From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755251Ab2BOUJR (ORCPT ); Wed, 15 Feb 2012 15:09:17 -0500 Received: from mail-iy0-f174.google.com ([209.85.210.174]:35648 "EHLO mail-iy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751555Ab2BOUJN (ORCPT ); Wed, 15 Feb 2012 15:09:13 -0500 Date: Wed, 15 Feb 2012 13:09:10 -0700 From: Grant Likely To: Ming Lei Cc: balbi@ti.com, Linus Walleij , Linux OMAP Mailing List , Linux Kernel Mailing List , Linux ARM Kernel Mailing List Subject: Re: Possible circular locking dependency (3.3-rc2) Message-ID: <20120215200910.GE25779@ponder.secretlab.ca> References: <20120208124147.GF16334@legolas.emea.dhcp.ti.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 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 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: [] gpio_value_store+0x24/0xcc > > [   84.860321] > > [   84.860321] but task is already holding lock: > > [   84.860321]  (s_active#22){++++.+}, at: [] 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]        [] check_prevs_add+0xdc/0x150 > > [   84.927886]        [] validate_chain.clone.24+0x564/0x694 > > [   84.927886]        [] __lock_acquire+0x49c/0x980 > > [   84.951660]        [] lock_acquire+0x98/0x100 > > [   84.951660]        [] sysfs_deactivate+0xb0/0x100 > > [   84.962982]        [] sysfs_addrm_finish+0x2c/0x6c > > [   84.962982]        [] sysfs_remove_dir+0x84/0x98 > > [   84.962982]        [] kobject_del+0x10/0x78 > > [   84.974670]        [] device_del+0x140/0x170 > > [   84.974670]        [] device_unregister+0xc/0x18 > > [   84.985382]        [] gpio_unexport+0xbc/0xdc > > [   84.985382]        [] gpio_free+0x14/0xfc > > [   85.001708]        [] unexport_store+0x78/0x8c > > [   85.001708]        [] class_attr_store+0x18/0x24 > > [   85.007293]        [] sysfs_write_file+0x100/0x184 > > [   85.018981]        [] vfs_write+0xb4/0x148 > > [   85.018981]        [] sys_write+0x40/0x70 > > [   85.018981]        [] ret_fast_syscall+0x0/0x3c > > [   85.035003] > > [   85.035003] -> #0 (sysfs_lock){+.+.+.}: > > [   85.035003]        [] check_prev_add+0x680/0x698 > > [   85.035003]        [] check_prevs_add+0xdc/0x150 > > [   85.052093]        [] validate_chain.clone.24+0x564/0x694 > > [   85.052093]        [] __lock_acquire+0x49c/0x980 > > [   85.052093]        [] lock_acquire+0x98/0x100 > > [   85.069885]        [] mutex_lock_nested+0x3c/0x2f4 > > [   85.069885]        [] gpio_value_store+0x24/0xcc > > [   85.069885]        [] dev_attr_store+0x18/0x24 > > [   85.087158]        [] sysfs_write_file+0x100/0x184 > > [   85.087158]        [] vfs_write+0xb4/0x148 > > [   85.098297]        [] sys_write+0x40/0x70 > > [   85.098297]        [] 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: [] sysfs_write_file+0x28/0x184 > > [   85.170349]  #1:  (s_active#22){++++.+}, at: [] sysfs_write_file+0xdc/0x184 > > [   85.170349] > > [   85.178588] stack backtrace: > > [   85.178588] [] (unwind_backtrace+0x0/0xf0) from [] (print_circular_bug+0x100/0x114) > > [   85.193023] [] (print_circular_bug+0x100/0x114) from [] (check_prev_add+0x680/0x698) > > [   85.193023] [] (check_prev_add+0x680/0x698) from [] (check_prevs_add+0xdc/0x150) > > [   85.212524] [] (check_prevs_add+0xdc/0x150) from [] (validate_chain.clone.24+0x564/0x694) > > [   85.212524] [] (validate_chain.clone.24+0x564/0x694) from [] (__lock_acquire+0x49c/0x980) > > [   85.233306] [] (__lock_acquire+0x49c/0x980) from [] (lock_acquire+0x98/0x100) > > [   85.233306] [] (lock_acquire+0x98/0x100) from [] (mutex_lock_nested+0x3c/0x2f4) > > [   85.242614] [] (mutex_lock_nested+0x3c/0x2f4) from [] (gpio_value_store+0x24/0xcc) > > [   85.261840] [] (gpio_value_store+0x24/0xcc) from [] (dev_attr_store+0x18/0x24) > > [   85.261840] [] (dev_attr_store+0x18/0x24) from [] (sysfs_write_file+0x100/0x184) > > [   85.271240] [] (sysfs_write_file+0x100/0x184) from [] (vfs_write+0xb4/0x148) > > [   85.290008] [] (vfs_write+0xb4/0x148) from [] (sys_write+0x40/0x70) > > [   85.298400] [] (sys_write+0x40/0x70) from [] (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