[SCSI] fusion: hold off error recovery while alternate ioc is initializing

After discussing this patch with LSI, I resubmitting with a recommended
40 second wait for the alternate ioc's initialization to complete.
--
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 up to 40 seconds)
error recovery will escalate to the level of host reset.  This host
reset might fail (as the other function is resetting) resulting in
all connected targets being taken offline.

This patch holds off mid-layer error recovery for up to 40 seconds
to permit initialization of the other function to complete.

Signed-off-by: Michael Reed <mdr@sgi.com>
Acked-by: "Desai, Kashyap" <Kashyap.Desai@lsi.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>

1 files changed, 11 insertions, 6 deletions

diff --git a/drivers/message/fusion/mptfc.c b/drivers/message/fusion/mptfc.c
index ebf6ae024da..612ab3c51a6 100644
--- a/drivers/message/fusion/mptfc.c
+++ b/drivers/message/fusion/mptfc.c
@@ -195,29 +195,34 @@ mptfc_block_error_handler(struct scsi_cmnd *SCpnt,
         unsigned long           flags;
         int                     ready;
         MPT_ADAPTER             *ioc;
+        int                     loops = 40;     /* seconds */
 
         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 ((ready = fc_remote_port_chkready(rport) >> 16) == DID_IMM_RETRY
+         || (loops > 0 && ioc->active == 0)) {
                 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",
+                        "%x, active flag %d, deferring %s recovery.\n",
                         ioc->name, ioc->sh->host_no,
-                        SCpnt->device->id, SCpnt->device->lun, caller));
+                        SCpnt->device->id, SCpnt->device->lun,
+                        ready, ioc->active, caller));
                 msleep(1000);
                 spin_lock_irqsave(shost->host_lock, flags);
+                loops --;
         }
         spin_unlock_irqrestore(shost->host_lock, flags);
 
-        if (ready == DID_NO_CONNECT || !SCpnt->device->hostdata) {
+        if (ready == DID_NO_CONNECT || !SCpnt->device->hostdata
+         || ioc->active == 0) {
                 dfcprintk (ioc, printk(MYIOC_s_DEBUG_FMT
                         "%s.%d: %d:%d, failing recovery, "
-                        "port state %d, vdevice %p.\n", caller,
+                        "port state %x, active %d, vdevice %p.\n", caller,
                         ioc->name, ioc->sh->host_no,
                         SCpnt->device->id, SCpnt->device->lun, ready,
-                        SCpnt->device->hostdata));
+                        ioc->active, SCpnt->device->hostdata));
                 return FAILED;
         }
         dfcprintk (ioc, printk(MYIOC_s_DEBUG_FMT