The semantics we employ now in the driver, performing a
BIG_HAMMER in the event of Get-ID (0x20) mailbox command
failing, should only be done for FC. On FC configurations, it
makes sense since advertising is only really performed once,
so a BIG_HAMMER to reinitiate the process is needed to
restart. Under FCoE, this is not needed, as there's a
continous stream of advertisements/ACks at the protocol layer
to initiate a relogin/reinitialization process.
Signed-off-by: Andrew Vasquez <andrew.vasquez@qlogic.com>
Signed-off-by: Madhuranath Iyengar <Madhu.Iyengar@qlogic.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
&loop_id, &al_pa, &area, &domain, &topo, &sw_cap);
if (rval != QLA_SUCCESS) {
if (LOOP_TRANSITION(vha) || atomic_read(&ha->loop_down_timer) ||
+ IS_QLA8XXX_TYPE(ha) ||
(rval == QLA_COMMAND_ERROR && loop_id == 0x7)) {
DEBUG2(printk("%s(%ld) Loop is in a transition state\n",
__func__, vha->host_no));