diff options
author | David S. Miller <davem@davemloft.net> | 2020-01-26 12:40:21 +0300 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2020-01-26 12:40:21 +0300 |
commit | 4d8773b68e83558025303f266070b31bc4101e73 (patch) | |
tree | 151cafa469fbc6a411d36b58ab802f67869cc0bb /net | |
parent | 3333e50b64fe30b7e53cf02456a2f567f689ae4f (diff) | |
parent | 2821e26f3a0a3872184581caac8115bb02641941 (diff) | |
download | linux-4d8773b68e83558025303f266070b31bc4101e73.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Minor conflict in mlx5 because changes happened to code that has
moved meanwhile.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
37 files changed, 286 insertions, 156 deletions
diff --git a/net/atm/proc.c b/net/atm/proc.c index d79221fd4dae..c31896707313 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -134,8 +134,7 @@ static void vcc_seq_stop(struct seq_file *seq, void *v) static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { v = vcc_walk(seq, 1); - if (v) - (*pos)++; + (*pos)++; return v; } diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index 76bd67891fb3..a0116b9503d9 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -62,7 +62,7 @@ static int cfusbl_transmit(struct cflayer *layr, struct cfpkt *pkt) hpad = (info->hdr_len + CFUSB_PAD_DESCR_SZ) & (CFUSB_ALIGNMENT - 1); if (skb_headroom(skb) < ETH_HLEN + CFUSB_PAD_DESCR_SZ + hpad) { - pr_warn("Headroom to small\n"); + pr_warn("Headroom too small\n"); kfree_skb(skb); return -EIO; } diff --git a/net/core/dev.c b/net/core/dev.c index 4dcc1b390667..c806b078097b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5489,9 +5489,29 @@ static void flush_all_backlogs(void) put_online_cpus(); } +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) +{ + list_add_tail(&skb->list, &napi->rx_list); + if (++napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int)); -static int napi_gro_complete(struct sk_buff *skb) +static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { struct packet_offload *ptype; __be16 type = skb->protocol; @@ -5524,7 +5544,8 @@ static int napi_gro_complete(struct sk_buff *skb) } out: - return netif_receive_skb_internal(skb); + gro_normal_one(napi, skb); + return NET_RX_SUCCESS; } static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, @@ -5537,7 +5558,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; skb_list_del_init(skb); - napi_gro_complete(skb); + napi_gro_complete(napi, skb); napi->gro_hash[index].count--; } @@ -5639,7 +5660,7 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) } } -static void gro_flush_oldest(struct list_head *head) +static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) { struct sk_buff *oldest; @@ -5655,7 +5676,7 @@ static void gro_flush_oldest(struct list_head *head) * SKB to the chain. */ skb_list_del_init(oldest); - napi_gro_complete(oldest); + napi_gro_complete(napi, oldest); } INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, @@ -5731,7 +5752,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (pp) { skb_list_del_init(pp); - napi_gro_complete(pp); + napi_gro_complete(napi, pp); napi->gro_hash[hash].count--; } @@ -5742,7 +5763,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff goto normal; if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) { - gro_flush_oldest(gro_head); + gro_flush_oldest(napi, gro_head); } else { napi->gro_hash[hash].count++; } @@ -5800,26 +5821,6 @@ struct packet_offload *gro_find_complete_by_type(__be16 type) } EXPORT_SYMBOL(gro_find_complete_by_type); -/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ -static void gro_normal_list(struct napi_struct *napi) -{ - if (!napi->rx_count) - return; - netif_receive_skb_list_internal(&napi->rx_list); - INIT_LIST_HEAD(&napi->rx_list); - napi->rx_count = 0; -} - -/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, - * pass the whole batch up to the stack. - */ -static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) -{ - list_add_tail(&skb->list, &napi->rx_list); - if (++napi->rx_count >= gro_normal_batch) - gro_normal_list(napi); -} - static void napi_skb_free_stolen_head(struct sk_buff *skb) { skb_dst_drop(skb); @@ -6198,8 +6199,6 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; - gro_normal_list(n); - if (n->gro_bitmask) { unsigned long timeout = 0; @@ -6215,6 +6214,9 @@ bool napi_complete_done(struct napi_struct *n, int work_done) hrtimer_start(&n->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); } + + gro_normal_list(n); + if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); @@ -6546,8 +6548,6 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } - gro_normal_list(n); - if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. @@ -6555,6 +6555,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) napi_gro_flush(n, HZ >= 1000); } + gro_normal_list(n); + /* Some drivers may have called napi_schedule * prior to exhausting their budget. */ @@ -8192,6 +8194,22 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) } EXPORT_SYMBOL(__dev_set_mtu); +int dev_validate_mtu(struct net_device *dev, int new_mtu, + struct netlink_ext_ack *extack) +{ + /* MTU must be positive, and in range */ + if (new_mtu < 0 || new_mtu < dev->min_mtu) { + NL_SET_ERR_MSG(extack, "mtu less than device minimum"); + return -EINVAL; + } + + if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { + NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); + return -EINVAL; + } + return 0; +} + /** * dev_set_mtu_ext - Change maximum transfer unit * @dev: device @@ -8208,16 +8226,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, if (new_mtu == dev->mtu) return 0; - /* MTU must be positive, and in range */ - if (new_mtu < 0 || new_mtu < dev->min_mtu) { - NL_SET_ERR_MSG(extack, "mtu less than device minimum"); - return -EINVAL; - } - - if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { - NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); - return -EINVAL; - } + err = dev_validate_mtu(dev, new_mtu, extack); + if (err) + return err; if (!netif_device_present(dev)) return -ENODEV; @@ -9317,8 +9328,10 @@ int register_netdevice(struct net_device *dev) goto err_uninit; ret = netdev_register_kobject(dev); - if (ret) + if (ret) { + dev->reg_state = NETREG_UNREGISTERED; goto err_uninit; + } dev->reg_state = NETREG_REGISTERED; __netdev_update_features(dev); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 920784a9b7ff..789a73aa7bd8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3290,6 +3290,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return per_cpu_ptr(tbl->stats, cpu); } + (*pos)++; return NULL; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 20bc406f3871..cdad6ed532c4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3053,8 +3053,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; - if (tb[IFLA_MTU]) - dev->mtu = nla_get_u32(tb[IFLA_MTU]); + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + int err; + + err = dev_validate_mtu(dev, mtu, extack); + if (err) { + free_netdev(dev); + return ERR_PTR(err); + } + dev->mtu = mtu; + } if (tb[IFLA_ADDRESS]) { memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]), nla_len(tb[IFLA_ADDRESS])); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 3866d7e20c07..ded2d5227678 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -594,8 +594,6 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy); void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - sock_owned_by_me(sk); - sk_psock_cork_free(psock); sk_psock_zap_ingress(psock); diff --git a/net/core/utils.c b/net/core/utils.c index 6b6e51db9f3b..1f31a39236d5 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -438,6 +438,23 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, } EXPORT_SYMBOL(inet_proto_csum_replace4); +/** + * inet_proto_csum_replace16 - update layer 4 header checksum field + * @sum: Layer 4 header checksum field + * @skb: sk_buff for the packet + * @from: old IPv6 address + * @to: new IPv6 address + * @pseudohdr: True if layer 4 header checksum includes pseudoheader + * + * Update layer 4 header as per the update in IPv6 src/dst address. + * + * There is no need to update skb->csum in this function, because update in two + * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other + * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to + * update skb->csum, because update in 3 fields a.) IPv4 src/dst address, + * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as + * L4 Header checksum for skb->csum calculation. + */ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr) @@ -449,9 +466,6 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum))); - if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) - skb->csum = ~csum_partial(diff, sizeof(diff), - ~skb->csum); } else if (pseudohdr) *sum = ~csum_fold(csum_partial(diff, sizeof(diff), csum_unfold(*sum))); diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 0e4a7cf6bc87..e2e219c7854a 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -57,6 +57,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, if (!x) goto out_reset; + skb->mark = xfrm_smark_get(skb->mark, x); + sp->xvec[sp->len++] = x; sp->olen++; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 30fa771d382a..dcc79ff54b41 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -662,8 +662,8 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, [FOU_ATTR_PEER_V4] = { .type = NLA_U32, }, - [FOU_ATTR_LOCAL_V6] = { .type = sizeof(struct in6_addr), }, - [FOU_ATTR_PEER_V6] = { .type = sizeof(struct in6_addr), }, + [FOU_ATTR_LOCAL_V6] = { .len = sizeof(struct in6_addr), }, + [FOU_ATTR_PEER_V6] = { .len = sizeof(struct in6_addr), }, [FOU_ATTR_PEER_PORT] = { .type = NLA_U16, }, [FOU_ATTR_IFINDEX] = { .type = NLA_S32, }, }; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0fe2a5d3e258..74e1d964a615 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1236,10 +1236,8 @@ int ip_tunnel_init(struct net_device *dev) iph->version = 4; iph->ihl = 5; - if (tunnel->collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (tunnel->collect_md) netif_keep_dst(dev); - } return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index e90b600c7a25..37cddd18f282 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -187,8 +187,17 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, int mtu; if (!dst) { - dev->stats.tx_carrier_errors++; - goto tx_error_icmp; + struct rtable *rt; + + fl->u.ip4.flowi4_oif = dev->ifindex; + fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + dst = &rt->dst; + skb_dst_set(skb, dst); } dst_hold(dst); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 2010888e68ca..d5c57b3f77d5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -271,6 +271,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } + (*pos)++; return NULL; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7dfb78caedaf..2857c853e2fd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2525,6 +2525,7 @@ static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); + tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); @@ -2615,7 +2616,6 @@ int tcp_disconnect(struct sock *sk, int flags) WRITE_ONCE(tp->write_seq, seq); icsk->icsk_backoff = 0; - tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index a6545ef0d27b..6c4d79baff26 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -779,8 +779,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) * bandwidth sample. Delivered is in packets and interval_us in uS and * ratio will be <<1 for most connections. So delivered is first scaled. */ - bw = (u64)rs->delivered * BW_UNIT; - do_div(bw, rs->interval_us); + bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us); /* If this sample is application-limited, it is likely to have a very * low delivered count that represents application behavior rather than diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2f475b897c11..4915de65d278 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3165,6 +3165,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; + tcp_highest_sack_replace(sk, skb, next); tcp_rtx_queue_unlink_and_free(skb, sk); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fec4b3a4b22d..306e25d743e8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3293,6 +3293,7 @@ int tcp_send_synack(struct sock *sk) if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); + tcp_highest_sack_replace(sk, skb, nskb); tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e4fd4408b775..db76b9609299 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1368,7 +1368,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2)) + if (size < (sk->sk_rcvbuf >> 2) && + !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index e31626ffccd1..fd535053245b 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -79,6 +79,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, if (!x) goto out_reset; + skb->mark = xfrm_smark_get(skb->mark, x); + sp->xvec[sp->len++] = x; sp->olen++; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b1e9a10e1133..58fbde244381 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2571,14 +2571,13 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; + ++(*pos); if (!v) goto iter_table; n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); - if (n) { - ++*pos; + if (n) return n; - } iter_table: ipv6_route_check_sernum(iter); @@ -2586,8 +2585,6 @@ iter_table: r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { - if (v) - ++*pos; return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index ee968d980746..55bfc5149d0c 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1466,7 +1466,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) dev->mtu -= 8; if (tunnel->parms.collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; netif_keep_dst(dev); } ip6gre_tnl_init_features(dev); @@ -1894,7 +1893,6 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); @@ -2197,7 +2195,6 @@ static void ip6erspan_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2f376dbc37d5..b5dd20c4599b 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1877,10 +1877,8 @@ static int ip6_tnl_dev_init(struct net_device *dev) if (err) return err; ip6_tnl_link_config(t); - if (t->parms.collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (t->parms.collect_md) netif_keep_dst(dev); - } return 0; } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 6f08b760c2a7..524006aa0d78 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -449,8 +449,17 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) int err = -1; int mtu; - if (!dst) - goto tx_err_link_failure; + if (!dst) { + fl->u.ip6.flowi6_oif = dev->ifindex; + fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; + dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); + if (dst->error) { + dst_release(dst); + dst = NULL; + goto tx_err_link_failure; + } + skb_dst_set(skb, dst); + } dst_hold(dst); dst = xfrm_lookup(t->net, dst, fl, NULL, 0); diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 85a5447a3e8d..7cbc19731997 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -23,6 +23,7 @@ #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/dst_cache.h> +#include <net/ip_tunnels.h> #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif @@ -135,7 +136,8 @@ static bool decap_and_validate(struct sk_buff *skb, int proto) skb_reset_network_header(skb); skb_reset_transport_header(skb); - skb->encapsulation = 0; + if (iptunnel_pull_offloads(skb)) + return false; return true; } diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 077a2cb65fcb..26ab0e9612d8 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -75,7 +75,7 @@ mtype_flush(struct ip_set *set) if (set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); - memset(map->members, 0, map->memsize); + bitmap_zero(map->members, map->elements); set->elements = 0; set->ext_size = 0; } diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index abe8f77d7d23..0a2196f59106 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -37,7 +37,7 @@ MODULE_ALIAS("ip_set_bitmap:ip"); /* Type structure */ struct bitmap_ip { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -220,7 +220,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, u32 first_ip, u32 last_ip, u32 elements, u32 hosts, u8 netmask) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_ip = first_ip; @@ -322,7 +322,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (!map) return -ENOMEM; - map->memsize = bitmap_bytes(0, elements - 1); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ip; if (!init_map_ip(set, map, first_ip, last_ip, elements, hosts, netmask)) { diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index b618713297da..739e343efaf6 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -42,7 +42,7 @@ enum { /* Type structure */ struct bitmap_ipmac { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -299,7 +299,7 @@ static bool init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, u32 first_ip, u32 last_ip, u32 elements) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_ip = first_ip; @@ -360,7 +360,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (!map) return -ENOMEM; - map->memsize = bitmap_bytes(0, elements - 1); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ipmac; if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) { kfree(map); diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 23d6095cb196..b49978dd810d 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -30,7 +30,7 @@ MODULE_ALIAS("ip_set_bitmap:port"); /* Type structure */ struct bitmap_port { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u16 first_port; /* host byte order, included in range */ u16 last_port; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -231,7 +231,7 @@ static bool init_map_port(struct ip_set *set, struct bitmap_port *map, u16 first_port, u16 last_port) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(map->elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_port = first_port; @@ -271,7 +271,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], return -ENOMEM; map->elements = elements; - map->memsize = bitmap_bytes(0, map->elements); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_port; if (!init_map_port(set, map, first_port, last_port)) { kfree(map); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 8dc892a9dc91..605e0f68f8bd 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1239,7 +1239,7 @@ static void ip_vs_process_message(struct netns_ipvs *ipvs, __u8 *buffer, p = msg_end; if (p + sizeof(s->v4) > buffer+buflen) { - IP_VS_ERR_RL("BACKUP, Dropping buffer, to small\n"); + IP_VS_ERR_RL("BACKUP, Dropping buffer, too small\n"); return; } s = (union ip_vs_sync_conn *)p; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 0399ae8f1188..4f897b14b606 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -114,7 +114,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, /* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, @@ -130,7 +130,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* REPLY */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ /* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, /* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, @@ -316,7 +316,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = sh->vtag; } - ct->proto.sctp.state = new_state; + ct->proto.sctp.state = SCTP_CONNTRACK_NONE; } return true; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 65f51a2e9c2a..7e63b481cc86 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -553,47 +553,70 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table) static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX]; static const struct nft_chain_type * +__nft_chain_type_get(u8 family, enum nft_chain_types type) +{ + if (family >= NFPROTO_NUMPROTO || + type >= NFT_CHAIN_T_MAX) + return NULL; + + return chain_type[family][type]; +} + +static const struct nft_chain_type * __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family) { + const struct nft_chain_type *type; int i; for (i = 0; i < NFT_CHAIN_T_MAX; i++) { - if (chain_type[family][i] != NULL && - !nla_strcmp(nla, chain_type[family][i]->name)) - return chain_type[family][i]; + type = __nft_chain_type_get(family, i); + if (!type) + continue; + if (!nla_strcmp(nla, type->name)) + return type; } return NULL; } -/* - * Loading a module requires dropping mutex that guards the transaction. - * A different client might race to start a new transaction meanwhile. Zap the - * list of pending transaction and then restore it once the mutex is grabbed - * again. Users of this function return EAGAIN which implicitly triggers the - * transaction abort path to clean up the list of pending transactions. - */ +struct nft_module_request { + struct list_head list; + char module[MODULE_NAME_LEN]; + bool done; +}; + #ifdef CONFIG_MODULES -static void nft_request_module(struct net *net, const char *fmt, ...) +static int nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; - LIST_HEAD(commit_list); + struct nft_module_request *req; va_list args; int ret; - list_splice_init(&net->nft.commit_list, &commit_list); - va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) - return; + return 0; - mutex_unlock(&net->nft.commit_mutex); - request_module("%s", module_name); - mutex_lock(&net->nft.commit_mutex); + list_for_each_entry(req, &net->nft.module_list, list) { + if (!strcmp(req->module, module_name)) { + if (req->done) + return 0; - WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); - list_splice(&commit_list, &net->nft.commit_list); + /* A request to load this module already exists. */ + return -EAGAIN; + } + } + + req = kmalloc(sizeof(*req), GFP_KERNEL); + if (!req) + return -ENOMEM; + + req->done = false; + strlcpy(req->module, module_name, MODULE_NAME_LEN); + list_add_tail(&req->list, &net->nft.module_list); + + return -EAGAIN; } #endif @@ -617,10 +640,9 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (autoload) { - nft_request_module(net, "nft-chain-%u-%.*s", family, - nla_len(nla), (const char *)nla_data(nla)); - type = __nf_tables_chain_type_lookup(nla, family); - if (type != NULL) + if (nft_request_module(net, "nft-chain-%u-%.*s", family, + nla_len(nla), + (const char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -1162,11 +1184,8 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) void nft_register_chain_type(const struct nft_chain_type *ctype) { - if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO)) - return; - nfnl_lock(NFNL_SUBSYS_NFTABLES); - if (WARN_ON(chain_type[ctype->family][ctype->type] != NULL)) { + if (WARN_ON(__nft_chain_type_get(ctype->family, ctype->type))) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); return; } @@ -1768,7 +1787,10 @@ static int nft_chain_parse_hook(struct net *net, hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); - type = chain_type[family][NFT_CHAIN_T_DEFAULT]; + type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT); + if (!type) + return -EOPNOTSUPP; + if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], family, autoload); @@ -2328,9 +2350,8 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, static int nft_expr_type_request_module(struct net *net, u8 family, struct nlattr *nla) { - nft_request_module(net, "nft-expr-%u-%.*s", family, - nla_len(nla), (char *)nla_data(nla)); - if (__nft_expr_type_get(family, nla)) + if (nft_request_module(net, "nft-expr-%u-%.*s", family, + nla_len(nla), (char *)nla_data(nla)) == -EAGAIN) return -EAGAIN; return 0; @@ -2356,9 +2377,9 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nft_expr_type_request_module(net, family, nla) == -EAGAIN) return ERR_PTR(-EAGAIN); - nft_request_module(net, "nft-expr-%.*s", - nla_len(nla), (char *)nla_data(nla)); - if (__nft_expr_type_get(family, nla)) + if (nft_request_module(net, "nft-expr-%.*s", + nla_len(nla), + (char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -2449,9 +2470,10 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, err = PTR_ERR(ops); #ifdef CONFIG_MODULES if (err == -EAGAIN) - nft_expr_type_request_module(ctx->net, - ctx->family, - tb[NFTA_EXPR_NAME]); + if (nft_expr_type_request_module(ctx->net, + ctx->family, + tb[NFTA_EXPR_NAME]) != -EAGAIN) + err = -ENOENT; #endif goto err1; } @@ -3288,8 +3310,7 @@ nft_select_set_ops(const struct nft_ctx *ctx, lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (list_empty(&nf_tables_set_types)) { - nft_request_module(ctx->net, "nft-set"); - if (!list_empty(&nf_tables_set_types)) + if (nft_request_module(ctx->net, "nft-set") == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -5415,8 +5436,7 @@ nft_obj_type_get(struct net *net, u32 objtype) lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { - nft_request_module(net, "nft-obj-%u", objtype); - if (__nft_obj_type_get(objtype)) + if (nft_request_module(net, "nft-obj-%u", objtype) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -5989,8 +6009,7 @@ nft_flowtable_type_get(struct net *net, u8 family) lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { - nft_request_module(net, "nf-flowtable-%u", family); - if (__nft_flowtable_type_get(family)) + if (nft_request_module(net, "nf-flowtable-%u", family) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -6992,6 +7011,18 @@ static void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nf_tables_module_autoload_cleanup(struct net *net) +{ + struct nft_module_request *req, *next; + + WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); + list_for_each_entry_safe(req, next, &net->nft.module_list, list) { + WARN_ON_ONCE(!req->done); + list_del(&req->list); + kfree(req); + } +} + static void nf_tables_commit_release(struct net *net) { struct nft_trans *trans; @@ -7004,6 +7035,7 @@ static void nf_tables_commit_release(struct net *net) * to prevent expensive synchronize_rcu() in commit phase. */ if (list_empty(&net->nft.commit_list)) { + nf_tables_module_autoload_cleanup(net); mutex_unlock(&net->nft.commit_mutex); return; } @@ -7018,6 +7050,7 @@ static void nf_tables_commit_release(struct net *net) list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list); spin_unlock(&nf_tables_destroy_list_lock); + nf_tables_module_autoload_cleanup(net); mutex_unlock(&net->nft.commit_mutex); schedule_work(&trans_destroy_work); @@ -7209,6 +7242,26 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return 0; } +static void nf_tables_module_autoload(struct net *net) +{ + struct nft_module_request *req, *next; + LIST_HEAD(module_list); + + list_splice_init(&net->nft.module_list, &module_list); + mutex_unlock(&net->nft.commit_mutex); + list_for_each_entry_safe(req, next, &module_list, list) { + if (req->done) { + list_del(&req->list); + kfree(req); + } else { + request_module("%s", req->module); + req->done = true; + } + } + mutex_lock(&net->nft.commit_mutex); + list_splice(&module_list, &net->nft.module_list); +} + static void nf_tables_abort_release(struct nft_trans *trans) { switch (trans->msg_type) { @@ -7238,7 +7291,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) kfree(trans); } -static int __nf_tables_abort(struct net *net) +static int __nf_tables_abort(struct net *net, bool autoload) { struct nft_trans *trans, *next; struct nft_trans_elem *te; @@ -7360,6 +7413,11 @@ static int __nf_tables_abort(struct net *net) nf_tables_abort_release(trans); } + if (autoload) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + return 0; } @@ -7368,9 +7426,9 @@ static void nf_tables_cleanup(struct net *net) nft_validate_state_update(net, NFT_VALIDATE_SKIP); } -static int nf_tables_abort(struct net *net, struct sk_buff *skb) +static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload) { - int ret = __nf_tables_abort(net); + int ret = __nf_tables_abort(net, autoload); mutex_unlock(&net->nft.commit_mutex); @@ -7965,6 +8023,7 @@ static int __net_init nf_tables_init_net(struct net *net) { INIT_LIST_HEAD(&net->nft.tables); INIT_LIST_HEAD(&net->nft.commit_list); + INIT_LIST_HEAD(&net->nft.module_list); mutex_init(&net->nft.commit_mutex); net->nft.base_seq = 1; net->nft.validate_state = NFT_VALIDATE_SKIP; @@ -7976,7 +8035,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) { mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) - __nf_tables_abort(net); + __nf_tables_abort(net, false); __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index a9ea29afb09f..2bb28483af22 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -564,7 +564,7 @@ static void nft_indr_block_cb(struct net_device *dev, mutex_lock(&net->nft.commit_mutex); chain = __nft_offload_get_chain(dev); - if (chain) { + if (chain && chain->flags & NFT_CHAIN_HW_OFFLOAD) { struct nft_base_chain *basechain; basechain = nft_base_chain(chain); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 4abbb452cf6c..99127e2d95a8 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -476,7 +476,7 @@ ack: } done: if (status & NFNL_BATCH_REPLAY) { - ss->abort(net, oskb); + ss->abort(net, oskb, true); nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); @@ -487,11 +487,11 @@ done: status |= NFNL_BATCH_REPLAY; goto done; } else if (err) { - ss->abort(net, oskb); + ss->abort(net, oskb, false); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } } else { - ss->abort(net, oskb); + ss->abort(net, oskb, false); } if (ss->cleanup) ss->cleanup(net); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index f54d6ae15bb1..b42247aa48a9 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -61,6 +61,9 @@ static int nft_osf_init(const struct nft_ctx *ctx, int err; u8 ttl; + if (!tb[NFTA_OSF_DREG]) + return -EINVAL; + if (tb[NFTA_OSF_TTL]) { ttl = nla_get_u8(tb[NFTA_OSF_TTL]); if (ttl > 2) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 46b8ff24020d..1e8eeb044b07 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1475,7 +1475,7 @@ static int __init rose_proto_init(void) int rc; if (rose_ndevs > 0x7FFFFFFF/sizeof(struct net_device *)) { - printk(KERN_ERR "ROSE: rose_proto_init - rose_ndevs parameter to large\n"); + printk(KERN_ERR "ROSE: rose_proto_init - rose_ndevs parameter too large\n"); rc = -EINVAL; goto out; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 76e0d122616a..c2cdd0fc2e70 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2055,9 +2055,8 @@ replay: &chain_info)); mutex_unlock(&chain->filter_chain_lock); - tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, chain, rtnl_held, - extack); + tp_new = tcf_proto_create(name, protocol, prio, chain, + rtnl_held, extack); if (IS_ERR(tp_new)) { err = PTR_ERR(tp_new); goto errout_tp; diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 8f2ad706784d..d0140a92694a 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -263,12 +263,12 @@ static int tcf_em_validate(struct tcf_proto *tp, } em->data = (unsigned long) v; } + em->datalen = data_len; } } em->matchid = em_hdr->matchid; em->flags = em_hdr->flags; - em->datalen = data_len; em->net = net; err = 0; diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 7ac1542feaf8..dc651a628dcf 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -268,9 +268,6 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) int err = -1; int mtu; - if (!dst) - goto tx_err_link_failure; - dst_hold(dst); dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id); if (IS_ERR(dst)) { @@ -297,7 +294,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) mtu = dst_mtu(dst); if (!skb->ignore_df && skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) @@ -343,6 +340,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net_device_stats *stats = &xi->dev->stats; + struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; @@ -352,10 +350,33 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) case htons(ETH_P_IPV6): xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + if (!dst) { + fl.u.ip6.flowi6_oif = dev->ifindex; + fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; + dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); + if (dst->error) { + dst_release(dst); + stats->tx_carrier_errors++; + goto tx_err; + } + skb_dst_set(skb, dst); + } break; case htons(ETH_P_IP): xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + if (!dst) { + struct rtable *rt; + + fl.u.ip4.flowi4_oif = dev->ifindex; + fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); + if (IS_ERR(rt)) { + stats->tx_carrier_errors++; + goto tx_err; + } + skb_dst_set(skb, &rt->dst); + } break; default: goto tx_err; @@ -563,12 +584,9 @@ static void xfrmi_dev_setup(struct net_device *dev) { dev->netdev_ops = &xfrmi_netdev_ops; dev->type = ARPHRD_NONE; - dev->hard_header_len = ETH_HLEN; - dev->min_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = ETH_DATA_LEN; - dev->addr_len = ETH_ALEN; + dev->max_mtu = IP_MAX_MTU; dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; |