Re: [PATCH 1/4] fix might_sleep warning on socket shutdown.

[Markus Pargmann]

Hi,

On Tuesday 24 May 2016 14:26:25 Pranay Kr. Srivastava wrote:
> spinlocked ranges should be small and not contain calls into huge
> subfunctions. Fix my mistake and just get the pointer to the socket
> instead of doing everything with spinlock held.
> 
> Reported-by: Mikulas Patocka <mikulas@xxxxxxxxxxxxx>
> Signed-off-by: Markus Pargmann <mpa@xxxxxxxxxxxxxx>
> 
> Changelog:
> Pranay Kr. Srivastava<pranjas@xxxxxxxxx>:
> 
> 1) Use spin_lock instead of irq version for sock_shutdown.
> 
> 2) Use system work queue to actually trigger the shutdown of
>    socket. This solves the issue when kernel_sendmsg is currently
>    blocked while a timeout occurs.
> Signed-off-by: Pranay Kr. Srivastava <pranjas@xxxxxxxxx>
> ---
>  drivers/block/nbd.c |   62 +++++++++++++++++++++++++++++----------------------
>  1 file changed, 35 insertions(+), 27 deletions(-)
> 
> diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
> index 08afbc7..a5dab48 100644
> --- a/drivers/block/nbd.c
> +++ b/drivers/block/nbd.c
> @@ -39,6 +39,7 @@
>  #include <asm/types.h>
>  
>  #include <linux/nbd.h>
> +#include <linux/workqueue.h>
>  
>  struct nbd_device {
>  	u32 flags;
> @@ -57,7 +58,7 @@ struct nbd_device {
>  	int blksize;
>  	loff_t bytesize;
>  	int xmit_timeout;
> -	bool timedout;
> +	atomic_t timedout;

Why are you using atomic here? It seems you are just counting the
occurences of timeouts with this but never actually use that number. 

>  	bool disconnect; /* a disconnect has been requested by user */
>  
>  	struct timer_list timeout_timer;
> @@ -69,6 +70,7 @@ struct nbd_device {
>  #if IS_ENABLED(CONFIG_DEBUG_FS)
>  	struct dentry *dbg_dir;
>  #endif
> +	struct work_struct ws_nbd;

Can you rename this so that it is clear that this is a worker struct
specifically for the socket shutdown?

>  };
>  
>  #if IS_ENABLED(CONFIG_DEBUG_FS)
> @@ -94,6 +96,7 @@ static int max_part;
>   * Thanks go to Jens Axboe and Al Viro for their LKML emails explaining this!
>   */
>  static DEFINE_SPINLOCK(nbd_lock);
> +static void nbd_work_func(struct work_struct *);

Same here. nbd_work_func() doesn't give any hint about the real purpose
of the function.

>  
>  static inline struct device *nbd_to_dev(struct nbd_device *nbd)
>  {
> @@ -172,39 +175,31 @@ static void nbd_end_request(struct nbd_device *nbd, struct request *req)
>   */
>  static void sock_shutdown(struct nbd_device *nbd)
>  {
> -	spin_lock_irq(&nbd->sock_lock);
> -
> -	if (!nbd->sock) {
> -		spin_unlock_irq(&nbd->sock_lock);
> -		return;
> -	}
> +	struct socket *sock;
>  
> -	dev_warn(disk_to_dev(nbd->disk), "shutting down socket\n");
> -	kernel_sock_shutdown(nbd->sock, SHUT_RDWR);
> -	sockfd_put(nbd->sock);
> +	spin_lock(&nbd->sock_lock);
> +	sock = nbd->sock;
>  	nbd->sock = NULL;
> -	spin_unlock_irq(&nbd->sock_lock);
> +	spin_unlock(&nbd->sock_lock);
> +
> +	if (!sock)
> +		return;
>  
>  	del_timer(&nbd->timeout_timer);
> +	dev_warn(disk_to_dev(nbd->disk), "shutting down socket\n");
> +	kernel_sock_shutdown(sock, SHUT_RDWR);
> +	sockfd_put(sock);
>  }
>  
>  static void nbd_xmit_timeout(unsigned long arg)
>  {
>  	struct nbd_device *nbd = (struct nbd_device *)arg;
> -	unsigned long flags;
>  
>  	if (list_empty(&nbd->queue_head))
>  		return;
> -
> -	spin_lock_irqsave(&nbd->sock_lock, flags);
> -
> -	nbd->timedout = true;
> -
> -	if (nbd->sock)
> -		kernel_sock_shutdown(nbd->sock, SHUT_RDWR);
> -
> -	spin_unlock_irqrestore(&nbd->sock_lock, flags);
> -
> +	atomic_inc(&nbd->timedout);
> +	schedule_work(&nbd->ws_nbd);
> +	wake_up(&nbd->waiting_wq);
>  	dev_err(nbd_to_dev(nbd), "Connection timed out, shutting down connection\n");
>  }
>  
> @@ -592,7 +587,11 @@ static int nbd_thread_send(void *data)
>  		spin_unlock_irq(&nbd->queue_lock);
>  
>  		/* handle request */
> -		nbd_handle_req(nbd, req);
> +		if (atomic_read(&nbd->timedout)) {
> +			req->errors++;
> +			nbd_end_request(nbd, req);
> +		} else
> +			nbd_handle_req(nbd, req);
>  	}
>  
>  	nbd->task_send = NULL;
> @@ -666,12 +665,13 @@ out:
>  static void nbd_reset(struct nbd_device *nbd)
>  {
>  	nbd->disconnect = false;
> -	nbd->timedout = false;
> +	atomic_set(&nbd->timedout, 0);
>  	nbd->blksize = 1024;
>  	nbd->bytesize = 0;
>  	set_capacity(nbd->disk, 0);
>  	nbd->flags = 0;
>  	nbd->xmit_timeout = 0;
> +	INIT_WORK(&nbd->ws_nbd, nbd_work_func);
>  	queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
>  	del_timer_sync(&nbd->timeout_timer);
>  }
> @@ -804,16 +804,16 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
>  		nbd_dev_dbg_close(nbd);
>  		kthread_stop(thread);
>  
> -		mutex_lock(&nbd->tx_lock);
> -
>  		sock_shutdown(nbd);
> +		mutex_lock(&nbd->tx_lock);
>  		nbd_clear_que(nbd);
>  		kill_bdev(bdev);
>  		nbd_bdev_reset(bdev);
>  
>  		if (nbd->disconnect) /* user requested, ignore socket errors */
>  			error = 0;
> -		if (nbd->timedout)
> +
> +		if (atomic_read(&nbd->timedout))
>  			error = -ETIMEDOUT;
>  
>  		nbd_reset(nbd);
> @@ -863,6 +863,14 @@ static const struct block_device_operations nbd_fops =
>  	.compat_ioctl =	nbd_ioctl,
>  };
>  
> +static void nbd_work_func(struct work_struct *ws_nbd)
> +{
> +	struct nbd_device *nbd_dev = container_of(ws_nbd, struct nbd_device,
> +								ws_nbd);

Please align line breaks on the opening bracket.

Best Regards,

Markus

-- 
Pengutronix e.K.                           |                             |
Industrial Linux Solutions                 | http://www.pengutronix.de/  |
Peiner Str. 6-8, 31137 Hildesheim, Germany | Phone: +49-5121-206917-0    |
Amtsgericht Hildesheim, HRA 2686           | Fax:   +49-5121-206917-5555 |

Attachment: signature.asc
Description: This is a digitally signed message part.