All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH 1/1] ipr: move setting of the allow_restart flag for vsets and disks
       [not found] <20100610214133.343780338@linux.vnet.ibm.com>
@ 2010-06-10 21:46 ` Wayne Boyer
  2010-06-14 14:41   ` Brian King
  0 siblings, 1 reply; 2+ messages in thread
From: Wayne Boyer @ 2010-06-10 21:46 UTC (permalink / raw)
  To: James Bottomley; +Cc: linux-scsi, Brian King, Kleber Sacilotto de Souza

A problem was found where the call to scsi_add_device() fails intermittently
for an adapter.  This is caused when __scsi_add_device() returns -ENODEV as
a result of not calling scsi_probe_and_add_lun() since the call to
scsi_host_scan_allowed() fails.  scsi_host_scan_allowed() fails because the
adapter state is set to SHOST_RECOVERY instead of SHOST_RUNNING. The state of
the adapter is being set to SHOST_RECOVERY by scsi_eh_scmd_add() during
error handling.

This problem is avoided by moving the setting of the allow_restart flag to
later in the device initialization sequence.  This prevents further error
handling if we get a NOT_READY response from a TUR command by causing
scsi_check_sense() to return SUCCESS.  Therefore, scsi_eh_scmd_add() will
not run and the adapter state will remain as SHOST_RUNNING.

Signed-off-by: Wayne Boyer <wayneb@linux.vnet.ibm.com>
---

 drivers/scsi/ipr.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

Index: b/drivers/scsi/ipr.c
===================================================================
--- a/drivers/scsi/ipr.c	2010-06-03 15:48:52.000000000 -0700
+++ b/drivers/scsi/ipr.c	2010-06-08 17:22:14.000000000 -0700
@@ -4350,8 +4350,6 @@ static int ipr_slave_configure(struct sc
 					     IPR_VSET_RW_TIMEOUT);
 			blk_queue_max_hw_sectors(sdev->request_queue, IPR_VSET_MAX_SECTORS);
 		}
-		if (ipr_is_vset_device(res) || ipr_is_scsi_disk(res))
-			sdev->allow_restart = 1;
 		if (ipr_is_gata(res) && res->sata_port)
 			ap = res->sata_port->ap;
 		spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
@@ -6768,7 +6766,8 @@ static int ipr_init_res_table(struct ipr
 			list_move_tail(&res->queue, &ioa_cfg->used_res_q);
 			ipr_init_res_entry(res, &cfgtew);
 			res->add_to_ml = 1;
-		}
+		} else if (res->sdev && (ipr_is_vset_device(res) || ipr_is_scsi_disk(res)))
+			res->sdev->allow_restart = 1;

 		if (found)
 			ipr_update_res_entry(res, &cfgtew);


^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [PATCH 1/1] ipr: move setting of the allow_restart flag for vsets and disks
  2010-06-10 21:46 ` [PATCH 1/1] ipr: move setting of the allow_restart flag for vsets and disks Wayne Boyer
@ 2010-06-14 14:41   ` Brian King
  0 siblings, 0 replies; 2+ messages in thread
From: Brian King @ 2010-06-14 14:41 UTC (permalink / raw)
  To: Wayne Boyer; +Cc: James Bottomley, linux-scsi, Kleber Sacilotto de Souza

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

On 06/10/2010 04:46 PM, Wayne Boyer wrote:
> A problem was found where the call to scsi_add_device() fails intermittently
> for an adapter.  This is caused when __scsi_add_device() returns -ENODEV as
> a result of not calling scsi_probe_and_add_lun() since the call to
> scsi_host_scan_allowed() fails.  scsi_host_scan_allowed() fails because the
> adapter state is set to SHOST_RECOVERY instead of SHOST_RUNNING. The state of
> the adapter is being set to SHOST_RECOVERY by scsi_eh_scmd_add() during
> error handling.
> 
> This problem is avoided by moving the setting of the allow_restart flag to
> later in the device initialization sequence.  This prevents further error
> handling if we get a NOT_READY response from a TUR command by causing
> scsi_check_sense() to return SUCCESS.  Therefore, scsi_eh_scmd_add() will
> not run and the adapter state will remain as SHOST_RUNNING.
> 
> Signed-off-by: Wayne Boyer <wayneb@linux.vnet.ibm.com>
> ---
> 
>  drivers/scsi/ipr.c |    5 ++---
>  1 file changed, 2 insertions(+), 3 deletions(-)
> 
> Index: b/drivers/scsi/ipr.c
> ===================================================================
> --- a/drivers/scsi/ipr.c	2010-06-03 15:48:52.000000000 -0700
> +++ b/drivers/scsi/ipr.c	2010-06-08 17:22:14.000000000 -0700
> @@ -4350,8 +4350,6 @@ static int ipr_slave_configure(struct sc
>  					     IPR_VSET_RW_TIMEOUT);
>  			blk_queue_max_hw_sectors(sdev->request_queue, IPR_VSET_MAX_SECTORS);
>  		}
> -		if (ipr_is_vset_device(res) || ipr_is_scsi_disk(res))
> -			sdev->allow_restart = 1;
>  		if (ipr_is_gata(res) && res->sata_port)
>  			ap = res->sata_port->ap;
>  		spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
> @@ -6768,7 +6766,8 @@ static int ipr_init_res_table(struct ipr
>  			list_move_tail(&res->queue, &ioa_cfg->used_res_q);
>  			ipr_init_res_entry(res, &cfgtew);
>  			res->add_to_ml = 1;
> -		}
> +		} else if (res->sdev && (ipr_is_vset_device(res) || ipr_is_scsi_disk(res)))
> +			res->sdev->allow_restart = 1;
> 
>  		if (found)
>  			ipr_update_res_entry(res, &cfgtew);
> 


-- 
Brian King
Linux on Power Virtualization
IBM Linux Technology Center



^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2010-06-14 14:42 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
     [not found] <20100610214133.343780338@linux.vnet.ibm.com>
2010-06-10 21:46 ` [PATCH 1/1] ipr: move setting of the allow_restart flag for vsets and disks Wayne Boyer
2010-06-14 14:41   ` Brian King

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.