diff options
Diffstat (limited to '')
41 files changed, 363 insertions, 335 deletions
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 7a54dc11ac2d..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); 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/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/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/ip_gre.c b/net/ipv4/ip_gre.c index 3978f807fa8b..6ae89f2b541b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1457,9 +1457,23 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if ((t->erspan_ver == 1 || t->erspan_ver == 2) && - !t->collect_md) - o_flags |= TUNNEL_KEY; + 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, @@ -1495,19 +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/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/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 801a9a0c217e..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) @@ -2100,9 +2107,23 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct __ip6_tnl_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if ((p->erspan_ver == 1 || p->erspan_ver == 2) && - !p->collect_md) - o_flags |= TUNNEL_KEY; + 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, @@ -2117,8 +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, @@ -2136,19 +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: @@ -2203,6 +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) { @@ -2248,6 +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/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/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/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/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 86afacb07e5f..ac8d848d7624 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -896,12 +896,13 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, { struct ip_vs_dest *dest; unsigned int atype, i; - int ret = 0; EnterFunction(2); #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) && diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5a92f23f179f..4893f248dfdc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -313,6 +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; 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/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/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/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/x25/af_x25.c b/net/x25/af_x25.c index ec3a828672ef..eff31348e20b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -679,8 +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; @@ -699,9 +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; |