diff options
Diffstat (limited to 'net')
102 files changed, 906 insertions, 435 deletions
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2560ed2f144d..e1a545c8a69f 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3996,14 +3996,10 @@ EXPORT_SYMBOL(hci_register_dev); /* Unregister HCI device */ void hci_unregister_dev(struct hci_dev *hdev) { - int id; - BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); hci_dev_set_flag(hdev, HCI_UNREGISTER); - id = hdev->id; - write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); @@ -4038,7 +4034,14 @@ void hci_unregister_dev(struct hci_dev *hdev) } device_del(&hdev->dev); + /* Actual cleanup is deferred until hci_cleanup_dev(). */ + hci_dev_put(hdev); +} +EXPORT_SYMBOL(hci_unregister_dev); +/* Cleanup HCI device */ +void hci_cleanup_dev(struct hci_dev *hdev) +{ debugfs_remove_recursive(hdev->debugfs); kfree_const(hdev->hw_info); kfree_const(hdev->fw_info); @@ -4063,11 +4066,8 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_blocked_keys_clear(hdev); hci_dev_unlock(hdev); - hci_dev_put(hdev); - - ida_simple_remove(&hci_index_ida, id); + ida_simple_remove(&hci_index_ida, hdev->id); } -EXPORT_SYMBOL(hci_unregister_dev); /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index b04a5a02ecf3..f1128c2134f0 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -59,6 +59,17 @@ struct hci_pinfo { char comm[TASK_COMM_LEN]; }; +static struct hci_dev *hci_hdev_from_sock(struct sock *sk) +{ + struct hci_dev *hdev = hci_pi(sk)->hdev; + + if (!hdev) + return ERR_PTR(-EBADFD); + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + return ERR_PTR(-EPIPE); + return hdev; +} + void hci_sock_set_flag(struct sock *sk, int nr) { set_bit(nr, &hci_pi(sk)->flags); @@ -759,19 +770,13 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) if (event == HCI_DEV_UNREG) { struct sock *sk; - /* Detach sockets from device */ + /* Wake up sockets using this dead device */ read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { - lock_sock(sk); if (hci_pi(sk)->hdev == hdev) { - hci_pi(sk)->hdev = NULL; sk->sk_err = EPIPE; - sk->sk_state = BT_OPEN; sk->sk_state_change(sk); - - hci_dev_put(hdev); } - release_sock(sk); } read_unlock(&hci_sk_list.lock); } @@ -930,10 +935,10 @@ static int hci_sock_reject_list_del(struct hci_dev *hdev, void __user *arg) static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { - struct hci_dev *hdev = hci_pi(sk)->hdev; + struct hci_dev *hdev = hci_hdev_from_sock(sk); - if (!hdev) - return -EBADFD; + if (IS_ERR(hdev)) + return PTR_ERR(hdev); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; @@ -1103,6 +1108,18 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, lock_sock(sk); + /* Allow detaching from dead device and attaching to alive device, if + * the caller wants to re-bind (instead of close) this socket in + * response to hci_sock_dev_event(HCI_DEV_UNREG) notification. + */ + hdev = hci_pi(sk)->hdev; + if (hdev && hci_dev_test_flag(hdev, HCI_UNREGISTER)) { + hci_pi(sk)->hdev = NULL; + sk->sk_state = BT_OPEN; + hci_dev_put(hdev); + } + hdev = NULL; + if (sk->sk_state == BT_BOUND) { err = -EALREADY; goto done; @@ -1379,9 +1396,9 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, lock_sock(sk); - hdev = hci_pi(sk)->hdev; - if (!hdev) { - err = -EBADFD; + hdev = hci_hdev_from_sock(sk); + if (IS_ERR(hdev)) { + err = PTR_ERR(hdev); goto done; } @@ -1743,9 +1760,9 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, goto done; } - hdev = hci_pi(sk)->hdev; - if (!hdev) { - err = -EBADFD; + hdev = hci_hdev_from_sock(sk); + if (IS_ERR(hdev)) { + err = PTR_ERR(hdev); goto done; } diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 9874844a95a9..b69d88b88d2e 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -83,6 +83,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn) static void bt_host_release(struct device *dev) { struct hci_dev *hdev = to_hci_dev(dev); + + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + hci_cleanup_dev(hdev); kfree(hdev); module_put(THIS_MODULE); } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index aa47af349ba8..caa16bf30fb5 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -7,6 +7,7 @@ #include <linux/vmalloc.h> #include <linux/etherdevice.h> #include <linux/filter.h> +#include <linux/rcupdate_trace.h> #include <linux/sched/signal.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> @@ -701,6 +702,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret; + if (prog->expected_attach_type == BPF_XDP_DEVMAP || + prog->expected_attach_type == BPF_XDP_CPUMAP) + return -EINVAL; if (kattr->test.ctx_in || kattr->test.ctx_out) return -EINVAL; @@ -948,7 +952,10 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, goto out; } } + + rcu_read_lock_trace(); retval = bpf_prog_run_pin_on_cpu(prog, ctx); + rcu_read_unlock_trace(); if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) { err = -EFAULT; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 2b862cffc03a..5dee30966ed3 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -780,7 +780,7 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, struct net_device *dst_dev; dst_dev = dst ? dst->dev : br->dev; - if (dst_dev != br_dev && dst_dev != dev) + if (dst_dev && dst_dev != dev) continue; err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx); @@ -1019,7 +1019,8 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, - u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[]) + u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[], + struct netlink_ext_ack *extack) { int err = 0; @@ -1038,6 +1039,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, rcu_read_unlock(); local_bh_enable(); } else if (ndm->ndm_flags & NTF_EXT_LEARNED) { + if (!p && !(ndm->ndm_state & NUD_PERMANENT)) { + NL_SET_ERR_MSG_MOD(extack, + "FDB entry towards bridge must be permanent"); + return -EINVAL; + } err = br_fdb_external_learn_add(br, p, addr, vid, true); } else { spin_lock_bh(&br->hash_lock); @@ -1110,9 +1116,11 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } /* VID was specified, so use it. */ - err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb, + extack); } else { - err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb, + extack); if (err || !vg || !vg->num_vlans) goto out; @@ -1124,7 +1132,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], if (!br_vlan_should_use(v)) continue; err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid, - nfea_tb); + nfea_tb, extack); if (err) goto out; } @@ -1281,6 +1289,10 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) flags |= BIT(BR_FDB_ADDED_BY_USER); + + if (!p) + flags |= BIT(BR_FDB_LOCAL); + fdb = fdb_create(br, p, addr, vid, flags); if (!fdb) { err = -ENOMEM; @@ -1307,6 +1319,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); + if (!p) + set_bit(BR_FDB_LOCAL, &fdb->flags); + if (modified) fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 6e4a32354a13..14cd6ef96111 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -616,6 +616,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, err = dev_set_allmulti(dev, 1); if (err) { + br_multicast_del_port(p); kfree(p); /* kobject not yet init'd, manually free */ goto err1; } @@ -729,6 +730,7 @@ err4: err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: + br_multicast_del_port(p); kobject_put(&p->kobj); dev_set_allmulti(dev, -1); err1: diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 8d033a75a766..fdbed3158555 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -88,6 +88,12 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, skb = ip_fraglist_next(&iter); } + + if (!err) + return 0; + + kfree_skb_list(iter.frag); + return err; } slow_path: diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 647554c9813b..e12fd3cad619 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -539,7 +539,8 @@ static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg, goto err; ret = -EINVAL; - if (unlikely(msg->msg_iter.iov->iov_base == NULL)) + if (unlikely(msg->msg_iter.nr_segs == 0) || + unlikely(msg->msg_iter.iov->iov_base == NULL)) goto err; noblock = msg->msg_flags & MSG_DONTWAIT; diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index c3946c355882..bdc95bd7a851 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1075,11 +1075,16 @@ static bool j1939_session_deactivate_locked(struct j1939_session *session) static bool j1939_session_deactivate(struct j1939_session *session) { + struct j1939_priv *priv = session->priv; bool active; - j1939_session_list_lock(session->priv); + j1939_session_list_lock(priv); + /* This function should be called with a session ref-count of at + * least 2. + */ + WARN_ON_ONCE(kref_read(&session->kref) < 2); active = j1939_session_deactivate_locked(session); - j1939_session_list_unlock(session->priv); + j1939_session_list_unlock(priv); return active; } @@ -1869,7 +1874,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, if (!session->transmission) j1939_tp_schedule_txtimer(session, 0); } else { - j1939_tp_set_rxtimeout(session, 250); + j1939_tp_set_rxtimeout(session, 750); } session->last_cmd = 0xff; consume_skb(se_skb); diff --git a/net/can/raw.c b/net/can/raw.c index ed4fcb7ab0c3..cd5a49380116 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -546,10 +546,18 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; } + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + if (count > 1) + kfree(filter); + err = -ENODEV; + goto out_fil; + } + } if (ro->bound) { /* (try to) register the new filters */ @@ -588,6 +596,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, dev_put(dev); release_sock(sk); + rtnl_unlock(); break; @@ -600,10 +609,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, err_mask &= CAN_ERR_MASK; + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + err = -ENODEV; + goto out_err; + } + } /* remove current error mask */ if (ro->bound) { @@ -627,6 +642,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, dev_put(dev); release_sock(sk); + rtnl_unlock(); break; diff --git a/net/core/dev.c b/net/core/dev.c index 64b21f0a2048..8f1a47ad6781 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -131,6 +131,7 @@ #include <trace/events/napi.h> #include <trace/events/net.h> #include <trace/events/skb.h> +#include <trace/events/qdisc.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> #include <linux/static_key.h> @@ -3844,6 +3845,18 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) } } +static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q, + struct sk_buff **to_free, + struct netdev_queue *txq) +{ + int rc; + + rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK; + if (rc == NET_XMIT_SUCCESS) + trace_qdisc_enqueue(q, txq, skb); + return rc; +} + static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) @@ -3862,8 +3875,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * of q->seqlock to protect from racing with requeuing. */ if (unlikely(!nolock_qdisc_is_empty(q))) { - rc = q->enqueue(skb, q, &to_free) & - NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); __qdisc_run(q); qdisc_run_end(q); @@ -3879,7 +3891,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return NET_XMIT_SUCCESS; } - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); qdisc_run(q); no_lock_out: @@ -3923,7 +3935,7 @@ no_lock_out: qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -9700,14 +9712,17 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) struct net_device *dev; int err, fd; + rtnl_lock(); dev = dev_get_by_index(net, attr->link_create.target_ifindex); - if (!dev) + if (!dev) { + rtnl_unlock(); return -EINVAL; + } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; - goto out_put_dev; + goto unlock; } bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog); @@ -9717,14 +9732,14 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); - goto out_put_dev; + goto unlock; } - rtnl_lock(); err = dev_xdp_attach_link(dev, NULL, link); rtnl_unlock(); if (err) { + link->dev = NULL; bpf_link_cleanup(&link_primer); goto out_put_dev; } @@ -9734,6 +9749,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) dev_put(dev); return fd; +unlock: + rtnl_unlock(); + out_put_dev: dev_put(dev); return err; diff --git a/net/core/devlink.c b/net/core/devlink.c index 8fdd04f00fd7..85032626de24 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -9328,18 +9328,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: - case DEVLINK_PORT_FLAVOUR_VIRTUAL: n = snprintf(name, len, "p%u", attrs->phys.port_number); if (n < len && attrs->split) n += snprintf(name + n, len - n, "s%u", attrs->phys.split_subport_number); - if (!attrs->split) - n = snprintf(name, len, "p%u", attrs->phys.port_number); - else - n = snprintf(name, len, "p%us%u", - attrs->phys.port_number, - attrs->phys.split_subport_number); - break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -9381,6 +9373,8 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; + case DEVLINK_PORT_FLAVOUR_VIRTUAL: + return -EOPNOTSUPP; } if (n >= len) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2aadbfc5193b..4b2415d34873 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1504,7 +1504,7 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow) } EXPORT_SYMBOL(flow_get_u32_dst); -/* Sort the source and destination IP (and the ports if the IP are the same), +/* Sort the source and destination IP and the ports, * to have consistent hash within the two directions */ static inline void __flow_hash_consistentify(struct flow_keys *keys) @@ -1515,11 +1515,11 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) case FLOW_DISSECTOR_KEY_IPV4_ADDRS: addr_diff = (__force u32)keys->addrs.v4addrs.dst - (__force u32)keys->addrs.v4addrs.src; - if ((addr_diff < 0) || - (addr_diff == 0 && - ((__force u16)keys->ports.dst < - (__force u16)keys->ports.src))) { + if (addr_diff < 0) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); + + if ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; @@ -1527,13 +1527,13 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) addr_diff = memcmp(&keys->addrs.v6addrs.dst, &keys->addrs.v6addrs.src, sizeof(keys->addrs.v6addrs.dst)); - if ((addr_diff < 0) || - (addr_diff == 0 && - ((__force u16)keys->ports.dst < - (__force u16)keys->ports.src))) { + if (addr_diff < 0) { for (i = 0; i < 4; i++) swap(keys->addrs.v6addrs.src.s6_addr32[i], keys->addrs.v6addrs.dst.s6_addr32[i]); + } + if ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 75431ca9300f..1a455847da54 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -158,7 +158,7 @@ static void linkwatch_do_dev(struct net_device *dev) clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); rfc2863_policy(dev); - if (dev->flags & IFF_UP && netif_device_present(dev)) { + if (dev->flags & IFF_UP) { if (netif_carrier_ok(dev)) dev_activate(dev); else @@ -204,7 +204,8 @@ static void __linkwatch_run_queue(int urgent_only) dev = list_first_entry(&wrk, struct net_device, link_watch_list); list_del_init(&dev->link_watch_list); - if (urgent_only && !linkwatch_urgent_event(dev)) { + if (!netif_device_present(dev) || + (urgent_only && !linkwatch_urgent_event(dev))) { list_add_tail(&dev->link_watch_list, &lweventlist); continue; } diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 5e4eb45b139c..8ab7b402244c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -634,7 +634,15 @@ bool page_pool_return_skb_page(struct page *page) struct page_pool *pp; page = compound_head(page); - if (unlikely(page->pp_magic != PP_SIGNATURE)) + + /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation + * in order to preserve any existing bits, such as bit 0 for the + * head page of compound page and bit 1 for pfmemalloc page, so + * mask those bits for freeing side when doing below checking, + * and page_is_pfmemalloc() is checked in __page_pool_put_page() + * to avoid recycling the pfmemalloc page. + */ + if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE)) return false; pp = page->pp; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f63de967ac25..fc7942c0dddc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -663,7 +663,7 @@ static void skb_release_data(struct sk_buff *skb) if (skb->cloned && atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, &shinfo->dataref)) - return; + goto exit; skb_zcopy_clear(skb, true); @@ -674,6 +674,17 @@ static void skb_release_data(struct sk_buff *skb) kfree_skb_list(shinfo->frag_list); skb_free_head(skb); +exit: + /* When we clone an SKB we copy the reycling bit. The pp_recycle + * bit is only set on the head though, so in order to avoid races + * while trying to recycle fragments on __skb_frag_unref() we need + * to make one SKB responsible for triggering the recycle path. + * So disable the recycling bit if an SKB is cloned and we have + * additional references to to the fragmented part of the SKB. + * Eventually the last SKB will have the recycling bit set and it's + * dataref set to 0, which will trigger the recycling + */ + skb->pp_recycle = 0; } /* @@ -3011,8 +3022,11 @@ skb_zerocopy_headlen(const struct sk_buff *from) if (!from->head_frag || skb_headlen(from) < L1_CACHE_BYTES || - skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) { hlen = skb_headlen(from); + if (!hlen) + hlen = from->len; + } if (skb_has_frag_list(from)) hlen = from->len; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 9b6160a191f8..2d6249b28928 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -508,10 +508,8 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, if (skb_linearize(skb)) return -EAGAIN; num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); - if (unlikely(num_sge < 0)) { - kfree(msg); + if (unlikely(num_sge < 0)) return num_sge; - } copied = skb->len; msg->sg.start = 0; @@ -530,6 +528,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) { struct sock *sk = psock->sk; struct sk_msg *msg; + int err; /* If we are receiving on the same sock skb->sk is already assigned, * skip memory accounting and owner transition seeing it already set @@ -548,7 +547,10 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * into user buffers. */ skb_set_owner_r(skb, sk); - return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + if (err < 0) + kfree(msg); + return err; } /* Puts an skb on the ingress queue of the socket already assigned to the @@ -559,12 +561,16 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb { struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); struct sock *sk = psock->sk; + int err; if (unlikely(!msg)) return -EAGAIN; sk_msg_init(msg); skb_set_owner_r(skb, sk); - return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + if (err < 0) + kfree(msg); + return err; } static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, @@ -578,29 +584,42 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } -static void sock_drop(struct sock *sk, struct sk_buff *skb) +static void sk_psock_skb_state(struct sk_psock *psock, + struct sk_psock_work_state *state, + struct sk_buff *skb, + int len, int off) { - sk_drops_add(sk, skb); - kfree_skb(skb); + spin_lock_bh(&psock->ingress_lock); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { + state->skb = skb; + state->len = len; + state->off = off; + } else { + sock_drop(psock->sk, skb); + } + spin_unlock_bh(&psock->ingress_lock); } static void sk_psock_backlog(struct work_struct *work) { struct sk_psock *psock = container_of(work, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; - struct sk_buff *skb; + struct sk_buff *skb = NULL; bool ingress; u32 len, off; int ret; mutex_lock(&psock->work_mutex); - if (state->skb) { + if (unlikely(state->skb)) { + spin_lock_bh(&psock->ingress_lock); skb = state->skb; len = state->len; off = state->off; state->skb = NULL; - goto start; + spin_unlock_bh(&psock->ingress_lock); } + if (skb) + goto start; while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; @@ -615,9 +634,8 @@ start: len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - state->skb = skb; - state->len = len; - state->off = off; + sk_psock_skb_state(psock, state, skb, + len, off); goto end; } /* Hard errors break pipe and stop xmit. */ @@ -716,6 +734,11 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } + kfree_skb(psock->work_state.skb); + /* We null the skb here to ensure that calls to sk_psock_backlog + * do not pick up the free'd skb. + */ + psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); } @@ -767,8 +790,6 @@ static void sk_psock_destroy(struct work_struct *work) void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - sk_psock_stop(psock, false); - write_lock_bh(&sk->sk_callback_lock); sk_psock_restore_proto(sk, psock); rcu_assign_sk_user_data(sk, NULL); @@ -778,6 +799,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); + sk_psock_stop(psock, false); + INIT_RCU_WORK(&psock->rwork, sk_psock_destroy); queue_rcu_work(system_wq, &psock->rwork); } diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 9cc9d1ee6cdb..c5c1d2b8045e 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -41,9 +41,9 @@ extern bool dccp_debug; #define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a) #define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a) #else -#define dccp_pr_debug(format, a...) -#define dccp_pr_debug_cat(format, a...) -#define dccp_debug(format, a...) +#define dccp_pr_debug(format, a...) do {} while (0) +#define dccp_pr_debug_cat(format, a...) do {} while (0) +#define dccp_debug(format, a...) do {} while (0) #endif extern struct inet_hashinfo dccp_hashinfo; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 5dbd45dc35ad..dc92a67baea3 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -816,7 +816,7 @@ static int dn_auto_bind(struct socket *sock) static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) { struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err; if (scp->state != DN_CR) @@ -826,11 +826,11 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) scp->segsize_loc = dst_metric_advmss(__sk_dst_get(sk)); dn_send_conn_conf(sk, allocation); - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); for(;;) { release_sock(sk); if (scp->state == DN_CC) - *timeo = schedule_timeout(*timeo); + *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); lock_sock(sk); err = 0; if (scp->state == DN_RUN) @@ -844,9 +844,8 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) err = -EAGAIN; if (!*timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); if (err == 0) { sk->sk_socket->state = SS_CONNECTED; } else if (scp->state != DN_CC) { @@ -858,7 +857,7 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) static int dn_wait_run(struct sock *sk, long *timeo) { struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err = 0; if (scp->state == DN_RUN) @@ -867,11 +866,11 @@ static int dn_wait_run(struct sock *sk, long *timeo) if (!*timeo) return -EALREADY; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); for(;;) { release_sock(sk); if (scp->state == DN_CI || scp->state == DN_CC) - *timeo = schedule_timeout(*timeo); + *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); lock_sock(sk); err = 0; if (scp->state == DN_RUN) @@ -885,9 +884,8 @@ static int dn_wait_run(struct sock *sk, long *timeo) err = -ETIMEDOUT; if (!*timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); out: if (err == 0) { sk->sk_socket->state = SS_CONNECTED; @@ -1032,16 +1030,16 @@ static void dn_user_copy(struct sk_buff *skb, struct optdata_dn *opt) static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) { - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sk_buff *skb = NULL; int err = 0; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); for(;;) { release_sock(sk); skb = skb_dequeue(&sk->sk_receive_queue); if (skb == NULL) { - *timeo = schedule_timeout(*timeo); + *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); skb = skb_dequeue(&sk->sk_receive_queue); } lock_sock(sk); @@ -1056,9 +1054,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) err = -EAGAIN; if (!*timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); return skb == NULL ? ERR_PTR(err) : skb; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index ffbba1e71551..23be8e01026b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1808,6 +1808,7 @@ void dsa_slave_setup_tagger(struct net_device *slave) struct dsa_slave_priv *p = netdev_priv(slave); const struct dsa_port *cpu_dp = dp->cpu_dp; struct net_device *master = cpu_dp->master; + const struct dsa_switch *ds = dp->ds; slave->needed_headroom = cpu_dp->tag_ops->needed_headroom; slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; @@ -1819,6 +1820,14 @@ void dsa_slave_setup_tagger(struct net_device *slave) slave->needed_tailroom += master->needed_tailroom; p->xmit = cpu_dp->tag_ops->xmit; + + slave->features = master->vlan_features | NETIF_F_HW_TC; + if (ds->ops->port_vlan_add && ds->ops->port_vlan_del) + slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + slave->hw_features |= NETIF_F_HW_TC; + slave->features |= NETIF_F_LLTX; + if (slave->needed_tailroom) + slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); } static struct lock_class_key dsa_slave_netdev_xmit_lock_key; @@ -1881,11 +1890,6 @@ int dsa_slave_create(struct dsa_port *port) if (slave_dev == NULL) return -ENOMEM; - slave_dev->features = master->vlan_features | NETIF_F_HW_TC; - if (ds->ops->port_vlan_add && ds->ops->port_vlan_del) - slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - slave_dev->hw_features |= NETIF_F_HW_TC; - slave_dev->features |= NETIF_F_LLTX; slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; if (!is_zero_ether_addr(port->mac)) ether_addr_copy(slave_dev->dev_addr, port->mac); @@ -2287,8 +2291,8 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, static void dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) { + struct switchdev_notifier_fdb_info info = {}; struct dsa_switch *ds = switchdev_work->ds; - struct switchdev_notifier_fdb_info info; struct dsa_port *dp; if (!dsa_is_user_port(ds, switchdev_work->port)) diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 53565f48934c..a201ccf2435d 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -53,6 +53,9 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) u8 *tag; u8 *addr; + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(skb); @@ -114,6 +117,9 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, u8 *addr; u16 val; + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN); addr = skb_mac_header(skb); @@ -164,6 +170,9 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, u8 *addr; u8 *tag; + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(skb); diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index a45a0401adc5..c25f7617770c 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -984,6 +984,11 @@ static const struct proto_ops ieee802154_dgram_ops = { .sendpage = sock_no_sendpage, }; +static void ieee802154_sock_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); +} + /* Create a socket. Initialise the socket, blank the addresses * set the state. */ @@ -1024,7 +1029,7 @@ static int ieee802154_create(struct net *net, struct socket *sock, sock->ops = ops; sock_init_data(sock, sk); - /* FIXME: sk->sk_destruct */ + sk->sk_destruct = ieee802154_sock_destruct; sk->sk_family = PF_IEEE802154; /* Checksums on by default */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6b3c558a4f23..00576bae183d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -803,10 +803,17 @@ static void igmp_gq_timer_expire(struct timer_list *t) static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); + u32 mr_ifc_count; igmpv3_send_cr(in_dev); - if (in_dev->mr_ifc_count) { - in_dev->mr_ifc_count--; +restart: + mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); + + if (mr_ifc_count) { + if (cmpxchg(&in_dev->mr_ifc_count, + mr_ifc_count, + mr_ifc_count - 1) != mr_ifc_count) + goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } @@ -818,7 +825,7 @@ static void igmp_ifc_event(struct in_device *in_dev) struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv); igmp_ifc_start_timer(in_dev, 1); } @@ -957,7 +964,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, in_dev->mr_qri; } /* cancel the interface change timer */ - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ @@ -1724,7 +1731,7 @@ void ip_mc_down(struct in_device *in_dev) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; @@ -1941,7 +1948,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); @@ -2120,7 +2127,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0dca00745ac3..be75b409445c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -390,7 +390,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } - skb_reset_network_header(skb); + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6ea3dc2e4219..6274462b86b4 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1041,7 +1041,7 @@ static void bbr_init(struct sock *sk) bbr->prior_cwnd = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; bbr->rtt_cnt = 0; - bbr->next_rtt_delivered = 0; + bbr->next_rtt_delivered = tp->delivered; bbr->prev_ca_state = TCP_CA_Open; bbr->packet_conservation = 0; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index f26916a62f25..d3e9386b493e 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -503,7 +503,7 @@ static int __init tcp_bpf_v4_build_proto(void) tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot); return 0; } -core_initcall(tcp_bpf_v4_build_proto); +late_initcall(tcp_bpf_v4_build_proto); static int tcp_bpf_assert_proto_ops(struct proto *ops) { diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 47c32604d38f..25fa4c01a17f 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -507,8 +507,18 @@ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); + if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout) + return; + + /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ + WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies); + + /* Paired with smp_rmb() in tcp_fastopen_active_should_disable(). + * We want net->ipv4.tfo_active_disable_stamp to be updated first. + */ + smp_mb__before_atomic(); atomic_inc(&net->ipv4.tfo_active_disable_times); - net->ipv4.tfo_active_disable_stamp = jiffies; + NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } @@ -519,17 +529,27 @@ void tcp_fastopen_active_disable(struct sock *sk) bool tcp_fastopen_active_should_disable(struct sock *sk) { unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; - int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); unsigned long timeout; + int tfo_da_times; int multiplier; + if (!tfo_bh_timeout) + return false; + + tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); if (!tfo_da_times) return false; + /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */ + smp_rmb(); + /* Limit timeout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); - timeout = multiplier * tfo_bh_timeout * HZ; - if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) + + /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */ + timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) + + multiplier * tfo_bh_timeout * HZ; + if (time_before(jiffies, timeout)) return true; /* Mark check bit so we can check for successful active TFO diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b9dc2d6197be..a692626c19e4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2965,7 +2965,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); - net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60; + net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); /* Reno is always built in */ diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index e09147ac9a99..fc61cd3fea65 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -298,6 +298,9 @@ int tcp_gro_complete(struct sk_buff *skb) if (th->cwr) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; + return 0; } EXPORT_SYMBOL(tcp_gro_complete); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 62cd4cd52e84..1a742b710e54 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -645,10 +645,12 @@ static struct sock *__udp4_lib_err_encap(struct net *net, const struct iphdr *iph, struct udphdr *uh, struct udp_table *udptable, + struct sock *sk, struct sk_buff *skb, u32 info) { + int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; - struct sock *sk; + struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -659,18 +661,28 @@ static struct sock *__udp4_lib_err_encap(struct net *net, /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, iph->ihl << 2); + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + sk = __udp4_lib_lookup(net, iph->daddr, uh->source, iph->saddr, uh->dest, skb->dev->ifindex, 0, udptable, NULL); if (sk) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(sk); + up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } +out: if (!sk) sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info)); @@ -707,15 +719,16 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udp_encap_needed_key)) { - sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb, + sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb, info); if (!sk) return 0; - } + } else + sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 45b8782aec0c..9f5a5cdc38e6 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -134,7 +134,7 @@ static int __init udp_bpf_v4_build_proto(void) udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot); return 0; } -core_initcall(udp_bpf_v4_build_proto); +late_initcall(udp_bpf_v4_build_proto); int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 9dde1e5fb449..1380a6b6f4ff 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -624,6 +624,10 @@ static int udp_gro_complete_segment(struct sk_buff *skb) skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; + + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; + return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 01bea76e3891..8e6ca9ad6812 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -74,7 +74,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * if (likely(nskb)) { if (skb->sk) - skb_set_owner_w(skb, skb->sk); + skb_set_owner_w(nskb, skb->sk); consume_skb(skb); } else { kfree_skb(skb); @@ -549,9 +549,10 @@ int ip6_forward(struct sk_buff *skb) if (net->ipv6.devconf_all->proxy_ndp && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); - if (proxied > 0) + if (proxied > 0) { + hdr->hop_limit--; return ip6_input(skb); - else if (proxied < 0) { + } else if (proxied < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7b756a7dc036..b6ddf23d3833 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3769,7 +3769,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, err = PTR_ERR(rt->fib6_metrics); /* Do not leave garbage there. */ rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; - goto out; + goto out_free; } if (cfg->fc_flags & RTF_ADDRCONF) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 0cc7ba531b34..c5e15e94bb00 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -502,12 +502,14 @@ static struct sock *__udp6_lib_err_encap(struct net *net, const struct ipv6hdr *hdr, int offset, struct udphdr *uh, struct udp_table *udptable, + struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, __be32 info) { + int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; - struct sock *sk; + struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -518,18 +520,28 @@ static struct sock *__udp6_lib_err_encap(struct net *net, /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, offset); + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source, &hdr->saddr, uh->dest, inet6_iif(skb), 0, udptable, skb); if (sk) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(sk); + up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } +out: if (!sk) { sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code, offset, info)); @@ -558,16 +570,17 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), inet6_sdif(skb), udptable, NULL); + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udpv6_encap_needed_key)) { sk = __udp6_lib_err_encap(net, hdr, offset, uh, - udptable, skb, + udptable, sk, skb, opt, type, code, info); if (!sk) return 0; - } + } else + sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 7180979114e4..ac5cadd02cfa 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -98,8 +98,16 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; - if (addr->sllc_test || addr->sllc_xid) + if (addr->sllc_test) rc = LLC_PDU_LEN_U; + else if (addr->sllc_xid) + /* We need to expand header to sizeof(struct llc_xid_info) + * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header + * as XID PDU. In llc_ui_sendmsg() we reserved header size and then + * filled all other space with user data. If we won't reserve this + * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data + */ + rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index b554f26c68ee..79d1cef8f15a 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -79,7 +79,7 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) struct llc_sap_state_ev *ev = llc_sap_ev(skb); int rc; - llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap, + llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 84cc7733ea66..4e6f11e63df3 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -152,6 +152,8 @@ static int ieee80211_change_iface(struct wiphy *wiphy, struct vif_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; int ret; ret = ieee80211_if_change_type(sdata, type); @@ -162,7 +164,24 @@ static int ieee80211_change_iface(struct wiphy *wiphy, RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + if (params->use_4addr == ifmgd->use_4addr) + return 0; + sdata->u.mgd.use_4addr = params->use_4addr; + if (!ifmgd->associated) + return 0; + + mutex_lock(&local->sta_mtx); + sta = sta_info_get(sdata, ifmgd->bssid); + if (sta) + drv_sta_set_4addr(local, sdata, &sta->sta, + params->use_4addr); + mutex_unlock(&local->sta_mtx); + + if (params->use_4addr) + ieee80211_send_4addr_nullfunc(local, sdata); } if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 22549b95d1aa..30ce6d2ec7ce 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2201,6 +2201,8 @@ void ieee80211_dynamic_ps_timer(struct timer_list *t); void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, bool powersave); +void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr, bool ack, u16 tx_time); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 05f4c3c72619..fcae76ddd586 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -260,6 +260,8 @@ static void ieee80211_restart_work(struct work_struct *work) flush_work(&local->radar_detected_work); rtnl_lock(); + /* we might do interface manipulations, so need both */ + wiphy_lock(local->hw.wiphy); WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), "%s called with hardware scan in progress\n", __func__); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a00f11a33699..c0ea3b1aa9e1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1095,8 +1095,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, ieee80211_tx_skb(sdata, skb); } -static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) +void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { struct sk_buff *skb; struct ieee80211_hdr *nullfunc; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 771921c057e8..2563473b5cf1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -730,7 +730,8 @@ ieee80211_make_monitor_skb(struct ieee80211_local *local, * Need to make a copy and possibly remove radiotap header * and FCS from the original. */ - skb = skb_copy_expand(*origskb, needed_headroom, 0, GFP_ATOMIC); + skb = skb_copy_expand(*origskb, needed_headroom + NET_SKB_PAD, + 0, GFP_ATOMIC); if (!skb) return NULL; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e96981144358..8509778ff31f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1147,6 +1147,29 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, return queued; } +static void +ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + struct rate_control_ref *ref = sdata->local->rate_ctrl; + u16 tid; + + if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) + return; + + if (!sta || !sta->sta.ht_cap.ht_supported || + !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || + skb->protocol == sdata->control_port_protocol) + return; + + tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; + if (likely(sta->ampdu_mlme.tid_tx[tid])) + return; + + ieee80211_start_tx_ba_session(&sta->sta, tid, 0); +} + /* * initialises @tx * pass %NULL for the station if unknown, a valid pointer if known @@ -1160,6 +1183,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_hdr *hdr; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + bool aggr_check = false; int tid; memset(tx, 0, sizeof(*tx)); @@ -1188,8 +1212,10 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, } else if (tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } - if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) + if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) { tx->sta = sta_info_get(sdata, hdr->addr1); + aggr_check = true; + } } if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) && @@ -1199,8 +1225,12 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_tx *tid_tx; tid = ieee80211_get_tid(hdr); - tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); + if (!tid_tx && aggr_check) { + ieee80211_aggr_check(sdata, tx->sta, skb); + tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); + } + if (tid_tx) { bool queued; @@ -4120,29 +4150,6 @@ void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) } EXPORT_SYMBOL(ieee80211_txq_schedule_start); -static void -ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, - struct sk_buff *skb) -{ - struct rate_control_ref *ref = sdata->local->rate_ctrl; - u16 tid; - - if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) - return; - - if (!sta || !sta->sta.ht_cap.ht_supported || - !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || - skb->protocol == sdata->control_port_protocol) - return; - - tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; - if (likely(sta->ampdu_mlme.tid_tx[tid])) - return; - - ieee80211_start_tx_ba_session(&sta->sta, tid, 0); -} - void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags, diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 4452455aef7f..7adcbc1f7d49 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -885,20 +885,16 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return subflow->mp_capable; } - if (mp_opt->dss && mp_opt->use_ack) { + if ((mp_opt->dss && mp_opt->use_ack) || + (mp_opt->add_addr && !mp_opt->echo)) { /* subflows are fully established as soon as we get any - * additional ack. + * additional ack, including ADD_ADDR. */ subflow->fully_established = 1; WRITE_ONCE(msk->fully_established, true); goto fully_established; } - if (mp_opt->add_addr) { - WRITE_ONCE(msk->fully_established, true); - return true; - } - /* If the first established packet does not contain MP_CAPABLE + data * then fallback to TCP. Fallback scenarios requires a reset for * MP_JOIN subflows. diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d2591ebf01d9..7b3794459783 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -27,7 +27,6 @@ struct mptcp_pm_addr_entry { struct mptcp_addr_info addr; u8 flags; int ifindex; - struct rcu_head rcu; struct socket *lsk; }; @@ -1136,36 +1135,12 @@ next: return 0; } -struct addr_entry_release_work { - struct rcu_work rwork; - struct mptcp_pm_addr_entry *entry; -}; - -static void mptcp_pm_release_addr_entry(struct work_struct *work) +/* caller must ensure the RCU grace period is already elapsed */ +static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) { - struct addr_entry_release_work *w; - struct mptcp_pm_addr_entry *entry; - - w = container_of(to_rcu_work(work), struct addr_entry_release_work, rwork); - entry = w->entry; - if (entry) { - if (entry->lsk) - sock_release(entry->lsk); - kfree(entry); - } - kfree(w); -} - -static void mptcp_pm_free_addr_entry(struct mptcp_pm_addr_entry *entry) -{ - struct addr_entry_release_work *w; - - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w) { - INIT_RCU_WORK(&w->rwork, mptcp_pm_release_addr_entry); - w->entry = entry; - queue_rcu_work(system_wq, &w->rwork); - } + if (entry->lsk) + sock_release(entry->lsk); + kfree(entry); } static int mptcp_nl_remove_id_zero_address(struct net *net, @@ -1245,7 +1220,8 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) spin_unlock_bh(&pernet->lock); mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr); - mptcp_pm_free_addr_entry(entry); + synchronize_rcu(); + __mptcp_pm_release_addr_entry(entry); return ret; } @@ -1298,6 +1274,7 @@ static void mptcp_nl_remove_addrs_list(struct net *net, } } +/* caller must ensure the RCU grace period is already elapsed */ static void __flush_addrs(struct list_head *list) { while (!list_empty(list)) { @@ -1306,7 +1283,7 @@ static void __flush_addrs(struct list_head *list) cur = list_entry(list->next, struct mptcp_pm_addr_entry, list); list_del_rcu(&cur->list); - mptcp_pm_free_addr_entry(cur); + __mptcp_pm_release_addr_entry(cur); } } @@ -1330,6 +1307,7 @@ static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info) bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); mptcp_nl_remove_addrs_list(sock_net(skb->sk), &free_list); + synchronize_rcu(); __flush_addrs(&free_list); return 0; } @@ -1940,7 +1918,8 @@ static void __net_exit pm_nl_exit_net(struct list_head *net_list) struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id); /* net is removed from namespace list, can't race with - * other modifiers + * other modifiers, also netns core already waited for a + * RCU grace period. */ __flush_addrs(&pernet->local_addr_list); } diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index d1bef23fd4f5..dd30c03d5a23 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -132,8 +132,11 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -144,6 +147,10 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); + /* 64bit division is not allowed on 32bit */ + if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) { ip = ntohl(h->next.ip); e.ip = htonl(ip); diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index 18346d18aa16..153de3457423 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -121,6 +121,8 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; + if (e.mark == 0 && e.ip == 0) + return -IPSET_ERR_HASH_ELEM; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) { @@ -133,8 +135,11 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (e.mark == 0 && ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -143,6 +148,9 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ip_set_mask_from_to(ip, ip_to, cidr); } + if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index e1ca11196515..7303138e46be 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -173,6 +173,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index ab179e064597..334fb1ad0e86 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -180,6 +180,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 8f075b44cf64..7df94f437f60 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -253,6 +253,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c1a11f041ac6..1422739d9aa2 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -140,7 +140,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -188,6 +188,15 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); do { diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index ddd51c2e1cb3..9810f5bf63f5 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -202,7 +202,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -256,6 +256,14 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; if (retried) ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 6532f0505e66..3d09eefe998a 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -168,7 +168,8 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0; - u32 ip2 = 0, ip2_from = 0, ip2_to = 0; + u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn; + u64 n = 0, m = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -244,6 +245,19 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index ec1564a1cb5a..09cf72eb37f8 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -158,7 +158,8 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 port, port_to, p = 0, ip = 0, ip_to = 0; + u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn; + u64 n = 0; bool with_ports = false; u8 cidr; int ret; @@ -235,6 +236,14 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr); + n++; + } while (ipn++ < ip_to); + + if (n*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 0e91d1e82f1c..19bcdb3141f6 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -182,7 +182,8 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2; + u32 ip2_from = 0, ip2_to = 0, ip2, ipn; + u64 n = 0, m = 0; bool with_ports = false; int ret; @@ -284,6 +285,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 83c52df85870..d31dbccbe7bd 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -66,22 +66,17 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash); struct conntrack_gc_work { struct delayed_work dwork; - u32 last_bucket; + u32 next_bucket; bool exiting; bool early_drop; - long next_gc_run; }; static __read_mostly struct kmem_cache *nf_conntrack_cachep; static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; -/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */ -#define GC_MAX_BUCKETS_DIV 128u -/* upper bound of full table scan */ -#define GC_MAX_SCAN_JIFFIES (16u * HZ) -/* desired ratio of entries found to be expired */ -#define GC_EVICT_RATIO 50u +#define GC_SCAN_INTERVAL (120u * HZ) +#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) static struct conntrack_gc_work conntrack_gc_work; @@ -670,8 +665,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) return false; tstamp = nf_conn_tstamp_find(ct); - if (tstamp && tstamp->stop == 0) + if (tstamp) { + s32 timeout = ct->timeout - nfct_time_stamp; + tstamp->stop = ktime_get_real_ns(); + if (timeout < 0) + tstamp->stop -= jiffies_to_nsecs(-timeout); + } if (nf_conntrack_event_report(IPCT_DESTROY, ct, portid, report) < 0) { @@ -1358,17 +1358,13 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct) static void gc_worker(struct work_struct *work) { - unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u); - unsigned int i, goal, buckets = 0, expired_count = 0; - unsigned int nf_conntrack_max95 = 0; + unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION; + unsigned int i, hashsz, nf_conntrack_max95 = 0; + unsigned long next_run = GC_SCAN_INTERVAL; struct conntrack_gc_work *gc_work; - unsigned int ratio, scanned = 0; - unsigned long next_run; - gc_work = container_of(work, struct conntrack_gc_work, dwork.work); - goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV; - i = gc_work->last_bucket; + i = gc_work->next_bucket; if (gc_work->early_drop) nf_conntrack_max95 = nf_conntrack_max / 100u * 95u; @@ -1376,15 +1372,15 @@ static void gc_worker(struct work_struct *work) struct nf_conntrack_tuple_hash *h; struct hlist_nulls_head *ct_hash; struct hlist_nulls_node *n; - unsigned int hashsz; struct nf_conn *tmp; - i++; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hashsz); - if (i >= hashsz) - i = 0; + if (i >= hashsz) { + rcu_read_unlock(); + break; + } hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) { struct nf_conntrack_net *cnet; @@ -1392,7 +1388,6 @@ static void gc_worker(struct work_struct *work) tmp = nf_ct_tuplehash_to_ctrack(h); - scanned++; if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) { nf_ct_offload_timeout(tmp); continue; @@ -1400,7 +1395,6 @@ static void gc_worker(struct work_struct *work) if (nf_ct_is_expired(tmp)) { nf_ct_gc_expired(tmp); - expired_count++; continue; } @@ -1433,7 +1427,14 @@ static void gc_worker(struct work_struct *work) */ rcu_read_unlock(); cond_resched(); - } while (++buckets < goal); + i++; + + if (time_after(jiffies, end_time) && i < hashsz) { + gc_work->next_bucket = i; + next_run = 0; + break; + } + } while (i < hashsz); if (gc_work->exiting) return; @@ -1444,40 +1445,17 @@ static void gc_worker(struct work_struct *work) * * This worker is only here to reap expired entries when system went * idle after a busy period. - * - * The heuristics below are supposed to balance conflicting goals: - * - * 1. Minimize time until we notice a stale entry - * 2. Maximize scan intervals to not waste cycles - * - * Normally, expire ratio will be close to 0. - * - * As soon as a sizeable fraction of the entries have expired - * increase scan frequency. */ - ratio = scanned ? expired_count * 100 / scanned : 0; - if (ratio > GC_EVICT_RATIO) { - gc_work->next_gc_run = min_interval; - } else { - unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV; - - BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0); - - gc_work->next_gc_run += min_interval; - if (gc_work->next_gc_run > max) - gc_work->next_gc_run = max; + if (next_run) { + gc_work->early_drop = false; + gc_work->next_bucket = 0; } - - next_run = gc_work->next_gc_run; - gc_work->last_bucket = i; - gc_work->early_drop = false; queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run); } static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) { INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker); - gc_work->next_gc_run = HZ; gc_work->exiting = false; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3259416f2ea4..af5115e127cf 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1478,7 +1478,6 @@ void nf_conntrack_tcp_init_net(struct net *net) #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) tn->offload_timeout = 30 * HZ; - tn->offload_pickup = 120 * HZ; #endif } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 698fee49e732..f8e3c0d2602f 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -271,7 +271,6 @@ void nf_conntrack_udp_init_net(struct net *net) #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) un->offload_timeout = 30 * HZ; - un->offload_pickup = 30 * HZ; #endif } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 214d9f9e499b..e84b499b7bfa 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -575,7 +575,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD, - NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP, #endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, @@ -585,7 +584,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD, - NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP, #endif NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP, NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6, @@ -776,12 +774,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = { - .procname = "nf_flowtable_tcp_pickup", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { .procname = "nf_conntrack_tcp_loose", @@ -832,12 +824,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = { - .procname = "nf_flowtable_udp_pickup", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = { .procname = "nf_conntrack_icmp_timeout", @@ -1018,7 +1004,6 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout; - table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup; #endif } @@ -1111,7 +1096,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED]; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout; - table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup; #endif nf_conntrack_standalone_init_tcp_sysctl(net, table); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 1e50908b1b7e..8788b519255e 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -183,7 +183,7 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) const struct nf_conntrack_l4proto *l4proto; struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); - unsigned int timeout; + s32 timeout; l4proto = nf_ct_l4proto_find(l4num); if (!l4proto) @@ -192,15 +192,20 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - timeout = tn->offload_pickup; + timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); - timeout = tn->offload_pickup; + timeout = tn->timeouts[UDP_CT_REPLIED]; + timeout -= tn->offload_timeout; } else { return; } + if (timeout < 0) + timeout = 0; + if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout) ct->timeout = nfct_time_stamp + timeout; } @@ -331,7 +336,11 @@ EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload *flow) { - flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); + u32 timeout; + + timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); + if (READ_ONCE(flow->timeout) != timeout) + WRITE_ONCE(flow->timeout, timeout); if (likely(!nf_flowtable_hw_offload(flow_table))) return; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index de182d1f7c4e..081437dd75b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8445,6 +8445,16 @@ static int nf_tables_commit_audit_alloc(struct list_head *adl, return 0; } +static void nf_tables_commit_audit_free(struct list_head *adl) +{ + struct nft_audit_data *adp, *adn; + + list_for_each_entry_safe(adp, adn, adl, list) { + list_del(&adp->list); + kfree(adp); + } +} + static void nf_tables_commit_audit_collect(struct list_head *adl, struct nft_table *table, u32 op) { @@ -8509,6 +8519,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); if (ret) { nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); return ret; } if (trans->msg_type == NFT_MSG_NEWRULE || @@ -8518,6 +8529,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) ret = nf_tables_commit_chain_prepare(net, chain); if (ret < 0) { nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); return ret; } } diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index 50b4e3c9347a..f554e2ea32ee 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -89,11 +89,15 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb, if (!nest2) goto cancel_nest; - ret = nla_put_string(nlskb, NFTA_CHAIN_TABLE, chain->table->name); + ret = nla_put_string(nlskb, NFNLA_CHAIN_TABLE, chain->table->name); if (ret) goto cancel_nest; - ret = nla_put_string(nlskb, NFTA_CHAIN_NAME, chain->name); + ret = nla_put_string(nlskb, NFNLA_CHAIN_NAME, chain->name); + if (ret) + goto cancel_nest; + + ret = nla_put_u8(nlskb, NFNLA_CHAIN_FAMILY, chain->table->family); if (ret) goto cancel_nest; @@ -109,18 +113,19 @@ cancel_nest: static int nfnl_hook_dump_one(struct sk_buff *nlskb, const struct nfnl_dump_hook_data *ctx, const struct nf_hook_ops *ops, - unsigned int seq) + int family, unsigned int seq) { u16 event = nfnl_msg_type(NFNL_SUBSYS_HOOK, NFNL_MSG_HOOK_GET); unsigned int portid = NETLINK_CB(nlskb).portid; struct nlmsghdr *nlh; int ret = -EMSGSIZE; + u32 hooknum; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; char *module_name; #endif nlh = nfnl_msg_put(nlskb, portid, seq, event, - NLM_F_MULTI, ops->pf, NFNETLINK_V0, 0); + NLM_F_MULTI, family, NFNETLINK_V0, 0); if (!nlh) goto nla_put_failure; @@ -135,6 +140,7 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, if (module_name) { char *end; + *module_name = '\0'; module_name += 2; end = strchr(module_name, ']'); if (end) { @@ -151,7 +157,12 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, goto nla_put_failure; #endif - ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(ops->hooknum)); + if (ops->pf == NFPROTO_INET && ops->hooknum == NF_INET_INGRESS) + hooknum = NF_NETDEV_INGRESS; + else + hooknum = ops->hooknum; + + ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(hooknum)); if (ret) goto nla_put_failure; @@ -174,7 +185,9 @@ static const struct nf_hook_entries * nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) { const struct nf_hook_entries *hook_head = NULL; +#ifdef CONFIG_NETFILTER_INGRESS struct net_device *netdev; +#endif switch (pf) { case NFPROTO_IPV4: @@ -257,7 +270,8 @@ static int nfnl_hook_dump(struct sk_buff *nlskb, ops = nf_hook_entries_get_hook_ops(e); for (; i < e->num_hook_entries; i++) { - err = nfnl_hook_dump_one(nlskb, ctx, ops[i], cb->seq); + err = nfnl_hook_dump_one(nlskb, ctx, ops[i], family, + cb->nlh->nlmsg_seq); if (err) break; } diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 8088b99f2ee3..304e33cbed9b 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -48,24 +48,30 @@ static void nft_last_eval(const struct nft_expr *expr, { struct nft_last_priv *priv = nft_expr_priv(expr); - priv->last_jiffies = jiffies; - priv->last_set = 1; + if (READ_ONCE(priv->last_jiffies) != jiffies) + WRITE_ONCE(priv->last_jiffies, jiffies); + if (READ_ONCE(priv->last_set) == 0) + WRITE_ONCE(priv->last_set, 1); } static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr) { struct nft_last_priv *priv = nft_expr_priv(expr); + unsigned long last_jiffies = READ_ONCE(priv->last_jiffies); + u32 last_set = READ_ONCE(priv->last_set); __be64 msecs; - if (time_before(jiffies, priv->last_jiffies)) - priv->last_set = 0; + if (time_before(jiffies, last_jiffies)) { + WRITE_ONCE(priv->last_set, 0); + last_set = 0; + } - if (priv->last_set) - msecs = nf_jiffies64_to_msecs(jiffies - priv->last_jiffies); + if (last_set) + msecs = nf_jiffies64_to_msecs(jiffies - last_jiffies); else msecs = 0; - if (nla_put_be32(skb, NFTA_LAST_SET, htonl(priv->last_set)) || + if (nla_put_be32(skb, NFTA_LAST_SET, htonl(last_set)) || nla_put_be64(skb, NFTA_LAST_MSECS, msecs, NFTA_LAST_PAD)) goto nla_put_failure; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 0840c635b752..be1595d6979d 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -201,7 +201,9 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, alen = sizeof_field(struct nf_nat_range, min_addr.ip6); break; default: - return -EAFNOSUPPORT; + if (tb[NFTA_NAT_REG_ADDR_MIN]) + return -EAFNOSUPPORT; + break; } priv->family = family; diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 9115f8a7dd45..a8da88db7893 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -121,11 +121,9 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { - sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); - sock_put(sk); - return; + goto out; } break; @@ -146,6 +144,8 @@ static void nr_heartbeat_expiry(struct timer_list *t) nr_start_heartbeat(sk); bh_unlock_sock(sk); +out: + sock_put(sk); } static void nr_t2timer_expiry(struct timer_list *t) @@ -159,6 +159,7 @@ static void nr_t2timer_expiry(struct timer_list *t) nr_enquiry_response(sk); } bh_unlock_sock(sk); + sock_put(sk); } static void nr_t4timer_expiry(struct timer_list *t) @@ -169,6 +170,7 @@ static void nr_t4timer_expiry(struct timer_list *t) bh_lock_sock(sk); nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY; bh_unlock_sock(sk); + sock_put(sk); } static void nr_idletimer_expiry(struct timer_list *t) @@ -197,6 +199,7 @@ static void nr_idletimer_expiry(struct timer_list *t) sock_set_flag(sk, SOCK_DEAD); } bh_unlock_sock(sk); + sock_put(sk); } static void nr_t1timer_expiry(struct timer_list *t) @@ -209,8 +212,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_1: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_CONNREQ); @@ -220,8 +222,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_2: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_DISCREQ); @@ -231,8 +232,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_3: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_requeue_frames(sk); @@ -241,5 +241,7 @@ static void nr_t1timer_expiry(struct timer_list *t) } nr_start_t1timer(sk); +out: bh_unlock_sock(sk); + sock_put(sk); } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index e586424d8b04..9713035b89e3 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -293,14 +293,14 @@ static bool icmp6hdr_ok(struct sk_buff *skb) } /** - * Parse vlan tag from vlan header. + * parse_vlan_tag - Parse vlan tag from vlan header. * @skb: skb containing frame to parse * @key_vh: pointer to parsed vlan tag * @untag_vlan: should the vlan header be removed from the frame * - * Returns ERROR on memory error. - * Returns 0 if it encounters a non-vlan or incomplete packet. - * Returns 1 after successfully parsing vlan tag. + * Return: ERROR on memory error. + * %0 if it encounters a non-vlan or incomplete packet. + * %1 after successfully parsing vlan tag. */ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh, bool untag_vlan) @@ -532,6 +532,7 @@ static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) * L3 header * @key: output flow key * + * Return: %0 if successful, otherwise a negative errno value. */ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) { @@ -748,8 +749,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * * The caller must ensure that skb->len >= ETH_HLEN. * - * Returns 0 if successful, otherwise a negative errno value. - * * Initializes @skb header fields as follows: * * - skb->mac_header: the L2 header. @@ -764,6 +763,8 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * * - skb->protocol: the type of the data starting at skb->network_header. * Equals to key->eth.type. + * + * Return: %0 if successful, otherwise a negative errno value. */ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) { diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 88deb5b41429..cf2ce5812489 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -507,6 +507,7 @@ void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto) } skb->dev = vport->dev; + skb->tstamp = 0; vport->ops->send(skb); return; diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index fa611678af05..1dc955ca57d3 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -15,6 +15,7 @@ struct qrtr_mhi_dev { struct qrtr_endpoint ep; struct mhi_device *mhi_dev; struct device *dev; + struct completion ready; }; /* From MHI to QRTR */ @@ -50,6 +51,10 @@ static int qcom_mhi_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb) struct qrtr_mhi_dev *qdev = container_of(ep, struct qrtr_mhi_dev, ep); int rc; + rc = wait_for_completion_interruptible(&qdev->ready); + if (rc) + goto free_skb; + if (skb->sk) sock_hold(skb->sk); @@ -79,7 +84,7 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, int rc; /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev); + rc = mhi_prepare_for_transfer(mhi_dev, 0); if (rc) return rc; @@ -96,6 +101,15 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, if (rc) return rc; + /* start channels */ + rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS); + if (rc) { + qrtr_endpoint_unregister(&qdev->ep); + dev_set_drvdata(&mhi_dev->dev, NULL); + return rc; + } + + complete_all(&qdev->ready); dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n"); return 0; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index e6f4a6202f82..171b7f3be6ef 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -518,8 +518,10 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!ipc) goto err; - if (sock_queue_rcv_skb(&ipc->sk, skb)) + if (sock_queue_rcv_skb(&ipc->sk, skb)) { + qrtr_port_put(ipc); goto err; + } qrtr_port_put(ipc); } @@ -839,6 +841,8 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, ipc = qrtr_port_lookup(to->sq_port); if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */ + if (ipc) + qrtr_port_put(ipc); kfree_skb(skb); return -ENODEV; } diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 9b6ffff72f2d..28c1b0022178 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -131,9 +131,9 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) cpu_relax(); } - ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_len, + ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len, &off, PAGE_SIZE); - if (unlikely(ret != ibmr->sg_len)) + if (unlikely(ret != ibmr->sg_dma_len)) return ret < 0 ? ret : -EINVAL; if (cmpxchg(&frmr->fr_state, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 7153c67f641e..2ef4cd2c848b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -273,6 +273,9 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } + /* All mirred/redirected skbs should clear previous ct info */ + nf_reset_ct(skb2); + want_ingress = tcf_mirred_act_wants_ingress(m_eaction); expects_nh = want_ingress || !m_mac_header_xmit; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 81a1c67335be..8d17a543cc9f 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -6,6 +6,7 @@ */ #include <linux/module.h> +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> @@ -33,6 +34,13 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&d->tcf_tm); bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + action = READ_ONCE(d->tcf_action); + if (unlikely(action == TC_ACT_SHOT)) + goto drop; + + if (!skb->dev || skb->dev->type != ARPHRD_ETHER) + return action; + /* XXX: if you are going to edit more fields beyond ethernet header * (example when you add IP header replacement or vlan swap) * then MAX_EDIT_LEN needs to change appropriately @@ -41,10 +49,6 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, if (unlikely(err)) /* best policy is to drop on the floor */ goto drop; - action = READ_ONCE(d->tcf_action); - if (unlikely(action == TC_ACT_SHOT)) - goto drop; - p = rcu_dereference_bh(d->skbmod_p); flags = p->flags; if (flags & SKBMOD_F_DMAC) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d73b5c5514a9..e3e79e9bd706 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2904,7 +2904,7 @@ replay: break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, - n->nlmsg_seq, n->nlmsg_type, true); + n->nlmsg_flags, n->nlmsg_type, true); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); break; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 5b274534264c..e9a8a2c86bbd 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -278,6 +278,8 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r, TCA_TCINDEX_POLICE); } +static void tcindex_free_perfect_hash(struct tcindex_data *cp); + static void tcindex_partial_destroy_work(struct work_struct *work) { struct tcindex_data *p = container_of(to_rcu_work(work), @@ -285,7 +287,8 @@ static void tcindex_partial_destroy_work(struct work_struct *work) rwork); rtnl_lock(); - kfree(p->perfect); + if (p->perfect) + tcindex_free_perfect_hash(p); kfree(p); rtnl_unlock(); } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 951542843cab..28af8b1e1bb1 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -720,7 +720,7 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, skip_hash: if (flow_override) flow_hash = flow_override - 1; - else if (use_skbhash) + else if (use_skbhash && (flow_mode & CAKE_FLOW_FLOWS)) flow_hash = skb->hash; if (host_override) { dsthost_hash = host_override - 1; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index d9ac60ffe927..a8dd06c74e31 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -913,7 +913,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); - lockdep_set_class(&sch->busylock, + lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); seqcount_init(&sch->running); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 07b30d0601d7..9c79374457a0 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1739,8 +1739,6 @@ static void taprio_attach(struct Qdisc *sch) if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); - if (ntx < dev->real_num_tx_queues) - qdisc_hash_add(qdisc, false); } else { old = dev_graft_qdisc(qdisc->dev_queue, sch); qdisc_refcount_inc(sch); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 6f8319b828b0..db6b7373d16c 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -857,12 +857,18 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, memcpy(key->data, &auth_key->sca_key[0], auth_key->sca_keylength); cur_key->key = key; - if (replace) { - list_del_init(&shkey->key_list); - sctp_auth_shkey_release(shkey); + if (!replace) { + list_add(&cur_key->key_list, sh_keys); + return 0; } + + list_del_init(&shkey->key_list); + sctp_auth_shkey_release(shkey); list_add(&cur_key->key_list, sh_keys); + if (asoc && asoc->active_key_id == auth_key->sca_keynumber) + sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); + return 0; } diff --git a/net/sctp/input.c b/net/sctp/input.c index eb3c2a34a31c..5ef86fdb1176 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -1203,7 +1203,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (unlikely(!af)) return NULL; - if (af->from_addr_param(&paddr, param, peer_port, 0)) + if (!af->from_addr_param(&paddr, param, peer_port, 0)) return NULL; return __sctp_lookup_association(net, laddr, &paddr, transportp); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e48dd909dee5..470dbdc27d58 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -100,8 +100,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, list_for_each_entry_safe(addr, temp, &net->sctp.local_addr_list, list) { if (addr->a.sa.sa_family == AF_INET6 && - ipv6_addr_equal(&addr->a.v6.sin6_addr, - &ifa->addr)) { + ipv6_addr_equal(&addr->a.v6.sin6_addr, + &ifa->addr) && + addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) { sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; diff --git a/net/sctp/output.c b/net/sctp/output.c index 9032ce60d50e..4dfb5ea82b05 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -104,8 +104,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); } else if (!sctp_transport_pl_enabled(tp) && - !sctp_transport_pmtu_check(tp)) { - if (asoc->param_flags & SPP_PMTUD_ENABLE) + asoc->param_flags & SPP_PMTUD_ENABLE) { + if (!sctp_transport_pmtu_check(tp)) sctp_assoc_sync_pmtu(asoc); } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 09a8f23ec709..32df65f68c12 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1109,12 +1109,12 @@ enum sctp_disposition sctp_sf_send_probe(struct net *net, if (!sctp_transport_pl_enabled(transport)) return SCTP_DISPOSITION_CONSUME; - sctp_transport_pl_send(transport); - - reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); - if (!reply) - return SCTP_DISPOSITION_NOMEM; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + if (sctp_transport_pl_send(transport)) { + reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); + if (!reply) + return SCTP_DISPOSITION_NOMEM; + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + } sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE, SCTP_TRANSPORT(transport)); @@ -1274,8 +1274,7 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net, !sctp_transport_pl_enabled(link)) return SCTP_DISPOSITION_DISCARD; - sctp_transport_pl_recv(link); - if (link->pl.state == SCTP_PL_COMPLETE) + if (sctp_transport_pl_recv(link)) return SCTP_DISPOSITION_CONSUME; return sctp_sf_send_probe(net, ep, asoc, type, link, commands); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e64e01f61b11..6b937bfd4751 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4577,6 +4577,10 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, } if (optlen > 0) { + /* Trim it to the biggest size sctp sockopt may need if necessary */ + optlen = min_t(unsigned int, optlen, + PAGE_ALIGN(USHRT_MAX + + sizeof(__u16) * sizeof(struct sctp_reset_streams))); kopt = memdup_sockptr(optval, optlen); if (IS_ERR(kopt)) return PTR_ERR(kopt); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 397a6244dd97..a3d3ca6dd63d 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -258,16 +258,13 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) sctp_transport_pl_update(transport); } -void sctp_transport_pl_send(struct sctp_transport *t) +bool sctp_transport_pl_send(struct sctp_transport *t) { - pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", - __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); - - if (t->pl.probe_count < SCTP_MAX_PROBES) { - t->pl.probe_count++; - return; - } + if (t->pl.probe_count < SCTP_MAX_PROBES) + goto out; + t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks; + t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */ t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ @@ -299,14 +296,27 @@ void sctp_transport_pl_send(struct sctp_transport *t) sctp_assoc_sync_pmtu(t->asoc); } } - t->pl.probe_count = 1; + +out: + if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count < 30 && + !t->pl.probe_count && t->pl.last_rtx_chunks == t->asoc->rtx_data_chunks) { + t->pl.raise_count++; + return false; + } + + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + t->pl.probe_count++; + return true; } -void sctp_transport_pl_recv(struct sctp_transport *t) +bool sctp_transport_pl_recv(struct sctp_transport *t) { pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks; t->pl.pmtu = t->pl.probe_size; t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { @@ -323,7 +333,7 @@ void sctp_transport_pl_recv(struct sctp_transport *t) if (!t->pl.probe_high) { t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, SCTP_MAX_PLPMTU); - return; + return false; } t->pl.probe_size += SCTP_PL_MIN_STEP; if (t->pl.probe_size >= t->pl.probe_high) { @@ -335,14 +345,13 @@ void sctp_transport_pl_recv(struct sctp_transport *t) t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } - } else if (t->pl.state == SCTP_PL_COMPLETE) { - t->pl.raise_count++; - if (t->pl.raise_count == 30) { - /* Raise probe_size again after 30 * interval in Search Complete */ - t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; - } + } else if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count == 30) { + /* Raise probe_size again after 30 * interval in Search Complete */ + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; } + + return t->pl.state == SCTP_PL_COMPLETE; } static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 898389611ae8..c038efc23ce3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -795,7 +795,7 @@ static int smc_connect_rdma(struct smc_sock *smc, reason_code = SMC_CLC_DECL_NOSRVLINK; goto connect_abort; } - smc->conn.lnk = link; + smc_switch_link_and_count(&smc->conn, link); } /* create send buffer and rmb */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index cd0d7c908b2a..c160ff50c053 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -917,8 +917,8 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, return rc; } -static void smc_switch_link_and_count(struct smc_connection *conn, - struct smc_link *to_lnk) +void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_lnk) { atomic_dec(&conn->lnk->conn_cnt); conn->lnk = to_lnk; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 6d6fd1397c87..c043ecdca5c4 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -97,6 +97,7 @@ struct smc_link { unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */ + atomic_t wr_tx_refcnt; /* tx refs to link */ struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */ struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */ @@ -109,6 +110,7 @@ struct smc_link { struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ + atomic_t wr_reg_refcnt; /* reg refs to link */ enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */ u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/ @@ -444,6 +446,8 @@ void smc_core_exit(void); int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini); void smcr_link_clear(struct smc_link *lnk, bool log); +void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_lnk); int smcr_buf_map_lgr(struct smc_link *lnk); int smcr_buf_reg_lgr(struct smc_link *lnk); void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type); diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 273eaf1bfe49..2e7560eba981 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -888,6 +888,7 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) if (!rc) goto out; out_clear_lnk: + lnk_new->state = SMC_LNK_INACTIVE; smcr_link_clear(lnk_new, false); out_reject: smc_llc_cli_add_link_reject(qentry); @@ -1184,6 +1185,7 @@ int smc_llc_srv_add_link(struct smc_link *link) goto out_err; return 0; out_err: + link_new->state = SMC_LNK_INACTIVE; smcr_link_clear(link_new, false); return rc; } @@ -1286,10 +1288,8 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) del_llc->reason = 0; smc_llc_send_message(lnk, &qentry->msg); /* response */ - if (smc_link_downing(&lnk_del->state)) { - if (smc_switch_conns(lgr, lnk_del, false)) - smc_wr_tx_wait_no_pending_sends(lnk_del); - } + if (smc_link_downing(&lnk_del->state)) + smc_switch_conns(lgr, lnk_del, false); smcr_link_clear(lnk_del, true); active_links = smc_llc_active_link_count(lgr); @@ -1805,8 +1805,6 @@ void smc_llc_link_clear(struct smc_link *link, bool log) link->smcibdev->ibdev->name, link->ibport); complete(&link->llc_testlink_resp); cancel_delayed_work_sync(&link->llc_testlink_wrk); - smc_wr_wakeup_reg_wait(link); - smc_wr_wakeup_tx_wait(link); } /* register a new rtoken at the remote peer (for all links) */ diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 289025cd545a..c79361dfcdfb 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -496,7 +496,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn, /* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit */ -static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) +static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; struct smc_link *link = conn->lnk; @@ -550,6 +550,22 @@ out_unlock: return rc; } +static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) +{ + struct smc_link *link = conn->lnk; + int rc = -ENOLINK; + + if (!link) + return rc; + + atomic_inc(&link->wr_tx_refcnt); + if (smc_link_usable(link)) + rc = _smcr_tx_sndbuf_nonempty(conn); + if (atomic_dec_and_test(&link->wr_tx_refcnt)) + wake_up_all(&link->wr_tx_wait); + return rc; +} + static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index cbc73a7e4d59..a419e9af36b9 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -322,9 +322,12 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr) if (rc) return rc; + atomic_inc(&link->wr_reg_refcnt); rc = wait_event_interruptible_timeout(link->wr_reg_wait, (link->wr_reg_state != POSTED), SMC_WR_REG_MR_WAIT_TIME); + if (atomic_dec_and_test(&link->wr_reg_refcnt)) + wake_up_all(&link->wr_reg_wait); if (!rc) { /* timeout - terminate link */ smcr_link_down_cond_sched(link); @@ -566,10 +569,15 @@ void smc_wr_free_link(struct smc_link *lnk) return; ibdev = lnk->smcibdev->ibdev; + smc_wr_wakeup_reg_wait(lnk); + smc_wr_wakeup_tx_wait(lnk); + if (smc_wr_tx_wait_no_pending_sends(lnk)) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); + wait_event(lnk->wr_reg_wait, (!atomic_read(&lnk->wr_reg_refcnt))); + wait_event(lnk->wr_tx_wait, (!atomic_read(&lnk->wr_tx_refcnt))); if (lnk->wr_rx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, @@ -728,7 +736,9 @@ int smc_wr_create_link(struct smc_link *lnk) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); init_waitqueue_head(&lnk->wr_tx_wait); + atomic_set(&lnk->wr_tx_refcnt, 0); init_waitqueue_head(&lnk->wr_reg_wait); + atomic_set(&lnk->wr_reg_refcnt, 0); return rc; dma_unmap: diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index e5c43d4d5a75..c9391d38de85 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -898,16 +898,10 @@ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead, if (unlikely(!aead)) return -ENOKEY; - /* Cow skb data if needed */ - if (likely(!skb_cloned(skb) && - (!skb_is_nonlinear(skb) || !skb_has_frag_list(skb)))) { - nsg = 1 + skb_shinfo(skb)->nr_frags; - } else { - nsg = skb_cow_data(skb, 0, &unused); - if (unlikely(nsg < 0)) { - pr_err("RX: skb_cow_data() returned %d\n", nsg); - return nsg; - } + nsg = skb_cow_data(skb, 0, &unused); + if (unlikely(nsg < 0)) { + pr_err("RX: skb_cow_data() returned %d\n", nsg); + return nsg; } /* Allocate memory for the AEAD operation */ diff --git a/net/tipc/link.c b/net/tipc/link.c index cf586840caeb..1b7a487c8841 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -913,7 +913,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, dnode, l->addr, dport, 0, 0); if (!skb) - return -ENOMEM; + return -ENOBUFS; msg_set_dest_droppable(buf_msg(skb), true); TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr); skb_queue_tail(&l->wakeupq, skb); @@ -1031,7 +1031,7 @@ void tipc_link_reset(struct tipc_link *l) * * Consumes the buffer chain. * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted - * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS or -ENOMEM + * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS */ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) @@ -1089,7 +1089,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, if (!_skb) { kfree_skb(skb); __skb_queue_purge(list); - return -ENOMEM; + return -ENOBUFS; } __skb_queue_tail(transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 34a97ea36cc8..8754bd885169 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -158,6 +158,7 @@ static void tipc_sk_remove(struct tipc_sock *tsk); static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz); static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz); static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack); +static int tipc_wait_for_connect(struct socket *sock, long *timeo_p); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -1515,8 +1516,13 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) rc = 0; } - if (unlikely(syn && !rc)) + if (unlikely(syn && !rc)) { tipc_set_sk_state(sk, TIPC_CONNECTING); + if (dlen && timeout) { + timeout = msecs_to_jiffies(timeout); + tipc_wait_for_connect(sock, &timeout); + } + } return rc ? rc : dlen; } @@ -1564,7 +1570,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) return -EMSGSIZE; /* Handle implicit connection setup */ - if (unlikely(dest)) { + if (unlikely(dest && sk->sk_state == TIPC_OPEN)) { rc = __tipc_sendmsg(sock, m, dlen); if (dlen && dlen == rc) { tsk->peer_caps = tipc_node_get_capabilities(net, dnode); @@ -2646,7 +2652,7 @@ static int tipc_listen(struct socket *sock, int len) static int tipc_wait_for_accept(struct socket *sock, long timeo) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err; /* True wake-one mechanism for incoming connections: only @@ -2655,12 +2661,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * anymore, the common case will execute the loop only once. */ for (;;) { - prepare_to_wait_exclusive(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -2672,7 +2678,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) if (signal_pending(current)) break; } - finish_wait(sk_sleep(sk), &wait); return err; } @@ -2689,9 +2694,10 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, bool kern) { struct sock *new_sk, *sk = sock->sk; - struct sk_buff *buf; struct tipc_sock *new_tsock; + struct msghdr m = {NULL,}; struct tipc_msg *msg; + struct sk_buff *buf; long timeo; int res; @@ -2737,19 +2743,17 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, } /* - * Respond to 'SYN-' by discarding it & returning 'ACK'-. - * Respond to 'SYN+' by queuing it on new socket. + * Respond to 'SYN-' by discarding it & returning 'ACK'. + * Respond to 'SYN+' by queuing it on new socket & returning 'ACK'. */ if (!msg_data_sz(msg)) { - struct msghdr m = {NULL,}; - tsk_advance_rx_queue(sk); - __tipc_sendstream(new_sock, &m, 0); } else { __skb_dequeue(&sk->sk_receive_queue); __skb_queue_head(&new_sk->sk_receive_queue, buf); skb_set_owner_r(buf, new_sk); } + __tipc_sendstream(new_sock, &m, 0); release_sock(new_sk); exit: release_sock(sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 23c92ad15c61..ba7ced947e51 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1526,6 +1526,53 @@ out: return err; } +static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = scm_fp_dup(UNIXCB(skb).fp); + + /* + * Garbage collection of unix sockets starts by selecting a set of + * candidate sockets which have reference only from being in flight + * (total_refs == inflight_refs). This condition is checked once during + * the candidate collection phase, and candidates are marked as such, so + * that non-candidates can later be ignored. While inflight_refs is + * protected by unix_gc_lock, total_refs (file count) is not, hence this + * is an instantaneous decision. + * + * Once a candidate, however, the socket must not be reinstalled into a + * file descriptor while the garbage collection is in progress. + * + * If the above conditions are met, then the directed graph of + * candidates (*) does not change while unix_gc_lock is held. + * + * Any operations that changes the file count through file descriptors + * (dup, close, sendmsg) does not change the graph since candidates are + * not installed in fds. + * + * Dequeing a candidate via recvmsg would install it into an fd, but + * that takes unix_gc_lock to decrement the inflight count, so it's + * serialized with garbage collection. + * + * MSG_PEEK is special in that it does not change the inflight count, + * yet does install the socket into an fd. The following lock/unlock + * pair is to ensure serialization with garbage collection. It must be + * done between incrementing the file count and installing the file into + * an fd. + * + * If garbage collection starts after the barrier provided by the + * lock/unlock, then it will see the elevated refcount and not mark this + * as a candidate. If a garbage collection is already in progress + * before the file count was incremented, then the lock/unlock pair will + * ensure that garbage collection is finished before progressing to + * installing the fd. + * + * (*) A -> B where B is on the queue of A or B is on the queue of C + * which is on the queue of listening socket A. + */ + spin_lock(&unix_gc_lock); + spin_unlock(&unix_gc_lock); +} + static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { int err = 0; @@ -2175,7 +2222,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, sk_peek_offset_fwd(sk, size); if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); } err = (flags & MSG_TRUNC) ? skb->len - skip : size; @@ -2418,7 +2465,7 @@ unlock: /* It is questionable, see note in unix_dgram_recvmsg. */ if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); sk_peek_offset_fwd(sk, chunk); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index e0c2c992ad9c..4f7c99dfd16c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -357,11 +357,14 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock) static void virtio_vsock_reset_sock(struct sock *sk) { - lock_sock(sk); + /* vmci_transport.c doesn't take sk_lock here either. At least we're + * under vsock_table_lock so the sock cannot disappear while we're + * executing. + */ + sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; sk_error_report(sk); - release_sock(sk); } static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 169ba8b72a63..081e7ae93cb1 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1079,6 +1079,9 @@ virtio_transport_recv_connected(struct sock *sk, virtio_transport_recv_enqueue(vsk, pkt); sk->sk_data_ready(sk); return err; + case VIRTIO_VSOCK_OP_CREDIT_REQUEST: + virtio_transport_send_credit_update(vsk); + break; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: sk->sk_write_space(sk); break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 50eb405b0690..16c88beea48b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2351,7 +2351,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, goto nla_put_failure; for (band = state->band_start; - band < NUM_NL80211_BANDS; band++) { + band < (state->split ? + NUM_NL80211_BANDS : + NL80211_BAND_60GHZ + 1); + band++) { struct ieee80211_supported_band *sband; /* omit higher bands for ancient software */ diff --git a/net/wireless/scan.c b/net/wireless/scan.c index f03c7ac8e184..7897b1478c3c 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1754,16 +1754,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, * be grouped with this beacon for updates ... */ if (!cfg80211_combine_bsses(rdev, new)) { - kfree(new); + bss_ref_put(rdev, new); goto drop; } } if (rdev->bss_entries >= bss_entries_limit && !cfg80211_bss_expire_oldest(rdev)) { - if (!list_empty(&new->hidden_list)) - list_del(&new->hidden_list); - kfree(new); + bss_ref_put(rdev, new); goto drop; } diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a20aec9d7393..2bf269390163 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -298,8 +298,16 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]); nla_for_each_attr(nla, attrs, len, remaining) { - int err = xfrm_xlate64_attr(dst, nla); + int err; + switch (type) { + case XFRM_MSG_NEWSPDINFO: + err = xfrm_nla_cpy(dst, nla, nla_len(nla)); + break; + default: + err = xfrm_xlate64_attr(dst, nla); + break; + } if (err) return err; } @@ -341,7 +349,8 @@ static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src /* Calculates len of translated 64-bit message. */ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src, - struct nlattr *attrs[XFRMA_MAX+1]) + struct nlattr *attrs[XFRMA_MAX + 1], + int maxtype) { size_t len = nlmsg_len(src); @@ -358,10 +367,20 @@ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src, case XFRM_MSG_POLEXPIRE: len += 8; break; + case XFRM_MSG_NEWSPDINFO: + /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ + return len; default: break; } + /* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please + * correct both 64=>32-bit and 32=>64-bit translators to copy + * new attributes. + */ + if (WARN_ON_ONCE(maxtype)) + return len; + if (attrs[XFRMA_SA]) len += 4; if (attrs[XFRMA_POLICY]) @@ -440,7 +459,8 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, struct nlattr *attrs[XFRMA_MAX+1], - size_t size, u8 type, struct netlink_ext_ack *extack) + size_t size, u8 type, int maxtype, + struct netlink_ext_ack *extack) { size_t pos; int i; @@ -520,6 +540,25 @@ static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, } pos = dst->nlmsg_len; + if (maxtype) { + /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ + WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO); + + for (i = 1; i <= maxtype; i++) { + int err; + + if (!attrs[i]) + continue; + + /* just copy - no need for translation */ + err = xfrm_attr_cpy32(dst, &pos, attrs[i], size, + nla_len(attrs[i]), nla_len(attrs[i])); + if (err) + return err; + } + return 0; + } + for (i = 1; i < XFRMA_MAX + 1; i++) { int err; @@ -564,7 +603,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, if (err < 0) return ERR_PTR(err); - len = xfrm_user_rcv_calculate_len64(h32, attrs); + len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype); /* The message doesn't need translation */ if (len == nlmsg_len(h32)) return NULL; @@ -574,7 +613,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, if (!h64) return ERR_PTR(-ENOMEM); - err = xfrm_xlate32(h64, h32, attrs, len, type, extack); + err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack); if (err < 0) { kvfree(h64); return ERR_PTR(err); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 2e8afe078d61..cb40ff0ff28d 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -241,7 +241,7 @@ static void ipcomp_free_tfms(struct crypto_comp * __percpu *tfms) break; } - WARN_ON(!pos); + WARN_ON(list_entry_is_head(pos, &ipcomp_tfms_list, list)); if (--pos->users) return; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 827d84255021..7f881f5a5897 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -155,7 +155,6 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; static struct kmem_cache *xfrm_dst_cache __ro_after_init; -static __read_mostly seqcount_mutex_t xfrm_policy_hash_generation; static struct rhashtable xfrm_policy_inexact_table; static const struct rhashtable_params xfrm_pol_inexact_params; @@ -585,7 +584,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); - write_seqcount_begin(&xfrm_policy_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)); @@ -596,7 +595,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst); net->xfrm.policy_bydst[dir].hmask = nhashmask; - write_seqcount_end(&xfrm_policy_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); synchronize_rcu(); @@ -1245,7 +1244,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); - write_seqcount_begin(&xfrm_policy_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. @@ -1354,7 +1353,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) out_unlock: __xfrm_policy_inexact_flush(net); - write_seqcount_end(&xfrm_policy_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); @@ -2091,15 +2090,12 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (unlikely(!daddr || !saddr)) return NULL; - retry: - sequence = read_seqcount_begin(&xfrm_policy_hash_generation); rcu_read_lock(); - - chain = policy_hash_direct(net, daddr, saddr, family, dir); - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { - rcu_read_unlock(); - goto retry; - } + retry: + do { + sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); + chain = policy_hash_direct(net, daddr, saddr, family, dir); + } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)); ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { @@ -2130,15 +2126,11 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } skip_inexact: - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { - rcu_read_unlock(); + if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)) goto retry; - } - if (ret && !xfrm_pol_hold_rcu(ret)) { - rcu_read_unlock(); + if (ret && !xfrm_pol_hold_rcu(ret)) goto retry; - } fail: rcu_read_unlock(); @@ -4089,6 +4081,7 @@ static int __net_init xfrm_net_init(struct net *net) /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); spin_lock_init(&net->xfrm.xfrm_policy_lock); + seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); rv = xfrm_statistics_init(net); @@ -4133,7 +4126,6 @@ void __init xfrm_init(void) { register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); - seqcount_mutex_init(&xfrm_policy_hash_generation, &hash_resize_mutex); xfrm_input_init(); #ifdef CONFIG_XFRM_ESPINTCP diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b47d613409b7..7aff641c717d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2811,6 +2811,16 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, err = link->doit(skb, nlh, attrs); + /* We need to free skb allocated in xfrm_alloc_compat() before + * returning from this function, because consume_skb() won't take + * care of frag_list since netlink destructor sets + * sbk->head to NULL. (see netlink_skb_destructor()) + */ + if (skb_has_frag_list(skb)) { + kfree_skb(skb_shinfo(skb)->frag_list); + skb_shinfo(skb)->frag_list = NULL; + } + err: kvfree(nlh64); return err; |