diff options
Diffstat (limited to 'net')
117 files changed, 1187 insertions, 689 deletions
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index e8090f099eb8..ef0dec20c7d8 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -104,6 +104,9 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo); + /* free the TID stats immediately */ + cfg80211_sinfo_release_content(&sinfo); + dev_put(real_netdev); if (ret == -ENOENT) { /* Node is not associated anymore! It would be diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 508f4416dfc9..415d494cbe22 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -20,7 +20,6 @@ #include "main.h" #include <linux/atomic.h> -#include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/gfp.h> @@ -179,8 +178,10 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) parent_dev = __dev_get_by_index((struct net *)parent_net, dev_get_iflink(net_dev)); /* if we got a NULL parent_dev there is something broken.. */ - if (WARN(!parent_dev, "Cannot find parent device")) + if (!parent_dev) { + pr_err("Cannot find parent device\n"); return false; + } if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net)) return false; diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5db5a0a4c959..ffc83bebfe40 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -221,10 +221,14 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, netif_trans_update(soft_iface); vid = batadv_get_vid(skb, 0); + + skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: + if (!pskb_may_pull(skb, sizeof(*vhdr))) + goto dropped; vhdr = vlan_eth_hdr(skb); /* drop batman-in-batman packets to prevent loops */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index fa2644d276ef..e31e1b20f7f4 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -13,27 +13,13 @@ #include <net/sock.h> #include <net/tcp.h> -static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx, - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) -{ - u32 ret; - - preempt_disable(); - rcu_read_lock(); - bpf_cgroup_storage_set(storage); - ret = BPF_PROG_RUN(prog, ctx); - rcu_read_unlock(); - preempt_enable(); - - return ret; -} - -static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret, - u32 *time) +static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, + u32 *retval, u32 *time) { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { 0 }; enum bpf_cgroup_storage_type stype; u64 time_start, time_spent = 0; + int ret = 0; u32 i; for_each_cgroup_storage_type(stype) { @@ -48,25 +34,42 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret, if (!repeat) repeat = 1; + + rcu_read_lock(); + preempt_disable(); time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { - *ret = bpf_test_run_one(prog, ctx, storage); + bpf_cgroup_storage_set(storage); + *retval = BPF_PROG_RUN(prog, ctx); + + if (signal_pending(current)) { + ret = -EINTR; + break; + } + if (need_resched()) { - if (signal_pending(current)) - break; time_spent += ktime_get_ns() - time_start; + preempt_enable(); + rcu_read_unlock(); + cond_resched(); + + rcu_read_lock(); + preempt_disable(); time_start = ktime_get_ns(); } } time_spent += ktime_get_ns() - time_start; + preempt_enable(); + rcu_read_unlock(); + do_div(time_spent, repeat); *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storage[stype]); - return 0; + return ret; } static int bpf_test_finish(const union bpf_attr *kattr, diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3aeff0895669..ac92b2eb32b1 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1204,14 +1204,7 @@ static void br_multicast_query_received(struct net_bridge *br, return; br_multicast_update_query_timer(br, query, max_delay); - - /* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules, - * the arrival port for IGMP Queries where the source address - * is 0.0.0.0 should not be added to router port list. - */ - if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) || - saddr->proto == htons(ETH_P_IPV6)) - br_multicast_mark_router(br, port); + br_multicast_mark_router(br, port); } static void br_ip4_multicast_query(struct net_bridge *br, diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 3661cdd927f1..7e71b0df1fbc 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2058,6 +2058,8 @@ static int process_connect(struct ceph_connection *con) dout("process_connect on %p tag %d\n", con, (int)con->in_tag); if (con->auth) { + int len = le32_to_cpu(con->in_reply.authorizer_len); + /* * Any connection that defines ->get_authorizer() * should also define ->add_authorizer_challenge() and @@ -2067,8 +2069,7 @@ static int process_connect(struct ceph_connection *con) */ if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) { ret = con->ops->add_authorizer_challenge( - con, con->auth->authorizer_reply_buf, - le32_to_cpu(con->in_reply.authorizer_len)); + con, con->auth->authorizer_reply_buf, len); if (ret < 0) return ret; @@ -2078,10 +2079,12 @@ static int process_connect(struct ceph_connection *con) return 0; } - ret = con->ops->verify_authorizer_reply(con); - if (ret < 0) { - con->error_msg = "bad authorize reply"; - return ret; + if (len) { + ret = con->ops->verify_authorizer_reply(con); + if (ret < 0) { + con->error_msg = "bad authorize reply"; + return ret; + } } } diff --git a/net/compat.c b/net/compat.c index 959d1c51826d..3d348198004f 100644 --- a/net/compat.c +++ b/net/compat.c @@ -388,8 +388,12 @@ static int __compat_sys_setsockopt(int fd, int level, int optname, char __user *optval, unsigned int optlen) { int err; - struct socket *sock = sockfd_lookup(fd, &err); + struct socket *sock; + + if (optlen > INT_MAX) + return -EINVAL; + sock = sockfd_lookup(fd, &err); if (sock) { err = security_socket_setsockopt(sock, level, optname); if (err) { diff --git a/net/core/dev.c b/net/core/dev.c index 8e276e0192a1..5d03889502eb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8152,7 +8152,7 @@ static netdev_features_t netdev_sync_upper_features(struct net_device *lower, netdev_features_t feature; int feature_bit; - for_each_netdev_feature(&upper_disables, feature_bit) { + for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { @@ -8172,7 +8172,7 @@ static void netdev_sync_lower_features(struct net_device *upper, netdev_features_t feature; int feature_bit; - for_each_netdev_feature(&upper_disables, feature_bit) { + for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", diff --git a/net/core/filter.c b/net/core/filter.c index 7559d6835ecb..f7d0004fc160 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2789,8 +2789,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2831,8 +2830,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); @@ -2957,8 +2955,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2987,8 +2984,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); @@ -4112,10 +4108,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: + val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_SNDBUF: + val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); break; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 26d848484912..2415d9cb9b89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -356,6 +356,8 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) */ void *netdev_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __netdev_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(netdev_alloc_frag); @@ -369,6 +371,8 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) void *napi_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __napi_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(napi_alloc_frag); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index d6d5c20d7044..8c826603bf36 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -545,8 +545,7 @@ static void sk_psock_destroy_deferred(struct work_struct *gc) struct sk_psock *psock = container_of(gc, struct sk_psock, gc); /* No sk_callback_lock since already detached. */ - if (psock->parser.enabled) - strp_done(&psock->parser.strp); + strp_done(&psock->parser.strp); cancel_work_sync(&psock->work); diff --git a/net/core/sock.c b/net/core/sock.c index 6aa2e7e0b4fb..bc3512f230a3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2380,7 +2380,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) } if (sk_has_memory_pressure(sk)) { - int alloc; + u64 alloc; if (!sk_under_memory_pressure(sk)) return 1; diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 6eb837a47b5c..baaaeb2b2c42 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len); } @@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len); } diff --git a/net/dsa/master.c b/net/dsa/master.c index 71bb15f491c8..54f5551fb799 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -205,6 +205,8 @@ static void dsa_master_reset_mtu(struct net_device *dev) rtnl_unlock(); } +static struct lock_class_key dsa_master_addr_list_lock_key; + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { int ret; @@ -218,6 +220,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; + lockdep_set_class(&dev->addr_list_lock, + &dsa_master_addr_list_lock_key); ret = dsa_master_ethtool_setup(dev); if (ret) diff --git a/net/dsa/port.c b/net/dsa/port.c index 2d7e01b23572..2a2a878b5ce3 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -69,7 +69,6 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) { - u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING; struct dsa_switch *ds = dp->ds; int port = dp->index; int err; @@ -80,7 +79,8 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) return err; } - dsa_port_set_state_now(dp, stp_state); + if (!dp->bridge_dev) + dsa_port_set_state_now(dp, BR_STATE_FORWARDING); return 0; } @@ -90,7 +90,8 @@ void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy) struct dsa_switch *ds = dp->ds; int port = dp->index; - dsa_port_set_state_now(dp, BR_STATE_DISABLED); + if (!dp->bridge_dev) + dsa_port_set_state_now(dp, BR_STATE_DISABLED); if (ds->ops->port_disable) ds->ops->port_disable(ds, port, phy); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a3fcc1d01615..a1c9fe155057 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { struct net_device *master = dsa_slave_to_master(dev); - - if (change & IFF_ALLMULTI) - dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) - dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1); + if (dev->flags & IFF_UP) { + if (change & IFF_ALLMULTI) + dev_set_allmulti(master, + dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(master, + dev->flags & IFF_PROMISC ? 1 : -1); + } } static void dsa_slave_set_rx_mode(struct net_device *dev) @@ -639,7 +642,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -659,7 +662,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 5459f41fc26f..10e809b296ec 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -328,7 +328,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 1a4e9ff02762..5731670c560b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,6 +108,7 @@ static size_t inet_sk_attr_size(struct sock *sk, + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) @@ -287,12 +288,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } - if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) { + if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { u32 classid = 0; #ifdef CONFIG_SOCK_CGROUP_DATA classid = sock_cgroup_classid(&sk->sk_cgrp_data); #endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) goto errout; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d757b9642d0d..be778599bfed 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; + p->n_redirects = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first * calculation of tokens is at its maximum. */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 20a64fe6254b..6ae89f2b541b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1455,12 +1455,31 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if (t->erspan_ver == 1 || t->erspan_ver == 2) { + if (!t->collect_md) + o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) + goto nla_put_failure; + + if (t->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) + goto nla_put_failure; + } else { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) + goto nla_put_failure; + } + } if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || @@ -1490,19 +1509,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) - goto nla_put_failure; - - if (t->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) - goto nla_put_failure; - } else if (t->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) - goto nla_put_failure; - } - return 0; nla_put_failure: diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 2687db015b6f..fa2ba7c500e4 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -215,6 +215,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, /* Change outer to look like the reply to an incoming packet */ nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c index a0aa13bcabda..0a8a60c1bf9a 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c @@ -105,6 +105,8 @@ static void fast_csum(struct snmp_ctx *ctx, unsigned char offset) int snmp_version(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { + if (datalen != 1) + return -EINVAL; if (*(unsigned char *)data > 1) return -ENOTSUPP; return 1; @@ -114,8 +116,11 @@ int snmp_helper(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { struct snmp_ctx *ctx = (struct snmp_ctx *)context; - __be32 *pdata = (__be32 *)data; + __be32 *pdata; + if (datalen != 4) + return -EINVAL; + pdata = (__be32 *)data; if (*pdata == ctx->from) { pr_debug("%s: %pI4 to %pI4\n", __func__, (void *)&ctx->from, (void *)&ctx->to); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ce92f73cf104..5163b64f8fb3 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ - if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) + if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; + peer->n_redirects = 0; + } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ - if (peer->rate_tokens >= ip_rt_redirect_number) { + if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } @@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->rate_tokens; + ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && peer->rate_tokens == ip_rt_redirect_number) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2079145a3b7c..cf3c5095c10e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2528,6 +2528,7 @@ void tcp_write_queue_purge(struct sock *sk) sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; + inet_csk(sk)->icsk_backoff = 0; } int tcp_disconnect(struct sock *sk, int flags) @@ -2576,7 +2577,6 @@ int tcp_disconnect(struct sock *sk, int flags) tp->write_seq += tp->max_window + 2; if (tp->write_seq == 0) tp->write_seq = 1; - icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index efc6fef692ff..ec3cea9d6828 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -536,12 +536,15 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (sock_owned_by_user(sk)) break; + skb = tcp_rtx_queue_head(sk); + if (WARN_ON_ONCE(!skb)) + break; + icsk->icsk_backoff--; icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); - skb = tcp_rtx_queue_head(sk); tcp_mstamp_refresh(tp); delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 730bc44dbad9..ccc78f3a4b60 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2347,6 +2347,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache; list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); + tcp_init_tso_segs(skb, mss_now); goto repair; /* Skip network transmission */ } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5c3cd5d84a6f..372fdc5381a9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -562,10 +562,12 @@ static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info) for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, u32 info); + const struct ip_tunnel_encap_ops *encap; - if (!iptun_encaps[i]) + encap = rcu_dereference(iptun_encaps[i]); + if (!encap) continue; - handler = rcu_dereference(iptun_encaps[i]->err_handler); + handler = encap->err_handler; if (handler && !handler(skb, info)) return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 84c358804355..72ffd3d760ff 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1165,7 +1165,8 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa == ifp) continue; - if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr, + if (ifa->prefix_len != ifp->prefix_len || + !ipv6_prefix_equal(&ifa->addr, &ifp->addr, ifp->prefix_len)) continue; if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE)) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 5afe9f83374d..239d4a65ad6e 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -296,7 +296,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index b858bd5280bf..867474abe269 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -72,7 +72,7 @@ static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, static int gue6_err_proto_handler(int proto, struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info) + u8 type, u8 code, int offset, __be32 info) { const struct inet6_protocol *ipprot; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4416368dbd49..26f25b6e2833 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1719,6 +1719,27 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } +static void ip6erspan_set_version(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + if (!data) + return; + + parms->erspan_ver = 1; + if (data[IFLA_GRE_ERSPAN_VER]) + parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); + + if (parms->erspan_ver == 1) { + if (data[IFLA_GRE_ERSPAN_INDEX]) + parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); + } else if (parms->erspan_ver == 2) { + if (data[IFLA_GRE_ERSPAN_DIR]) + parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); + if (data[IFLA_GRE_ERSPAN_HWID]) + parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); + } +} + static void ip6gre_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { @@ -1767,20 +1788,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[], if (data[IFLA_GRE_COLLECT_METADATA]) parms->collect_md = true; - - parms->erspan_ver = 1; - if (data[IFLA_GRE_ERSPAN_VER]) - parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); - - if (parms->erspan_ver == 1) { - if (data[IFLA_GRE_ERSPAN_INDEX]) - parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); - } else if (parms->erspan_ver == 2) { - if (data[IFLA_GRE_ERSPAN_DIR]) - parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); - if (data[IFLA_GRE_ERSPAN_HWID]) - parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); - } } static int ip6gre_tap_init(struct net_device *dev) @@ -2098,12 +2105,31 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if (p->erspan_ver == 1 || p->erspan_ver == 2) { + if (!p->collect_md) + o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) + goto nla_put_failure; + + if (p->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) + goto nla_put_failure; + } else { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid)) + goto nla_put_failure; + } + } if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) || @@ -2112,8 +2138,7 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) || nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) || - nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark) || - nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) + nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, @@ -2131,19 +2156,6 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) - goto nla_put_failure; - - if (p->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) - goto nla_put_failure; - } else if (p->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid)) - goto nla_put_failure; - } - return 0; nla_put_failure: @@ -2198,6 +2210,7 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev, int err; ip6gre_netlink_parms(data, &nt->parms); + ip6erspan_set_version(data, &nt->parms); ign = net_generic(net, ip6gre_net_id); if (nt->parms.collect_md) { @@ -2243,6 +2256,7 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[], if (IS_ERR(t)) return PTR_ERR(t); + ip6erspan_set_version(data, &p); ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 8b075f0bc351..6d0b1f3e927b 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -23,9 +23,11 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; + int strict = (ipv6_addr_type(&iph->daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0, + strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 23022447eb49..7a41ee3c11b4 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -226,6 +226,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, } nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 964491cf3672..ce15dc4ccbfa 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1274,18 +1274,29 @@ static DEFINE_SPINLOCK(rt6_exception_lock); static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { + struct fib6_info *from; struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); + net->ipv6.rt6_stats->fib_rt_cache--; + + /* purge completely the exception to allow releasing the held resources: + * some [sk] cache may keep the dst around for unlimited time + */ + from = rcu_dereference_protected(rt6_ex->rt6i->from, + lockdep_is_held(&rt6_exception_lock)); + rcu_assign_pointer(rt6_ex->rt6i->from, NULL); + fib6_info_release(from); + dst_dev_put(&rt6_ex->rt6i->dst); + hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; - net->ipv6.rt6_stats->fib_rt_cache--; } /* Remove oldest rt6_ex in bucket and free the memory @@ -1599,15 +1610,15 @@ static int rt6_remove_exception_rt(struct rt6_info *rt) static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct rt6_exception_bucket *bucket; - struct fib6_info *from = rt->from; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; - - if (!from || - !(rt->rt6i_flags & RTF_CACHE)) - return; + struct fib6_info *from; rcu_read_lock(); + from = rcu_dereference(rt->from); + if (!from || !(rt->rt6i_flags & RTF_CACHE)) + goto unlock; + bucket = rcu_dereference(from->rt6i_exception_bucket); #ifdef CONFIG_IPV6_SUBTREES @@ -1626,6 +1637,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) if (rt6_ex) rt6_ex->stamp = jiffies; +unlock: rcu_read_unlock(); } @@ -2742,20 +2754,24 @@ static int ip6_route_check_nh_onlink(struct net *net, u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT; + struct fib6_info *from; struct rt6_info *grt; int err; err = 0; grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0); if (grt) { + rcu_read_lock(); + from = rcu_dereference(grt->from); if (!grt->dst.error && /* ignore match if it is the default route */ - grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) && + from && !ipv6_addr_any(&from->fib6_dst.addr) && (grt->rt6i_flags & flags || dev != grt->dst.dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } + rcu_read_unlock(); ip6_rt_put(grt); } @@ -4649,7 +4665,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; - rtm->rtm_table = table; + rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 8d0ba757a46c..9b2f272ca164 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -221,9 +221,7 @@ static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); genlmsg_end(msg, hdr); - genlmsg_reply(msg, info); - - return 0; + return genlmsg_reply(msg, info); nla_put_failure: rcu_read_unlock(); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 8181ee7e1e27..ee5403cbe655 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); } hdr->nexthdr = NEXTHDR_ROUTING; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1e03305c0549..e8a1dabef803 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info) } err = 0; - if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) + if (__in6_dev_get(skb->dev) && + !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 2596ffdeebea..b444483cdb2b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -288,8 +288,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int peeked, peeking, off; int err; int is_udplite = IS_UDPLITE(sk); + struct udp_mib __percpu *mib; bool checksum_valid = false; - struct udp_mib *mib; int is_udp4; if (flags & MSG_ERRQUEUE) @@ -420,17 +420,19 @@ EXPORT_SYMBOL(udpv6_encap_enable); */ static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info) + u8 type, u8 code, int offset, __be32 info) { int i; for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info); + u8 type, u8 code, int offset, __be32 info); + const struct ip6_tnl_encap_ops *encap; - if (!ip6tun_encaps[i]) + encap = rcu_dereference(ip6tun_encaps[i]); + if (!encap) continue; - handler = rcu_dereference(ip6tun_encaps[i]->err_handler); + handler = encap->err_handler; if (handler && !handler(skb, opt, type, code, offset, info)) return 0; } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f5b4febeaa25..bc65db782bfb 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -344,8 +344,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index 655c787f9d54..5651c29cb5bd 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -196,30 +196,22 @@ static int pfkey_release(struct socket *sock) return 0; } -static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, - gfp_t allocation, struct sock *sk) +static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation, + struct sock *sk) { int err = -ENOBUFS; - sock_hold(sk); - if (*skb2 == NULL) { - if (refcount_read(&skb->users) != 1) { - *skb2 = skb_clone(skb, allocation); - } else { - *skb2 = skb; - refcount_inc(&skb->users); - } - } - if (*skb2 != NULL) { - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { - skb_set_owner_r(*skb2, sk); - skb_queue_tail(&sk->sk_receive_queue, *skb2); - sk->sk_data_ready(sk); - *skb2 = NULL; - err = 0; - } + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return err; + + skb = skb_clone(skb, allocation); + + if (skb) { + skb_set_owner_r(skb, sk); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk); + err = 0; } - sock_put(sk); return err; } @@ -234,7 +226,6 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; - struct sk_buff *skb2 = NULL; int err = -ESRCH; /* XXX Do we need something like netlink_overrun? I think @@ -253,7 +244,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, * socket. */ if (pfk->promisc) - pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* the exact target will be processed later */ if (sk == one_sk) @@ -268,7 +259,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, continue; } - err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* Error is cleared after successful sending to at least one * registered KM */ @@ -278,9 +269,8 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, rcu_read_unlock(); if (one_sk != NULL) - err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk); + err = pfkey_broadcast_one(skb, allocation, one_sk); - kfree_skb(skb2); kfree_skb(skb); return err; } @@ -1783,7 +1773,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true); + err = xfrm_state_flush(net, proto, true, false); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 26f1d435696a..fed6becc5daf 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -83,8 +83,7 @@ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff -#define L2TP_HDR_SIZE_SEQ 10 -#define L2TP_HDR_SIZE_NOSEQ 6 +#define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 @@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ - if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) { + if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { l2tp_info(tunnel, L2TP_MSG_DATA, "%s: recv short packet (len=%d)\n", tunnel->name, skb->len); @@ -884,6 +883,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) goto error; } + if (tunnel->version == L2TP_HDR_VER_3 && + l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto error; + l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9c9afe94d389..b2ce90260c35 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel) } #endif +static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb, + unsigned char **ptr, unsigned char **optr) +{ + int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session); + + if (opt_len > 0) { + int off = *ptr - *optr; + + if (!pskb_may_pull(skb, off + opt_len)) + return -1; + + if (skb->data != *optr) { + *optr = skb->data; + *ptr = skb->data + off; + } + } + + return 0; +} + #define l2tp_printk(ptr, type, func, fmt, ...) \ do { \ if (((ptr)->debug) & (type)) \ diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 35f6f86d4dcc..d4c60523c549 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 237f1a4a0b0c..0ae6899edac0 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 69e831bc317b..54821fb1a960 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018 - 2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -366,6 +366,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); + ieee80211_agg_stop_txq(sta, tid); + spin_unlock_bh(&sta->lock); ht_dbg(sta->sdata, "Tx BA session stop requested for %pM tid %u\n", diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 2493c74c2d37..96496b2c1670 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -941,6 +941,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER; int err; + int prev_beacon_int; old = sdata_dereference(sdata->u.ap.beacon, sdata); if (old) @@ -963,6 +964,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->needed_rx_chains = sdata->local->rx_chains; + prev_beacon_int = sdata->vif.bss_conf.beacon_int; sdata->vif.bss_conf.beacon_int = params->beacon_interval; if (params->he_cap) @@ -974,8 +976,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (!err) ieee80211_vif_copy_chanctx_to_vlans(sdata, false); mutex_unlock(&local->mtx); - if (err) + if (err) { + sdata->vif.bss_conf.beacon_int = prev_beacon_int; return err; + } /* * Apply control port protocol, this allows us to diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 87a729926734..977dea436ee8 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -615,13 +615,13 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, * We need a bit of data queued to build aggregates properly, so * instruct the TCP stack to allow more than a single ms of data * to be queued in the stack. The value is a bit-shift of 1 - * second, so 8 is ~4ms of queued data. Only affects local TCP + * second, so 7 is ~8ms of queued data. Only affects local TCP * sockets. * This is the default, anyhow - drivers may need to override it * for local reasons (longer buffers, longer completion time, or * similar). */ - local->hw.tx_sk_pacing_shift = 8; + local->hw.tx_sk_pacing_shift = 7; /* set up some defaults */ local->hw.queues = 1; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index cad6592c52a1..2ec7011a4d07 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -70,6 +70,7 @@ enum mesh_deferred_task_flags { * @dst: mesh path destination mac address * @mpp: mesh proxy mac address * @rhash: rhashtable list pointer + * @walk_list: linked list containing all mesh_path objects. * @gate_list: list pointer for known gates list * @sdata: mesh subif * @next_hop: mesh neighbor to which frames for this destination will be @@ -105,6 +106,7 @@ struct mesh_path { u8 dst[ETH_ALEN]; u8 mpp[ETH_ALEN]; /* used for MPP or MAP */ struct rhash_head rhash; + struct hlist_node walk_list; struct hlist_node gate_list; struct ieee80211_sub_if_data *sdata; struct sta_info __rcu *next_hop; @@ -133,12 +135,16 @@ struct mesh_path { * gate's mpath may or may not be resolved and active. * @gates_lock: protects updates to known_gates * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr + * @walk_head: linked list containging all mesh_path objects + * @walk_lock: lock protecting walk_head * @entries: number of entries in the table */ struct mesh_table { struct hlist_head known_gates; spinlock_t gates_lock; struct rhashtable rhead; + struct hlist_head walk_head; + spinlock_t walk_lock; atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ }; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index a5125624a76d..88a6d5e18ccc 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -59,8 +59,10 @@ static struct mesh_table *mesh_table_alloc(void) return NULL; INIT_HLIST_HEAD(&newtbl->known_gates); + INIT_HLIST_HEAD(&newtbl->walk_head); atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); + spin_lock_init(&newtbl->walk_lock); return newtbl; } @@ -249,28 +251,15 @@ mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) static struct mesh_path * __mesh_path_lookup_by_idx(struct mesh_table *tbl, int idx) { - int i = 0, ret; - struct mesh_path *mpath = NULL; - struct rhashtable_iter iter; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return NULL; - - rhashtable_walk_start(&iter); + int i = 0; + struct mesh_path *mpath; - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) { if (i++ == idx) break; } - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); - if (IS_ERR(mpath) || !mpath) + if (!mpath) return NULL; if (mpath_expired(mpath)) { @@ -432,6 +421,7 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, return ERR_PTR(-ENOMEM); tbl = sdata->u.mesh.mesh_paths; + spin_lock_bh(&tbl->walk_lock); do { ret = rhashtable_lookup_insert_fast(&tbl->rhead, &new_mpath->rhash, @@ -441,20 +431,20 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, mpath = rhashtable_lookup_fast(&tbl->rhead, dst, mesh_rht_params); - + else if (!ret) + hlist_add_head(&new_mpath->walk_list, &tbl->walk_head); } while (unlikely(ret == -EEXIST && !mpath)); + spin_unlock_bh(&tbl->walk_lock); - if (ret && ret != -EEXIST) - return ERR_PTR(ret); - - /* At this point either new_mpath was added, or we found a - * matching entry already in the table; in the latter case - * free the unnecessary new entry. - */ - if (ret == -EEXIST) { + if (ret) { kfree(new_mpath); + + if (ret != -EEXIST) + return ERR_PTR(ret); + new_mpath = mpath; } + sdata->u.mesh.mesh_paths_generation++; return new_mpath; } @@ -480,9 +470,17 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, memcpy(new_mpath->mpp, mpp, ETH_ALEN); tbl = sdata->u.mesh.mpp_paths; + + spin_lock_bh(&tbl->walk_lock); ret = rhashtable_lookup_insert_fast(&tbl->rhead, &new_mpath->rhash, mesh_rht_params); + if (!ret) + hlist_add_head_rcu(&new_mpath->walk_list, &tbl->walk_head); + spin_unlock_bh(&tbl->walk_lock); + + if (ret) + kfree(new_mpath); sdata->u.mesh.mpp_paths_generation++; return ret; @@ -503,20 +501,9 @@ void mesh_plink_broken(struct sta_info *sta) struct mesh_table *tbl = sdata->u.mesh.mesh_paths; static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + rcu_read_lock(); + hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) { if (rcu_access_pointer(mpath->next_hop) == sta && mpath->flags & MESH_PATH_ACTIVE && !(mpath->flags & MESH_PATH_FIXED)) { @@ -530,8 +517,7 @@ void mesh_plink_broken(struct sta_info *sta) WLAN_REASON_MESH_PATH_DEST_UNREACHABLE, bcast); } } - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + rcu_read_unlock(); } static void mesh_path_free_rcu(struct mesh_table *tbl, @@ -551,6 +537,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, static void __mesh_path_del(struct mesh_table *tbl, struct mesh_path *mpath) { + hlist_del_rcu(&mpath->walk_list); rhashtable_remove_fast(&tbl->rhead, &mpath->rhash, mesh_rht_params); mesh_path_free_rcu(tbl, mpath); } @@ -571,27 +558,14 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) struct ieee80211_sub_if_data *sdata = sta->sdata; struct mesh_table *tbl = sdata->u.mesh.mesh_paths; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + struct hlist_node *n; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if (rcu_access_pointer(mpath->next_hop) == sta) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, @@ -599,51 +573,26 @@ static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, { struct mesh_table *tbl = sdata->u.mesh.mpp_paths; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + struct hlist_node *n; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if (ether_addr_equal(mpath->mpp, proxy)) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } static void table_flush_by_iface(struct mesh_table *tbl) { struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); + struct hlist_node *n; - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } /** @@ -675,15 +624,15 @@ static int table_path_del(struct mesh_table *tbl, { struct mesh_path *mpath; - rcu_read_lock(); + spin_lock_bh(&tbl->walk_lock); mpath = rhashtable_lookup_fast(&tbl->rhead, addr, mesh_rht_params); if (!mpath) { - rcu_read_unlock(); + spin_unlock_bh(&tbl->walk_lock); return -ENXIO; } __mesh_path_del(tbl, mpath); - rcu_read_unlock(); + spin_unlock_bh(&tbl->walk_lock); return 0; } @@ -854,28 +803,16 @@ void mesh_path_tbl_expire(struct ieee80211_sub_if_data *sdata, struct mesh_table *tbl) { struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; + struct hlist_node *n; - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_KERNEL); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if ((!(mpath->flags & MESH_PATH_RESOLVING)) && (!(mpath->flags & MESH_PATH_FIXED)) && time_after(jiffies, mpath->exp_time + MESH_PATH_EXPIRE)) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } void mesh_path_expire(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bb4d71efb6fb..c2a6da5d80da 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2644,6 +2644,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u16 ac, q, hdrlen; + int tailroom = 0; hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -2732,8 +2733,12 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (!ifmsh->mshcfg.dot11MeshForwarding) goto out; + if (sdata->crypto_tx_tailroom_needed_cnt) + tailroom = IEEE80211_ENCRYPT_TAILROOM; + fwd_skb = skb_copy_expand(skb, local->tx_headroom + - sdata->encrypt_headroom, 0, GFP_ATOMIC); + sdata->encrypt_headroom, + tailroom, GFP_ATOMIC); if (!fwd_skb) goto out; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f170d6c6629a..928f13a208b0 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1938,9 +1938,16 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, int head_need, bool may_encrypt) { struct ieee80211_local *local = sdata->local; + struct ieee80211_hdr *hdr; + bool enc_tailroom; int tail_need = 0; - if (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt) { + hdr = (struct ieee80211_hdr *) skb->data; + enc_tailroom = may_encrypt && + (sdata->crypto_tx_tailroom_needed_cnt || + ieee80211_is_mgmt(hdr->frame_control)); + + if (enc_tailroom) { tail_need = IEEE80211_ENCRYPT_TAILROOM; tail_need -= skb_tailroom(skb); tail_need = max_t(int, tail_need, 0); @@ -1948,8 +1955,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, if (skb_cloned(skb) && (!ieee80211_hw_check(&local->hw, SUPPORTS_CLONED_SKBS) || - !skb_clone_writable(skb, ETH_HLEN) || - (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt))) + !skb_clone_writable(skb, ETH_HLEN) || enc_tailroom)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) I802_DEBUG_INC(local->tx_expand_skb_head); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index d0eb38b890aa..ba950ae974fc 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -5,7 +5,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2146,6 +2146,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: break; + case NL80211_IFTYPE_ADHOC: + if (sdata->vif.bss_conf.ibss_joined) + WARN_ON(drv_join_ibss(local, sdata)); + /* fall through */ default: ieee80211_reconfig_stations(sdata); /* fall through */ diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index cad48d07c818..8401cefd9f65 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -29,6 +29,7 @@ config IP_VS_IPV6 bool "IPv6 support for IPVS" depends on IPV6 = y || IP_VS = IPV6 select IP6_NF_IPTABLES + select NF_DEFRAG_IPV6 ---help--- Add IPv6 support to IPVS. diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index fe9abf3cc10a..235205c93e14 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1536,14 +1536,12 @@ ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); - if (iph->fragoffs) { - /* Fragment that couldn't be mapped to a conn entry - * is missing module nf_defrag_ipv6 - */ - IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); + + /* Fragment couldn't be mapped to a conn entry */ + if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); - } + *verdict = NF_ACCEPT; return 0; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 7d6318664eb2..ac8d848d7624 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -43,6 +43,7 @@ #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/route.h> #include <net/sock.h> @@ -900,11 +901,17 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, #ifdef CONFIG_IP_VS_IPV6 if (udest->af == AF_INET6) { + int ret; + atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6)) return -EINVAL; + + ret = nf_defrag_ipv6_enable(svc->ipvs->net); + if (ret) + return ret; } else #endif { @@ -1228,6 +1235,10 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ret = -EINVAL; goto out_err; } + + ret = nf_defrag_ipv6_enable(ipvs->net); + if (ret) + goto out_err; } #endif diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 741b533148ba..db4d46332e86 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1007,6 +1007,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, } if (nf_ct_key_equal(h, tuple, zone, net)) { + /* Tuple is taken already, so caller will need to find + * a new source port to use. + * + * Only exception: + * If the *original tuples* are identical, then both + * conntracks refer to the same flow. + * This is a rare situation, it can occur e.g. when + * more than one UDP packet is sent from same socket + * in different threads. + * + * Let nf_ct_resolve_clash() deal with this later. + */ + if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) + continue; + NF_CT_STAT_INC_ATOMIC(net, found); rcu_read_unlock(); return 1; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fb07f6cfc719..4893f248dfdc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -116,6 +116,23 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_set_is_anonymous(set)) + return; + + list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + if (trans->msg_type == NFT_MSG_NEWSET && + nft_trans_set(trans) == set) { + nft_trans_set_bound(trans) = true; + break; + } + } +} + static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) @@ -211,18 +228,6 @@ static int nft_delchain(struct nft_ctx *ctx) return err; } -/* either expr ops provide both activate/deactivate, or neither */ -static bool nft_expr_check_ops(const struct nft_expr_ops *ops) -{ - if (!ops) - return true; - - if (WARN_ON_ONCE((!ops->activate ^ !ops->deactivate))) - return false; - - return true; -} - static void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { @@ -238,14 +243,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule) + struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr; expr = nft_expr_first(rule); while (expr != nft_expr_last(rule) && expr->ops) { if (expr->ops->deactivate) - expr->ops->deactivate(ctx, expr); + expr->ops->deactivate(ctx, expr, phase); expr = nft_expr_next(expr); } @@ -296,7 +302,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule) nft_trans_destroy(trans); return err; } - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE); return 0; } @@ -307,6 +313,9 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx) int err; list_for_each_entry(rule, &ctx->chain->rules, list) { + if (!nft_is_active_next(ctx->net, rule)) + continue; + err = nft_delrule(ctx, rule); if (err < 0) return err; @@ -1929,9 +1938,6 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, */ int nft_register_expr(struct nft_expr_type *type) { - if (!nft_expr_check_ops(type->ops)) - return -EINVAL; - nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); @@ -2079,10 +2085,6 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, err = PTR_ERR(ops); goto err1; } - if (!nft_expr_check_ops(ops)) { - err = -EINVAL; - goto err1; - } } else ops = type->ops; @@ -2511,7 +2513,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -3708,39 +3710,30 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, bind: binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); + nft_set_trans_bind(ctx, set); + return 0; } EXPORT_SYMBOL_GPL(nf_tables_bind_set); -void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) -{ - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) - list_add_tail_rcu(&set->list, &ctx->table->sets); - - list_add_tail_rcu(&binding->list, &set->bindings); -} -EXPORT_SYMBOL_GPL(nf_tables_rebind_set); - void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) + struct nft_set_binding *binding, bool event) { list_del_rcu(&binding->list); - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + if (event) + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, + GFP_KERNEL); + } } EXPORT_SYMBOL_GPL(nf_tables_unbind_set); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) { - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC); + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) nft_set_destroy(set); - } } EXPORT_SYMBOL_GPL(nf_tables_destroy_set); @@ -6535,6 +6528,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_DELRULE); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_COMMIT); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -6621,7 +6617,8 @@ static void nf_tables_abort_release(struct nft_trans *trans) nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_NEWSET: - nft_set_destroy(nft_trans_set(trans)); + if (!nft_trans_set_bound(trans)) + nft_set_destroy(nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), @@ -6682,7 +6679,9 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWRULE: trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); - nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans)); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_ABORT); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; @@ -6692,7 +6691,8 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWSET: trans->ctx.table->use--; - list_del_rcu(&nft_trans_set(trans)->list); + if (!nft_trans_set_bound(trans)) + list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: trans->ctx.table->use++; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 5eb269428832..0a4bad55a8aa 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -61,6 +61,21 @@ static struct nft_compat_net *nft_compat_pernet(struct net *net) return net_generic(net, nft_compat_net_id); } +static void nft_xt_get(struct nft_xt *xt) +{ + /* refcount_inc() warns on 0 -> 1 transition, but we can't + * init the reference count to 1 in .select_ops -- we can't + * undo such an increase when another expression inside the same + * rule fails afterwards. + */ + if (xt->listcnt == 0) + refcount_set(&xt->refcnt, 1); + else + refcount_inc(&xt->refcnt); + + xt->listcnt++; +} + static bool nft_xt_put(struct nft_xt *xt) { if (refcount_dec_and_test(&xt->refcnt)) { @@ -291,7 +306,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; nft_xt = container_of(expr->ops, struct nft_xt, ops); - refcount_inc(&nft_xt->refcnt); + nft_xt_get(nft_xt); return 0; } @@ -300,6 +315,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; void *info = nft_expr_priv(expr); + struct module *me = target->me; struct xt_tgdtor_param par; par.net = ctx->net; @@ -310,7 +326,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) par.target->destroy(&par); if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(target->me); + module_put(me); } static int nft_extension_dump_info(struct sk_buff *skb, int attr, @@ -504,7 +520,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return ret; nft_xt = container_of(expr->ops, struct nft_xt, ops); - refcount_inc(&nft_xt->refcnt); + nft_xt_get(nft_xt); return 0; } @@ -558,41 +574,16 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); } -static void nft_compat_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - struct list_head *h) -{ - struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); - - if (xt->listcnt == 0) - list_add(&xt->head, h); - - xt->listcnt++; -} - -static void nft_compat_activate_mt(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_compat_net *cn = nft_compat_pernet(ctx->net); - - nft_compat_activate(ctx, expr, &cn->nft_match_list); -} - -static void nft_compat_activate_tg(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_compat_net *cn = nft_compat_pernet(ctx->net); - - nft_compat_activate(ctx, expr, &cn->nft_target_list); -} - static void nft_compat_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); - if (--xt->listcnt == 0) - list_del_init(&xt->head); + if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) { + if (--xt->listcnt == 0) + list_del_init(&xt->head); + } } static void @@ -848,7 +839,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.eval = nft_match_eval; nft_match->ops.init = nft_match_init; nft_match->ops.destroy = nft_match_destroy; - nft_match->ops.activate = nft_compat_activate_mt; nft_match->ops.deactivate = nft_compat_deactivate; nft_match->ops.dump = nft_match_dump; nft_match->ops.validate = nft_match_validate; @@ -866,7 +856,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.size = matchsize; - nft_match->listcnt = 1; + nft_match->listcnt = 0; list_add(&nft_match->head, &cn->nft_match_list); return &nft_match->ops; @@ -953,7 +943,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; nft_target->ops.destroy = nft_target_destroy; - nft_target->ops.activate = nft_compat_activate_tg; nft_target->ops.deactivate = nft_compat_deactivate; nft_target->ops.dump = nft_target_dump; nft_target->ops.validate = nft_target_validate; @@ -964,7 +953,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, else nft_target->ops.eval = nft_target_eval_xt; - nft_target->listcnt = 1; + nft_target->listcnt = 0; list_add(&nft_target->head, &cn->nft_target_list); return &nft_target->ops; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 07d4efd3d851..f1172f99752b 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -235,20 +235,17 @@ err1: return err; } -static void nft_dynset_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_dynset *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_dynset_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_dynset *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_dynset_destroy(const struct nft_ctx *ctx, @@ -296,7 +293,6 @@ static const struct nft_expr_ops nft_dynset_ops = { .eval = nft_dynset_eval, .init = nft_dynset_init, .destroy = nft_dynset_destroy, - .activate = nft_dynset_activate, .deactivate = nft_dynset_deactivate, .dump = nft_dynset_dump, }; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 0777a93211e2..3f6d1d2a6281 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, } static void nft_immediate_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + if (phase == NFT_TRANS_COMMIT) + return; + return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg)); } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 227b2b15a19c..14496da5141d 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -121,20 +121,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return 0; } -static void nft_lookup_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_lookup *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_lookup_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_lookup *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_lookup_destroy(const struct nft_ctx *ctx, @@ -225,7 +222,6 @@ static const struct nft_expr_ops nft_lookup_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)), .eval = nft_lookup_eval, .init = nft_lookup_init, - .activate = nft_lookup_activate, .deactivate = nft_lookup_deactivate, .destroy = nft_lookup_destroy, .dump = nft_lookup_dump, diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index a3185ca2a3a9..ae178e914486 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -155,20 +155,17 @@ nla_put_failure: return -1; } -static void nft_objref_map_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_objref_map *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_objref_map_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_objref_map *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_objref_map_destroy(const struct nft_ctx *ctx, @@ -185,7 +182,6 @@ static const struct nft_expr_ops nft_objref_map_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), .eval = nft_objref_map_eval, .init = nft_objref_map_init, - .activate = nft_objref_map_activate, .deactivate = nft_objref_map_deactivate, .destroy = nft_objref_map_destroy, .dump = nft_objref_map_dump, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index aecadd471e1d..13e1ac333fa4 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1899,7 +1899,7 @@ static int __init xt_init(void) seqcount_init(&per_cpu(xt_recseq, i)); } - xt = kmalloc_array(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); + xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); if (!xt) return -ENOMEM; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3b1a78906bc0..1cd1d83a4be0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4292,7 +4292,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; - if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr)) + if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 9fc76b19cd3c..db3473540303 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -132,7 +132,7 @@ static int pep_indicate(struct sock *sk, u8 id, u8 code, ph->utid = 0; ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -153,7 +153,7 @@ static int pipe_handler_request(struct sock *sk, u8 id, u8 code, ph->utid = id; /* whatever */ ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -208,7 +208,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, struct pnpipehdr *ph; struct sockaddr_pn dst; u8 data[4] = { - oph->data[0], /* PEP type */ + oph->pep_type, /* PEP type */ code, /* error code, at an unusual offset */ PAD, PAD, }; @@ -221,7 +221,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, ph->utid = oph->utid; ph->message_id = PNS_PEP_CTRL_RESP; ph->pipe_handle = oph->pipe_handle; - ph->data[0] = oph->data[1]; /* CTRL id */ + ph->data0 = oph->data[0]; /* CTRL id */ pn_skb_get_src_sockaddr(oskb, &dst); return pn_skb_send(sk, skb, &dst); @@ -272,17 +272,17 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) return -EINVAL; hdr = pnp_hdr(skb); - if (hdr->data[0] != PN_PEP_TYPE_COMMON) { + if (hdr->pep_type != PN_PEP_TYPE_COMMON) { net_dbg_ratelimited("Phonet unknown PEP type: %u\n", - (unsigned int)hdr->data[0]); + (unsigned int)hdr->pep_type); return -EOPNOTSUPP; } - switch (hdr->data[1]) { + switch (hdr->data[0]) { case PN_PEP_IND_FLOW_CONTROL: switch (pn->tx_fc) { case PN_LEGACY_FLOW_CONTROL: - switch (hdr->data[4]) { + switch (hdr->data[3]) { case PEP_IND_BUSY: atomic_set(&pn->tx_credits, 0); break; @@ -292,7 +292,7 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) } break; case PN_ONE_CREDIT_FLOW_CONTROL: - if (hdr->data[4] == PEP_IND_READY) + if (hdr->data[3] == PEP_IND_READY) atomic_set(&pn->tx_credits, wake = 1); break; } @@ -301,12 +301,12 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) case PN_PEP_IND_ID_MCFC_GRANT_CREDITS: if (pn->tx_fc != PN_MULTI_CREDIT_FLOW_CONTROL) break; - atomic_add(wake = hdr->data[4], &pn->tx_credits); + atomic_add(wake = hdr->data[3], &pn->tx_credits); break; default: net_dbg_ratelimited("Phonet unknown PEP indication: %u\n", - (unsigned int)hdr->data[1]); + (unsigned int)hdr->data[0]); return -EOPNOTSUPP; } if (wake) @@ -318,7 +318,7 @@ static int pipe_rcv_created(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr = pnp_hdr(skb); - u8 n_sb = hdr->data[0]; + u8 n_sb = hdr->data0; pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL; __skb_pull(skb, sizeof(*hdr)); @@ -506,7 +506,7 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb) return -ECONNREFUSED; /* Parse sub-blocks */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[6], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -739,7 +739,7 @@ static int pipe_do_remove(struct sock *sk) ph->utid = 0; ph->message_id = PNS_PIPE_REMOVE_REQ; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = PAD; + ph->data0 = PAD; return pn_skb_send(sk, skb, NULL); } @@ -817,7 +817,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, peer_type = hdr->other_pep_type << 8; /* Parse sub-blocks (options) */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[1], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -1109,7 +1109,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb) ph->utid = 0; if (pn->aligned) { ph->message_id = PNS_PIPE_ALIGNED_DATA; - ph->data[0] = 0; /* padding */ + ph->data0 = 0; /* padding */ } else ph->message_id = PNS_PIPE_DATA; ph->pipe_handle = pn->pipe_handle; diff --git a/net/rds/bind.c b/net/rds/bind.c index 762d2c6788a3..17c9d9f0c848 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); - if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) - rds_sock_addref(rs); - else + if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || + !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index eaf19ebaa964..3f7bb11f3290 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -596,6 +596,7 @@ error_requeue_call: } error_no_call: release_sock(&rx->sk); +error_trace: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); return ret; @@ -604,7 +605,7 @@ wait_interrupted: wait_error: finish_wait(sk_sleep(&rx->sk), &wait); call = NULL; - goto error_no_call; + goto error_trace; } /** diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f6aa57fbbbaf..12ca9d13db83 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1371,7 +1371,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (!tc_skip_hw(fnew->flags)) { err = fl_hw_replace_filter(tp, fnew, extack); if (err) - goto errout_mask; + goto errout_mask_ht; } if (!tc_in_hw(fnew->flags)) @@ -1401,6 +1401,10 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, kfree(mask); return 0; +errout_mask_ht: + rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); + errout_mask: fl_mask_put(head, fnew->mask, false); diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 9ccc93f257db..38bb882bb958 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -48,7 +48,7 @@ struct tcindex_data { u32 hash; /* hash table size; 0 if undefined */ u32 alloc_hash; /* allocated size */ u32 fall_through; /* 0: only classify if explicit match */ - struct rcu_head rcu; + struct rcu_work rwork; }; static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) @@ -221,17 +221,11 @@ found: return 0; } -static int tcindex_destroy_element(struct tcf_proto *tp, - void *arg, struct tcf_walker *walker) -{ - bool last; - - return tcindex_delete(tp, arg, &last, NULL); -} - -static void __tcindex_destroy(struct rcu_head *head) +static void tcindex_destroy_work(struct work_struct *work) { - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + struct tcindex_data *p = container_of(to_rcu_work(work), + struct tcindex_data, + rwork); kfree(p->perfect); kfree(p->h); @@ -258,9 +252,11 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r) return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); } -static void __tcindex_partial_destroy(struct rcu_head *head) +static void tcindex_partial_destroy_work(struct work_struct *work) { - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + struct tcindex_data *p = container_of(to_rcu_work(work), + struct tcindex_data, + rwork); kfree(p->perfect); kfree(p); @@ -275,7 +271,7 @@ static void tcindex_free_perfect_hash(struct tcindex_data *cp) kfree(cp->perfect); } -static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) +static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) { int i, err = 0; @@ -289,6 +285,9 @@ static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) goto errout; +#ifdef CONFIG_NET_CLS_ACT + cp->perfect[i].exts.net = net; +#endif } return 0; @@ -305,9 +304,9 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) { struct tcindex_filter_result new_filter_result, *old_r = r; - struct tcindex_filter_result cr; struct tcindex_data *cp = NULL, *oldp; struct tcindex_filter *f = NULL; /* make gcc behave */ + struct tcf_result cr = {}; int err, balloc = 0; struct tcf_exts e; @@ -337,7 +336,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (p->perfect) { int i; - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout; for (i = 0; i < cp->hash; i++) cp->perfect[i].res = p->perfect[i].res; @@ -348,11 +347,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcindex_filter_result_init(&new_filter_result); if (err < 0) goto errout1; - err = tcindex_filter_result_init(&cr); - if (err < 0) - goto errout1; if (old_r) - cr.res = r->res; + cr = r->res; if (tb[TCA_TCINDEX_HASH]) cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); @@ -406,7 +402,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = -ENOMEM; if (!cp->perfect && !cp->h) { if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout_alloc; balloc = 1; } else { @@ -443,8 +439,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } if (tb[TCA_TCINDEX_CLASSID]) { - cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr.res, base); + cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); + tcf_bind_filter(tp, &cr, base); } if (old_r && old_r != r) { @@ -456,7 +452,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } oldp = p; - r->res = cr.res; + r->res = cr; tcf_exts_change(&r->exts, &e); rcu_assign_pointer(tp->root, cp); @@ -475,10 +471,12 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, ; /* nothing */ rcu_assign_pointer(*fp, f); + } else { + tcf_exts_destroy(&new_filter_result.exts); } if (oldp) - call_rcu(&oldp->rcu, __tcindex_partial_destroy); + tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work); return 0; errout_alloc: @@ -487,7 +485,6 @@ errout_alloc: else if (balloc == 2) kfree(cp->h); errout1: - tcf_exts_destroy(&cr.exts); tcf_exts_destroy(&new_filter_result.exts); errout: kfree(cp); @@ -562,15 +559,34 @@ static void tcindex_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcf_walker walker; + int i; pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); - walker.count = 0; - walker.skip = 0; - walker.fn = tcindex_destroy_element; - tcindex_walk(tp, &walker); - call_rcu(&p->rcu, __tcindex_destroy); + if (p->perfect) { + for (i = 0; i < p->hash; i++) { + struct tcindex_filter_result *r = p->perfect + i; + + tcf_unbind_filter(tp, &r->res); + if (tcf_exts_get_net(&r->exts)) + tcf_queue_work(&r->rwork, + tcindex_destroy_rexts_work); + else + __tcindex_destroy_rexts(r); + } + } + + for (i = 0; p->h && i < p->hash; i++) { + struct tcindex_filter *f, *next; + bool last; + + for (f = rtnl_dereference(p->h[i]); f; f = next) { + next = rtnl_dereference(f->next); + tcindex_delete(tp, &f->result, &last, NULL); + } + } + + tcf_queue_work(&p->rwork, tcindex_destroy_work); } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 66ba2ce2320f..968a85fe4d4a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -500,7 +500,7 @@ static void dev_watchdog_down(struct net_device *dev) * netif_carrier_on - set carrier * @dev: network device * - * Device has detected that carrier. + * Device has detected acquisition of carrier. */ void netif_carrier_on(struct net_device *dev) { diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 078f01a8d582..435847d98b51 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -256,6 +256,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) + nla_total_size(sizeof(struct inet_diag_meminfo)) diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 123e9f2dc226..edfcf16e704c 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -36,6 +36,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; skb->csum_not_inet = 0; + gso_reset_checksum(skb, ~0); return sctp_compute_cksum(skb, skb_transport_offset(skb)); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f93c3cf9e567..65d6d04546ae 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2027,7 +2027,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_transport *transport = NULL; struct sctp_sndrcvinfo _sinfo, *sinfo; - struct sctp_association *asoc; + struct sctp_association *asoc, *tmp; struct sctp_cmsgs cmsgs; union sctp_addr *daddr; bool new = false; @@ -2053,7 +2053,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) /* SCTP_SENDALL process */ if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) { - list_for_each_entry(asoc, &ep->asocs, asocs) { + list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err == 0) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 80e0ae5534ec..2936ed17bf9e 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count) } } +static size_t fa_index(struct flex_array *fa, void *elem, size_t count) +{ + size_t index = 0; + + while (count--) { + if (elem == flex_array_get(fa, index)) + break; + index++; + } + + return index; +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -131,8 +144,10 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, } } - for (i = outcnt; i < stream->outcnt; i++) + for (i = outcnt; i < stream->outcnt; i++) { kfree(SCTP_SO(stream, i)->ext); + SCTP_SO(stream, i)->ext = NULL; + } } static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, @@ -147,6 +162,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, if (stream->out) { fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt)); + if (stream->out_curr) { + size_t index = fa_index(stream->out, stream->out_curr, + stream->outcnt); + + BUG_ON(index == stream->outcnt); + stream->out_curr = flex_array_get(out, index); + } fa_free(stream->out); } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 033696e6f74f..ad158d311ffa 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -207,7 +207,8 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport) /* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies + sctp_transport_timeout(transport); - if (time_before(transport->hb_timer.expires, expires) && + if ((time_before(transport->hb_timer.expires, expires) || + !timer_pending(&transport->hb_timer)) && !mod_timer(&transport->hb_timer, expires + prandom_u32_max(transport->rto))) sctp_transport_hold(transport); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c4e56602e0c6..b04a813fc865 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1505,6 +1505,11 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, smc = smc_sk(sk); lock_sock(sk); + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if ((sk->sk_state == SMC_INIT) || (sk->sk_state == SMC_LISTEN) || (sk->sk_state == SMC_CLOSED)) @@ -1840,7 +1845,11 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, smc = smc_sk(sk); lock_sock(sk); - + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if (sk->sk_state == SMC_INIT || sk->sk_state == SMC_LISTEN || sk->sk_state == SMC_CLOSED) diff --git a/net/smc/smc.h b/net/smc/smc.h index 5721416d0605..adbdf195eb08 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -113,9 +113,9 @@ struct smc_host_cdc_msg { /* Connection Data Control message */ } __aligned(8); enum smc_urg_state { - SMC_URG_VALID, /* data present */ - SMC_URG_NOTYET, /* data pending */ - SMC_URG_READ /* data was already read */ + SMC_URG_VALID = 1, /* data present */ + SMC_URG_NOTYET = 2, /* data pending */ + SMC_URG_READ = 3, /* data was already read */ }; struct smc_connection { diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index db83332ac1c8..fb07ad8d69a6 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -21,13 +21,6 @@ /********************************** send *************************************/ -struct smc_cdc_tx_pend { - struct smc_connection *conn; /* socket connection */ - union smc_host_cursor cursor; /* tx sndbuf cursor sent */ - union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ - u16 ctrl_seq; /* conn. tx sequence # */ -}; - /* handler for send/transmission completion of a CDC msg */ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, struct smc_link *link, @@ -61,12 +54,14 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend) { struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int rc; rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf, + wr_rdma_buf, (struct smc_wr_tx_pend_priv **)pend); if (!conn->alert_token_local) /* abnormal termination */ @@ -96,6 +91,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, struct smc_cdc_tx_pend *pend) { + union smc_host_cursor cfed; struct smc_link *link; int rc; @@ -105,12 +101,10 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->tx_cdc_seq++; conn->local_tx_ctrl.seqno = conn->tx_cdc_seq; - smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, - &conn->local_tx_ctrl, conn); + smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed); rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend); if (!rc) - smc_curs_copy(&conn->rx_curs_confirmed, - &conn->local_tx_ctrl.cons, conn); + smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn); return rc; } @@ -121,11 +115,14 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, NULL, &pend); if (rc) return rc; - return smc_cdc_msg_send(conn, wr_buf, pend); + spin_lock_bh(&conn->send_lock); + rc = smc_cdc_msg_send(conn, wr_buf, pend); + spin_unlock_bh(&conn->send_lock); + return rc; } int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index b5bfe38c7f9b..f1cdde9d4b89 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -160,7 +160,9 @@ static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt, #endif } -/* calculate cursor difference between old and new, where old <= new */ +/* calculate cursor difference between old and new, where old <= new and + * difference cannot exceed size + */ static inline int smc_curs_diff(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) @@ -185,28 +187,51 @@ static inline int smc_curs_comp(unsigned int size, return smc_curs_diff(size, old, new); } +/* calculate cursor difference between old and new, where old <= new and + * difference may exceed size + */ +static inline int smc_curs_diff_large(unsigned int size, + union smc_host_cursor *old, + union smc_host_cursor *new) +{ + if (old->wrap < new->wrap) + return min_t(int, + (size - old->count) + new->count + + (new->wrap - old->wrap - 1) * size, + size); + + if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */ + return min_t(int, + (size - old->count) + new->count + + (new->wrap + 0xffff - old->wrap) * size, + size); + + return max_t(int, 0, (new->count - old->count)); +} + static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, + union smc_host_cursor *save, struct smc_connection *conn) { - union smc_host_cursor temp; - - smc_curs_copy(&temp, local, conn); - peer->count = htonl(temp.count); - peer->wrap = htons(temp.wrap); + smc_curs_copy(save, local, conn); + peer->count = htonl(save->count); + peer->wrap = htons(save->wrap); /* peer->reserved = htons(0); must be ensured by caller */ } static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer, - struct smc_host_cdc_msg *local, - struct smc_connection *conn) + struct smc_connection *conn, + union smc_host_cursor *save) { + struct smc_host_cdc_msg *local = &conn->local_tx_ctrl; + peer->common.type = local->common.type; peer->len = local->len; peer->seqno = htons(local->seqno); peer->token = htonl(local->token); - smc_host_cursor_to_cdc(&peer->prod, &local->prod, conn); - smc_host_cursor_to_cdc(&peer->cons, &local->cons, conn); + smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn); + smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn); peer->prod_flags = local->prod_flags; peer->conn_state_flags = local->conn_state_flags; } @@ -270,10 +295,16 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, smcr_cdc_msg_to_host(local, peer, conn); } -struct smc_cdc_tx_pend; +struct smc_cdc_tx_pend { + struct smc_connection *conn; /* socket connection */ + union smc_host_cursor cursor; /* tx sndbuf cursor sent */ + union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ + u16 ctrl_seq; /* conn. tx sequence # */ +}; int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend); void smc_cdc_tx_dismiss_slots(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 776e9dfc915d..d53fd588d1f5 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) vec.iov_len = sizeof(struct smc_clc_msg_decline); len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(struct smc_clc_msg_decline)); - if (len < sizeof(struct smc_clc_msg_decline)) + if (len < 0 || len < sizeof(struct smc_clc_msg_decline)) len = -EPROTO; return len > 0 ? 0 : len; } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index ea2b87f29469..e39cadda1bf5 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -345,14 +345,7 @@ static void smc_close_passive_work(struct work_struct *work) switch (sk->sk_state) { case SMC_INIT: - if (atomic_read(&conn->bytes_to_rcv) || - (rxflags->peer_done_writing && - !smc_cdc_rxed_any_close(conn))) { - sk->sk_state = SMC_APPCLOSEWAIT1; - } else { - sk->sk_state = SMC_CLOSED; - sock_put(sk); /* passive closing */ - } + sk->sk_state = SMC_APPCLOSEWAIT1; break; case SMC_ACTIVE: sk->sk_state = SMC_APPCLOSEWAIT1; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 35c1cdc93e1c..aa1c551cee81 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -128,6 +128,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!lgr) + return; write_lock_bh(&lgr->conns_lock); if (conn->alert_token_local) { __smc_lgr_unregister_conn(conn); @@ -300,13 +302,13 @@ static void smc_buf_unuse(struct smc_connection *conn, conn->sndbuf_desc->used = 0; if (conn->rmb_desc) { if (!conn->rmb_desc->regerr) { - conn->rmb_desc->used = 0; if (!lgr->is_smcd) { /* unregister rmb with peer */ smc_llc_do_delete_rkey( &lgr->lnk[SMC_SINGLE_LINK], conn->rmb_desc); } + conn->rmb_desc->used = 0; } else { /* buf registration failed, reuse not possible */ write_lock_bh(&lgr->rmbs_lock); @@ -628,6 +630,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, local_contact = SMC_REUSE_CONTACT; conn->lgr = lgr; smc_lgr_register_conn(conn); /* add smc conn to lgr */ + if (delayed_work_pending(&lgr->free_work)) + cancel_delayed_work(&lgr->free_work); write_unlock_bh(&lgr->conns_lock); break; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index b00287989a3d..8806d2afa6ed 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -52,6 +52,24 @@ enum smc_wr_reg_state { FAILED /* ib_wr_reg_mr response: failure */ }; +struct smc_rdma_sge { /* sges for RDMA writes */ + struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE]; +}; + +#define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per + * message send + */ + +struct smc_rdma_sges { /* sges per message send */ + struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES]; +}; + +struct smc_rdma_wr { /* work requests per message + * send + */ + struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES]; +}; + struct smc_link { struct smc_ib_device *smcibdev; /* ib-device */ u8 ibport; /* port - values 1 | 2 */ @@ -64,6 +82,8 @@ struct smc_link { struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */ struct ib_send_wr *wr_tx_ibs; /* WR send meta data */ struct ib_sge *wr_tx_sges; /* WR send gather meta data */ + struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/ + struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */ struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ /* above four vectors have wr_tx_cnt elements and use the same index */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index e519ef29c0ff..76487a16934e 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -289,8 +289,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) { - struct smc_ib_device *smcibdev = - (struct smc_ib_device *)ibevent->device; + struct smc_link *lnk = (struct smc_link *)priv; + struct smc_ib_device *smcibdev = lnk->smcibdev; u8 port_idx; switch (ibevent->event) { @@ -298,7 +298,7 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) case IB_EVENT_GID_CHANGE: case IB_EVENT_PORT_ERR: case IB_EVENT_QP_ACCESS_ERR: - port_idx = ibevent->element.port_num - 1; + port_idx = ibevent->element.qp->port - 1; set_bit(port_idx, &smcibdev->port_event_mask); schedule_work(&smcibdev->port_event_work); break; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a6d3623d06f4..4fd60c522802 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -166,7 +166,8 @@ static int smc_llc_add_pending_send(struct smc_link *link, { int rc; - rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, pend); + rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, NULL, + pend); if (rc < 0) return rc; BUILD_BUG_ON_MSG( diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7cb3e4f07c10..632c3109dee5 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -27,7 +27,7 @@ static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, - .len = SMC_MAX_PNETID_LEN - 1 + .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index d8366ed51757..f93f3580c100 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -165,12 +165,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { + if (send_done) + return send_done; rc = smc_tx_wait(smc, msg->msg_flags); - if (rc) { - if (send_done) - return send_done; + if (rc) goto out_err; - } continue; } @@ -267,27 +266,23 @@ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, - int num_sges, struct ib_sge sges[]) + int num_sges, struct ib_rdma_wr *rdma_wr) { struct smc_link_group *lgr = conn->lgr; - struct ib_rdma_wr rdma_wr; struct smc_link *link; int rc; - memset(&rdma_wr, 0, sizeof(rdma_wr)); link = &lgr->lnk[SMC_SINGLE_LINK]; - rdma_wr.wr.wr_id = smc_wr_tx_get_next_wr_id(link); - rdma_wr.wr.sg_list = sges; - rdma_wr.wr.num_sge = num_sges; - rdma_wr.wr.opcode = IB_WR_RDMA_WRITE; - rdma_wr.remote_addr = + rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link); + rdma_wr->wr.num_sge = num_sges; + rdma_wr->remote_addr = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr + /* RMBE within RMB */ conn->tx_off + /* offset within RMBE */ peer_rmbe_offset; - rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; - rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL); + rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; + rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) { conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; smc_lgr_terminate(lgr); @@ -314,24 +309,25 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn, /* SMC-R helper for smc_tx_rdma_writes() */ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, - size_t dst_off, size_t dst_len) + size_t dst_off, size_t dst_len, + struct smc_rdma_wr *wr_rdma_buf) { dma_addr_t dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl); - struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int src_len_sum = src_len, dst_len_sum = dst_len; - struct ib_sge sges[SMC_IB_MAX_SEND_SGE]; int sent_count = src_off; int srcchunk, dstchunk; int num_sges; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { + struct ib_sge *sge = + wr_rdma_buf->wr_tx_rdma[dstchunk].wr.sg_list; + num_sges = 0; for (srcchunk = 0; srcchunk < 2; srcchunk++) { - sges[srcchunk].addr = dma_addr + src_off; - sges[srcchunk].length = src_len; - sges[srcchunk].lkey = link->roce_pd->local_dma_lkey; + sge[srcchunk].addr = dma_addr + src_off; + sge[srcchunk].length = src_len; num_sges++; src_off += src_len; @@ -344,7 +340,8 @@ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } - rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges); + rc = smc_tx_rdma_write(conn, dst_off, num_sges, + &wr_rdma_buf->wr_tx_rdma[dstchunk]); if (rc) return rc; if (dst_len_sum == len) @@ -403,7 +400,8 @@ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len, /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; * usable snd_wnd as max transmit */ -static int smc_tx_rdma_writes(struct smc_connection *conn) +static int smc_tx_rdma_writes(struct smc_connection *conn, + struct smc_rdma_wr *wr_rdma_buf) { size_t len, src_len, dst_off, dst_len; /* current chunk values */ union smc_host_cursor sent, prep, prod, cons; @@ -464,7 +462,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) dst_off, dst_len); else rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len, - dst_off, dst_len); + dst_off, dst_len, wr_rdma_buf); if (rc) return rc; @@ -485,31 +483,30 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags; + struct smc_rdma_wr *wr_rdma_buf; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc; - spin_lock_bh(&conn->send_lock); - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &wr_rdma_buf, &pend); if (rc < 0) { if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); - if (smc->sk.sk_err == ECONNABORTED) { - rc = sock_error(&smc->sk); - goto out_unlock; - } + if (smc->sk.sk_err == ECONNABORTED) + return sock_error(&smc->sk); rc = 0; if (conn->alert_token_local) /* connection healthy */ mod_delayed_work(system_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } - goto out_unlock; + return rc; } + spin_lock_bh(&conn->send_lock); if (!conn->local_tx_ctrl.prod_flags.urg_data_present) { - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, wr_rdma_buf); if (rc) { smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], (struct smc_wr_tx_pend_priv *)pend); @@ -536,7 +533,7 @@ static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) spin_lock_bh(&conn->send_lock); if (!pflags->urg_data_present) - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, NULL); if (!rc) rc = smcd_cdc_msg_send(conn); @@ -598,7 +595,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) if (to_confirm > conn->rmbe_update_limit) { smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn); sender_free = conn->rmb_desc->len - - smc_curs_diff(conn->rmb_desc->len, &prod, &cfed); + smc_curs_diff_large(conn->rmb_desc->len, + &cfed, &prod); } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index c2694750a6a8..253aa75dc2b6 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -160,6 +160,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) * @link: Pointer to smc_link used to later send the message. * @handler: Send completion handler function pointer. * @wr_buf: Out value returns pointer to message buffer. + * @wr_rdma_buf: Out value returns pointer to rdma work request. * @wr_pend_priv: Out value returns pointer serving as handler context. * * Return: 0 on success, or -errno on error. @@ -167,6 +168,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_wr_tx_pend_priv **wr_pend_priv) { struct smc_wr_tx_pend *wr_pend; @@ -204,6 +206,8 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, wr_ib = &link->wr_tx_ibs[idx]; wr_ib->wr_id = wr_id; *wr_buf = &link->wr_tx_bufs[idx]; + if (wr_rdma_buf) + *wr_rdma_buf = &link->wr_tx_rdmas[idx]; *wr_pend_priv = &wr_pend->priv; return 0; } @@ -218,10 +222,10 @@ int smc_wr_tx_put_slot(struct smc_link *link, u32 idx = pend->idx; /* clear the full struct smc_wr_tx_pend including .priv */ - memset(&link->wr_tx_pends[pend->idx], 0, - sizeof(link->wr_tx_pends[pend->idx])); - memset(&link->wr_tx_bufs[pend->idx], 0, - sizeof(link->wr_tx_bufs[pend->idx])); + memset(&link->wr_tx_pends[idx], 0, + sizeof(link->wr_tx_pends[idx])); + memset(&link->wr_tx_bufs[idx], 0, + sizeof(link->wr_tx_bufs[idx])); test_and_clear_bit(idx, link->wr_tx_mask); return 1; } @@ -465,12 +469,26 @@ static void smc_wr_init_sge(struct smc_link *lnk) lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE; lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE; lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; lnk->wr_tx_ibs[i].next = NULL; lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i]; lnk->wr_tx_ibs[i].num_sge = 1; lnk->wr_tx_ibs[i].opcode = IB_WR_SEND; lnk->wr_tx_ibs[i].send_flags = IB_SEND_SIGNALED | IB_SEND_SOLICITED; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge; } for (i = 0; i < lnk->wr_rx_cnt; i++) { lnk->wr_rx_sges[i].addr = @@ -521,8 +539,12 @@ void smc_wr_free_link_mem(struct smc_link *lnk) lnk->wr_tx_mask = NULL; kfree(lnk->wr_tx_sges); lnk->wr_tx_sges = NULL; + kfree(lnk->wr_tx_rdma_sges); + lnk->wr_tx_rdma_sges = NULL; kfree(lnk->wr_rx_sges); lnk->wr_rx_sges = NULL; + kfree(lnk->wr_tx_rdmas); + lnk->wr_tx_rdmas = NULL; kfree(lnk->wr_rx_ibs); lnk->wr_rx_ibs = NULL; kfree(lnk->wr_tx_ibs); @@ -552,10 +574,20 @@ int smc_wr_alloc_link_mem(struct smc_link *link) GFP_KERNEL); if (!link->wr_rx_ibs) goto no_mem_wr_tx_ibs; + link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdmas[0]), + GFP_KERNEL); + if (!link->wr_tx_rdmas) + goto no_mem_wr_rx_ibs; + link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdma_sges[0]), + GFP_KERNEL); + if (!link->wr_tx_rdma_sges) + goto no_mem_wr_tx_rdmas; link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]), GFP_KERNEL); if (!link->wr_tx_sges) - goto no_mem_wr_rx_ibs; + goto no_mem_wr_tx_rdma_sges; link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3, sizeof(link->wr_rx_sges[0]), GFP_KERNEL); @@ -579,6 +611,10 @@ no_mem_wr_rx_sges: kfree(link->wr_rx_sges); no_mem_wr_tx_sges: kfree(link->wr_tx_sges); +no_mem_wr_tx_rdma_sges: + kfree(link->wr_tx_rdma_sges); +no_mem_wr_tx_rdmas: + kfree(link->wr_tx_rdmas); no_mem_wr_rx_ibs: kfree(link->wr_rx_ibs); no_mem_wr_tx_ibs: diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index 1d85bb14fd6f..09bf32fd3959 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -85,6 +85,7 @@ void smc_wr_add_dev(struct smc_ib_device *smcibdev); int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wrs, struct smc_wr_tx_pend_priv **wr_pend_priv); int smc_wr_tx_put_slot(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv); diff --git a/net/socket.c b/net/socket.c index e89884e2197b..d80d87a395ea 100644 --- a/net/socket.c +++ b/net/socket.c @@ -941,8 +941,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg, - unsigned int ifreq_size) + unsigned int cmd, unsigned long arg) { int err; void __user *argp = (void __user *)arg; @@ -968,11 +967,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, ifreq_size)) + if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, ifreq_size)) + if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; } return err; @@ -1071,8 +1070,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct ifreq)); + err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; @@ -2780,8 +2778,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2797,8 +2794,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -2994,6 +2990,54 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, return dev_ioctl(net, cmd, &ifreq, NULL); } +static int compat_ifreq_ioctl(struct net *net, struct socket *sock, + unsigned int cmd, + struct compat_ifreq __user *uifr32) +{ + struct ifreq __user *uifr; + int err; + + /* Handle the fact that while struct ifreq has the same *layout* on + * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, + * which are handled elsewhere, it still has different *size* due to + * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, + * resulting in struct ifreq being 32 and 40 bytes respectively). + * As a result, if the struct happens to be at the end of a page and + * the next page isn't readable/writable, we get a fault. To prevent + * that, copy back and forth to the full size. + */ + + uifr = compat_alloc_user_space(sizeof(*uifr)); + if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) + return -EFAULT; + + err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); + + if (!err) { + switch (cmd) { + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFMEM: + case SIOCGIFHWADDR: + case SIOCGIFINDEX: + case SIOCGIFADDR: + case SIOCGIFBRDADDR: + case SIOCGIFDSTADDR: + case SIOCGIFNETMASK: + case SIOCGIFPFLAGS: + case SIOCGIFTXQLEN: + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCGIFNAME: + if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) + err = -EFAULT; + break; + } + } + return err; +} + static int compat_sioc_ifmap(struct net *net, unsigned int cmd, struct compat_ifreq __user *uifr32) { @@ -3109,8 +3153,7 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, - sizeof(struct compat_ifreq)); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); set_fs(old_fs); out: @@ -3210,21 +3253,22 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSIFTXQLEN: case SIOCBRADDIF: case SIOCBRDELIF: + case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: - case SIOCSARP: - case SIOCGARP: - case SIOCDARP: - case SIOCATMARK: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct compat_ifreq)); + return compat_ifreq_ioctl(net, sock, cmd, argp); + + case SIOCSARP: + case SIOCGARP: + case SIOCDARP: + case SIOCATMARK: + return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index fb6656295204..507105127095 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -44,7 +44,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, unsigned char *cksum, unsigned char *buf) { struct crypto_sync_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code; dprintk("RPC: %s:\n", __func__); @@ -52,6 +52,10 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, if (IS_ERR(cipher)) return PTR_ERR(cipher); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) ((seqnum >> 24) & 0xff); plain[1] = (unsigned char) ((seqnum >> 16) & 0xff); plain[2] = (unsigned char) ((seqnum >> 8) & 0xff); @@ -67,6 +71,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, code = krb5_encrypt(cipher, cksum, plain, buf, 8); out: + kfree(plain); crypto_free_sync_skcipher(cipher); return code; } @@ -77,12 +82,17 @@ krb5_make_seq_num(struct krb5_ctx *kctx, u32 seqnum, unsigned char *cksum, unsigned char *buf) { - unsigned char plain[8]; + unsigned char *plain; + s32 code; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_make_rc4_seq_num(kctx, direction, seqnum, cksum, buf); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) (seqnum & 0xff); plain[1] = (unsigned char) ((seqnum >> 8) & 0xff); plain[2] = (unsigned char) ((seqnum >> 16) & 0xff); @@ -93,7 +103,9 @@ krb5_make_seq_num(struct krb5_ctx *kctx, plain[6] = direction; plain[7] = direction; - return krb5_encrypt(key, cksum, plain, buf, 8); + code = krb5_encrypt(key, cksum, plain, buf, 8); + kfree(plain); + return code; } static s32 @@ -101,7 +113,7 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, unsigned char *buf, int *direction, s32 *seqnum) { struct crypto_sync_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code; dprintk("RPC: %s:\n", __func__); @@ -113,20 +125,28 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, if (code) goto out; + plain = kmalloc(8, GFP_NOFS); + if (!plain) { + code = -ENOMEM; + goto out; + } + code = krb5_decrypt(cipher, cksum, buf, plain, 8); if (code) - goto out; + goto out_plain; if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || (plain[4] != plain[7])) { code = (s32)KG_BAD_SEQ; - goto out; + goto out_plain; } *direction = plain[4]; *seqnum = ((plain[0] << 24) | (plain[1] << 16) | (plain[2] << 8) | (plain[3])); +out_plain: + kfree(plain); out: crypto_free_sync_skcipher(cipher); return code; @@ -139,7 +159,7 @@ krb5_get_seq_num(struct krb5_ctx *kctx, int *direction, u32 *seqnum) { s32 code; - unsigned char plain[8]; + unsigned char *plain; struct crypto_sync_skcipher *key = kctx->seq; dprintk("RPC: krb5_get_seq_num:\n"); @@ -147,18 +167,25 @@ krb5_get_seq_num(struct krb5_ctx *kctx, if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_get_rc4_seq_num(kctx, cksum, buf, direction, seqnum); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; if ((code = krb5_decrypt(key, cksum, buf, plain, 8))) - return code; + goto out; if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || - (plain[4] != plain[7])) - return (s32)KG_BAD_SEQ; + (plain[4] != plain[7])) { + code = (s32)KG_BAD_SEQ; + goto out; + } *direction = plain[4]; *seqnum = ((plain[0]) | (plain[1] << 8) | (plain[2] << 16) | (plain[3] << 24)); - return 0; +out: + kfree(plain); + return code; } diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c index 45a033329cd4..19bb356230ed 100644 --- a/net/sunrpc/debugfs.c +++ b/net/sunrpc/debugfs.c @@ -146,7 +146,7 @@ rpc_clnt_debugfs_register(struct rpc_clnt *clnt) rcu_read_lock(); xprt = rcu_dereference(clnt->cl_xprt); /* no "debugfs" dentry? Don't bother with the symlink. */ - if (!xprt->debugfs) { + if (IS_ERR_OR_NULL(xprt->debugfs)) { rcu_read_unlock(); return; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index cf51b8f9b15f..1f200119268c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -537,6 +537,99 @@ void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma, DMA_TO_DEVICE); } +/* If the xdr_buf has more elements than the device can + * transmit in a single RDMA Send, then the reply will + * have to be copied into a bounce buffer. + */ +static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma, + struct xdr_buf *xdr, + __be32 *wr_lst) +{ + int elements; + + /* xdr->head */ + elements = 1; + + /* xdr->pages */ + if (!wr_lst) { + unsigned int remaining; + unsigned long pageoff; + + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + ++elements; + remaining -= min_t(u32, PAGE_SIZE - pageoff, + remaining); + pageoff = 0; + } + } + + /* xdr->tail */ + if (xdr->tail[0].iov_len) + ++elements; + + /* assume 1 SGE is needed for the transport header */ + return elements >= rdma->sc_max_send_sges; +} + +/* The device is not capable of sending the reply directly. + * Assemble the elements of @xdr into the transport header + * buffer. + */ +static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt, + struct xdr_buf *xdr, __be32 *wr_lst) +{ + unsigned char *dst, *tailbase; + unsigned int taillen; + + dst = ctxt->sc_xprt_buf; + dst += ctxt->sc_sges[0].length; + + memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len); + dst += xdr->head[0].iov_len; + + tailbase = xdr->tail[0].iov_base; + taillen = xdr->tail[0].iov_len; + if (wr_lst) { + u32 xdrpad; + + xdrpad = xdr_padsize(xdr->page_len); + if (taillen && xdrpad) { + tailbase += xdrpad; + taillen -= xdrpad; + } + } else { + unsigned int len, remaining; + unsigned long pageoff; + struct page **ppages; + + ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + len = min_t(u32, PAGE_SIZE - pageoff, remaining); + + memcpy(dst, page_address(*ppages), len); + remaining -= len; + dst += len; + pageoff = 0; + } + } + + if (taillen) + memcpy(dst, tailbase, taillen); + + ctxt->sc_sges[0].length += xdr->len; + ib_dma_sync_single_for_device(rdma->sc_pd->device, + ctxt->sc_sges[0].addr, + ctxt->sc_sges[0].length, + DMA_TO_DEVICE); + + return 0; +} + /* svc_rdma_map_reply_msg - Map the buffer holding RPC message * @rdma: controlling transport * @ctxt: send_ctxt for the Send WR @@ -559,8 +652,10 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, u32 xdr_pad; int ret; - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + if (svc_rdma_pull_up_needed(rdma, xdr, wr_lst)) + return svc_rdma_pull_up_reply_msg(rdma, ctxt, xdr, wr_lst); + + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, xdr->head[0].iov_base, xdr->head[0].iov_len); @@ -591,8 +686,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - page_off, remaining); - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_page(rdma, ctxt, *ppages++, page_off, len); if (ret < 0) @@ -606,8 +700,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, len = xdr->tail[0].iov_len; tail: if (len) { - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, base, len); if (ret < 0) return ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 924c17d46903..57f86c63a463 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -419,12 +419,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* Transport header, head iovec, tail iovec */ newxprt->sc_max_send_sges = 3; /* Add one SGE per page list entry */ - newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE; - if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) { - pr_err("svcrdma: too few Send SGEs available (%d needed)\n", - newxprt->sc_max_send_sges); - goto errout; - } + newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1; + if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) + newxprt->sc_max_send_sges = dev->attrs.max_send_sge; newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = svcrdma_max_requests; newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 4994e75945b8..21113bfd4eca 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -527,7 +527,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, sendcq = ib_alloc_cq(ia->ri_device, NULL, ep->rep_attr.cap.max_send_wr + 1, - 1, IB_POLL_WORKQUEUE); + ia->ri_device->num_comp_vectors > 1 ? 1 : 0, + IB_POLL_WORKQUEUE); if (IS_ERR(sendcq)) { rc = PTR_ERR(sendcq); goto out1; diff --git a/net/tipc/link.c b/net/tipc/link.c index 2792a3cae682..85ad5c0678d0 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1145,7 +1145,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, default: pr_warn("Dropping received illegal msg type\n"); kfree_skb(skb); - return false; + return true; }; } @@ -1425,6 +1425,10 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, l->rcv_unacked = 0; } else { /* RESET_MSG or ACTIVATE_MSG */ + if (mtyp == ACTIVATE_MSG) { + msg_set_dest_session_valid(hdr, 1); + msg_set_dest_session(hdr, l->peer_session); + } msg_set_max_pkt(hdr, l->advertised_mtu); strcpy(data, l->if_name); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); @@ -1642,6 +1646,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); break; } + + /* If this endpoint was re-created while peer was ESTABLISHING + * it doesn't know current session number. Force re-synch. + */ + if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) && + l->session != msg_dest_session(hdr)) { + if (less(l->session, msg_dest_session(hdr))) + l->session = msg_dest_session(hdr) + 1; + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index a0924956bb61..d7e4b8b93f9d 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -360,6 +360,28 @@ static inline void msg_set_bcast_ack(struct tipc_msg *m, u16 n) msg_set_bits(m, 1, 0, 0xffff, n); } +/* Note: reusing bits in word 1 for ACTIVATE_MSG only, to re-synch + * link peer session number + */ +static inline bool msg_dest_session_valid(struct tipc_msg *m) +{ + return msg_bits(m, 1, 16, 0x1); +} + +static inline void msg_set_dest_session_valid(struct tipc_msg *m, bool valid) +{ + msg_set_bits(m, 1, 16, 0x1, valid); +} + +static inline u16 msg_dest_session(struct tipc_msg *m) +{ + return msg_bits(m, 1, 0, 0xffff); +} + +static inline void msg_set_dest_session(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 1, 0, 0xffff, n); +} /* * Word 2 diff --git a/net/tipc/node.c b/net/tipc/node.c index db2a6c3e0be9..2dc4919ab23c 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -830,15 +830,16 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) tipc_node_write_lock(n); if (!tipc_link_is_establishing(l)) { __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); - if (delete) { - kfree(l); - le->link = NULL; - n->link_cnt--; - } } else { /* Defuse pending tipc_node_link_up() */ + tipc_link_reset(l); tipc_link_fsm_evt(l, LINK_RESET_EVT); } + if (delete) { + kfree(l); + le->link = NULL; + n->link_cnt--; + } trace_tipc_node_link_down(n, true, "node link down or deleted!"); tipc_node_write_unlock(n); if (delete) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1217c90a363b..684f2125fc6b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -388,7 +388,7 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) rc_ = tipc_sk_sock_err((sock_), timeo_); \ if (rc_) \ break; \ - prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \ + add_wait_queue(sk_sleep(sk_), &wait_); \ release_sock(sk_); \ *(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \ sched_annotate_sleep(); \ @@ -1677,7 +1677,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk) static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); long timeo = *timeop; int err = sock_error(sk); @@ -1685,15 +1685,17 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) return err; for (;;) { - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { if (sk->sk_shutdown & RCV_SHUTDOWN) { err = -ENOTCONN; break; } + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + sched_annotate_sleep(); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -1709,7 +1711,6 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) if (err) break; } - finish_wait(sk_sleep(sk), &wait); *timeop = timeo; return err; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 74d1eed7cbd4..a95d479caeea 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -890,7 +890,7 @@ retry: addr->hash ^= sk->sk_type; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(&unix_socket_table[addr->hash], sk); spin_unlock(&unix_table_lock); err = 0; @@ -1060,7 +1060,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = 0; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(list, sk); out_unlock: @@ -1331,15 +1331,29 @@ restart: RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); - /* copy address information from listening to new sock*/ - if (otheru->addr) { - refcount_inc(&otheru->addr->refcnt); - newu->addr = otheru->addr; - } + /* copy address information from listening to new sock + * + * The contents of *(otheru->addr) and otheru->path + * are seen fully set up here, since we have found + * otheru in hash under unix_table_lock. Insertion + * into the hash chain we'd found it in had been done + * in an earlier critical area protected by unix_table_lock, + * the same one where we'd set *(otheru->addr) contents, + * as well as otheru->path and otheru->addr itself. + * + * Using smp_store_release() here to set newu->addr + * is enough to make those stores, as well as stores + * to newu->path visible to anyone who gets newu->addr + * by smp_load_acquire(). IOW, the same warranties + * as for unix_sock instances bound in unix_bind() or + * in unix_autobind(). + */ if (otheru->path.dentry) { path_get(&otheru->path); newu->path = otheru->path; } + refcount_inc(&otheru->addr->refcnt); + smp_store_release(&newu->addr, otheru->addr); /* Set credentials */ copy_peercred(sk, other); @@ -1453,7 +1467,7 @@ out: static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; - struct unix_sock *u; + struct unix_address *addr; DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr); int err = 0; @@ -1468,19 +1482,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) sock_hold(sk); } - u = unix_sk(sk); - unix_state_lock(sk); - if (!u->addr) { + addr = smp_load_acquire(&unix_sk(sk)->addr); + if (!addr) { sunaddr->sun_family = AF_UNIX; sunaddr->sun_path[0] = 0; err = sizeof(short); } else { - struct unix_address *addr = u->addr; - err = addr->len; memcpy(sunaddr, addr->name, addr->len); } - unix_state_unlock(sk); sock_put(sk); out: return err; @@ -2073,11 +2083,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { - struct unix_sock *u = unix_sk(sk); + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); - if (u->addr) { - msg->msg_namelen = u->addr->len; - memcpy(msg->msg_name, u->addr->name, u->addr->len); + if (addr) { + msg->msg_namelen = addr->len; + memcpy(msg->msg_name, addr->name, addr->len); } } @@ -2581,15 +2591,14 @@ static int unix_open_file(struct sock *sk) if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; - unix_state_lock(sk); + if (!smp_load_acquire(&unix_sk(sk)->addr)) + return -ENOENT; + path = unix_sk(sk)->path; - if (!path.dentry) { - unix_state_unlock(sk); + if (!path.dentry) return -ENOENT; - } path_get(&path); - unix_state_unlock(sk); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) @@ -2830,7 +2839,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) (s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING), sock_i_ino(s)); - if (u->addr) { + if (u->addr) { // under unix_table_lock here int i, len; seq_putc(seq, ' '); diff --git a/net/unix/diag.c b/net/unix/diag.c index 384c84e83462..3183d9b8ab33 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -10,7 +10,8 @@ static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb) { - struct unix_address *addr = unix_sk(sk)->addr; + /* might or might not have unix_table_lock */ + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); if (!addr) return 0; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 5d3cce9e8744..15eb5d3d4750 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void) { struct virtio_vsock *vsock = virtio_vsock_get(); + if (!vsock) + return VMADDR_CID_ANY; + return vsock->guest_cid; } @@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) virtio_vsock_update_guest_cid(vsock); - ret = vsock_core_init(&virtio_transport.transport); - if (ret < 0) - goto out_vqs; - vsock->rx_buf_nr = 0; vsock->rx_buf_max_nr = 0; atomic_set(&vsock->queued_replies, 0); @@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_unlock(&the_virtio_vsock_mutex); return 0; -out_vqs: - vsock->vdev->config->del_vqs(vsock->vdev); out: kfree(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -637,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev) flush_work(&vsock->event_work); flush_work(&vsock->send_pkt_work); + /* Reset all connected sockets when the device disappear */ + vsock_for_each_connected_socket(virtio_vsock_reset_sock); + vdev->config->reset(vdev); mutex_lock(&vsock->rx_lock); @@ -669,7 +669,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev) mutex_lock(&the_virtio_vsock_mutex); the_virtio_vsock = NULL; - vsock_core_exit(); mutex_unlock(&the_virtio_vsock_mutex); vdev->config->del_vqs(vdev); @@ -702,14 +701,28 @@ static int __init virtio_vsock_init(void) virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); if (!virtio_vsock_workqueue) return -ENOMEM; + ret = register_virtio_driver(&virtio_vsock_driver); if (ret) - destroy_workqueue(virtio_vsock_workqueue); + goto out_wq; + + ret = vsock_core_init(&virtio_transport.transport); + if (ret) + goto out_vdr; + + return 0; + +out_vdr: + unregister_virtio_driver(&virtio_vsock_driver); +out_wq: + destroy_workqueue(virtio_vsock_workqueue); return ret; + } static void __exit virtio_vsock_exit(void) { + vsock_core_exit(); unregister_virtio_driver(&virtio_vsock_driver); destroy_workqueue(virtio_vsock_workqueue); } diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c361ce782412..c3d5ab01fba7 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1651,6 +1651,10 @@ static void vmci_transport_cleanup(struct work_struct *work) static void vmci_transport_destruct(struct vsock_sock *vsk) { + /* transport can be NULL if we hit a failure at init() time */ + if (!vmci_trans(vsk)) + return; + /* Ensure that the detach callback doesn't use the sk/vsk * we are about to destruct. */ diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 882d97bdc6bf..550ac9d827fe 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -41,6 +41,8 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, cfg80211_sched_dfs_chan_update(rdev); } + schedule_work(&cfg80211_disconnect_work); + return err; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 623dfe5e211c..b36ad8efb5e5 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1068,6 +1068,8 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) ASSERT_RTNL(); + flush_work(&wdev->pmsr_free_wk); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE); list_del_rcu(&wdev->list); diff --git a/net/wireless/core.h b/net/wireless/core.h index c5d6f3418601..f6b40563dc63 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -445,6 +445,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz); +extern struct work_struct cfg80211_disconnect_work; + /** * cfg80211_chandef_dfs_usable - checks if chandef is DFS usable * @wiphy: the wiphy to validate against diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 74150ad95823..d91a408db113 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -250,7 +250,7 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] = NLA_POLICY_MAX(NLA_U8, 15), [NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] = - NLA_POLICY_MAX(NLA_U8, 15), + NLA_POLICY_MAX(NLA_U8, 31), [NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC] = { .type = NLA_FLAG }, diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index de9286703280..0216ab555249 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -256,8 +256,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) if (err) goto out_err; } else { - memcpy(req->mac_addr, nla_data(info->attrs[NL80211_ATTR_MAC]), - ETH_ALEN); + memcpy(req->mac_addr, wdev_address(wdev), ETH_ALEN); memset(req->mac_addr_mask, 0xff, ETH_ALEN); } @@ -272,6 +271,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) req->n_peers = count; req->cookie = cfg80211_assign_cookie(rdev); + req->nl_portid = info->snd_portid; err = rdev_start_pmsr(rdev, wdev, req); if (err) @@ -530,14 +530,14 @@ free: } EXPORT_SYMBOL_GPL(cfg80211_pmsr_report); -void cfg80211_pmsr_free_wk(struct work_struct *work) +static void cfg80211_pmsr_process_abort(struct wireless_dev *wdev) { - struct wireless_dev *wdev = container_of(work, struct wireless_dev, - pmsr_free_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmsr_request *req, *tmp; LIST_HEAD(free_list); + lockdep_assert_held(&wdev->mtx); + spin_lock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &wdev->pmsr_list, list) { if (req->nl_portid) @@ -547,14 +547,22 @@ void cfg80211_pmsr_free_wk(struct work_struct *work) spin_unlock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &free_list, list) { - wdev_lock(wdev); rdev_abort_pmsr(rdev, wdev, req); - wdev_unlock(wdev); kfree(req); } } +void cfg80211_pmsr_free_wk(struct work_struct *work) +{ + struct wireless_dev *wdev = container_of(work, struct wireless_dev, + pmsr_free_wk); + + wdev_lock(wdev); + cfg80211_pmsr_process_abort(wdev); + wdev_unlock(wdev); +} + void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) { struct cfg80211_pmsr_request *req; @@ -568,8 +576,8 @@ void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) spin_unlock_bh(&wdev->pmsr_lock); if (found) - schedule_work(&wdev->pmsr_free_wk); - flush_work(&wdev->pmsr_free_wk); + cfg80211_pmsr_process_abort(wdev); + WARN_ON(!list_empty(&wdev->pmsr_list)); } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f741d8376a46..7d34cb884840 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -667,7 +667,7 @@ static void disconnect_work(struct work_struct *work) rtnl_unlock(); } -static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); +DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); /* diff --git a/net/wireless/util.c b/net/wireless/util.c index cd48cdd582c0..ec30e3732c7b 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,7 +5,7 @@ * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2019 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> @@ -19,6 +19,7 @@ #include <linux/mpls.h> #include <linux/gcd.h> #include <linux/bitfield.h> +#include <linux/nospec.h> #include "core.h" #include "rdev-ops.h" @@ -715,20 +716,25 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, { unsigned int dscp; unsigned char vlan_priority; + unsigned int ret; /* skb->priority values from 256->263 are magic values to * directly indicate a specific 802.1d priority. This is used * to allow 802.1d priority to be passed directly in from VLAN * tags, etc. */ - if (skb->priority >= 256 && skb->priority <= 263) - return skb->priority - 256; + if (skb->priority >= 256 && skb->priority <= 263) { + ret = skb->priority - 256; + goto out; + } if (skb_vlan_tag_present(skb)) { vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - if (vlan_priority > 0) - return vlan_priority; + if (vlan_priority > 0) { + ret = vlan_priority; + goto out; + } } switch (skb->protocol) { @@ -747,8 +753,9 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, if (!mpls) return 0; - return (ntohl(mpls->entry) & MPLS_LS_TC_MASK) + ret = (ntohl(mpls->entry) & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; + goto out; } case htons(ETH_P_80221): /* 802.21 is always network control traffic */ @@ -761,18 +768,24 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, unsigned int i, tmp_dscp = dscp >> 2; for (i = 0; i < qos_map->num_des; i++) { - if (tmp_dscp == qos_map->dscp_exception[i].dscp) - return qos_map->dscp_exception[i].up; + if (tmp_dscp == qos_map->dscp_exception[i].dscp) { + ret = qos_map->dscp_exception[i].up; + goto out; + } } for (i = 0; i < 8; i++) { if (tmp_dscp >= qos_map->up[i].low && - tmp_dscp <= qos_map->up[i].high) - return i; + tmp_dscp <= qos_map->up[i].high) { + ret = i; + goto out; + } } } - return dscp >> 5; + ret = dscp >> 5; +out: + return array_index_nospec(ret, IEEE80211_NUM_TIDS); } EXPORT_SYMBOL(cfg80211_classify8021d); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5121729b8b63..eff31348e20b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -352,17 +352,15 @@ static unsigned int x25_new_lci(struct x25_neigh *nb) unsigned int lci = 1; struct sock *sk; - read_lock_bh(&x25_list_lock); - - while ((sk = __x25_find_socket(lci, nb)) != NULL) { + while ((sk = x25_find_socket(lci, nb)) != NULL) { sock_put(sk); if (++lci == 4096) { lci = 0; break; } + cond_resched(); } - read_unlock_bh(&x25_list_lock); return lci; } @@ -681,8 +679,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr; int len, i, rc = 0; - if (!sock_flag(sk, SOCK_ZAPPED) || - addr_len != sizeof(struct sockaddr_x25) || + if (addr_len != sizeof(struct sockaddr_x25) || addr->sx25_family != AF_X25) { rc = -EINVAL; goto out; @@ -701,9 +698,13 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } lock_sock(sk); - x25_sk(sk)->source_addr = addr->sx25_addr; - x25_insert_socket(sk); - sock_reset_flag(sk, SOCK_ZAPPED); + if (sock_flag(sk, SOCK_ZAPPED)) { + x25_sk(sk)->source_addr = addr->sx25_addr; + x25_insert_socket(sk); + sock_reset_flag(sk, SOCK_ZAPPED); + } else { + rc = -EINVAL; + } release_sock(sk); SOCK_DEBUG(sk, "x25_bind: socket is bound\n"); out: diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index d4de871e7d4d..37e1fe180769 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -125,9 +125,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, return 0; err_unreg_umem: - xdp_clear_umem_at_qid(dev, queue_id); if (!force_zc) err = 0; /* fallback to copy mode */ + if (err) + xdp_clear_umem_at_qid(dev, queue_id); out_rtnl_unlock: rtnl_unlock(); return err; @@ -259,10 +260,10 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem) if (!umem->pgs) return -ENOMEM; - down_write(¤t->mm->mmap_sem); - npgs = get_user_pages(umem->address, umem->npgs, - gup_flags, &umem->pgs[0], NULL); - up_write(¤t->mm->mmap_sem); + down_read(¤t->mm->mmap_sem); + npgs = get_user_pages_longterm(umem->address, umem->npgs, + gup_flags, &umem->pgs[0], NULL); + up_read(¤t->mm->mmap_sem); if (npgs != umem->npgs) { if (npgs >= 0) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index a03268454a27..85e4fe4f18cc 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -366,7 +366,6 @@ static int xsk_release(struct socket *sock) xskq_destroy(xs->rx); xskq_destroy(xs->tx); - xdp_put_umem(xs->umem); sock_orphan(sk); sock->sk = NULL; @@ -669,6 +668,8 @@ static int xsk_mmap(struct file *file, struct socket *sock, if (!umem) return -EINVAL; + /* Matches the smp_wmb() in XDP_UMEM_REG */ + smp_rmb(); if (offset == XDP_UMEM_PGOFF_FILL_RING) q = READ_ONCE(umem->fq); else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) @@ -678,6 +679,8 @@ static int xsk_mmap(struct file *file, struct socket *sock, if (!q) return -EINVAL; + /* Matches the smp_wmb() in xsk_init_queue */ + smp_rmb(); qpg = virt_to_head_page(q->ring); if (size > (PAGE_SIZE << compound_order(qpg))) return -EINVAL; @@ -714,6 +717,18 @@ static const struct proto_ops xsk_proto_ops = { .sendpage = sock_no_sendpage, }; +static void xsk_destruct(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + + if (!sock_flag(sk, SOCK_DEAD)) + return; + + xdp_put_umem(xs->umem); + + sk_refcnt_debug_dec(sk); +} + static int xsk_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -740,6 +755,9 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, sk->sk_family = PF_XDP; + sk->sk_destruct = xsk_destruct; + sk_refcnt_debug_inc(sk); + sock_set_flag(sk, SOCK_RCU_FREE); xs = xdp_sk(sk); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 6be8c7df15bb..dbb3c1945b5c 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -76,10 +76,10 @@ static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb) int ifindex; struct xfrm_if *xi; - if (!skb->dev) + if (!secpath_exists(skb) || !skb->dev) return NULL; - xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id); + xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id); ifindex = skb->dev->ifindex; for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ba0a4048c846..8d1a898d0ba5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3314,8 +3314,10 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (ifcb) { xi = ifcb->decode_session(skb); - if (xi) + if (xi) { if_id = xi->p.if_id; + net = xi->net; + } } rcu_read_unlock(); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 23c92891758a..1bb971f46fc6 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -432,7 +432,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); -static void xfrm_state_gc_destroy(struct xfrm_state *x) +static void ___xfrm_state_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); @@ -474,7 +474,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - xfrm_state_gc_destroy(x); + ___xfrm_state_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -598,14 +598,19 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) } EXPORT_SYMBOL(xfrm_state_alloc); -void __xfrm_state_destroy(struct xfrm_state *x) +void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); + if (sync) { + synchronize_rcu(); + ___xfrm_state_destroy(x); + } else { + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); + } } EXPORT_SYMBOL(__xfrm_state_destroy); @@ -708,7 +713,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) { int i, err = 0, cnt = 0; @@ -730,7 +735,10 @@ restart: err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); - xfrm_state_put(x); + if (sync) + xfrm_state_put_sync(x); + else + xfrm_state_put(x); if (!err) cnt++; @@ -2215,7 +2223,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) if (atomic_read(&t->tunnel_users) == 2) xfrm_state_delete(t); atomic_dec(&t->tunnel_users); - xfrm_state_put(t); + xfrm_state_put_sync(t); x->tunnel = NULL; } } @@ -2375,8 +2383,8 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c6d26afcf89d..a131f9ff979e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1932,7 +1932,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true); + err = xfrm_state_flush(net, p->proto, true, false); if (err) { if (err == -ESRCH) /* empty table */ return 0; |