linux-stable.git/drivers/net, branch v4.16.2 Linux kernel stable tree nfp: use full 40 bits of the NSP buffer address 2018-04-12T10:30:01+00:00 Dirk van der Merwe dirk.vandermerwe@netronome.com 2018-04-04T00:24:23+00:00 87d1acd833dfee77dbe927bdb2099628129308ba [ Upstream commit 1489bbd10e16079ce30a53d3c22a431fd47af791 ] The NSP default buffer is a piece of NFP memory where additional command data can be placed. Its format has been copied from host buffer, but the PCIe selection bits do not make sense in this case. If those get masked out from a NFP address - writes to random place in the chip memory may be issued and crash the device. Even in the general NSP buffer case, it doesn't make sense to have the PCIe selection bits there anymore. These are unused at the moment, and when it becomes necessary, the PCIe selection bits should rather be moved to another register to utilise more bits for the buffer address. This has never been an issue because the buffer used to be allocated in memory with less-than-38-bit-long address but that is about to change. Fixes: 1a64821c6af7 ("nfp: add support for service processor access") Signed-off-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 1489bbd10e16079ce30a53d3c22a431fd47af791 ]

The NSP default buffer is a piece of NFP memory where additional
command data can be placed.  Its format has been copied from
host buffer, but the PCIe selection bits do not make sense in
this case.  If those get masked out from a NFP address - writes
to random place in the chip memory may be issued and crash the
device.

Even in the general NSP buffer case, it doesn't make sense to have the
PCIe selection bits there anymore. These are unused at the moment, and
when it becomes necessary, the PCIe selection bits should rather be
moved to another register to utilise more bits for the buffer address.

This has never been an issue because the buffer used to be
allocated in memory with less-than-38-bit-long address but that
is about to change.

Fixes: 1a64821c6af7 ("nfp: add support for service processor access")
Signed-off-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
sky2: Increase D3 delay to sky2 stops working after suspend 2018-04-12T10:30:00+00:00 Kai-Heng Feng kai.heng.feng@canonical.com 2018-03-31T15:42:03+00:00 22714d6e24a7da2d07f49162790d6b1973702da9 [ Upstream commit afb133637071be6deeb8b3d0e55593ffbf63c527 ] The sky2 ethernet stops working after system resume from suspend: [ 582.852065] sky2 0000:04:00.0: Refused to change power state, currently in D3 The current 150ms delay is not enough, change it to 200ms can solve the issue. BugLink: https://bugs.launchpad.net/bugs/1758507 Cc: Stable <stable@vger.kernel.org> Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit afb133637071be6deeb8b3d0e55593ffbf63c527 ]

The sky2 ethernet stops working after system resume from suspend:
[ 582.852065] sky2 0000:04:00.0: Refused to change power state, currently in D3

The current 150ms delay is not enough, change it to 200ms can solve the
issue.

BugLink: https://bugs.launchpad.net/bugs/1758507
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
pptp: remove a buggy dst release in pptp_connect() 2018-04-12T10:29:59+00:00 Eric Dumazet edumazet@google.com 2018-04-03T01:48:37+00:00 141ce92477bdee39fbc41f52396630bb079645b0 [ Upstream commit bfacfb457b36911a10140b8cb3ce76a74883ac5a ] Once dst has been cached in socket via sk_setup_caps(), it is illegal to call ip_rt_put() (or dst_release()), since sk_setup_caps() did not change dst refcount. We can still dereference it since we hold socket lock. Caugth by syzbot : BUG: KASAN: use-after-free in atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline] BUG: KASAN: use-after-free in dst_release+0x27/0xa0 net/core/dst.c:185 Write of size 4 at addr ffff8801c54dc040 by task syz-executor4/20088 CPU: 1 PID: 20088 Comm: syz-executor4 Not tainted 4.16.0+ #376 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x1a7/0x27d lib/dump_stack.c:53 print_address_description+0x73/0x250 mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report+0x23c/0x360 mm/kasan/report.c:412 check_memory_region_inline mm/kasan/kasan.c:260 [inline] check_memory_region+0x137/0x190 mm/kasan/kasan.c:267 kasan_check_write+0x14/0x20 mm/kasan/kasan.c:278 atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline] dst_release+0x27/0xa0 net/core/dst.c:185 sk_dst_set include/net/sock.h:1812 [inline] sk_dst_reset include/net/sock.h:1824 [inline] sock_setbindtodevice net/core/sock.c:610 [inline] sock_setsockopt+0x431/0x1b20 net/core/sock.c:707 SYSC_setsockopt net/socket.c:1845 [inline] SyS_setsockopt+0x2ff/0x360 net/socket.c:1828 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 RIP: 0033:0x4552d9 RSP: 002b:00007f4878126c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 00007f48781276d4 RCX: 00000000004552d9 RDX: 0000000000000019 RSI: 0000000000000001 RDI: 0000000000000013 RBP: 000000000072bea0 R08: 0000000000000010 R09: 0000000000000000 R10: 00000000200010c0 R11: 0000000000000246 R12: 00000000ffffffff R13: 0000000000000526 R14: 00000000006fac30 R15: 0000000000000000 Allocated by task 20088: save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:552 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489 kmem_cache_alloc+0x12e/0x760 mm/slab.c:3542 dst_alloc+0x11f/0x1a0 net/core/dst.c:104 rt_dst_alloc+0xe9/0x540 net/ipv4/route.c:1520 __mkroute_output net/ipv4/route.c:2265 [inline] ip_route_output_key_hash_rcu+0xa49/0x2c60 net/ipv4/route.c:2493 ip_route_output_key_hash+0x20b/0x370 net/ipv4/route.c:2322 __ip_route_output_key include/net/route.h:126 [inline] ip_route_output_flow+0x26/0xa0 net/ipv4/route.c:2577 ip_route_output_ports include/net/route.h:163 [inline] pptp_connect+0xa84/0x1170 drivers/net/ppp/pptp.c:453 SYSC_connect+0x213/0x4a0 net/socket.c:1639 SyS_connect+0x24/0x30 net/socket.c:1620 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 Freed by task 20082: save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:520 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:527 __cache_free mm/slab.c:3486 [inline] kmem_cache_free+0x83/0x2a0 mm/slab.c:3744 dst_destroy+0x266/0x380 net/core/dst.c:140 dst_destroy_rcu+0x16/0x20 net/core/dst.c:153 __rcu_reclaim kernel/rcu/rcu.h:178 [inline] rcu_do_batch kernel/rcu/tree.c:2675 [inline] invoke_rcu_callbacks kernel/rcu/tree.c:2930 [inline] __rcu_process_callbacks kernel/rcu/tree.c:2897 [inline] rcu_process_callbacks+0xd6c/0x17b0 kernel/rcu/tree.c:2914 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285 The buggy address belongs to the object at ffff8801c54dc000 which belongs to the cache ip_dst_cache of size 168 The buggy address is located 64 bytes inside of 168-byte region [ffff8801c54dc000, ffff8801c54dc0a8) The buggy address belongs to the page: page:ffffea0007153700 count:1 mapcount:0 mapping:ffff8801c54dc000 index:0x0 flags: 0x2fffc0000000100(slab) raw: 02fffc0000000100 ffff8801c54dc000 0000000000000000 0000000100000010 raw: ffffea0006b34b20 ffffea0006b6c1e0 ffff8801d674a1c0 0000000000000000 page dumped because: kasan: bad access detected Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit bfacfb457b36911a10140b8cb3ce76a74883ac5a ]

Once dst has been cached in socket via sk_setup_caps(),
it is illegal to call ip_rt_put() (or dst_release()),
since sk_setup_caps() did not change dst refcount.

We can still dereference it since we hold socket lock.

Caugth by syzbot :

BUG: KASAN: use-after-free in atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline]
BUG: KASAN: use-after-free in dst_release+0x27/0xa0 net/core/dst.c:185
Write of size 4 at addr ffff8801c54dc040 by task syz-executor4/20088

CPU: 1 PID: 20088 Comm: syz-executor4 Not tainted 4.16.0+ #376
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1a7/0x27d lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report+0x23c/0x360 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x137/0x190 mm/kasan/kasan.c:267
 kasan_check_write+0x14/0x20 mm/kasan/kasan.c:278
 atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline]
 dst_release+0x27/0xa0 net/core/dst.c:185
 sk_dst_set include/net/sock.h:1812 [inline]
 sk_dst_reset include/net/sock.h:1824 [inline]
 sock_setbindtodevice net/core/sock.c:610 [inline]
 sock_setsockopt+0x431/0x1b20 net/core/sock.c:707
 SYSC_setsockopt net/socket.c:1845 [inline]
 SyS_setsockopt+0x2ff/0x360 net/socket.c:1828
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4552d9
RSP: 002b:00007f4878126c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00007f48781276d4 RCX: 00000000004552d9
RDX: 0000000000000019 RSI: 0000000000000001 RDI: 0000000000000013
RBP: 000000000072bea0 R08: 0000000000000010 R09: 0000000000000000
R10: 00000000200010c0 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000526 R14: 00000000006fac30 R15: 0000000000000000

Allocated by task 20088:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:552
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc+0x12e/0x760 mm/slab.c:3542
 dst_alloc+0x11f/0x1a0 net/core/dst.c:104
 rt_dst_alloc+0xe9/0x540 net/ipv4/route.c:1520
 __mkroute_output net/ipv4/route.c:2265 [inline]
 ip_route_output_key_hash_rcu+0xa49/0x2c60 net/ipv4/route.c:2493
 ip_route_output_key_hash+0x20b/0x370 net/ipv4/route.c:2322
 __ip_route_output_key include/net/route.h:126 [inline]
 ip_route_output_flow+0x26/0xa0 net/ipv4/route.c:2577
 ip_route_output_ports include/net/route.h:163 [inline]
 pptp_connect+0xa84/0x1170 drivers/net/ppp/pptp.c:453
 SYSC_connect+0x213/0x4a0 net/socket.c:1639
 SyS_connect+0x24/0x30 net/socket.c:1620
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Freed by task 20082:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:520
 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:527
 __cache_free mm/slab.c:3486 [inline]
 kmem_cache_free+0x83/0x2a0 mm/slab.c:3744
 dst_destroy+0x266/0x380 net/core/dst.c:140
 dst_destroy_rcu+0x16/0x20 net/core/dst.c:153
 __rcu_reclaim kernel/rcu/rcu.h:178 [inline]
 rcu_do_batch kernel/rcu/tree.c:2675 [inline]
 invoke_rcu_callbacks kernel/rcu/tree.c:2930 [inline]
 __rcu_process_callbacks kernel/rcu/tree.c:2897 [inline]
 rcu_process_callbacks+0xd6c/0x17b0 kernel/rcu/tree.c:2914
 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285

The buggy address belongs to the object at ffff8801c54dc000
 which belongs to the cache ip_dst_cache of size 168
The buggy address is located 64 bytes inside of
 168-byte region [ffff8801c54dc000, ffff8801c54dc0a8)
The buggy address belongs to the page:
page:ffffea0007153700 count:1 mapcount:0 mapping:ffff8801c54dc000 index:0x0
flags: 0x2fffc0000000100(slab)
raw: 02fffc0000000100 ffff8801c54dc000 0000000000000000 0000000100000010
raw: ffffea0006b34b20 ffffea0006b6c1e0 ffff8801d674a1c0 0000000000000000
page dumped because: kasan: bad access detected

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
net: mvneta: fix enable of all initialized RXQs 2018-03-30T18:27:47+00:00 Yelena Krivosheev yelena@marvell.com 2018-03-30T10:05:31+00:00 e81b5e01c14add8395dfba7130f8829206bb507d In mvneta_port_up() we enable relevant RX and TX port queues by write queues bit map to an appropriate register. q_map must be ZERO in the beginning of this process. Signed-off-by: Yelena Krivosheev <yelena@marvell.com> Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com> Acked-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
In mvneta_port_up() we enable relevant RX and TX port queues by write
queues bit map to an appropriate register.

q_map must be ZERO in the beginning of this process.

Signed-off-by: Yelena Krivosheev <yelena@marvell.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Acked-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
vrf: Fix use after free and double free in vrf_finish_output 2018-03-30T18:20:23+00:00 David Ahern dsahern@gmail.com 2018-03-29T19:49:52+00:00 82dd0d2a9a76fc8fa2b18d80b987d455728bf83a Miguel reported an skb use after free / double free in vrf_finish_output when neigh_output returns an error. The vrf driver should return after the call to neigh_output as it takes over the skb on error path as well. Patch is a simplified version of Miguel's patch which was written for 4.9, and updated to top of tree. Fixes: 8f58336d3f78a ("net: Add ethernet header for pass through VRF device") Signed-off-by: Miguel Fadon Perlines <mfadon@teldat.com> Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Miguel reported an skb use after free / double free in vrf_finish_output
when neigh_output returns an error. The vrf driver should return after
the call to neigh_output as it takes over the skb on error path as well.

Patch is a simplified version of Miguel's patch which was written for 4.9,
and updated to top of tree.

Fixes: 8f58336d3f78a ("net: Add ethernet header for pass through VRF device")
Signed-off-by: Miguel Fadon Perlines <mfadon@teldat.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf 2018-03-30T01:49:19+00:00 David S. Miller davem@davemloft.net 2018-03-30T01:49:19+00:00 74957cbfb7eabe7639a22bd58f45a99bde42fd0c Daniel Borkman says: ==================== pull-request: bpf 2018-03-29 The following pull-request contains BPF updates for your *net* tree. The main changes are: 1) Fix nfp to properly check max insn count while emitting instructions in the JIT which was wrongly comparing bytes against number of instructions before, from Jakub. 2) Fix for bpftool to avoid usage of hex numbers in JSON output since JSON doesn't accept hex numbers with 0x prefix, also from Jakub. ==================== Signed-off-by: David S. Miller <davem@davemloft.net> 
Daniel Borkman says:

====================
pull-request: bpf 2018-03-29

The following pull-request contains BPF updates for your *net* tree.

The main changes are:

1) Fix nfp to properly check max insn count while emitting
   instructions in the JIT which was wrongly comparing bytes
   against number of instructions before, from Jakub.

2) Fix for bpftool to avoid usage of hex numbers in JSON
   output since JSON doesn't accept hex numbers with 0x
   prefix, also from Jakub.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
qede: Do not drop rx-checksum invalidated packets. 2018-03-29T18:32:15+00:00 Manish Chopra manish.chopra@cavium.com 2018-03-28T10:35:52+00:00 58f101bf87e32753342a6924772c6ebb0fbde24a Today, driver drops received packets which are indicated as invalid checksum by the device. Instead of dropping such packets, pass them to the stack with CHECKSUM_NONE indication in skb. Signed-off-by: Ariel Elior <ariel.elior@cavium.com> Signed-off-by: Manish Chopra <manish.chopra@cavium.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Today, driver drops received packets which are indicated as
invalid checksum by the device. Instead of dropping such packets,
pass them to the stack with CHECKSUM_NONE indication in skb.

Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
hv_netvsc: enable multicast if necessary 2018-03-29T15:45:06+00:00 Stephen Hemminger stephen@networkplumber.org 2018-03-27T18:28:48+00:00 f03dbb06dc380274e351ca4b1ee1587ed4529e62 My recent change to netvsc drive in how receive flags are handled broke multicast. The Hyper-v/Azure virtual interface there is not a multicast filter list, filtering is only all or none. The driver must enable all multicast if any multicast address is present. Fixes: 009f766ca238 ("hv_netvsc: filter multicast/broadcast") Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
My recent change to netvsc drive in how receive flags are handled
broke multicast.  The Hyper-v/Azure virtual interface there is not a
multicast filter list, filtering is only all or none. The driver must
enable all multicast if any multicast address is present.

Fixes: 009f766ca238 ("hv_netvsc: filter multicast/broadcast")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
lan78xx: Crash in lan78xx_writ_reg (Workqueue: events lan78xx_deferred_multicast_write) 2018-03-29T15:35:51+00:00 Raghuram Chary J raghuramchary.jallipalli@microchip.com 2018-03-27T09:21:16+00:00 2d2d99ec13f62d5d2cecb6169dfdb6bbe05356d0 Description: Crash was reported with syzkaller pointing to lan78xx_write_reg routine. Root-cause: Proper cleanup of workqueues and init/setup routines was not happening in failure conditions. Fix: Handled the error conditions by cleaning up the queues and init/setup routines. Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") Reported-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Raghuram Chary J <raghuramchary.jallipalli@microchip.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Description:
Crash was reported with syzkaller pointing to lan78xx_write_reg routine.

Root-cause:
Proper cleanup of workqueues and init/setup routines was not happening
in failure conditions.

Fix:
Handled the error conditions by cleaning up the queues and init/setup
routines.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Raghuram Chary J <raghuramchary.jallipalli@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
qede: Fix barrier usage after tx doorbell write. 2018-03-27T17:11:46+00:00 Manish Chopra manish.chopra@cavium.com 2018-03-27T13:34:41+00:00 b9fc828debc8ac2bb21b5819a44d2aea456f1c95 Since commit c5ad119fb6c09b0297446be05bd66602fa564758 ("net: sched: pfifo_fast use skb_array") driver is exposed to an issue where it is hitting NULL skbs while handling TX completions. Driver uses mmiowb() to flush the writes to the doorbell bar which is a write-combined bar, however on x86 mmiowb() does not flush the write combined buffer. This patch fixes this problem by replacing mmiowb() with wmb() after the write combined doorbell write so that writes are flushed and synchronized from more than one processor. V1->V2: ------- This patch was marked as "superseded" in patchwork. (Not really sure for what reason).Resending it as v2. Signed-off-by: Ariel Elior <ariel.elior@cavium.com> Signed-off-by: Manish Chopra <manish.chopra@cavium.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Since commit c5ad119fb6c09b0297446be05bd66602fa564758
("net: sched: pfifo_fast use skb_array") driver is exposed
to an issue where it is hitting NULL skbs while handling TX
completions. Driver uses mmiowb() to flush the writes to the
doorbell bar which is a write-combined bar, however on x86
mmiowb() does not flush the write combined buffer.

This patch fixes this problem by replacing mmiowb() with wmb()
after the write combined doorbell write so that writes are
flushed and synchronized from more than one processor.

V1->V2:
-------
This patch was marked as "superseded" in patchwork.
(Not really sure for what reason).Resending it as v2.

Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: Manish Chopra <manish.chopra@cavium.com>

Signed-off-by: David S. Miller <davem@davemloft.net>