From 9203344cb8ecc554a1d36eae6661235ed422cf59 Mon Sep 17 00:00:00 2001 From: Mark Haverkamp Date: Tue, 20 Sep 2005 12:56:50 -0700 Subject: [SCSI] aacraid: initialization timeout Received from Mark Salyzyn from Adaptec. In the rare instances where the adapter, or the motherboard, is misbehaving; driver initialization or shutdown becomes problematic. By introducing a 3 minute timeout on the first interrupt driven command during initialization, or the issuance of the adapter shutdown command during driver unload, we can resolve the lockup problems induced by common (but rare) hardware misbehaviors. The timeout during initialization, should it occur, is accompanied by a message presented to the console and the logs indicating that the user should inspect and resolve problems with interrupt routing. Signed-off-by: Mark Haverkamp Signed-off-by: James Bottomley --- drivers/scsi/aacraid/commsup.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) (limited to 'drivers/scsi/aacraid/commsup.c') diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 69985b08a27..3b983f3ed96 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -41,6 +41,7 @@ #include #include #include +#include #include "aacraid.h" @@ -541,7 +542,34 @@ int fib_send(u16 command, struct fib * fibptr, unsigned long size, int priority if (wait) { spin_unlock_irqrestore(&fibptr->event_lock, flags); - down(&fibptr->event_wait); + /* Only set for first known interruptable command */ + if (wait < 0) { + /* + * *VERY* Dangerous to time out a command, the + * assumption is made that we have no hope of + * functioning because an interrupt routing or other + * hardware failure has occurred. + */ + unsigned long count = 36000000L; /* 3 minutes */ + unsigned long qflags; + while (down_trylock(&fibptr->event_wait)) { + if (--count == 0) { + spin_lock_irqsave(q->lock, qflags); + q->numpending--; + list_del(&fibptr->queue); + spin_unlock_irqrestore(q->lock, qflags); + if (wait == -1) { + printk(KERN_ERR "aacraid: fib_send: first asynchronous command timed out.\n" + "Usually a result of a PCI interrupt routing problem;\n" + "update mother board BIOS or consider utilizing one of\n" + "the SAFE mode kernel options (acpi, apic etc)\n"); + } + return -ETIMEDOUT; + } + udelay(5); + } + } else + down(&fibptr->event_wait); if(fibptr->done == 0) BUG(); -- cgit v1.2.3