diff options
Diffstat (limited to 'net')
92 files changed, 827 insertions, 531 deletions
diff --git a/net/Makefile b/net/Makefile index 6a62e5b27378..0914bea9c335 100644 --- a/net/Makefile +++ b/net/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ +obj-$(CONFIG_NET_DEVLINK) += devlink/ obj-$(CONFIG_NET_DSA) += dsa/ obj-$(CONFIG_ATALK) += appletalk/ obj-$(CONFIG_X25) += x25/ diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index f1741fbfb617..98a624f32b94 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -506,7 +506,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_elp_packet *elp_packet; struct batadv_hard_iface *primary_if; - struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); + struct ethhdr *ethhdr; bool res; int ret = NET_RX_DROP; @@ -514,6 +514,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, if (!res) goto free_skb; + ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 033639df96d8..9f4815f4c8e8 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -124,8 +124,10 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - if (hard_iface->if_status != BATADV_IF_ACTIVE) + if (hard_iface->if_status != BATADV_IF_ACTIVE) { + kfree_skb(skb); return; + } batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_TX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES, @@ -986,7 +988,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_ogm2_packet *ogm_packet; - struct ethhdr *ethhdr = eth_hdr(skb); + struct ethhdr *ethhdr; int ogm_offset; u8 *packet_pos; int ret = NET_RX_DROP; @@ -1000,6 +1002,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN)) goto free_skb; + ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 41c1ad33d009..24c9c0c3f316 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -630,7 +630,19 @@ out: */ void batadv_update_min_mtu(struct net_device *soft_iface) { - soft_iface->mtu = batadv_hardif_min_mtu(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + int limit_mtu; + int mtu; + + mtu = batadv_hardif_min_mtu(soft_iface); + + if (bat_priv->mtu_set_by_user) + limit_mtu = bat_priv->mtu_set_by_user; + else + limit_mtu = ETH_DATA_LEN; + + mtu = min(mtu, limit_mtu); + dev_set_mtu(soft_iface, mtu); /* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU. diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index a5e4a4e976cf..86e0664e0511 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -495,7 +495,10 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); + + rtnl_lock(); batadv_update_min_mtu(bat_priv->soft_iface); + rtnl_unlock(); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) { diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 0f5c0679b55a..38d411a52f33 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -154,11 +154,14 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) { + struct batadv_priv *bat_priv = netdev_priv(dev); + /* check ranges */ if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev)) return -EINVAL; dev->mtu = new_mtu; + bat_priv->mtu_set_by_user = new_mtu; return 0; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 01d30c1e412c..5d8cee74772f 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -774,7 +774,6 @@ check_roaming: if (roamed_back) { batadv_tt_global_free(bat_priv, tt_global, "Roaming canceled"); - tt_global = NULL; } else { /* The global entry has to be marked as ROAMING and * has to be kept for consistency purpose diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 758cd797a063..76791815b26b 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1547,6 +1547,12 @@ struct batadv_priv { struct net_device *soft_iface; /** + * @mtu_set_by_user: MTU was set once by user + * protected by rtnl_lock + */ + int mtu_set_by_user; + + /** * @bat_counters: mesh internal traffic statistic counters (see * batadv_counters) */ diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 02fc9961464c..a7899857aee5 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6375,9 +6375,14 @@ static inline int l2cap_le_command_rej(struct l2cap_conn *conn, if (!chan) goto done; + chan = l2cap_chan_hold_unless_zero(chan); + if (!chan) + goto done; + l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNREFUSED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); done: mutex_unlock(&conn->chan_lock); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index eebe256104bc..947ca580bb9a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -46,6 +46,7 @@ static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern); +static void l2cap_sock_cleanup_listen(struct sock *parent); bool l2cap_is_socket(struct socket *sock) { @@ -1415,6 +1416,7 @@ static int l2cap_sock_release(struct socket *sock) if (!sk) return 0; + l2cap_sock_cleanup_listen(sk); bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, SHUT_RDWR); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 89c94f3e96bc..d2e8565d0b33 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7277,7 +7277,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - memcpy(&rp.addr, &cp->addr.bdaddr, sizeof(rp.addr)); + memcpy(&rp.addr, &cp->addr, sizeof(rp.addr)); status = mgmt_status(err); if (status == MGMT_STATUS_SUCCESS) { diff --git a/net/can/isotp.c b/net/can/isotp.c index b3c2a49b189c..8c97f4061ffd 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -175,12 +175,6 @@ static bool isotp_register_rxid(struct isotp_sock *so) return (isotp_bc_flags(so) == 0); } -static bool isotp_register_txecho(struct isotp_sock *so) -{ - /* all modes but SF_BROADCAST register for tx echo skbs */ - return (isotp_bc_flags(so) != CAN_ISOTP_SF_BROADCAST); -} - static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, @@ -1176,7 +1170,7 @@ static int isotp_release(struct socket *sock) lock_sock(sk); /* remove current filters & unregister */ - if (so->bound && isotp_register_txecho(so)) { + if (so->bound) { if (so->ifindex) { struct net_device *dev; @@ -1293,14 +1287,12 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id), isotp_rcv, sk, "isotp", sk); - if (isotp_register_txecho(so)) { - /* no consecutive frame echo skb in flight */ - so->cfecho = 0; + /* no consecutive frame echo skb in flight */ + so->cfecho = 0; - /* register for echo skb's */ - can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), - isotp_rcv_echo, sk, "isotpe", sk); - } + /* register for echo skb's */ + can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), + isotp_rcv_echo, sk, "isotpe", sk); dev_put(dev); @@ -1521,7 +1513,7 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (so->bound && isotp_register_txecho(so)) { + if (so->bound) { if (isotp_register_rxid(so)) can_rx_unregister(dev_net(dev), dev, so->rxid, SINGLE_MASK(so->rxid), diff --git a/net/can/raw.c b/net/can/raw.c index 4abab2c3011a..8c104339d538 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,6 +84,8 @@ struct raw_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; + netdevice_tracker dev_tracker; struct list_head notifier; int loopback; int recv_own_msgs; @@ -277,21 +279,24 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return; - if (ro->ifindex != dev->ifindex) + if (ro->dev != dev) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (ro->bound) + if (ro->bound) { raw_disable_allfilters(dev_net(dev), dev, sk); + netdev_put(dev, &ro->dev_tracker); + } if (ro->count > 1) kfree(ro->filter); ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; release_sock(sk); @@ -337,6 +342,7 @@ static int raw_init(struct sock *sk) ro->bound = 0; ro->ifindex = 0; + ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; @@ -383,18 +389,14 @@ static int raw_release(struct socket *sock) list_del(&ro->notifier); spin_unlock(&raw_notifier_lock); + rtnl_lock(); lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) { - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), dev, sk); - dev_put(dev); - } + if (ro->dev) { + raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); + netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } @@ -405,6 +407,7 @@ static int raw_release(struct socket *sock) ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); @@ -412,6 +415,8 @@ static int raw_release(struct socket *sock) sock->sk = NULL; release_sock(sk); + rtnl_unlock(); + sock_put(sk); return 0; @@ -422,6 +427,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); + struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; @@ -431,24 +437,23 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (addr->can_family != AF_CAN) return -EINVAL; + rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { - struct net_device *dev; - dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; } if (dev->type != ARPHRD_CAN) { - dev_put(dev); err = -ENODEV; - goto out; + goto out_put_dev; } + if (!(dev->flags & IFF_UP)) notify_enetdown = 1; @@ -456,7 +461,9 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), dev, sk); - dev_put(dev); + if (err) + goto out_put_dev; + } else { ifindex = 0; @@ -467,26 +474,30 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), - ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), - dev, sk); - dev_put(dev); - } + if (ro->dev) { + raw_disable_allfilters(dev_net(ro->dev), + ro->dev, sk); + /* drop reference to old ro->dev */ + netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } } ro->ifindex = ifindex; ro->bound = 1; + /* bind() ok -> hold a reference for new ro->dev */ + ro->dev = dev; + if (ro->dev) + netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL); } - out: +out_put_dev: + /* remove potential reference from dev_get_by_index() */ + if (dev) + dev_put(dev); +out: release_sock(sk); + rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -552,9 +563,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; @@ -595,7 +606,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->count = count; out_fil: - dev_put(dev); release_sock(sk); rtnl_unlock(); @@ -613,9 +623,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } @@ -639,7 +649,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->err_mask = err_mask; out_err: - dev_put(dev); release_sock(sk); rtnl_unlock(); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 4e4f1e4bc265..c22bb06b450e 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -3334,17 +3334,24 @@ static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq) int ret; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->reg_commit_wait); + ret = wait_for_completion_killable(&lreq->reg_commit_wait); return ret ?: lreq->reg_commit_error; } -static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq) +static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq, + unsigned long timeout) { - int ret; + long left; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->notify_finish_wait); - return ret ?: lreq->notify_finish_error; + left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait, + ceph_timeout_jiffies(timeout)); + if (left <= 0) + left = left ?: -ETIMEDOUT; + else + left = lreq->notify_finish_error; /* completed */ + + return left; } /* @@ -4896,7 +4903,8 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (!ret) - ret = linger_notify_finish_wait(lreq); + ret = linger_notify_finish_wait(lreq, + msecs_to_jiffies(2 * timeout * MSEC_PER_SEC)); else dout("lreq %p failed to initiate notify %d\n", lreq, ret); diff --git a/net/core/Makefile b/net/core/Makefile index 5857cec87b83..10edd66a8a37 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o -obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 94374d529ea4..ad01b1bea52e 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -531,8 +531,11 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) return ERR_PTR(-EPERM); nla_for_each_nested(nla, nla_stgs, rem) { - if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { + if (nla_len(nla) != sizeof(u32)) + return ERR_PTR(-EINVAL); nr_maps++; + } } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); diff --git a/net/core/filter.c b/net/core/filter.c index da71e6812ab5..419ce7c61bd6 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4064,12 +4064,6 @@ BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) if (unlikely(data_end > data_hard_end)) return -EINVAL; - /* ALL drivers MUST init xdp->frame_sz, chicken check below */ - if (unlikely(xdp->frame_sz > PAGE_SIZE)) { - WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz); - return -EINVAL; - } - if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5625ed30a06f..9d4507aa736b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2220,13 +2220,27 @@ out_err: return err; } -int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, - struct netlink_ext_ack *exterr) +int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, + struct netlink_ext_ack *exterr) { - return nla_parse_deprecated(tb, IFLA_MAX, head, len, ifla_policy, + const struct ifinfomsg *ifmp; + const struct nlattr *attrs; + size_t len; + + ifmp = nla_data(nla_peer); + attrs = nla_data(nla_peer) + sizeof(struct ifinfomsg); + len = nla_len(nla_peer) - sizeof(struct ifinfomsg); + + if (ifmp->ifi_index < 0) { + NL_SET_ERR_MSG_ATTR(exterr, nla_peer, + "ifindex can't be negative"); + return -EINVAL; + } + + return nla_parse_deprecated(tb, IFLA_MAX, attrs, len, ifla_policy, exterr); } -EXPORT_SYMBOL(rtnl_nla_parse_ifla); +EXPORT_SYMBOL(rtnl_nla_parse_ifinfomsg); struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { @@ -3451,6 +3465,9 @@ replay: if (ifm->ifi_index > 0) { link_specified = true; dev = __dev_get_by_index(net, ifm->ifi_index); + } else if (ifm->ifi_index < 0) { + NL_SET_ERR_MSG(extack, "ifindex can't be negative"); + return -EINVAL; } else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) { link_specified = true; dev = rtnl_dev_get(net, tb); @@ -5030,13 +5047,17 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { if (nla_len(attr) < sizeof(flags)) return -EINVAL; have_flags = true; flags = nla_get_u16(attr); - break; + } + + if (nla_type(attr) == IFLA_BRIDGE_MODE) { + if (nla_len(attr) < sizeof(u16)) + return -EINVAL; } } } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 65fb6f5b21b2..296e45b6c3c0 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1117,13 +1117,19 @@ static void sk_psock_strp_data_ready(struct sock *sk) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { + int ret; + static const struct strp_callbacks cb = { .rcv_msg = sk_psock_strp_read, .read_sock_done = sk_psock_strp_read_done, .parse_msg = sk_psock_strp_parse, }; - return strp_init(&psock->strp, sk, &cb); + ret = strp_init(&psock->strp, sk, &cb); + if (!ret) + sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + + return ret; } void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) @@ -1151,7 +1157,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ - if (psock->progs.stream_parser) + if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED)) strp_done(&psock->strp); } #else diff --git a/net/core/sock.c b/net/core/sock.c index 0c1baa5517f1..509773919d30 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -800,7 +800,7 @@ EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { lock_sock(sk); - sk->sk_priority = priority; + WRITE_ONCE(sk->sk_priority, priority); release_sock(sk); } EXPORT_SYMBOL(sock_set_priority); @@ -977,7 +977,7 @@ EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { - sk->sk_mark = val; + WRITE_ONCE(sk->sk_mark, val); sk_dst_reset(sk); } } @@ -996,7 +996,7 @@ static void sock_release_reserved_memory(struct sock *sk, int bytes) bytes = round_down(bytes, PAGE_SIZE); WARN_ON(bytes > sk->sk_reserved_mem); - sk->sk_reserved_mem -= bytes; + WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes); sk_mem_reclaim(sk); } @@ -1033,7 +1033,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes) } sk->sk_forward_alloc += pages << PAGE_SHIFT; - sk->sk_reserved_mem += pages << PAGE_SHIFT; + WRITE_ONCE(sk->sk_reserved_mem, + sk->sk_reserved_mem + (pages << PAGE_SHIFT)); return 0; } @@ -1202,7 +1203,7 @@ set_sndbuf: if ((val >= 0 && val <= 6) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) - sk->sk_priority = val; + WRITE_ONCE(sk->sk_priority, val); else ret = -EPERM; break; @@ -1425,7 +1426,8 @@ set_sndbuf: cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); - sk->sk_max_pacing_rate = ulval; + /* Pairs with READ_ONCE() from sk_getsockopt() */ + WRITE_ONCE(sk->sk_max_pacing_rate, ulval); sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval); break; } @@ -1520,7 +1522,9 @@ set_sndbuf: } if ((u8)val == SOCK_TXREHASH_DEFAULT) val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* Paired with READ_ONCE() in tcp_rtx_synack() */ + /* Paired with READ_ONCE() in tcp_rtx_synack() + * and sk_getsockopt(). + */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -1620,11 +1624,11 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_SNDBUF: - v.val = sk->sk_sndbuf; + v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: - v.val = sk->sk_rcvbuf; + v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: @@ -1666,7 +1670,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_PRIORITY: - v.val = sk->sk_priority; + v.val = READ_ONCE(sk->sk_priority); break; case SO_LINGER: @@ -1713,7 +1717,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_RCVLOWAT: - v.val = sk->sk_rcvlowat; + v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: @@ -1792,7 +1796,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, return security_socket_getpeersec_stream(sock, optval.user, optlen.user, len); case SO_MARK: - v.val = sk->sk_mark; + v.val = READ_ONCE(sk->sk_mark); break; case SO_RCVMARK: @@ -1811,7 +1815,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, if (!sock->ops->set_peek_off) return -EOPNOTSUPP; - v.val = sk->sk_peek_off; + v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); @@ -1841,7 +1845,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: - v.val = sk->sk_ll_usec; + v.val = READ_ONCE(sk->sk_ll_usec); break; case SO_PREFER_BUSY_POLL: v.val = READ_ONCE(sk->sk_prefer_busy_poll); @@ -1849,12 +1853,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #endif case SO_MAX_PACING_RATE: + /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); - v.ulval = sk->sk_max_pacing_rate; + v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ - v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U); + v.val = min_t(unsigned long, ~0U, + READ_ONCE(sk->sk_max_pacing_rate)); } break; @@ -1922,11 +1928,12 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_RESERVE_MEM: - v.val = sk->sk_reserved_mem; + v.val = READ_ONCE(sk->sk_reserved_mem); break; case SO_TXREHASH: - v.val = sk->sk_txrehash; + /* Paired with WRITE_ONCE() in sk_setsockopt() */ + v.val = READ_ONCE(sk->sk_txrehash); break; default: @@ -3092,7 +3099,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount) if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); - if (sk_under_memory_pressure(sk) && + if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } @@ -3112,7 +3119,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index d38267201892..96db7409baa1 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -117,7 +117,6 @@ static void sock_map_sk_acquire(struct sock *sk) __acquires(&sk->sk_lock.slock) { lock_sock(sk); - preempt_disable(); rcu_read_lock(); } @@ -125,7 +124,6 @@ static void sock_map_sk_release(struct sock *sk) __releases(&sk->sk_lock.slock) { rcu_read_unlock(); - preempt_enable(); release_sock(sk); } @@ -150,13 +148,13 @@ static void sock_map_del_link(struct sock *sk, list_for_each_entry_safe(link, tmp, &psock->link, list) { if (link->link_raw == link_raw) { struct bpf_map *map = link->map; - struct bpf_stab *stab = container_of(map, struct bpf_stab, - map); - if (psock->saved_data_ready && stab->progs.stream_parser) + struct sk_psock_progs *progs = sock_map_progs(map); + + if (psock->saved_data_ready && progs->stream_parser) strp_stop = true; - if (psock->saved_data_ready && stab->progs.stream_verdict) + if (psock->saved_data_ready && progs->stream_verdict) verdict_stop = true; - if (psock->saved_data_ready && stab->progs.skb_verdict) + if (psock->saved_data_ready && progs->skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index dc4fb699b56c..d2981e89d363 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -946,7 +946,7 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX, - tb[DCB_ATTR_BCN], dcbnl_pfc_up_nest, + tb[DCB_ATTR_BCN], dcbnl_bcn_nest, NULL); if (ret) return ret; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b780827f5e0a..bfececa9e244 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -130,7 +130,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16()); err = dccp_connect(sk); rt = NULL; @@ -430,7 +430,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16()); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index c0fd8f5f3b94..b51ce6f8ceba 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -237,8 +237,8 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass, - sk->sk_priority); + err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt, + np->tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } diff --git a/net/dccp/output.c b/net/dccp/output.c index b8a24734385e..fd2eb148d24d 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -187,7 +187,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; - dp->dccps_mss_cache = cur_mps; + WRITE_ONCE(dp->dccps_mss_cache, cur_mps); return cur_mps; } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a06b5641287a..c522c76a9f89 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -312,11 +312,15 @@ EXPORT_SYMBOL_GPL(dccp_disconnect); __poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait) { - __poll_t mask; struct sock *sk = sock->sk; + __poll_t mask; + u8 shutdown; + int state; sock_poll_wait(file, sock, wait); - if (sk->sk_state == DCCP_LISTEN) + + state = inet_sk_state_load(sk); + if (state == DCCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events @@ -325,20 +329,21 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, */ mask = 0; - if (sk->sk_err) + if (READ_ONCE(sk->sk_err)) mask = EPOLLERR; + shutdown = READ_ONCE(sk->sk_shutdown); - if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED) + if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected? */ - if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { + if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { if (atomic_read(&sk->sk_rmem_alloc) > 0) mask |= EPOLLIN | EPOLLRDNORM; - if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { + if (!(shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ @@ -356,7 +361,6 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, } return mask; } - EXPORT_SYMBOL_GPL(dccp_poll); int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) @@ -627,7 +631,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: - val = dp->dccps_mss_cache; + val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); @@ -736,7 +740,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) trace_dccp_probe(sk, len); - if (len > dp->dccps_mss_cache) + if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); @@ -769,6 +773,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out_discard; } + /* We need to check dccps_mss_cache after socket is locked. */ + if (len > dp->dccps_mss_cache) { + rc = -EMSGSIZE; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) diff --git a/net/devlink/Makefile b/net/devlink/Makefile new file mode 100644 index 000000000000..3a60959f71ee --- /dev/null +++ b/net/devlink/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y := leftover.o diff --git a/net/core/devlink.c b/net/devlink/leftover.c index 5a4a4b34ac15..63188d6a50fe 100644 --- a/net/core/devlink.c +++ b/net/devlink/leftover.c @@ -9727,6 +9727,7 @@ static void devlink_notify_unregister(struct devlink *devlink) struct devlink_param_item *param_item; struct devlink_trap_item *trap_item; struct devlink_port *devlink_port; + struct devlink_linecard *linecard; struct devlink_rate *rate_node; struct devlink_region *region; @@ -9753,6 +9754,8 @@ static void devlink_notify_unregister(struct devlink *devlink) list_for_each_entry_reverse(devlink_port, &devlink->port_list, list) devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + list_for_each_entry_reverse(linecard, &devlink->linecard_list, list) + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); devlink_notify(devlink, DEVLINK_CMD_DEL); } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ebb737ac9e89..04853c83c85c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -340,7 +340,7 @@ lookup_protocol: else inet->pmtudisc = IP_PMTUDISC_WANT; - inet->inet_id = 0; + atomic_set(&inet->inet_id, 0); sock_init_data(sock, sk); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 4d1af0cd7d99..cb5dbee9e018 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16()); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index b812eb36f0e3..f7426926a104 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -150,7 +150,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, } #endif - if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, READ_ONCE(sk->sk_mark))) goto errout; if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || @@ -799,7 +799,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.ifindex = sk->sk_bound_dev_if; entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; if (sk_fullsock(sk)) - entry.mark = sk->sk_mark; + entry.mark = READ_ONCE(sk->sk_mark); else if (sk->sk_state == TCP_NEW_SYN_RECV) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; else if (sk->sk_state == TCP_TIME_WAIT) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7b4ab545c06e..acfe58d2f1dd 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -182,9 +182,9 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, ip_options_build(skb, &opt->opt, daddr, rt); } - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); if (!skb->mark) - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); /* Send it out. */ return ip_local_out(net, skb->sk, skb); @@ -526,8 +526,8 @@ packet_routed: skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->priority = READ_ONCE(sk->sk_priority); + skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); rcu_read_unlock(); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index a7fd035b5b4f..63aa52becd88 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -591,7 +591,7 @@ void __ip_sock_set_tos(struct sock *sk, int val) } if (inet_sk(sk)->tos != val) { inet_sk(sk)->tos = val; - sk->sk_priority = rt_tos2priority(val); + WRITE_ONCE(sk->sk_priority, rt_tos2priority(val)); sk_dst_reset(sk); } } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 92c02c886fe7..586b1b3e35b8 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -224,7 +224,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) .un.frag.__unused = 0, .un.frag.mtu = htons(mtu), }; - icmph->checksum = ip_compute_csum(icmph, len); + icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0)); skb_reset_transport_header(skb); niph = skb_push(skb, sizeof(*niph)); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 8c2bd1d9ddce..615c1dcf3a28 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -287,12 +287,12 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) switch (skb->protocol) { case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); break; case htons(ETH_P_IPV6): - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); break; default: goto tx_err; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index d8ef05347fd9..9cc287902454 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3221,13 +3221,9 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) &rtm_dump_nexthop_cb, &filter); if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; @@ -3367,25 +3363,19 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, dd->filter.res_bucket_nh_id != nhge->nh->id) continue; + dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); - if (err < 0) { - if (likely(skb->len)) - goto out; - goto out_err; - } + if (err) + return err; } dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1; - bucket_index = 0; + dd->ctx->bucket_index = 0; -out: - err = skb->len; -out_err: - dd->ctx->bucket_index = bucket_index; - return err; + return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, @@ -3434,13 +3424,9 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 86197634dcf5..639aa5abda9d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -346,7 +346,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error; skb_reserve(skb, hlen); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_dst_set(skb, &rt->dst); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cd1fa9f70f1a..51bd9a50a1d1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -518,7 +518,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct inet_sock *inet = inet_sk(sk); oif = sk->sk_bound_dev_if; - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; @@ -552,7 +552,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; - flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk) & IPTOS_RT_MASK, ip_sock_rt_scope(sk), inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9a8d59e9303a..f9b8a4a1d2ed 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -312,7 +312,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr)); } - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16()); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -931,9 +931,9 @@ static void tcp_v4_send_ack(const struct sock *sk, ctl_sk = this_cpu_read(ipv4_tcp_sk); sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_mark : sk->sk_mark; + inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_priority : sk->sk_priority; + inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -1539,7 +1539,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16()); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 82f4575f9cd9..99ac5efe244d 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -40,7 +40,7 @@ struct tcp_fastopen_metrics { struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; - possible_net_t tcpm_net; + struct net *tcpm_net; struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; @@ -51,34 +51,38 @@ struct tcp_metrics_block { struct rcu_head rcu_head; }; -static inline struct net *tm_net(struct tcp_metrics_block *tm) +static inline struct net *tm_net(const struct tcp_metrics_block *tm) { - return read_pnet(&tm->tcpm_net); + /* Paired with the WRITE_ONCE() in tcpm_new() */ + return READ_ONCE(tm->tcpm_net); } static bool tcp_metric_locked(struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_lock & (1 << idx); + /* Paired with WRITE_ONCE() in tcpm_suck_dst() */ + return READ_ONCE(tm->tcpm_lock) & (1 << idx); } -static u32 tcp_metric_get(struct tcp_metrics_block *tm, +static u32 tcp_metric_get(const struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_vals[idx]; + /* Paired with WRITE_ONCE() in tcp_metric_set() */ + return READ_ONCE(tm->tcpm_vals[idx]); } static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) { - tm->tcpm_vals[idx] = val; + /* Paired with READ_ONCE() in tcp_metric_get() */ + WRITE_ONCE(tm->tcpm_vals[idx], val); } static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { - return inetpeer_addr_cmp(a, b) == 0; + return (a->family == b->family) && !inetpeer_addr_cmp(a, b); } struct tcpm_hash_bucket { @@ -89,6 +93,7 @@ static struct tcpm_hash_bucket *tcp_metrics_hash __read_mostly; static unsigned int tcp_metrics_hash_log __read_mostly; static DEFINE_SPINLOCK(tcp_metrics_lock); +static DEFINE_SEQLOCK(fastopen_seqlock); static void tcpm_suck_dst(struct tcp_metrics_block *tm, const struct dst_entry *dst, @@ -97,7 +102,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, u32 msval; u32 val; - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); val = 0; if (dst_metric_locked(dst, RTAX_RTT)) @@ -110,30 +115,42 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, val |= 1 << TCP_METRIC_CWND; if (dst_metric_locked(dst, RTAX_REORDERING)) val |= 1 << TCP_METRIC_REORDERING; - tm->tcpm_lock = val; + /* Paired with READ_ONCE() in tcp_metric_locked() */ + WRITE_ONCE(tm->tcpm_lock, val); msval = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + tcp_metric_set(tm, TCP_METRIC_RTT, msval * USEC_PER_MSEC); msval = dst_metric_raw(dst, RTAX_RTTVAR); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; - tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); - tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); - tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, msval * USEC_PER_MSEC); + tcp_metric_set(tm, TCP_METRIC_SSTHRESH, + dst_metric_raw(dst, RTAX_SSTHRESH)); + tcp_metric_set(tm, TCP_METRIC_CWND, + dst_metric_raw(dst, RTAX_CWND)); + tcp_metric_set(tm, TCP_METRIC_REORDERING, + dst_metric_raw(dst, RTAX_REORDERING)); if (fastopen_clear) { + write_seqlock(&fastopen_seqlock); tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; tm->tcpm_fastopen.try_exp = 0; tm->tcpm_fastopen.cookie.exp = false; tm->tcpm_fastopen.cookie.len = 0; + write_sequnlock(&fastopen_seqlock); } } #define TCP_METRICS_TIMEOUT (60 * 60 * HZ) -static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) +static void tcpm_check_stamp(struct tcp_metrics_block *tm, + const struct dst_entry *dst) { - if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) + unsigned long limit; + + if (!tm) + return; + limit = READ_ONCE(tm->tcpm_stamp) + TCP_METRICS_TIMEOUT; + if (unlikely(time_after(jiffies, limit))) tcpm_suck_dst(tm, dst, false); } @@ -174,20 +191,23 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, oldest = deref_locked(tcp_metrics_hash[hash].chain); for (tm = deref_locked(oldest->tcpm_next); tm; tm = deref_locked(tm->tcpm_next)) { - if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp)) + if (time_before(READ_ONCE(tm->tcpm_stamp), + READ_ONCE(oldest->tcpm_stamp))) oldest = tm; } tm = oldest; } else { - tm = kmalloc(sizeof(*tm), GFP_ATOMIC); + tm = kzalloc(sizeof(*tm), GFP_ATOMIC); if (!tm) goto out_unlock; } - write_pnet(&tm->tcpm_net, net); + /* Paired with the READ_ONCE() in tm_net() */ + WRITE_ONCE(tm->tcpm_net, net); + tm->tcpm_saddr = *saddr; tm->tcpm_daddr = *daddr; - tcpm_suck_dst(tm, dst, true); + tcpm_suck_dst(tm, dst, reclaim); if (likely(!reclaim)) { tm->tcpm_next = tcp_metrics_hash[hash].chain; @@ -434,7 +454,7 @@ void tcp_update_metrics(struct sock *sk) tp->reordering); } } - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); out_unlock: rcu_read_unlock(); } @@ -539,8 +559,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) return ret; } -static DEFINE_SEQLOCK(fastopen_seqlock); - void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { @@ -647,7 +665,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, } if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE, - jiffies - tm->tcpm_stamp, + jiffies - READ_ONCE(tm->tcpm_stamp), TCP_METRICS_ATTR_PAD) < 0) goto nla_put_failure; @@ -658,7 +676,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, if (!nest) goto nla_put_failure; for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { - u32 val = tm->tcpm_vals[i]; + u32 val = tcp_metric_get(tm, i); if (!val) continue; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0b5d0a2867a8..cf354c29ec12 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -586,7 +586,9 @@ out_reset_timer: tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; - icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX); + icsk->icsk_rto = clamp(__tcp_set_rto(tp), + tcp_rto_min(sk), + TCP_RTO_MAX); } else { /* Use normal (exponential) backoff */ icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 151337d7f67b..cb71463bbbab 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -570,12 +570,12 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) vti6_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); break; case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); break; default: goto tx_err; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index facdc78a43e5..27fb5479988a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1073,7 +1073,7 @@ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ - skb_push(skb, -skb_network_offset(pkt)); + __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 3a553494ff16..a4d43eb45a9d 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS || + return opt->nd_opt_type == ND_OPT_PREFIX_INFO || + opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64 || diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 4651aaf70db4..4d5a27dd9a4b 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -120,7 +120,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init_sk(&ipc6, np); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); fl6.flowi6_oif = oif; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 33852fc38ad9..df3abd9e5237 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -612,7 +612,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; @@ -772,12 +772,12 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = fl6.flowi6_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0b060cb8681f..960ab43a49c4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2952,7 +2952,8 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); - ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid); + ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), + sk->sk_uid); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || @@ -3173,8 +3174,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { - ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark, - sk->sk_uid); + ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + READ_ONCE(sk->sk_mark), sk->sk_uid); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d9253aa764fa..4bdd356bb5c4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -567,8 +567,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, - tclass, sk->sk_priority); + err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark), + opt, tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -943,7 +943,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 if (sk->sk_state == TCP_TIME_WAIT) mark = inet_twsk(sk)->tw_mark; else - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); skb_set_delivery_time(buff, tcp_transmit_time(sk), true); } if (txhash) { @@ -1132,7 +1132,8 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), - ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, + ipv6_get_dsfield(ipv6_hdr(skb)), 0, + READ_ONCE(sk->sk_priority), READ_ONCE(tcp_rsk(req)->txhash)); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 04f1d696503c..27348172b25b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -622,7 +622,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == NDISC_REDIRECT) { if (tunnel) { ip6_redirect(skb, sock_net(sk), inet6_iif(skb), - sk->sk_mark, sk->sk_uid); + READ_ONCE(sk->sk_mark), sk->sk_uid); } else { ip6_sk_redirect(skb, sk); } @@ -1350,7 +1350,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init(&ipc6); ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); /* destination address check */ if (sin6) { diff --git a/net/key/af_key.c b/net/key/af_key.c index 8c21de50eadf..8a8f2429d5d9 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1848,9 +1848,9 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; - if ((xfilter->sadb_x_filter_splen >= + if ((xfilter->sadb_x_filter_splen > (sizeof(xfrm_address_t) << 3)) || - (xfilter->sadb_x_filter_dplen >= + (xfilter->sadb_x_filter_dplen > (sizeof(xfrm_address_t) << 3))) { mutex_unlock(&pfk->dump_lock); return -EINVAL; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 5137ea1861ce..bce4132b0a5c 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -519,7 +519,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* Get and verify the address */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0f81492da0b4..55dc0610e863 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1102,7 +1102,8 @@ static inline bool ieee80211_rx_reorder_ready(struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *tail = skb_peek_tail(frames); struct ieee80211_rx_status *status; - if (tid_agg_rx->reorder_buf_filtered & BIT_ULL(index)) + if (tid_agg_rx->reorder_buf_filtered && + tid_agg_rx->reorder_buf_filtered & BIT_ULL(index)) return true; if (!tail) @@ -1143,7 +1144,8 @@ static void ieee80211_release_reorder_frame(struct ieee80211_sub_if_data *sdata, } no_frame: - tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); + if (tid_agg_rx->reorder_buf_filtered) + tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); tid_agg_rx->head_seq_num = ieee80211_sn_inc(tid_agg_rx->head_seq_num); } @@ -4162,6 +4164,7 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, u16 ssn, u64 filtered, u16 received_mpdus) { + struct ieee80211_local *local; struct sta_info *sta; struct tid_ampdu_rx *tid_agg_rx; struct sk_buff_head frames; @@ -4179,6 +4182,11 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, sta = container_of(pubsta, struct sta_info, sta); + local = sta->sdata->local; + WARN_ONCE(local->hw.max_rx_aggregation_subframes > 64, + "RX BA marker can't support max_rx_aggregation_subframes %u > 64\n", + local->hw.max_rx_aggregation_subframes); + if (!ieee80211_rx_data_set_sta(&rx, sta, -1)) return; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f6f2e6417dcb..61fefa1a82db 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2367,7 +2367,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if (flags & MPTCP_CF_FASTCLOSE) { + if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_disconnect() path, * to generate the egress reset */ @@ -3370,7 +3370,7 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); - if (unlikely(&msk->cb_flags)) { + if (unlikely(msk->cb_flags)) { /* be sure to set the current sk state before tacking actions * depending on sk_state, that is processing MPTCP_ERROR_REPORT */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index fc00dd587a29..d77b25636125 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -312,7 +312,6 @@ struct mptcp_sock { u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; - struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 696ba398d699..937bd4c55615 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -102,7 +102,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in break; case SO_MARK: if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) { - ssk->sk_mark = sk->sk_mark; + WRITE_ONCE(ssk->sk_mark, sk->sk_mark); sk_dst_reset(ssk); } break; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 047e46dd028d..52a747a80e88 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1724,16 +1724,31 @@ static void subflow_state_change(struct sock *sk) void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) { struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - struct sock *sk; + struct request_sock *req, *head, *tail; + struct mptcp_subflow_context *subflow; + struct sock *sk, *ssk; - /* build a list of all unaccepted mptcp sockets */ + /* Due to lock dependencies no relevant lock can be acquired under rskq_lock. + * Splice the req list, so that accept() can not reach the pending ssk after + * the listener socket is released below. + */ spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; + head = queue->rskq_accept_head; + tail = queue->rskq_accept_tail; + queue->rskq_accept_head = NULL; + queue->rskq_accept_tail = NULL; + spin_unlock_bh(&queue->rskq_lock); + + if (!head) + return; + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (req = head; req; req = req->dl_next) { + ssk = req->sk; if (!sk_is_mptcp(ssk)) continue; @@ -1741,32 +1756,10 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s if (!subflow || !subflow->conn) continue; - /* skip if already in list */ sk = subflow->conn; - msk = mptcp_sk(sk); - if (msk->dl_next || msk == head) - continue; - sock_hold(sk); - msk->dl_next = head; - head = msk; - } - spin_unlock_bh(&queue->rskq_lock); - if (!head) - return; - - /* can't acquire the msk socket lock under the subflow one, - * or will cause ABBA deadlock - */ - release_sock(listener_ssk); - - for (msk = head; msk; msk = next) { - sk = (struct sock *)msk; lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->dl_next = NULL; - __mptcp_unaccepted_force_close(sk); release_sock(sk); @@ -1790,6 +1783,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s /* we are still under the listener msk socket lock */ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); + + /* restore the listener queue, to let the TCP code clean it up */ + spin_lock_bh(&queue->rskq_lock); + WARN_ON_ONCE(queue->rskq_accept_head); + queue->rskq_accept_head = head; + queue->rskq_accept_tail = tail; + spin_unlock_bh(&queue->rskq_lock); } static int subflow_ulp_init(struct sock *sk) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 03af6a2ffd56..17a1b731a76b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1798,6 +1798,7 @@ static int proc_do_sync_threshold(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { + struct netns_ipvs *ipvs = table->extra2; int *valp = table->data; int val[2]; int rc; @@ -1807,6 +1808,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write, .mode = table->mode, }; + mutex_lock(&ipvs->sync_mutex); memcpy(val, valp, sizeof(val)); rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write) { @@ -1816,6 +1818,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write, else memcpy(valp, val, sizeof(val)); } + mutex_unlock(&ipvs->sync_mutex); return rc; } @@ -4080,6 +4083,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD; ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD; tbl[idx].data = &ipvs->sysctl_sync_threshold; + tbl[idx].extra2 = ipvs; tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold); ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD; tbl[idx++].data = &ipvs->sysctl_sync_refresh_period; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 895e0ca54299..7247af51bdfc 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -49,8 +49,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, - [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, - [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, + [SCTP_CONNTRACK_SHUTDOWN_SENT] = 3 SECS, + [SCTP_CONNTRACK_SHUTDOWN_RECD] = 3 SECS, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, }; @@ -105,7 +105,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW}, +/* init */ {sCL, sCL, sCW, sCE, sES, sCL, sCL, sSA, sCW}, /* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL}, /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL}, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index dd57a9ebe113..3c5cac9bd9b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -255,8 +255,10 @@ int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) if (chain->bound) return -EBUSY; + if (!nft_use_inc(&chain->use)) + return -EMFILE; + chain->bound = true; - chain->use++; nft_chain_trans_bind(ctx, chain); return 0; @@ -439,7 +441,7 @@ static int nft_delchain(struct nft_ctx *ctx) if (IS_ERR(trans)) return PTR_ERR(trans); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nft_deactivate_next(ctx->net, ctx->chain); return 0; @@ -478,7 +480,7 @@ nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) /* You cannot delete the same rule twice */ if (nft_is_active_next(ctx->net, rule)) { nft_deactivate_next(ctx->net, rule); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); return 0; } return -ENOENT; @@ -645,7 +647,7 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) nft_map_deactivate(ctx, set); nft_deactivate_next(ctx->net, set); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -677,7 +679,7 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; nft_deactivate_next(ctx->net, obj); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -712,7 +714,7 @@ static int nft_delflowtable(struct nft_ctx *ctx, return err; nft_deactivate_next(ctx->net, flowtable); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -2358,9 +2360,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, unsigned int data_size; int err; - if (table->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_CHAIN_HOOK]) { struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook; @@ -2457,6 +2456,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (err < 0) goto err_destroy_chain; + if (!nft_use_inc(&table->use)) { + err = -EMFILE; + goto err_use; + } + trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -2473,10 +2477,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err_unregister_hook; } - table->use++; - return 0; + err_unregister_hook: + nft_use_dec_restore(&table->use); +err_use: nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -3663,9 +3668,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return -EINVAL; handle = nf_tables_alloc_handle(table); - if (chain->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_RULE_POSITION]) { pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); old_rule = __nft_rule_lookup(chain, pos_handle); @@ -3759,6 +3761,11 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } + if (!nft_use_inc(&chain->use)) { + err = -EMFILE; + goto err_release_rule; + } + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { err = nft_delrule(&ctx, old_rule); if (err < 0) @@ -3790,7 +3797,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } kvfree(expr_info); - chain->use++; if (flow) nft_trans_flow_rule(trans) = flow; @@ -3801,6 +3807,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return 0; err_destroy_flow_rule: + nft_use_dec_restore(&chain->use); if (flow) nft_flow_rule_destroy(flow); err_release_rule: @@ -4818,9 +4825,15 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, alloc_size = sizeof(*set) + size + udlen; if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; + + if (!nft_use_inc(&table->use)) + return -EMFILE; + set = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT); - if (!set) - return -ENOMEM; + if (!set) { + err = -ENOMEM; + goto err_alloc; + } name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL_ACCOUNT); if (!name) { @@ -4878,7 +4891,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); - table->use++; + return 0; err_set_expr_alloc: @@ -4890,6 +4903,9 @@ err_set_init: kfree(set->name); err_set_name: kvfree(set); +err_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -5024,9 +5040,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *i; struct nft_set_iter iter; - if (set->use == UINT_MAX) - return -EOVERFLOW; - if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; @@ -5054,10 +5067,12 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, return iter.err; } bind: + if (!nft_use_inc(&set->use)) + return -EMFILE; + binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); nft_set_trans_bind(ctx, set); - set->use++; return 0; } @@ -5131,7 +5146,7 @@ void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) nft_clear(ctx->net, set); } - set->use++; + nft_use_inc_restore(&set->use); } EXPORT_SYMBOL_GPL(nf_tables_activate_set); @@ -5147,7 +5162,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, else list_del_rcu(&binding->list); - set->use--; + nft_use_dec(&set->use); break; case NFT_TRANS_PREPARE: if (nft_set_is_anonymous(set)) { @@ -5156,7 +5171,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_deactivate_next(ctx->net, set); } - set->use--; + nft_use_dec(&set->use); return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: @@ -5164,7 +5179,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); - set->use--; + nft_use_dec(&set->use); fallthrough; default: nf_tables_unbind_set(ctx, set, binding, @@ -5933,7 +5948,7 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); kfree(elem); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); @@ -6435,8 +6450,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); + obj = NULL; goto err_parse_key_end; } + + if (!nft_use_inc(&obj->use)) { + err = -EMFILE; + obj = NULL; + goto err_parse_key_end; + } + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); if (err < 0) goto err_parse_key_end; @@ -6505,10 +6528,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (flags) *nft_set_ext_flags(ext) = flags; - if (obj) { + if (obj) *nft_set_ext_obj(ext) = obj; - obj->use++; - } + if (ulen > 0) { if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) { err = -EINVAL; @@ -6573,12 +6595,13 @@ err_element_clash: kfree(trans); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); - if (obj) - obj->use--; err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); err_parse_key_end: + if (obj) + nft_use_dec_restore(&obj->use); + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); err_parse_key: nft_data_release(&elem.key.val, NFT_DATA_VALUE); @@ -6659,7 +6682,7 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use++; + nft_use_inc_restore(&chain->use); break; } } @@ -6674,7 +6697,7 @@ static void nft_setelem_data_activate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use++; + nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } static void nft_setelem_data_deactivate(const struct net *net, @@ -6686,7 +6709,7 @@ static void nft_setelem_data_deactivate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); } static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, @@ -6851,6 +6874,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, ret = __nft_set_catchall_flush(ctx, set, &elem); if (ret < 0) break; + nft_set_elem_change_active(ctx->net, set, ext); } return ret; @@ -7225,9 +7249,14 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + type = nft_obj_type_get(net, objtype); - if (IS_ERR(type)) - return PTR_ERR(type); + if (IS_ERR(type)) { + err = PTR_ERR(type); + goto err_type; + } obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { @@ -7261,7 +7290,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); - table->use++; + return 0; err_obj_ht: /* queued in transaction log */ @@ -7277,6 +7306,9 @@ err_strdup: kfree(obj); err_init: module_put(type->owner); +err_type: + nft_use_dec_restore(&table->use); + return err; } @@ -7667,7 +7699,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: - flowtable->use--; + nft_use_dec(&flowtable->use); fallthrough; default: return; @@ -8015,9 +8047,14 @@ static int nf_tables_newflowtable(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL_ACCOUNT); - if (!flowtable) - return -ENOMEM; + if (!flowtable) { + err = -ENOMEM; + goto flowtable_alloc; + } flowtable->table = table; flowtable->handle = nf_tables_alloc_handle(table); @@ -8072,7 +8109,6 @@ static int nf_tables_newflowtable(struct sk_buff *skb, goto err5; list_add_tail_rcu(&flowtable->list, &table->flowtables); - table->use++; return 0; err5: @@ -8089,6 +8125,9 @@ err2: kfree(flowtable->name); err1: kfree(flowtable); +flowtable_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -9374,7 +9413,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) */ if (nft_set_is_anonymous(nft_trans_set(trans)) && !list_empty(&nft_trans_set(trans)->bindings)) - trans->ctx.table->use--; + nft_use_dec(&trans->ctx.table->use); } nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); @@ -9593,7 +9632,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, @@ -9601,7 +9640,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELCHAIN: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, trans->ctx.chain); nft_trans_destroy(trans); break; @@ -9610,7 +9649,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.chain->use--; + nft_use_dec_restore(&trans->ctx.chain->use); list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), @@ -9619,7 +9658,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: - trans->ctx.chain->use++; + nft_use_inc_restore(&trans->ctx.chain->use); nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) @@ -9632,7 +9671,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; @@ -9640,7 +9679,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_set(trans)); if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_activate(&trans->ctx, nft_trans_set(trans)); @@ -9683,12 +9722,12 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_obj_del(nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; @@ -9697,7 +9736,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); @@ -9708,7 +9747,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); } nft_trans_destroy(trans); @@ -10161,8 +10200,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (desc->flags & NFT_DATA_DESC_SETELEM && chain->flags & NFT_CHAIN_BINDING) return -EINVAL; + if (!nft_use_inc(&chain->use)) + return -EMFILE; - chain->use++; data->verdict.chain = chain; break; } @@ -10180,7 +10220,7 @@ static void nft_verdict_uninit(const struct nft_data *data) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use--; + nft_use_dec(&chain->use); break; } } @@ -10349,11 +10389,11 @@ int __nft_release_basechain(struct nft_ctx *ctx) nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); nf_tables_rule_release(ctx, rule); } nft_chain_del(ctx->chain); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nf_tables_chain_destroy(ctx); return 0; @@ -10406,18 +10446,18 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); - chain->use--; + nft_use_dec(&chain->use); nf_tables_rule_release(&ctx, rule); } } list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { list_del(&flowtable->list); - table->use--; + nft_use_dec(&table->use); nf_tables_flowtable_destroy(flowtable); } list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); - table->use--; + nft_use_dec(&table->use); if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(&ctx, set); @@ -10425,13 +10465,13 @@ static void __nft_release_table(struct net *net, struct nft_table *table) } list_for_each_entry_safe(obj, ne, &table->objects, list) { nft_obj_del(obj); - table->use--; + nft_use_dec(&table->use); nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { ctx.chain = chain; nft_chain_del(chain); - table->use--; + nft_use_dec(&table->use); nf_tables_chain_destroy(&ctx); } nf_tables_table_destroy(&ctx); @@ -10469,7 +10509,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, deleted = 0; mutex_lock(&nft_net->commit_mutex); if (!list_empty(&nf_tables_destroy_list)) - rcu_barrier(); + nf_tables_trans_destroy_flush_work(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index e65a83328b55..cf9a1ae87d9b 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -191,6 +191,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_OBJECT) + return -EOPNOTSUPP; + if (set->ops->update == NULL) return -EOPNOTSUPP; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index a25c88bc8b75..8a43f6f9c90b 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -404,8 +404,10 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, if (IS_ERR(flowtable)) return PTR_ERR(flowtable); + if (!nft_use_inc(&flowtable->use)) + return -EMFILE; + priv->flowtable = flowtable; - flowtable->use++; return nf_ct_netns_get(ctx->net, ctx->family); } @@ -424,7 +426,7 @@ static void nft_flow_offload_activate(const struct nft_ctx *ctx, { struct nft_flow_offload *priv = nft_expr_priv(expr); - priv->flowtable->use++; + nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 391c18e4b3eb..5f59dbab3e93 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -168,7 +168,7 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, nft_immediate_chain_deactivate(ctx, chain, phase); nft_chain_del(chain); chain->bound = false; - chain->table->use--; + nft_use_dec(&chain->table->use); break; } break; @@ -207,7 +207,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, * let the transaction records release this chain and its rules. */ if (chain->bound) { - chain->use--; + nft_use_dec(&chain->use); break; } @@ -215,9 +215,9 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, chain_ctx = *ctx; chain_ctx.chain = chain; - chain->use--; + nft_use_dec(&chain->use); list_for_each_entry_safe(rule, n, &chain->rules, list) { - chain->use--; + nft_use_dec(&chain->use); list_del(&rule->list); nf_tables_rule_destroy(&chain_ctx, rule); } diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 7f8e480b6be5..0017bd341872 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -41,8 +41,10 @@ static int nft_objref_init(const struct nft_ctx *ctx, if (IS_ERR(obj)) return -ENOENT; + if (!nft_use_inc(&obj->use)) + return -EMFILE; + nft_objref_priv(expr) = obj; - obj->use++; return 0; } @@ -71,7 +73,7 @@ static void nft_objref_deactivate(const struct nft_ctx *ctx, if (phase == NFT_TRANS_COMMIT) return; - obj->use--; + nft_use_dec(&obj->use); } static void nft_objref_activate(const struct nft_ctx *ctx, @@ -79,7 +81,7 @@ static void nft_objref_activate(const struct nft_ctx *ctx, { struct nft_object *obj = nft_objref_priv(expr); - obj->use++; + nft_use_inc_restore(&obj->use); } static struct nft_expr_type nft_objref_type; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index a81829c10fea..8c16681884b7 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -901,12 +901,14 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f) static int pipapo_insert(struct nft_pipapo_field *f, const uint8_t *k, int mask_bits) { - int rule = f->rules++, group, ret, bit_offset = 0; + int rule = f->rules, group, ret, bit_offset = 0; - ret = pipapo_resize(f, f->rules - 1, f->rules); + ret = pipapo_resize(f, f->rules, f->rules + 1); if (ret) return ret; + f->rules++; + for (group = 0; group < f->groups; group++) { int i, v; u8 mask; @@ -1051,7 +1053,9 @@ static int pipapo_expand(struct nft_pipapo_field *f, step++; if (step >= len) { if (!masks) { - pipapo_insert(f, base, 0); + err = pipapo_insert(f, base, 0); + if (err < 0) + return err; masks = 1; } goto out; @@ -1234,6 +1238,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else ret = pipapo_expand(f, start, end, f->groups * f->bb); + if (ret < 0) + return ret; + if (f->bsize > bsize_max) bsize_max = f->bsize; @@ -1665,6 +1672,17 @@ static void nft_pipapo_commit(const struct nft_set *set) priv->clone = new_clone; } +static bool nft_pipapo_transaction_mutex_held(const struct nft_set *set) +{ +#ifdef CONFIG_PROVE_LOCKING + const struct net *net = read_pnet(&set->net); + + return lockdep_is_held(&nft_pernet(net)->commit_mutex); +#else + return true; +#endif +} + static void nft_pipapo_abort(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); @@ -1673,7 +1691,7 @@ static void nft_pipapo_abort(const struct nft_set *set) if (!priv->dirty) return; - m = rcu_dereference(priv->match); + m = rcu_dereference_protected(priv->match, nft_pipapo_transaction_mutex_held(set)); new_clone = pipapo_clone(m); if (IS_ERR(new_clone)) diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 49a5348a6a14..777561b71fcb 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -107,7 +107,7 @@ static void nft_socket_eval(const struct nft_expr *expr, break; case NFT_SOCKET_MARK: if (sk_fullsock(sk)) { - *dest = sk->sk_mark; + *dest = READ_ONCE(sk->sk_mark); } else { regs->verdict.code = NFT_BREAK; return; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 7013f55f05d1..76e01f292aaf 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -77,7 +77,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); @@ -138,7 +138,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 5920fdca1287..3c7b24535409 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1806,7 +1806,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.port_no = OVSP_LOCAL; parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX] - ? nla_get_u32(a[OVS_DP_ATTR_IFINDEX]) : 0; + ? nla_get_s32(a[OVS_DP_ATTR_IFINDEX]) : 0; /* So far only local changes have been made, now need the lock. */ ovs_lock(); @@ -2026,7 +2026,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, [OVS_DP_ATTR_MASKS_CACHE_SIZE] = NLA_POLICY_RANGE(NLA_U32, 0, PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)), - [OVS_DP_ATTR_IFINDEX] = {.type = NLA_U32 }, + [OVS_DP_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), }; static const struct genl_small_ops dp_datapath_genl_ops[] = { @@ -2276,7 +2276,7 @@ restart: parms.port_no = port_no; parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX] - ? nla_get_u32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; + ? nla_get_s32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; vport = new_vport(&parms); err = PTR_ERR(vport); @@ -2513,7 +2513,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC }, [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, - [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, }; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6ab9d5b54338..451bd8bfafd2 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -404,18 +404,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; + /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; + WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - h.h2->tp_status = status; + WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: - h.h3->tp_status = status; + WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: @@ -432,17 +434,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame) smp_rmb(); + /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); - return h.h1->tp_status; + return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); - return h.h2->tp_status; + return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); - return h.h3->tp_status; + return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); @@ -2052,8 +2056,8 @@ retry: skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->priority = READ_ONCE(sk->sk_priority); + skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); @@ -2575,8 +2579,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->protocol = proto; skb->dev = dev; - skb->priority = po->sk.sk_priority; - skb->mark = po->sk.sk_mark; + skb->priority = READ_ONCE(po->sk.sk_priority); + skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -2978,7 +2982,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; sockcm_init(&sockc, sk); - sockc.mark = sk->sk_mark; + sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) @@ -3052,7 +3056,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 1212b057b129..6160ef7d646a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -265,7 +265,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; fnew->id = f->id; - fnew->res = f->res; fnew->ifindex = f->ifindex; fnew->tp = f->tp; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 9e43b929d4ca..306188bf2d1f 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -511,7 +511,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (fold) { f->id = fold->id; f->iif = fold->iif; - f->res = fold->res; f->handle = fold->handle; f->tp = fold->tp; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 1280736a7b92..ba93e2a6bdbb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -824,7 +824,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->ifindex = n->ifindex; new->fshift = n->fshift; - new->res = n->res; new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); @@ -1022,18 +1021,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } + /* At this point, we need to derive the new handle that will be used to + * uniquely map the identity of this table match entry. The + * identity of the entry that we need to construct is 32 bits made of: + * htid(12b):bucketid(8b):node/entryid(12b) + * + * At this point _we have the table(ht)_ in which we will insert this + * entry. We carry the table's id in variable "htid". + * Note that earlier code picked the ht selection either by a) the user + * providing the htid specified via TCA_U32_HASH attribute or b) when + * no such attribute is passed then the root ht, is default to at ID + * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0. + * If OTOH the user passed us the htid, they may also pass a bucketid of + * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is + * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be + * passed via the htid, so even if it was non-zero it will be ignored. + * + * We may also have a handle, if the user passed one. The handle also + * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b). + * Rule: the bucketid on the handle is ignored even if one was passed; + * rather the value on "htid" is always assumed to be the bucketid. + */ if (handle) { + /* Rule: The htid from handle and tableid from htid must match */ if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) { NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch"); return -EINVAL; } - handle = htid | TC_U32_NODE(handle); - err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle, - GFP_KERNEL); - if (err) - return err; - } else + /* Ok, so far we have a valid htid(12b):bucketid(8b) but we + * need to finalize the table entry identification with the last + * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for + * entries. Rule: nodeid of 0 is reserved only for tables(see + * earlier code which processes TC_U32_DIVISOR attribute). + * Rule: The nodeid can only be derived from the handle (and not + * htid). + * Rule: if the handle specified zero for the node id example + * 0x60000000, then pick a new nodeid from the pool of IDs + * this hash table has been allocating from. + * If OTOH it is specified (i.e for example the user passed a + * handle such as 0x60000123), then we use it generate our final + * handle which is used to uniquely identify the match entry. + */ + if (!TC_U32_NODE(handle)) { + handle = gen_new_kid(ht, htid); + } else { + handle = htid | TC_U32_NODE(handle); + err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, + handle, GFP_KERNEL); + if (err) + return err; + } + } else { + /* The user did not give us a handle; lets just generate one + * from the table's pool of nodeids. + */ handle = gen_new_kid(ht, htid); + } if (tb[TCA_U32_SEL] == NULL) { NL_SET_ERR_MSG_MOD(extack, "Selector not specified"); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 01d07e6a6811..e8f988e1c7e6 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1550,10 +1550,28 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, return 0; } +static bool req_create_or_replace(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_REPLACE); +} + +static bool req_create_exclusive(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_EXCL); +} + +static bool req_change(struct nlmsghdr *n) +{ + return (!(n->nlmsg_flags & NLM_F_CREATE) && + !(n->nlmsg_flags & NLM_F_REPLACE) && + !(n->nlmsg_flags & NLM_F_EXCL)); +} + /* * Create/change qdisc. */ - static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -1647,27 +1665,35 @@ replay: * * We know, that some child q is already * attached to this parent and have choice: - * either to change it or to create/graft new one. + * 1) change it or 2) create/graft new one. + * If the requested qdisc kind is different + * than the existing one, then we choose graft. + * If they are the same then this is "change" + * operation - just let it fallthrough.. * * 1. We are allowed to create/graft only - * if CREATE and REPLACE flags are set. + * if the request is explicitly stating + * "please create if it doesn't exist". * - * 2. If EXCL is set, requestor wanted to say, - * that qdisc tcm_handle is not expected + * 2. If the request is to exclusive create + * then the qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. + * This will happen when for example tc + * utility issues a "change" command. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. - * For now we select create/graft, if - * user gave KIND, which does not match existing. + * For now we select create/graft. */ - if ((n->nlmsg_flags & NLM_F_CREATE) && - (n->nlmsg_flags & NLM_F_REPLACE) && - ((n->nlmsg_flags & NLM_F_EXCL) || - (tca[TCA_KIND] && - nla_strcmp(tca[TCA_KIND], q->ops->id)))) - goto create_n_graft; + if (tca[TCA_KIND] && + nla_strcmp(tca[TCA_KIND], q->ops->id)) { + if (req_create_or_replace(n) || + req_create_exclusive(n)) + goto create_n_graft; + else if (req_change(n)) + goto create_n_graft2; + } } } } else { @@ -1701,6 +1727,7 @@ create_n_graft: NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; } +create_n_graft2: if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index aa9842158df0..d0e045116d4e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -773,12 +773,10 @@ static void dist_free(struct disttable *d) * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, - const struct nlattr *attr) +static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); - spinlock_t *root_lock; struct disttable *d; int i; @@ -793,13 +791,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, for (i = 0; i < n; i++) d->table[i] = data[i]; - root_lock = qdisc_root_sleeping_lock(sch); - - spin_lock_bh(root_lock); - swap(*tbl, d); - spin_unlock_bh(root_lock); - - dist_free(d); + *tbl = d; return 0; } @@ -956,6 +948,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; + struct disttable *delay_dist = NULL; + struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; @@ -966,6 +960,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (ret < 0) return ret; + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto table_free; + } + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; @@ -975,26 +981,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; + q->clg = old_clg; goto unlock; } } else { q->loss_model = CLG_RANDOM; } - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, &q->delay_dist, - tb[TCA_NETEM_DELAY_DIST]); - if (ret) - goto get_table_failure; - } - - if (tb[TCA_NETEM_SLOT_DIST]) { - ret = get_dist_table(sch, &q->slot_dist, - tb[TCA_NETEM_SLOT_DIST]); - if (ret) - goto get_table_failure; - } - + if (delay_dist) + swap(q->delay_dist, delay_dist); + if (slot_dist) + swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); @@ -1044,17 +1041,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, unlock: sch_tree_unlock(sch); - return ret; -get_table_failure: - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; - - goto unlock; +table_free: + dist_free(delay_dist); + dist_free(slot_dist); + return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index a274a9332f33..8d5eebb2dd1b 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -769,6 +769,11 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, }; +static struct netlink_range_validation_signed taprio_cycle_time_range = { + .min = 0, + .max = INT_MAX, +}; + static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) @@ -777,7 +782,8 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, - [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = + NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range), [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, @@ -913,6 +919,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, return -EINVAL; } + if (cycle < 0 || cycle > INT_MAX) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); + return -EINVAL; + } + new->cycle_time = cycle; } @@ -1110,7 +1121,7 @@ static void setup_txtime(struct taprio_sched *q, struct sched_gate_list *sched, ktime_t base) { struct sched_entry *entry; - u32 interval = 0; + u64 interval = 0; list_for_each_entry(entry, &sched->entries, list) { entry->next_txtime = ktime_add_ns(base, interval); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c806d272107a..a11b0d903514 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -98,7 +98,7 @@ struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) { - sctp_memory_pressure = 1; + WRITE_ONCE(sctp_memory_pressure, 1); } @@ -9472,7 +9472,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16()); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 02d1daae7739..84219c5121bc 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -379,8 +379,8 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; - WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(net->smc.sysctl_wmem)); - WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(net->smc.sysctl_rmem)); + WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); + WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); @@ -438,24 +438,9 @@ out: return rc; } -static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, - unsigned long mask) -{ - /* options we don't get control via setsockopt for */ - nsk->sk_type = osk->sk_type; - nsk->sk_sndbuf = osk->sk_sndbuf; - nsk->sk_rcvbuf = osk->sk_rcvbuf; - nsk->sk_sndtimeo = osk->sk_sndtimeo; - nsk->sk_rcvtimeo = osk->sk_rcvtimeo; - nsk->sk_mark = osk->sk_mark; - nsk->sk_priority = osk->sk_priority; - nsk->sk_rcvlowat = osk->sk_rcvlowat; - nsk->sk_bound_dev_if = osk->sk_bound_dev_if; - nsk->sk_err = osk->sk_err; - - nsk->sk_flags &= ~mask; - nsk->sk_flags |= osk->sk_flags & mask; -} +/* copy only relevant settings and flags of SOL_SOCKET level from smc to + * clc socket (since smc is not called for these options from net/core) + */ #define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \ (1UL << SOCK_KEEPOPEN) | \ @@ -472,9 +457,55 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, (1UL << SOCK_NOFCS) | \ (1UL << SOCK_FILTER_LOCKED) | \ (1UL << SOCK_TSTAMP_NEW)) -/* copy only relevant settings and flags of SOL_SOCKET level from smc to - * clc socket (since smc is not called for these options from net/core) - */ + +/* if set, use value set by setsockopt() - else use IPv4 or SMC sysctl value */ +static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + struct net *nnet = sock_net(nsk); + + nsk->sk_userlocks = osk->sk_userlocks; + if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) { + nsk->sk_sndbuf = osk->sk_sndbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_sndbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1])); + else + WRITE_ONCE(nsk->sk_sndbuf, + 2 * READ_ONCE(nnet->smc.sysctl_wmem)); + } + if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) { + nsk->sk_rcvbuf = osk->sk_rcvbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_rcvbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1])); + else + WRITE_ONCE(nsk->sk_rcvbuf, + 2 * READ_ONCE(nnet->smc.sysctl_rmem)); + } +} + +static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + /* options we don't get control via setsockopt for */ + nsk->sk_type = osk->sk_type; + nsk->sk_sndtimeo = osk->sk_sndtimeo; + nsk->sk_rcvtimeo = osk->sk_rcvtimeo; + nsk->sk_mark = READ_ONCE(osk->sk_mark); + nsk->sk_priority = osk->sk_priority; + nsk->sk_rcvlowat = osk->sk_rcvlowat; + nsk->sk_bound_dev_if = osk->sk_bound_dev_if; + nsk->sk_err = osk->sk_err; + + nsk->sk_flags &= ~mask; + nsk->sk_flags |= osk->sk_flags & mask; + + smc_adjust_sock_bufsizes(nsk, osk, mask); +} + static void smc_copy_sock_settings_to_clc(struct smc_sock *smc) { smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC); @@ -2466,8 +2497,6 @@ static void smc_tcp_listen_work(struct work_struct *work) sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); - new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; - new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work)) sock_put(&new_smc->sk); diff --git a/net/smc/smc.h b/net/smc/smc.h index 5ed765ea0c73..1d36720fc019 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -161,7 +161,7 @@ struct smc_connection { struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */ struct smc_buf_desc *rmb_desc; /* RMBE descriptor */ - int rmbe_size_short;/* compressed notation */ + int rmbe_size_comp; /* compressed notation */ int rmbe_update_limit; /* lower limit for consumer * cursor update diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index dfb9797f7bc6..9b8999e2afca 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -1002,7 +1002,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->hdr.typev1 = SMC_TYPE_D; clc->d0.gid = conn->lgr->smcd->local_gid; clc->d0.token = conn->rmb_desc->token; - clc->d0.dmbe_size = conn->rmbe_size_short; + clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { @@ -1045,7 +1045,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); break; } - clc->r0.rmbe_size = conn->rmbe_size_short; + clc->r0.rmbe_size = conn->rmbe_size_comp; clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ? cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) : cpu_to_be64((u64)sg_dma_address diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f82f43573a15..c676d92af7b7 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -852,8 +852,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */ - mutex_init(&lgr->sndbufs_lock); - mutex_init(&lgr->rmbs_lock); + init_rwsem(&lgr->sndbufs_lock); + init_rwsem(&lgr->rmbs_lock); rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); @@ -1095,7 +1095,7 @@ err_out: static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link_group *lgr) { - struct mutex *lock; /* lock buffer list */ + struct rw_semaphore *lock; /* lock buffer list */ int rc; if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) { @@ -1115,9 +1115,9 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, /* buf registration failed, reuse not possible */ lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; - mutex_lock(lock); + down_write(lock); list_del(&buf_desc->list); - mutex_unlock(lock); + up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); } else { @@ -1220,15 +1220,16 @@ static void smcr_buf_unmap_lgr(struct smc_link *lnk) int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) smcr_buf_unmap_link(buf_desc, true, lnk); - mutex_unlock(&lgr->rmbs_lock); - mutex_lock(&lgr->sndbufs_lock); + up_write(&lgr->rmbs_lock); + + down_write(&lgr->sndbufs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) smcr_buf_unmap_link(buf_desc, false, lnk); - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); } } @@ -1986,19 +1987,19 @@ int smc_uncompress_bufsize(u8 compressed) * buffer size; if not available, return NULL */ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, - struct mutex *lock, + struct rw_semaphore *lock, struct list_head *buf_list) { struct smc_buf_desc *buf_slot; - mutex_lock(lock); + down_read(lock); list_for_each_entry(buf_slot, buf_list, list) { if (cmpxchg(&buf_slot->used, 0, 1) == 0) { - mutex_unlock(lock); + up_read(lock); return buf_slot; } } - mutex_unlock(lock); + up_read(lock); return NULL; } @@ -2107,13 +2108,13 @@ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc) return 0; } -static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, +static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock, struct list_head *lst, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf; int rc = 0; - mutex_lock(lock); + down_write(lock); list_for_each_entry_safe(buf_desc, bf, lst, list) { if (!buf_desc->used) continue; @@ -2122,7 +2123,7 @@ static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, goto out; } out: - mutex_unlock(lock); + up_write(lock); return rc; } @@ -2155,37 +2156,37 @@ int smcr_buf_reg_lgr(struct smc_link *lnk) int i, rc = 0; /* reg all RMBs for a new link */ - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) { if (!buf_desc->used) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } } } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) return rc; /* reg all vzalloced sndbufs for a new link */ - mutex_lock(&lgr->sndbufs_lock); + down_write(&lgr->sndbufs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) { if (!buf_desc->used || !buf_desc->is_vm) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } } } - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } @@ -2304,31 +2305,30 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; - int bufsize, bufsize_short; + int bufsize, bufsize_comp; + struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - struct mutex *lock; /* lock buffer list */ - int sk_buf_size; if (is_rmb) /* use socket recv buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_rcvbuf; + bufsize = smc->sk.sk_rcvbuf / 2; else /* use socket send buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_sndbuf; + bufsize = smc->sk.sk_sndbuf / 2; - for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb); - bufsize_short >= 0; bufsize_short--) { + for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb); + bufsize_comp >= 0; bufsize_comp--) { if (is_rmb) { lock = &lgr->rmbs_lock; - buf_list = &lgr->rmbs[bufsize_short]; + buf_list = &lgr->rmbs[bufsize_comp]; } else { lock = &lgr->sndbufs_lock; - buf_list = &lgr->sndbufs[bufsize_short]; + buf_list = &lgr->sndbufs[bufsize_comp]; } - bufsize = smc_uncompress_bufsize(bufsize_short); + bufsize = smc_uncompress_bufsize(bufsize_comp); /* check for reusable slot in the link group */ - buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); + buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); @@ -2354,9 +2354,9 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; - mutex_lock(lock); + down_write(lock); list_add(&buf_desc->list, buf_list); - mutex_unlock(lock); + up_write(lock); break; /* found */ } @@ -2372,8 +2372,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (is_rmb) { conn->rmb_desc = buf_desc; - conn->rmbe_size_short = bufsize_short; - smc->sk.sk_rcvbuf = bufsize; + conn->rmbe_size_comp = bufsize_comp; + smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(buf_desc->len); @@ -2381,7 +2381,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; - smc->sk.sk_sndbuf = bufsize; + smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } return 0; @@ -2430,9 +2430,9 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); if (rc) { - mutex_lock(&smc->conn.lgr->sndbufs_lock); + down_write(&smc->conn.lgr->sndbufs_lock); list_del(&smc->conn.sndbuf_desc->list); - mutex_unlock(&smc->conn.lgr->sndbufs_lock); + up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 285f9bd8e232..6051d9227013 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -252,9 +252,9 @@ struct smc_link_group { unsigned short vlan_id; /* vlan id of link group */ struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */ - struct mutex sndbufs_lock; /* protects tx buffers */ + struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ - struct mutex rmbs_lock; /* protects rx buffers */ + struct rw_semaphore rmbs_lock; /* protects rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 760f8bbff822..fcb24a0ccf76 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -611,7 +611,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, prim_lnk_idx = link->link_idx; lnk_idx = link_new->link_idx; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); ext->num_rkeys = lgr->conns_num; if (!ext->num_rkeys) goto out; @@ -631,7 +631,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, } len += i * sizeof(ext->rt[0]); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return len; } @@ -892,7 +892,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -919,7 +919,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, break; } while (num_rkeys_send || num_rkeys_recv); - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } @@ -1002,14 +1002,14 @@ static void smc_llc_save_add_link_rkeys(struct smc_link *link, ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 + SMC_WR_TX_SIZE); max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < max; i++) { smc_rtoken_set(lgr, link->link_idx, link_new->link_idx, ext->rt[i].rmb_key, ext->rt[i].rmb_vaddr_new, ext->rt[i].rmb_key_new); } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); } static void smc_llc_save_add_link_info(struct smc_link *link, @@ -1316,7 +1316,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -1341,7 +1341,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); } while (num_rkeys_send || num_rkeys_recv); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index b6f79fabb9d3..0b2a957ca5f5 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -21,6 +21,10 @@ static int min_sndbuf = SMC_BUF_MIN_SIZE; static int min_rcvbuf = SMC_BUF_MIN_SIZE; +static int max_sndbuf = INT_MAX / 2; +static int max_rcvbuf = INT_MAX / 2; +static const int net_smc_wmem_init = (64 * 1024); +static const int net_smc_rmem_init = (64 * 1024); static struct ctl_table smc_table[] = { { @@ -53,6 +57,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_sndbuf, + .extra2 = &max_sndbuf, }, { .procname = "rmem", @@ -61,6 +66,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, + .extra2 = &max_rcvbuf, }, { } }; @@ -88,8 +94,8 @@ int __net_init smc_sysctl_net_init(struct net *net) net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS; net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME; - WRITE_ONCE(net->smc.sysctl_wmem, READ_ONCE(net->ipv4.sysctl_tcp_wmem[1])); - WRITE_ONCE(net->smc.sysctl_rmem, READ_ONCE(net->ipv4.sysctl_tcp_rmem[1])); + WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init); + WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); return 0; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index b098fde373ab..28c0771c4e8c 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -935,9 +935,6 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, if (!rep->rr_rdmabuf) goto out_free; - if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) - goto out_free_regbuf; - rep->rr_cid.ci_completion_id = atomic_inc_return(&r_xprt->rx_ep->re_completion_ids); @@ -956,8 +953,6 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, spin_unlock(&buf->rb_lock); return rep; -out_free_regbuf: - rpcrdma_regbuf_free(rep->rr_rdmabuf); out_free: kfree(rep); out: @@ -1363,6 +1358,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp) rep = rpcrdma_rep_create(r_xprt, temp); if (!rep) break; + if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) { + rpcrdma_rep_put(buf, rep); + break; + } rep->rr_cid.ci_queue_id = ep->re_attr.recv_cq->res.id; trace_xprtrdma_post_recv(rep); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index bf69c9d6d06c..184982788473 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); +static struct page *dummy_page; + static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) { @@ -313,36 +315,33 @@ static int tls_push_record(struct sock *sk, return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } -static int tls_device_record_close(struct sock *sk, - struct tls_context *ctx, - struct tls_record_info *record, - struct page_frag *pfrag, - unsigned char record_type) +static void tls_device_record_close(struct sock *sk, + struct tls_context *ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; - int ret; + struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) - * if we can't allocate memory now, steal some back from data + * if we can't allocate memory now use the dummy page */ - if (likely(skb_page_frag_refill(prot->tag_size, pfrag, - sk->sk_allocation))) { - ret = 0; - tls_append_frag(record, pfrag, prot->tag_size); - } else { - ret = prot->tag_size; - if (record->len <= prot->overhead_size) - return -ENOMEM; + if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && + !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { + dummy_tag_frag.page = dummy_page; + dummy_tag_frag.offset = 0; + pfrag = &dummy_tag_frag; } + tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); - return ret; } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, @@ -535,18 +534,8 @@ last_record: if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { - rc = tls_device_record_close(sk, tls_ctx, record, - pfrag, record_type); - if (rc) { - if (rc > 0) { - size += rc; - } else { - size = orig_size; - destroy_record(record); - ctx->open_record = NULL; - break; - } - } + tls_device_record_close(sk, tls_ctx, record, + pfrag, record_type); rc = tls_push_record(sk, tls_ctx, @@ -1466,14 +1455,26 @@ int __init tls_device_init(void) { int err; - destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); - if (!destruct_wq) + dummy_page = alloc_page(GFP_KERNEL); + if (!dummy_page) return -ENOMEM; + destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); + if (!destruct_wq) { + err = -ENOMEM; + goto err_free_dummy; + } + err = register_netdevice_notifier(&tls_dev_notifier); if (err) - destroy_workqueue(destruct_wq); + goto err_destroy_wq; + return 0; + +err_destroy_wq: + destroy_workqueue(destruct_wq); +err_free_dummy: + put_page(dummy_page); return err; } @@ -1482,4 +1483,5 @@ void __exit tls_device_cleanup(void) unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); + put_page(dummy_page); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5b19b6c53a2c..ca31847a6c70 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -779,7 +779,7 @@ static int unix_set_peek_off(struct sock *sk, int val) if (mutex_lock_interruptible(&u->iolock)) return -EINTR; - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); mutex_unlock(&u->iolock); return 0; @@ -2290,6 +2290,7 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, if (false) { alloc_skb: + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, @@ -2329,6 +2330,7 @@ alloc_skb: init_scm = false; } + spin_lock(&other->sk_receive_queue.lock); skb = skb_peek_tail(&other->sk_receive_queue); if (tail && tail == skb) { skb = newskb; @@ -2359,14 +2361,11 @@ alloc_skb: refcount_add(size, &sk->sk_wmem_alloc); if (newskb) { - err = unix_scm_to_skb(&scm, skb, false); - if (err) - goto err_state_unlock; - spin_lock(&other->sk_receive_queue.lock); + unix_scm_to_skb(&scm, skb, false); __skb_queue_tail(&other->sk_receive_queue, newskb); - spin_unlock(&other->sk_receive_queue.lock); } + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 087c0c442e23..c2363d44a1ff 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5378,8 +5378,11 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) if (!wiphy->mbssid_max_interfaces) return ERR_PTR(-EINVAL); - nla_for_each_nested(nl_elems, attrs, rem_elems) + nla_for_each_nested(nl_elems, attrs, rem_elems) { + if (num_elems >= 255) + return ERR_PTR(-EINVAL); num_elems++; + } elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); if (!elems) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index efe9283e9893..e5c1510c098f 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -643,7 +643,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp); if (ret) - return ret; + return 0; /* RNR IE may contain more than one NEIGHBOR_AP_INFO */ while (pos + sizeof(*ap_info) <= end) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 371d269d22fa..f7592638e61d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -504,7 +504,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->dev = dev; skb->priority = xs->sk.sk_priority; - skb->mark = xs->sk.sk_mark; + skb->mark = READ_ONCE(xs->sk.sk_mark); skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr; skb->destructor = xsk_destruct_skb; @@ -994,6 +994,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) err = xp_alloc_tx_descs(xs->pool, xs); if (err) { xp_put_pool(xs->pool); + xs->pool = NULL; sockfd_put(sock); goto out_unlock; } diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 8cbf45a8bcdc..655fe4ff8621 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -108,7 +108,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, - [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) }, + [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 94a3609548b1..d71dbe822096 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -528,8 +528,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) switch (skb->protocol) { case htons(ETH_P_IPV6): - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); if (!dst) { fl.u.ip6.flowi6_oif = dev->ifindex; fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; @@ -543,8 +543,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) } break; case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); if (!dst) { struct rtable *rt; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7b1b93584bdb..e65de78cb61b 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2174,7 +2174,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, match = xfrm_selector_match(&pol->selector, fl, family); if (match) { - if ((sk->sk_mark & pol->mark.m) != pol->mark.v || + if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v || pol->if_id != if_id) { pol = NULL; goto out; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 2d68a173b227..d042ca01211f 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -615,7 +615,7 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH]; - if (re) { + if (re && x->replay_esn && x->preplay_esn) { struct xfrm_replay_state_esn *replay_esn; replay_esn = nla_data(re); memcpy(x->replay_esn, replay_esn, @@ -1250,6 +1250,15 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) sizeof(*filter), GFP_KERNEL); if (filter == NULL) return -ENOMEM; + + /* see addr_match(), (prefix length >> 5) << 2 + * will be used to compare xfrm_address_t + */ + if (filter->splen > (sizeof(xfrm_address_t) << 3) || + filter->dplen > (sizeof(xfrm_address_t) << 3)) { + kfree(filter); + return -EINVAL; + } } if (attrs[XFRMA_PROTO]) @@ -2960,7 +2969,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, - [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) }, + [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, @@ -2980,6 +2989,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, + [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(xfrma_policy); |