4.9.26-stable review

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

This reverts commit d84be51d1c1d3fa148a3abdeeb1455690df59e63 which is commit a0e3142869d29688de6f77be31aa7a401a4a88f1 upstream.

It causes problems and would need other patches backported to resolve it, and it shouldn't have been applied to 4.9-stable.

---
 drivers/mmc/host/sdhci-msm.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

@@ -524,9 +524,7 @@ static const struct sdhci_ops sdhci_msm_
 static const struct sdhci_pltfm_data sdhci_msm_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_CARD_DETECTION |
 		  SDHCI_QUIRK_NO_CARD_NO_RESET |
-		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
-		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
-	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+		  SDHCI_QUIRK_SINGLE_POWER_WRITE,
 	.ops = &sdhci_msm_ops,
 };
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Guillaume Nault <[email protected]>

[ Upstream commit 94d7ee0baa8b764cf64ad91ed69464c1a6a0066b ]

The code following l2tp_tunnel_find() expects that a new reference is held on sk. Either sk_receive_skb() or the discard_put error path will drop a reference from the tunnel's socket.

This issue exists in both l2tp_ip and l2tp_ip6.

---
 net/l2tp/l2tp_ip.c  |    5 +++--
 net/l2tp/l2tp_ip6.c |    5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

@@ -178,9 +178,10 @@ pass_up:
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
 	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL)
+	if (tunnel) {
 		sk = tunnel->sock;
-	else {
+		sock_hold(sk);
+	} else {
 		struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
 
 		read_lock_bh(&l2tp_ip_lock);

@@ -191,9 +191,10 @@ pass_up:
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
 	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL)
+	if (tunnel) {
 		sk = tunnel->sock;
-	else {
+		sock_hold(sk);
+	} else {
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		read_lock_bh(&l2tp_ip6_lock);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrey Konovalov <[email protected]>

[ Upstream commit 8f8d28e4d6d815a391285e121c3a53a0b6cb9e7b ]

When calculating rb->frames_per_block * req->tp_block_nr the result can overflow.

Add a check that tp_block_size * tp_block_nr <= UINT_MAX.

Since frames_per_block <= tp_block_size, the expression would never overflow.

---
 net/packet/af_packet.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -4247,6 +4247,8 @@ static int packet_set_ring(struct sock *
 		rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
 		if (unlikely(rb->frames_per_block == 0))
 			goto out;
+		if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+			goto out;
 		if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
 					req->tp_frame_nr))
 			goto out;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrey Konovalov <[email protected]>

[ Upstream commit bcc5364bdcfe131e6379363f089e7b4108d35b70 ]

When calculating po->tp_hdrlen + po->tp_reserve the result can overflow.

Fix by checking that tp_reserve <= INT_MAX on assign.

---
 net/packet/af_packet.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -3702,6 +3702,8 @@ packet_setsockopt(struct socket *sock, i
 			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
+		if (val > INT_MAX)
+			return -EINVAL;
 		po->tp_reserve = val;
 		return 0;
 	}

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nikolay Aleksandrov <[email protected]>

[ Upstream commit 723b929ca0f79c0796f160c2eeda4597ee98d2b8 ]

Andrey Konovalov reported a BUG caused by the ip6mr code which is caused because we call unregister_netdevice_many for a device that is already being destroyed. In IPv4's ipmr that has been resolved by two commits long time ago by introducing the "notify" parameter to the delete function and avoiding the unregister when called from a notifier, so let's do the same for ip6mr.

The trace from Andrey:

------------[ cut here ]------------
kernel BUG at net/core/dev.c:6813!
invalid opcode: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 1 PID: 1165 Comm: kworker/u4:3 Not tainted 4.11.0-rc7+ #251
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
Workqueue: netns cleanup_net
task: ffff880069208000 task.stack: ffff8800692d8000
RIP: 0010:rollback_registered_many+0x348/0xeb0 net/core/dev.c:6813
RSP: 0018:ffff8800692de7f0 EFLAGS: 00010297
RAX: ffff880069208000 RBX: 0000000000000002 RCX: 0000000000000001
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88006af90569
RBP: ffff8800692de9f0 R08: ffff8800692dec60 R09: 0000000000000000
R10: 0000000000000006 R11: 0000000000000000 R12: ffff88006af90070
R13: ffff8800692debf0 R14: dffffc0000000000 R15: ffff88006af90000
FS:  0000000000000000(0000) GS:ffff88006cb00000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fe7e897d870 CR3: 00000000657e7000 CR4: 00000000000006e0
Call Trace:
 unregister_netdevice_many.part.105+0x87/0x440 net/core/dev.c:7881
 unregister_netdevice_many+0xc8/0x120 net/core/dev.c:7880
 ip6mr_device_event+0x362/0x3f0 net/ipv6/ip6mr.c:1346
 notifier_call_chain+0x145/0x2f0 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394
 raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x51/0x90 net/core/dev.c:1647
 call_netdevice_notifiers net/core/dev.c:1663
 rollback_registered_many+0x919/0xeb0 net/core/dev.c:6841
 unregister_netdevice_many.part.105+0x87/0x440 net/core/dev.c:7881
 unregister_netdevice_many net/core/dev.c:7880
 default_device_exit_batch+0x4fa/0x640 net/core/dev.c:8333
 ops_exit_list.isra.4+0x100/0x150 net/core/net_namespace.c:144
 cleanup_net+0x5a8/0xb40 net/core/net_namespace.c:463
 process_one_work+0xc04/0x1c10 kernel/workqueue.c:2097
 worker_thread+0x223/0x19c0 kernel/workqueue.c:2231
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x31/0x40 arch/x86/entry/entry_64.S:430
Code: 3c 32 00 0f 85 70 0b 00 00 48 b8 00 02 00 00 00 00 ad de 49 89
47 78 e9 93 fe ff ff 49 8d 57 70 49 8d 5f 78 eb 9e e8 88 7a 14 fe <0f>
0b 48 8b 9d 28 fe ff ff e8 7a 7a 14 fe 48 b8 00 00 00 00 00
RIP: rollback_registered_many+0x348/0xeb0 RSP: ffff8800692de7f0
---[ end trace e0b29c57e9b3292c ]---

---
 net/ipv6/ip6mr.c |   13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

@@ -774,7 +774,8 @@ failure:
  *	Delete a VIF entry
  */
 
-static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
+static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
+		       struct list_head *head)
 {
 	struct mif_device *v;
 	struct net_device *dev;

@@ -820,7 +821,7 @@ static int mif6_delete(struct mr6_table
 					     dev->ifindex, &in6_dev->cnf);
 	}
 
-	if (v->flags & MIFF_REGISTER)
+	if ((v->flags & MIFF_REGISTER) && !notify)
 		unregister_netdevice_queue(dev, head);
 
 	dev_put(dev);

@@ -1331,7 +1332,6 @@ static int ip6mr_device_event(struct not
 	struct mr6_table *mrt;
 	struct mif_device *v;
 	int ct;
-	LIST_HEAD(list);
 
 	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;

@@ -1340,10 +1340,9 @@ static int ip6mr_device_event(struct not
 		v = &mrt->vif6_table[0];
 		for (ct = 0; ct < mrt->maxvif; ct++, v++) {
 			if (v->dev == dev)
-				mif6_delete(mrt, ct, &list);
+				mif6_delete(mrt, ct, 1, NULL);
 		}
 	}
-	unregister_netdevice_many(&list);
 
 	return NOTIFY_DONE;
 }

@@ -1552,7 +1551,7 @@ static void mroute_clean_tables(struct m
 	for (i = 0; i < mrt->maxvif; i++) {
 		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
 			continue;
-		mif6_delete(mrt, i, &list);
+		mif6_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 

@@ -1706,7 +1705,7 @@ int ip6_mroute_setsockopt(struct sock *s
 		if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
 			return -EFAULT;
 		rtnl_lock();
-		ret = mif6_delete(mrt, mifi, NULL);
+		ret = mif6_delete(mrt, mifi, 0, NULL);
 		rtnl_unlock();
 		return ret;
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mohamad Haj Yahia <[email protected]>

[ Upstream commit 55378a238e04b39cc82957d91d16499704ea719b ]

If FW is stuck in initializing state we will skip the driver load, but current error handling flow doesn't clean previously allocated command interface resources.

---
 drivers/net/ethernet/mellanox/mlx5/core/main.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -966,7 +966,7 @@ static int mlx5_load_one(struct mlx5_cor
 	if (err) {
 		dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n",
 			FW_INIT_TIMEOUT_MILI);
-		goto out_err;
+		goto err_cmd_cleanup;
 	}
 
 	err = mlx5_core_enable_hca(dev, 0);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Ahern <[email protected]>

[ Upstream commit 8048ced9beb21a52e3305f3332ae82020619f24e ]

Taking down the loopback device wreaks havoc on IPv6 routing. By extension, taking down a VRF device wreaks havoc on its table.

Dmitry and Andrey both reported heap out-of-bounds reports in the IPv6 FIB code while running syzkaller fuzzer. The root cause is a dead dst that is on the garbage list gets reinserted into the IPv6 FIB. While on the gc (or perhaps when it gets added to the gc list) the dst->next is set to an IPv4 dst. A subsequent walk of the ipv6 tables causes the out-of-bounds access.

Andrey's reproducer was the key to getting to the bottom of this.

With IPv6, host routes for an address have the dst->dev set to the loopback device. When the 'lo' device is taken down, rt6_ifdown initiates a walk of the fib evicting routes with the 'lo' device which means all host routes are removed. That process moves the dst which is attached to an inet6_ifaddr to the gc list and marks it as dead.

The recent change to keep global IPv6 addresses added a new function, fixup_permanent_addr, that is called on admin up. That function restarts dad for an inet6_ifaddr and when it completes the host route attached to it is inserted into the fib. Since the route was marked dead and moved to the gc list, re-inserting the route causes the reported out-of-bounds accesses. If the device with the address is taken down or the address is removed, the WARN_ON in fib6_del is triggered.

All of those faults are fixed by regenerating the host route if the existing one has been moved to the gc list, something that can be determined by checking if the rt6i_ref counter is 0.

---
 net/ipv6/addrconf.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

@@ -3253,14 +3253,24 @@ static void addrconf_gre_config(struct n
 static int fixup_permanent_addr(struct inet6_dev *idev,
 				struct inet6_ifaddr *ifp)
 {
-	if (!ifp->rt) {
-		struct rt6_info *rt;
+	/* rt6i_ref == 0 means the host route was removed from the
+	 * FIB, for example, if 'lo' device is taken down. In that
+	 * case regenerate the host route.
+	 */
+	if (!ifp->rt || !atomic_read(&ifp->rt->rt6i_ref)) {
+		struct rt6_info *rt, *prev;
 
 		rt = addrconf_dst_alloc(idev, &ifp->addr, false);
 		if (unlikely(IS_ERR(rt)))
 			return PTR_ERR(rt);
 
+		/* ifp->rt can be accessed outside of rtnl */
+		spin_lock(&ifp->lock);
+		prev = ifp->rt;
 		ifp->rt = rt;
+		spin_unlock(&ifp->lock);
+
+		ip6_rt_put(prev);
 	}
 
 	if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Takashi Sakamoto <[email protected]>

commit dfb00a56935186171abb5280b3407c3f910011f1 upstream.

An abstraction of asynchronous transaction for transmission of MIDI messages was introduced in Linux v4.4. Each driver can utilize this abstraction to transfer MIDI messages via fixed-length payload of transaction to a certain unit address. Filling payload of the transaction is done by callback. In this callback, each driver can return negative error code, however current implementation assigns the return value to unsigned variable.

This commit changes type of the variable to fix the bug.

---
 sound/firewire/lib.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -45,7 +45,7 @@ struct snd_fw_async_midi_port {
 
 	struct snd_rawmidi_substream *substream;
 	snd_fw_async_midi_port_fill fill;
-	unsigned int consume_bytes;
+	int consume_bytes;
 };
 
 int snd_fw_async_midi_port_init(struct snd_fw_async_midi_port *port,

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Takashi Iwai <[email protected]>

commit 4e7655fd4f47c23e5249ea260dc802f909a64611 upstream.

The snd_use_lock_sync() (thus its implementation snd_use_lock_sync_helper()) has the 5 seconds timeout to break out of the sync loop. It was introduced from the beginning, just to be "safer", in terms of avoiding the stupid bugs.

However, as Ben Hutchings suggested, this timeout rather introduces a potential leak or use-after-free that was apparently fixed by the commit 2d7d54002e39 ("ALSA: seq: Fix race during FIFO resize"):
for example, snd_seq_fifo_event_in() -> snd_seq_event_dup() -> copy_from_user() could block for a long time, and snd_use_lock_sync() goes timeout and still leaves the cell at releasing the pool.

For fixing such a problem, we remove the break by the timeout while still keeping the warning.

---
 sound/core/seq/seq_lock.c |    9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

@@ -28,19 +28,16 @@
 /* wait until all locks are released */
 void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line)
 {
-	int max_count = 5 * HZ;
+	int warn_count = 5 * HZ;
 
 	if (atomic_read(lockp) < 0) {
 		pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line);
 		return;
 	}
 	while (atomic_read(lockp) > 0) {
-		if (max_count == 0) {
-			pr_warn("ALSA: seq_lock: timeout [%d left] in %s:%d\n", atomic_read(lockp), file, line);
-			break;
-		}
+		if (warn_count-- == 0)
+			pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line);
 		schedule_timeout_uninterruptible(1);
-		max_count--;
 	}
 }
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Josh Poimboeuf <[email protected]>

commit 34a477e5297cbaa6ecc6e17c042a866e1cbe80d6 upstream.

On x86-32, with CONFIG_FIRMWARE and multiple CPUs, if you enable function graph tracing and then suspend to RAM, it will triple fault and reboot when it resumes.

The first fault happens when booting a secondary CPU:

startup_32_smp()
load_ucode_ap()
prepare_ftrace_return()
ftrace_graph_is_dead()
(accesses 'kill_ftrace_graph')

The early head_32.S code calls into load_ucode_ap(), which has an an ftrace hook, so it calls prepare_ftrace_return(), which calls ftrace_graph_is_dead(), which tries to access the global 'kill_ftrace_graph' variable with a virtual address, causing a fault because the CPU is still in real mode.

The fix is to add a check in prepare_ftrace_return() to make sure it's running in protected mode before continuing. The check makes sure the stack pointer is a virtual kernel address. It's a bit of a hack, but it's not very intrusive and it works well enough.

For reference, here are a few other (more difficult) ways this could have potentially been fixed:

- Move startup_32_smp()'s call to load_ucode_ap() down to *after* paging is enabled. (No idea what that would break.)

- Track down load_ucode_ap()'s entire callee tree and mark all the functions 'notrace'. (Probably not realistic.)

- Pause graph tracing in ftrace_suspend_notifier_call() or bringup_cpu() or __cpu_up(), and ensure that the pause facility can be queried from real mode.

---
 arch/x86/kernel/ftrace.c |   12 ++++++++++++
 1 file changed, 12 insertions(+)

@@ -983,6 +983,18 @@ void prepare_ftrace_return(unsigned long
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
+	/*
+	 * When resuming from suspend-to-ram, this function can be indirectly
+	 * called from early CPU startup code while the CPU is in real mode,
+	 * which would fail miserably.  Make sure the stack pointer is a
+	 * virtual address.
+	 *
+	 * This check isn't as accurate as virt_addr_valid(), but it should be
+	 * good enough for this purpose, and it's fast.
+	 */
+	if (unlikely((long)__builtin_frame_address(0) >= 0))
+		return;
+
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Guillaume Nault <[email protected]>

[ Upstream commit e91793bb615cf6cdd59c0b6749fe173687bb0947 ]

The Rx path may grab the socket right before pppol2tp_release(), but nothing guarantees that it will enqueue packets before skb_queue_purge(). Therefore, the socket can be destroyed without its queues fully purged.

Fix this by purging queues in pppol2tp_session_destruct() where we're guaranteed nothing is still referencing the socket.

---
 net/l2tp/l2tp_ppp.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -450,6 +450,10 @@ static void pppol2tp_session_close(struc
 static void pppol2tp_session_destruct(struct sock *sk)
 {
 	struct l2tp_session *session = sk->sk_user_data;
+
+	skb_queue_purge(&sk->sk_receive_queue);
+	skb_queue_purge(&sk->sk_write_queue);
+
 	if (session) {
 		sk->sk_user_data = NULL;
 		BUG_ON(session->magic != L2TP_SESSION_MAGIC);

@@ -488,9 +492,6 @@ static int pppol2tp_release(struct socke
 		l2tp_session_queue_purge(session);
 		sock_put(sk);
 	}
-	skb_queue_purge(&sk->sk_receive_queue);
-	skb_queue_purge(&sk->sk_write_queue);
-
 	release_sock(sk);
 
 	/* This will delete the session context via

This is the start of the stable review cycle for the 4.9.26 release. There are 54 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed May 3 21:26:19 UTC 2017. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.9.26-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.9.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.9.26-rc1

Josh Poimboeuf <[email protected]>
ftrace/x86: Fix triple fault with graph tracing and suspend-to-ram

Vineet Gupta <[email protected]>
ARCv2: save r30 on kernel entry as gcc uses it for code-gen

Maksim Salau <[email protected]>
net: can: usb: gs_usb: Fix buffer on stack

Jason A. Donenfeld <[email protected]>
macsec: avoid heap overflow in skb_to_sgvec

Yan, Zheng <[email protected]>
ceph: fix recursion between ceph_set_acl() and __ceph_setattr()

J. Bruce Fields <[email protected]>
nfsd: stricter decoding of write-like NFSv2/v3 ops

J. Bruce Fields <[email protected]>
nfsd4: minor NFSv2/v3 write decoding cleanup

J. Bruce Fields <[email protected]>
nfsd: check for oversized NFSv2/v3 arguments

Dmitry Torokhov <[email protected]>
Input: i8042 - add Clevo P650RS to the i8042 reset list

Takashi Iwai <[email protected]>
ASoC: intel: Fix PM and non-atomic crash in bytcr drivers

Al Viro <[email protected]>
p9_client_readdir() fix

James Cowgill <[email protected]>
MIPS: Avoid BUG warning in arch_check_elf

James Hogan <[email protected]>
MIPS: cevt-r4k: Fix out-of-bounds array access

James Hogan <[email protected]>
MIPS: KGDB: Use kernel context for sleeping threads

Noam Camus <[email protected]>
ARC: [plat-eznps] Fix build error

Takashi Iwai <[email protected]>
ALSA: seq: Don't break snd_use_lock_sync() loop by timeout

Takashi Sakamoto <[email protected]>
ALSA: firewire-lib: fix inappropriate assignment between signed/unsigned type

Takashi Sakamoto <[email protected]>
ALSA: oxfw: fix regression to handle Stanton SCS.1m/1d

Jamie Bainbridge <[email protected]>
ipv6: check raw payload size correctly in ioctl

Wei Wang <[email protected]>
tcp: memset ca_priv data to 0 properly

WANG Cong <[email protected]>

    ipv6: check skb->protocol before lookup for nexthop

Alexander Kochetkov <[email protected]>
net: phy: fix auto-negotiation stall due to unavailable interrupt

David Ahern <[email protected]>
net: ipv6: regenerate host route if moved to gc list

Herbert Xu <[email protected]>
macvlan: Fix device ref leak when purging bc_queue

Ilan Tayari <[email protected]>
net/mlx5e: Fix ETHTOOL_GRXCLSRLALL handling

Eugenia Emantayev <[email protected]>
net/mlx5e: Fix small packet threshold

Mohamad Haj Yahia <[email protected]>
net/mlx5: Fix driver load bad flow when having fw initializing timeout

Nikolay Aleksandrov <[email protected]>
ip6mr: fix notification device destruction

Tushar Dave <[email protected]>

    netpoll: Check for skb->queue_mapping

David Ahern <[email protected]>
net: ipv6: RTF_PCPU should not be settable from userspace

Ilan Tayari <[email protected]>
gso: Validate assumption of frag_list segementation

Dan Carpenter <[email protected]>
dp83640: don't recieve time stamps twice

Sergei Shtylyov <[email protected]>
sh_eth: unmap DMA buffers when freeing rings

David Ahern <[email protected]>
net: vrf: Fix setting NLM_F_EXCL flag when adding l3mdev rule

Willem de Bruijn <[email protected]>
net-timestamp: avoid use-after-free in ip_recv_error

Rabin Vincent <[email protected]>

    ipv6: Fix idev->addr_list corruption

Eric Dumazet <[email protected]>
tcp: clear saved_syn in tcp_disconnect()

Xin Long <[email protected]>
sctp: listen on the sock only when it's state is listening or closed

Florian Larysch <[email protected]>
net: ipv4: fix multipath RTM_GETROUTE behavior when iif is given

Guillaume Nault <[email protected]>
l2tp: fix PPP pseudo-wire auto-loading

Guillaume Nault <[email protected]>
l2tp: take reference on sessions being dumped

Andrey Konovalov <[email protected]>
net/packet: fix overflow in check for tp_reserve

Andrey Konovalov <[email protected]>
net/packet: fix overflow in check for tp_frame_nr

Guillaume Nault <[email protected]>
l2tp: purge socket queues in the .destruct() callback

Guillaume Nault <[email protected]>
l2tp: hold tunnel socket when handling control frames in l2tp_ip and l2tp_ip6

Talat Batheesh <[email protected]>
net/mlx5: Avoid dereferencing uninitialized pointer

Alexei Starovoitov <[email protected]>
bpf: improve verifier packet range checks

WANG Cong <[email protected]>
kcm: return immediately after copy_from_user() failure

Nathan Sullivan <[email protected]>
net: phy: handle state correctly in phy_stop_machine

Eric Dumazet <[email protected]>
net: neigh: guard against NULL solicit() method

Tom Hromatka <[email protected]>
sparc64: Fix kernel panic due to erroneous #ifdef surrounding pmd_write()

bob picco <[email protected]>
sparc64: kern_addr_valid regression

Eric Dumazet <[email protected]>
ping: implement proper locking

Greg Kroah-Hartman <[email protected]>
Revert "mmc: sdhci-msm: Enable few quirks"

-------------

Diffstat:

 Makefile                                           |   4 +-
 arch/arc/include/asm/atomic.h                      |   3 +-
 arch/arc/include/asm/entry-arcv2.h                 |   2 +
 arch/arc/include/asm/ptrace.h                      |   2 +-
 arch/mips/kernel/cevt-r4k.c                        |   2 +-
 arch/mips/kernel/elf.c                             |   2 +-
 arch/mips/kernel/kgdb.c                            |  48 +++++---
 arch/sparc/include/asm/pgtable_64.h                |  15 +--
 arch/sparc/mm/init_64.c                            |   2 +-
 arch/x86/kernel/ftrace.c                           |  12 ++
 drivers/input/serio/i8042-x86ia64io.h              |   7 ++
 drivers/mmc/host/sdhci-msm.c                       |   4 +-
 drivers/net/can/usb/gs_usb.c                       |  17 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   2 +-
 .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c    |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/lag.c      |   5 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   2 +-
 drivers/net/ethernet/renesas/sh_eth.c              | 122 +++++++++++----------
 drivers/net/macsec.c                               |   2 +-
 drivers/net/macvlan.c                              |  11 +-
 drivers/net/phy/dp83640.c                          |   2 -
 drivers/net/phy/phy.c                              |  42 ++++++-
 drivers/net/vrf.c                                  |   2 +-
 fs/ceph/inode.c                                    |  22 ++--
 fs/nfsd/nfs3xdr.c                                  |  13 ++-
 fs/nfsd/nfssvc.c                                   |  36 ++++++
 fs/nfsd/nfsxdr.c                                   |  10 +-
 include/linux/phy.h                                |   1 +
 include/uapi/linux/ipv6_route.h                    |   2 +-
 kernel/bpf/verifier.c                              |   5 +-
 net/9p/client.c                                    |   4 +
 net/core/neighbour.c                               |   3 +-
 net/core/netpoll.c                                 |  10 +-
 net/core/skbuff.c                                  |  19 +++-
 net/ipv4/ip_sockglue.c                             |   9 +-
 net/ipv4/ping.c                                    |   5 +-
 net/ipv4/route.c                                   |   2 +-
 net/ipv4/tcp.c                                     |   1 +
 net/ipv4/tcp_cong.c                                |  11 +-
 net/ipv6/addrconf.c                                |  25 ++++-
 net/ipv6/datagram.c                                |  10 +-
 net/ipv6/ip6_tunnel.c                              |  34 +++---
 net/ipv6/ip6mr.c                                   |  13 +--
 net/ipv6/raw.c                                     |   3 +-
 net/ipv6/route.c                                   |   4 +
 net/kcm/kcmsock.c                                  |   6 +-
 net/l2tp/l2tp_core.c                               |   8 +-
 net/l2tp/l2tp_core.h                               |   3 +-
 net/l2tp/l2tp_debugfs.c                            |  10 +-
 net/l2tp/l2tp_ip.c                                 |   5 +-
 net/l2tp/l2tp_ip6.c                                |   5 +-
 net/l2tp/l2tp_netlink.c                            |   7 +-
 net/l2tp/l2tp_ppp.c                                |  19 ++--
 net/packet/af_packet.c                             |   4 +
 net/sctp/socket.c                                  |   3 +
 sound/core/seq/seq_lock.c                          |   9 +-
 sound/firewire/lib.h                               |   2 +-
 sound/firewire/oxfw/oxfw.c                         |   4 +-
 sound/soc/intel/boards/bytcr_rt5640.c              |   4 +-
 sound/soc/intel/boards/bytcr_rt5651.c              |   2 -
 60 files changed, 417 insertions(+), 227 deletions(-)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Guillaume Nault <[email protected]>

[ Upstream commit e08293a4ccbcc993ded0fdc46f1e57926b833d63 ]

Take a reference on the sessions returned by l2tp_session_find_nth() (and rename it l2tp_session_get_nth() to reflect this change), so that caller is assured that the session isn't going to disappear while processing it.

For procfs and debugfs handlers, the session is held in the .start() callback and dropped in .show(). Given that pppol2tp_seq_session_show() dereferences the associated PPPoL2TP socket and that l2tp_dfs_seq_session_show() might call pppol2tp_show(), we also need to call the session's .ref() callback to prevent the socket from going away from under us.

---
 net/l2tp/l2tp_core.c    |    8 ++++++--
 net/l2tp/l2tp_core.h    |    3 ++-
 net/l2tp/l2tp_debugfs.c |   10 +++++++---
 net/l2tp/l2tp_netlink.c |    7 +++++--
 net/l2tp/l2tp_ppp.c     |   10 +++++++---
 5 files changed, 27 insertions(+), 11 deletions(-)

@@ -278,7 +278,8 @@ struct l2tp_session *l2tp_session_find(s
 }
 EXPORT_SYMBOL_GPL(l2tp_session_find);
 
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref)
 {
 	int hash;
 	struct l2tp_session *session;

@@ -288,6 +289,9 @@ struct l2tp_session *l2tp_session_find_n
 	for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
 		hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
 			if (++count > nth) {
+				l2tp_session_inc_refcount(session);
+				if (do_ref && session->ref)
+					session->ref(session);
 				read_unlock_bh(&tunnel->hlist_lock);
 				return session;
 			}

@@ -298,7 +302,7 @@ struct l2tp_session *l2tp_session_find_n
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
 
 /* Lookup a session by interface name.
  * This is very inefficient but is only used by management interfaces.

@@ -243,7 +243,8 @@ out:
 struct l2tp_session *l2tp_session_find(struct net *net,
 				       struct l2tp_tunnel *tunnel,
 				       u32 session_id);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref);
 struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
 struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);

@@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct
 
 static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {

@@ -238,10 +238,14 @@ static int l2tp_dfs_seq_show(struct seq_
 	}
 
 	/* Show the tunnel or session context */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		l2tp_dfs_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;

@@ -844,7 +844,7 @@ static int l2tp_nl_cmd_session_dump(stru
 				goto out;
 		}
 
-		session = l2tp_session_find_nth(tunnel, si);
+		session = l2tp_session_get_nth(tunnel, si, false);
 		if (session == NULL) {
 			ti++;
 			tunnel = NULL;

@@ -854,8 +854,11 @@ static int l2tp_nl_cmd_session_dump(stru
 
 		if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					 session, L2TP_CMD_SESSION_GET) < 0)
+					 session, L2TP_CMD_SESSION_GET) < 0) {
+			l2tp_session_dec_refcount(session);
 			break;
+		}
+		l2tp_session_dec_refcount(session);
 
 		si++;
 	}

@@ -1555,7 +1555,7 @@ static void pppol2tp_next_tunnel(struct
 
 static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {

@@ -1682,10 +1682,14 @@ static int pppol2tp_seq_show(struct seq_
 
 	/* Show the tunnel or session context.
 	 */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		pppol2tp_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		pppol2tp_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Guillaume Nault <[email protected]>

[ Upstream commit 249ee819e24c180909f43c1173c8ef6724d21faf ]

PPP pseudo-wire type is 7 (11 is L2TP_PWTYPE_IP).

---
 net/l2tp/l2tp_ppp.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1848,4 +1848,4 @@ MODULE_DESCRIPTION("PPP over L2TP over U
 MODULE_LICENSE("GPL");
 MODULE_VERSION(PPPOL2TP_DRV_VERSION);
 MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OL2TP);
-MODULE_ALIAS_L2TP_PWTYPE(11);
+MODULE_ALIAS_L2TP_PWTYPE(7);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Larysch <[email protected]>

[ Upstream commit a8801799c6975601fd58ae62f48964caec2eb83f ]

inet_rtm_getroute synthesizes a skeletal ICMP skb, which is passed to ip_route_input when iif is given. If a multipath route is present for the designated destination, ip_multipath_icmp_hash ends up being called, which uses the source/destination addresses within the skb to calculate a hash. However, those are not set in the synthetic skb, causing it to return an arbitrary and incorrect result.

Instead, use UDP, which gets no such special treatment.

---
 net/ipv4/route.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2569,7 +2569,7 @@ static int inet_rtm_getroute(struct sk_b
 	skb_reset_network_header(skb);
 
 	/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
-	ip_hdr(skb)->protocol = IPPROTO_ICMP;
+	ip_hdr(skb)->protocol = IPPROTO_UDP;
 	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
 
 	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit 34b2789f1d9bf8dcca9b5cb553d076ca2cd898ee ]

Now sctp doesn't check sock's state before listening on it. It could even cause changing a sock with any state to become a listening sock when doing sctp_listen.

This patch is to fix it by checking sock's state in sctp_listen, so that it will listen on the sock with right state.

---
 net/sctp/socket.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -6861,6 +6861,9 @@ int sctp_inet_listen(struct socket *sock
 	if (sock->state != SS_UNCONNECTED)
 		goto out;
 
+	if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED))
+		goto out;
+
 	/* If backlog is zero, disable listening. */
 	if (!backlog) {
 		if (sctp_sstate(sk, CLOSED))

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

commit 43a6684519ab0a6c52024b5e25322476cabad893 upstream.

We got a report of yet another bug in ping

http://www.openwall.com/lists/oss-security/2017/03/24/6

->disconnect() is not called with socket lock held.

Fix this by acquiring ping rwlock earlier.

Thanks to Daniel, Alexander and Andrey for letting us know this problem.

---
 net/ipv4/ping.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

@@ -156,17 +156,18 @@ int ping_hash(struct sock *sk)
 void ping_unhash(struct sock *sk)
 {
 	struct inet_sock *isk = inet_sk(sk);
+
 	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+	write_lock_bh(&ping_table.lock);
 	if (sk_hashed(sk)) {
-		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
 		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-		write_unlock_bh(&ping_table.lock);
 	}
+	write_unlock_bh(&ping_table.lock);
 }
 EXPORT_SYMBOL_GPL(ping_unhash);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Willem de Bruijn <[email protected]>

[ Upstream commit 1862d6208db0aeca9c8ace44915b08d5ab2cd667 ]

Syzkaller reported a use-after-free in ip_recv_error at line

    info->ipi_ifindex = skb->dev->ifindex;

This function is called on dequeue from the error queue, at which point the device pointer may no longer be valid.

Save ifindex on enqueue in __skb_complete_tx_timestamp, when the pointer is valid or NULL. Store it in temporary storage skb->cb.

It is safe to reference skb->dev here, as called from device drivers or dev_queue_xmit. The exception is when called from tcp_ack_tstamp; in that case it is NULL and ifindex is set to 0 (invalid).

Do not return a pktinfo cmsg if ifindex is 0. This maintains the current behavior of not returning a cmsg if skb->dev was NULL.

On dequeue, the ipv4 path will cast from sock_exterr_skb to in_pktinfo. Both have ifindex as their first element, so no explicit conversion is needed. This is by design, introduced in commit 0b922b7a829c ("net: original ingress device index in PKTINFO"). For ipv6 ip6_datagram_support_cmsg converts to in6_pktinfo.

---
 net/core/skbuff.c      |    1 +
 net/ipv4/ip_sockglue.c |    9 ++++-----
 net/ipv6/datagram.c    |   10 +---------
 3 files changed, 6 insertions(+), 14 deletions(-)

@@ -3779,6 +3779,7 @@ static void __skb_complete_tx_timestamp(
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	serr->ee.ee_info = tstype;
+	serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
 		if (sk->sk_protocol == IPPROTO_TCP &&

@@ -474,16 +474,15 @@ static bool ipv4_datagram_support_cmsg(c
 		return false;
 
 	/* Support IP_PKTINFO on tstamp packets if requested, to correlate
-	 * timestamp with egress dev. Not possible for packets without dev
+	 * timestamp with egress dev. Not possible for packets without iif
 	 * or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
 	 */
-	if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
-	    (!skb->dev))
+	info = PKTINFO_SKB_CB(skb);
+	if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) ||
+	    !info->ipi_ifindex)
 		return false;
 
-	info = PKTINFO_SKB_CB(skb);
 	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
-	info->ipi_ifindex = skb->dev->ifindex;
 	return true;
 }
 

@@ -400,9 +400,6 @@ static inline bool ipv6_datagram_support
  * At one point, excluding local errors was a quick test to identify icmp/icmp6
  * errors. This is no longer true, but the test remained, so the v6 stack,
  * unlike v4, also honors cmsg requests on all wifi and timestamp errors.
- *
- * Timestamp code paths do not initialize the fields expected by cmsg:
- * the PKTINFO fields in skb->cb[]. Fill those in here.
  */
 static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
 				      struct sock_exterr_skb *serr)

@@ -414,14 +411,9 @@ static bool ip6_datagram_support_cmsg(st
 	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL)
 		return false;
 
-	if (!skb->dev)
+	if (!IP6CB(skb)->iif)
 		return false;
 
-	if (skb->protocol == htons(ETH_P_IPV6))
-		IP6CB(skb)->iif = skb->dev->ifindex;
-	else
-		PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex;
-
 	return true;
 }
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Ahern <[email protected]>

[ Upstream commit 426c87caa2b4578b43cd3f689f02c65b743b2559 ]

Only need 1 l3mdev FIB rule. Fix setting NLM_F_EXCL in the nlmsghdr.

---
 drivers/net/vrf.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1124,7 +1124,7 @@ static int vrf_fib_rule(const struct net
 		goto nla_put_failure;
 
 	/* rule only needs to appear once */
-	nlh->nlmsg_flags &= NLM_F_EXCL;
+	nlh->nlmsg_flags |= NLM_F_EXCL;
 
 	frh = nlmsg_data(nlh);
 	memset(frh, 0, sizeof(*frh));

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sergei Shtylyov <[email protected]>

[ Upstream commit 1debdc8f9ebd07daf140e417b3841596911e0066 ]

The DMA API debugging (when enabled) causes:

WARNING: CPU: 0 PID: 1445 at lib/dma-debug.c:519 add_dma_entry+0xe0/0x12c

DMA-API: exceeded 7 overlapping mappings of cacheline 0x01b2974d

to be printed after repeated initialization of the Ether device, e.g. suspend/resume or 'ifconfig' up/down. This is because DMA buffers mapped using dma_map_single() in sh_eth_ring_format() and sh_eth_start_xmit() are never unmapped. Resolve this problem by unmapping the buffers when freeing the descriptor rings; in order to do it right, we'd have to add an extra parameter to sh_eth_txfree() (we rename this function to sh_eth_tx_free(), while at it).

Based on the commit a47b70ea86bd ("ravb: unmap descriptors when freeing rings").

---
 drivers/net/ethernet/renesas/sh_eth.c |  122 ++++++++++++++++++----------------
 1 file changed, 67 insertions(+), 55 deletions(-)

@@ -1059,12 +1059,70 @@ static struct mdiobb_ops bb_ops = {
 	.get_mdio_data = sh_get_mdio,
 };
 
+/* free Tx skb function */
+static int sh_eth_tx_free(struct net_device *ndev, bool sent_only)
+{
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+	struct sh_eth_txdesc *txdesc;
+	int free_num = 0;
+	int entry;
+	bool sent;
+
+	for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
+		entry = mdp->dirty_tx % mdp->num_tx_ring;
+		txdesc = &mdp->tx_ring[entry];
+		sent = !(txdesc->status & cpu_to_le32(TD_TACT));
+		if (sent_only && !sent)
+			break;
+		/* TACT bit must be checked before all the following reads */
+		dma_rmb();
+		netif_info(mdp, tx_done, ndev,
+			   "tx entry %d status 0x%08x\n",
+			   entry, le32_to_cpu(txdesc->status));
+		/* Free the original skb. */
+		if (mdp->tx_skbuff[entry]) {
+			dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
+					 le32_to_cpu(txdesc->len) >> 16,
+					 DMA_TO_DEVICE);
+			dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
+			mdp->tx_skbuff[entry] = NULL;
+			free_num++;
+		}
+		txdesc->status = cpu_to_le32(TD_TFP);
+		if (entry >= mdp->num_tx_ring - 1)
+			txdesc->status |= cpu_to_le32(TD_TDLE);
+
+		if (sent) {
+			ndev->stats.tx_packets++;
+			ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
+		}
+	}
+	return free_num;
+}
+
 /* free skb and descriptor buffer */
 static void sh_eth_ring_free(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
 	int ringsize, i;
 
+	if (mdp->rx_ring) {
+		for (i = 0; i < mdp->num_rx_ring; i++) {
+			if (mdp->rx_skbuff[i]) {
+				struct sh_eth_rxdesc *rxdesc = &mdp->rx_ring[i];
+
+				dma_unmap_single(&ndev->dev,
+						 le32_to_cpu(rxdesc->addr),
+						 ALIGN(mdp->rx_buf_sz, 32),
+						 DMA_FROM_DEVICE);
+			}
+		}
+		ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
+		dma_free_coherent(NULL, ringsize, mdp->rx_ring,
+				  mdp->rx_desc_dma);
+		mdp->rx_ring = NULL;
+	}
+
 	/* Free Rx skb ringbuffer */
 	if (mdp->rx_skbuff) {
 		for (i = 0; i < mdp->num_rx_ring; i++)

@@ -1073,27 +1131,18 @@ static void sh_eth_ring_free(struct net_
 	kfree(mdp->rx_skbuff);
 	mdp->rx_skbuff = NULL;
 
-	/* Free Tx skb ringbuffer */
-	if (mdp->tx_skbuff) {
-		for (i = 0; i < mdp->num_tx_ring; i++)
-			dev_kfree_skb(mdp->tx_skbuff[i]);
-	}
-	kfree(mdp->tx_skbuff);
-	mdp->tx_skbuff = NULL;
-
-	if (mdp->rx_ring) {
-		ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
-		dma_free_coherent(NULL, ringsize, mdp->rx_ring,
-				  mdp->rx_desc_dma);
-		mdp->rx_ring = NULL;
-	}
-
 	if (mdp->tx_ring) {
+		sh_eth_tx_free(ndev, false);
+
 		ringsize = sizeof(struct sh_eth_txdesc) * mdp->num_tx_ring;
 		dma_free_coherent(NULL, ringsize, mdp->tx_ring,
 				  mdp->tx_desc_dma);
 		mdp->tx_ring = NULL;
 	}
+
+	/* Free Tx skb ringbuffer */
+	kfree(mdp->tx_skbuff);
+	mdp->tx_skbuff = NULL;
 }
 
 /* format skb and descriptor buffer */

@@ -1341,43 +1390,6 @@ static void sh_eth_dev_exit(struct net_d
 	update_mac_address(ndev);
 }
 
-/* free Tx skb function */
-static int sh_eth_txfree(struct net_device *ndev)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	struct sh_eth_txdesc *txdesc;
-	int free_num = 0;
-	int entry;
-
-	for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
-		entry = mdp->dirty_tx % mdp->num_tx_ring;
-		txdesc = &mdp->tx_ring[entry];
-		if (txdesc->status & cpu_to_le32(TD_TACT))
-			break;
-		/* TACT bit must be checked before all the following reads */
-		dma_rmb();
-		netif_info(mdp, tx_done, ndev,
-			   "tx entry %d status 0x%08x\n",
-			   entry, le32_to_cpu(txdesc->status));
-		/* Free the original skb. */
-		if (mdp->tx_skbuff[entry]) {
-			dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
-					 le32_to_cpu(txdesc->len) >> 16,
-					 DMA_TO_DEVICE);
-			dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
-			mdp->tx_skbuff[entry] = NULL;
-			free_num++;
-		}
-		txdesc->status = cpu_to_le32(TD_TFP);
-		if (entry >= mdp->num_tx_ring - 1)
-			txdesc->status |= cpu_to_le32(TD_TDLE);
-
-		ndev->stats.tx_packets++;
-		ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
-	}
-	return free_num;
-}
-
 /* Packet receive function */
 static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 {

@@ -1620,7 +1632,7 @@ ignore_link:
 			   intr_status, mdp->cur_tx, mdp->dirty_tx,
 			   (u32)ndev->state, edtrr);
 		/* dirty buffer free */
-		sh_eth_txfree(ndev);
+		sh_eth_tx_free(ndev, true);
 
 		/* SH7712 BUG */
 		if (edtrr ^ sh_eth_get_edtrr_trns(mdp)) {

@@ -1679,7 +1691,7 @@ static irqreturn_t sh_eth_interrupt(int
 		/* Clear Tx interrupts */
 		sh_eth_write(ndev, intr_status & cd->tx_check, EESR);
 
-		sh_eth_txfree(ndev);
+		sh_eth_tx_free(ndev, true);
 		netif_wake_queue(ndev);
 	}
 

@@ -2307,7 +2319,7 @@ static int sh_eth_start_xmit(struct sk_b
 
 	spin_lock_irqsave(&mdp->lock, flags);
 	if ((mdp->cur_tx - mdp->dirty_tx) >= (mdp->num_tx_ring - 4)) {
-		if (!sh_eth_txfree(ndev)) {
+		if (!sh_eth_tx_free(ndev, true)) {
 			netif_warn(mdp, tx_queued, ndev, "TxFD exhausted.\n");
 			netif_stop_queue(ndev);
 			spin_unlock_irqrestore(&mdp->lock, flags);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 17c3060b1701fc69daedb4c90be6325d3d9fca8e ]

In the (very unlikely) case a passive socket becomes a listener, we do not want to duplicate its saved SYN headers.

This would lead to double frees, use after free, and please hackers and various fuzzers

Tested:

    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3

+0 setsockopt(3, IPPROTO_TCP, TCP_SAVE_SYN, [1], 4) = 0 +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0

+0 bind(3, ..., ...) = 0
+0 listen(3, 5) = 0

+0 < S 0:0(0) win 32972 <mss 1460,nop,wscale 7> +0 > S. 0:0(0) ack 1 <...>
+.1 < . 1:1(0) ack 1 win 257
+0 accept(3, ..., ...) = 4

+0 connect(4, AF_UNSPEC, ...) = 0
+0 close(3) = 0
+0 bind(4, ..., ...) = 0
+0 listen(4, 5) = 0

+0 < S 0:0(0) win 32972 <mss 1460,nop,wscale 7> +0 > S. 0:0(0) ack 1 <...>
+.1 < . 1:1(0) ack 1 win 257

---
 net/ipv4/tcp.c |    1 +
 1 file changed, 1 insertion(+)

@@ -2297,6 +2297,7 @@ int tcp_disconnect(struct sock *sk, int
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
+	tcp_saved_syn_free(tp);
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ilan Tayari <[email protected]>

[ Upstream commit 43170c4e0ba709c79130c3fe5a41e66279950cd0 ]

Commit 07b26c9454a2 ("gso: Support partial splitting at the frag_list pointer") assumes that all SKBs in a frag_list (except maybe the last one) contain the same amount of GSO payload.

This assumption is not always correct, resulting in the following warning message in the log:
skb_segment: too many frags

For example, mlx5 driver in Striding RQ mode creates some RX SKBs with one frag, and some with 2 frags.
After GRO, the frag_list SKBs end up having different amounts of payload. If this frag_list SKB is then forwarded, the aforementioned assumption is violated.

Validate the assumption, and fall back to software GSO if it not true.

---
 net/core/skbuff.c |   18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

@@ -3076,22 +3076,32 @@ struct sk_buff *skb_segment(struct sk_bu
 	if (sg && csum && (mss != GSO_BY_FRAGS))  {
 		if (!(features & NETIF_F_GSO_PARTIAL)) {
 			struct sk_buff *iter;
+			unsigned int frag_len;
 
 			if (!list_skb ||
 			    !net_gso_ok(features, skb_shinfo(head_skb)->gso_type))
 				goto normal;
 
-			/* Split the buffer at the frag_list pointer.
-			 * This is based on the assumption that all
-			 * buffers in the chain excluding the last
-			 * containing the same amount of data.
+			/* If we get here then all the required
+			 * GSO features except frag_list are supported.
+			 * Try to split the SKB to multiple GSO SKBs
+			 * with no frag_list.
+			 * Currently we can do that only when the buffers don't
+			 * have a linear part and all the buffers except
+			 * the last are of the same length.
 			 */
+			frag_len = list_skb->len;
 			skb_walk_frags(head_skb, iter) {
+				if (frag_len != iter->len && iter->next)
+					goto normal;
 				if (skb_headlen(iter))
 					goto normal;
 
 				len -= iter->len;
 			}
+
+			if (len != frag_len)
+				goto normal;
 		}
 
 		/* GSO partial only requires that we trim off any excess that

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Ahern <[email protected]>

[ Upstream commit 557c44be917c322860665be3d28376afa84aa936 ]

Andrey reported a fault in the IPv6 route code:

kasan: GPF could be caused by NULL-ptr deref or user memory access

general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 1 PID: 4035 Comm: a.out Not tainted 4.11.0-rc7+ #250
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
task: ffff880069809600 task.stack: ffff880062dc8000
RIP: 0010:ip6_rt_cache_alloc+0xa6/0x560 net/ipv6/route.c:975
RSP: 0018:ffff880062dced30 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: ffff8800670561c0 RCX: 0000000000000006
RDX: 0000000000000003 RSI: ffff880062dcfb28 RDI: 0000000000000018
RBP: ffff880062dced68 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: ffff880062dcfb28 R14: dffffc0000000000 R15: 0000000000000000
FS:  00007feebe37e7c0(0000) GS:ffff88006cb00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000205a0fe4 CR3: 000000006b5c9000 CR4: 00000000000006e0
Call Trace:
 ip6_pol_route+0x1512/0x1f20 net/ipv6/route.c:1128
 ip6_pol_route_output+0x4c/0x60 net/ipv6/route.c:1212

...

Andrey's syzkaller program passes rtmsg.rtmsg_flags with the RTF_PCPU bit set. Flags passed to the kernel are blindly copied to the allocated rt6_info by ip6_route_info_create making a newly inserted route appear as though it is a per-cpu route. ip6_rt_cache_alloc sees the flag set and expects rt->dst.from to be set - which it is not since it is not really a per-cpu copy. The subsequent call to __ip6_dst_alloc then generates the fault.

Fix by checking for the flag and failing with EINVAL.

---
 include/uapi/linux/ipv6_route.h |    2 +-
 net/ipv6/route.c                |    4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

@@ -34,7 +34,7 @@
 #define RTF_PREF(pref)	((pref) << 27)
 #define RTF_PREF_MASK	0x18000000
 
-#define RTF_PCPU	0x40000000
+#define RTF_PCPU	0x40000000	/* read-only: can not be set by user */
 #define RTF_LOCAL	0x80000000
 
 

@@ -1826,6 +1826,10 @@ static struct rt6_info *ip6_route_info_c
 	int addr_type;
 	int err = -EINVAL;
 
+	/* RTF_PCPU is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_PCPU)
+		goto out;
+
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
 		goto out;
 #ifndef CONFIG_IPV6_SUBTREES

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tushar Dave <[email protected]>

[ Upstream commit c70b17b775edb21280e9de7531acf6db3b365274 ]

Reducing real_num_tx_queues needs to be in sync with skb queue_mapping otherwise skbs with queue_mapping greater than real_num_tx_queues can be sent to the underlying driver and can result in kernel panic.

One such event is running netconsole and enabling VF on the same device. Or running netconsole and changing number of tx queues via ethtool on same device.

e.g.

Unable to handle kernel NULL pointer dereference
tsk->{mm,active_mm}->context = 0000000000001525
tsk->{mm,active_mm}->pgd = fff800130ff9a000
              \|/ ____ \|/
              "@'/ .. \`@"
              /_| \__/ |_\
                 \__U_/
kworker/48:1(475): Oops [#1]
CPU: 48 PID: 475 Comm: kworker/48:1 Tainted: G           OE
4.11.0-rc3-davem-net+ #7
Workqueue: events queue_process

task: fff80013113299c0 task.stack: fff800131132c000
TSTATE: 0000004480e01600 TPC: 00000000103f9e3c TNPC: 00000000103f9e40 Y:
00000000 Tainted: G OE
TPC: <ixgbe_xmit_frame_ring+0x7c/0x6c0 [ixgbe]>
g0: 0000000000000000 g1: 0000000000003fff g2: 0000000000000000 g3:
0000000000000001
g4: fff80013113299c0 g5: fff8001fa6808000 g6: fff800131132c000 g7:
00000000000000c0
o0: fff8001fa760c460 o1: fff8001311329a50 o2: fff8001fa7607504 o3:
0000000000000003
o4: fff8001f96e63a40 o5: fff8001311d77ec0 sp: fff800131132f0e1 ret_pc:
000000000049ed94
RPC: <set_next_entity+0x34/0xb80>
l0: 0000000000000000 l1: 0000000000000800 l2: 0000000000000000 l3:
0000000000000000
l4: 000b2aa30e34b10d l5: 0000000000000000 l6: 0000000000000000 l7:
fff8001fa7605028
i0: fff80013111a8a00 i1: fff80013155a0780 i2: 0000000000000000 i3:
0000000000000000
i4: 0000000000000000 i5: 0000000000100000 i6: fff800131132f1a1 i7:
00000000103fa4b0
I7: <ixgbe_xmit_frame+0x30/0xa0 [ixgbe]>

Call Trace:
 [00000000103fa4b0] ixgbe_xmit_frame+0x30/0xa0 [ixgbe]
 [0000000000998c74] netpoll_start_xmit+0xf4/0x200
 [0000000000998e10] queue_process+0x90/0x160
 [0000000000485fa8] process_one_work+0x188/0x480
 [0000000000486410] worker_thread+0x170/0x4c0
 [000000000048c6b8] kthread+0xd8/0x120
 [0000000000406064] ret_from_fork+0x1c/0x2c
 [0000000000000000]           (null)

Disabling lock debugging due to kernel taint Caller[00000000103fa4b0]: ixgbe_xmit_frame+0x30/0xa0 [ixgbe] Caller[0000000000998c74]: netpoll_start_xmit+0xf4/0x200 Caller[0000000000998e10]: queue_process+0x90/0x160 Caller[0000000000485fa8]: process_one_work+0x188/0x480 Caller[0000000000486410]: worker_thread+0x170/0x4c0 Caller[000000000048c6b8]: kthread+0xd8/0x120 Caller[0000000000406064]: ret_from_fork+0x1c/0x2c
Caller[0000000000000000]: (null)

---
 net/core/netpoll.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

@@ -105,15 +105,21 @@ static void queue_process(struct work_st
 	while ((skb = skb_dequeue(&npinfo->txq))) {
 		struct net_device *dev = skb->dev;
 		struct netdev_queue *txq;
+		unsigned int q_index;
 
 		if (!netif_device_present(dev) || !netif_running(dev)) {
 			kfree_skb(skb);
 			continue;
 		}
 
-		txq = skb_get_tx_queue(dev, skb);
-
 		local_irq_save(flags);
+		/* check if skb->queue_mapping is still valid */
+		q_index = skb_get_queue_mapping(skb);
+		if (unlikely(q_index >= dev->real_num_tx_queues)) {
+			q_index = q_index % dev->real_num_tx_queues;
+			skb_set_queue_mapping(skb, q_index);
+		}
+		txq = netdev_get_tx_queue(dev, q_index);
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
 		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Rabin Vincent <[email protected]>

[ Upstream commit a2d6cbb0670d54806f18192cb0db266b4a6d285a ]

addrconf_ifdown() removes elements from the idev->addr_list without holding the idev->lock.

If this happens while the loop in __ipv6_dev_get_saddr() is handling the same element, that function ends up in an infinite loop:

NMI watchdog: BUG: soft lockup - CPU#1 stuck for 23s! [test:1719]

  Call Trace:
   ipv6_get_saddr_eval+0x13c/0x3a0
   __ipv6_dev_get_saddr+0xe4/0x1f0
   ipv6_dev_get_saddr+0x1b4/0x204
   ip6_dst_lookup_tail+0xcc/0x27c
   ip6_dst_lookup_flow+0x38/0x80
   udpv6_sendmsg+0x708/0xba8
   sock_sendmsg+0x18/0x30
   SyS_sendto+0xb8/0xf8
   syscall_common+0x34/0x58

---
 net/ipv6/addrconf.c |   11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

@@ -3602,14 +3602,19 @@ restart:
 	INIT_LIST_HEAD(&del_list);
 	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
 		struct rt6_info *rt = NULL;
+		bool keep;
 
 		addrconf_del_dad_work(ifa);
 
+		keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
+			!addr_is_local(&ifa->addr);
+		if (!keep)
+			list_move(&ifa->if_list, &del_list);
+
 		write_unlock_bh(&idev->lock);
 		spin_lock_bh(&ifa->lock);
 
-		if (keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
-		    !addr_is_local(&ifa->addr)) {
+		if (keep) {
 			/* set state to skip the notifier below */
 			state = INET6_IFADDR_STATE_DEAD;
 			ifa->state = 0;

@@ -3621,8 +3626,6 @@ restart:
 		} else {
 			state = ifa->state;
 			ifa->state = INET6_IFADDR_STATE_DEAD;
-
-			list_move(&ifa->if_list, &del_list);
 		}
 
 		spin_unlock_bh(&ifa->lock);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ilan Tayari <[email protected]>

[ Upstream commit 5e82c9e4ed60beba83f46a1a5a8307b99a23e982 ]

Handler for ETHTOOL_GRXCLSRLALL must set info->data to the size of the table, regardless of the amount of entries in it. Existing code does not do that, and this breaks all usage of ethtool -N or -n without explicit location, with this error:
rmgr: Invalid RX class rules table size: Success

Set info->data to the table size.

Tested:
ethtool -n ens8
ethtool -N ens8 flow-type ip4 src-ip 1.1.1.1 dst-ip 2.2.2.2 action 1 ethtool -N ens8 flow-type ip4 src-ip 1.1.1.1 dst-ip 2.2.2.2 action 1 loc 55 ethtool -n ens8
ethtool -N ens8 delete 1023
ethtool -N ens8 delete 55

---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c |    1 +
 1 file changed, 1 insertion(+)

@@ -563,6 +563,7 @@ int mlx5e_ethtool_get_all_flows(struct m
 	int idx = 0;
 	int err = 0;
 
+	info->data = MAX_NUM_OF_ETHTOOL_RULES;
 	while ((!err || err == -ENOENT) && idx < info->rule_cnt) {
 		err = mlx5e_ethtool_get_flow(priv, info, location);
 		if (!err)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: bob picco <[email protected]>

[ Upstream commit adfae8a5d833fa2b46577a8081f350e408851f5b ]

I encountered this bug when using /proc/kcore to examine the kernel. Plus a coworker inquired about debugging tools. We computed pa but did not use it during the maximum physical address bits test. Instead we used the identity mapped virtual address which will always fail this test.

I believe the defect came in here:
[bpicco@zareason linus.git]$ git describe --contains bb4e6e85daa52 v3.18-rc1~87^2~4
.

---
 arch/sparc/mm/init_64.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1495,7 +1495,7 @@ bool kern_addr_valid(unsigned long addr)
 	if ((long)addr < 0L) {
 		unsigned long pa = __pa(addr);
 
-		if ((addr >> max_phys_bits) != 0UL)
+		if ((pa >> max_phys_bits) != 0UL)
 			return false;
 
 		return pfn_valid(pa >> PAGE_SHIFT);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: WANG Cong <[email protected]>

[ Upstream commit 199ab00f3cdb6f154ea93fa76fd80192861a821d ]

Andrey reported a out-of-bound access in ip6_tnl_xmit(), this is because we use an ipv4 dst in ip6_tnl_xmit() and cast an IPv4 neigh key as an IPv6 address:

        neigh = dst_neigh_lookup(skb_dst(skb),
                                 &ipv6_hdr(skb)->daddr);
        if (!neigh)
                goto tx_err_link_failure;

        addr6 = (struct in6_addr *)&neigh->primary_key; // <=== HERE
        addr_type = ipv6_addr_type(addr6);

        if (addr_type == IPV6_ADDR_ANY)
                addr6 = &ipv6_hdr(skb)->daddr;

        memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));

Also the network header of the skb at this point should be still IPv4 for 4in6 tunnels, we shold not just use it as IPv6 header.

This patch fixes it by checking if skb->protocol is ETH_P_IPV6: if it is, we are safe to do the nexthop lookup using skb_dst() and ipv6_hdr(skb)->daddr; if not (aka IPv4), we have no clue about which dest address we can pick here, we have to rely on callers to fill it from tunnel config, so just fall to ip6_route_output() to make the decision.

---
 net/ipv6/ip6_tunnel.c |   44 +++++++++++++++++++++++---------------------
 1 file changed, 23 insertions(+), 21 deletions(-)

@@ -1037,7 +1037,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, st
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net *net = t->net;
 	struct net_device_stats *stats = &t->dev->stats;
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	struct ipv6_tel_txoption opt;
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;

@@ -1057,26 +1057,28 @@ int ip6_tnl_xmit(struct sk_buff *skb, st
 
 	/* NBMA tunnel */
 	if (ipv6_addr_any(&t->parms.raddr)) {
-		struct in6_addr *addr6;
-		struct neighbour *neigh;
-		int addr_type;
-
-		if (!skb_dst(skb))
-			goto tx_err_link_failure;
-
-		neigh = dst_neigh_lookup(skb_dst(skb),
-					 &ipv6_hdr(skb)->daddr);
-		if (!neigh)
-			goto tx_err_link_failure;
-
-		addr6 = (struct in6_addr *)&neigh->primary_key;
-		addr_type = ipv6_addr_type(addr6);
-
-		if (addr_type == IPV6_ADDR_ANY)
-			addr6 = &ipv6_hdr(skb)->daddr;
-
-		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
-		neigh_release(neigh);
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			struct in6_addr *addr6;
+			struct neighbour *neigh;
+			int addr_type;
+
+			if (!skb_dst(skb))
+				goto tx_err_link_failure;
+
+			neigh = dst_neigh_lookup(skb_dst(skb),
+						 &ipv6_hdr(skb)->daddr);
+			if (!neigh)
+				goto tx_err_link_failure;
+
+			addr6 = (struct in6_addr *)&neigh->primary_key;
+			addr_type = ipv6_addr_type(addr6);
+
+			if (addr_type == IPV6_ADDR_ANY)
+				addr6 = &ipv6_hdr(skb)->daddr;
+
+			memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
+			neigh_release(neigh);
+		}
 	} else if (!(t->parms.flags &
 		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
 		/* enable the cache only only if the routing decision does

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wei Wang <[email protected]>

[ Upstream commit c1201444075009507a6818de6518e2822b9a87c8 ]

Always zero out ca_priv data in tcp_assign_congestion_control() so that ca_priv data is cleared out during socket creation.
Also always zero out ca_priv data in tcp_reinit_congestion_control() so that when cc algorithm is changed, ca_priv data is cleared out as well. We should still zero out ca_priv data even in TCP_CLOSE state because user could call connect() on AF_UNSPEC to disconnect the socket and leave it in TCP_CLOSE state and later call setsockopt() to switch cc algorithm on this socket.

---
 net/ipv4/tcp_cong.c |   11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

@@ -167,12 +167,8 @@ void tcp_assign_congestion_control(struc
 	}
 out:
 	rcu_read_unlock();
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	/* Clear out private data before diag gets it and
-	 * the ca has not been initialized.
-	 */
-	if (ca->get_info)
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	if (ca->flags & TCP_CONG_NEEDS_ECN)
 		INET_ECN_xmit(sk);
 	else

@@ -199,11 +195,10 @@ static void tcp_reinit_congestion_contro
 	tcp_cleanup_congestion_control(sk);
 	icsk->icsk_ca_ops = ca;
 	icsk->icsk_ca_setsockopt = 1;
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE) {
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	if (sk->sk_state != TCP_CLOSE)
 		tcp_init_congestion_control(sk);
-	}
 }
 
 /* Manage refcounts on socket close. */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jamie Bainbridge <[email protected]>

[ Upstream commit 105f5528b9bbaa08b526d3405a5bcd2ff0c953c8 ]

In situations where an skb is paged, the transport header pointer and tail pointer can be the same because the skb contents are in frags.

This results in ioctl(SIOCINQ/FIONREAD) incorrectly returning a length of 0 when the length to receive is actually greater than zero.

skb->len is already correctly set in ip6_input_finish() with pskb_pull(), so use skb->len as it always returns the correct result for both linear and paged data.

---
 net/ipv6/raw.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -1171,8 +1171,7 @@ static int rawv6_ioctl(struct sock *sk,
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
-			amount = skb_tail_pointer(skb) -
-				skb_transport_header(skb);
+			amount = skb->len;
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return put_user(amount, (int __user *)arg);
 	}

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tom Hromatka <[email protected]>

[ Upstream commit 9ae34dbd8afd790cb5f52467e4f816434379eafa ]

This commit moves sparc64's prototype of pmd_write() outside of the CONFIG_TRANSPARENT_HUGEPAGE ifdef.

In 2013, commit a7b9403f0e6d ("sparc64: Encode huge PMDs using PTE encoding.") exposed a path where pmd_write() could be called without CONFIG_TRANSPARENT_HUGEPAGE defined. This can result in the panic below.

The diff is awkward to read, but the changes are straightforward. pmd_write() was moved outside of #ifdef CONFIG_TRANSPARENT_HUGEPAGE. Also, __HAVE_ARCH_PMD_WRITE was defined.

kernel BUG at include/asm-generic/pgtable.h:576!

              \|/ ____ \|/
              "@'/ .. \`@"
              /_| \__/ |_\
                 \__U_/
oracle_8114_cdb(8114): Kernel bad sw trap 5 [#1]
CPU: 120 PID: 8114 Comm: oracle_8114_cdb Not tainted

4.1.12-61.7.1.el6uek.rc1.sparc64 #1
task: fff8400700a24d60 ti: fff8400700bc4000 task.ti: fff8400700bc4000
TSTATE: 0000004411e01607 TPC: 00000000004609f8 TNPC: 00000000004609fc Y:
00000005 Not tainted
TPC: <gup_huge_pmd+0x198/0x1e0>
g0: 000000000001c000 g1: 0000000000ef3954 g2: 0000000000000000 g3: 0000000000000001
g4: fff8400700a24d60 g5: fff8001fa5c10000 g6: fff8400700bc4000 g7: 0000000000000720
o0: 0000000000bc5058 o1: 0000000000000240 o2: 0000000000006000 o3: 0000000000001c00
o4: 0000000000000000 o5: 0000048000080000 sp: fff8400700bc6ab1 ret_pc: 00000000004609f0
RPC: <gup_huge_pmd+0x190/0x1e0>
l0: fff8400700bc74fc l1: 0000000000020000 l2: 0000000000002000 l3: 0000000000000000
l4: fff8001f93250950 l5: 000000000113f800 l6: 0000000000000004 l7: 0000000000000000
i0: fff8400700ca46a0 i1: bd0000085e800453 i2: 000000026a0c4000 i3: 000000026a0c6000
i4: 0000000000000001 i5: fff800070c958de8 i6: fff8400700bc6b61 i7: 0000000000460dd0
I7: <gup_pud_range+0x170/0x1a0>

Call Trace:
 [0000000000460dd0] gup_pud_range+0x170/0x1a0
 [0000000000460e84] get_user_pages_fast+0x84/0x120
 [00000000006f5a18] iov_iter_get_pages+0x98/0x240
 [00000000005fa744] do_direct_IO+0xf64/0x1e00
 [00000000005fbbc0] __blockdev_direct_IO+0x360/0x15a0
 [00000000101f74fc] ext4_ind_direct_IO+0xdc/0x400 [ext4]
 [00000000101af690] ext4_ext_direct_IO+0x1d0/0x2c0 [ext4]
 [00000000101af86c] ext4_direct_IO+0xec/0x220 [ext4]
 [0000000000553bd4] generic_file_read_iter+0x114/0x140
 [00000000005bdc2c] __vfs_read+0xac/0x100
 [00000000005bf254] vfs_read+0x54/0x100
 [00000000005bf368] SyS_pread64+0x68/0x80

---
 arch/sparc/include/asm/pgtable_64.h |   15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

@@ -673,26 +673,27 @@ static inline unsigned long pmd_pfn(pmd_
 	return pte_pfn(pte);
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_dirty(pmd_t pmd)
+#define __HAVE_ARCH_PMD_WRITE
+static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_dirty(pte);
+	return pte_write(pte);
 }
 
-static inline unsigned long pmd_young(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_dirty(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_young(pte);
+	return pte_dirty(pte);
 }
 
-static inline unsigned long pmd_write(pmd_t pmd)
+static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_write(pte);
+	return pte_young(pte);
 }
 
 static inline unsigned long pmd_trans_huge(pmd_t pmd)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Herbert Xu <[email protected]>

[ Upstream commit f6478218e6edc2a587b8f132f66373baa7b2497c ]

When a parent macvlan device is destroyed we end up purging its broadcast queue without dropping the device reference count on the packet source device. This causes the source device to linger.

This patch drops that reference count.

---
 drivers/net/macvlan.c |   11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

@@ -1140,6 +1140,7 @@ static int macvlan_port_create(struct ne
 static void macvlan_port_destroy(struct net_device *dev)
 {
 	struct macvlan_port *port = macvlan_port_get_rtnl(dev);
+	struct sk_buff *skb;
 
 	dev->priv_flags &= ~IFF_MACVLAN_PORT;
 	netdev_rx_handler_unregister(dev);

@@ -1148,7 +1149,15 @@ static void macvlan_port_destroy(struct
 	 * but we need to cancel it and purge left skbs if any.
 	 */
 	cancel_work_sync(&port->bc_work);
-	__skb_queue_purge(&port->bc_queue);
+
+	while ((skb = __skb_dequeue(&port->bc_queue))) {
+		const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
+
+		if (src)
+			dev_put(src->dev);
+
+		kfree_skb(skb);
+	}
 
 	kfree_rcu(port, rcu);
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 48481c8fa16410ffa45939b13b6c53c2ca609e5f ]

Dmitry posted a nice reproducer of a bug triggering in neigh_probe() when dereferencing a NULL neigh->ops->solicit method.

This can happen for arp_direct_ops/ndisc_direct_ops and similar, which can be used for NUD_NOARP neighbours (created when dev->header_ops is NULL). Admin can then force changing nud_state to some other state that would fire neigh timer.

---
 net/core/neighbour.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -859,7 +859,8 @@ static void neigh_probe(struct neighbour
 	if (skb)
 		skb = skb_clone(skb, GFP_ATOMIC);
 	write_unlock(&neigh->lock);
-	neigh->ops->solicit(neigh, skb);
+	if (neigh->ops->solicit)
+		neigh->ops->solicit(neigh, skb);
 	atomic_inc(&neigh->probes);
 	kfree_skb(skb);
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nathan Sullivan <[email protected]>

[ Upstream commit 49d52e8108a21749dc2114b924c907db43358984 ]

If the PHY is halted on stop, then do not set the state to PHY_UP. This ensures the phy will be restarted later in phy_start when the machine is started again.

---
 drivers/net/phy/phy.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -639,7 +639,7 @@ void phy_stop_machine(struct phy_device
 	cancel_delayed_work_sync(&phydev->state_queue);
 
 	mutex_lock(&phydev->lock);
-	if (phydev->state > PHY_UP)
+	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eugenia Emantayev <[email protected]>

[ Upstream commit cbad8cddb6ed7ef3a5f0a9a70f1711d4d7fb9a8f ]

RX packet headers are meant to be contained in SKB linear part,
and chose a threshold of 128.
It turns out this is not enough, i.e. for IPv6 packet over VxLAN.
In this case, UDP/IPv4 needs 42 bytes, GENEVE header is 8 bytes,
and 86 bytes for TCP/IPv6. In total 136 bytes that is more than current 128 bytes. In this case expand header flow is reached.
The warning in skb_try_coalesce() caused by a wrong truesize
was already fixed here:
commit 158f323b9868 ("net: adjust skb->truesize in pskb_expand_head()"). Still, we prefer to totally avoid the expand header flow for performance reasons. Tested regular TCP_STREAM with iperf for 1 and 8 streams, no degradation was found.

---
 drivers/net/ethernet/mellanox/mlx5/core/en.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -82,7 +82,7 @@
 #define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) <= U16_MAX)
 
 #define MLX5_UMR_ALIGN				(2048)
-#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(128)
+#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(256)
 
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_DEFAULT_LRO_TIMEOUT                       32

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexander Kochetkov <[email protected]>

[ Upstream commit f555f34fdc586a56204cd16d9a7c104ec6cb6650 ]

The Ethernet link on an interrupt driven PHY was not coming up if the Ethernet cable was plugged before the Ethernet interface was brought up.

The patch trigger PHY state machine to update link state if PHY was requested to do auto-negotiation and auto-negotiation complete flag already set.

During power-up cycle the PHY do auto-negotiation, generate interrupt and set auto-negotiation complete flag. Interrupt is handled by PHY state machine but doesn't update link state because PHY is in PHY_READY state. After some time MAC bring up, start and request PHY to do auto-negotiation. If there are no new settings to advertise genphy_config_aneg() doesn't start PHY auto-negotiation. PHY continue to stay in auto-negotiation complete state and doesn't fire interrupt. At the same time PHY state machine expect that PHY started auto-negotiation and is waiting for interrupt from PHY and it won't get it.

---
 drivers/net/phy/phy.c |   40 ++++++++++++++++++++++++++++++++++++----
 include/linux/phy.h   |    1 +
 2 files changed, 37 insertions(+), 4 deletions(-)

@@ -552,16 +552,18 @@ int phy_mii_ioctl(struct phy_device *phy
 EXPORT_SYMBOL(phy_mii_ioctl);
 
 /**
- * phy_start_aneg - start auto-negotiation for this PHY device
+ * phy_start_aneg_priv - start auto-negotiation for this PHY device
  * @phydev: the phy_device struct
+ * @sync: indicate whether we should wait for the workqueue cancelation
  *
  * Description: Sanitizes the settings (if we're not autonegotiating
  *   them), and then calls the driver's config_aneg function.
  *   If the PHYCONTROL Layer is operating, we change the state to
  *   reflect the beginning of Auto-negotiation or forcing.
  */
-int phy_start_aneg(struct phy_device *phydev)
+static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 {
+	bool trigger = 0;
 	int err;
 
 	mutex_lock(&phydev->lock);

@@ -586,10 +588,40 @@ int phy_start_aneg(struct phy_device *ph
 		}
 	}
 
+	/* Re-schedule a PHY state machine to check PHY status because
+	 * negotiation may already be done and aneg interrupt may not be
+	 * generated.
+	 */
+	if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+		err = phy_aneg_done(phydev);
+		if (err > 0) {
+			trigger = true;
+			err = 0;
+		}
+	}
+
 out_unlock:
 	mutex_unlock(&phydev->lock);
+
+	if (trigger)
+		phy_trigger_machine(phydev, sync);
+
 	return err;
 }
+
+/**
+ * phy_start_aneg - start auto-negotiation for this PHY device
+ * @phydev: the phy_device struct
+ *
+ * Description: Sanitizes the settings (if we're not autonegotiating
+ *   them), and then calls the driver's config_aneg function.
+ *   If the PHYCONTROL Layer is operating, we change the state to
+ *   reflect the beginning of Auto-negotiation or forcing.
+ */
+int phy_start_aneg(struct phy_device *phydev)
+{
+	return phy_start_aneg_priv(phydev, true);
+}
 EXPORT_SYMBOL(phy_start_aneg);
 
 /**

@@ -617,7 +649,7 @@ void phy_start_machine(struct phy_device
  *   state machine runs.
  */
 
-static void phy_trigger_machine(struct phy_device *phydev, bool sync)
+void phy_trigger_machine(struct phy_device *phydev, bool sync)
 {
 	if (sync)
 		cancel_delayed_work_sync(&phydev->state_queue);

@@ -1100,7 +1132,7 @@ void phy_state_machine(struct work_struc
 	mutex_unlock(&phydev->lock);
 
 	if (needs_aneg)
-		err = phy_start_aneg(phydev);
+		err = phy_start_aneg_priv(phydev, false);
 	else if (do_suspend)
 		phy_suspend(phydev);
 

@@ -806,6 +806,7 @@ void phy_change(struct work_struct *work
 void phy_mac_interrupt(struct phy_device *phydev, int new_link);
 void phy_start_machine(struct phy_device *phydev);
 void phy_stop_machine(struct phy_device *phydev);
+void phy_trigger_machine(struct phy_device *phydev, bool sync);
 int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 int phy_ethtool_ksettings_get(struct phy_device *phydev,

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: WANG Cong <[email protected]>

[ Upstream commit a80db69e47d764bbcaf2fec54b1f308925e7c490 ]

There is no reason to continue after a copy_from_user() failure.

---
 net/kcm/kcmsock.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -1685,7 +1685,7 @@ static int kcm_ioctl(struct socket *sock
 		struct kcm_attach info;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_attach_ioctl(sock, &info);
 

@@ -1695,7 +1695,7 @@ static int kcm_ioctl(struct socket *sock
 		struct kcm_unattach info;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_unattach_ioctl(sock, &info);
 

@@ -1706,7 +1706,7 @@ static int kcm_ioctl(struct socket *sock
 		struct socket *newsock = NULL;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_clone(sock, &info, &newsock);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexei Starovoitov <[email protected]>

[ Upstream commit b1977682a3858b5584ffea7cfb7bd863f68db18d ]

llvm can optimize the 'if (ptr > data_end)' checks to be in the order slightly different than the original C code which will confuse verifier. Like:
if (ptr + 16 > data_end)
return TC_ACT_SHOT;
// may be followed by
if (ptr + 14 > data_end)
return TC_ACT_SHOT;
while llvm can see that 'ptr' is valid for all 16 bytes,
the verifier could not.
Fix verifier logic to account for such case and add a test.

---
 kernel/bpf/verifier.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

@@ -1829,14 +1829,15 @@ static void find_good_pkt_pointers(struc
 
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
-			regs[i].range = dst_reg->off;
+			/* keep the maximum range already checked */
+			regs[i].range = max(regs[i].range, dst_reg->off);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
 		reg = &state->spilled_regs[i / BPF_REG_SIZE];
 		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
-			reg->range = dst_reg->off;
+			reg->range = max(reg->range, dst_reg->off);
 	}
 }
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Talat Batheesh <[email protected]>

[ Upstream commit e497ec680c4cd51e76bfcdd49363d9ab8d32a757 ]

In NETDEV_CHANGEUPPER event the upper_info field is valid only when linking is true. Otherwise it should be ignored.

---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

@@ -294,7 +294,7 @@ static int mlx5_handle_changeupper_event
 					 struct netdev_notifier_changeupper_info *info)
 {
 	struct net_device *upper = info->upper_dev, *ndev_tmp;
-	struct netdev_lag_upper_info *lag_upper_info;
+	struct netdev_lag_upper_info *lag_upper_info = NULL;
 	bool is_bonded;
 	int bond_status = 0;
 	int num_slaves = 0;

@@ -303,7 +303,8 @@ static int mlx5_handle_changeupper_event
 	if (!netif_is_lag_master(upper))
 		return 0;
 
-	lag_upper_info = info->upper_info;
+	if (info->linking)
+		lag_upper_info = info->upper_info;
 
 	/* The event may still be of interest if the slave does not belong to
 	 * us, but is enslaved to a master which has one or more of our netdevs

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jason A. Donenfeld <[email protected]>

commit 4d6fa57b4dab0d77f4d8e9d9c73d1e63f6fe8fee upstream.

While this may appear as a humdrum one line change, it's actually quite important. An sk_buff stores data in three places:

1. A linear chunk of allocated memory in skb->data. This is the easiest one to work with, but it precludes using scatterdata since the memory must be linear.
2. The array skb_shinfo(skb)->frags, which is of maximum length MAX_SKB_FRAGS. This is nice for scattergather, since these fragments can point to different pages.
3. skb_shinfo(skb)->frag_list, which is a pointer to another sk_buff, which in turn can have data in either (1) or (2).

The first two are rather easy to deal with, since they're of a fixed maximum length, while the third one is not, since there can be potentially limitless chains of fragments. Fortunately dealing with frag_list is opt-in for drivers, so drivers don't actually have to deal with this mess. For whatever reason, macsec decided it wanted pain, and so it explicitly specified NETIF_F_FRAGLIST.

Because dealing with (1), (2), and (3) is insane, most users of sk_buff doing any sort of crypto or paging operation calls a convenient function called skb_to_sgvec (which happens to be recursive if (3) is in use!). This takes a sk_buff as input, and writes into its output pointer an array of scattergather list items. Sometimes people like to declare a fixed size scattergather list on the stack; othertimes people like to allocate a fixed size scattergather list on the heap. However, if you're doing it in a fixed-size fashion, you really shouldn't be using NETIF_F_FRAGLIST too (unless you're also ensuring the sk_buff and its frag_list children arent't shared and then you check the number of fragments in total required.)

Macsec specifically does this:

        size += sizeof(struct scatterlist) * (MAX_SKB_FRAGS + 1);
        tmp = kmalloc(size, GFP_ATOMIC);
        *sg = (struct scatterlist *)(tmp + sg_offset);
	...
        sg_init_table(sg, MAX_SKB_FRAGS + 1);
        skb_to_sgvec(skb, sg, 0, skb->len);

Specifying MAX_SKB_FRAGS + 1 is the right answer usually, but not if you're using NETIF_F_FRAGLIST, in which case the call to skb_to_sgvec will overflow the heap, and disaster ensues.

---
 drivers/net/macsec.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2709,7 +2709,7 @@ static netdev_tx_t macsec_start_xmit(str
 }
 
 #define MACSEC_FEATURES \
-	(NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST)
+	(NETIF_F_SG | NETIF_F_HIGHDMA)
 static struct lock_class_key macsec_netdev_addr_lock_key;
 
 static int macsec_dev_init(struct net_device *dev)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maksim Salau <[email protected]>

commit b05c73bd1e3ec60357580eb042ee932a5ed754d5 upstream.

Allocate buffers on HEAP instead of STACK for local structures that are to be sent using usb_control_msg().

---
 drivers/net/can/usb/gs_usb.c |   17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

@@ -740,13 +740,18 @@ static const struct net_device_ops gs_us
 static int gs_usb_set_identify(struct net_device *netdev, bool do_identify)
 {
 	struct gs_can *dev = netdev_priv(netdev);
-	struct gs_identify_mode imode;
+	struct gs_identify_mode *imode;
 	int rc;
 
+	imode = kmalloc(sizeof(*imode), GFP_KERNEL);
+
+	if (!imode)
+		return -ENOMEM;
+
 	if (do_identify)
-		imode.mode = GS_CAN_IDENTIFY_ON;
+		imode->mode = GS_CAN_IDENTIFY_ON;
 	else
-		imode.mode = GS_CAN_IDENTIFY_OFF;
+		imode->mode = GS_CAN_IDENTIFY_OFF;
 
 	rc = usb_control_msg(interface_to_usbdev(dev->iface),
 			     usb_sndctrlpipe(interface_to_usbdev(dev->iface),

@@ -756,10 +761,12 @@ static int gs_usb_set_identify(struct ne
 			     USB_RECIP_INTERFACE,
 			     dev->channel,
 			     0,
-			     &imode,
-			     sizeof(imode),
+			     imode,
+			     sizeof(*imode),
 			     100);
 
+	kfree(imode);
+
 	return (rc > 0) ? 0 : rc;
 }
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vineet Gupta <[email protected]>

commit ecd43afdbe72017aefe48080631eb625e177ef4d upstream.

This is not exposed to userspace debugers yet, which can be done independently as a seperate patch !

---
 arch/arc/include/asm/entry-arcv2.h |    2 ++
 arch/arc/include/asm/ptrace.h      |    2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

@@ -16,6 +16,7 @@
 	;
 	; Now manually save: r12, sp, fp, gp, r25
 
+	PUSH	r30
 	PUSH	r12
 
 	; Saving pt_regs->sp correctly requires some extra work due to the way

@@ -72,6 +73,7 @@
 	POPAX	AUX_USER_SP
 1:
 	POP	r12
+	POP	r30
 
 .endm
 

@@ -84,7 +84,7 @@ struct pt_regs {
 	unsigned long fp;
 	unsigned long sp;	/* user/kernel sp depending on where we came from  */
 
-	unsigned long r12;
+	unsigned long r12, r30;
 
 	/*------- Below list auto saved by h/w -----------*/
 	unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: James Hogan <[email protected]>

commit 162b270c664dca2e0944308e92f9fcc887151a72 upstream.

KGDB is a kernel debug stub and it can't be used to debug userland as it can only safely access kernel memory.

On MIPS however KGDB has always got the register state of sleeping processes from the userland register context at the beginning of the kernel stack. This is meaningless for kernel threads (which never enter userland), and for user threads it prevents the user seeing what it is doing while in the kernel:

(gdb) info threads
Id Target Id Frame
...

  3    Thread 2 (kthreadd) 0x0000000000000000 in ?? ()
  2    Thread 1 (init)   0x000000007705c4b4 in ?? ()
  1    Thread -2 (shadowCPU0) 0xffffffff8012524c in arch_kgdb_breakpoint () at arch/mips/kernel/kgdb.c:201

Get the register state instead from the (partial) kernel register context stored in the task's thread_struct for resume() to restore. All threads now correctly appear to be in context_switch():

(gdb) info threads
Id Target Id Frame
...

  3    Thread 2 (kthreadd) context_switch (rq=<optimized out>, cookie=..., next=<optimized out>, prev=0x0) at kernel/sched/core.c:2903
  2    Thread 1 (init)   context_switch (rq=<optimized out>, cookie=..., next=<optimized out>, prev=0x0) at kernel/sched/core.c:2903
  1    Thread -2 (shadowCPU0) 0xffffffff8012524c in arch_kgdb_breakpoint () at arch/mips/kernel/kgdb.c:201

Call clobbered registers which aren't saved and exception registers (BadVAddr & Cause) which can't be easily determined without stack unwinding are reported as 0. The PC is taken from the return address, such that the state presented matches that found immediately after returning from resume().

Patchwork: https://patchwork.linux-mips.org/patch/15829/

---
 arch/mips/kernel/kgdb.c |   48 +++++++++++++++++++++++++++++++++---------------
 1 file changed, 33 insertions(+), 15 deletions(-)

@@ -244,9 +244,6 @@ static int compute_signal(int tt)
 void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 {
 	int reg;
-	struct thread_info *ti = task_thread_info(p);
-	unsigned long ksp = (unsigned long)ti + THREAD_SIZE - 32;
-	struct pt_regs *regs = (struct pt_regs *)ksp - 1;
 #if (KGDB_GDB_REG_SIZE == 32)
 	u32 *ptr = (u32 *)gdb_regs;
 #else

@@ -254,25 +251,46 @@ void sleeping_thread_to_gdb_regs(unsigne
 #endif
 
 	for (reg = 0; reg < 16; reg++)
-		*(ptr++) = regs->regs[reg];
+		*(ptr++) = 0;
 
 	/* S0 - S7 */
-	for (reg = 16; reg < 24; reg++)
-		*(ptr++) = regs->regs[reg];
+	*(ptr++) = p->thread.reg16;
+	*(ptr++) = p->thread.reg17;
+	*(ptr++) = p->thread.reg18;
+	*(ptr++) = p->thread.reg19;
+	*(ptr++) = p->thread.reg20;
+	*(ptr++) = p->thread.reg21;
+	*(ptr++) = p->thread.reg22;
+	*(ptr++) = p->thread.reg23;
 
 	for (reg = 24; reg < 28; reg++)
 		*(ptr++) = 0;
 
 	/* GP, SP, FP, RA */
-	for (reg = 28; reg < 32; reg++)
-		*(ptr++) = regs->regs[reg];
-
-	*(ptr++) = regs->cp0_status;
-	*(ptr++) = regs->lo;
-	*(ptr++) = regs->hi;
-	*(ptr++) = regs->cp0_badvaddr;
-	*(ptr++) = regs->cp0_cause;
-	*(ptr++) = regs->cp0_epc;
+	*(ptr++) = (long)p;
+	*(ptr++) = p->thread.reg29;
+	*(ptr++) = p->thread.reg30;
+	*(ptr++) = p->thread.reg31;
+
+	*(ptr++) = p->thread.cp0_status;
+
+	/* lo, hi */
+	*(ptr++) = 0;
+	*(ptr++) = 0;
+
+	/*
+	 * BadVAddr, Cause
+	 * Ideally these would come from the last exception frame up the stack
+	 * but that requires unwinding, otherwise we can't know much for sure.
+	 */
+	*(ptr++) = 0;
+	*(ptr++) = 0;
+
+	/*
+	 * PC
+	 * use return address (RA), i.e. the moment after return from resume()
+	 */
+	*(ptr++) = p->thread.reg31;
 }
 
 void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: James Cowgill <[email protected]>

commit c46f59e90226fa5bfcc83650edebe84ae47d454b upstream.

arch_check_elf contains a usage of current_cpu_data that will call smp_processor_id() with preemption enabled and therefore triggers a "BUG: using smp_processor_id() in preemptible" warning when an fpxx executable is loaded.

As a follow-up to commit b244614a60ab ("MIPS: Avoid a BUG warning during prctl(PR_SET_FP_MODE, ...)"), apply the same fix to arch_check_elf by using raw_current_cpu_data instead. The rationale quoted from the previous commit:

"It is assumed throughout the kernel that if any CPU has an FPU, then all CPUs would have an FPU as well, so it is safe to perform the check with preemption enabled - change the code to use raw_ variant of the check to avoid the warning."

Patchwork: https://patchwork.linux-mips.org/patch/15951/

---
 arch/mips/kernel/elf.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -257,7 +257,7 @@ int arch_check_elf(void *_ehdr, bool has
 	else if ((prog_req.fr1 && prog_req.frdefault) ||
 		 (prog_req.single && !prog_req.frdefault))
 		/* Make sure 64-bit MIPS III/IV/64R1 will not pick FR1 */
-		state->overall_fp_mode = ((current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
+		state->overall_fp_mode = ((raw_current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
 					  cpu_has_mips_r2_r6) ?
 					  FP_FR1 : FP_FR0;
 	else if (prog_req.fr1)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Al Viro <[email protected]>

commit 71d6ad08379304128e4bdfaf0b4185d54375423e upstream.

Don't assume that server is sane and won't return more data than asked for.

---
 net/9p/client.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -2101,6 +2101,10 @@ int p9_client_readdir(struct p9_fid *fid
 		trace_9p_protocol_dump(clnt, req->rc);
 		goto free_and_error;
 	}
+	if (rsize < count) {
+		pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize);
+		count = rsize;
+	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Takashi Iwai <[email protected]>

commit 6e4cac23c5a648d50b107d1b53e9c4e1120c7943 upstream.

The FE setups of Intel SST bytcr_rt5640 and bytcr_rt5651 drivers carry the ignore_suspend flag, and this prevents the suspend/resume working properly while the stream is running, since SST core code has the check of the running streams and returns -EBUSY. Drop these superfluous flags for fixing the behavior.

Also, the bytcr_rt5640 driver lacks of nonatomic flag in some FE definitions, which leads to the kernel Oops at suspend/resume like:

  BUG: scheduling while atomic: systemd-sleep/3144/0x00000003
  Call Trace:
   dump_stack+0x5c/0x7a
   __schedule_bug+0x55/0x70
   __schedule+0x63c/0x8c0
   schedule+0x3d/0x90
   schedule_timeout+0x16b/0x320
   ? del_timer_sync+0x50/0x50
   ? sst_wait_timeout+0xa9/0x170 [snd_intel_sst_core]
   ? sst_wait_timeout+0xa9/0x170 [snd_intel_sst_core]
   ? remove_wait_queue+0x60/0x60
   ? sst_prepare_and_post_msg+0x275/0x960 [snd_intel_sst_core]
   ? sst_pause_stream+0x9b/0x110 [snd_intel_sst_core]
   ....

This patch addresses these appropriately, too.

---
 sound/soc/intel/boards/bytcr_rt5640.c |    4 ++--
 sound/soc/intel/boards/bytcr_rt5651.c |    2 --
 2 files changed, 2 insertions(+), 4 deletions(-)

@@ -621,7 +621,7 @@ static struct snd_soc_dai_link byt_rt564
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.codec_name = "snd-soc-dummy",
 		.platform_name = "sst-mfld-platform",
-		.ignore_suspend = 1,
+		.nonatomic = true,
 		.dynamic = 1,
 		.dpcm_playback = 1,
 		.dpcm_capture = 1,

@@ -634,7 +634,6 @@ static struct snd_soc_dai_link byt_rt564
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.codec_name = "snd-soc-dummy",
 		.platform_name = "sst-mfld-platform",
-		.ignore_suspend = 1,
 		.nonatomic = true,
 		.dynamic = 1,
 		.dpcm_playback = 1,

@@ -661,6 +660,7 @@ static struct snd_soc_dai_link byt_rt564
 						| SND_SOC_DAIFMT_CBS_CFS,
 		.be_hw_params_fixup = byt_rt5640_codec_fixup,
 		.ignore_suspend = 1,
+		.nonatomic = true,
 		.dpcm_playback = 1,
 		.dpcm_capture = 1,
 		.init = byt_rt5640_init,

@@ -235,7 +235,6 @@ static struct snd_soc_dai_link byt_rt565
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.codec_name = "snd-soc-dummy",
 		.platform_name = "sst-mfld-platform",
-		.ignore_suspend = 1,
 		.nonatomic = true,
 		.dynamic = 1,
 		.dpcm_playback = 1,

@@ -249,7 +248,6 @@ static struct snd_soc_dai_link byt_rt565
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.codec_name = "snd-soc-dummy",
 		.platform_name = "sst-mfld-platform",
-		.ignore_suspend = 1,
 		.nonatomic = true,
 		.dynamic = 1,
 		.dpcm_playback = 1,

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Takashi Sakamoto <[email protected]>

commit 3d016d57fdc5e6caa4cd67896f4b081bccad6e2c upstream.

At a commit 6c29230e2a5f ("ALSA: oxfw: delayed registration of sound card"), ALSA oxfw driver fails to handle SCS.1m/1d, due to -EBUSY at a call of snd_card_register(). The cause is that the driver manages to register two rawmidi instances with the same device number 0. This is a regression introduced since kernel 4.7.

This commit fixes the regression, by fixing up device property after discovering stream formats.

---
 sound/firewire/oxfw/oxfw.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -226,11 +226,11 @@ static void do_registration(struct work_
 	if (err < 0)
 		goto error;
 
-	err = detect_quirks(oxfw);
+	err = snd_oxfw_stream_discover(oxfw);
 	if (err < 0)
 		goto error;
 
-	err = snd_oxfw_stream_discover(oxfw);
+	err = detect_quirks(oxfw);
 	if (err < 0)
 		goto error;
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: James Hogan <[email protected]>

commit 9d7f29cdb4ca53506115cf1d7a02ce6013894df0 upstream.

calculate_min_delta() may incorrectly access a 4th element of buf2[] which only has 3 elements. This may trigger undefined behaviour and has been reported to cause strange crashes in start_kernel() sometime after timer initialization when built with GCC 5.3, possibly due to register/stack corruption:

sched_clock: 32 bits at 200MHz, resolution 5ns, wraps every 10737418237ns
CPU 0 Unable to handle kernel paging request at virtual address ffffb0aa, epc == 8067daa8, ra == 8067da84 Oops[#1]:

CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.9.18 #51
task: 8065e3e0 task.stack: 80644000
$ 0   : 00000000 00000001 00000000 00000000
$ 4   : 8065b4d0 00000000 805d0000 00000010
$ 8   : 00000010 80321400 fffff000 812de408
$12   : 00000000 00000000 00000000 ffffffff
$16   : 00000002 ffffffff 80660000 806a666c
$20   : 806c0000 00000000 00000000 00000000
$24   : 00000000 00000010
$28   : 80644000 80645ed0 00000000 8067da84
Hi    : 00000000
Lo    : 00000000
epc   : 8067daa8 start_kernel+0x33c/0x500
ra    : 8067da84 start_kernel+0x318/0x500
Status: 11000402 KERNEL EXL
Cause : 4080040c (ExcCode 03)
BadVA : ffffb0aa
PrId  : 0501992c (MIPS 1004Kc)
Modules linked in:
Process swapper/0 (pid: 0, threadinfo=80644000, task=8065e3e0, tls=00000000)
Call Trace:
[<8067daa8>] start_kernel+0x33c/0x500
Code: 24050240  0c0131f9  24849c64 <a200b0a8> 41606020  000000c0  0c1a45e6 00000000  0c1a5f44

UBSAN also detects the same issue:

================================================================

UBSAN: Undefined behaviour in arch/mips/kernel/cevt-r4k.c:85:41
load of address 80647e4c with insufficient space
for an object of type 'unsigned int'
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.9.18 #47
Call Trace:
[<80028f70>] show_stack+0x88/0xa4
[<80312654>] dump_stack+0x84/0xc0
[<8034163c>] ubsan_epilogue+0x14/0x50
[<803417d8>] __ubsan_handle_type_mismatch+0x160/0x168
[<8002dab0>] r4k_clockevent_init+0x544/0x764
[<80684d34>] time_init+0x18/0x90
[<8067fa5c>] start_kernel+0x2f0/0x500
=================================================================

buf2[] is intentionally only 3 elements so that the last element is the median once 5 samples have been inserted, so explicitly prevent the possibility of comparing against the 4th element rather than extending the array.

Patchwork: https://patchwork.linux-mips.org/patch/15892/

---
 arch/mips/kernel/cevt-r4k.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -80,7 +80,7 @@ static unsigned int calculate_min_delta(
 		}
 
 		/* Sorted insert of 75th percentile into buf2 */
-		for (k = 0; k < i; ++k) {
+		for (k = 0; k < i && k < ARRAY_SIZE(buf2); ++k) {
 			if (buf1[ARRAY_SIZE(buf1) - 1] < buf2[k]) {
 				l = min_t(unsigned int,
 					  i, ARRAY_SIZE(buf2) - 1);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: J. Bruce Fields <[email protected]>

commit db44bac41bbfc0c0d9dd943092d8bded3c9db19b upstream.

Use a couple shortcuts that will simplify a following bugfix.

---
 fs/nfsd/nfs3xdr.c |    9 +++++----
 fs/nfsd/nfsxdr.c  |    8 ++++----
 2 files changed, 9 insertions(+), 8 deletions(-)

@@ -358,6 +358,8 @@ nfs3svc_decode_writeargs(struct svc_rqst
 {
 	unsigned int len, v, hdr, dlen;
 	u32 max_blocksize = svc_max_payload(rqstp);
+	struct kvec *head = rqstp->rq_arg.head;
+	struct kvec *tail = rqstp->rq_arg.tail;
 
 	p = decode_fh(p, &args->fh);
 	if (!p)

@@ -377,9 +379,8 @@ nfs3svc_decode_writeargs(struct svc_rqst
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		+ rqstp->rq_arg.tail[0].iov_len - hdr;
+	hdr = (void*)p - head->iov_base;
+	dlen = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len - hdr;
 	/*
 	 * Round the length of the data which was specified up to
 	 * the next multiple of XDR units and then compare that

@@ -396,7 +397,7 @@ nfs3svc_decode_writeargs(struct svc_rqst
 		len = args->len = max_blocksize;
 	}
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;

@@ -280,6 +280,7 @@ nfssvc_decode_writeargs(struct svc_rqst
 					struct nfsd_writeargs *args)
 {
 	unsigned int len, hdr, dlen;
+	struct kvec *head = rqstp->rq_arg.head;
 	int v;
 
 	p = decode_fh(p, &args->fh);

@@ -300,9 +301,8 @@ nfssvc_decode_writeargs(struct svc_rqst
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		- hdr;
+	hdr = (void*)p - head->iov_base;
+	dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
 
 	/*
 	 * Round the length of the data which was specified up to

@@ -316,7 +316,7 @@ nfssvc_decode_writeargs(struct svc_rqst
 		return 0;
 
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yan, Zheng <[email protected]>

commit 8179a101eb5f4ef0ac9a915fcea9a9d3109efa90 upstream.

ceph_set_acl() calls __ceph_setattr() if the setacl operation needs to modify inode's i_mode. __ceph_setattr() updates inode's i_mode, then calls posix_acl_chmod().

The problem is that __ceph_setattr() calls posix_acl_chmod() before sending the setattr request. The get_acl() call in posix_acl_chmod() can trigger a getxattr request. The reply of the getxattr request can restore inode's i_mode to its old value. The set_acl() call in posix_acl_chmod() sees old value of inode's i_mode, so it calls __ceph_setattr() again.

---
 fs/ceph/inode.c |   22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

@@ -2080,11 +2080,6 @@ int __ceph_setattr(struct inode *inode,
 	if (inode_dirty_flags)
 		__mark_inode_dirty(inode, inode_dirty_flags);
 
-	if (ia_valid & ATTR_MODE) {
-		err = posix_acl_chmod(inode, attr->ia_mode);
-		if (err)
-			goto out_put;
-	}
 
 	if (mask) {
 		req->r_inode = inode;

@@ -2098,13 +2093,11 @@ int __ceph_setattr(struct inode *inode,
 	     ceph_cap_string(dirtied), mask);
 
 	ceph_mdsc_put_request(req);
-	if (mask & CEPH_SETATTR_SIZE)
-		__ceph_do_pending_vmtruncate(inode);
-	ceph_free_cap_flush(prealloc_cf);
-	return err;
-out_put:
-	ceph_mdsc_put_request(req);
 	ceph_free_cap_flush(prealloc_cf);
+
+	if (err >= 0 && (mask & CEPH_SETATTR_SIZE))
+		__ceph_do_pending_vmtruncate(inode);
+
 	return err;
 }
 

@@ -2123,7 +2116,12 @@ int ceph_setattr(struct dentry *dentry,
 	if (err != 0)
 		return err;
 
-	return __ceph_setattr(inode, attr);
+	err = __ceph_setattr(inode, attr);
+
+	if (err >= 0 && (attr->ia_valid & ATTR_MODE))
+		err = posix_acl_chmod(inode, attr->ia_mode);
+
+	return err;
 }
 
 /*

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Noam Camus <[email protected]>

commit 6492f09e864417d382e22b922ae30693a7ce2982 upstream.

Make ATOMIC_INIT available for all ARC platforms (including plat-eznps)

---
 arch/arc/include/asm/atomic.h |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -17,10 +17,11 @@
 #include <asm/barrier.h>
 #include <asm/smp.h>
 
+#define ATOMIC_INIT(i)	{ (i) }
+
 #ifndef CONFIG_ARC_PLAT_EZNPS
 
 #define atomic_read(v)  READ_ONCE((v)->counter)
-#define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef CONFIG_ARC_HAS_LLSC
 

Compiled and booted on my test system. No dmesg regressions.

thanks,
-- Shuah

Build results:

	total: 149 pass: 149 fail: 0
Qemu test results:
        total: 122 pass: 122 fail: 0

Details are available at http://kerneltests.org/builders.

Guenter