diff options
author | Jakub Kicinski <kuba@kernel.org> | 2021-06-29 15:45:27 -0700 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2021-06-29 15:45:27 -0700 |
commit | b6df00789e2831fff7a2c65aa7164b2a4dcbe599 (patch) | |
tree | a94cbeeca3f0ae2fffed008cb287c02dbee4dceb /net | |
parent | 3f8ad50a9e43b6a59070e6c9c5eec79626f81095 (diff) | |
parent | a118ff661889ecee3ca90f8125bad8fb5bbc07d5 (diff) | |
download | lwn-b6df00789e2831fff7a2c65aa7164b2a4dcbe599.tar.gz lwn-b6df00789e2831fff7a2c65aa7164b2a4dcbe599.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Trivial conflict in net/netfilter/nf_tables_api.c.
Duplicate fix in tools/testing/selftests/net/devlink_port_split.py
- take the net-next version.
skmsg, and L4 bpf - keep the bpf code but remove the flags
and err params.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
41 files changed, 381 insertions, 241 deletions
diff --git a/net/can/bcm.c b/net/can/bcm.c index e15a7dbe5f6c..508f67de0b80 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -785,6 +785,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, bcm_rx_handler, op); list_del(&op->list); + synchronize_rcu(); bcm_remove_op(op); return 1; /* done */ } @@ -1533,9 +1534,13 @@ static int bcm_release(struct socket *sock) REGMASK(op->can_id), bcm_rx_handler, op); - bcm_remove_op(op); } + synchronize_rcu(); + + list_for_each_entry_safe(op, next, &bo->rx_ops, list) + bcm_remove_op(op); + #if IS_ENABLED(CONFIG_PROC_FS) /* remove procfs entry */ if (net->can.bcmproc_dir && bo->bcm_proc_read) diff --git a/net/can/gw.c b/net/can/gw.c index ba4124805602..d8861e862f15 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -596,6 +596,7 @@ static int cgw_notifier(struct notifier_block *nb, if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); } } @@ -1154,6 +1155,7 @@ static void cgw_remove_all_jobs(struct net *net) hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); } } @@ -1222,6 +1224,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); err = 0; break; diff --git a/net/can/isotp.c b/net/can/isotp.c index 9fd274cf166b..caaa532ece94 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1030,9 +1030,6 @@ static int isotp_release(struct socket *sock) lock_sock(sk); - hrtimer_cancel(&so->txtimer); - hrtimer_cancel(&so->rxtimer); - /* remove current filters & unregister */ if (so->bound && (!(so->opt.flags & CAN_ISOTP_SF_BROADCAST))) { if (so->ifindex) { @@ -1044,10 +1041,14 @@ static int isotp_release(struct socket *sock) SINGLE_MASK(so->rxid), isotp_rcv, sk); dev_put(dev); + synchronize_rcu(); } } } + hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->rxtimer); + so->ifindex = 0; so->bound = 0; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index da3a7a7bcff2..08c8606cfd9c 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -193,6 +193,10 @@ static void j1939_can_rx_unregister(struct j1939_priv *priv) can_rx_unregister(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, j1939_can_recv, priv); + /* The last reference of priv is dropped by the RCU deferred + * j1939_sk_sock_destruct() of the last socket, so we can + * safely drop this reference here. + */ j1939_priv_put(priv); } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index bf18a32dc6ae..54f6d521492f 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -398,6 +398,9 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + + /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ + sock_set_flag(sk, SOCK_RCU_FREE); sk->sk_destruct = j1939_sk_sock_destruct; sk->sk_protocol = CAN_J1939; @@ -673,7 +676,7 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case SO_J1939_FILTER: - if (!sockptr_is_null(optval)) { + if (!sockptr_is_null(optval) && optlen != 0) { struct j1939_filter *f; int c; diff --git a/net/core/dev.c b/net/core/dev.c index d609366da95c..316b4032317e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5304,9 +5304,9 @@ another_round: if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret2; - preempt_disable(); + migrate_disable(); ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); - preempt_enable(); + migrate_enable(); if (ret2 != XDP_PASS) { ret = NET_RX_DROP; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index f0b9decdf279..9b6160a191f8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -399,28 +399,6 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int ret = 0; - - if (sk->sk_shutdown & RCV_SHUTDOWN) - return 1; - - if (!timeo) - return ret; - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - ret = sk_wait_event(sk, &timeo, - !list_empty(&psock->ingress_msg) || - !skb_queue_empty(&sk->sk_receive_queue), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - return ret; -} -EXPORT_SYMBOL_GPL(sk_msg_wait_data); - /* Receive sk_msg from psock->ingress_msg to @msg. */ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags) @@ -600,6 +578,12 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } +static void sock_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + kfree_skb(skb); +} + static void sk_psock_backlog(struct work_struct *work) { struct sk_psock *psock = container_of(work, struct sk_psock, work); @@ -639,7 +623,7 @@ start: /* Hard errors break pipe and stop xmit. */ sk_psock_report_error(psock, ret ? -ret : EPIPE); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); - kfree_skb(skb); + sock_drop(psock->sk, skb); goto end; } off += ret; @@ -730,7 +714,7 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) { skb_bpf_redirect_clear(skb); - kfree_skb(skb); + sock_drop(psock->sk, skb); } __sk_psock_purge_ingress_msg(psock); } @@ -846,7 +830,7 @@ out: } EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); -static void sk_psock_skb_redirect(struct sk_buff *skb) +static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; @@ -856,8 +840,8 @@ static void sk_psock_skb_redirect(struct sk_buff *skb) * return code, but then didn't set a redirect interface. */ if (unlikely(!sk_other)) { - kfree_skb(skb); - return; + sock_drop(from->sk, skb); + return -EIO; } psock_other = sk_psock(sk_other); /* This error indicates the socket is being torn down or had another @@ -865,26 +849,30 @@ static void sk_psock_skb_redirect(struct sk_buff *skb) * a socket that is in this state so we drop the skb. */ if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) { - kfree_skb(skb); - return; + skb_bpf_redirect_clear(skb); + sock_drop(from->sk, skb); + return -EIO; } spin_lock_bh(&psock_other->ingress_lock); if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) { spin_unlock_bh(&psock_other->ingress_lock); - kfree_skb(skb); - return; + skb_bpf_redirect_clear(skb); + sock_drop(from->sk, skb); + return -EIO; } skb_queue_tail(&psock_other->ingress_skb, skb); schedule_work(&psock_other->work); spin_unlock_bh(&psock_other->ingress_lock); + return 0; } -static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict) +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, + struct sk_psock *from, int verdict) { switch (verdict) { case __SK_REDIRECT: - sk_psock_skb_redirect(skb); + sk_psock_skb_redirect(from, skb); break; case __SK_PASS: case __SK_DROP: @@ -908,20 +896,21 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } - sk_psock_tls_verdict_apply(skb, psock->sk, ret); + sk_psock_tls_verdict_apply(skb, psock, ret); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); -static void sk_psock_verdict_apply(struct sk_psock *psock, - struct sk_buff *skb, int verdict) +static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, + int verdict) { struct sock *sk_other; - int err = -EIO; + int err = 0; switch (verdict) { case __SK_PASS: + err = -EIO; sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { @@ -944,18 +933,25 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { skb_queue_tail(&psock->ingress_skb, skb); schedule_work(&psock->work); + err = 0; } spin_unlock_bh(&psock->ingress_lock); + if (err < 0) { + skb_bpf_redirect_clear(skb); + goto out_free; + } } break; case __SK_REDIRECT: - sk_psock_skb_redirect(skb); + err = sk_psock_skb_redirect(psock, skb); break; case __SK_DROP: default: out_free: - kfree_skb(skb); + sock_drop(psock->sk, skb); } + + return err; } static void sk_psock_write_space(struct sock *sk) @@ -987,7 +983,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) sk = strp->sk; psock = sk_psock(sk); if (unlikely(!psock)) { - kfree_skb(skb); + sock_drop(sk, skb); goto out; } prog = READ_ONCE(psock->progs.stream_verdict); @@ -1108,7 +1104,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, psock = sk_psock(sk); if (unlikely(!psock)) { len = 0; - kfree_skb(skb); + sock_drop(sk, skb); goto out; } prog = READ_ONCE(psock->progs.stream_verdict); @@ -1122,7 +1118,8 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } - sk_psock_verdict_apply(psock, skb, ret); + if (sk_psock_verdict_apply(psock, skb, ret) < 0) + len = 0; out: rcu_read_unlock(); return len; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 6f1b82b8ad49..60decd6420ca 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -48,7 +48,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) bpf_map_init_from_attr(&stab->map, attr); raw_spin_lock_init(&stab->lock); - stab->sks = bpf_map_area_alloc(stab->map.max_entries * + stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries * sizeof(struct sock *), stab->map.numa_node); if (!stab->sks) { diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index f5362b9d75eb..f414ad246fdf 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -673,7 +673,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index af8814a11378..a933bd6345b1 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -371,6 +371,8 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; + } else { + swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 66aacb939d3e..99c06944501a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1306,7 +1306,7 @@ INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; mtu = READ_ONCE(dst->dev->mtu); @@ -1315,6 +1315,7 @@ INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = 576; } +out: mtu = min_t(unsigned int, mtu, IP_MAX_MTU); return mtu - lwtunnel_headroom(dst->lwtstate, mtu); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index a80de92ea3b6..f26916a62f25 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -163,6 +163,28 @@ static bool tcp_bpf_stream_read(const struct sock *sk) return !empty; } +static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, + long timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = sk_wait_event(sk, &timeo, + !list_empty(&psock->ingress_msg) || + !skb_queue_empty(&sk->sk_receive_queue), &wait); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -188,7 +210,7 @@ msg_bytes_ready: int data; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, timeo); + data = tcp_msg_wait_data(sk, psock, timeo); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f86ccbf7c135..62682807b4b2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1798,11 +1798,13 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc, if (used <= 0) { if (!copied) copied = used; + kfree_skb(skb); break; } else if (used <= skb->len) { copied += used; } + kfree_skb(skb); if (!desc->count) break; } diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index b07e4b6dda25..45b8782aec0c 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -21,6 +21,45 @@ static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, return udp_prot.recvmsg(sk, msg, len, noblock, flags, addr_len); } +static bool udp_sk_has_data(struct sock *sk) +{ + return !skb_queue_empty(&udp_sk(sk)->reader_queue) || + !skb_queue_empty(&sk->sk_receive_queue); +} + +static bool psock_has_data(struct sk_psock *psock) +{ + return !skb_queue_empty(&psock->ingress_skb) || + !sk_psock_queue_empty(psock); +} + +#define udp_msg_has_data(__sk, __psock) \ + ({ udp_sk_has_data(__sk) || psock_has_data(__psock); }) + +static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock, + long timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = udp_msg_has_data(sk, psock); + if (!ret) { + wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + ret = udp_msg_has_data(sk, psock); + } + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -34,8 +73,7 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(!psock)) return sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - lock_sock(sk); - if (sk_psock_queue_empty(psock)) { + if (!psock_has_data(psock)) { ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); goto out; } @@ -47,9 +85,9 @@ msg_bytes_ready: int data; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, timeo); + data = udp_msg_wait_data(sk, psock, timeo); if (data) { - if (!sk_psock_queue_empty(psock)) + if (psock_has_data(psock)) goto msg_bytes_ready; ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); goto out; @@ -58,7 +96,6 @@ msg_bytes_ready: } ret = copied; out: - release_sock(sk); sk_psock_put(sk, psock); return ret; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 37c4b1726c5e..ed2f061b8768 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -708,7 +708,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 56e479d158b7..26882e165c9e 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -135,18 +135,23 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, len -= 2; while (len > 0) { - int optlen = nh[off + 1] + 2; - int i; + int optlen, i; - switch (nh[off]) { - case IPV6_TLV_PAD1: - optlen = 1; + if (nh[off] == IPV6_TLV_PAD1) { padlen++; if (padlen > 7) goto bad; - break; + off++; + len--; + continue; + } + if (len < 2) + goto bad; + optlen = nh[off + 1] + 2; + if (optlen > len) + goto bad; - case IPV6_TLV_PADN: + if (nh[off] == IPV6_TLV_PADN) { /* RFC 2460 states that the purpose of PadN is * to align the containing header to multiples * of 8. 7 is therefore the highest valid value. @@ -163,12 +168,7 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, if (nh[off + i] != 0) goto bad; } - break; - - default: /* Other TLV code so scan list */ - if (optlen > len) - goto bad; - + } else { tlv_count++; if (tlv_count > max_count) goto bad; @@ -188,7 +188,6 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, return false; padlen = 0; - break; } off += optlen; len -= optlen; @@ -306,7 +305,7 @@ fail_and_free: #endif if (ip6_parse_tlv(tlvprocdestopt_lst, skb, - init_net.ipv6.sysctl.max_dst_opts_cnt)) { + net->ipv6.sysctl.max_dst_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) @@ -1037,7 +1036,7 @@ fail_and_free: opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(tlvprochopopt_lst, skb, - init_net.ipv6.sysctl.max_hbh_opts_cnt)) { + net->ipv6.sysctl.max_hbh_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 0b8a38687ce4..322698d9fcf4 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1240,8 +1240,6 @@ route_lookup: if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; - skb_set_inner_ipproto(skb, proto); - err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) return err; @@ -1378,6 +1376,8 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; + skb_set_inner_ipproto(skb, protocol); + err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, protocol); if (err != 0) { diff --git a/net/mptcp/options.c b/net/mptcp/options.c index a05270996613..b5850afea343 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -942,19 +942,20 @@ reset: return false; } -static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit) +u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq) { - u32 old_ack32, cur_ack32; - - if (use_64bit) - return cur_ack; - - old_ack32 = (u32)old_ack; - cur_ack32 = (u32)cur_ack; - cur_ack = (old_ack & GENMASK_ULL(63, 32)) + cur_ack32; - if (unlikely(before(cur_ack32, old_ack32))) - return cur_ack + (1LL << 32); - return cur_ack; + u32 old_seq32, cur_seq32; + + old_seq32 = (u32)old_seq; + cur_seq32 = (u32)cur_seq; + cur_seq = (old_seq & GENMASK_ULL(63, 32)) + cur_seq32; + if (unlikely(cur_seq32 < old_seq32 && before(old_seq32, cur_seq32))) + return cur_seq + (1LL << 32); + + /* reverse wrap could happen, too */ + if (unlikely(cur_seq32 > old_seq32 && after(old_seq32, cur_seq32))) + return cur_seq - (1LL << 32); + return cur_seq; } static void ack_update_msk(struct mptcp_sock *msk, @@ -972,7 +973,7 @@ static void ack_update_msk(struct mptcp_sock *msk, * more dangerous than missing an ack */ old_snd_una = msk->snd_una; - new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64); + new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64); /* ACK for data not even sent yet? Ignore. */ if (after64(new_snd_una, snd_nxt)) @@ -1009,7 +1010,7 @@ bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool us return false; WRITE_ONCE(msk->rcv_data_fin_seq, - expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit)); + mptcp_expand_seq(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit)); WRITE_ONCE(msk->rcv_data_fin, 1); return true; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7bb82424e551..7a5afa8c6866 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2896,6 +2896,11 @@ static void mptcp_release_cb(struct sock *sk) spin_lock_bh(&sk->sk_lock.slock); } + /* be sure to set the current sk state before tacking actions + * depending on sk_state + */ + if (test_and_clear_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags)) + __mptcp_set_connected(sk); if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags)) __mptcp_clean_una_wakeup(sk); if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags)) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index d8ad3270dfab..426ed80fe72f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -112,6 +112,7 @@ #define MPTCP_ERROR_REPORT 8 #define MPTCP_RETRANSMIT 9 #define MPTCP_WORK_SYNC_SETSOCKOPT 10 +#define MPTCP_CONNECTED 11 static inline bool before64(__u64 seq1, __u64 seq2) { @@ -600,6 +601,7 @@ void mptcp_get_options(const struct sock *sk, struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); +void __mptcp_set_connected(struct sock *sk); static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && @@ -614,6 +616,14 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname, int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option); +u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq); +static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit) +{ + if (use_64bit) + return cur_seq; + + return __mptcp_expand_seq(old_seq, cur_seq); +} void __mptcp_check_push(struct sock *sk, struct sock *ssk); void __mptcp_data_acked(struct sock *sk); void __mptcp_error_report(struct sock *sk); @@ -775,9 +785,6 @@ unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk); unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk); -int mptcp_setsockopt(struct sock *sk, int level, int optname, - sockptr_t optval, unsigned int optlen); - void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_all(struct mptcp_sock *msk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 706a26a1b0fe..66d0b1893d26 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -373,6 +373,24 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; } +void __mptcp_set_connected(struct sock *sk) +{ + if (sk->sk_state == TCP_SYN_SENT) { + inet_sk_state_store(sk, TCP_ESTABLISHED); + sk->sk_state_change(sk); + } +} + +static void mptcp_set_connected(struct sock *sk) +{ + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_set_connected(sk); + else + set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags); + mptcp_data_unlock(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -381,10 +399,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); - if (inet_sk_state_load(parent) == TCP_SYN_SENT) { - inet_sk_state_store(parent, TCP_ESTABLISHED); - parent->sk_state_change(parent); - } /* be sure no special action on any packet other than syn-ack */ if (subflow->conn_finished) @@ -417,6 +431,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->remote_key); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); + mptcp_set_connected(parent); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -457,6 +472,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(mptcp_sk(parent), sk); + mptcp_set_connected(parent); } return; @@ -564,6 +580,7 @@ static void mptcp_sock_destruct(struct sock *sk) static void mptcp_force_close(struct sock *sk) { + /* the msk is not yet exposed to user-space */ inet_sk_state_store(sk, TCP_CLOSE); sk_common_release(sk); } @@ -781,15 +798,6 @@ enum mapping_status { MAPPING_DUMMY }; -static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) -{ - if ((u32)seq == (u32)old_seq) - return old_seq; - - /* Assume map covers data not mapped yet. */ - return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); -} - static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", @@ -995,13 +1003,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_len--; } - if (!mpext->dsn64) { - map_seq = expand_seq(subflow->map_seq, subflow->map_data_len, - mpext->data_seq); - pr_debug("expanded seq=%llu", subflow->map_seq); - } else { - map_seq = mpext->data_seq; - } + map_seq = mptcp_expand_seq(READ_ONCE(msk->ack_seq), mpext->data_seq, mpext->dsn64); WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64); if (subflow->map_valid) { @@ -1592,10 +1594,7 @@ static void subflow_state_change(struct sock *sk) mptcp_rcv_space_init(mptcp_sk(parent), sk); pr_fallback(mptcp_sk(parent)); subflow->conn_finished = 1; - if (inet_sk_state_load(parent) == TCP_SYN_SENT) { - inet_sk_state_store(parent, TCP_ESTABLISHED); - parent->sk_state_change(parent); - } + mptcp_set_connected(parent); } /* as recvmsg() does not acquire the subflow socket for ssk selection diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d6214242fe7f..390d4466567f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -571,7 +571,7 @@ static struct nft_table *nft_table_lookup(const struct net *net, table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && - table->nlpid != nlpid) + nlpid && table->nlpid != nlpid) return ERR_PTR(-EPERM); return table; @@ -583,7 +583,7 @@ static struct nft_table *nft_table_lookup(const struct net *net, static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, - u8 genmask) + u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; @@ -591,8 +591,13 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, nft_net = nft_pernet(net); list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && - nft_active_genmask(table, genmask)) + nft_active_genmask(table, genmask)) { + if (nft_table_has_owner(table) && + nlpid && table->nlpid != nlpid) + return ERR_PTR(-EPERM); + return table; + } } return ERR_PTR(-ENOENT); @@ -1276,7 +1281,8 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_TABLE_HANDLE]) { attr = nla[NFTA_TABLE_HANDLE]; - table = nft_table_lookup_byhandle(net, attr, genmask); + table = nft_table_lookup_byhandle(net, attr, genmask, + NETLINK_CB(skb).portid); } else { attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask, @@ -3237,8 +3243,8 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, struct nft_rule *rule, *old_rule = NULL; struct nft_expr_info *expr_info = NULL; u8 family = info->nfmsg->nfgen_family; + struct nft_flow_rule *flow = NULL; struct net *net = info->net; - struct nft_flow_rule *flow; struct nft_userdata *udata; struct nft_table *table; struct nft_chain *chain; @@ -3333,13 +3339,13 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) { err = -EINVAL; if (nla_type(tmp) != NFTA_LIST_ELEM) - goto err1; + goto err_release_expr; if (n == NFT_RULE_MAXEXPRS) - goto err1; + goto err_release_expr; err = nf_tables_expr_parse(&ctx, tmp, &expr_info[n]); if (err < 0) { NL_SET_BAD_ATTR(extack, tmp); - goto err1; + goto err_release_expr; } size += expr_info[n].ops->size; n++; @@ -3348,7 +3354,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, /* Check for overflow of dlen field */ err = -EFBIG; if (size >= 1 << 12) - goto err1; + goto err_release_expr; if (nla[NFTA_RULE_USERDATA]) { ulen = nla_len(nla[NFTA_RULE_USERDATA]); @@ -3359,7 +3365,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, err = -ENOMEM; rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL); if (rule == NULL) - goto err1; + goto err_release_expr; nft_activate_next(net, rule); @@ -3378,7 +3384,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_newexpr(&ctx, &expr_info[i], expr); if (err < 0) { NL_SET_BAD_ATTR(extack, expr_info[i].attr); - goto err2; + goto err_release_rule; } if (expr_info[i].ops->validate) @@ -3388,16 +3394,24 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, expr = nft_expr_next(expr); } + if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { + flow = nft_flow_rule_create(net, rule); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto err_release_rule; + } + } + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } err = nft_delrule(&ctx, old_rule); if (err < 0) { nft_trans_destroy(trans); - goto err2; + goto err_destroy_flow_rule; } list_add_tail_rcu(&rule->list, &old_rule->list); @@ -3405,7 +3419,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (!trans) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } if (info->nlh->nlmsg_flags & NLM_F_APPEND) { @@ -3423,21 +3437,19 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, kvfree(expr_info); chain->use++; + if (flow) + nft_trans_flow_rule(trans) = flow; + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); - if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { - flow = nft_flow_rule_create(net, rule); - if (IS_ERR(flow)) - return PTR_ERR(flow); - - nft_trans_flow_rule(trans) = flow; - } - return 0; -err2: + +err_destroy_flow_rule: + nft_flow_rule_destroy(flow); +err_release_rule: nf_tables_rule_release(&ctx, rule); -err1: +err_release_expr: for (i = 0; i < n; i++) { if (expr_info[i].ops) { module_put(expr_info[i].ops->type->owner); @@ -8805,11 +8817,16 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_ABORT); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index a48c5fd53a80..b58d73a96523 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -54,15 +54,10 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; - struct nft_offload_ethertype ethertype; - - if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL) && - match->key.basic.n_proto != htons(ETH_P_8021Q) && - match->key.basic.n_proto != htons(ETH_P_8021AD)) - return; - - ethertype.value = match->key.basic.n_proto; - ethertype.mask = match->mask.basic.n_proto; + struct nft_offload_ethertype ethertype = { + .value = match->key.basic.n_proto, + .mask = match->mask.basic.n_proto, + }; if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || @@ -76,7 +71,9 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); - } else { + } else if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC) && + (match->key.basic.n_proto == htons(ETH_P_8021Q) || + match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; @@ -594,23 +591,6 @@ int nft_flow_rule_offload_commit(struct net *net) } } - list_for_each_entry(trans, &nft_net->commit_list, list) { - if (trans->ctx.family != NFPROTO_NETDEV) - continue; - - switch (trans->msg_type) { - case NFT_MSG_NEWRULE: - case NFT_MSG_DELRULE: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) - continue; - - nft_flow_rule_destroy(nft_trans_flow_rule(trans)); - break; - default: - break; - } - } - return err; } diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 4f583d2e220e..af4ee874a067 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -44,6 +44,9 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, unsigned int offset = 0; int err; + if (pkt->skb->protocol != htons(ETH_P_IPV6)) + goto err; + err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); if (priv->flags & NFT_EXTHDR_F_PRESENT) { nft_reg_store8(dest, err >= 0); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index ac61f708b82d..d82677e83400 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -28,6 +28,11 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nf_osf_data data; struct tcphdr _tcph; + if (pkt->tprot != IPPROTO_TCP) { + regs->verdict.code = NFT_BREAK; + return; + } + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); if (!tcp) { diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 18e79c0fd3cf..b5b09a902c7a 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -30,6 +30,12 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr, __be16 tport = 0; struct sock *sk; + if (pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) { + regs->verdict.code = NFT_BREAK; + return; + } + hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (!hp) { regs->verdict.code = NFT_BREAK; @@ -91,7 +97,8 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, memset(&taddr, 0, sizeof(taddr)); - if (!pkt->tprot_set) { + if (pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) { regs->verdict.code = NFT_BREAK; return; } diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index c4007b9cd16d..5b274534264c 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -304,7 +304,7 @@ static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) int i, err = 0; cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!cp->perfect) return -ENOMEM; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 1db9d4a2ef5e..b692a0de1ad5 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -485,11 +485,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl->qdisc != &noop_qdisc) qdisc_hash_add(cl->qdisc, true); - sch_tree_lock(sch); - qdisc_class_hash_insert(&q->clhash, &cl->common); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); set_change_agg: sch_tree_lock(sch); @@ -507,8 +502,11 @@ set_change_agg: } if (existing) qfq_deact_rm_from_agg(q, cl); + else + qdisc_class_hash_insert(&q->clhash, &cl->common); qfq_add_to_agg(q, new_agg, cl); sch_tree_unlock(sch); + qdisc_class_hash_grow(sch, &q->clhash); *arg = (unsigned long)cl; return 0; diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 53e5ed79f63f..59e653b528b1 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -270,22 +270,19 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list, rawaddr = (union sctp_addr_param *)raw_addr_list; af = sctp_get_af_specific(param_type2af(param->type)); - if (unlikely(!af)) { + if (unlikely(!af) || + !af->from_addr_param(&addr, rawaddr, htons(port), 0)) { retval = -EINVAL; - sctp_bind_addr_clean(bp); - break; + goto out_err; } - af->from_addr_param(&addr, rawaddr, htons(port), 0); if (sctp_bind_addr_state(bp, &addr) != -1) goto next; retval = sctp_add_bind_addr(bp, &addr, sizeof(addr), SCTP_ADDR_SRC, gfp); - if (retval) { + if (retval) /* Can't finish building the list, clean up. */ - sctp_bind_addr_clean(bp); - break; - } + goto out_err; next: len = ntohs(param->length); @@ -294,6 +291,12 @@ next: } return retval; + +out_err: + if (retval) + sctp_bind_addr_clean(bp); + + return retval; } /******************************************************************** diff --git a/net/sctp/input.c b/net/sctp/input.c index 76dcc137f761..02e73264e81e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -1155,7 +1155,8 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, if (!af) continue; - af->from_addr_param(paddr, params.addr, sh->source, 0); + if (!af->from_addr_param(paddr, params.addr, sh->source, 0)) + continue; asoc = __sctp_lookup_association(net, laddr, paddr, transportp); if (asoc) @@ -1191,6 +1192,9 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( union sctp_addr_param *param; union sctp_addr paddr; + if (ntohs(ch->length) < sizeof(*asconf) + sizeof(struct sctp_paramhdr)) + return NULL; + /* Skip over the ADDIP header and find the Address parameter */ param = (union sctp_addr_param *)(asconf + 1); @@ -1198,7 +1202,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (unlikely(!af)) return NULL; - af->from_addr_param(&paddr, param, peer_port, 0); + if (af->from_addr_param(&paddr, param, peer_port, 0)) + return NULL; return __sctp_lookup_association(net, laddr, &paddr, transportp); } @@ -1269,7 +1274,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, ch = (struct sctp_chunkhdr *)ch_end; chunk_num++; - } while (ch_end < skb_tail_pointer(skb)); + } while (ch_end + sizeof(*ch) < skb_tail_pointer(skb)); return asoc; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index d041bed86322..e48dd909dee5 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -577,15 +577,20 @@ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk) } /* Initialize a sctp_addr from an address parameter. */ -static void sctp_v6_from_addr_param(union sctp_addr *addr, +static bool sctp_v6_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { + if (ntohs(param->v6.param_hdr.length) < sizeof(struct sctp_ipv6addr_param)) + return false; + addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = port; addr->v6.sin6_flowinfo = 0; /* BUG */ addr->v6.sin6_addr = param->v6.addr; addr->v6.sin6_scope_id = iif; + + return true; } /* Initialize an address parameter from a sctp_addr and return the length diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index bc5db0b404ce..3c1fbf38f4f7 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -254,14 +254,19 @@ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk) } /* Initialize a sctp_addr from an address parameter. */ -static void sctp_v4_from_addr_param(union sctp_addr *addr, +static bool sctp_v4_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { + if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param)) + return false; + addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); + + return true; } /* Initialize an address parameter from a sctp_addr and return the length diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index b0eaa93a9cc6..6c08e5048d38 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2195,9 +2195,16 @@ static enum sctp_ierror sctp_verify_param(struct net *net, break; case SCTP_PARAM_SET_PRIMARY: - if (ep->asconf_enable) - break; - goto unhandled; + if (!ep->asconf_enable) + goto unhandled; + + if (ntohs(param.p->length) < sizeof(struct sctp_addip_param) + + sizeof(struct sctp_paramhdr)) { + sctp_process_inv_paramlength(asoc, param.p, + chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + } + break; case SCTP_PARAM_HOST_NAME_ADDRESS: /* Tell the peer, we won't support this param. */ @@ -2375,11 +2382,13 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, /* Process the initialization parameters. */ sctp_walk_params(param, peer_init, init_hdr.params) { - if (!src_match && (param.p->type == SCTP_PARAM_IPV4_ADDRESS || - param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { + if (!src_match && + (param.p->type == SCTP_PARAM_IPV4_ADDRESS || + param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { af = sctp_get_af_specific(param_type2af(param.p->type)); - af->from_addr_param(&addr, param.addr, - chunk->sctp_hdr->source, 0); + if (!af->from_addr_param(&addr, param.addr, + chunk->sctp_hdr->source, 0)) + continue; if (sctp_cmp_addr_exact(sctp_source(chunk), &addr)) src_match = 1; } @@ -2560,7 +2569,8 @@ static int sctp_process_param(struct sctp_association *asoc, break; do_addr_param: af = sctp_get_af_specific(param_type2af(param.p->type)); - af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0)) + break; scope = sctp_scope(peer_addr); if (sctp_in_scope(net, &addr, scope)) if (!sctp_assoc_add_peer(asoc, &addr, gfp, SCTP_UNCONFIRMED)) @@ -2661,15 +2671,13 @@ do_addr_param: addr_param = param.v + sizeof(struct sctp_addip_param); af = sctp_get_af_specific(param_type2af(addr_param->p.type)); - if (af == NULL) + if (!af) break; - af->from_addr_param(&addr, addr_param, - htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, addr_param, + htons(asoc->peer.port), 0)) + break; - /* if the address is invalid, we can't process it. - * XXX: see spec for what to do. - */ if (!af->addr_valid(&addr, NULL, NULL)) break; @@ -3083,7 +3091,8 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, if (unlikely(!af)) return SCTP_ERROR_DNS_FAILED; - af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0)) + return SCTP_ERROR_DNS_FAILED; /* ADDIP 4.2.1 This parameter MUST NOT contain a broadcast * or multicast address. @@ -3360,7 +3369,8 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, /* We have checked the packet before, so we do not check again. */ af = sctp_get_af_specific(param_type2af(addr_param->p.type)); - af->from_addr_param(&addr, addr_param, htons(bp->port), 0); + if (!af->from_addr_param(&addr, addr_param, htons(bp->port), 0)) + return; switch (asconf_param->param_hdr.type) { case SCTP_PARAM_ADD_IP: diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index f0fbb079cbaa..4feb95e34b64 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1153,7 +1153,7 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, int ret = 0; bool eor; - eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST)); + eor = !(flags & MSG_SENDPAGE_NOTLAST); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* Call the sk_stream functions to manage the sndbuf mem. */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9f12da1ff406..3e02cc3b24f8 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1395,7 +1395,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, if (signal_pending(current)) { err = sock_intr_errno(timeout); - sk->sk_state = TCP_CLOSE; + sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 9d2a89d793c0..9ae13cccfb28 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -128,12 +128,15 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 chunk; - - if (desc->len > pool->chunk_size) - return false; + u64 chunk, chunk_end; chunk = xp_aligned_extract_addr(pool, desc->addr); + if (likely(desc->len)) { + chunk_end = xp_aligned_extract_addr(pool, desc->addr + desc->len - 1); + if (chunk != chunk_end) + return false; + } + if (chunk >= pool->addrs_cnt) return false; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 6d6917b68856..e843b0d9e2a6 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -268,6 +268,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, xso->num_exthdrs = 0; xso->flags = 0; xso->dev = NULL; + xso->real_dev = NULL; dev_put(dev); if (err != -EOPNOTSUPP) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index ab2fbe432261..229544bc70c2 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -827,15 +827,8 @@ out: static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) - unsigned int ptr = 0; int err; - if (x->outer_mode.encap == XFRM_MODE_BEET && - ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL) >= 0) { - net_warn_ratelimited("BEET mode doesn't support inner IPv6 fragments\n"); - return -EAFNOSUPPORT; - } - err = xfrm6_tunnel_check_size(skb); if (err) return err; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1e24b21457f7..837df4b5c1bc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2092,12 +2092,15 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (unlikely(!daddr || !saddr)) return NULL; - rcu_read_lock(); retry: - do { - sequence = read_seqcount_begin(&xfrm_policy_hash_generation); - chain = policy_hash_direct(net, daddr, saddr, family, dir); - } while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)); + sequence = read_seqcount_begin(&xfrm_policy_hash_generation); + rcu_read_lock(); + + chain = policy_hash_direct(net, daddr, saddr, family, dir); + if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { + rcu_read_unlock(); + goto retry; + } ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { @@ -2128,11 +2131,15 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } skip_inexact: - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) + if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { + rcu_read_unlock(); goto retry; + } - if (ret && !xfrm_pol_hold_rcu(ret)) + if (ret && !xfrm_pol_hold_rcu(ret)) { + rcu_read_unlock(); goto retry; + } fail: rcu_read_unlock(); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index c2ce1e6f4760..a2f4001221d1 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2550,7 +2550,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_delete_tunnel); -u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) +u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; @@ -2581,7 +2581,17 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - net_adj) & ~(blksize - 1)) + net_adj - 2; } -EXPORT_SYMBOL_GPL(xfrm_state_mtu); +EXPORT_SYMBOL_GPL(__xfrm_state_mtu); + +u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) +{ + mtu = __xfrm_state_mtu(x, mtu); + + if (x->props.family == AF_INET6 && mtu < IPV6_MIN_MTU) + return IPV6_MIN_MTU; + + return mtu; +} int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index f0aecee4d539..b47d613409b7 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -580,6 +580,20 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, copy_from_user_state(x, p); + if (attrs[XFRMA_ENCAP]) { + x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), + sizeof(*x->encap), GFP_KERNEL); + if (x->encap == NULL) + goto error; + } + + if (attrs[XFRMA_COADDR]) { + x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), + sizeof(*x->coaddr), GFP_KERNEL); + if (x->coaddr == NULL) + goto error; + } + if (attrs[XFRMA_SA_EXTRA_FLAGS]) x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]); @@ -600,23 +614,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, attrs[XFRMA_ALG_COMP]))) goto error; - if (attrs[XFRMA_ENCAP]) { - x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), - sizeof(*x->encap), GFP_KERNEL); - if (x->encap == NULL) - goto error; - } - if (attrs[XFRMA_TFCPAD]) x->tfcpad = nla_get_u32(attrs[XFRMA_TFCPAD]); - if (attrs[XFRMA_COADDR]) { - x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), - sizeof(*x->coaddr), GFP_KERNEL); - if (x->coaddr == NULL) - goto error; - } - xfrm_mark_get(attrs, &x->mark); xfrm_smark_init(attrs, &x->props.smark); |