From: Reza Arbab <ar...@linux.ibm.com>
Add an mce notifier intended to service memcpy_mcsafe().
The notifier uses this heuristic; if a UE occurs when accessing device
memory, and the faulting instruction had a fixup entry, the callback
will return NOTIFY_STOP.
This causes the notification mechanism to consider the MCE handled and
continue execution at the fixup address, which returns -EFAULT from the
memcpy_mcsafe() call.
Signed-off-by: Reza Arbab <ar...@linux.ibm.com>
---
arch/powerpc/kernel/mce.c | 34 ++++++++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 0233c0ee45ab..a8348a9bea5b 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -56,6 +56,40 @@ int mce_unregister_notifier(struct notifier_block *nb)
return blocking_notifier_chain_unregister(&mce_notifier_list, nb);
}
+static int check_memcpy_mcsafe(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct machine_check_event *evt = data;
+ unsigned long pfn;
+ struct page *page;
+
+ if (evt->error_type != MCE_ERROR_TYPE_UE ||
+ !evt->u.ue_error.physical_address_provided)
+ return NOTIFY_DONE;
+
+ pfn = evt->u.ue_error.physical_address >> PAGE_SHIFT;
+ page = pfn_to_page(pfn);
+ if (!page)
+ return NOTIFY_DONE;
+
+ /* HMM and PMEM */
+ if (is_zone_device_page(page) && evt->u.ue_error.fixup_address_provided)
+ return NOTIFY_STOP;
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block memcpy_mcsafe_nb = {
+ .notifier_call = check_memcpy_mcsafe
+};
+
+static int __init mce_mcsafe_register(void)
+{
+ mce_register_notifier(&memcpy_mcsafe_nb);
+ return 0;
+}
+arch_initcall(mce_mcsafe_register);
+
static void mce_set_error_info(struct machine_check_event *mce,
struct mce_error_info *mce_err)
{
--
2.20.1
