* [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.