type, ev.soft); - - list_for_each_entry(rfkill, &rfkill_list, node) { - if (rfkill->idx != ev.idx && ev.op != RFKILL_OP_CHANGE_ALL) - continue; - - if (rfkill->type != ev.type && ev.type != RFKILL_TYPE_ALL) - continue; - - rfkill_set_block(rfkill, ev.soft); + list_for_each_entry(rfkill, &rfkill_list, node) + if (rfkill->type == ev.type || + ev.type == RFKILL_TYPE_ALL) + rfkill_set_block(rfkill, ev.soft); + ret = 0; + break; + case RFKILL_OP_CHANGE: + list_for_each_entry(rfkill, &rfkill_list, node) + if (rfkill->idx == ev.idx && + (rfkill->type == ev.type || + ev.type == RFKILL_TYPE_ALL)) + rfkill_set_block(rfkill, ev.soft); + ret = 0; + break; + default: + ret = -EINVAL; + break; } + mutex_unlock(&rfkill_global_mutex); - return count; + return ret ?: count; } static int rfkill_fop_release(struct inode *inode, struct file *file) diff --git a/net/rxrpc/Kconfig b/net/rxrpc/Kconfig index 23dcef12b986..784c53163b7b 100644 --- a/net/rxrpc/Kconfig +++ b/net/rxrpc/Kconfig @@ -30,7 +30,7 @@ config AF_RXRPC_DEBUG config RXKAD - tristate "RxRPC Kerberos security" + bool "RxRPC Kerberos security" depends on AF_RXRPC select CRYPTO select CRYPTO_MANAGER diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index ec126f91276b..e05a06ef2254 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -18,11 +18,12 @@ af-rxrpc-y := \ ar-recvmsg.o \ ar-security.o \ ar-skbuff.o \ - ar-transport.o + ar-transport.o \ + insecure.o \ + misc.o af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o +af-rxrpc-$(CONFIG_RXKAD) += rxkad.o af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o obj-$(CONFIG_AF_RXRPC) += af-rxrpc.o - -obj-$(CONFIG_RXKAD) += rxkad.o diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 9d935fa5a2a9..e45e94ca030f 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -806,6 +806,12 @@ static int __init af_rxrpc_init(void) goto error_work_queue; } + ret = rxrpc_init_security(); + if (ret < 0) { + printk(KERN_CRIT "RxRPC: Cannot initialise security\n"); + goto error_security; + } + ret = proto_register(&rxrpc_proto, 1); if (ret < 0) { printk(KERN_CRIT "RxRPC: Cannot register protocol\n"); @@ -853,6 +859,8 @@ error_sock: proto_unregister(&rxrpc_proto); error_proto: destroy_workqueue(rxrpc_workqueue); +error_security: + rxrpc_exit_security(); error_work_queue: kmem_cache_destroy(rxrpc_call_jar); error_call_jar: @@ -883,6 +891,7 @@ static void __exit af_rxrpc_exit(void) remove_proc_entry("rxrpc_conns", init_net.proc_net); remove_proc_entry("rxrpc_calls", init_net.proc_net); destroy_workqueue(rxrpc_workqueue); + rxrpc_exit_security(); kmem_cache_destroy(rxrpc_call_jar); _leave(""); } diff --git a/net/rxrpc/ar-accept.c b/net/rxrpc/ar-accept.c index 277731a5e67a..e7a7f05f13e2 100644 --- a/net/rxrpc/ar-accept.c +++ b/net/rxrpc/ar-accept.c @@ -108,7 +108,7 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, goto error; } - conn = rxrpc_incoming_connection(trans, &sp->hdr, GFP_NOIO); + conn = rxrpc_incoming_connection(trans, &sp->hdr); rxrpc_put_transport(trans); if (IS_ERR(conn)) { _debug("no conn"); @@ -116,7 +116,7 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, goto error; } - call = rxrpc_incoming_call(rx, conn, &sp->hdr, GFP_NOIO); + call = rxrpc_incoming_call(rx, conn, &sp->hdr); rxrpc_put_connection(conn); if (IS_ERR(call)) { _debug("no call"); diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c index 16d967075eaf..374478e006e7 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/ar-ack.c @@ -20,74 +20,6 @@ #include "ar-internal.h" /* - * How long to wait before scheduling ACK generation after seeing a - * packet with RXRPC_REQUEST_ACK set (in jiffies). - */ -unsigned int rxrpc_requested_ack_delay = 1; - -/* - * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). - * - * We use this when we've received new data packets. If those packets aren't - * all consumed within this time we will send a DELAY ACK if an ACK was not - * requested to let the sender know it doesn't need to resend. - */ -unsigned int rxrpc_soft_ack_delay = 1 * HZ; - -/* - * How long to wait before scheduling an ACK with subtype IDLE (in jiffies). - * - * We use this when we've consumed some previously soft-ACK'd packets when - * further packets aren't immediately received to decide when to send an IDLE - * ACK let the other end know that it can free up its Tx buffer space. - */ -unsigned int rxrpc_idle_ack_delay = 0.5 * HZ; - -/* - * Receive window size in packets. This indicates the maximum number of - * unconsumed received packets we're willing to retain in memory. Once this - * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further - * packets. - */ -unsigned int rxrpc_rx_window_size = 32; - -/* - * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet - * made by gluing normal packets together that we're willing to handle. - */ -unsigned int rxrpc_rx_mtu = 5692; - -/* - * The maximum number of fragments in a received jumbo packet that we tell the - * sender that we're willing to handle. - */ -unsigned int rxrpc_rx_jumbo_max = 4; - -static const char *rxrpc_acks(u8 reason) -{ - static const char *const str[] = { - "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", - "IDL", "-?-" - }; - - if (reason >= ARRAY_SIZE(str)) - reason = ARRAY_SIZE(str) - 1; - return str[reason]; -} - -static const s8 rxrpc_ack_priority[] = { - [0] = 0, - [RXRPC_ACK_DELAY] = 1, - [RXRPC_ACK_REQUESTED] = 2, - [RXRPC_ACK_IDLE] = 3, - [RXRPC_ACK_PING_RESPONSE] = 4, - [RXRPC_ACK_DUPLICATE] = 5, - [RXRPC_ACK_OUT_OF_SEQUENCE] = 6, - [RXRPC_ACK_EXCEEDS_WINDOW] = 7, - [RXRPC_ACK_NOSPACE] = 8, -}; - -/* * propose an ACK be sent */ void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, @@ -426,7 +358,7 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, u32 hard) int tail = call->acks_tail, old_tail; int win = CIRC_CNT(call->acks_head, tail, call->acks_winsz); - kenter("{%u,%u},%u", call->acks_hard, win, hard); + _enter("{%u,%u},%u", call->acks_hard, win, hard); ASSERTCMP(hard - call->acks_hard, <=, win); @@ -656,7 +588,8 @@ process_further: _proto("OOSQ DATA %%%u { #%u }", sp->hdr.serial, sp->hdr.seq); /* secured packets must be verified and possibly decrypted */ - if (rxrpc_verify_packet(call, skb, _abort_code) < 0) + if (call->conn->security->verify_packet(call, skb, + _abort_code) < 0) goto protocol_error; rxrpc_insert_oos_packet(call, skb); @@ -901,8 +834,8 @@ void rxrpc_process_call(struct work_struct *work) /* there's a good chance we're going to have to send a message, so set * one up in advance */ - msg.msg_name = &call->conn->trans->peer->srx.transport.sin; - msg.msg_namelen = sizeof(call->conn->trans->peer->srx.transport.sin); + msg.msg_name = &call->conn->trans->peer->srx.transport; + msg.msg_namelen = call->conn->trans->peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -973,7 +906,7 @@ void rxrpc_process_call(struct work_struct *work) ECONNABORTED, true) < 0) goto no_mem; whdr.type = RXRPC_PACKET_TYPE_ABORT; - data = htonl(call->abort_code); + data = htonl(call->local_abort); iov[1].iov_base = &data; iov[1].iov_len = sizeof(data); genbit = RXRPC_CALL_EV_ABORT; @@ -1036,7 +969,7 @@ void rxrpc_process_call(struct work_struct *work) write_lock_bh(&call->state_lock); if (call->state <= RXRPC_CALL_COMPLETE) { call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->abort_code = RX_CALL_TIMEOUT; + call->local_abort = RX_CALL_TIMEOUT; set_bit(RXRPC_CALL_EV_ABORT, &call->events); } write_unlock_bh(&call->state_lock); diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c index 7c8d300ade9b..571a41fd5a32 100644 --- a/net/rxrpc/ar-call.c +++ b/net/rxrpc/ar-call.c @@ -411,18 +411,17 @@ found_extant_second: */ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_connection *conn, - struct rxrpc_host_header *hdr, - gfp_t gfp) + struct rxrpc_host_header *hdr) { struct rxrpc_call *call, *candidate; struct rb_node **p, *parent; u32 call_id; - _enter(",%d,,%x", conn->debug_id, gfp); + _enter(",%d", conn->debug_id); ASSERT(rx != NULL); - candidate = rxrpc_alloc_call(gfp); + candidate = rxrpc_alloc_call(GFP_NOIO); if (!candidate) return ERR_PTR(-EBUSY); @@ -682,7 +681,7 @@ void rxrpc_release_call(struct rxrpc_call *call) call->state != RXRPC_CALL_CLIENT_FINAL_ACK) { _debug("+++ ABORTING STATE %d +++\n", call->state); call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->abort_code = RX_CALL_DEAD; + call->local_abort = RX_CALL_DEAD; set_bit(RXRPC_CALL_EV_ABORT, &call->events); rxrpc_queue_call(call); } @@ -758,7 +757,7 @@ static void rxrpc_mark_call_released(struct rxrpc_call *call) if (call->state < RXRPC_CALL_COMPLETE) { _debug("abort call %p", call); call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->abort_code = RX_CALL_DEAD; + call->local_abort = RX_CALL_DEAD; if (!test_and_set_bit(RXRPC_CALL_EV_ABORT, &call->events)) sched = true; } diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 9942da1edbf6..97f4fae74bca 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -207,6 +207,7 @@ static struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) INIT_LIST_HEAD(&conn->bundle_link); conn->calls = RB_ROOT; skb_queue_head_init(&conn->rx_queue); + conn->security = &rxrpc_no_security; rwlock_init(&conn->lock); spin_lock_init(&conn->state_lock); atomic_set(&conn->usage, 1); @@ -564,8 +565,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, candidate->debug_id, candidate->trans->debug_id); rxrpc_assign_connection_id(candidate); - if (candidate->security) - candidate->security->prime_packet_security(candidate); + candidate->security->prime_packet_security(candidate); /* leave the candidate lurking in zombie mode attached to the * bundle until we're ready for it */ @@ -619,8 +619,7 @@ interrupted: */ struct rxrpc_connection * rxrpc_incoming_connection(struct rxrpc_transport *trans, - struct rxrpc_host_header *hdr, - gfp_t gfp) + struct rxrpc_host_header *hdr) { struct rxrpc_connection *conn, *candidate = NULL; struct rb_node *p, **pp; @@ -659,7 +658,7 @@ rxrpc_incoming_connection(struct rxrpc_transport *trans, /* not yet present - create a candidate for a new record and then * redo the search */ - candidate = rxrpc_alloc_connection(gfp); + candidate = rxrpc_alloc_connection(GFP_NOIO); if (!candidate) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); @@ -831,7 +830,10 @@ static void rxrpc_destroy_connection(struct rxrpc_connection *conn) ASSERT(RB_EMPTY_ROOT(&conn->calls)); rxrpc_purge_queue(&conn->rx_queue); - rxrpc_clear_conn_security(conn); + conn->security->clear(conn); + key_put(conn->key); + key_put(conn->server_key); + rxrpc_put_transport(conn->trans); kfree(conn); _leave(""); diff --git a/net/rxrpc/ar-connevent.c b/net/rxrpc/ar-connevent.c index 1bdaaed8cdc4..5f9563968a5b 100644 --- a/net/rxrpc/ar-connevent.c +++ b/net/rxrpc/ar-connevent.c @@ -40,11 +40,13 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, int state, write_lock(&call->state_lock); if (call->state <= RXRPC_CALL_COMPLETE) { call->state = state; - call->abort_code = abort_code; - if (state == RXRPC_CALL_LOCALLY_ABORTED) + if (state == RXRPC_CALL_LOCALLY_ABORTED) { + call->local_abort = conn->local_abort; set_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events); - else + } else { + call->remote_abort = conn->remote_abort; set_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); + } rxrpc_queue_call(call); } write_unlock(&call->state_lock); @@ -84,8 +86,8 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code); - msg.msg_name = &conn->trans->peer->srx.transport.sin; - msg.msg_namelen = sizeof(conn->trans->peer->srx.transport.sin); + msg.msg_name = &conn->trans->peer->srx.transport; + msg.msg_namelen = conn->trans->peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -101,7 +103,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, whdr._rsvd = 0; whdr.serviceId = htons(conn->service_id); - word = htonl(abort_code); + word = htonl(conn->local_abort); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); @@ -112,7 +114,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, serial = atomic_inc_return(&conn->serial); whdr.serial = htonl(serial); - _proto("Tx CONN ABORT %%%u { %d }", serial, abort_code); + _proto("Tx CONN ABORT %%%u { %d }", serial, conn->local_abort); ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 2, len); if (ret < 0) { @@ -172,15 +174,10 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return -ECONNABORTED; case RXRPC_PACKET_TYPE_CHALLENGE: - if (conn->security) - return conn->security->respond_to_challenge( - conn, skb, _abort_code); - return -EPROTO; + return conn->security->respond_to_challenge(conn, skb, + _abort_code); case RXRPC_PACKET_TYPE_RESPONSE: - if (!conn->security) - return -EPROTO; - ret = conn->security->verify_response(conn, skb, _abort_code); if (ret < 0) return ret; @@ -236,8 +233,6 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn) } } - ASSERT(conn->security != NULL); - if (conn->security->issue_challenge(conn) < 0) { abort_code = RX_CALL_DEAD; ret = -ENOMEM; diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 63ed75c40e29..01e038146b7c 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -25,12 +25,6 @@ #include <net/net_namespace.h> #include "ar-internal.h" -const char *rxrpc_pkts[] = { - "?00", - "DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG", - "?09", "?10", "?11", "?12", "VERSION", "?14", "?15" -}; - /* * queue a packet for recvmsg to pass to userspace * - the caller must hold a lock on call->lock @@ -199,7 +193,7 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, /* if the packet need security things doing to it, then it goes down * the slow path */ - if (call->conn->security) + if (call->conn->security_ix) goto enqueue_packet; sp->call = call; @@ -355,7 +349,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) write_lock_bh(&call->state_lock); if (call->state < RXRPC_CALL_COMPLETE) { call->state = RXRPC_CALL_REMOTELY_ABORTED; - call->abort_code = abort_code; + call->remote_abort = abort_code; set_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); rxrpc_queue_call(call); } @@ -428,7 +422,7 @@ protocol_error: protocol_error_locked: if (call->state <= RXRPC_CALL_COMPLETE) { call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->abort_code = RX_PROTOCOL_ERROR; + call->local_abort = RX_PROTOCOL_ERROR; set_bit(RXRPC_CALL_EV_ABORT, &call->events); rxrpc_queue_call(call); } @@ -500,7 +494,7 @@ protocol_error: write_lock_bh(&call->state_lock); if (call->state <= RXRPC_CALL_COMPLETE) { call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->abort_code = RX_PROTOCOL_ERROR; + call->local_abort = RX_PROTOCOL_ERROR; set_bit(RXRPC_CALL_EV_ABORT, &call->events); rxrpc_queue_call(call); } @@ -612,9 +606,9 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) struct rxrpc_wire_header whdr; /* dig out the RxRPC connection details */ - if (skb_copy_bits(skb, sizeof(struct udphdr), &whdr, sizeof(whdr)) < 0) + if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) return -EBADMSG; - if (!pskb_pull(skb, sizeof(struct udphdr) + sizeof(whdr))) + if (!pskb_pull(skb, sizeof(whdr))) BUG(); memset(sp, 0, sizeof(*sp)); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index cd6cdbe87125..f0b807a163fa 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -9,6 +9,7 @@ * 2 of the License, or (at your option) any later version. */ +#include <net/sock.h> #include <rxrpc/packet.h> #if 0 @@ -124,11 +125,15 @@ enum rxrpc_command { * RxRPC security module interface */ struct rxrpc_security { - struct module *owner; /* providing module */ - struct list_head link; /* link in master list */ const char *name; /* name of this service */ u8 security_index; /* security type provided */ + /* Initialise a security service */ + int (*init)(void); + + /* Clean up a security service */ + void (*exit)(void); + /* initialise a connection's security */ int (*init_connection_security)(struct rxrpc_connection *); @@ -268,7 +273,7 @@ struct rxrpc_connection { struct rb_root calls; /* calls on this connection */ struct sk_buff_head rx_queue; /* received conn-level packets */ struct rxrpc_call *channels[RXRPC_MAXCALLS]; /* channels (active calls) */ - struct rxrpc_security *security; /* applied security module */ + const struct rxrpc_security *security; /* applied security module */ struct key *key; /* security for this connection (client) */ struct key *server_key; /* security for this service */ struct crypto_skcipher *cipher; /* encryption handle */ @@ -289,7 +294,9 @@ struct rxrpc_connection { RXRPC_CONN_LOCALLY_ABORTED, /* - conn aborted locally */ RXRPC_CONN_NETWORK_ERROR, /* - conn terminated by network error */ } state; - int error; /* error code for local abort */ + u32 local_abort; /* local abort code */ + u32 remote_abort; /* remote abort code */ + int error; /* local error incurred */ int debug_id; /* debug ID for printks */ unsigned int call_counter; /* call ID counter */ atomic_t serial; /* packet serial number counter */ @@ -399,7 +406,9 @@ struct rxrpc_call { rwlock_t state_lock; /* lock for state transition */ atomic_t usage; atomic_t sequence; /* Tx data packet sequence counter */ - u32 abort_code; /* local/remote abort code */ + u32 local_abort; /* local abort code */ + u32 remote_abort; /* remote abort code */ + int error; /* local error incurred */ enum rxrpc_call_state state : 8; /* current state of call */ int debug_id; /* debug ID for printks */ u8 channel; /* connection channel occupied by this call */ @@ -453,7 +462,7 @@ static inline void rxrpc_abort_call(struct rxrpc_call *call, u32 abort_code) { write_lock_bh(&call->state_lock); if (call->state < RXRPC_CALL_COMPLETE) { - call->abort_code = abort_code; + call->local_abort = abort_code; call->state = RXRPC_CALL_LOCALLY_ABORTED; set_bit(RXRPC_CALL_EV_ABORT, &call->events); } @@ -478,13 +487,6 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * ar-ack.c */ -extern unsigned int rxrpc_requested_ack_delay; -extern unsigned int rxrpc_soft_ack_delay; -extern unsigned int rxrpc_idle_ack_delay; -extern unsigned int rxrpc_rx_window_size; -extern unsigned int rxrpc_rx_mtu; -extern unsigned int rxrpc_rx_jumbo_max; - void __rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool); void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool); void rxrpc_process_call(struct work_struct *); @@ -506,7 +508,7 @@ struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *, unsigned long, int, gfp_t); struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_connection *, - struct rxrpc_host_header *, gfp_t); + struct rxrpc_host_header *); struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *, unsigned long); void rxrpc_release_call(struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); @@ -531,8 +533,7 @@ void __exit rxrpc_destroy_all_connections(void); struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *, struct rxrpc_host_header *); extern struct rxrpc_connection * -rxrpc_incoming_connection(struct rxrpc_transport *, struct rxrpc_host_header *, - gfp_t); +rxrpc_incoming_connection(struct rxrpc_transport *, struct rxrpc_host_header *); /* * ar-connevent.c @@ -550,8 +551,6 @@ void rxrpc_UDP_error_handler(struct work_struct *); /* * ar-input.c */ -extern const char *rxrpc_pkts[]; - void rxrpc_data_ready(struct sock *); int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool); void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *); @@ -610,14 +609,10 @@ int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* * ar-security.c */ -int rxrpc_register_security(struct rxrpc_security *); -void rxrpc_unregister_security(struct rxrpc_security *); +int __init rxrpc_init_security(void); +void rxrpc_exit_security(void); int rxrpc_init_client_conn_security(struct rxrpc_connection *); int rxrpc_init_server_conn_security(struct rxrpc_connection *); -int rxrpc_secure_packet(const struct rxrpc_call *, struct sk_buff *, size_t, - void *); -int rxrpc_verify_packet(const struct rxrpc_call *, struct sk_buff *, u32 *); -void rxrpc_clear_conn_security(struct rxrpc_connection *); /* * ar-skbuff.c @@ -637,6 +632,33 @@ struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *, struct rxrpc_peer *); /* + * insecure.c + */ +extern const struct rxrpc_security rxrpc_no_security; + +/* + * misc.c + */ +extern unsigned int rxrpc_requested_ack_delay; +extern unsigned int rxrpc_soft_ack_delay; +extern unsigned int rxrpc_idle_ack_delay; +extern unsigned int rxrpc_rx_window_size; +extern unsigned int rxrpc_rx_mtu; +extern unsigned int rxrpc_rx_jumbo_max; + +extern const char *const rxrpc_pkts[]; +extern const s8 rxrpc_ack_priority[]; + +extern const char *rxrpc_acks(u8 reason); + +/* + * rxkad.c + */ +#ifdef CONFIG_RXKAD +extern const struct rxrpc_security rxkad; +#endif + +/* * sysctl.c */ #ifdef CONFIG_SYSCTL diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index d36fb6e1a29c..51cb10062a8d 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -110,7 +110,7 @@ static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code) if (call->state <= RXRPC_CALL_COMPLETE) { call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->abort_code = abort_code; + call->local_abort = abort_code; set_bit(RXRPC_CALL_EV_ABORT, &call->events); del_timer_sync(&call->resend_timer); del_timer_sync(&call->ack_timer); @@ -663,7 +663,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, size_t pad; /* pad out if we're using security */ - if (conn->security) { + if (conn->security_ix) { pad = conn->security_size + skb->mark; pad = conn->size_align - pad; pad &= conn->size_align - 1; @@ -695,7 +695,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, if (more && seq & 1) sp->hdr.flags |= RXRPC_REQUEST_ACK; - ret = rxrpc_secure_packet( + ret = conn->security->secure_packet( call, skb, skb->mark, skb->head + sizeof(struct rxrpc_wire_header)); if (ret < 0) diff --git a/net/rxrpc/ar-proc.c b/net/rxrpc/ar-proc.c index 525b2ba5a8f4..225163bc658d 100644 --- a/net/rxrpc/ar-proc.c +++ b/net/rxrpc/ar-proc.c @@ -80,7 +80,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call->conn->in_clientflag ? "Svc" : "Clt", atomic_read(&call->usage), rxrpc_call_states[call->state], - call->abort_code, + call->remote_abort ?: call->local_abort, call->user_call_ID); return 0; diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 64facba24a45..160f0927aa3e 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -288,7 +288,11 @@ receive_non_data_message: ret = put_cmsg(msg, SOL_RXRPC, RXRPC_BUSY, 0, &abort_code); break; case RXRPC_SKB_MARK_REMOTE_ABORT: - abort_code = call->abort_code; + abort_code = call->remote_abort; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &abort_code); + break; + case RXRPC_SKB_MARK_LOCAL_ABORT: + abort_code = call->local_abort; ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &abort_code); break; case RXRPC_SKB_MARK_NET_ERROR: @@ -303,6 +307,7 @@ receive_non_data_message: &abort_code); break; default: + pr_err("RxRPC: Unknown packet mark %u\n", skb->mark); BUG(); break; } @@ -401,9 +406,14 @@ u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - ASSERTCMP(skb->mark, ==, RXRPC_SKB_MARK_REMOTE_ABORT); - - return sp->call->abort_code; + switch (skb->mark) { + case RXRPC_SKB_MARK_REMOTE_ABORT: + return sp->call->remote_abort; + case RXRPC_SKB_MARK_LOCAL_ABORT: + return sp->call->local_abort; + default: + BUG(); + } } EXPORT_SYMBOL(rxrpc_kernel_get_abort_code); diff --git a/net/rxrpc/ar-security.c b/net/rxrpc/ar-security.c index ceff6394a65f..d223253b22fa 100644 --- a/net/rxrpc/ar-security.c +++ b/net/rxrpc/ar-security.c @@ -22,109 +22,60 @@ static LIST_HEAD(rxrpc_security_methods); static DECLARE_RWSEM(rxrpc_security_sem); -/* - * get an RxRPC security module - */ -static struct rxrpc_security *rxrpc_security_get(struct rxrpc_security *sec) -{ - return try_module_get(sec->owner) ? sec : NULL; -} - -/* - * release an RxRPC security module - */ -static void rxrpc_security_put(struct rxrpc_security *sec) +static const struct rxrpc_security *rxrpc_security_types[] = { + [RXRPC_SECURITY_NONE] = &rxrpc_no_security, +#ifdef CONFIG_RXKAD + [RXRPC_SECURITY_RXKAD] = &rxkad, +#endif +}; + +int __init rxrpc_init_security(void) { - module_put(sec->owner); -} - -/* - * look up an rxrpc security module - */ -static struct rxrpc_security *rxrpc_security_lookup(u8 security_index) -{ - struct rxrpc_security *sec = NULL; - - _enter(""); + int i, ret; - down_read(&rxrpc_security_sem); - - list_for_each_entry(sec, &rxrpc_security_methods, link) { - if (sec->security_index == security_index) { - if (unlikely(!rxrpc_security_get(sec))) - break; - goto out; + for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++) { + if (rxrpc_security_types[i]) { + ret = rxrpc_security_types[i]->init(); + if (ret < 0) + goto failed; } } - sec = NULL; -out: - up_read(&rxrpc_security_sem); - _leave(" = %p [%s]", sec, sec ? sec->name : ""); - return sec; + return 0; + +failed: + for (i--; i >= 0; i--) + if (rxrpc_security_types[i]) + rxrpc_security_types[i]->exit(); + return ret; } -/** - * rxrpc_register_security - register an RxRPC security handler - * @sec: security module - * - * register an RxRPC security handler for use by RxRPC - */ -int rxrpc_register_security(struct rxrpc_security *sec) +void rxrpc_exit_security(void) { - struct rxrpc_security *psec; - int ret; + int i; - _enter(""); - down_write(&rxrpc_security_sem); - - ret = -EEXIST; - list_for_each_entry(psec, &rxrpc_security_methods, link) { - if (psec->security_index == sec->security_index) - goto out; - } - - list_add(&sec->link, &rxrpc_security_methods); - - printk(KERN_NOTICE "RxRPC: Registered security type %d '%s'\n", - sec->security_index, sec->name); - ret = 0; - -out: - up_write(&rxrpc_security_sem); - _leave(" = %d", ret); - return ret; + for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++) + if (rxrpc_security_types[i]) + rxrpc_security_types[i]->exit(); } -EXPORT_SYMBOL_GPL(rxrpc_register_security); - -/** - * rxrpc_unregister_security - unregister an RxRPC security handler - * @sec: security module - * - * unregister an RxRPC security handler +/* + * look up an rxrpc security module */ -void rxrpc_unregister_security(struct rxrpc_security *sec) +static const struct rxrpc_security *rxrpc_security_lookup(u8 security_index) { - - _enter(""); - down_write(&rxrpc_security_sem); - list_del_init(&sec->link); - up_write(&rxrpc_security_sem); - - printk(KERN_NOTICE "RxRPC: Unregistered security type %d '%s'\n", - sec->security_index, sec->name); + if (security_index >= ARRAY_SIZE(rxrpc_security_types)) + return NULL; + return rxrpc_security_types[security_index]; } -EXPORT_SYMBOL_GPL(rxrpc_unregister_security); - /* * initialise the security on a client connection */ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) { + const struct rxrpc_security *sec; struct rxrpc_key_token *token; - struct rxrpc_security *sec; struct key *key = conn->key; int ret; @@ -148,8 +99,7 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) ret = conn->security->init_connection_security(conn); if (ret < 0) { - rxrpc_security_put(conn->security); - conn->security = NULL; + conn->security = &rxrpc_no_security; return ret; } @@ -162,7 +112,7 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) */ int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) { - struct rxrpc_security *sec; + const struct rxrpc_security *sec; struct rxrpc_local *local = conn->trans->local; struct rxrpc_sock *rx; struct key *key; @@ -188,14 +138,12 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) /* the service appears to have died */ read_unlock_bh(&local->services_lock); - rxrpc_security_put(sec); _leave(" = -ENOENT"); return -ENOENT; found_service: if (!rx->securities) { read_unlock_bh(&local->services_lock); - rxrpc_security_put(sec); _leave(" = -ENOKEY"); return -ENOKEY; } @@ -205,7 +153,6 @@ found_service: &key_type_rxrpc_s, kdesc); if (IS_ERR(kref)) { read_unlock_bh(&local->services_lock); - rxrpc_security_put(sec); _leave(" = %ld [search]", PTR_ERR(kref)); return PTR_ERR(kref); } @@ -219,46 +166,3 @@ found_service: _leave(" = 0"); return 0; } - -/* - * secure a packet prior to transmission - */ -int rxrpc_secure_packet(const struct rxrpc_call *call, - struct sk_buff *skb, - size_t data_size, - void *sechdr) -{ - if (call->conn->security) - return call->conn->security->secure_packet( - call, skb, data_size, sechdr); - return 0; -} - -/* - * secure a packet prior to transmission - */ -int rxrpc_verify_packet(const struct rxrpc_call *call, struct sk_buff *skb, - u32 *_abort_code) -{ - if (call->conn->security) - return call->conn->security->verify_packet( - call, skb, _abort_code); - return 0; -} - -/* - * clear connection security - */ -void rxrpc_clear_conn_security(struct rxrpc_connection *conn) -{ - _enter("{%d}", conn->debug_id); - - if (conn->security) { - conn->security->clear(conn); - rxrpc_security_put(conn->security); - conn->security = NULL; - } - - key_put(conn->key); - key_put(conn->server_key); -} diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c new file mode 100644 index 000000000000..e571403613c1 --- /dev/null +++ b/net/rxrpc/insecure.c @@ -0,0 +1,83 @@ +/* Null security operations. + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static int none_init_connection_security(struct rxrpc_connection *conn) +{ + return 0; +} + +static void none_prime_packet_security(struct rxrpc_connection *conn) +{ +} + +static int none_secure_packet(const struct rxrpc_call *call, + struct sk_buff *skb, + size_t data_size, + void *sechdr) +{ + return 0; +} + +static int none_verify_packet(const struct rxrpc_call *call, + struct sk_buff *skb, + u32 *_abort_code) +{ + return 0; +} + +static int none_respond_to_challenge(struct rxrpc_connection *conn, + struct sk_buff *skb, + u32 *_abort_code) +{ + *_abort_code = RX_PROTOCOL_ERROR; + return -EPROTO; +} + +static int none_verify_response(struct rxrpc_connection *conn, + struct sk_buff *skb, + u32 *_abort_code) +{ + *_abort_code = RX_PROTOCOL_ERROR; + return -EPROTO; +} + +static void none_clear(struct rxrpc_connection *conn) +{ +} + +static int none_init(void) +{ + return 0; +} + +static void none_exit(void) +{ +} + +/* + * RxRPC Kerberos-based security + */ +const struct rxrpc_security rxrpc_no_security = { + .name = "none", + .security_index = RXRPC_SECURITY_NONE, + .init = none_init, + .exit = none_exit, + .init_connection_security = none_init_connection_security, + .prime_packet_security = none_prime_packet_security, + .secure_packet = none_secure_packet, + .verify_packet = none_verify_packet, + .respond_to_challenge = none_respond_to_challenge, + .verify_response = none_verify_response, + .clear = none_clear, +}; diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c new file mode 100644 index 000000000000..1afe9876e79f --- /dev/null +++ b/net/rxrpc/misc.c @@ -0,0 +1,89 @@ +/* Miscellaneous bits + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +/* + * How long to wait before scheduling ACK generation after seeing a + * packet with RXRPC_REQUEST_ACK set (in jiffies). + */ +unsigned int rxrpc_requested_ack_delay = 1; + +/* + * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). + * + * We use this when we've received new data packets. If those packets aren't + * all consumed within this time we will send a DELAY ACK if an ACK was not + * requested to let the sender know it doesn't need to resend. + */ +unsigned int rxrpc_soft_ack_delay = 1 * HZ; + +/* + * How long to wait before scheduling an ACK with subtype IDLE (in jiffies). + * + * We use this when we've consumed some previously soft-ACK'd packets when + * further packets aren't immediately received to decide when to send an IDLE + * ACK let the other end know that it can free up its Tx buffer space. + */ +unsigned int rxrpc_idle_ack_delay = 0.5 * HZ; + +/* + * Receive window size in packets. This indicates the maximum number of + * unconsumed received packets we're willing to retain in memory. Once this + * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further + * packets. + */ +unsigned int rxrpc_rx_window_size = 32; + +/* + * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet + * made by gluing normal packets together that we're willing to handle. + */ +unsigned int rxrpc_rx_mtu = 5692; + +/* + * The maximum number of fragments in a received jumbo packet that we tell the + * sender that we're willing to handle. + */ +unsigned int rxrpc_rx_jumbo_max = 4; + +const char *const rxrpc_pkts[] = { + "?00", + "DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG", + "?09", "?10", "?11", "?12", "VERSION", "?14", "?15" +}; + +const s8 rxrpc_ack_priority[] = { + [0] = 0, + [RXRPC_ACK_DELAY] = 1, + [RXRPC_ACK_REQUESTED] = 2, + [RXRPC_ACK_IDLE] = 3, + [RXRPC_ACK_PING_RESPONSE] = 4, + [RXRPC_ACK_DUPLICATE] = 5, + [RXRPC_ACK_OUT_OF_SEQUENCE] = 6, + [RXRPC_ACK_EXCEEDS_WINDOW] = 7, + [RXRPC_ACK_NOSPACE] = 8, +}; + +const char *rxrpc_acks(u8 reason) +{ + static const char *const str[] = { + "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", + "IDL", "-?-" + }; + + if (reason >= ARRAY_SIZE(str)) + reason = ARRAY_SIZE(str) - 1; + return str[reason]; +} diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index f0aeb8163688..6b726a046a7d 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -20,7 +20,6 @@ #include <net/sock.h> #include <net/af_rxrpc.h> #include <keys/rxrpc-type.h> -#define rxrpc_debug rxkad_debug #include "ar-internal.h" #define RXKAD_VERSION 2 @@ -31,10 +30,6 @@ #define REALM_SZ 40 /* size of principal's auth domain */ #define SNAME_SZ 40 /* size of service name */ -unsigned int rxrpc_debug; -module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(debug, "rxkad debugging mask"); - struct rxkad_level1_hdr { __be32 data_size; /* true data size (excluding padding) */ }; @@ -44,10 +39,6 @@ struct rxkad_level2_hdr { __be32 checksum; /* decrypted data checksum */ }; -MODULE_DESCRIPTION("RxRPC network protocol type-2 security (Kerberos 4)"); -MODULE_AUTHOR("Red Hat, Inc."); -MODULE_LICENSE("GPL"); - /* * this holds a pinned cipher so that keventd doesn't get called by the cipher * alloc routine, but since we have it to hand, we use it to decrypt RESPONSE @@ -1164,12 +1155,35 @@ static void rxkad_clear(struct rxrpc_connection *conn) } /* + * Initialise the rxkad security service. + */ +static int rxkad_init(void) +{ + /* pin the cipher we need so that the crypto layer doesn't invoke + * keventd to go get it */ + rxkad_ci = crypto_alloc_skcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(rxkad_ci)) + return PTR_ERR(rxkad_ci); + return 0; +} + +/* + * Clean up the rxkad security service. + */ +static void rxkad_exit(void) +{ + if (rxkad_ci) + crypto_free_skcipher(rxkad_ci); +} + +/* * RxRPC Kerberos-based security */ -static struct rxrpc_security rxkad = { - .owner = THIS_MODULE, +const struct rxrpc_security rxkad = { .name = "rxkad", .security_index = RXRPC_SECURITY_RXKAD, + .init = rxkad_init, + .exit = rxkad_exit, .init_connection_security = rxkad_init_connection_security, .prime_packet_security = rxkad_prime_packet_security, .secure_packet = rxkad_secure_packet, @@ -1179,28 +1193,3 @@ static struct rxrpc_security rxkad = { .verify_response = rxkad_verify_response, .clear = rxkad_clear, }; - -static __init int rxkad_init(void) -{ - _enter(""); - - /* pin the cipher we need so that the crypto layer doesn't invoke - * keventd to go get it */ - rxkad_ci = crypto_alloc_skcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(rxkad_ci)) - return PTR_ERR(rxkad_ci); - - return rxrpc_register_security(&rxkad); -} - -module_init(rxkad_init); - -static __exit void rxkad_exit(void) -{ - _enter(""); - - rxrpc_unregister_security(&rxkad); - crypto_free_skcipher(rxkad_ci); -} - -module_exit(rxkad_exit); diff --git a/net/sctp/output.c b/net/sctp/output.c index 736c004abfbc..9844fe573029 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -401,7 +401,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sk = chunk->skb->sk; /* Allocate the new skb. */ - nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC); + nskb = alloc_skb(packet->size + MAX_HEADER, gfp); if (!nskb) goto nomem; @@ -523,8 +523,8 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) */ if (auth) sctp_auth_calculate_hmac(asoc, nskb, - (struct sctp_auth_chunk *)auth, - GFP_ATOMIC); + (struct sctp_auth_chunk *)auth, + gfp); /* 2) Calculate the Adler-32 checksum of the whole packet, * including the SCTP common header and all the @@ -705,7 +705,8 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, /* Check whether this chunk and all the rest of pending data will fit * or delay in hopes of bundling a full sized packet. */ - if (chunk->skb->len + q->out_qlen >= transport->pathmtu - packet->overhead) + if (chunk->skb->len + q->out_qlen > + transport->pathmtu - packet->overhead - sizeof(sctp_data_chunk_t) - 4) /* Enough data queued to fill a packet */ return SCTP_XMIT_OK; diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 5cfac8d5d3b3..6d45d53321e6 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -319,7 +319,8 @@ static int sctp_transport_walk_start(struct seq_file *seq) struct sctp_ht_iter *iter = seq->private; int err; - err = rhashtable_walk_init(&sctp_transport_hashtable, &iter->hti); + err = rhashtable_walk_init(&sctp_transport_hashtable, &iter->hti, + GFP_KERNEL); if (err) return err; diff --git a/net/socket.c b/net/socket.c index 5f77a8e93830..afa3c3470717 100644 --- a/net/socket.c +++ b/net/socket.c @@ -587,20 +587,20 @@ void sock_release(struct socket *sock) } EXPORT_SYMBOL(sock_release); -void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags) +void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) { u8 flags = *tx_flags; - if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_HARDWARE) + if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) flags |= SKBTX_HW_TSTAMP; - if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) + if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) flags |= SKBTX_SW_TSTAMP; - if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED) + if (tsflags & SOF_TIMESTAMPING_TX_SCHED) flags |= SKBTX_SCHED_TSTAMP; - if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK) + if (tsflags & SOF_TIMESTAMPING_TX_ACK) flags |= SKBTX_ACK_TSTAMP; *tx_flags = flags; @@ -1046,7 +1046,7 @@ static int sock_fasync(int fd, struct file *filp, int on) return -EINVAL; lock_sock(sk); - wq = rcu_dereference_protected(sock->wq, sock_owned_by_user(sk)); + wq = rcu_dereference_protected(sock->wq, lockdep_sock_is_held(sk)); fasync_helper(fd, filp, on, &wq->fasync_list); if (!wq->fasync_list) diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 8c6bc795f060..15612ffa8d57 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1728,8 +1728,8 @@ alloc_enc_pages(struct rpc_rqst *rqstp) return 0; } - first = snd_buf->page_base >> PAGE_CACHE_SHIFT; - last = (snd_buf->page_base + snd_buf->page_len - 1) >> PAGE_CACHE_SHIFT; + first = snd_buf->page_base >> PAGE_SHIFT; + last = (snd_buf->page_base + snd_buf->page_len - 1) >> PAGE_SHIFT; rqstp->rq_enc_pages_num = last - first + 1 + 1; rqstp->rq_enc_pages = kmalloc(rqstp->rq_enc_pages_num * sizeof(struct page *), @@ -1775,10 +1775,10 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, status = alloc_enc_pages(rqstp); if (status) return status; - first = snd_buf->page_base >> PAGE_CACHE_SHIFT; + first = snd_buf->page_base >> PAGE_SHIFT; inpages = snd_buf->pages + first; snd_buf->pages = rqstp->rq_enc_pages; - snd_buf->page_base -= first << PAGE_CACHE_SHIFT; + snd_buf->page_base -= first << PAGE_SHIFT; /* * Give the tail its own page, in case we need extra space in the * head when wrapping: diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index d94a8e1e9f05..045e11ecd332 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -465,7 +465,7 @@ encryptor(struct scatterlist *sg, void *data) page_pos = desc->pos - outbuf->head[0].iov_len; if (page_pos >= 0 && page_pos < outbuf->page_len) { /* pages are not in place: */ - int i = (page_pos + outbuf->page_base) >> PAGE_CACHE_SHIFT; + int i = (page_pos + outbuf->page_base) >> PAGE_SHIFT; in_page = desc->pages[i]; } else { in_page = sg_page(sg); diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 765088e4ad84..a737c2da0837 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -79,9 +79,9 @@ gss_krb5_remove_padding(struct xdr_buf *buf, int blocksize) len -= buf->head[0].iov_len; if (len <= buf->page_len) { unsigned int last = (buf->page_base + len - 1) - >>PAGE_CACHE_SHIFT; + >>PAGE_SHIFT; unsigned int offset = (buf->page_base + len - 1) - & (PAGE_CACHE_SIZE - 1); + & (PAGE_SIZE - 1); ptr = kmap_atomic(buf->pages[last]); pad = *(ptr + offset); kunmap_atomic(ptr); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 008c25d1b9f9..553bf95f7003 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -881,7 +881,7 @@ static ssize_t cache_downcall(struct address_space *mapping, char *kaddr; ssize_t ret = -ENOMEM; - if (count >= PAGE_CACHE_SIZE) + if (count >= PAGE_SIZE) goto out_slow; page = find_or_create_page(mapping, 0, GFP_KERNEL); @@ -892,7 +892,7 @@ static ssize_t cache_downcall(struct address_space *mapping, ret = cache_do_downcall(kaddr, buf, count, cd); kunmap(page); unlock_page(page); - page_cache_release(page); + put_page(page); return ret; out_slow: return cache_slow_downcall(buf, count, cd); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 31789ef3e614..fc48eca21fd2 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1390,8 +1390,8 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); int err; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = RPCAUTH_GSSMAGIC; sb->s_op = &s_ops; sb->s_d_op = &simple_dentry_operations; diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 2df87f78e518..f217c348b341 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -96,8 +96,8 @@ ssize_t xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base, struct if (base || xdr->page_base) { pglen -= base; base += xdr->page_base; - ppage += base >> PAGE_CACHE_SHIFT; - base &= ~PAGE_CACHE_MASK; + ppage += base >> PAGE_SHIFT; + base &= ~PAGE_MASK; } do { char *kaddr; @@ -113,7 +113,7 @@ ssize_t xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base, struct } } - len = PAGE_CACHE_SIZE; + len = PAGE_SIZE; kaddr = kmap_atomic(*ppage); if (base) { len -= base; @@ -155,7 +155,7 @@ int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb) struct xdr_skb_reader desc; desc.skb = skb; - desc.offset = sizeof(struct udphdr); + desc.offset = 0; desc.count = skb->len - desc.offset; if (skb_csum_unnecessary(skb)) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 1413cdcc131c..71d6072664d2 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -617,7 +617,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) svsk->sk_sk->sk_stamp = skb->tstamp; set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */ - len = skb->len - sizeof(struct udphdr); + len = skb->len; rqstp->rq_arg.len = len; rqstp->rq_prot = IPPROTO_UDP; @@ -641,8 +641,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) skb_free_datagram_locked(svsk->sk_sk, skb); } else { /* we can use it in-place */ - rqstp->rq_arg.head[0].iov_base = skb->data + - sizeof(struct udphdr); + rqstp->rq_arg.head[0].iov_base = skb->data; rqstp->rq_arg.head[0].iov_len = len; if (skb_checksum_complete(skb)) goto out_free; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 4439ac4c1b53..6bdb3865212d 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -164,7 +164,7 @@ EXPORT_SYMBOL_GPL(xdr_inline_pages); * Note: the addresses pgto_base and pgfrom_base are both calculated in * the same way: * if a memory area starts at byte 'base' in page 'pages[i]', - * then its address is given as (i << PAGE_CACHE_SHIFT) + base + * then its address is given as (i << PAGE_SHIFT) + base * Also note: pgfrom_base must be < pgto_base, but the memory areas * they point to may overlap. */ @@ -181,20 +181,20 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base, pgto_base += len; pgfrom_base += len; - pgto = pages + (pgto_base >> PAGE_CACHE_SHIFT); - pgfrom = pages + (pgfrom_base >> PAGE_CACHE_SHIFT); + pgto = pages + (pgto_base >> PAGE_SHIFT); + pgfrom = pages + (pgfrom_base >> PAGE_SHIFT); - pgto_base &= ~PAGE_CACHE_MASK; - pgfrom_base &= ~PAGE_CACHE_MASK; + pgto_base &= ~PAGE_MASK; + pgfrom_base &= ~PAGE_MASK; do { /* Are any pointers crossing a page boundary? */ if (pgto_base == 0) { - pgto_base = PAGE_CACHE_SIZE; + pgto_base = PAGE_SIZE; pgto--; } if (pgfrom_base == 0) { - pgfrom_base = PAGE_CACHE_SIZE; + pgfrom_base = PAGE_SIZE; pgfrom--; } @@ -236,11 +236,11 @@ _copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len) char *vto; size_t copy; - pgto = pages + (pgbase >> PAGE_CACHE_SHIFT); - pgbase &= ~PAGE_CACHE_MASK; + pgto = pages + (pgbase >> PAGE_SHIFT); + pgbase &= ~PAGE_MASK; for (;;) { - copy = PAGE_CACHE_SIZE - pgbase; + copy = PAGE_SIZE - pgbase; if (copy > len) copy = len; @@ -253,7 +253,7 @@ _copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len) break; pgbase += copy; - if (pgbase == PAGE_CACHE_SIZE) { + if (pgbase == PAGE_SIZE) { flush_dcache_page(*pgto); pgbase = 0; pgto++; @@ -280,11 +280,11 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len) char *vfrom; size_t copy; - pgfrom = pages + (pgbase >> PAGE_CACHE_SHIFT); - pgbase &= ~PAGE_CACHE_MASK; + pgfrom = pages + (pgbase >> PAGE_SHIFT); + pgbase &= ~PAGE_MASK; do { - copy = PAGE_CACHE_SIZE - pgbase; + copy = PAGE_SIZE - pgbase; if (copy > len) copy = len; @@ -293,7 +293,7 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len) kunmap_atomic(vfrom); pgbase += copy; - if (pgbase == PAGE_CACHE_SIZE) { + if (pgbase == PAGE_SIZE) { pgbase = 0; pgfrom++; } @@ -1038,8 +1038,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, if (base < buf->page_len) { subbuf->page_len = min(buf->page_len - base, len); base += buf->page_base; - subbuf->page_base = base & ~PAGE_CACHE_MASK; - subbuf->pages = &buf->pages[base >> PAGE_CACHE_SHIFT]; + subbuf->page_base = base & ~PAGE_MASK; + subbuf->pages = &buf->pages[base >> PAGE_SHIFT]; len -= subbuf->page_len; base = 0; } else { @@ -1297,9 +1297,9 @@ xdr_xcode_array2(struct xdr_buf *buf, unsigned int base, todo -= avail_here; base += buf->page_base; - ppages = buf->pages + (base >> PAGE_CACHE_SHIFT); - base &= ~PAGE_CACHE_MASK; - avail_page = min_t(unsigned int, PAGE_CACHE_SIZE - base, + ppages = buf->pages + (base >> PAGE_SHIFT); + base &= ~PAGE_MASK; + avail_page = min_t(unsigned int, PAGE_SIZE - base, avail_here); c = kmap(*ppages) + base; @@ -1383,7 +1383,7 @@ xdr_xcode_array2(struct xdr_buf *buf, unsigned int base, } avail_page = min(avail_here, - (unsigned int) PAGE_CACHE_SIZE); + (unsigned int) PAGE_SIZE); } base = buf->page_len; /* align to start of tail */ } @@ -1479,9 +1479,9 @@ xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, if (page_len > len) page_len = len; len -= page_len; - page_offset = (offset + buf->page_base) & (PAGE_CACHE_SIZE - 1); - i = (offset + buf->page_base) >> PAGE_CACHE_SHIFT; - thislen = PAGE_CACHE_SIZE - page_offset; + page_offset = (offset + buf->page_base) & (PAGE_SIZE - 1); + i = (offset + buf->page_base) >> PAGE_SHIFT; + thislen = PAGE_SIZE - page_offset; do { if (thislen > page_len) thislen = page_len; @@ -1492,7 +1492,7 @@ xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, page_len -= thislen; i++; page_offset = 0; - thislen = PAGE_CACHE_SIZE; + thislen = PAGE_SIZE; } while (page_len != 0); offset = 0; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 65e759569e48..c1fc7b20bbc1 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -995,15 +995,14 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt, u32 _xid; __be32 *xp; - repsize = skb->len - sizeof(struct udphdr); + repsize = skb->len; if (repsize < 4) { dprintk("RPC: impossible RPC reply size %d!\n", repsize); return; } /* Copy the XID from the skb... */ - xp = skb_header_pointer(skb, sizeof(struct udphdr), - sizeof(_xid), &_xid); + xp = skb_header_pointer(skb, 0, sizeof(_xid), &_xid); if (xp == NULL) return; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8b5833c1ff2e..2b9b98f1c2ff 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1079,7 +1079,7 @@ nla_put_failure: * @filter_dev: filter device * @idx: * - * Delete FDB entry from switch device. + * Dump FDB entries from switch device. */ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 27a5406213c6..6f11c62bc8f9 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -205,6 +205,7 @@ static int tipc_enable_bearer(struct net *net, const char *name, struct tipc_bearer *b; struct tipc_media *m; struct tipc_bearer_names b_names; + struct sk_buff *skb; char addr_string[16]; u32 bearer_id; u32 with_this_prio; @@ -301,7 +302,7 @@ restart: b->net_plane = bearer_id + 'A'; b->priority = priority; - res = tipc_disc_create(net, b, &b->bcast_addr); + res = tipc_disc_create(net, b, &b->bcast_addr, &skb); if (res) { bearer_disable(net, b); pr_warn("Bearer <%s> rejected, discovery object creation failed\n", @@ -310,7 +311,8 @@ restart: } rcu_assign_pointer(tn->bearer_list[bearer_id], b); - + if (skb) + tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr); pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n", name, tipc_addr_string_fill(addr_string, disc_domain), priority); @@ -335,23 +337,16 @@ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b) */ static void bearer_disable(struct net *net, struct tipc_bearer *b) { - struct tipc_net *tn = net_generic(net, tipc_net_id); - u32 i; + struct tipc_net *tn = tipc_net(net); + int bearer_id = b->identity; pr_info("Disabling bearer <%s>\n", b->name); b->media->disable_media(b); - - tipc_node_delete_links(net, b->identity); + tipc_node_delete_links(net, bearer_id); RCU_INIT_POINTER(b->media_ptr, NULL); if (b->link_req) tipc_disc_delete(b->link_req); - - for (i = 0; i < MAX_BEARERS; i++) { - if (b == rtnl_dereference(tn->bearer_list[i])) { - RCU_INIT_POINTER(tn->bearer_list[i], NULL); - break; - } - } + RCU_INIT_POINTER(tn->bearer_list[bearer_id], NULL); kfree_rcu(b, rcu); } @@ -394,7 +389,7 @@ void tipc_disable_l2_media(struct tipc_bearer *b) /** * tipc_l2_send_msg - send a TIPC packet out over an L2 interface - * @buf: the packet to be sent + * @skb: the packet to be sent * @b: the bearer through which the packet is to be sent * @dest: peer destination address */ @@ -403,17 +398,21 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb, { struct net_device *dev; int delta; + void *tipc_ptr; dev = (struct net_device *)rcu_dereference_rtnl(b->media_ptr); if (!dev) return 0; + /* Send RESET message even if bearer is detached from device */ + tipc_ptr = rtnl_dereference(dev->tipc_ptr); + if (unlikely(!tipc_ptr && !msg_is_reset(buf_msg(skb)))) + goto drop; + delta = dev->hard_header_len - skb_headroom(skb); if ((delta > 0) && - pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { - kfree_skb(skb); - return 0; - } + pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) + goto drop; skb_reset_network_header(skb); skb->dev = dev; @@ -422,6 +421,9 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb, dev->dev_addr, skb->len); dev_queue_xmit(skb); return 0; +drop: + kfree_skb(skb); + return 0; } int tipc_bearer_mtu(struct net *net, u32 bearer_id) @@ -450,6 +452,8 @@ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); if (likely(b)) b->media->send_msg(net, skb, b, dest); + else + kfree_skb(skb); rcu_read_unlock(); } @@ -468,11 +472,11 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, rcu_read_lock(); b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); - if (likely(b)) { - skb_queue_walk_safe(xmitq, skb, tmp) { - __skb_dequeue(xmitq); - b->media->send_msg(net, skb, b, dst); - } + if (unlikely(!b)) + __skb_queue_purge(xmitq); + skb_queue_walk_safe(xmitq, skb, tmp) { + __skb_dequeue(xmitq); + b->media->send_msg(net, skb, b, dst); } rcu_read_unlock(); } @@ -490,14 +494,14 @@ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, rcu_read_lock(); b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); - if (likely(b)) { - skb_queue_walk_safe(xmitq, skb, tmp) { - hdr = buf_msg(skb); - msg_set_non_seq(hdr, 1); - msg_set_mc_netid(hdr, net_id); - __skb_dequeue(xmitq); - b->media->send_msg(net, skb, b, &b->bcast_addr); - } + if (unlikely(!b)) + __skb_queue_purge(xmitq); + skb_queue_walk_safe(xmitq, skb, tmp) { + hdr = buf_msg(skb); + msg_set_non_seq(hdr, 1); + msg_set_mc_netid(hdr, net_id); + __skb_dequeue(xmitq); + b->media->send_msg(net, skb, b, &b->bcast_addr); } rcu_read_unlock(); } @@ -513,24 +517,21 @@ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, * ignores packets sent using interface multicast, and traffic sent to other * nodes (which can happen if interface is running in promiscuous mode). */ -static int tipc_l2_rcv_msg(struct sk_buff *buf, struct net_device *dev, +static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct tipc_bearer *b; rcu_read_lock(); b = rcu_dereference_rtnl(dev->tipc_ptr); - if (likely(b)) { - if (likely(buf->pkt_type <= PACKET_BROADCAST)) { - buf->next = NULL; - tipc_rcv(dev_net(dev), buf, b); - rcu_read_unlock(); - return NET_RX_SUCCESS; - } + if (likely(b && (skb->pkt_type <= PACKET_BROADCAST))) { + skb->next = NULL; + tipc_rcv(dev_net(dev), skb, b); + rcu_read_unlock(); + return NET_RX_SUCCESS; } rcu_read_unlock(); - - kfree_skb(buf); + kfree_skb(skb); return NET_RX_DROP; } @@ -548,9 +549,18 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); + struct tipc_net *tn = tipc_net(net); struct tipc_bearer *b; + int i; b = rtnl_dereference(dev->tipc_ptr); + if (!b) { + for (i = 0; i < MAX_BEARERS; b = NULL, i++) { + b = rtnl_dereference(tn->bearer_list[i]); + if (b && (b->media_ptr == dev)) + break; + } + } if (!b) return NOTIFY_DONE; @@ -560,13 +570,20 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, case NETDEV_CHANGE: if (netif_carrier_ok(dev)) break; + case NETDEV_UP: + rcu_assign_pointer(dev->tipc_ptr, b); + break; case NETDEV_GOING_DOWN: + RCU_INIT_POINTER(dev->tipc_ptr, NULL); + synchronize_net(); + tipc_reset_bearer(net, b); + break; case NETDEV_CHANGEMTU: tipc_reset_bearer(net, b); break; case NETDEV_CHANGEADDR: b->media->raw2addr(b, &b->addr, - (char *)dev->dev_addr); + (char *)dev->dev_addr); tipc_reset_bearer(net, b); break; case NETDEV_UNREGISTER: diff --git a/net/tipc/discover.c b/net/tipc/discover.c index f1e738e80535..ad9d477cc242 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -268,10 +268,9 @@ exit: * Returns 0 if successful, otherwise -errno. */ int tipc_disc_create(struct net *net, struct tipc_bearer *b, - struct tipc_media_addr *dest) + struct tipc_media_addr *dest, struct sk_buff **skb) { struct tipc_link_req *req; - struct sk_buff *skb; req = kmalloc(sizeof(*req), GFP_ATOMIC); if (!req) @@ -293,9 +292,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b, setup_timer(&req->timer, disc_timeout, (unsigned long)req); mod_timer(&req->timer, jiffies + req->timer_intv); b->link_req = req; - skb = skb_clone(req->buf, GFP_ATOMIC); - if (skb) - tipc_bearer_xmit_skb(net, req->bearer_id, skb, &req->dest); + *skb = skb_clone(req->buf, GFP_ATOMIC); return 0; } diff --git a/net/tipc/discover.h b/net/tipc/discover.h index c9b12770c5ed..b80a335389c0 100644 --- a/net/tipc/discover.h +++ b/net/tipc/discover.h @@ -40,7 +40,7 @@ struct tipc_link_req; int tipc_disc_create(struct net *net, struct tipc_bearer *b_ptr, - struct tipc_media_addr *dest); + struct tipc_media_addr *dest, struct sk_buff **skb); void tipc_disc_delete(struct tipc_link_req *req); void tipc_disc_reset(struct net *net, struct tipc_bearer *b_ptr); void tipc_disc_add_dest(struct tipc_link_req *req); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 55778a0aebf3..f34f639df643 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -779,6 +779,11 @@ static inline bool msg_peer_node_is_up(struct tipc_msg *m) return msg_redundant_link(m); } +static inline bool msg_is_reset(struct tipc_msg *hdr) +{ + return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG); +} + struct sk_buff *tipc_buf_acquire(u32 size); bool tipc_msg_validate(struct sk_buff *skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 0a369bb440e7..662bdd20a748 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -842,7 +842,7 @@ static void vmci_transport_peer_detach_cb(u32 sub_id, * qp_handle. */ if (vmci_handle_is_invalid(e_payload->handle) || - vmci_handle_is_equal(trans->qp_handle, e_payload->handle)) + !vmci_handle_is_equal(trans->qp_handle, e_payload->handle)) return; /* We don't ask for delayed CBs when we subscribe to this event (we @@ -2154,7 +2154,7 @@ module_exit(vmci_transport_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMCI transport for Virtual Sockets"); -MODULE_VERSION("1.0.2.0-k"); +MODULE_VERSION("1.0.3.0-k"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("vmware_vsock"); MODULE_ALIAS_NETPROTO(PF_VSOCK); diff --git a/net/wireless/core.c b/net/wireless/core.c index 9f1c4aa851ef..5327e4b974fa 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -626,6 +626,13 @@ int wiphy_register(struct wiphy *wiphy) !rdev->ops->set_mac_acl))) return -EINVAL; + /* assure only valid behaviours are flagged by driver + * hence subtract 2 as bit 0 is invalid. + */ + if (WARN_ON(wiphy->bss_select_support && + (wiphy->bss_select_support & ~(BIT(__NL80211_BSS_SELECT_ATTR_AFTER_LAST) - 2)))) + return -EINVAL; + if (wiphy->addresses) memcpy(wiphy->perm_addr, wiphy->addresses[0].addr, ETH_ALEN); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 98c924260b3d..4f45a2913104 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -402,6 +402,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_SCHED_SCAN_DELAY] = { .type = NLA_U32 }, [NL80211_ATTR_REG_INDOOR] = { .type = NLA_FLAG }, [NL80211_ATTR_PBSS] = { .type = NLA_FLAG }, + [NL80211_ATTR_BSS_SELECT] = { .type = NLA_NESTED }, + [NL80211_ATTR_STA_SUPPORT_P2P_PS] = { .type = NLA_U8 }, }; /* policy for the key attributes */ @@ -486,6 +488,15 @@ nl80211_plan_policy[NL80211_SCHED_SCAN_PLAN_MAX + 1] = { [NL80211_SCHED_SCAN_PLAN_ITERATIONS] = { .type = NLA_U32 }, }; +static const struct nla_policy +nl80211_bss_select_policy[NL80211_BSS_SELECT_ATTR_MAX + 1] = { + [NL80211_BSS_SELECT_ATTR_RSSI] = { .type = NLA_FLAG }, + [NL80211_BSS_SELECT_ATTR_BAND_PREF] = { .type = NLA_U32 }, + [NL80211_BSS_SELECT_ATTR_RSSI_ADJUST] = { + .len = sizeof(struct nl80211_bss_select_rssi_adjust) + }, +}; + static int nl80211_prepare_wdev_dump(struct sk_buff *skb, struct netlink_callback *cb, struct cfg80211_registered_device **rdev, @@ -1731,6 +1742,25 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.ext_features)) goto nla_put_failure; + if (rdev->wiphy.bss_select_support) { + struct nlattr *nested; + u32 bss_select_support = rdev->wiphy.bss_select_support; + + nested = nla_nest_start(msg, NL80211_ATTR_BSS_SELECT); + if (!nested) + goto nla_put_failure; + + i = 0; + while (bss_select_support) { + if ((bss_select_support & 1) && + nla_put_flag(msg, i)) + goto nla_put_failure; + i++; + bss_select_support >>= 1; + } + nla_nest_end(msg, nested); + } + /* done */ state->split_start = 0; break; @@ -3977,6 +4007,10 @@ int cfg80211_check_station_change(struct wiphy *wiphy, statype != CFG80211_STA_AP_CLIENT_UNASSOC) return -EINVAL; + if (params->support_p2p_ps != -1 && + statype != CFG80211_STA_AP_CLIENT_UNASSOC) + return -EINVAL; + if (params->aid && !(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) && statype != CFG80211_STA_AP_CLIENT_UNASSOC) @@ -4270,6 +4304,18 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) else params.listen_interval = -1; + if (info->attrs[NL80211_ATTR_STA_SUPPORT_P2P_PS]) { + u8 tmp; + + tmp = nla_get_u8(info->attrs[NL80211_ATTR_STA_SUPPORT_P2P_PS]); + if (tmp >= NUM_NL80211_P2P_PS_STATUS) + return -EINVAL; + + params.support_p2p_ps = tmp; + } else { + params.support_p2p_ps = -1; + } + if (!info->attrs[NL80211_ATTR_MAC]) return -EINVAL; @@ -4393,6 +4439,23 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.listen_interval = nla_get_u16(info->attrs[NL80211_ATTR_STA_LISTEN_INTERVAL]); + if (info->attrs[NL80211_ATTR_STA_SUPPORT_P2P_PS]) { + u8 tmp; + + tmp = nla_get_u8(info->attrs[NL80211_ATTR_STA_SUPPORT_P2P_PS]); + if (tmp >= NUM_NL80211_P2P_PS_STATUS) + return -EINVAL; + + params.support_p2p_ps = tmp; + } else { + /* + * if not specified, assume it's supported for P2P GO interface, + * and is NOT supported for AP interface + */ + params.support_p2p_ps = + dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO; + } + if (info->attrs[NL80211_ATTR_PEER_AID]) params.aid = nla_get_u16(info->attrs[NL80211_ATTR_PEER_AID]); else @@ -5758,6 +5821,73 @@ static int validate_scan_freqs(struct nlattr *freqs) return n_channels; } +static bool is_band_valid(struct wiphy *wiphy, enum ieee80211_band b) +{ + return b < IEEE80211_NUM_BANDS && wiphy->bands[b]; +} + +static int parse_bss_select(struct nlattr *nla, struct wiphy *wiphy, + struct cfg80211_bss_selection *bss_select) +{ + struct nlattr *attr[NL80211_BSS_SELECT_ATTR_MAX + 1]; + struct nlattr *nest; + int err; + bool found = false; + int i; + + /* only process one nested attribute */ + nest = nla_data(nla); + if (!nla_ok(nest, nla_len(nest))) + return -EINVAL; + + err = nla_parse(attr, NL80211_BSS_SELECT_ATTR_MAX, nla_data(nest), + nla_len(nest), nl80211_bss_select_policy); + if (err) + return err; + + /* only one attribute may be given */ + for (i = 0; i <= NL80211_BSS_SELECT_ATTR_MAX; i++) { + if (attr[i]) { + if (found) + return -EINVAL; + found = true; + } + } + + bss_select->behaviour = __NL80211_BSS_SELECT_ATTR_INVALID; + + if (attr[NL80211_BSS_SELECT_ATTR_RSSI]) + bss_select->behaviour = NL80211_BSS_SELECT_ATTR_RSSI; + + if (attr[NL80211_BSS_SELECT_ATTR_BAND_PREF]) { + bss_select->behaviour = NL80211_BSS_SELECT_ATTR_BAND_PREF; + bss_select->param.band_pref = + nla_get_u32(attr[NL80211_BSS_SELECT_ATTR_BAND_PREF]); + if (!is_band_valid(wiphy, bss_select->param.band_pref)) + return -EINVAL; + } + + if (attr[NL80211_BSS_SELECT_ATTR_RSSI_ADJUST]) { + struct nl80211_bss_select_rssi_adjust *adj_param; + + adj_param = nla_data(attr[NL80211_BSS_SELECT_ATTR_RSSI_ADJUST]); + bss_select->behaviour = NL80211_BSS_SELECT_ATTR_RSSI_ADJUST; + bss_select->param.adjust.band = adj_param->band; + bss_select->param.adjust.delta = adj_param->delta; + if (!is_band_valid(wiphy, bss_select->param.adjust.band)) + return -EINVAL; + } + + /* user-space did not provide behaviour attribute */ + if (bss_select->behaviour == __NL80211_BSS_SELECT_ATTR_INVALID) + return -EINVAL; + + if (!(wiphy->bss_select_support & BIT(bss_select->behaviour))) + return -EINVAL; + + return 0; +} + static int nl80211_parse_random_mac(struct nlattr **attrs, u8 *mac_addr, u8 *mac_addr_mask) { @@ -5996,6 +6126,12 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) request->no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); + if (info->attrs[NL80211_ATTR_MAC]) + memcpy(request->bssid, nla_data(info->attrs[NL80211_ATTR_MAC]), + ETH_ALEN); + else + eth_broadcast_addr(request->bssid); + request->wdev = wdev; request->wiphy = &rdev->wiphy; request->scan_start = jiffies; @@ -7922,6 +8058,10 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) connect.mfp = NL80211_MFP_NO; } + if (info->attrs[NL80211_ATTR_PREV_BSSID]) + connect.prev_bssid = + nla_data(info->attrs[NL80211_ATTR_PREV_BSSID]); + if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { connect.channel = nl80211_get_valid_chan( wiphy, info->attrs[NL80211_ATTR_WIPHY_FREQ]); @@ -7995,8 +8135,24 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; } + if (info->attrs[NL80211_ATTR_BSS_SELECT]) { + /* bss selection makes no sense if bssid is set */ + if (connect.bssid) { + kzfree(connkeys); + return -EINVAL; + } + + err = parse_bss_select(info->attrs[NL80211_ATTR_BSS_SELECT], + wiphy, &connect.bss_select); + if (err) { + kzfree(connkeys); + return err; + } + } + wdev_lock(dev->ieee80211_ptr); - err = cfg80211_connect(rdev, dev, &connect, connkeys, NULL); + err = cfg80211_connect(rdev, dev, &connect, connkeys, + connect.prev_bssid); wdev_unlock(dev->ieee80211_ptr); if (err) kzfree(connkeys); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 14d5369eb778..50ea8e3fcbeb 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1293,6 +1293,8 @@ int cfg80211_wext_siwscan(struct net_device *dev, if (wiphy->bands[i]) creq->rates[i] = (1 << wiphy->bands[i]->n_bitrates) - 1; + eth_broadcast_addr(creq->bssid); + rdev->scan_req = creq; err = rdev_scan(rdev, creq); if (err) { diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 544558171787..1fba41676428 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -119,6 +119,8 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) wdev->conn->params.ssid_len); request->ssids[0].ssid_len = wdev->conn->params.ssid_len; + eth_broadcast_addr(request->bssid); + request->wdev = wdev; request->wiphy = &rdev->wiphy; request->scan_start = jiffies; @@ -490,8 +492,18 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, if (!rdev->ops->auth || !rdev->ops->assoc) return -EOPNOTSUPP; - if (wdev->current_bss) - return -EALREADY; + if (wdev->current_bss) { + if (!prev_bssid) + return -EALREADY; + if (prev_bssid && + !ether_addr_equal(prev_bssid, wdev->current_bss->pub.bssid)) + return -ENOTCONN; + cfg80211_unhold_bss(wdev->current_bss); + cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); + wdev->current_bss = NULL; + + cfg80211_sme_free(wdev); + } if (WARN_ON(wdev->conn)) return -EINPROGRESS; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 09b242b09bed..8da1fae23cfb 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1259,6 +1259,7 @@ TRACE_EVENT(rdev_connect, __field(bool, privacy) __field(u32, wpa_versions) __field(u32, flags) + MAC_ENTRY(prev_bssid) ), TP_fast_assign( WIPHY_ASSIGN; @@ -1270,13 +1271,14 @@ TRACE_EVENT(rdev_connect, __entry->privacy = sme->privacy; __entry->wpa_versions = sme->crypto.wpa_versions; __entry->flags = sme->flags; + MAC_ASSIGN(prev_bssid, sme->prev_bssid); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT ", ssid: %s, auth type: %d, privacy: %s, wpa versions: %u, " - "flags: %u", + "flags: %u, previous bssid: " MAC_PR_FMT, WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(bssid), __entry->ssid, __entry->auth_type, BOOL_TO_STR(__entry->privacy), - __entry->wpa_versions, __entry->flags) + __entry->wpa_versions, __entry->flags, MAC_PR_ARG(prev_bssid)) ); TRACE_EVENT(rdev_set_cqm_rssi_config, diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index b50ee5d622e1..6250b1cfcde5 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -399,7 +399,10 @@ static int __init wireless_nlevent_init(void) if (err) return err; - return register_netdevice_notifier(&wext_netdev_notifier); + err = register_netdevice_notifier(&wext_netdev_notifier); + if (err) + unregister_pernet_subsys(&wext_pernet_ops); + return err; } subsys_initcall(wireless_nlevent_init); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index ad7f5b3f9b61..1c4ad477ce93 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -292,12 +292,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; skb_dst_force(skb); + dev_hold(skb->dev); nexthdr = x->type->input(x, skb); if (nexthdr == -EINPROGRESS) return 0; resume: + dev_put(skb->dev); + spin_lock(&x->lock); if (nexthdr <= 0) { if (nexthdr == -EBADMSG) { |