diff options
author | Deepak Nibade <dnibade@nvidia.com> | 2013-08-14 16:23:39 +0530 |
---|---|---|
committer | Deepak Nibade <dnibade@nvidia.com> | 2013-08-14 16:23:39 +0530 |
commit | 9282699d7fd7954f11d59254e568e5d4bfbbe71a (patch) | |
tree | 4d945260bc8eb63b0db0423ad55ad7021eb5d4ac /net | |
parent | 933d6b11dbd7fda89ac094321d0cd9992afb5592 (diff) | |
parent | 67e6589a34ea5360b00869aaaec4a844c29cf713 (diff) |
Merge branch 'linux-3.4.57' into rel-17
Bug 1348440
Change-Id: If25c49f027dc2a69642f7ed4733e965962b2a5a2
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Diffstat (limited to 'net')
89 files changed, 853 insertions, 365 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index cf4a49c5623c..e22b8ada799c 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -86,13 +86,6 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) grp = &vlan_info->grp; - /* Take it out of our own structures, but be sure to interlock with - * HW accelerating devices or SW vlan input packet processing if - * VLAN is not 0 (leave it there for 802.1p). - */ - if (vlan_id) - vlan_vid_del(real_dev, vlan_id); - grp->nr_vlan_devs--; if (vlan->flags & VLAN_FLAG_GVRP) @@ -108,6 +101,13 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) if (grp->nr_vlan_devs == 0) vlan_gvrp_uninit_applicant(real_dev); + /* Take it out of our own structures, but be sure to interlock with + * HW accelerating devices or SW vlan input packet processing if + * VLAN is not 0 (leave it there for 802.1p). + */ + if (vlan_id) + vlan_vid_del(real_dev, vlan_id); + /* Get rid of the vlan's reference to real_dev */ dev_put(real_dev); } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 9757c193c86b..8f453927cc51 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -73,6 +73,8 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb) { struct vlan_priority_tci_mapping *mp; + smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */ + mp = vlan_dev_priv(dev)->egress_priority_map[(skb->priority & 0xF)]; while (mp) { if (mp->priority == skb->priority) { @@ -235,6 +237,11 @@ int vlan_dev_set_egress_priority(const struct net_device *dev, np->next = mp; np->priority = skb_prio; np->vlan_qos = vlan_qos; + /* Before inserting this element in hash table, make sure all its fields + * are committed to memory. + * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask() + */ + smp_wmb(); vlan->egress_priority_map[skb_prio & 0xF] = np; if (vlan_qos) vlan->nr_egress_mappings++; @@ -598,7 +605,7 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev, netdev_features_t features) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; - u32 old_features = features; + netdev_features_t old_features = features; features &= real_dev->vlan_features; features |= NETIF_F_RXCSUM; diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index de8df957867d..2ee3879161b1 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -24,11 +24,11 @@ */ void p9_release_pages(struct page **pages, int nr_pages) { - int i = 0; - while (pages[i] && nr_pages--) { - put_page(pages[i]); - i++; - } + int i; + + for (i = 0; i < nr_pages; i++) + if (pages[i]) + put_page(pages[i]); } EXPORT_SYMBOL(p9_release_pages); diff --git a/net/atm/common.c b/net/atm/common.c index 0c0ad930a632..f0a9b7eb3732 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -520,6 +520,8 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, struct sk_buff *skb; int copied, error = -EINVAL; + msg->msg_namelen = 0; + if (sock->state != SS_CONNECTED) return -ENOTCONN; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 9d9a6a3edbd5..68b39927ecda 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1646,6 +1646,7 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock, ax25_address src; const unsigned char *mac = skb_mac_header(skb); + memset(sax, 0, sizeof(struct full_sockaddr_ax25)); ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL, &digi, NULL, NULL); sax->sax25_family = AF_AX25; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index b9af14e8a9ee..31c4543619fc 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -278,6 +278,8 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags & (MSG_OOB)) return -EOPNOTSUPP; + msg->msg_namelen = 0; + skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) @@ -285,8 +287,6 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, return err; } - msg->msg_namelen = 0; - copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index a1365e065799..ffa8b0a7705e 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1136,11 +1136,15 @@ EXPORT_SYMBOL(hci_free_dev); static void hci_power_on(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, power_on); + int err; BT_DBG("%s", hdev->name); - if (hci_dev_open(hdev->id) < 0) + err = hci_dev_open(hdev->id); + if (err < 0) { + mgmt_set_powered_failed(hdev, err); return; + } if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) schedule_delayed_work(&hdev->power_off, diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index e49f200c68e5..09c7eb1fa02b 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1880,6 +1880,9 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, BT_DBG("conn %p, code 0x%2.2x, ident 0x%2.2x, len %d", conn, code, ident, dlen); + if (conn->mtu < L2CAP_HDR_SIZE + L2CAP_CMD_HDR_SIZE) + return NULL; + len = L2CAP_HDR_SIZE + L2CAP_CMD_HDR_SIZE + dlen; count = min_t(unsigned int, conn->mtu, len); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 00879b8215e7..bd227e6a85a6 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2833,6 +2833,27 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered) return err; } +int mgmt_set_powered_failed(struct hci_dev *hdev, int err) +{ + struct pending_cmd *cmd; + u8 status; + + cmd = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev); + if (!cmd) + return -ENOENT; + + if (err == -ERFKILL) + status = MGMT_STATUS_RFKILLED; + else + status = MGMT_STATUS_FAILED; + + err = cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_POWERED, status); + + mgmt_pending_remove(cmd); + + return err; +} + int mgmt_discoverable(struct hci_dev *hdev, u8 discoverable) { struct cmd_lookup match = { NULL, hdev }; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 8d1edd7207df..c79db7f7533b 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -628,6 +628,7 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { rfcomm_dlc_accept(d); + msg->msg_namelen = 0; return 0; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 458cec074114..4f4eb6c2ff41 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -381,6 +381,7 @@ static void __sco_sock_close(struct sock *sk) sco_chan_del(sk, ECONNRESET); break; + case BT_CONNECT2: case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 27ca25ed7021..9069071b68b4 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -467,8 +467,9 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, skb_set_transport_header(skb, skb->len); mldq = (struct mld_msg *) icmp6_hdr(skb); - interval = ipv6_addr_any(group) ? br->multicast_last_member_interval : - br->multicast_query_response_interval; + interval = ipv6_addr_any(group) ? + br->multicast_query_response_interval : + br->multicast_last_member_interval; mldq->mld_type = ICMPV6_MGM_QUERY; mldq->mld_code = 0; diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 58de2a0f9975..c83ee7915fb0 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -107,7 +107,7 @@ static void br_tcn_timer_expired(unsigned long arg) br_debug(br, "tcn timer expired\n"); spin_lock(&br->lock); - if (br->dev->flags & IFF_UP) { + if (!br_is_root_bridge(br) && (br->dev->flags & IFF_UP)) { br_transmit_tcn(br); mod_timer(&br->tcn_timer,jiffies + br->bridge_hello_time); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 5016fa57b623..24a68861881c 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -287,6 +287,8 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock, if (m->msg_flags&MSG_OOB) goto read_error; + m->msg_namelen = 0; + skb = skb_recv_datagram(sk, flags, 0 , &ret); if (!skb) goto read_error; diff --git a/net/can/gw.c b/net/can/gw.c index 3d79b127881e..f78f8985e082 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -436,7 +436,7 @@ static int cgw_notifier(struct notifier_block *nb, if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); } } } @@ -850,7 +850,7 @@ static void cgw_remove_all_jobs(void) hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); } } @@ -903,7 +903,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); err = 0; break; } diff --git a/net/ceph/auth.c b/net/ceph/auth.c index b4bf4ac090f1..6b923bcaa2a4 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -47,6 +47,7 @@ struct ceph_auth_client *ceph_auth_init(const char *name, const struct ceph_cryp if (!ac) goto out; + mutex_init(&ac->mutex); ac->negotiating = true; if (name) ac->name = name; @@ -73,10 +74,12 @@ void ceph_auth_destroy(struct ceph_auth_client *ac) */ void ceph_auth_reset(struct ceph_auth_client *ac) { + mutex_lock(&ac->mutex); dout("auth_reset %p\n", ac); if (ac->ops && !ac->negotiating) ac->ops->reset(ac); ac->negotiating = true; + mutex_unlock(&ac->mutex); } int ceph_entity_name_encode(const char *name, void **p, void *end) @@ -102,6 +105,7 @@ int ceph_auth_build_hello(struct ceph_auth_client *ac, void *buf, size_t len) int i, num; int ret; + mutex_lock(&ac->mutex); dout("auth_build_hello\n"); monhdr->have_version = 0; monhdr->session_mon = cpu_to_le16(-1); @@ -122,15 +126,19 @@ int ceph_auth_build_hello(struct ceph_auth_client *ac, void *buf, size_t len) ret = ceph_entity_name_encode(ac->name, &p, end); if (ret < 0) - return ret; + goto out; ceph_decode_need(&p, end, sizeof(u64), bad); ceph_encode_64(&p, ac->global_id); ceph_encode_32(&lenp, p - lenp - sizeof(u32)); - return p - buf; + ret = p - buf; +out: + mutex_unlock(&ac->mutex); + return ret; bad: - return -ERANGE; + ret = -ERANGE; + goto out; } static int ceph_build_auth_request(struct ceph_auth_client *ac, @@ -151,11 +159,13 @@ static int ceph_build_auth_request(struct ceph_auth_client *ac, if (ret < 0) { pr_err("error %d building auth method %s request\n", ret, ac->ops->name); - return ret; + goto out; } dout(" built request %d bytes\n", ret); ceph_encode_32(&p, ret); - return p + ret - msg_buf; + ret = p + ret - msg_buf; +out: + return ret; } /* @@ -176,6 +186,7 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac, int result_msg_len; int ret = -EINVAL; + mutex_lock(&ac->mutex); dout("handle_auth_reply %p %p\n", p, end); ceph_decode_need(&p, end, sizeof(u32) * 3 + sizeof(u64), bad); protocol = ceph_decode_32(&p); @@ -227,33 +238,103 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac, ret = ac->ops->handle_reply(ac, result, payload, payload_end); if (ret == -EAGAIN) { - return ceph_build_auth_request(ac, reply_buf, reply_len); + ret = ceph_build_auth_request(ac, reply_buf, reply_len); } else if (ret) { pr_err("auth method '%s' error %d\n", ac->ops->name, ret); - return ret; } - return 0; -bad: - pr_err("failed to decode auth msg\n"); out: + mutex_unlock(&ac->mutex); return ret; + +bad: + pr_err("failed to decode auth msg\n"); + ret = -EINVAL; + goto out; } int ceph_build_auth(struct ceph_auth_client *ac, void *msg_buf, size_t msg_len) { + int ret = 0; + + mutex_lock(&ac->mutex); if (!ac->protocol) - return ceph_auth_build_hello(ac, msg_buf, msg_len); - BUG_ON(!ac->ops); - if (ac->ops->should_authenticate(ac)) - return ceph_build_auth_request(ac, msg_buf, msg_len); - return 0; + ret = ceph_auth_build_hello(ac, msg_buf, msg_len); + else if (ac->ops->should_authenticate(ac)) + ret = ceph_build_auth_request(ac, msg_buf, msg_len); + mutex_unlock(&ac->mutex); + return ret; } int ceph_auth_is_authenticated(struct ceph_auth_client *ac) { - if (!ac->ops) - return 0; - return ac->ops->is_authenticated(ac); + int ret = 0; + + mutex_lock(&ac->mutex); + if (ac->ops) + ret = ac->ops->is_authenticated(ac); + mutex_unlock(&ac->mutex); + return ret; +} +EXPORT_SYMBOL(ceph_auth_is_authenticated); + +int ceph_auth_create_authorizer(struct ceph_auth_client *ac, + int peer_type, + struct ceph_auth_handshake *auth) +{ + int ret = 0; + + mutex_lock(&ac->mutex); + if (ac->ops && ac->ops->create_authorizer) + ret = ac->ops->create_authorizer(ac, peer_type, auth); + mutex_unlock(&ac->mutex); + return ret; +} +EXPORT_SYMBOL(ceph_auth_create_authorizer); + +void ceph_auth_destroy_authorizer(struct ceph_auth_client *ac, + struct ceph_authorizer *a) +{ + mutex_lock(&ac->mutex); + if (ac->ops && ac->ops->destroy_authorizer) + ac->ops->destroy_authorizer(ac, a); + mutex_unlock(&ac->mutex); +} +EXPORT_SYMBOL(ceph_auth_destroy_authorizer); + +int ceph_auth_update_authorizer(struct ceph_auth_client *ac, + int peer_type, + struct ceph_auth_handshake *a) +{ + int ret = 0; + + mutex_lock(&ac->mutex); + if (ac->ops && ac->ops->update_authorizer) + ret = ac->ops->update_authorizer(ac, peer_type, a); + mutex_unlock(&ac->mutex); + return ret; +} +EXPORT_SYMBOL(ceph_auth_update_authorizer); + +int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac, + struct ceph_authorizer *a, size_t len) +{ + int ret = 0; + + mutex_lock(&ac->mutex); + if (ac->ops && ac->ops->verify_authorizer_reply) + ret = ac->ops->verify_authorizer_reply(ac, a, len); + mutex_unlock(&ac->mutex); + return ret; +} +EXPORT_SYMBOL(ceph_auth_verify_authorizer_reply); + +void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac, int peer_type) +{ + mutex_lock(&ac->mutex); + if (ac->ops && ac->ops->invalidate_authorizer) + ac->ops->invalidate_authorizer(ac, peer_type); + mutex_unlock(&ac->mutex); } +EXPORT_SYMBOL(ceph_auth_invalidate_authorizer); diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c index 925ca583c09c..8c93fa8d81bc 100644 --- a/net/ceph/auth_none.c +++ b/net/ceph/auth_none.c @@ -39,6 +39,11 @@ static int should_authenticate(struct ceph_auth_client *ac) return xi->starting; } +static int build_request(struct ceph_auth_client *ac, void *buf, void *end) +{ + return 0; +} + /* * the generic auth code decode the global_id, and we carry no actual * authenticate state, so nothing happens here. @@ -106,6 +111,7 @@ static const struct ceph_auth_client_ops ceph_auth_none_ops = { .destroy = destroy, .is_authenticated = is_authenticated, .should_authenticate = should_authenticate, + .build_request = build_request, .handle_reply = handle_reply, .create_authorizer = ceph_auth_none_create_authorizer, .destroy_authorizer = ceph_auth_none_destroy_authorizer, diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index a16bf14eb027..96238ba95f2b 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -298,6 +298,7 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, return -ENOMEM; } au->service = th->service; + au->secret_id = th->secret_id; msg_a = au->buf->vec.iov_base; msg_a->struct_v = 1; @@ -555,6 +556,26 @@ static int ceph_x_create_authorizer( return 0; } +static int ceph_x_update_authorizer( + struct ceph_auth_client *ac, int peer_type, + struct ceph_auth_handshake *auth) +{ + struct ceph_x_authorizer *au; + struct ceph_x_ticket_handler *th; + + th = get_ticket_handler(ac, peer_type); + if (IS_ERR(th)) + return PTR_ERR(th); + + au = (struct ceph_x_authorizer *)auth->authorizer; + if (au->secret_id < th->secret_id) { + dout("ceph_x_update_authorizer service %u secret %llu < %llu\n", + au->service, au->secret_id, th->secret_id); + return ceph_x_build_authorizer(ac, th, au); + } + return 0; +} + static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, struct ceph_authorizer *a, size_t len) { @@ -630,7 +651,7 @@ static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac, th = get_ticket_handler(ac, peer_type); if (!IS_ERR(th)) - remove_ticket_handler(ac, th); + memset(&th->validity, 0, sizeof(th->validity)); } @@ -641,6 +662,7 @@ static const struct ceph_auth_client_ops ceph_x_ops = { .build_request = ceph_x_build_request, .handle_reply = ceph_x_handle_reply, .create_authorizer = ceph_x_create_authorizer, + .update_authorizer = ceph_x_update_authorizer, .verify_authorizer_reply = ceph_x_verify_authorizer_reply, .destroy_authorizer = ceph_x_destroy_authorizer, .invalidate_authorizer = ceph_x_invalidate_authorizer, diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h index e02da7a5c5a1..5c2ad4e12c51 100644 --- a/net/ceph/auth_x.h +++ b/net/ceph/auth_x.h @@ -29,6 +29,7 @@ struct ceph_x_authorizer { struct ceph_buffer *buf; unsigned service; u64 nonce; + u64 secret_id; char reply_buf[128]; /* big enough for encrypted blob */ }; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index ba1037ceb496..7f703ae081c7 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1542,7 +1542,6 @@ static int process_connect(struct ceph_connection *con) con->error_msg = "connect authorization failure"; return -1; } - con->auth_retry = 1; con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) @@ -1627,7 +1626,7 @@ static int process_connect(struct ceph_connection *con) WARN_ON(con->state != CON_STATE_NEGOTIATING); con->state = CON_STATE_OPEN; - + con->auth_retry = 0; /* we authenticated; clear flag */ con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq); con->connect_seq++; con->peer_features = server_feat; diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 89a6409b4e1d..6765da36f78f 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -737,7 +737,7 @@ static void delayed_work(struct work_struct *work) __validate_auth(monc); - if (monc->auth->ops->is_authenticated(monc->auth)) + if (ceph_auth_is_authenticated(monc->auth)) __send_subscribe(monc); } __schedule_delayed(monc); @@ -893,8 +893,7 @@ static void handle_auth_reply(struct ceph_mon_client *monc, mutex_lock(&monc->mutex); had_debugfs_info = have_debugfs_info(monc); - if (monc->auth->ops) - was_auth = monc->auth->ops->is_authenticated(monc->auth); + 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, @@ -905,7 +904,7 @@ static void handle_auth_reply(struct ceph_mon_client *monc, wake_up_all(&monc->client->auth_wq); } else if (ret > 0) { __send_prepared_auth_request(monc, ret); - } else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) { + } else if (!was_auth && ceph_auth_is_authenticated(monc->auth)) { dout("authenticated, starting session\n"); monc->client->msgr.inst.name.type = CEPH_ENTITY_TYPE_CLIENT; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b16dfa25e750..8e3aa4dc5bec 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -671,8 +671,7 @@ static void put_osd(struct ceph_osd *osd) if (atomic_dec_and_test(&osd->o_ref) && osd->o_auth.authorizer) { struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth; - if (ac->ops && ac->ops->destroy_authorizer) - ac->ops->destroy_authorizer(ac, osd->o_auth.authorizer); + ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer); kfree(osd); } } @@ -1337,13 +1336,13 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) __register_request(osdc, req); __unregister_linger_request(osdc, req); } + reset_changed_osds(osdc); mutex_unlock(&osdc->request_mutex); if (needmap) { dout("%d requests for down osds, need new map\n", needmap); ceph_monc_request_next_osdmap(&osdc->client->monc); } - reset_changed_osds(osdc); } @@ -2127,13 +2126,17 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, struct ceph_auth_handshake *auth = &o->o_auth; if (force_new && auth->authorizer) { - if (ac->ops && ac->ops->destroy_authorizer) - ac->ops->destroy_authorizer(ac, auth->authorizer); + ceph_auth_destroy_authorizer(ac, auth->authorizer); auth->authorizer = NULL; } - if (!auth->authorizer && ac->ops && ac->ops->create_authorizer) { - int ret = ac->ops->create_authorizer(ac, CEPH_ENTITY_TYPE_OSD, - auth); + if (!auth->authorizer) { + int ret = ceph_auth_create_authorizer(ac, CEPH_ENTITY_TYPE_OSD, + auth); + if (ret) + return ERR_PTR(ret); + } else { + int ret = ceph_auth_update_authorizer(ac, CEPH_ENTITY_TYPE_OSD, + auth); if (ret) return ERR_PTR(ret); } @@ -2149,11 +2152,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len) struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; - /* - * XXX If ac->ops or ac->ops->verify_authorizer_reply is null, - * XXX which do we do: succeed or fail? - */ - return ac->ops->verify_authorizer_reply(ac, o->o_auth.authorizer, len); + return ceph_auth_verify_authorizer_reply(ac, o->o_auth.authorizer, len); } static int invalidate_authorizer(struct ceph_connection *con) @@ -2162,9 +2161,7 @@ static int invalidate_authorizer(struct ceph_connection *con) struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; - if (ac->ops && ac->ops->invalidate_authorizer) - ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD); - + ceph_auth_invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD); return ceph_monc_validate_auth(&osdc->client->monc); } diff --git a/net/compat.c b/net/compat.c index ae6d67ad03b3..014e1c78ecc5 100644 --- a/net/compat.c +++ b/net/compat.c @@ -743,19 +743,25 @@ static unsigned char nas[21] = { asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags) { - return sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags) { + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { - return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len, unsigned flags) @@ -777,6 +783,9 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, int datagrams; struct timespec ktspec; + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + if (COMPAT_USE_64BIT_TIME) return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, diff --git a/net/core/dev.c b/net/core/dev.c index eb858dc6ab86..7db83d64e4f7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1482,7 +1482,6 @@ void net_enable_timestamp(void) return; } #endif - WARN_ON(in_interrupt()); static_key_slow_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); @@ -1629,6 +1628,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb->mark = 0; secpath_reset(skb); nf_reset(skb); + nf_reset_trace(skb); return netif_rx(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -1895,6 +1895,9 @@ static void skb_warn_bad_offload(const struct sk_buff *skb) struct net_device *dev = skb->dev; const char *driver = ""; + if (!net_ratelimit()) + return; + if (dev && dev->dev.parent) driver = dev_driver_string(dev->dev.parent); @@ -2167,7 +2170,7 @@ EXPORT_SYMBOL(netif_skb_features); * support DMA from it. */ static inline int skb_needs_linearize(struct sk_buff *skb, - int features) + netdev_features_t features) { return skb_is_nonlinear(skb) && ((skb_has_frag_list(skb) && @@ -3125,6 +3128,7 @@ int netdev_rx_handler_register(struct net_device *dev, if (dev->rx_handler) return -EBUSY; + /* Note: rx_handler_data must be set before rx_handler */ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); rcu_assign_pointer(dev->rx_handler, rx_handler); @@ -3145,6 +3149,11 @@ void netdev_rx_handler_unregister(struct net_device *dev) ASSERT_RTNL(); RCU_INIT_POINTER(dev->rx_handler, NULL); + /* a reader seeing a non NULL rx_handler in a rcu_read_lock() + * section has a guarantee to see a non NULL rx_handler_data + * as well. + */ + synchronize_net(); RCU_INIT_POINTER(dev->rx_handler_data, NULL); } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); @@ -3230,6 +3239,7 @@ ncls: } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: + ret = NET_RX_SUCCESS; goto out; case RX_HANDLER_ANOTHER: goto another_round; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 76f6d0b02f28..0346e5901902 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -57,7 +57,7 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, ha->type = addr_type; ha->refcount = 1; ha->global_use = global; - ha->synced = false; + ha->synced = 0; list_add_tail_rcu(&ha->list, &list->list); list->count++; return 0; @@ -155,7 +155,7 @@ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, addr_len, ha->type); if (err) break; - ha->synced = true; + ha->synced++; ha->refcount++; } else if (ha->refcount == 1) { __hw_addr_del(to_list, ha->addr, addr_len, ha->type); @@ -176,7 +176,7 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, if (ha->synced) { __hw_addr_del(to_list, ha->addr, addr_len, ha->type); - ha->synced = false; + ha->synced--; __hw_addr_del(from_list, ha->addr, addr_len, ha->type); } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 6d6d7d25caaa..7becb3f9ef65 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1286,7 +1286,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) void __user *useraddr = ifr->ifr_data; u32 ethcmd; int rc; - u32 old_features; + netdev_features_t old_features; if (!dev || !netif_device_present(dev)) return -ENODEV; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ac88107d1bc9..69b7ca35c461 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -237,7 +237,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) we must kill timers etc. and move it to safe state. */ - skb_queue_purge(&n->arp_queue); + __skb_queue_purge(&n->arp_queue); n->arp_queue_len_bytes = 0; n->output = neigh_blackhole; if (n->nud_state & NUD_VALID) @@ -300,7 +300,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device if (!n) goto out_entries; - skb_queue_head_init(&n->arp_queue); + __skb_queue_head_init(&n->arp_queue); rwlock_init(&n->lock); seqlock_init(&n->ha_lock); n->updated = n->used = now; @@ -721,7 +721,9 @@ void neigh_destroy(struct neighbour *neigh) if (neigh_del_timer(neigh)) printk(KERN_WARNING "Impossible event.\n"); - skb_queue_purge(&neigh->arp_queue); + write_lock_bh(&neigh->lock); + __skb_queue_purge(&neigh->arp_queue); + write_unlock_bh(&neigh->lock); neigh->arp_queue_len_bytes = 0; if (dev->netdev_ops->ndo_neigh_destroy) @@ -867,7 +869,7 @@ static void neigh_invalidate(struct neighbour *neigh) neigh->ops->error_report(neigh, skb); write_lock(&neigh->lock); } - skb_queue_purge(&neigh->arp_queue); + __skb_queue_purge(&neigh->arp_queue); neigh->arp_queue_len_bytes = 0; } @@ -1206,7 +1208,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, write_lock_bh(&neigh->lock); } - skb_queue_purge(&neigh->arp_queue); + __skb_queue_purge(&neigh->arp_queue); neigh->arp_queue_len_bytes = 0; } out: diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 900fc6162c42..a1334275a7da 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -975,6 +975,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, * report anything. */ ivi.spoofchk = -1; + memset(ivi.mac, 0, sizeof(ivi.mac)); if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) break; vf_mac.vf = @@ -1065,7 +1066,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; - if (nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) @@ -1909,7 +1910,7 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) u32 ext_filter_mask = 0; u16 min_ifinfo_dump_size = 0; - if (nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@ -2049,7 +2050,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len); while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; + unsigned int flavor = attr->rta_type & NLA_TYPE_MASK; if (flavor) { if (flavor > rta_max[sz_idx]) return -EINVAL; diff --git a/net/core/sock.c b/net/core/sock.c index 4b469e367923..561eb57f590c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -815,15 +815,20 @@ EXPORT_SYMBOL(sock_setsockopt); void cred_to_ucred(struct pid *pid, const struct cred *cred, - struct ucred *ucred) + struct ucred *ucred, bool use_effective) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; if (cred) { struct user_namespace *current_ns = current_user_ns(); - ucred->uid = user_ns_map_uid(current_ns, cred, cred->euid); - ucred->gid = user_ns_map_gid(current_ns, cred, cred->egid); + if (use_effective) { + ucred->uid = user_ns_map_uid(current_ns, cred, cred->euid); + ucred->gid = user_ns_map_gid(current_ns, cred, cred->egid); + } else { + ucred->uid = user_ns_map_uid(current_ns, cred, cred->uid); + ucred->gid = user_ns_map_gid(current_ns, cred, cred->gid); + } } } EXPORT_SYMBOL_GPL(cred_to_ucred); @@ -984,7 +989,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); - cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, + &peercred, true); if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; @@ -1087,18 +1093,6 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) #endif } -/* - * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes - * un-modified. Special care is taken when initializing object to zero. - */ -static inline void sk_prot_clear_nulls(struct sock *sk, int size) -{ - if (offsetof(struct sock, sk_node.next) != 0) - memset(sk, 0, offsetof(struct sock, sk_node.next)); - memset(&sk->sk_node.pprev, 0, - size - offsetof(struct sock, sk_node.pprev)); -} - void sk_prot_clear_portaddr_nulls(struct sock *sk, int size) { unsigned long nulls1, nulls2; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index d86053002c16..2f9517ddb605 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -336,6 +336,7 @@ static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlattr **tb, dcb->dcb_family = AF_UNSPEC; dcb->cmd = DCB_CMD_GPERM_HWADDR; + memset(perm_addr, 0, sizeof(perm_addr)); netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr); ret = nla_put(dcbnl_skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), @@ -1238,6 +1239,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_getets) { struct ieee_ets ets; + memset(&ets, 0, sizeof(ets)); err = ops->ieee_getets(netdev, &ets); if (!err) NLA_PUT(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets); @@ -1245,6 +1247,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_getpfc) { struct ieee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_getpfc(netdev, &pfc); if (!err) NLA_PUT(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc); @@ -1277,6 +1280,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) /* get peer info if available */ if (ops->ieee_peer_getets) { struct ieee_ets ets; + memset(&ets, 0, sizeof(ets)); err = ops->ieee_peer_getets(netdev, &ets); if (!err) NLA_PUT(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets); @@ -1284,6 +1288,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_peer_getpfc) { struct ieee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_peer_getpfc(netdev, &pfc); if (!err) NLA_PUT(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc); @@ -1463,6 +1468,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) /* peer info if available */ if (ops->cee_peer_getpg) { struct cee_pg pg; + memset(&pg, 0, sizeof(pg)); err = ops->cee_peer_getpg(netdev, &pg); if (!err) NLA_PUT(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg); @@ -1470,6 +1476,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->cee_peer_getpfc) { struct cee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); err = ops->cee_peer_getpfc(netdev, &pfc); if (!err) NLA_PUT(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc); diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h index aeff3f310482..60b5ef5f64d9 100644 --- a/net/ieee802154/6lowpan.h +++ b/net/ieee802154/6lowpan.h @@ -87,7 +87,7 @@ (memcmp(addr1, addr2, length >> 3) == 0) /* local link, i.e. FE80::/10 */ -#define is_addr_link_local(a) (((a)->s6_addr16[0]) == 0x80FE) +#define is_addr_link_local(a) (((a)->s6_addr16[0]) == htons(0xFE80)) /* * check whether we can compress the IID to 16 bits, diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index cb982a61536f..e814e2a9fa65 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -139,8 +139,6 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) /* skb is pure payload to encrypt */ - err = -ENOMEM; - esp = x->data; aead = esp->aead; alen = crypto_aead_authsize(aead); @@ -176,8 +174,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) } tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); - if (!tmp) + if (!tmp) { + err = -ENOMEM; goto error; + } seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 5ff2a51b6d0c..210b7102cc4f 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -21,6 +21,7 @@ #include <linux/rtnetlink.h> #include <linux/slab.h> +#include <net/sock.h> #include <net/inet_frag.h> static void inet_frag_secret_rebuild(unsigned long dummy) @@ -271,6 +272,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, { struct inet_frag_queue *q; struct hlist_node *n; + int depth = 0; hlist_for_each_entry(q, n, &f->hash[hash], list) { if (q->net == nf && f->match(q, key)) { @@ -278,9 +280,25 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, read_unlock(&f->lock); return q; } + depth++; } read_unlock(&f->lock); - return inet_frag_create(nf, f, key); + if (depth <= INETFRAGS_MAXDEPTH) + return inet_frag_create(nf, f, key); + else + return ERR_PTR(-ENOBUFS); } EXPORT_SYMBOL(inet_frag_find); + +void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q, + const char *prefix) +{ + static const char msg[] = "inet_frag_find: Fragment hash bucket" + " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH) + ". Dropping fragment.\n"; + + if (PTR_ERR(q) == -ENOBUFS) + LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg); +} +EXPORT_SYMBOL(inet_frag_maybe_warn_overflow); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b7bf6e30adbc..4a40457d8d14 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -251,8 +251,7 @@ static void ip_expire(unsigned long arg) if (!head->dev) goto out_rcu_unlock; - /* skb dst is stale, drop it, and perform route lookup again */ - skb_dst_drop(head); + /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); err = ip_route_input_noref(head, iph->daddr, iph->saddr, iph->tos, head->dev); @@ -295,14 +294,11 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash); - if (q == NULL) - goto out_nomem; - + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } return container_of(q, struct ipq, q); - -out_nomem: - LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n")); - return NULL; } /* Is the fragment too far ahead to be part of ipq? */ @@ -520,8 +516,16 @@ found: qp->q.last_in |= INET_FRAG_FIRST_IN; if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - qp->q.meat == qp->q.len) - return ip_frag_reasm(qp, prev, dev); + qp->q.meat == qp->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + err = ip_frag_reasm(qp, prev, dev); + skb->_skb_refdst = orefdst; + return err; + } + + skb_dst_drop(skb); write_lock(&ip4_frags.lock); list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index b57532d4742c..a16509cba75d 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -722,6 +722,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev tiph = &tunnel->parms.iph; } + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); if ((dst = tiph->daddr) == 0) { /* NBMA tunnel */ @@ -865,7 +866,6 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev skb_reset_transport_header(skb); skb_push(skb, gre_hlen); skb_reset_network_header(skb); - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_drop(skb); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index a0d0d9d9b870..b69a3700642b 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -360,7 +360,6 @@ int ip_options_compile(struct net *net, } switch (optptr[3]&0xF) { case IPOPT_TS_TSONLY: - opt->ts = optptr - iph; if (skb) timeptr = &optptr[optptr[2]-1]; opt->ts_needtime = 1; @@ -371,7 +370,6 @@ int ip_options_compile(struct net *net, pp_ptr = optptr + 2; goto error; } - opt->ts = optptr - iph; if (rt) { memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4); timeptr = &optptr[optptr[2]+3]; @@ -385,7 +383,6 @@ int ip_options_compile(struct net *net, pp_ptr = optptr + 2; goto error; } - opt->ts = optptr - iph; { __be32 addr; memcpy(&addr, &optptr[optptr[2]-1], 4); @@ -418,12 +415,12 @@ int ip_options_compile(struct net *net, pp_ptr = optptr + 3; goto error; } - opt->ts = optptr - iph; if (skb) { optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4); opt->is_changed = 1; } } + opt->ts = optptr - iph; break; case IPOPT_RA: if (optlen < 4) { diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index ae1413e3f2f8..d2f634880bdd 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -448,6 +448,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (tos & 1) tos = old_iph->tos; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); if (!dst) { /* NBMA tunnel */ if ((rt = skb_rtable(skb)) == NULL) { @@ -530,7 +531,6 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb->transport_header = skb->network_header; skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_drop(skb); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index eab2a7fb15d1..550aa2a9d323 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -347,8 +347,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), - RT_SCOPE_UNIVERSE, IPPROTO_TCP, + flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark, + RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, ireq->loc_addr, th->source, th->dest); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index bf7a604c695c..086c97327b9b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -34,6 +34,8 @@ static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; static int ip_ttl_min = 1; static int ip_ttl_max = 255; +static int tcp_syn_retries_min = 1; +static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; @@ -276,7 +278,9 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_syn_retries, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_syn_retries_min, + .extra2 = &tcp_syn_retries_max }, { .procname = "tcp_synack_retries", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8429ac5eb914..b91152394991 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -708,7 +708,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) * Make sure that we have exactly size bytes * available to the caller, no more, no less. */ - skb->avail_size = size; + skb->reserved_tailroom = skb->end - skb->tail - size; return skb; } __kfree_skb(skb); @@ -3070,8 +3070,11 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, for (i = 0; i < shi->nr_frags; ++i) { const struct skb_frag_struct *f = &shi->frags[i]; - struct page *page = skb_frag_page(f); - sg_set_page(&sg, page, skb_frag_size(f), f->page_offset); + unsigned int offset = f->page_offset; + struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT); + + sg_set_page(&sg, page, skb_frag_size(f), + offset_in_page(offset)); if (crypto_hash_update(desc, &sg, skb_frag_size(f))) return 1; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b40e05b9c451..43409e431475 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -116,6 +116,7 @@ int sysctl_tcp_abc __read_mostly; #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ #define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ +#define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ #define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) @@ -2260,11 +2261,8 @@ void tcp_enter_loss(struct sock *sk, int how) if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); - if (!how) { - /* Push undo marker, if it was plain RTO and nothing - * was retransmitted. */ - tp->undo_marker = tp->snd_una; - } else { + tp->undo_marker = tp->snd_una; + if (how) { tp->sacked_out = 0; tp->fackets_out = 0; } @@ -3040,8 +3038,8 @@ static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, * tcp_xmit_retransmit_queue(). */ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, - int prior_sacked, bool is_dupack, - int flag) + int prior_sacked, int prior_packets, + bool is_dupack, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -3107,7 +3105,8 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, tcp_add_reno_sack(sk); } else do_lost = tcp_try_undo_partial(sk, pkts_acked); - newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked; + newly_acked_sacked = prior_packets - tp->packets_out + + tp->sacked_out - prior_sacked; break; case TCP_CA_Loss: if (flag & FLAG_DATA_ACKED) @@ -3129,7 +3128,8 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, if (is_dupack) tcp_add_reno_sack(sk); } - newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked; + newly_acked_sacked = prior_packets - tp->packets_out + + tp->sacked_out - prior_sacked; if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); @@ -3710,6 +3710,27 @@ static void tcp_send_challenge_ack(struct sock *sk) } } +static void tcp_store_ts_recent(struct tcp_sock *tp) +{ + tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; + tp->rx_opt.ts_recent_stamp = get_seconds(); +} + +static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) +{ + if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { + /* PAWS bug workaround wrt. ACK frames, the PAWS discard + * extra check below makes sure this can only happen + * for pure ACK frames. -DaveM + * + * Not only, also it occurs for expired timestamps. + */ + + if (tcp_paws_check(&tp->rx_opt, 0)) + tcp_store_ts_recent(tp); + } +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@ -3721,9 +3742,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) bool is_dupack = false; u32 prior_in_flight; u32 prior_fackets; - int prior_packets; + int prior_packets = tp->packets_out; int prior_sacked = tp->sacked_out; int pkts_acked = 0; + int previous_packets_out = 0; int frto_cwnd = 0; /* If the ack is older than previous acks @@ -3759,6 +3781,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + if (flag & FLAG_UPDATE_TS_RECENT) + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) { /* Window is constant, pure forward advance. * No more checks are required. @@ -3794,14 +3822,14 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) sk->sk_err_soft = 0; icsk->icsk_probes_out = 0; tp->rcv_tstamp = tcp_time_stamp; - prior_packets = tp->packets_out; if (!prior_packets) goto no_queue; /* See if we can take anything off of the retransmit queue. */ + previous_packets_out = tp->packets_out; flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); - pkts_acked = prior_packets - tp->packets_out; + pkts_acked = previous_packets_out - tp->packets_out; if (tp->frto_counter) frto_cwnd = tcp_process_frto(sk, flag); @@ -3816,7 +3844,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_cong_avoid(sk, ack, prior_in_flight); is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, - is_dupack, flag); + prior_packets, is_dupack, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) tcp_cong_avoid(sk, ack, prior_in_flight); @@ -3831,7 +3859,7 @@ no_queue: /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, - is_dupack, flag); + prior_packets, is_dupack, flag); /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. @@ -3851,7 +3879,7 @@ old_ack: if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, - is_dupack, flag); + prior_packets, is_dupack, flag); } SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt); @@ -4056,27 +4084,6 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) EXPORT_SYMBOL(tcp_parse_md5sig_option); #endif -static inline void tcp_store_ts_recent(struct tcp_sock *tp) -{ - tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; - tp->rx_opt.ts_recent_stamp = get_seconds(); -} - -static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) -{ - if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { - /* PAWS bug workaround wrt. ACK frames, the PAWS discard - * extra check below makes sure this can only happen - * for pure ACK frames. -DaveM - * - * Not only, also it occurs for expired timestamps. - */ - - if (tcp_paws_check(&tp->rx_opt, 0)) - tcp_store_ts_recent(tp); - } -} - /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM * * It is not fatal. If this ACK does _not_ change critical state (seqs, window) @@ -5521,6 +5528,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tcp_checksum_complete_user(sk, skb)) goto csum_error; + if ((int)skb->truesize > sk->sk_forward_alloc) + goto step5; + /* Predicted packet is in window by definition. * seq == rcv_nxt and rcv_wup <= rcv_nxt. * Hence, check seq<=rcv_wup reduces to: @@ -5532,9 +5542,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_rcv_rtt_measure_ts(sk, skb); - if ((int)skb->truesize > sk->sk_forward_alloc) - goto step5; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ @@ -5582,14 +5589,10 @@ slow_path: return 0; step5: - if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) + if (th->ack && + tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0) goto discard; - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - tcp_rcv_rtt_measure_ts(sk, skb); /* Process urgent data. */ @@ -5953,7 +5956,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* step 5: check the ACK field */ if (th->ack) { - int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0; + int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT) > 0; switch (sk->sk_state) { case TCP_SYN_RECV: @@ -6060,11 +6064,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } else goto discard; - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - /* step 6: check the URG bit */ tcp_urg(sk, skb, th); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 76f50e1b53af..ae03b7b75af6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -974,7 +974,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; - key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET); + key = tcp_md5_do_lookup(sk, addr, family); if (key) { /* Pre-existing entry - just update that one. */ memcpy(key->key, newkey, newkeylen); @@ -1019,7 +1019,7 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) struct tcp_md5sig_key *key; struct tcp_md5sig_info *md5sig; - key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET); + key = tcp_md5_do_lookup(sk, addr, family); if (!key) return -ENOENT; hlist_del_rcu(&key->node); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2d27e1af9303..12999a3aaf95 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -835,11 +835,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, &md5); tcp_header_size = tcp_options_size + sizeof(struct tcphdr); - if (tcp_packets_in_flight(tp) == 0) { + if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); - skb->ooo_okay = 1; - } else - skb->ooo_okay = 0; + + /* if no packet is in qdisc/device queue, then allow XPS to select + * another queue. + */ + skb->ooo_okay = sk_wmem_alloc_get(sk) == 0; skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -1096,7 +1098,6 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) eat = min_t(int, len, skb_headlen(skb)); if (eat) { __skb_pull(skb, eat); - skb->avail_size -= eat; len -= eat; if (!len) return; @@ -1588,8 +1589,11 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) goto send_now; } - /* Ok, it looks like it is advisable to defer. */ - tp->tso_deferred = 1 | (jiffies << 1); + /* Ok, it looks like it is advisable to defer. + * Do not rearm the timer if already set to not break TCP ACK clocking. + */ + if (!tp->tso_deferred) + tp->tso_deferred = 1 | (jiffies << 1); return 1; @@ -2152,8 +2156,12 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) */ TCP_SKB_CB(skb)->when = tcp_time_stamp; - /* make sure skb->data is aligned on arches that require it */ - if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) { + /* make sure skb->data is aligned on arches that require it + * and check if ack-trimming & collapsing extended the headroom + * beyond what csum_start can cover. + */ + if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || + skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index fe141052a1be..0b6136d578f6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -768,7 +768,7 @@ send: /* * Push out all pending data as one UDP datagram. Socket is locked. */ -static int udp_push_pending_frames(struct sock *sk) +int udp_push_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); @@ -787,6 +787,7 @@ out: up->pending = 0; return err; } +EXPORT_SYMBOL(udp_push_pending_frames); int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 81e0ad2442c7..d427f1bae2e2 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1233,6 +1233,23 @@ try_nextdev: } EXPORT_SYMBOL(ipv6_dev_get_saddr); +int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, + unsigned char banned_flags) +{ + struct inet6_ifaddr *ifp; + int err = -EADDRNOTAVAIL; + + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ifp->scope == IFA_LINK && + !(ifp->flags & banned_flags)) { + *addr = ifp->addr; + err = 0; + break; + } + } + return err; +} + int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, unsigned char banned_flags) { @@ -1242,17 +1259,8 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - struct inet6_ifaddr *ifp; - read_lock_bh(&idev->lock); - list_for_each_entry(ifp, &idev->addr_list, if_list) { - if (ifp->scope == IFA_LINK && - !(ifp->flags & banned_flags)) { - *addr = ifp->addr; - err = 0; - break; - } - } + err = __ipv6_get_lladdr(idev, addr, banned_flags); read_unlock_bh(&idev->lock); } rcu_read_unlock(); @@ -2399,6 +2407,9 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) static void init_loopback(struct net_device *dev) { struct inet6_dev *idev; + struct net_device *sp_dev; + struct inet6_ifaddr *sp_ifa; + struct rt6_info *sp_rt; /* ::1 */ @@ -2410,6 +2421,35 @@ static void init_loopback(struct net_device *dev) } add_addr(idev, &in6addr_loopback, 128, IFA_HOST); + + /* Add routes to other interface's IPv6 addresses */ + for_each_netdev(dev_net(dev), sp_dev) { + if (!strcmp(sp_dev->name, dev->name)) + continue; + + idev = __in6_dev_get(sp_dev); + if (!idev) + continue; + + read_lock_bh(&idev->lock); + list_for_each_entry(sp_ifa, &idev->addr_list, if_list) { + + if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE)) + continue; + + if (sp_ifa->rt) + continue; + + sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0); + + /* Failure cases are ignored */ + if (!IS_ERR(sp_rt)) { + sp_ifa->rt = sp_rt; + ip6_ins_rt(sp_rt); + } + } + read_unlock_bh(&idev->lock); + } } static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr) @@ -4686,26 +4726,20 @@ static void addrconf_sysctl_unregister(struct inet6_dev *idev) static int __net_init addrconf_init_net(struct net *net) { - int err; + int err = -ENOMEM; struct ipv6_devconf *all, *dflt; - err = -ENOMEM; - all = &ipv6_devconf; - dflt = &ipv6_devconf_dflt; + all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL); + if (all == NULL) + goto err_alloc_all; - if (!net_eq(net, &init_net)) { - all = kmemdup(all, sizeof(ipv6_devconf), GFP_KERNEL); - if (all == NULL) - goto err_alloc_all; + dflt = kmemdup(&ipv6_devconf_dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); + if (dflt == NULL) + goto err_alloc_dflt; - dflt = kmemdup(dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); - if (dflt == NULL) - goto err_alloc_dflt; - } else { - /* these will be inherited by all namespaces */ - dflt->autoconf = ipv6_defaults.autoconf; - dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; - } + /* these will be inherited by all namespaces */ + dflt->autoconf = ipv6_defaults.autoconf; + dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; net->ipv6.devconf_all = all; net->ipv6.devconf_dflt = dflt; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 1ca5d45a12e8..37aceed4c06f 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -111,6 +111,27 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt ipv6_addr_loopback(&hdr->daddr)) goto err; + /* RFC4291 Errata ID: 3480 + * Interface-Local scope spans only a single interface on a + * node and is useful only for loopback transmission of + * multicast. Packets with interface-local scope received + * from another node must be discarded. + */ + if (!(skb->pkt_type == PACKET_LOOPBACK || + dev->flags & IFF_LOOPBACK) && + ipv6_addr_is_multicast(&hdr->daddr) && + IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1) + goto err; + + /* RFC4291 2.7 + * Nodes must not originate a packet to a multicast address whose scope + * field contains the reserved value 0; if such a packet is received, it + * must be silently dropped. + */ + if (ipv6_addr_is_multicast(&hdr->daddr) && + IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0) + goto err; + /* * RFC4291 2.7 * Multicast addresses must not be used as source addresses in IPv6 @@ -265,7 +286,8 @@ int ip6_mc_input(struct sk_buff *skb) * IPv6 multicast router mode is now supported ;) */ if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding && - !(ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&hdr->daddr) & + (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { /* * Okay, we try to forward - split and duplicate diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ce661baa60cb..d6b9d56b5ec3 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -912,11 +912,17 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, const struct flowi6 *fl6) { struct ipv6_pinfo *np = inet6_sk(sk); - struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_info *rt; if (!dst) goto out; + if (dst->ops->family != AF_INET6) { + dst_release(dst); + return NULL; + } + + rt = (struct rt6_info *)dst; /* Yes, checking route validity in not connected * case is not very simple. Take into account, * that we do not support routing by source, TOS, @@ -1181,11 +1187,12 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } -static void ip6_append_data_mtu(int *mtu, +static void ip6_append_data_mtu(unsigned int *mtu, int *maxfraglen, unsigned int fragheaderlen, struct sk_buff *skb, - struct rt6_info *rt) + struct rt6_info *rt, + bool pmtuprobe) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (skb == NULL) { @@ -1197,7 +1204,9 @@ static void ip6_append_data_mtu(int *mtu, * this fragment is not first, the headers * space is regarded as data space. */ - *mtu = dst_mtu(rt->dst.path); + *mtu = min(*mtu, pmtuprobe ? + rt->dst.dev->mtu : + dst_mtu(rt->dst.path)); } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); @@ -1214,11 +1223,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_cork *cork; struct sk_buff *skb, *skb_prev = NULL; - unsigned int maxfraglen, fragheaderlen; + unsigned int maxfraglen, fragheaderlen, mtu; int exthdrlen; int dst_exthdrlen; int hh_len; - int mtu; int copy; int err; int offset = 0; @@ -1236,7 +1244,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (WARN_ON(np->cork.opt)) return -EINVAL; - np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation); + np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation); if (unlikely(np->cork.opt == NULL)) return -ENOBUFS; @@ -1381,7 +1389,9 @@ alloc_new_skb: /* update mtu and maxfraglen if necessary */ if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, - fragheaderlen, skb, rt); + fragheaderlen, skb, rt, + np->pmtudisc == + IPV6_PMTUDISC_PROBE); skb_prev = skb; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 8110362e0af5..d5e4615e52c4 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -256,10 +256,12 @@ static void __net_exit ip6mr_rules_exit(struct net *net) { struct mr6_table *mrt, *next; + rtnl_lock(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { list_del(&mrt->list); ip6mr_free_table(mrt); } + rtnl_unlock(); fib_rules_unregister(net->ipv6.mr6_rules_ops); } #else @@ -286,7 +288,10 @@ static int __net_init ip6mr_rules_init(struct net *net) static void __net_exit ip6mr_rules_exit(struct net *net) { + rtnl_lock(); ip6mr_free_table(net->ipv6.mrt6); + net->ipv6.mrt6 = NULL; + rtnl_unlock(); } #endif diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index b2869cab2092..6a4ab24a5d65 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1334,8 +1334,9 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) return scount; } -static struct sk_buff *mld_newpack(struct net_device *dev, int size) +static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size) { + struct net_device *dev = idev->dev; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.igmp_sk; struct sk_buff *skb; @@ -1360,7 +1361,7 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) skb_reserve(skb, hlen); - if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { + if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. @@ -1456,7 +1457,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, struct mld2_grec *pgr; if (!skb) - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(pmc->idev, dev->mtu); if (!skb) return NULL; pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec)); @@ -1476,7 +1477,8 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) { - struct net_device *dev = pmc->idev->dev; + struct inet6_dev *idev = pmc->idev; + struct net_device *dev = idev->dev; struct mld2_report *pmr; struct mld2_grec *pgr = NULL; struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list; @@ -1505,7 +1507,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(idev, dev->mtu); } } first = 1; @@ -1532,7 +1534,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(idev, dev->mtu); first = 1; scount = 0; } @@ -1587,8 +1589,8 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) struct sk_buff *skb = NULL; int type; + read_lock_bh(&idev->lock); if (!pmc) { - read_lock_bh(&idev->lock); for (pmc=idev->mc_list; pmc; pmc=pmc->next) { if (pmc->mca_flags & MAF_NOREPORT) continue; @@ -1600,7 +1602,6 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->mca_lock); } - read_unlock_bh(&idev->lock); } else { spin_lock_bh(&pmc->mca_lock); if (pmc->mca_sfcount[MCAST_EXCLUDE]) @@ -1610,6 +1611,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->mca_lock); } + read_unlock_bh(&idev->lock); if (skb) mld_sendpack(skb); } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 38f00b0298d3..52e2f65ff3a3 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -14,6 +14,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "IPv6-nf: " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> @@ -176,13 +178,12 @@ fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst) q = inet_frag_find(&nf_init_frags, &nf_frags, &arg, hash); local_bh_enable(); - if (q == NULL) - goto oom; + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } return container_of(q, struct nf_ct_frag6_queue, q); - -oom: - return NULL; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 9447bd69873a..6bda7aa551b8 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -26,6 +26,9 @@ * YOSHIFUJI,H. @USAGI Always remove fragment header to * calculate ICV correctly. */ + +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> @@ -240,9 +243,10 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6 hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd); q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); - if (q == NULL) + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); return NULL; - + } return container_of(q, struct frag_queue, q); } @@ -381,8 +385,17 @@ found: } if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len) - return ip6_frag_reasm(fq, prev, dev); + fq->q.meat == fq->q.len) { + int res; + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + res = ip6_frag_reasm(fq, prev, dev); + skb->_skb_refdst = orefdst; + return res; + } + + skb_dst_drop(skb); write_lock(&ip6_frags.lock); list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 493490f052a0..016ed7c22fc9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1032,10 +1032,13 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { - if (rt->rt6i_flags & RTF_CACHE) - rt6_update_expires(rt, 0); - else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) + if (rt->rt6i_flags & RTF_CACHE) { + dst_hold(&rt->dst); + if (ip6_del_rt(rt)) + dst_free(&rt->dst); + } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; + } } } @@ -1973,7 +1976,8 @@ void rt6_purge_dflt_routers(struct net *net) restart: read_lock_bh(&table->tb6_lock); for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { + if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && + (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); ip6_del_rt(rt); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3889e0204183..7ee712167732 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2079,6 +2079,17 @@ void tcp6_proc_exit(struct net *net) } #endif +static void tcp_v6_clear_sk(struct sock *sk, int size) +{ + struct inet_sock *inet = inet_sk(sk); + + /* we do not want to clear pinet6 field, because of RCU lookups */ + sk_prot_clear_nulls(sk, offsetof(struct inet_sock, pinet6)); + + size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6); + memset(&inet->pinet6 + 1, 0, size); +} + struct proto tcpv6_prot = { .name = "TCPv6", .owner = THIS_MODULE, @@ -2120,6 +2131,7 @@ struct proto tcpv6_prot = { #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM .proto_cgroup = tcp_proto_cgroup, #endif + .clear_sk = tcp_v6_clear_sk, }; static const struct inet6_protocol tcpv6_protocol = { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 37b0699e95e5..f79bfdbc247f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -895,11 +895,16 @@ static int udp_v6_push_pending_frames(struct sock *sk) struct udphdr *uh; struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); - struct flowi6 *fl6 = &inet->cork.fl.u.ip6; + struct flowi6 *fl6; int err = 0; int is_udplite = IS_UDPLITE(sk); __wsum csum = 0; + if (up->pending == AF_INET) + return udp_push_pending_frames(sk); + + fl6 = &inet->cork.fl.u.ip6; + /* Grab the skbuff where UDP header space exists. */ if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) goto out; @@ -1457,6 +1462,17 @@ void udp6_proc_exit(struct net *net) { } #endif /* CONFIG_PROC_FS */ +void udp_v6_clear_sk(struct sock *sk, int size) +{ + struct inet_sock *inet = inet_sk(sk); + + /* we do not want to clear pinet6 field, because of RCU lookups */ + sk_prot_clear_portaddr_nulls(sk, offsetof(struct inet_sock, pinet6)); + + size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6); + memset(&inet->pinet6 + 1, 0, size); +} + /* ------------------------------------------------------------------------ */ struct proto udpv6_prot = { @@ -1487,7 +1503,7 @@ struct proto udpv6_prot = { .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif - .clear_sk = sk_prot_clear_portaddr_nulls, + .clear_sk = udp_v6_clear_sk, }; static struct inet_protosw udpv6_protosw = { diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index d7571046bfc4..4691ed50a928 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -31,6 +31,8 @@ extern int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, extern int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb); extern void udpv6_destroy_sock(struct sock *sk); +extern void udp_v6_clear_sk(struct sock *sk, int size); + #ifdef CONFIG_PROC_FS extern int udp6_seq_show(struct seq_file *seq, void *v); #endif diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 1d08e21d9f69..dfcc4be46898 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -56,7 +56,7 @@ struct proto udplitev6_prot = { .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif - .clear_sk = sk_prot_clear_portaddr_nulls, + .clear_sk = udp_v6_clear_sk, }; static struct inet_protosw udplite6_protosw = { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8ea65e032733..808fd080eb34 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -96,8 +96,10 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, dev_hold(dev); xdst->u.rt6.rt6i_idev = in6_dev_get(dev); - if (!xdst->u.rt6.rt6i_idev) + if (!xdst->u.rt6.rt6i_idev) { + dev_put(dev); return -ENODEV; + } xdst->u.rt6.rt6i_peer = rt->rt6i_peer; if (rt->rt6i_peer) diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index bb14c3477680..bd25678b1d50 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1386,6 +1386,8 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(4, "%s()\n", __func__); + msg->msg_namelen = 0; + skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); if (!skb) @@ -2584,8 +2586,10 @@ bed: NULL, NULL, NULL); /* Check if the we got some results */ - if (!self->cachedaddr) - return -EAGAIN; /* Didn't find any devices */ + if (!self->cachedaddr) { + err = -EAGAIN; /* Didn't find any devices */ + goto out; + } daddr = self->cachedaddr; /* Cleanup */ self->cachedaddr = 0; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index cd6f7a991d80..625bc50391cc 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1331,6 +1331,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct sk_buff *skb, *rskb, *cskb; int err = 0; + msg->msg_namelen = 0; + if ((sk->sk_state == IUCV_DISCONN) && skb_queue_empty(&iucv->backlog_skb_q) && skb_queue_empty(&sk->sk_receive_queue) && diff --git a/net/key/af_key.c b/net/key/af_key.c index 7e5d927b576f..60109f417dc2 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1705,6 +1705,7 @@ static int key_notify_sa_flush(const struct km_event *c) hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); + hdr->sadb_msg_reserved = 0; pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); @@ -2072,6 +2073,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * pol->sadb_x_policy_type = IPSEC_POLICY_NONE; } pol->sadb_x_policy_dir = dir+1; + pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; pol->sadb_x_policy_priority = xp->priority; @@ -2686,6 +2688,7 @@ static int key_notify_policy_flush(const struct km_event *c) hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); + hdr->sadb_msg_reserved = 0; pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; @@ -3106,7 +3109,9 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = dir+1; + pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; + pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ if (x->id.proto == IPPROTO_AH) @@ -3494,6 +3499,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = dir + 1; + pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = 0; pol->sadb_x_policy_priority = 0; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1addd9f3f40a..b2982f4214d1 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -350,18 +350,19 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh skb_put(skb, 2); /* Copy user data into skb */ - error = memcpy_fromiovec(skb->data, m->msg_iov, total_len); + error = memcpy_fromiovec(skb_put(skb, total_len), m->msg_iov, + total_len); if (error < 0) { kfree_skb(skb); goto error_put_sess_tun; } - skb_put(skb, total_len); l2tp_xmit_skb(session, skb, session->hdr_len); sock_put(ps->tunnel_sock); + sock_put(sk); - return error; + return total_len; error_put_sess_tun: sock_put(ps->tunnel_sock); @@ -1777,7 +1778,8 @@ static const struct proto_ops pppol2tp_ops = { static const struct pppox_proto pppol2tp_proto = { .create = pppol2tp_create, - .ioctl = pppol2tp_ioctl + .ioctl = pppol2tp_ioctl, + .owner = THIS_MODULE, }; #ifdef CONFIG_L2TP_V3 diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index df08d7779e1d..e4d2fbb59a7e 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -721,6 +721,8 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, int target; /* Read at least this many bytes */ long timeo; + msg->msg_namelen = 0; + lock_sock(sk); copied = -ENOTCONN; if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN)) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 48f937e1ecf8..95a04f02f30b 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1257,6 +1257,15 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) ASSERT_RTNL(); + /* + * Close all AP_VLAN interfaces first, as otherwise they + * might be closed while the AP interface they belong to + * is closed, causing unregister_netdevice_many() to crash. + */ + list_for_each_entry(sdata, &local->interfaces, list) + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + dev_close(sdata->dev); + mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 8ce9feb13010..067aa2a23055 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -831,8 +831,14 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); - /* Drop duplicate 802.11 retransmissions (IEEE 802.11 Chap. 9.2.9) */ - if (rx->sta && !is_multicast_ether_addr(hdr->addr1)) { + /* + * Drop duplicate 802.11 retransmissions + * (IEEE 802.11-2012: 9.3.2.10 "Duplicate detection and recovery") + */ + if (rx->skb->len >= 24 && rx->sta && + !ieee80211_is_ctl(hdr->frame_control) && + !ieee80211_is_qos_nullfunc(hdr->frame_control) && + !is_multicast_ether_addr(hdr->addr1)) { if (unlikely(ieee80211_has_retry(hdr->frame_control) && rx->sta->last_seq_ctrl[rx->seqno_idx] == hdr->seq_ctrl)) { diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index 1aa5cac748c4..55add9325422 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -37,14 +37,10 @@ static int get_callid(const char *dptr, unsigned int dataoff, if (ret > 0) break; if (!ret) - return 0; + return -EINVAL; dataoff += *matchoff; } - /* Empty callid is useless */ - if (!*matchlen) - return -EINVAL; - /* Too large is useless */ if (*matchlen > IP_VS_PEDATA_MAXLEN) return -EINVAL; diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index d8d424337550..6bb1d42f0fac 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -245,6 +245,71 @@ static void netlbl_domhsh_audit_add(struct netlbl_dom_map *entry, } } +/** + * netlbl_domhsh_validate - Validate a new domain mapping entry + * @entry: the entry to validate + * + * This function validates the new domain mapping entry to ensure that it is + * a valid entry. Returns zero on success, negative values on failure. + * + */ +static int netlbl_domhsh_validate(const struct netlbl_dom_map *entry) +{ + struct netlbl_af4list *iter4; + struct netlbl_domaddr4_map *map4; +#if IS_ENABLED(CONFIG_IPV6) + struct netlbl_af6list *iter6; + struct netlbl_domaddr6_map *map6; +#endif /* IPv6 */ + + if (entry == NULL) + return -EINVAL; + + switch (entry->type) { + case NETLBL_NLTYPE_UNLABELED: + if (entry->type_def.cipsov4 != NULL || + entry->type_def.addrsel != NULL) + return -EINVAL; + break; + case NETLBL_NLTYPE_CIPSOV4: + if (entry->type_def.cipsov4 == NULL) + return -EINVAL; + break; + case NETLBL_NLTYPE_ADDRSELECT: + netlbl_af4list_foreach(iter4, &entry->type_def.addrsel->list4) { + map4 = netlbl_domhsh_addr4_entry(iter4); + switch (map4->type) { + case NETLBL_NLTYPE_UNLABELED: + if (map4->type_def.cipsov4 != NULL) + return -EINVAL; + break; + case NETLBL_NLTYPE_CIPSOV4: + if (map4->type_def.cipsov4 == NULL) + return -EINVAL; + break; + default: + return -EINVAL; + } + } +#if IS_ENABLED(CONFIG_IPV6) + netlbl_af6list_foreach(iter6, &entry->type_def.addrsel->list6) { + map6 = netlbl_domhsh_addr6_entry(iter6); + switch (map6->type) { + case NETLBL_NLTYPE_UNLABELED: + break; + default: + return -EINVAL; + } + } +#endif /* IPv6 */ + break; + default: + return -EINVAL; + } + + return 0; +} + /* * Domain Hash Table Functions */ @@ -311,6 +376,10 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, struct netlbl_af6list *tmp6; #endif /* IPv6 */ + ret_val = netlbl_domhsh_validate(entry); + if (ret_val != 0) + return ret_val; + /* XXX - we can remove this RCU read lock as the spinlock protects the * entire function, but before we do we need to fixup the * netlbl_af[4,6]list RCU functions to do "the right thing" with diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index e7ff694f1049..7fe20d068dd6 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1189,8 +1189,6 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, struct netlbl_unlhsh_walk_arg cb_arg; u32 skip_bkt = cb->args[0]; u32 skip_chain = cb->args[1]; - u32 skip_addr4 = cb->args[2]; - u32 skip_addr6 = cb->args[3]; u32 iter_bkt; u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; @@ -1215,7 +1213,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, continue; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < skip_addr4) + if (iter_addr4++ < cb->args[2]) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1231,7 +1229,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < skip_addr6) + if (iter_addr6++ < cb->args[3]) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1250,10 +1248,10 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, unlabel_staticlist_return: rcu_read_unlock(); - cb->args[0] = skip_bkt; - cb->args[1] = skip_chain; - cb->args[2] = skip_addr4; - cb->args[3] = skip_addr6; + cb->args[0] = iter_bkt; + cb->args[1] = iter_chain; + cb->args[2] = iter_addr4; + cb->args[3] = iter_addr6; return skb->len; } @@ -1273,12 +1271,9 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, { struct netlbl_unlhsh_walk_arg cb_arg; struct netlbl_unlhsh_iface *iface; - u32 skip_addr4 = cb->args[0]; - u32 skip_addr6 = cb->args[1]; - u32 iter_addr4 = 0; + u32 iter_addr4 = 0, iter_addr6 = 0; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) - u32 iter_addr6 = 0; struct netlbl_af6list *addr6; #endif @@ -1292,7 +1287,7 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, goto unlabel_staticlistdef_return; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < skip_addr4) + if (iter_addr4++ < cb->args[0]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, @@ -1305,7 +1300,7 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, } #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < skip_addr6) + if (iter_addr6++ < cb->args[1]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, @@ -1320,8 +1315,8 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, unlabel_staticlistdef_return: rcu_read_unlock(); - cb->args[0] = skip_addr4; - cb->args[1] = skip_addr6; + cb->args[0] = iter_addr4; + cb->args[1] = iter_addr6; return skb->len; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 9f40441d7a7d..73d3f0c84ceb 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -142,6 +142,7 @@ int genl_register_mc_group(struct genl_family *family, int err = 0; BUG_ON(grp->name[0] == '\0'); + BUG_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL); genl_lock(); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 1b9024ee963c..7ed9b1d0c102 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1177,6 +1177,7 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock, } if (sax != NULL) { + memset(sax, 0, sizeof(*sax)); sax->sax25_family = AF_NETROM; skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call, AX25_ADDR_LEN); diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c index c13e02ebdef9..0c2115f31c8a 100644 --- a/net/nfc/llcp/sock.c +++ b/net/nfc/llcp/sock.c @@ -514,6 +514,8 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock, pr_debug("%p %zu\n", sk, len); + msg->msg_namelen = 0; + lock_sock(sk); if (sk->sk_state == LLCP_CLOSED && diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 38ca5e07d520..8ed5d9302e88 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -812,37 +812,27 @@ static void prb_open_block(struct tpacket_kbdq_core *pkc1, smp_rmb(); - if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd1))) { - - /* We could have just memset this but we will lose the - * flexibility of making the priv area sticky - */ - BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; - BLOCK_NUM_PKTS(pbd1) = 0; - BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); - getnstimeofday(&ts); - h1->ts_first_pkt.ts_sec = ts.tv_sec; - h1->ts_first_pkt.ts_nsec = ts.tv_nsec; - pkc1->pkblk_start = (char *)pbd1; - pkc1->nxt_offset = (char *)(pkc1->pkblk_start + - BLK_PLUS_PRIV(pkc1->blk_sizeof_priv)); - BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); - BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; - pbd1->version = pkc1->version; - pkc1->prev = pkc1->nxt_offset; - pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; - prb_thaw_queue(pkc1); - _prb_refresh_rx_retire_blk_timer(pkc1); - - smp_wmb(); - - return; - } + /* We could have just memset this but we will lose the + * flexibility of making the priv area sticky + */ + BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; + BLOCK_NUM_PKTS(pbd1) = 0; + BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); + getnstimeofday(&ts); + h1->ts_first_pkt.ts_sec = ts.tv_sec; + h1->ts_first_pkt.ts_nsec = ts.tv_nsec; + pkc1->pkblk_start = (char *)pbd1; + pkc1->nxt_offset = (char *)(pkc1->pkblk_start + + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv)); + BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); + BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; + pbd1->version = pkc1->version; + pkc1->prev = pkc1->nxt_offset; + pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; + prb_thaw_queue(pkc1); + _prb_refresh_rx_retire_blk_timer(pkc1); - WARN(1, "ERROR block:%p is NOT FREE status:%d kactive_blk_num:%d\n", - pbd1, BLOCK_STATUS(pbd1), pkc1->kactive_blk_num); - dump_stack(); - BUG(); + smp_wmb(); } /* @@ -933,10 +923,6 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, prb_close_block(pkc, pbd, po, status); return; } - - WARN(1, "ERROR-pbd[%d]:%p\n", pkc->kactive_blk_num, pbd); - dump_stack(); - BUG(); } static int prb_curr_blk_in_use(struct tpacket_kbdq_core *pkc, @@ -2862,12 +2848,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); if (dev) - strncpy(uaddr->sa_data, dev->name, 14); - else - memset(uaddr->sa_data, 0, 14); + strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); *uaddr_len = sizeof(*uaddr); diff --git a/net/rds/message.c b/net/rds/message.c index f0a4658f3273..aff589cc022e 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -197,6 +197,9 @@ struct rds_message *rds_message_alloc(unsigned int extra_len, gfp_t gfp) { struct rds_message *rm; + if (extra_len > KMALLOC_MAX_SIZE - sizeof(struct rds_message)) + return NULL; + rm = kzalloc(sizeof(struct rds_message) + extra_len, gfp); if (!rm) goto out; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index c4719ce604c2..7f645d115795 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1257,6 +1257,7 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); if (srose != NULL) { + memset(srose, 0, msg->msg_namelen); srose->srose_family = AF_ROSE; srose->srose_addr = rose->dest_addr; srose->srose_call = rose->dest_call; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 60f8f616e8fa..57827bf06823 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -8,7 +8,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * Copyright: Jamal Hadi Salim (2002-4) + * Copyright: Jamal Hadi Salim (2002-13) */ #include <linux/types.h> @@ -299,17 +299,44 @@ static struct tc_action_ops act_ipt_ops = { .walk = tcf_generic_walker }; -MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); +static struct tc_action_ops act_xt_ops = { + .kind = "xt", + .hinfo = &ipt_hash_info, + .type = TCA_ACT_IPT, + .capab = TCA_CAP_NONE, + .owner = THIS_MODULE, + .act = tcf_ipt, + .dump = tcf_ipt_dump, + .cleanup = tcf_ipt_cleanup, + .lookup = tcf_hash_search, + .init = tcf_ipt_init, + .walk = tcf_generic_walker +}; + +MODULE_AUTHOR("Jamal Hadi Salim(2002-13)"); MODULE_DESCRIPTION("Iptables target actions"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("act_xt"); static int __init ipt_init_module(void) { - return tcf_register_action(&act_ipt_ops); + int ret1, ret2; + ret1 = tcf_register_action(&act_xt_ops); + if (ret1 < 0) + printk("Failed to load xt action\n"); + ret2 = tcf_register_action(&act_ipt_ops); + if (ret2 < 0) + printk("Failed to load ipt action\n"); + + if (ret1 < 0 && ret2 < 0) + return ret1; + else + return 0; } static void __exit ipt_cleanup_module(void) { + tcf_unregister_action(&act_xt_ops); tcf_unregister_action(&act_ipt_ops); } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index e25e49061a0d..6e38ef0040b8 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -606,6 +606,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, struct sockaddr_atmpvc pvc; int state; + memset(&pvc, 0, sizeof(pvc)); pvc.sap_family = AF_ATMPVC; pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; pvc.sap_addr.vpi = flow->vcc->vpi; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 599f67ada1ed..7f599447b3ca 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -963,8 +963,11 @@ cbq_dequeue(struct Qdisc *sch) cbq_update(q); if ((incr -= incr2) < 0) incr = 0; + q->now += incr; + } else { + if (now > q->now) + q->now = now; } - q->now += incr; q->now_rt = now; for (;;) { @@ -1464,6 +1467,7 @@ static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_wrropt opt; + memset(&opt, 0, sizeof(opt)); opt.flags = 0; opt.allot = cl->allot; opt.priority = cl->priority + 1; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index acd2edbc073e..3c04692d699a 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1050,7 +1050,7 @@ struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *asoc, transports) { if (transport == active) - break; + continue; list_for_each_entry(chunk, &transport->transmitted, transmitted_list) { if (key == chunk->subh.data_hdr->tsn) { diff --git a/net/sctp/auth.c b/net/sctp/auth.c index bf812048cf6f..333926d4d356 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -71,7 +71,7 @@ void sctp_auth_key_put(struct sctp_auth_bytes *key) return; if (atomic_dec_and_test(&key->refcnt)) { - kfree(key); + kzfree(key); SCTP_DBG_OBJCNT_DEC(keys); } } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 96eb168a1f47..3dd7207d33ad 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -205,6 +205,8 @@ static inline int sctp_cacc_skip(struct sctp_transport *primary, */ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) { + memset(q, 0, sizeof(struct sctp_outq)); + q->asoc = asoc; INIT_LIST_HEAD(&q->out_chunk_list); INIT_LIST_HEAD(&q->control_chunk_list); @@ -212,13 +214,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); - q->fast_rtx = 0; - q->outstanding_bytes = 0; q->empty = 1; - q->cork = 0; - - q->malloced = 0; - q->out_qlen = 0; } /* Free the outqueue structure and any related pending chunks. diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 891f5db8cc31..cb1c4303a07a 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2044,7 +2044,7 @@ sctp_disposition_t sctp_sf_do_5_2_4_dupcook(const struct sctp_endpoint *ep, } /* Delete the tempory new association. */ - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); + sctp_add_cmd_sf(commands, SCTP_CMD_SET_ASOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); /* Restore association pointer to provide SCTP command interpeter diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9fd05edef190..4bc6e0bbf978 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3929,6 +3929,12 @@ SCTP_STATIC void sctp_destroy_sock(struct sock *sk) /* Release our hold on the endpoint. */ sp = sctp_sk(sk); + /* This could happen during socket init, thus we bail out + * early, since the rest of the below is not setup either. + */ + if (sp->ep == NULL) + return; + if (sp->do_auto_asconf) { sp->do_auto_asconf = 0; list_del(&sp->auto_asconf_list); diff --git a/net/socket.c b/net/socket.c index dab317686ad3..47ce3ea44300 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1899,9 +1899,9 @@ struct used_address { unsigned int name_len; }; -static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, - struct msghdr *msg_sys, unsigned flags, - struct used_address *used_address) +static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, + struct msghdr *msg_sys, unsigned flags, + struct used_address *used_address) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; @@ -2017,22 +2017,30 @@ out: * BSD sendmsg interface */ -SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) +long __sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) { int fput_needed, err; struct msghdr msg_sys; - struct socket *sock = sockfd_lookup_light(fd, &err, &fput_needed); + struct socket *sock; + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; - err = __sys_sendmsg(sock, msg, &msg_sys, flags, NULL); + err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL); fput_light(sock->file, fput_needed); out: return err; } +SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned int, flags) +{ + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + return __sys_sendmsg(fd, msg, flags); +} + /* * Linux sendmmsg interface */ @@ -2063,15 +2071,16 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, while (datagrams < vlen) { if (MSG_CMSG_COMPAT & flags) { - err = __sys_sendmsg(sock, (struct msghdr __user *)compat_entry, - &msg_sys, flags, &used_address); + err = ___sys_sendmsg(sock, (struct msghdr __user *)compat_entry, + &msg_sys, flags, &used_address); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { - err = __sys_sendmsg(sock, (struct msghdr __user *)entry, - &msg_sys, flags, &used_address); + err = ___sys_sendmsg(sock, + (struct msghdr __user *)entry, + &msg_sys, flags, &used_address); if (err < 0) break; err = put_user(err, &entry->msg_len); @@ -2095,11 +2104,13 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags) { + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; return __sys_sendmmsg(fd, mmsg, vlen, flags); } -static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg, - struct msghdr *msg_sys, unsigned flags, int nosec) +static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, + struct msghdr *msg_sys, unsigned flags, int nosec) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; @@ -2192,23 +2203,31 @@ out: * BSD recvmsg interface */ -SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, - unsigned int, flags) +long __sys_recvmsg(int fd, struct msghdr __user *msg, unsigned flags) { int fput_needed, err; struct msghdr msg_sys; - struct socket *sock = sockfd_lookup_light(fd, &err, &fput_needed); + struct socket *sock; + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; - err = __sys_recvmsg(sock, msg, &msg_sys, flags, 0); + err = ___sys_recvmsg(sock, msg, &msg_sys, flags, 0); fput_light(sock->file, fput_needed); out: return err; } +SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, + unsigned int, flags) +{ + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + return __sys_recvmsg(fd, msg, flags); +} + /* * Linux recvmmsg interface */ @@ -2246,17 +2265,18 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, * No need to ask LSM for more than the first datagram. */ if (MSG_CMSG_COMPAT & flags) { - err = __sys_recvmsg(sock, (struct msghdr __user *)compat_entry, - &msg_sys, flags & ~MSG_WAITFORONE, - datagrams); + err = ___sys_recvmsg(sock, (struct msghdr __user *)compat_entry, + &msg_sys, flags & ~MSG_WAITFORONE, + datagrams); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { - err = __sys_recvmsg(sock, (struct msghdr __user *)entry, - &msg_sys, flags & ~MSG_WAITFORONE, - datagrams); + err = ___sys_recvmsg(sock, + (struct msghdr __user *)entry, + &msg_sys, flags & ~MSG_WAITFORONE, + datagrams); if (err < 0) break; err = put_user(err, &entry->msg_len); @@ -2323,6 +2343,9 @@ SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, int datagrams; struct timespec timeout_sys; + if (flags & MSG_CMSG_COMPAT) + return -EINVAL; + if (!timeout) return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL); diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 85b9235fbee2..72d89e129caa 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -143,6 +143,8 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]); task->tk_waitqueue = queue; queue->qlen++; + /* barrier matches the read in rpc_wake_up_task_queue_locked() */ + smp_wmb(); rpc_set_queued(task); dprintk("RPC: %5u added to queue %p \"%s\"\n", @@ -399,8 +401,11 @@ static void __rpc_do_wake_up_task(struct rpc_wait_queue *queue, struct rpc_task */ static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct rpc_task *task) { - if (RPC_IS_QUEUED(task) && task->tk_waitqueue == queue) - __rpc_do_wake_up_task(queue, task); + if (RPC_IS_QUEUED(task)) { + smp_rmb(); + if (task->tk_waitqueue == queue) + __rpc_do_wake_up_task(queue, task); + } } /* diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index feea4741edda..f1a63c1885dc 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -485,13 +485,17 @@ EXPORT_SYMBOL_GPL(xprt_wake_pending_tasks); * xprt_wait_for_buffer_space - wait for transport output buffer to clear * @task: task to be put to sleep * @action: function pointer to be executed after wait + * + * Note that we only set the timer for the case of RPC_IS_SOFT(), since + * we don't in general want to force a socket disconnection due to + * an incomplete RPC call transmission. */ void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - task->tk_timeout = req->rq_timeout; + task->tk_timeout = RPC_IS_SOFT(task) ? req->rq_timeout : 0; rpc_sleep_on(&xprt->pending, task, action); } EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 29e957f64458..1441ab70b98c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -829,6 +829,7 @@ static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) if (addr) { addr->family = AF_TIPC; addr->addrtype = TIPC_ADDR_ID; + memset(&addr->addr, 0, sizeof(addr->addr)); addr->addr.id.ref = msg_origport(msg); addr->addr.id.node = msg_orignode(msg); addr->addr.name.domain = 0; /* could leave uninitialized */ @@ -948,6 +949,9 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock, goto exit; } + /* will be updated in set_orig_addr() if needed */ + m->msg_namelen = 0; + timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); restart: @@ -1074,6 +1078,9 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, goto exit; } + /* will be updated in set_orig_addr() if needed */ + m->msg_namelen = 0; + target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len); timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); restart: diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 109e30beaa69..c4821fd23b79 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -374,7 +374,7 @@ static void unix_sock_destructor(struct sock *sk) #endif } -static int unix_release_sock(struct sock *sk, int embrion) +static void unix_release_sock(struct sock *sk, int embrion) { struct unix_sock *u = unix_sk(sk); struct path path; @@ -443,8 +443,6 @@ static int unix_release_sock(struct sock *sk, int embrion) if (unix_tot_inflight) unix_gc(); /* Garbage collect fds */ - - return 0; } static void init_peercred(struct sock *sk) @@ -694,9 +692,10 @@ static int unix_release(struct socket *sock) if (!sk) return 0; + unix_release_sock(sk, 0); sock->sk = NULL; - return unix_release_sock(sk, 0); + return 0; } static int unix_autobind(struct socket *sock) @@ -1987,7 +1986,7 @@ again: if ((UNIXCB(skb).pid != siocb->scm->pid) || (UNIXCB(skb).cred != siocb->scm->cred)) break; - } else { + } else if (test_bit(SOCK_PASSCRED, &sock->flags)) { /* Copy credentials */ scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred); check_creds = 1; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4371ed4729d5..e759b2872c46 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5083,12 +5083,14 @@ EXPORT_SYMBOL(cfg80211_testmode_alloc_event_skb); void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp) { + struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0]; void *hdr = ((void **)skb->cb)[1]; struct nlattr *data = ((void **)skb->cb)[2]; nla_nest_end(skb, data); genlmsg_end(skb, hdr); - genlmsg_multicast(skb, 0, nl80211_testmode_mcgrp.id, gfp); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), skb, 0, + nl80211_testmode_mcgrp.id, gfp); } EXPORT_SYMBOL(cfg80211_testmode_event); #endif @@ -7774,7 +7776,8 @@ void nl80211_send_mgmt_tx_status(struct cfg80211_registered_device *rdev, genlmsg_end(msg, hdr); - genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, gfp); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); return; nla_put_failure: diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 4dc83474db2e..796a0eeb26a9 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -862,7 +862,7 @@ static void handle_channel(struct wiphy *wiphy, return; REG_DBG_PRINT("Disabling freq %d MHz\n", chan->center_freq); - chan->flags = IEEE80211_CHAN_DISABLED; + chan->flags |= IEEE80211_CHAN_DISABLED; return; } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index a306bc66000e..b943e3e71bd2 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1586,11 +1586,11 @@ out_cud_release: case SIOCX25CALLACCPTAPPRV: { rc = -EINVAL; lock_sock(sk); - if (sk->sk_state != TCP_CLOSE) - break; - clear_bit(X25_ACCPT_APPRV_FLAG, &x25->flags); + if (sk->sk_state == TCP_CLOSE) { + clear_bit(X25_ACCPT_APPRV_FLAG, &x25->flags); + rc = 0; + } release_sock(sk); - rc = 0; break; } @@ -1598,14 +1598,15 @@ out_cud_release: rc = -EINVAL; lock_sock(sk); if (sk->sk_state != TCP_ESTABLISHED) - break; + goto out_sendcallaccpt_release; /* must call accptapprv above */ if (test_bit(X25_ACCPT_APPRV_FLAG, &x25->flags)) - break; + goto out_sendcallaccpt_release; x25_write_internal(sk, X25_CALL_ACCEPTED); x25->state = X25_STATE_3; - release_sock(sk); rc = 0; +out_sendcallaccpt_release: + release_sock(sk); break; } |