From mboxrd@z Thu Jan 1 00:00:00 1970 From: Michael Reed Subject: [PATCH 1/1] fusion: hold off error recovery while alternate ioc is initializing Date: Wed, 16 Dec 2009 15:20:49 -0600 Message-ID: <4B294F31.5030109@sgi.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: Received: from relay1.sgi.com ([192.48.179.29]:36741 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1756127AbZLPVUu (ORCPT ); Wed, 16 Dec 2009 16:20:50 -0500 Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: linux-scsi Cc: "Moore, Eric" , Jeremy Higdon , Robin Holt , kashyap.desai@lsi.com Fusion FC chips are two function with some shared resources. During initialization of one function its driver inhibits the ability of the other function's driver to allocate message frames by clearing its "active" flag. Should mid-layer error recovery be initiated for a scsi command during this initialization (which can take many seconds) error recovery will escalate to the level of host reset. This host reset might fail resulting in all connected targets being taken offline. This patch holds off mid-layer error recovery for up to 60 seconds to permit initialization of the other function to complete. Applies to scsi-misc. Signed-off-by: Michael Reed == --- a/drivers/message/fusion/mptfc.c 2009-12-16 15:09:22.817382765 -0600 +++ b/drivers/message/fusion/mptfc.c 2009-12-16 15:10:31.949380663 -0600 @@ -195,29 +195,31 @@ mptfc_block_error_handler(struct scsi_cm unsigned long flags; int ready; MPT_ADAPTER *ioc; + int sleep_interval = 1000; + int loops = 60 * sleep_interval; hd = shost_priv(SCpnt->device->host); ioc = hd->ioc; spin_lock_irqsave(shost->host_lock, flags); - while ((ready = fc_remote_port_chkready(rport) >> 16) == DID_IMM_RETRY) { + + while ((loops > 0 && ioc->active == 0) + || (ready = fc_remote_port_chkready(rport) >> 16) == DID_IMM_RETRY) { + spin_unlock_irqrestore(shost->host_lock, flags); - dfcprintk (ioc, printk(MYIOC_s_DEBUG_FMT - "mptfc_block_error_handler.%d: %d:%d, port status is " - "DID_IMM_RETRY, deferring %s recovery.\n", - ioc->name, ioc->sh->host_no, - SCpnt->device->id, SCpnt->device->lun, caller)); - msleep(1000); + msleep(sleep_interval); + loops -= sleep_interval; spin_lock_irqsave(shost->host_lock, flags); } spin_unlock_irqrestore(shost->host_lock, flags); - if (ready == DID_NO_CONNECT || !SCpnt->device->hostdata) { + if (ioc->active == 0 + || ready == DID_NO_CONNECT || !SCpnt->device->hostdata) { dfcprintk (ioc, printk(MYIOC_s_DEBUG_FMT - "%s.%d: %d:%d, failing recovery, " + "%s.%d: %d:%d, failing recovery, active %d, " "port state %d, vdevice %p.\n", caller, ioc->name, ioc->sh->host_no, - SCpnt->device->id, SCpnt->device->lun, ready, - SCpnt->device->hostdata)); + SCpnt->device->id, SCpnt->device->lun, + ioc->active, ready, SCpnt->device->hostdata)); return FAILED; } dfcprintk (ioc, printk(MYIOC_s_DEBUG_FMT