From a294865978b701e4d0d90135672749531b9a900d Mon Sep 17 00:00:00 2001
From: Dan Rosenberg <drosenberg@vsecurity.com>
Date: Fri, 6 May 2011 03:27:18 +0000
Subject: dccp: handle invalid feature options length
A length of zero (after subtracting two for the type and len fields) for
the DCCPO_{CHANGE,CONFIRM}_{L,R} options will cause an underflow due to
the subtraction. The subsequent code may read past the end of the
options value buffer when parsing. I'm unsure of what the consequences
of this might be, but it's probably not good.
Signed-off-by: Dan Rosenberg <drosenberg@vsecurity.com>
Cc: stable@kernel.org
Acked-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dccp/options.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/dccp/options.c b/net/dccp/options.c
index f06ffcfc8d7..4b2ab657ac8 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -123,6 +123,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R:
if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */
break;
+ if (len == 0)
+ goto out_invalid_option;
rc = dccp_feat_parse_options(sk, dreq, mandatory, opt,
*value, value + 1, len - 1);
if (rc)
--
cgit v1.2.3-18-g5258
From e328d410826d52e9ee348aff9064c4a207f2adb1 Mon Sep 17 00:00:00 2001
From: Roland Dreier <roland@purestorage.com>
Date: Fri, 6 May 2011 08:32:53 +0000
Subject: vmxnet3: Consistently disable irqs when taking adapter->cmd_lock
Using the vmxnet3 driver produces a lockdep warning because
vmxnet3_set_mc(), which is called with mc->mca_lock held, takes
adapter->cmd_lock. However, there are a couple of places where
adapter->cmd_lock is taken with softirqs enabled, lockdep warns that a
softirq that tries to take mc->mca_lock could happen while
adapter->cmd_lock is held, leading to an AB-BA deadlock.
I'm not sure if this is a real potential deadlock or not, but the
simplest and best fix seems to be simply to make sure we take cmd_lock
with spin_lock_irqsave() everywhere -- the places with plain spin_lock
just look like oversights.
The full enormous lockdep warning is:
=========================================================
[ INFO: possible irq lock inversion dependency detected ]
2.6.39-rc6+ #1
---------------------------------------------------------
ifconfig/567 just changed the state of lock:
(&(&mc->mca_lock)->rlock){+.-...}, at: [<ffffffff81531e9f>] mld_ifc_timer_expire+0xff/0x280
but this lock took another, SOFTIRQ-unsafe lock in the past:
(&(&adapter->cmd_lock)->rlock){+.+...}
and interrupts could create inverse lock ordering between them.
other info that might help us debug this:
4 locks held by ifconfig/567:
#0: (rtnl_mutex){+.+.+.}, at: [<ffffffff8147d547>] rtnl_lock+0x17/0x20
#1: ((inetaddr_chain).rwsem){.+.+.+}, at: [<ffffffff810896cf>] __blocking_notifier_call_chain+0x5f/0xb0
#2: (&idev->mc_ifc_timer){+.-...}, at: [<ffffffff8106f21b>] run_timer_softirq+0xeb/0x3f0
#3: (&ndev->lock){++.-..}, at: [<ffffffff81531dd2>] mld_ifc_timer_expire+0x32/0x280
the shortest dependencies between 2nd lock and 1st lock:
-> (&(&adapter->cmd_lock)->rlock){+.+...} ops: 11 {
HARDIRQ-ON-W at:
[<ffffffff8109ad86>] __lock_acquire+0x7f6/0x1e10
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff81571156>] _raw_spin_lock+0x36/0x70
[<ffffffffa000d212>] vmxnet3_alloc_intr_resources+0x22/0x230 [vmxnet3]
[<ffffffffa0014031>] vmxnet3_probe_device+0x5f6/0x15c5 [vmxnet3]
[<ffffffff812df67f>] local_pci_probe+0x5f/0xd0
[<ffffffff812dfde9>] pci_device_probe+0x119/0x120
[<ffffffff81373df6>] driver_probe_device+0x96/0x1c0
[<ffffffff81373fcb>] __driver_attach+0xab/0xb0
[<ffffffff81372a1e>] bus_for_each_dev+0x5e/0x90
[<ffffffff81373a2e>] driver_attach+0x1e/0x20
[<ffffffff813735b8>] bus_add_driver+0xc8/0x290
[<ffffffff813745b6>] driver_register+0x76/0x140
[<ffffffff812e0046>] __pci_register_driver+0x66/0xe0
[<ffffffffa001b03a>] serio_raw_poll+0x3a/0x60 [serio_raw]
[<ffffffff81002165>] do_one_initcall+0x45/0x190
[<ffffffff810aa76b>] sys_init_module+0xfb/0x250
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
SOFTIRQ-ON-W at:
[<ffffffff8109adb7>] __lock_acquire+0x827/0x1e10
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff81571156>] _raw_spin_lock+0x36/0x70
[<ffffffffa000d212>] vmxnet3_alloc_intr_resources+0x22/0x230 [vmxnet3]
[<ffffffffa0014031>] vmxnet3_probe_device+0x5f6/0x15c5 [vmxnet3]
[<ffffffff812df67f>] local_pci_probe+0x5f/0xd0
[<ffffffff812dfde9>] pci_device_probe+0x119/0x120
[<ffffffff81373df6>] driver_probe_device+0x96/0x1c0
[<ffffffff81373fcb>] __driver_attach+0xab/0xb0
[<ffffffff81372a1e>] bus_for_each_dev+0x5e/0x90
[<ffffffff81373a2e>] driver_attach+0x1e/0x20
[<ffffffff813735b8>] bus_add_driver+0xc8/0x290
[<ffffffff813745b6>] driver_register+0x76/0x140
[<ffffffff812e0046>] __pci_register_driver+0x66/0xe0
[<ffffffffa001b03a>] serio_raw_poll+0x3a/0x60 [serio_raw]
[<ffffffff81002165>] do_one_initcall+0x45/0x190
[<ffffffff810aa76b>] sys_init_module+0xfb/0x250
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
INITIAL USE at:
[<ffffffff8109a9e9>] __lock_acquire+0x459/0x1e10
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff81571156>] _raw_spin_lock+0x36/0x70
[<ffffffffa000d212>] vmxnet3_alloc_intr_resources+0x22/0x230 [vmxnet3]
[<ffffffffa0014031>] vmxnet3_probe_device+0x5f6/0x15c5 [vmxnet3]
[<ffffffff812df67f>] local_pci_probe+0x5f/0xd0
[<ffffffff812dfde9>] pci_device_probe+0x119/0x120
[<ffffffff81373df6>] driver_probe_device+0x96/0x1c0
[<ffffffff81373fcb>] __driver_attach+0xab/0xb0
[<ffffffff81372a1e>] bus_for_each_dev+0x5e/0x90
[<ffffffff81373a2e>] driver_attach+0x1e/0x20
[<ffffffff813735b8>] bus_add_driver+0xc8/0x290
[<ffffffff813745b6>] driver_register+0x76/0x140
[<ffffffff812e0046>] __pci_register_driver+0x66/0xe0
[<ffffffffa001b03a>] serio_raw_poll+0x3a/0x60 [serio_raw]
[<ffffffff81002165>] do_one_initcall+0x45/0x190
[<ffffffff810aa76b>] sys_init_module+0xfb/0x250
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
}
... key at: [<ffffffffa0017590>] __key.42516+0x0/0xffffffffffffda70 [vmxnet3]
... acquired at:
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff81571bb5>] _raw_spin_lock_irqsave+0x55/0xa0
[<ffffffffa000de27>] vmxnet3_set_mc+0x97/0x1a0 [vmxnet3]
[<ffffffff8146ffa0>] __dev_set_rx_mode+0x40/0xb0
[<ffffffff81470040>] dev_set_rx_mode+0x30/0x50
[<ffffffff81470127>] __dev_open+0xc7/0x100
[<ffffffff814703c1>] __dev_change_flags+0xa1/0x180
[<ffffffff81470568>] dev_change_flags+0x28/0x70
[<ffffffff814da960>] devinet_ioctl+0x730/0x800
[<ffffffff814db508>] inet_ioctl+0x88/0xa0
[<ffffffff814541f0>] sock_do_ioctl+0x30/0x70
[<ffffffff814542a9>] sock_ioctl+0x79/0x2f0
[<ffffffff81188798>] do_vfs_ioctl+0x98/0x570
[<ffffffff81188d01>] sys_ioctl+0x91/0xa0
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
-> (_xmit_ETHER){+.....} ops: 6 {
HARDIRQ-ON-W at:
[<ffffffff8109ad86>] __lock_acquire+0x7f6/0x1e10
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff8157124b>] _raw_spin_lock_bh+0x3b/0x70
[<ffffffff81475618>] __dev_mc_add+0x38/0x90
[<ffffffff814756a0>] dev_mc_add+0x10/0x20
[<ffffffff81532c9e>] igmp6_group_added+0x10e/0x1b0
[<ffffffff81533f2d>] ipv6_dev_mc_inc+0x2cd/0x430
[<ffffffff81515e17>] ipv6_add_dev+0x357/0x450
[<ffffffff81519f27>] addrconf_notify+0x2f7/0xb10
[<ffffffff81575c1c>] notifier_call_chain+0x8c/0xc0
[<ffffffff81089586>] raw_notifier_call_chain+0x16/0x20
[<ffffffff814689b7>] call_netdevice_notifiers+0x37/0x70
[<ffffffff8146a944>] register_netdevice+0x244/0x2d0
[<ffffffff8146aa0f>] register_netdev+0x3f/0x60
[<ffffffffa001419b>] vmxnet3_probe_device+0x760/0x15c5 [vmxnet3]
[<ffffffff812df67f>] local_pci_probe+0x5f/0xd0
[<ffffffff812dfde9>] pci_device_probe+0x119/0x120
[<ffffffff81373df6>] driver_probe_device+0x96/0x1c0
[<ffffffff81373fcb>] __driver_attach+0xab/0xb0
[<ffffffff81372a1e>] bus_for_each_dev+0x5e/0x90
[<ffffffff81373a2e>] driver_attach+0x1e/0x20
[<ffffffff813735b8>] bus_add_driver+0xc8/0x290
[<ffffffff813745b6>] driver_register+0x76/0x140
[<ffffffff812e0046>] __pci_register_driver+0x66/0xe0
[<ffffffffa001b03a>] serio_raw_poll+0x3a/0x60 [serio_raw]
[<ffffffff81002165>] do_one_initcall+0x45/0x190
[<ffffffff810aa76b>] sys_init_module+0xfb/0x250
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
INITIAL USE at:
[<ffffffff8109a9e9>] __lock_acquire+0x459/0x1e10
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff8157124b>] _raw_spin_lock_bh+0x3b/0x70
[<ffffffff81475618>] __dev_mc_add+0x38/0x90
[<ffffffff814756a0>] dev_mc_add+0x10/0x20
[<ffffffff81532c9e>] igmp6_group_added+0x10e/0x1b0
[<ffffffff81533f2d>] ipv6_dev_mc_inc+0x2cd/0x430
[<ffffffff81515e17>] ipv6_add_dev+0x357/0x450
[<ffffffff81519f27>] addrconf_notify+0x2f7/0xb10
[<ffffffff81575c1c>] notifier_call_chain+0x8c/0xc0
[<ffffffff81089586>] raw_notifier_call_chain+0x16/0x20
[<ffffffff814689b7>] call_netdevice_notifiers+0x37/0x70
[<ffffffff8146a944>] register_netdevice+0x244/0x2d0
[<ffffffff8146aa0f>] register_netdev+0x3f/0x60
[<ffffffffa001419b>] vmxnet3_probe_device+0x760/0x15c5 [vmxnet3]
[<ffffffff812df67f>] local_pci_probe+0x5f/0xd0
[<ffffffff812dfde9>] pci_device_probe+0x119/0x120
[<ffffffff81373df6>] driver_probe_device+0x96/0x1c0
[<ffffffff81373fcb>] __driver_attach+0xab/0xb0
[<ffffffff81372a1e>] bus_for_each_dev+0x5e/0x90
[<ffffffff81373a2e>] driver_attach+0x1e/0x20
[<ffffffff813735b8>] bus_add_driver+0xc8/0x290
[<ffffffff813745b6>] driver_register+0x76/0x140
[<ffffffff812e0046>] __pci_register_driver+0x66/0xe0
[<ffffffffa001b03a>] serio_raw_poll+0x3a/0x60 [serio_raw]
[<ffffffff81002165>] do_one_initcall+0x45/0x190
[<ffffffff810aa76b>] sys_init_module+0xfb/0x250
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
}
... key at: [<ffffffff827fd868>] netdev_addr_lock_key+0x8/0x1e0
... acquired at:
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff8157124b>] _raw_spin_lock_bh+0x3b/0x70
[<ffffffff81475618>] __dev_mc_add+0x38/0x90
[<ffffffff814756a0>] dev_mc_add+0x10/0x20
[<ffffffff81532c9e>] igmp6_group_added+0x10e/0x1b0
[<ffffffff81533f2d>] ipv6_dev_mc_inc+0x2cd/0x430
[<ffffffff81515e17>] ipv6_add_dev+0x357/0x450
[<ffffffff81519f27>] addrconf_notify+0x2f7/0xb10
[<ffffffff81575c1c>] notifier_call_chain+0x8c/0xc0
[<ffffffff81089586>] raw_notifier_call_chain+0x16/0x20
[<ffffffff814689b7>] call_netdevice_notifiers+0x37/0x70
[<ffffffff8146a944>] register_netdevice+0x244/0x2d0
[<ffffffff8146aa0f>] register_netdev+0x3f/0x60
[<ffffffffa001419b>] vmxnet3_probe_device+0x760/0x15c5 [vmxnet3]
[<ffffffff812df67f>] local_pci_probe+0x5f/0xd0
[<ffffffff812dfde9>] pci_device_probe+0x119/0x120
[<ffffffff81373df6>] driver_probe_device+0x96/0x1c0
[<ffffffff81373fcb>] __driver_attach+0xab/0xb0
[<ffffffff81372a1e>] bus_for_each_dev+0x5e/0x90
[<ffffffff81373a2e>] driver_attach+0x1e/0x20
[<ffffffff813735b8>] bus_add_driver+0xc8/0x290
[<ffffffff813745b6>] driver_register+0x76/0x140
[<ffffffff812e0046>] __pci_register_driver+0x66/0xe0
[<ffffffffa001b03a>] serio_raw_poll+0x3a/0x60 [serio_raw]
[<ffffffff81002165>] do_one_initcall+0x45/0x190
[<ffffffff810aa76b>] sys_init_module+0xfb/0x250
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
-> (&(&mc->mca_lock)->rlock){+.-...} ops: 6 {
HARDIRQ-ON-W at:
[<ffffffff8109ad86>] __lock_acquire+0x7f6/0x1e10
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff8157124b>] _raw_spin_lock_bh+0x3b/0x70
[<ffffffff81532bd5>] igmp6_group_added+0x45/0x1b0
[<ffffffff81533f2d>] ipv6_dev_mc_inc+0x2cd/0x430
[<ffffffff81515e17>] ipv6_add_dev+0x357/0x450
[<ffffffff81ce0d16>] addrconf_init+0x4e/0x183
[<ffffffff81ce0ba1>] inet6_init+0x191/0x2a6
[<ffffffff81002165>] do_one_initcall+0x45/0x190
[<ffffffff81ca4d3f>] kernel_init+0xe3/0x168
[<ffffffff8157b2e4>] kernel_thread_helper+0x4/0x10
IN-SOFTIRQ-W at:
[<ffffffff8109ad5e>] __lock_acquire+0x7ce/0x1e10
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff8157124b>] _raw_spin_lock_bh+0x3b/0x70
[<ffffffff81531e9f>] mld_ifc_timer_expire+0xff/0x280
[<ffffffff8106f2a9>] run_timer_softirq+0x179/0x3f0
[<ffffffff810666d0>] __do_softirq+0xc0/0x210
[<ffffffff8157b3dc>] call_softirq+0x1c/0x30
[<ffffffff8100d42d>] do_softirq+0xad/0xe0
[<ffffffff81066afe>] irq_exit+0x9e/0xb0
[<ffffffff8157bd40>] smp_apic_timer_interrupt+0x70/0x9b
[<ffffffff8157ab93>] apic_timer_interrupt+0x13/0x20
[<ffffffff8149d857>] rt_do_flush+0x87/0x2a0
[<ffffffff814a16b6>] rt_cache_flush+0x46/0x60
[<ffffffff814e36e0>] fib_disable_ip+0x40/0x60
[<ffffffff814e5447>] fib_inetaddr_event+0xd7/0xe0
[<ffffffff81575c1c>] notifier_call_chain+0x8c/0xc0
[<ffffffff810896e8>] __blocking_notifier_call_chain+0x78/0xb0
[<ffffffff81089736>] blocking_notifier_call_chain+0x16/0x20
[<ffffffff814d8021>] __inet_del_ifa+0xf1/0x2e0
[<ffffffff814d8223>] inet_del_ifa+0x13/0x20
[<ffffffff814da731>] devinet_ioctl+0x501/0x800
[<ffffffff814db508>] inet_ioctl+0x88/0xa0
[<ffffffff814541f0>] sock_do_ioctl+0x30/0x70
[<ffffffff814542a9>] sock_ioctl+0x79/0x2f0
[<ffffffff81188798>] do_vfs_ioctl+0x98/0x570
[<ffffffff81188d01>] sys_ioctl+0x91/0xa0
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
INITIAL USE at:
[<ffffffff8109a9e9>] __lock_acquire+0x459/0x1e10
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff8157124b>] _raw_spin_lock_bh+0x3b/0x70
[<ffffffff81532bd5>] igmp6_group_added+0x45/0x1b0
[<ffffffff81533f2d>] ipv6_dev_mc_inc+0x2cd/0x430
[<ffffffff81515e17>] ipv6_add_dev+0x357/0x450
[<ffffffff81ce0d16>] addrconf_init+0x4e/0x183
[<ffffffff81ce0ba1>] inet6_init+0x191/0x2a6
[<ffffffff81002165>] do_one_initcall+0x45/0x190
[<ffffffff81ca4d3f>] kernel_init+0xe3/0x168
[<ffffffff8157b2e4>] kernel_thread_helper+0x4/0x10
}
... key at: [<ffffffff82801be2>] __key.40877+0x0/0x8
... acquired at:
[<ffffffff810997bc>] check_usage_forwards+0x9c/0x110
[<ffffffff8109a32c>] mark_lock+0x19c/0x400
[<ffffffff8109ad5e>] __lock_acquire+0x7ce/0x1e10
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff8157124b>] _raw_spin_lock_bh+0x3b/0x70
[<ffffffff81531e9f>] mld_ifc_timer_expire+0xff/0x280
[<ffffffff8106f2a9>] run_timer_softirq+0x179/0x3f0
[<ffffffff810666d0>] __do_softirq+0xc0/0x210
[<ffffffff8157b3dc>] call_softirq+0x1c/0x30
[<ffffffff8100d42d>] do_softirq+0xad/0xe0
[<ffffffff81066afe>] irq_exit+0x9e/0xb0
[<ffffffff8157bd40>] smp_apic_timer_interrupt+0x70/0x9b
[<ffffffff8157ab93>] apic_timer_interrupt+0x13/0x20
[<ffffffff8149d857>] rt_do_flush+0x87/0x2a0
[<ffffffff814a16b6>] rt_cache_flush+0x46/0x60
[<ffffffff814e36e0>] fib_disable_ip+0x40/0x60
[<ffffffff814e5447>] fib_inetaddr_event+0xd7/0xe0
[<ffffffff81575c1c>] notifier_call_chain+0x8c/0xc0
[<ffffffff810896e8>] __blocking_notifier_call_chain+0x78/0xb0
[<ffffffff81089736>] blocking_notifier_call_chain+0x16/0x20
[<ffffffff814d8021>] __inet_del_ifa+0xf1/0x2e0
[<ffffffff814d8223>] inet_del_ifa+0x13/0x20
[<ffffffff814da731>] devinet_ioctl+0x501/0x800
[<ffffffff814db508>] inet_ioctl+0x88/0xa0
[<ffffffff814541f0>] sock_do_ioctl+0x30/0x70
[<ffffffff814542a9>] sock_ioctl+0x79/0x2f0
[<ffffffff81188798>] do_vfs_ioctl+0x98/0x570
[<ffffffff81188d01>] sys_ioctl+0x91/0xa0
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
stack backtrace:
Pid: 567, comm: ifconfig Not tainted 2.6.39-rc6+ #1
Call Trace:
<IRQ> [<ffffffff810996f6>] print_irq_inversion_bug+0x146/0x170
[<ffffffff81099720>] ? print_irq_inversion_bug+0x170/0x170
[<ffffffff810997bc>] check_usage_forwards+0x9c/0x110
[<ffffffff8109a32c>] mark_lock+0x19c/0x400
[<ffffffff8109ad5e>] __lock_acquire+0x7ce/0x1e10
[<ffffffff8109a383>] ? mark_lock+0x1f3/0x400
[<ffffffff8109b497>] ? __lock_acquire+0xf07/0x1e10
[<ffffffff81012255>] ? native_sched_clock+0x15/0x70
[<ffffffff8109ca4d>] lock_acquire+0x9d/0x130
[<ffffffff81531e9f>] ? mld_ifc_timer_expire+0xff/0x280
[<ffffffff8109759d>] ? lock_release_holdtime+0x3d/0x1a0
[<ffffffff8157124b>] _raw_spin_lock_bh+0x3b/0x70
[<ffffffff81531e9f>] ? mld_ifc_timer_expire+0xff/0x280
[<ffffffff8157170b>] ? _raw_spin_unlock+0x2b/0x40
[<ffffffff81531e9f>] mld_ifc_timer_expire+0xff/0x280
[<ffffffff8106f2a9>] run_timer_softirq+0x179/0x3f0
[<ffffffff8106f21b>] ? run_timer_softirq+0xeb/0x3f0
[<ffffffff810122b9>] ? sched_clock+0x9/0x10
[<ffffffff81531da0>] ? mld_gq_timer_expire+0x30/0x30
[<ffffffff810666d0>] __do_softirq+0xc0/0x210
[<ffffffff8109455f>] ? tick_program_event+0x1f/0x30
[<ffffffff8157b3dc>] call_softirq+0x1c/0x30
[<ffffffff8100d42d>] do_softirq+0xad/0xe0
[<ffffffff81066afe>] irq_exit+0x9e/0xb0
[<ffffffff8157bd40>] smp_apic_timer_interrupt+0x70/0x9b
[<ffffffff8157ab93>] apic_timer_interrupt+0x13/0x20
<EOI> [<ffffffff81571f14>] ? retint_restore_args+0x13/0x13
[<ffffffff810974a7>] ? lock_is_held+0x17/0xd0
[<ffffffff8149d857>] rt_do_flush+0x87/0x2a0
[<ffffffff814a16b6>] rt_cache_flush+0x46/0x60
[<ffffffff814e36e0>] fib_disable_ip+0x40/0x60
[<ffffffff814e5447>] fib_inetaddr_event+0xd7/0xe0
[<ffffffff81575c1c>] notifier_call_chain+0x8c/0xc0
[<ffffffff810896e8>] __blocking_notifier_call_chain+0x78/0xb0
[<ffffffff81089736>] blocking_notifier_call_chain+0x16/0x20
[<ffffffff814d8021>] __inet_del_ifa+0xf1/0x2e0
[<ffffffff814d8223>] inet_del_ifa+0x13/0x20
[<ffffffff814da731>] devinet_ioctl+0x501/0x800
[<ffffffff8108a3af>] ? local_clock+0x6f/0x80
[<ffffffff81575898>] ? do_page_fault+0x268/0x560
[<ffffffff814db508>] inet_ioctl+0x88/0xa0
[<ffffffff814541f0>] sock_do_ioctl+0x30/0x70
[<ffffffff814542a9>] sock_ioctl+0x79/0x2f0
[<ffffffff810dfe87>] ? __call_rcu+0xa7/0x190
[<ffffffff81188798>] do_vfs_ioctl+0x98/0x570
[<ffffffff8117737e>] ? fget_light+0x33e/0x430
[<ffffffff81571ef9>] ? retint_swapgs+0x13/0x1b
[<ffffffff81188d01>] sys_ioctl+0x91/0xa0
[<ffffffff8157a142>] system_call_fastpath+0x16/0x1b
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Shreyas N Bhatewara <sbhatewara@vmware.com>
Signed-off-by: Scott J. Goldman <scottjg@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 0d47c3a0530..c16ed961153 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -178,6 +178,7 @@ static void
vmxnet3_process_events(struct vmxnet3_adapter *adapter)
{
int i;
+ unsigned long flags;
u32 events = le32_to_cpu(adapter->shared->ecr);
if (!events)
return;
@@ -190,10 +191,10 @@ vmxnet3_process_events(struct vmxnet3_adapter *adapter)
/* Check if there is an error on xmit/recv queues */
if (events & (VMXNET3_ECR_TQERR | VMXNET3_ECR_RQERR)) {
- spin_lock(&adapter->cmd_lock);
+ spin_lock_irqsave(&adapter->cmd_lock, flags);
VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
VMXNET3_CMD_GET_QUEUE_STATUS);
- spin_unlock(&adapter->cmd_lock);
+ spin_unlock_irqrestore(&adapter->cmd_lock, flags);
for (i = 0; i < adapter->num_tx_queues; i++)
if (adapter->tqd_start[i].status.stopped)
@@ -2733,13 +2734,14 @@ static void
vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
{
u32 cfg;
+ unsigned long flags;
/* intr settings */
- spin_lock(&adapter->cmd_lock);
+ spin_lock_irqsave(&adapter->cmd_lock, flags);
VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
VMXNET3_CMD_GET_CONF_INTR);
cfg = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
- spin_unlock(&adapter->cmd_lock);
+ spin_unlock_irqrestore(&adapter->cmd_lock, flags);
adapter->intr.type = cfg & 0x3;
adapter->intr.mask_mode = (cfg >> 2) & 0x3;
--
cgit v1.2.3-18-g5258
From 9c412942a0bb19ba18f7bd939d42eff1e132a901 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Tue, 3 May 2011 07:49:25 +0000
Subject: ipheth: Properly distinguish length and alignment in URBs and skbs
The USB protocol this driver implements appears to require 2 bytes of
padding in front of each received packet. This used to be equal to
the value of NET_IP_ALIGN on x86, so the driver abused that constant
and mostly worked, but this is no longer the case. The driver also
mixed up the URB and packet lengths, resulting in 2 bytes of junk at
the end of the skb.
Introduce a private constant for the 2 bytes of padding; fix this
confusion and check for the under-length case.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/usb/ipheth.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 7d42f9a2c06..81126ff85e0 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -65,6 +65,7 @@
#define IPHETH_USBINTF_PROTO 1
#define IPHETH_BUF_SIZE 1516
+#define IPHETH_IP_ALIGN 2 /* padding at front of URB */
#define IPHETH_TX_TIMEOUT (5 * HZ)
#define IPHETH_INTFNUM 2
@@ -202,18 +203,21 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
return;
}
- len = urb->actual_length;
- buf = urb->transfer_buffer;
+ if (urb->actual_length <= IPHETH_IP_ALIGN) {
+ dev->net->stats.rx_length_errors++;
+ return;
+ }
+ len = urb->actual_length - IPHETH_IP_ALIGN;
+ buf = urb->transfer_buffer + IPHETH_IP_ALIGN;
- skb = dev_alloc_skb(NET_IP_ALIGN + len);
+ skb = dev_alloc_skb(len);
if (!skb) {
err("%s: dev_alloc_skb: -ENOMEM", __func__);
dev->net->stats.rx_dropped++;
return;
}
- skb_reserve(skb, NET_IP_ALIGN);
- memcpy(skb_put(skb, len), buf + NET_IP_ALIGN, len - NET_IP_ALIGN);
+ memcpy(skb_put(skb, len), buf, len);
skb->dev = dev->net;
skb->protocol = eth_type_trans(skb, dev->net);
--
cgit v1.2.3-18-g5258
From b9f47a3aaeabdce3b42829bbb27765fa340f76ba Mon Sep 17 00:00:00 2001
From: stephen hemminger <shemminger@vyatta.com>
Date: Wed, 4 May 2011 10:04:56 +0000
Subject: tcp_cubic: limit delayed_ack ratio to prevent divide error
TCP Cubic keeps a metric that estimates the amount of delayed
acknowledgements to use in adjusting the window. If an abnormally
large number of packets are acknowledged at once, then the update
could wrap and reach zero. This kind of ACK could only
happen when there was a large window and huge number of
ACK's were lost.
This patch limits the value of delayed ack ratio. The choice of 32
is just a conservative value since normally it should be range of
1 to 4 packets.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp_cubic.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 34340c9c95f..f376b05cca8 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -93,6 +93,7 @@ struct bictcp {
u32 ack_cnt; /* number of acks */
u32 tcp_cwnd; /* estimated tcp cwnd */
#define ACK_RATIO_SHIFT 4
+#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT)
u16 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */
u8 sample_cnt; /* number of samples to decide curr_rtt */
u8 found; /* the exit point is found? */
@@ -398,8 +399,12 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
u32 delay;
if (icsk->icsk_ca_state == TCP_CA_Open) {
- cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
- ca->delayed_ack += cnt;
+ u32 ratio = ca->delayed_ack;
+
+ ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
+ ratio += cnt;
+
+ ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT);
}
/* Some calls are for duplicates without timetamps */
--
cgit v1.2.3-18-g5258
From dcbe14b91a920657ff3a9ba0efb7c5b5562f956a Mon Sep 17 00:00:00 2001
From: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Date: Wed, 4 May 2011 13:05:11 +0000
Subject: ehea: fix wrongly reported speed and port
Currently EHEA reports to ethtool as supporting 10M, 100M, 1G and
10G and connected to FIBRE independent of the hardware configuration.
However, when connected to FIBRE the only supported speed is 10G
full-duplex, and the other speeds and modes are only supported
when connected to twisted pair.
Signed-off-by: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Acked-by: Breno Leitao <leitao@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ehea/ehea_ethtool.c | 21 +++++++++++++--------
1 file changed, 13 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ehea/ehea_ethtool.c b/drivers/net/ehea/ehea_ethtool.c
index 3e2e734fecb..f3bbdcef338 100644
--- a/drivers/net/ehea/ehea_ethtool.c
+++ b/drivers/net/ehea/ehea_ethtool.c
@@ -55,15 +55,20 @@ static int ehea_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
cmd->duplex = -1;
}
- cmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_1000baseT_Full
- | SUPPORTED_100baseT_Full | SUPPORTED_100baseT_Half
- | SUPPORTED_10baseT_Full | SUPPORTED_10baseT_Half
- | SUPPORTED_Autoneg | SUPPORTED_FIBRE);
-
- cmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_Autoneg
- | ADVERTISED_FIBRE);
+ if (cmd->speed == SPEED_10000) {
+ cmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
+ cmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
+ cmd->port = PORT_FIBRE;
+ } else {
+ cmd->supported = (SUPPORTED_1000baseT_Full | SUPPORTED_100baseT_Full
+ | SUPPORTED_100baseT_Half | SUPPORTED_10baseT_Full
+ | SUPPORTED_10baseT_Half | SUPPORTED_Autoneg
+ | SUPPORTED_TP);
+ cmd->advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg
+ | ADVERTISED_TP);
+ cmd->port = PORT_TP;
+ }
- cmd->port = PORT_FIBRE;
cmd->autoneg = port->autoneg == 1 ? AUTONEG_ENABLE : AUTONEG_DISABLE;
return 0;
--
cgit v1.2.3-18-g5258
From 6709d9521df05c105343473ab8b147e2ef1e13d8 Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@emulex.com>
Date: Wed, 4 May 2011 22:40:46 +0000
Subject: be2net: Fixed bugs related to PVID.
Fixed bug to make sure 'pvid' retrieval will work on big endian hosts.
Fixed incorrect comparison between the Rx Completion's 16-bit VLAN TCI
and the PVID. Now comparing only the relevant 12 bits corresponding to
the VID.
Renamed 'vid' field under Rx Completion to 'vlan_tag' to reflect
accurate description.
Signed-off-by: Somnath Kotur <somnath.kotur@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/benet/be.h | 2 +-
drivers/net/benet/be_cmds.c | 2 +-
drivers/net/benet/be_main.c | 18 ++++++++++++------
3 files changed, 14 insertions(+), 8 deletions(-)
diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h
index 66823eded7a..2353eca3259 100644
--- a/drivers/net/benet/be.h
+++ b/drivers/net/benet/be.h
@@ -213,7 +213,7 @@ struct be_rx_stats {
struct be_rx_compl_info {
u32 rss_hash;
- u16 vid;
+ u16 vlan_tag;
u16 pkt_size;
u16 rxq_idx;
u16 mac_id;
diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c
index 1e2d825bb94..9dc9394fd4c 100644
--- a/drivers/net/benet/be_cmds.c
+++ b/drivers/net/benet/be_cmds.c
@@ -132,7 +132,7 @@ static void be_async_grp5_pvid_state_process(struct be_adapter *adapter,
struct be_async_event_grp5_pvid_state *evt)
{
if (evt->enabled)
- adapter->pvid = evt->tag;
+ adapter->pvid = le16_to_cpu(evt->tag);
else
adapter->pvid = 0;
}
diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c
index 02a0443d182..9187fb4e08f 100644
--- a/drivers/net/benet/be_main.c
+++ b/drivers/net/benet/be_main.c
@@ -1018,7 +1018,8 @@ static void be_rx_compl_process(struct be_adapter *adapter,
kfree_skb(skb);
return;
}
- vlan_hwaccel_receive_skb(skb, adapter->vlan_grp, rxcp->vid);
+ vlan_hwaccel_receive_skb(skb, adapter->vlan_grp,
+ rxcp->vlan_tag);
} else {
netif_receive_skb(skb);
}
@@ -1076,7 +1077,8 @@ static void be_rx_compl_process_gro(struct be_adapter *adapter,
if (likely(!rxcp->vlanf))
napi_gro_frags(&eq_obj->napi);
else
- vlan_gro_frags(&eq_obj->napi, adapter->vlan_grp, rxcp->vid);
+ vlan_gro_frags(&eq_obj->napi, adapter->vlan_grp,
+ rxcp->vlan_tag);
}
static void be_parse_rx_compl_v1(struct be_adapter *adapter,
@@ -1102,7 +1104,8 @@ static void be_parse_rx_compl_v1(struct be_adapter *adapter,
rxcp->pkt_type =
AMAP_GET_BITS(struct amap_eth_rx_compl_v1, cast_enc, compl);
rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vtm, compl);
- rxcp->vid = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vlan_tag, compl);
+ rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vlan_tag,
+ compl);
}
static void be_parse_rx_compl_v0(struct be_adapter *adapter,
@@ -1128,7 +1131,8 @@ static void be_parse_rx_compl_v0(struct be_adapter *adapter,
rxcp->pkt_type =
AMAP_GET_BITS(struct amap_eth_rx_compl_v0, cast_enc, compl);
rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vtm, compl);
- rxcp->vid = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vlan_tag, compl);
+ rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vlan_tag,
+ compl);
}
static struct be_rx_compl_info *be_rx_compl_get(struct be_rx_obj *rxo)
@@ -1155,9 +1159,11 @@ static struct be_rx_compl_info *be_rx_compl_get(struct be_rx_obj *rxo)
rxcp->vlanf = 0;
if (!lancer_chip(adapter))
- rxcp->vid = swab16(rxcp->vid);
+ rxcp->vlan_tag = swab16(rxcp->vlan_tag);
- if ((adapter->pvid == rxcp->vid) && !adapter->vlan_tag[rxcp->vid])
+ if (((adapter->pvid & VLAN_VID_MASK) ==
+ (rxcp->vlan_tag & VLAN_VID_MASK)) &&
+ !adapter->vlan_tag[rxcp->vlan_tag])
rxcp->vlanf = 0;
/* As the compl has been parsed, reset it; we wont touch it again */
--
cgit v1.2.3-18-g5258
From 057bef938896e6266ae24ec4266d24792d27c29a Mon Sep 17 00:00:00 2001
From: Matvejchikov Ilya <matvejchikov@gmail.com>
Date: Fri, 6 May 2011 06:23:09 +0000
Subject: NET: slip, fix ldisc->open retval
TTY layer expects 0 if the ldisc->open operation succeeded.
Signed-off-by : Matvejchikov Ilya <matvejchikov@gmail.com>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/slip.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/slip.c b/drivers/net/slip.c
index 86cbb9ea2f2..8ec1a9a0bb9 100644
--- a/drivers/net/slip.c
+++ b/drivers/net/slip.c
@@ -853,7 +853,9 @@ static int slip_open(struct tty_struct *tty)
/* Done. We have linked the TTY line to a channel. */
rtnl_unlock();
tty->receive_room = 65536; /* We don't flow control */
- return sl->dev->base_addr;
+
+ /* TTY layer expects 0 on success */
+ return 0;
err_free_bufs:
sl_free_bufs(sl);
--
cgit v1.2.3-18-g5258
From ce3dad0f74e6b240f0b1dedbd8ea268a3f298d82 Mon Sep 17 00:00:00 2001
From: Toshiharu Okada <toshiharu-linux@dsn.okisemi.com>
Date: Fri, 6 May 2011 02:53:51 +0000
Subject: PCH_GbE : Fixed the issue of collision detection
The collision detection setting was invalid.
When collision occurred, because data was not resent,
there was an issue to which a transmitting throughput falls.
This patch enables the collision detection.
Signed-off-by: Toshiharu Okada <toshiharu-linux@dsn.okisemi.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/pch_gbe/pch_gbe_main.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/pch_gbe/pch_gbe_main.c b/drivers/net/pch_gbe/pch_gbe_main.c
index 2ef2f9cdefa..4ebd1d4ad3e 100644
--- a/drivers/net/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/pch_gbe/pch_gbe_main.c
@@ -43,8 +43,7 @@ const char pch_driver_version[] = DRV_VERSION;
#define PCH_GBE_MAC_RGMII_CTRL_SETTING ( \
PCH_GBE_CHIP_TYPE_INTERNAL | \
- PCH_GBE_RGMII_MODE_RGMII | \
- PCH_GBE_CRS_SEL \
+ PCH_GBE_RGMII_MODE_RGMII \
)
/* Ethertype field values */
--
cgit v1.2.3-18-g5258
From 5d05a04d283061b586e8dc819cfa6f4b8cfd5948 Mon Sep 17 00:00:00 2001
From: Toshiharu Okada <toshiharu-linux@dsn.okisemi.com>
Date: Fri, 6 May 2011 02:53:56 +0000
Subject: PCH_GbE : Fixed the issue of checksum judgment
The checksum judgment was mistaken.
Judgment result
0:Correct 1:Wrong
This patch fixes the issue.
Signed-off-by: Toshiharu Okada <toshiharu-linux@dsn.okisemi.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/pch_gbe/pch_gbe_main.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/net/pch_gbe/pch_gbe_main.c b/drivers/net/pch_gbe/pch_gbe_main.c
index 4ebd1d4ad3e..9f6c4025c6e 100644
--- a/drivers/net/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/pch_gbe/pch_gbe_main.c
@@ -1493,12 +1493,11 @@ pch_gbe_clean_rx(struct pch_gbe_adapter *adapter,
/* Write meta date of skb */
skb_put(skb, length);
skb->protocol = eth_type_trans(skb, netdev);
- if ((tcp_ip_status & PCH_GBE_RXD_ACC_STAT_TCPIPOK) ==
- PCH_GBE_RXD_ACC_STAT_TCPIPOK) {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- } else {
+ if (tcp_ip_status & PCH_GBE_RXD_ACC_STAT_TCPIPOK)
skb->ip_summed = CHECKSUM_NONE;
- }
+ else
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
napi_gro_receive(&adapter->napi, skb);
(*work_done)++;
pr_debug("Receive skb->ip_summed: %d length: %d\n",
--
cgit v1.2.3-18-g5258
From b0e6baf5619a6fa3eaf43b55fdb4daa362c3c916 Mon Sep 17 00:00:00 2001
From: Tomoya <tomoya-linux@dsn.okisemi.com>
Date: Mon, 9 May 2011 01:19:37 +0000
Subject: pch_gbe: support ML7223 IOH
Support new device OKI SEMICONDUCTOR ML7223 IOH(Input/Output Hub).
The ML7223 IOH is for MP(Media Phone) use.
The ML7223 is companion chip for Intel Atom E6xx series.
The ML7223 is completely compatible for Intel EG20T PCH.
Signed-off-by: Tomoya MORINAGA <tomoya-linux@dsn.okisemi.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/Kconfig | 8 +++++++-
drivers/net/pch_gbe/pch_gbe_main.c | 11 +++++++++++
2 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index dc280bc8eba..6c884ef1b06 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2536,7 +2536,7 @@ config S6GMAC
source "drivers/net/stmmac/Kconfig"
config PCH_GBE
- tristate "PCH Gigabit Ethernet"
+ tristate "Intel EG20T PCH / OKI SEMICONDUCTOR ML7223 IOH GbE"
depends on PCI
select MII
---help---
@@ -2548,6 +2548,12 @@ config PCH_GBE
to Gigabit Ethernet.
This driver enables Gigabit Ethernet function.
+ This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
+ Output Hub), ML7223.
+ ML7223 IOH is for MP(Media Phone) use.
+ ML7223 is companion chip for Intel Atom E6xx series.
+ ML7223 is completely compatible for Intel EG20T PCH.
+
endif # NETDEV_1000
#
diff --git a/drivers/net/pch_gbe/pch_gbe_main.c b/drivers/net/pch_gbe/pch_gbe_main.c
index 9f6c4025c6e..56d049a472d 100644
--- a/drivers/net/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/pch_gbe/pch_gbe_main.c
@@ -34,6 +34,10 @@ const char pch_driver_version[] = DRV_VERSION;
#define PCH_GBE_COPYBREAK_DEFAULT 256
#define PCH_GBE_PCI_BAR 1
+/* Macros for ML7223 */
+#define PCI_VENDOR_ID_ROHM 0x10db
+#define PCI_DEVICE_ID_ROHM_ML7223_GBE 0x8013
+
#define PCH_GBE_TX_WEIGHT 64
#define PCH_GBE_RX_WEIGHT 64
#define PCH_GBE_RX_BUFFER_WRITE 16
@@ -2418,6 +2422,13 @@ static DEFINE_PCI_DEVICE_TABLE(pch_gbe_pcidev_id) = {
.class = (PCI_CLASS_NETWORK_ETHERNET << 8),
.class_mask = (0xFFFF00)
},
+ {.vendor = PCI_VENDOR_ID_ROHM,
+ .device = PCI_DEVICE_ID_ROHM_ML7223_GBE,
+ .subvendor = PCI_ANY_ID,
+ .subdevice = PCI_ANY_ID,
+ .class = (PCI_CLASS_NETWORK_ETHERNET << 8),
+ .class_mask = (0xFFFF00)
+ },
/* required last entry */
{0}
};
--
cgit v1.2.3-18-g5258
From 315c34dae0069d0c67abd714bb846cd466289c7f Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 21 Apr 2011 10:55:07 +0200
Subject: netfilter: ctnetlink: fix timestamp support for new conntracks
This patch fixes the missing initialization of the start time if
the timestamp support is enabled.
libnetfilter_conntrack/utils# conntrack -E &
libnetfilter_conntrack/utils# ./conntrack_create
tcp 6 109 ESTABLISHED src=1.1.1.1 dst=2.2.2.2 sport=1025 dport=21 packets=0 bytes=0 [UNREPLIED] src=2.2.2.2 dst=1.1.1.1 sport=21 dport=1025 packets=0 bytes=0 mark=0 delta-time=1303296401 use=2
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
net/netfilter/nf_conntrack_netlink.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 30bf8a167fc..482e90c6185 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1334,6 +1334,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
struct nf_conn *ct;
int err = -EINVAL;
struct nf_conntrack_helper *helper;
+ struct nf_conn_tstamp *tstamp;
ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC);
if (IS_ERR(ct))
@@ -1451,6 +1452,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
__set_bit(IPS_EXPECTED_BIT, &ct->status);
ct->master = master_ct;
}
+ tstamp = nf_conn_tstamp_find(ct);
+ if (tstamp)
+ tstamp->start = ktime_to_ns(ktime_get_real());
add_timer(&ct->timeout);
nf_conntrack_hash_insert(ct);
--
cgit v1.2.3-18-g5258
From 5a6351eecf8c87afed9c883bb6341d09406d74ba Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 21 Apr 2011 10:57:21 +0200
Subject: netfilter: fix ebtables compat support
commit 255d0dc34068a976 (netfilter: x_table: speedup compat operations)
made ebtables not working anymore.
1) xt_compat_calc_jump() is not an exact match lookup
2) compat_table_info() has a typo in xt_compat_init_offsets() call
3) compat_do_replace() misses a xt_compat_init_offsets() call
Reported-by: dann frazier <dannf@dannf.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
net/bridge/netfilter/ebtables.c | 3 ++-
net/netfilter/x_tables.c | 4 ++--
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 893669caa8d..9707079bc40 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1766,7 +1766,7 @@ static int compat_table_info(const struct ebt_table_info *info,
newinfo->entries_size = size;
- xt_compat_init_offsets(AF_INET, info->nentries);
+ xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries);
return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
entries, newinfo);
}
@@ -2240,6 +2240,7 @@ static int compat_do_replace(struct net *net, void __user *user,
xt_compat_lock(NFPROTO_BRIDGE);
+ xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
if (ret < 0)
goto out_unlock;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index a9adf4c6b29..8a025a585d2 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -455,6 +455,7 @@ void xt_compat_flush_offsets(u_int8_t af)
vfree(xt[af].compat_tab);
xt[af].compat_tab = NULL;
xt[af].number = 0;
+ xt[af].cur = 0;
}
}
EXPORT_SYMBOL_GPL(xt_compat_flush_offsets);
@@ -473,8 +474,7 @@ int xt_compat_calc_jump(u_int8_t af, unsigned int offset)
else
return mid ? tmp[mid - 1].delta : 0;
}
- WARN_ON_ONCE(1);
- return 0;
+ return left ? tmp[left - 1].delta : 0;
}
EXPORT_SYMBOL_GPL(xt_compat_calc_jump);
--
cgit v1.2.3-18-g5258
From 103a9778e07bcc0cd34b5c35a87281454eec719e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 21 Apr 2011 10:58:25 +0200
Subject: netfilter: ebtables: only call xt_compat_add_offset once per rule
The optimizations in commit 255d0dc34068a976
(netfilter: x_table: speedup compat operations) assume that
xt_compat_add_offset is called once per rule.
ebtables however called it for each match/target found in a rule.
The match/watcher/target parser already returns the needed delta, so it
is sufficient to move the xt_compat_add_offset call to a more reasonable
location.
While at it, also get rid of the unused COMPAT iterator macros.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
net/bridge/netfilter/ebtables.c | 61 ++++++-----------------------------------
1 file changed, 9 insertions(+), 52 deletions(-)
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 9707079bc40..1a92b369c82 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1882,7 +1882,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt,
struct xt_match *match;
struct xt_target *wt;
void *dst = NULL;
- int off, pad = 0, ret = 0;
+ int off, pad = 0;
unsigned int size_kern, entry_offset, match_size = mwt->match_size;
strlcpy(name, mwt->u.name, sizeof(name));
@@ -1935,13 +1935,6 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt,
break;
}
- if (!dst) {
- ret = xt_compat_add_offset(NFPROTO_BRIDGE, entry_offset,
- off + ebt_compat_entry_padsize());
- if (ret < 0)
- return ret;
- }
-
state->buf_kern_offset += match_size + off;
state->buf_user_offset += match_size;
pad = XT_ALIGN(size_kern) - size_kern;
@@ -2016,50 +2009,6 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32,
return growth;
}
-#define EBT_COMPAT_WATCHER_ITERATE(e, fn, args...) \
-({ \
- unsigned int __i; \
- int __ret = 0; \
- struct compat_ebt_entry_mwt *__watcher; \
- \
- for (__i = e->watchers_offset; \
- __i < (e)->target_offset; \
- __i += __watcher->watcher_size + \
- sizeof(struct compat_ebt_entry_mwt)) { \
- __watcher = (void *)(e) + __i; \
- __ret = fn(__watcher , ## args); \
- if (__ret != 0) \
- break; \
- } \
- if (__ret == 0) { \
- if (__i != (e)->target_offset) \
- __ret = -EINVAL; \
- } \
- __ret; \
-})
-
-#define EBT_COMPAT_MATCH_ITERATE(e, fn, args...) \
-({ \
- unsigned int __i; \
- int __ret = 0; \
- struct compat_ebt_entry_mwt *__match; \
- \
- for (__i = sizeof(struct ebt_entry); \
- __i < (e)->watchers_offset; \
- __i += __match->match_size + \
- sizeof(struct compat_ebt_entry_mwt)) { \
- __match = (void *)(e) + __i; \
- __ret = fn(__match , ## args); \
- if (__ret != 0) \
- break; \
- } \
- if (__ret == 0) { \
- if (__i != (e)->watchers_offset) \
- __ret = -EINVAL; \
- } \
- __ret; \
-})
-
/* called for all ebt_entry structures. */
static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base,
unsigned int *total,
@@ -2132,6 +2081,14 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base,
}
}
+ if (state->buf_kern_start == NULL) {
+ unsigned int offset = buf_start - (char *) base;
+
+ ret = xt_compat_add_offset(NFPROTO_BRIDGE, offset, new_offset);
+ if (ret < 0)
+ return ret;
+ }
+
startoff = state->buf_user_offset - startoff;
BUG_ON(*total < startoff);
--
cgit v1.2.3-18-g5258
From 1ae132b0347907ac95b8bc9dba37934f59d2a508 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans@schillstrom.com>
Date: Tue, 3 May 2011 22:09:30 +0200
Subject: IPVS: Change of socket usage to enable name space exit.
If the sync daemons run in a name space while it crashes
or get killed, there is no way to stop them except for a reboot.
When all patches are there, ip_vs_core will handle register_pernet_(),
i.e. ip_vs_sync_init() and ip_vs_sync_cleanup() will be removed.
Kernel threads should not increment the use count of a socket.
By calling sk_change_net() after creating a socket this is avoided.
sock_release cant be used intead sk_release_kernel() should be used.
Thanks Eric W Biederman for your advices.
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
[horms@verge.net.au: minor edit to changelog]
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_core.c | 2 +-
net/netfilter/ipvs/ip_vs_sync.c | 58 ++++++++++++++++++++++++++---------------
2 files changed, 38 insertions(+), 22 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 07accf6b240..a0791dc05a2 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1896,7 +1896,7 @@ static int __net_init __ip_vs_init(struct net *net)
static void __net_exit __ip_vs_cleanup(struct net *net)
{
- IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen);
+ IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen);
}
static struct pernet_operations ipvs_core_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3e7961e85e9..0cce9531082 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1303,13 +1303,18 @@ static struct socket *make_send_sock(struct net *net)
struct socket *sock;
int result;
- /* First create a socket */
- result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1);
+ /* First create a socket move it to right name space later */
+ result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
return ERR_PTR(result);
}
-
+ /*
+ * Kernel sockets that are a part of a namespace, should not
+ * hold a reference to a namespace in order to allow to stop it.
+ * After sk_change_net should be released using sk_release_kernel.
+ */
+ sk_change_net(sock->sk, net);
result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn);
if (result < 0) {
pr_err("Error setting outbound mcast interface\n");
@@ -1334,8 +1339,8 @@ static struct socket *make_send_sock(struct net *net)
return sock;
- error:
- sock_release(sock);
+error:
+ sk_release_kernel(sock->sk);
return ERR_PTR(result);
}
@@ -1350,12 +1355,17 @@ static struct socket *make_receive_sock(struct net *net)
int result;
/* First create a socket */
- result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1);
+ result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
return ERR_PTR(result);
}
-
+ /*
+ * Kernel sockets that are a part of a namespace, should not
+ * hold a reference to a namespace in order to allow to stop it.
+ * After sk_change_net should be released using sk_release_kernel.
+ */
+ sk_change_net(sock->sk, net);
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = 1;
@@ -1377,8 +1387,8 @@ static struct socket *make_receive_sock(struct net *net)
return sock;
- error:
- sock_release(sock);
+error:
+ sk_release_kernel(sock->sk);
return ERR_PTR(result);
}
@@ -1473,7 +1483,7 @@ static int sync_thread_master(void *data)
ip_vs_sync_buff_release(sb);
/* release the sending multicast socket */
- sock_release(tinfo->sock);
+ sk_release_kernel(tinfo->sock->sk);
kfree(tinfo);
return 0;
@@ -1513,7 +1523,7 @@ static int sync_thread_backup(void *data)
}
/* release the sending multicast socket */
- sock_release(tinfo->sock);
+ sk_release_kernel(tinfo->sock->sk);
kfree(tinfo->buf);
kfree(tinfo);
@@ -1601,7 +1611,7 @@ outtinfo:
outbuf:
kfree(buf);
outsocket:
- sock_release(sock);
+ sk_release_kernel(sock->sk);
out:
return result;
}
@@ -1610,6 +1620,7 @@ out:
int stop_sync_thread(struct net *net, int state)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ int retc = -EINVAL;
IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
@@ -1629,7 +1640,7 @@ int stop_sync_thread(struct net *net, int state)
spin_lock_bh(&ipvs->sync_lock);
ipvs->sync_state &= ~IP_VS_STATE_MASTER;
spin_unlock_bh(&ipvs->sync_lock);
- kthread_stop(ipvs->master_thread);
+ retc = kthread_stop(ipvs->master_thread);
ipvs->master_thread = NULL;
} else if (state == IP_VS_STATE_BACKUP) {
if (!ipvs->backup_thread)
@@ -1639,16 +1650,14 @@ int stop_sync_thread(struct net *net, int state)
task_pid_nr(ipvs->backup_thread));
ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
- kthread_stop(ipvs->backup_thread);
+ retc = kthread_stop(ipvs->backup_thread);
ipvs->backup_thread = NULL;
- } else {
- return -EINVAL;
}
/* decrease the module use count */
ip_vs_use_count_dec();
- return 0;
+ return retc;
}
/*
@@ -1670,8 +1679,15 @@ static int __net_init __ip_vs_sync_init(struct net *net)
static void __ip_vs_sync_cleanup(struct net *net)
{
- stop_sync_thread(net, IP_VS_STATE_MASTER);
- stop_sync_thread(net, IP_VS_STATE_BACKUP);
+ int retc;
+
+ retc = stop_sync_thread(net, IP_VS_STATE_MASTER);
+ if (retc && retc != -ESRCH)
+ pr_err("Failed to stop Master Daemon\n");
+
+ retc = stop_sync_thread(net, IP_VS_STATE_BACKUP);
+ if (retc && retc != -ESRCH)
+ pr_err("Failed to stop Backup Daemon\n");
}
static struct pernet_operations ipvs_sync_ops = {
@@ -1682,10 +1698,10 @@ static struct pernet_operations ipvs_sync_ops = {
int __init ip_vs_sync_init(void)
{
- return register_pernet_subsys(&ipvs_sync_ops);
+ return register_pernet_device(&ipvs_sync_ops);
}
void ip_vs_sync_cleanup(void)
{
- unregister_pernet_subsys(&ipvs_sync_ops);
+ unregister_pernet_device(&ipvs_sync_ops);
}
--
cgit v1.2.3-18-g5258
From 7a4f0761fce32ff4918a7c23b08db564ad33092d Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans@schillstrom.com>
Date: Tue, 3 May 2011 22:09:31 +0200
Subject: IPVS: init and cleanup restructuring
DESCRIPTION
This patch tries to restore the initial init and cleanup
sequences that was before namspace patch.
Netns also requires action when net devices unregister
which has never been implemented. I.e this patch also
covers when a device moves into a network namespace,
and has to be released.
IMPLEMENTATION
The number of calls to register_pernet_device have been
reduced to one for the ip_vs.ko
Schedulers still have their own calls.
This patch adds a function __ip_vs_service_cleanup()
and an enable flag for the netfilter hooks.
The nf hooks will be enabled when the first service is loaded
and never disabled again, except when a namespace exit starts.
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
[horms@verge.net.au: minor edit to changelog]
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 17 ++++++
net/netfilter/ipvs/ip_vs_app.c | 15 +----
net/netfilter/ipvs/ip_vs_conn.c | 12 +---
net/netfilter/ipvs/ip_vs_core.c | 101 +++++++++++++++++++++++++++++---
net/netfilter/ipvs/ip_vs_ctl.c | 120 ++++++++++++++++++++++++++++++++-------
net/netfilter/ipvs/ip_vs_est.c | 14 +----
net/netfilter/ipvs/ip_vs_proto.c | 11 +---
net/netfilter/ipvs/ip_vs_sync.c | 13 +----
8 files changed, 223 insertions(+), 80 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d516f00c8e0..86aefed6140 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -791,6 +791,7 @@ struct ip_vs_app {
/* IPVS in network namespace */
struct netns_ipvs {
int gen; /* Generation */
+ int enable; /* enable like nf_hooks do */
/*
* Hash table: for real service lookups
*/
@@ -1089,6 +1090,22 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
atomic_inc(&ctl_cp->n_control);
}
+/*
+ * IPVS netns init & cleanup functions
+ */
+extern int __ip_vs_estimator_init(struct net *net);
+extern int __ip_vs_control_init(struct net *net);
+extern int __ip_vs_protocol_init(struct net *net);
+extern int __ip_vs_app_init(struct net *net);
+extern int __ip_vs_conn_init(struct net *net);
+extern int __ip_vs_sync_init(struct net *net);
+extern void __ip_vs_conn_cleanup(struct net *net);
+extern void __ip_vs_app_cleanup(struct net *net);
+extern void __ip_vs_protocol_cleanup(struct net *net);
+extern void __ip_vs_control_cleanup(struct net *net);
+extern void __ip_vs_estimator_cleanup(struct net *net);
+extern void __ip_vs_sync_cleanup(struct net *net);
+extern void __ip_vs_service_cleanup(struct net *net);
/*
* IPVS application functions
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 2dc6de13ac1..51f3af7c474 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -576,7 +576,7 @@ static const struct file_operations ip_vs_app_fops = {
};
#endif
-static int __net_init __ip_vs_app_init(struct net *net)
+int __net_init __ip_vs_app_init(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
@@ -585,26 +585,17 @@ static int __net_init __ip_vs_app_init(struct net *net)
return 0;
}
-static void __net_exit __ip_vs_app_cleanup(struct net *net)
+void __net_exit __ip_vs_app_cleanup(struct net *net)
{
proc_net_remove(net, "ip_vs_app");
}
-static struct pernet_operations ip_vs_app_ops = {
- .init = __ip_vs_app_init,
- .exit = __ip_vs_app_cleanup,
-};
-
int __init ip_vs_app_init(void)
{
- int rv;
-
- rv = register_pernet_subsys(&ip_vs_app_ops);
- return rv;
+ return 0;
}
void ip_vs_app_cleanup(void)
{
- unregister_pernet_subsys(&ip_vs_app_ops);
}
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index c97bd45975b..d3fd91bbba4 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1258,22 +1258,17 @@ int __net_init __ip_vs_conn_init(struct net *net)
return 0;
}
-static void __net_exit __ip_vs_conn_cleanup(struct net *net)
+void __net_exit __ip_vs_conn_cleanup(struct net *net)
{
/* flush all the connection entries first */
ip_vs_conn_flush(net);
proc_net_remove(net, "ip_vs_conn");
proc_net_remove(net, "ip_vs_conn_sync");
}
-static struct pernet_operations ipvs_conn_ops = {
- .init = __ip_vs_conn_init,
- .exit = __ip_vs_conn_cleanup,
-};
int __init ip_vs_conn_init(void)
{
int idx;
- int retc;
/* Compute size and mask */
ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
@@ -1309,17 +1304,14 @@ int __init ip_vs_conn_init(void)
rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
}
- retc = register_pernet_subsys(&ipvs_conn_ops);
-
/* calculate the random value for connection hash */
get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd));
- return retc;
+ return 0;
}
void ip_vs_conn_cleanup(void)
{
- unregister_pernet_subsys(&ipvs_conn_ops);
/* Release the empty cache */
kmem_cache_destroy(ip_vs_conn_cachep);
vfree(ip_vs_conn_tab);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index a0791dc05a2..a74dae6c5db 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1113,6 +1113,9 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
return NF_ACCEPT;
net = skb_net(skb);
+ if (!net_ipvs(net)->enable)
+ return NF_ACCEPT;
+
ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
@@ -1343,6 +1346,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
return NF_ACCEPT; /* The packet looks wrong, ignore */
net = skb_net(skb);
+
pd = ip_vs_proto_data_get(net, cih->protocol);
if (!pd)
return NF_ACCEPT;
@@ -1529,6 +1533,11 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
IP_VS_DBG_ADDR(af, &iph.daddr), hooknum);
return NF_ACCEPT;
}
+ /* ipvs enabled in this netns ? */
+ net = skb_net(skb);
+ if (!net_ipvs(net)->enable)
+ return NF_ACCEPT;
+
ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
/* Bad... Do not break raw sockets */
@@ -1562,7 +1571,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
}
- net = skb_net(skb);
/* Protocol supported? */
pd = ip_vs_proto_data_get(net, iph.protocol);
if (unlikely(!pd))
@@ -1588,7 +1596,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
}
IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
- net = skb_net(skb);
ipvs = net_ipvs(net);
/* Check the server status */
if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
@@ -1743,10 +1750,16 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
int (*okfn)(struct sk_buff *))
{
int r;
+ struct net *net;
if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
return NF_ACCEPT;
+ /* ipvs enabled in this netns ? */
+ net = skb_net(skb);
+ if (!net_ipvs(net)->enable)
+ return NF_ACCEPT;
+
return ip_vs_in_icmp(skb, &r, hooknum);
}
@@ -1757,10 +1770,16 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
int (*okfn)(struct sk_buff *))
{
int r;
+ struct net *net;
if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6)
return NF_ACCEPT;
+ /* ipvs enabled in this netns ? */
+ net = skb_net(skb);
+ if (!net_ipvs(net)->enable)
+ return NF_ACCEPT;
+
return ip_vs_in_icmp_v6(skb, &r, hooknum);
}
#endif
@@ -1884,21 +1903,72 @@ static int __net_init __ip_vs_init(struct net *net)
pr_err("%s(): no memory.\n", __func__);
return -ENOMEM;
}
+ /* Hold the beast until a service is registerd */
+ ipvs->enable = 0;
ipvs->net = net;
/* Counters used for creating unique names */
ipvs->gen = atomic_read(&ipvs_netns_cnt);
atomic_inc(&ipvs_netns_cnt);
net->ipvs = ipvs;