aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGautham R Shenoy <ego@in.ibm.com>2008-10-25 10:22:38 +0530
committerThomas Gleixner <tglx@linutronix.de>2008-11-11 10:46:42 +0100
commit5d5254f0d3b9bebc47d97e357374c0ad0c291a7d (patch)
treefea216db5914228fe80139f5e31621de86cc9e5d
parentae99286b4f1be7788f2d6947c66a91dbd6351eec (diff)
timers: handle HRTIMER_CB_IRQSAFE_UNLOCKED correctly from softirq context
Impact: fix incorrect locking triggered during hotplug-intense stress-tests While migrating the the CB_IRQSAFE_UNLOCKED timers during a cpu-offline, we queue them on the cb_pending list, so that they won't go stale. Thus, when the callbacks of the timers run from the softirq context, they could run into potential deadlocks, since these callbacks assume that they're running with irq's disabled, thereby annoying lockdep! Fix this by emulating hardirq context while running these callbacks from the hrtimer softirq. ================================= [ INFO: inconsistent lock state ] 2.6.27 #2 -------------------------------- inconsistent {in-hardirq-W} -> {hardirq-on-W} usage. ksoftirqd/0/4 [HC0[0]:SC1[1]:HE1:SE0] takes: (&rq->lock){++..}, at: [<c011db84>] sched_rt_period_timer+0x9e/0x1fc {in-hardirq-W} state was registered at: [<c014103c>] __lock_acquire+0x549/0x121e [<c0107890>] native_sched_clock+0x88/0x99 [<c013aa12>] clocksource_get_next+0x39/0x3f [<c0139abc>] update_wall_time+0x616/0x7df [<c0141d6b>] lock_acquire+0x5a/0x74 [<c0121724>] scheduler_tick+0x3a/0x18d [<c047ed45>] _spin_lock+0x1c/0x45 [<c0121724>] scheduler_tick+0x3a/0x18d [<c0121724>] scheduler_tick+0x3a/0x18d [<c012c436>] update_process_times+0x3a/0x44 [<c013c044>] tick_periodic+0x63/0x6d [<c013c062>] tick_handle_periodic+0x14/0x5e [<c010568c>] timer_interrupt+0x44/0x4a [<c0150c9f>] handle_IRQ_event+0x13/0x3d [<c0151c14>] handle_level_irq+0x79/0xbd [<c0105634>] do_IRQ+0x69/0x7d [<c01041e4>] common_interrupt+0x28/0x30 [<c047007b>] aac_probe_one+0x1a3/0x3f3 [<c047ec2d>] _spin_unlock_irqrestore+0x36/0x39 [<c01512b4>] setup_irq+0x1be/0x1f9 [<c065d70b>] start_kernel+0x259/0x2c5 [<ffffffff>] 0xffffffff irq event stamp: 50102 hardirqs last enabled at (50102): [<c047ebf4>] _spin_unlock_irq+0x20/0x23 hardirqs last disabled at (50101): [<c047edc2>] _spin_lock_irq+0xa/0x4b softirqs last enabled at (50088): [<c0128ba6>] do_softirq+0x37/0x4d softirqs last disabled at (50099): [<c0128ba6>] do_softirq+0x37/0x4d other info that might help us debug this: no locks held by ksoftirqd/0/4. stack backtrace: Pid: 4, comm: ksoftirqd/0 Not tainted 2.6.27 #2 [<c013f6cb>] print_usage_bug+0x13e/0x147 [<c013fef5>] mark_lock+0x493/0x797 [<c01410b1>] __lock_acquire+0x5be/0x121e [<c0141d6b>] lock_acquire+0x5a/0x74 [<c011db84>] sched_rt_period_timer+0x9e/0x1fc [<c047ed45>] _spin_lock+0x1c/0x45 [<c011db84>] sched_rt_period_timer+0x9e/0x1fc [<c011db84>] sched_rt_period_timer+0x9e/0x1fc [<c01210fd>] finish_task_switch+0x41/0xbd [<c0107890>] native_sched_clock+0x88/0x99 [<c011dae6>] sched_rt_period_timer+0x0/0x1fc [<c0136dda>] run_hrtimer_pending+0x54/0xe5 [<c011dae6>] sched_rt_period_timer+0x0/0x1fc [<c0128afb>] __do_softirq+0x7b/0xef [<c0128ba6>] do_softirq+0x37/0x4d [<c0128c12>] ksoftirqd+0x56/0xc5 [<c0128bbc>] ksoftirqd+0x0/0xc5 [<c0134649>] kthread+0x38/0x5d [<c0134611>] kthread+0x0/0x5d [<c0104477>] kernel_thread_helper+0x7/0x10 ======================= Signed-off-by: Gautham R Shenoy <ego@in.ibm.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--kernel/hrtimer.c17
1 files changed, 16 insertions, 1 deletions
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 2b465dfde42..95d3949f2ae 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1209,6 +1209,7 @@ static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
enum hrtimer_restart (*fn)(struct hrtimer *);
struct hrtimer *timer;
int restart;
+ int emulate_hardirq_ctx = 0;
timer = list_entry(cpu_base->cb_pending.next,
struct hrtimer, cb_entry);
@@ -1217,10 +1218,24 @@ static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
timer_stats_account_hrtimer(timer);
fn = timer->function;
+ /*
+ * A timer might have been added to the cb_pending list
+ * when it was migrated during a cpu-offline operation.
+ * Emulate hardirq context for such timers.
+ */
+ if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
+ timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED)
+ emulate_hardirq_ctx = 1;
+
__remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
spin_unlock_irq(&cpu_base->lock);
- restart = fn(timer);
+ if (unlikely(emulate_hardirq_ctx)) {
+ local_irq_disable();
+ restart = fn(timer);
+ local_irq_enable();
+ } else
+ restart = fn(timer);
spin_lock_irq(&cpu_base->lock);