From 2f7c68cb55ecb7331f2381deb497c27155f32faf Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 03 Jan 2024 09:43:39 +0000
Subject: [PATCH] update kernel to 5.10.198
---
kernel/drivers/scsi/qla2xxx/qla_os.c | 248 +++++++++++++++++++++++++++++--------------------
1 files changed, 148 insertions(+), 100 deletions(-)
diff --git a/kernel/drivers/scsi/qla2xxx/qla_os.c b/kernel/drivers/scsi/qla2xxx/qla_os.c
index 4191561..8d199de 100644
--- a/kernel/drivers/scsi/qla2xxx/qla_os.c
+++ b/kernel/drivers/scsi/qla2xxx/qla_os.c
@@ -879,8 +879,8 @@
goto qc24_fail_command;
}
- if (!fcport) {
- cmd->result = DID_NO_CONNECT << 16;
+ if (!fcport || fcport->deleted) {
+ cmd->result = DID_IMM_RETRY << 16;
goto qc24_fail_command;
}
@@ -961,8 +961,15 @@
goto qc24_fail_command;
}
- if (!fcport) {
+ if (!qpair->online) {
+ ql_dbg(ql_dbg_io, vha, 0x3077,
+ "qpair not online. eeh_busy=%d.\n", ha->flags.eeh_busy);
cmd->result = DID_NO_CONNECT << 16;
+ goto qc24_fail_command;
+ }
+
+ if (!fcport || fcport->deleted) {
+ cmd->result = DID_IMM_RETRY << 16;
goto qc24_fail_command;
}
@@ -1190,35 +1197,6 @@
return return_status;
}
-#define ISP_REG_DISCONNECT 0xffffffffU
-/**************************************************************************
-* qla2x00_isp_reg_stat
-*
-* Description:
-* Read the host status register of ISP before aborting the command.
-*
-* Input:
-* ha = pointer to host adapter structure.
-*
-*
-* Returns:
-* Either true or false.
-*
-* Note: Return true if there is register disconnect.
-**************************************************************************/
-static inline
-uint32_t qla2x00_isp_reg_stat(struct qla_hw_data *ha)
-{
- struct device_reg_24xx __iomem *reg = &ha->iobase->isp24;
- struct device_reg_82xx __iomem *reg82 = &ha->iobase->isp82;
-
- if (IS_P3P_TYPE(ha))
- return ((rd_reg_dword(®82->host_int)) == ISP_REG_DISCONNECT);
- else
- return ((rd_reg_dword(®->host_status)) ==
- ISP_REG_DISCONNECT);
-}
-
/**************************************************************************
* qla2xxx_eh_abort
*
@@ -1253,6 +1231,7 @@
if (qla2x00_isp_reg_stat(ha)) {
ql_log(ql_log_info, vha, 0x8042,
"PCI/Register disconnect, exiting.\n");
+ qla_pci_set_eeh_busy(vha);
return FAILED;
}
@@ -1444,6 +1423,7 @@
if (qla2x00_isp_reg_stat(ha)) {
ql_log(ql_log_info, vha, 0x803e,
"PCI/Register disconnect, exiting.\n");
+ qla_pci_set_eeh_busy(vha);
return FAILED;
}
@@ -1460,6 +1440,7 @@
if (qla2x00_isp_reg_stat(ha)) {
ql_log(ql_log_info, vha, 0x803f,
"PCI/Register disconnect, exiting.\n");
+ qla_pci_set_eeh_busy(vha);
return FAILED;
}
@@ -1495,6 +1476,7 @@
if (qla2x00_isp_reg_stat(ha)) {
ql_log(ql_log_info, vha, 0x8040,
"PCI/Register disconnect, exiting.\n");
+ qla_pci_set_eeh_busy(vha);
return FAILED;
}
@@ -1572,7 +1554,7 @@
if (qla2x00_isp_reg_stat(ha)) {
ql_log(ql_log_info, vha, 0x8041,
"PCI/Register disconnect, exiting.\n");
- schedule_work(&ha->board_disable);
+ qla_pci_set_eeh_busy(vha);
return SUCCESS;
}
@@ -1762,6 +1744,17 @@
for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
sp = req->outstanding_cmds[cnt];
if (sp) {
+ /*
+ * perform lockless completion during driver unload
+ */
+ if (qla2x00_chip_is_down(vha)) {
+ req->outstanding_cmds[cnt] = NULL;
+ spin_unlock_irqrestore(qp->qp_lock_ptr, flags);
+ sp->done(sp, res);
+ spin_lock_irqsave(qp->qp_lock_ptr, flags);
+ continue;
+ }
+
switch (sp->cmd_type) {
case TYPE_SRB:
qla2x00_abort_srb(qp, sp, res, &flags);
@@ -2855,7 +2848,6 @@
ha->max_exchg = FW_MAX_EXCHANGES_CNT;
atomic_set(&ha->num_pend_mbx_stage1, 0);
atomic_set(&ha->num_pend_mbx_stage2, 0);
- atomic_set(&ha->num_pend_mbx_stage3, 0);
atomic_set(&ha->zio_threshold, DEFAULT_ZIO_THRESHOLD);
ha->last_zio_threshold = DEFAULT_ZIO_THRESHOLD;
@@ -3130,6 +3122,13 @@
host->max_id = ha->max_fibre_devices;
host->cmd_per_lun = 3;
host->unique_id = host->host_no;
+
+ if (ql2xenabledif && ql2xenabledif != 2) {
+ ql_log(ql_log_warn, base_vha, 0x302d,
+ "Invalid value for ql2xenabledif, resetting it to default (2)\n");
+ ql2xenabledif = 2;
+ }
+
if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif)
host->max_cmd_len = 32;
else
@@ -3362,8 +3361,6 @@
base_vha->flags.difdix_supported = 1;
ql_dbg(ql_dbg_init, base_vha, 0x00f1,
"Registering for DIF/DIX type 1 and 3 protection.\n");
- if (ql2xenabledif == 1)
- prot = SHOST_DIX_TYPE0_PROTECTION;
if (ql2xprotmask)
scsi_host_set_prot(host, ql2xprotmask);
else
@@ -4866,7 +4863,8 @@
}
INIT_DELAYED_WORK(&vha->scan.scan_work, qla_scan_work_fn);
- sprintf(vha->host_str, "%s_%lu", QLA2XXX_DRIVER_NAME, vha->host_no);
+ snprintf(vha->host_str, sizeof(vha->host_str), "%s_%lu",
+ QLA2XXX_DRIVER_NAME, vha->host_no);
ql_dbg(ql_dbg_init, vha, 0x0041,
"Allocated the host=%p hw=%p vha=%p dev_name=%s",
vha->host, vha->hw, vha,
@@ -6660,6 +6658,9 @@
schedule();
+ if (test_and_clear_bit(DO_EEH_RECOVERY, &base_vha->dpc_flags))
+ qla_pci_set_eeh_busy(base_vha);
+
if (!base_vha->flags.init_done || ha->flags.mbox_busy)
goto end_loop;
@@ -6899,9 +6900,12 @@
}
}
loop_resync_check:
- if (test_and_clear_bit(LOOP_RESYNC_NEEDED,
+ if (!qla2x00_reset_active(base_vha) &&
+ test_and_clear_bit(LOOP_RESYNC_NEEDED,
&base_vha->dpc_flags)) {
-
+ /*
+ * Allow abort_isp to complete before moving on to scanning.
+ */
ql_dbg(ql_dbg_dpc, base_vha, 0x400f,
"Loop resync scheduled.\n");
@@ -6953,26 +6957,21 @@
mutex_unlock(&ha->mq_lock);
}
- if (test_and_clear_bit(SET_NVME_ZIO_THRESHOLD_NEEDED,
- &base_vha->dpc_flags)) {
- ql_log(ql_log_info, base_vha, 0xffffff,
- "nvme: SET ZIO Activity exchange threshold to %d.\n",
- ha->nvme_last_rptd_aen);
- if (qla27xx_set_zio_threshold(base_vha,
- ha->nvme_last_rptd_aen)) {
- ql_log(ql_log_info, base_vha, 0xffffff,
- "nvme: Unable to SET ZIO Activity exchange threshold to %d.\n",
- ha->nvme_last_rptd_aen);
- }
- }
-
if (test_and_clear_bit(SET_ZIO_THRESHOLD_NEEDED,
- &base_vha->dpc_flags)) {
+ &base_vha->dpc_flags)) {
+ u16 threshold = ha->nvme_last_rptd_aen + ha->last_zio_threshold;
+
+ if (threshold > ha->orig_fw_xcb_count)
+ threshold = ha->orig_fw_xcb_count;
+
ql_log(ql_log_info, base_vha, 0xffffff,
- "SET ZIO Activity exchange threshold to %d.\n",
- ha->last_zio_threshold);
- qla27xx_set_zio_threshold(base_vha,
- ha->last_zio_threshold);
+ "SET ZIO Activity exchange threshold to %d.\n",
+ threshold);
+ if (qla27xx_set_zio_threshold(base_vha, threshold)) {
+ ql_log(ql_log_info, base_vha, 0xffffff,
+ "Unable to SET ZIO Activity exchange threshold to %d.\n",
+ threshold);
+ }
}
if (!IS_QLAFX00(ha))
@@ -7145,7 +7144,7 @@
/* if the loop has been down for 4 minutes, reinit adapter */
if (atomic_dec_and_test(&vha->loop_down_timer) != 0) {
- if (!(vha->device_flags & DFLG_NO_CABLE)) {
+ if (!(vha->device_flags & DFLG_NO_CABLE) && !vha->vp_idx) {
ql_log(ql_log_warn, vha, 0x6009,
"Loop down - aborting ISP.\n");
@@ -7190,14 +7189,13 @@
index = atomic_read(&ha->nvme_active_aen_cnt);
if (!vha->vp_idx &&
(index != ha->nvme_last_rptd_aen) &&
- (index >= DEFAULT_ZIO_THRESHOLD) &&
ha->zio_mode == QLA_ZIO_MODE_6 &&
!ha->flags.host_shutting_down) {
+ ha->nvme_last_rptd_aen = atomic_read(&ha->nvme_active_aen_cnt);
ql_log(ql_log_info, vha, 0x3002,
"nvme: Sched: Set ZIO exchange threshold to %d.\n",
ha->nvme_last_rptd_aen);
- ha->nvme_last_rptd_aen = atomic_read(&ha->nvme_active_aen_cnt);
- set_bit(SET_NVME_ZIO_THRESHOLD_NEEDED, &vha->dpc_flags);
+ set_bit(SET_ZIO_THRESHOLD_NEEDED, &vha->dpc_flags);
start_dpc++;
}
@@ -7370,6 +7368,8 @@
int i;
unsigned long flags;
+ ql_dbg(ql_dbg_aer, vha, 0x9000,
+ "%s\n", __func__);
ha->chip_reset++;
ha->base_qpair->chip_reset = ha->chip_reset;
@@ -7379,28 +7379,16 @@
ha->base_qpair->chip_reset;
}
- /* purge MBox commands */
- if (atomic_read(&ha->num_pend_mbx_stage3)) {
- clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
- complete(&ha->mbx_intr_comp);
- }
-
- i = 0;
-
- while (atomic_read(&ha->num_pend_mbx_stage3) ||
- atomic_read(&ha->num_pend_mbx_stage2) ||
- atomic_read(&ha->num_pend_mbx_stage1)) {
- msleep(20);
- i++;
- if (i > 50)
- break;
- }
-
- ha->flags.purge_mbox = 0;
+ /*
+ * purge mailbox might take a while. Slot Reset/chip reset
+ * will take care of the purge
+ */
mutex_lock(&ha->mq_lock);
+ ha->base_qpair->online = 0;
list_for_each_entry(qpair, &base_vha->qp_list, qp_list_elem)
qpair->online = 0;
+ wmb();
mutex_unlock(&ha->mq_lock);
qla2x00_mark_all_devices_lost(vha);
@@ -7437,14 +7425,17 @@
{
scsi_qla_host_t *vha = pci_get_drvdata(pdev);
struct qla_hw_data *ha = vha->hw;
+ pci_ers_result_t ret = PCI_ERS_RESULT_NEED_RESET;
- ql_dbg(ql_dbg_aer, vha, 0x9000,
- "PCI error detected, state %x.\n", state);
+ ql_log(ql_log_warn, vha, 0x9000,
+ "PCI error detected, state %x.\n", state);
+ ha->pci_error_state = QLA_PCI_ERR_DETECTED;
if (!atomic_read(&pdev->enable_cnt)) {
ql_log(ql_log_info, vha, 0xffff,
"PCI device is disabled,state %x\n", state);
- return PCI_ERS_RESULT_NEED_RESET;
+ ret = PCI_ERS_RESULT_NEED_RESET;
+ goto out;
}
switch (state) {
@@ -7454,11 +7445,12 @@
set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
qla2xxx_wake_dpc(vha);
}
- return PCI_ERS_RESULT_CAN_RECOVER;
+ ret = PCI_ERS_RESULT_CAN_RECOVER;
+ break;
case pci_channel_io_frozen:
- ha->flags.eeh_busy = 1;
- qla_pci_error_cleanup(vha);
- return PCI_ERS_RESULT_NEED_RESET;
+ qla_pci_set_eeh_busy(vha);
+ ret = PCI_ERS_RESULT_NEED_RESET;
+ break;
case pci_channel_io_perm_failure:
ha->flags.pci_channel_io_perm_failure = 1;
qla2x00_abort_all_cmds(vha, DID_NO_CONNECT << 16);
@@ -7466,9 +7458,12 @@
set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
qla2xxx_wake_dpc(vha);
}
- return PCI_ERS_RESULT_DISCONNECT;
+ ret = PCI_ERS_RESULT_DISCONNECT;
}
- return PCI_ERS_RESULT_NEED_RESET;
+out:
+ ql_dbg(ql_dbg_aer, vha, 0x600d,
+ "PCI error detected returning [%x].\n", ret);
+ return ret;
}
static pci_ers_result_t
@@ -7482,6 +7477,10 @@
struct device_reg_2xxx __iomem *reg = &ha->iobase->isp;
struct device_reg_24xx __iomem *reg24 = &ha->iobase->isp24;
+ ql_log(ql_log_warn, base_vha, 0x9000,
+ "mmio enabled\n");
+
+ ha->pci_error_state = QLA_PCI_MMIO_ENABLED;
if (IS_QLA82XX(ha))
return PCI_ERS_RESULT_RECOVERED;
@@ -7505,10 +7504,11 @@
ql_log(ql_log_info, base_vha, 0x9003,
"RISC paused -- mmio_enabled, Dumping firmware.\n");
qla2xxx_dump_fw(base_vha);
-
- return PCI_ERS_RESULT_NEED_RESET;
- } else
- return PCI_ERS_RESULT_RECOVERED;
+ }
+ /* 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");
+ return PCI_ERS_RESULT_NEED_RESET;
}
static pci_ers_result_t
@@ -7520,9 +7520,10 @@
int rc;
struct qla_qpair *qpair = NULL;
- ql_dbg(ql_dbg_aer, base_vha, 0x9004,
- "Slot Reset.\n");
+ ql_log(ql_log_warn, base_vha, 0x9004,
+ "Slot Reset.\n");
+ ha->pci_error_state = QLA_PCI_SLOT_RESET;
/* Workaround: qla2xxx driver which access hardware earlier
* needs error state to be pci_channel_io_online.
* Otherwise mailbox command timesout.
@@ -7556,16 +7557,24 @@
qpair->online = 1;
mutex_unlock(&ha->mq_lock);
+ ha->flags.eeh_busy = 0;
base_vha->flags.online = 1;
set_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags);
- if (ha->isp_ops->abort_isp(base_vha) == QLA_SUCCESS)
- ret = PCI_ERS_RESULT_RECOVERED;
+ ha->isp_ops->abort_isp(base_vha);
clear_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags);
+ if (qla2x00_isp_reg_stat(ha)) {
+ ha->flags.eeh_busy = 1;
+ qla_pci_error_cleanup(base_vha);
+ ql_log(ql_log_warn, base_vha, 0x9005,
+ "Device unable to recover from PCI error.\n");
+ } else {
+ ret = PCI_ERS_RESULT_RECOVERED;
+ }
exit_slot_reset:
ql_dbg(ql_dbg_aer, base_vha, 0x900e,
- "slot_reset return %x.\n", ret);
+ "Slot Reset returning %x.\n", ret);
return ret;
}
@@ -7577,16 +7586,55 @@
struct qla_hw_data *ha = base_vha->hw;
int ret;
- ql_dbg(ql_dbg_aer, base_vha, 0x900f,
- "pci_resume.\n");
+ ql_log(ql_log_warn, base_vha, 0x900f,
+ "Pci Resume.\n");
- ha->flags.eeh_busy = 0;
ret = qla2x00_wait_for_hba_online(base_vha);
if (ret != QLA_SUCCESS) {
ql_log(ql_log_fatal, base_vha, 0x9002,
"The device failed to resume I/O from slot/link_reset.\n");
}
+ ha->pci_error_state = QLA_PCI_RESUME;
+ ql_dbg(ql_dbg_aer, base_vha, 0x600d,
+ "Pci Resume returning.\n");
+}
+
+void qla_pci_set_eeh_busy(struct scsi_qla_host *vha)
+{
+ struct qla_hw_data *ha = vha->hw;
+ struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+ bool do_cleanup = false;
+ unsigned long flags;
+
+ if (ha->flags.eeh_busy)
+ return;
+
+ spin_lock_irqsave(&base_vha->work_lock, flags);
+ if (!ha->flags.eeh_busy) {
+ ha->flags.eeh_busy = 1;
+ do_cleanup = true;
+ }
+ spin_unlock_irqrestore(&base_vha->work_lock, flags);
+
+ if (do_cleanup)
+ qla_pci_error_cleanup(base_vha);
+}
+
+/*
+ * this routine will schedule a task to pause IO from interrupt context
+ * if caller sees a PCIE error event (register read = 0xf's)
+ */
+void qla_schedule_eeh_work(struct scsi_qla_host *vha)
+{
+ struct qla_hw_data *ha = vha->hw;
+ struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+
+ if (ha->flags.eeh_busy)
+ return;
+
+ set_bit(DO_EEH_RECOVERY, &base_vha->dpc_flags);
+ qla2xxx_wake_dpc(base_vha);
}
static void
--
Gitblit v1.6.2