diff mbox series

ipr: System hung while dlpar adding primary ipr adapter back

Message ID 1537489932-24594-1-git-send-email-wenxiong@linux.vnet.ibm.com (mailing list archive)
State Accepted
Headers show
Series ipr: System hung while dlpar adding primary ipr adapter back | expand

Commit Message

wenxiong@linux.vnet.ibm.com Sept. 21, 2018, 12:32 a.m. UTC 
From: Wen Xiong <wenxiong@linux.vnet.ibm.com>

While dlpar adding primary ipr adapter back, driver goes through
adapter initilization then schedule ipr_worker_thread to start
te disk scan by dropping the host lock, calling scsi_add_device.
Then get the adapter reset request again, so driver does
scsi_block_requests, this will cause the scsi_add_device get hung
until we unblock. But we can't run ipr_worker_thread to do the
unblock because its stuck in scsi_add_device.

This patch fixes the issue.

Signed-off-by: Wen Xiong <wenxiong@linux.vnet.ibm.com>
---
 drivers/scsi/ipr.c |  106 ++++++++++++++++++++++++++++++----------------------
 drivers/scsi/ipr.h |    1 +
 2 files changed, 62 insertions(+), 45 deletions(-)

Comments

Brian King Sept. 21, 2018, 4:22 p.m. UTC | #1 
On 09/20/2018 07:32 PM, wenxiong@linux.vnet.ibm.com wrote:
> +
> +	list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
> +		if (res->add_to_ml) {
> +			bus = res->bus;
> +			target = res->target;
> +			lun = res->lun;
> +			res->add_to_ml = 0;
> +			spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
> +			scsi_add_device(ioa_cfg->host, bus, target, lun);
> +			spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
> +			goto restart;
> +		}
> +	}	
         ^^^

You have some trailing whitespace here. 

Otherwise, looks good. Thanks!

Acked-by: Brian King <brking@linux.vnet.ibm.com>
diff mbox series

Patch

diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index f2ec80b..699d4df 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -3335,6 +3335,65 @@  static void ipr_release_dump(struct kref *kref)
 	LEAVE;
 }
 
+static void ipr_add_remove_thread(struct work_struct *work)
+{
+	unsigned long lock_flags;
+	struct ipr_resource_entry *res;
+	struct scsi_device *sdev;
+	struct ipr_ioa_cfg *ioa_cfg =
+		container_of(work, struct ipr_ioa_cfg, scsi_add_work_q);
+	u8 bus, target, lun;
+	int did_work;
+
+	ENTER;
+	spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+
+restart:
+	do {
+		did_work = 0;
+		if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].allow_cmds) {
+			spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
+			return;
+		}
+
+		list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
+			if (res->del_from_ml && res->sdev) {
+				did_work = 1;
+				sdev = res->sdev;
+				if (!scsi_device_get(sdev)) {
+					if (!res->add_to_ml)
+						list_move_tail(&res->queue, &ioa_cfg->free_res_q);
+					else
+						res->del_from_ml = 0;
+					spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
+					scsi_remove_device(sdev);
+					scsi_device_put(sdev);
+					spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+				}
+				break;
+			}
+		}
+	} while (did_work);
+
+	list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
+		if (res->add_to_ml) {
+			bus = res->bus;
+			target = res->target;
+			lun = res->lun;
+			res->add_to_ml = 0;
+			spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
+			scsi_add_device(ioa_cfg->host, bus, target, lun);
+			spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+			goto restart;
+		}
+	}	
+
+	ioa_cfg->scan_done = 1;
+	spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
+	kobject_uevent(&ioa_cfg->host->shost_dev.kobj, KOBJ_CHANGE);
+	LEAVE;
+}
+
 /**
  * ipr_worker_thread - Worker thread
  * @work:		ioa config struct
@@ -3349,13 +3408,9 @@  static void ipr_release_dump(struct kref *kref)
 static void ipr_worker_thread(struct work_struct *work)
 {
 	unsigned long lock_flags;
-	struct ipr_resource_entry *res;
-	struct scsi_device *sdev;
 	struct ipr_dump *dump;
 	struct ipr_ioa_cfg *ioa_cfg =
 		container_of(work, struct ipr_ioa_cfg, work_q);
-	u8 bus, target, lun;
-	int did_work;
 
 	ENTER;
 	spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
@@ -3393,49 +3448,9 @@  static void ipr_worker_thread(struct work_struct *work)
 		return;
 	}
 
-restart:
-	do {
-		did_work = 0;
-		if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].allow_cmds) {
-			spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
-			return;
-		}
-
-		list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
-			if (res->del_from_ml && res->sdev) {
-				did_work = 1;
-				sdev = res->sdev;
-				if (!scsi_device_get(sdev)) {
-					if (!res->add_to_ml)
-						list_move_tail(&res->queue, &ioa_cfg->free_res_q);
-					else
-						res->del_from_ml = 0;
-					spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
-					scsi_remove_device(sdev);
-					scsi_device_put(sdev);
-					spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
-				}
-				break;
-			}
-		}
-	} while (did_work);
-
-	list_for_each_entry(res, &ioa_cfg->used_res_q, queue) {
-		if (res->add_to_ml) {
-			bus = res->bus;
-			target = res->target;
-			lun = res->lun;
-			res->add_to_ml = 0;
-			spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
-			scsi_add_device(ioa_cfg->host, bus, target, lun);
-			spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
-			goto restart;
-		}
-	}
+	schedule_work(&ioa_cfg->scsi_add_work_q);
 
-	ioa_cfg->scan_done = 1;
 	spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
-	kobject_uevent(&ioa_cfg->host->shost_dev.kobj, KOBJ_CHANGE);
 	LEAVE;
 }
 
@@ -9933,6 +9948,7 @@  static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg,
 	INIT_LIST_HEAD(&ioa_cfg->free_res_q);
 	INIT_LIST_HEAD(&ioa_cfg->used_res_q);
 	INIT_WORK(&ioa_cfg->work_q, ipr_worker_thread);
+	INIT_WORK(&ioa_cfg->scsi_add_work_q, ipr_add_remove_thread);
 	init_waitqueue_head(&ioa_cfg->reset_wait_q);
 	init_waitqueue_head(&ioa_cfg->msi_wait_q);
 	init_waitqueue_head(&ioa_cfg->eeh_wait_q);
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 68afbbd..f6baa23 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1575,6 +1575,7 @@  struct ipr_ioa_cfg {
 	u8 saved_mode_page_len;
 
 	struct work_struct work_q;
+	struct work_struct scsi_add_work_q;
 	struct workqueue_struct *reset_work_q;
 
 	wait_queue_head_t reset_wait_q;