[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <11ff242b-195c-de75-d3d2-3e7b17a2ef3c@quicinc.com>
Date: Fri, 22 Apr 2022 15:33:08 +0530
From: Mukesh Ojha <quic_mojha@...cinc.com>
To: <linux-kernel@...r.kernel.org>,
Greg KH <gregkh@...uxfoundation.org>
CC: <tglx@...utronix.de>, <sboyd@...nel.org>, <rafael@...nel.org>,
<johannes@...solutions.net>
Subject: Re: [PATCH] devcoredump : Serialize devcd_del work
Hi All,
Request you all the review comments on the fix of the described problem?
-Mukesh
On 4/19/2022 3:57 PM, Mukesh Ojha wrote:
> In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd
> device to the framework which sends uevent notification to userspace
> and another thread Y reads this uevent and call to devcd_data_write()
> which eventually try to delete the queued timer that is not initialized/queued yet.
>
> So, debug object reports some warning and in the meantime, timer is initialized
> and queued from X path. and from Y path, it gets reinitialized again and
> timer->entry.pprev=NULL and try_to_grab_pending() stucks.
>
> To fix this, introduce mutex to serialize the behaviour.
>
> cpu0(X) cpu1(Y)
>
> dev_coredump() uevent sent to userspace
> device_add() =========================> userspace process Y reads the uevents
> writes to devcd fd which
> results into writes to
>
> devcd_data_write()
> mod_delayed_work()
> try_to_grab_pending()
> del_timer()
> debug_assert_init()
> INIT_DELAYED_WORK
> schedule_delayed_work
> debug_object_fixup()
> timer_fixup_assert_init()
> timer_setup()
> do_init_timer() ==> reinitialized the
> timer to
> timer->entry.pprev=NULL
>
> timer_pending()
> !hlist_unhashed_lockless(&timer->entry)
> !h->pprev ==> del_timer checks
> and finds it to be NULL
> try_to_grab_pending() stucks.
>
> Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/
> Signed-off-by: Mukesh Ojha <quic_mojha@...cinc.com>
> ---
> drivers/base/devcoredump.c | 11 +++++++++--
> 1 file changed, 9 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c
> index f4d794d..316f566 100644
> --- a/drivers/base/devcoredump.c
> +++ b/drivers/base/devcoredump.c
> @@ -25,6 +25,7 @@ struct devcd_entry {
> struct device devcd_dev;
> void *data;
> size_t datalen;
> + struct mutex mutex;
> struct module *owner;
> ssize_t (*read)(char *buffer, loff_t offset, size_t count,
> void *data, size_t datalen);
> @@ -84,7 +85,9 @@ static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj,
> struct device *dev = kobj_to_dev(kobj);
> struct devcd_entry *devcd = dev_to_devcd(dev);
>
> + mutex_lock(&devcd->mutex);
> mod_delayed_work(system_wq, &devcd->del_wk, 0);
> + mutex_unlock(&devcd->mutex);
>
> return count;
> }
> @@ -112,7 +115,9 @@ static int devcd_free(struct device *dev, void *data)
> {
> struct devcd_entry *devcd = dev_to_devcd(dev);
>
> + mutex_lock(&devcd->mutex);
> flush_delayed_work(&devcd->del_wk);
> + mutex_unlock(&devcd->mutex);
> return 0;
> }
>
> @@ -278,13 +283,14 @@ void dev_coredumpm(struct device *dev, struct module *owner,
> devcd->read = read;
> devcd->free = free;
> devcd->failing_dev = get_device(dev);
> -
> + mutex_init(&devcd->mutex);
> device_initialize(&devcd->devcd_dev);
>
> dev_set_name(&devcd->devcd_dev, "devcd%d",
> atomic_inc_return(&devcd_count));
> devcd->devcd_dev.class = &devcd_class;
>
> + mutex_lock(&devcd->mutex);
> if (device_add(&devcd->devcd_dev))
> goto put_device;
>
> @@ -301,10 +307,11 @@ void dev_coredumpm(struct device *dev, struct module *owner,
>
> INIT_DELAYED_WORK(&devcd->del_wk, devcd_del);
> schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT);
> -
> + mutex_unlock(&devcd->mutex);
> return;
> put_device:
> put_device(&devcd->devcd_dev);
> + mutex_unlock(&devcd->mutex);
> put_module:
> module_put(owner);
> free:
Powered by blists - more mailing lists