Re: [PATCH V2] mmc: core: Fix recursive locking issue in CQE recovery path

[Adrian Hunter]

On 7/05/20 7:15 pm, Veerabhadrarao Badiganti wrote:
> From: Sarthak Garg <sartgarg@xxxxxxxxxxxxxx>
> 
> Consider the following stack trace
> 
> -001|raw_spin_lock_irqsave
> -002|mmc_blk_cqe_complete_rq
> -003|__blk_mq_complete_request(inline)
> -003|blk_mq_complete_request(rq)
> -004|mmc_cqe_timed_out(inline)
> -004|mmc_mq_timed_out
> 
> mmc_mq_timed_out acquires the queue_lock for the first
> time. The mmc_blk_cqe_complete_rq function also tries to acquire
> the same queue lock resulting in recursive locking where the task
> is spinning for the same lock which it has already acquired leading
> to watchdog bark.
> 
> Fix this issue with the lock only for the required critical section.
> 
> Cc: <stable@xxxxxxxxxxxxxxx>
> Fixes: 1e8e55b67030 ("mmc: block: Add CQE support")
> Suggested-by: Sahitya Tummala <stummala@xxxxxxxxxxxxxx>
> Signed-off-by: Sarthak Garg <sartgarg@xxxxxxxxxxxxxx>

Acked-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>

> ---
>  drivers/mmc/core/queue.c | 13 ++++---------
>  1 file changed, 4 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
> index 25bee3d..b5fd3bc 100644
> --- a/drivers/mmc/core/queue.c
> +++ b/drivers/mmc/core/queue.c
> @@ -107,7 +107,7 @@ static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
>  	case MMC_ISSUE_DCMD:
>  		if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) {
>  			if (recovery_needed)
> -				__mmc_cqe_recovery_notifier(mq);
> +				mmc_cqe_recovery_notifier(mrq);
>  			return BLK_EH_RESET_TIMER;
>  		}
>  		/* No timeout (XXX: huh? comment doesn't make much sense) */
> @@ -127,18 +127,13 @@ static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req,
>  	struct mmc_card *card = mq->card;
>  	struct mmc_host *host = card->host;
>  	unsigned long flags;
> -	int ret;
> +	bool ignore_tout;
>  
>  	spin_lock_irqsave(&mq->lock, flags);
> -
> -	if (mq->recovery_needed || !mq->use_cqe || host->hsq_enabled)
> -		ret = BLK_EH_RESET_TIMER;
> -	else
> -		ret = mmc_cqe_timed_out(req);
> -
> +	ignore_tout = mq->recovery_needed || !mq->use_cqe || host->hsq_enabled;
>  	spin_unlock_irqrestore(&mq->lock, flags);
>  
> -	return ret;
> +	return ignore_tout ? BLK_EH_RESET_TIMER : mmc_cqe_timed_out(req);
>  }
>  
>  static void mmc_mq_recovery_handler(struct work_struct *work)
>