From b4730fb6e54a634a145c9c71c5cf856f00beb5cd Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Tue, 18 Dec 2012 14:45:30 +0100 Subject: [SCSI] mpt2sas: fix for driver fails EEH, recovery from injected pci bus error This patch stops the driver to invoke kthread (which remove the dead ioc) for some time while EEH recovery has started. [thenzl: add a 'non_operational_loop' reset.] Signed-off-by: Sreekanth Reddy Signed-off-by: Tomas Henzl Signed-off-by: James Bottomley --- drivers/scsi/mpt2sas/mpt2sas_base.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'drivers/scsi/mpt2sas/mpt2sas_base.c') diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index ffd85c511c8e..5e24e7e73714 100644 --- 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 @@ -193,6 +207,8 @@ _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); @@ -4386,6 +4402,7 @@ 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; -- cgit v1.2.2