@@ -55,6 +55,21 @@ config ACPI_APEI_SEA
option allows the OS to look for such hardware error record, and
take appropriate action.
+config ACPI_APEI_SEI
+ bool "APEI SError(System Error) Interrupt logging/recovering support"
+ depends on ARM64 && ACPI_APEI_GHES
+ default y
+ help
+ This option should be enabled if the system supports
+ firmware first handling of SEI (SError interrupt).
+
+ SEI happens with asynchronous external abort for errors on device
+ memory reads on ARMv8 systems. If a system supports firmware first
+ handling of SEI, the platform analyzes and handles hardware error
+ notifications from SEI, and it may then form a hardware error record for
+ the OS to parse and handle. This option allows the OS to look for
+ such hardware error record, and take appropriate action.
+
config ACPI_APEI_MEMORY_FAILURE
bool "APEI memory error recovering support"
depends on ACPI_APEI && MEMORY_FAILURE
@@ -827,6 +827,46 @@ static inline void ghes_sea_add(struct ghes *ghes) { }
static inline void ghes_sea_remove(struct ghes *ghes) { }
#endif /* CONFIG_ACPI_APEI_SEA */
+#ifdef CONFIG_ACPI_APEI_SEI
+static LIST_HEAD(ghes_sei);
+
+/*
+ * Return 0 only if one of the SEI error sources successfully reported an error
+ * record sent from the firmware.
+ */
+int ghes_notify_sei(void)
+{
+ struct ghes *ghes;
+ int ret = -ENOENT;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ghes, &ghes_sei, list) {
+ if (!ghes_proc(ghes))
+ ret = 0;
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+static void ghes_sei_add(struct ghes *ghes)
+{
+ mutex_lock(&ghes_list_mutex);
+ list_add_rcu(&ghes->list, &ghes_sei);
+ mutex_unlock(&ghes_list_mutex);
+}
+
+static void ghes_sei_remove(struct ghes *ghes)
+{
+ mutex_lock(&ghes_list_mutex);
+ list_del_rcu(&ghes->list);
+ mutex_unlock(&ghes_list_mutex);
+ synchronize_rcu();
+}
+#else /* CONFIG_ACPI_APEI_SEI */
+static inline void ghes_sei_add(struct ghes *ghes) { }
+static inline void ghes_sei_remove(struct ghes *ghes) { }
+#endif /* CONFIG_ACPI_APEI_SEI */
+
#ifdef CONFIG_HAVE_ACPI_APEI_NMI
/*
* printk is not safe in NMI context. So in NMI handler, we allocate
@@ -1055,6 +1095,13 @@ static int ghes_probe(struct platform_device *ghes_dev)
goto err;
}
break;
+ case ACPI_HEST_NOTIFY_SEI:
+ if (!IS_ENABLED(CONFIG_ACPI_APEI_SEI)) {
+ pr_warn(GHES_PFX "Generic hardware error source: %d notified via SEI is not supported!\n",
+ generic->header.source_id);
+ goto err;
+ }
+ break;
case ACPI_HEST_NOTIFY_NMI:
if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) {
pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n",
@@ -1126,6 +1173,9 @@ static int ghes_probe(struct platform_device *ghes_dev)
case ACPI_HEST_NOTIFY_SEA:
ghes_sea_add(ghes);
break;
+ case ACPI_HEST_NOTIFY_SEI:
+ ghes_sei_add(ghes);
+ break;
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_add(ghes);
break;
@@ -1179,6 +1229,9 @@ static int ghes_remove(struct platform_device *ghes_dev)
case ACPI_HEST_NOTIFY_SEA:
ghes_sea_remove(ghes);
break;
+ case ACPI_HEST_NOTIFY_SEI:
+ ghes_sei_remove(ghes);
+ break;
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_remove(ghes);
break;
@@ -120,5 +120,6 @@ static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata)
section = acpi_hest_get_next(section))
int ghes_notify_sea(void);
+int ghes_notify_sei(void);
#endif /* GHES_H */
ACPI 6.x adds support for NOTIFY_SEI as a GHES notification mechanism, so add new GHES notification handling functions. Expose API ghes_notify_sei() to arch code, arch code will call this API when it gets this NOTIFY_SEI. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Note: Firmware will follow the SError mask rule, if the SError is masked, the firmware will not deliver NOTIFY_SEI notification. --- drivers/acpi/apei/Kconfig | 15 ++++++++++++++ drivers/acpi/apei/ghes.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++ include/acpi/ghes.h | 1 + 3 files changed, 69 insertions(+)