diff mbox series

[05/16] qla2xxx: Fix premature hw access after pci error

Message ID 20211224070712.17905-6-njavali@marvell.com
State Superseded
Headers show
Series qla2xxx misc bug fixes and features | expand

Commit Message

Nilesh Javali Dec. 24, 2021, 7:07 a.m. UTC 
From: Quinn Tran <qutran@marvell.com>

Fix premature hw access after pci error.
After a recoverable PCI error has been detected and recovered, qla driver
needs to check to see if the error condition still persist and/or wait until
the OS to give the resume signal.

Sep  8 22:26:03 localhost kernel: WARNING: CPU: 9 PID: 124606 at qla_tmpl.c:440
qla27xx_fwdt_entry_t266+0x55/0x60 [qla2xxx]
Sep  8 22:26:03 localhost kernel: RIP: 0010:qla27xx_fwdt_entry_t266+0x55/0x60
[qla2xxx]
Sep  8 22:26:03 localhost kernel: Call Trace:
Sep  8 22:26:03 localhost kernel: ? qla27xx_walk_template+0xb1/0x1b0 [qla2xxx]
Sep  8 22:26:03 localhost kernel: ? qla27xx_execute_fwdt_template+0x12a/0x160
[qla2xxx]
Sep  8 22:26:03 localhost kernel: ? qla27xx_fwdump+0xa0/0x1c0 [qla2xxx]
Sep  8 22:26:03 localhost kernel: ? qla2xxx_pci_mmio_enabled+0xfb/0x120
[qla2xxx]
Sep  8 22:26:03 localhost kernel: ? report_mmio_enabled+0x44/0x80
Sep  8 22:26:03 localhost kernel: ? report_slot_reset+0x80/0x80
Sep  8 22:26:03 localhost kernel: ? pci_walk_bus+0x70/0x90
Sep  8 22:26:03 localhost kernel: ? aer_dev_correctable_show+0xc0/0xc0
Sep  8 22:26:03 localhost kernel: ? pcie_do_recovery+0x1bb/0x240
Sep  8 22:26:03 localhost kernel: ? aer_recover_work_func+0xaa/0xd0
Sep  8 22:26:03 localhost kernel: ? process_one_work+0x1a7/0x360
..
Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-8041:22: detected PCI
disconnect.
Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-107ff:22:
qla27xx_fwdt_entry_t262: dump ram MB failed. Area 5h start 198013h end 198013h
Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-107ff:22: Unable to
capture FW dump
Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-1015:22: cmd=0x0,
waited 5221 msecs
Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-680d:22: mmio
enabled returning.
Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-d04c:22: MBX
Command timeout for cmd 0, iocontrol=ffffffff jiffies=10140f2e5
mb[0-3]=[0xffff 0xffff 0xffff 0xffff]

Cc: stable@vger.kernel.org
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
---
 drivers/scsi/qla2xxx/qla_os.c   | 10 +++++++++-
 drivers/scsi/qla2xxx/qla_tmpl.c |  9 +++++++--
 2 files changed, 16 insertions(+), 3 deletions(-)

Comments

Himanshu Madhani Jan. 3, 2022, 12:39 a.m. UTC | #1 
> On Dec 23, 2021, at 11:07 PM, Nilesh Javali <njavali@marvell.com> wrote:
> 
> From: Quinn Tran <qutran@marvell.com>
> 
> Fix premature hw access after pci error.
> After a recoverable PCI error has been detected and recovered, qla driver
> needs to check to see if the error condition still persist and/or wait until
> the OS to give the resume signal.
> 
> Sep  8 22:26:03 localhost kernel: WARNING: CPU: 9 PID: 124606 at qla_tmpl.c:440
> qla27xx_fwdt_entry_t266+0x55/0x60 [qla2xxx]
> Sep  8 22:26:03 localhost kernel: RIP: 0010:qla27xx_fwdt_entry_t266+0x55/0x60
> [qla2xxx]
> Sep  8 22:26:03 localhost kernel: Call Trace:
> Sep  8 22:26:03 localhost kernel: ? qla27xx_walk_template+0xb1/0x1b0 [qla2xxx]
> Sep  8 22:26:03 localhost kernel: ? qla27xx_execute_fwdt_template+0x12a/0x160
> [qla2xxx]
> Sep  8 22:26:03 localhost kernel: ? qla27xx_fwdump+0xa0/0x1c0 [qla2xxx]
> Sep  8 22:26:03 localhost kernel: ? qla2xxx_pci_mmio_enabled+0xfb/0x120
> [qla2xxx]
> Sep  8 22:26:03 localhost kernel: ? report_mmio_enabled+0x44/0x80
> Sep  8 22:26:03 localhost kernel: ? report_slot_reset+0x80/0x80
> Sep  8 22:26:03 localhost kernel: ? pci_walk_bus+0x70/0x90
> Sep  8 22:26:03 localhost kernel: ? aer_dev_correctable_show+0xc0/0xc0
> Sep  8 22:26:03 localhost kernel: ? pcie_do_recovery+0x1bb/0x240
> Sep  8 22:26:03 localhost kernel: ? aer_recover_work_func+0xaa/0xd0
> Sep  8 22:26:03 localhost kernel: ? process_one_work+0x1a7/0x360
> ..
> Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-8041:22: detected PCI
> disconnect.
> Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-107ff:22:
> qla27xx_fwdt_entry_t262: dump ram MB failed. Area 5h start 198013h end 198013h
> Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-107ff:22: Unable to
> capture FW dump
> Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-1015:22: cmd=0x0,
> waited 5221 msecs
> Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-680d:22: mmio
> enabled returning.
> Sep  8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-d04c:22: MBX
> Command timeout for cmd 0, iocontrol=ffffffff jiffies=10140f2e5
> mb[0-3]=[0xffff 0xffff 0xffff 0xffff]
> 
> Cc: stable@vger.kernel.org
> Signed-off-by: Quinn Tran <qutran@marvell.com>
> Signed-off-by: Nilesh Javali <njavali@marvell.com>
> ---
> drivers/scsi/qla2xxx/qla_os.c   | 10 +++++++++-
> drivers/scsi/qla2xxx/qla_tmpl.c |  9 +++++++--
> 2 files changed, 16 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
> index 0a7b00d165c7..c4b4b4496399 100644
> --- a/drivers/scsi/qla2xxx/qla_os.c
> +++ b/drivers/scsi/qla2xxx/qla_os.c
> @@ -7639,7 +7639,7 @@ qla2xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
> 
> 	switch (state) {
> 	case pci_channel_io_normal:
> -		ha->flags.eeh_busy = 0;
> +		qla_pci_set_eeh_busy(vha);
> 		if (ql2xmqsupport || ql2xnvmeenable) {
> 			set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
> 			qla2xxx_wake_dpc(vha);
> @@ -7680,9 +7680,16 @@ qla2xxx_pci_mmio_enabled(struct pci_dev *pdev)
> 	       "mmio enabled\n");
> 
> 	ha->pci_error_state = QLA_PCI_MMIO_ENABLED;
> +
> 	if (IS_QLA82XX(ha))
> 		return PCI_ERS_RESULT_RECOVERED;
> 
> +	if (qla2x00_isp_reg_stat(ha)) {
> +		ql_log(ql_log_info, base_vha, 0x803f,
> +		    "During mmio enabled, PCI/Register disconnect still detected.\n");
> +		goto out;
> +	}
> +
> 	spin_lock_irqsave(&ha->hardware_lock, flags);
> 	if (IS_QLA2100(ha) || IS_QLA2200(ha)){
> 		stat = rd_reg_word(&reg->hccr);
> @@ -7704,6 +7711,7 @@ qla2xxx_pci_mmio_enabled(struct pci_dev *pdev)
> 		    "RISC paused -- mmio_enabled, Dumping firmware.\n");
> 		qla2xxx_dump_fw(base_vha);
> 	}
> +out:
> 	/* set PCI_ERS_RESULT_NEED_RESET to trigger call to qla2xxx_pci_slot_reset */
> 	ql_dbg(ql_dbg_aer, base_vha, 0x600d,
> 	       "mmio enabled returning.\n");
> diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
> index 26c13a953b97..b0a74b036cf4 100644
> --- a/drivers/scsi/qla2xxx/qla_tmpl.c
> +++ b/drivers/scsi/qla2xxx/qla_tmpl.c
> @@ -435,8 +435,13 @@ qla27xx_fwdt_entry_t266(struct scsi_qla_host *vha,
> {
> 	ql_dbg(ql_dbg_misc, vha, 0xd20a,
> 	    "%s: reset risc [%lx]\n", __func__, *len);
> -	if (buf)
> -		WARN_ON_ONCE(qla24xx_soft_reset(vha->hw) != QLA_SUCCESS);
> +	if (buf) {
> +		if (qla24xx_soft_reset(vha->hw) != QLA_SUCCESS) {
> +			ql_dbg(ql_dbg_async, vha, 0x5001,
> +			    "%s: unable to soft reset\n", __func__);
> +			return INVALID_ENTRY;
> +		}
> +	}
> 
> 	return qla27xx_next_entry(ent);
> }
> -- 
> 2.23.1
> 

Looks Good.

Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>

--
Himanshu Madhani	 Oracle Linux Engineering
diff mbox series

Patch

diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 0a7b00d165c7..c4b4b4496399 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -7639,7 +7639,7 @@  qla2xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
 
 	switch (state) {
 	case pci_channel_io_normal:
-		ha->flags.eeh_busy = 0;
+		qla_pci_set_eeh_busy(vha);
 		if (ql2xmqsupport || ql2xnvmeenable) {
 			set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
 			qla2xxx_wake_dpc(vha);
@@ -7680,9 +7680,16 @@  qla2xxx_pci_mmio_enabled(struct pci_dev *pdev)
 	       "mmio enabled\n");
 
 	ha->pci_error_state = QLA_PCI_MMIO_ENABLED;
+
 	if (IS_QLA82XX(ha))
 		return PCI_ERS_RESULT_RECOVERED;
 
+	if (qla2x00_isp_reg_stat(ha)) {
+		ql_log(ql_log_info, base_vha, 0x803f,
+		    "During mmio enabled, PCI/Register disconnect still detected.\n");
+		goto out;
+	}
+
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	if (IS_QLA2100(ha) || IS_QLA2200(ha)){
 		stat = rd_reg_word(&reg->hccr);
@@ -7704,6 +7711,7 @@  qla2xxx_pci_mmio_enabled(struct pci_dev *pdev)
 		    "RISC paused -- mmio_enabled, Dumping firmware.\n");
 		qla2xxx_dump_fw(base_vha);
 	}
+out:
 	/* set PCI_ERS_RESULT_NEED_RESET to trigger call to qla2xxx_pci_slot_reset */
 	ql_dbg(ql_dbg_aer, base_vha, 0x600d,
 	       "mmio enabled returning.\n");
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index 26c13a953b97..b0a74b036cf4 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -435,8 +435,13 @@  qla27xx_fwdt_entry_t266(struct scsi_qla_host *vha,
 {
 	ql_dbg(ql_dbg_misc, vha, 0xd20a,
 	    "%s: reset risc [%lx]\n", __func__, *len);
-	if (buf)
-		WARN_ON_ONCE(qla24xx_soft_reset(vha->hw) != QLA_SUCCESS);
+	if (buf) {
+		if (qla24xx_soft_reset(vha->hw) != QLA_SUCCESS) {
+			ql_dbg(ql_dbg_async, vha, 0x5001,
+			    "%s: unable to soft reset\n", __func__);
+			return INVALID_ENTRY;
+		}
+	}
 
 	return qla27xx_next_entry(ent);
 }