Re: [PATCH 07/14] scsi: convert host_busy to atomic_t

[Hannes Reinecke <hare@suse.de>]

On 06/25/2014 06:51 PM, Christoph Hellwig wrote:
> Avoid taking the host-wide host_lock to check the per-host queue limit.
> Instead we do an atomic_inc_return early on to grab our slot in the queue,
> and if nessecary decrement it after finishing all checks.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>   drivers/scsi/advansys.c             |    4 +-
>   drivers/scsi/libiscsi.c             |    4 +-
>   drivers/scsi/libsas/sas_scsi_host.c |    5 ++-
>   drivers/scsi/qlogicpti.c            |    2 +-
>   drivers/scsi/scsi.c                 |    2 +-
>   drivers/scsi/scsi_error.c           |    7 ++--
>   drivers/scsi/scsi_lib.c             |   71 +++++++++++++++++++++--------------
>   drivers/scsi/scsi_sysfs.c           |    9 ++++-
>   include/scsi/scsi_host.h            |   10 ++---
>   9 files changed, 66 insertions(+), 48 deletions(-)
>
> diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
> index e716d0a..43761c1 100644
> --- a/drivers/scsi/advansys.c
> +++ b/drivers/scsi/advansys.c
> @@ -2512,7 +2512,7 @@ static void asc_prt_scsi_host(struct Scsi_Host *s)
>
>   	printk("Scsi_Host at addr 0x%p, device %s\n", s, dev_name(boardp->dev));
>   	printk(" host_busy %u, host_no %d,\n",
> -	       s->host_busy, s->host_no);
> +	       atomic_read(&s->host_busy), s->host_no);
>
>   	printk(" base 0x%lx, io_port 0x%lx, irq %d,\n",
>   	       (ulong)s->base, (ulong)s->io_port, boardp->irq);
> @@ -3346,7 +3346,7 @@ static void asc_prt_driver_conf(struct seq_file *m, struct Scsi_Host *shost)
>
>   	seq_printf(m,
>   		   " host_busy %u, max_id %u, max_lun %llu, max_channel %u\n",
> -		   shost->host_busy, shost->max_id,
> +		   atomic_read(&shost->host_busy), shost->max_id,
>   		   shost->max_lun, shost->max_channel);
>
>   	seq_printf(m,
> diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
> index f2db82b..f9f3a12 100644
> --- a/drivers/scsi/libiscsi.c
> +++ b/drivers/scsi/libiscsi.c
> @@ -2971,7 +2971,7 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn)
>   	 */
>   	for (;;) {
>   		spin_lock_irqsave(session->host->host_lock, flags);
> -		if (!session->host->host_busy) { /* OK for ERL == 0 */
> +		if (!atomic_read(&session->host->host_busy)) { /* OK for ERL == 0 */
>   			spin_unlock_irqrestore(session->host->host_lock, flags);
>   			break;
>   		}
> @@ -2979,7 +2979,7 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn)
>   		msleep_interruptible(500);
>   		iscsi_conn_printk(KERN_INFO, conn, "iscsi conn_destroy(): "
>   				  "host_busy %d host_failed %d\n",
> -				  session->host->host_busy,
> +				  atomic_read(&session->host->host_busy),
>   				  session->host->host_failed);
>   		/*
>   		 * force eh_abort() to unblock
> diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
> index 7d02a19..24e477d 100644
> --- a/drivers/scsi/libsas/sas_scsi_host.c
> +++ b/drivers/scsi/libsas/sas_scsi_host.c
> @@ -813,7 +813,7 @@ retry:
>   	spin_unlock_irq(shost->host_lock);
>
>   	SAS_DPRINTK("Enter %s busy: %d failed: %d\n",
> -		    __func__, shost->host_busy, shost->host_failed);
> +		    __func__, atomic_read(&shost->host_busy), shost->host_failed);
>   	/*
>   	 * Deal with commands that still have SAS tasks (i.e. they didn't
>   	 * complete via the normal sas_task completion mechanism),
> @@ -858,7 +858,8 @@ out:
>   		goto retry;
>
>   	SAS_DPRINTK("--- Exit %s: busy: %d failed: %d tries: %d\n",
> -		    __func__, shost->host_busy, shost->host_failed, tries);
> +		    __func__, atomic_read(&shost->host_busy),
> +		    shost->host_failed, tries);
>   }
>
>   enum blk_eh_timer_return sas_scsi_timed_out(struct scsi_cmnd *cmd)
> diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
> index 6d48d30..740ae49 100644
> --- a/drivers/scsi/qlogicpti.c
> +++ b/drivers/scsi/qlogicpti.c
> @@ -959,7 +959,7 @@ static inline void update_can_queue(struct Scsi_Host *host, u_int in_ptr, u_int
>   	/* Temporary workaround until bug is found and fixed (one bug has been found
>   	   already, but fixing it makes things even worse) -jj */
>   	int num_free = QLOGICPTI_REQ_QUEUE_LEN - REQ_QUEUE_DEPTH(in_ptr, out_ptr) - 64;
> -	host->can_queue = host->host_busy + num_free;
> +	host->can_queue = atomic_read(&host->host_busy) + num_free;
>   	host->sg_tablesize = QLOGICPTI_MAX_SG(num_free);
>   }
>
> diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
> index d3bd6cf..35a23e2 100644
> --- a/drivers/scsi/scsi.c
> +++ b/drivers/scsi/scsi.c
> @@ -603,7 +603,7 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition)
>   			if (level > 3)
>   				scmd_printk(KERN_INFO, cmd,
>   					    "scsi host busy %d failed %d\n",
> -					    cmd->device->host->host_busy,
> +					    atomic_read(&cmd->device->host->host_busy),
>   					    cmd->device->host->host_failed);
>   		}
>   	}
> diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
> index e4a5324..5db8454 100644
> --- a/drivers/scsi/scsi_error.c
> +++ b/drivers/scsi/scsi_error.c
> @@ -59,7 +59,7 @@ static int scsi_try_to_abort_cmd(struct scsi_host_template *,
>   /* called with shost->host_lock held */
>   void scsi_eh_wakeup(struct Scsi_Host *shost)
>   {
> -	if (shost->host_busy == shost->host_failed) {
> +	if (atomic_read(&shost->host_busy) == shost->host_failed) {
>   		trace_scsi_eh_wakeup(shost);
>   		wake_up_process(shost->ehandler);
>   		SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost,
> @@ -2164,7 +2164,7 @@ int scsi_error_handler(void *data)
>   	while (!kthread_should_stop()) {
>   		set_current_state(TASK_INTERRUPTIBLE);
>   		if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) ||
> -		    shost->host_failed != shost->host_busy) {
> +		    shost->host_failed != atomic_read(&shost->host_busy)) {
>   			SCSI_LOG_ERROR_RECOVERY(1,
>   				shost_printk(KERN_INFO, shost,
>   					     "scsi_eh_%d: sleeping\n",
> @@ -2178,7 +2178,8 @@ int scsi_error_handler(void *data)
>   			shost_printk(KERN_INFO, shost,
>   				     "scsi_eh_%d: waking up %d/%d/%d\n",
>   				     shost->host_no, shost->host_eh_scheduled,
> -				     shost->host_failed, shost->host_busy));
> +				     shost->host_failed,
> +				     atomic_read(&shost->host_busy)));
>
>   		/*
>   		 * We have a host that is failing for some reason.  Figure out
> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
> index 5e269d6..5d37d79 100644
> --- a/drivers/scsi/scsi_lib.c
> +++ b/drivers/scsi/scsi_lib.c
> @@ -292,14 +292,17 @@ void scsi_device_unbusy(struct scsi_device *sdev)
>   	struct scsi_target *starget = scsi_target(sdev);
>   	unsigned long flags;
>
> -	spin_lock_irqsave(shost->host_lock, flags);
> -	shost->host_busy--;
> +	atomic_dec(&shost->host_busy);
>   	atomic_dec(&starget->target_busy);
> +
>   	if (unlikely(scsi_host_in_recovery(shost) &&
> -		     (shost->host_failed || shost->host_eh_scheduled)))
> +		     (shost->host_failed || shost->host_eh_scheduled))) {
> +		spin_lock_irqsave(shost->host_lock, flags);
>   		scsi_eh_wakeup(shost);
> -	spin_unlock(shost->host_lock);
> -	spin_lock(sdev->request_queue->queue_lock);
> +		spin_unlock_irqrestore(shost->host_lock, flags);
> +	}
> +
> +	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
>   	sdev->device_busy--;
>   	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
>   }
> @@ -367,7 +370,8 @@ static inline int scsi_target_is_busy(struct scsi_target *starget)
>
>   static inline int scsi_host_is_busy(struct Scsi_Host *shost)
>   {
> -	if ((shost->can_queue > 0 && shost->host_busy >= shost->can_queue) ||
> +	if ((shost->can_queue > 0 &&
> +	     atomic_read(&shost->host_busy) >= shost->can_queue) ||
>   	    shost->host_blocked || shost->host_self_blocked)
>   		return 1;
>
> @@ -1359,38 +1363,51 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
>   				   struct Scsi_Host *shost,
>   				   struct scsi_device *sdev)
>   {
> -	int ret = 0;
> -
> -	spin_lock_irq(shost->host_lock);
> +	unsigned int busy;
>
>   	if (scsi_host_in_recovery(shost))
> -		goto out;
> -	if (shost->host_busy == 0 && shost->host_blocked) {
> +		return 0;
> +
> +	busy = atomic_inc_return(&shost->host_busy) - 1;
> +	if (busy == 0 && shost->host_blocked) {
>   		/*
>   		 * unblock after host_blocked iterates to zero
>   		 */
> -		if (--shost->host_blocked != 0)
> -			goto out;
> +		spin_lock_irq(shost->host_lock);
> +		if (--shost->host_blocked != 0) {
> +			spin_unlock_irq(shost->host_lock);
> +			goto out_dec;
> +		}
> +		spin_unlock_irq(shost->host_lock);
>
>   		SCSI_LOG_MLQUEUE(3,
>   			shost_printk(KERN_INFO, shost,
>   				     "unblocking host at zero depth\n"));
>   	}
> -	if (scsi_host_is_busy(shost)) {
> -		if (list_empty(&sdev->starved_entry))
> -			list_add_tail(&sdev->starved_entry, &shost->starved_list);
> -		goto out;
> -	}
> +
> +	if (shost->can_queue > 0 && busy >= shost->can_queue)
> +		goto starved;
> +	if (shost->host_blocked || shost->host_self_blocked)
> +		goto starved;
>
>   	/* We're OK to process the command, so we can't be starved */
> -	if (!list_empty(&sdev->starved_entry))
> -		list_del_init(&sdev->starved_entry);
> +	if (!list_empty(&sdev->starved_entry)) {
> +		spin_lock_irq(shost->host_lock);
> +		if (!list_empty(&sdev->starved_entry))
> +			list_del_init(&sdev->starved_entry);
> +		spin_unlock_irq(shost->host_lock);
> +	}
>
> -	shost->host_busy++;
> -	ret = 1;
> -out:
> +	return 1;
> +
> +starved:
> +	spin_lock_irq(shost->host_lock);
> +	if (list_empty(&sdev->starved_entry))
> +		list_add_tail(&sdev->starved_entry, &shost->starved_list);
>   	spin_unlock_irq(shost->host_lock);
> -	return ret;
> +out_dec:
> +	atomic_dec(&shost->host_busy);
> +	return 0;
>   }
>
>   /*
> @@ -1454,12 +1471,8 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
>   	 * with the locks as normal issue path does.
>   	 */
>   	sdev->device_busy++;
> -	spin_unlock(sdev->request_queue->queue_lock);
> -	spin_lock(shost->host_lock);
> -	shost->host_busy++;
> +	atomic_inc(&shost->host_busy);
>   	atomic_inc(&starget->target_busy);
> -	spin_unlock(shost->host_lock);
> -	spin_lock(sdev->request_queue->queue_lock);
>
>   	blk_complete_request(req);
>   }
> diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
> index 5f36788..7ec5e06 100644
> --- a/drivers/scsi/scsi_sysfs.c
> +++ b/drivers/scsi/scsi_sysfs.c
> @@ -334,7 +334,6 @@ store_shost_eh_deadline(struct device *dev, struct device_attribute *attr,
>   static DEVICE_ATTR(eh_deadline, S_IRUGO | S_IWUSR, show_shost_eh_deadline, store_shost_eh_deadline);
>
>   shost_rd_attr(unique_id, "%u\n");
> -shost_rd_attr(host_busy, "%hu\n");
>   shost_rd_attr(cmd_per_lun, "%hd\n");
>   shost_rd_attr(can_queue, "%hd\n");
>   shost_rd_attr(sg_tablesize, "%hu\n");
> @@ -344,6 +343,14 @@ shost_rd_attr(prot_capabilities, "%u\n");
>   shost_rd_attr(prot_guard_type, "%hd\n");
>   shost_rd_attr2(proc_name, hostt->proc_name, "%s\n");
>
> +static ssize_t
> +show_host_busy(struct device *dev, struct device_attribute *attr, char *buf)
> +{
> +	struct Scsi_Host *shost = class_to_shost(dev);
> +	return snprintf(buf, 20, "%hu\n", atomic_read(&shost->host_busy));
> +}
> +static DEVICE_ATTR(host_busy, S_IRUGO, show_host_busy, NULL);
> +
>   static struct attribute *scsi_sysfs_shost_attrs[] = {
>   	&dev_attr_unique_id.attr,
>   	&dev_attr_host_busy.attr,
> diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
> index abb6958..3d124f7 100644
> --- a/include/scsi/scsi_host.h
> +++ b/include/scsi/scsi_host.h
> @@ -603,13 +603,9 @@ struct Scsi_Host {
>   	 */
>   	struct blk_queue_tag	*bqt;
>
> -	/*
> -	 * The following two fields are protected with host_lock;
> -	 * however, eh routines can safely access during eh processing
> -	 * without acquiring the lock.
> -	 */
> -	unsigned int host_busy;		   /* commands actually active on low-level */
> -	unsigned int host_failed;	   /* commands that failed. */
> +	atomic_t host_busy;		   /* commands actually active on low-level */
> +	unsigned int host_failed;	   /* commands that failed.
> +					      protected by host_lock */
>   	unsigned int host_eh_scheduled;    /* EH scheduled without command */
>
>   	unsigned int host_no;  /* Used for IOCTL_GET_IDLUN, /proc/scsi et al. */
>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Cheers,

Hannes
-- 
Dr. Hannes Reinecke		      zSeries & Storage
hare@suse.de			      +49 911 74053 688
SUSE LINUX Products GmbH, Maxfeldstr. 5, 90409 Nürnberg
GF: J. Hawn, J. Guild, F. Imendörffer, HRB 16746 (AG Nürnberg)