scsi: convert host_busy to atomic_t

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 necessary decrement it after finishing all checks.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Webb Scales <webbnh@hp.com>
Acked-by: Jens Axboe <axboe@kernel.dk>
Tested-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Robert Elliott <elliott@hp.com>

include/scsi/scsi_host.h

@@ -582,13 +582,9 @@ 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. */