diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-03-05 11:29:24 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-03-05 11:29:24 -0800 |
commit | 547046141f44dba075207fd343e3e032e129c9ac (patch) | |
tree | 3979961d838def5efa9f3835d19e05d60b3b4d88 /net | |
parent | 661e50bc853209e41a5c14a290ca4decc43cbfd1 (diff) | |
parent | a7f0fb1bfb66ded5d556d6723d691b77a7146b6f (diff) | |
download | linux-547046141f44dba075207fd343e3e032e129c9ac.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
1) Use an appropriate TSQ pacing shift in mac80211, from Toke
Høiland-Jørgensen.
2) Just like ipv4's ip_route_me_harder(), we have to use skb_to_full_sk
in ip6_route_me_harder, from Eric Dumazet.
3) Fix several shutdown races and similar other problems in l2tp, from
James Chapman.
4) Handle missing XDP flush properly in tuntap, for real this time.
From Jason Wang.
5) Out-of-bounds access in powerpc ebpf tailcalls, from Daniel
Borkmann.
6) Fix phy_resume() locking, from Andrew Lunn.
7) IFLA_MTU values are ignored on newlink for some tunnel types, fix
from Xin Long.
8) Revert F-RTO middle box workarounds, they only handle one dimension
of the problem. From Yuchung Cheng.
9) Fix socket refcounting in RDS, from Ka-Cheong Poon.
10) Don't allow ppp unit registration to an unregistered channel, from
Guillaume Nault.
11) Various hv_netvsc fixes from Stephen Hemminger.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (98 commits)
hv_netvsc: propagate rx filters to VF
hv_netvsc: filter multicast/broadcast
hv_netvsc: defer queue selection to VF
hv_netvsc: use napi_schedule_irqoff
hv_netvsc: fix race in napi poll when rescheduling
hv_netvsc: cancel subchannel setup before halting device
hv_netvsc: fix error unwind handling if vmbus_open fails
hv_netvsc: only wake transmit queue if link is up
hv_netvsc: avoid retry on send during shutdown
virtio-net: re enable XDP_REDIRECT for mergeable buffer
ppp: prevent unregistered channels from connecting to PPP units
tc-testing: skbmod: fix match value of ethertype
mlxsw: spectrum_switchdev: Check success of FDB add operation
net: make skb_gso_*_seglen functions private
net: xfrm: use skb_gso_validate_network_len() to check gso sizes
net: sched: tbf: handle GSO_BY_FRAGS case in enqueue
net: rename skb_gso_validate_mtu -> skb_gso_validate_network_len
rds: Incorrect reference counting in TCP socket creation
net: ethtool: don't ignore return from driver get_fecparam method
vrf: check forwarding on the original netdevice when generating ICMP dest unreachable
...
Diffstat (limited to 'net')
58 files changed, 433 insertions, 357 deletions
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 79e326383726..99abeadf416e 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -157,7 +157,7 @@ static void batadv_iv_ogm_orig_free(struct batadv_orig_node *orig_node) * Return: 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, - int max_if_num) + unsigned int max_if_num) { void *data_ptr; size_t old_size; @@ -201,7 +201,8 @@ unlock: */ static void batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t chunk_size; size_t if_offset; @@ -239,7 +240,8 @@ batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, */ static void batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t if_offset; void *data_ptr; @@ -276,7 +278,8 @@ batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, * Return: 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); @@ -311,7 +314,8 @@ static struct batadv_orig_node * batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; - int size, hash_added; + int hash_added; + size_t size; orig_node = batadv_orig_hash_find(bat_priv, addr); if (orig_node) @@ -893,7 +897,7 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) u32 i; size_t word_index; u8 *w; - int if_num; + unsigned int if_num; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1023,7 +1027,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_neigh_node *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; - int if_num; + unsigned int if_num; u8 sum_orig, sum_neigh; u8 *neigh_addr; u8 tq_avg; @@ -1182,7 +1186,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, u8 total_count; u8 orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; - int if_num; + unsigned int if_num; unsigned int tq_asym_penalty, inv_asym_penalty; unsigned int combined_tq; unsigned int tq_iface_penalty; @@ -1702,9 +1706,9 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, if (is_my_orig) { unsigned long *word; - int offset; + size_t offset; s32 bit_pos; - s16 if_num; + unsigned int if_num; u8 *weight; orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, @@ -2729,7 +2733,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; struct batadv_gw_node *curr_gw; - int ret = -EINVAL; + int ret = 0; void *hdr; router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 27e165ac9302..c74f81341dab 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -928,7 +928,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; struct batadv_gw_node *curr_gw; - int ret = -EINVAL; + int ret = 0; void *hdr; router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index fad47853ad3c..b1a08374088b 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -2161,22 +2161,25 @@ batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_bla_claim *claim; int idx = 0; + int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { if (idx++ < *idx_skip) continue; - if (batadv_bla_claim_dump_entry(msg, portid, seq, - primary_if, claim)) { + + ret = batadv_bla_claim_dump_entry(msg, portid, seq, + primary_if, claim); + if (ret) { *idx_skip = idx - 1; goto unlock; } } - *idx_skip = idx; + *idx_skip = 0; unlock: rcu_read_unlock(); - return 0; + return ret; } /** @@ -2391,22 +2394,25 @@ batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_bla_backbone_gw *backbone_gw; int idx = 0; + int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (idx++ < *idx_skip) continue; - if (batadv_bla_backbone_dump_entry(msg, portid, seq, - primary_if, backbone_gw)) { + + ret = batadv_bla_backbone_dump_entry(msg, portid, seq, + primary_if, backbone_gw); + if (ret) { *idx_skip = idx - 1; goto unlock; } } - *idx_skip = idx; + *idx_skip = 0; unlock: rcu_read_unlock(); - return 0; + return ret; } /** diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 22dde42fd80e..5afe641ee4b0 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -288,7 +288,8 @@ batadv_frag_merge_packets(struct hlist_head *chain) /* Move the existing MAC header to just before the payload. (Override * the fragment header.) */ - skb_pull_rcsum(skb_out, hdr_size); + skb_pull(skb_out, hdr_size); + skb_out->ip_summed = CHECKSUM_NONE; memmove(skb_out->data - ETH_HLEN, skb_mac_header(skb_out), ETH_HLEN); skb_set_mac_header(skb_out, -ETH_HLEN); skb_reset_network_header(skb_out); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 5f186bff284a..68b54a39c51d 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -763,6 +763,11 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); + if (bat_priv->num_ifaces >= UINT_MAX) { + ret = -ENOSPC; + goto err_dev; + } + ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface, NULL, NULL, NULL); if (ret) @@ -876,7 +881,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface); /* nobody uses this interface anymore */ - if (!bat_priv->num_ifaces) { + if (bat_priv->num_ifaces == 0) { batadv_gw_check_client_stop(bat_priv); if (autodel == BATADV_IF_CLEANUP_AUTO) @@ -912,7 +917,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) if (ret) goto free_if; - hard_iface->if_num = -1; + hard_iface->if_num = 0; hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 58a7d9274435..74782426bb77 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1569,7 +1569,7 @@ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) * Return: 0 on success or negative error number in case of failure */ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_algo_ops *bao = bat_priv->algo_ops; @@ -1611,7 +1611,7 @@ err: * Return: 0 on success or negative error number in case of failure */ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 8e543a3cdc6c..15d896b2de6f 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -73,9 +73,9 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 900c5ce21cd4..367a81fb785f 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -459,13 +459,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* skb->dev & skb->pkt_type are set here */ skb->protocol = eth_type_trans(skb, soft_iface); - - /* should not be necessary anymore as we use skb_pull_rcsum() - * TODO: please verify this and remove this TODO - * -- Dec 21st 2009, Simon Wunderlich - */ - - /* skb->ip_summed = CHECKSUM_UNNECESSARY; */ + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); batadv_inc_counter(bat_priv, BATADV_CNT_RX); batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index bb1578410e0c..a5aa6d61f4e2 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -167,7 +167,7 @@ struct batadv_hard_iface { struct list_head list; /** @if_num: identificator of the interface */ - s16 if_num; + unsigned int if_num; /** @if_status: status of the interface for batman-adv */ char if_status; @@ -1596,7 +1596,7 @@ struct batadv_priv { atomic_t batman_queue_left; /** @num_ifaces: number of interfaces assigned to this mesh interface */ - char num_ifaces; + unsigned int num_ifaces; /** @mesh_obj: kobject for sysfs mesh subdirectory */ struct kobject *mesh_obj; @@ -2186,15 +2186,16 @@ struct batadv_algo_orig_ops { * orig_node due to a new hard-interface being added into the mesh * (optional) */ - int (*add_if)(struct batadv_orig_node *orig_node, int max_if_num); + int (*add_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num); /** * @del_if: ask the routing algorithm to apply the needed changes to the * orig_node due to an hard-interface being removed from the mesh * (optional) */ - int (*del_if)(struct batadv_orig_node *orig_node, int max_if_num, - int del_if_num); + int (*del_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num, unsigned int del_if_num); #ifdef CONFIG_BATMAN_ADV_DEBUGFS /** @print: print the originator table (optional) */ diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 27f1d4f2114a..9b16eaf33819 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -214,7 +214,7 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) - goto inhdr_error; + goto csum_error; len = ntohs(iph->tot_len); if (skb->len < len) { @@ -236,6 +236,8 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) */ return 0; +csum_error: + __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); drop: diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 51935270c651..9896f4975353 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -168,6 +168,8 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; + refcount_set(&masterv->refcnt, 1); + return masterv; } refcount_inc(&masterv->refcnt); diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c index ce7152a12bd8..c5afb4232ecb 100644 --- a/net/bridge/netfilter/ebt_among.c +++ b/net/bridge/netfilter/ebt_among.c @@ -172,18 +172,35 @@ ebt_among_mt(const struct sk_buff *skb, struct xt_action_param *par) return true; } +static bool poolsize_invalid(const struct ebt_mac_wormhash *w) +{ + return w && w->poolsize >= (INT_MAX / sizeof(struct ebt_mac_wormhash_tuple)); +} + static int ebt_among_mt_check(const struct xt_mtchk_param *par) { const struct ebt_among_info *info = par->matchinfo; const struct ebt_entry_match *em = container_of(par->matchinfo, const struct ebt_entry_match, data); - int expected_length = sizeof(struct ebt_among_info); + unsigned int expected_length = sizeof(struct ebt_among_info); const struct ebt_mac_wormhash *wh_dst, *wh_src; int err; + if (expected_length > em->match_size) + return -EINVAL; + wh_dst = ebt_among_wh_dst(info); - wh_src = ebt_among_wh_src(info); + if (poolsize_invalid(wh_dst)) + return -EINVAL; + expected_length += ebt_mac_wormhash_size(wh_dst); + if (expected_length > em->match_size) + return -EINVAL; + + wh_src = ebt_among_wh_src(info); + if (poolsize_invalid(wh_src)) + 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 02c4b409d317..254ef9f49567 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1641,7 +1641,8 @@ static int compat_match_to_user(struct ebt_entry_match *m, void __user **dstptr, int off = ebt_compat_match_offset(match, m->match_size); compat_uint_t msize = m->match_size - off; - BUG_ON(off >= m->match_size); + if (WARN_ON(off >= m->match_size)) + return -EINVAL; if (copy_to_user(cm->u.name, match->name, strlen(match->name) + 1) || put_user(msize, &cm->match_size)) @@ -1671,7 +1672,8 @@ static int compat_target_to_user(struct ebt_entry_target *t, int off = xt_compat_target_offset(target); compat_uint_t tsize = t->target_size - off; - BUG_ON(off >= t->target_size); + if (WARN_ON(off >= t->target_size)) + return -EINVAL; if (copy_to_user(cm->u.name, target->name, strlen(target->name) + 1) || put_user(tsize, &cm->match_size)) @@ -1902,7 +1904,8 @@ static int ebt_buf_add(struct ebt_entries_buf_state *state, if (state->buf_kern_start == NULL) goto count_only; - BUG_ON(state->buf_kern_offset + sz > state->buf_kern_len); + if (WARN_ON(state->buf_kern_offset + sz > state->buf_kern_len)) + return -EINVAL; memcpy(state->buf_kern_start + state->buf_kern_offset, data, sz); @@ -1915,7 +1918,8 @@ static int ebt_buf_add_pad(struct ebt_entries_buf_state *state, unsigned int sz) { char *b = state->buf_kern_start; - BUG_ON(b && state->buf_kern_offset > state->buf_kern_len); + if (WARN_ON(b && state->buf_kern_offset > state->buf_kern_len)) + return -EINVAL; if (b != NULL && sz > 0) memset(b + state->buf_kern_offset, 0, sz); @@ -1992,8 +1996,10 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, pad = XT_ALIGN(size_kern) - size_kern; if (pad > 0 && dst) { - BUG_ON(state->buf_kern_len <= pad); - BUG_ON(state->buf_kern_offset - (match_size + off) + size_kern > state->buf_kern_len - pad); + if (WARN_ON(state->buf_kern_len <= pad)) + return -EINVAL; + if (WARN_ON(state->buf_kern_offset - (match_size + off) + size_kern > state->buf_kern_len - pad)) + return -EINVAL; memset(dst + size_kern, 0, pad); } return off + match_size; @@ -2043,7 +2049,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (ret < 0) return ret; - BUG_ON(ret < match32->match_size); + if (WARN_ON(ret < match32->match_size)) + return -EINVAL; growth += ret - match32->match_size; growth += ebt_compat_entry_padsize(); @@ -2053,7 +2060,9 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - WARN_ON(type == EBT_COMPAT_TARGET && size_left); + if (WARN_ON(type == EBT_COMPAT_TARGET && size_left)) + return -EINVAL; + match32 = (struct compat_ebt_entry_mwt *) buf; } @@ -2109,6 +2118,15 @@ 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) + return -EINVAL; + if (i == 0) + continue; + if (offsets[i-1] > offsets[i]) + return -EINVAL; + } + for (i = 0, j = 1 ; j < 4 ; j++, i++) { struct compat_ebt_entry_mwt *match32; unsigned int size; @@ -2140,7 +2158,8 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, startoff = state->buf_user_offset - startoff; - BUG_ON(*total < startoff); + if (WARN_ON(*total < startoff)) + return -EINVAL; *total -= startoff; return 0; } @@ -2267,7 +2286,8 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - BUG_ON(ret < 0); /* parses same data again */ + if (WARN_ON(ret < 0)) + goto out_unlock; vfree(entries_tmp); tmp.entries_size = size64; diff --git a/net/core/dev.c b/net/core/dev.c index d4362befe7e2..2cedf520cb28 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6396,6 +6396,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, .linking = true, .upper_info = upper_info, }; + struct net_device *master_dev; int ret = 0; ASSERT_RTNL(); @@ -6407,11 +6408,14 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; - if (netdev_has_upper_dev(dev, upper_dev)) - return -EEXIST; - - if (master && netdev_master_upper_dev_get(dev)) - return -EBUSY; + if (!master) { + if (netdev_has_upper_dev(dev, upper_dev)) + return -EEXIST; + } else { + master_dev = netdev_master_upper_dev_get(dev); + if (master_dev) + return master_dev == upper_dev ? -EEXIST : -EBUSY; + } ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); diff --git a/net/core/devlink.c b/net/core/devlink.c index 18d385ed8237..2f2307d94787 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1695,10 +1695,11 @@ static int devlink_dpipe_table_put(struct sk_buff *skb, goto nla_put_failure; if (table->resource_valid) { - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, - table->resource_id, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, - table->resource_units, DEVLINK_ATTR_PAD); + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, + table->resource_id, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, + table->resource_units, DEVLINK_ATTR_PAD)) + goto nla_put_failure; } if (devlink_dpipe_matches_put(table, skb)) goto nla_put_failure; @@ -2332,7 +2333,7 @@ devlink_resource_validate_children(struct devlink_resource *resource) list_for_each_entry(child_resource, &resource->resource_list, list) parts_size += child_resource->size_new; - if (parts_size > resource->size) + if (parts_size > resource->size_new) size_valid = false; out: resource->size_valid = size_valid; @@ -2372,20 +2373,22 @@ static int devlink_nl_cmd_resource_set(struct sk_buff *skb, return 0; } -static void +static int devlink_resource_size_params_put(struct devlink_resource *resource, struct sk_buff *skb) { struct devlink_resource_size_params *size_params; - size_params = resource->size_params; - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, - size_params->size_granularity, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, - size_params->size_max, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, - size_params->size_min, DEVLINK_ATTR_PAD); - nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit); + size_params = &resource->size_params; + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, + size_params->size_granularity, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, + size_params->size_max, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, + size_params->size_min, DEVLINK_ATTR_PAD) || + nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit)) + return -EMSGSIZE; + return 0; } static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, @@ -2409,10 +2412,12 @@ static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_NEW, resource->size_new, DEVLINK_ATTR_PAD); if (resource->resource_ops && resource->resource_ops->occ_get) - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, - resource->resource_ops->occ_get(devlink), - DEVLINK_ATTR_PAD); - devlink_resource_size_params_put(resource, skb); + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, + resource->resource_ops->occ_get(devlink), + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (devlink_resource_size_params_put(resource, skb)) + goto nla_put_failure; if (list_empty(&resource->resource_list)) goto out; @@ -3151,7 +3156,7 @@ int devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops) { struct devlink_resource *resource; @@ -3194,7 +3199,8 @@ int devlink_resource_register(struct devlink *devlink, resource->id = resource_id; resource->resource_ops = resource_ops; resource->size_valid = true; - resource->size_params = size_params; + memcpy(&resource->size_params, size_params, + sizeof(resource->size_params)); INIT_LIST_HEAD(&resource->resource_list); list_add_tail(&resource->list, resource_list); out: diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 494e6a5d7306..3f89c76d5c24 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -2520,11 +2520,14 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr) static int ethtool_get_fecparam(struct net_device *dev, void __user *useraddr) { struct ethtool_fecparam fecparam = { ETHTOOL_GFECPARAM }; + int rc; if (!dev->ethtool_ops->get_fecparam) return -EOPNOTSUPP; - dev->ethtool_ops->get_fecparam(dev, &fecparam); + rc = dev->ethtool_ops->get_fecparam(dev, &fecparam); + if (rc) + return rc; if (copy_to_user(useraddr, &fecparam, sizeof(fecparam))) return -EFAULT; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 09bd89c90a71..0bb0d8877954 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4891,7 +4891,7 @@ EXPORT_SYMBOL_GPL(skb_scrub_packet); * * The MAC/L2 or network (IP, IPv6) headers are not accounted for. */ -unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) +static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int thlen = 0; @@ -4913,7 +4913,40 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) */ return thlen + shinfo->gso_size; } -EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + + return hdr_len + skb_gso_transport_seglen(skb); +} + +/** + * skb_gso_mac_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_mac_seglen is used to determine the real size of the + * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 + * headers (TCP/UDP). + */ +static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + + return hdr_len + skb_gso_transport_seglen(skb); +} /** * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS @@ -4955,19 +4988,20 @@ static inline bool skb_gso_size_check(const struct sk_buff *skb, } /** - * skb_gso_validate_mtu - Return in case such skb fits a given MTU + * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU? * * @skb: GSO skb * @mtu: MTU to validate against * - * skb_gso_validate_mtu validates if a given skb will fit a wanted MTU - * once split. + * skb_gso_validate_network_len validates if a given skb will fit a + * wanted MTU once split. It considers L3 headers, L4 headers, and the + * payload. */ -bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu) +bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu) { return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu); } -EXPORT_SYMBOL_GPL(skb_gso_validate_mtu); +EXPORT_SYMBOL_GPL(skb_gso_validate_network_len); /** * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length? diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 2dd21c3281a1..b54b948b0596 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -55,7 +55,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 45d97e9b2759..0901de42ed85 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -970,9 +970,6 @@ static void __gre_tunnel_init(struct net_device *dev) t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; - dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -1290,8 +1287,6 @@ static int erspan_tunnel_init(struct net_device *dev) erspan_hdr_len(tunnel->erspan_ver); t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e8e675be60ec..66340ab750e6 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -248,7 +248,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, /* common case: seglen is <= mtu */ - if (skb_gso_validate_mtu(skb, mtu)) + if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index d786a8441bce..6d21068f9b55 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -710,16 +710,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } } - if (tunnel->fwmark) { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - tunnel->fwmark); - } - else { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - skb->mark); - } + init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, + tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->fwmark); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 4b02ab39ebc5..8a8ae61cea71 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -232,7 +232,6 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->hash_mode = i->hash_mode; c->hash_initval = i->hash_initval; refcount_set(&c->refcount, 1); - refcount_set(&c->entries, 1); spin_lock_bh(&cn->lock); if (__clusterip_config_find(net, ip)) { @@ -263,8 +262,10 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->notifier.notifier_call = clusterip_netdev_event; err = register_netdevice_notifier(&c->notifier); - if (!err) + if (!err) { + refcount_set(&c->entries, 1); return c; + } #ifdef CONFIG_PROC_FS proc_remove(c->pde); @@ -273,7 +274,7 @@ err: spin_lock_bh(&cn->lock); list_del_rcu(&c->list); spin_unlock_bh(&cn->lock); - kfree(c); + clusterip_config_put(c); return ERR_PTR(err); } @@ -496,12 +497,15 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) return PTR_ERR(config); } } - cipinfo->config = config; ret = nf_ct_netns_get(par->net, par->family); - if (ret < 0) + if (ret < 0) { pr_info("cannot load conntrack support for proto=%u\n", par->family); + clusterip_config_entry_put(par->net, config); + clusterip_config_put(config); + return ret; + } if (!par->net->xt.clusterip_deprecated_warning) { pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, " @@ -509,6 +513,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) par->net->xt.clusterip_deprecated_warning = true; } + cipinfo->config = config; return ret; } diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index 25d2975da156..0cd46bffa469 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -111,6 +111,7 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, default: return -1; } + csum_replace4(&iph->check, addr, new_addr); return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); } @@ -185,7 +186,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a4f44d815a61..860b3fd2f54b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -128,10 +128,11 @@ static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; -static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; +static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; + /* * Interface to generic destination cache. */ @@ -930,14 +931,23 @@ out_put_peer: static int ip_error(struct sk_buff *skb) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); struct rtable *rt = skb_rtable(skb); + struct net_device *dev = skb->dev; + struct in_device *in_dev; struct inet_peer *peer; unsigned long now; struct net *net; bool send; int code; + if (netif_is_l3_master(skb->dev)) { + dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); + if (!dev) + goto out; + } + + in_dev = __in_dev_get_rcu(dev); + /* IP on this device is disabled. */ if (!in_dev) goto out; @@ -2818,6 +2828,7 @@ void ip_rt_multicast_event(struct in_device *in_dev) static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; +static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, void __user *buffer, @@ -2933,7 +2944,8 @@ static struct ctl_table ipv4_route_table[] = { .data = &ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &ip_min_valid_pmtu, }, { .procname = "min_adv_mss", diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 7c843578f233..faddf4f9a707 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -6,7 +6,7 @@ * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" - * http://www.ifp.illinois.edu/~srikant/Papers/liubassri06perf.pdf + * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 575d3c1fb6e8..9a1b3c1c1c14 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1971,11 +1971,6 @@ void tcp_enter_loss(struct sock *sk) /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous * loss recovery is underway except recurring timeout(s) on * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing - * - * In theory F-RTO can be used repeatedly during loss recovery. - * In practice this interacts badly with broken middle-boxes that - * falsely raise the receive window, which results in repeated - * timeouts and stop-and-go behavior. */ tp->frto = net->ipv4.sysctl_tcp_frto && (new_recovery || icsk->icsk_retransmits) && @@ -2631,18 +2626,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, tcp_try_undo_loss(sk, false)) return; - /* The ACK (s)acks some never-retransmitted data meaning not all - * the data packets before the timeout were lost. Therefore we - * undo the congestion window and state. This is essentially - * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since - * a retransmitted skb is permantly marked, we can apply such an - * operation even if F-RTO was not used. - */ - if ((flag & FLAG_ORIG_SACK_ACKED) && - tcp_try_undo_loss(sk, tp->undo_marker)) - return; - if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + if ((flag & FLAG_ORIG_SACK_ACKED) && + tcp_try_undo_loss(sk, true)) + return; + if (after(tp->snd_nxt, tp->high_seq)) { if (flag & FLAG_DATA_SACKED || is_dupack) tp->frto = 0; /* Step 3.a. loss was real */ @@ -4001,6 +3992,7 @@ void tcp_reset(struct sock *sk) /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); + tcp_write_queue_purge(sk); tcp_done(sk); if (!sock_flag(sk, SOCK_DEAD)) diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 94b8702603bc..be980c195fc5 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -30,7 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) mtu = dst_mtu(skb_dst(skb)); if ((!skb_is_gso(skb) && skb->len > mtu) || - (skb_is_gso(skb) && skb_gso_network_seglen(skb) > ip_skb_dst_mtu(skb->sk, skb))) { + (skb_is_gso(skb) && + !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) { skb->protocol = htons(ETH_P_IP); if (skb->sk) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 997c7f19ad62..a8a919520090 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -412,7 +412,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4b15fe928278..6e0f21eed88a 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1982,14 +1982,14 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - struct ip6_tnl *nt, *t; struct ip_tunnel_encap ipencap; + struct ip6_tnl *nt, *t; + int err; nt = netdev_priv(dev); if (ip6_tnl_netlink_encap_parms(data, &ipencap)) { - int err = ip6_tnl_encap_setup(nt, &ipencap); - + err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return err; } @@ -2005,7 +2005,11 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, return -EEXIST; } - return ip6_tnl_create2(dev); + err = ip6_tnl_create2(dev); + if (!err && tb[IFLA_MTU]) + ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + + return err; } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index d95ceca7ff8f..531d6957af36 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -21,18 +21,19 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); + struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; struct flowi6 fl6 = { - .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, + .flowi6_oif = sk ? sk->sk_bound_dev_if : 0, .flowi6_mark = skb->mark, - .flowi6_uid = sock_net_uid(net, skb->sk), + .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, .saddr = iph->saddr, }; int err; - dst = ip6_route_output(net, skb->sk, &fl6); + dst = ip6_route_output(net, sk, &fl6); err = dst->error; if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -50,7 +51,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) { skb_dst_set(skb, NULL); - dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0); + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); skb_dst_set(skb, dst); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 94deb69bbbda..91ed25a24b79 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -48,10 +48,6 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, } fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - if ((flags & XT_RPFILTER_LOOSE) == 0) { - fl6.flowi6_oif = dev->ifindex; - lookup_flags |= RT6_LOOKUP_F_IFACE; - } rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags); if (rt->dst.error) diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index d346705d6ee6..207cb35569b1 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -178,7 +178,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index bed57ee65f7b..6b7f075f811f 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -99,6 +99,10 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff, target, maniptype)) return false; + + /* must reload, offset might have changed */ + ipv6h = (void *)skb->data + iphdroff; + manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index cc5174c7254c..62fc84d7bdff 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -180,7 +180,6 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, } *dest = 0; - again: rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags); if (rt->dst.error) goto put_rt_err; @@ -189,15 +188,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; - if (oif && oif != rt->rt6i_idev->dev) { - /* multipath route? Try again with F_IFACE */ - if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) { - lookup_flags |= RT6_LOOKUP_F_IFACE; - fl6.flowi6_oif = oif->ifindex; - ip6_rt_put(rt); - goto again; - } - } + if (oif && oif != rt->rt6i_idev->dev) + goto put_rt_err; switch (priv->result) { case NFT_FIB_RESULT_OIF: diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3a1775a62973..0195598f7bb5 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1578,6 +1578,13 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + + if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len) + dev->mtu = mtu; + } + #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) err = ipip6_tunnel_update_6rd(nt, &ip6rd); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8ae87d4ec5ff..5959ce9620eb 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -82,7 +82,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && - skb_gso_network_seglen(skb) > ip6_skb_dst_mtu(skb))) { + !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) { skb->dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 194a7483bb93..83421c6f0bef 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -136,51 +136,6 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) } -/* Lookup the tunnel socket, possibly involving the fs code if the socket is - * owned by userspace. A struct sock returned from this function must be - * released using l2tp_tunnel_sock_put once you're done with it. - */ -static struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) -{ - int err = 0; - struct socket *sock = NULL; - struct sock *sk = NULL; - - if (!tunnel) - goto out; - - if (tunnel->fd >= 0) { - /* Socket is owned by userspace, who might be in the process - * of closing it. Look the socket up using the fd to ensure - * consistency. - */ - sock = sockfd_lookup(tunnel->fd, &err); - if (sock) - sk = sock->sk; - } else { - /* Socket is owned by kernelspace */ - sk = tunnel->sock; - sock_hold(sk); - } - -out: - return sk; -} - -/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */ -static void l2tp_tunnel_sock_put(struct sock *sk) -{ - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); - if (tunnel) { - if (tunnel->fd >= 0) { - /* Socket is owned by userspace */ - sockfd_put(sk->sk_socket); - } - sock_put(sk); - } - sock_put(sk); -} - /* Session hash list. * The session_id SHOULD be random according to RFC2661, but several * L2TP implementations (Cisco and Microsoft) use incrementing @@ -193,6 +148,13 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; } +void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) +{ + sock_put(tunnel->sock); + /* the tunnel is freed in the socket destructor */ +} +EXPORT_SYMBOL(l2tp_tunnel_free); + /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) { @@ -345,13 +307,11 @@ int l2tp_session_register(struct l2tp_session *session, } l2tp_tunnel_inc_refcount(tunnel); - sock_hold(tunnel->sock); hlist_add_head_rcu(&session->global_hlist, g_head); spin_unlock_bh(&pn->l2tp_session_hlist_lock); } else { l2tp_tunnel_inc_refcount(tunnel); - sock_hold(tunnel->sock); } hlist_add_head(&session->hlist, head); @@ -969,7 +929,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; - tunnel = l2tp_sock_to_tunnel(sk); + tunnel = l2tp_tunnel(sk); if (tunnel == NULL) goto pass_up; @@ -977,13 +937,10 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) tunnel->name, skb->len); if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook)) - goto pass_up_put; + goto pass_up; - sock_put(sk); return 0; -pass_up_put: - sock_put(sk); pass_up: return 1; } @@ -1207,14 +1164,12 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); static void l2tp_tunnel_destruct(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); - struct l2tp_net *pn; if (tunnel == NULL) goto end; l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); - /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: @@ -1231,18 +1186,11 @@ static void l2tp_tunnel_destruct(struct sock *sk) sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; - /* Remove the tunnel struct from the tunnel list */ - pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_del_rcu(&tunnel->list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - - tunnel->sock = NULL; - l2tp_tunnel_dec_refcount(tunnel); - /* Call the original destructor */ if (sk->sk_destruct) (*sk->sk_destruct)(sk); + + kfree_rcu(tunnel, rcu); end: return; } @@ -1303,49 +1251,43 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall); /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } + struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + + if (tunnel) + l2tp_tunnel_delete(tunnel); } /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { - struct l2tp_tunnel *tunnel = NULL; - struct socket *sock = NULL; - struct sock *sk = NULL; - - tunnel = container_of(work, struct l2tp_tunnel, del_work); + struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, + del_work); + struct sock *sk = tunnel->sock; + struct socket *sock = sk->sk_socket; + struct l2tp_net *pn; l2tp_tunnel_closeall(tunnel); - sk = l2tp_tunnel_sock_lookup(tunnel); - if (!sk) - goto out; - - sock = sk->sk_socket; - - /* If the tunnel socket was created by userspace, then go through the - * inet layer to shut the socket down, and let userspace close it. - * Otherwise, if we created the socket directly within the kernel, use + /* If the tunnel socket was created within the kernel, use * the sk API to release it here. - * In either case the tunnel resources are freed in the socket - * destructor when the tunnel socket goes away. */ - if (tunnel->fd >= 0) { - if (sock) - inet_shutdown(sock, 2); - } else { + if (tunnel->fd < 0) { if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } } - l2tp_tunnel_sock_put(sk); -out: + /* Remove the tunnel struct from the tunnel list */ + pn = l2tp_pernet(tunnel->l2tp_net); + spin_lock_bh(&pn->l2tp_tunnel_list_lock); + list_del_rcu(&tunnel->list); + spin_unlock_bh(&pn->l2tp_tunnel_list_lock); + + /* drop initial ref */ + l2tp_tunnel_dec_refcount(tunnel); + + /* drop workqueue ref */ l2tp_tunnel_dec_refcount(tunnel); } @@ -1598,13 +1540,22 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 sk->sk_user_data = tunnel; } + /* Bump the reference count. The tunnel context is deleted + * only when this drops to zero. A reference is also held on + * the tunnel socket to ensure that it is not released while + * the tunnel is extant. Must be done before sk_destruct is + * set. + */ + refcount_set(&tunnel->ref_count, 1); + sock_hold(sk); + tunnel->sock = sk; + tunnel->fd = fd; + /* Hook on the tunnel socket destructor so that we can cleanup * if the tunnel socket goes away. */ tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; - tunnel->sock = sk; - tunnel->fd = fd; lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; @@ -1614,11 +1565,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Add tunnel to our list */ INIT_LIST_HEAD(&tunnel->list); - - /* Bump the reference count. The tunnel context is deleted - * only when this drops to zero. Must be done before list insertion - */ - refcount_set(&tunnel->ref_count, 1); spin_lock_bh(&pn->l2tp_tunnel_list_lock); list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); spin_unlock_bh(&pn->l2tp_tunnel_list_lock); @@ -1659,8 +1605,6 @@ void l2tp_session_free(struct l2tp_session *session) if (tunnel) { BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - sock_put(tunnel->sock); - session->tunnel = NULL; l2tp_tunnel_dec_refcount(tunnel); } diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9bbee90e9963..a1aa9550f04e 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -214,27 +214,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session) return &session->priv[0]; } -static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk) -{ - struct l2tp_tunnel *tunnel; - - if (sk == NULL) - return NULL; - - sock_hold(sk); - tunnel = (struct l2tp_tunnel *)(sk->sk_user_data); - if (tunnel == NULL) { - sock_put(sk); - goto out; - } - - BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - -out: - return tunnel; -} - struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); +void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); struct l2tp_session *l2tp_session_get(const struct net *net, struct l2tp_tunnel *tunnel, @@ -283,7 +264,7 @@ static inline void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) - kfree_rcu(tunnel, rcu); + l2tp_tunnel_free(tunnel); } /* Session reference counts. Incremented when code obtains a reference diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index ff61124fdf59..3428fba6f2b7 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -234,17 +234,13 @@ static void l2tp_ip_close(struct sock *sk, long timeout) static void l2tp_ip_destroy_sock(struct sock *sk) { struct sk_buff *skb; - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + struct l2tp_tunnel *tunnel = sk->sk_user_data; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } - - sk_refcnt_debug_dec(sk); + if (tunnel) + l2tp_tunnel_delete(tunnel); } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 192344688c06..6f009eaa5fbe 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -248,16 +248,14 @@ static void l2tp_ip6_close(struct sock *sk, long timeout) static void l2tp_ip6_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + struct l2tp_tunnel *tunnel = sk->sk_user_data; lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } + if (tunnel) + l2tp_tunnel_delete(tunnel); inet6_destroy_sock(sk); } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 59f246d7b290..3b02f24ea9ec 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -416,20 +416,28 @@ abort: * Session (and tunnel control) socket create/destroy. *****************************************************************************/ +static void pppol2tp_put_sk(struct rcu_head *head) +{ + struct pppol2tp_session *ps; + + ps = container_of(head, typeof(*ps), rcu); + sock_put(ps->__sk); +} + /* Called by l2tp_core when a session socket is being closed. */ static void pppol2tp_session_close(struct l2tp_session *session) { - struct sock *sk; - - BUG_ON(session->magic != L2TP_SESSION_MAGIC); + struct pppol2tp_session *ps; - sk = pppol2tp_session_get_sock(session); - if (sk) { - if (sk->sk_socket) - inet_shutdown(sk->sk_socket, SEND_SHUTDOWN); - sock_put(sk); - } + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + if (ps->__sk) + call_rcu(&ps->rcu, pppol2tp_put_sk); + mutex_unlock(&ps->sk_lock); } /* Really kill the session socket. (Called from sock_put() if @@ -449,14 +457,6 @@ static void pppol2tp_session_destruct(struct sock *sk) } } -static void pppol2tp_put_sk(struct rcu_head *head) -{ - struct pppol2tp_session *ps; - - ps = container_of(head, typeof(*ps), rcu); - sock_put(ps->__sk); -} - /* Called when the PPPoX socket (session) is closed. */ static int pppol2tp_release(struct socket *sock) @@ -480,26 +480,17 @@ static int pppol2tp_release(struct socket *sock) sock_orphan(sk); sock->sk = NULL; + /* If the socket is associated with a session, + * l2tp_session_delete will call pppol2tp_session_close which + * will drop the session's ref on the socket. + */ session = pppol2tp_sock_to_session(sk); - - if (session != NULL) { - struct pppol2tp_session *ps; - + if (session) { l2tp_session_delete(session); - - ps = l2tp_session_priv(session); - mutex_lock(&ps->sk_lock); - ps->__sk = rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock)); - RCU_INIT_POINTER(ps->sk, NULL); - mutex_unlock(&ps->sk_lock); - call_rcu(&ps->rcu, pppol2tp_put_sk); - - /* Rely on the sock_put() call at the end of the function for - * dropping the reference held by pppol2tp_sock_to_session(). - * The last reference will be dropped by pppol2tp_put_sk(). - */ + /* drop the ref obtained by pppol2tp_sock_to_session */ + sock_put(sk); } + release_sock(sk); /* This will delete the session context via @@ -796,6 +787,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, out_no_ppp: /* This is how we get the session context from the socket. */ + sock_hold(sk); sk->sk_user_data = session; rcu_assign_pointer(ps->sk, sk); mutex_unlock(&ps->sk_lock); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fd580614085b..56fe16b07538 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3921,7 +3921,7 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, if ((hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS)) != fast_rx->expected_ds_bits) - goto drop; + return false; /* assign the key to drop unencrypted frames (later) * and strip the IV/MIC if necessary diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 25904af38839..69722504e3e1 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3574,6 +3574,14 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, if (!IS_ERR_OR_NULL(sta)) { struct ieee80211_fast_tx *fast_tx; + /* We need a bit of data queued to build aggregates properly, so + * instruct the TCP stack to allow more than a single ms of data + * to be queued in the stack. The value is a bit-shift of 1 + * second, so 8 is ~4ms of queued data. Only affects local TCP + * sockets. + */ + sk_pacing_shift_update(skb->sk, 8); + fast_tx = rcu_dereference(sta->fast_tx); if (fast_tx && diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index e545a3c9365f..7a4de6d618b1 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -122,7 +122,7 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 3e17d32b629d..58d5d05aec24 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -260,7 +260,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, buf_len = strlen(buf); ct = nf_ct_get(skb, &ctinfo); - if (ct && (ct->status & IPS_NAT_MASK)) { + if (ct) { bool mangled; /* If mangling fails this function will return 0 diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8b9fe30de0cd..558593e6a0a3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5037,9 +5037,9 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nf_flowtable_type *type; + struct nft_flowtable *flowtable, *ft; u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; - struct nft_flowtable *flowtable; struct nft_table *table; struct nft_ctx ctx; int err, i, k; @@ -5099,6 +5099,22 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, goto err3; for (i = 0; i < flowtable->ops_len; i++) { + if (!flowtable->ops[i].dev) + continue; + + list_for_each_entry(ft, &table->flowtables, list) { + for (k = 0; k < ft->ops_len; k++) { + if (!ft->ops[k].dev) + continue; + + if (flowtable->ops[i].dev == ft->ops[k].dev && + flowtable->ops[i].pf == ft->ops[k].pf) { + err = -EBUSY; + goto err4; + } + } + } + err = nf_register_net_hook(net, &flowtable->ops[i]); if (err < 0) goto err4; @@ -5120,7 +5136,7 @@ err5: i = flowtable->ops_len; err4: for (k = i - 1; k >= 0; k--) - nf_unregister_net_hook(net, &flowtable->ops[i]); + nf_unregister_net_hook(net, &flowtable->ops[k]); kfree(flowtable->ops); err3: @@ -5145,6 +5161,11 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, struct nft_table *table; struct nft_ctx ctx; + if (!nla[NFTA_FLOWTABLE_TABLE] || + (!nla[NFTA_FLOWTABLE_NAME] && + !nla[NFTA_FLOWTABLE_HANDLE])) + return -EINVAL; + table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask); if (IS_ERR(table)) diff --git a/net/qrtr/smd.c b/net/qrtr/smd.c index 50615d5efac1..9cf089b9754e 100644 --- a/net/qrtr/smd.c +++ b/net/qrtr/smd.c @@ -114,5 +114,6 @@ static struct rpmsg_driver qcom_smd_qrtr_driver = { module_rpmsg_driver(qcom_smd_qrtr_driver); +MODULE_ALIAS("rpmsg:IPCRTR"); MODULE_DESCRIPTION("Qualcomm IPC-Router SMD interface driver"); MODULE_LICENSE("GPL v2"); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index c061d6eb465d..22571189f21e 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 Oracle. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -142,12 +142,20 @@ int rds_tcp_accept_one(struct socket *sock) if (ret) goto out; - new_sock->type = sock->type; - new_sock->ops = sock->ops; ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); if (ret < 0) goto out; + /* sock_create_lite() does not get a hold on the owner module so we + * need to do it here. Note that sock_release() uses sock->ops to + * determine if it needs to decrement the reference count. So set + * sock->ops after calling accept() in case that fails. And there's + * no need to do try_module_get() as the listener should have a hold + * already. + */ + new_sock->ops = sock->ops; + __module_get(new_sock->ops->owner); + ret = rds_tcp_keepalive(new_sock); if (ret < 0) goto out; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 229172d509cc..03225a8df973 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -188,7 +188,8 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, int ret; if (qdisc_pkt_len(skb) > q->max_size) { - if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size) + if (skb_is_gso(skb) && + skb_gso_validate_mac_len(skb, q->max_size)) return tbf_segment(skb, sch, to_free); return qdisc_drop(skb, sch, to_free); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index da1a5cdefd13..8cc97834d4f6 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1406,8 +1406,10 @@ static int smc_create(struct net *net, struct socket *sock, int protocol, smc->use_fallback = false; /* assume rdma capability first */ rc = sock_create_kern(net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &smc->clcsock); - if (rc) + if (rc) { sk_common_release(sk); + goto out; + } smc->sk.sk_sndbuf = max(smc->clcsock->sk->sk_sndbuf, SMC_BUF_MIN_SIZE); smc->sk.sk_rcvbuf = max(smc->clcsock->sk->sk_rcvbuf, SMC_BUF_MIN_SIZE); diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 3cd086e5bd28..b42395d24cba 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -269,7 +269,7 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved)) return; /* short message */ - if (cdc->len != sizeof(*cdc)) + if (cdc->len != SMC_WR_TX_SIZE) return; /* invalid message */ smc_cdc_msg_recv(cdc, link, wc->wr_id); } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2424c7100aaf..645dd226177b 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -177,6 +177,7 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr, lnk = &lgr->lnk[SMC_SINGLE_LINK]; /* initialize link */ + lnk->link_id = SMC_SINGLE_LINK; lnk->smcibdev = smcibdev; lnk->ibport = ibport; lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu; @@ -465,7 +466,7 @@ create: rc = smc_link_determine_gid(conn->lgr); } conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; - conn->local_tx_ctrl.len = sizeof(struct smc_cdc_msg); + conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 92fe4cc8c82c..b4aa4fcedb96 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -92,7 +92,7 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[], memcpy(confllc->sender_mac, mac, ETH_ALEN); memcpy(confllc->sender_gid, gid, SMC_GID_SIZE); hton24(confllc->sender_qp_num, link->roce_qp->qp_num); - /* confllc->link_num = SMC_SINGLE_LINK; already done by memset above */ + confllc->link_num = link->link_id; memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE); confllc->max_links = SMC_LINKS_PER_LGR_MAX; /* send llc message */ diff --git a/net/tipc/group.c b/net/tipc/group.c index 122162a31816..04e516d18054 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -189,6 +189,7 @@ struct tipc_group *tipc_group_create(struct net *net, u32 portid, grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; grp->open = group_is_open; + *grp->open = false; filter |= global ? TIPC_SUB_CLUSTER_SCOPE : TIPC_SUB_NODE_SCOPE; if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, filter, &grp->subid)) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b0323ec7971e..7dfa9fc99ec3 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -473,6 +473,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, sk->sk_write_space = tipc_write_space; sk->sk_destruct = tipc_sock_destruct; tsk->conn_timeout = CONN_TIMEOUT_DEFAULT; + tsk->group_is_open = true; atomic_set(&tsk->dupl_rcvcnt, 0); /* Start out with safe limits until we receive an advertised window */ diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index e9b4b53ab53e..d824d548447e 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -46,16 +46,26 @@ MODULE_DESCRIPTION("Transport Layer Security Support"); MODULE_LICENSE("Dual BSD/GPL"); enum { + TLSV4, + TLSV6, + TLS_NUM_PROTS, +}; + +enum { TLS_BASE_TX, TLS_SW_TX, TLS_NUM_CONFIG, }; -static struct proto tls_prots[TLS_NUM_CONFIG]; +static struct proto *saved_tcpv6_prot; +static DEFINE_MUTEX(tcpv6_prot_mutex); +static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG]; static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx) { - sk->sk_prot = &tls_prots[ctx->tx_conf]; + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; + + sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf]; } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -453,8 +463,21 @@ static int tls_setsockopt(struct sock *sk, int level, int optname, return do_tls_setsockopt(sk, optname, optval, optlen); } +static void build_protos(struct proto *prot, struct proto *base) +{ + prot[TLS_BASE_TX] = *base; + prot[TLS_BASE_TX].setsockopt = tls_setsockopt; + prot[TLS_BASE_TX].getsockopt = tls_getsockopt; + prot[TLS_BASE_TX].close = tls_sk_proto_close; + + prot[TLS_SW_TX] = prot[TLS_BASE_TX]; + prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; + prot[TLS_SW_TX].sendpage = tls_sw_sendpage; +} + static int tls_init(struct sock *sk) { + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx; int rc = 0; @@ -479,6 +502,17 @@ static int tls_init(struct sock *sk) ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; + /* Build IPv6 TLS whenever the address of tcpv6_prot changes */ + if (ip_ver == TLSV6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + mutex_lock(&tcpv6_prot_mutex); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(tls_prots[TLSV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + mutex_unlock(&tcpv6_prot_mutex); + } + ctx->tx_conf = TLS_BASE_TX; update_sk_prot(sk, ctx); out: @@ -493,21 +527,9 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .init = tls_init, }; -static void build_protos(struct proto *prot, struct proto *base) -{ - prot[TLS_BASE_TX] = *base; - prot[TLS_BASE_TX].setsockopt = tls_setsockopt; - prot[TLS_BASE_TX].getsockopt = tls_getsockopt; - prot[TLS_BASE_TX].close = tls_sk_proto_close; - - prot[TLS_SW_TX] = prot[TLS_BASE_TX]; - prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; - prot[TLS_SW_TX].sendpage = tls_sw_sendpage; -} - static int __init tls_register(void) { - build_protos(tls_prots, &tcp_prot); + build_protos(tls_prots[TLSV4], &tcp_prot); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 1abcc4fc4df1..41722046b937 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -34,9 +34,10 @@ config CFG80211 When built as a module it will be called cfg80211. +if CFG80211 + config NL80211_TESTMODE bool "nl80211 testmode command" - depends on CFG80211 help The nl80211 testmode command helps implementing things like factory calibration or validation tools for wireless chips. @@ -51,7 +52,6 @@ config NL80211_TESTMODE config CFG80211_DEVELOPER_WARNINGS bool "enable developer warnings" - depends on CFG80211 default n help This option enables some additional warnings that help @@ -68,7 +68,7 @@ config CFG80211_DEVELOPER_WARNINGS config CFG80211_CERTIFICATION_ONUS bool "cfg80211 certification onus" - depends on CFG80211 && EXPERT + depends on EXPERT default n ---help--- You should disable this option unless you are both capable @@ -159,7 +159,6 @@ config CFG80211_REG_RELAX_NO_IR config CFG80211_DEFAULT_PS bool "enable powersave by default" - depends on CFG80211 default y help This option enables powersave mode by default. @@ -170,7 +169,6 @@ config CFG80211_DEFAULT_PS config CFG80211_DEBUGFS bool "cfg80211 DebugFS entries" - depends on CFG80211 depends on DEBUG_FS ---help--- You can enable this if you want debugfs entries for cfg80211. @@ -180,7 +178,6 @@ config CFG80211_DEBUGFS config CFG80211_CRDA_SUPPORT bool "support CRDA" if EXPERT default y - depends on CFG80211 help You should enable this option unless you know for sure you have no need for it, for example when using internal regdb (above) or the @@ -190,7 +187,6 @@ config CFG80211_CRDA_SUPPORT config CFG80211_WEXT bool "cfg80211 wireless extensions compatibility" if !CFG80211_WEXT_EXPORT - depends on CFG80211 select WEXT_CORE default y if CFG80211_WEXT_EXPORT help @@ -199,11 +195,12 @@ config CFG80211_WEXT config CFG80211_WEXT_EXPORT bool - depends on CFG80211 help Drivers should select this option if they require cfg80211's wext compatibility symbols to be exported. +endif # CFG80211 + config LIB80211 tristate default n diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 8e70291e586a..e87d6c4dd5b6 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -217,7 +217,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) if (skb->len <= mtu) goto ok; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } |