diff options
author | David S. Miller <davem@davemloft.net> | 2018-03-23 11:24:57 -0400 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2018-03-23 11:31:58 -0400 |
commit | 03fe2debbb2771fb90881e4ce8109b09cf772a5c (patch) | |
tree | fbaf8738296b2e9dcba81c6daef2d515b6c4948c /net | |
parent | 6686c459e1449a3ee5f3fd313b0a559ace7a700e (diff) | |
parent | f36b7534b83357cf52e747905de6d65b4f7c2512 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Fun set of conflict resolutions here...
For the mac80211 stuff, these were fortunately just parallel
adds. Trivially resolved.
In drivers/net/phy/phy.c we had a bug fix in 'net' that moved the
function phy_disable_interrupts() earlier in the file, whilst in
'net-next' the phy_error() call from this function was removed.
In net/ipv4/xfrm4_policy.c, David Ahern's changes to remove the
'rt_table_id' member of rtable collided with a bug fix in 'net' that
added a new struct member "rt_mtu_locked" which needs to be copied
over here.
The mlxsw driver conflict consisted of net-next separating
the span code and definitions into separate files, whilst
a 'net' bug fix made some changes to that moved code.
The mlx5 infiniband conflict resolution was quite non-trivial,
the RDMA tree's merge commit was used as a guide here, and
here are their notes:
====================
Due to bug fixes found by the syzkaller bot and taken into the for-rc
branch after development for the 4.17 merge window had already started
being taken into the for-next branch, there were fairly non-trivial
merge issues that would need to be resolved between the for-rc branch
and the for-next branch. This merge resolves those conflicts and
provides a unified base upon which ongoing development for 4.17 can
be based.
Conflicts:
drivers/infiniband/hw/mlx5/main.c - Commit 42cea83f9524
(IB/mlx5: Fix cleanup order on unload) added to for-rc and
commit b5ca15ad7e61 (IB/mlx5: Add proper representors support)
add as part of the devel cycle both needed to modify the
init/de-init functions used by mlx5. To support the new
representors, the new functions added by the cleanup patch
needed to be made non-static, and the init/de-init list
added by the representors patch needed to be modified to
match the init/de-init list changes made by the cleanup
patch.
Updates:
drivers/infiniband/hw/mlx5/mlx5_ib.h - Update function
prototypes added by representors patch to reflect new function
names as changed by cleanup patch
drivers/infiniband/hw/mlx5/ib_rep.c - Update init/de-init
stage list to match new order from cleanup patch
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
69 files changed, 489 insertions, 267 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 64aa9f755e1d..45c9bf5ff3a0 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -48,8 +48,8 @@ bool vlan_do_receive(struct sk_buff **skbp) * original position later */ skb_push(skb, offset); - skb = *skbp = vlan_insert_tag(skb, skb->vlan_proto, - skb->vlan_tci); + skb = *skbp = vlan_insert_inner_tag(skb, skb->vlan_proto, + skb->vlan_tci, skb->mac_len); if (!skb) return false; skb_pull(skb, offset + VLAN_HLEN); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 75dda9454ccf..a60bacf7120b 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -400,7 +400,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, batadv_arp_hw_src(skb, hdr_size), &ip_src, batadv_arp_hw_dst(skb, hdr_size), &ip_dst); - if (hdr_size == 0) + if (hdr_size < sizeof(struct batadv_unicast_packet)) return; unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 7d5e9abb7a65..55c358ad3331 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -24,6 +24,7 @@ #include <linux/debugfs.h> #include <linux/errno.h> #include <linux/etherdevice.h> +#include <linux/eventpoll.h> #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index 52d8a4b848c0..853773e45f79 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -22,6 +22,7 @@ #include <linux/compiler.h> #include <linux/debugfs.h> #include <linux/errno.h> +#include <linux/eventpoll.h> #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 5615b6abea6f..de3a055f7dd8 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -598,8 +598,8 @@ update: bat_priv->mcast.enabled = true; } - return !(mcast_data.flags & - (BATADV_MCAST_WANT_ALL_IPV4 | BATADV_MCAST_WANT_ALL_IPV6)); + return !(mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV4 && + mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV6); } /** diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 289df027ecdd..cc3ed93a6d51 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -759,6 +759,7 @@ free_skb: /** * batadv_reroute_unicast_packet() - update the unicast header for re-routing * @bat_priv: the bat priv with all the soft interface information + * @skb: unicast packet to process * @unicast_packet: the unicast header to be updated * @dst_addr: the payload destination * @vid: VLAN identifier @@ -770,7 +771,7 @@ free_skb: * Return: true if the packet header has been updated, false otherwise */ static bool -batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, +batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_unicast_packet *unicast_packet, u8 *dst_addr, unsigned short vid) { @@ -799,8 +800,10 @@ batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, } /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, orig_addr); unicast_packet->ttvn = orig_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ret = true; out: @@ -841,7 +844,7 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * the packet to */ if (batadv_tt_local_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) { - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, @@ -887,7 +890,7 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * destination can possibly be updated and forwarded towards the new * target host */ - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) { batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, "Rerouting unicast packet to %pM (dst=%pM): TTVN mismatch old_ttvn=%u new_ttvn=%u\n", @@ -910,12 +913,14 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, if (!primary_if) return false; + /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, primary_if->net_dev->dev_addr); + unicast_packet->ttvn = curr_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); batadv_hardif_put(primary_if); - unicast_packet->ttvn = curr_ttvn; - return true; } @@ -968,14 +973,10 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, struct batadv_orig_node *orig_node = NULL, *orig_node_gw = NULL; int check, hdr_size = sizeof(*unicast_packet); enum batadv_subtype subtype; - struct ethhdr *ethhdr; int ret = NET_RX_DROP; bool is4addr, is_gw; unicast_packet = (struct batadv_unicast_packet *)skb->data; - unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; - ethhdr = eth_hdr(skb); - is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR; /* the caller function should have already pulled 2 bytes */ if (is4addr) @@ -995,12 +996,14 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, if (!batadv_check_unicast_ttvn(bat_priv, skb, hdr_size)) goto free_skb; + unicast_packet = (struct batadv_unicast_packet *)skb->data; + /* packet for me */ if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { /* If this is a unicast packet from another backgone gw, * drop it. */ - orig_addr_gw = ethhdr->h_source; + orig_addr_gw = eth_hdr(skb)->h_source; orig_node_gw = batadv_orig_hash_find(bat_priv, orig_addr_gw); if (orig_node_gw) { is_gw = batadv_bla_is_backbone_gw(skb, orig_node_gw, @@ -1015,6 +1018,8 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, } if (is4addr) { + unicast_4addr_packet = + (struct batadv_unicast_4addr_packet *)skb->data; subtype = unicast_4addr_packet->subtype; batadv_dat_inc_counter(bat_priv, subtype); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 01117ae84f1d..a2ddae2f37d7 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2296,8 +2296,14 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) else sec_level = authreq_to_seclevel(auth); - if (smp_sufficient_security(hcon, sec_level, SMP_USE_LTK)) + if (smp_sufficient_security(hcon, sec_level, SMP_USE_LTK)) { + /* If link is already encrypted with sufficient security we + * still need refresh encryption as per Core Spec 5.0 Vol 3, + * Part H 2.4.6 + */ + smp_ltk_encrypt(conn, hcon->sec_level); return 0; + } if (sec_level > hcon->pending_sec_level) hcon->pending_sec_level = sec_level; diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c index c5afb4232ecb..620e54f08296 100644 --- a/net/bridge/netfilter/ebt_among.c +++ b/net/bridge/netfilter/ebt_among.c @@ -177,6 +177,28 @@ static bool poolsize_invalid(const struct ebt_mac_wormhash *w) return w && w->poolsize >= (INT_MAX / sizeof(struct ebt_mac_wormhash_tuple)); } +static bool wormhash_offset_invalid(int off, unsigned int len) +{ + if (off == 0) /* not present */ + return false; + + if (off < (int)sizeof(struct ebt_among_info) || + off % __alignof__(struct ebt_mac_wormhash)) + return true; + + off += sizeof(struct ebt_mac_wormhash); + + return off > len; +} + +static bool wormhash_sizes_valid(const struct ebt_mac_wormhash *wh, int a, int b) +{ + if (a == 0) + a = sizeof(struct ebt_among_info); + + return ebt_mac_wormhash_size(wh) + a == b; +} + static int ebt_among_mt_check(const struct xt_mtchk_param *par) { const struct ebt_among_info *info = par->matchinfo; @@ -189,6 +211,10 @@ static int ebt_among_mt_check(const struct xt_mtchk_param *par) if (expected_length > em->match_size) return -EINVAL; + if (wormhash_offset_invalid(info->wh_dst_ofs, em->match_size) || + wormhash_offset_invalid(info->wh_src_ofs, em->match_size)) + return -EINVAL; + wh_dst = ebt_among_wh_dst(info); if (poolsize_invalid(wh_dst)) return -EINVAL; @@ -201,6 +227,14 @@ static int ebt_among_mt_check(const struct xt_mtchk_param *par) if (poolsize_invalid(wh_src)) return -EINVAL; + if (info->wh_src_ofs < info->wh_dst_ofs) { + if (!wormhash_sizes_valid(wh_src, info->wh_src_ofs, info->wh_dst_ofs)) + return -EINVAL; + } else { + if (!wormhash_sizes_valid(wh_dst, info->wh_dst_ofs, info->wh_src_ofs)) + return -EINVAL; + } + expected_length += ebt_mac_wormhash_size(wh_src); if (em->match_size != EBT_ALIGN(expected_length)) { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 254ef9f49567..a94d23b0a9af 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2119,8 +2119,12 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, * offsets are relative to beginning of struct ebt_entry (i.e., 0). */ for (i = 0; i < 4 ; ++i) { - if (offsets[i] >= *total) + if (offsets[i] > *total) return -EINVAL; + + if (i < 3 && offsets[i] == *total) + return -EINVAL; + if (i == 0) continue; if (offsets[i-1] > offsets[i]) diff --git a/net/core/dev.c b/net/core/dev.c index d8887cc38e7b..f9c28f44286c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3278,15 +3278,23 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { - struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); + const struct netprio_map *map; + const struct sock *sk; + unsigned int prioidx; - if (!skb->priority && skb->sk && map) { - unsigned int prioidx = - sock_cgroup_prioidx(&skb->sk->sk_cgrp_data); + if (skb->priority) + return; + map = rcu_dereference_bh(skb->dev->priomap); + if (!map) + return; + sk = skb_to_full_sk(skb); + if (!sk) + return; - if (prioidx < map->priomap_len) - skb->priority = map->priomap[prioidx]; - } + prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 0ab1af04296c..a04e1e88bf3a 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -402,8 +402,6 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c if (colon) *colon = 0; - dev_load(net, ifr->ifr_name); - /* * See which interface the caller is talking about. */ @@ -423,6 +421,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCGIFMAP: case SIOCGIFINDEX: case SIOCGIFTXQLEN: + dev_load(net, ifr->ifr_name); rcu_read_lock(); ret = dev_ifsioc_locked(net, ifr, cmd); rcu_read_unlock(); @@ -431,6 +430,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c return ret; case SIOCETHTOOL: + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ethtool(net, ifr); rtnl_unlock(); @@ -447,6 +447,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSIFNAME: + dev_load(net, ifr->ifr_name); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); @@ -494,6 +495,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c /* fall through */ case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ifsioc(net, ifr, cmd); rtnl_unlock(); @@ -518,6 +520,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c cmd == SIOCGHWTSTAMP || (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15)) { + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ifsioc(net, ifr, cmd); rtnl_unlock(); diff --git a/net/core/devlink.c b/net/core/devlink.c index d03b96f87c25..9236e421bd62 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1798,7 +1798,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } @@ -1807,7 +1807,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: -err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; @@ -2073,7 +2072,7 @@ static int devlink_dpipe_entries_fill(struct genl_info *info, table->counters_enabled, &dump_ctx); if (err) - goto err_entries_dump; + return err; send_done: nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, @@ -2081,16 +2080,10 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(dump_ctx.skb, info); - -err_entries_dump: -err_skb_send_alloc: - genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr); - nlmsg_free(dump_ctx.skb); - return err; } static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, @@ -2229,7 +2222,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(skb, info); @@ -2237,7 +2230,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: -err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; diff --git a/net/core/filter.c b/net/core/filter.c index c86f03fd9ea5..00c711c5f1a2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2283,6 +2283,10 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -2292,19 +2296,21 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV4 needs to be changed into * SKB_GSO_TCPV6. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV4; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; + if (shinfo->gso_type & SKB_GSO_TCPV4) { + shinfo->gso_type &= ~SKB_GSO_TCPV4; + shinfo->gso_type |= SKB_GSO_TCPV6; } /* Due to IPv6 header, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IPV6); @@ -2319,6 +2325,10 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -2328,19 +2338,21 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV6 needs to be changed into * SKB_GSO_TCPV4. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV6; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; + if (shinfo->gso_type & SKB_GSO_TCPV6) { + shinfo->gso_type &= ~SKB_GSO_TCPV6; + shinfo->gso_type |= SKB_GSO_TCPV4; } /* Due to IPv4 header, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IP); @@ -2439,6 +2451,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -2448,11 +2464,13 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header grow, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; @@ -2463,6 +2481,10 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -2472,11 +2494,13 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header shrink, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 715c13495ba6..46cb22215ff4 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4181,7 +4181,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + sk->sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -4906,7 +4906,7 @@ static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); - } else if (unlikely(shinfo->gso_type & SKB_GSO_SCTP)) { + } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); } /* UFO sets gso_size to the size of the fragmentation @@ -5022,13 +5022,16 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { + int mac_len; + if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN, - 2 * ETH_ALEN); + mac_len = skb->data - skb_mac_header(skb); + memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), + mac_len - VLAN_HLEN - ETH_TLEN); skb->mac_header += VLAN_HLEN; return skb; } diff --git a/net/core/sock.c b/net/core/sock.c index f704324d1219..e689496dfd8a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3326,6 +3326,27 @@ void proto_unregister(struct proto *prot) } EXPORT_SYMBOL(proto_unregister); +int sock_load_diag_module(int family, int protocol) +{ + if (!protocol) { + if (!sock_is_registered(family)) + return -ENOENT; + + return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family); + } + +#ifdef CONFIG_INET + if (family == AF_INET && + !rcu_access_pointer(inet_protos[protocol])) + return -ENOENT; +#endif + + return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family, protocol); +} +EXPORT_SYMBOL(sock_load_diag_module); + #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index aee5642affd9..a3392a8f9276 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -220,8 +220,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; if (sock_diag_handlers[req->sdiag_family] == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, req->sdiag_family); + sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; @@ -247,8 +246,7 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) @@ -281,14 +279,12 @@ static int sock_diag_bind(struct net *net, int group) case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!sock_diag_handlers[AF_INET]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET6); + sock_load_diag_module(AF_INET6, 0); break; } return 0; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 15bdc002d90c..84cd4e3fd01b 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -794,6 +794,11 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (skb == NULL) goto out_release; + if (sk->sk_state == DCCP_CLOSED) { + rc = -ENOTCONN; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index cb54b81d0bd9..42a7b85b84e1 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -194,7 +194,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, ds->ports[i].dn = cd->port_dn[i]; ds->ports[i].cpu_dp = dst->cpu_dp; - if (dsa_is_user_port(ds, i)) + if (!dsa_is_user_port(ds, i)) continue; ret = dsa_slave_create(&ds->ports[i]); diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index e4f305320519..275449b0d633 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -207,9 +207,13 @@ static inline void lowpan_netlink_fini(void) static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *wdev = netdev_notifier_info_to_dev(ptr); + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + struct wpan_dev *wpan_dev; - if (wdev->type != ARPHRD_IEEE802154) + if (ndev->type != ARPHRD_IEEE802154) + return NOTIFY_DONE; + wpan_dev = ndev->ieee802154_ptr; + if (!wpan_dev) return NOTIFY_DONE; switch (event) { @@ -218,8 +222,8 @@ static int lowpan_device_event(struct notifier_block *unused, * also delete possible lowpan interfaces which belongs * to the wpan interface. */ - if (wdev->ieee802154_ptr->lowpan_dev) - lowpan_dellink(wdev->ieee802154_ptr->lowpan_dev, NULL); + if (wpan_dev->lowpan_dev) + lowpan_dellink(wpan_dev->lowpan_dev, NULL); break; default: return NOTIFY_DONE; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index a383f299ce24..4e5bc4b2f14e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -53,8 +53,7 @@ static DEFINE_MUTEX(inet_diag_table_mutex); static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { if (!inet_diag_table[proto]) - request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET, proto); + sock_load_diag_module(AF_INET, proto); mutex_lock(&inet_diag_table_mutex); if (!inet_diag_table[proto]) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 26a3d0315728..e8ec28999f5c 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -119,6 +119,9 @@ out: static bool inet_fragq_should_evict(const struct inet_frag_queue *q) { + if (!hlist_unhashed(&q->list_evictor)) + return false; + return q->net->low_thresh == 0 || frag_mem_limit(q->net) >= q->net->low_thresh; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e74ee837b300..4ac5728689f5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -635,6 +635,7 @@ static inline u32 fnhe_hashfun(__be32 daddr) static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; + rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { @@ -645,7 +646,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh } static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, - u32 pmtu, unsigned long expires) + u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; @@ -682,8 +683,10 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; - if (pmtu) + if (pmtu) { fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; + } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); @@ -707,6 +710,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = expires; /* Exception created; mark the cached routes for the nexthop @@ -788,7 +792,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, jiffies + ip_rt_gc_timeout); + 0, false, + jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1010,15 +1015,18 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct fib_result res; + bool lock = false; - if (dst_metric_locked(dst, RTAX_MTU)) + if (ip_mtu_locked(dst)) return; if (ipv4_mtu(dst) < mtu) return; - if (mtu < ip_rt_min_pmtu) + if (mtu < ip_rt_min_pmtu) { + lock = true; mtu = ip_rt_min_pmtu; + } if (rt->rt_pmtu == mtu && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) @@ -1028,7 +1036,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); - update_or_create_fnhe(nh, fl4->daddr, 0, mtu, + update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } rcu_read_unlock(); @@ -1281,7 +1289,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = READ_ONCE(dst->dev->mtu); - if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { + if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@ -1394,7 +1402,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); -static void rt_add_uncached_list(struct rtable *rt) +void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); @@ -1405,14 +1413,8 @@ static void rt_add_uncached_list(struct rtable *rt) spin_unlock_bh(&ul->lock); } -static void ipv4_dst_destroy(struct dst_entry *dst) +void rt_del_uncached_list(struct rtable *rt) { - struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); - struct rtable *rt = (struct rtable *) dst; - - if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) - kfree(p); - if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@ -1422,6 +1424,17 @@ static void ipv4_dst_destroy(struct dst_entry *dst) } } +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); + struct rtable *rt = (struct rtable *)dst; + + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); + + rt_del_uncached_list(rt); +} + void rt_flush_dev(struct net_device *dev) { struct net *net = dev_net(dev); @@ -1517,6 +1530,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; + rt->rt_mtu_locked = 0; rt->rt_gateway = 0; rt->rt_uses_gateway = 0; INIT_LIST_HEAD(&rt->rt_uncached); @@ -2533,6 +2547,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; + rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; @@ -2635,6 +2650,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; + if (rt->rt_mtu_locked && expires) + metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d763fae1b574..0c31be306572 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3545,6 +3545,7 @@ int tcp_abort(struct sock *sk, int err) bh_unlock_sock(sk); local_bh_enable(); + tcp_write_queue_purge(sk); release_sock(sk); return 0; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 71fc60f1b326..f7d944855f8e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -34,6 +34,7 @@ static void tcp_write_err(struct sock *sk) sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; sk->sk_error_report(sk); + tcp_write_queue_purge(sk); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); } diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 63faeee989a9..2a9764bd1719 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -92,7 +92,8 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); - eth_hdr(skb)->h_proto = skb->protocol; + if (skb->mac_len) + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 0c752dc3f93b..6c76a757fa4a 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,7 +100,9 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); + rt_add_uncached_list(&xdst->u.rt); return 0; } @@ -240,7 +242,8 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); - + if (xdst->u.rt.rt_uncached_list) + rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index b27333d7b099..88bc2ef7c7a8 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -146,10 +146,12 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_addr *daddr; + struct in6_addr *daddr, old_daddr; + __be32 fl6_flowlabel = 0; + __be32 old_fl6_flowlabel; + __be16 old_dport; int addr_type; int err; - __be32 fl6_flowlabel = 0; if (usin->sin6_family == AF_INET) { if (__ipv6_only_sock(sk)) @@ -238,9 +240,13 @@ ipv4_connected: } } + /* save the current peer information before updating it */ + old_daddr = sk->sk_v6_daddr; + old_fl6_flowlabel = np->flow_label; + old_dport = inet->inet_dport; + sk->sk_v6_daddr = *daddr; np->flow_label = fl6_flowlabel; - inet->inet_dport = usin->sin6_port; /* @@ -250,11 +256,12 @@ ipv4_connected: err = ip6_datagram_dst_update(sk, true); if (err) { - /* Reset daddr and dport so that udp_v6_early_demux() - * fails to find this socket + /* Restore the socket peer info, to keep it consistent with + * the old socket state */ - memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); - inet->inet_dport = 0; + sk->sk_v6_daddr = old_daddr; + np->flow_label = old_fl6_flowlabel; + inet->inet_dport = old_dport; goto out; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 6adbcf40cf8c..3a98c694da5f 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -126,7 +126,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, struct ip6_tnl *t, *cand = NULL; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); int dev_type = (gre_proto == htons(ETH_P_TEB) || - gre_proto == htons(ETH_P_ERSPAN)) ? + gre_proto == htons(ETH_P_ERSPAN) || + gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; @@ -905,6 +906,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, truncate = true; } + if (skb_cow_head(skb, dev->needed_headroom)) + goto tx_err; + t->parms.o_flags &= ~TUNNEL_KEY; IPCB(skb)->flags = 0; @@ -947,6 +951,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + } else { + goto tx_err; } } else { switch (skb->protocol) { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 10024eb0c521..d1d0b2fa7a07 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1554,7 +1554,8 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, *(opt++) = (rd_len >> 3); opt += 6; - memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8); + skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, + rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 939d122e71b4..a2ed9fdd58d4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -128,7 +128,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); -static void rt6_uncached_list_add(struct rt6_info *rt) +void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); @@ -139,7 +139,7 @@ static void rt6_uncached_list_add(struct rt6_info *rt) spin_unlock_bh(&ul->lock); } -static void rt6_uncached_list_del(struct rt6_info *rt) +void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; @@ -1514,7 +1514,30 @@ static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) } } -static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) +static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) +{ + /* If the new MTU is lower than the route PMTU, this new MTU will be the + * lowest MTU in the path: always allow updating the route PMTU to + * reflect PMTU decreases. + * + * If the new MTU is higher, and the route PMTU is equal to the local + * MTU, this means the old MTU is the lowest in the path, so allow + * updating it: if other nodes now have lower MTUs, PMTU discovery will + * handle this. + */ + + if (dst_mtu(&rt->dst) >= mtu) + return true; + + if (dst_mtu(&rt->dst) == idev->cnf.mtu6) + return true; + + return false; +} + +static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1523,20 +1546,22 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); - if (bucket) { - for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { - struct rt6_info *entry = rt6_ex->rt6i; - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) - entry->rt6i_pmtu = mtu; - } - bucket++; + if (!bucket) + return; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected + * route), the metrics of its rt->dst.from have already + * been updated. + */ + if (entry->rt6i_pmtu && + rt6_mtu_change_route_allowed(idev, entry, mtu)) + entry->rt6i_pmtu = mtu; } + bucket++; } } @@ -3899,25 +3924,13 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) Since RFC 1981 doesn't include administrative MTU increase update PMTU increase is a MUST. (i.e. jumbo frame) */ - /* - If new MTU is less than route PMTU, this new MTU will be the - lowest MTU in the path, update the route PMTU to reflect PMTU - decreases; if new MTU is greater than route PMTU, and the - old MTU is the lowest MTU in the path, update the route PMTU - to reflect the increase. In this case if the other nodes' MTU - also have the lowest MTU, TOO BIG MESSAGE will be lead to - PMTU discovery. - */ if (rt->dst.dev == arg->dev && - dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { spin_lock_bh(&rt6_exception_lock); - if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + if (dst_metric_raw(&rt->dst, RTAX_MTU) && + rt6_mtu_change_route_allowed(idev, rt, arg->mtu)) dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); - } - rt6_exceptions_update_pmtu(rt, arg->mtu); + rt6_exceptions_update_pmtu(idev, rt, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; @@ -4189,6 +4202,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, r_cfg.fc_encap_type = nla_get_u16(nla); } + r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index bd6cc688bd19..7a78dcfda68a 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -93,7 +93,8 @@ static void set_tun_src(struct net *net, struct net_device *dev, /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(dst->dev); struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; @@ -134,7 +135,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; - set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { @@ -418,7 +419,7 @@ static int seg6_build_state(struct nlattr *nla, slwt = seg6_lwt_lwtunnel(newts); - err = dst_cache_init(&slwt->cache, GFP_KERNEL); + err = dst_cache_init(&slwt->cache, GFP_ATOMIC); if (err) { kfree(newts); return err; diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index bb935a3b7fea..de1b0b8c53b0 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -92,7 +92,8 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); - eth_hdr(skb)->h_proto = skb->protocol; + if (skb->mac_len) + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 88cd0c90fa81..cbb270bd81b0 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -113,6 +113,9 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; + INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached); + rt6_uncached_list_add(&xdst->u.rt6); + atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache); return 0; } @@ -244,6 +247,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); + if (xdst->u.rt6.rt6i_uncached_list) + rt6_uncached_list_del(&xdst->u.rt6); xfrm_dst_destroy(xdst); } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 81ce15ffb878..893a022f9620 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -2432,9 +2432,11 @@ static int afiucv_iucv_init(void) af_iucv_dev->driver = &af_iucv_driver; err = device_register(af_iucv_dev); if (err) - goto out_driver; + goto out_iucv_dev; return 0; +out_iucv_dev: + put_device(af_iucv_dev); out_driver: driver_unregister(&af_iucv_driver); out_iucv: diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index a6cd0712e063..516cfad71b85 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1381,24 +1381,32 @@ static int kcm_attach(struct socket *sock, struct socket *csock, .parse_msg = kcm_parse_func_strparser, .read_sock_done = kcm_read_sock_done, }; - int err; + int err = 0; csk = csock->sk; if (!csk) return -EINVAL; + lock_sock(csk); + /* Only allow TCP sockets to be attached for now */ if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) || - csk->sk_protocol != IPPROTO_TCP) - return -EOPNOTSUPP; + csk->sk_protocol != IPPROTO_TCP) { + err = -EOPNOTSUPP; + goto out; + } /* Don't allow listeners or closed sockets */ - if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) - return -EOPNOTSUPP; + if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) { + err = -EOPNOTSUPP; + goto out; + } psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); - if (!psock) - return -ENOMEM; + if (!psock) { + err = -ENOMEM; + goto out; + } psock->mux = mux; psock->sk = csk; @@ -1407,7 +1415,7 @@ static int kcm_attach(struct socket *sock, struct socket *csock, err = strp_init(&psock->strp, csk, &cb); if (err) { kmem_cache_free(kcm_psockp, psock); - return err; + goto out; } write_lock_bh(&csk->sk_callback_lock); @@ -1420,7 +1428,8 @@ static int kcm_attach(struct socket *sock, struct socket *csock, strp_stop(&psock->strp); strp_done(&psock->strp); kmem_cache_free(kcm_psockp, psock); - return -EALREADY; + err = -EALREADY; + goto out; } psock->save_data_ready = csk->sk_data_ready; @@ -1456,7 +1465,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock, /* Schedule RX work in case there are already bytes queued */ strp_check_rcv(&psock->strp); - return 0; +out: + release_sock(csk); + + return err; } static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) @@ -1508,6 +1520,7 @@ static void kcm_unattach(struct kcm_psock *psock) if (WARN_ON(psock->rx_kcm)) { write_unlock_bh(&csk->sk_callback_lock); + release_sock(csk); return; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 189a12a5e4ac..b86868da50d4 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -111,6 +111,13 @@ struct l2tp_net { spinlock_t l2tp_session_hlist_lock; }; +#if IS_ENABLED(CONFIG_IPV6) +static bool l2tp_sk_is_v6(struct sock *sk) +{ + return sk->sk_family == PF_INET6 && + !ipv6_addr_v4mapped(&sk->sk_v6_daddr); +} +#endif static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) { @@ -1049,7 +1056,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->ignore_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped) + if (l2tp_sk_is_v6(tunnel->sock)) error = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif @@ -1112,6 +1119,15 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len goto out_unlock; } + /* The user-space may change the connection status for the user-space + * provided socket at run time: we must check it under the socket lock + */ + if (tunnel->fd >= 0 && sk->sk_state != TCP_ESTABLISHED) { + kfree_skb(skb); + ret = NET_XMIT_DROP; + goto out_unlock; + } + /* Get routing info from the tunnel socket */ skb_dst_drop(skb); skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0))); @@ -1131,7 +1147,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) + if (l2tp_sk_is_v6(sk)) udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, &sk->sk_v6_daddr, udp_len); @@ -1457,9 +1473,14 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 encap = cfg->encap; /* Quick sanity checks */ + err = -EPROTONOSUPPORT; + if (sk->sk_type != SOCK_DGRAM) { + pr_debug("tunl %hu: fd %d wrong socket type\n", + tunnel_id, fd); + goto err; + } switch (encap) { case L2TP_ENCAPTYPE_UDP: - err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_UDP) { pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP); @@ -1467,7 +1488,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 } break; case L2TP_ENCAPTYPE_IP: - err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_L2TP) { pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP); @@ -1507,24 +1527,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 if (cfg != NULL) tunnel->debug = cfg->debug; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - - if (ipv6_addr_v4mapped(&np->saddr) && - ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { - struct inet_sock *inet = inet_sk(sk); - - tunnel->v4mapped = true; - inet->inet_saddr = np->saddr.s6_addr32[3]; - inet->inet_rcv_saddr = sk->sk_v6_rcv_saddr.s6_addr32[3]; - inet->inet_daddr = sk->sk_v6_daddr.s6_addr32[3]; - } else { - tunnel->v4mapped = false; - } - } -#endif - /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ tunnel->encap = encap; if (encap == L2TP_ENCAPTYPE_UDP) { diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index a1aa9550f04e..2718d0b284d0 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -188,9 +188,6 @@ struct l2tp_tunnel { struct sock *sock; /* Parent socket */ int fd; /* Parent fd, if tunnel socket * was created by userspace */ -#if IS_ENABLED(CONFIG_IPV6) - bool v4mapped; -#endif struct work_struct del_work; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index a75653affbf7..b5adf3625d16 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -213,6 +213,7 @@ static const char *hw_flag_names[] = { FLAG(SUPPORTS_TX_FRAG), FLAG(SUPPORTS_TDLS_BUFFER_STA), FLAG(DEAUTH_NEED_MGD_TX_PREP), + FLAG(DOESNT_SUPPORT_QOS_NDP), #undef FLAG }; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0024eff9bb84..fe4aefb06d9f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -897,7 +897,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_hdr_3addr *nullfunc; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, true); + skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, + !ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP)); if (!skb) return; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8e19c86d1aa6..fd13d28e4ca7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5423,6 +5423,7 @@ err: static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { cancel_delayed_work_sync(&flowtable->data.gc_work); + kfree(flowtable->ops); kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); rhashtable_destroy(&flowtable->data.rhashtable); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 3f1624ee056f..d40591fe1b2f 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -674,7 +674,7 @@ static const struct nft_set_ops * nft_hash_select_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, u32 flags) { - if (desc->size) { + if (desc->size && !(flags & NFT_SET_TIMEOUT)) { switch (desc->klen) { case 4: return &nft_hash_fast_ops; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index d9deebe599ec..6de1f6a4cb80 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -423,6 +423,36 @@ textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) return buf; } +/** + * xt_check_proc_name - check that name is suitable for /proc file creation + * + * @name: file name candidate + * @size: length of buffer + * + * some x_tables modules wish to create a file in /proc. + * This function makes sure that the name is suitable for this + * purpose, it checks that name is NUL terminated and isn't a 'special' + * name, like "..". + * + * returns negative number on error or 0 if name is useable. + */ +int xt_check_proc_name(const char *name, unsigned int size) +{ + if (name[0] == '\0') + return -EINVAL; + + if (strnlen(name, size) == size) + return -ENAMETOOLONG; + + if (strcmp(name, ".") == 0 || + strcmp(name, "..") == 0 || + strchr(name, '/')) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL(xt_check_proc_name); + int xt_check_match(struct xt_mtchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index db2fe0911740..ef65b7a9173e 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -917,8 +917,9 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) struct hashlimit_cfg3 cfg = {}; int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); @@ -935,8 +936,9 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) struct hashlimit_cfg3 cfg = {}; int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); @@ -950,9 +952,11 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) static int hashlimit_mt_check(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo3 *info = par->matchinfo; + int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, info->name, 3); diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 19efdb757944..486dd24da78b 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -361,9 +361,9 @@ static int recent_mt_check(const struct xt_mtchk_param *par, info->hit_count, XT_RECENT_MAX_NSTAMPS - 1); return -EINVAL; } - if (info->name[0] == '\0' || - strnlen(info->name, XT_RECENT_NAME_LEN) == XT_RECENT_NAME_LEN) - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; if (ip_pkt_list_tot && info->hit_count < ip_pkt_list_tot) nstamp_mask = roundup_pow_of_two(ip_pkt_list_tot) - 1; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index a6f63a5faee7..af51b8c0a2cb 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1107,7 +1107,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, if (!err) delivered = true; else if (err != -ESRCH) - goto error; + return err; return delivered ? 0 : -ESRCH; error: kfree_skb(skb); diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 04b94281a30b..b891a91577f8 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -242,14 +242,20 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]); band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]); + if (band->rate == 0) { + err = -EINVAL; + goto exit_free_meter; + } + band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]); /* Figure out max delta_t that is enough to fill any bucket. * Keep max_delta_t size to the bucket units: * pkts => 1/1000 packets, kilobits => bits. + * + * Start with a full bucket. */ - band_max_delta_t = (band->burst_size + band->rate) * 1000; - /* Start with a full bucket. */ - band->bucket = band_max_delta_t; + band->bucket = (band->burst_size + band->rate) * 1000; + band_max_delta_t = band->bucket / band->rate; if (band_max_delta_t > meter->max_delta_t) meter->max_delta_t = band_max_delta_t; band++; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index da72e0cf2b1f..5cb9b268e8ff 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -352,7 +352,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return res; out: if (res == ACT_P_CREATED) - tcf_idr_cleanup(*act, est); + tcf_idr_release(*act, bind); return ret; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 1fb1f1f6a555..a527e287c086 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -350,7 +350,7 @@ static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, { struct sctphdr *sctph; - if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return 1; sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); @@ -626,7 +626,8 @@ static void tcf_csum_cleanup(struct tc_action *a) struct tcf_csum_params *params; params = rcu_dereference_protected(p->params, 1); - kfree_rcu(params, rcu); + if (params) + kfree_rcu(params, rcu); } static int tcf_csum_walker(struct net *net, struct sk_buff *skb, diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 10866717f88e..b5e8565b89c7 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -80,9 +80,12 @@ static void ipt_destroy_target(struct xt_entry_target *t) static void tcf_ipt_release(struct tc_action *a) { struct tcf_ipt *ipt = to_ipt(a); - ipt_destroy_target(ipt->tcfi_t); + + if (ipt->tcfi_t) { + ipt_destroy_target(ipt->tcfi_t); + kfree(ipt->tcfi_t); + } kfree(ipt->tcfi_tname); - kfree(ipt->tcfi_t); } static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { @@ -187,7 +190,7 @@ err2: kfree(tname); err1: if (ret == ACT_P_CREATED) - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 5e8cc8f63acd..f392ccaaa0d8 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -176,7 +176,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, p = to_pedit(*a); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); kfree(keys_ex); return -ENOMEM; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 51fe4fe343f7..7081ec75e696 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -196,7 +196,7 @@ failure: qdisc_put_rtab(P_tab); qdisc_put_rtab(R_tab); if (ret == ACT_P_CREATED) - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 238dfd27e995..3a89f98f17e6 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -103,7 +103,8 @@ static void tcf_sample_cleanup(struct tc_action *a) psample_group = rtnl_dereference(s->psample_group); RCU_INIT_POINTER(s->psample_group, NULL); - psample_group_put(psample_group); + if (psample_group) + psample_group_put(psample_group); } static bool tcf_sample_dev_ok_push(struct net_device *dev) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 91816d73f3f3..e84768ae610a 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -121,7 +121,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, d = to_defact(*a); ret = alloc_defdata(d, defdata); if (ret < 0) { - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return ret; } d->tcf_action = parm->action; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index febec75f4f7a..142a996ac776 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -152,7 +152,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, ASSERT_RTNL(); p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL); if (unlikely(!p)) { - if (ovr) + if (ret == ACT_P_CREATED) tcf_idr_release(*a, bind); return -ENOMEM; } @@ -190,7 +190,8 @@ static void tcf_skbmod_cleanup(struct tc_action *a) struct tcf_skbmod_params *p; p = rcu_dereference_protected(d->skbmod_p, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 9169b7e78ada..a1c8dd406a04 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -153,6 +153,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; break; default: + ret = -EINVAL; goto err_out; } @@ -207,11 +208,12 @@ static void tunnel_key_release(struct tc_action *a) struct tcf_tunnel_key_params *params; params = rcu_dereference_protected(t->params, 1); + if (params) { + if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + dst_release(¶ms->tcft_enc_metadata->dst); - if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) - dst_release(¶ms->tcft_enc_metadata->dst); - - kfree_rcu(params, rcu); + kfree_rcu(params, rcu); + } } static int tunnel_key_dump_addresses(struct sk_buff *skb, diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index c2ee7fd51cc9..4595391c2129 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -195,7 +195,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, ASSERT_RTNL(); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) { - if (ovr) + if (ret == ACT_P_CREATED) tcf_idr_release(*a, bind); return -ENOMEM; } @@ -225,7 +225,8 @@ static void tcf_vlan_cleanup(struct tc_action *a) struct tcf_vlan_params *p; p = rcu_dereference_protected(v->vlan_p, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 190570f21b20..7e3fbe9cc936 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -106,6 +106,14 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, __skb_queue_tail(&q->skb_bad_txq, skb); + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_backlog_inc(q, skb); + qdisc_qstats_cpu_qlen_inc(q); + } else { + qdisc_qstats_backlog_inc(q, skb); + q->q.qlen++; + } + if (lock) spin_unlock(lock); } @@ -196,14 +204,6 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, break; if (unlikely(skb_get_queue_mapping(nskb) != mapping)) { qdisc_enqueue_skb_bad_txq(q, nskb); - - if (qdisc_is_percpu_stats(q)) { - qdisc_qstats_cpu_backlog_inc(q, nskb); - qdisc_qstats_cpu_qlen_inc(q); - } else { - qdisc_qstats_backlog_inc(q, nskb); - q->q.qlen++; - } break; } skb->next = nskb; @@ -628,6 +628,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, int band = prio2band[skb->priority & TC_PRIO_MAX]; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct skb_array *q = band2list(priv, band); + unsigned int pkt_len = qdisc_pkt_len(skb); int err; err = skb_array_produce(q, skb); @@ -636,7 +637,10 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, return qdisc_drop_cpu(skb, qdisc, to_free); qdisc_qstats_cpu_qlen_inc(qdisc); - qdisc_qstats_cpu_backlog_inc(qdisc, skb); + /* Note: skb can not be used after skb_array_produce(), + * so we better not use qdisc_qstats_cpu_backlog_inc() + */ + this_cpu_add(qdisc->cpu_qstats->backlog, pkt_len); return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 7c179addebcd..7d6801fc5340 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -509,7 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_all(skb, sch, to_free); qdisc_qstats_backlog_inc(sch, skb); diff --git a/net/sctp/input.c b/net/sctp/input.c index 0247cc432e02..b381d78548ac 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -106,6 +106,7 @@ int sctp_rcv(struct sk_buff *skb) int family; struct sctp_af *af; struct net *net = dev_net(skb->dev); + bool is_gso = skb_is_gso(skb) && skb_is_gso_sctp(skb); if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -123,8 +124,7 @@ int sctp_rcv(struct sk_buff *skb) * it's better to just linearize it otherwise crc computing * takes longer. */ - if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && - skb_linearize(skb)) || + if ((!is_gso && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; @@ -135,7 +135,7 @@ int sctp_rcv(struct sk_buff *skb) if (skb_csum_unnecessary(skb)) __skb_decr_checksum_unnecessary(skb); else if (!sctp_checksum_disable && - !(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + !is_gso && sctp_rcv_checksum(net, skb) < 0) goto discard_it; skb->csum_valid = 1; @@ -1218,7 +1218,7 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, * issue as packets hitting this are mostly INIT or INIT-ACK and * those cannot be on GSO-style anyway. */ - if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return NULL; ch = (struct sctp_chunkhdr *)skb->data; diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 48392552ee7c..23ebc5318edc 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -170,7 +170,7 @@ next_chunk: chunk = list_entry(entry, struct sctp_chunk, list); - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { + if (skb_is_gso(chunk->skb) && skb_is_gso_sctp(chunk->skb)) { /* GSO-marked skbs but without frags, handle * them normally */ diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 35bc7106d182..123e9f2dc226 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -45,7 +45,7 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EINVAL); struct sctphdr *sh; - if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP)) + if (!skb_is_gso_sctp(skb)) goto out; sh = sctp_hdr(skb); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 86913eb5cfa0..5f8046c62d90 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -983,10 +983,6 @@ out: lsmc->clcsock = NULL; } release_sock(lsk); - /* no more listening, wake up smc_close_wait_listen_clcsock and - * accept - */ - lsk->sk_state_change(lsk); sock_put(&lsmc->sk); /* sock_hold in smc_listen */ } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index e339c0186dcf..fa41d9881741 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -30,27 +30,6 @@ static void smc_close_cleanup_listen(struct sock *parent) smc_close_non_accepted(sk); } -static void smc_close_wait_listen_clcsock(struct smc_sock *smc) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - struct sock *sk = &smc->sk; - signed long timeout; - - timeout = SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME; - add_wait_queue(sk_sleep(sk), &wait); - do { - release_sock(sk); - if (smc->clcsock) - timeout = wait_woken(&wait, TASK_UNINTERRUPTIBLE, - timeout); - sched_annotate_sleep(); - lock_sock(sk); - if (!smc->clcsock) - break; - } while (timeout); - remove_wait_queue(sk_sleep(sk), &wait); -} - /* wait for sndbuf data being transmitted */ static void smc_close_stream_wait(struct smc_sock *smc, long timeout) { @@ -204,9 +183,11 @@ again: rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); /* wake up kernel_accept of smc_tcp_listen_worker */ smc->clcsock->sk->sk_data_ready(smc->clcsock->sk); - smc_close_wait_listen_clcsock(smc); } smc_close_cleanup_listen(sk); + release_sock(sk); + flush_work(&smc->tcp_listen_work); + lock_sock(sk); break; case SMC_ACTIVE: smc_close_stream_wait(smc, timeout); diff --git a/net/socket.c b/net/socket.c index d9a1ac233b35..3d1948d27a25 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2590,6 +2590,11 @@ void sock_unregister(int family) } EXPORT_SYMBOL(sock_unregister); +bool sock_is_registered(int family) +{ + return family < NPROTO && rcu_access_pointer(net_families[family]); +} + static int __init sock_init(void) { int err; diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index ccfdc7115a83..a00ec715aa46 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -283,7 +283,7 @@ static struct crypto_comp * __percpu *ipcomp_alloc_tfms(const char *alg_name) struct crypto_comp *tfm; /* This can be any valid CPU ID so we don't need locking. */ - tfm = __this_cpu_read(*pos->tfms); + tfm = this_cpu_read(*pos->tfms); if (!strcmp(crypto_comp_name(tfm), alg_name)) { pos->users++; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 77d9d1ab05ce..cb3bb9ae4407 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1458,10 +1458,13 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, static int xfrm_get_tos(const struct flowi *fl, int family) { const struct xfrm_policy_afinfo *afinfo; - int tos = 0; + int tos; afinfo = xfrm_policy_get_afinfo(family); - tos = afinfo ? afinfo->get_tos(fl) : 0; + if (!afinfo) + return 0; + + tos = afinfo->get_tos(fl); rcu_read_unlock(); @@ -1891,7 +1894,7 @@ static void xfrm_policy_queue_process(struct timer_list *t) spin_unlock(&pq->hold_queue.lock); dst_hold(xfrm_dst_path(dst)); - dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, 0); + dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) goto purge_queue; @@ -2729,14 +2732,14 @@ static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst, while (dst->xfrm) { const struct xfrm_state *xfrm = dst->xfrm; + dst = xfrm_dst_child(dst); + if (xfrm->props.mode == XFRM_MODE_TRANSPORT) continue; if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR) daddr = xfrm->coaddr; else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR)) daddr = &xfrm->id.daddr; - - dst = xfrm_dst_child(dst); } return daddr; } diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 1d38c6acf8af..9e3a5e85f828 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -660,7 +660,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff } else { XFRM_SKB_CB(skb)->seq.output.low = oseq + 1; XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi; - xo->seq.low = oseq = oseq + 1; + xo->seq.low = oseq + 1; xo->seq.hi = oseq_hi; oseq += skb_shinfo(skb)->gso_segs; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 54e21f19d722..f9d2f2233f09 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2056,6 +2056,11 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + return -EOPNOTSUPP; +#endif + if (!optval && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index aff2e84ec761..e92b8c019c88 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -121,22 +121,17 @@ static inline int verify_replay(struct xfrm_usersa_info *p, struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; struct xfrm_replay_state_esn *rs; - if (p->flags & XFRM_STATE_ESN) { - if (!rt) - return -EINVAL; + if (!rt) + return (p->flags & XFRM_STATE_ESN) ? -EINVAL : 0; - rs = nla_data(rt); + rs = nla_data(rt); - if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) - return -EINVAL; - - if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && - nla_len(rt) != sizeof(*rs)) - return -EINVAL; - } + if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) + return -EINVAL; - if (!rt) - return 0; + if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && + nla_len(rt) != sizeof(*rs)) + return -EINVAL; /* As only ESP and AH support ESN feature. */ if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH)) |