--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Date: Tue, 10 Nov 2015 16:23:15 +0100
+Subject: af-unix: fix use-after-free with concurrent readers while splicing
+
+From: Hannes Frederic Sowa <hannes@stressinduktion.org>
+
+[ Upstream commit 73ed5d25dce0354ea381d6dc93005c3085fae03d ]
+
+During splicing an af-unix socket to a pipe we have to drop all
+af-unix socket locks. While doing so we allow another reader to enter
+unix_stream_read_generic which can read, copy and finally free another
+skb. If exactly this skb is just in process of being spliced we get a
+use-after-free report by kasan.
+
+First, we must make sure to not have a free while the skb is used during
+the splice operation. We simply increment its use counter before unlocking
+the reader lock.
+
+Stream sockets have the nice characteristic that we don't care about
+zero length writes and they never reach the peer socket's queue. That
+said, we can take the UNIXCB.consumed field as the indicator if the
+skb was already freed from the socket's receive queue. If the skb was
+fully consumed after we locked the reader side again we know it has been
+dropped by a second reader. We indicate a short read to user space and
+abort the current splice operation.
+
+This bug has been found with syzkaller
+(http://github.com/google/syzkaller) by Dmitry Vyukov.
+
+Fixes: 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets")
+Reported-by: Dmitry Vyukov <dvyukov@google.com>
+Cc: Dmitry Vyukov <dvyukov@google.com>
+Cc: Eric Dumazet <eric.dumazet@gmail.com>
+Acked-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/unix/af_unix.c | 18 ++++++++++++++++++
+ 1 file changed, 18 insertions(+)
+
+--- a/net/unix/af_unix.c
++++ b/net/unix/af_unix.c
+@@ -440,6 +440,7 @@ static void unix_release_sock(struct soc
+ if (state == TCP_LISTEN)
+ unix_release_sock(skb->sk, 1);
+ /* passed fds are erased in the kfree_skb hook */
++ UNIXCB(skb).consumed = skb->len;
+ kfree_skb(skb);
+ }
+
+@@ -2071,6 +2072,7 @@ static int unix_stream_read_generic(stru
+
+ do {
+ int chunk;
++ bool drop_skb;
+ struct sk_buff *skb, *last;
+
+ unix_state_lock(sk);
+@@ -2151,7 +2153,11 @@ unlock:
+ }
+
+ chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
++ skb_get(skb);
+ chunk = state->recv_actor(skb, skip, chunk, state);
++ drop_skb = !unix_skb_len(skb);
++ /* skb is only safe to use if !drop_skb */
++ consume_skb(skb);
+ if (chunk < 0) {
+ if (copied == 0)
+ copied = -EFAULT;
+@@ -2160,6 +2166,18 @@ unlock:
+ copied += chunk;
+ size -= chunk;
+
++ if (drop_skb) {
++ /* the skb was touched by a concurrent reader;
++ * we should not expect anything from this skb
++ * anymore and assume it invalid - we can be
++ * sure it was dropped from the socket queue
++ *
++ * let's report a short read
++ */
++ err = 0;
++ break;
++ }
++
+ /* Mark read part of skb as used */
+ if (!(flags & MSG_PEEK)) {
+ UNIXCB(skb).consumed += chunk;
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Date: Thu, 26 Nov 2015 12:08:18 +0100
+Subject: af-unix: passcred support for sendpage
+
+From: Hannes Frederic Sowa <hannes@stressinduktion.org>
+
+[ Upstream commit 9490f886b192964796285907d777ff00fba1fa0f ]
+
+sendpage did not care about credentials at all. This could lead to
+situations in which because of fd passing between processes we could
+append data to skbs with different scm data. It is illegal to splice those
+skbs together. Instead we have to allocate a new skb and if requested
+fill out the scm details.
+
+Fixes: 869e7c62486ec ("net: af_unix: implement stream sendpage support")
+Reported-by: Al Viro <viro@zeniv.linux.org.uk>
+Cc: Al Viro <viro@zeniv.linux.org.uk>
+Cc: Eric Dumazet <edumazet@google.com>
+Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/unix/af_unix.c | 79 ++++++++++++++++++++++++++++++++++++++++++-----------
+ 1 file changed, 64 insertions(+), 15 deletions(-)
+
+--- a/net/unix/af_unix.c
++++ b/net/unix/af_unix.c
+@@ -1550,6 +1550,14 @@ static int unix_scm_to_skb(struct scm_co
+ return err;
+ }
+
++static bool unix_passcred_enabled(const struct socket *sock,
++ const struct sock *other)
++{
++ return test_bit(SOCK_PASSCRED, &sock->flags) ||
++ !other->sk_socket ||
++ test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
++}
++
+ /*
+ * Some apps rely on write() giving SCM_CREDENTIALS
+ * We include credentials if source or destination socket
+@@ -1560,14 +1568,41 @@ static void maybe_add_creds(struct sk_bu
+ {
+ if (UNIXCB(skb).pid)
+ return;
+- if (test_bit(SOCK_PASSCRED, &sock->flags) ||
+- !other->sk_socket ||
+- test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) {
++ if (unix_passcred_enabled(sock, other)) {
+ UNIXCB(skb).pid = get_pid(task_tgid(current));
+ current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
+ }
+ }
+
++static int maybe_init_creds(struct scm_cookie *scm,
++ struct socket *socket,
++ const struct sock *other)
++{
++ int err;
++ struct msghdr msg = { .msg_controllen = 0 };
++
++ err = scm_send(socket, &msg, scm, false);
++ if (err)
++ return err;
++
++ if (unix_passcred_enabled(socket, other)) {
++ scm->pid = get_pid(task_tgid(current));
++ current_uid_gid(&scm->creds.uid, &scm->creds.gid);
++ }
++ return err;
++}
++
++static bool unix_skb_scm_eq(struct sk_buff *skb,
++ struct scm_cookie *scm)
++{
++ const struct unix_skb_parms *u = &UNIXCB(skb);
++
++ return u->pid == scm->pid &&
++ uid_eq(u->uid, scm->creds.uid) &&
++ gid_eq(u->gid, scm->creds.gid) &&
++ unix_secdata_eq(scm, skb);
++}
++
+ /*
+ * Send AF_UNIX data.
+ */
+@@ -1883,8 +1918,10 @@ out_err:
+ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
+ int offset, size_t size, int flags)
+ {
+- int err = 0;
+- bool send_sigpipe = true;
++ int err;
++ bool send_sigpipe = false;
++ bool init_scm = true;
++ struct scm_cookie scm;
+ struct sock *other, *sk = socket->sk;
+ struct sk_buff *skb, *newskb = NULL, *tail = NULL;
+
+@@ -1902,7 +1939,7 @@ alloc_skb:
+ newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
+ &err, 0);
+ if (!newskb)
+- return err;
++ goto err;
+ }
+
+ /* we must acquire readlock as we modify already present
+@@ -1911,12 +1948,12 @@ alloc_skb:
+ err = mutex_lock_interruptible(&unix_sk(other)->readlock);
+ if (err) {
+ err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
+- send_sigpipe = false;
+ goto err;
+ }
+
+ if (sk->sk_shutdown & SEND_SHUTDOWN) {
+ err = -EPIPE;
++ send_sigpipe = true;
+ goto err_unlock;
+ }
+
+@@ -1925,17 +1962,27 @@ alloc_skb:
+ if (sock_flag(other, SOCK_DEAD) ||
+ other->sk_shutdown & RCV_SHUTDOWN) {
+ err = -EPIPE;
++ send_sigpipe = true;
+ goto err_state_unlock;
+ }
+
++ if (init_scm) {
++ err = maybe_init_creds(&scm, socket, other);
++ if (err)
++ goto err_state_unlock;
++ init_scm = false;
++ }
++
+ skb = skb_peek_tail(&other->sk_receive_queue);
+ if (tail && tail == skb) {
+ skb = newskb;
+- } else if (!skb) {
+- if (newskb)
++ } else if (!skb || !unix_skb_scm_eq(skb, &scm)) {
++ if (newskb) {
+ skb = newskb;
+- else
++ } else {
++ tail = skb;
+ goto alloc_skb;
++ }
+ } else if (newskb) {
+ /* this is fast path, we don't necessarily need to
+ * call to kfree_skb even though with newskb == NULL
+@@ -1956,6 +2003,9 @@ alloc_skb:
+ atomic_add(size, &sk->sk_wmem_alloc);
+
+ if (newskb) {
++ err = unix_scm_to_skb(&scm, skb, false);
++ if (err)
++ goto err_state_unlock;
+ spin_lock(&other->sk_receive_queue.lock);
+ __skb_queue_tail(&other->sk_receive_queue, newskb);
+ spin_unlock(&other->sk_receive_queue.lock);
+@@ -1965,7 +2015,7 @@ alloc_skb:
+ mutex_unlock(&unix_sk(other)->readlock);
+
+ other->sk_data_ready(other);
+-
++ scm_destroy(&scm);
+ return size;
+
+ err_state_unlock:
+@@ -1976,6 +2026,8 @@ err:
+ kfree_skb(newskb);
+ if (send_sigpipe && !(flags & MSG_NOSIGNAL))
+ send_sig(SIGPIPE, current, 0);
++ if (!init_scm)
++ scm_destroy(&scm);
+ return err;
+ }
+
+@@ -2279,10 +2331,7 @@ unlock:
+
+ if (check_creds) {
+ /* Never glue messages from different writers */
+- if ((UNIXCB(skb).pid != scm.pid) ||
+- !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
+- !gid_eq(UNIXCB(skb).gid, scm.creds.gid) ||
+- !unix_secdata_eq(&scm, skb))
++ if (!unix_skb_scm_eq(skb, &scm))
+ break;
+ } else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
+ /* Copy credentials */
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Date: Mon, 16 Nov 2015 16:25:56 +0100
+Subject: af_unix: don't append consumed skbs to sk_receive_queue
+
+From: Hannes Frederic Sowa <hannes@stressinduktion.org>
+
+[ Upstream commit 8844f97238ca6c1ca92a5d6c69f53efd361a266f ]
+
+In case multiple writes to a unix stream socket race we could end up in a
+situation where we pre-allocate a new skb for use in unix_stream_sendpage
+but have to free it again in the locked section because another skb
+has been appended meanwhile, which we must use. Accidentally we didn't
+clear the pointer after consuming it and so we touched freed memory
+while appending it to the sk_receive_queue. So, clear the pointer after
+consuming the skb.
+
+This bug has been found with syzkaller
+(http://github.com/google/syzkaller) by Dmitry Vyukov.
+
+Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support")
+Reported-by: Dmitry Vyukov <dvyukov@google.com>
+Cc: Dmitry Vyukov <dvyukov@google.com>
+Cc: Eric Dumazet <eric.dumazet@gmail.com>
+Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Acked-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/unix/af_unix.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/net/unix/af_unix.c
++++ b/net/unix/af_unix.c
+@@ -1799,6 +1799,7 @@ alloc_skb:
+ * this - does no harm
+ */
+ consume_skb(newskb);
++ newskb = NULL;
+ }
+
+ if (skb_append_pagefrags(skb, page, offset, size)) {
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Date: Tue, 17 Nov 2015 15:10:59 +0100
+Subject: af_unix: take receive queue lock while appending new skb
+
+From: Hannes Frederic Sowa <hannes@stressinduktion.org>
+
+[ Upstream commit a3a116e04cc6a94d595ead4e956ab1bc1d2f4746 ]
+
+While possibly in future we don't necessarily need to use
+sk_buff_head.lock this is a rather larger change, as it affects the
+af_unix fd garbage collector, diag and socket cleanups. This is too much
+for a stable patch.
+
+For the time being grab sk_buff_head.lock without disabling bh and irqs,
+so don't use locked skb_queue_tail.
+
+Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support")
+Cc: Eric Dumazet <edumazet@google.com>
+Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Reported-by: Eric Dumazet <edumazet@google.com>
+Acked-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/unix/af_unix.c | 5 ++++-
+ 1 file changed, 4 insertions(+), 1 deletion(-)
+
+--- a/net/unix/af_unix.c
++++ b/net/unix/af_unix.c
+@@ -1812,8 +1812,11 @@ alloc_skb:
+ skb->truesize += size;
+ atomic_add(size, &sk->sk_wmem_alloc);
+
+- if (newskb)
++ if (newskb) {
++ spin_lock(&other->sk_receive_queue.lock);
+ __skb_queue_tail(&other->sk_receive_queue, newskb);
++ spin_unlock(&other->sk_receive_queue.lock);
++ }
+
+ unix_state_unlock(other);
+ mutex_unlock(&unix_sk(other)->readlock);
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Daniel Borkmann <daniel@iogearbox.net>
+Date: Mon, 30 Nov 2015 13:02:56 +0100
+Subject: bpf, array: fix heap out-of-bounds access when updating elements
+
+From: Daniel Borkmann <daniel@iogearbox.net>
+
+[ Upstream commit fbca9d2d35c6ef1b323fae75cc9545005ba25097 ]
+
+During own review but also reported by Dmitry's syzkaller [1] it has been
+noticed that we trigger a heap out-of-bounds access on eBPF array maps
+when updating elements. This happens with each map whose map->value_size
+(specified during map creation time) is not multiple of 8 bytes.
+
+In array_map_alloc(), elem_size is round_up(attr->value_size, 8) and
+used to align array map slots for faster access. However, in function
+array_map_update_elem(), we update the element as ...
+
+memcpy(array->value + array->elem_size * index, value, array->elem_size);
+
+... where we access 'value' out-of-bounds, since it was allocated from
+map_update_elem() from syscall side as kmalloc(map->value_size, GFP_USER)
+and later on copied through copy_from_user(value, uvalue, map->value_size).
+Thus, up to 7 bytes, we can access out-of-bounds.
+
+Same could happen from within an eBPF program, where in worst case we
+access beyond an eBPF program's designated stack.
+
+Since 1be7f75d1668 ("bpf: enable non-root eBPF programs") didn't hit an
+official release yet, it only affects priviledged users.
+
+In case of array_map_lookup_elem(), the verifier prevents eBPF programs
+from accessing beyond map->value_size through check_map_access(). Also
+from syscall side map_lookup_elem() only copies map->value_size back to
+user, so nothing could leak.
+
+ [1] http://github.com/google/syzkaller
+
+Fixes: 28fbcfa08d8e ("bpf: add array type of eBPF maps")
+Reported-by: Dmitry Vyukov <dvyukov@google.com>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Acked-by: Alexei Starovoitov <ast@kernel.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/bpf/arraymap.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/kernel/bpf/arraymap.c
++++ b/kernel/bpf/arraymap.c
+@@ -104,7 +104,7 @@ static int array_map_update_elem(struct
+ /* all elements already exist */
+ return -EEXIST;
+
+- memcpy(array->value + array->elem_size * index, value, array->elem_size);
++ memcpy(array->value + array->elem_size * index, value, map->value_size);
+ return 0;
+ }
+
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Aaro Koskinen <aaro.koskinen@iki.fi>
+Date: Sun, 22 Nov 2015 01:08:54 +0200
+Subject: broadcom: fix PHY_ID_BCM5481 entry in the id table
+
+From: Aaro Koskinen <aaro.koskinen@iki.fi>
+
+[ Upstream commit 3c25a860d17b7378822f35d8c9141db9507e3beb ]
+
+Commit fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
+updated broadcom_tbl to use PHY_IDs, but incorrectly replaced 0x0143bca0
+with PHY_ID_BCM5482 (making a duplicate entry, and completely omitting
+the original). Fix that.
+
+Fixes: fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
+Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/net/phy/broadcom.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/drivers/net/phy/broadcom.c
++++ b/drivers/net/phy/broadcom.c
+@@ -675,7 +675,7 @@ static struct mdio_device_id __maybe_unu
+ { PHY_ID_BCM5461, 0xfffffff0 },
+ { PHY_ID_BCM54616S, 0xfffffff0 },
+ { PHY_ID_BCM5464, 0xfffffff0 },
+- { PHY_ID_BCM5482, 0xfffffff0 },
++ { PHY_ID_BCM5481, 0xfffffff0 },
+ { PHY_ID_BCM5482, 0xfffffff0 },
+ { PHY_ID_BCM50610, 0xfffffff0 },
+ { PHY_ID_BCM50610M, 0xfffffff0 },
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Thu, 12 Nov 2015 17:35:58 +0100
+Subject: ip_tunnel: disable preemption when updating per-cpu tstats
+
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+
+[ Upstream commit b4fe85f9c9146f60457e9512fb6055e69e6a7a65 ]
+
+Drivers like vxlan use the recently introduced
+udp_tunnel_xmit_skb/udp_tunnel6_xmit_skb APIs. udp_tunnel6_xmit_skb
+makes use of ip6tunnel_xmit, and ip6tunnel_xmit, after sending the
+packet, updates the struct stats using the usual
+u64_stats_update_begin/end calls on this_cpu_ptr(dev->tstats).
+udp_tunnel_xmit_skb makes use of iptunnel_xmit, which doesn't touch
+tstats, so drivers like vxlan, immediately after, call
+iptunnel_xmit_stats, which does the same thing - calls
+u64_stats_update_begin/end on this_cpu_ptr(dev->tstats).
+
+While vxlan is probably fine (I don't know?), calling a similar function
+from, say, an unbound workqueue, on a fully preemptable kernel causes
+real issues:
+
+[ 188.434537] BUG: using smp_processor_id() in preemptible [00000000] code: kworker/u8:0/6
+[ 188.435579] caller is debug_smp_processor_id+0x17/0x20
+[ 188.435583] CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 4.2.6 #2
+[ 188.435607] Call Trace:
+[ 188.435611] [<ffffffff8234e936>] dump_stack+0x4f/0x7b
+[ 188.435615] [<ffffffff81915f3d>] check_preemption_disabled+0x19d/0x1c0
+[ 188.435619] [<ffffffff81915f77>] debug_smp_processor_id+0x17/0x20
+
+The solution would be to protect the whole
+this_cpu_ptr(dev->tstats)/u64_stats_update_begin/end blocks with
+disabling preemption and then reenabling it.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/ip6_tunnel.h | 3 ++-
+ include/net/ip_tunnels.h | 3 ++-
+ 2 files changed, 4 insertions(+), 2 deletions(-)
+
+--- a/include/net/ip6_tunnel.h
++++ b/include/net/ip6_tunnel.h
+@@ -83,11 +83,12 @@ static inline void ip6tunnel_xmit(struct
+ err = ip6_local_out_sk(sk, skb);
+
+ if (net_xmit_eval(err) == 0) {
+- struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
++ struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->tx_bytes += pkt_len;
+ tstats->tx_packets++;
+ u64_stats_update_end(&tstats->syncp);
++ put_cpu_ptr(tstats);
+ } else {
+ stats->tx_errors++;
+ stats->tx_aborted_errors++;
+--- a/include/net/ip_tunnels.h
++++ b/include/net/ip_tunnels.h
+@@ -207,12 +207,13 @@ static inline void iptunnel_xmit_stats(i
+ struct pcpu_sw_netstats __percpu *stats)
+ {
+ if (err > 0) {
+- struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats);
++ struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats);
+
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->tx_bytes += err;
+ tstats->tx_packets++;
+ u64_stats_update_end(&tstats->syncp);
++ put_cpu_ptr(tstats);
+ } else if (err < 0) {
+ err_stats->tx_errors++;
+ err_stats->tx_aborted_errors++;
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Eric Dumazet <edumazet@google.com>
+Date: Sun, 29 Nov 2015 19:37:57 -0800
+Subject: ipv6: add complete rcu protection around np->opt
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 45f6fad84cc305103b28d73482b344d7f5b76f39 ]
+
+This patch addresses multiple problems :
+
+UDP/RAW sendmsg() need to get a stable struct ipv6_txoptions
+while socket is not locked : Other threads can change np->opt
+concurrently. Dmitry posted a syzkaller
+(http://github.com/google/syzkaller) program desmonstrating
+use-after-free.
+
+Starting with TCP/DCCP lockless listeners, tcp_v6_syn_recv_sock()
+and dccp_v6_request_recv_sock() also need to use RCU protection
+to dereference np->opt once (before calling ipv6_dup_options())
+
+This patch adds full RCU protection to np->opt
+
+Reported-by: Dmitry Vyukov <dvyukov@google.com>
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/linux/ipv6.h | 2 +-
+ include/net/ipv6.h | 21 ++++++++++++++++++++-
+ net/dccp/ipv6.c | 33 +++++++++++++++++++++------------
+ net/ipv6/af_inet6.c | 13 +++++++++----
+ net/ipv6/datagram.c | 4 +++-
+ net/ipv6/exthdrs.c | 3 ++-
+ net/ipv6/inet6_connection_sock.c | 11 ++++++++---
+ net/ipv6/ipv6_sockglue.c | 33 ++++++++++++++++++++++-----------
+ net/ipv6/raw.c | 8 ++++++--
+ net/ipv6/syncookies.c | 2 +-
+ net/ipv6/tcp_ipv6.c | 28 +++++++++++++++++-----------
+ net/ipv6/udp.c | 8 ++++++--
+ net/l2tp/l2tp_ip6.c | 8 ++++++--
+ 13 files changed, 122 insertions(+), 52 deletions(-)
+
+--- a/include/linux/ipv6.h
++++ b/include/linux/ipv6.h
+@@ -224,7 +224,7 @@ struct ipv6_pinfo {
+ struct ipv6_ac_socklist *ipv6_ac_list;
+ struct ipv6_fl_socklist __rcu *ipv6_fl_list;
+
+- struct ipv6_txoptions *opt;
++ struct ipv6_txoptions __rcu *opt;
+ struct sk_buff *pktoptions;
+ struct sk_buff *rxpmtu;
+ struct inet6_cork cork;
+--- a/include/net/ipv6.h
++++ b/include/net/ipv6.h
+@@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock;
+ */
+
+ struct ipv6_txoptions {
++ atomic_t refcnt;
+ /* Length of this structure */
+ int tot_len;
+
+@@ -217,7 +218,7 @@ struct ipv6_txoptions {
+ struct ipv6_opt_hdr *dst0opt;
+ struct ipv6_rt_hdr *srcrt; /* Routing Header */
+ struct ipv6_opt_hdr *dst1opt;
+-
++ struct rcu_head rcu;
+ /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
+ };
+
+@@ -252,6 +253,24 @@ struct ipv6_fl_socklist {
+ struct rcu_head rcu;
+ };
+
++static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
++{
++ struct ipv6_txoptions *opt;
++
++ rcu_read_lock();
++ opt = rcu_dereference(np->opt);
++ if (opt && !atomic_inc_not_zero(&opt->refcnt))
++ opt = NULL;
++ rcu_read_unlock();
++ return opt;
++}
++
++static inline void txopt_put(struct ipv6_txoptions *opt)
++{
++ if (opt && atomic_dec_and_test(&opt->refcnt))
++ kfree_rcu(opt, rcu);
++}
++
+ struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
+ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
+ struct ip6_flowlabel *fl,
+--- a/net/dccp/ipv6.c
++++ b/net/dccp/ipv6.c
+@@ -202,7 +202,9 @@ static int dccp_v6_send_response(struct
+ security_req_classify_flow(req, flowi6_to_flowi(&fl6));
+
+
+- final_p = fl6_update_dst(&fl6, np->opt, &final);
++ rcu_read_lock();
++ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
++ rcu_read_unlock();
+
+ dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+ if (IS_ERR(dst)) {
+@@ -219,7 +221,10 @@ static int dccp_v6_send_response(struct
+ &ireq->ir_v6_loc_addr,
+ &ireq->ir_v6_rmt_addr);
+ fl6.daddr = ireq->ir_v6_rmt_addr;
+- err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
++ rcu_read_lock();
++ err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
++ np->tclass);
++ rcu_read_unlock();
+ err = net_xmit_eval(err);
+ }
+
+@@ -415,6 +420,7 @@ static struct sock *dccp_v6_request_recv
+ {
+ struct inet_request_sock *ireq = inet_rsk(req);
+ struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
++ struct ipv6_txoptions *opt;
+ struct inet_sock *newinet;
+ struct dccp6_sock *newdp6;
+ struct sock *newsk;
+@@ -534,13 +540,15 @@ static struct sock *dccp_v6_request_recv
+ * Yes, keeping reference count would be much more clever, but we make
+ * one more one thing there: reattach optmem to newsk.
+ */
+- if (np->opt != NULL)
+- newnp->opt = ipv6_dup_options(newsk, np->opt);
+-
++ opt = rcu_dereference(np->opt);
++ if (opt) {
++ opt = ipv6_dup_options(newsk, opt);
++ RCU_INIT_POINTER(newnp->opt, opt);
++ }
+ inet_csk(newsk)->icsk_ext_hdr_len = 0;
+- if (newnp->opt != NULL)
+- inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
+- newnp->opt->opt_flen);
++ if (opt)
++ inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
++ opt->opt_flen;
+
+ dccp_sync_mss(newsk, dst_mtu(dst));
+
+@@ -793,6 +801,7 @@ static int dccp_v6_connect(struct sock *
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct dccp_sock *dp = dccp_sk(sk);
+ struct in6_addr *saddr = NULL, *final_p, final;
++ struct ipv6_txoptions *opt;
+ struct flowi6 fl6;
+ struct dst_entry *dst;
+ int addr_type;
+@@ -892,7 +901,8 @@ static int dccp_v6_connect(struct sock *
+ fl6.fl6_sport = inet->inet_sport;
+ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+- final_p = fl6_update_dst(&fl6, np->opt, &final);
++ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
++ final_p = fl6_update_dst(&fl6, opt, &final);
+
+ dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+ if (IS_ERR(dst)) {
+@@ -912,9 +922,8 @@ static int dccp_v6_connect(struct sock *
+ __ip6_dst_store(sk, dst, NULL, NULL);
+
+ icsk->icsk_ext_hdr_len = 0;
+- if (np->opt != NULL)
+- icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
+- np->opt->opt_nflen);
++ if (opt)
++ icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
+
+ inet->inet_dport = usin->sin6_port;
+
+--- a/net/ipv6/af_inet6.c
++++ b/net/ipv6/af_inet6.c
+@@ -426,9 +426,11 @@ void inet6_destroy_sock(struct sock *sk)
+
+ /* Free tx options */
+
+- opt = xchg(&np->opt, NULL);
+- if (opt)
+- sock_kfree_s(sk, opt, opt->tot_len);
++ opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
++ if (opt) {
++ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
++ txopt_put(opt);
++ }
+ }
+ EXPORT_SYMBOL_GPL(inet6_destroy_sock);
+
+@@ -657,7 +659,10 @@ int inet6_sk_rebuild_header(struct sock
+ fl6.fl6_sport = inet->inet_sport;
+ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+- final_p = fl6_update_dst(&fl6, np->opt, &final);
++ rcu_read_lock();
++ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
++ &final);
++ rcu_read_unlock();
+
+ dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+ if (IS_ERR(dst)) {
+--- a/net/ipv6/datagram.c
++++ b/net/ipv6/datagram.c
+@@ -167,8 +167,10 @@ ipv4_connected:
+
+ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+- opt = flowlabel ? flowlabel->opt : np->opt;
++ rcu_read_lock();
++ opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
+ final_p = fl6_update_dst(&fl6, opt, &final);
++ rcu_read_unlock();
+
+ dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+ err = 0;
+--- a/net/ipv6/exthdrs.c
++++ b/net/ipv6/exthdrs.c
+@@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct
+ *((char **)&opt2->dst1opt) += dif;
+ if (opt2->srcrt)
+ *((char **)&opt2->srcrt) += dif;
++ atomic_set(&opt2->refcnt, 1);
+ }
+ return opt2;
+ }
+@@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, stru
+ return ERR_PTR(-ENOBUFS);
+
+ memset(opt2, 0, tot_len);
+-
++ atomic_set(&opt2->refcnt, 1);
+ opt2->tot_len = tot_len;
+ p = (char *)(opt2 + 1);
+
+--- a/net/ipv6/inet6_connection_sock.c
++++ b/net/ipv6/inet6_connection_sock.c
+@@ -77,7 +77,9 @@ struct dst_entry *inet6_csk_route_req(st
+ memset(fl6, 0, sizeof(*fl6));
+ fl6->flowi6_proto = IPPROTO_TCP;
+ fl6->daddr = ireq->ir_v6_rmt_addr;
+- final_p = fl6_update_dst(fl6, np->opt, &final);
++ rcu_read_lock();
++ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
++ rcu_read_unlock();
+ fl6->saddr = ireq->ir_v6_loc_addr;
+ fl6->flowi6_oif = ireq->ir_iif;
+ fl6->flowi6_mark = ireq->ir_mark;
+@@ -207,7 +209,9 @@ static struct dst_entry *inet6_csk_route
+ fl6->fl6_dport = inet->inet_dport;
+ security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+
+- final_p = fl6_update_dst(fl6, np->opt, &final);
++ rcu_read_lock();
++ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
++ rcu_read_unlock();
+
+ dst = __inet6_csk_dst_check(sk, np->dst_cookie);
+ if (!dst) {
+@@ -240,7 +244,8 @@ int inet6_csk_xmit(struct sock *sk, stru
+ /* Restore final destination back after routing done */
+ fl6.daddr = sk->sk_v6_daddr;
+
+- res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
++ res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
++ np->tclass);
+ rcu_read_unlock();
+ return res;
+ }
+--- a/net/ipv6/ipv6_sockglue.c
++++ b/net/ipv6/ipv6_sockglue.c
+@@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_optio
+ icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
+ }
+ }
+- opt = xchg(&inet6_sk(sk)->opt, opt);
++ opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
++ opt);
+ sk_dst_reset(sk);
+
+ return opt;
+@@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct soc
+ sk->sk_socket->ops = &inet_dgram_ops;
+ sk->sk_family = PF_INET;
+ }
+- opt = xchg(&np->opt, NULL);
+- if (opt)
+- sock_kfree_s(sk, opt, opt->tot_len);
++ opt = xchg((__force struct ipv6_txoptions **)&np->opt,
++ NULL);
++ if (opt) {
++ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
++ txopt_put(opt);
++ }
+ pktopt = xchg(&np->pktoptions, NULL);
+ kfree_skb(pktopt);
+
+@@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct soc
+ if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
+ break;
+
+- opt = ipv6_renew_options(sk, np->opt, optname,
++ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
++ opt = ipv6_renew_options(sk, opt, optname,
+ (struct ipv6_opt_hdr __user *)optval,
+ optlen);
+ if (IS_ERR(opt)) {
+@@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct soc
+ retv = 0;
+ opt = ipv6_update_options(sk, opt);
+ sticky_done:
+- if (opt)
+- sock_kfree_s(sk, opt, opt->tot_len);
++ if (opt) {
++ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
++ txopt_put(opt);
++ }
+ break;
+ }
+
+@@ -486,6 +493,7 @@ sticky_done:
+ break;
+
+ memset(opt, 0, sizeof(*opt));
++ atomic_set(&opt->refcnt, 1);
+ opt->tot_len = sizeof(*opt) + optlen;
+ retv = -EFAULT;
+ if (copy_from_user(opt+1, optval, optlen))
+@@ -502,8 +510,10 @@ update:
+ retv = 0;
+ opt = ipv6_update_options(sk, opt);
+ done:
+- if (opt)
+- sock_kfree_s(sk, opt, opt->tot_len);
++ if (opt) {
++ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
++ txopt_put(opt);
++ }
+ break;
+ }
+ case IPV6_UNICAST_HOPS:
+@@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct soc
+ case IPV6_RTHDR:
+ case IPV6_DSTOPTS:
+ {
++ struct ipv6_txoptions *opt;
+
+ lock_sock(sk);
+- len = ipv6_getsockopt_sticky(sk, np->opt,
+- optname, optval, len);
++ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
++ len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
+ release_sock(sk);
+ /* check if ipv6_getsockopt_sticky() returns err code */
+ if (len < 0)
+--- a/net/ipv6/raw.c
++++ b/net/ipv6/raw.c
+@@ -731,6 +731,7 @@ static int raw6_getfrag(void *from, char
+
+ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
+ {
++ struct ipv6_txoptions *opt_to_free = NULL;
+ struct ipv6_txoptions opt_space;
+ DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
+ struct in6_addr *daddr, *final_p, final;
+@@ -837,8 +838,10 @@ static int rawv6_sendmsg(struct sock *sk
+ if (!(opt->opt_nflen|opt->opt_flen))
+ opt = NULL;
+ }
+- if (!opt)
+- opt = np->opt;
++ if (!opt) {
++ opt = txopt_get(np);
++ opt_to_free = opt;
++ }
+ if (flowlabel)
+ opt = fl6_merge_options(&opt_space, flowlabel, opt);
+ opt = ipv6_fixup_options(&opt_space, opt);
+@@ -904,6 +907,7 @@ done:
+ dst_release(dst);
+ out:
+ fl6_sock_release(flowlabel);
++ txopt_put(opt_to_free);
+ return err < 0 ? err : len;
+ do_confirm:
+ dst_confirm(dst);
+--- a/net/ipv6/syncookies.c
++++ b/net/ipv6/syncookies.c
+@@ -225,7 +225,7 @@ struct sock *cookie_v6_check(struct sock
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_proto = IPPROTO_TCP;
+ fl6.daddr = ireq->ir_v6_rmt_addr;
+- final_p = fl6_update_dst(&fl6, np->opt, &final);
++ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+ fl6.saddr = ireq->ir_v6_loc_addr;
+ fl6.flowi6_oif = sk->sk_bound_dev_if;
+ fl6.flowi6_mark = ireq->ir_mark;
+--- a/net/ipv6/tcp_ipv6.c
++++ b/net/ipv6/tcp_ipv6.c
+@@ -120,6 +120,7 @@ static int tcp_v6_connect(struct sock *s
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct in6_addr *saddr = NULL, *final_p, final;
++ struct ipv6_txoptions *opt;
+ struct flowi6 fl6;
+ struct dst_entry *dst;
+ int addr_type;
+@@ -235,7 +236,8 @@ static int tcp_v6_connect(struct sock *s
+ fl6.fl6_dport = usin->sin6_port;
+ fl6.fl6_sport = inet->inet_sport;
+
+- final_p = fl6_update_dst(&fl6, np->opt, &final);
++ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
++ final_p = fl6_update_dst(&fl6, opt, &final);
+
+ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+@@ -263,9 +265,9 @@ static int tcp_v6_connect(struct sock *s
+ tcp_fetch_timewait_stamp(sk, dst);
+
+ icsk->icsk_ext_hdr_len = 0;
+- if (np->opt)
+- icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
+- np->opt->opt_nflen);
++ if (opt)
++ icsk->icsk_ext_hdr_len = opt->opt_flen +
++ opt->opt_nflen;
+
+ tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
+
+@@ -461,7 +463,8 @@ static int tcp_v6_send_synack(struct soc
+ fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
+
+ skb_set_queue_mapping(skb, queue_mapping);
+- err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
++ err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
++ np->tclass);
+ err = net_xmit_eval(err);
+ }
+
+@@ -991,6 +994,7 @@ static struct sock *tcp_v6_syn_recv_sock
+ struct inet_request_sock *ireq;
+ struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
+ struct tcp6_sock *newtcp6sk;
++ struct ipv6_txoptions *opt;
+ struct inet_sock *newinet;
+ struct tcp_sock *newtp;
+ struct sock *newsk;
+@@ -1126,13 +1130,15 @@ static struct sock *tcp_v6_syn_recv_sock
+ but we make one more one thing there: reattach optmem
+ to newsk.
+ */
+- if (np->opt)
+- newnp->opt = ipv6_dup_options(newsk, np->opt);
+-
++ opt = rcu_dereference(np->opt);
++ if (opt) {
++ opt = ipv6_dup_options(newsk, opt);
++ RCU_INIT_POINTER(newnp->opt, opt);
++ }
+ inet_csk(newsk)->icsk_ext_hdr_len = 0;
+- if (newnp->opt)
+- inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
+- newnp->opt->opt_flen);
++ if (opt)
++ inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
++ opt->opt_flen;
+
+ tcp_ca_openreq_child(newsk, dst);
+
+--- a/net/ipv6/udp.c
++++ b/net/ipv6/udp.c
+@@ -1107,6 +1107,7 @@ int udpv6_sendmsg(struct sock *sk, struc
+ DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
+ struct in6_addr *daddr, *final_p, final;
+ struct ipv6_txoptions *opt = NULL;
++ struct ipv6_txoptions *opt_to_free = NULL;
+ struct ip6_flowlabel *flowlabel = NULL;
+ struct flowi6 fl6;
+ struct dst_entry *dst;
+@@ -1260,8 +1261,10 @@ do_udp_sendmsg:
+ opt = NULL;
+ connected = 0;
+ }
+- if (!opt)
+- opt = np->opt;
++ if (!opt) {
++ opt = txopt_get(np);
++ opt_to_free = opt;
++ }
+ if (flowlabel)
+ opt = fl6_merge_options(&opt_space, flowlabel, opt);
+ opt = ipv6_fixup_options(&opt_space, opt);
+@@ -1370,6 +1373,7 @@ release_dst:
+ out:
+ dst_release(dst);
+ fl6_sock_release(flowlabel);
++ txopt_put(opt_to_free);
+ if (!err)
+ return len;
+ /*
+--- a/net/l2tp/l2tp_ip6.c
++++ b/net/l2tp/l2tp_ip6.c
+@@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock
+ DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
+ struct in6_addr *daddr, *final_p, final;
+ struct ipv6_pinfo *np = inet6_sk(sk);
++ struct ipv6_txoptions *opt_to_free = NULL;
+ struct ipv6_txoptions *opt = NULL;
+ struct ip6_flowlabel *flowlabel = NULL;
+ struct dst_entry *dst = NULL;
+@@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock
+ opt = NULL;
+ }
+
+- if (opt == NULL)
+- opt = np->opt;
++ if (!opt) {
++ opt = txopt_get(np);
++ opt_to_free = opt;
++ }
+ if (flowlabel)
+ opt = fl6_merge_options(&opt_space, flowlabel, opt);
+ opt = ipv6_fixup_options(&opt_space, opt);
+@@ -631,6 +634,7 @@ done:
+ dst_release(dst);
+ out:
+ fl6_sock_release(flowlabel);
++ txopt_put(opt_to_free);
+
+ return err < 0 ? err : len;
+
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Martin KaFai Lau <kafai@fb.com>
+Date: Wed, 11 Nov 2015 11:51:06 -0800
+Subject: ipv6: Avoid creating RTF_CACHE from a rt that is not managed by fib6 tree
+
+From: Martin KaFai Lau <kafai@fb.com>
+
+[ Upstream commit 0d3f6d297bfb7af24d0508460fdb3d1ec4903fa3 ]
+
+The original bug report:
+https://bugzilla.redhat.com/show_bug.cgi?id=1272571
+
+The setup has a IPv4 GRE tunnel running in a IPSec. The bug
+happens when ndisc starts sending router solicitation at the gre
+interface. The simplified oops stack is like:
+
+__lock_acquire+0x1b2/0x1c30
+lock_acquire+0xb9/0x140
+_raw_write_lock_bh+0x3f/0x50
+__ip6_ins_rt+0x2e/0x60
+ip6_ins_rt+0x49/0x50
+~~~~~~~~
+__ip6_rt_update_pmtu.part.54+0x145/0x250
+ip6_rt_update_pmtu+0x2e/0x40
+~~~~~~~~
+ip_tunnel_xmit+0x1f1/0xf40
+__gre_xmit+0x7a/0x90
+ipgre_xmit+0x15a/0x220
+dev_hard_start_xmit+0x2bd/0x480
+__dev_queue_xmit+0x696/0x730
+dev_queue_xmit+0x10/0x20
+neigh_direct_output+0x11/0x20
+ip6_finish_output2+0x21f/0x770
+ip6_finish_output+0xa7/0x1d0
+ip6_output+0x56/0x190
+~~~~~~~~
+ndisc_send_skb+0x1d9/0x400
+ndisc_send_rs+0x88/0xc0
+~~~~~~~~
+
+The rt passed to ip6_rt_update_pmtu() is created by
+icmp6_dst_alloc() and it is not managed by the fib6 tree,
+so its rt6i_table == NULL. When __ip6_rt_update_pmtu() creates
+a RTF_CACHE clone, the newly created clone also has rt6i_table == NULL
+and it causes the ip6_ins_rt() oops.
+
+During pmtu update, we only want to create a RTF_CACHE clone
+from a rt which is currently managed (or owned) by the
+fib6 tree. It means either rt->rt6i_node != NULL or
+rt is a RTF_PCPU clone.
+
+It is worth to note that rt6i_table may not be NULL even it is
+not (yet) managed by the fib6 tree (e.g. addrconf_dst_alloc()).
+Hence, rt6i_node is a better check instead of rt6i_table.
+
+Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu")
+Signed-off-by: Martin KaFai Lau <kafai@fb.com>
+Reported-by: Chris Siebenmann <cks-rhbugzilla@cs.toronto.edu>
+Cc: Chris Siebenmann <cks-rhbugzilla@cs.toronto.edu>
+Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/ipv6/route.c | 8 +++++++-
+ 1 file changed, 7 insertions(+), 1 deletion(-)
+
+--- a/net/ipv6/route.c
++++ b/net/ipv6/route.c
+@@ -1326,6 +1326,12 @@ static void rt6_do_update_pmtu(struct rt
+ rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
+ }
+
++static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
++{
++ return !(rt->rt6i_flags & RTF_CACHE) &&
++ (rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
++}
++
+ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
+ const struct ipv6hdr *iph, u32 mtu)
+ {
+@@ -1339,7 +1345,7 @@ static void __ip6_rt_update_pmtu(struct
+ if (mtu >= dst_mtu(dst))
+ return;
+
+- if (rt6->rt6i_flags & RTF_CACHE) {
++ if (!rt6_cache_allowed_for_pmtu(rt6)) {
+ rt6_do_update_pmtu(rt6, mtu);
+ } else {
+ const struct in6_addr *daddr, *saddr;
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Martin KaFai Lau <kafai@fb.com>
+Date: Wed, 11 Nov 2015 11:51:07 -0800
+Subject: ipv6: Check expire on DST_NOCACHE route
+
+From: Martin KaFai Lau <kafai@fb.com>
+
+[ Upstream commit 5973fb1e245086071bf71994c8b54d99526ded03 ]
+
+Since the expires of the DST_NOCACHE rt can be set during
+the ip6_rt_update_pmtu(), we also need to consider the expires
+value when doing ip6_dst_check().
+
+This patches creates __rt6_check_expired() to only
+check the expire value (if one exists) of the current rt.
+
+In rt6_dst_from_check(), it adds __rt6_check_expired() as
+one of the condition check.
+
+Signed-off-by: Martin KaFai Lau <kafai@fb.com>
+Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/ipv6/route.c | 11 ++++++++++-
+ 1 file changed, 10 insertions(+), 1 deletion(-)
+
+--- a/net/ipv6/route.c
++++ b/net/ipv6/route.c
+@@ -401,6 +401,14 @@ static void ip6_dst_ifdown(struct dst_en
+ }
+ }
+
++static bool __rt6_check_expired(const struct rt6_info *rt)
++{
++ if (rt->rt6i_flags & RTF_EXPIRES)
++ return time_after(jiffies, rt->dst.expires);
++ else
++ return false;
++}
++
+ static bool rt6_check_expired(const struct rt6_info *rt)
+ {
+ if (rt->rt6i_flags & RTF_EXPIRES) {
+@@ -1255,7 +1263,8 @@ static struct dst_entry *rt6_check(struc
+
+ static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
+ {
+- if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
++ if (!__rt6_check_expired(rt) &&
++ rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+ rt6_check((struct rt6_info *)(rt->dst.from), cookie))
+ return &rt->dst;
+ else
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Martin KaFai Lau <kafai@fb.com>
+Date: Wed, 11 Nov 2015 11:51:08 -0800
+Subject: ipv6: Check rt->dst.from for the DST_NOCACHE route
+
+From: Martin KaFai Lau <kafai@fb.com>
+
+[ Upstrem commit 02bcf4e082e4dc634409a6a6cb7def8806d6e5e6 ]
+
+All DST_NOCACHE rt6_info used to have rt->dst.from set to
+its parent.
+
+After commit 8e3d5be73681 ("ipv6: Avoid double dst_free"),
+DST_NOCACHE is also set to rt6_info which does not have
+a parent (i.e. rt->dst.from is NULL).
+
+This patch catches the rt->dst.from == NULL case.
+
+Fixes: 8e3d5be73681 ("ipv6: Avoid double dst_free")
+Signed-off-by: Martin KaFai Lau <kafai@fb.com>
+Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/ip6_fib.h | 3 ++-
+ net/ipv6/route.c | 3 ++-
+ 2 files changed, 4 insertions(+), 2 deletions(-)
+
+--- a/include/net/ip6_fib.h
++++ b/include/net/ip6_fib.h
+@@ -165,7 +165,8 @@ static inline void rt6_update_expires(st
+
+ static inline u32 rt6_get_cookie(const struct rt6_info *rt)
+ {
+- if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE))
++ if (rt->rt6i_flags & RTF_PCPU ||
++ (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from))
+ rt = (struct rt6_info *)(rt->dst.from);
+
+ return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+--- a/net/ipv6/route.c
++++ b/net/ipv6/route.c
+@@ -1284,7 +1284,8 @@ static struct dst_entry *ip6_dst_check(s
+
+ rt6_dst_from_metrics_check(rt);
+
+- if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
++ if (rt->rt6i_flags & RTF_PCPU ||
++ (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from))
+ return rt6_dst_from_check(rt, cookie);
+ else
+ return rt6_check(rt, cookie);
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
+Date: Tue, 24 Nov 2015 15:07:11 +0100
+Subject: ipv6: distinguish frag queues by device for multicast and link-local packets
+
+From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
+
+[ Upstream commit 264640fc2c5f4f913db5c73fa3eb1ead2c45e9d7 ]
+
+If a fragmented multicast packet is received on an ethernet device which
+has an active macvlan on top of it, each fragment is duplicated and
+received both on the underlying device and the macvlan. If some
+fragments for macvlan are processed before the whole packet for the
+underlying device is reassembled, the "overlapping fragments" test in
+ip6_frag_queue() discards the whole fragment queue.
+
+To resolve this, add device ifindex to the search key and require it to
+match reassembling multicast packets and packets to link-local
+addresses.
+
+Note: similar patch has been already submitted by Yoshifuji Hideaki in
+
+ http://patchwork.ozlabs.org/patch/220979/
+
+but got lost and forgotten for some reason.
+
+Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/ipv6.h | 1 +
+ net/ipv6/netfilter/nf_conntrack_reasm.c | 5 +++--
+ net/ipv6/reassembly.c | 10 +++++++---
+ 3 files changed, 11 insertions(+), 5 deletions(-)
+
+--- a/include/net/ipv6.h
++++ b/include/net/ipv6.h
+@@ -490,6 +490,7 @@ struct ip6_create_arg {
+ u32 user;
+ const struct in6_addr *src;
+ const struct in6_addr *dst;
++ int iif;
+ u8 ecn;
+ };
+
+--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
++++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
+@@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned
+ /* Creation primitives. */
+ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
+ u32 user, struct in6_addr *src,
+- struct in6_addr *dst, u8 ecn)
++ struct in6_addr *dst, int iif, u8 ecn)
+ {
+ struct inet_frag_queue *q;
+ struct ip6_create_arg arg;
+@@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find
+ arg.user = user;
+ arg.src = src;
+ arg.dst = dst;
++ arg.iif = iif;
+ arg.ecn = ecn;
+
+ local_bh_disable();
+@@ -603,7 +604,7 @@ struct sk_buff *nf_ct_frag6_gather(struc
+ fhdr = (struct frag_hdr *)skb_transport_header(clone);
+
+ fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
+- ip6_frag_ecn(hdr));
++ skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ if (fq == NULL) {
+ pr_debug("Can't find and can't create new queue\n");
+ goto ret_orig;
+--- a/net/ipv6/reassembly.c
++++ b/net/ipv6/reassembly.c
+@@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_fr
+ return fq->id == arg->id &&
+ fq->user == arg->user &&
+ ipv6_addr_equal(&fq->saddr, arg->src) &&
+- ipv6_addr_equal(&fq->daddr, arg->dst);
++ ipv6_addr_equal(&fq->daddr, arg->dst) &&
++ (arg->iif == fq->iif ||
++ !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
++ IPV6_ADDR_LINKLOCAL)));
+ }
+ EXPORT_SYMBOL(ip6_frag_match);
+
+@@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned lon
+
+ static struct frag_queue *
+ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
+- const struct in6_addr *dst, u8 ecn)
++ const struct in6_addr *dst, int iif, u8 ecn)
+ {
+ struct inet_frag_queue *q;
+ struct ip6_create_arg arg;
+@@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, cons
+ arg.user = IP6_DEFRAG_LOCAL_DELIVER;
+ arg.src = src;
+ arg.dst = dst;
++ arg.iif = iif;
+ arg.ecn = ecn;
+
+ hash = inet6_hash_frag(id, src, dst);
+@@ -551,7 +555,7 @@ static int ipv6_frag_rcv(struct sk_buff
+ }
+
+ fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
+- ip6_frag_ecn(hdr));
++ skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ if (fq) {
+ int ret;
+
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Eric Dumazet <edumazet@google.com>
+Date: Tue, 1 Dec 2015 07:20:07 -0800
+Subject: ipv6: sctp: implement sctp_v6_destroy_sock()
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 602dd62dfbda3e63a2d6a3cbde953ebe82bf5087 ]
+
+Dmitry Vyukov reported a memory leak using IPV6 SCTP sockets.
+
+We need to call inet6_destroy_sock() to properly release
+inet6 specific fields.
+
+Reported-by: Dmitry Vyukov <dvyukov@google.com>
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Acked-by: Daniel Borkmann <daniel@iogearbox.net>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/sctp/socket.c | 9 ++++++++-
+ 1 file changed, 8 insertions(+), 1 deletion(-)
+
+--- a/net/sctp/socket.c
++++ b/net/sctp/socket.c
+@@ -7375,6 +7375,13 @@ struct proto sctp_prot = {
+
+ #if IS_ENABLED(CONFIG_IPV6)
+
++#include <net/transp_v6.h>
++static void sctp_v6_destroy_sock(struct sock *sk)
++{
++ sctp_destroy_sock(sk);
++ inet6_destroy_sock(sk);
++}
++
+ struct proto sctpv6_prot = {
+ .name = "SCTPv6",
+ .owner = THIS_MODULE,
+@@ -7384,7 +7391,7 @@ struct proto sctpv6_prot = {
+ .accept = sctp_accept,
+ .ioctl = sctp_ioctl,
+ .init = sctp_init_sock,
+- .destroy = sctp_destroy_sock,
++ .destroy = sctp_v6_destroy_sock,
+ .shutdown = sctp_shutdown,
+ .setsockopt = sctp_setsockopt,
+ .getsockopt = sctp_getsockopt,
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
+Date: Fri, 20 Nov 2015 13:54:20 +0100
+Subject: net: ip6mr: fix static mfc/dev leaks on table destruction
+
+From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
+
+[ Upstream commit 4c6980462f32b4f282c5d8e5f7ea8070e2937725 ]
+
+Similar to ipv4, when destroying an mrt table the static mfc entries and
+the static devices are kept, which leads to devices that can never be
+destroyed (because of refcnt taken) and leaked memory. Make sure that
+everything is cleaned up on netns destruction.
+
+Fixes: 8229efdaef1e ("netns: ip6mr: enable namespace support in ipv6 multicast forwarding code")
+CC: Benjamin Thery <benjamin.thery@bull.net>
+Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
+Reviewed-by: Cong Wang <cwang@twopensource.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/ipv6/ip6mr.c | 15 ++++++++-------
+ 1 file changed, 8 insertions(+), 7 deletions(-)
+
+--- a/net/ipv6/ip6mr.c
++++ b/net/ipv6/ip6mr.c
+@@ -118,7 +118,7 @@ static void mr6_netlink_event(struct mr6
+ int cmd);
+ static int ip6mr_rtm_dumproute(struct sk_buff *skb,
+ struct netlink_callback *cb);
+-static void mroute_clean_tables(struct mr6_table *mrt);
++static void mroute_clean_tables(struct mr6_table *mrt, bool all);
+ static void ipmr_expire_process(unsigned long arg);
+
+ #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
+@@ -335,7 +335,7 @@ static struct mr6_table *ip6mr_new_table
+ static void ip6mr_free_table(struct mr6_table *mrt)
+ {
+ del_timer_sync(&mrt->ipmr_expire_timer);
+- mroute_clean_tables(mrt);
++ mroute_clean_tables(mrt, true);
+ kfree(mrt);
+ }
+
+@@ -1543,7 +1543,7 @@ static int ip6mr_mfc_add(struct net *net
+ * Close the multicast socket, and clear the vif tables etc
+ */
+
+-static void mroute_clean_tables(struct mr6_table *mrt)
++static void mroute_clean_tables(struct mr6_table *mrt, bool all)
+ {
+ int i;
+ LIST_HEAD(list);
+@@ -1553,8 +1553,9 @@ static void mroute_clean_tables(struct m
+ * Shut down all active vif entries
+ */
+ for (i = 0; i < mrt->maxvif; i++) {
+- if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
+- mif6_delete(mrt, i, &list);
++ if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
++ continue;
++ mif6_delete(mrt, i, &list);
+ }
+ unregister_netdevice_many(&list);
+
+@@ -1563,7 +1564,7 @@ static void mroute_clean_tables(struct m
+ */
+ for (i = 0; i < MFC6_LINES; i++) {
+ list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
+- if (c->mfc_flags & MFC_STATIC)
++ if (!all && (c->mfc_flags & MFC_STATIC))
+ continue;
+ write_lock_bh(&mrt_lock);
+ list_del(&c->list);
+@@ -1626,7 +1627,7 @@ int ip6mr_sk_done(struct sock *sk)
+ net->ipv6.devconf_all);
+ write_unlock_bh(&mrt_lock);
+
+- mroute_clean_tables(mrt);
++ mroute_clean_tables(mrt, false);
+ err = 0;
+ break;
+ }
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
+Date: Fri, 20 Nov 2015 13:54:19 +0100
+Subject: net: ipmr: fix static mfc/dev leaks on table destruction
+
+From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
+
+[ Upstream commit 0e615e9601a15efeeb8942cf7cd4dadba0c8c5a7 ]
+
+When destroying an mrt table the static mfc entries and the static
+devices are kept, which leads to devices that can never be destroyed
+(because of refcnt taken) and leaked memory, for example:
+unreferenced object 0xffff880034c144c0 (size 192):
+ comm "mfc-broken", pid 4777, jiffies 4320349055 (age 46001.964s)
+ hex dump (first 32 bytes):
+ 98 53 f0 34 00 88 ff ff 98 53 f0 34 00 88 ff ff .S.4.....S.4....
+ ef 0a 0a 14 01 02 03 04 00 00 00 00 01 00 00 00 ................
+ backtrace:
+ [<ffffffff815c1b9e>] kmemleak_alloc+0x4e/0xb0
+ [<ffffffff811ea6e0>] kmem_cache_alloc+0x190/0x300
+ [<ffffffff815931cb>] ip_mroute_setsockopt+0x5cb/0x910
+ [<ffffffff8153d575>] do_ip_setsockopt.isra.11+0x105/0xff0
+ [<ffffffff8153e490>] ip_setsockopt+0x30/0xa0
+ [<ffffffff81564e13>] raw_setsockopt+0x33/0x90
+ [<ffffffff814d1e14>] sock_common_setsockopt+0x14/0x20
+ [<ffffffff814d0b51>] SyS_setsockopt+0x71/0xc0
+ [<ffffffff815cdbf6>] entry_SYSCALL_64_fastpath+0x16/0x7a
+ [<ffffffffffffffff>] 0xffffffffffffffff
+
+Make sure that everything is cleaned on netns destruction.
+
+Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
+Reviewed-by: Cong Wang <cwang@twopensource.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/ipv4/ipmr.c | 15 ++++++++-------
+ 1 file changed, 8 insertions(+), 7 deletions(-)
+
+--- a/net/ipv4/ipmr.c
++++ b/net/ipv4/ipmr.c
+@@ -134,7 +134,7 @@ static int __ipmr_fill_mroute(struct mr_
+ struct mfc_cache *c, struct rtmsg *rtm);
+ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
+ int cmd);
+-static void mroute_clean_tables(struct mr_table *mrt);
++static void mroute_clean_tables(struct mr_table *mrt, bool all);
+ static void ipmr_expire_process(unsigned long arg);
+
+ #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+@@ -351,7 +351,7 @@ static struct mr_table *ipmr_new_table(s
+ static void ipmr_free_table(struct mr_table *mrt)
+ {
+ del_timer_sync(&mrt->ipmr_expire_timer);
+- mroute_clean_tables(mrt);
++ mroute_clean_tables(mrt, true);
+ kfree(mrt);
+ }
+
+@@ -1209,7 +1209,7 @@ static int ipmr_mfc_add(struct net *net,
+ * Close the multicast socket, and clear the vif tables etc
+ */
+
+-static void mroute_clean_tables(struct mr_table *mrt)
++static void mroute_clean_tables(struct mr_table *mrt, bool all)
+ {
+ int i;
+ LIST_HEAD(list);
+@@ -1218,8 +1218,9 @@ static void mroute_clean_tables(struct m
+ /* Shut down all active vif entries */
+
+ for (i = 0; i < mrt->maxvif; i++) {
+- if (!(mrt->vif_table[i].flags & VIFF_STATIC))
+- vif_delete(mrt, i, 0, &list);
++ if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
++ continue;
++ vif_delete(mrt, i, 0, &list);
+ }
+ unregister_netdevice_many(&list);
+
+@@ -1227,7 +1228,7 @@ static void mroute_clean_tables(struct m
+
+ for (i = 0; i < MFC_LINES; i++) {
+ list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
+- if (c->mfc_flags & MFC_STATIC)
++ if (!all && (c->mfc_flags & MFC_STATIC))
+ continue;
+ list_del_rcu(&c->list);
+ mroute_netlink_event(mrt, c, RTM_DELROUTE);
+@@ -1262,7 +1263,7 @@ static void mrtsock_destruct(struct sock
+ NETCONFA_IFINDEX_ALL,
+ net->ipv4.devconf_all);
+ RCU_INIT_POINTER(mrt->mroute_sk, NULL);
+- mroute_clean_tables(mrt);
++ mroute_clean_tables(mrt, false);
+ }
+ }
+ rtnl_unlock();
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Eran Ben Elisha <eranbe@mellanox.com>
+Date: Thu, 12 Nov 2015 19:35:29 +0200
+Subject: net/mlx4_core: Fix sleeping while holding spinlock at rem_slave_counters
+
+From: Eran Ben Elisha <eranbe@mellanox.com>
+
+[ Upstream commit f5adbfee72282bb1f456d52b04adacd4fe6ac502 ]
+
+When cleaning slave's counter resources, we hold a spinlock that
+protects the slave's counters list. As part of the clean, we call
+__mlx4_clear_if_stat which calls mlx4_alloc_cmd_mailbox which is a
+sleepable function.
+
+In order to fix this issue, hold the spinlock, and copy all counter
+indices into a temporary array, and release the spinlock. Afterwards,
+iterate over this array and free every counter. Repeat this scenario
+until the original list is empty (a new counter might have been added
+while releasing the counters from the temporary array).
+
+Fixes: b72ca7e96acf ("net/mlx4_core: Reset counters data when freed")
+Reported-by: Moni Shoua <monis@mellanox.com>
+Tested-by: Moni Shoua <monis@mellanox.com>
+Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
+Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
+Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 39 ++++++++++++------
+ 1 file changed, 27 insertions(+), 12 deletions(-)
+
+--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
++++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+@@ -4934,26 +4934,41 @@ static void rem_slave_counters(struct ml
+ struct res_counter *counter;
+ struct res_counter *tmp;
+ int err;
+- int index;
++ int *counters_arr = NULL;
++ int i, j;
+
+ err = move_all_busy(dev, slave, RES_COUNTER);
+ if (err)
+ mlx4_warn(dev, "rem_slave_counters: Could not move all counters - too busy for slave %d\n",
+ slave);
+
+- spin_lock_irq(mlx4_tlock(dev));
+- list_for_each_entry_safe(counter, tmp, counter_list, com.list) {
+- if (counter->com.owner == slave) {
+- index = counter->com.res_id;
+- rb_erase(&counter->com.node,
+- &tracker->res_tree[RES_COUNTER]);
+- list_del(&counter->com.list);
+- kfree(counter);
+- __mlx4_counter_free(dev, index);
++ counters_arr = kmalloc_array(dev->caps.max_counters,
++ sizeof(*counters_arr), GFP_KERNEL);
++ if (!counters_arr)
++ return;
++
++ do {
++ i = 0;
++ j = 0;
++ spin_lock_irq(mlx4_tlock(dev));
++ list_for_each_entry_safe(counter, tmp, counter_list, com.list) {
++ if (counter->com.owner == slave) {
++ counters_arr[i++] = counter->com.res_id;
++ rb_erase(&counter->com.node,
++ &tracker->res_tree[RES_COUNTER]);
++ list_del(&counter->com.list);
++ kfree(counter);
++ }
++ }
++ spin_unlock_irq(mlx4_tlock(dev));
++
++ while (j < i) {
++ __mlx4_counter_free(dev, counters_arr[j++]);
+ mlx4_release_resource(dev, slave, RES_COUNTER, 1, 0);
+ }
+- }
+- spin_unlock_irq(mlx4_tlock(dev));
++ } while (i);
++
++ kfree(counters_arr);
+ }
+
+ static void rem_slave_xrcdns(struct mlx4_dev *dev, int slave)
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Konstantin Khlebnikov <koct9i@gmail.com>
+Date: Tue, 1 Dec 2015 01:14:48 +0300
+Subject: net/neighbour: fix crash at dumping device-agnostic proxy entries
+
+From: Konstantin Khlebnikov <koct9i@gmail.com>
+
+[ Upstream commit 6adc5fd6a142c6e2c80574c1db0c7c17dedaa42e ]
+
+Proxy entries could have null pointer to net-device.
+
+Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
+Fixes: 84920c1420e2 ("net: Allow ipv6 proxies and arp proxies be shown with iproute2")
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/core/neighbour.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/net/core/neighbour.c
++++ b/net/core/neighbour.c
+@@ -2210,7 +2210,7 @@ static int pneigh_fill_info(struct sk_bu
+ ndm->ndm_pad2 = 0;
+ ndm->ndm_flags = pn->flags | NTF_PROXY;
+ ndm->ndm_type = RTN_UNICAST;
+- ndm->ndm_ifindex = pn->dev->ifindex;
++ ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0;
+ ndm->ndm_state = NUD_NONE;
+
+ if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
+@@ -2285,7 +2285,7 @@ static int pneigh_dump_table(struct neig
+ if (h > s_h)
+ s_idx = 0;
+ for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
+- if (dev_net(n->dev) != net)
++ if (pneigh_net(n) != net)
+ continue;
+ if (idx < s_idx)
+ goto next;
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
+Date: Wed, 18 Nov 2015 21:13:07 +0100
+Subject: net: qmi_wwan: add XS Stick W100-2 from 4G Systems
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
+
+[ Upstream commit 68242a5a1e2edce39b069385cbafb82304eac0f1 ]
+
+Thomas reports
+"
+4gsystems sells two total different LTE-surfsticks under the same name.
+..
+The newer version of XS Stick W100 is from "omega"
+..
+Under windows the driver switches to the same ID, and uses MI03\6 for
+network and MI01\6 for modem.
+..
+echo "1c9e 9b01" > /sys/bus/usb/drivers/qmi_wwan/new_id
+echo "1c9e 9b01" > /sys/bus/usb-serial/drivers/option1/new_id
+
+T: Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 4 Spd=480 MxCh= 0
+D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1
+P: Vendor=1c9e ProdID=9b01 Rev=02.32
+S: Manufacturer=USB Modem
+S: Product=USB Modem
+S: SerialNumber=
+C: #Ifs= 5 Cfg#= 1 Atr=80 MxPwr=500mA
+I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
+I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
+I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
+I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
+I: If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage
+
+Now all important things are there:
+
+wwp0s29f7u2i3 (net), ttyUSB2 (at), cdc-wdm0 (qmi), ttyUSB1 (at)
+
+There is also ttyUSB0, but it is not usable, at least not for at.
+
+The device works well with qmi and ModemManager-NetworkManager.
+"
+
+Reported-by: Thomas Schäfer <tschaefer@t-online.de>
+Signed-off-by: Bjørn Mork <bjorn@mork.no>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/net/usb/qmi_wwan.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/drivers/net/usb/qmi_wwan.c
++++ b/drivers/net/usb/qmi_wwan.c
+@@ -775,6 +775,7 @@ static const struct usb_device_id produc
+ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */
+ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */
+ {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */
++ {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */
+ {QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */
+ {QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */
+ {QMI_FIXED_INTF(0x0b3c, 0xc002, 4)}, /* Olivetti Olicard 140 */
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Daniel Borkmann <daniel@iogearbox.net>
+Date: Fri, 20 Nov 2015 00:11:56 +0100
+Subject: net, scm: fix PaX detected msg_controllen overflow in scm_detach_fds
+
+From: Daniel Borkmann <daniel@iogearbox.net>
+
+[ Upstream commit 6900317f5eff0a7070c5936e5383f589e0de7a09 ]
+
+David and HacKurx reported a following/similar size overflow triggered
+in a grsecurity kernel, thanks to PaX's gcc size overflow plugin:
+
+(Already fixed in later grsecurity versions by Brad and PaX Team.)
+
+[ 1002.296137] PAX: size overflow detected in function scm_detach_fds net/core/scm.c:314
+ cicus.202_127 min, count: 4, decl: msg_controllen; num: 0; context: msghdr;
+[ 1002.296145] CPU: 0 PID: 3685 Comm: scm_rights_recv Not tainted 4.2.3-grsec+ #7
+[ 1002.296149] Hardware name: Apple Inc. MacBookAir5,1/Mac-66F35F19FE2A0D05, [...]
+[ 1002.296153] ffffffff81c27366 0000000000000000 ffffffff81c27375 ffffc90007843aa8
+[ 1002.296162] ffffffff818129ba 0000000000000000 ffffffff81c27366 ffffc90007843ad8
+[ 1002.296169] ffffffff8121f838 fffffffffffffffc fffffffffffffffc ffffc90007843e60
+[ 1002.296176] Call Trace:
+[ 1002.296190] [<ffffffff818129ba>] dump_stack+0x45/0x57
+[ 1002.296200] [<ffffffff8121f838>] report_size_overflow+0x38/0x60
+[ 1002.296209] [<ffffffff816a979e>] scm_detach_fds+0x2ce/0x300
+[ 1002.296220] [<ffffffff81791899>] unix_stream_read_generic+0x609/0x930
+[ 1002.296228] [<ffffffff81791c9f>] unix_stream_recvmsg+0x4f/0x60
+[ 1002.296236] [<ffffffff8178dc00>] ? unix_set_peek_off+0x50/0x50
+[ 1002.296243] [<ffffffff8168fac7>] sock_recvmsg+0x47/0x60
+[ 1002.296248] [<ffffffff81691522>] ___sys_recvmsg+0xe2/0x1e0
+[ 1002.296257] [<ffffffff81693496>] __sys_recvmsg+0x46/0x80
+[ 1002.296263] [<ffffffff816934fc>] SyS_recvmsg+0x2c/0x40
+[ 1002.296271] [<ffffffff8181a3ab>] entry_SYSCALL_64_fastpath+0x12/0x85
+
+Further investigation showed that this can happen when an *odd* number of
+fds are being passed over AF_UNIX sockets.
+
+In these cases CMSG_LEN(i * sizeof(int)) and CMSG_SPACE(i * sizeof(int)),
+where i is the number of successfully passed fds, differ by 4 bytes due
+to the extra CMSG_ALIGN() padding in CMSG_SPACE() to an 8 byte boundary
+on 64 bit. The padding is used to align subsequent cmsg headers in the
+control buffer.
+
+When the control buffer passed in from the receiver side *lacks* these 4
+bytes (e.g. due to buggy/wrong API usage), then msg->msg_controllen will
+overflow in scm_detach_fds():
+
+ int cmlen = CMSG_LEN(i * sizeof(int)); <--- cmlen w/o tail-padding
+ err = put_user(SOL_SOCKET, &cm->cmsg_level);
+ if (!err)
+ err = put_user(SCM_RIGHTS, &cm->cmsg_type);
+ if (!err)
+ err = put_user(cmlen, &cm->cmsg_len);
+ if (!err) {
+ cmlen = CMSG_SPACE(i * sizeof(int)); <--- cmlen w/ 4 byte extra tail-padding
+ msg->msg_control += cmlen;
+ msg->msg_controllen -= cmlen; <--- iff no tail-padding space here ...
+ } ... wrap-around
+
+F.e. it will wrap to a length of 18446744073709551612 bytes in case the
+receiver passed in msg->msg_controllen of 20 bytes, and the sender
+properly transferred 1 fd to the receiver, so that its CMSG_LEN results
+in 20 bytes and CMSG_SPACE in 24 bytes.
+
+In case of MSG_CMSG_COMPAT (scm_detach_fds_compat()), I haven't seen an
+issue in my tests as alignment seems always on 4 byte boundary. Same
+should be in case of native 32 bit, where we end up with 4 byte boundaries
+as well.
+
+In practice, passing msg->msg_controllen of 20 to recvmsg() while receiving
+a single fd would mean that on successful return, msg->msg_controllen is
+being set by the kernel to 24 bytes instead, thus more than the input
+buffer advertised. It could f.e. become an issue if such application later
+on zeroes or copies the control buffer based on the returned msg->msg_controllen
+elsewhere.
+
+Maximum number of fds we can send is a hard upper limit SCM_MAX_FD (253).
+
+Going over the code, it seems like msg->msg_controllen is not being read
+after scm_detach_fds() in scm_recv() anymore by the kernel, good!
+
+Relevant recvmsg() handler are unix_dgram_recvmsg() (unix_seqpacket_recvmsg())
+and unix_stream_recvmsg(). Both return back to their recvmsg() caller,
+and ___sys_recvmsg() places the updated length, that is, new msg_control -
+old msg_control pointer into msg->msg_controllen (hence the 24 bytes seen
+in the example).
+
+Long time ago, Wei Yongjun fixed something related in commit 1ac70e7ad24a
+("[NET]: Fix function put_cmsg() which may cause usr application memory
+overflow").
+
+RFC3542, section 20.2. says:
+
+ The fields shown as "XX" are possible padding, between the cmsghdr
+ structure and the data, and between the data and the next cmsghdr
+ structure, if required by the implementation. While sending an
+ application may or may not include padding at the end of last
+ ancillary data in msg_controllen and implementations must accept both
+ as valid. On receiving a portable application must provide space for
+ padding at the end of the last ancillary data as implementations may
+ copy out the padding at the end of the control message buffer and
+ include it in the received msg_controllen. When recvmsg() is called
+ if msg_controllen is too small for all the ancillary data items
+ including any trailing padding after the last item an implementation
+ may set MSG_CTRUNC.
+
+Since we didn't place MSG_CTRUNC for already quite a long time, just do
+the same as in 1ac70e7ad24a to avoid an overflow.
+
+Btw, even man-page author got this wrong :/ See db939c9b26e9 ("cmsg.3: Fix
+error in SCM_RIGHTS code sample"). Some people must have copied this (?),
+thus it got triggered in the wild (reported several times during boot by
+David and HacKurx).
+
+No Fixes tag this time as pre 2002 (that is, pre history tree).
+
+Reported-by: David Sterba <dave@jikos.cz>
+Reported-by: HacKurx <hackurx@gmail.com>
+Cc: PaX Team <pageexec@freemail.hu>
+Cc: Emese Revfy <re.emese@gmail.com>
+Cc: Brad Spengler <spender@grsecurity.net>
+Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
+Cc: Eric Dumazet <edumazet@google.com>
+Reviewed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/core/scm.c | 2 ++
+ 1 file changed, 2 insertions(+)
+
+--- a/net/core/scm.c
++++ b/net/core/scm.c
+@@ -305,6 +305,8 @@ void scm_detach_fds(struct msghdr *msg,
+ err = put_user(cmlen, &cm->cmsg_len);
+ if (!err) {
+ cmlen = CMSG_SPACE(i*sizeof(int));
++ if (msg->msg_controllen < cmlen)
++ cmlen = msg->msg_controllen;
+ msg->msg_control += cmlen;
+ msg->msg_controllen -= cmlen;
+ }
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Dragos Tatulea <dragos@endocode.com>
+Date: Mon, 16 Nov 2015 10:52:48 +0100
+Subject: net: switchdev: fix return code of fdb_dump stub
+
+From: Dragos Tatulea <dragos@endocode.com>
+
+[ Upstream commit 24cb7055a3066634a0f3fa0cd6a4780652905d35 ]
+
+rtnl_fdb_dump always expects an index to be returned by the ndo_fdb_dump op,
+but when CONFIG_NET_SWITCHDEV is off, it returns an error.
+
+Fix that by returning the given unmodified idx.
+
+A similar fix was 0890cf6cb6ab ("switchdev: fix return value of
+switchdev_port_fdb_dump in case of error") but for the CONFIG_NET_SWITCHDEV=y
+case.
+
+Fixes: 45d4122ca7cd ("switchdev: add support for fdb add/del/dump via switchdev_port_obj ops.")
+Signed-off-by: Dragos Tatulea <dragos@endocode.com>
+Acked-by: Jiri Pirko <jiri@mellanox.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/switchdev.h | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/include/net/switchdev.h
++++ b/include/net/switchdev.h
+@@ -268,7 +268,7 @@ static inline int switchdev_port_fdb_dum
+ struct net_device *filter_dev,
+ int idx)
+ {
+- return -EOPNOTSUPP;
++ return idx;
+ }
+
+ #endif
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Pavel Fedin <p.fedin@samsung.com>
+Date: Mon, 16 Nov 2015 17:51:34 +0300
+Subject: net: thunder: Check for driver data in nicvf_remove()
+
+From: Pavel Fedin <p.fedin@samsung.com>
+
+[ Upstream commit 7750130d93decff06120df0d8ea024ff8a038a21 ]
+
+In some cases the crash is caused by nicvf_remove() being called from
+outside. For example, if we try to feed the device to vfio after the
+probe has failed for some reason. So, move the check to better place.
+
+Signed-off-by: Pavel Fedin <p.fedin@samsung.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/net/ethernet/cavium/thunder/nicvf_main.c | 7 ++++++-
+ 1 file changed, 6 insertions(+), 1 deletion(-)
+
+--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
++++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+@@ -1325,7 +1325,12 @@ err_disable_device:
+ static void nicvf_remove(struct pci_dev *pdev)
+ {
+ struct net_device *netdev = pci_get_drvdata(pdev);
+- struct nicvf *nic = netdev_priv(netdev);
++ struct nicvf *nic;
++
++ if (!netdev)
++ return;
++
++ nic = netdev_priv(netdev);
+
+ unregister_netdev(netdev);
+ nicvf_unregister_interrupts(nic);
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Eric Dumazet <edumazet@google.com>
+Date: Tue, 1 Dec 2015 20:08:51 -0800
+Subject: net_sched: fix qdisc_tree_decrease_qlen() races
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 4eaf3b84f2881c9c028f1d5e76c52ab575fe3a66 ]
+
+qdisc_tree_decrease_qlen() suffers from two problems on multiqueue
+devices.
+
+One problem is that it updates sch->q.qlen and sch->qstats.drops
+on the mq/mqprio root qdisc, while it should not : Daniele
+reported underflows errors :
+[ 681.774821] PAX: sch->q.qlen: 0 n: 1
+[ 681.774825] PAX: size overflow detected in function qdisc_tree_decrease_qlen net/sched/sch_api.c:769 cicus.693_49 min, count: 72, decl: qlen; num: 0; context: sk_buff_head;
+[ 681.774954] CPU: 2 PID: 19 Comm: ksoftirqd/2 Tainted: G O 4.2.6.201511282239-1-grsec #1
+[ 681.774955] Hardware name: ASUSTeK COMPUTER INC. X302LJ/X302LJ, BIOS X302LJ.202 03/05/2015
+[ 681.774956] ffffffffa9a04863 0000000000000000 0000000000000000 ffffffffa990ff7c
+[ 681.774959] ffffc90000d3bc38 ffffffffa95d2810 0000000000000007 ffffffffa991002b
+[ 681.774960] ffffc90000d3bc68 ffffffffa91a44f4 0000000000000001 0000000000000001
+[ 681.774962] Call Trace:
+[ 681.774967] [<ffffffffa95d2810>] dump_stack+0x4c/0x7f
+[ 681.774970] [<ffffffffa91a44f4>] report_size_overflow+0x34/0x50
+[ 681.774972] [<ffffffffa94d17e2>] qdisc_tree_decrease_qlen+0x152/0x160
+[ 681.774976] [<ffffffffc02694b1>] fq_codel_dequeue+0x7b1/0x820 [sch_fq_codel]
+[ 681.774978] [<ffffffffc02680a0>] ? qdisc_peek_dequeued+0xa0/0xa0 [sch_fq_codel]
+[ 681.774980] [<ffffffffa94cd92d>] __qdisc_run+0x4d/0x1d0
+[ 681.774983] [<ffffffffa949b2b2>] net_tx_action+0xc2/0x160
+[ 681.774985] [<ffffffffa90664c1>] __do_softirq+0xf1/0x200
+[ 681.774987] [<ffffffffa90665ee>] run_ksoftirqd+0x1e/0x30
+[ 681.774989] [<ffffffffa90896b0>] smpboot_thread_fn+0x150/0x260
+[ 681.774991] [<ffffffffa9089560>] ? sort_range+0x40/0x40
+[ 681.774992] [<ffffffffa9085fe4>] kthread+0xe4/0x100
+[ 681.774994] [<ffffffffa9085f00>] ? kthread_worker_fn+0x170/0x170
+[ 681.774995] [<ffffffffa95d8d1e>] ret_from_fork+0x3e/0x70
+
+mq/mqprio have their own ways to report qlen/drops by folding stats on
+all their queues, with appropriate locking.
+
+A second problem is that qdisc_tree_decrease_qlen() calls qdisc_lookup()
+without proper locking : concurrent qdisc updates could corrupt the list
+that qdisc_match_from_root() parses to find a qdisc given its handle.
+
+Fix first problem adding a TCQ_F_NOPARENT qdisc flag that
+qdisc_tree_decrease_qlen() can use to abort its tree traversal,
+as soon as it meets a mq/mqprio qdisc children.
+
+Second problem can be fixed by RCU protection.
+Qdisc are already freed after RCU grace period, so qdisc_list_add() and
+qdisc_list_del() simply have to use appropriate rcu list variants.
+
+A future patch will add a per struct netdev_queue list anchor, so that
+qdisc_tree_decrease_qlen() can have more efficient lookups.
+
+Reported-by: Daniele Fucini <dfucini@gmail.com>
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Cc: Cong Wang <cwang@twopensource.com>
+Cc: Jamal Hadi Salim <jhs@mojatatu.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/sch_generic.h | 3 +++
+ net/sched/sch_api.c | 27 ++++++++++++++++++---------
+ net/sched/sch_generic.c | 2 +-
+ net/sched/sch_mq.c | 4 ++--
+ net/sched/sch_mqprio.c | 4 ++--
+ 5 files changed, 26 insertions(+), 14 deletions(-)
+
+--- a/include/net/sch_generic.h
++++ b/include/net/sch_generic.h
+@@ -61,6 +61,9 @@ struct Qdisc {
+ */
+ #define TCQ_F_WARN_NONWC (1 << 16)
+ #define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */
++#define TCQ_F_NOPARENT 0x40 /* root of its hierarchy :
++ * qdisc_tree_decrease_qlen() should stop.
++ */
+ u32 limit;
+ const struct Qdisc_ops *ops;
+ struct qdisc_size_table __rcu *stab;
+--- a/net/sched/sch_api.c
++++ b/net/sched/sch_api.c
+@@ -253,7 +253,8 @@ int qdisc_set_default(const char *name)
+ }
+
+ /* We know handle. Find qdisc among all qdisc's attached to device
+- (root qdisc, all its children, children of children etc.)
++ * (root qdisc, all its children, children of children etc.)
++ * Note: caller either uses rtnl or rcu_read_lock()
+ */
+
+ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
+@@ -264,7 +265,7 @@ static struct Qdisc *qdisc_match_from_ro
+ root->handle == handle)
+ return root;
+
+- list_for_each_entry(q, &root->list, list) {
++ list_for_each_entry_rcu(q, &root->list, list) {
+ if (q->handle == handle)
+ return q;
+ }
+@@ -277,15 +278,18 @@ void qdisc_list_add(struct Qdisc *q)
+ struct Qdisc *root = qdisc_dev(q)->qdisc;
+
+ WARN_ON_ONCE(root == &noop_qdisc);
+- list_add_tail(&q->list, &root->list);
++ ASSERT_RTNL();
++ list_add_tail_rcu(&q->list, &root->list);
+ }
+ }
+ EXPORT_SYMBOL(qdisc_list_add);
+
+ void qdisc_list_del(struct Qdisc *q)
+ {
+- if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
+- list_del(&q->list);
++ if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
++ ASSERT_RTNL();
++ list_del_rcu(&q->list);
++ }
+ }
+ EXPORT_SYMBOL(qdisc_list_del);
+
+@@ -750,14 +754,18 @@ void qdisc_tree_decrease_qlen(struct Qdi
+ if (n == 0)
+ return;
+ drops = max_t(int, n, 0);
++ rcu_read_lock();
+ while ((parentid = sch->parent)) {
+ if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
+- return;
++ break;
+
++ if (sch->flags & TCQ_F_NOPARENT)
++ break;
++ /* TODO: perform the search on a per txq basis */
+ sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
+ if (sch == NULL) {
+- WARN_ON(parentid != TC_H_ROOT);
+- return;
++ WARN_ON_ONCE(parentid != TC_H_ROOT);
++ break;
+ }
+ cops = sch->ops->cl_ops;
+ if (cops->qlen_notify) {
+@@ -768,6 +776,7 @@ void qdisc_tree_decrease_qlen(struct Qdi
+ sch->q.qlen -= n;
+ __qdisc_qstats_drop(sch, drops);
+ }
++ rcu_read_unlock();
+ }
+ EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
+
+@@ -941,7 +950,7 @@ qdisc_create(struct net_device *dev, str
+ }
+ lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
+ if (!netif_is_multiqueue(dev))
+- sch->flags |= TCQ_F_ONETXQUEUE;
++ sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+ }
+
+ sch->handle = handle;
+--- a/net/sched/sch_generic.c
++++ b/net/sched/sch_generic.c
+@@ -743,7 +743,7 @@ static void attach_one_default_qdisc(str
+ return;
+ }
+ if (!netif_is_multiqueue(dev))
+- qdisc->flags |= TCQ_F_ONETXQUEUE;
++ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+ }
+ dev_queue->qdisc_sleeping = qdisc;
+ }
+--- a/net/sched/sch_mq.c
++++ b/net/sched/sch_mq.c
+@@ -63,7 +63,7 @@ static int mq_init(struct Qdisc *sch, st
+ if (qdisc == NULL)
+ goto err;
+ priv->qdiscs[ntx] = qdisc;
+- qdisc->flags |= TCQ_F_ONETXQUEUE;
++ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+ }
+
+ sch->flags |= TCQ_F_MQROOT;
+@@ -156,7 +156,7 @@ static int mq_graft(struct Qdisc *sch, u
+
+ *old = dev_graft_qdisc(dev_queue, new);
+ if (new)
+- new->flags |= TCQ_F_ONETXQUEUE;
++ new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+ if (dev->flags & IFF_UP)
+ dev_activate(dev);
+ return 0;
+--- a/net/sched/sch_mqprio.c
++++ b/net/sched/sch_mqprio.c
+@@ -132,7 +132,7 @@ static int mqprio_init(struct Qdisc *sch
+ goto err;
+ }
+ priv->qdiscs[i] = qdisc;
+- qdisc->flags |= TCQ_F_ONETXQUEUE;
++ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+ }
+
+ /* If the mqprio options indicate that hardware should own
+@@ -209,7 +209,7 @@ static int mqprio_graft(struct Qdisc *sc
+ *old = dev_graft_qdisc(dev_queue, new);
+
+ if (new)
+- new->flags |= TCQ_F_ONETXQUEUE;
++ new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+
+ if (dev->flags & IFF_UP)
+ dev_activate(dev);
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Daniel Borkmann <daniel@iogearbox.net>
+Date: Wed, 11 Nov 2015 23:25:41 +0100
+Subject: packet: always probe for transport header
+
+From: Daniel Borkmann <daniel@iogearbox.net>
+
+[ Upstream commit 8fd6c80d9dd938ca338c70698533a7e304752846 ]
+
+We concluded that the skb_probe_transport_header() should better be
+called unconditionally. Avoiding the call into the flow dissector has
+also not really much to do with the direct xmit mode.
+
+While it seems that only virtio_net code makes use of GSO from non
+RX/TX ring packet socket paths, we should probe for a transport header
+nevertheless before they hit devices.
+
+Reference: http://thread.gmane.org/gmane.linux.network/386173/
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Acked-by: Jason Wang <jasowang@redhat.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/packet/af_packet.c | 7 +++----
+ 1 file changed, 3 insertions(+), 4 deletions(-)
+
+--- a/net/packet/af_packet.c
++++ b/net/packet/af_packet.c
+@@ -2328,8 +2328,7 @@ static int tpacket_fill_skb(struct packe
+ len = ((to_write > len_max) ? len_max : to_write);
+ }
+
+- if (!packet_use_direct_xmit(po))
+- skb_probe_transport_header(skb, 0);
++ skb_probe_transport_header(skb, 0);
+
+ return tp_len;
+ }
+@@ -2681,8 +2680,8 @@ static int packet_snd(struct socket *soc
+ len += vnet_hdr_len;
+ }
+
+- if (!packet_use_direct_xmit(po))
+- skb_probe_transport_header(skb, reserve);
++ skb_probe_transport_header(skb, reserve);
++
+ if (unlikely(extra_len == 4))
+ skb->no_fcs = 1;
+
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Daniel Borkmann <daniel@iogearbox.net>
+Date: Wed, 11 Nov 2015 23:25:40 +0100
+Subject: packet: do skb_probe_transport_header when we actually have data
+
+From: Daniel Borkmann <daniel@iogearbox.net>
+
+[ Upstream commit efdfa2f7848f64517008136fb41f53c4a1faf93a ]
+
+In tpacket_fill_skb() commit c1aad275b029 ("packet: set transport
+header before doing xmit") and later on 40893fd0fd4e ("net: switch
+to use skb_probe_transport_header()") was probing for a transport
+header on the skb from a ring buffer slot, but at a time, where
+the skb has _not even_ been filled with data yet. So that call into
+the flow dissector is pretty useless. Lets do it after we've set
+up the skb frags.
+
+Fixes: c1aad275b029 ("packet: set transport header before doing xmit")
+Reported-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Acked-by: Jason Wang <jasowang@redhat.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/packet/af_packet.c | 5 +++--
+ 1 file changed, 3 insertions(+), 2 deletions(-)
+
+--- a/net/packet/af_packet.c
++++ b/net/packet/af_packet.c
+@@ -2249,8 +2249,6 @@ static int tpacket_fill_skb(struct packe
+ skb_reserve(skb, hlen);
+ skb_reset_network_header(skb);
+
+- if (!packet_use_direct_xmit(po))
+- skb_probe_transport_header(skb, 0);
+ if (unlikely(po->tp_tx_has_off)) {
+ int off_min, off_max, off;
+ off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
+@@ -2330,6 +2328,9 @@ static int tpacket_fill_skb(struct packe
+ len = ((to_write > len_max) ? len_max : to_write);
+ }
+
++ if (!packet_use_direct_xmit(po))
++ skb_probe_transport_header(skb, 0);
++
+ return tp_len;
+ }
+
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Daniel Borkmann <daniel@iogearbox.net>
+Date: Wed, 11 Nov 2015 23:25:44 +0100
+Subject: packet: fix tpacket_snd max frame len
+
+From: Daniel Borkmann <daniel@iogearbox.net>
+
+[ Upstream commit 5cfb4c8d05b4409c4044cb9c05b19705c1d9818b ]
+
+Since it's introduction in commit 69e3c75f4d54 ("net: TX_RING and
+packet mmap"), TX_RING could be used from SOCK_DGRAM and SOCK_RAW
+side. When used with SOCK_DGRAM only, the size_max > dev->mtu +
+reserve check should have reserve as 0, but currently, this is
+unconditionally set (in it's original form as dev->hard_header_len).
+
+I think this is not correct since tpacket_fill_skb() would then
+take dev->mtu and dev->hard_header_len into account for SOCK_DGRAM,
+the extra VLAN_HLEN could be possible in both cases. Presumably, the
+reserve code was copied from packet_snd(), but later on missed the
+check. Make it similar as we have it in packet_snd().
+
+Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap")
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Acked-by: Willem de Bruijn <willemb@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/packet/af_packet.c | 9 +++++----
+ 1 file changed, 5 insertions(+), 4 deletions(-)
+
+--- a/net/packet/af_packet.c
++++ b/net/packet/af_packet.c
+@@ -2391,12 +2391,13 @@ static int tpacket_snd(struct packet_soc
+ if (unlikely(!(dev->flags & IFF_UP)))
+ goto out_put;
+
+- reserve = dev->hard_header_len + VLAN_HLEN;
++ if (po->sk.sk_socket->type == SOCK_RAW)
++ reserve = dev->hard_header_len;
+ size_max = po->tx_ring.frame_size
+ - (po->tp_hdrlen - sizeof(struct sockaddr_ll));
+
+- if (size_max > dev->mtu + reserve)
+- size_max = dev->mtu + reserve;
++ if (size_max > dev->mtu + reserve + VLAN_HLEN)
++ size_max = dev->mtu + reserve + VLAN_HLEN;
+
+ do {
+ ph = packet_current_frame(po, &po->tx_ring,
+@@ -2423,7 +2424,7 @@ static int tpacket_snd(struct packet_soc
+ tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
+ addr, hlen);
+ if (likely(tp_len >= 0) &&
+- tp_len > dev->mtu + dev->hard_header_len &&
++ tp_len > dev->mtu + reserve &&
+ !packet_extra_vlan_len_allowed(dev, skb))
+ tp_len = -EMSGSIZE;
+
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Daniel Borkmann <daniel@iogearbox.net>
+Date: Wed, 11 Nov 2015 23:25:43 +0100
+Subject: packet: infer protocol from ethernet header if unset
+
+From: Daniel Borkmann <daniel@iogearbox.net>
+
+[ Upstream commit c72219b75fde768efccf7666342282fab7f9e4e7 ]
+
+In case no struct sockaddr_ll has been passed to packet
+socket's sendmsg() when doing a TX_RING flush run, then
+skb->protocol is set to po->num instead, which is the protocol
+passed via socket(2)/bind(2).
+
+Applications only xmitting can go the path of allocating the
+socket as socket(PF_PACKET, <mode>, 0) and do a bind(2) on the
+TX_RING with sll_protocol of 0. That way, register_prot_hook()
+is neither called on creation nor on bind time, which saves
+cycles when there's no interest in capturing anyway.
+
+That leaves us however with po->num 0 instead and therefore
+the TX_RING flush run sets skb->protocol to 0 as well. Eric
+reported that this leads to problems when using tools like
+trafgen over bonding device. I.e. the bonding's hash function
+could invoke the kernel's flow dissector, which depends on
+skb->protocol being properly set. In the current situation, all
+the traffic is then directed to a single slave.
+
+Fix it up by inferring skb->protocol from the Ethernet header
+when not set and we have ARPHRD_ETHER device type. This is only
+done in case of SOCK_RAW and where we have a dev->hard_header_len
+length. In case of ARPHRD_ETHER devices, this is guaranteed to
+cover ETH_HLEN, and therefore being accessed on the skb after
+the skb_store_bits().
+
+Reported-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Acked-by: Willem de Bruijn <willemb@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/packet/af_packet.c | 11 +++++++++++
+ 1 file changed, 11 insertions(+)
+
+--- a/net/packet/af_packet.c
++++ b/net/packet/af_packet.c
+@@ -2219,6 +2219,15 @@ static bool ll_header_truncated(const st
+ return false;
+ }
+
++static void tpacket_set_protocol(const struct net_device *dev,
++ struct sk_buff *skb)
++{
++ if (dev->type == ARPHRD_ETHER) {
++ skb_reset_mac_header(skb);
++ skb->protocol = eth_hdr(skb)->h_proto;
++ }
++}
++
+ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
+ void *frame, struct net_device *dev, int size_max,
+ __be16 proto, unsigned char *addr, int hlen)
+@@ -2300,6 +2309,8 @@ static int tpacket_fill_skb(struct packe
+ dev->hard_header_len);
+ if (unlikely(err))
+ return err;
++ if (!skb->protocol)
++ tpacket_set_protocol(dev, skb);
+
+ data += dev->hard_header_len;
+ to_write -= dev->hard_header_len;
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Daniel Borkmann <daniel@iogearbox.net>
+Date: Wed, 11 Nov 2015 23:25:42 +0100
+Subject: packet: only allow extra vlan len on ethernet devices
+
+From: Daniel Borkmann <daniel@iogearbox.net>
+
+[ Upstream commit 3c70c132488794e2489ab045559b0ce0afcf17de ]
+
+Packet sockets can be used by various net devices and are not
+really restricted to ARPHRD_ETHER device types. However, when
+currently checking for the extra 4 bytes that can be transmitted
+in VLAN case, our assumption is that we generally probe on
+ARPHRD_ETHER devices. Therefore, before looking into Ethernet
+header, check the device type first.
+
+This also fixes the issue where non-ARPHRD_ETHER devices could
+have no dev->hard_header_len in TX_RING SOCK_RAW case, and thus
+the check would test unfilled linear part of the skb (instead
+of non-linear).
+
+Fixes: 57f89bfa2140 ("network: Allow af_packet to transmit +4 bytes for VLAN packets.")
+Fixes: 52f1454f629f ("packet: allow to transmit +4 byte in TX_RING slot for VLAN case")
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Acked-by: Willem de Bruijn <willemb@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/packet/af_packet.c | 60 ++++++++++++++++++++-----------------------------
+ 1 file changed, 25 insertions(+), 35 deletions(-)
+
+--- a/net/packet/af_packet.c
++++ b/net/packet/af_packet.c
+@@ -1622,6 +1622,20 @@ static void fanout_release(struct sock *
+ kfree_rcu(po->rollover, rcu);
+ }
+
++static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
++ struct sk_buff *skb)
++{
++ /* Earlier code assumed this would be a VLAN pkt, double-check
++ * this now that we have the actual packet in hand. We can only
++ * do this check on Ethernet devices.
++ */
++ if (unlikely(dev->type != ARPHRD_ETHER))
++ return false;
++
++ skb_reset_mac_header(skb);
++ return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q));
++}
++
+ static const struct proto_ops packet_ops;
+
+ static const struct proto_ops packet_ops_spkt;
+@@ -1783,18 +1797,10 @@ retry:
+ goto retry;
+ }
+
+- if (len > (dev->mtu + dev->hard_header_len + extra_len)) {
+- /* Earlier code assumed this would be a VLAN pkt,
+- * double-check this now that we have the actual
+- * packet in hand.
+- */
+- struct ethhdr *ehdr;
+- skb_reset_mac_header(skb);
+- ehdr = eth_hdr(skb);
+- if (ehdr->h_proto != htons(ETH_P_8021Q)) {
+- err = -EMSGSIZE;
+- goto out_unlock;
+- }
++ if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
++ !packet_extra_vlan_len_allowed(dev, skb)) {
++ err = -EMSGSIZE;
++ goto out_unlock;
+ }
+
+ skb->protocol = proto;
+@@ -2406,18 +2412,10 @@ static int tpacket_snd(struct packet_soc
+ tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
+ addr, hlen);
+ if (likely(tp_len >= 0) &&
+- tp_len > dev->mtu + dev->hard_header_len) {
+- struct ethhdr *ehdr;
+- /* Earlier code assumed this would be a VLAN pkt,
+- * double-check this now that we have the actual
+- * packet in hand.
+- */
++ tp_len > dev->mtu + dev->hard_header_len &&
++ !packet_extra_vlan_len_allowed(dev, skb))
++ tp_len = -EMSGSIZE;
+
+- skb_reset_mac_header(skb);
+- ehdr = eth_hdr(skb);
+- if (ehdr->h_proto != htons(ETH_P_8021Q))
+- tp_len = -EMSGSIZE;
+- }
+ if (unlikely(tp_len < 0)) {
+ if (po->tp_loss) {
+ __packet_set_status(po, ph,
+@@ -2638,18 +2636,10 @@ static int packet_snd(struct socket *soc
+
+ sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
+
+- if (!gso_type && (len > dev->mtu + reserve + extra_len)) {
+- /* Earlier code assumed this would be a VLAN pkt,
+- * double-check this now that we have the actual
+- * packet in hand.
+- */
+- struct ethhdr *ehdr;
+- skb_reset_mac_header(skb);
+- ehdr = eth_hdr(skb);
+- if (ehdr->h_proto != htons(ETH_P_8021Q)) {
+- err = -EMSGSIZE;
+- goto out_free;
+- }
++ if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
++ !packet_extra_vlan_len_allowed(dev, skb)) {
++ err = -EMSGSIZE;
++ goto out_free;
+ }
+
+ skb->protocol = proto;
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Quentin Casasnovas <quentin.casasnovas@oracle.com>
+Date: Tue, 24 Nov 2015 17:13:21 -0500
+Subject: RDS: fix race condition when sending a message on unbound socket
+
+From: Quentin Casasnovas <quentin.casasnovas@oracle.com>
+
+[ Upstream commit 8c7188b23474cca017b3ef354c4a58456f68303a ]
+
+Sasha's found a NULL pointer dereference in the RDS connection code when
+sending a message to an apparently unbound socket. The problem is caused
+by the code checking if the socket is bound in rds_sendmsg(), which checks
+the rs_bound_addr field without taking a lock on the socket. This opens a
+race where rs_bound_addr is temporarily set but where the transport is not
+in rds_bind(), leading to a NULL pointer dereference when trying to
+dereference 'trans' in __rds_conn_create().
+
+Vegard wrote a reproducer for this issue, so kindly ask him to share if
+you're interested.
+
+I cannot reproduce the NULL pointer dereference using Vegard's reproducer
+with this patch, whereas I could without.
+
+Complete earlier incomplete fix to CVE-2015-6937:
+
+ 74e98eb08588 ("RDS: verify the underlying transport exists before creating a connection")
+
+Cc: David S. Miller <davem@davemloft.net>
+Cc: stable@vger.kernel.org
+
+Reviewed-by: Vegard Nossum <vegard.nossum@oracle.com>
+Reviewed-by: Sasha Levin <sasha.levin@oracle.com>
+Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
+Signed-off-by: Quentin Casasnovas <quentin.casasnovas@oracle.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/rds/connection.c | 6 ------
+ net/rds/send.c | 4 +++-
+ 2 files changed, 3 insertions(+), 7 deletions(-)
+
+--- a/net/rds/connection.c
++++ b/net/rds/connection.c
+@@ -187,12 +187,6 @@ new_conn:
+ }
+ }
+
+- if (trans == NULL) {
+- kmem_cache_free(rds_conn_slab, conn);
+- conn = ERR_PTR(-ENODEV);
+- goto out;
+- }
+-
+ conn->c_trans = trans;
+
+ ret = trans->conn_alloc(conn, gfp);
+--- a/net/rds/send.c
++++ b/net/rds/send.c
+@@ -986,11 +986,13 @@ int rds_sendmsg(struct socket *sock, str
+ release_sock(sk);
+ }
+
+- /* racing with another thread binding seems ok here */
++ lock_sock(sk);
+ if (daddr == 0 || rs->rs_bound_addr == 0) {
++ release_sock(sk);
+ ret = -ENOTCONN; /* XXX not a great errno */
+ goto out;
+ }
++ release_sock(sk);
+
+ /* size of rm including all sgs */
+ ret = rds_rm_size(msg, payload_len);
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: lucien <lucien.xin@gmail.com>
+Date: Thu, 12 Nov 2015 13:07:07 +0800
+Subject: sctp: translate host order to network order when setting a hmacid
+
+From: lucien <lucien.xin@gmail.com>
+
+[ Upstream commit ed5a377d87dc4c87fb3e1f7f698cba38cd893103 ]
+
+now sctp auth cannot work well when setting a hmacid manually, which
+is caused by that we didn't use the network order for hmacid, so fix
+it by adding the transformation in sctp_auth_ep_set_hmacs.
+
+even we set hmacid with the network order in userspace, it still
+can't work, because of this condition in sctp_auth_ep_set_hmacs():
+
+ if (id > SCTP_AUTH_HMAC_ID_MAX)
+ return -EOPNOTSUPP;
+
+so this wasn't working before and thus it won't break compatibility.
+
+Fixes: 65b07e5d0d09 ("[SCTP]: API updates to suport SCTP-AUTH extensions.")
+Signed-off-by: Xin Long <lucien.xin@gmail.com>
+Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+Acked-by: Neil Horman <nhorman@tuxdriver.com>
+Acked-by: Vlad Yasevich <vyasevich@gmail.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/sctp/auth.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/net/sctp/auth.c
++++ b/net/sctp/auth.c
+@@ -809,8 +809,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_e
+ if (!has_sha1)
+ return -EINVAL;
+
+- memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0],
+- hmacs->shmac_num_idents * sizeof(__u16));
++ for (i = 0; i < hmacs->shmac_num_idents; i++)
++ ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]);
+ ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) +
+ hmacs->shmac_num_idents * sizeof(__u16));
+ return 0;
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Neil Horman <nhorman@tuxdriver.com>
+Date: Mon, 16 Nov 2015 13:09:10 -0500
+Subject: snmp: Remove duplicate OUTMCAST stat increment
+
+From: Neil Horman <nhorman@tuxdriver.com>
+
+[ Upstream commit 41033f029e393a64e81966cbe34d66c6cf8a2e7e ]
+
+the OUTMCAST stat is double incremented, getting bumped once in the mcast code
+itself, and again in the common ip output path. Remove the mcast bump, as its
+not needed
+
+Validated by the reporter, with good results
+
+Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
+Reported-by: Claus Jensen <claus.jensen@microsemi.com>
+CC: Claus Jensen <claus.jensen@microsemi.com>
+CC: David Miller <davem@davemloft.net>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/ipv6/mcast.c | 2 --
+ 1 file changed, 2 deletions(-)
+
+--- a/net/ipv6/mcast.c
++++ b/net/ipv6/mcast.c
+@@ -1651,7 +1651,6 @@ out:
+ if (!err) {
+ ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
+ ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+- IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
+ } else {
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+ }
+@@ -2014,7 +2013,6 @@ out:
+ if (!err) {
+ ICMP6MSGOUT_INC_STATS(net, idev, type);
+ ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+- IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len);
+ } else
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Yuchung Cheng <ycheng@google.com>
+Date: Wed, 18 Nov 2015 18:17:30 -0800
+Subject: tcp: disable Fast Open on timeouts after handshake
+
+From: Yuchung Cheng <ycheng@google.com>
+
+[ Upstream commit 0e45f4da5981895e885dd72fe912a3f8e32bae73 ]
+
+Some middle-boxes black-hole the data after the Fast Open handshake
+(https://www.ietf.org/proceedings/94/slides/slides-94-tcpm-13.pdf).
+The exact reason is unknown. The work-around is to disable Fast Open
+temporarily after multiple recurring timeouts with few or no data
+delivered in the established state.
+
+Signed-off-by: Yuchung Cheng <ycheng@google.com>
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reported-by: Christoph Paasch <cpaasch@apple.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/ipv4/tcp_timer.c | 12 ++++++++++++
+ 1 file changed, 12 insertions(+)
+
+--- a/net/ipv4/tcp_timer.c
++++ b/net/ipv4/tcp_timer.c
+@@ -176,6 +176,18 @@ static int tcp_write_timeout(struct sock
+ syn_set = true;
+ } else {
+ if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
++ /* Some middle-boxes may black-hole Fast Open _after_
++ * the handshake. Therefore we conservatively disable
++ * Fast Open on this path on recurring timeouts with
++ * few or zero bytes acked after Fast Open.
++ */
++ if (tp->syn_data_acked &&
++ tp->bytes_acked <= tp->rx_opt.mss_clamp) {
++ tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
++ if (icsk->icsk_retransmits == sysctl_tcp_retries1)
++ NET_INC_STATS_BH(sock_net(sk),
++ LINUX_MIB_TCPFASTOPENACTIVEFAIL);
++ }
+ /* Black hole detection */
+ tcp_mtu_probing(icsk, sk);
+
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Eric Dumazet <edumazet@google.com>
+Date: Wed, 18 Nov 2015 21:03:33 -0800
+Subject: tcp: fix potential huge kmalloc() calls in TCP_REPAIR
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 5d4c9bfbabdb1d497f21afd81501e5c54b0c85d9 ]
+
+tcp_send_rcvq() is used for re-injecting data into tcp receive queue.
+
+Problems :
+
+- No check against size is performed, allowed user to fool kernel in
+ attempting very large memory allocations, eventually triggering
+ OOM when memory is fragmented.
+
+- In case of fault during the copy we do not return correct errno.
+
+Lets use alloc_skb_with_frags() to cook optimal skbs.
+
+Fixes: 292e8d8c8538 ("tcp: Move rcvq sending to tcp_input.c")
+Fixes: c0e88ff0f256 ("tcp: Repair socket queues")
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Cc: Pavel Emelyanov <xemul@parallels.com>
+Acked-by: Pavel Emelyanov <xemul@parallels.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/ipv4/tcp_input.c | 22 +++++++++++++++++++---
+ 1 file changed, 19 insertions(+), 3 deletions(-)
+
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -4434,19 +4434,34 @@ static int __must_check tcp_queue_rcv(st
+ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
+ {
+ struct sk_buff *skb;
++ int err = -ENOMEM;
++ int data_len = 0;
+ bool fragstolen;
+
+ if (size == 0)
+ return 0;
+
+- skb = alloc_skb(size, sk->sk_allocation);
++ if (size > PAGE_SIZE) {
++ int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
++
++ data_len = npages << PAGE_SHIFT;
++ size = data_len + (size & ~PAGE_MASK);
++ }
++ skb = alloc_skb_with_frags(size - data_len, data_len,
++ PAGE_ALLOC_COSTLY_ORDER,
++ &err, sk->sk_allocation);
+ if (!skb)
+ goto err;
+
++ skb_put(skb, size - data_len);
++ skb->data_len = data_len;
++ skb->len = size;
++
+ if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+ goto err_free;
+
+- if (memcpy_from_msg(skb_put(skb, size), msg, size))
++ err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
++ if (err)
+ goto err_free;
+
+ TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
+@@ -4462,7 +4477,8 @@ int tcp_send_rcvq(struct sock *sk, struc
+ err_free:
+ kfree_skb(skb);
+ err:
+- return -ENOMEM;
++ return err;
++
+ }
+
+ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Eric Dumazet <edumazet@google.com>
+Date: Thu, 26 Nov 2015 08:18:14 -0800
+Subject: tcp: initialize tp->copied_seq in case of cross SYN connection
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 142a2e7ece8d8ac0e818eb2c91f99ca894730e2a ]
+
+Dmitry provided a syzkaller (http://github.com/google/syzkaller)
+generated program that triggers the WARNING at
+net/ipv4/tcp.c:1729 in tcp_recvmsg() :
+
+WARN_ON(tp->copied_seq != tp->rcv_nxt &&
+ !(flags & (MSG_PEEK | MSG_TRUNC)));
+
+His program is specifically attempting a Cross SYN TCP exchange,
+that we support (for the pleasure of hackers ?), but it looks we
+lack proper tcp->copied_seq initialization.
+
+Thanks again Dmitry for your report and testings.
+
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reported-by: Dmitry Vyukov <dvyukov@google.com>
+Tested-by: Dmitry Vyukov <dvyukov@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/ipv4/tcp_input.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -5636,6 +5636,7 @@ discard:
+ }
+
+ tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
++ tp->copied_seq = tp->rcv_nxt;
+ tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
+
+ /* RFC1323: The window in SYN & SYN/ACK segments is
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Eric Dumazet <edumazet@google.com>
+Date: Wed, 18 Nov 2015 12:40:13 -0800
+Subject: tcp: md5: fix lockdep annotation
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 1b8e6a01e19f001e9f93b39c32387961c91ed3cc ]
+
+When a passive TCP is created, we eventually call tcp_md5_do_add()
+with sk pointing to the child. It is not owner by the user yet (we
+will add this socket into listener accept queue a bit later anyway)
+
+But we do own the spinlock, so amend the lockdep annotation to avoid
+following splat :
+
+[ 8451.090932] net/ipv4/tcp_ipv4.c:923 suspicious rcu_dereference_protected() usage!
+[ 8451.090932]
+[ 8451.090932] other info that might help us debug this:
+[ 8451.090932]
+[ 8451.090934]
+[ 8451.090934] rcu_scheduler_active = 1, debug_locks = 1
+[ 8451.090936] 3 locks held by socket_sockopt_/214795:
+[ 8451.090936] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff855c6ac1>] __netif_receive_skb_core+0x151/0xe90
+[ 8451.090947] #1: (rcu_read_lock){.+.+..}, at: [<ffffffff85618143>] ip_local_deliver_finish+0x43/0x2b0
+[ 8451.090952] #2: (slock-AF_INET){+.-...}, at: [<ffffffff855acda5>] sk_clone_lock+0x1c5/0x500
+[ 8451.090958]
+[ 8451.090958] stack backtrace:
+[ 8451.090960] CPU: 7 PID: 214795 Comm: socket_sockopt_
+
+[ 8451.091215] Call Trace:
+[ 8451.091216] <IRQ> [<ffffffff856fb29c>] dump_stack+0x55/0x76
+[ 8451.091229] [<ffffffff85123b5b>] lockdep_rcu_suspicious+0xeb/0x110
+[ 8451.091235] [<ffffffff8564544f>] tcp_md5_do_add+0x1bf/0x1e0
+[ 8451.091239] [<ffffffff85645751>] tcp_v4_syn_recv_sock+0x1f1/0x4c0
+[ 8451.091242] [<ffffffff85642b27>] ? tcp_v4_md5_hash_skb+0x167/0x190
+[ 8451.091246] [<ffffffff85647c78>] tcp_check_req+0x3c8/0x500
+[ 8451.091249] [<ffffffff856451ae>] ? tcp_v4_inbound_md5_hash+0x11e/0x190
+[ 8451.091253] [<ffffffff85647170>] tcp_v4_rcv+0x3c0/0x9f0
+[ 8451.091256] [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
+[ 8451.091260] [<ffffffff856181b6>] ip_local_deliver_finish+0xb6/0x2b0
+[ 8451.091263] [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
+[ 8451.091267] [<ffffffff85618d38>] ip_local_deliver+0x48/0x80
+[ 8451.091270] [<ffffffff85618510>] ip_rcv_finish+0x160/0x700
+[ 8451.091273] [<ffffffff8561900e>] ip_rcv+0x29e/0x3d0
+[ 8451.091277] [<ffffffff855c74b7>] __netif_receive_skb_core+0xb47/0xe90
+
+Fixes: a8afca0329988 ("tcp: md5: protects md5sig_info with RCU")
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reported-by: Willem de Bruijn <willemb@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/ipv4/tcp_ipv4.c | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+--- a/net/ipv4/tcp_ipv4.c
++++ b/net/ipv4/tcp_ipv4.c
+@@ -922,7 +922,8 @@ int tcp_md5_do_add(struct sock *sk, cons
+ }
+
+ md5sig = rcu_dereference_protected(tp->md5sig_info,
+- sock_owned_by_user(sk));
++ sock_owned_by_user(sk) ||
++ lockdep_is_held(&sk->sk_lock.slock));
+ if (!md5sig) {
+ md5sig = kmalloc(sizeof(*md5sig), gfp);
+ if (!md5sig)
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Kamal Mostafa <kamal@canonical.com>
+Date: Wed, 11 Nov 2015 14:24:27 -0800
+Subject: tools/net: Use include/uapi with __EXPORTED_HEADERS__
+
+From: Kamal Mostafa <kamal@canonical.com>
+
+[ Upstream commit d7475de58575c904818efa369c82e88c6648ce2e ]
+
+Use the local uapi headers to keep in sync with "recently" added #define's
+(e.g. SKF_AD_VLAN_TPID). Refactored CFLAGS, and bpf_asm doesn't need -I.
+
+Fixes: 3f356385e8a4 ("filter: bpf_asm: add minimal bpf asm tool")
+Signed-off-by: Kamal Mostafa <kamal@canonical.com>
+Acked-by: Daniel Borkmann <daniel@iogearbox.net>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ tools/net/Makefile | 7 ++++---
+ 1 file changed, 4 insertions(+), 3 deletions(-)
+
+--- a/tools/net/Makefile
++++ b/tools/net/Makefile
+@@ -4,6 +4,9 @@ CC = gcc
+ LEX = flex
+ YACC = bison
+
++CFLAGS += -Wall -O2
++CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
++
+ %.yacc.c: %.y
+ $(YACC) -o $@ -d $<
+
+@@ -12,15 +15,13 @@ YACC = bison
+
+ all : bpf_jit_disasm bpf_dbg bpf_asm
+
+-bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm'
++bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
+ bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
+ bpf_jit_disasm : bpf_jit_disasm.o
+
+-bpf_dbg : CFLAGS = -Wall -O2
+ bpf_dbg : LDLIBS = -lreadline
+ bpf_dbg : bpf_dbg.o
+
+-bpf_asm : CFLAGS = -Wall -O2 -I.
+ bpf_asm : LDLIBS =
+ bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
+ bpf_exp.lex.o : bpf_exp.yacc.c
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
+Date: Fri, 20 Nov 2015 22:07:23 +0000
+Subject: unix: avoid use-after-free in ep_remove_wait_queue
+
+From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
+
+[ Upstream commit 7d267278a9ece963d77eefec61630223fce08c6c ]
+
+Rainer Weikusat <rweikusat@mobileactivedefense.com> writes:
+An AF_UNIX datagram socket being the client in an n:1 association with
+some server socket is only allowed to send messages to the server if the
+receive queue of this socket contains at most sk_max_ack_backlog
+datagrams. This implies that prospective writers might be forced to go
+to sleep despite none of the message presently enqueued on the server
+receive queue were sent by them. In order to ensure that these will be
+woken up once space becomes again available, the present unix_dgram_poll
+routine does a second sock_poll_wait call with the peer_wait wait queue
+of the server socket as queue argument (unix_dgram_recvmsg does a wake
+up on this queue after a datagram was received). This is inherently
+problematic because the server socket is only guaranteed to remain alive
+for as long as the client still holds a reference to it. In case the
+connection is dissolved via connect or by the dead peer detection logic
+in unix_dgram_sendmsg, the server socket may be freed despite "the
+polling mechanism" (in particular, epoll) still has a pointer to the
+corresponding peer_wait queue. There's no way to forcibly deregister a
+wait queue with epoll.
+
+Based on an idea by Jason Baron, the patch below changes the code such
+that a wait_queue_t belonging to the client socket is enqueued on the
+peer_wait queue of the server whenever the peer receive queue full
+condition is detected by either a sendmsg or a poll. A wake up on the
+peer queue is then relayed to the ordinary wait queue of the client
+socket via wake function. The connection to the peer wait queue is again
+dissolved if either a wake up is about to be relayed or the client
+socket reconnects or a dead peer is detected or the client socket is
+itself closed. This enables removing the second sock_poll_wait from
+unix_dgram_poll, thus avoiding the use-after-free, while still ensuring
+that no blocked writer sleeps forever.
+
+Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
+Fixes: ec0d215f9420 ("af_unix: fix 'poll for write'/connected DGRAM sockets")
+Reviewed-by: Jason Baron <jbaron@akamai.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/af_unix.h | 1
+ net/unix/af_unix.c | 183 ++++++++++++++++++++++++++++++++++++++++++++------
+ 2 files changed, 165 insertions(+), 19 deletions(-)
+
+--- a/include/net/af_unix.h
++++ b/include/net/af_unix.h
+@@ -62,6 +62,7 @@ struct unix_sock {
+ #define UNIX_GC_CANDIDATE 0
+ #define UNIX_GC_MAYBE_CYCLE 1
+ struct socket_wq peer_wq;
++ wait_queue_t peer_wake;
+ };
+
+ static inline struct unix_sock *unix_sk(struct sock *sk)
+--- a/net/unix/af_unix.c
++++ b/net/unix/af_unix.c
+@@ -326,6 +326,118 @@ found:
+ return s;
+ }
+
++/* Support code for asymmetrically connected dgram sockets
++ *
++ * If a datagram socket is connected to a socket not itself connected
++ * to the first socket (eg, /dev/log), clients may only enqueue more
++ * messages if the present receive queue of the server socket is not
++ * "too large". This means there's a second writeability condition
++ * poll and sendmsg need to test. The dgram recv code will do a wake
++ * up on the peer_wait wait queue of a socket upon reception of a
++ * datagram which needs to be propagated to sleeping would-be writers
++ * since these might not have sent anything so far. This can't be
++ * accomplished via poll_wait because the lifetime of the server
++ * socket might be less than that of its clients if these break their
++ * association with it or if the server socket is closed while clients
++ * are still connected to it and there's no way to inform "a polling
++ * implementation" that it should let go of a certain wait queue
++ *
++ * In order to propagate a wake up, a wait_queue_t of the client
++ * socket is enqueued on the peer_wait queue of the server socket
++ * whose wake function does a wake_up on the ordinary client socket
++ * wait queue. This connection is established whenever a write (or
++ * poll for write) hit the flow control condition and broken when the
++ * association to the server socket is dissolved or after a wake up
++ * was relayed.
++ */
++
++static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
++ void *key)
++{
++ struct unix_sock *u;
++ wait_queue_head_t *u_sleep;
++
++ u = container_of(q, struct unix_sock, peer_wake);
++
++ __remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
++ q);
++ u->peer_wake.private = NULL;
++
++ /* relaying can only happen while the wq still exists */
++ u_sleep = sk_sleep(&u->sk);
++ if (u_sleep)
++ wake_up_interruptible_poll(u_sleep, key);
++
++ return 0;
++}
++
++static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
++{
++ struct unix_sock *u, *u_other;
++ int rc;
++
++ u = unix_sk(sk);
++ u_other = unix_sk(other);
++ rc = 0;
++ spin_lock(&u_other->peer_wait.lock);
++
++ if (!u->peer_wake.private) {
++ u->peer_wake.private = other;
++ __add_wait_queue(&u_other->peer_wait, &u->peer_wake);
++
++ rc = 1;
++ }
++
++ spin_unlock(&u_other->peer_wait.lock);
++ return rc;
++}
++
++static void unix_dgram_peer_wake_disconnect(struct sock *sk,
++ struct sock *other)
++{
++ struct unix_sock *u, *u_other;
++
++ u = unix_sk(sk);
++ u_other = unix_sk(other);
++ spin_lock(&u_other->peer_wait.lock);
++
++ if (u->peer_wake.private == other) {
++ __remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
++ u->peer_wake.private = NULL;
++ }
++
++ spin_unlock(&u_other->peer_wait.lock);
++}
++
++static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
++ struct sock *other)
++{
++ unix_dgram_peer_wake_disconnect(sk, other);
++ wake_up_interruptible_poll(sk_sleep(sk),
++ POLLOUT |
++ POLLWRNORM |
++ POLLWRBAND);
++}
++
++/* preconditions:
++ * - unix_peer(sk) == other
++ * - association is stable
++ */
++static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
++{
++ int connected;
++
++ connected = unix_dgram_peer_wake_connect(sk, other);
++
++ if (unix_recvq_full(other))
++ return 1;
++
++ if (connected)
++ unix_dgram_peer_wake_disconnect(sk, other);
++
++ return 0;
++}
++
+ static inline int unix_writable(struct sock *sk)
+ {
+ return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
+@@ -430,6 +542,8 @@ static void unix_release_sock(struct soc
+ skpair->sk_state_change(skpair);
+ sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
+ }
++
++ unix_dgram_peer_wake_disconnect(sk, skpair);
+ sock_put(skpair); /* It may now die */
+ unix_peer(sk) = NULL;
+ }
+@@ -665,6 +779,7 @@ static struct sock *unix_create1(struct
+ INIT_LIST_HEAD(&u->link);
+ mutex_init(&u->readlock); /* single task reading lock */
+ init_waitqueue_head(&u->peer_wait);
++ init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
+ unix_insert_socket(unix_sockets_unbound(sk), sk);
+ out:
+ if (sk == NULL)
+@@ -1032,6 +1147,8 @@ restart:
+ if (unix_peer(sk)) {
+ struct sock *old_peer = unix_peer(sk);
+ unix_peer(sk) = other;
++ unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
++
+ unix_state_double_unlock(sk, other);
+
+ if (other != old_peer)
+@@ -1471,6 +1588,7 @@ static int unix_dgram_sendmsg(struct soc
+ struct scm_cookie scm;
+ int max_level;
+ int data_len = 0;
++ int sk_locked;
+
+ wait_for_unix_gc();
+ err = scm_send(sock, msg, &scm, false);
+@@ -1549,12 +1667,14 @@ restart:
+ goto out_free;
+ }
+
++ sk_locked = 0;
+ unix_state_lock(other);
++restart_locked:
+ err = -EPERM;
+ if (!unix_may_send(sk, other))
+ goto out_unlock;
+
+- if (sock_flag(other, SOCK_DEAD)) {
++ if (unlikely(sock_flag(other, SOCK_DEAD))) {
+ /*
+ * Check with 1003.1g - what should
+ * datagram error
+@@ -1562,10 +1682,14 @@ restart:
+ unix_state_unlock(other);
+ sock_put(other);
+
++ if (!sk_locked)
++ unix_state_lock(sk);
++
+ err = 0;
+- unix_state_lock(sk);
+ if (unix_peer(sk) == other) {
+ unix_peer(sk) = NULL;
++ unix_dgram_peer_wake_disconnect_wakeup(sk, other);
++
+ unix_state_unlock(sk);
+
+ unix_dgram_disconnected(sk, other);
+@@ -1591,21 +1715,38 @@ restart:
+ goto out_unlock;
+ }
+
+- if (unix_peer(other) != sk && unix_recvq_full(other)) {
+- if (!timeo) {
+- err = -EAGAIN;
+- goto out_unlock;
++ if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
++ if (timeo) {
++ timeo = unix_wait_for_peer(other, timeo);
++
++ err = sock_intr_errno(timeo);
++ if (signal_pending(current))
++ goto out_free;
++
++ goto restart;
+ }
+
+- timeo = unix_wait_for_peer(other, timeo);
++ if (!sk_locked) {
++ unix_state_unlock(other);
++ unix_state_double_lock(sk, other);
++ }
+
+- err = sock_intr_errno(timeo);
+- if (signal_pending(current))
+- goto out_free;
++ if (unix_peer(sk) != other ||
++ unix_dgram_peer_wake_me(sk, other)) {
++ err = -EAGAIN;
++ sk_locked = 1;
++ goto out_unlock;
++ }
+
+- goto restart;
++ if (!sk_locked) {
++ sk_locked = 1;
++ goto restart_locked;
++ }
+ }
+
++ if (unlikely(sk_locked))
++ unix_state_unlock(sk);
++
+ if (sock_flag(other, SOCK_RCVTSTAMP))
+ __net_timestamp(skb);
+ maybe_add_creds(skb, sock, other);
+@@ -1619,6 +1760,8 @@ restart:
+ return len;
+
+ out_unlock:
++ if (sk_locked)
++ unix_state_unlock(sk);
+ unix_state_unlock(other);
+ out_free:
+ kfree_skb(skb);
+@@ -2475,14 +2618,16 @@ static unsigned int unix_dgram_poll(stru
+ return mask;
+
+ writable = unix_writable(sk);
+- other = unix_peer_get(sk);
+- if (other) {
+- if (unix_peer(other) != sk) {
+- sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
+- if (unix_recvq_full(other))
+- writable = 0;
+- }
+- sock_put(other);
++ if (writable) {
++ unix_state_lock(sk);
++
++ other = unix_peer(sk);
++ if (other && unix_peer(other) != sk &&
++ unix_recvq_full(other) &&
++ unix_dgram_peer_wake_me(sk, other))
++ writable = 0;
++
++ unix_state_unlock(sk);
+ }
+
+ if (writable)
--- /dev/null
+From foo@baz Fri Dec 11 11:38:35 EST 2015
+From: Andrej Ota <andrej@ota.si>
+Date: Thu, 15 Oct 2015 00:14:37 +0200
+Subject: via-rhine: fix VLAN receive handling regression.
+
+From: Andrej Ota <andrej@ota.si>
+
+[ Upstream commit 5f715c097965c0ad037f64393d0b95c50287775b ]
+
+Because eth_type_trans() consumes ethernet header worth of bytes, a call
+to read TCI from end of packet using rhine_rx_vlan_tag() no longer works
+as it's reading from an invalid offset.
+
+Tested to be working on PCEngines Alix board.
+
+Fixes: 810f19bcb862 ("via-rhine: add consistent memory barrier in vlan receive code.")
+Signed-off-by: Andrej Ota <andrej@ota.si>
+Acked-by: Francois Romieu <romieu@fr.zoreil.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/net/ethernet/via/via-rhine.c | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+--- a/drivers/net/ethernet/via/via-rhine.c
++++ b/drivers/net/ethernet/via/via-rhine.c
+@@ -2134,10 +2134,11 @@ static int rhine_rx(struct net_device *d
+ }
+
+ skb_put(skb, pkt_len);
+- skb->protocol = eth_type_trans(skb, dev);
+
+ rhine_rx_vlan_tag(skb, desc, data_size);
+
++ skb->protocol = eth_type_trans(skb, dev);
++
+ netif_receive_skb(skb);
+
+ u64_stats_update_begin(&rp->rx_stats.syncp);
projects / thirdparty / kernel / stable-queue.git / commitdiff
