From 8826f3b0397562eee6f8785d548be9dfdb169100 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 11 May 2011 05:41:41 -0700 Subject: rcu: Avoid acquiring rcu_node locks in timer functions This commit switches manipulations of the rcu_node ->wakemask field to atomic operations, which allows rcu_cpu_kthread_timer() to avoid acquiring the rcu_node lock. This should avoid the following lockdep splat reported by Valdis Kletnieks: [ 12.872150] usb 1-4: new high speed USB device number 3 using ehci_hcd [ 12.986667] usb 1-4: New USB device found, idVendor=413c, idProduct=2513 [ 12.986679] usb 1-4: New USB device strings: Mfr=0, Product=0, SerialNumber=0 [ 12.987691] hub 1-4:1.0: USB hub found [ 12.987877] hub 1-4:1.0: 3 ports detected [ 12.996372] input: PS/2 Generic Mouse as /devices/platform/i8042/serio1/input/input10 [ 13.071471] udevadm used greatest stack depth: 3984 bytes left [ 13.172129] [ 13.172130] ======================================================= [ 13.172425] [ INFO: possible circular locking dependency detected ] [ 13.172650] 2.6.39-rc6-mmotm0506 #1 [ 13.172773] ------------------------------------------------------- [ 13.172997] blkid/267 is trying to acquire lock: [ 13.173009] (&p->pi_lock){-.-.-.}, at: [] try_to_wake_up+0x29/0x1aa [ 13.173009] [ 13.173009] but task is already holding lock: [ 13.173009] (rcu_node_level_0){..-...}, at: [] rcu_cpu_kthread_timer+0x27/0x58 [ 13.173009] [ 13.173009] which lock already depends on the new lock. [ 13.173009] [ 13.173009] [ 13.173009] the existing dependency chain (in reverse order) is: [ 13.173009] [ 13.173009] -> #2 (rcu_node_level_0){..-...}: [ 13.173009] [] check_prevs_add+0x8b/0x104 [ 13.173009] [] validate_chain+0x36f/0x3ab [ 13.173009] [] __lock_acquire+0x369/0x3e2 [ 13.173009] [] lock_acquire+0xfc/0x14c [ 13.173009] [] _raw_spin_lock+0x36/0x45 [ 13.173009] [] rcu_read_unlock_special+0x8c/0x1d5 [ 13.173009] [] __rcu_read_unlock+0x4f/0xd7 [ 13.173009] [] rcu_read_unlock+0x21/0x23 [ 13.173009] [] cpuacct_charge+0x6c/0x75 [ 13.173009] [] update_curr+0x101/0x12e [ 13.173009] [] check_preempt_wakeup+0xf7/0x23b [ 13.173009] [] check_preempt_curr+0x2b/0x68 [ 13.173009] [] ttwu_do_wakeup+0x76/0x128 [ 13.173009] [] ttwu_do_activate.constprop.63+0x57/0x5c [ 13.173009] [] scheduler_ipi+0x48/0x5d [ 13.173009] [] smp_reschedule_interrupt+0x16/0x18 [ 13.173009] [] reschedule_interrupt+0x13/0x20 [ 13.173009] [] rcu_read_unlock+0x21/0x23 [ 13.173009] [] find_get_page+0xa9/0xb9 [ 13.173009] [] filemap_fault+0x6a/0x34d [ 13.173009] [] __do_fault+0x54/0x3e6 [ 13.173009] [] handle_pte_fault+0x12c/0x1ed [ 13.173009] [] handle_mm_fault+0x1cd/0x1e0 [ 13.173009] [] do_page_fault+0x42d/0x5de [ 13.173009] [] page_fault+0x1f/0x30 [ 13.173009] [ 13.173009] -> #1 (&rq->lock){-.-.-.}: [ 13.173009] [] check_prevs_add+0x8b/0x104 [ 13.173009] [] validate_chain+0x36f/0x3ab [ 13.173009] [] __lock_acquire+0x369/0x3e2 [ 13.173009] [] lock_acquire+0xfc/0x14c [ 13.173009] [] _raw_spin_lock+0x36/0x45 [ 13.173009] [] __task_rq_lock+0x8b/0xd3 [ 13.173009] [] wake_up_new_task+0x41/0x108 [ 13.173009] [] do_fork+0x265/0x33f [ 13.173009] [] kernel_thread+0x6b/0x6d [ 13.173009] [] rest_init+0x21/0xd2 [ 13.173009] [] start_kernel+0x3bb/0x3c6 [ 13.173009] [] x86_64_start_reservations+0xaf/0xb3 [ 13.173009] [] x86_64_start_kernel+0xf0/0xf7 [ 13.173009] [ 13.173009] -> #0 (&p->pi_lock){-.-.-.}: [ 13.173009] [] check_prev_add+0x68/0x20e [ 13.173009] [] check_prevs_add+0x8b/0x104 [ 13.173009] [] validate_chain+0x36f/0x3ab [ 13.173009] [] __lock_acquire+0x369/0x3e2 [ 13.173009] [] lock_acquire+0xfc/0x14c [ 13.173009] [] _raw_spin_lock_irqsave+0x44/0x57 [ 13.173009] [] try_to_wake_up+0x29/0x1aa [ 13.173009] [] wake_up_process+0x10/0x12 [ 13.173009] [] rcu_cpu_kthread_timer+0x44/0x58 [ 13.173009] [] call_timer_fn+0xac/0x1e9 [ 13.173009] [] run_timer_softirq+0x1aa/0x1f2 [ 13.173009] [] __do_softirq+0x109/0x26a [ 13.173009] [] call_softirq+0x1c/0x30 [ 13.173009] [] do_softirq+0x44/0xf1 [ 13.173009] [] irq_exit+0x58/0xc8 [ 13.173009] [] smp_apic_timer_interrupt+0x79/0x87 [ 13.173009] [] apic_timer_interrupt+0x13/0x20 [ 13.173009] [] get_page_from_freelist+0x2aa/0x310 [ 13.173009] [] __alloc_pages_nodemask+0x178/0x243 [ 13.173009] [] pte_alloc_one+0x1e/0x3a [ 13.173009] [] __pte_alloc+0x22/0x14b [ 13.173009] [] handle_mm_fault+0x17e/0x1e0 [ 13.173009] [] do_page_fault+0x42d/0x5de [ 13.173009] [] page_fault+0x1f/0x30 [ 13.173009] [ 13.173009] other info that might help us debug this: [ 13.173009] [ 13.173009] Chain exists of: [ 13.173009] &p->pi_lock --> &rq->lock --> rcu_node_level_0 [ 13.173009] [ 13.173009] Possible unsafe locking scenario: [ 13.173009] [ 13.173009] CPU0 CPU1 [ 13.173009] ---- ---- [ 13.173009] lock(rcu_node_level_0); [ 13.173009] lock(&rq->lock); [ 13.173009] lock(rcu_node_level_0); [ 13.173009] lock(&p->pi_lock); [ 13.173009] [ 13.173009] *** DEADLOCK *** [ 13.173009] [ 13.173009] 3 locks held by blkid/267: [ 13.173009] #0: (&mm->mmap_sem){++++++}, at: [] do_page_fault+0x1f3/0x5de [ 13.173009] #1: (&yield_timer){+.-...}, at: [] call_timer_fn+0x0/0x1e9 [ 13.173009] #2: (rcu_node_level_0){..-...}, at: [] rcu_cpu_kthread_timer+0x27/0x58 [ 13.173009] [ 13.173009] stack backtrace: [ 13.173009] Pid: 267, comm: blkid Not tainted 2.6.39-rc6-mmotm0506 #1 [ 13.173009] Call Trace: [ 13.173009] [] print_circular_bug+0xc8/0xd9 [ 13.173009] [] check_prev_add+0x68/0x20e [ 13.173009] [] ? save_stack_trace+0x28/0x46 [ 13.173009] [] check_prevs_add+0x8b/0x104 [ 13.173009] [] validate_chain+0x36f/0x3ab [ 13.173009] [] __lock_acquire+0x369/0x3e2 [ 13.173009] [] ? try_to_wake_up+0x29/0x1aa [ 13.173009] [] lock_acquire+0xfc/0x14c [ 13.173009] [] ? try_to_wake_up+0x29/0x1aa [ 13.173009] [] ? rcu_check_quiescent_state+0x82/0x82 [ 13.173009] [] _raw_spin_lock_irqsave+0x44/0x57 [ 13.173009] [] ? try_to_wake_up+0x29/0x1aa [ 13.173009] [] try_to_wake_up+0x29/0x1aa [ 13.173009] [] ? rcu_check_quiescent_state+0x82/0x82 [ 13.173009] [] wake_up_process+0x10/0x12 [ 13.173009] [] rcu_cpu_kthread_timer+0x44/0x58 [ 13.173009] [] ? rcu_check_quiescent_state+0x82/0x82 [ 13.173009] [] call_timer_fn+0xac/0x1e9 [ 13.173009] [] ? del_timer+0x75/0x75 [ 13.173009] [] ? rcu_check_quiescent_state+0x82/0x82 [ 13.173009] [] run_timer_softirq+0x1aa/0x1f2 [ 13.173009] [] __do_softirq+0x109/0x26a [ 13.173009] [] ? tick_dev_program_event+0x37/0xf6 [ 13.173009] [] ? time_hardirqs_off+0x1b/0x2f [ 13.173009] [] call_softirq+0x1c/0x30 [ 13.173009] [] do_softirq+0x44/0xf1 [ 13.173009] [] irq_exit+0x58/0xc8 [ 13.173009] [] smp_apic_timer_interrupt+0x79/0x87 [ 13.173009] [] apic_timer_interrupt+0x13/0x20 [ 13.173009] [] ? get_page_from_freelist+0x114/0x310 [ 13.173009] [] ? get_page_from_freelist+0x2aa/0x310 [ 13.173009] [] ? clear_page_c+0x7/0x10 [ 13.173009] [] ? prep_new_page+0x14c/0x1cd [ 13.173009] [] get_page_from_freelist+0x2aa/0x310 [ 13.173009] [] __alloc_pages_nodemask+0x178/0x243 [ 13.173009] [] ? __pmd_alloc+0x87/0x99 [ 13.173009] [] pte_alloc_one+0x1e/0x3a [ 13.173009] [] ? __pmd_alloc+0x87/0x99 [ 13.173009] [] __pte_alloc+0x22/0x14b [ 13.173009] [] handle_mm_fault+0x17e/0x1e0 [ 13.173009] [] do_page_fault+0x42d/0x5de [ 13.173009] [] ? sys_brk+0x32/0x10c [ 13.173009] [] ? time_hardirqs_off+0x1b/0x2f [ 13.173009] [] ? trace_hardirqs_off_caller+0x3f/0x9c [ 13.173009] [] ? trace_hardirqs_off_thunk+0x3a/0x3c [ 13.173009] [] page_fault+0x1f/0x30 [ 14.010075] usb 5-1: new full speed USB device number 2 using uhci_hcd Reported-by: Valdis Kletnieks Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- kernel/rcutree.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/rcutree.h') diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 93d4a1c2e88b..561dcb9a8d2c 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -119,7 +119,9 @@ struct rcu_node { /* elements that need to drain to allow the */ /* current expedited grace period to */ /* complete (only for TREE_PREEMPT_RCU). */ - unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */ + atomic_t wakemask; /* CPUs whose kthread needs to be awakened. */ + /* Since this has meaning only for leaf */ + /* rcu_node structures, 32 bits suffices. */ unsigned long qsmaskinit; /* Per-GP initial value for qsmask & expmask. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ -- cgit v1.2.3