We needn't the the whole backtrace other than one-line message in
the error reporting interrupt handler. For errors triggered by
access PCI config space or MMIO, we replace "WARN(1, ...)" with
pr_err() and dump_stack(). The patch also adds more output messages
to indicate what EEH core is doing. Besides, some printk() are
replaced with pr_warning().
Signed-off-by: Gavin Shan <sha...@linux.vnet.ibm.com>
---
arch/powerpc/kernel/eeh.c | 9 +++++++--
arch/powerpc/kernel/eeh_driver.c | 23 ++++++++++++++++++-----
arch/powerpc/platforms/powernv/eeh-ioda.c | 25 ++++++++++++++++---------
3 files changed, 41 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 2dd0bd1..f7f2775 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -324,7 +324,9 @@ static int eeh_phb_check_failure(struct eeh_pe *pe)
eeh_serialize_unlock(flags);
eeh_send_failure_event(phb_pe);
- WARN(1, "EEH: PHB failure detected\n");
+ pr_err("EEH: PHB#%x failure detected\n",
+ phb_pe->phb->global_number);
+ dump_stack();
return 1;
out:
@@ -453,7 +455,10 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
* a stack trace will help the device-driver authors figure
* out what happened. So print that out.
*/
- WARN(1, "EEH: failure detected\n");
+ pr_err("EEH: Frozen PE#%x detected on PHB#%x\n",
+ pe->addr, pe->phb->global_number);
+ dump_stack();
+
return 1;
dn_unlock:
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 0974e13..2b1ce17 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -425,6 +425,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
* status ... if any child can't handle the reset, then the entire
* slot is dlpar removed and added.
*/
+ pr_info("EEH: Notify device drivers to shutdown\n");
eeh_pe_dev_traverse(pe, eeh_report_error, &result);
/* Get the current PCI slot state. This can take a long time,
@@ -432,7 +433,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
*/
rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
- printk(KERN_WARNING "EEH: Permanent failure\n");
+ pr_warning("EEH: Permanent failure\n");
goto hard_fail;
}
@@ -440,6 +441,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
* don't post the error log until after all dev drivers
* have been informed.
*/
+ pr_info("EEH: Collect temporary log\n");
eeh_slot_error_detail(pe, EEH_LOG_TEMP);
/* If all device drivers were EEH-unaware, then shut
@@ -447,15 +449,18 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
* go down willingly, without panicing the system.
*/
if (result == PCI_ERS_RESULT_NONE) {
+ pr_info("EEH: Reset with hotplug activity\n");
rc = eeh_reset_device(pe, frozen_bus);
if (rc) {
- printk(KERN_WARNING "EEH: Unable to reset, rc=%d\n",
rc);
+ pr_warning("%s: Unable to reset, err=%d\n",
+ __func__, rc);
goto hard_fail;
}
}
/* If all devices reported they can proceed, then re-enable MMIO */
if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+ pr_info("EEH: Enable I/O for affected devices\n");
rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
if (rc < 0)
@@ -463,6 +468,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
if (rc) {
result = PCI_ERS_RESULT_NEED_RESET;
} else {
+ pr_info("EEH: Notify device drivers to resume I/O\n");
result = PCI_ERS_RESULT_NONE;
eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled,
&result);
}
@@ -470,6 +476,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
/* If all devices reported they can proceed, then re-enable DMA */
if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+ pr_info("EEH: Enabled DMA for affected devices\n");
rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
if (rc < 0)
@@ -482,17 +489,22 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
/* If any device has a hard failure, then shut off everything. */
if (result == PCI_ERS_RESULT_DISCONNECT) {
- printk(KERN_WARNING "EEH: Device driver gave up\n");
+ pr_warning("EEH: Device driver gave up\n");
goto hard_fail;
}
/* If any device called out for a reset, then reset the slot */
if (result == PCI_ERS_RESULT_NEED_RESET) {
+ pr_info("EEH: Reset without hotplug activity\n");
rc = eeh_reset_device(pe, NULL);
if (rc) {
- printk(KERN_WARNING "EEH: Cannot reset, rc=%d\n", rc);
+ pr_warning("%s: Cannot reset, err=%d\n",
+ __func__, rc);
goto hard_fail;
}
+
+ pr_info("EEH: Notify device drivers "
+ "the completion of reset\n");
result = PCI_ERS_RESULT_NONE;
eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
}
@@ -500,11 +512,12 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
/* All devices should claim they have recovered by now. */
if ((result != PCI_ERS_RESULT_RECOVERED) &&
(result != PCI_ERS_RESULT_NONE)) {
- printk(KERN_WARNING "EEH: Not recovered\n");
+ pr_warning("EEH: Not recovered\n");
goto hard_fail;
}
/* Tell all device drivers that they can resume operations */
+ pr_info("EEH: Notify device driver to resume\n");
eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
return;
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c
b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 85025d7..0cd1c4a 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -853,11 +853,14 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
phb->eeh_state |= PNV_EEH_STATE_REMOVED;
}
- WARN(1, "EEH: dead IOC detected\n");
+ pr_err("EEH: dead IOC detected\n");
ret = 4;
goto out;
- } else if (severity == OPAL_EEH_SEV_INF)
+ } else if (severity == OPAL_EEH_SEV_INF) {
+ pr_info("EEH: IOC informative error "
+ "detected\n");
ioda_eeh_hub_diag(hose);
+ }
break;
case OPAL_EEH_PHB_ERROR:
@@ -865,8 +868,8 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
if (ioda_eeh_get_phb_pe(hose, pe))
break;
- WARN(1, "EEH: dead PHB#%x detected\n",
- hose->global_number);
+ pr_err("EEH: dead PHB#%x detected\n",
+ hose->global_number);
phb->eeh_state |= PNV_EEH_STATE_REMOVED;
ret = 3;
goto out;
@@ -874,20 +877,24 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
if (ioda_eeh_get_phb_pe(hose, pe))
break;
- WARN(1, "EEH: fenced PHB#%x detected\n",
- hose->global_number);
+ pr_err("EEH: fenced PHB#%x detected\n",
+ hose->global_number);
ret = 2;
goto out;
- } else if (severity == OPAL_EEH_SEV_INF)
+ } else if (severity == OPAL_EEH_SEV_INF) {
+ pr_info("EEH: PHB#%x informative error "
+ "detected\n",
+ hose->global_number);
ioda_eeh_phb_diag(hose);
+ }
break;
case OPAL_EEH_PE_ERROR:
if (ioda_eeh_get_pe(hose, frozen_pe_no, pe))
break;
- WARN(1, "EEH: Frozen PE#%x on PHB#%x detected\n",
- (*pe)->addr, (*pe)->phb->global_number);
+ pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
+ (*pe)->addr, (*pe)->phb->global_number);
ret = 1;
goto out;
}
--
1.7.5.4
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
