lkml.org 
[lkml]   [2012]   [Feb]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: Possible circular locking dependency (3.3-rc2)
    Felipe, can you confirm whether or not Ming's patch below solves your
    problem?

    g.

    On Mon, Feb 13, 2012 at 10:53:20PM +0800, Ming Lei wrote:
    > Hi,
    >
    > On Wed, Feb 8, 2012 at 8:41 PM, Felipe Balbi <balbi@ti.com> wrote:
    > > Hi guys,
    > >
    > > I have just triggered the folllowing:
    > >
    > > [   84.860321] ======================================================
    > > [   84.860321] [ INFO: possible circular locking dependency detected ]
    > > [   84.860321] 3.3.0-rc2-00026-ge4e8a39 #474 Not tainted
    > > [   84.860321] -------------------------------------------------------
    > > [   84.860321] bash/949 is trying to acquire lock:
    > > [   84.860321]  (sysfs_lock){+.+.+.}, at: [<c0275358>] gpio_value_store+0x24/0xcc
    > > [   84.860321]
    > > [   84.860321] but task is already holding lock:
    > > [   84.860321]  (s_active#22){++++.+}, at: [<c016996c>] sysfs_write_file+0xdc/0x184
    > > [   84.911468]
    > > [   84.911468] which lock already depends on the new lock.
    > > [   84.911468]
    > > [   84.920043]
    > > [   84.920043] the existing dependency chain (in reverse order) is:
    > > [   84.920043]
    > > [   84.927886] -> #1 (s_active#22){++++.+}:
    > > [   84.927886]        [<c008f640>] check_prevs_add+0xdc/0x150
    > > [   84.927886]        [<c008fc18>] validate_chain.clone.24+0x564/0x694
    > > [   84.927886]        [<c0090cdc>] __lock_acquire+0x49c/0x980
    > > [   84.951660]        [<c0091838>] lock_acquire+0x98/0x100
    > > [   84.951660]        [<c016a8e8>] sysfs_deactivate+0xb0/0x100
    > > [   84.962982]        [<c016b1b4>] sysfs_addrm_finish+0x2c/0x6c
    > > [   84.962982]        [<c016b8bc>] sysfs_remove_dir+0x84/0x98
    > > [   84.962982]        [<c02590d8>] kobject_del+0x10/0x78
    > > [   84.974670]        [<c02c29e8>] device_del+0x140/0x170
    > > [   84.974670]        [<c02c2a24>] device_unregister+0xc/0x18
    > > [   84.985382]        [<c0276894>] gpio_unexport+0xbc/0xdc
    > > [   84.985382]        [<c02768c8>] gpio_free+0x14/0xfc
    > > [   85.001708]        [<c0276a28>] unexport_store+0x78/0x8c
    > > [   85.001708]        [<c02c5af8>] class_attr_store+0x18/0x24
    > > [   85.007293]        [<c0169990>] sysfs_write_file+0x100/0x184
    > > [   85.018981]        [<c0109d48>] vfs_write+0xb4/0x148
    > > [   85.018981]        [<c0109fd0>] sys_write+0x40/0x70
    > > [   85.018981]        [<c0013cc0>] ret_fast_syscall+0x0/0x3c
    > > [   85.035003]
    > > [   85.035003] -> #0 (sysfs_lock){+.+.+.}:
    > > [   85.035003]        [<c008f54c>] check_prev_add+0x680/0x698
    > > [   85.035003]        [<c008f640>] check_prevs_add+0xdc/0x150
    > > [   85.052093]        [<c008fc18>] validate_chain.clone.24+0x564/0x694
    > > [   85.052093]        [<c0090cdc>] __lock_acquire+0x49c/0x980
    > > [   85.052093]        [<c0091838>] lock_acquire+0x98/0x100
    > > [   85.069885]        [<c047e280>] mutex_lock_nested+0x3c/0x2f4
    > > [   85.069885]        [<c0275358>] gpio_value_store+0x24/0xcc
    > > [   85.069885]        [<c02c18dc>] dev_attr_store+0x18/0x24
    > > [   85.087158]        [<c0169990>] sysfs_write_file+0x100/0x184
    > > [   85.087158]        [<c0109d48>] vfs_write+0xb4/0x148
    > > [   85.098297]        [<c0109fd0>] sys_write+0x40/0x70
    > > [   85.098297]        [<c0013cc0>] ret_fast_syscall+0x0/0x3c
    > > [   85.109069]
    > > [   85.109069] other info that might help us debug this:
    > > [   85.109069]
    > > [   85.117462]  Possible unsafe locking scenario:
    > > [   85.117462]
    > > [   85.117462]        CPU0                    CPU1
    > > [   85.128417]        ----                    ----
    > > [   85.128417]   lock(s_active#22);
    > > [   85.128417]                                lock(sysfs_lock);
    > > [   85.128417]                                lock(s_active#22);
    > > [   85.142486]   lock(sysfs_lock);
    > > [   85.151794]
    > > [   85.151794]  *** DEADLOCK ***
    > > [   85.151794]
    > > [   85.151794] 2 locks held by bash/949:
    > > [   85.158020]  #0:  (&buffer->mutex){+.+.+.}, at: [<c01698b8>] sysfs_write_file+0x28/0x184
    > > [   85.170349]  #1:  (s_active#22){++++.+}, at: [<c016996c>] sysfs_write_file+0xdc/0x184
    > > [   85.170349]
    > > [   85.178588] stack backtrace:
    > > [   85.178588] [<c001b824>] (unwind_backtrace+0x0/0xf0) from [<c008de64>] (print_circular_bug+0x100/0x114)
    > > [   85.193023] [<c008de64>] (print_circular_bug+0x100/0x114) from [<c008f54c>] (check_prev_add+0x680/0x698)
    > > [   85.193023] [<c008f54c>] (check_prev_add+0x680/0x698) from [<c008f640>] (check_prevs_add+0xdc/0x150)
    > > [   85.212524] [<c008f640>] (check_prevs_add+0xdc/0x150) from [<c008fc18>] (validate_chain.clone.24+0x564/0x694)
    > > [   85.212524] [<c008fc18>] (validate_chain.clone.24+0x564/0x694) from [<c0090cdc>] (__lock_acquire+0x49c/0x980)
    > > [   85.233306] [<c0090cdc>] (__lock_acquire+0x49c/0x980) from [<c0091838>] (lock_acquire+0x98/0x100)
    > > [   85.233306] [<c0091838>] (lock_acquire+0x98/0x100) from [<c047e280>] (mutex_lock_nested+0x3c/0x2f4)
    > > [   85.242614] [<c047e280>] (mutex_lock_nested+0x3c/0x2f4) from [<c0275358>] (gpio_value_store+0x24/0xcc)
    > > [   85.261840] [<c0275358>] (gpio_value_store+0x24/0xcc) from [<c02c18dc>] (dev_attr_store+0x18/0x24)
    > > [   85.261840] [<c02c18dc>] (dev_attr_store+0x18/0x24) from [<c0169990>] (sysfs_write_file+0x100/0x184)
    > > [   85.271240] [<c0169990>] (sysfs_write_file+0x100/0x184) from [<c0109d48>] (vfs_write+0xb4/0x148)
    > > [   85.290008] [<c0109d48>] (vfs_write+0xb4/0x148) from [<c0109fd0>] (sys_write+0x40/0x70)
    > > [   85.298400] [<c0109fd0>] (sys_write+0x40/0x70) from [<c0013cc0>] (ret_fast_syscall+0x0/0x3c)
    > > -bash: echo: write error: Operation not permitted
    > >
    > > the way to trigger is:
    > >
    > >
    > > root@legolas:~# cd /sys/class/gpio/
    > > root@legolas:/sys/class/gpio# echo 2 > export
    > > root@legolas:/sys/class/gpio# echo 2 > unexport
    > > root@legolas:/sys/class/gpio# echo 2 > export
    > > root@legolas:/sys/class/gpio# cd gpio2/
    > > root@legolas:/sys/class/gpio/gpio2# echo 1 > value
    >
    > Looks 'sysfs_lock' needn't to be held for unregister, so the patch below may
    > fix the problem.
    >
    > diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
    > index 17fdf4b..d773540 100644
    > --- a/drivers/gpio/gpiolib.c
    > +++ b/drivers/gpio/gpiolib.c
    > @@ -873,6 +873,7 @@ void gpio_unexport(unsigned gpio)
    > {
    > struct gpio_desc *desc;
    > int status = 0;
    > + struct device *dev = NULL;
    >
    > if (!gpio_is_valid(gpio)) {
    > status = -EINVAL;
    > @@ -884,19 +885,20 @@ void gpio_unexport(unsigned gpio)
    > desc = &gpio_desc[gpio];
    >
    > if (test_bit(FLAG_EXPORT, &desc->flags)) {
    > - struct device *dev = NULL;
    >
    > dev = class_find_device(&gpio_class, NULL, desc, match_export);
    > if (dev) {
    > gpio_setup_irq(desc, dev, 0);
    > clear_bit(FLAG_EXPORT, &desc->flags);
    > - put_device(dev);
    > - device_unregister(dev);
    > } else
    > status = -ENODEV;
    > }
    >
    > mutex_unlock(&sysfs_lock);
    > + if (dev) {
    > + device_unregister(dev);
    > + put_device(dev);
    > + }
    > done:
    > if (status)
    > pr_debug("%s: gpio%d status %d\n", __func__, gpio, status);
    >
    >
    > thanks,
    > --
    > Ming Lei
    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

    \
     
     \ /
      Last update: 2012-02-15 21:11    [W:0.032 / U:31.352 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site