)]}'
{
  "commit": "5d5254f0d3b9bebc47d97e357374c0ad0c291a7d",
  "tree": "fea216db5914228fe80139f5e31621de86cc9e5d",
  "parents": [
    "ae99286b4f1be7788f2d6947c66a91dbd6351eec"
  ],
  "author": {
    "name": "Gautham R Shenoy",
    "email": "ego@in.ibm.com",
    "time": "Sat Oct 25 10:22:38 2008 +0530"
  },
  "committer": {
    "name": "Thomas Gleixner",
    "email": "tglx@linutronix.de",
    "time": "Tue Nov 11 10:46:42 2008 +0100"
  },
  "message": "timers: handle HRTIMER_CB_IRQSAFE_UNLOCKED correctly from softirq context\n\nImpact: fix incorrect locking triggered during hotplug-intense stress-tests\n\nWhile migrating the the CB_IRQSAFE_UNLOCKED timers during a cpu-offline,\nwe queue them on the cb_pending list, so that they won\u0027t go\nstale.\n\nThus, when the callbacks of the timers run from the softirq context,\nthey could run into potential deadlocks, since these callbacks\nassume that they\u0027re running with irq\u0027s disabled, thereby annoying\nlockdep!\n\nFix this by emulating hardirq context while running these callbacks from\nthe hrtimer softirq.\n\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n[ INFO: inconsistent lock state ]\n2.6.27 #2\n--------------------------------\ninconsistent {in-hardirq-W} -\u003e {hardirq-on-W} usage.\nksoftirqd/0/4 [HC0[0]:SC1[1]:HE1:SE0] takes:\n (\u0026rq-\u003elock){++..}, at: [\u003cc011db84\u003e] sched_rt_period_timer+0x9e/0x1fc\n{in-hardirq-W} state was registered at:\n  [\u003cc014103c\u003e] __lock_acquire+0x549/0x121e\n  [\u003cc0107890\u003e] native_sched_clock+0x88/0x99\n  [\u003cc013aa12\u003e] clocksource_get_next+0x39/0x3f\n  [\u003cc0139abc\u003e] update_wall_time+0x616/0x7df\n  [\u003cc0141d6b\u003e] lock_acquire+0x5a/0x74\n  [\u003cc0121724\u003e] scheduler_tick+0x3a/0x18d\n  [\u003cc047ed45\u003e] _spin_lock+0x1c/0x45\n  [\u003cc0121724\u003e] scheduler_tick+0x3a/0x18d\n  [\u003cc0121724\u003e] scheduler_tick+0x3a/0x18d\n  [\u003cc012c436\u003e] update_process_times+0x3a/0x44\n  [\u003cc013c044\u003e] tick_periodic+0x63/0x6d\n  [\u003cc013c062\u003e] tick_handle_periodic+0x14/0x5e\n  [\u003cc010568c\u003e] timer_interrupt+0x44/0x4a\n  [\u003cc0150c9f\u003e] handle_IRQ_event+0x13/0x3d\n  [\u003cc0151c14\u003e] handle_level_irq+0x79/0xbd\n  [\u003cc0105634\u003e] do_IRQ+0x69/0x7d\n  [\u003cc01041e4\u003e] common_interrupt+0x28/0x30\n  [\u003cc047007b\u003e] aac_probe_one+0x1a3/0x3f3\n  [\u003cc047ec2d\u003e] _spin_unlock_irqrestore+0x36/0x39\n  [\u003cc01512b4\u003e] setup_irq+0x1be/0x1f9\n  [\u003cc065d70b\u003e] start_kernel+0x259/0x2c5\n  [\u003cffffffff\u003e] 0xffffffff\nirq event stamp: 50102\nhardirqs last  enabled at (50102): [\u003cc047ebf4\u003e] _spin_unlock_irq+0x20/0x23\nhardirqs last disabled at (50101): [\u003cc047edc2\u003e] _spin_lock_irq+0xa/0x4b\nsoftirqs last  enabled at (50088): [\u003cc0128ba6\u003e] do_softirq+0x37/0x4d\nsoftirqs last disabled at (50099): [\u003cc0128ba6\u003e] do_softirq+0x37/0x4d\n\nother info that might help us debug this:\nno locks held by ksoftirqd/0/4.\n\nstack backtrace:\nPid: 4, comm: ksoftirqd/0 Not tainted 2.6.27 #2\n [\u003cc013f6cb\u003e] print_usage_bug+0x13e/0x147\n [\u003cc013fef5\u003e] mark_lock+0x493/0x797\n [\u003cc01410b1\u003e] __lock_acquire+0x5be/0x121e\n [\u003cc0141d6b\u003e] lock_acquire+0x5a/0x74\n [\u003cc011db84\u003e] sched_rt_period_timer+0x9e/0x1fc\n [\u003cc047ed45\u003e] _spin_lock+0x1c/0x45\n [\u003cc011db84\u003e] sched_rt_period_timer+0x9e/0x1fc\n [\u003cc011db84\u003e] sched_rt_period_timer+0x9e/0x1fc\n [\u003cc01210fd\u003e] finish_task_switch+0x41/0xbd\n [\u003cc0107890\u003e] native_sched_clock+0x88/0x99\n [\u003cc011dae6\u003e] sched_rt_period_timer+0x0/0x1fc\n [\u003cc0136dda\u003e] run_hrtimer_pending+0x54/0xe5\n [\u003cc011dae6\u003e] sched_rt_period_timer+0x0/0x1fc\n [\u003cc0128afb\u003e] __do_softirq+0x7b/0xef\n [\u003cc0128ba6\u003e] do_softirq+0x37/0x4d\n [\u003cc0128c12\u003e] ksoftirqd+0x56/0xc5\n [\u003cc0128bbc\u003e] ksoftirqd+0x0/0xc5\n [\u003cc0134649\u003e] kthread+0x38/0x5d\n [\u003cc0134611\u003e] kthread+0x0/0x5d\n [\u003cc0104477\u003e] kernel_thread_helper+0x7/0x10\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\nSigned-off-by: Gautham R Shenoy \u003cego@in.ibm.com\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nAcked-by: \"Paul E. McKenney\" \u003cpaulmck@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "2b465dfde4269b6d4609957999c9eecb0a148a36",
      "old_mode": 33188,
      "old_path": "kernel/hrtimer.c",
      "new_id": "95d3949f2ae51135b181906f632b8de7f5e3f8e7",
      "new_mode": 33188,
      "new_path": "kernel/hrtimer.c"
    }
  ]
}