@@ -28,6 +28,7 @@
#include <linux/pci.h>
#include <linux/proc_fs.h>
#include <linux/rbtree.h>
+#include <linux/reboot.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/export.h>
@@ -747,6 +748,17 @@ int __exit eeh_ops_unregister(const char *name)
return -EEXIST;
}
+static int eeh_reboot_notifier(struct notifier_block *nb,
+ unsigned long action, void *unused)
+{
+ eeh_set_enable(false);
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_reboot_nb = {
+ .notifier_call = eeh_reboot_notifier,
+};
+
/**
* eeh_init - EEH initialization
*
@@ -778,6 +790,14 @@ int eeh_init(void)
if (machine_is(powernv) && cnt++ <= 0)
return ret;
+ /* Register reboot notifier */
+ ret = register_reboot_notifier(&eeh_reboot_nb);
+ if (ret) {
+ pr_warn("%s: Failed to register notifier (%d)\n",
+ __func__, ret);
+ return ret;
+ }
+
/* call platform initialization function */
if (!eeh_ops) {
pr_warning("%s: Platform EEH operation not found\n",
@@ -44,7 +44,8 @@ static int ioda_eeh_event(struct notifier_block *nb,
/* We simply send special EEH event */
if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
- (events & OPAL_EVENT_PCI_ERROR))
+ (events & OPAL_EVENT_PCI_ERROR) &&
+ eeh_enabled())
eeh_send_failure_event(NULL);
return 0;
We possiblly detect EEH errors during reboot, particularly in kexec path, but it's impossible for device drivers and EEH core to handle or recover them properly. The patch registers one reboot notifier for EEH and disable EEH subsystem during reboot. That means the EEH errors is going to be cleared by hardware reset or second kernel during early stage of PCI probe. Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com> --- arch/powerpc/kernel/eeh.c | 20 ++++++++++++++++++++ arch/powerpc/platforms/powernv/eeh-ioda.c | 3 ++- 2 files changed, 22 insertions(+), 1 deletion(-)