diff options
Diffstat (limited to 'net')
142 files changed, 1203 insertions, 917 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 09bf1c3..edf44d0 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -549,6 +549,23 @@ static const struct header_ops vlan_header_ops = { .parse = eth_header_parse, }; +static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, + const void *daddr, const void *saddr, + unsigned int len) +{ + struct vlan_dev_priv *vlan = vlan_dev_priv(dev); + struct net_device *real_dev = vlan->real_dev; + + return dev_hard_header(skb, real_dev, type, daddr, saddr, len); +} + +static const struct header_ops vlan_passthru_header_ops = { + .create = vlan_passthru_hard_header, + .rebuild = dev_rebuild_header, + .parse = eth_header_parse, +}; + static struct device_type vlan_type = { .name = "vlan", }; @@ -592,7 +609,7 @@ static int vlan_dev_init(struct net_device *dev) dev->needed_headroom = real_dev->needed_headroom; if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) { - dev->header_ops = real_dev->header_ops; + dev->header_ops = &vlan_passthru_header_ops; dev->hard_header_len = real_dev->hard_header_len; } else { dev->header_ops = &vlan_header_ops; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 990afab..c76a438 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -340,7 +340,10 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, int count = nr_pages; while (nr_pages) { s = rest_of_page(data); - pages[index++] = kmap_to_page(data); + if (is_vmalloc_addr(data)) + pages[index++] = vmalloc_to_page(data); + else + pages[index++] = kmap_to_page(data); data += s; nr_pages--; } diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 7fee50d..7d424ac 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1735,7 +1735,6 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr size_t size, int flags) { struct sock *sk = sock->sk; - struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name; struct ddpehdr *ddp; int copied = 0; int offset = 0; @@ -1764,14 +1763,13 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr } err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied); - if (!err) { - if (sat) { - sat->sat_family = AF_APPLETALK; - sat->sat_port = ddp->deh_sport; - sat->sat_addr.s_node = ddp->deh_snode; - sat->sat_addr.s_net = ddp->deh_snet; - } - msg->msg_namelen = sizeof(*sat); + if (!err && msg->msg_name) { + struct sockaddr_at *sat = msg->msg_name; + sat->sat_family = AF_APPLETALK; + sat->sat_port = ddp->deh_sport; + sat->sat_addr.s_node = ddp->deh_snode; + sat->sat_addr.s_net = ddp->deh_snet; + msg->msg_namelen = sizeof(*sat); } skb_free_datagram(sk, skb); /* Free the datagram. */ diff --git a/net/atm/common.c b/net/atm/common.c index 737bef5..7b49100 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -531,8 +531,6 @@ 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 4b4d2b7..78c474f 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1636,11 +1636,11 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock, skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); - if (msg->msg_namelen != 0) { - struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name; + if (msg->msg_name) { ax25_digi digi; ax25_address src; const unsigned char *mac = skb_mac_header(skb); + struct sockaddr_ax25 *sax = msg->msg_name; memset(sax, 0, sizeof(struct full_sockaddr_ax25)); ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL, diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 9096137..6629cdc 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -221,8 +221,6 @@ 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) @@ -287,8 +285,6 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags & MSG_OOB) return -EOPNOTSUPP; - msg->msg_namelen = 0; - BT_DBG("sk %p size %zu", sk, size); lock_sock(sk); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 9bd7d95..fa4bf66 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -752,8 +752,6 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return err; - msg->msg_namelen = 0; - copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 30b3721..c1c6028 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -608,7 +608,6 @@ 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 96bd388..d021e44 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -715,7 +715,6 @@ static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock, test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { sco_conn_defer_accept(pi->conn->hcon, pi->setting); sk->sk_state = BT_CONFIG; - msg->msg_namelen = 0; release_sock(sk); return 0; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ca04163..0d34001 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -219,6 +219,33 @@ static void br_netpoll_cleanup(struct net_device *dev) br_netpoll_disable(p); } +static int __br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) +{ + struct netpoll *np; + int err; + + np = kzalloc(sizeof(*p->np), gfp); + if (!np) + return -ENOMEM; + + err = __netpoll_setup(np, p->dev, gfp); + if (err) { + kfree(np); + return err; + } + + p->np = np; + return err; +} + +int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) +{ + if (!p->br->dev->npinfo) + return 0; + + return __br_netpoll_enable(p, gfp); +} + static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp) { @@ -229,7 +256,7 @@ static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, list_for_each_entry(p, &br->port_list, list) { if (!p->dev) continue; - err = br_netpoll_enable(p, gfp); + err = __br_netpoll_enable(p, gfp); if (err) goto fail; } @@ -242,28 +269,6 @@ fail: goto out; } -int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) -{ - struct netpoll *np; - int err; - - if (!p->br->dev->npinfo) - return 0; - - np = kzalloc(sizeof(*p->np), gfp); - if (!np) - return -ENOMEM; - - err = __netpoll_setup(np, p->dev, gfp); - if (err) { - kfree(np); - return err; - } - - p->np = np; - return err; -} - void br_netpoll_disable(struct net_bridge_port *p) { struct netpoll *np = p->np; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index c41d5fb..547504c 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -172,6 +172,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } + br_fdb_delete_by_port(br, NULL, 1); + del_timer_sync(&br->gc_timer); br_sysfs_delbr(br->dev); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 8b0b610..1b148a3 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2004,7 +2004,7 @@ int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val) u32 old; struct net_bridge_mdb_htable *mdb; - spin_lock(&br->multicast_lock); + spin_lock_bh(&br->multicast_lock); if (!netif_running(br->dev)) goto unlock; @@ -2036,7 +2036,7 @@ rollback: } unlock: - spin_unlock(&br->multicast_lock); + spin_unlock_bh(&br->multicast_lock); return err; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e14c33b..9a63c42 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -442,6 +442,16 @@ extern netdev_features_t br_features_recompute(struct net_bridge *br, extern int br_handle_frame_finish(struct sk_buff *skb); extern rx_handler_result_t br_handle_frame(struct sk_buff **pskb); +static inline bool br_rx_handler_check_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->rx_handler) == br_handle_frame; +} + +static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev) +{ + return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL; +} + /* br_ioctl.c */ extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *arg); diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 8660ea3..bdb459d 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -153,7 +153,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) goto err; - p = br_port_get_rcu(dev); + p = br_port_get_check_rcu(dev); if (!p) goto err; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 05a41c7..d6be3ed 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -286,8 +286,6 @@ 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; @@ -361,8 +359,6 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags&MSG_OOB) goto out; - msg->msg_namelen = 0; - /* * Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg diff --git a/net/can/af_can.c b/net/can/af_can.c index 3ab8dd2..ae3f07e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -57,6 +57,7 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/can/skb.h> #include <linux/ratelimit.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -290,7 +291,7 @@ int can_send(struct sk_buff *skb, int loop) return -ENOMEM; } - newskb->sk = skb->sk; + can_skb_set_owner(newskb, skb->sk); newskb->ip_summed = CHECKSUM_UNNECESSARY; newskb->pkt_type = PACKET_BROADCAST; } diff --git a/net/can/bcm.c b/net/can/bcm.c index 46f20bf..b57452a 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -268,7 +268,7 @@ static void bcm_can_tx(struct bcm_op *op) /* send with loopback */ skb->dev = dev; - skb->sk = op->sk; + can_skb_set_owner(skb, op->sk); can_send(skb, 1); /* update statistics */ @@ -1223,7 +1223,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) can_skb_prv(skb)->ifindex = dev->ifindex; skb->dev = dev; - skb->sk = sk; + can_skb_set_owner(skb, sk); err = can_send(skb, 1); /* send with loopback */ dev_put(dev); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 4a5df7b..464303f 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3126,7 +3126,6 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, INIT_LIST_HEAD(&m->data); /* front */ - m->front_max = front_len; if (front_len) { if (front_len > PAGE_CACHE_SIZE) { m->front.iov_base = __vmalloc(front_len, flags, @@ -3143,7 +3142,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, } else { m->front.iov_base = NULL; } - m->front.iov_len = front_len; + m->front_alloc_len = m->front.iov_len = front_len; dout("ceph_msg_new %p front %d\n", m, front_len); return m; @@ -3301,8 +3300,8 @@ EXPORT_SYMBOL(ceph_msg_last_put); void ceph_msg_dump(struct ceph_msg *msg) { - pr_debug("msg_dump %p (front_max %d length %zd)\n", msg, - msg->front_max, msg->data_length); + pr_debug("msg_dump %p (front_alloc_len %d length %zd)\n", msg, + msg->front_alloc_len, msg->data_length); print_hex_dump(KERN_DEBUG, "header: ", DUMP_PREFIX_OFFSET, 16, 1, &msg->hdr, sizeof(msg->hdr), true); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 1fe25cd..2ac9ef3 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -152,7 +152,7 @@ static int __open_session(struct ceph_mon_client *monc) /* initiatiate authentication handshake */ ret = ceph_auth_build_hello(monc->auth, monc->m_auth->front.iov_base, - monc->m_auth->front_max); + monc->m_auth->front_alloc_len); __send_prepared_auth_request(monc, ret); } else { dout("open_session mon%d already open\n", monc->cur_mon); @@ -196,7 +196,7 @@ static void __send_subscribe(struct ceph_mon_client *monc) int num; p = msg->front.iov_base; - end = p + msg->front_max; + end = p + msg->front_alloc_len; num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap; ceph_encode_32(&p, num); @@ -897,7 +897,7 @@ static void handle_auth_reply(struct ceph_mon_client *monc, ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base, msg->front.iov_len, monc->m_auth->front.iov_base, - monc->m_auth->front_max); + monc->m_auth->front_alloc_len); if (ret < 0) { monc->client->auth_err = ret; wake_up_all(&monc->client->auth_wq); @@ -939,7 +939,7 @@ static int __validate_auth(struct ceph_mon_client *monc) return 0; ret = ceph_build_auth(monc->auth, monc->m_auth->front.iov_base, - monc->m_auth->front_max); + monc->m_auth->front_alloc_len); if (ret <= 0) return ret; /* either an error, or no need to authenticate */ __send_prepared_auth_request(monc, ret); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 2b4b32a..e6b2db6 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1232,6 +1232,22 @@ void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, EXPORT_SYMBOL(ceph_osdc_set_request_linger); /* + * Returns whether a request should be blocked from being sent + * based on the current osdmap and osd_client settings. + * + * Caller should hold map_sem for read. + */ +static bool __req_should_be_paused(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD); + bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL); + return (req->r_flags & CEPH_OSD_FLAG_READ && pauserd) || + (req->r_flags & CEPH_OSD_FLAG_WRITE && pausewr); +} + +/* * Pick an osd (the first 'up' osd in the pg), allocate the osd struct * (as needed), and set the request r_osd appropriately. If there is * no up osd, set r_osd to NULL. Move the request to the appropriate list @@ -1248,6 +1264,7 @@ static int __map_request(struct ceph_osd_client *osdc, int acting[CEPH_PG_MAX_SIZE]; int o = -1, num = 0; int err; + bool was_paused; dout("map_request %p tid %lld\n", req, req->r_tid); err = ceph_calc_ceph_pg(&pgid, req->r_oid, osdc->osdmap, @@ -1264,12 +1281,18 @@ static int __map_request(struct ceph_osd_client *osdc, num = err; } + was_paused = req->r_paused; + req->r_paused = __req_should_be_paused(osdc, req); + if (was_paused && !req->r_paused) + force_resend = 1; + if ((!force_resend && req->r_osd && req->r_osd->o_osd == o && req->r_sent >= req->r_osd->o_incarnation && req->r_num_pg_osds == num && memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) || - (req->r_osd == NULL && o == -1)) + (req->r_osd == NULL && o == -1) || + req->r_paused) return 0; /* no change */ dout("map_request tid %llu pgid %lld.%x osd%d (was osd%d)\n", @@ -1613,14 +1636,17 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) * * Caller should hold map_sem for read. */ -static void kick_requests(struct ceph_osd_client *osdc, int force_resend) +static void kick_requests(struct ceph_osd_client *osdc, bool force_resend, + bool force_resend_writes) { struct ceph_osd_request *req, *nreq; struct rb_node *p; int needmap = 0; int err; + bool force_resend_req; - dout("kick_requests %s\n", force_resend ? " (force resend)" : ""); + dout("kick_requests %s %s\n", force_resend ? " (force resend)" : "", + force_resend_writes ? " (force resend writes)" : ""); mutex_lock(&osdc->request_mutex); for (p = rb_first(&osdc->requests); p; ) { req = rb_entry(p, struct ceph_osd_request, r_node); @@ -1645,7 +1671,10 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) continue; } - err = __map_request(osdc, req, force_resend); + force_resend_req = force_resend || + (force_resend_writes && + req->r_flags & CEPH_OSD_FLAG_WRITE); + err = __map_request(osdc, req, force_resend_req); if (err < 0) continue; /* error */ if (req->r_osd == NULL) { @@ -1665,7 +1694,8 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) r_linger_item) { dout("linger req=%p req->r_osd=%p\n", req, req->r_osd); - err = __map_request(osdc, req, force_resend); + err = __map_request(osdc, req, + force_resend || force_resend_writes); dout("__map_request returned %d\n", err); if (err == 0) continue; /* no change and no osd was specified */ @@ -1707,6 +1737,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) struct ceph_osdmap *newmap = NULL, *oldmap; int err; struct ceph_fsid fsid; + bool was_full; dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0); p = msg->front.iov_base; @@ -1720,6 +1751,8 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) down_write(&osdc->map_sem); + was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL); + /* incremental maps */ ceph_decode_32_safe(&p, end, nr_maps, bad); dout(" %d inc maps\n", nr_maps); @@ -1744,7 +1777,10 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) ceph_osdmap_destroy(osdc->osdmap); osdc->osdmap = newmap; } - kick_requests(osdc, 0); + was_full = was_full || + ceph_osdmap_flag(osdc->osdmap, + CEPH_OSDMAP_FULL); + kick_requests(osdc, 0, was_full); } else { dout("ignoring incremental map %u len %d\n", epoch, maplen); @@ -1787,7 +1823,10 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) skipped_map = 1; ceph_osdmap_destroy(oldmap); } - kick_requests(osdc, skipped_map); + was_full = was_full || + ceph_osdmap_flag(osdc->osdmap, + CEPH_OSDMAP_FULL); + kick_requests(osdc, skipped_map, was_full); } p += maplen; nr_maps--; @@ -1804,7 +1843,9 @@ done: * we find out when we are no longer full and stop returning * ENOSPC. */ - if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) + if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR)) ceph_monc_request_next_osdmap(&osdc->client->monc); mutex_lock(&osdc->request_mutex); @@ -2454,7 +2495,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, struct ceph_osd_client *osdc = osd->o_osdc; struct ceph_msg *m; struct ceph_osd_request *req; - int front = le32_to_cpu(hdr->front_len); + int front_len = le32_to_cpu(hdr->front_len); int data_len = le32_to_cpu(hdr->data_len); u64 tid; @@ -2474,12 +2515,13 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, req->r_reply, req->r_reply->con); ceph_msg_revoke_incoming(req->r_reply); - if (front > req->r_reply->front.iov_len) { + if (front_len > req->r_reply->front_alloc_len) { pr_warning("get_reply front %d > preallocated %d (%u#%llu)\n", - front, (int)req->r_reply->front.iov_len, + front_len, req->r_reply->front_alloc_len, (unsigned int)con->peer_name.type, le64_to_cpu(con->peer_name.num)); - m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front, GFP_NOFS, false); + m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS, + false); if (!m) goto out; ceph_msg_put(req->r_reply); diff --git a/net/compat.c b/net/compat.c index 8903258..f50161f 100644 --- a/net/compat.c +++ b/net/compat.c @@ -72,7 +72,7 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) - return -EINVAL; + kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_name = compat_ptr(tmp1); kmsg->msg_iov = compat_ptr(tmp2); kmsg->msg_control = compat_ptr(tmp3); @@ -93,7 +93,8 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, if (err < 0) return err; } - kern_msg->msg_name = kern_address; + if (kern_msg->msg_name) + kern_msg->msg_name = kern_address; } else kern_msg->msg_name = NULL; @@ -779,21 +780,16 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, 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, - (struct timespec *) timeout); - if (timeout == NULL) return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, NULL); - if (get_compat_timespec(&ktspec, timeout)) + if (compat_get_timespec(&ktspec, timeout)) return -EFAULT; datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, &ktspec); - if (datagrams > 0 && put_compat_timespec(&ktspec, timeout)) + if (datagrams > 0 && compat_put_timespec(&ktspec, timeout)) datagrams = -EFAULT; return datagrams; diff --git a/net/core/dev.c b/net/core/dev.c index 22719ed..50f47e1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1691,13 +1691,9 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) kfree_skb(skb); return NET_RX_DROP; } - skb->protocol = eth_type_trans(skb, dev); - /* eth_type_trans() can set pkt_type. - * call skb_scrub_packet() after it to clear pkt_type _after_ calling - * eth_type_trans(). - */ skb_scrub_packet(skb, true); + skb->protocol = eth_type_trans(skb, dev); return netif_rx(skb); } @@ -2402,7 +2398,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; @@ -2482,34 +2478,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - netdev_features_t features) + const struct net_device *dev, + netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, skb_network_protocol(skb))) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(skb->dev, skb)) { + } else if (illegal_highdma(dev, skb)) { features &= ~NETIF_F_SG; } return features; } -netdev_features_t netif_skb_features(struct sk_buff *skb) +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev) { __be16 protocol = skb->protocol; - netdev_features_t features = skb->dev->features; + netdev_features_t features = dev->features; - if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } - features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) @@ -2517,9 +2515,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } -EXPORT_SYMBOL(netif_skb_features); +EXPORT_SYMBOL(netif_skb_dev_features); /* * Returns true if either: @@ -4838,7 +4836,7 @@ static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; - if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags) + if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 5e78d44..f27d126 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -64,7 +64,6 @@ static struct genl_family net_drop_monitor_family = { .hdrsize = 0, .name = "NET_DM", .version = 2, - .maxattr = NET_DM_CMD_MAX, }; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 2e65413..185c341 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -460,7 +460,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (frh->action && (frh->action != rule->action)) continue; - if (frh->table && (frh_get_table(frh, tb) != rule->table)) + if (frh_get_table(frh, tb) && + (frh_get_table(frh, tb) != rule->table)) continue; if (tb[FRA_PRIORITY] && @@ -744,6 +745,13 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, attach_rules(&ops->rules_list, dev); break; + case NETDEV_CHANGENAME: + list_for_each_entry(ops, &net->rules_ops, list) { + detach_rules(&ops->rules_list, dev); + attach_rules(&ops->rules_list, dev); + } + break; + case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); diff --git a/net/core/filter.c b/net/core/filter.c index 01b7808..ad30d62 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -36,7 +36,6 @@ #include <asm/uaccess.h> #include <asm/unaligned.h> #include <linux/filter.h> -#include <linux/reciprocal_div.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> #include <linux/if_vlan.h> @@ -166,7 +165,7 @@ unsigned int sk_run_filter(const struct sk_buff *skb, A /= X; continue; case BPF_S_ALU_DIV_K: - A = reciprocal_divide(A, K); + A /= K; continue; case BPF_S_ALU_MOD_X: if (X == 0) @@ -553,11 +552,6 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) /* Some instructions need special checks */ switch (code) { case BPF_S_ALU_DIV_K: - /* check for division by zero */ - if (ftest->k == 0) - return -EINVAL; - ftest->k = reciprocal_value(ftest->k); - break; case BPF_S_ALU_MOD_K: /* check for division by zero */ if (ftest->k == 0) @@ -853,27 +847,7 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) to->code = decodes[code]; to->jt = filt->jt; to->jf = filt->jf; - - if (code == BPF_S_ALU_DIV_K) { - /* - * When loaded this rule user gave us X, which was - * translated into R = r(X). Now we calculate the - * RR = r(R) and report it back. If next time this - * value is loaded and RRR = r(RR) is calculated - * then the R == RRR will be true. - * - * One exception. X == 1 translates into R == 0 and - * we can't calculate RR out of it with r(). - */ - - if (filt->k == 0) - to->k = 1; - else - to->k = reciprocal_value(filt->k); - - BUG_ON(reciprocal_value(to->k) != filt->k); - } else - to->k = filt->k; + to->k = filt->k; } int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 8d7d0dd..143b6fd 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -40,7 +40,7 @@ again: struct iphdr _iph; ip: iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); - if (!iph) + if (!iph || iph->ihl < 5) return false; if (ip_is_fragment(iph)) diff --git a/net/core/iovec.c b/net/core/iovec.c index b77eeec..7d84ea1 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -48,7 +48,8 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a if (err < 0) return err; } - m->msg_name = address; + if (m->msg_name) + m->msg_name = address; } else { m->msg_name = NULL; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6072610..467e3e0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -764,9 +764,6 @@ static void neigh_periodic_work(struct work_struct *work) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) < tbl->gc_thresh1) - goto out; - /* * periodically recompute ReachableTime from random function */ @@ -779,6 +776,9 @@ static void neigh_periodic_work(struct work_struct *work) neigh_rand_reach_time(p->base_reachable_time); } + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + for (i = 0 ; i < (1 << nht->hash_shift); i++) { np = &nht->hash_buckets[i]; @@ -1274,7 +1274,7 @@ int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb) if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, skb->len) < 0 && - dev->header_ops->rebuild(skb)) + dev_rebuild_header(skb)) return 0; return dev_queue_xmit(skb); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 730cfbd..9e9a6fe 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -386,8 +386,14 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, !vlan_hw_offload_capable(netif_skb_features(skb), skb->vlan_proto)) { skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb)); - if (unlikely(!skb)) - break; + if (unlikely(!skb)) { + /* This is actually a packet drop, but we + * don't want the code at the end of this + * function to try and re-queue a NULL skb. + */ + status = NETDEV_TX_OK; + goto unlock_txq; + } skb->vlan_tci = 0; } @@ -395,6 +401,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, if (status == NETDEV_TX_OK) txq_trans_update(txq); } + unlock_txq: __netif_tx_unlock(txq); if (status == NETDEV_TX_OK) @@ -941,6 +948,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; int ipv6; + bool ipversion_set = false; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) @@ -953,6 +961,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) cur++; if (*cur != '/') { + ipversion_set = true; if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; @@ -995,7 +1004,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); if (ipv6 < 0) goto parse_failed; - else if (np->ipv6 != (bool)ipv6) + else if (ipversion_set && np->ipv6 != (bool)ipv6) goto parse_failed; else np->ipv6 = (bool)ipv6; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 261357a..a797fff 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2527,6 +2527,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, if (x) { int ret; __u8 *eth; + struct iphdr *iph; + nhead = x->props.header_len - skb_headroom(skb); if (nhead > 0) { ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); @@ -2548,6 +2550,11 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, eth = (__u8 *) skb_push(skb, ETH_HLEN); memcpy(eth, pkt_dev->hh, 12); *(u16 *) ð[12] = protocol; + + /* Update IPv4 header len as well as checksum value */ + iph = ip_hdr(skb); + iph->tot_len = htons(skb->len - ETH_HLEN); + ip_send_check(iph); } } return 1; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0effa7b..15f9c56 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -47,6 +47,8 @@ #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> +#include <linux/tcp.h> +#include <linux/udp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> @@ -74,36 +76,6 @@ struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; -static void sock_pipe_buf_release(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - put_page(buf->page); -} - -static void sock_pipe_buf_get(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - get_page(buf->page); -} - -static int sock_pipe_buf_steal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - return 1; -} - - -/* Pipe buffer operations for a socket. */ -static const struct pipe_buf_operations sock_pipe_buf_ops = { - .can_merge = 0, - .map = generic_pipe_buf_map, - .unmap = generic_pipe_buf_unmap, - .confirm = generic_pipe_buf_confirm, - .release = sock_pipe_buf_release, - .steal = sock_pipe_buf_steal, - .get = sock_pipe_buf_get, -}; - /** * skb_panic - private function for out-of-line support * @skb: buffer @@ -580,9 +552,6 @@ static void skb_release_head_state(struct sk_buff *skb) #if IS_ENABLED(CONFIG_NF_CONNTRACK) nf_conntrack_put(skb->nfct); #endif -#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED - nf_conntrack_put_reasm(skb->nfct_reasm); -#endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(skb->nf_bridge); #endif @@ -1852,7 +1821,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, .partial = partial, .nr_pages_max = MAX_SKB_FRAGS, .flags = flags, - .ops = &sock_pipe_buf_ops, + .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; struct sk_buff *frag_iter; @@ -2807,6 +2776,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *fskb = skb_shinfo(skb)->frag_list; + skb_frag_t *skb_frag = skb_shinfo(skb)->frags; unsigned int mss = skb_shinfo(skb)->gso_size; unsigned int doffset = skb->data - skb_mac_header(skb); unsigned int offset = doffset; @@ -2846,16 +2816,38 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) if (hsize > len || !sg) hsize = len; - if (!hsize && i >= nfrags) { - BUG_ON(fskb->len != len); + if (!hsize && i >= nfrags && skb_headlen(fskb) && + (skb_headlen(fskb) == len || sg)) { + BUG_ON(skb_headlen(fskb) > len); + + i = 0; + nfrags = skb_shinfo(fskb)->nr_frags; + skb_frag = skb_shinfo(fskb)->frags; + pos += skb_headlen(fskb); + + while (pos < offset + len) { + BUG_ON(i >= nfrags); + + size = skb_frag_size(skb_frag); + if (pos + size > offset + len) + break; + + i++; + pos += size; + skb_frag++; + } - pos += len; nskb = skb_clone(fskb, GFP_ATOMIC); fskb = fskb->next; if (unlikely(!nskb)) goto err; + if (unlikely(pskb_trim(nskb, len))) { + kfree_skb(nskb); + goto err; + } + hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); @@ -2899,7 +2891,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) nskb->data - tnl_hlen, doffset + tnl_hlen); - if (fskb != skb_shinfo(skb)->frag_list) + if (nskb->len == len + doffset) goto perform_csum_check; if (!sg) { @@ -2917,8 +2909,28 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; - while (pos < offset + len && i < nfrags) { - *frag = skb_shinfo(skb)->frags[i]; + while (pos < offset + len) { + if (i >= nfrags) { + BUG_ON(skb_headlen(fskb)); + + i = 0; + nfrags = skb_shinfo(fskb)->nr_frags; + skb_frag = skb_shinfo(fskb)->frags; + + BUG_ON(!nfrags); + + fskb = fskb->next; + } + + if (unlikely(skb_shinfo(nskb)->nr_frags >= + MAX_SKB_FRAGS)) { + net_warn_ratelimited( + "skb_segment: too many frags: %u %u\n", + pos, mss); + goto err; + } + + *frag = *skb_frag; __skb_frag_ref(frag); size = skb_frag_size(frag); @@ -2931,6 +2943,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) if (pos + size <= offset + len) { i++; + skb_frag++; pos += size; } else { skb_frag_size_sub(frag, pos + size - (offset + len)); @@ -2940,25 +2953,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) frag++; } - if (pos < offset + len) { - struct sk_buff *fskb2 = fskb; - - BUG_ON(pos + fskb->len != offset + len); - - pos += fskb->len; - fskb = fskb->next; - - if (fskb2->next) { - fskb2 = skb_clone(fskb2, GFP_ATOMIC); - if (!fskb2) - goto err; - } else - skb_get(fskb2); - - SKB_FRAG_ASSERT(nskb); - skb_shinfo(nskb)->frag_list = fskb2; - } - skip_fraglist: nskb->data_len = len - hsize; nskb->len += nskb->data_len; @@ -3568,6 +3562,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; + skb->local_df = 0; skb_dst_drop(skb); skb->mark = 0; secpath_reset(skb); @@ -3575,3 +3570,26 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) nf_reset_trace(skb); } EXPORT_SYMBOL_GPL(skb_scrub_packet); + +/** + * skb_gso_transport_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_transport_seglen is used to determine the real size of the + * individual segments, including Layer4 headers (TCP/UDP). + * + * The MAC/L2 or network (IP, IPv6) headers are not accounted for. + */ +unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + unsigned int hdr_len; + + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len = tcp_hdrlen(skb); + else + hdr_len = sizeof(struct udphdr); + return hdr_len + shinfo->gso_size; +} +EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); diff --git a/net/core/sock.c b/net/core/sock.c index 0b39e7a..831a0d0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -888,7 +888,7 @@ set_rcvbuf: case SO_PEEK_OFF: if (sock->ops->set_peek_off) - sock->ops->set_peek_off(sk, val); + ret = sock->ops->set_peek_off(sk, val); else ret = -EOPNOTSUPP; break; @@ -1795,7 +1795,9 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, while (order) { if (npages >= 1 << order) { page = alloc_pages(sk->sk_allocation | - __GFP_COMP | __GFP_NOWARN, + __GFP_COMP | + __GFP_NOWARN | + __GFP_NORETRY, order); if (page) goto fill_page; @@ -1857,7 +1859,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) gfp_t gfp = sk->sk_allocation; if (order) - gfp |= __GFP_COMP | __GFP_NOWARN; + gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; pfrag->page = alloc_pages(gfp, order); if (likely(pfrag->page)) { pfrag->offset = 0; diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index ff41b4d..ceabe6f 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -957,7 +957,7 @@ lowpan_process_data(struct sk_buff *skb) * Traffic class carried in-line * ECN + DSCP (1 byte), Flow Label is elided */ - case 1: /* 10b */ + case 2: /* 10b */ if (lowpan_fetch_skb_u8(skb, &tmp)) goto drop; @@ -968,7 +968,7 @@ lowpan_process_data(struct sk_buff *skb) * Flow Label carried in-line * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided */ - case 2: /* 01b */ + case 1: /* 01b */ if (lowpan_fetch_skb_u8(skb, &tmp)) goto drop; @@ -1261,7 +1261,27 @@ static struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; +static struct lock_class_key lowpan_tx_busylock; +static struct lock_class_key lowpan_netdev_xmit_lock_key; + +static void lowpan_set_lockdep_class_one(struct net_device *dev, + struct netdev_queue *txq, + void *_unused) +{ + lockdep_set_class(&txq->_xmit_lock, + &lowpan_netdev_xmit_lock_key); +} + + +static int lowpan_dev_init(struct net_device *dev) +{ + netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL); + dev->qdisc_tx_busylock = &lowpan_tx_busylock; + return 0; +} + static const struct net_device_ops lowpan_netdev_ops = { + .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_set_mac_address = lowpan_set_address, }; diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 581a595..1865fdf 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -315,9 +315,8 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, if (saddr) { saddr->family = AF_IEEE802154; saddr->addr = mac_cb(skb)->sa; - } - if (addr_len) *addr_len = sizeof(*saddr); + } if (flags & MSG_TRUNC) copied = skb->len; diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 22b1a70..4efd237 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -224,8 +224,10 @@ static int ieee802154_add_iface(struct sk_buff *skb, if (info->attrs[IEEE802154_ATTR_DEV_TYPE]) { type = nla_get_u8(info->attrs[IEEE802154_ATTR_DEV_TYPE]); - if (type >= __IEEE802154_DEV_MAX) - return -EINVAL; + if (type >= __IEEE802154_DEV_MAX) { + rc = -EINVAL; + goto nla_put_failure; + } } dev = phy->add_iface(phy, devname, type); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index b28e863..19e3637 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -57,7 +57,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) - IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); goto out; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a1b5bcb..f4b34d8 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1435,7 +1435,8 @@ static size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ - + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ + + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b3f627a..f7f8cff 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1049,6 +1049,8 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo } in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) + return NOTIFY_DONE; switch (event) { case NETDEV_UP: diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 523be38..f2e1573 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -104,7 +104,10 @@ errout: static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) { struct fib_result *result = (struct fib_result *) arg->result; - struct net_device *dev = result->fi->fib_dev; + struct net_device *dev = NULL; + + if (result->fi) + dev = result->fi->fib_dev; /* do not accept result if the route does * not meet the required prefix length diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 55e6bfb..db98705 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -28,6 +28,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t enc_features; int ghl = GRE_HEADER_SECTION; struct gre_base_hdr *greh; + u16 mac_offset = skb->mac_header; int mac_len = skb->mac_len; __be16 protocol = skb->protocol; int tnl_hlen; @@ -57,13 +58,13 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, } else csum = false; + if (unlikely(!pskb_may_pull(skb, ghl))) + goto out; + /* setup inner skb. */ skb->protocol = greh->protocol; skb->encapsulation = 0; - if (unlikely(!pskb_may_pull(skb, ghl))) - goto out; - __skb_pull(skb, ghl); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); @@ -72,8 +73,10 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, /* segment inner packet. */ enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); segs = skb_mac_gso_segment(skb, enc_features); - if (!segs || IS_ERR(segs)) + if (!segs || IS_ERR(segs)) { + skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len); goto out; + } skb = segs; tnl_hlen = skb_tnl_header_len(skb); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 5f64875..45dbdab 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -106,6 +106,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->id.idiag_sport = inet->inet_sport; r->id.idiag_dport = inet->inet_dport; + + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; @@ -240,12 +244,19 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, r->idiag_family = tw->tw_family; r->idiag_retrans = 0; + r->id.idiag_if = tw->tw_bound_dev_if; sock_diag_save_cookie(tw, r->id.idiag_cookie); + r->id.idiag_sport = tw->tw_sport; r->id.idiag_dport = tw->tw_dport; + + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + r->id.idiag_src[0] = tw->tw_rcv_saddr; r->id.idiag_dst[0] = tw->tw_daddr; + r->idiag_state = tw->tw_substate; r->idiag_timer = 3; r->idiag_expires = DIV_ROUND_UP(tmo * 1000, HZ); @@ -732,8 +743,13 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->id.idiag_sport = inet->inet_sport; r->id.idiag_dport = ireq->rmt_port; + + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + r->id.idiag_src[0] = ireq->loc_addr; r->id.idiag_dst[0] = ireq->rmt_addr; + r->idiag_expires = jiffies_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; @@ -945,7 +961,7 @@ next_normal: ++num; } - if (r->idiag_states & TCPF_TIME_WAIT) { + if (r->idiag_states & (TCPF_TIME_WAIT | TCPF_FIN_WAIT2)) { struct inet_timewait_sock *tw; inet_twsk_for_each(tw, node, @@ -955,6 +971,8 @@ next_normal: if (num < s_num) goto next_dying; + if (!(r->idiag_states & (1 << tw->tw_substate))) + goto next_dying; if (r->sdiag_family != AF_UNSPEC && tw->tw_family != r->sdiag_family) goto next_dying; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index feb6c22..4582ea3 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -39,6 +39,71 @@ #include <net/route.h> #include <net/xfrm.h> +static bool ip_may_fragment(const struct sk_buff *skb) +{ + return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || + !skb->local_df; +} + +static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + +static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb) +{ + unsigned int mtu; + + if (skb->local_df || !skb_is_gso(skb)) + return false; + + mtu = dst_mtu(skb_dst(skb)); + + /* if seglen > mtu, do software segmentation for IP fragmentation on + * output. DF bit cannot be set since ip_forward would have sent + * icmp error. + */ + return skb_gso_network_seglen(skb) > mtu; +} + +/* called if GSO skb needs to be fragmented on forward */ +static int ip_forward_finish_gso(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + netdev_features_t features; + struct sk_buff *segs; + int ret = 0; + + features = netif_skb_dev_features(skb, dst->dev); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = dst_output(segs); + + if (err && ret == 0) + ret = err; + segs = nskb; + } while (segs); + + return ret; +} + static int ip_forward_finish(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); + if (ip_gso_exceeds_dst_mtu(skb)) + return ip_forward_finish_gso(skb); + return dst_output(skb); } @@ -88,8 +156,7 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; - if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && - (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { + if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, dst_mtu(&rt->dst))) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(dst_mtu(&rt->dst))); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index d7aea4c..d306360 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -178,7 +178,7 @@ static int ipgre_err(struct sk_buff *skb, u32 info, else itn = net_generic(net, ipgre_net_id); - iph = (const struct iphdr *)skb->data; + iph = (const struct iphdr *)(icmp_hdr(skb) + 1); t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); @@ -217,6 +217,7 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) iph->saddr, iph->daddr, tpi->key); if (tunnel) { + skb_pop_mac_header(skb); ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error); return PACKET_RCVD; } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index c83963a..c12f79b 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -315,7 +315,7 @@ static int ip_rcv_finish(struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; - if (sysctl_ip_early_demux && !skb_dst(skb)) { + if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { const struct net_protocol *ipprot; int protocol = iph->protocol; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index d9c4f11..23e6ab0 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -368,7 +368,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf /* * Handle MSG_ERRQUEUE */ -int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct sock_exterr_skb *serr; struct sk_buff *skb, *skb2; @@ -405,6 +405,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) serr->addr_offset); sin->sin_port = serr->port; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 63a6d6d..995a0bb 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -454,6 +454,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); + if (tunnel->dev->type == ARPHRD_ETHER) { skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); @@ -461,8 +463,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, skb->dev = tunnel->dev; } - skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); - gro_cells_receive(&tunnel->gro_cells, skb); return 0; @@ -618,6 +618,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index c31e3ad..ba22cc3 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -109,7 +109,6 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) secpath_reset(skb); if (!skb->l4_rxhash) skb->rxhash = 0; - skb_dst_drop(skb); skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); skb->pkt_type = PACKET_HOST; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 6e87f85..26847e1 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -190,6 +190,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (!rt->dst.xfrm || rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) { dev->stats.tx_carrier_errors++; + ip_rt_put(rt); goto tx_error_icmp; } tdev = rt->dst.dev; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 62212c7..1672409 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -157,9 +157,12 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id) static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { - struct ipmr_result res; - struct fib_lookup_arg arg = { .result = &res, }; int err; + struct ipmr_result res; + struct fib_lookup_arg arg = { + .result = &res, + .flags = FIB_LOOKUP_NOREF, + }; err = fib_rules_lookup(net->ipv4.mr_rules_ops, flowi4_to_flowi(flp4), 0, &arg); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index d7d9882..c482f7c 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -769,7 +769,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -827,8 +827,6 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, { struct inet_sock *isk = inet_sk(sk); int family = sk->sk_family; - struct sockaddr_in *sin; - struct sockaddr_in6 *sin6; struct sk_buff *skb; int copied, err; @@ -838,19 +836,13 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto out; - if (addr_len) { - if (family == AF_INET) - *addr_len = sizeof(*sin); - else if (family == AF_INET6 && addr_len) - *addr_len = sizeof(*sin6); - } - if (flags & MSG_ERRQUEUE) { if (family == AF_INET) { - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { - return pingv6_ops.ipv6_recv_error(sk, msg, len); + return pingv6_ops.ipv6_recv_error(sk, msg, len, + addr_len); #endif } } @@ -874,11 +866,15 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* Copy the address and add cmsg data. */ if (family == AF_INET) { - sin = (struct sockaddr_in *) msg->msg_name; - sin->sin_family = AF_INET; - sin->sin_port = 0 /* skb->h.uh->source */; - sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + + if (sin) { + sin->sin_family = AF_INET; + sin->sin_port = 0 /* skb->h.uh->source */; + sin->sin_addr.s_addr = ip_hdr(skb)->saddr; + memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); + } if (isk->cmsg_flags) ip_cmsg_recv(msg, skb); @@ -887,17 +883,21 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } else if (family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *ip6 = ipv6_hdr(skb); - sin6 = (struct sockaddr_in6 *) msg->msg_name; - sin6->sin6_family = AF_INET6; - sin6->sin6_port = 0; - sin6->sin6_addr = ip6->saddr; - - sin6->sin6_flowinfo = 0; - if (np->sndflow) - sin6->sin6_flowinfo = ip6_flowinfo(ip6); - - sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, - IP6CB(skb)->iif); + struct sockaddr_in6 *sin6 = + (struct sockaddr_in6 *)msg->msg_name; + + if (sin6) { + sin6->sin6_family = AF_INET6; + sin6->sin6_port = 0; + sin6->sin6_addr = ip6->saddr; + sin6->sin6_flowinfo = 0; + if (np->sndflow) + sin6->sin6_flowinfo = ip6_flowinfo(ip6); + sin6->sin6_scope_id = + ipv6_iface_scope_id(&sin6->sin6_addr, + IP6CB(skb)->iif); + *addr_len = sizeof(*sin6); + } if (inet6_sk(sk)->rxopt.all) pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 193db03..7d3db78 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -694,11 +694,8 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*sin); - if (flags & MSG_ERRQUEUE) { - err = ip_recv_error(sk, msg, len); + err = ip_recv_error(sk, msg, len, addr_len); goto out; } @@ -724,6 +721,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index fcbd95f..d000b34 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1604,6 +1604,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rth->dst.output = ip_output; @@ -1705,8 +1706,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (err != 0) goto no_route; - RT_CACHE_STAT_INC(in_slow_tot); - if (res.type == RTN_BROADCAST) goto brd_input; @@ -1775,13 +1774,18 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } - if (do_cache) - rt_cache_route(&FIB_RES_NH(res), rth); + if (do_cache) { + if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) { + rth->dst.flags |= DST_NOCACHE; + rt_add_uncached_list(rth); + } + } skb_dst_set(skb, &rth->dst); err = 0; goto out; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 14a15c4..15e0241 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -89,8 +89,7 @@ __u32 cookie_init_timestamp(struct request_sock *req) static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport, - __be16 dport, __u32 sseq, __u32 count, - __u32 data) + __be16 dport, __u32 sseq, __u32 data) { /* * Compute the secure sequence number. @@ -102,7 +101,7 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport, * As an extra hack, we add a small "data" value that encodes the * MSS into the second hash value. */ - + u32 count = tcp_cookie_time(); return (cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq + (count << COOKIEBITS) + ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data) @@ -114,22 +113,21 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport, * If the syncookie is bad, the data returned will be out of * range. This must be checked by the caller. * - * The count value used to generate the cookie must be within - * "maxdiff" if the current (passed-in) "count". The return value - * is (__u32)-1 if this test fails. + * The count value used to generate the cookie must be less than + * MAX_SYNCOOKIE_AGE minutes in the past. + * The return value (__u32)-1 if this test fails. */ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr, - __be16 sport, __be16 dport, __u32 sseq, - __u32 count, __u32 maxdiff) + __be16 sport, __be16 dport, __u32 sseq) { - __u32 diff; + u32 diff, count = tcp_cookie_time(); /* Strip away the layers from the cookie */ cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; /* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */ diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS); - if (diff >= maxdiff) + if (diff >= MAX_SYNCOOKIE_AGE) return (__u32)-1; return (cookie - @@ -138,22 +136,22 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr, } /* - * MSS Values are taken from the 2009 paper - * 'Measuring TCP Maximum Segment Size' by S. Alcock and R. Nelson: - * - values 1440 to 1460 accounted for 80% of observed mss values - * - values outside the 536-1460 range are rare (<0.2%). + * MSS Values are chosen based on the 2011 paper + * 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson. + * Values .. + * .. lower than 536 are rare (< 0.2%) + * .. between 537 and 1299 account for less than < 1.5% of observed values + * .. in the 1300-1349 range account for about 15 to 20% of observed mss values + * .. exceeding 1460 are very rare (< 0.04%) * - * Table must be sorted. + * 1460 is the single most frequently announced mss value (30 to 46% depending + * on monitor location). Table must be sorted. */ static __u16 const msstab[] = { - 64, - 512, 536, - 1024, - 1440, + 1300, + 1440, /* 1440, 1452: PPPoE */ 1460, - 4312, - 8960, }; /* @@ -173,7 +171,7 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, return secure_tcp_syn_cookie(iph->saddr, iph->daddr, th->source, th->dest, ntohl(th->seq), - jiffies / (HZ * 60), mssind); + mssind); } EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence); @@ -189,13 +187,6 @@ __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) } /* - * This (misnamed) value is the age of syncookie which is permitted. - * Its ideal value should be dependent on TCP_TIMEOUT_INIT and - * sysctl_tcp_retries1. It's a rather complicated formula (exponential - * backoff) to compute at runtime so it's currently hardcoded here. - */ -#define COUNTER_TRIES 4 -/* * Check if a ack sequence number is a valid syncookie. * Return the decoded mss if it is, or 0 if not. */ @@ -204,9 +195,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, { __u32 seq = ntohl(th->seq) - 1; __u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr, - th->source, th->dest, seq, - jiffies / (HZ * 60), - COUNTER_TRIES); + th->source, th->dest, seq); return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6e5617b..531ab57 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -806,12 +806,6 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, xmit_size_goal = min_t(u32, gso_size, sk->sk_gso_max_size - 1 - hlen); - /* TSQ : try to have at least two segments in flight - * (one in NIC TX ring, another in Qdisc) - */ - xmit_size_goal = min_t(u32, xmit_size_goal, - sysctl_tcp_limit_output_bytes >> 1); - xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal); /* We try hard to avoid divides here */ @@ -1006,7 +1000,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } } -static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, + int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); int err, flags; @@ -1021,11 +1016,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) if (unlikely(tp->fastopen_req == NULL)) return -ENOBUFS; tp->fastopen_req->data = msg; + tp->fastopen_req->size = size; flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags); - *size = tp->fastopen_req->copied; + *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); return err; } @@ -1045,7 +1041,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flags = msg->msg_flags; if (flags & MSG_FASTOPEN) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a16b01b..068c8fb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2856,7 +2856,8 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) + if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && + flag & FLAG_ACKED) seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; if (seq_rtt < 0) @@ -2871,14 +2872,19 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, } /* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ -static void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) +static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp) { struct tcp_sock *tp = tcp_sk(sk); s32 seq_rtt = -1; - if (tp->lsndtime && !tp->total_retrans) - seq_rtt = tcp_time_stamp - tp->lsndtime; - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); + if (synack_stamp && !tp->total_retrans) + seq_rtt = tcp_time_stamp - synack_stamp; + + /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets + * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack() + */ + if (!tp->srtt) + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); } static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) @@ -2981,6 +2987,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, s32 seq_rtt = -1; s32 ca_seq_rtt = -1; ktime_t last_ackt = net_invalid_timestamp(); + bool rtt_update; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); @@ -3057,14 +3064,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - if (tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt) || - (flag & FLAG_ACKED)) - tcp_rearm_rto(sk); + rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt); if (flag & FLAG_ACKED) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; + tcp_rearm_rto(sk); if (unlikely(icsk->icsk_mtup.probe_size && !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) { tcp_mtup_probe_success(sk); @@ -3103,6 +3109,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, ca_ops->pkts_acked(sk, pkts_acked, rtt_us); } + } else if (skb && rtt_update && sack_rtt >= 0 && + sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) { + /* Do not re-arm RTO if the sack RTT is measured from data sent + * after when the head was last (re)transmitted. Otherwise the + * timeout may continue to extend in loss recovery. + */ + tcp_rearm_rto(sk); } #if FASTRETRANS_DEBUG > 0 @@ -5587,6 +5600,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct request_sock *req; int queued = 0; bool acceptable; + u32 synack_stamp; tp->rx_opt.saw_tstamp = 0; @@ -5669,9 +5683,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * so release it. */ if (req) { + synack_stamp = tcp_rsk(req)->snt_synack; tp->total_retrans = req->num_retrans; reqsk_fastopen_remove(sk, req, false); } else { + synack_stamp = tp->lsndtime; /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); tcp_init_congestion_control(sk); @@ -5694,7 +5710,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_una = TCP_SKB_CB(skb)->ack_seq; tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - tcp_synack_rtt_meas(sk, req); + tcp_synack_rtt_meas(sk, synack_stamp); if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b14266b..5031f68 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -177,7 +177,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) - IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); return err; } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 52f3c6b..75c7f53 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -22,6 +22,9 @@ int sysctl_tcp_nometrics_save __read_mostly; +static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr, + struct net *net, unsigned int hash); + struct tcp_fastopen_metrics { u16 mss; u16 syn_loss:10; /* Recurring Fast Open SYN losses */ @@ -130,16 +133,41 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, } } +#define TCP_METRICS_TIMEOUT (60 * 60 * HZ) + +static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) +{ + if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) + tcpm_suck_dst(tm, dst, false); +} + +#define TCP_METRICS_RECLAIM_DEPTH 5 +#define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL + static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, struct inetpeer_addr *addr, - unsigned int hash, - bool reclaim) + unsigned int hash) { struct tcp_metrics_block *tm; struct net *net; + bool reclaim = false; spin_lock_bh(&tcp_metrics_lock); net = dev_net(dst->dev); + + /* While waiting for the spin-lock the cache might have been populated + * with this entry and so we have to check again. + */ + tm = __tcp_get_metrics(addr, net, hash); + if (tm == TCP_METRICS_RECLAIM_PTR) { + reclaim = true; + tm = NULL; + } + if (tm) { + tcpm_check_stamp(tm, dst); + goto out_unlock; + } + if (unlikely(reclaim)) { struct tcp_metrics_block *oldest; @@ -169,17 +197,6 @@ out_unlock: return tm; } -#define TCP_METRICS_TIMEOUT (60 * 60 * HZ) - -static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) -{ - if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) - tcpm_suck_dst(tm, dst, false); -} - -#define TCP_METRICS_RECLAIM_DEPTH 5 -#define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL - static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth) { if (tm) @@ -280,7 +297,6 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, struct inetpeer_addr addr; unsigned int hash; struct net *net; - bool reclaim; addr.family = sk->sk_family; switch (addr.family) { @@ -300,13 +316,10 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); tm = __tcp_get_metrics(&addr, net, hash); - reclaim = false; - if (tm == TCP_METRICS_RECLAIM_PTR) { - reclaim = true; + if (tm == TCP_METRICS_RECLAIM_PTR) tm = NULL; - } if (!tm && create) - tm = tcpm_new(dst, &addr, hash, reclaim); + tm = tcpm_new(dst, &addr, hash); else tcpm_check_stamp(tm, dst); @@ -659,10 +672,13 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost) { + struct dst_entry *dst = __sk_dst_get(sk); struct tcp_metrics_block *tm; + if (!dst) + return; rcu_read_lock(); - tm = tcp_get_metrics(sk, __sk_dst_get(sk), true); + tm = tcp_get_metrics(sk, dst, true); if (tm) { struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 3a7525e..910ab81 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -18,6 +18,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int sum_truesize = 0; struct tcphdr *th; unsigned int thlen; unsigned int seq; @@ -102,13 +103,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, if (copy_destructor) { skb->destructor = gso_skb->destructor; skb->sk = gso_skb->sk; - /* {tcp|sock}_wfree() use exact truesize accounting : - * sum(skb->truesize) MUST be exactly be gso_skb->truesize - * So we account mss bytes of 'true size' for each segment. - * The last segment will contain the remaining. - */ - skb->truesize = mss; - gso_skb->truesize -= mss; + sum_truesize += skb->truesize; } skb = skb->next; th = tcp_hdr(skb); @@ -125,7 +120,9 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, if (copy_destructor) { swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); - swap(gso_skb->truesize, skb->truesize); + sum_truesize += skb->truesize; + atomic_add(sum_truesize - gso_skb->truesize, + &skb->sk->sk_wmem_alloc); } delta = htonl(oldlen + (skb_tail_pointer(skb) - @@ -275,33 +272,32 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff * { const struct iphdr *iph = skb_gro_network_header(skb); __wsum wsum; - __sum16 sum; + + /* Don't bother verifying checksum if we're going to flush anyway. */ + if (NAPI_GRO_CB(skb)->flush) + goto skip_csum; + + wsum = skb->csum; switch (skb->ip_summed) { + case CHECKSUM_NONE: + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), + 0); + + /* fall through */ + case CHECKSUM_COMPLETE: if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr, - skb->csum)) { + wsum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; break; } -flush: + NAPI_GRO_CB(skb)->flush = 1; return NULL; - - case CHECKSUM_NONE: - wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb_gro_len(skb), IPPROTO_TCP, 0); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; } +skip_csum: return tcp_gro_receive(head, skb); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d46f214..e088932 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -696,7 +696,8 @@ static void tcp_tsq_handler(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) - tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC); + tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle, + 0, GFP_ATOMIC); } /* * One tasklest per cpu tries to send more skbs. @@ -1875,12 +1876,24 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, * - better RTT estimation and ACK scheduling * - faster recovery * - high rates + * Alas, some drivers / subsystems require a fair amount + * of queued bytes to ensure line rate. + * One example is wifi aggregation (802.11 AMPDU) */ - limit = max(skb->truesize, sk->sk_pacing_rate >> 10); + limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes, + sk->sk_pacing_rate >> 10); if (atomic_read(&sk->sk_wmem_alloc) > limit) { set_bit(TSQ_THROTTLED, &tp->tsq_flags); - break; + /* It is possible TX completion already happened + * before we set TSQ_THROTTLED, so we must + * test again the condition. + * We abuse smp_mb__after_clear_bit() because + * there is no smp_mb__after_set_bit() yet + */ + smp_mb__after_clear_bit(); + if (atomic_read(&sk->sk_wmem_alloc) > limit) + break; } limit = mss_now; @@ -2889,7 +2902,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; - syn_data = skb_copy_expand(syn, skb_headroom(syn), space, + space = min_t(size_t, space, fo->size); + + /* limit to order-0 allocations */ + space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); + + syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, sk->sk_allocation); if (syn_data == NULL) goto fallback; @@ -3108,7 +3126,6 @@ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; - tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq; tcp_xmit_probe_skb(sk, 0); } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0ca44df..6ca9907 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -973,7 +973,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -1072,6 +1072,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, struct udp_sock *up = udp_sk(sk); int ret; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + if (!up->pending) { struct msghdr msg = { .msg_flags = flags|MSG_MORE }; @@ -1209,14 +1212,8 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int is_udplite = IS_UDPLITE(sk); bool slow; - /* - * Check any passed addresses - */ - if (addr_len) - *addr_len = sizeof(*sin); - if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), @@ -1276,6 +1273,7 @@ try_again: sin->sin_port = udp_hdr(skb)->source; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); @@ -2296,6 +2294,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; int mac_len = skb->mac_len; int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); __be16 protocol = skb->protocol; @@ -2315,8 +2314,11 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, /* segment inner packet. */ enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); segs = skb_mac_gso_segment(skb, enc_features); - if (!segs || IS_ERR(segs)) + if (!segs || IS_ERR(segs)) { + skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, + mac_len); goto out; + } outer_hlen = skb_tnl_header_len(skb); skb = segs; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index f35ecca..6b809e4 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -41,6 +41,14 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; + int offset; + __wsum csum; + + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) { + segs = skb_udp_tunnel_segment(skb, features); + goto out; + } mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) @@ -62,27 +70,20 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, goto out; } + /* Do software UFO. Complete and fill in the UDP checksum as + * HW cannot do checksum of UDP packets sent as multiple + * IP fragments. + */ + offset = skb_checksum_start_offset(skb); + csum = skb_checksum(skb, offset, skb->len - offset, 0); + offset += skb->csum_offset; + *(__sum16 *)(skb->data + offset) = csum_fold(csum); + skb->ip_summed = CHECKSUM_NONE; + /* Fragment the skb. IP headers of the fragments are updated in * inet_gso_segment() */ - if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) - segs = skb_udp_tunnel_segment(skb, features); - else { - int offset; - __wsum csum; - - /* Do software UFO. Complete and fill in the UDP checksum as - * HW cannot do checksum of UDP packets sent as multiple - * IP fragments. - */ - offset = skb_checksum_start_offset(skb); - csum = skb_checksum(skb, offset, skb->len - offset, 0); - offset += skb->csum_offset; - *(__sum16 *)(skb->data + offset) = csum_fold(csum); - skb->ip_summed = CHECKSUM_NONE; - - segs = skb_segment(skb, features); - } + segs = skb_segment(skb, features); out: return segs; } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index ccde542..adf9983 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -104,10 +104,14 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) const struct iphdr *iph = ip_hdr(skb); u8 *xprth = skb_network_header(skb) + iph->ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; - fl4->flowi4_oif = skb_dst(skb)->dev->ifindex; + fl4->flowi4_oif = reverse ? skb->skb_iif : oif; if (!ip_is_fragment(iph)) { switch (iph->protocol) { diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 7c96100..8132b44 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -965,10 +965,10 @@ out: #ifdef CONFIG_SYSCTL sysctl_fail: - ipv6_packet_cleanup(); + pingv6_exit(); #endif pingv6_fail: - pingv6_exit(); + ipv6_packet_cleanup(); ipv6_packet_fail: tcpv6_exit(); tcpv6_fail: diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 48b6bd2..c66c6df 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -318,7 +318,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) /* * Handle MSG_ERRQUEUE */ -int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; @@ -369,6 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) &sin->sin6_addr); sin->sin6_scope_id = 0; } + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); @@ -377,6 +378,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; + sin->sin6_port = 0; if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) @@ -423,7 +425,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU */ -int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; @@ -457,6 +460,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; + *addr_len = sizeof(*sin); } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 140748d..8af3eb5 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -212,7 +212,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, found = (nexthdr == target); if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { - if (target < 0) + if (target < 0 || found) break; return -ENOENT; } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index e275916..3fd0a57 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -122,7 +122,11 @@ out: static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) { struct rt6_info *rt = (struct rt6_info *) arg->result; - struct net_device *dev = rt->rt6i_idev->dev; + struct net_device *dev = NULL; + + if (rt->rt6i_idev) + dev = rt->rt6i_idev->dev; + /* do not accept result if the route does * not meet the required prefix length */ diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 46e8843..f0ccdb7 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -453,8 +453,10 @@ static int mem_check(struct sock *sk) if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; + rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) count++; + rcu_read_unlock_bh(); if (room <= 0 || ((count >= FL_MAX_PER_SOCK || diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 302d6fb..51d54dc 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -49,7 +49,7 @@ int ip6_rcv_finish(struct sk_buff *skb) { - if (sysctl_ip_early_demux && !skb_dst(skb)) { + if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { const struct inet6_protocol *ipprot; ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 92cf3af..4bb2d80 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -116,8 +116,8 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_unlock_bh(); - IP6_INC_STATS_BH(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } @@ -125,7 +125,8 @@ static int ip6_finish_output2(struct sk_buff *skb) static int ip6_finish_output(struct sk_buff *skb) { if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb))) + dst_allfrag(skb_dst(skb)) || + (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(skb, ip6_finish_output2); else return ip6_finish_output2(skb); @@ -320,6 +321,20 @@ static inline int ip6_forward_finish(struct sk_buff *skb) return dst_output(skb); } +static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) + return true; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -442,8 +457,7 @@ int ip6_forward(struct sk_buff *skb) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) || - (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { + if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 583b77e..c1e11b5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1635,6 +1635,15 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], return ip6_tnl_update(t, &p); } +static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev != ip6n->fb_tnl_dev) + unregister_netdevice_queue(dev, head); +} + static size_t ip6_tnl_get_size(const struct net_device *dev) { return @@ -1699,6 +1708,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = { .validate = ip6_tnl_validate, .newlink = ip6_tnl_newlink, .changelink = ip6_tnl_changelink, + .dellink = ip6_tnl_dellink, .get_size = ip6_tnl_get_size, .fill_info = ip6_tnl_fill_info, }; @@ -1715,9 +1725,9 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .priority = 1, }; -static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) +static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) { - struct net *net = dev_net(ip6n->fb_tnl_dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct net_device *dev, *aux; int h; struct ip6_tnl *t; @@ -1785,10 +1795,8 @@ err_alloc_dev: static void __net_exit ip6_tnl_exit_net(struct net *net) { - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - rtnl_lock(); - ip6_tnl_destroy_tunnels(ip6n); + ip6_tnl_destroy_tunnels(net); rtnl_unlock(); } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f365310..0eb4038 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -141,9 +141,12 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr6_table **mrt) { - struct ip6mr_result res; - struct fib_lookup_arg arg = { .result = &res, }; int err; + struct ip6mr_result res; + struct fib_lookup_arg arg = { + .result = &res, + .flags = FIB_LOOKUP_NOREF, + }; err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flowi6_to_flowi(flp6), 0, &arg); diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index d6e4dd8..83ab37c 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -169,63 +169,13 @@ out: return nf_conntrack_confirm(skb); } -static unsigned int __ipv6_conntrack_in(struct net *net, - unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *reasm = skb->nfct_reasm; - const struct nf_conn_help *help; - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - - /* This packet is fragmented and has reassembled packet. */ - if (reasm) { - /* Reassembled packet isn't parsed yet ? */ - if (!reasm->nfct) { - unsigned int ret; - - ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm); - if (ret != NF_ACCEPT) - return ret; - } - - /* Conntrack helpers need the entire reassembled packet in the - * POST_ROUTING hook. In case of unconfirmed connections NAT - * might reassign a helper, so the entire packet is also - * required. - */ - ct = nf_ct_get(reasm, &ctinfo); - if (ct != NULL && !nf_ct_is_untracked(ct)) { - help = nfct_help(ct); - if ((help && help->helper) || !nf_ct_is_confirmed(ct)) { - nf_conntrack_get_reasm(reasm); - NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm, - (struct net_device *)in, - (struct net_device *)out, - okfn, NF_IP6_PRI_CONNTRACK + 1); - return NF_DROP_ERR(-ECANCELED); - } - } - - nf_conntrack_get(reasm->nfct); - skb->nfct = reasm->nfct; - skb->nfctinfo = reasm->nfctinfo; - return NF_ACCEPT; - } - - return nf_conntrack_in(net, PF_INET6, hooknum, skb); -} - static unsigned int ipv6_conntrack_in(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn); + return nf_conntrack_in(dev_net(in), PF_INET6, hooknum, skb); } static unsigned int ipv6_conntrack_local(unsigned int hooknum, @@ -239,7 +189,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } - return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn); + return nf_conntrack_in(dev_net(out), PF_INET6, hooknum, skb); } static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index dffdc1a..253566a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -621,31 +621,16 @@ ret_orig: return skb; } -void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, - struct net_device *in, struct net_device *out, - int (*okfn)(struct sk_buff *)) +void nf_ct_frag6_consume_orig(struct sk_buff *skb) { struct sk_buff *s, *s2; - unsigned int ret = 0; for (s = NFCT_FRAG6_CB(skb)->orig; s;) { - nf_conntrack_put_reasm(s->nfct_reasm); - nf_conntrack_get_reasm(skb); - s->nfct_reasm = skb; - s2 = s->next; s->next = NULL; - - if (ret != -ECANCELED) - ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, - in, out, okfn, - NF_IP6_PRI_CONNTRACK_DEFRAG + 1); - else - kfree_skb(s); - + consume_skb(s); s = s2; } - nf_conntrack_put_reasm(skb); } static int nf_ct_net_init(struct net *net) diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index aacd121..581dd9e 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -75,8 +75,11 @@ static unsigned int ipv6_defrag(unsigned int hooknum, if (reasm == skb) return NF_ACCEPT; - nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in, - (struct net_device *)out, okfn); + nf_ct_frag6_consume_orig(reasm); + + NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm, + (struct net_device *) in, (struct net_device *) out, + okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); return NF_STOLEN; } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 18f19df..7856e96 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -57,7 +57,8 @@ static struct inet_protosw pingv6_protosw = { /* Compatibility glue so we can support IPv6 when it's compiled as a module */ -static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { return -EAFNOSUPPORT; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a4ed241..430067c 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -466,14 +466,11 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (flags & MSG_OOB) return -EOPNOTSUPP; - if (addr_len) - *addr_len=sizeof(*sin6); - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) @@ -507,6 +504,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, IP6CB(skb)->iif); + *addr_len = sizeof(*sin6); } sock_recv_ts_and_drops(msg, sk, skb); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2ee530d..58eed5f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -88,6 +88,8 @@ static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct sk_buff *skb); +static int ip6_pkt_prohibit(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); @@ -238,9 +240,6 @@ static const struct rt6_info ip6_null_entry_template = { #ifdef CONFIG_IPV6_MULTIPLE_TABLES -static int ip6_pkt_prohibit(struct sk_buff *skb); -static int ip6_pkt_prohibit_out(struct sk_buff *skb); - static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), @@ -735,8 +734,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, prefix = &prefix_buf; } - rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, - dev->ifindex); + if (rinfo->prefix_len == 0) + rt = rt6_get_dflt_router(gwaddr, dev); + else + rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, + gwaddr, dev->ifindex); if (rt && !lifetime) { ip6_del_rt(rt); @@ -1097,10 +1099,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) return NULL; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) - return dst; + if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + return NULL; - return NULL; + if (rt6_check_expired(rt)) + return NULL; + + return dst; } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -1574,21 +1579,24 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } } - rt->dst.output = ip6_pkt_discard_out; - rt->dst.input = ip6_pkt_discard; rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP; switch (cfg->fc_type) { case RTN_BLACKHOLE: rt->dst.error = -EINVAL; + rt->dst.output = dst_discard; + rt->dst.input = dst_discard; break; case RTN_PROHIBIT: rt->dst.error = -EACCES; + rt->dst.output = ip6_pkt_prohibit_out; + rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: - rt->dst.error = -EAGAIN; - break; default: - rt->dst.error = -ENETUNREACH; + rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN + : -ENETUNREACH; + rt->dst.output = ip6_pkt_discard_out; + rt->dst.input = ip6_pkt_discard; break; } goto install_route; @@ -1918,9 +1926,7 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, else rt->rt6i_gateway = *dest; rt->rt6i_flags = ort->rt6i_flags; - if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == - (RTF_DEFAULT | RTF_ADDRCONF)) - rt6_set_from(rt, ort); + rt6_set_from(rt, ort); rt->rt6i_metric = 0; #ifdef CONFIG_IPV6_SUBTREES @@ -2159,8 +2165,6 @@ static int ip6_pkt_discard_out(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } -#ifdef CONFIG_IPV6_MULTIPLE_TABLES - static int ip6_pkt_prohibit(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); @@ -2172,8 +2176,6 @@ static int ip6_pkt_prohibit_out(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } -#endif - /* * Allocate a dst for local (unicast / anycast) address. */ @@ -2183,12 +2185,10 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, bool anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL); - - if (!rt) { - net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n"); + struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, + DST_NOCOUNT, NULL); + if (!rt) return ERR_PTR(-ENOMEM); - } in6_dev_hold(idev); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1926945..b433884 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1594,6 +1594,15 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { #endif }; +static void ipip6_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + + if (dev != sitn->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); +} + static struct rtnl_link_ops sit_link_ops __read_mostly = { .kind = "sit", .maxtype = IFLA_IPTUN_MAX, @@ -1605,6 +1614,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = { .changelink = ipip6_changelink, .get_size = ipip6_get_size, .fill_info = ipip6_fill_info, + .dellink = ipip6_dellink, }; static struct xfrm_tunnel sit_handler __read_mostly = { @@ -1619,9 +1629,10 @@ static struct xfrm_tunnel ipip_handler __read_mostly = { .priority = 2, }; -static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) +static void __net_exit sit_destroy_tunnels(struct net *net, + struct list_head *head) { - struct net *net = dev_net(sitn->fb_tunnel_dev); + struct sit_net *sitn = net_generic(net, sit_net_id); struct net_device *dev, *aux; int prio; @@ -1696,11 +1707,10 @@ err_alloc_dev: static void __net_exit sit_exit_net(struct net *net) { - struct sit_net *sitn = net_generic(net, sit_net_id); LIST_HEAD(list); rtnl_lock(); - sit_destroy_tunnels(sitn, &list); + sit_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index bf63ac8..d703218 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -24,26 +24,21 @@ #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) -/* Table must be sorted. */ +/* RFC 2460, Section 8.3: + * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..] + * + * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows + * using higher values than ipv4 tcp syncookies. + * The other values are chosen based on ethernet (1500 and 9k MTU), plus + * one that accounts for common encap (PPPoe) overhead. Table must be sorted. + */ static __u16 const msstab[] = { - 64, - 512, - 536, - 1280 - 60, + 1280 - 60, /* IPV6_MIN_MTU - 60 */ 1480 - 60, 1500 - 60, - 4460 - 60, 9000 - 60, }; -/* - * This (misnamed) value is the age of syncookie which is permitted. - * Its ideal value should be dependent on TCP_TIMEOUT_INIT and - * sysctl_tcp_retries1. It's a rather complicated formula (exponential - * backoff) to compute at runtime so it's currently hardcoded here. - */ -#define COUNTER_TRIES 4 - static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) @@ -86,8 +81,9 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, __u32 sseq, - __u32 count, __u32 data) + __u32 data) { + u32 count = tcp_cookie_time(); return (cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq + (count << COOKIEBITS) + ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data) @@ -96,15 +92,14 @@ static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr, static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, - __be16 dport, __u32 sseq, __u32 count, - __u32 maxdiff) + __be16 dport, __u32 sseq) { - __u32 diff; + __u32 diff, count = tcp_cookie_time(); cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS); - if (diff >= maxdiff) + if (diff >= MAX_SYNCOOKIE_AGE) return (__u32)-1; return (cookie - @@ -125,8 +120,7 @@ u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, *mssp = msstab[mssind]; return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source, - th->dest, ntohl(th->seq), - jiffies / (HZ * 60), mssind); + th->dest, ntohl(th->seq), mssind); } EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence); @@ -146,8 +140,7 @@ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, { __u32 seq = ntohl(th->seq) - 1; __u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr, - th->source, th->dest, seq, - jiffies / (HZ * 60), COUNTER_TRIES); + th->source, th->dest, seq); return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 2ec6bf6..a7a2384 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -37,34 +37,32 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, { const struct ipv6hdr *iph = skb_gro_network_header(skb); __wsum wsum; - __sum16 sum; + + /* Don't bother verifying checksum if we're going to flush anyway. */ + if (NAPI_GRO_CB(skb)->flush) + goto skip_csum; + + wsum = skb->csum; switch (skb->ip_summed) { + case CHECKSUM_NONE: + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), + wsum); + + /* fall through */ + case CHECKSUM_COMPLETE: if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, - skb->csum)) { + wsum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; break; } -flush: + NAPI_GRO_CB(skb)->flush = 1; return NULL; - - case CHECKSUM_NONE: - wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), - IPPROTO_TCP, 0)); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; } +skip_csum: return tcp_gro_receive(head, skb); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1878609..3d2758d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -374,14 +374,11 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, int is_udp4; bool slow; - if (addr_len) - *addr_len = sizeof(struct sockaddr_in6); - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), @@ -462,7 +459,7 @@ try_again: ipv6_iface_scope_id(&sin6->sin6_addr, IP6CB(skb)->iif); } - + *addr_len = sizeof(*sin6); } if (is_udp4) { if (inet->cmsg_flags) diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 6055951..ab4569d 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -88,7 +88,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Check if there is enough headroom to insert fragment header. */ tnl_hlen = skb_tnl_header_len(skb); - if (skb_headroom(skb) < (tnl_hlen + frag_hdr_sz)) { + if (skb_mac_header(skb) < skb->head + tnl_hlen + frag_hdr_sz) { if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) goto out; } @@ -111,7 +111,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; - ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); + fptr->identification = skb_shinfo(skb)->ip6_frag_id; /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 08ed277..550b195 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -135,10 +135,14 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) struct ipv6_opt_hdr *exthdr; const unsigned char *nh = skb_network_header(skb); u8 nexthdr = nh[IP6CB(skb)->nhoff]; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; - fl6->flowi6_oif = skb_dst(skb)->dev->ifindex; + fl6->flowi6_oif = reverse ? skb->skb_iif : oif; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 7a1e0fc..e096025 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1823,8 +1823,6 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, if (skb->tstamp.tv64) sk->sk_stamp = skb->tstamp; - msg->msg_namelen = sizeof(*sipx); - if (sipx) { sipx->sipx_family = AF_IPX; sipx->sipx_port = ipx->ipx_source.sock; @@ -1832,6 +1830,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, sipx->sipx_network = IPX_SKB_CB(skb)->ipx_source_net; sipx->sipx_type = ipx->ipx_type; sipx->sipx_zero = 0; + msg->msg_namelen = sizeof(*sipx); } rc = copied; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 0578d4f..a5e62ef5 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1385,8 +1385,6 @@ 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) @@ -1451,8 +1449,6 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, noblock); - msg->msg_namelen = 0; - do { int chunk; struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 168aff5..c4b7218 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1324,8 +1324,6 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, int err = 0; u32 offset; - 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 911ef03..545f047 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3616,7 +3616,6 @@ static int pfkey_recvmsg(struct kiocb *kiocb, if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT)) goto out; - msg->msg_namelen = 0; skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 571db8d..da1a1ce 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -518,9 +518,6 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*sin); - skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; @@ -543,6 +540,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index b8a6039..e6e8408 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -665,7 +665,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, *addr_len = sizeof(*lsa); if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 8c46b27..44441c0 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -197,8 +197,6 @@ static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock, if (sk->sk_state & PPPOX_BOUND) goto end; - msg->msg_namelen = 0; - err = 0; skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 6cba486..c71b699 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -715,13 +715,11 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, unsigned long cpu_flags; size_t copied = 0; u32 peek_seq = 0; - u32 *seq; + u32 *seq, skb_len; unsigned long used; 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)) @@ -814,6 +812,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, } continue; found_ok_skb: + skb_len = skb->len; /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) @@ -846,7 +845,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, } /* Partial read */ - if (used + offset < skb->len) + if (used + offset < skb_len) continue; } while (len > 0); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 629dee7..c6d417a 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -995,8 +995,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, IEEE80211_P2P_OPPPS_ENABLE_BIT; err = ieee80211_assign_beacon(sdata, ¶ms->beacon); - if (err < 0) + if (err < 0) { + ieee80211_vif_release_channel(sdata); return err; + } changed |= err; err = drv_start_ap(sdata->local, sdata); @@ -1005,6 +1007,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (old) kfree_rcu(old, rcu_head); RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); + ieee80211_vif_release_channel(sdata); return err; } @@ -2386,8 +2389,7 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - if (sdata->vif.type != NL80211_IFTYPE_STATION && - sdata->vif.type != NL80211_IFTYPE_MESH_POINT) + if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) @@ -2507,6 +2509,24 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, INIT_DELAYED_WORK(&roc->work, ieee80211_sw_roc_work); INIT_LIST_HEAD(&roc->dependents); + /* + * cookie is either the roc cookie (for normal roc) + * or the SKB (for mgmt TX) + */ + if (!txskb) { + /* local->mtx protects this */ + local->roc_cookie_counter++; + roc->cookie = local->roc_cookie_counter; + /* wow, you wrapped 64 bits ... more likely a bug */ + if (WARN_ON(roc->cookie == 0)) { + roc->cookie = 1; + local->roc_cookie_counter++; + } + *cookie = roc->cookie; + } else { + *cookie = (unsigned long)txskb; + } + /* if there's one pending or we're scanning, queue this one */ if (!list_empty(&local->roc_list) || local->scanning || local->radar_detect_enabled) @@ -2641,24 +2661,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, if (!queued) list_add_tail(&roc->list, &local->roc_list); - /* - * cookie is either the roc cookie (for normal roc) - * or the SKB (for mgmt TX) - */ - if (!txskb) { - /* local->mtx protects this */ - local->roc_cookie_counter++; - roc->cookie = local->roc_cookie_counter; - /* wow, you wrapped 64 bits ... more likely a bug */ - if (WARN_ON(roc->cookie == 0)) { - roc->cookie = 1; - local->roc_cookie_counter++; - } - *cookie = roc->cookie; - } else { - *cookie = (unsigned long)txskb; - } - return 0; } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 21d5d44..e765f77 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1047,6 +1047,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) cancel_work_sync(&local->restart_work); cancel_work_sync(&local->reconfig_filter); + flush_work(&local->sched_scan_stopped_work); ieee80211_clear_tx_pending(local); rate_control_deinitialize(local); diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 22290a9..641f432 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -36,6 +36,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta) sdata->vif.addr); nullfunc->frame_control = fc; nullfunc->duration_id = 0; + nullfunc->seq_ctrl = 0; /* no address resolution for this frame -> set addr 1 immediately */ memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memset(skb_put(skb, 2), 0, 2); /* append QoS control field */ diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 86e4ad5..8d7f4ab 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -282,6 +282,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, switch (vht_oper->chan_width) { case IEEE80211_VHT_CHANWIDTH_USE_HT: vht_chandef.width = chandef->width; + vht_chandef.center_freq1 = chandef->center_freq1; break; case IEEE80211_VHT_CHANWIDTH_80MHZ: vht_chandef.width = NL80211_CHAN_WIDTH_80; @@ -331,6 +332,28 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ret = 0; out: + /* + * When tracking the current AP, don't do any further checks if the + * new chandef is identical to the one we're currently using for the + * connection. This keeps us from playing ping-pong with regulatory, + * without it the following can happen (for example): + * - connect to an AP with 80 MHz, world regdom allows 80 MHz + * - AP advertises regdom US + * - CRDA loads regdom US with 80 MHz prohibited (old database) + * - the code below detects an unsupported channel, downgrades, and + * we disconnect from the AP in the caller + * - disconnect causes CRDA to reload world regdomain and the game + * starts anew. + * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881) + * + * It seems possible that there are still scenarios with CSA or real + * bandwidth changes where a this could happen, but those cases are + * less common and wouldn't completely prevent using the AP. + */ + if (tracking && + cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef)) + return ret; + /* don't print the message below for VHT mismatch if VHT is disabled */ if (ret & IEEE80211_STA_DISABLE_VHT) vht_chandef = *chandef; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 674eac1..1e5bd0d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -911,7 +911,8 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, u16 sc; u8 tid, ack_policy; - if (!ieee80211_is_data_qos(hdr->frame_control)) + if (!ieee80211_is_data_qos(hdr->frame_control) || + is_multicast_ether_addr(hdr->addr1)) goto dont_reorder; /* diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index d2d17a4..8f2f003 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -1089,6 +1089,6 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw) trace_api_sched_scan_stopped(local); - ieee80211_queue_work(&local->hw, &local->sched_scan_stopped_work); + schedule_work(&local->sched_scan_stopped_work); } EXPORT_SYMBOL(ieee80211_sched_scan_stopped); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index aeb967a..db41c19 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -340,6 +340,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, return NULL; spin_lock_init(&sta->lock); + spin_lock_init(&sta->ps_lock); INIT_WORK(&sta->drv_unblock_wk, sta_unblock); INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); mutex_init(&sta->ampdu_mlme.mtx); @@ -1049,6 +1050,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) skb_queue_head_init(&pending); + /* sync with ieee80211_tx_h_unicast_ps_buf */ + spin_lock(&sta->ps_lock); /* Send all buffered frames to the station */ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { int count = skb_queue_len(&pending), tmp; @@ -1068,6 +1071,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) } ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta); + spin_unlock(&sta->ps_lock); local->total_ps_buffered -= buffered; @@ -1114,6 +1118,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN); memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN); + nullfunc->seq_ctrl = 0; skb->priority = tid; skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 4208dbd..492d59c 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -245,6 +245,7 @@ struct sta_ampdu_mlme { * @drv_unblock_wk: used for driver PS unblocking * @listen_interval: listen interval of this station, when we're acting as AP * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly + * @ps_lock: used for powersave (when mac80211 is the AP) related locking * @ps_tx_buf: buffers (per AC) of frames to transmit to this station * when it leaves power saving state or polls * @tx_filtered: buffers (per AC) of frames we already tried to @@ -328,10 +329,8 @@ struct sta_info { /* use the accessors defined below */ unsigned long _flags; - /* - * STA powersave frame queues, no more than the internal - * locking required. - */ + /* STA powersave lock and frame queues */ + spinlock_t ps_lock; struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS]; struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS]; unsigned long driver_buffered_tids; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 70b5a05..d6a47e7 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -463,7 +463,6 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) { struct sta_info *sta = tx->sta; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; struct ieee80211_local *local = tx->local; if (unlikely(!sta)) @@ -474,19 +473,24 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) { int ac = skb_get_queue_mapping(tx->skb); - /* only deauth, disassoc and action are bufferable MMPDUs */ - if (ieee80211_is_mgmt(hdr->frame_control) && - !ieee80211_is_deauth(hdr->frame_control) && - !ieee80211_is_disassoc(hdr->frame_control) && - !ieee80211_is_action(hdr->frame_control)) { - info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; - return TX_CONTINUE; - } - ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n", sta->sta.addr, sta->sta.aid, ac); if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) purge_old_ps_buffers(tx->local); + + /* sync with ieee80211_sta_ps_deliver_wakeup */ + spin_lock(&sta->ps_lock); + /* + * STA woke up the meantime and all the frames on ps_tx_buf have + * been queued to pending queue. No reordering can happen, go + * ahead and Tx the packet. + */ + if (!test_sta_flag(sta, WLAN_STA_PS_STA) && + !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { + spin_unlock(&sta->ps_lock); + return TX_CONTINUE; + } + if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) { struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]); ps_dbg(tx->sdata, @@ -500,6 +504,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) info->control.vif = &tx->sdata->vif; info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb); + spin_unlock(&sta->ps_lock); if (!timer_pending(&local->sta_cleanup)) mod_timer(&local->sta_cleanup, @@ -525,9 +530,22 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) static ieee80211_tx_result debug_noinline ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; + if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED)) return TX_CONTINUE; + /* only deauth, disassoc and action are bufferable MMPDUs */ + if (ieee80211_is_mgmt(hdr->frame_control) && + !ieee80211_is_deauth(hdr->frame_control) && + !ieee80211_is_disassoc(hdr->frame_control) && + !ieee80211_is_action(hdr->frame_control)) { + if (tx->flags & IEEE80211_TX_UNICAST) + info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; + return TX_CONTINUE; + } + if (tx->flags & IEEE80211_TX_UNICAST) return ieee80211_tx_h_unicast_ps_buf(tx); else @@ -871,7 +889,7 @@ static int ieee80211_fragment(struct ieee80211_tx_data *tx, } /* adjust first fragment's length */ - skb->len = hdrlen + per_fragm; + skb_trim(skb, hdrlen + per_fragm); return 0; } diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index afba19c..a282fdd 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -153,6 +153,11 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, return IEEE80211_AC_BE; } + if (skb->protocol == sdata->control_port_protocol) { + skb->priority = 7; + return ieee80211_downgrade_queue(sdata, skb); + } + /* use the data classifier to determine what 802.1d tag the * data frame has */ skb->priority = cfg80211_classify8021d(skb); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 4c8e5c0..d585626 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -871,11 +871,11 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, cp->protocol = p->protocol; ip_vs_addr_set(p->af, &cp->caddr, p->caddr); cp->cport = p->cport; - ip_vs_addr_set(p->af, &cp->vaddr, p->vaddr); - cp->vport = p->vport; - /* proto should only be IPPROTO_IP if d_addr is a fwmark */ + /* proto should only be IPPROTO_IP if p->vaddr is a fwmark */ ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, - &cp->daddr, daddr); + &cp->vaddr, p->vaddr); + cp->vport = p->vport; + ip_vs_addr_set(p->af, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; cp->fwmark = fwmark; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 74fd00c..3581736 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1139,12 +1139,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iph_skb(af, skb, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (!iph.fragoffs && skb_nfct_reasm(skb)) { - struct sk_buff *reasm = skb_nfct_reasm(skb); - /* Save fw mark for coming frags */ - reasm->ipvs_property = 1; - reasm->mark = skb->mark; - } if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_out_icmp_v6(skb, &related, @@ -1614,12 +1608,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (!iph.fragoffs && skb_nfct_reasm(skb)) { - struct sk_buff *reasm = skb_nfct_reasm(skb); - /* Save fw mark for coming frags. */ - reasm->ipvs_property = 1; - reasm->mark = skb->mark; - } if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum, @@ -1671,9 +1659,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, 0, "ip_vs_in: packet continues traversal as normal"); - if (iph.fragoffs && !skb_nfct_reasm(skb)) { + if (iph.fragoffs) { /* Fragment that couldn't be mapped to a conn entry - * and don't have any pointer to a reasm skb * is missing module nf_defrag_ipv6 */ IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); @@ -1756,38 +1743,6 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 /* - * AF_INET6 fragment handling - * Copy info from first fragment, to the rest of them. - */ -static unsigned int -ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *reasm = skb_nfct_reasm(skb); - struct net *net; - - /* Skip if not a "replay" from nf_ct_frag6_output or first fragment. - * ipvs_property is set when checking first fragment - * in ip_vs_in() and ip_vs_out(). - */ - if (reasm) - IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property); - if (!reasm || !reasm->ipvs_property) - return NF_ACCEPT; - - net = skb_net(skb); - if (!net_ipvs(net)->enable) - return NF_ACCEPT; - - /* Copy stored fw mark, saved in ip_vs_{in,out} */ - skb->mark = reasm->mark; - - return NF_ACCEPT; -} - -/* * AF_INET6 handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ @@ -1924,14 +1879,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .priority = 100, }, #ifdef CONFIG_IP_VS_IPV6 - /* After mangle & nat fetch 2:nd fragment and following */ - { - .hook = ip_vs_preroute_frag6, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_NAT_DST + 1, - }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index 9ef22bd..bed5f70 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -65,7 +65,6 @@ static int get_callid(const char *dptr, unsigned int dataoff, static int ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) { - struct sk_buff *reasm = skb_nfct_reasm(skb); struct ip_vs_iphdr iph; unsigned int dataoff, datalen, matchoff, matchlen; const char *dptr; @@ -79,15 +78,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) /* todo: IPv6 fragments: * I think this only should be done for the first fragment. /HS */ - if (reasm) { - skb = reasm; - dataoff = iph.thoff_reasm + sizeof(struct udphdr); - } else - dataoff = iph.len + sizeof(struct udphdr); + dataoff = iph.len + sizeof(struct udphdr); if (dataoff >= skb->len) return -EINVAL; - /* todo: Check if this will mess-up the reasm skb !!! /HS */ retc = skb_linearize(skb); if (retc < 0) return retc; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index a99b6c3..59359be 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -428,7 +428,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const char *msg; u_int8_t state; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh); + dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); BUG_ON(dh == NULL); state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; @@ -486,7 +486,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, u_int8_t type, old_state, new_state; enum ct_dccp_roles role; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh); + dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); BUG_ON(dh == NULL); type = dh->dccph_type; @@ -577,7 +577,7 @@ static int dccp_error(struct net *net, struct nf_conn *tmpl, unsigned int cscov; const char *msg; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh); + dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); if (dh == NULL) { msg = "nf_ct_dccp: short packet "; goto out_invalid; diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index 5f9bfd0..17c1bcb 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -41,8 +41,8 @@ int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo, spin_lock_bh(&ct->lock); this_way = &seqadj->seq[dir]; if (this_way->offset_before == this_way->offset_after || - before(this_way->correction_pos, seq)) { - this_way->correction_pos = seq; + before(this_way->correction_pos, ntohl(seq))) { + this_way->correction_pos = ntohl(seq); this_way->offset_before = this_way->offset_after; this_way->offset_after += off; } diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c index f02b360..1fb2258 100644 --- a/net/netfilter/nf_nat_irc.c +++ b/net/netfilter/nf_nat_irc.c @@ -34,10 +34,14 @@ static unsigned int help(struct sk_buff *skb, struct nf_conntrack_expect *exp) { char buffer[sizeof("4294967296 65635")]; + struct nf_conn *ct = exp->master; + union nf_inet_addr newaddr; u_int16_t port; unsigned int ret; /* Reply comes from server. */ + newaddr = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3; + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; exp->dir = IP_CT_DIR_REPLY; exp->expectfn = nf_nat_follow_master; @@ -57,17 +61,35 @@ static unsigned int help(struct sk_buff *skb, } if (port == 0) { - nf_ct_helper_log(skb, exp->master, "all ports in use"); + nf_ct_helper_log(skb, ct, "all ports in use"); return NF_DROP; } - ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo, - protoff, matchoff, matchlen, buffer, - strlen(buffer)); + /* strlen("\1DCC CHAT chat AAAAAAAA P\1\n")=27 + * strlen("\1DCC SCHAT chat AAAAAAAA P\1\n")=28 + * strlen("\1DCC SEND F AAAAAAAA P S\1\n")=26 + * strlen("\1DCC MOVE F AAAAAAAA P S\1\n")=26 + * strlen("\1DCC TSEND F AAAAAAAA P S\1\n")=27 + * + * AAAAAAAAA: bound addr (1.0.0.0==16777216, min 8 digits, + * 255.255.255.255==4294967296, 10 digits) + * P: bound port (min 1 d, max 5d (65635)) + * F: filename (min 1 d ) + * S: size (min 1 d ) + * 0x01, \n: terminators + */ + /* AAA = "us", ie. where server normally talks to. */ + snprintf(buffer, sizeof(buffer), "%u %u", ntohl(newaddr.ip), port); + pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n", + buffer, &newaddr.ip, port); + + ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff, + matchlen, buffer, strlen(buffer)); if (ret != NF_ACCEPT) { - nf_ct_helper_log(skb, exp->master, "cannot mangle packet"); + nf_ct_helper_log(skb, ct, "cannot mangle packet"); nf_ct_unexpect_related(exp); } + return ret; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 8df7f64..6135635 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2335,8 +2335,6 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, } #endif - msg->msg_namelen = 0; - copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 698814b..53c19a3 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1179,10 +1179,9 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock, sax->sax25_family = AF_NETROM; skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call, AX25_ADDR_LEN); + msg->msg_namelen = sizeof(*sax); } - msg->msg_namelen = sizeof(*sax); - skb_free_datagram(sk, skb); release_sock(sk); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index d308402..824c605 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -807,8 +807,6 @@ 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/nfc/rawsock.c b/net/nfc/rawsock.c index 313bf1b..5d11f4a 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -241,8 +241,6 @@ static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return rc; - msg->msg_namelen = 0; - copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2e8286b..88cfbc1 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -237,6 +237,30 @@ struct packet_skb_cb { static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); +static struct net_device *packet_cached_dev_get(struct packet_sock *po) +{ + struct net_device *dev; + + rcu_read_lock(); + dev = rcu_dereference(po->cached_dev); + if (likely(dev)) + dev_hold(dev); + rcu_read_unlock(); + + return dev; +} + +static void packet_cached_dev_assign(struct packet_sock *po, + struct net_device *dev) +{ + rcu_assign_pointer(po->cached_dev, dev); +} + +static void packet_cached_dev_reset(struct packet_sock *po) +{ + RCU_INIT_POINTER(po->cached_dev, NULL); +} + /* register_prot_hook must be invoked with the po->bind_lock held, * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). @@ -244,11 +268,13 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po); static void register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); + if (!po->running) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); + sock_hold(sk); po->running = 1; } @@ -266,10 +292,12 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) struct packet_sock *po = pkt_sk(sk); po->running = 0; + if (po->fanout) __fanout_unlink(sk, po); else __dev_remove_pack(&po->prot_hook); + __sock_put(sk); if (sync) { @@ -432,9 +460,9 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po, pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc; - spin_lock(&rb_queue->lock); + spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; - spin_unlock(&rb_queue->lock); + spin_unlock_bh(&rb_queue->lock); prb_del_retire_blk_timer(pkc); } @@ -2057,7 +2085,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) struct sk_buff *skb; struct net_device *dev; __be16 proto; - bool need_rls_dev = false; int err, reserve = 0; void *ph; struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; @@ -2069,8 +2096,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) mutex_lock(&po->pg_vec_lock); - if (saddr == NULL) { - dev = po->prot_hook.dev; + if (likely(saddr == NULL)) { + dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; } else { @@ -2084,19 +2111,17 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) proto = saddr->sll_protocol; addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); - need_rls_dev = true; } err = -ENXIO; if (unlikely(dev == NULL)) goto out; - - reserve = dev->hard_header_len; - err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; + reserve = dev->hard_header_len; + size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2173,8 +2198,7 @@ out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: - if (need_rls_dev) - dev_put(dev); + dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; @@ -2212,7 +2236,6 @@ static int packet_snd(struct socket *sock, struct sk_buff *skb; struct net_device *dev; __be16 proto; - bool need_rls_dev = false; unsigned char *addr; int err, reserve = 0; struct virtio_net_hdr vnet_hdr = { 0 }; @@ -2227,8 +2250,8 @@ static int packet_snd(struct socket *sock, * Get and verify the address. */ - if (saddr == NULL) { - dev = po->prot_hook.dev; + if (likely(saddr == NULL)) { + dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; } else { @@ -2240,19 +2263,17 @@ static int packet_snd(struct socket *sock, proto = saddr->sll_protocol; addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); - need_rls_dev = true; } err = -ENXIO; - if (dev == NULL) + if (unlikely(dev == NULL)) goto out_unlock; - if (sock->type == SOCK_RAW) - reserve = dev->hard_header_len; - err = -ENETDOWN; - if (!(dev->flags & IFF_UP)) + if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; + if (sock->type == SOCK_RAW) + reserve = dev->hard_header_len; if (po->has_vnet_hdr) { vnet_hdr_len = sizeof(vnet_hdr); @@ -2386,15 +2407,14 @@ static int packet_snd(struct socket *sock, if (err > 0 && (err = net_xmit_errno(err)) != 0) goto out_unlock; - if (need_rls_dev) - dev_put(dev); + dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: - if (dev && need_rls_dev) + if (dev) dev_put(dev); out: return err; @@ -2439,6 +2459,8 @@ static int packet_release(struct socket *sock) spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); + packet_cached_dev_reset(po); + if (po->prot_hook.dev) { dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -2494,14 +2516,17 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc spin_lock(&po->bind_lock); unregister_prot_hook(sk, true); + po->num = protocol; po->prot_hook.type = protocol; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); - po->prot_hook.dev = dev; + po->prot_hook.dev = dev; po->ifindex = dev ? dev->ifindex : 0; + packet_cached_dev_assign(po, dev); + if (protocol == 0) goto out_unlock; @@ -2615,6 +2640,8 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, sk->sk_family = PF_PACKET; po->num = proto; + packet_cached_dev_reset(po); + sk->sk_destruct = packet_sock_destruct; sk_refcnt_debug_inc(sk); @@ -2660,7 +2687,6 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; - struct sockaddr_ll *sll; int vnet_hdr_len = 0; err = -EINVAL; @@ -2744,22 +2770,10 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, goto out_free; } - /* - * If the address length field is there to be filled in, we fill - * it in now. + /* You lose any data beyond the buffer you gave. If it worries + * a user program they can ask the device for its MTU + * anyway. */ - - sll = &PACKET_SKB_CB(skb)->sa.ll; - if (sock->type == SOCK_PACKET) - msg->msg_namelen = sizeof(struct sockaddr_pkt); - else - msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); - - /* - * You lose any data beyond the buffer you gave. If it worries a - * user program they can ask the device for its MTU anyway. - */ - copied = skb->len; if (copied > len) { copied = len; @@ -2772,9 +2786,20 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, sock_recv_ts_and_drops(msg, sk, skb); - if (msg->msg_name) + if (msg->msg_name) { + /* If the address length field is there to be filled + * in, we fill it in now. + */ + if (sock->type == SOCK_PACKET) { + msg->msg_namelen = sizeof(struct sockaddr_pkt); + } else { + struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + msg->msg_namelen = sll->sll_halen + + offsetof(struct sockaddr_ll, sll_addr); + } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, msg->msg_namelen); + } if (pkt_sk(sk)->auxdata) { struct tpacket_auxdata aux; @@ -3326,6 +3351,7 @@ static int packet_notifier(struct notifier_block *this, sk->sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { + packet_cached_dev_reset(po); po->ifindex = -1; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); diff --git a/net/packet/internal.h b/net/packet/internal.h index c4e4b45..1035fa2 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -113,6 +113,7 @@ struct packet_sock { unsigned int tp_loss:1; unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; + struct net_device __rcu *cached_dev; struct packet_type prot_hook ____cacheline_aligned_in_smp; }; diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 12c30f3..38946b2 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -139,9 +139,6 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk, MSG_CMSG_COMPAT)) goto out_nofree; - if (addr_len) - *addr_len = sizeof(sa); - skb = skb_recv_datagram(sk, flags, noblock, &rval); if (skb == NULL) goto out_nofree; @@ -162,8 +159,10 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk, rval = (flags & MSG_TRUNC) ? skb->len : copylen; - if (msg->msg_name != NULL) - memcpy(msg->msg_name, &sa, sizeof(struct sockaddr_pn)); + if (msg->msg_name != NULL) { + memcpy(msg->msg_name, &sa, sizeof(sa)); + *addr_len = sizeof(sa); + } out: skb_free_datagram(sk, skb); diff --git a/net/rds/ib.c b/net/rds/ib.c index b4c8b00..ba2dffe 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -338,7 +338,8 @@ static int rds_ib_laddr_check(__be32 addr) ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); /* due to this, we will claim to support iWARP devices unless we check node_type. */ - if (ret || cm_id->device->node_type != RDMA_NODE_IB_CA) + if (ret || !cm_id->device || + cm_id->device->node_type != RDMA_NODE_IB_CA) ret = -EADDRNOTAVAIL; rdsdebug("addr %pI4 ret %d node type %d\n", diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 8eb9501..b7ebe23 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -421,8 +421,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item, struct rds_ib_refill_cache *cache) { unsigned long flags; - struct list_head *old; - struct list_head __percpu *chpfirst; + struct list_head *old, *chpfirst; local_irq_save(flags); @@ -432,7 +431,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item, else /* put on front */ list_add_tail(new_item, chpfirst); - __this_cpu_write(chpfirst, new_item); + __this_cpu_write(cache->percpu->first, new_item); __this_cpu_inc(cache->percpu->count); if (__this_cpu_read(cache->percpu->count) < RDS_IB_RECYCLE_BATCH_COUNT) @@ -452,7 +451,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item, } while (old); - __this_cpu_write(chpfirst, NULL); + __this_cpu_write(cache->percpu->first, NULL); __this_cpu_write(cache->percpu->count, 0); end: local_irq_restore(flags); diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index e590949..37be6e2 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -552,9 +552,8 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { rds_cong_map_updated(conn->c_fcong, ~(u64) 0); scat = &rm->data.op_sg[sg]; - ret = sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; - ret = min_t(int, ret, scat->length - conn->c_xmit_data_off); - return ret; + ret = max_t(int, RDS_CONG_MAP_BYTES, scat->length); + return sizeof(struct rds_header) + ret; } /* FIXME we may overallocate here */ diff --git a/net/rds/recv.c b/net/rds/recv.c index 9f0f17c..de339b2 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -410,8 +410,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo); - msg->msg_namelen = 0; - if (msg_flags & MSG_OOB) goto out; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index e98fcfb..62ced65 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1216,7 +1216,6 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); - struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name; size_t copied; unsigned char *asmptr; struct sk_buff *skb; @@ -1252,24 +1251,19 @@ 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); + if (msg->msg_name) { + struct sockaddr_rose *srose; + struct full_sockaddr_rose *full_srose = msg->msg_name; + + memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose)); + srose = msg->msg_name; srose->srose_family = AF_ROSE; srose->srose_addr = rose->dest_addr; srose->srose_call = rose->dest_call; srose->srose_ndigis = rose->dest_ndigis; - if (msg->msg_namelen >= sizeof(struct full_sockaddr_rose)) { - struct full_sockaddr_rose *full_srose = (struct full_sockaddr_rose *)msg->msg_name; - for (n = 0 ; n < rose->dest_ndigis ; n++) - full_srose->srose_digis[n] = rose->dest_digis[n]; - msg->msg_namelen = sizeof(struct full_sockaddr_rose); - } else { - if (rose->dest_ndigis >= 1) { - srose->srose_ndigis = 1; - srose->srose_digi = rose->dest_digis[0]; - } - msg->msg_namelen = sizeof(struct sockaddr_rose); - } + for (n = 0 ; n < rose->dest_ndigis ; n++) + full_srose->srose_digis[n] = rose->dest_digis[n]; + msg->msg_namelen = sizeof(struct full_sockaddr_rose); } skb_free_datagram(sk, skb); diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 4b48687..898492a 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -143,10 +143,13 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, /* copy the peer address and timestamp */ if (!continue_call) { - if (msg->msg_name && msg->msg_namelen > 0) + if (msg->msg_name) { + size_t len = + sizeof(call->conn->trans->peer->srx); memcpy(msg->msg_name, - &call->conn->trans->peer->srx, - sizeof(call->conn->trans->peer->srx)); + &call->conn->trans->peer->srx, len); + msg->msg_namelen = len; + } sock_recv_ts_and_drops(msg, &rx->sk, skb); } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a9dfdda..2e55f81 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -88,7 +88,7 @@ struct fq_sched_data { struct fq_flow internal; /* for non classified or high prio packets */ u32 quantum; u32 initial_quantum; - u32 flow_default_rate;/* rate per flow : bytes per second */ + u32 flow_refill_delay; u32 flow_max_rate; /* optional max rate per flow */ u32 flow_plimit; /* max packets per flow */ struct rb_root *fq_root; @@ -115,6 +115,7 @@ static struct fq_flow detached, throttled; static void fq_flow_set_detached(struct fq_flow *f) { f->next = &detached; + f->age = jiffies; } static bool fq_flow_is_detached(const struct fq_flow *f) @@ -209,21 +210,15 @@ static void fq_gc(struct fq_sched_data *q, } } -static const u8 prio2band[TC_PRIO_MAX + 1] = { - 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 -}; - static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) { struct rb_node **p, *parent; struct sock *sk = skb->sk; struct rb_root *root; struct fq_flow *f; - int band; /* warning: no starvation prevention... */ - band = prio2band[skb->priority & TC_PRIO_MAX]; - if (unlikely(band == 0)) + if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL)) return &q->internal; if (unlikely(!sk)) { @@ -372,17 +367,20 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch) } f->qlen++; - flow_queue_add(f, skb); if (skb_is_retransmit(skb)) q->stat_tcp_retrans++; sch->qstats.backlog += qdisc_pkt_len(skb); if (fq_flow_is_detached(f)) { fq_flow_add_tail(&q->new_flows, f); - if (q->quantum > f->credit) - f->credit = q->quantum; + if (time_after(jiffies, f->age + q->flow_refill_delay)) + f->credit = max_t(u32, f->credit, q->quantum); q->inactive_flows--; qdisc_unthrottled(sch); } + + /* Note: this overwrites f->age */ + flow_queue_add(f, skb); + if (unlikely(f == &q->internal)) { q->stat_internal_packets++; qdisc_unthrottled(sch); @@ -460,7 +458,6 @@ begin: fq_flow_add_tail(&q->old_flows, f); } else { fq_flow_set_detached(f); - f->age = jiffies; q->inactive_flows++; } goto begin; @@ -614,6 +611,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_FLOW_DEFAULT_RATE] = { .type = NLA_U32 }, [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, + [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, }; static int fq_change(struct Qdisc *sch, struct nlattr *opt) @@ -655,7 +653,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]); if (tb[TCA_FQ_FLOW_DEFAULT_RATE]) - q->flow_default_rate = nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE]); + pr_warn_ratelimited("sch_fq: defrate %u ignored.\n", + nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE])); if (tb[TCA_FQ_FLOW_MAX_RATE]) q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); @@ -669,6 +668,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) err = -EINVAL; } + if (tb[TCA_FQ_FLOW_REFILL_DELAY]) { + u32 usecs_delay = nla_get_u32(tb[TCA_FQ_FLOW_REFILL_DELAY]) ; + + q->flow_refill_delay = usecs_to_jiffies(usecs_delay); + } + if (!err) err = fq_resize(q, fq_log); @@ -704,7 +709,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) q->flow_plimit = 100; q->quantum = 2 * psched_mtu(qdisc_dev(sch)); q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch)); - q->flow_default_rate = 0; + q->flow_refill_delay = msecs_to_jiffies(40); q->flow_max_rate = ~0U; q->rate_enable = 1; q->new_flows.first = NULL; @@ -731,15 +736,16 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) if (opts == NULL) goto nla_put_failure; - /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore, - * do not bother giving its value - */ + /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore */ + if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) || nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) || nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) || nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) || nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) || nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) || + nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY, + jiffies_to_usecs(q->flow_refill_delay)) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 8994543..29e1c2a 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -130,6 +130,16 @@ struct tbf_sched_data { }; +/* + * Return length of individual segments of a gso packet, + * including all headers (MAC, IP, TCP/UDP) + */ +static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + return hdr_len + skb_gso_transport_seglen(skb); +} + /* GSO packet is too big, segment it so that tbf can transmit * each segment in time */ @@ -149,12 +159,8 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) while (segs) { nskb = segs->next; segs->next = NULL; - if (likely(segs->len <= q->max_size)) { - qdisc_skb_cb(segs)->pkt_len = segs->len; - ret = qdisc_enqueue(segs, q->qdisc); - } else { - ret = qdisc_reshape_fail(skb, sch); - } + qdisc_skb_cb(segs)->pkt_len = segs->len; + ret = qdisc_enqueue(segs, q->qdisc); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) sch->qstats.drops++; @@ -176,7 +182,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) int ret; if (qdisc_pkt_len(skb) > q->max_size) { - if (skb_is_gso(skb)) + if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size) return tbf_segment(skb, sch); return qdisc_reshape_fail(skb, sch); } @@ -329,6 +335,11 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) if (max_size < 0) goto done; + if (max_size < psched_mtu(qdisc_dev(sch))) + pr_warn_ratelimited("sch_tbf: burst %u is lower than device %s mtu (%u) !\n", + max_size, qdisc_dev(sch)->name, + psched_mtu(qdisc_dev(sch))); + if (q->qdisc != &noop_qdisc) { err = fifo_set_limit(q->qdisc, qopt->limit); if (err) diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 666c668..1a6eef3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -860,7 +860,6 @@ static void sctp_cmd_delete_tcb(sctp_cmd_seq_t *cmds, (!asoc->temp) && (sk->sk_shutdown != SHUTDOWN_MASK)) return; - BUG_ON(asoc->peer.primary_path == NULL); sctp_unhash_established(asoc); sctp_association_free(asoc); } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index dfe3f36..56ebe71 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -759,6 +759,13 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, struct sctp_chunk auth; sctp_ierror_t ret; + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { + kfree_skb(chunk->auth_chunk); + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + /* set-up our fake chunk so that we can process it */ auth.skb = chunk->auth_chunk; auth.asoc = chunk->asoc; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 911b71b..14c8015 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -65,6 +65,7 @@ #include <linux/crypto.h> #include <linux/slab.h> #include <linux/file.h> +#include <linux/compat.h> #include <net/ip.h> #include <net/icmp.h> @@ -1369,11 +1370,19 @@ static int sctp_setsockopt_connectx(struct sock* sk, /* * New (hopefully final) interface for the API. * We use the sctp_getaddrs_old structure so that use-space library - * can avoid any unnecessary allocations. The only defferent part + * can avoid any unnecessary allocations. The only different part * is that we store the actual length of the address buffer into the - * addrs_num structure member. That way we can re-use the existing + * addrs_num structure member. That way we can re-use the existing * code. */ +#ifdef CONFIG_COMPAT +struct compat_sctp_getaddrs_old { + sctp_assoc_t assoc_id; + s32 addr_num; + compat_uptr_t addrs; /* struct sockaddr * */ +}; +#endif + static int sctp_getsockopt_connectx3(struct sock* sk, int len, char __user *optval, int __user *optlen) @@ -1382,16 +1391,30 @@ static int sctp_getsockopt_connectx3(struct sock* sk, int len, sctp_assoc_t assoc_id = 0; int err = 0; - if (len < sizeof(param)) - return -EINVAL; +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + struct compat_sctp_getaddrs_old param32; - if (copy_from_user(¶m, optval, sizeof(param))) - return -EFAULT; + if (len < sizeof(param32)) + return -EINVAL; + if (copy_from_user(¶m32, optval, sizeof(param32))) + return -EFAULT; - err = __sctp_setsockopt_connectx(sk, - (struct sockaddr __user *)param.addrs, - param.addr_num, &assoc_id); + param.assoc_id = param32.assoc_id; + param.addr_num = param32.addr_num; + param.addrs = compat_ptr(param32.addrs); + } else +#endif + { + if (len < sizeof(param)) + return -EINVAL; + if (copy_from_user(¶m, optval, sizeof(param))) + return -EFAULT; + } + err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *) + param.addrs, param.addr_num, + &assoc_id); if (err == 0 || err == -EINPROGRESS) { if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) return -EFAULT; diff --git a/net/socket.c b/net/socket.c index c226ace..e83c416 100644 --- a/net/socket.c +++ b/net/socket.c @@ -221,12 +221,13 @@ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, int err; int len; + BUG_ON(klen > sizeof(struct sockaddr_storage)); err = get_user(len, ulen); if (err) return err; if (len > klen) len = klen; - if (len < 0 || len > sizeof(struct sockaddr_storage)) + if (len < 0) return -EINVAL; if (len) { if (audit_sockaddr(klen, kaddr)) @@ -1840,8 +1841,10 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, msg.msg_iov = &iov; iov.iov_len = size; iov.iov_base = ubuf; - msg.msg_name = (struct sockaddr *)&address; - msg.msg_namelen = sizeof(address); + /* Save some cycles and don't copy the address if not needed */ + msg.msg_name = addr ? (struct sockaddr *)&address : NULL; + /* We assume all kernel code knows the size of sockaddr_storage */ + msg.msg_namelen = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, size, flags); @@ -1970,7 +1973,7 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) return -EFAULT; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) - return -EINVAL; + kmsg->msg_namelen = sizeof(struct sockaddr_storage); return 0; } @@ -2221,16 +2224,14 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, goto out; } - /* - * Save the user-mode address (verify_iovec will change the - * kernel msghdr to use the kernel address space) + /* Save the user-mode address (verify_iovec will change the + * kernel msghdr to use the kernel address space) */ - uaddr = (__force void __user *)msg_sys->msg_name; uaddr_len = COMPAT_NAMELEN(msg); - if (MSG_CMSG_COMPAT & flags) { + if (MSG_CMSG_COMPAT & flags) err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE); - } else + else err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE); if (err < 0) goto out_freeiov; @@ -2239,6 +2240,9 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); + /* We assume all kernel code knows the size of sockaddr_storage */ + msg_sys->msg_namelen = 0; + if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 0846566..bb035f8 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -108,6 +108,7 @@ struct gss_auth { static DEFINE_SPINLOCK(pipe_version_lock); static struct rpc_wait_queue pipe_version_rpc_waitqueue; static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue); +static void gss_put_auth(struct gss_auth *gss_auth); static void gss_free_ctx(struct gss_cl_ctx *); static const struct rpc_pipe_ops gss_upcall_ops_v0; @@ -320,6 +321,7 @@ gss_release_msg(struct gss_upcall_msg *gss_msg) if (gss_msg->ctx != NULL) gss_put_ctx(gss_msg->ctx); rpc_destroy_wait_queue(&gss_msg->rpc_waitqueue); + gss_put_auth(gss_msg->auth); kfree(gss_msg); } @@ -482,9 +484,11 @@ gss_alloc_msg(struct gss_auth *gss_auth, switch (vers) { case 0: gss_encode_v0_msg(gss_msg); + break; default: gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name); }; + kref_get(&gss_auth->kref); return gss_msg; } @@ -1052,6 +1056,12 @@ gss_free_callback(struct kref *kref) } static void +gss_put_auth(struct gss_auth *gss_auth) +{ + kref_put(&gss_auth->kref, gss_free_callback); +} + +static void gss_destroy(struct rpc_auth *auth) { struct gss_auth *gss_auth = container_of(auth, @@ -1072,7 +1082,7 @@ gss_destroy(struct rpc_auth *auth) gss_auth->gss_pipe[1] = NULL; rpcauth_destroy_credcache(auth); - kref_put(&gss_auth->kref, gss_free_callback); + gss_put_auth(gss_auth); } /* @@ -1243,7 +1253,7 @@ gss_destroy_nullcred(struct rpc_cred *cred) call_rcu(&cred->cr_rcu, gss_free_cred_callback); if (ctx) gss_put_ctx(ctx); - kref_put(&gss_auth->kref, gss_free_callback); + gss_put_auth(gss_auth); } static void @@ -1498,7 +1508,7 @@ out: static int gss_refresh_null(struct rpc_task *task) { - return -EACCES; + return 0; } static __be32 * diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index f1eb0d1..23fa3c1 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -137,7 +137,6 @@ void init_gssp_clnt(struct sunrpc_net *sn) { mutex_init(&sn->gssp_lock); sn->gssp_clnt = NULL; - init_waitqueue_head(&sn->gssp_wq); } int set_gssp_clnt(struct net *net) @@ -154,7 +153,6 @@ int set_gssp_clnt(struct net *net) sn->gssp_clnt = clnt; } mutex_unlock(&sn->gssp_lock); - wake_up(&sn->gssp_wq); return ret; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 09fb638..e18be86 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1295,34 +1295,9 @@ static int set_gss_proxy(struct net *net, int type) else ret = -EBUSY; spin_unlock(&use_gssp_lock); - wake_up(&sn->gssp_wq); return ret; } -static inline bool gssp_ready(struct sunrpc_net *sn) -{ - switch (sn->use_gss_proxy) { - case -1: - return false; - case 0: - return true; - case 1: - return sn->gssp_clnt; - } - WARN_ON_ONCE(1); - return false; -} - -static int wait_for_gss_proxy(struct net *net, struct file *file) -{ - struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); - - if (file->f_flags & O_NONBLOCK && !gssp_ready(sn)) - return -EAGAIN; - return wait_event_interruptible(sn->gssp_wq, gssp_ready(sn)); -} - - static ssize_t write_gssp(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -1355,16 +1330,12 @@ static ssize_t read_gssp(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct net *net = PDE_DATA(file_inode(file)); + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); unsigned long p = *ppos; char tbuf[10]; size_t len; - int ret; - - ret = wait_for_gss_proxy(net, file); - if (ret) - return ret; - snprintf(tbuf, sizeof(tbuf), "%d\n", use_gss_proxy(net)); + snprintf(tbuf, sizeof(tbuf), "%d\n", sn->use_gss_proxy); len = strlen(tbuf); if (p >= len) return 0; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 7747960..f318a95 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -656,14 +656,16 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client); /* * Free an RPC client */ -static void +static struct rpc_clnt * rpc_free_client(struct rpc_clnt *clnt) { + struct rpc_clnt *parent = NULL; + dprintk_rcu("RPC: destroying %s client for %s\n", clnt->cl_program->name, rcu_dereference(clnt->cl_xprt)->servername); if (clnt->cl_parent != clnt) - rpc_release_client(clnt->cl_parent); + parent = clnt->cl_parent; rpc_clnt_remove_pipedir(clnt); rpc_unregister_client(clnt); rpc_free_iostats(clnt->cl_metrics); @@ -672,18 +674,17 @@ rpc_free_client(struct rpc_clnt *clnt) rpciod_down(); rpc_free_clid(clnt); kfree(clnt); + return parent; } /* * Free an RPC client */ -static void +static struct rpc_clnt * rpc_free_auth(struct rpc_clnt *clnt) { - if (clnt->cl_auth == NULL) { - rpc_free_client(clnt); - return; - } + if (clnt->cl_auth == NULL) + return rpc_free_client(clnt); /* * Note: RPCSEC_GSS may need to send NULL RPC calls in order to @@ -694,7 +695,8 @@ rpc_free_auth(struct rpc_clnt *clnt) rpcauth_release(clnt->cl_auth); clnt->cl_auth = NULL; if (atomic_dec_and_test(&clnt->cl_count)) - rpc_free_client(clnt); + return rpc_free_client(clnt); + return NULL; } /* @@ -705,10 +707,13 @@ rpc_release_client(struct rpc_clnt *clnt) { dprintk("RPC: rpc_release_client(%p)\n", clnt); - if (list_empty(&clnt->cl_tasks)) - wake_up(&destroy_wait); - if (atomic_dec_and_test(&clnt->cl_count)) - rpc_free_auth(clnt); + do { + if (list_empty(&clnt->cl_tasks)) + wake_up(&destroy_wait); + if (!atomic_dec_and_test(&clnt->cl_count)) + break; + clnt = rpc_free_auth(clnt); + } while (clnt != NULL); } EXPORT_SYMBOL_GPL(rpc_release_client); @@ -1428,9 +1433,13 @@ call_refreshresult(struct rpc_task *task) task->tk_action = call_refresh; switch (status) { case 0: - if (rpcauth_uptodatecred(task)) + if (rpcauth_uptodatecred(task)) { task->tk_action = call_allocate; - return; + return; + } + /* Use rate-limiting and a max number of retries if refresh + * had status 0 but failed to update the cred. + */ case -ETIMEDOUT: rpc_delay(task, 3*HZ); case -EAGAIN: diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h index 779742c..3a260e4 100644 --- a/net/sunrpc/netns.h +++ b/net/sunrpc/netns.h @@ -26,7 +26,6 @@ struct sunrpc_net { unsigned int rpcb_is_af_local : 1; struct mutex gssp_lock; - wait_queue_head_t gssp_wq; struct rpc_clnt *gssp_clnt; int use_gss_proxy; int pipe_version; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ee03d35..1d03482 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -393,8 +393,10 @@ static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, return kernel_sendmsg(sock, &msg, NULL, 0, 0); } -static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more) +static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy) { + ssize_t (*do_sendpage)(struct socket *sock, struct page *page, + int offset, size_t size, int flags); struct page **ppage; unsigned int remainder; int err, sent = 0; @@ -403,6 +405,9 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i base += xdr->page_base; ppage = xdr->pages + (base >> PAGE_SHIFT); base &= ~PAGE_MASK; + do_sendpage = sock->ops->sendpage; + if (!zerocopy) + do_sendpage = sock_no_sendpage; for(;;) { unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder); int flags = XS_SENDMSG_FLAGS; @@ -410,7 +415,7 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i remainder -= len; if (remainder != 0 || more) flags |= MSG_MORE; - err = sock->ops->sendpage(sock, *ppage, base, len, flags); + err = do_sendpage(sock, *ppage, base, len, flags); if (remainder == 0 || err != len) break; sent += err; @@ -431,9 +436,10 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i * @addrlen: UDP only -- length of destination address * @xdr: buffer containing this request * @base: starting position in the buffer + * @zerocopy: true if it is safe to use sendpage() * */ -static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base) +static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy) { unsigned int remainder = xdr->len - base; int err, sent = 0; @@ -461,7 +467,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (base < xdr->page_len) { unsigned int len = xdr->page_len - base; remainder -= len; - err = xs_send_pagedata(sock, xdr, base, remainder != 0); + err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy); if (remainder == 0 || err != len) goto out; sent += err; @@ -498,6 +504,7 @@ static int xs_nospace(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + struct sock *sk = transport->inet; int ret = -EAGAIN; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", @@ -515,7 +522,7 @@ static int xs_nospace(struct rpc_task *task) * window size */ set_bit(SOCK_NOSPACE, &transport->sock->flags); - transport->inet->sk_write_pending++; + sk->sk_write_pending++; /* ...and wait for more buffer space */ xprt_wait_for_buffer_space(task, xs_nospace_callback); } @@ -525,6 +532,9 @@ static int xs_nospace(struct rpc_task *task) } spin_unlock_bh(&xprt->transport_lock); + + /* Race breaker in case memory is freed before above code is called */ + sk->sk_write_space(sk); return ret; } @@ -564,7 +574,7 @@ static int xs_local_send_request(struct rpc_task *task) req->rq_svec->iov_base, req->rq_svec->iov_len); status = xs_sendpages(transport->sock, NULL, 0, - xdr, req->rq_bytes_sent); + xdr, req->rq_bytes_sent, true); dprintk("RPC: %s(%u) = %d\n", __func__, xdr->len - req->rq_bytes_sent, status); if (likely(status >= 0)) { @@ -620,7 +630,7 @@ static int xs_udp_send_request(struct rpc_task *task) status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen, xdr, - req->rq_bytes_sent); + req->rq_bytes_sent, true); dprintk("RPC: xs_udp_send_request(%u) = %d\n", xdr->len - req->rq_bytes_sent, status); @@ -693,6 +703,7 @@ static int xs_tcp_send_request(struct rpc_task *task) struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct xdr_buf *xdr = &req->rq_snd_buf; + bool zerocopy = true; int status; xs_encode_stream_record_marker(&req->rq_snd_buf); @@ -700,13 +711,20 @@ static int xs_tcp_send_request(struct rpc_task *task) xs_pktdump("packet data:", req->rq_svec->iov_base, req->rq_svec->iov_len); + /* Don't use zero copy if this is a resend. If the RPC call + * completes while the socket holds a reference to the pages, + * then we may end up resending corrupted data. + */ + if (task->tk_flags & RPC_TASK_SENT) + zerocopy = false; /* Continue transmitting the packet/record. We must be careful * to cope with writespace callbacks arriving _after_ we have * called sendmsg(). */ while (1) { status = xs_sendpages(transport->sock, - NULL, 0, xdr, req->rq_bytes_sent); + NULL, 0, xdr, req->rq_bytes_sent, + zerocopy); dprintk("RPC: xs_tcp_send_request(%u) = %d\n", xdr->len - req->rq_bytes_sent, status); @@ -835,6 +853,8 @@ static void xs_close(struct rpc_xprt *xprt) dprintk("RPC: xs_close xprt %p\n", xprt); + cancel_delayed_work_sync(&transport->connect_worker); + xs_reset_transport(transport); xprt->reestablish_timeout = 0; @@ -869,12 +889,8 @@ static void xs_local_destroy(struct rpc_xprt *xprt) */ static void xs_destroy(struct rpc_xprt *xprt) { - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - dprintk("RPC: xs_destroy xprt %p\n", xprt); - cancel_delayed_work_sync(&transport->connect_worker); - xs_local_destroy(xprt); } @@ -1816,6 +1832,10 @@ static inline void xs_reclassify_socket(int family, struct socket *sock) } #endif +static void xs_dummy_setup_socket(struct work_struct *work) +{ +} + static struct socket *xs_create_sock(struct rpc_xprt *xprt, struct sock_xprt *transport, int family, int type, int protocol) { @@ -2655,6 +2675,9 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) xprt->ops = &xs_local_ops; xprt->timeout = &xs_local_default_timeout; + INIT_DELAYED_WORK(&transport->connect_worker, + xs_dummy_setup_socket); + switch (sun->sun_family) { case AF_LOCAL: if (sun->sun_path[0] != '/') { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 6cc7ddd..dffdbea 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -984,9 +984,6 @@ 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: @@ -1095,9 +1092,6 @@ 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); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c1f403b..d7c1ac6 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -161,9 +161,8 @@ static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb) static inline unsigned int unix_hash_fold(__wsum n) { - unsigned int hash = (__force unsigned int)n; + unsigned int hash = (__force unsigned int)csum_fold(n); - hash ^= hash>>16; hash ^= hash>>8; return hash&(UNIX_HASH_SIZE-1); } @@ -530,13 +529,17 @@ static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, int); -static void unix_set_peek_off(struct sock *sk, int val) +static int unix_set_peek_off(struct sock *sk, int val) { struct unix_sock *u = unix_sk(sk); - mutex_lock(&u->readlock); + if (mutex_lock_interruptible(&u->readlock)) + return -EINTR; + sk->sk_peek_off = val; mutex_unlock(&u->readlock); + + return 0; } @@ -714,7 +717,9 @@ static int unix_autobind(struct socket *sock) int err; unsigned int retries = 0; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) + return err; err = 0; if (u->addr) @@ -873,7 +878,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) + goto out; err = -EINVAL; if (u->addr) @@ -1754,7 +1761,6 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { struct unix_sock *u = unix_sk(sk); - msg->msg_namelen = 0; if (u->addr) { msg->msg_namelen = u->addr->len; memcpy(msg->msg_name, u->addr->name, u->addr->len); @@ -1778,8 +1784,6 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags&MSG_OOB) goto out; - msg->msg_namelen = 0; - err = mutex_lock_interruptible(&u->readlock); if (err) { err = sock_intr_errno(sock_rcvtimeo(sk, noblock)); @@ -1924,8 +1928,6 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, target = sock_rcvlowat(sk, flags&MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT); - msg->msg_namelen = 0; - /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 545c08b..5adfd94 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1662,8 +1662,6 @@ vsock_stream_recvmsg(struct kiocb *kiocb, vsk = vsock_sk(sk); err = 0; - msg->msg_namelen = 0; - lock_sock(sk); if (sk->sk_state != SS_CONNECTED) { diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 9d69866..687360d 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1746,8 +1746,6 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb, if (flags & MSG_OOB || flags & MSG_ERRQUEUE) return -EOPNOTSUPP; - msg->msg_namelen = 0; - /* Retrieve the head sk_buff from the socket's receive queue. */ err = 0; skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err); diff --git a/net/wireless/core.c b/net/wireless/core.c index aff959e..00a65ba 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -451,6 +451,9 @@ int wiphy_register(struct wiphy *wiphy) int i; u16 ifmodes = wiphy->interface_modes; + /* support for 5/10 MHz is broken due to nl80211 API mess - disable */ + wiphy->flags &= ~WIPHY_FLAG_SUPPORTS_5_10_MHZ; + #ifdef CONFIG_PM if (WARN_ON(wiphy->wowlan && (wiphy->wowlan->flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE) && diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 626dc3b..c2853bb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1655,9 +1655,10 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) * We can then retry with the larger buffer. */ if ((ret == -ENOBUFS || ret == -EMSGSIZE) && - !skb->len && + !skb->len && !state->split && cb->min_dump_alloc < 4096) { cb->min_dump_alloc = 4096; + state->split_start = 0; rtnl_unlock(); return 1; } diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index a271c27..722da61 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -124,6 +124,10 @@ int ieee80211_radiotap_iterator_init( /* find payload start allowing for extended bitmap(s) */ if (iterator->_bitmap_shifter & (1<<IEEE80211_RADIOTAP_EXT)) { + if ((unsigned long)iterator->_arg - + (unsigned long)iterator->_rtheader + sizeof(uint32_t) > + (unsigned long)iterator->_max_length) + return -EINVAL; while (get_unaligned_le32(iterator->_arg) & (1 << IEEE80211_RADIOTAP_EXT)) { iterator->_arg += sizeof(uint32_t); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index eeb7148..d4397eb 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -254,10 +254,10 @@ void __cfg80211_sched_scan_results(struct work_struct *wk) rdev = container_of(wk, struct cfg80211_registered_device, sched_scan_results_wk); - request = rdev->sched_scan_req; - rtnl_lock(); + request = rdev->sched_scan_req; + /* we don't have sched_scan_req anymore if the scan is stopping */ if (request) { if (request->flags & NL80211_SCAN_FLAG_FLUSH) { diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 45a3ab5..7622789 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1340,10 +1340,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, if (sx25) { sx25->sx25_family = AF_X25; sx25->sx25_addr = x25->dest_addr; + msg->msg_namelen = sizeof(*sx25); } - msg->msg_namelen = sizeof(struct sockaddr_x25); - x25_check_rbuf(sk); rc = copied; out_free_dgram: diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 2906d52..3be02b6 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -141,14 +141,14 @@ static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) const int plen = skb->len; int dlen = IPCOMP_SCRATCH_SIZE; u8 *start = skb->data; - const int cpu = get_cpu(); - u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu); - struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu); + struct crypto_comp *tfm; + u8 *scratch; int err; local_bh_disable(); + scratch = *this_cpu_ptr(ipcomp_scratches); + tfm = *this_cpu_ptr(ipcd->tfms); err = crypto_comp_compress(tfm, start, plen, scratch, &dlen); - local_bh_enable(); if (err) goto out; @@ -158,13 +158,13 @@ static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) } memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen); - put_cpu(); + local_bh_enable(); pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr)); return 0; out: - put_cpu(); + local_bh_enable(); return err; } |