powerpc/mce: Add MCE notification chain

Introduce notification chain which lets us know about uncorrected memory
errors(UE). This would help prospective users in pmem or nvdimm subsystem
to track bad blocks for better handling of persistent memory allocations.

Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
Signed-off-by: Ganesh Goudar <ganeshgr@linux.ibm.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200709135142.721504-1-santosh@fossix.org

diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 376a395..7bdd0cd 100644 (file)
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -220,6 +220,8 @@ extern void machine_check_print_event_info(struct machine_check_event *evt,
 unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr);
 extern void mce_common_process_ue(struct pt_regs *regs,
                                  struct mce_error_info *mce_err);
+int mce_register_notifier(struct notifier_block *nb);
+int mce_unregister_notifier(struct notifier_block *nb);
 #ifdef CONFIG_PPC_BOOK3S_64
 void flush_and_reload_slb(void);
 #endif /* CONFIG_PPC_BOOK3S_64 */

diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index fd90c0e..b7b3ed4 100644 (file)
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -49,6 +49,20 @@ static struct irq_work mce_ue_event_irq_work = {
 
 DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
 
+static BLOCKING_NOTIFIER_HEAD(mce_notifier_list);
+
+int mce_register_notifier(struct notifier_block *nb)
+{
+       return blocking_notifier_chain_register(&mce_notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(mce_register_notifier);
+
+int mce_unregister_notifier(struct notifier_block *nb)
+{
+       return blocking_notifier_chain_unregister(&mce_notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(mce_unregister_notifier);
+
 static void mce_set_error_info(struct machine_check_event *mce,
                               struct mce_error_info *mce_err)
 {
@@ -278,6 +292,7 @@ static void machine_process_ue_event(struct work_struct *work)
        while (__this_cpu_read(mce_ue_count) > 0) {
                index = __this_cpu_read(mce_ue_count) - 1;
                evt = this_cpu_ptr(&mce_ue_event_queue[index]);
+               blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
 #ifdef CONFIG_MEMORY_FAILURE
                /*
                 * This should probably queued elsewhere, but