diff options
Diffstat (limited to 'net')
79 files changed, 858 insertions, 248 deletions
diff --git a/net/802/garp.c b/net/802/garp.c index 400bd857e5f5..f6012f8e59f0 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -203,6 +203,19 @@ static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr kfree(attr); } +static void garp_attr_destroy_all(struct garp_applicant *app) +{ + struct rb_node *node, *next; + struct garp_attr *attr; + + for (node = rb_first(&app->gid); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct garp_attr, node); + garp_attr_destroy(app, attr); + } +} + static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; @@ -609,6 +622,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); + garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); diff --git a/net/802/mrp.c b/net/802/mrp.c index bea6e43d45a0..35e04cc5390c 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -292,6 +292,19 @@ static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr) kfree(attr); } +static void mrp_attr_destroy_all(struct mrp_applicant *app) +{ + struct rb_node *node, *next; + struct mrp_attr *attr; + + for (node = rb_first(&app->mad); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct mrp_attr, node); + mrp_attr_destroy(app, attr); + } +} + static int mrp_pdu_init(struct mrp_applicant *app) { struct sk_buff *skb; @@ -895,6 +908,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); + mrp_attr_destroy_all(app); mrp_pdu_queue(app); spin_unlock_bh(&app->lock); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index aa47af349ba8..1cc75c811e24 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -701,6 +701,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret; + if (prog->expected_attach_type == BPF_XDP_DEVMAP || + prog->expected_attach_type == BPF_XDP_CPUMAP) + return -EINVAL; if (kattr->test.ctx_in || kattr->test.ctx_out) return -EINVAL; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 2b862cffc03a..a16191dcaed1 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -780,7 +780,7 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, struct net_device *dst_dev; dst_dev = dst ? dst->dev : br->dev; - if (dst_dev != br_dev && dst_dev != dev) + if (dst_dev && dst_dev != dev) continue; err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f7d2f472ae24..6e4a32354a13 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -562,7 +562,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, struct net_bridge_port *p; int err = 0; unsigned br_hr, dev_hr; - bool changed_addr; + bool changed_addr, fdb_synced = false; /* Don't allow bridging non-ethernet like devices. */ if ((dev->flags & IFF_LOOPBACK) || @@ -652,6 +652,19 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, list_add_rcu(&p->list, &br->port_list); nbp_update_port_count(br); + if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) { + /* When updating the port count we also update all ports' + * promiscuous mode. + * A port leaving promiscuous mode normally gets the bridge's + * fdb synced to the unicast filter (if supported), however, + * `br_port_clear_promisc` does not distinguish between + * non-promiscuous ports and *new* ports, so we need to + * sync explicitly here. + */ + fdb_synced = br_fdb_sync_static(br, p) == 0; + if (!fdb_synced) + netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n"); + } netdev_update_features(br->dev); @@ -701,6 +714,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, return 0; err7: + if (fdb_synced) + br_fdb_unsync_static(br, p); list_del_rcu(&p->list); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 53c3a9d80d9c..d0434dc8c03b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3264,7 +3264,9 @@ static void br_multicast_pim(struct net_bridge *br, pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; + spin_lock(&br->multicast_lock); br_ip4_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); } static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, @@ -3275,7 +3277,9 @@ static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, igmp_hdr(skb)->type != IGMP_MRDISC_ADV) return -ENOMSG; + spin_lock(&br->multicast_lock); br_ip4_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); return 0; } @@ -3343,7 +3347,9 @@ static void br_ip6_multicast_mrd_rcv(struct net_bridge *br, if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) return; + spin_lock(&br->multicast_lock); br_ip6_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); } static int br_multicast_ipv6_rcv(struct net_bridge *br, diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 647554c9813b..e12fd3cad619 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -539,7 +539,8 @@ static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg, goto err; ret = -EINVAL; - if (unlikely(msg->msg_iter.iov->iov_base == NULL)) + if (unlikely(msg->msg_iter.nr_segs == 0) || + unlikely(msg->msg_iter.iov->iov_base == NULL)) goto err; noblock = msg->msg_flags & MSG_DONTWAIT; diff --git a/net/core/dev.c b/net/core/dev.c index c253c2aafe97..8f1a47ad6781 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -131,6 +131,7 @@ #include <trace/events/napi.h> #include <trace/events/net.h> #include <trace/events/skb.h> +#include <trace/events/qdisc.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> #include <linux/static_key.h> @@ -3844,6 +3845,18 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) } } +static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q, + struct sk_buff **to_free, + struct netdev_queue *txq) +{ + int rc; + + rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK; + if (rc == NET_XMIT_SUCCESS) + trace_qdisc_enqueue(q, txq, skb); + return rc; +} + static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) @@ -3862,8 +3875,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * of q->seqlock to protect from racing with requeuing. */ if (unlikely(!nolock_qdisc_is_empty(q))) { - rc = q->enqueue(skb, q, &to_free) & - NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); __qdisc_run(q); qdisc_run_end(q); @@ -3879,7 +3891,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return NET_XMIT_SUCCESS; } - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); qdisc_run(q); no_lock_out: @@ -3923,7 +3935,7 @@ no_lock_out: qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -6008,6 +6020,19 @@ static void gro_list_prepare(const struct list_head *head, diffs = memcmp(skb_mac_header(p), skb_mac_header(skb), maclen); + + diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); +#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + if (!diffs) { + struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT); + struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT); + + diffs |= (!!p_ext) ^ (!!skb_ext); + if (!diffs && unlikely(skb_ext)) + diffs |= p_ext->chain ^ skb_ext->chain; + } +#endif + NAPI_GRO_CB(p)->same_flow = !diffs; } } @@ -6221,6 +6246,8 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi, case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); + else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) + __kfree_skb(skb); else __kfree_skb_defer(skb); break; @@ -6270,6 +6297,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); skb_ext_reset(skb); + nf_reset_ct(skb); napi->skb = skb; } @@ -9684,14 +9712,17 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) struct net_device *dev; int err, fd; + rtnl_lock(); dev = dev_get_by_index(net, attr->link_create.target_ifindex); - if (!dev) + if (!dev) { + rtnl_unlock(); return -EINVAL; + } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; - goto out_put_dev; + goto unlock; } bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog); @@ -9701,14 +9732,14 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); - goto out_put_dev; + goto unlock; } - rtnl_lock(); err = dev_xdp_attach_link(dev, NULL, link); rtnl_unlock(); if (err) { + link->dev = NULL; bpf_link_cleanup(&link_primer); goto out_put_dev; } @@ -9718,6 +9749,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) dev_put(dev); return fd; +unlock: + rtnl_unlock(); + out_put_dev: dev_put(dev); return err; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 12aabcda6db2..fc7942c0dddc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -663,7 +663,7 @@ static void skb_release_data(struct sk_buff *skb) if (skb->cloned && atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, &shinfo->dataref)) - return; + goto exit; skb_zcopy_clear(skb, true); @@ -674,6 +674,17 @@ static void skb_release_data(struct sk_buff *skb) kfree_skb_list(shinfo->frag_list); skb_free_head(skb); +exit: + /* When we clone an SKB we copy the reycling bit. The pp_recycle + * bit is only set on the head though, so in order to avoid races + * while trying to recycle fragments on __skb_frag_unref() we need + * to make one SKB responsible for triggering the recycle path. + * So disable the recycling bit if an SKB is cloned and we have + * additional references to to the fragmented part of the SKB. + * Eventually the last SKB will have the recycling bit set and it's + * dataref set to 0, which will trigger the recycling + */ + skb->pp_recycle = 0; } /* @@ -943,6 +954,7 @@ void __kfree_skb_defer(struct sk_buff *skb) void napi_skb_free_stolen_head(struct sk_buff *skb) { + nf_reset_ct(skb); skb_dst_drop(skb); skb_ext_put(skb); napi_skb_cache_put(skb); @@ -3010,8 +3022,11 @@ skb_zerocopy_headlen(const struct sk_buff *from) if (!from->head_frag || skb_headlen(from) < L1_CACHE_BYTES || - skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) { hlen = skb_headlen(from); + if (!hlen) + hlen = from->len; + } if (skb_has_frag_list(from)) hlen = from->len; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 9b6160a191f8..15d71288e741 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -508,10 +508,8 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, if (skb_linearize(skb)) return -EAGAIN; num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); - if (unlikely(num_sge < 0)) { - kfree(msg); + if (unlikely(num_sge < 0)) return num_sge; - } copied = skb->len; msg->sg.start = 0; @@ -530,6 +528,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) { struct sock *sk = psock->sk; struct sk_msg *msg; + int err; /* If we are receiving on the same sock skb->sk is already assigned, * skip memory accounting and owner transition seeing it already set @@ -548,7 +547,10 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * into user buffers. */ skb_set_owner_r(skb, sk); - return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + if (err < 0) + kfree(msg); + return err; } /* Puts an skb on the ingress queue of the socket already assigned to the @@ -559,12 +561,16 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb { struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); struct sock *sk = psock->sk; + int err; if (unlikely(!msg)) return -EAGAIN; sk_msg_init(msg); skb_set_owner_r(skb, sk); - return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + if (err < 0) + kfree(msg); + return err; } static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, diff --git a/net/core/sock.c b/net/core/sock.c index ba1c0f75cd45..a3eea6e0b30a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,6 +139,8 @@ #include <net/tcp.h> #include <net/busy_poll.h> +#include <linux/ethtool.h> + static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); @@ -810,8 +812,47 @@ void sock_set_timestamp(struct sock *sk, int optname, bool valbool) } } -int sock_set_timestamping(struct sock *sk, int optname, int val) +static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) +{ + struct net *net = sock_net(sk); + struct net_device *dev = NULL; + bool match = false; + int *vclock_index; + int i, num; + + if (sk->sk_bound_dev_if) + dev = dev_get_by_index(net, sk->sk_bound_dev_if); + + if (!dev) { + pr_err("%s: sock not bind to device\n", __func__); + return -EOPNOTSUPP; + } + + num = ethtool_get_phc_vclocks(dev, &vclock_index); + for (i = 0; i < num; i++) { + if (*(vclock_index + i) == phc_index) { + match = true; + break; + } + } + + if (num > 0) + kfree(vclock_index); + + if (!match) + return -EINVAL; + + sk->sk_bind_phc = phc_index; + + return 0; +} + +int sock_set_timestamping(struct sock *sk, int optname, + struct so_timestamping timestamping) { + int val = timestamping.flags; + int ret; + if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; @@ -832,6 +873,12 @@ int sock_set_timestamping(struct sock *sk, int optname, int val) !(val & SOF_TIMESTAMPING_OPT_TSONLY)) return -EINVAL; + if (val & SOF_TIMESTAMPING_BIND_PHC) { + ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc); + if (ret) + return ret; + } + sk->sk_tsflags = val; sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); @@ -907,6 +954,7 @@ EXPORT_SYMBOL(sock_set_mark); int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct so_timestamping timestamping; struct sock_txtime sk_txtime; struct sock *sk = sock->sk; int val; @@ -1068,12 +1116,22 @@ set_sndbuf: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: - sock_set_timestamp(sk, valbool, optname); + sock_set_timestamp(sk, optname, valbool); break; case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: - ret = sock_set_timestamping(sk, optname, val); + if (optlen == sizeof(timestamping)) { + if (copy_from_sockptr(×tamping, optval, + sizeof(timestamping))) { + ret = -EFAULT; + break; + } + } else { + memset(×tamping, 0, sizeof(timestamping)); + timestamping.flags = val; + } + ret = sock_set_timestamping(sk, optname, timestamping); break; case SO_RCVLOWAT: @@ -1201,7 +1259,7 @@ set_sndbuf: if (val < 0) ret = -EINVAL; else - sk->sk_ll_usec = val; + WRITE_ONCE(sk->sk_ll_usec, val); } break; case SO_PREFER_BUSY_POLL: @@ -1348,6 +1406,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; + struct so_timestamping timestamping; } v; int lv = sizeof(int); @@ -1451,7 +1510,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_TIMESTAMPING_OLD: - v.val = sk->sk_tsflags; + lv = sizeof(v.timestamping); + v.timestamping.flags = sk->sk_tsflags; + v.timestamping.bind_phc = sk->sk_bind_phc; break; case SO_RCVTIMEO_OLD: diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 5dbd45dc35ad..dc92a67baea3 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -816,7 +816,7 @@ static int dn_auto_bind(struct socket *sock) static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) { struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err; if (scp->state != DN_CR) @@ -826,11 +826,11 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) scp->segsize_loc = dst_metric_advmss(__sk_dst_get(sk)); dn_send_conn_conf(sk, allocation); - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); for(;;) { release_sock(sk); if (scp->state == DN_CC) - *timeo = schedule_timeout(*timeo); + *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); lock_sock(sk); err = 0; if (scp->state == DN_RUN) @@ -844,9 +844,8 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) err = -EAGAIN; if (!*timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); if (err == 0) { sk->sk_socket->state = SS_CONNECTED; } else if (scp->state != DN_CC) { @@ -858,7 +857,7 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) static int dn_wait_run(struct sock *sk, long *timeo) { struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err = 0; if (scp->state == DN_RUN) @@ -867,11 +866,11 @@ static int dn_wait_run(struct sock *sk, long *timeo) if (!*timeo) return -EALREADY; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); for(;;) { release_sock(sk); if (scp->state == DN_CI || scp->state == DN_CC) - *timeo = schedule_timeout(*timeo); + *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); lock_sock(sk); err = 0; if (scp->state == DN_RUN) @@ -885,9 +884,8 @@ static int dn_wait_run(struct sock *sk, long *timeo) err = -ETIMEDOUT; if (!*timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); out: if (err == 0) { sk->sk_socket->state = SS_CONNECTED; @@ -1032,16 +1030,16 @@ static void dn_user_copy(struct sk_buff *skb, struct optdata_dn *opt) static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) { - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sk_buff *skb = NULL; int err = 0; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); for(;;) { release_sock(sk); skb = skb_dequeue(&sk->sk_receive_queue); if (skb == NULL) { - *timeo = schedule_timeout(*timeo); + *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); skb = skb_dequeue(&sk->sk_receive_queue); } lock_sock(sk); @@ -1056,9 +1054,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) err = -EAGAIN; if (!*timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); return skb == NULL ? ERR_PTR(err) : skb; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index ffbba1e71551..532085da8d8f 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1808,6 +1808,7 @@ void dsa_slave_setup_tagger(struct net_device *slave) struct dsa_slave_priv *p = netdev_priv(slave); const struct dsa_port *cpu_dp = dp->cpu_dp; struct net_device *master = cpu_dp->master; + const struct dsa_switch *ds = dp->ds; slave->needed_headroom = cpu_dp->tag_ops->needed_headroom; slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; @@ -1819,6 +1820,14 @@ void dsa_slave_setup_tagger(struct net_device *slave) slave->needed_tailroom += master->needed_tailroom; p->xmit = cpu_dp->tag_ops->xmit; + + slave->features = master->vlan_features | NETIF_F_HW_TC; + if (ds->ops->port_vlan_add && ds->ops->port_vlan_del) + slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + slave->hw_features |= NETIF_F_HW_TC; + slave->features |= NETIF_F_LLTX; + if (slave->needed_tailroom) + slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); } static struct lock_class_key dsa_slave_netdev_xmit_lock_key; @@ -1881,11 +1890,6 @@ int dsa_slave_create(struct dsa_port *port) if (slave_dev == NULL) return -ENOMEM; - slave_dev->features = master->vlan_features | NETIF_F_HW_TC; - if (ds->ops->port_vlan_add && ds->ops->port_vlan_del) - slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - slave_dev->hw_features |= NETIF_F_HW_TC; - slave_dev->features |= NETIF_F_LLTX; slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; if (!is_zero_ether_addr(port->mac)) ether_addr_copy(slave_dev->dev_addr, port->mac); diff --git a/net/dsa/switch.c b/net/dsa/switch.c index af71b8638098..5ece05dfd8f2 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -113,11 +113,11 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, int err, port; if (dst->index == info->tree_index && ds->index == info->sw_index && - ds->ops->port_bridge_join) + ds->ops->port_bridge_leave) ds->ops->port_bridge_leave(ds, info->port, info->br); if ((dst->index != info->tree_index || ds->index != info->sw_index) && - ds->ops->crosschip_bridge_join) + ds->ops->crosschip_bridge_leave) ds->ops->crosschip_bridge_leave(ds, info->tree_index, info->sw_index, info->port, info->br); @@ -427,7 +427,7 @@ static int dsa_switch_lag_join(struct dsa_switch *ds, info->port, info->lag, info->info); - return 0; + return -EOPNOTSUPP; } static int dsa_switch_lag_leave(struct dsa_switch *ds, @@ -440,7 +440,7 @@ static int dsa_switch_lag_leave(struct dsa_switch *ds, return ds->ops->crosschip_lag_leave(ds, info->sw_index, info->port, info->lag); - return 0; + return -EOPNOTSUPP; } static int dsa_switch_mdb_add(struct dsa_switch *ds, diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 53565f48934c..a201ccf2435d 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -53,6 +53,9 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) u8 *tag; u8 *addr; + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(skb); @@ -114,6 +117,9 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, u8 *addr; u16 val; + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN); addr = skb_mac_header(skb); @@ -164,6 +170,9 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, u8 *addr; u8 *tag; + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(skb); diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 723c9a8a8cdf..0a19470efbfb 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ - tunnels.o fec.o eeprom.o stats.o + tunnels.o fec.o eeprom.o stats.o phc_vclocks.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c index f9dcbad84788..c63e0739dc6a 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -4,6 +4,7 @@ #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/rtnetlink.h> +#include <linux/ptp_clock_kernel.h> #include "common.h" @@ -397,6 +398,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = { [const_ilog2(SOF_TIMESTAMPING_OPT_STATS)] = "option-stats", [const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo", [const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw", + [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc", }; static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT); @@ -554,6 +556,18 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) return 0; } +int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index) +{ + struct ethtool_ts_info info = { }; + int num = 0; + + if (!__ethtool_get_ts_info(dev, &info)) + num = ptp_get_vclocks_index(info.phc_index, vclock_index); + + return num; +} +EXPORT_SYMBOL(ethtool_get_phc_vclocks); + const struct ethtool_phy_ops *ethtool_phy_ops; void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops) diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index a7346346114f..73e0f5b626bf 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -248,6 +248,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops, [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, + [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -958,6 +959,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_stats_get_policy, .maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_phc_vclocks_get_policy, + .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 3e25a47fd482..3fc395c86702 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -347,6 +347,7 @@ extern const struct ethnl_request_ops ethnl_tsinfo_request_ops; extern const struct ethnl_request_ops ethnl_fec_request_ops; extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops; extern const struct ethnl_request_ops ethnl_stats_request_ops; +extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -382,6 +383,7 @@ extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1]; extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; +extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/phc_vclocks.c b/net/ethtool/phc_vclocks.c new file mode 100644 index 000000000000..637b2f5297d5 --- /dev/null +++ b/net/ethtool/phc_vclocks.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 NXP + */ +#include "netlink.h" +#include "common.h" + +struct phc_vclocks_req_info { + struct ethnl_req_info base; +}; + +struct phc_vclocks_reply_data { + struct ethnl_reply_data base; + int num; + int *index; +}; + +#define PHC_VCLOCKS_REPDATA(__reply_base) \ + container_of(__reply_base, struct phc_vclocks_reply_data, base) + +const struct nla_policy ethnl_phc_vclocks_get_policy[] = { + [ETHTOOL_A_PHC_VCLOCKS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + data->num = ethtool_get_phc_vclocks(dev, &data->index); + ethnl_ops_complete(dev); + + return ret; +} + +static int phc_vclocks_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct phc_vclocks_reply_data *data = + PHC_VCLOCKS_REPDATA(reply_base); + int len = 0; + + if (data->num > 0) { + len += nla_total_size(sizeof(u32)); + len += nla_total_size(sizeof(s32) * data->num); + } + + return len; +} + +static int phc_vclocks_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct phc_vclocks_reply_data *data = + PHC_VCLOCKS_REPDATA(reply_base); + + if (data->num <= 0) + return 0; + + if (nla_put_u32(skb, ETHTOOL_A_PHC_VCLOCKS_NUM, data->num) || + nla_put(skb, ETHTOOL_A_PHC_VCLOCKS_INDEX, + sizeof(s32) * data->num, data->index)) + return -EMSGSIZE; + + return 0; +} + +static void phc_vclocks_cleanup_data(struct ethnl_reply_data *reply_base) +{ + const struct phc_vclocks_reply_data *data = + PHC_VCLOCKS_REPDATA(reply_base); + + kfree(data->index); +} + +const struct ethnl_request_ops ethnl_phc_vclocks_request_ops = { + .request_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, + .reply_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, + .hdr_attr = ETHTOOL_A_PHC_VCLOCKS_HEADER, + .req_info_size = sizeof(struct phc_vclocks_req_info), + .reply_data_size = sizeof(struct phc_vclocks_reply_data), + + .prepare_data = phc_vclocks_prepare_data, + .reply_size = phc_vclocks_reply_size, + .fill_reply = phc_vclocks_fill_reply, + .cleanup_data = phc_vclocks_cleanup_data, +}; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a933bd6345b1..9fe13e4f5d08 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1376,7 +1376,7 @@ static void nl_fib_input(struct sk_buff *skb) portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ - netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT); + nlmsg_unicast(net->ipv4.fibnl, skb, portid); } static int __net_init nl_fib_lookup_init(struct net *net) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e65f4ef024a4..ef7897226f08 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -580,10 +580,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, nlmsg_free(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); out: if (sk) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index f6cc26de5ed3..0dca00745ac3 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) } dev->needed_headroom = t_hlen + hlen; - mtu -= t_hlen; + mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0); if (mtu < IPV4_MIN_MTU) mtu = IPV4_MIN_MTU; @@ -348,6 +348,9 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU - t_hlen; + if (dev->type == ARPHRD_ETHER) + dev->max_mtu -= dev->hard_header_len; + ip_tunnel_add(itn, nt); return nt; @@ -489,11 +492,14 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; pkt_size = skb->len - tunnel_hlen; + pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; - if (df) + if (df) { mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen); - else + mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; + } else { mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + } if (skb_valid_dst(skb)) skb_dst_update_pmtu_no_confirm(skb, mtu); @@ -972,6 +978,9 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) int t_hlen = tunnel->hlen + sizeof(struct iphdr); int max_mtu = IP_MAX_MTU - t_hlen; + if (dev->type == ARPHRD_ETHER) + max_mtu -= dev->hard_header_len; + if (new_mtu < ETH_MIN_MTU) return -EINVAL; @@ -1149,6 +1158,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], if (tb[IFLA_MTU]) { unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr)); + if (dev->type == ARPHRD_ETHER) + max -= dev->hard_header_len; + mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max); } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7b12a40dd465..2dda856ca260 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2119,7 +2119,7 @@ int ip_mr_input(struct sk_buff *skb) raw_rcv(mroute_sk, skb); return 0; } - } + } } /* already under rcu_read_lock() */ diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index 1b5b8af27aaf..ccacbde30a2c 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -119,11 +119,8 @@ static int raw_diag_dump_one(struct netlink_callback *cb, return err; } - err = netlink_unicast(net->diag_nlsk, rep, - NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + return err; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d5ab5f243640..8cb44040ec68 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1375,6 +1375,9 @@ new_segment: } pfrag->offset += copy; } else { + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_space; + err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index f26916a62f25..d3e9386b493e 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -503,7 +503,7 @@ static int __init tcp_bpf_v4_build_proto(void) tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot); return 0; } -core_initcall(tcp_bpf_v4_build_proto); +late_initcall(tcp_bpf_v4_build_proto); static int tcp_bpf_assert_proto_ops(struct proto *ops) { diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 47c32604d38f..25fa4c01a17f 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -507,8 +507,18 @@ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); + if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout) + return; + + /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ + WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies); + + /* Paired with smp_rmb() in tcp_fastopen_active_should_disable(). + * We want net->ipv4.tfo_active_disable_stamp to be updated first. + */ + smp_mb__before_atomic(); atomic_inc(&net->ipv4.tfo_active_disable_times); - net->ipv4.tfo_active_disable_stamp = jiffies; + NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } @@ -519,17 +529,27 @@ void tcp_fastopen_active_disable(struct sock *sk) bool tcp_fastopen_active_should_disable(struct sock *sk) { unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; - int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); unsigned long timeout; + int tfo_da_times; int multiplier; + if (!tfo_bh_timeout) + return false; + + tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); if (!tfo_da_times) return false; + /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */ + smp_rmb(); + /* Limit timeout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); - timeout = multiplier * tfo_bh_timeout * HZ; - if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) + + /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */ + timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) + + multiplier * tfo_bh_timeout * HZ; + if (time_before(jiffies, timeout)) return true; /* Mark check bit so we can check for successful active TFO diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e6ca5a1f3b59..149ceb5c94ff 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4247,6 +4247,9 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) { trace_tcp_receive_reset(sk); + /* mptcp can't tell us to ignore reset pkts, + * so just ignore the return value of mptcp_incoming_options(). + */ if (sk_is_mptcp(sk)) mptcp_incoming_options(sk, skb); @@ -4941,8 +4944,13 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) bool fragstolen; int eaten; - if (sk_is_mptcp(sk)) - mptcp_incoming_options(sk, skb); + /* If a subflow has been reset, the packet should not continue + * to be processed, drop the packet. + */ + if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) { + __kfree_skb(skb); + return; + } if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { __kfree_skb(skb); @@ -5922,8 +5930,8 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); tp->snd_cwnd_stamp = tcp_jiffies32; - icsk->icsk_ca_initialized = 0; bpf_skops_established(sk, bpf_op, skb); + /* Initialize congestion control unless BPF initialized it already: */ if (!icsk->icsk_ca_initialized) tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); @@ -6523,8 +6531,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_CLOSING: case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { - if (sk_is_mptcp(sk)) - mptcp_incoming_options(sk, skb); + /* If a subflow has been reset, the packet should not + * continue to be processed, drop the packet. + */ + if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) + goto discard; break; } fallthrough; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e66ad6bfe808..a692626c19e4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -342,7 +342,7 @@ void tcp_v4_mtu_reduced(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - mtu = tcp_sk(sk)->mtu_info; + mtu = READ_ONCE(tcp_sk(sk)->mtu_info); dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -546,7 +546,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) if (sk->sk_state == TCP_LISTEN) goto out; - tp->mtu_info = info; + WRITE_ONCE(tp->mtu_info, info); if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); } else { @@ -2965,7 +2965,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); - net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60; + net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); /* Reno is always built in */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bde781f46b41..29553fce8502 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1732,6 +1732,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } +EXPORT_SYMBOL(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 62682807b4b2..1a742b710e54 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -645,10 +645,12 @@ static struct sock *__udp4_lib_err_encap(struct net *net, const struct iphdr *iph, struct udphdr *uh, struct udp_table *udptable, + struct sock *sk, struct sk_buff *skb, u32 info) { + int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; - struct sock *sk; + struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -659,18 +661,28 @@ static struct sock *__udp4_lib_err_encap(struct net *net, /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, iph->ihl << 2); + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + sk = __udp4_lib_lookup(net, iph->daddr, uh->source, iph->saddr, uh->dest, skb->dev->ifindex, 0, udptable, NULL); if (sk) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(sk); + up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } +out: if (!sk) sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info)); @@ -707,15 +719,16 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udp_encap_needed_key)) { - sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb, + sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb, info); if (!sk) return 0; - } + } else + sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); @@ -1102,7 +1115,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); - ipc.gso_size = up->gso_size; + ipc.gso_size = READ_ONCE(up->gso_size); if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); @@ -2695,7 +2708,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, case UDP_SEGMENT: if (val < 0 || val > USHRT_MAX) return -EINVAL; - up->gso_size = val; + WRITE_ONCE(up->gso_size, val); break; case UDP_GRO: @@ -2790,7 +2803,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, break; case UDP_SEGMENT: - val = up->gso_size; + val = READ_ONCE(up->gso_size); break; case UDP_GRO: diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 45b8782aec0c..9f5a5cdc38e6 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -134,7 +134,7 @@ static int __init udp_bpf_v4_build_proto(void) udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot); return 0; } -core_initcall(udp_bpf_v4_build_proto); +late_initcall(udp_bpf_v4_build_proto); int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index b2cee9a307d4..1ed8c4d78e5c 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -77,10 +77,8 @@ static int udp_dump_one(struct udp_table *tbl, kfree_skb(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: if (sk) sock_put(sk); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 54e06b88af69..9dde1e5fb449 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -525,8 +525,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) - pp = call_gro_receive(udp_gro_receive_segment, head, skb); - return pp; + return call_gro_receive(udp_gro_receive_segment, head, skb); + + /* no GRO, be sure flush the current packet */ + goto out; } if (NAPI_GRO_CB(skb)->encap_mark || diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 984050f35c61..e1b9f7ac8bad 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -60,10 +60,38 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + unsigned int hh_len = LL_RESERVED_SPACE(dev); + int delta = hh_len - skb_headroom(skb); const struct in6_addr *nexthop; struct neighbour *neigh; int ret; + /* Be paranoid, rather than too clever. */ + if (unlikely(delta > 0) && dev->header_ops) { + /* pskb_expand_head() might crash, if skb is shared */ + if (skb_shared(skb)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (likely(nskb)) { + if (skb->sk) + skb_set_owner_w(nskb, skb->sk); + consume_skb(skb); + } else { + kfree_skb(skb); + } + skb = nskb; + } + if (skb && + pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { + kfree_skb(skb); + skb = NULL; + } + if (!skb) { + IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); + return -ENOMEM; + } + } + if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); @@ -479,7 +507,9 @@ int ip6_forward(struct sk_buff *skb) if (skb_warn_if_lro(skb)) goto drop; - if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { + if (!net->ipv6.devconf_all->disable_policy && + !idev->cnf.disable_policy && + !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7b756a7dc036..b6ddf23d3833 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3769,7 +3769,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, err = PTR_ERR(rt->fib6_metrics); /* Do not leave garbage there. */ rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; - goto out; + goto out_free; } if (cfg->fc_flags & RTF_ADDRCONF) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 578ab6305c3f..0ce52d46e4f8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -348,11 +348,20 @@ failure: static void tcp_v6_mtu_reduced(struct sock *sk) { struct dst_entry *dst; + u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info); + mtu = READ_ONCE(tcp_sk(sk)->mtu_info); + + /* Drop requests trying to increase our current mss. + * Check done in __ip6_rt_update_pmtu() is too late. + */ + if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache) + return; + + dst = inet6_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -433,6 +442,8 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } if (type == ICMPV6_PKT_TOOBIG) { + u32 mtu = ntohl(info); + /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). @@ -443,7 +454,11 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!ip6_sk_accept_pmtu(sk)) goto out; - tp->mtu_info = ntohl(info); + if (mtu < IPV6_MIN_MTU) + goto out; + + WRITE_ONCE(tp->mtu_info, mtu); + if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, @@ -540,7 +555,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, + err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 368972dbd919..c5e15e94bb00 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -502,12 +502,14 @@ static struct sock *__udp6_lib_err_encap(struct net *net, const struct ipv6hdr *hdr, int offset, struct udphdr *uh, struct udp_table *udptable, + struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, __be32 info) { + int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; - struct sock *sk; + struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -518,18 +520,28 @@ static struct sock *__udp6_lib_err_encap(struct net *net, /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, offset); + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source, &hdr->saddr, uh->dest, inet6_iif(skb), 0, udptable, skb); if (sk) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(sk); + up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } +out: if (!sk) { sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code, offset, info)); @@ -558,16 +570,17 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), inet6_sdif(skb), udptable, NULL); + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udpv6_encap_needed_key)) { sk = __udp6_lib_err_encap(net, hdr, offset, uh, - udptable, skb, + udptable, sk, skb, opt, type, code, info); if (!sk) return 0; - } + } else + sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), @@ -1296,7 +1309,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); ipcm6_init(&ipc6); - ipc6.gso_size = up->gso_size; + ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 57fa27c1cdf9..d0d280077721 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -49,7 +49,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; - int mtu; + unsigned int mtu; bool toobig; #ifdef CONFIG_NETFILTER diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 349c6ac3313f..e6795d5a546a 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1635,14 +1635,16 @@ struct iucv_message_pending { u8 iptype; u32 ipmsgid; u32 iptrgcls; - union { - u32 iprmmsg1_u32; - u8 iprmmsg1[4]; - } ln1msg1; - union { - u32 ipbfln1f; - u8 iprmmsg2[4]; - } ln1msg2; + struct { + union { + u32 iprmmsg1_u32; + u8 iprmmsg1[4]; + } ln1msg1; + union { + u32 ipbfln1f; + u8 iprmmsg2[4]; + } ln1msg2; + } rmmsg; u32 res1[3]; u32 ipbfln2f; u8 ippollfg; @@ -1660,10 +1662,10 @@ static void iucv_message_pending(struct iucv_irq_data *data) msg.id = imp->ipmsgid; msg.class = imp->iptrgcls; if (imp->ipflags1 & IUCV_IPRMDATA) { - memcpy(msg.rmmsg, imp->ln1msg1.iprmmsg1, 8); + memcpy(msg.rmmsg, &imp->rmmsg, 8); msg.length = 8; } else - msg.length = imp->ln1msg2.ipbfln1f; + msg.length = imp->rmmsg.ln1msg2.ipbfln1f; msg.reply_size = imp->ipbfln2f; path->handler->message_pending(path, &msg); } diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 52ea2517e856..ff2cc0e3273d 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -44,6 +44,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), + SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED), SNMP_MIB_SENTINEL }; diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 193466c9b549..0663cb12b448 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -37,6 +37,7 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ + MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */ __MPTCP_MIB_MAX }; diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index 8f88ddeab6a2..f48eb6315bbb 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -57,10 +57,8 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb, kfree_skb(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: sock_put(sk); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b5850afea343..4452455aef7f 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1035,7 +1035,8 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, return hmac == mp_opt->ahmac; } -void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) +/* Return false if a subflow has been reset, else return true */ +bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); @@ -1053,12 +1054,16 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) __mptcp_check_push(subflow->conn, sk); __mptcp_data_acked(subflow->conn); mptcp_data_unlock(subflow->conn); - return; + return true; } mptcp_get_options(sk, skb, &mp_opt); + + /* The subflow can be in close state only if check_fully_established() + * just sent a reset. If so, tell the caller to ignore the current packet. + */ if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) - return; + return sk->sk_state != TCP_CLOSE; if (mp_opt.fastclose && msk->local_key == mp_opt.rcvr_key) { @@ -1100,7 +1105,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) } if (!mp_opt.dss) - return; + return true; /* we can't wait for recvmsg() to update the ack_seq, otherwise * monodirectional flows will stuck @@ -1119,12 +1124,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) schedule_work(&msk->work)) sock_hold(subflow->conn); - return; + return true; } mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) - return; + return true; memset(mpext, 0, sizeof(*mpext)); @@ -1153,6 +1158,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) if (mpext->csum_reqd) mpext->csum = mp_opt.csum; } + + return true; } static void mptcp_set_rwin(const struct tcp_sock *tp) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7a5afa8c6866..a88924947815 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -474,7 +474,7 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) bool cleanup, rx_empty; cleanup = (space > 0) && (space >= (old_space << 1)); - rx_empty = !atomic_read(&sk->sk_rmem_alloc); + rx_empty = !__mptcp_rmem(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); @@ -720,8 +720,10 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) + if (__mptcp_rmem(sk) > sk_rbuf) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); return; + } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); @@ -1754,7 +1756,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, if (!(flags & MSG_PEEK)) { /* we will bulk release the skb memory later */ skb->destructor = NULL; - msk->rmem_released += skb->truesize; + WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); __skb_unlink(skb, &msk->receive_queue); __kfree_skb(skb); } @@ -1873,7 +1875,7 @@ static void __mptcp_update_rmem(struct sock *sk) atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, msk->rmem_released); - msk->rmem_released = 0; + WRITE_ONCE(msk->rmem_released, 0); } static void __mptcp_splice_receive_queue(struct sock *sk) @@ -2380,7 +2382,7 @@ static int __mptcp_init_sock(struct sock *sk) msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->wmem_reserved = 0; - msk->rmem_released = 0; + WRITE_ONCE(msk->rmem_released, 0); msk->tx_pending_data = 0; msk->first = NULL; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 426ed80fe72f..0f0c026c5f8b 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -296,9 +296,17 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk) return (struct mptcp_sock *)sk; } +/* the msk socket don't use the backlog, also account for the bulk + * free memory + */ +static inline int __mptcp_rmem(const struct sock *sk) +{ + return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released); +} + static inline int __mptcp_space(const struct sock *sk) { - return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_released); + return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk)); } static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 092d1f635d27..8c03afac5ca0 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -157,19 +157,7 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); - switch (optname) { - case SO_TIMESTAMP_OLD: - case SO_TIMESTAMP_NEW: - case SO_TIMESTAMPNS_OLD: - case SO_TIMESTAMPNS_NEW: - sock_set_timestamp(sk, optname, !!val); - break; - case SO_TIMESTAMPING_NEW: - case SO_TIMESTAMPING_OLD: - sock_set_timestamping(sk, optname, val); - break; - } - + sock_set_timestamp(sk, optname, !!val); unlock_sock_fast(ssk, slow); } @@ -178,7 +166,8 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam } static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, - sockptr_t optval, unsigned int optlen) + sockptr_t optval, + unsigned int optlen) { int val, ret; @@ -205,14 +194,56 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: - case SO_TIMESTAMPING_OLD: - case SO_TIMESTAMPING_NEW: return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val); } return -ENOPROTOOPT; } +static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, + int optname, + sockptr_t optval, + unsigned int optlen) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + struct so_timestamping timestamping; + int ret; + + if (optlen == sizeof(timestamping)) { + if (copy_from_sockptr(×tamping, optval, + sizeof(timestamping))) + return -EFAULT; + } else if (optlen == sizeof(int)) { + memset(×tamping, 0, sizeof(timestamping)); + + if (copy_from_sockptr(×tamping.flags, optval, sizeof(int))) + return -EFAULT; + } else { + return -EINVAL; + } + + ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, + KERNEL_SOCKPTR(×tamping), + sizeof(timestamping)); + if (ret) + return ret; + + lock_sock(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow = lock_sock_fast(ssk); + + sock_set_timestamping(sk, optname, timestamping); + unlock_sock_fast(ssk, slow); + } + + release_sock(sk); + + return 0; +} + static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval, unsigned int optlen) { @@ -299,9 +330,12 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: + return mptcp_setsockopt_sol_socket_int(msk, optname, optval, + optlen); case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: - return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen); + return mptcp_setsockopt_sol_socket_timestamping(msk, optname, + optval, optlen); case SO_LINGER: return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen); case SO_RCVLOWAT: diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 66d0b1893d26..966f777d35ce 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -214,11 +214,6 @@ again: ntohs(inet_sk(sk_listener)->inet_sport), ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { - sock_put((struct sock *)subflow_req->msk); - mptcp_token_destroy_request(req); - tcp_request_sock_ops.destructor(req); - subflow_req->msk = NULL; - subflow_req->mp_join = 0; SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); return -EPERM; } @@ -230,6 +225,8 @@ again: if (unlikely(req->syncookie)) { if (mptcp_can_accept_new_subflow(subflow_req->msk)) subflow_init_req_cookie_join_save(subflow_req, skb); + else + return -EPERM; } pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, @@ -269,9 +266,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, if (!mptcp_token_join_cookie_init_state(subflow_req, skb)) return -EINVAL; - if (mptcp_can_accept_new_subflow(subflow_req->msk)) - subflow_req->mp_join = 1; - + subflow_req->mp_join = 1; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; } diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c index abe0fd099746..37127781aee9 100644 --- a/net/mptcp/syncookies.c +++ b/net/mptcp/syncookies.c @@ -37,7 +37,21 @@ static spinlock_t join_entry_locks[COOKIE_JOIN_SLOTS] __cacheline_aligned_in_smp static u32 mptcp_join_entry_hash(struct sk_buff *skb, struct net *net) { - u32 i = skb_get_hash(skb) ^ net_hash_mix(net); + static u32 mptcp_join_hash_secret __read_mostly; + struct tcphdr *th = tcp_hdr(skb); + u32 seq, i; + + net_get_random_once(&mptcp_join_hash_secret, + sizeof(mptcp_join_hash_secret)); + + if (th->syn) + seq = TCP_SKB_CB(skb)->seq; + else + seq = TCP_SKB_CB(skb)->seq - 1; + + i = jhash_3words(seq, net_hash_mix(net), + (__force __u32)th->source << 16 | (__force __u32)th->dest, + mptcp_join_hash_secret); return i % ARRAY_SIZE(join_entries); } diff --git a/net/ncsi/Kconfig b/net/ncsi/Kconfig index 93309081f5a4..ea1dd32b6b1f 100644 --- a/net/ncsi/Kconfig +++ b/net/ncsi/Kconfig @@ -17,3 +17,9 @@ config NCSI_OEM_CMD_GET_MAC help This allows to get MAC address from NCSI firmware and set them back to controller. +config NCSI_OEM_CMD_KEEP_PHY + bool "Keep PHY Link up" + depends on NET_NCSI + help + This allows to keep PHY link up and prevents any channel resets during + the host load. diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index cbbb0de4750a..0b6cfd3b31e0 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -78,6 +78,9 @@ enum { /* OEM Vendor Manufacture ID */ #define NCSI_OEM_MFR_MLX_ID 0x8119 #define NCSI_OEM_MFR_BCM_ID 0x113d +#define NCSI_OEM_MFR_INTEL_ID 0x157 +/* Intel specific OEM command */ +#define NCSI_OEM_INTEL_CMD_KEEP_PHY 0x20 /* CMD ID for Keep PHY up */ /* Broadcom specific OEM Command */ #define NCSI_OEM_BCM_CMD_GMA 0x01 /* CMD ID for Get MAC */ /* Mellanox specific OEM Command */ @@ -86,6 +89,7 @@ enum { #define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */ #define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */ /* OEM Command payload lengths*/ +#define NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN 7 #define NCSI_OEM_BCM_CMD_GMA_LEN 12 #define NCSI_OEM_MLX_CMD_GMA_LEN 8 #define NCSI_OEM_MLX_CMD_SMAF_LEN 60 @@ -271,6 +275,7 @@ enum { ncsi_dev_state_probe_mlx_gma, ncsi_dev_state_probe_mlx_smaf, ncsi_dev_state_probe_cis, + ncsi_dev_state_probe_keep_phy, ncsi_dev_state_probe_gvi, ncsi_dev_state_probe_gc, ncsi_dev_state_probe_gls, diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index ca04b6df1341..89c7742cd72e 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -689,6 +689,35 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, return 0; } +#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) + +static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca) +{ + unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN]; + int ret = 0; + + nca->payload = NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN; + + memset(data, 0, NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN); + *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID); + + data[4] = NCSI_OEM_INTEL_CMD_KEEP_PHY; + + /* PHY Link up attribute */ + data[6] = 0x1; + + nca->data = data; + + ret = ncsi_xmit_cmd(nca); + if (ret) + netdev_err(nca->ndp->ndev.dev, + "NCSI: Failed to transmit cmd 0x%x during configure\n", + nca->type); + return ret; +} + +#endif + #if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) /* NCSI OEM Command APIs */ @@ -700,7 +729,7 @@ static int ncsi_oem_gma_handler_bcm(struct ncsi_cmd_arg *nca) nca->payload = NCSI_OEM_BCM_CMD_GMA_LEN; memset(data, 0, NCSI_OEM_BCM_CMD_GMA_LEN); - *(unsigned int *)data = ntohl(NCSI_OEM_MFR_BCM_ID); + *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_BCM_ID); data[5] = NCSI_OEM_BCM_CMD_GMA; nca->data = data; @@ -724,7 +753,7 @@ static int ncsi_oem_gma_handler_mlx(struct ncsi_cmd_arg *nca) nca->payload = NCSI_OEM_MLX_CMD_GMA_LEN; memset(&u, 0, sizeof(u)); - u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID); + u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID); u.data_u8[5] = NCSI_OEM_MLX_CMD_GMA; u.data_u8[6] = NCSI_OEM_MLX_CMD_GMA_PARAM; @@ -747,7 +776,7 @@ static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca) int ret = 0; memset(&u, 0, sizeof(u)); - u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID); + u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID); u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF; u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM; memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET], @@ -1392,7 +1421,23 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) } nd->state = ncsi_dev_state_probe_gvi; + if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)) + nd->state = ncsi_dev_state_probe_keep_phy; + break; +#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) + case ncsi_dev_state_probe_keep_phy: + ndp->pending_req_num = 1; + + nca.type = NCSI_PKT_CMD_OEM; + nca.package = ndp->active_package->id; + nca.channel = 0; + ret = ncsi_oem_keep_phy_intel(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_probe_gvi; break; +#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */ case ncsi_dev_state_probe_gvi: case ncsi_dev_state_probe_gc: case ncsi_dev_state_probe_gls: diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 888ccc2d4e34..d48374894817 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -403,7 +403,7 @@ static int ncsi_rsp_handler_ev(struct ncsi_request *nr) /* Update to VLAN mode */ cmd = (struct ncsi_cmd_ev_pkt *)skb_network_header(nr->cmd); ncm->enable = 1; - ncm->data[0] = ntohl(cmd->mode); + ncm->data[0] = ntohl((__force __be32)cmd->mode); return 0; } @@ -699,12 +699,19 @@ static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr) return 0; } +/* Response handler for Intel card */ +static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr) +{ + return 0; +} + static struct ncsi_rsp_oem_handler { unsigned int mfr_id; int (*handler)(struct ncsi_request *nr); } ncsi_rsp_oem_handlers[] = { { NCSI_OEM_MFR_MLX_ID, ncsi_rsp_handler_oem_mlx }, - { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm } + { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm }, + { NCSI_OEM_MFR_INTEL_ID, ncsi_rsp_handler_oem_intel } }; /* Response handler for OEM command */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 96ba19fc8155..83c52df85870 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -149,7 +149,15 @@ static void nf_conntrack_all_lock(void) spin_lock(&nf_conntrack_locks_all_lock); - nf_conntrack_locks_all = true; + /* For nf_contrack_locks_all, only the latest time when another + * CPU will see an update is controlled, by the "release" of the + * spin_lock below. + * The earliest time is not controlled, an thus KCSAN could detect + * a race when nf_conntract_lock() reads the variable. + * WRITE_ONCE() is used to ensure the compiler will not + * optimize the write. + */ + WRITE_ONCE(nf_conntrack_locks_all, true); for (i = 0; i < CONNTRACK_LOCKS; i++) { spin_lock(&nf_conntrack_locks[i]); @@ -2457,7 +2465,6 @@ i_see_dead_people: } list_for_each_entry(net, net_exit_list, exit_list) { - nf_conntrack_proto_pernet_fini(net); nf_conntrack_ecache_pernet_fini(net); nf_conntrack_expect_pernet_fini(net); free_percpu(net->ct.stat); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 4e1a9dba7077..e81af33b233b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -218,6 +218,7 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb, if (!help) return 0; + rcu_read_lock(); helper = rcu_dereference(help->helper); if (!helper) goto out; @@ -233,9 +234,11 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb, nla_nest_end(skb, nest_helper); out: + rcu_read_unlock(); return 0; nla_put_failure: + rcu_read_unlock(); return -1; } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 55647409a9be..8f7a9837349c 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -697,13 +697,6 @@ void nf_conntrack_proto_pernet_init(struct net *net) #endif } -void nf_conntrack_proto_pernet_fini(struct net *net) -{ -#ifdef CONFIG_NF_CT_PROTO_GRE - nf_ct_gre_keymap_flush(net); -#endif -} - module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, &nf_conntrack_htable_size, 0600); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index db11e403d818..728eeb0aea87 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -55,19 +55,6 @@ static inline struct nf_gre_net *gre_pernet(struct net *net) return &net->ct.nf_ct_proto.gre; } -void nf_ct_gre_keymap_flush(struct net *net) -{ - struct nf_gre_net *net_gre = gre_pernet(net); - struct nf_ct_gre_keymap *km, *tmp; - - spin_lock_bh(&keymap_lock); - list_for_each_entry_safe(km, tmp, &net_gre->keymap_list, list) { - list_del_rcu(&km->list); - kfree_rcu(km, rcu); - } - spin_unlock_bh(&keymap_lock); -} - static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, const struct nf_conntrack_tuple *t) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index f7e8baf59b51..3259416f2ea4 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -823,6 +823,22 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; } +static bool tcp_can_early_drop(const struct nf_conn *ct) +{ + switch (ct->proto.tcp.state) { + case TCP_CONNTRACK_FIN_WAIT: + case TCP_CONNTRACK_LAST_ACK: + case TCP_CONNTRACK_TIME_WAIT: + case TCP_CONNTRACK_CLOSE: + case TCP_CONNTRACK_CLOSE_WAIT: + return true; + default: + break; + } + + return false; +} + /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_tcp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -1030,10 +1046,30 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, if (index != TCP_RST_SET) break; - if (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) { + /* If we are closing, tuple might have been re-used already. + * last_index, last_ack, and all other ct fields used for + * sequence/window validation are outdated in that case. + * + * As the conntrack can already be expired by GC under pressure, + * just skip validation checks. + */ + if (tcp_can_early_drop(ct)) + goto in_window; + + /* td_maxack might be outdated if we let a SYN through earlier */ + if ((ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) && + ct->proto.tcp.last_index != TCP_SYN_SET) { u32 seq = ntohl(th->seq); - if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) { + /* If we are not in established state and SEQ=0 this is most + * likely an answer to a SYN we let go through above (last_index + * can be updated due to out-of-order ACKs). + */ + if (seq == 0 && !nf_conntrack_tcp_established(ct)) + break; + + if (before(seq, ct->proto.tcp.seen[!dir].td_maxack) && + !tn->tcp_ignore_invalid_rst) { /* Invalid RST */ spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst"); @@ -1134,6 +1170,16 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } + + if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) { + /* do not renew timeout on SYN retransmit. + * + * Else port reuse by client or NAT middlebox can keep + * entry alive indefinitely (including nat info). + */ + return NF_ACCEPT; + } + /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection * pickup with loose=1. Avoid large ESTABLISHED timeout. */ @@ -1155,22 +1201,6 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, return NF_ACCEPT; } -static bool tcp_can_early_drop(const struct nf_conn *ct) -{ - switch (ct->proto.tcp.state) { - case TCP_CONNTRACK_FIN_WAIT: - case TCP_CONNTRACK_LAST_ACK: - case TCP_CONNTRACK_TIME_WAIT: - case TCP_CONNTRACK_CLOSE: - case TCP_CONNTRACK_CLOSE_WAIT: - return true; - default: - break; - } - - return false; -} - #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> @@ -1437,6 +1467,9 @@ void nf_conntrack_tcp_init_net(struct net *net) */ tn->tcp_be_liberal = 0; + /* If it's non-zero, we turn off RST sequence number check */ + tn->tcp_ignore_invalid_rst = 0; + /* Max number of the retransmitted packets without receiving an (acceptable) * ACK from the destination. If this number is reached, a shorter timer * will be started. diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index f57a951c9b5e..214d9f9e499b 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -579,6 +579,7 @@ enum nf_ct_sysctl_index { #endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, + NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST, NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, @@ -798,6 +799,14 @@ static struct ctl_table nf_ct_sysctl_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + [NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST] = { + .procname = "nf_conntrack_tcp_ignore_invalid_rst", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, [NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = { .procname = "nf_conntrack_tcp_max_retrans", .maxlen = sizeof(u8), @@ -1004,6 +1013,7 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, XASSIGN(LOOSE, &tn->tcp_loose); XASSIGN(LIBERAL, &tn->tcp_be_liberal); XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans); + XASSIGN(IGNORE_INVALID_RST, &tn->tcp_ignore_invalid_rst); #undef XASSIGN #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 390d4466567f..de182d1f7c4e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3446,7 +3446,8 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return 0; err_destroy_flow_rule: - nft_flow_rule_destroy(flow); + if (flow) + nft_flow_rule_destroy(flow); err_release_rule: nf_tables_rule_release(&ctx, rule); err_release_expr: diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 913ac45167f2..8088b99f2ee3 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -23,15 +23,21 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, { struct nft_last_priv *priv = nft_expr_priv(expr); u64 last_jiffies; + u32 last_set = 0; int err; - if (tb[NFTA_LAST_MSECS]) { + if (tb[NFTA_LAST_SET]) { + last_set = ntohl(nla_get_be32(tb[NFTA_LAST_SET])); + if (last_set == 1) + priv->last_set = 1; + } + + if (last_set && tb[NFTA_LAST_MSECS]) { err = nf_msecs_to_jiffies64(tb[NFTA_LAST_MSECS], &last_jiffies); if (err < 0) return err; - priv->last_jiffies = jiffies + (unsigned long)last_jiffies; - priv->last_set = 1; + priv->last_jiffies = jiffies - (unsigned long)last_jiffies; } return 0; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index d233ac4a91b6..380f95aacdec 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2471,7 +2471,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, nlmsg_end(skb, rep); - netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); + nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); } EXPORT_SYMBOL(netlink_ack); diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 9115f8a7dd45..a8da88db7893 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -121,11 +121,9 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { - sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); - sock_put(sk); - return; + goto out; } break; @@ -146,6 +144,8 @@ static void nr_heartbeat_expiry(struct timer_list *t) nr_start_heartbeat(sk); bh_unlock_sock(sk); +out: + sock_put(sk); } static void nr_t2timer_expiry(struct timer_list *t) @@ -159,6 +159,7 @@ static void nr_t2timer_expiry(struct timer_list *t) nr_enquiry_response(sk); } bh_unlock_sock(sk); + sock_put(sk); } static void nr_t4timer_expiry(struct timer_list *t) @@ -169,6 +170,7 @@ static void nr_t4timer_expiry(struct timer_list *t) bh_lock_sock(sk); nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY; bh_unlock_sock(sk); + sock_put(sk); } static void nr_idletimer_expiry(struct timer_list *t) @@ -197,6 +199,7 @@ static void nr_idletimer_expiry(struct timer_list *t) sock_set_flag(sk, SOCK_DEAD); } bh_unlock_sock(sk); + sock_put(sk); } static void nr_t1timer_expiry(struct timer_list *t) @@ -209,8 +212,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_1: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_CONNREQ); @@ -220,8 +222,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_2: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_DISCREQ); @@ -231,8 +232,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_3: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_requeue_frames(sk); @@ -241,5 +241,7 @@ static void nr_t1timer_expiry(struct timer_list *t) } nr_start_t1timer(sk); +out: bh_unlock_sock(sk); + sock_put(sk); } diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index c89c8da99f1a..d4a2db0b2299 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -670,13 +670,13 @@ static bool cmp_key(const struct sw_flow_key *key1, { const long *cp1 = (const long *)((const u8 *)key1 + key_start); const long *cp2 = (const long *)((const u8 *)key2 + key_start); - long diffs = 0; int i; for (i = key_start; i < key_end; i += sizeof(long)) - diffs |= *cp1++ ^ *cp2++; + if (*cp1++ ^ *cp2++) + return false; - return diffs == 0; + return true; } static bool flow_cmp_masked_key(const struct sw_flow *flow, diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index a656baa321fe..1b4b3514c94f 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -322,11 +322,22 @@ err_alloc: static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { + struct flow_block_cb *block_cb, *tmp_cb; struct tcf_ct_flow_table *ct_ft; + struct flow_block *block; ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table, rwork); nf_flow_table_free(&ct_ft->nf_ft); + + /* Remove any remaining callbacks before cleanup */ + block = &ct_ft->nf_ft.flow_block; + down_write(&ct_ft->nf_ft.flow_block_lock); + list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) { + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + } + up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); module_put(THIS_MODULE); @@ -1026,7 +1037,8 @@ do_nat: /* This will take care of sending queued events * even if the connection is already confirmed. */ - nf_conntrack_confirm(skb); + if (nf_conntrack_confirm(skb) != NF_ACCEPT) + goto drop; } if (!skip_add) diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 81a1c67335be..8d17a543cc9f 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -6,6 +6,7 @@ */ #include <linux/module.h> +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> @@ -33,6 +34,13 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&d->tcf_tm); bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + action = READ_ONCE(d->tcf_action); + if (unlikely(action == TC_ACT_SHOT)) + goto drop; + + if (!skb->dev || skb->dev->type != ARPHRD_ETHER) + return action; + /* XXX: if you are going to edit more fields beyond ethernet header * (example when you add IP header replacement or vlan swap) * then MAX_EDIT_LEN needs to change appropriately @@ -41,10 +49,6 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, if (unlikely(err)) /* best policy is to drop on the floor */ goto drop; - action = READ_ONCE(d->tcf_action); - if (unlikely(action == TC_ACT_SHOT)) - goto drop; - p = rcu_dereference_bh(d->skbmod_p); flags = p->flags; if (flags & SKBMOD_F_DMAC) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d73b5c5514a9..e3e79e9bd706 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2904,7 +2904,7 @@ replay: break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, - n->nlmsg_seq, n->nlmsg_type, true); + n->nlmsg_flags, n->nlmsg_type, true); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); break; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 5b274534264c..e9a8a2c86bbd 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -278,6 +278,8 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r, TCA_TCINDEX_POLICE); } +static void tcindex_free_perfect_hash(struct tcindex_data *cp); + static void tcindex_partial_destroy_work(struct work_struct *work) { struct tcindex_data *p = container_of(to_rcu_work(work), @@ -285,7 +287,8 @@ static void tcindex_partial_destroy_work(struct work_struct *work) rwork); rtnl_lock(); - kfree(p->perfect); + if (p->perfect) + tcindex_free_perfect_hash(p); kfree(p); rtnl_unlock(); } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 66fe2b82af9a..07b30d0601d7 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -564,7 +564,7 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch) /* if there's no entry, it means that the schedule didn't * start yet, so force all gates to be open, this is in * accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5 - * "AdminGateSates" + * "AdminGateStates" */ gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 6f8319b828b0..fe74c5f95630 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -860,6 +860,8 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, if (replace) { list_del_init(&shkey->key_list); sctp_auth_shkey_release(shkey); + if (asoc && asoc->active_key_id == auth_key->sca_keynumber) + sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); } list_add(&cur_key->key_list, sh_keys); diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 493fc01e5d2b..760b367644c1 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -284,10 +284,8 @@ static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p) goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: return err; } diff --git a/net/sctp/output.c b/net/sctp/output.c index 9032ce60d50e..4dfb5ea82b05 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -104,8 +104,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); } else if (!sctp_transport_pl_enabled(tp) && - !sctp_transport_pmtu_check(tp)) { - if (asoc->param_flags & SPP_PMTUD_ENABLE) + asoc->param_flags & SPP_PMTUD_ENABLE) { + if (!sctp_transport_pmtu_check(tp)) sctp_assoc_sync_pmtu(asoc); } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 3c1fbf38f4f7..ec0f52567c16 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -398,7 +398,8 @@ static enum sctp_scope sctp_v4_scope(union sctp_addr *addr) retval = SCTP_SCOPE_LINK; } else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) || ipv4_is_private_172(addr->v4.sin_addr.s_addr) || - ipv4_is_private_192(addr->v4.sin_addr.s_addr)) { + ipv4_is_private_192(addr->v4.sin_addr.s_addr) || + ipv4_is_test_198(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_PRIVATE; } else { retval = SCTP_SCOPE_GLOBAL; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 6c08e5048d38..b8fa8f1a7277 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1163,7 +1163,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport, __u32 probe_size) { - struct sctp_sender_hb_info hbinfo; + struct sctp_sender_hb_info hbinfo = {}; struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e64e01f61b11..6b937bfd4751 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4577,6 +4577,10 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, } if (optlen > 0) { + /* Trim it to the biggest size sctp sockopt may need if necessary */ + optlen = min_t(unsigned int, optlen, + PAGE_ALIGN(USHRT_MAX + + sizeof(__u16) * sizeof(struct sctp_reset_streams))); kopt = memdup_sockptr(optval, optlen); if (IS_ERR(kopt)) return PTR_ERR(kopt); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 5f23804f21c7..397a6244dd97 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -335,10 +335,13 @@ void sctp_transport_pl_recv(struct sctp_transport *t) t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } - } else if (t->pl.state == SCTP_PL_COMPLETE && ++t->pl.raise_count == 30) { - /* Raise probe_size again after 30 * interval in Search Complete */ - t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; + } else if (t->pl.state == SCTP_PL_COMPLETE) { + t->pl.raise_count++; + if (t->pl.raise_count == 30) { + /* Raise probe_size again after 30 * interval in Search Complete */ + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; + } } } diff --git a/net/socket.c b/net/socket.c index bd9233da2497..0b2dad3bdf7f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -104,6 +104,7 @@ #include <linux/sockios.h> #include <net/busy_poll.h> #include <linux/errqueue.h> +#include <linux/ptp_clock_kernel.h> #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; @@ -873,12 +874,18 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && - !skb_is_swtx_tstamp(skb, false_tstamp) && - ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { - empty = 0; - if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && - !skb_is_err_queue(skb)) - put_ts_pktinfo(msg, skb); + !skb_is_swtx_tstamp(skb, false_tstamp)) { + if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC) + ptp_convert_timestamp(shhwtstamps, sk->sk_bind_phc); + + if (ktime_to_timespec64_cond(shhwtstamps->hwtstamp, + tss.ts + 2)) { + empty = 0; + + if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && + !skb_is_err_queue(skb)) + put_ts_pktinfo(msg, skb); + } } if (!empty) { if (sock_flag(sk, SOCK_TSTAMP_NEW)) diff --git a/net/unix/diag.c b/net/unix/diag.c index 9ff64f9df1f3..7e7d7f45685a 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -295,10 +295,8 @@ again: goto again; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: if (sk) sock_put(sk); |