Re: [PATCH v2] driver core: Fix sleeping in invalid context during device link deletion

[Marek Szyprowski]

Hi Saravana,

On 16.07.2020 23:45, Saravana Kannan wrote:
> Marek and Guenter reported that commit 287905e68dd2 ("driver core:
> Expose device link details in sysfs") caused sleeping/scheduling while
> atomic warnings.
>
> BUG: sleeping function called from invalid context at kernel/locking/mutex.c:935
> in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 12, name: kworker/0:1
> 2 locks held by kworker/0:1/12:
>    #0: ee8074a8 ((wq_completion)rcu_gp){+.+.}-{0:0}, at: process_one_work+0x174/0x7dc
>    #1: ee921f20 ((work_completion)(&sdp->work)){+.+.}-{0:0}, at: process_one_work+0x174/0x7dc
> Preemption disabled at:
> [<c01b10f0>] srcu_invoke_callbacks+0xc0/0x154
> ----- 8< ----- SNIP
> [<c064590c>] (device_del) from [<c0645c9c>] (device_unregister+0x24/0x64)
> [<c0645c9c>] (device_unregister) from [<c01b10fc>] (srcu_invoke_callbacks+0xcc/0x154)
> [<c01b10fc>] (srcu_invoke_callbacks) from [<c01493c4>] (process_one_work+0x234/0x7dc)
> [<c01493c4>] (process_one_work) from [<c01499b0>] (worker_thread+0x44/0x51c)
> [<c01499b0>] (worker_thread) from [<c0150bf4>] (kthread+0x158/0x1a0)
> [<c0150bf4>] (kthread) from [<c0100114>] (ret_from_fork+0x14/0x20)
> Exception stack(0xee921fb0 to 0xee921ff8)
>
> This was caused by the device link device being released in the context
> of srcu_invoke_callbacks().  There is no need to wait till the RCU
> callback to release the device link device.  So release the device
> earlier and move the call_srcu() into the device release code. That way,
> the memory will get freed only after the device is released AND the RCU
> callback is called.
>
> Fixes: 287905e68dd2 ("driver core: Expose device link details in sysfs")
> Reported-by: Marek Szyprowski <m.szyprowski@xxxxxxxxxxx>
> Reported-by: Guenter Roeck <linux@xxxxxxxxxxxx>
> Signed-off-by: Saravana Kannan <saravanak@xxxxxxxxxx>
> ---
>
> v1->v2:
> - Better fix
> - Changed subject
> - v1 is this patch https://lore.kernel.org/lkml/20200716050846.2047110-1-saravanak@xxxxxxxxxx/
>
> Marek and Guenter,
>
> I reproduced the original issue and tested this fix. Seems to work for
> me. Can you confirm?

Confirmed, this one fixes the issue! :)

Tested-by: Marek Szyprowski <m.szyprowski@xxxxxxxxxxx>

> Thanks,
> Saravana
>
>   drivers/base/core.c | 45 +++++++++++++++++++++++++++------------------
>   1 file changed, 27 insertions(+), 18 deletions(-)
>
> diff --git a/drivers/base/core.c b/drivers/base/core.c
> index 5373ddd029f6..ec16b97d45ed 100644
> --- a/drivers/base/core.c
> +++ b/drivers/base/core.c
> @@ -306,10 +306,34 @@ static struct attribute *devlink_attrs[] = {
>   };
>   ATTRIBUTE_GROUPS(devlink);
>   
> +static void device_link_free(struct device_link *link)
> +{
> +	while (refcount_dec_not_one(&link->rpm_active))
> +		pm_runtime_put(link->supplier);
> +
> +	put_device(link->consumer);
> +	put_device(link->supplier);
> +	kfree(link);
> +}
> +
> +#ifdef CONFIG_SRCU
> +static void __device_link_free_srcu(struct rcu_head *rhead)
> +{
> +	device_link_free(container_of(rhead, struct device_link, rcu_head));
> +}
> +
>   static void devlink_dev_release(struct device *dev)
>   {
> -	kfree(to_devlink(dev));
> +	struct device_link *link = to_devlink(dev);
> +
> +	call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu);
>   }
> +#else
> +static void devlink_dev_release(struct device *dev)
> +{
> +	device_link_free(to_devlink(dev));
> +}
> +#endif
>   
>   static struct class devlink_class = {
>   	.name = "devlink",
> @@ -730,22 +754,7 @@ static void device_link_add_missing_supplier_links(void)
>   	mutex_unlock(&wfs_lock);
>   }
>   
> -static void device_link_free(struct device_link *link)
> -{
> -	while (refcount_dec_not_one(&link->rpm_active))
> -		pm_runtime_put(link->supplier);
> -
> -	put_device(link->consumer);
> -	put_device(link->supplier);
> -	device_unregister(&link->link_dev);
> -}
> -
>   #ifdef CONFIG_SRCU
> -static void __device_link_free_srcu(struct rcu_head *rhead)
> -{
> -	device_link_free(container_of(rhead, struct device_link, rcu_head));
> -}
> -
>   static void __device_link_del(struct kref *kref)
>   {
>   	struct device_link *link = container_of(kref, struct device_link, kref);
> @@ -758,7 +767,7 @@ static void __device_link_del(struct kref *kref)
>   
>   	list_del_rcu(&link->s_node);
>   	list_del_rcu(&link->c_node);
> -	call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu);
> +	device_unregister(&link->link_dev);
>   }
>   #else /* !CONFIG_SRCU */
>   static void __device_link_del(struct kref *kref)
> @@ -773,7 +782,7 @@ static void __device_link_del(struct kref *kref)
>   
>   	list_del(&link->s_node);
>   	list_del(&link->c_node);
> -	device_link_free(link);
> +	device_unregister(&link->link_dev);
>   }
>   #endif /* !CONFIG_SRCU */
>   

Best regards
-- 
Marek Szyprowski, PhD
Samsung R&D Institute Poland