Re: [PATCH] [SCSI] mpt2sas: fix for driver fails EEH recovery from injected pci bus error

2012-12-18 Thread Tomas Henzl 
On 12/18/2012 06:07 AM, Reddy, Sreekanth wrote:
 Yes Thomas, we need to reset the non_operational_loop to zero after the 
 transient event.

OK, so let me repost a V2 of the whole patch. 


 Thanks,
 Sreekanth.

 -Original Message-
 From: Tomas Henzl [mailto:the...@redhat.com] 
 Sent: Monday, December 17, 2012 6:43 PM
 To: Reddy, Sreekanth
 Cc: j...@kernel.org; Nandigama, Nagalakshmi; jbottom...@parallels.com; 
 linux-scsi@vger.kernel.org; Prakash, Sathya
 Subject: Re: [PATCH] [SCSI] mpt2sas: fix for driver fails EEH recovery from 
 injected pci bus error

 On 12/17/2012 10:58 PM, Sreekanth Reddy wrote:
 This patch stops the driver to invoke kthread (which remove the dead 
 ioc) for some time while EEH recovery has started.
 Thank you for posting this, the issue we have seen is resolved now.
 Shouldn't be an additional initialization added?
 So after a transient event the non_operational_loop is reset again?

 Tomas
  
 diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c 
 b/drivers/scsi/mpt2sas/mpt2sas_base.c
 index fd3b3d7..480111c 100644
 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c
 +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
 @@ -208,6 +208,8 @@ _base_fault_reset_work(struct work_struct *work)
   return; /* don't rearm timer */
   }
  
 + ioc-non_operational_loop = 0;
 +
   if ((doorbell  MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
   rc = mpt2sas_base_hard_reset_handler(ioc, CAN_SLEEP,
   FORCE_BIG_HAMMER);



 Signed-off-by: Sreekanth Reddy sreekanth.re...@lsi.com
 ---

 diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c 
 b/drivers/scsi/mpt2sas/mpt2sas_base.c
 index ffd85c5..2349531 100755
 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c
 +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
 @@ -155,7 +155,7 @@ _base_fault_reset_work(struct work_struct *work)
  struct task_struct *p;
  
  spin_lock_irqsave(ioc-ioc_reset_in_progress_lock, flags);
 -if (ioc-shost_recovery)
 +if (ioc-shost_recovery || ioc-pci_error_recovery)
  goto rearm_timer;
  spin_unlock_irqrestore(ioc-ioc_reset_in_progress_lock, flags);
  
 @@ -164,6 +164,20 @@ _base_fault_reset_work(struct work_struct *work)
  printk(MPT2SAS_INFO_FMT %s : SAS host is non-operational 
 \n,
  ioc-name, __func__);
  
 +/* It may be possible that EEH recovery can resolve some of
 + * pci bus failure issues rather removing the dead ioc function
 + * by considering controller is in a non-operational state. So
 + * here priority is given to the EEH recovery. If it doesn't
 + * not resolve this issue, mpt2sas driver will consider this
 + * controller to non-operational state and remove the dead ioc
 + * function.
 + */
 +if (ioc-non_operational_loop++  5) {
 +spin_lock_irqsave(ioc-ioc_reset_in_progress_lock,
 + flags);
 +goto rearm_timer;
 +}
 +
  /*
   * Call _scsih_flush_pending_cmds callback so that we flush all
   * pending commands back to OS. This call is required to aovid 
 @@ 
 -4386,6 +4400,7 @@ mpt2sas_base_attach(struct MPT2SAS_ADAPTER *ioc)
  if (missing_delay[0] != -1  missing_delay[1] != -1)
  _base_update_missing_delay(ioc, missing_delay[0],
  missing_delay[1]);
 +ioc-non_operational_loop = 0;
  
  return 0;
  
 diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.h 
 b/drivers/scsi/mpt2sas/mpt2sas_base.h
 index 543d8d6..c6ee7aa 100755
 --- a/drivers/scsi/mpt2sas/mpt2sas_base.h
 +++ b/drivers/scsi/mpt2sas/mpt2sas_base.h
 @@ -835,6 +835,7 @@ struct MPT2SAS_ADAPTER {
  u16 cpu_msix_table_sz;
  u32 ioc_reset_count;
  MPT2SAS_FLUSH_RUNNING_CMDS schedule_dead_ioc_flush_running_cmds;
 +u32 non_operational_loop;
  
  /* internal commands, callback index */
  u8  scsi_io_cb_idx;
 --
 To unsubscribe from this list: send the line unsubscribe linux-scsi 
 in the body of a message to majord...@vger.kernel.org More majordomo 
 info at  http://vger.kernel.org/majordomo-info.html
 --
 To unsubscribe from this list: send the line unsubscribe linux-scsi in
 the body of a message to majord...@vger.kernel.org
 More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line unsubscribe linux-scsi in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH] [SCSI] mpt2sas: fix for driver fails EEH recovery from injected pci bus error

2012-12-17 Thread Sreekanth Reddy 
This patch stops the driver to invoke kthread (which remove the dead ioc)
for some time while EEH recovery has started.

Signed-off-by: Sreekanth Reddy sreekanth.re...@lsi.com
---

diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c 
b/drivers/scsi/mpt2sas/mpt2sas_base.c
index ffd85c5..2349531 100755
--- a/drivers/scsi/mpt2sas/mpt2sas_base.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
@@ -155,7 +155,7 @@ _base_fault_reset_work(struct work_struct *work)
struct task_struct *p;
 
spin_lock_irqsave(ioc-ioc_reset_in_progress_lock, flags);
-   if (ioc-shost_recovery)
+   if (ioc-shost_recovery || ioc-pci_error_recovery)
goto rearm_timer;
spin_unlock_irqrestore(ioc-ioc_reset_in_progress_lock, flags);
 
@@ -164,6 +164,20 @@ _base_fault_reset_work(struct work_struct *work)
printk(MPT2SAS_INFO_FMT %s : SAS host is non-operational 
\n,
ioc-name, __func__);
 
+   /* It may be possible that EEH recovery can resolve some of
+* pci bus failure issues rather removing the dead ioc function
+* by considering controller is in a non-operational state. So
+* here priority is given to the EEH recovery. If it doesn't
+* not resolve this issue, mpt2sas driver will consider this
+* controller to non-operational state and remove the dead ioc
+* function.
+*/
+   if (ioc-non_operational_loop++  5) {
+   spin_lock_irqsave(ioc-ioc_reset_in_progress_lock,
+flags);
+   goto rearm_timer;
+   }
+
/*
 * Call _scsih_flush_pending_cmds callback so that we flush all
 * pending commands back to OS. This call is required to aovid
@@ -4386,6 +4400,7 @@ mpt2sas_base_attach(struct MPT2SAS_ADAPTER *ioc)
if (missing_delay[0] != -1  missing_delay[1] != -1)
_base_update_missing_delay(ioc, missing_delay[0],
missing_delay[1]);
+   ioc-non_operational_loop = 0;
 
return 0;
 
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.h 
b/drivers/scsi/mpt2sas/mpt2sas_base.h
index 543d8d6..c6ee7aa 100755
--- a/drivers/scsi/mpt2sas/mpt2sas_base.h
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.h
@@ -835,6 +835,7 @@ struct MPT2SAS_ADAPTER {
u16 cpu_msix_table_sz;
u32 ioc_reset_count;
MPT2SAS_FLUSH_RUNNING_CMDS schedule_dead_ioc_flush_running_cmds;
+   u32 non_operational_loop;
 
/* internal commands, callback index */
u8  scsi_io_cb_idx;
--
To unsubscribe from this list: send the line unsubscribe linux-scsi in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

RE: [PATCH] [SCSI] mpt2sas: fix for driver fails EEH recovery from injected pci bus error

2012-12-17 Thread Reddy, Sreekanth 
Yes Thomas, we need to reset the non_operational_loop to zero after the 
transient event.

Thanks,
Sreekanth.

-Original Message-
From: Tomas Henzl [mailto:the...@redhat.com] 
Sent: Monday, December 17, 2012 6:43 PM
To: Reddy, Sreekanth
Cc: j...@kernel.org; Nandigama, Nagalakshmi; jbottom...@parallels.com; 
linux-scsi@vger.kernel.org; Prakash, Sathya
Subject: Re: [PATCH] [SCSI] mpt2sas: fix for driver fails EEH recovery from 
injected pci bus error

On 12/17/2012 10:58 PM, Sreekanth Reddy wrote:
 This patch stops the driver to invoke kthread (which remove the dead 
 ioc) for some time while EEH recovery has started.

Thank you for posting this, the issue we have seen is resolved now.
Shouldn't be an additional initialization added?
So after a transient event the non_operational_loop is reset again?

Tomas
 
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c 
b/drivers/scsi/mpt2sas/mpt2sas_base.c
index fd3b3d7..480111c 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
@@ -208,6 +208,8 @@ _base_fault_reset_work(struct work_struct *work)
return; /* don't rearm timer */
}
 
+   ioc-non_operational_loop = 0;
+
if ((doorbell  MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
rc = mpt2sas_base_hard_reset_handler(ioc, CAN_SLEEP,
FORCE_BIG_HAMMER);




 Signed-off-by: Sreekanth Reddy sreekanth.re...@lsi.com
 ---

 diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c 
 b/drivers/scsi/mpt2sas/mpt2sas_base.c
 index ffd85c5..2349531 100755
 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c
 +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
 @@ -155,7 +155,7 @@ _base_fault_reset_work(struct work_struct *work)
   struct task_struct *p;
  
   spin_lock_irqsave(ioc-ioc_reset_in_progress_lock, flags);
 - if (ioc-shost_recovery)
 + if (ioc-shost_recovery || ioc-pci_error_recovery)
   goto rearm_timer;
   spin_unlock_irqrestore(ioc-ioc_reset_in_progress_lock, flags);
  
 @@ -164,6 +164,20 @@ _base_fault_reset_work(struct work_struct *work)
   printk(MPT2SAS_INFO_FMT %s : SAS host is non-operational 
 \n,
   ioc-name, __func__);
  
 + /* It may be possible that EEH recovery can resolve some of
 +  * pci bus failure issues rather removing the dead ioc function
 +  * by considering controller is in a non-operational state. So
 +  * here priority is given to the EEH recovery. If it doesn't
 +  * not resolve this issue, mpt2sas driver will consider this
 +  * controller to non-operational state and remove the dead ioc
 +  * function.
 +  */
 + if (ioc-non_operational_loop++  5) {
 + spin_lock_irqsave(ioc-ioc_reset_in_progress_lock,
 +  flags);
 + goto rearm_timer;
 + }
 +
   /*
* Call _scsih_flush_pending_cmds callback so that we flush all
* pending commands back to OS. This call is required to aovid 
 @@ 
 -4386,6 +4400,7 @@ mpt2sas_base_attach(struct MPT2SAS_ADAPTER *ioc)
   if (missing_delay[0] != -1  missing_delay[1] != -1)
   _base_update_missing_delay(ioc, missing_delay[0],
   missing_delay[1]);
 + ioc-non_operational_loop = 0;
  
   return 0;
  
 diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.h 
 b/drivers/scsi/mpt2sas/mpt2sas_base.h
 index 543d8d6..c6ee7aa 100755
 --- a/drivers/scsi/mpt2sas/mpt2sas_base.h
 +++ b/drivers/scsi/mpt2sas/mpt2sas_base.h
 @@ -835,6 +835,7 @@ struct MPT2SAS_ADAPTER {
   u16 cpu_msix_table_sz;
   u32 ioc_reset_count;
   MPT2SAS_FLUSH_RUNNING_CMDS schedule_dead_ioc_flush_running_cmds;
 + u32 non_operational_loop;
  
   /* internal commands, callback index */
   u8  scsi_io_cb_idx;
 --
 To unsubscribe from this list: send the line unsubscribe linux-scsi 
 in the body of a message to majord...@vger.kernel.org More majordomo 
 info at  http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line unsubscribe linux-scsi in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html