summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-07-24 17:31:47 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-07-24 17:31:47 -0700
commit0723090656a03940c5ea536342f109e34b8d1257 (patch)
treee44648aec5b63bbdd7ab71501b6207d6431dc709 /net
parentf89ed2f880ccb117246ba095e12087d9c3df89c5 (diff)
parent03bc7cab7d7218088412a75e141696a89059ab00 (diff)
downloadlwn-0723090656a03940c5ea536342f109e34b8d1257.tar.gz
lwn-0723090656a03940c5ea536342f109e34b8d1257.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller: 1) Handle stations tied to AP_VLANs properly during mac80211 hw reconfig. From Manikanta Pubbisetty. 2) Fix jump stack depth validation in nf_tables, from Taehee Yoo. 3) Fix quota handling in aRFS flow expiration of mlx5 driver, from Eran Ben Elisha. 4) Exit path handling fix in powerpc64 BPF JIT, from Daniel Borkmann. 5) Use ptr_ring_consume_bh() in page pool code, from Tariq Toukan. 6) Fix cached netdev name leak in nf_tables, from Florian Westphal. 7) Fix memory leaks on chain rename, also from Florian Westphal. 8) Several fixes to DCTCP congestion control ACK handling, from Yuchunk Cheng. 9) Missing rcu_read_unlock() in CAIF protocol code, from Yue Haibing. 10) Fix link local address handling with VRF, from David Ahern. 11) Don't clobber 'err' on a successful call to __skb_linearize() in skb_segment(). From Eric Dumazet. 12) Fix vxlan fdb notification races, from Roopa Prabhu. 13) Hash UDP fragments consistently, from Paolo Abeni. 14) If TCP receives lots of out of order tiny packets, we do really silly stuff. Make the out-of-order queue ending more robust to this kind of behavior, from Eric Dumazet. 15) Don't leak netlink dump state in nf_tables, from Florian Westphal. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (76 commits) net: axienet: Fix double deregister of mdio qmi_wwan: fix interface number for DW5821e production firmware ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull bnx2x: Fix invalid memory access in rss hash config path. net/mlx4_core: Save the qpn from the input modifier in RST2INIT wrapper r8169: restore previous behavior to accept BIOS WoL settings cfg80211: never ignore user regulatory hint sock: fix sg page frag coalescing in sk_alloc_sg netfilter: nf_tables: move dumper state allocation into ->start tcp: add tcp_ooo_try_coalesce() helper tcp: call tcp_drop() from tcp_data_queue_ofo() tcp: detect malicious patterns in tcp_collapse_ofo_queue() tcp: avoid collapses in tcp_prune_queue() if possible tcp: free batches of packets in tcp_prune_ofo_queue() ip: hash fragments consistently ipv6: use fib6_info_hold_safe() when necessary can: xilinx_can: fix power management handling can: xilinx_can: fix incorrect clear of non-processed interrupts can: xilinx_can: fix RX overflow interrupt not being enabled can: xilinx_can: keep only 1-2 frames in TX FIFO to fix TX accounting ...
Diffstat (limited to 'net')
-rw-r--r--net/caif/caif_dev.c4
-rw-r--r--net/core/page_pool.c2
-rw-r--r--net/core/rtnetlink.c9
-rw-r--r--net/core/skbuff.c10
-rw-r--r--net/core/sock.c6
-rw-r--r--net/ipv4/igmp.c3
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c7
-rw-r--r--net/ipv4/tcp_dctcp.c52
-rw-r--r--net/ipv4/tcp_input.c65
-rw-r--r--net/ipv4/tcp_output.c32
-rw-r--r--net/ipv6/addrconf.c3
-rw-r--r--net/ipv6/datagram.c7
-rw-r--r--net/ipv6/icmp.c5
-rw-r--r--net/ipv6/ip6_output.c2
-rw-r--r--net/ipv6/mcast.c3
-rw-r--r--net/ipv6/route.c41
-rw-r--r--net/ipv6/tcp_ipv6.c6
-rw-r--r--net/mac80211/rx.c5
-rw-r--r--net/mac80211/util.c3
-rw-r--r--net/netfilter/nf_conntrack_proto_dccp.c8
-rw-r--r--net/netfilter/nf_tables_api.c304
-rw-r--r--net/netfilter/nft_immediate.c3
-rw-r--r--net/netfilter/nft_lookup.c13
-rw-r--r--net/netfilter/nft_set_hash.c1
-rw-r--r--net/netfilter/nft_set_rbtree.c7
-rw-r--r--net/tls/tls_sw.c3
-rw-r--r--net/wireless/nl80211.c25
-rw-r--r--net/wireless/reg.c28
-rw-r--r--net/wireless/trace.h18
30 files changed, 390 insertions, 287 deletions
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index e0adcd123f48..711d7156efd8 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -131,8 +131,10 @@ static void caif_flow_cb(struct sk_buff *skb)
caifd = caif_get(skb->dev);
WARN_ON(caifd == NULL);
- if (caifd == NULL)
+ if (!caifd) {
+ rcu_read_unlock();
return;
+ }
caifd_hold(caifd);
rcu_read_unlock();
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 68bf07206744..43a932cb609b 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool)
struct page *page;
/* Empty recycle ring */
- while ((page = ptr_ring_consume(&pool->ring))) {
+ while ((page = ptr_ring_consume_bh(&pool->ring))) {
/* Verify the refcnt invariant of cached pages */
if (!(page_ref_count(page) == 1))
pr_crit("%s() page_pool refcnt %d violation\n",
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ef61222fdef..e3f743c141b3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2759,9 +2759,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
return err;
}
- dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
- __dev_notify_flags(dev, old_flags, ~0U);
+ if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+ __dev_notify_flags(dev, old_flags, 0U);
+ } else {
+ dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+ __dev_notify_flags(dev, old_flags, ~0U);
+ }
return 0;
}
EXPORT_SYMBOL(rtnl_configure_link);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8e51f8555e11..fb35b62af272 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3720,6 +3720,7 @@ normal:
net_warn_ratelimited(
"skb_segment: too many frags: %u %u\n",
pos, mss);
+ err = -EINVAL;
goto err;
}
@@ -3753,11 +3754,10 @@ skip_fraglist:
perform_csum_check:
if (!csum) {
- if (skb_has_shared_frag(nskb)) {
- err = __skb_linearize(nskb);
- if (err)
- goto err;
- }
+ if (skb_has_shared_frag(nskb) &&
+ __skb_linearize(nskb))
+ goto err;
+
if (!nskb->remcsum_offload)
nskb->ip_summed = CHECKSUM_NONE;
SKB_GSO_CB(nskb)->csum =
diff --git a/net/core/sock.c b/net/core/sock.c
index 9e8f65585b81..bc2d7a37297f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2277,9 +2277,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
pfrag->offset += use;
sge = sg + sg_curr - 1;
- if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page &&
- sg->offset + sg->length == orig_offset) {
- sg->length += use;
+ if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page &&
+ sge->offset + sge->length == orig_offset) {
+ sge->length += use;
} else {
sge = sg + sg_curr;
sg_unmark_end(sge);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index b3c899a630a0..28fef7d15959 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1200,8 +1200,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
spin_lock_bh(&im->lock);
if (pmc) {
im->interface = pmc->interface;
- im->sfmode = pmc->sfmode;
- if (pmc->sfmode == MCAST_INCLUDE) {
+ if (im->sfmode == MCAST_INCLUDE) {
im->tomb = pmc->tomb;
im->sources = pmc->sources;
for (psf = im->sources; psf; psf = psf->sf_next)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b3308e9d9762..0e3edd25f881 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->dev = from->dev;
to->mark = from->mark;
+ skb_copy_hash(to, from);
+
/* Copy the flags to each fragment. */
IPCB(to)->flags = IPCB(from)->flags;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 64c76dcf7386..c0fe5ad996f2 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
{
struct sockaddr_in sin;
const struct iphdr *iph = ip_hdr(skb);
- __be16 *ports = (__be16 *)skb_transport_header(skb);
+ __be16 *ports;
+ int end;
- if (skb_transport_offset(skb) + 4 > (int)skb->len)
+ end = skb_transport_offset(skb) + 4;
+ if (end > 0 && !pskb_may_pull(skb, end))
return;
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
+ ports = (__be16 *)skb_transport_header(skb);
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = iph->daddr;
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5869f89ca656..8b637f9f23a2 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -129,24 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
- /* State has changed from CE=0 to CE=1 and delayed
- * ACK has not sent yet.
- */
- if (!ca->ce_state &&
- inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
- u32 tmp_rcv_nxt;
-
- /* Save current rcv_nxt. */
- tmp_rcv_nxt = tp->rcv_nxt;
-
- /* Generate previous ack with CE=0. */
- tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
- tp->rcv_nxt = ca->prior_rcv_nxt;
-
- tcp_send_ack(sk);
-
- /* Recover current rcv_nxt. */
- tp->rcv_nxt = tmp_rcv_nxt;
+ if (!ca->ce_state) {
+ /* State has changed from CE=0 to CE=1, force an immediate
+ * ACK to reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+ __tcp_send_ack(sk, ca->prior_rcv_nxt);
+ tcp_enter_quickack_mode(sk, 1);
}
ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -160,24 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
- /* State has changed from CE=1 to CE=0 and delayed
- * ACK has not sent yet.
- */
- if (ca->ce_state &&
- inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
- u32 tmp_rcv_nxt;
-
- /* Save current rcv_nxt. */
- tmp_rcv_nxt = tp->rcv_nxt;
-
- /* Generate previous ack with CE=1. */
- tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
- tp->rcv_nxt = ca->prior_rcv_nxt;
-
- tcp_send_ack(sk);
-
- /* Recover current rcv_nxt. */
- tp->rcv_nxt = tmp_rcv_nxt;
+ if (ca->ce_state) {
+ /* State has changed from CE=1 to CE=0, force an immediate
+ * ACK to reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+ __tcp_send_ack(sk, ca->prior_rcv_nxt);
+ tcp_enter_quickack_mode(sk, 1);
}
ca->prior_rcv_nxt = tp->rcv_nxt;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8e5522c6833a..3bcd30a2ba06 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -215,7 +215,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
icsk->icsk_ack.quick = quickacks;
}
-static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
{
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -223,6 +223,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
icsk->icsk_ack.pingpong = 0;
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
/* Send ACKs quickly, if "quick" count is not exhausted
* and the session is not interactive.
@@ -4357,6 +4358,23 @@ static bool tcp_try_coalesce(struct sock *sk,
return true;
}
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+ struct sk_buff *to,
+ struct sk_buff *from,
+ bool *fragstolen)
+{
+ bool res = tcp_try_coalesce(sk, to, from, fragstolen);
+
+ /* In case tcp_drop() is called later, update to->gso_segs */
+ if (res) {
+ u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+ max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+ skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+ }
+ return res;
+}
+
static void tcp_drop(struct sock *sk, struct sk_buff *skb)
{
sk_drops_add(sk, skb);
@@ -4480,8 +4498,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
/* In the typical case, we are adding an skb to the end of the list.
* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
*/
- if (tcp_try_coalesce(sk, tp->ooo_last_skb,
- skb, &fragstolen)) {
+ if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
+ skb, &fragstolen)) {
coalesce_done:
tcp_grow_window(sk, skb);
kfree_skb_partial(skb, fragstolen);
@@ -4509,7 +4527,7 @@ coalesce_done:
/* All the bits are present. Drop. */
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb);
+ tcp_drop(sk, skb);
skb = NULL;
tcp_dsack_set(sk, seq, end_seq);
goto add_sack;
@@ -4528,11 +4546,11 @@ coalesce_done:
TCP_SKB_CB(skb1)->end_seq);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb1);
+ tcp_drop(sk, skb1);
goto merge_right;
}
- } else if (tcp_try_coalesce(sk, skb1,
- skb, &fragstolen)) {
+ } else if (tcp_ooo_try_coalesce(sk, skb1,
+ skb, &fragstolen)) {
goto coalesce_done;
}
p = &parent->rb_right;
@@ -4901,6 +4919,7 @@ end:
static void tcp_collapse_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 range_truesize, sum_tiny = 0;
struct sk_buff *skb, *head;
u32 start, end;
@@ -4912,6 +4931,7 @@ new_range:
}
start = TCP_SKB_CB(skb)->seq;
end = TCP_SKB_CB(skb)->end_seq;
+ range_truesize = skb->truesize;
for (head = skb;;) {
skb = skb_rb_next(skb);
@@ -4922,11 +4942,20 @@ new_range:
if (!skb ||
after(TCP_SKB_CB(skb)->seq, end) ||
before(TCP_SKB_CB(skb)->end_seq, start)) {
- tcp_collapse(sk, NULL, &tp->out_of_order_queue,
- head, skb, start, end);
+ /* Do not attempt collapsing tiny skbs */
+ if (range_truesize != head->truesize ||
+ end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+ tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+ head, skb, start, end);
+ } else {
+ sum_tiny += range_truesize;
+ if (sum_tiny > sk->sk_rcvbuf >> 3)
+ return;
+ }
goto new_range;
}
+ range_truesize += skb->truesize;
if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
start = TCP_SKB_CB(skb)->seq;
if (after(TCP_SKB_CB(skb)->end_seq, end))
@@ -4941,6 +4970,7 @@ new_range:
* 2) not add too big latencies if thousands of packets sit there.
* (But if application shrinks SO_RCVBUF, we could still end up
* freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
*
* Return true if queue has shrunk.
*/
@@ -4948,20 +4978,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct rb_node *node, *prev;
+ int goal;
if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
return false;
NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+ goal = sk->sk_rcvbuf >> 3;
node = &tp->ooo_last_skb->rbnode;
do {
prev = rb_prev(node);
rb_erase(node, &tp->out_of_order_queue);
+ goal -= rb_to_skb(node)->truesize;
tcp_drop(sk, rb_to_skb(node));
- sk_mem_reclaim(sk);
- if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
- !tcp_under_memory_pressure(sk))
- break;
+ if (!prev || goal <= 0) {
+ sk_mem_reclaim(sk);
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+ !tcp_under_memory_pressure(sk))
+ break;
+ goal = sk->sk_rcvbuf >> 3;
+ }
node = prev;
} while (node);
tp->ooo_last_skb = rb_to_skb(prev);
@@ -4996,6 +5032,9 @@ static int tcp_prune_queue(struct sock *sk)
else if (tcp_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+ return 0;
+
tcp_collapse_ofo_queue(sk);
if (!skb_queue_empty(&sk->sk_receive_queue))
tcp_collapse(sk, &sk->sk_receive_queue, NULL,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 00e5a300ddb9..c4172c1fb198 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
}
/* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+ u32 rcv_nxt)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
__sock_put(sk);
}
+
+ if (unlikely(rcv_nxt != tp->rcv_nxt))
+ return; /* Special ACK sent by DCTCP to reflect ECN */
tcp_dec_quickack_mode(sk, pkts);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
@@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
* We are working here with either a clone of the original
* SKB, or a fresh unique copy made by the retransmit engine.
*/
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
- gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+ int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet;
@@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
th->source = inet->inet_sport;
th->dest = inet->inet_dport;
th->seq = htonl(tcb->seq);
- th->ack_seq = htonl(tp->rcv_nxt);
+ th->ack_seq = htonl(rcv_nxt);
*(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
tcb->tcp_flags);
@@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
icsk->icsk_af_ops->send_check(sk, skb);
if (likely(tcb->tcp_flags & TCPHDR_ACK))
- tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+ tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
if (skb->len != tcp_header_size) {
tcp_event_data_sent(tp, sk);
@@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
return err;
}
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+ gfp_t gfp_mask)
+{
+ return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+ tcp_sk(sk)->rcv_nxt);
+}
+
/* This routine just queues the buffer for sending.
*
* NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -3571,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk)
}
/* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
{
struct sk_buff *buff;
@@ -3604,9 +3615,14 @@ void tcp_send_ack(struct sock *sk)
skb_set_tcp_pure_ack(buff);
/* Send it off, this clears delayed acks for us. */
- tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+ __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
}
-EXPORT_SYMBOL_GPL(tcp_send_ack);
/* This routine sends a packet with an out of date sequence
* number. It assumes the other end will try to ack it.
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 91580c62bb86..f66a1cae3366 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2374,7 +2374,8 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
continue;
if ((rt->fib6_flags & noflags) != 0)
continue;
- fib6_info_hold(rt);
+ if (!fib6_info_hold_safe(rt))
+ continue;
break;
}
out:
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2ee08b6a86a4..1a1f876f8e28 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -700,13 +700,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
}
if (np->rxopt.bits.rxorigdstaddr) {
struct sockaddr_in6 sin6;
- __be16 *ports = (__be16 *) skb_transport_header(skb);
+ __be16 *ports;
+ int end;
- if (skb_transport_offset(skb) + 4 <= (int)skb->len) {
+ end = skb_transport_offset(skb) + 4;
+ if (end <= 0 || pskb_may_pull(skb, end)) {
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
+ ports = (__be16 *)skb_transport_header(skb);
sin6.sin6_family = AF_INET6;
sin6.sin6_addr = ipv6_hdr(skb)->daddr;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index be491bf6ab6e..ef2505aefc15 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -402,9 +402,10 @@ static int icmp6_iif(const struct sk_buff *skb)
/* for local traffic to local address, skb dev is the loopback
* device. Check if there is a dst attached to the skb and if so
- * get the real device index.
+ * get the real device index. Same is needed for replies to a link
+ * local address on a device enslaved to an L3 master device
*/
- if (unlikely(iif == LOOPBACK_IFINDEX)) {
+ if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
const struct rt6_info *rt6 = skb_rt6_info(skb);
if (rt6)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a14fb4fcdf18..3168847c30d1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -570,6 +570,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->dev = from->dev;
to->mark = from->mark;
+ skb_copy_hash(to, from);
+
#ifdef CONFIG_NET_SCHED
to->tc_index = from->tc_index;
#endif
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 2699be7202be..f60f310785fd 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -790,8 +790,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
spin_lock_bh(&im->mca_lock);
if (pmc) {
im->idev = pmc->idev;
- im->mca_sfmode = pmc->mca_sfmode;
- if (pmc->mca_sfmode == MCAST_INCLUDE) {
+ if (im->mca_sfmode == MCAST_INCLUDE) {
im->mca_tomb = pmc->mca_tomb;
im->mca_sources = pmc->mca_sources;
for (psf = im->mca_sources; psf; psf = psf->sf_next)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2ce0bd17de4f..ec18b3ce8b6d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -972,10 +972,10 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
rt->dst.lastuse = jiffies;
}
+/* Caller must already hold reference to @from */
static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
{
rt->rt6i_flags &= ~RTF_EXPIRES;
- fib6_info_hold(from);
rcu_assign_pointer(rt->from, from);
dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
if (from->fib6_metrics != &dst_default_metrics) {
@@ -984,6 +984,7 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
}
}
+/* Caller must already hold reference to @ort */
static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
{
struct net_device *dev = fib6_info_nh_dev(ort);
@@ -1044,9 +1045,14 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
struct net_device *dev = rt->fib6_nh.nh_dev;
struct rt6_info *nrt;
+ if (!fib6_info_hold_safe(rt))
+ return NULL;
+
nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
if (nrt)
ip6_rt_copy_init(nrt, rt);
+ else
+ fib6_info_release(rt);
return nrt;
}
@@ -1178,10 +1184,15 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
* Clone the route.
*/
+ if (!fib6_info_hold_safe(ort))
+ return NULL;
+
dev = ip6_rt_get_dev_rcu(ort);
rt = ip6_dst_alloc(dev_net(dev), dev, 0);
- if (!rt)
+ if (!rt) {
+ fib6_info_release(ort);
return NULL;
+ }
ip6_rt_copy_init(rt, ort);
rt->rt6i_flags |= RTF_CACHE;
@@ -1210,12 +1221,17 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt)
struct net_device *dev;
struct rt6_info *pcpu_rt;
+ if (!fib6_info_hold_safe(rt))
+ return NULL;
+
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(rt);
pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags);
rcu_read_unlock();
- if (!pcpu_rt)
+ if (!pcpu_rt) {
+ fib6_info_release(rt);
return NULL;
+ }
ip6_rt_copy_init(pcpu_rt, rt);
pcpu_rt->rt6i_flags |= RTF_PCPU;
return pcpu_rt;
@@ -2486,7 +2502,7 @@ restart:
out:
if (ret)
- dst_hold(&ret->dst);
+ ip6_hold_safe(net, &ret, true);
else
ret = ip6_create_rt_rcu(rt);
@@ -3303,7 +3319,8 @@ static int ip6_route_del(struct fib6_config *cfg,
continue;
if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol)
continue;
- fib6_info_hold(rt);
+ if (!fib6_info_hold_safe(rt))
+ continue;
rcu_read_unlock();
/* if gateway was specified only delete the one hop */
@@ -3409,6 +3426,9 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
rcu_read_lock();
from = rcu_dereference(rt->from);
+ /* This fib6_info_hold() is safe here because we hold reference to rt
+ * and rt already holds reference to fib6_info.
+ */
fib6_info_hold(from);
rcu_read_unlock();
@@ -3470,7 +3490,8 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
continue;
if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
continue;
- fib6_info_hold(rt);
+ if (!fib6_info_hold_safe(rt))
+ continue;
break;
}
out:
@@ -3530,8 +3551,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net,
ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr))
break;
}
- if (rt)
- fib6_info_hold(rt);
+ if (rt && !fib6_info_hold_safe(rt))
+ rt = NULL;
rcu_read_unlock();
return rt;
}
@@ -3579,8 +3600,8 @@ restart:
struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL;
if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
- (!idev || idev->cnf.accept_ra != 2)) {
- fib6_info_hold(rt);
+ (!idev || idev->cnf.accept_ra != 2) &&
+ fib6_info_hold_safe(rt)) {
rcu_read_unlock();
ip6_del_rt(net, rt);
goto restart;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7efa9fd7e109..03e6b7a2bc53 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -938,7 +938,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
&tcp_hashinfo, NULL, 0,
&ipv6h->saddr,
th->source, &ipv6h->daddr,
- ntohs(th->source), tcp_v6_iif(skb),
+ ntohs(th->source),
+ tcp_v6_iif_l3_slave(skb),
tcp_v6_sdif(skb));
if (!sk1)
goto out;
@@ -1609,7 +1610,8 @@ do_time_wait:
skb, __tcp_hdrlen(th),
&ipv6_hdr(skb)->saddr, th->source,
&ipv6_hdr(skb)->daddr,
- ntohs(th->dest), tcp_v6_iif(skb),
+ ntohs(th->dest),
+ tcp_v6_iif_l3_slave(skb),
sdif);
if (sk2) {
struct inet_timewait_sock *tw = inet_twsk(sk);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 0a38cc1cbebc..932985ca4e66 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2254,11 +2254,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb,
sdata->control_port_over_nl80211)) {
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
bool noencrypt = status->flag & RX_FLAG_DECRYPTED;
- struct ethhdr *ehdr = eth_hdr(skb);
- cfg80211_rx_control_port(dev, skb->data, skb->len,
- ehdr->h_source,
- be16_to_cpu(skb->protocol), noencrypt);
+ cfg80211_rx_control_port(dev, skb, noencrypt);
dev_kfree_skb(skb);
} else {
/* deliver to local stack */
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 5e2e511c4a6f..d02fbfec3783 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2111,7 +2111,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
if (!sta->uploaded)
continue;
- if (sta->sdata->vif.type != NL80211_IFTYPE_AP)
+ if (sta->sdata->vif.type != NL80211_IFTYPE_AP &&
+ sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN)
continue;
for (state = IEEE80211_STA_NOTEXIST;
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index abe647d5b8c6..9ce6336d1e55 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -243,14 +243,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
* We currently ignore Sync packets
*
* sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
- sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
},
[DCCP_PKT_SYNCACK] = {
/*
* We currently ignore SyncAck packets
*
* sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
- sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
},
},
[CT_DCCP_ROLE_SERVER] = {
@@ -371,14 +371,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
* We currently ignore Sync packets
*
* sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
- sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
},
[DCCP_PKT_SYNCACK] = {
/*
* We currently ignore SyncAck packets
*
* sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
- sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
},
},
};
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 896d4a36081d..f5745e4c6513 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -75,6 +75,7 @@ static void nft_ctx_init(struct nft_ctx *ctx,
{
ctx->net = net;
ctx->family = family;
+ ctx->level = 0;
ctx->table = table;
ctx->chain = chain;
ctx->nla = nla;
@@ -1597,7 +1598,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
struct nft_base_chain *basechain;
struct nft_stats *stats = NULL;
struct nft_chain_hook hook;
- const struct nlattr *name;
struct nf_hook_ops *ops;
struct nft_trans *trans;
int err;
@@ -1645,12 +1645,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
return PTR_ERR(stats);
}
+ err = -ENOMEM;
trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN,
sizeof(struct nft_trans_chain));
- if (trans == NULL) {
- free_percpu(stats);
- return -ENOMEM;
- }
+ if (trans == NULL)
+ goto err;
nft_trans_chain_stats(trans) = stats;
nft_trans_chain_update(trans) = true;
@@ -1660,19 +1659,37 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
else
nft_trans_chain_policy(trans) = -1;
- name = nla[NFTA_CHAIN_NAME];
- if (nla[NFTA_CHAIN_HANDLE] && name) {
- nft_trans_chain_name(trans) =
- nla_strdup(name, GFP_KERNEL);
- if (!nft_trans_chain_name(trans)) {
- kfree(trans);
- free_percpu(stats);
- return -ENOMEM;
+ if (nla[NFTA_CHAIN_HANDLE] &&
+ nla[NFTA_CHAIN_NAME]) {
+ struct nft_trans *tmp;
+ char *name;
+
+ err = -ENOMEM;
+ name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL);
+ if (!name)
+ goto err;
+
+ err = -EEXIST;
+ list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) {
+ if (tmp->msg_type == NFT_MSG_NEWCHAIN &&
+ tmp->ctx.table == table &&
+ nft_trans_chain_update(tmp) &&
+ nft_trans_chain_name(tmp) &&
+ strcmp(name, nft_trans_chain_name(tmp)) == 0) {
+ kfree(name);
+ goto err;
+ }
}
+
+ nft_trans_chain_name(trans) = name;
}
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
+err:
+ free_percpu(stats);
+ kfree(trans);
+ return err;
}
static int nf_tables_newchain(struct net *net, struct sock *nlsk,
@@ -2254,6 +2271,39 @@ done:
return skb->len;
}
+static int nf_tables_dump_rules_start(struct netlink_callback *cb)
+{
+ const struct nlattr * const *nla = cb->data;
+ struct nft_rule_dump_ctx *ctx = NULL;
+
+ if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) {
+ ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
+ if (!ctx)
+ return -ENOMEM;
+
+ if (nla[NFTA_RULE_TABLE]) {
+ ctx->table = nla_strdup(nla[NFTA_RULE_TABLE],
+ GFP_ATOMIC);
+ if (!ctx->table) {
+ kfree(ctx);
+ return -ENOMEM;
+ }
+ }
+ if (nla[NFTA_RULE_CHAIN]) {
+ ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN],
+ GFP_ATOMIC);
+ if (!ctx->chain) {
+ kfree(ctx->table);
+ kfree(ctx);
+ return -ENOMEM;
+ }
+ }
+ }
+
+ cb->data = ctx;
+ return 0;
+}
+
static int nf_tables_dump_rules_done(struct netlink_callback *cb)
{
struct nft_rule_dump_ctx *ctx = cb->data;
@@ -2283,38 +2333,13 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start= nf_tables_dump_rules_start,
.dump = nf_tables_dump_rules,
.done = nf_tables_dump_rules_done,
.module = THIS_MODULE,
+ .data = (void *)nla,
};
- if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) {
- struct nft_rule_dump_ctx *ctx;
-
- ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
- if (!ctx)
- return -ENOMEM;
-
- if (nla[NFTA_RULE_TABLE]) {
- ctx->table = nla_strdup(nla[NFTA_RULE_TABLE],
- GFP_ATOMIC);
- if (!ctx->table) {
- kfree(ctx);
- return -ENOMEM;
- }
- }
- if (nla[NFTA_RULE_CHAIN]) {
- ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN],
- GFP_ATOMIC);
- if (!ctx->chain) {
- kfree(ctx->table);
- kfree(ctx);
- return -ENOMEM;
- }
- }
- c.data = ctx;
- }
-
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
@@ -2384,6 +2409,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
struct nft_rule *rule;
int err;
+ if (ctx->level == NFT_JUMP_STACK_SIZE)
+ return -EMLINK;
+
list_for_each_entry(rule, &chain->rules, list) {
if (!nft_is_active_next(ctx->net, rule))
continue;
@@ -3161,6 +3189,18 @@ done:
return skb->len;
}
+static int nf_tables_dump_sets_start(struct netlink_callback *cb)
+{
+ struct nft_ctx *ctx_dump = NULL;
+
+ ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC);
+ if (ctx_dump == NULL)
+ return -ENOMEM;
+
+ cb->data = ctx_dump;
+ return 0;
+}
+
static int nf_tables_dump_sets_done(struct netlink_callback *cb)
{
kfree(cb->data);
@@ -3188,18 +3228,12 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start = nf_tables_dump_sets_start,
.dump = nf_tables_dump_sets,
.done = nf_tables_dump_sets_done,
+ .data = &ctx,
.module = THIS_MODULE,
};
- struct nft_ctx *ctx_dump;
-
- ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC);
- if (ctx_dump == NULL)
- return -ENOMEM;
-
- *ctx_dump = ctx;
- c.data = ctx_dump;
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
@@ -3849,6 +3883,15 @@ nla_put_failure:
return -ENOSPC;
}
+static int nf_tables_dump_set_start(struct netlink_callback *cb)
+{
+ struct nft_set_dump_ctx *dump_ctx = cb->data;
+
+ cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC);
+
+ return cb->data ? 0 : -ENOMEM;
+}
+
static int nf_tables_dump_set_done(struct netlink_callback *cb)
{
kfree(cb->data);
@@ -4002,20 +4045,17 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start = nf_tables_dump_set_start,
.dump = nf_tables_dump_set,
.done = nf_tables_dump_set_done,
.module = THIS_MODULE,
};
- struct nft_set_dump_ctx *dump_ctx;
-
- dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC);
- if (!dump_ctx)
- return -ENOMEM;
-
- dump_ctx->set = set;
- dump_ctx->ctx = ctx;
+ struct nft_set_dump_ctx dump_ctx = {
+ .set = set,
+ .ctx = ctx,
+ };
- c.data = dump_ctx;
+ c.data = &dump_ctx;
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
@@ -4975,38 +5015,42 @@ done:
return skb->len;
}
-static int nf_tables_dump_obj_done(struct netlink_callback *cb)
+static int nf_tables_dump_obj_start(struct netlink_callback *cb)
{
- struct nft_obj_filter *filter = cb->data;
+ const struct nlattr * const *nla = cb->data;
+ struct nft_obj_filter *filter = NULL;
- if (filter) {
- kfree(filter->table);
- kfree(filter);
+ if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) {
+ filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
+ if (!filter)
+ return -ENOMEM;
+
+ if (nla[NFTA_OBJ_TABLE]) {
+ filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC);
+ if (!filter->table) {
+ kfree(filter);
+ return -ENOMEM;
+ }
+ }
+
+ if (nla[NFTA_OBJ_TYPE])
+ filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
}
+ cb->data = filter;
return 0;
}
-static struct nft_obj_filter *
-nft_obj_filter_alloc(const struct nlattr * const nla[])
+static int nf_tables_dump_obj_done(struct netlink_callback *cb)
{
- struct nft_obj_filter *filter;
-
- filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
- if (!filter)
- return ERR_PTR(-ENOMEM);
+ struct nft_obj_filter *filter = cb->data;
- if (nla[NFTA_OBJ_TABLE]) {
- filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC);
- if (!filter->table) {
- kfree(filter);
- return ERR_PTR(-ENOMEM);
- }
+ if (filter) {
+ kfree(filter->table);
+ kfree(filter);
}
- if (nla[NFTA_OBJ_TYPE])
- filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
- return filter;
+ return 0;
}
/* called with rcu_read_lock held */
@@ -5027,21 +5071,13 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start = nf_tables_dump_obj_start,
.dump = nf_tables_dump_obj,
.done = nf_tables_dump_obj_done,
.module = THIS_MODULE,
+ .data = (void *)nla,
};
- if (nla[NFTA_OBJ_TABLE] ||
- nla[NFTA_OBJ_TYPE]) {
- struct nft_obj_filter *filter;
-
- filter = nft_obj_filter_alloc(nla);
- if (IS_ERR(filter))
- return -ENOMEM;
-
- c.data = filter;
- }
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
@@ -5320,8 +5356,6 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
flowtable->ops[i].priv = &flowtable->data;
flowtable->ops[i].hook = flowtable->data.type->hook;
flowtable->ops[i].dev = dev_array[i];
- flowtable->dev_name[i] = kstrdup(dev_array[i]->name,
- GFP_KERNEL);
}
return err;
@@ -5479,10 +5513,8 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
err6:
i = flowtable->ops_len;
err5:
- for (k = i - 1; k >= 0; k--) {
- kfree(flowtable->dev_name[k]);
+ for (k = i - 1; k >= 0; k--)
nf_unregister_net_hook(net, &flowtable->ops[k]);
- }
kfree(flowtable->ops);
err4:
@@ -5581,9 +5613,10 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
goto nla_put_failure;
for (i = 0; i < flowtable->ops_len; i++) {
- if (flowtable->dev_name[i][0] &&
- nla_put_string(skb, NFTA_DEVICE_NAME,
- flowtable->dev_name[i]))
+ const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev);
+
+ if (dev &&
+ nla_put_string(skb, NFTA_DEVICE_NAME, dev->name))
goto nla_put_failure;
}
nla_nest_end(skb, nest_devs);
@@ -5650,37 +5683,39 @@ done:
return skb->len;
}
-static int nf_tables_dump_flowtable_done(struct netlink_callback *cb)
+static int nf_tables_dump_flowtable_start(struct netlink_callback *cb)
{
- struct nft_flowtable_filter *filter = cb->data;
+ const struct nlattr * const *nla = cb->data;
+ struct nft_flowtable_filter *filter = NULL;
- if (!filter)
- return 0;
+ if (nla[NFTA_FLOWTABLE_TABLE]) {
+ filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
+ if (!filter)
+ return -ENOMEM;
- kfree(filter->table);
- kfree(filter);
+ filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE],
+ GFP_ATOMIC);
+ if (!filter->table) {
+ kfree(filter);
+ return -ENOMEM;
+ }
+ }
+ cb->data = filter;
return 0;
}
-static struct nft_flowtable_filter *
-nft_flowtable_filter_alloc(const struct nlattr * const nla[])
+static int nf_tables_dump_flowtable_done(struct netlink_callback *cb)
{
- struct nft_flowtable_filter *filter;
+ struct nft_flowtable_filter *filter = cb->data;
- filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
if (!filter)
- return ERR_PTR(-ENOMEM);
+ return 0;
- if (nla[NFTA_FLOWTABLE_TABLE]) {
- filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE],
- GFP_ATOMIC);
- if (!filter->table) {
- kfree(filter);
- return ERR_PTR(-ENOMEM);
- }
- }
- return filter;
+ kfree(filter->table);
+ kfree(filter);
+
+ return 0;
}
/* called with rcu_read_lock held */
@@ -5700,20 +5735,13 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
+ .start = nf_tables_dump_flowtable_start,
.dump = nf_tables_dump_flowtable,
.done = nf_tables_dump_flowtable_done,
.module = THIS_MODULE,
+ .data = (void *)nla,
};
- if (nla[NFTA_FLOWTABLE_TABLE]) {
- struct nft_flowtable_filter *filter;
-
- filter = nft_flowtable_filter_alloc(nla);
- if (IS_ERR(filter))
- return -ENOMEM;
-
- c.data = filter;
- }
return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
}
@@ -5783,6 +5811,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
kfree(flowtable->name);
flowtable->data.type->free(&flowtable->data);
module_put(flowtable->data.type->owner);
+ kfree(flowtable);
}
static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
@@ -5825,7 +5854,6 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev,
continue;
nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]);
- flowtable->dev_name[i][0] = '\0';
flowtable->ops[i].dev = NULL;
break;
}
@@ -6086,6 +6114,9 @@ static void nft_commit_release(struct nft_trans *trans)
case NFT_MSG_DELTABLE:
nf_tables_table_destroy(&trans->ctx);
break;
+ case NFT_MSG_NEWCHAIN:
+ kfree(nft_trans_chain_name(trans));
+ break;
case NFT_MSG_DELCHAIN:
nf_tables_chain_destroy(&trans->ctx);
break;
@@ -6315,13 +6346,15 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE);
break;
case NFT_MSG_NEWCHAIN:
- if (nft_trans_chain_update(trans))
+ if (nft_trans_chain_update(trans)) {
nft_chain_commit_update(trans);
- else
+ nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+ /* trans destroyed after rcu grace period */
+ } else {
nft_clear(net, trans->ctx.chain);
-
- nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
- nft_trans_destroy(trans);
+ nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+ nft_trans_destroy(trans);
+ }
break;
case NFT_MSG_DELCHAIN:
nft_chain_del(trans->ctx.chain);
@@ -6471,7 +6504,7 @@ static int __nf_tables_abort(struct net *net)
case NFT_MSG_NEWCHAIN:
if (nft_trans_chain_update(trans)) {
free_percpu(nft_trans_chain_stats(trans));
-
+ kfree(nft_trans_chain_name(trans));
nft_trans_destroy(trans);
} else {
trans->ctx.table->use--;
@@ -6837,13 +6870,6 @@ int nft_validate_register_store(const struct nft_ctx *ctx,
err = nf_tables_check_loops(ctx, data->verdict.chain);
if (err < 0)
return err;
-
- if (ctx->chain->level + 1 >
- data->verdict.chain->level) {
- if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE)
- return -EMLINK;
- data->verdict.chain->level = ctx->chain->level + 1;
- }
}
return 0;
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 15adf8ca82c3..0777a93211e2 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -98,6 +98,7 @@ static int nft_immediate_validate(const struct nft_ctx *ctx,
const struct nft_data **d)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+ struct nft_ctx *pctx = (struct nft_ctx *)ctx;
const struct nft_data *data;
int err;
@@ -109,9 +110,11 @@ static int nft_immediate_validate(const struct nft_ctx *ctx,
switch (data->verdict.code) {
case NFT_JUMP:
case NFT_GOTO:
+ pctx->level++;
err = nft_chain_validate(ctx, data->verdict.chain);
if (err < 0)
return err;
+ pctx->level--;
break;
default:
break;
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 42e6fadf1417..c2a1d84cdfc4 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -155,7 +155,9 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx,
struct nft_set_elem *elem)
{
const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+ struct nft_ctx *pctx = (struct nft_ctx *)ctx;
const struct nft_data *data;
+ int err;
if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
*nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
@@ -165,10 +167,17 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx,
switch (data->verdict.code) {
case NFT_JUMP:
case NFT_GOTO:
- return nft_chain_validate(ctx, data->verdict.chain);
+ pctx->level++;
+ err = nft_chain_validate(ctx, data->verdict.chain);
+ if (err < 0)
+ return err;
+ pctx->level--;
+ break;
default:
- return 0;
+ break;
}
+
+ return 0;
}
static int nft_lookup_validate(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 72ef35b51cac..90c3e7e6cacb 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -387,6 +387,7 @@ static void nft_rhash_destroy(const struct nft_set *set)
struct nft_rhash *priv = nft_set_priv(set);
cancel_delayed_work_sync(&priv->gc_work);
+ rcu_barrier();
rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy,
(void *)set);
}
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 1f8f257cb518..9873d734b494 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -381,7 +381,7 @@ static void nft_rbtree_gc(struct work_struct *work)
gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
if (!gcb)
- goto out;
+ break;
atomic_dec(&set->nelems);
nft_set_gc_batch_add(gcb, rbe);
@@ -390,10 +390,12 @@ static void nft_rbtree_gc(struct work_struct *work)
rbe = rb_entry(prev, struct nft_rbtree_elem, node);
atomic_dec(&set->nelems);
nft_set_gc_batch_add(gcb, rbe);
+ prev = NULL;
}
node = rb_next(node);
+ if (!node)
+ break;
}
-out:
if (gcb) {
for (i = 0; i < gcb->head.cnt; i++) {
rbe = gcb->elems[i];
@@ -440,6 +442,7 @@ static void nft_rbtree_destroy(const struct nft_set *set)
struct rb_node *node;
cancel_delayed_work_sync(&priv->gc_work);
+ rcu_barrier();
while ((node = priv->root.rb_node) != NULL) {
rb_erase(node, &priv->root);
rbe = rb_entry(node, struct nft_rbtree_elem, node);
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4618f1c31137..1f3d9789af30 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -646,6 +646,9 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags,
return NULL;
}
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ return NULL;
+
if (sock_flag(sk, SOCK_DONE))
return NULL;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 4eece06be1e7..80bc986c79e5 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4409,6 +4409,7 @@ static int parse_station_flags(struct genl_info *info,
params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) |
BIT(NL80211_STA_FLAG_MFP) |
BIT(NL80211_STA_FLAG_AUTHORIZED);
+ break;
default:
return -EINVAL;
}
@@ -14923,20 +14924,24 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
EXPORT_SYMBOL(cfg80211_mgmt_tx_status);
static int __nl80211_rx_control_port(struct net_device *dev,
- const u8 *buf, size_t len,
- const u8 *addr, u16 proto,
+ struct sk_buff *skb,
bool unencrypted, gfp_t gfp)
{
struct wireless_dev *wdev = dev->ieee80211_ptr;
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+ struct ethhdr *ehdr = eth_hdr(skb);
+ const u8 *addr = ehdr->h_source;
+ u16 proto = be16_to_cpu(skb->protocol);
struct sk_buff *msg;
void *hdr;
+ struct nlattr *frame;
+
u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid);
if (!nlportid)
return -ENOENT;
- msg = nlmsg_new(100 + len, gfp);
+ msg = nlmsg_new(100 + skb->len, gfp);
if (!msg)
return -ENOMEM;
@@ -14950,13 +14955,17 @@ static int __nl80211_rx_control_port(struct net_device *dev,
nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev),
NL80211_ATTR_PAD) ||
- nla_put(msg, NL80211_ATTR_FRAME, len, buf) ||
nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) ||
nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) ||
(unencrypted && nla_put_flag(msg,
NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT)))
goto nla_put_failure;
+ frame = nla_reserve(msg, NL80211_ATTR_FRAME, skb->len);
+ if (!frame)
+ goto nla_put_failure;
+
+ skb_copy_bits(skb, 0, nla_data(frame), skb->len);
genlmsg_end(msg, hdr);
return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid);
@@ -14967,14 +14976,12 @@ static int __nl80211_rx_control_port(struct net_device *dev,
}
bool cfg80211_rx_control_port(struct net_device *dev,
- const u8 *buf, size_t len,
- const u8 *addr, u16 proto, bool unencrypted)
+ struct sk_buff *skb, bool unencrypted)
{
int ret;
- trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted);
- ret = __nl80211_rx_control_port(dev, buf, len, addr, proto,
- unencrypted, GFP_ATOMIC);
+ trace_cfg80211_rx_control_port(dev, skb, unencrypted);
+ ret = __nl80211_rx_control_port(dev, skb, unencrypted, GFP_ATOMIC);
trace_cfg80211_return_bool(ret == 0);
return ret == 0;
}
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index bbe6298e4bb9..4fc66a117b7d 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2240,7 +2240,9 @@ static void wiphy_update_regulatory(struct wiphy *wiphy,
* as some drivers used this to restore its orig_* reg domain.
*/
if (initiator == NL80211_REGDOM_SET_BY_CORE &&
- wiphy->regulatory_flags & REGULATORY_CUSTOM_REG)
+ wiphy->regulatory_flags & REGULATORY_CUSTOM_REG &&
+ !(wiphy->regulatory_flags &
+ REGULATORY_WIPHY_SELF_MANAGED))
reg_call_notifier(wiphy, lr);
return;
}
@@ -2787,26 +2789,6 @@ static void notify_self_managed_wiphys(struct regulatory_request *request)
}
}
-static bool reg_only_self_managed_wiphys(void)
-{
- struct cfg80211_registered_device *rdev;
- struct wiphy *wiphy;
- bool self_managed_found = false;
-
- ASSERT_RTNL();
-
- list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
- wiphy = &rdev->wiphy;
- if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
- self_managed_found = true;
- else
- return false;
- }
-
- /* make sure at least one self-managed wiphy exists */
- return self_managed_found;
-}
-
/*
* Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_*
* Regulatory hints come on a first come first serve basis and we
@@ -2839,10 +2821,6 @@ static void reg_process_pending_hints(void)
spin_unlock(&reg_requests_lock);
notify_self_managed_wiphys(reg_request);
- if (reg_only_self_managed_wiphys()) {
- reg_free_request(reg_request);
- return;
- }
reg_process_hint(reg_request);
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 2b417a2fe63f..7c73510b161f 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2627,23 +2627,25 @@ TRACE_EVENT(cfg80211_mgmt_tx_status,
);
TRACE_EVENT(cfg80211_rx_control_port,
- TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len,
- const u8 *addr, u16 proto, bool unencrypted),
- TP_ARGS(netdev, buf, len, addr, proto, unencrypted),
+ TP_PROTO(struct net_device *netdev, struct sk_buff *skb,
+ bool unencrypted),
+ TP_ARGS(netdev, skb, unencrypted),
TP_STRUCT__entry(
NETDEV_ENTRY
- MAC_ENTRY(addr)
+ __field(int, len)
+ MAC_ENTRY(from)
__field(u16, proto)
__field(bool, unencrypted)
),
TP_fast_assign(
NETDEV_ASSIGN;
- MAC_ASSIGN(addr, addr);
- __entry->proto = proto;
+ __entry->len = skb->len;
+ MAC_ASSIGN(from, eth_hdr(skb)->h_source);
+ __entry->proto = be16_to_cpu(skb->protocol);
__entry->unencrypted = unencrypted;
),
- TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s",
- NETDEV_PR_ARG, MAC_PR_ARG(addr),
+ TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s",
+ NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from),
__entry->proto, BOOL_TO_STR(__entry->unencrypted))
);