{pktgen, xfrm} Correct xfrm_state_lock usage in xfrm_stateonly_find

Acquiring xfrm_state_lock in process context is expected to turn BH off,
as this lock is also used in BH context, namely xfrm state timer handler.
Otherwise it surprises LOCKDEP with below messages.

[   81.422781] pktgen: Packet Generator for packet performance testing. Version: 2.74
[   81.725194]
[   81.725211] =========================================================
[   81.725212] [ INFO: possible irq lock inversion dependency detected ]
[   81.725215] 3.13.0-rc2+ #92 Not tainted
[   81.725216] ---------------------------------------------------------
[   81.725218] kpktgend_0/2780 just changed the state of lock:
[   81.725220]  (xfrm_state_lock){+.+...}, at: [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0
[   81.725231] but this lock was taken by another, SOFTIRQ-safe lock in the past:
[   81.725232]  (&(&x->lock)->rlock){+.-...}
[   81.725232]
[   81.725232] and interrupts could create inverse lock ordering between them.
[   81.725232]
[   81.725235]
[   81.725235] other info that might help us debug this:
[   81.725237]  Possible interrupt unsafe locking scenario:
[   81.725237]
[   81.725238]        CPU0                    CPU1
[   81.725240]        ----                    ----
[   81.725241]   lock(xfrm_state_lock);
[   81.725243]                                local_irq_disable();
[   81.725244]                                lock(&(&x->lock)->rlock);
[   81.725246]                                lock(xfrm_state_lock);
[   81.725248]   <Interrupt>
[   81.725249]     lock(&(&x->lock)->rlock);
[   81.725251]
[   81.725251]  *** DEADLOCK ***
[   81.725251]
[   81.725254] no locks held by kpktgend_0/2780.
[   81.725255]
[   81.725255] the shortest dependencies between 2nd lock and 1st lock:
[   81.725269]  -> (&(&x->lock)->rlock){+.-...} ops: 8 {
[   81.725274]     HARDIRQ-ON-W at:
[   81.725276]                       [<ffffffff8109a64b>] __lock_acquire+0x65b/0x1d70
[   81.725282]                       [<ffffffff8109c3c7>] lock_acquire+0x97/0x130
[   81.725284]                       [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70
[   81.725289]                       [<ffffffff816dc3a3>] xfrm_timer_handler+0x43/0x290
[   81.725292]                       [<ffffffff81059437>] __tasklet_hrtimer_trampoline+0x17/0x40
[   81.725300]                       [<ffffffff8105a1b7>] tasklet_hi_action+0xd7/0xf0
[   81.725303]                       [<ffffffff81059ac6>] __do_softirq+0xe6/0x2d0
[   81.725305]                       [<ffffffff8105a026>] irq_exit+0x96/0xc0
[   81.725308]                       [<ffffffff8177fd0a>] smp_apic_timer_interrupt+0x4a/0x60
[   81.725313]                       [<ffffffff8177e96f>] apic_timer_interrupt+0x6f/0x80
[   81.725316]                       [<ffffffff8100b7c6>] arch_cpu_idle+0x26/0x30
[   81.725329]                       [<ffffffff810ace28>] cpu_startup_entry+0x88/0x2b0
[   81.725333]                       [<ffffffff8102e5b0>] start_secondary+0x190/0x1f0
[   81.725338]     IN-SOFTIRQ-W at:
[   81.725340]                       [<ffffffff8109a61d>] __lock_acquire+0x62d/0x1d70
[   81.725342]                       [<ffffffff8109c3c7>] lock_acquire+0x97/0x130
[   81.725344]                       [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70
[   81.725347]                       [<ffffffff816dc3a3>] xfrm_timer_handler+0x43/0x290
[   81.725349]                       [<ffffffff81059437>] __tasklet_hrtimer_trampoline+0x17/0x40
[   81.725352]                       [<ffffffff8105a1b7>] tasklet_hi_action+0xd7/0xf0
[   81.725355]                       [<ffffffff81059ac6>] __do_softirq+0xe6/0x2d0
[   81.725358]                       [<ffffffff8105a026>] irq_exit+0x96/0xc0
[   81.725360]                       [<ffffffff8177fd0a>] smp_apic_timer_interrupt+0x4a/0x60
[   81.725363]                       [<ffffffff8177e96f>] apic_timer_interrupt+0x6f/0x80
[   81.725365]                       [<ffffffff8100b7c6>] arch_cpu_idle+0x26/0x30
[   81.725368]                       [<ffffffff810ace28>] cpu_startup_entry+0x88/0x2b0
[   81.725370]                       [<ffffffff8102e5b0>] start_secondary+0x190/0x1f0
[   81.725373]     INITIAL USE at:
[   81.725375]                      [<ffffffff8109a31a>] __lock_acquire+0x32a/0x1d70
[   81.725385]                      [<ffffffff8109c3c7>] lock_acquire+0x97/0x130
[   81.725388]                      [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70
[   81.725390]                      [<ffffffff816dc3a3>] xfrm_timer_handler+0x43/0x290
[   81.725394]                      [<ffffffff81059437>] __tasklet_hrtimer_trampoline+0x17/0x40
[   81.725398]                      [<ffffffff8105a1b7>] tasklet_hi_action+0xd7/0xf0
[   81.725401]                      [<ffffffff81059ac6>] __do_softirq+0xe6/0x2d0
[   81.725404]                      [<ffffffff8105a026>] irq_exit+0x96/0xc0
[   81.725407]                      [<ffffffff8177fd0a>] smp_apic_timer_interrupt+0x4a/0x60
[   81.725409]                      [<ffffffff8177e96f>] apic_timer_interrupt+0x6f/0x80
[   81.725412]                      [<ffffffff8100b7c6>] arch_cpu_idle+0x26/0x30
[   81.725415]                      [<ffffffff810ace28>] cpu_startup_entry+0x88/0x2b0
[   81.725417]                      [<ffffffff8102e5b0>] start_secondary+0x190/0x1f0
[   81.725420]   }
[   81.725421]   ... key      at: [<ffffffff8295b9c8>] __key.46349+0x0/0x8
[   81.725445]   ... acquired at:
[   81.725446]    [<ffffffff8109c3c7>] lock_acquire+0x97/0x130
[   81.725449]    [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70
[   81.725452]    [<ffffffff816dc057>] __xfrm_state_delete+0x37/0x140
[   81.725454]    [<ffffffff816dc18c>] xfrm_state_delete+0x2c/0x50
[   81.725456]    [<ffffffff816dc277>] xfrm_state_flush+0xc7/0x1b0
[   81.725458]    [<ffffffffa005f6cc>] pfkey_flush+0x7c/0x100 [af_key]
[   81.725465]    [<ffffffffa005efb7>] pfkey_process+0x1c7/0x1f0 [af_key]
[   81.725468]    [<ffffffffa005f139>] pfkey_sendmsg+0x159/0x260 [af_key]
[   81.725471]    [<ffffffff8162c16f>] sock_sendmsg+0xaf/0xc0
[   81.725476]    [<ffffffff8162c99c>] SYSC_sendto+0xfc/0x130
[   81.725479]    [<ffffffff8162cf3e>] SyS_sendto+0xe/0x10
[   81.725482]    [<ffffffff8177dd12>] system_call_fastpath+0x16/0x1b
[   81.725484]
[   81.725486] -> (xfrm_state_lock){+.+...} ops: 11 {
[   81.725490]    HARDIRQ-ON-W at:
[   81.725493]                     [<ffffffff8109a64b>] __lock_acquire+0x65b/0x1d70
[   81.725504]                     [<ffffffff8109c3c7>] lock_acquire+0x97/0x130
[   81.725507]                     [<ffffffff81774e4b>] _raw_spin_lock_bh+0x3b/0x70
[   81.725510]                     [<ffffffff816dc1df>] xfrm_state_flush+0x2f/0x1b0
[   81.725513]                     [<ffffffffa005f6cc>] pfkey_flush+0x7c/0x100 [af_key]
[   81.725516]                     [<ffffffffa005efb7>] pfkey_process+0x1c7/0x1f0 [af_key]
[   81.725519]                     [<ffffffffa005f139>] pfkey_sendmsg+0x159/0x260 [af_key]
[   81.725522]                     [<ffffffff8162c16f>] sock_sendmsg+0xaf/0xc0
[   81.725525]                     [<ffffffff8162c99c>] SYSC_sendto+0xfc/0x130
[   81.725527]                     [<ffffffff8162cf3e>] SyS_sendto+0xe/0x10
[   81.725530]                     [<ffffffff8177dd12>] system_call_fastpath+0x16/0x1b
[   81.725533]    SOFTIRQ-ON-W at:
[   81.725534]                     [<ffffffff8109a67a>] __lock_acquire+0x68a/0x1d70
[   81.725537]                     [<ffffffff8109c3c7>] lock_acquire+0x97/0x130
[   81.725539]                     [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70
[   81.725541]                     [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0
[   81.725544]                     [<ffffffffa008af03>] mod_cur_headers+0x793/0x7f0 [pktgen]
[   81.725547]                     [<ffffffffa008bca2>] pktgen_thread_worker+0xd42/0x1880 [pktgen]
[   81.725550]                     [<ffffffff81078f84>] kthread+0xe4/0x100
[   81.725555]                     [<ffffffff8177dc6c>] ret_from_fork+0x7c/0xb0
[   81.725565]    INITIAL USE at:
[   81.725567]                    [<ffffffff8109a31a>] __lock_acquire+0x32a/0x1d70
[   81.725569]                    [<ffffffff8109c3c7>] lock_acquire+0x97/0x130
[   81.725572]                    [<ffffffff81774e4b>] _raw_spin_lock_bh+0x3b/0x70
[   81.725574]                    [<ffffffff816dc1df>] xfrm_state_flush+0x2f/0x1b0
[   81.725576]                    [<ffffffffa005f6cc>] pfkey_flush+0x7c/0x100 [af_key]
[   81.725580]                    [<ffffffffa005efb7>] pfkey_process+0x1c7/0x1f0 [af_key]
[   81.725583]                    [<ffffffffa005f139>] pfkey_sendmsg+0x159/0x260 [af_key]
[   81.725586]                    [<ffffffff8162c16f>] sock_sendmsg+0xaf/0xc0
[   81.725589]                    [<ffffffff8162c99c>] SYSC_sendto+0xfc/0x130
[   81.725594]                    [<ffffffff8162cf3e>] SyS_sendto+0xe/0x10
[   81.725597]                    [<ffffffff8177dd12>] system_call_fastpath+0x16/0x1b
[   81.725599]  }
[   81.725600]  ... key      at: [<ffffffff81cadef8>] xfrm_state_lock+0x18/0x50
[   81.725606]  ... acquired at:
[   81.725607]    [<ffffffff810995c0>] check_usage_backwards+0x110/0x150
[   81.725609]    [<ffffffff81099e96>] mark_lock+0x196/0x2f0
[   81.725611]    [<ffffffff8109a67a>] __lock_acquire+0x68a/0x1d70
[   81.725614]    [<ffffffff8109c3c7>] lock_acquire+0x97/0x130
[   81.725616]    [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70
[   81.725627]    [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0
[   81.725629]    [<ffffffffa008af03>] mod_cur_headers+0x793/0x7f0 [pktgen]
[   81.725632]    [<ffffffffa008bca2>] pktgen_thread_worker+0xd42/0x1880 [pktgen]
[   81.725635]    [<ffffffff81078f84>] kthread+0xe4/0x100
[   81.725637]    [<ffffffff8177dc6c>] ret_from_fork+0x7c/0xb0
[   81.725640]
[   81.725641]
[   81.725641] stack backtrace:
[   81.725645] CPU: 0 PID: 2780 Comm: kpktgend_0 Not tainted 3.13.0-rc2+ #92
[   81.725647] Hardware name: innotek GmbH VirtualBox, BIOS VirtualBox 12/01/2006
[   81.725649]  ffffffff82537b80 ffff880018199988 ffffffff8176af37 0000000000000007
[   81.725652]  ffff8800181999f0 ffff8800181999d8 ffffffff81099358 ffffffff82537b80
[   81.725655]  ffffffff81a32def ffff8800181999f4 0000000000000000 ffff880002cbeaa8
[   81.725659] Call Trace:
[   81.725664]  [<ffffffff8176af37>] dump_stack+0x46/0x58
[   81.725667]  [<ffffffff81099358>] print_irq_inversion_bug.part.42+0x1e8/0x1f0
[   81.725670]  [<ffffffff810995c0>] check_usage_backwards+0x110/0x150
[   81.725672]  [<ffffffff81099e96>] mark_lock+0x196/0x2f0
[   81.725675]  [<ffffffff810994b0>] ? check_usage_forwards+0x150/0x150
[   81.725685]  [<ffffffff8109a67a>] __lock_acquire+0x68a/0x1d70
[   81.725691]  [<ffffffff810899a5>] ? sched_clock_local+0x25/0x90
[   81.725694]  [<ffffffff81089b38>] ? sched_clock_cpu+0xa8/0x120
[   81.725697]  [<ffffffff8109a31a>] ? __lock_acquire+0x32a/0x1d70
[   81.725699]  [<ffffffff816dd751>] ? xfrm_stateonly_find+0x41/0x1f0
[   81.725702]  [<ffffffff8109c3c7>] lock_acquire+0x97/0x130
[   81.725704]  [<ffffffff816dd751>] ? xfrm_stateonly_find+0x41/0x1f0
[   81.725707]  [<ffffffff810899a5>] ? sched_clock_local+0x25/0x90
[   81.725710]  [<ffffffff81774af6>] _raw_spin_lock+0x36/0x70
[   81.725712]  [<ffffffff816dd751>] ? xfrm_stateonly_find+0x41/0x1f0
[   81.725715]  [<ffffffff810971ec>] ? lock_release_holdtime.part.26+0x1c/0x1a0
[   81.725717]  [<ffffffff816dd751>] xfrm_stateonly_find+0x41/0x1f0
[   81.725721]  [<ffffffffa008af03>] mod_cur_headers+0x793/0x7f0 [pktgen]
[   81.725724]  [<ffffffffa008bca2>] pktgen_thread_worker+0xd42/0x1880 [pktgen]
[   81.725727]  [<ffffffffa008ba71>] ? pktgen_thread_worker+0xb11/0x1880 [pktgen]
[   81.725729]  [<ffffffff8109cf9d>] ? trace_hardirqs_on+0xd/0x10
[   81.725733]  [<ffffffff81775410>] ? _raw_spin_unlock_irq+0x30/0x40
[   81.725745]  [<ffffffff8151faa0>] ? e1000_clean+0x9d0/0x9d0
[   81.725751]  [<ffffffff81094310>] ? __init_waitqueue_head+0x60/0x60
[   81.725753]  [<ffffffff81094310>] ? __init_waitqueue_head+0x60/0x60
[   81.725757]  [<ffffffffa008af60>] ? mod_cur_headers+0x7f0/0x7f0 [pktgen]
[   81.725759]  [<ffffffff81078f84>] kthread+0xe4/0x100
[   81.725762]  [<ffffffff81078ea0>] ? flush_kthread_worker+0x170/0x170
[   81.725765]  [<ffffffff8177dc6c>] ret_from_fork+0x7c/0xb0
[   81.725768]  [<ffffffff81078ea0>] ? flush_kthread_worker+0x170/0x170

Signed-off-by: Fan Du <fan.du@windriver.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 9e6a4d6a9d8f569edefc8291e93907c5f92d7bf1..300744094ad86095f6663e4f474d1f0db39acd4a 100644 (file)
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -890,7 +890,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
        unsigned int h;
        struct xfrm_state *rx = NULL, *x = NULL;
 
-       spin_lock(&net->xfrm.xfrm_state_lock);
+       spin_lock_bh(&net->xfrm.xfrm_state_lock);
        h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
        hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
                if (x->props.family == family &&
@@ -908,7 +908,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
 
        if (rx)
                xfrm_state_hold(rx);
-       spin_unlock(&net->xfrm.xfrm_state_lock);
+       spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 
        return rx;