From: Andrew Vasquez Date: Wed, 22 Dec 2010 00:00:23 +0000 (-0800) Subject: [SCSI] qla2xxx: Don't perform a BIG_HAMMER if Get-ID (0x20) mailbox command fails... X-Git-Tag: Ubuntu-goldfish-3.4.0-4.27~4904^2~16 X-Git-Url: https://git.proxmox.com/?a=commitdiff_plain;h=7a44b86e777fc5d7a267df984d12b05fca59f487;p=mirror_ubuntu-zesty-kernel.git [SCSI] qla2xxx: Don't perform a BIG_HAMMER if Get-ID (0x20) mailbox command fails on CNAs. 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 Signed-off-by: Madhuranath Iyengar Signed-off-by: James Bottomley --- diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index d0a0dc9d6d36..f948e1a73aec 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2024,6 +2024,7 @@ qla2x00_configure_hba(scsi_qla_host_t *vha) &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));