Merge tag 'scsi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull final round of SCSI updates from James Bottomley:
 "This is the remaining set of SCSI patches for the merge window.  It's
  mostly driver updates (scsi_debug, qla2xxx, storvsc, mp3sas).  There
  are also several bug fixes in fcoe, libfc, and megaraid_sas.  We also
  have a couple of core changes to try to make device destruction more
  deterministic"

* tag 'scsi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (46 commits)
  [SCSI] scsi constants: command, sense key + additional sense strings
  fcoe: Reduce number of sparse warnings
  fcoe: Stop fc_rport_priv structure leak
  libfcoe: Fix meaningless log statement
  libfc: Differentiate echange timer cancellation debug statements
  libfc: Remove extra space in fc_exch_timer_cancel definition
  fcoe: fix the link error status block sparse warnings
  fcoe: Fix smatch warning in fcoe_fdmi_info function
  libfc: Reject PLOGI from nodes with incompatible role
  [SCSI] enable destruction of blocked devices which fail LUN scanning
  [SCSI] Fix race between starved list and device removal
  [SCSI] megaraid_sas: fix a bug for 64 bit arches
  [SCSI] scsi_debug: reduce duplication between prot_verify_read and prot_verify_write
  [SCSI] scsi_debug: simplify offset calculation for dif_storep
  [SCSI] scsi_debug: invalidate protection info for unmapped region
  [SCSI] scsi_debug: fix NULL pointer dereference with parameters dif=0 dix=1
  [SCSI] scsi_debug: fix incorrectly nested kmap_atomic()
  [SCSI] scsi_debug: fix invalid address passed to kunmap_atomic()
  [SCSI] mpt3sas: Bump driver version to v02.100.00.00
  [SCSI] mpt3sas: when async scanning is enabled then while scanning, devices are removed but their transport layer entries are not removed
  ...

1 files changed, 22 insertions, 5 deletions

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 86d522004a20..124392f3091e 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -434,6 +434,8 @@ static void scsi_run_queue(struct request_queue *q)
 	list_splice_init(&shost->starved_list, &starved_list);
 
 	while (!list_empty(&starved_list)) {
+		struct request_queue *slq;
+
 		/*
 		 * As long as shost is accepting commands and we have
 		 * starved queues, call blk_run_queue. scsi_request_fn
@@ -456,11 +458,25 @@ static void scsi_run_queue(struct request_queue *q)
 			continue;
 		}
 
-		spin_unlock(shost->host_lock);
-		spin_lock(sdev->request_queue->queue_lock);
-		__blk_run_queue(sdev->request_queue);
-		spin_unlock(sdev->request_queue->queue_lock);
-		spin_lock(shost->host_lock);
+		/*
+		 * Once we drop the host lock, a racing scsi_remove_device()
+		 * call may remove the sdev from the starved list and destroy
+		 * it and the queue.  Mitigate by taking a reference to the
+		 * queue and never touching the sdev again after we drop the
+		 * host lock.  Note: if __scsi_remove_device() invokes
+		 * blk_cleanup_queue() before the queue is run from this
+		 * function then blk_run_queue() will return immediately since
+		 * blk_cleanup_queue() marks the queue with QUEUE_FLAG_DYING.
+		 */
+		slq = sdev->request_queue;
+		if (!blk_get_queue(slq))
+			continue;
+		spin_unlock_irqrestore(shost->host_lock, flags);
+
+		blk_run_queue(slq);
+		blk_put_queue(slq);
+
+		spin_lock_irqsave(shost->host_lock, flags);
 	}
 	/* put any unprocessed entries back */
 	list_splice(&starved_list, &shost->starved_list);
@@ -2177,6 +2193,7 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
 		case SDEV_OFFLINE:
 		case SDEV_TRANSPORT_OFFLINE:
 		case SDEV_CANCEL:
+		case SDEV_CREATED_BLOCK:
 			break;
 		default:
 			goto illegal;