From f3c0eb05e258c6a48c2d1ef2fa71ffb6ff63cd18 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 18 May 2017 18:01:43 +0200 Subject: netfilter: conntrack: fix false CRC32c mismatch using paged skb sctp_compute_cksum() implementation assumes that at least the SCTP header is in the linear part of skb: modify conntrack error callback to avoid false CRC32c mismatch, if the transport header is partially/entirely paged. Fixes: cf6e007eef83 ("netfilter: conntrack: validate SCTP crc32c in PREROUTING") Signed-off-by: Davide Caratti Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_sctp.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 13875d5..1c5b14a 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -512,16 +512,19 @@ static int sctp_error(struct net *net, struct nf_conn *tpl, struct sk_buff *skb, u8 pf, unsigned int hooknum) { const struct sctphdr *sh; - struct sctphdr _sctph; const char *logmsg; - sh = skb_header_pointer(skb, dataoff, sizeof(_sctph), &_sctph); - if (!sh) { + if (skb->len < dataoff + sizeof(struct sctphdr)) { logmsg = "nf_ct_sctp: short packet "; goto out_invalid; } if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && skb->ip_summed == CHECKSUM_NONE) { + if (!skb_make_writable(skb, dataoff + sizeof(struct sctphdr))) { + logmsg = "nf_ct_sctp: failed to read header "; + goto out_invalid; + } + sh = (const struct sctphdr *)(skb->data + dataoff); if (sh->checksum != sctp_compute_cksum(skb, dataoff)) { logmsg = "nf_ct_sctp: bad CRC "; goto out_invalid; -- cgit v1.1 From d2df92e98a34a5619dadd29c6291113c009181e7 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 21 May 2017 00:37:10 +0200 Subject: netfilter: nft_set_rbtree: handle element re-addition after deletion The existing code selects no next branch to be inspected when re-inserting an inactive element into the rb-tree, looping endlessly. This patch restricts the check for active elements to the EEXIST case only. Fixes: e701001e7cbe ("netfilter: nft_rbtree: allow adjacent intervals with dynamic updates") Reported-by: Wolfgang Bumiller Tested-by: Wolfgang Bumiller Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_set_rbtree.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index e97e2fb..fbdbaa0 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -116,17 +116,17 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, else if (d > 0) p = &parent->rb_right; else { - if (nft_set_elem_active(&rbe->ext, genmask)) { - if (nft_rbtree_interval_end(rbe) && - !nft_rbtree_interval_end(new)) - p = &parent->rb_left; - else if (!nft_rbtree_interval_end(rbe) && - nft_rbtree_interval_end(new)) - p = &parent->rb_right; - else { - *ext = &rbe->ext; - return -EEXIST; - } + if (nft_rbtree_interval_end(rbe) && + !nft_rbtree_interval_end(new)) { + p = &parent->rb_left; + } else if (!nft_rbtree_interval_end(rbe) && + nft_rbtree_interval_end(new)) { + p = &parent->rb_right; + } else if (nft_set_elem_active(&rbe->ext, genmask)) { + *ext = &rbe->ext; + return -EEXIST; + } else { + p = &parent->rb_left; } } } -- cgit v1.1 From 124dffea9e8e372509e055aebd118e85518fd644 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 21 May 2017 22:38:11 +0800 Subject: netfilter: nat: use atomic bit op to clear the _SRC_NAT_DONE_BIT We need to clear the IPS_SRC_NAT_DONE_BIT to indicate that the ct has been removed from nat_bysource table. But unfortunately, we use the non-atomic bit operation: "ct->status &= ~IPS_NAT_DONE_MASK". So there's a race condition that we may clear the _DYING_BIT set by another CPU unexpectedly. Since we don't care about the IPS_DST_NAT_DONE_BIT, so just using clear_bit to clear the IPS_SRC_NAT_DONE_BIT is enough. Also note, this is the last user which use the non-atomic bit operation to update the confirmed ct->status. Reported-by: Florian Westphal Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index ef0be32..6c72922 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -566,7 +566,7 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack() * will delete entry from already-freed table. */ - ct->status &= ~IPS_NAT_DONE_MASK; + clear_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, nf_nat_bysource_params); -- cgit v1.1 From fefa92679dbe0c613e62b6c27235dcfbe9640ad1 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 21 May 2017 07:22:49 +0800 Subject: netfilter: ctnetlink: fix incorrect nf_ct_put during hash resize If nf_conntrack_htable_size was adjusted by the user during the ct dump operation, we may invoke nf_ct_put twice for the same ct, i.e. the "last" ct. This will cause the ct will be freed but still linked in hash buckets. It's very easy to reproduce the problem by the following commands: # while : ; do echo $RANDOM > /proc/sys/net/netfilter/nf_conntrack_buckets done # while : ; do conntrack -L done # iperf -s 127.0.0.1 & # iperf -c 127.0.0.1 -P 60 -t 36000 After a while, the system will hang like this: NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [bash:20184] NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [iperf:20382] ... So at last if we find cb->args[1] is equal to "last", this means hash resize happened, then we can set cb->args[1] to 0 to fix the above issue. Fixes: d205dc40798d ("[NETFILTER]: ctnetlink: fix deadlock in table dumping") Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9799a50..a8be9b7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -890,8 +890,13 @@ restart: } out: local_bh_enable(); - if (last) + if (last) { + /* nf ct hash resize happened, now clear the leftover. */ + if ((struct nf_conn *)cb->args[1] == last) + cb->args[1] = 0; + nf_ct_put(last); + } while (i) { i--; -- cgit v1.1 From 7a7c0a6438b8e7636d5a22e572892cc234f68297 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 27 May 2017 00:27:25 +0200 Subject: mac80211: fix TX aggregation start/stop callback race When starting or stopping an aggregation session, one of the steps is that the driver calls back to mac80211 that the start/stop can proceed. This is handled by queueing up a fake SKB and processing it from the normal iface/sdata work. Since this isn't flushed when disassociating, the following race is possible: * associate * start aggregation session * driver callback * disassociate * associate again to the same AP * callback processing runs, leading to a WARN_ON() that the TID hadn't requested aggregation If the second association isn't to the same AP, there would only be a message printed ("Could not find station: "), but the same race could happen. Fix this by not going the whole detour with a fake SKB etc. but simply looking up the aggregation session in the driver callback, marking it with a START_CB/STOP_CB bit and then scheduling the regular aggregation work that will now process these bits as well. This also simplifies the code and gets rid of the whole problem with allocation failures of said skb, which could have left the session in limbo. Reported-by: Jouni Malinen Signed-off-by: Johannes Berg --- net/mac80211/agg-tx.c | 128 ++++++++++++++++++--------------------------- net/mac80211/ht.c | 16 ++++-- net/mac80211/ieee80211_i.h | 14 ++--- net/mac80211/iface.c | 11 +--- net/mac80211/sta_info.h | 2 + 5 files changed, 71 insertions(+), 100 deletions(-) (limited to 'net') diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 60e2a62..cf2392b2 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -7,7 +7,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007, Michael Wu * Copyright 2007-2010, Intel Corporation - * Copyright(c) 2015 Intel Deutschland GmbH + * Copyright(c) 2015-2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -741,46 +741,43 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, ieee80211_agg_start_txq(sta, tid, true); } -void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid) +void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid, + struct tid_ampdu_tx *tid_tx) { - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - struct sta_info *sta; - struct tid_ampdu_tx *tid_tx; - trace_api_start_tx_ba_cb(sdata, ra, tid); + if (WARN_ON(test_and_set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state))) + return; + + if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) + ieee80211_agg_tx_operational(local, sta, tid); +} + +static struct tid_ampdu_tx * +ieee80211_lookup_tid_tx(struct ieee80211_sub_if_data *sdata, + const u8 *ra, u16 tid, struct sta_info **sta) +{ + struct tid_ampdu_tx *tid_tx; if (tid >= IEEE80211_NUM_TIDS) { ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n", tid, IEEE80211_NUM_TIDS); - return; + return NULL; } - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, ra); - if (!sta) { - mutex_unlock(&local->sta_mtx); + *sta = sta_info_get_bss(sdata, ra); + if (!*sta) { ht_dbg(sdata, "Could not find station: %pM\n", ra); - return; + return NULL; } - mutex_lock(&sta->ampdu_mlme.mtx); - tid_tx = rcu_dereference_protected_tid_tx(sta, tid); + tid_tx = rcu_dereference((*sta)->ampdu_mlme.tid_tx[tid]); - if (WARN_ON(!tid_tx)) { + if (WARN_ON(!tid_tx)) ht_dbg(sdata, "addBA was not requested!\n"); - goto unlock; - } - if (WARN_ON(test_and_set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state))) - goto unlock; - - if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) - ieee80211_agg_tx_operational(local, sta, tid); - - unlock: - mutex_unlock(&sta->ampdu_mlme.mtx); - mutex_unlock(&local->sta_mtx); + return tid_tx; } void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, @@ -788,19 +785,20 @@ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; - struct ieee80211_ra_tid *ra_tid; - struct sk_buff *skb = dev_alloc_skb(0); + struct sta_info *sta; + struct tid_ampdu_tx *tid_tx; - if (unlikely(!skb)) - return; + trace_api_start_tx_ba_cb(sdata, ra, tid); - ra_tid = (struct ieee80211_ra_tid *) &skb->cb; - memcpy(&ra_tid->ra, ra, ETH_ALEN); - ra_tid->tid = tid; + rcu_read_lock(); + tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta); + if (!tid_tx) + goto out; - skb->pkt_type = IEEE80211_SDATA_QUEUE_AGG_START; - skb_queue_tail(&sdata->skb_queue, skb); - ieee80211_queue_work(&local->hw, &sdata->work); + set_bit(HT_AGG_STATE_START_CB, &tid_tx->state); + ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work); + out: + rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_start_tx_ba_cb_irqsafe); @@ -860,37 +858,18 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid) } EXPORT_SYMBOL(ieee80211_stop_tx_ba_session); -void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) +void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, + struct tid_ampdu_tx *tid_tx) { - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); - struct ieee80211_local *local = sdata->local; - struct sta_info *sta; - struct tid_ampdu_tx *tid_tx; + struct ieee80211_sub_if_data *sdata = sta->sdata; bool send_delba = false; - trace_api_stop_tx_ba_cb(sdata, ra, tid); - - if (tid >= IEEE80211_NUM_TIDS) { - ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n", - tid, IEEE80211_NUM_TIDS); - return; - } - - ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n", ra, tid); - - mutex_lock(&local->sta_mtx); - - sta = sta_info_get_bss(sdata, ra); - if (!sta) { - ht_dbg(sdata, "Could not find station: %pM\n", ra); - goto unlock; - } + ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n", + sta->sta.addr, tid); - mutex_lock(&sta->ampdu_mlme.mtx); spin_lock_bh(&sta->lock); - tid_tx = rcu_dereference_protected_tid_tx(sta, tid); - if (!tid_tx || !test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { + if (!test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { ht_dbg(sdata, "unexpected callback to A-MPDU stop for %pM tid %d\n", sta->sta.addr, tid); @@ -906,12 +885,8 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) spin_unlock_bh(&sta->lock); if (send_delba) - ieee80211_send_delba(sdata, ra, tid, + ieee80211_send_delba(sdata, sta->sta.addr, tid, WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE); - - mutex_unlock(&sta->ampdu_mlme.mtx); - unlock: - mutex_unlock(&local->sta_mtx); } void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, @@ -919,19 +894,20 @@ void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; - struct ieee80211_ra_tid *ra_tid; - struct sk_buff *skb = dev_alloc_skb(0); + struct sta_info *sta; + struct tid_ampdu_tx *tid_tx; - if (unlikely(!skb)) - return; + trace_api_stop_tx_ba_cb(sdata, ra, tid); - ra_tid = (struct ieee80211_ra_tid *) &skb->cb; - memcpy(&ra_tid->ra, ra, ETH_ALEN); - ra_tid->tid = tid; + rcu_read_lock(); + tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta); + if (!tid_tx) + goto out; - skb->pkt_type = IEEE80211_SDATA_QUEUE_AGG_STOP; - skb_queue_tail(&sdata->skb_queue, skb); - ieee80211_queue_work(&local->hw, &sdata->work); + set_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state); + ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work); + out: + rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_stop_tx_ba_cb_irqsafe); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index f4a5287..6ca5442 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -7,6 +7,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007, Michael Wu * Copyright 2007-2010, Intel Corporation + * Copyright 2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -289,8 +290,6 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, { int i; - cancel_work_sync(&sta->ampdu_mlme.work); - for (i = 0; i < IEEE80211_NUM_TIDS; i++) { __ieee80211_stop_tx_ba_session(sta, i, reason); __ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, @@ -298,6 +297,9 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, reason != AGG_STOP_DESTROY_STA && reason != AGG_STOP_PEER_REQUEST); } + + /* stopping might queue the work again - so cancel only afterwards */ + cancel_work_sync(&sta->ampdu_mlme.work); } void ieee80211_ba_session_work(struct work_struct *work) @@ -352,10 +354,16 @@ void ieee80211_ba_session_work(struct work_struct *work) spin_unlock_bh(&sta->lock); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); - if (tid_tx && test_and_clear_bit(HT_AGG_STATE_WANT_STOP, - &tid_tx->state)) + if (!tid_tx) + continue; + + if (test_and_clear_bit(HT_AGG_STATE_START_CB, &tid_tx->state)) + ieee80211_start_tx_ba_cb(sta, tid, tid_tx); + if (test_and_clear_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state)) ___ieee80211_stop_tx_ba_session(sta, tid, AGG_STOP_LOCAL_REQUEST); + if (test_and_clear_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state)) + ieee80211_stop_tx_ba_cb(sta, tid, tid_tx); } mutex_unlock(&sta->ampdu_mlme.mtx); } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index f8f6c14..665501a 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1036,8 +1036,6 @@ struct ieee80211_rx_agg { enum sdata_queue_type { IEEE80211_SDATA_QUEUE_TYPE_FRAME = 0, - IEEE80211_SDATA_QUEUE_AGG_START = 1, - IEEE80211_SDATA_QUEUE_AGG_STOP = 2, IEEE80211_SDATA_QUEUE_RX_AGG_START = 3, IEEE80211_SDATA_QUEUE_RX_AGG_STOP = 4, }; @@ -1427,12 +1425,6 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata) return local->hw.wiphy->bands[band]; } -/* this struct represents 802.11n's RA/TID combination */ -struct ieee80211_ra_tid { - u8 ra[ETH_ALEN]; - u16 tid; -}; - /* this struct holds the value parsing from channel switch IE */ struct ieee80211_csa_ie { struct cfg80211_chan_def chandef; @@ -1794,8 +1786,10 @@ int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_agg_stop_reason reason); int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_agg_stop_reason reason); -void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid); -void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid); +void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid, + struct tid_ampdu_tx *tid_tx); +void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, + struct tid_ampdu_tx *tid_tx); void ieee80211_ba_session_work(struct work_struct *work); void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid); void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 3bd5b81..8fae1a7 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1237,7 +1237,6 @@ static void ieee80211_iface_work(struct work_struct *work) struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct sta_info *sta; - struct ieee80211_ra_tid *ra_tid; struct ieee80211_rx_agg *rx_agg; if (!ieee80211_sdata_running(sdata)) @@ -1253,15 +1252,7 @@ static void ieee80211_iface_work(struct work_struct *work) while ((skb = skb_dequeue(&sdata->skb_queue))) { struct ieee80211_mgmt *mgmt = (void *)skb->data; - if (skb->pkt_type == IEEE80211_SDATA_QUEUE_AGG_START) { - ra_tid = (void *)&skb->cb; - ieee80211_start_tx_ba_cb(&sdata->vif, ra_tid->ra, - ra_tid->tid); - } else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_AGG_STOP) { - ra_tid = (void *)&skb->cb; - ieee80211_stop_tx_ba_cb(&sdata->vif, ra_tid->ra, - ra_tid->tid); - } else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_START) { + if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_START) { rx_agg = (void *)&skb->cb; mutex_lock(&local->sta_mtx); sta = sta_info_get_bss(sdata, rx_agg->addr); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 5609cac..ea0747d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -116,6 +116,8 @@ enum ieee80211_sta_info_flags { #define HT_AGG_STATE_STOPPING 3 #define HT_AGG_STATE_WANT_START 4 #define HT_AGG_STATE_WANT_STOP 5 +#define HT_AGG_STATE_START_CB 6 +#define HT_AGG_STATE_STOP_CB 7 enum ieee80211_agg_stop_reason { AGG_STOP_DECLINED, -- cgit v1.1 From 15e5651525c2e580a523568ed207e4a3fb11cc33 Mon Sep 17 00:00:00 2001 From: Douglas Caetano dos Santos Date: Fri, 26 May 2017 14:28:00 -0300 Subject: tcp: reinitialize MTU probing when setting MSS in a TCP repair MTU probing initialization occurred only at connect() and at SYN or SYN-ACK reception, but the former sets MSS to either the default or the user set value (through TCP_MAXSEG sockopt) and the latter never happens with repaired sockets. The result was that, with MTU probing enabled and unless TCP_MAXSEG sockopt was used before connect(), probing would be stuck at tcp_base_mss value until tcp_probe_interval seconds have passed. Signed-off-by: Douglas Caetano dos Santos Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 59792d2..b5ea036 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2381,9 +2381,10 @@ static int tcp_repair_set_window(struct tcp_sock *tp, char __user *optbuf, int l return 0; } -static int tcp_repair_options_est(struct tcp_sock *tp, +static int tcp_repair_options_est(struct sock *sk, struct tcp_repair_opt __user *optbuf, unsigned int len) { + struct tcp_sock *tp = tcp_sk(sk); struct tcp_repair_opt opt; while (len >= sizeof(opt)) { @@ -2396,6 +2397,7 @@ static int tcp_repair_options_est(struct tcp_sock *tp, switch (opt.opt_code) { case TCPOPT_MSS: tp->rx_opt.mss_clamp = opt.opt_val; + tcp_mtup_init(sk); break; case TCPOPT_WINDOW: { @@ -2555,7 +2557,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (!tp->repair) err = -EINVAL; else if (sk->sk_state == TCP_ESTABLISHED) - err = tcp_repair_options_est(tp, + err = tcp_repair_options_est(sk, (struct tcp_repair_opt __user *)optval, optlen); else -- cgit v1.1 From c2e8471d98f072f0f18acdd7df5b401ed0d29a2c Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Tue, 30 May 2017 23:50:36 -0700 Subject: mpls: fix clearing of dead nh_flags on link up recent fixes to use WRITE_ONCE for nh_flags on link up, accidently ended up leaving the deadflags on a nh. This patch fixes the WRITE_ONCE to use freshly evaluated nh_flags. Fixes: 39eb8cd17588 ("net: mpls: rt_nhn_alive and nh_flags should be accessed using READ_ONCE") Reported-by: Satish Ashok Signed-off-by: Roopa Prabhu Acked-by: David Ahern Signed-off-by: David S. Miller --- net/mpls/af_mpls.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 257ec66..7b05fd1 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1418,7 +1418,7 @@ static void mpls_ifup(struct net_device *dev, unsigned int flags) continue; alive++; nh_flags &= ~flags; - WRITE_ONCE(nh->nh_flags, flags); + WRITE_ONCE(nh->nh_flags, nh_flags); } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); -- cgit v1.1 From 7212462fa6fdae61f7f40a4ead048def45bb23cb Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 1 Jun 2017 10:00:07 +0200 Subject: netlink: don't send unknown nsid The NETLINK_F_LISTEN_ALL_NSID otion enables to listen all netns that have a nsid assigned into the netns where the netlink socket is opened. The nsid is sent as metadata to userland, but the existence of this nsid is checked only for netns that are different from the socket netns. Thus, if no nsid is assigned to the socket netns, NETNSA_NSID_NOT_ASSIGNED is reported to the userland. This value is confusing and useless. After this patch, only valid nsid are sent to userland. Reported-by: Flavio Leitner Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index ee841f0..7586d44 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -62,6 +62,7 @@ #include #include #include +#include #include #include @@ -1415,7 +1416,8 @@ static void do_one_broadcast(struct sock *sk, goto out; } NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net); - NETLINK_CB(p->skb2).nsid_is_set = true; + if (NETLINK_CB(p->skb2).nsid != NETNSA_NSID_NOT_ASSIGNED) + NETLINK_CB(p->skb2).nsid_is_set = true; val = netlink_broadcast_deliver(sk, p->skb2); if (val < 0) { netlink_overrun(sk); -- cgit v1.1 From aeb073241fe7a2b932e04e20c60e47718332877f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 1 Jun 2017 18:07:55 +0300 Subject: net: bridge: start hello timer only if device is up When the transition of NO_STP -> KERNEL_STP was fixed by always calling mod_timer in br_stp_start, it introduced a new regression which causes the timer to be armed even when the bridge is down, and since we stop the timers in its ndo_stop() function, they never get disabled if the device is destroyed before it's upped. To reproduce: $ while :; do ip l add br0 type bridge hello_time 100; brctl stp br0 on; ip l del br0; done; CC: Xin Long CC: Ivan Vecera CC: Sebastian Ott Reported-by: Sebastian Ott Fixes: 6d18c732b95c ("bridge: start hello_timer when enabling KERNEL_STP in br_stp_start") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_stp_if.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 0db8102..6f12a52 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -179,7 +179,8 @@ static void br_stp_start(struct net_bridge *br) br_debug(br, "using kernel STP\n"); /* To start timers on any ports left in blocking */ - mod_timer(&br->hello_timer, jiffies + br->hello_time); + if (br->dev->flags & IFF_UP) + mod_timer(&br->hello_timer, jiffies + br->hello_time); br_port_state_selection(br); } -- cgit v1.1 From e165bc02a02c70e40d5c811c705ba269aeca0497 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 1 Jun 2017 21:26:03 +0200 Subject: mac80211: fix dropped counter in multiqueue RX In the commit enabling per-CPU station statistics, I inadvertedly copy-pasted some code to update rx_packets and forgot to change it to update rx_dropped_misc. Fix that. This addresses https://bugzilla.kernel.org/show_bug.cgi?id=195953. Fixes: c9c5962b56c1 ("mac80211: enable collecting station statistics per-CPU") Reported-by: Petru-Florin Mihancea Signed-off-by: Johannes Berg --- net/mac80211/sta_info.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 7cdf7a8..403e3cc 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2155,7 +2155,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) struct ieee80211_sta_rx_stats *cpurxs; cpurxs = per_cpu_ptr(sta->pcpu_rx_stats, cpu); - sinfo->rx_packets += cpurxs->dropped; + sinfo->rx_dropped_misc += cpurxs->dropped; } } -- cgit v1.1 From ac2629a4797fdc839f7a4775cc141e6f53e064cf Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 1 Jun 2017 19:53:04 -0700 Subject: net: dsa: Move dsa_switch_{suspend,resume} out of legacy.c dsa_switch_suspend() and dsa_switch_resume() are functions that belong in net/dsa/dsa.c and are not part of the legacy platform support code. Fixes: a6a71f19fe5e ("net: dsa: isolate legacy code") Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- net/dsa/dsa.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++ net/dsa/legacy.c | 47 ----------------------------------------------- 2 files changed, 47 insertions(+), 47 deletions(-) (limited to 'net') diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 26130ae..90038d4 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -223,6 +223,53 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, return 0; } +#ifdef CONFIG_PM_SLEEP +int dsa_switch_suspend(struct dsa_switch *ds) +{ + int i, ret = 0; + + /* Suspend slave network devices */ + for (i = 0; i < ds->num_ports; i++) { + if (!dsa_is_port_initialized(ds, i)) + continue; + + ret = dsa_slave_suspend(ds->ports[i].netdev); + if (ret) + return ret; + } + + if (ds->ops->suspend) + ret = ds->ops->suspend(ds); + + return ret; +} +EXPORT_SYMBOL_GPL(dsa_switch_suspend); + +int dsa_switch_resume(struct dsa_switch *ds) +{ + int i, ret = 0; + + if (ds->ops->resume) + ret = ds->ops->resume(ds); + + if (ret) + return ret; + + /* Resume slave network devices */ + for (i = 0; i < ds->num_ports; i++) { + if (!dsa_is_port_initialized(ds, i)) + continue; + + ret = dsa_slave_resume(ds->ports[i].netdev); + if (ret) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(dsa_switch_resume); +#endif + static struct packet_type dsa_pack_type __read_mostly = { .type = cpu_to_be16(ETH_P_XDSA), .func = dsa_switch_rcv, diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index ad345c8..7281098 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -289,53 +289,6 @@ static void dsa_switch_destroy(struct dsa_switch *ds) dsa_switch_unregister_notifier(ds); } -#ifdef CONFIG_PM_SLEEP -int dsa_switch_suspend(struct dsa_switch *ds) -{ - int i, ret = 0; - - /* Suspend slave network devices */ - for (i = 0; i < ds->num_ports; i++) { - if (!dsa_is_port_initialized(ds, i)) - continue; - - ret = dsa_slave_suspend(ds->ports[i].netdev); - if (ret) - return ret; - } - - if (ds->ops->suspend) - ret = ds->ops->suspend(ds); - - return ret; -} -EXPORT_SYMBOL_GPL(dsa_switch_suspend); - -int dsa_switch_resume(struct dsa_switch *ds) -{ - int i, ret = 0; - - if (ds->ops->resume) - ret = ds->ops->resume(ds); - - if (ret) - return ret; - - /* Resume slave network devices */ - for (i = 0; i < ds->num_ports; i++) { - if (!dsa_is_port_initialized(ds, i)) - continue; - - ret = dsa_slave_resume(ds->ports[i].netdev); - if (ret) - return ret; - } - - return 0; -} -EXPORT_SYMBOL_GPL(dsa_switch_resume); -#endif - /* platform driver init and cleanup *****************************************/ static int dev_is_class(struct device *dev, void *class) { -- cgit v1.1 From 6e80ac5cc992ab6256c3dae87f7e57db15e1a58c Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Wed, 31 May 2017 13:15:41 +0100 Subject: ipv6: xfrm: Handle errors reported by xfrm6_find_1stfragopt() xfrm6_find_1stfragopt() may now return an error code and we must not treat it as a length. Fixes: 2423496af35d ("ipv6: Prevent overrun when parsing v6 header options") Signed-off-by: Ben Hutchings Acked-by: Craig Gallek Signed-off-by: David S. Miller --- net/ipv6/xfrm6_mode_ro.c | 2 ++ net/ipv6/xfrm6_mode_transport.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'net') diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c index 0e01590..07d3657 100644 --- a/net/ipv6/xfrm6_mode_ro.c +++ b/net/ipv6/xfrm6_mode_ro.c @@ -47,6 +47,8 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) iph = ipv6_hdr(skb); hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + if (hdr_len < 0) + return hdr_len; skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); skb_set_network_header(skb, -x->props.header_len); skb->transport_header = skb->network_header + hdr_len; diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c index 7a92c0f..9ad07a9 100644 --- a/net/ipv6/xfrm6_mode_transport.c +++ b/net/ipv6/xfrm6_mode_transport.c @@ -30,6 +30,8 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) skb_set_inner_transport_header(skb, skb_transport_offset(skb)); hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + if (hdr_len < 0) + return hdr_len; skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); skb_set_network_header(skb, -x->props.header_len); skb->transport_header = skb->network_header + hdr_len; -- cgit v1.1 From 44abafc4cc094214a99f860f778c48ecb23422fc Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 31 May 2017 11:21:27 -0700 Subject: tcp: disallow cwnd undo when switching congestion control When the sender switches its congestion control during loss recovery, if the recovery is spurious then it may incorrectly revert cwnd and ssthresh to the older values set by a previous congestion control. Consider a congestion control (like BBR) that does not use ssthresh and keeps it infinite: the connection may incorrectly revert cwnd to an infinite value when switching from BBR to another congestion control. This patch fixes it by disallowing such cwnd undo operation upon switching congestion control. Note that undo_marker is not reset s.t. the packets that were incorrectly marked lost would be corrected. We only avoid undoing the cwnd in tcp_undo_cwnd_reduction(). Signed-off-by: Yuchung Cheng Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_cong.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 6e3c512..324c9bc 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -180,6 +180,7 @@ void tcp_init_congestion_control(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + tcp_sk(sk)->prior_ssthresh = 0; if (icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); if (tcp_ca_needs_ecn(sk)) -- cgit v1.1 From 5f733ee68f9a4df94775299ac6a7ab260704f6ed Mon Sep 17 00:00:00 2001 From: Liam McBirnie Date: Thu, 1 Jun 2017 15:36:01 +1000 Subject: ip6_tunnel: fix traffic class routing for tunnels ip6_route_output() requires that the flowlabel contains the traffic class for policy routing. Commit 0e9a709560db ("ip6_tunnel, ip6_gre: fix setting of DSCP on encapsulated packets") removed the code which previously added the traffic class to the flowlabel. The traffic class is added here because only route lookup needs the flowlabel to contain the traffic class. Fixes: 0e9a709560db ("ip6_tunnel, ip6_gre: fix setting of DSCP on encapsulated packets") Signed-off-by: Liam McBirnie Acked-by: Peter Dawson Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 7ae6c50..9b37f97 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1095,6 +1095,9 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, if (!dst) { route_lookup: + /* add dsfield to flowlabel for route lookup */ + fl6->flowlabel = ip6_make_flowinfo(dsfield, fl6->flowlabel); + dst = ip6_route_output(net, NULL, fl6); if (dst->error) -- cgit v1.1 From 38b257938ac6655d0d6333743303231b9c465ec1 Mon Sep 17 00:00:00 2001 From: Soheil Hassas Yeganeh Date: Fri, 2 Jun 2017 12:38:22 -0400 Subject: sock: reset sk_err when the error queue is empty Prior to f5f99309fa74 (sock: do not set sk_err in sock_dequeue_err_skb), sk_err was reset to the error of the skb on the head of the error queue. Applications, most notably ping, are relying on this behavior to reset sk_err for ICMP packets. Set sk_err to the ICMP error when there is an ICMP packet at the head of the error queue. Fixes: f5f99309fa74 (sock: do not set sk_err in sock_dequeue_err_skb) Reported-by: Cyril Hrubis Tested-by: Cyril Hrubis Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Eric Dumazet Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/core/skbuff.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 346d3e8..b1be7c0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3754,8 +3754,11 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk) spin_lock_irqsave(&q->lock, flags); skb = __skb_dequeue(q); - if (skb && (skb_next = skb_peek(q))) + if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); + if (icmp_next) + sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin; + } spin_unlock_irqrestore(&q->lock, flags); if (is_icmp_err_skb(skb) && !icmp_next) -- cgit v1.1 From e3e86b5119f81e5e2499bea7ea1ebe8ac6aab789 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 4 Jun 2017 21:41:10 -0400 Subject: ipv6: Fix leak in ipv6_gso_segment(). If ip6_find_1stfragopt() fails and we return an error we have to free up 'segs' because nobody else is going to. Fixes: 2423496af35d ("ipv6: Prevent overrun when parsing v6 header options") Reported-by: Ben Hutchings Signed-off-by: David S. Miller --- net/ipv6/ip6_offload.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 280268f..cdb3728 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -116,8 +116,10 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (udpfrag) { int err = ip6_find_1stfragopt(skb, &prevhdr); - if (err < 0) + if (err < 0) { + kfree_skb_list(segs); return ERR_PTR(err); + } fptr = (struct frag_hdr *)((u8 *)ipv6h + err); fptr->frag_off = htons(offset); if (skb->next) -- cgit v1.1 From b07ac9894644202614ca87c69f3f45e424a82fef Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 2 Jun 2017 22:05:23 -0700 Subject: net: dsa: Fix stale cpu_switch reference after unbind then bind Commit 9520ed8fb841 ("net: dsa: use cpu_switch instead of ds[0]") replaced the use of dst->ds[0] with dst->cpu_switch since that is functionally equivalent, however, we can now run into an use after free scenario after unbinding then rebinding the switch driver. The use after free happens because we do correctly initialize dst->cpu_switch the first time we probe in dsa_cpu_parse(), then we unbind the driver: dsa_dst_unapply() is called, and we rebind again. dst->cpu_switch now points to a freed "ds" structure, and so when we finally dereference it in dsa_cpu_port_ethtool_setup(), we oops. To fix this, simply set dst->cpu_switch to NULL in dsa_dst_unapply() which guarantees that we always correctly re-assign dst->cpu_switch in dsa_cpu_parse(). Fixes: 9520ed8fb841 ("net: dsa: use cpu_switch instead of ds[0]") Signed-off-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- net/dsa/dsa2.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 033b3bf..7796580 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -484,8 +484,10 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) dsa_ds_unapply(dst, ds); } - if (dst->cpu_switch) + if (dst->cpu_switch) { dsa_cpu_port_ethtool_restore(dst->cpu_switch); + dst->cpu_switch = NULL; + } pr_info("DSA: tree %d unapplied\n", dst->tree); dst->applied = false; -- cgit v1.1 From 77d4b1d36926a9b8387c6b53eeba42bcaaffcea3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 3 Jun 2017 09:29:25 -0700 Subject: net: ping: do not abuse udp_poll() Alexander reported various KASAN messages triggered in recent kernels The problem is that ping sockets should not use udp_poll() in the first place, and recent changes in UDP stack finally exposed this old bug. Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") Fixes: 6d0bfe226116 ("net: ipv6: Add IPv6 support to the ping socket.") Signed-off-by: Eric Dumazet Reported-by: Sasha Levin Cc: Solar Designer Cc: Vasiliy Kulikov Cc: Lorenzo Colitti Acked-By: Lorenzo Colitti Tested-By: Lorenzo Colitti Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 2 +- net/ipv6/ping.c | 2 +- net/ipv6/raw.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f3dad16..58925b6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1043,7 +1043,7 @@ static struct inet_protosw inetsw_array[] = .type = SOCK_DGRAM, .protocol = IPPROTO_ICMP, .prot = &ping_prot, - .ops = &inet_dgram_ops, + .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, }, diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 9b522fa..ac826dd 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -192,7 +192,7 @@ static struct inet_protosw pingv6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMPV6, .prot = &pingv6_prot, - .ops = &inet6_dgram_ops, + .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 1f992d9..60be012 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1338,7 +1338,7 @@ void raw6_proc_exit(void) #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ -static const struct proto_ops inet6_sockraw_ops = { +const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, -- cgit v1.1 From b699d0035836f6712917a41e7ae58d84359b8ff9 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Sun, 4 Jun 2017 14:43:43 +0800 Subject: sit: reload iphdr in ipip6_rcv Since iptunnel_pull_header() can call pskb_may_pull(), we must reload any pointer that was related to skb->head. Fixes: a09a4c8dd1ec ("tunnels: Remove encapsulation offloads on decap") Signed-off-by: Haishuang Yan Signed-off-by: David S. Miller --- net/ipv6/sit.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 61e5902..af832e7 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -657,6 +657,7 @@ static int ipip6_rcv(struct sk_buff *skb) if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6), !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out; + iph = ip_hdr(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { -- cgit v1.1 From 6044bd4a7d580d4459b992bc6631c817486a1514 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Mon, 5 Jun 2017 08:57:21 +0800 Subject: devlink: fix potential memort leak We must free allocated skb when genlmsg_put() return fails. Fixes: 1555d204e743 ("devlink: Support for pipeline debug (dpipe)") Signed-off-by: Haishuang Yan Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/devlink.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/core/devlink.c b/net/core/devlink.c index b0b87a2..a0adfc3 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1680,8 +1680,10 @@ start_again: hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &devlink_nl_family, NLM_F_MULTI, cmd); - if (!hdr) + if (!hdr) { + nlmsg_free(skb); return -EMSGSIZE; + } if (devlink_nl_put_handle(skb, devlink)) goto nla_put_failure; @@ -2098,8 +2100,10 @@ start_again: hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &devlink_nl_family, NLM_F_MULTI, cmd); - if (!hdr) + if (!hdr) { + nlmsg_free(skb); return -EMSGSIZE; + } if (devlink_nl_put_handle(skb, devlink)) goto nla_put_failure; -- cgit v1.1 From f4eb17e1efe538d4da7d574bedb00a8dafcc26b7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 6 Jun 2017 11:34:06 -0400 Subject: Revert "sit: reload iphdr in ipip6_rcv" This reverts commit b699d0035836f6712917a41e7ae58d84359b8ff9. As per Eric Dumazet, the pskb_may_pull() is a NOP in this particular case, so the 'iph' reload is unnecessary. Signed-off-by: David S. Miller --- net/ipv6/sit.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net') diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index af832e7..61e5902 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -657,7 +657,6 @@ static int ipip6_rcv(struct sk_buff *skb) if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6), !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out; - iph = ip_hdr(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { -- cgit v1.1 From e3ebdb20fddacded2740a333ff66781e0d28b05c Mon Sep 17 00:00:00 2001 From: Richard Haines Date: Mon, 5 Jun 2017 16:44:40 +0100 Subject: net/ipv6: Fix CALIPSO causing GPF with datagram support When using CALIPSO with IPPROTO_UDP it is possible to trigger a GPF as the IP header may have moved. Also update the payload length after adding the CALIPSO option. Signed-off-by: Richard Haines Acked-by: Paul Moore Signed-off-by: Huw Davies Signed-off-by: David S. Miller --- net/ipv6/calipso.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 37ac9de..8d772fe 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1319,7 +1319,7 @@ static int calipso_skbuff_setattr(struct sk_buff *skb, struct ipv6hdr *ip6_hdr; struct ipv6_opt_hdr *hop; unsigned char buf[CALIPSO_MAX_BUFFER]; - int len_delta, new_end, pad; + int len_delta, new_end, pad, payload; unsigned int start, end; ip6_hdr = ipv6_hdr(skb); @@ -1346,6 +1346,8 @@ static int calipso_skbuff_setattr(struct sk_buff *skb, if (ret_val < 0) return ret_val; + ip6_hdr = ipv6_hdr(skb); /* Reset as skb_cow() may have moved it */ + if (len_delta) { if (len_delta > 0) skb_push(skb, len_delta); @@ -1355,6 +1357,8 @@ static int calipso_skbuff_setattr(struct sk_buff *skb, sizeof(*ip6_hdr) + start); skb_reset_network_header(skb); ip6_hdr = ipv6_hdr(skb); + payload = ntohs(ip6_hdr->payload_len); + ip6_hdr->payload_len = htons(payload + len_delta); } hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1); -- cgit v1.1 From 1020ce3108cc26fbf09d70550ea2937cb1a211d2 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Jun 2017 01:26:24 +0300 Subject: net: bridge: fix a null pointer dereference in br_afspec We might call br_afspec() with p == NULL which is a valid use case if the action is on the bridge device itself, but the bridge tunnel code dereferences the p pointer without checking, so check if p is null first. Reported-by: Gustavo A. R. Silva Fixes: efa5356b0d97 ("bridge: per vlan dst_metadata netlink support") Signed-off-by: Nikolay Aleksandrov Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- net/bridge/br_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 574f788..32bd3ea 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -595,7 +595,7 @@ static int br_afspec(struct net_bridge *br, err = 0; switch (nla_type(attr)) { case IFLA_BRIDGE_VLAN_TUNNEL_INFO: - if (!(p->flags & BR_VLAN_TUNNEL)) + if (!p || !(p->flags & BR_VLAN_TUNNEL)) return -EINVAL; err = br_parse_vlan_tunnel_info(attr, &tinfo_curr); if (err) -- cgit v1.1