EDAC/ghes: Add a notifier for reporting memory errors

In order to make it a proper module and disentangle it from facilities,
add a notifier for reporting memory errors. Use an atomic notifier
because calls sites like ghes_proc_in_irq() run in interrupt context.

  [ bp: Massage commit message. ]

Suggested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Jia He <justin.he@arm.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20221010023559.69655-3-justin.he@arm.com

2 files changed, 32 insertions, 3 deletions

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 80ad530583c9..55013e024ba3 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -94,6 +94,8 @@
 #define FIX_APEI_GHES_SDEI_CRITICAL	__end_of_fixed_addresses
 #endif
 
+static ATOMIC_NOTIFIER_HEAD(ghes_report_chain);
+
 static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 {
 	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
@@ -645,7 +647,7 @@ static bool ghes_do_proc(struct ghes *ghes,
 		if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
 			struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
 
-			ghes_edac_report_mem_error(sev, mem_err);
+			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
 			queued = ghes_handle_memory_failure(gdata, sev);
@@ -1497,3 +1499,15 @@ void __init acpi_ghes_init(void)
 	else
 		pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");
 }
+
+void ghes_register_report_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_register(&ghes_report_chain, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_register_report_chain);
+
+void ghes_unregister_report_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_unregister(&ghes_report_chain, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_unregister_report_chain);
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index c8fa7dcfdbd0..7b8d56a769f6 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -14,6 +14,7 @@
 #include <linux/dmi.h>
 #include "edac_module.h"
 #include <ras/ras_event.h>
+#include <linux/notifier.h>
 
 #define OTHER_DETAIL_LEN	400
 
@@ -267,11 +268,14 @@ out:
 	return n;
 }
 
-void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
+static int ghes_edac_report_mem_error(struct notifier_block *nb,
+				      unsigned long val, void *data)
 {
+	struct cper_sec_mem_err *mem_err = (struct cper_sec_mem_err *)data;
 	struct cper_mem_err_compact cmem;
 	struct edac_raw_error_desc *e;
 	struct mem_ctl_info *mci;
+	unsigned long sev = val;
 	struct ghes_pvt *pvt;
 	unsigned long flags;
 	char *p;
@@ -282,7 +286,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 	 * know.
 	 */
 	if (WARN_ON_ONCE(in_nmi()))
-		return;
+		return NOTIFY_OK;
 
 	spin_lock_irqsave(&ghes_lock, flags);
 
@@ -374,8 +378,15 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 unlock:
 	spin_unlock_irqrestore(&ghes_lock, flags);
+
+	return NOTIFY_OK;
 }
 
+static struct notifier_block ghes_edac_mem_err_nb = {
+	.notifier_call	= ghes_edac_report_mem_error,
+	.priority	= 0,
+};
+
 /*
  * Known systems that are safe to enable this module.
  */
@@ -503,6 +514,8 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
 	ghes_pvt = pvt;
 	spin_unlock_irqrestore(&ghes_lock, flags);
 
+	ghes_register_report_chain(&ghes_edac_mem_err_nb);
+
 	/* only set on success */
 	refcount_set(&ghes_refcount, 1);
 
@@ -548,6 +561,8 @@ void ghes_edac_unregister(struct ghes *ghes)
 	if (mci)
 		edac_mc_free(mci);
 
+	ghes_unregister_report_chain(&ghes_edac_mem_err_nb);
+
 unlock:
 	mutex_unlock(&ghes_reg_mutex);
 }