From 2be1a8c6f10a697e241453f379ad67feff63d3b8 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Wed, 15 Jun 2022 22:35:07 -0700 Subject: [PATCH] scsi: qla2xxx: Fix erroneous mailbox timeout after PCI error injection Clear wait for mailbox interrupt flag to prevent stale mailbox: Feb 22 05:22:56 ltcden4-lp7 kernel: qla2xxx [0135:90:00.1]-500a:4: LOOP UP detected (16 Gbps). Feb 22 05:22:59 ltcden4-lp7 kernel: qla2xxx [0135:90:00.1]-d04c:4: MBX Command timeout for cmd 69, ... To fix the issue, driver needs to clear the MBX_INTR_WAIT flag on purging the mailbox. When the stale mailbox completion does arrive, it will be dropped. Link: https://lore.kernel.org/r/20220616053508.27186-11-njavali@marvell.com Fixes: 2cf4e8006eab ("scsi: qla2xxx: Serialize mailbox request") Cc: Naresh Bannoth Cc: Kyle Mahlkuch Cc: stable@vger.kernel.org Reported-by: Naresh Bannoth Tested-by: Naresh Bannoth Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_mbx.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 16a736a7130d8..643fa0052f5ad 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -274,6 +274,12 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) atomic_inc(&ha->num_pend_mbx_stage3); if (!wait_for_completion_timeout(&ha->mbx_intr_comp, mcp->tov * HZ)) { + ql_dbg(ql_dbg_mbx, vha, 0x117a, + "cmd=%x Timeout.\n", command); + spin_lock_irqsave(&ha->hardware_lock, flags); + clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags); + spin_unlock_irqrestore(&ha->hardware_lock, flags); + if (chip_reset != ha->chip_reset) { eeh_delay = ha->flags.eeh_busy ? 1 : 0; @@ -286,12 +292,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) rval = QLA_ABORTED; goto premature_exit; } - ql_dbg(ql_dbg_mbx, vha, 0x117a, - "cmd=%x Timeout.\n", command); - spin_lock_irqsave(&ha->hardware_lock, flags); - clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags); - spin_unlock_irqrestore(&ha->hardware_lock, flags); - } else if (ha->flags.purge_mbox || chip_reset != ha->chip_reset) { eeh_delay = ha->flags.eeh_busy ? 1 : 0; -- 2.39.5