[PATCH v2] acpi: apei: Add SEI notification type support for ARMv8

From: Dongjiu Geng
Date: Thu Sep 14 2017 - 03:00:05 EST


ARMv8.2 requires implementation of the RAS extension, in
this extension it adds SEI(SError Interrupt) notification
type, this patch adds new GHES error source SEI handling
functions. Because this error source parsing and handling
methods are similar with the SEA. so share some SEA handling
functions with the SEI

Expose one API ghes_notify_abort() to external users. External
modules can call this exposed API to parse and handling the
SEA or SEI.

Note: For the SEI(SError Interrupt), because it is asynchronous
external abort, the error address is not accurate, so EL3 firmware
should identify the address to a invalid value.

Signed-off-by: Dongjiu Geng <gengdongjiu@xxxxxxxxxx>
---
arch/arm64/Kconfig | 4 ++--
arch/arm64/mm/fault.c | 4 ++--
drivers/acpi/apei/Kconfig | 15 +++++++++++++
drivers/acpi/apei/ghes.c | 56 +++++++++++++++++++++++++++++++++++------------
include/acpi/ghes.h | 2 +-
5 files changed, 62 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4d87aa963d83..9989ecce9a72 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -21,7 +21,7 @@ config ARM64
select ARCH_HAS_STRICT_KERNEL_RWX
select ARCH_HAS_STRICT_MODULE_RWX
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
- select ARCH_HAVE_NMI_SAFE_CMPXCHG if ACPI_APEI_SEA
+ select ARCH_HAVE_NMI_SAFE_CMPXCHG if (ACPI_APEI_SEA || ACPI_APEI_SEI)
select ARCH_USE_CMPXCHG_LOCKREF
select ARCH_SUPPORTS_MEMORY_FAILURE
select ARCH_SUPPORTS_ATOMIC_RMW
@@ -97,7 +97,7 @@ config ARM64
select HAVE_IRQ_TIME_ACCOUNTING
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP if NUMA
- select HAVE_NMI if ACPI_APEI_SEA
+ select HAVE_NMI if (ACPI_APEI_SEA || ACPI_APEI_SEI)
select HAVE_PATA_PLATFORM
select HAVE_PERF_EVENTS
select HAVE_PERF_REGS
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2509e4fe6992..c98c1b30aab5 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -585,7 +585,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
if (interrupts_enabled(regs))
nmi_enter();

- ret = ghes_notify_sea();
+ ret = ghes_notify_abort(ACPI_HEST_NOTIFY_SEA);

if (interrupts_enabled(regs))
nmi_exit();
@@ -682,7 +682,7 @@ int handle_guest_sea(phys_addr_t addr, unsigned int esr)
int ret = -ENOENT;

if (IS_ENABLED(CONFIG_ACPI_APEI_SEA))
- ret = ghes_notify_sea();
+ ret = ghes_notify_abort(ACPI_HEST_NOTIFY_SEA);

return ret;
}
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index de14d49a5c90..47fcb0c82e1e 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -54,6 +54,21 @@ 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 Asynchronous SError 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 (asynchronous 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 HW 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
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index c15a08db2c7c..47be1841f9fe 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -814,33 +814,52 @@ static struct notifier_block ghes_notifier_hed = {
};

static LIST_HEAD(ghes_sea);
+static LIST_HEAD(ghes_sei);

/*
- * Return 0 only if one of the SEA error sources successfully reported an error
+ * Return 0 only if one of the SEA or SEI error sources successfully reported an error
* record sent from the firmware.
*/
-int ghes_notify_sea(void)
+int ghes_notify_abort(u8 type)
{
struct ghes *ghes;
+ struct list_head *head = NULL;
int ret = -ENOENT;

- rcu_read_lock();
- list_for_each_entry_rcu(ghes, &ghes_sea, list) {
- if (!ghes_proc(ghes))
- ret = 0;
+ if (type == ACPI_HEST_NOTIFY_SEA)
+ head = &ghes_sea;
+ else if (type == ACPI_HEST_NOTIFY_SEI)
+ head = &ghes_sei;
+
+ if (head) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(ghes, head, list) {
+ if (!ghes_proc(ghes))
+ ret = 0;
+ }
+ rcu_read_unlock();
}
- rcu_read_unlock();
return ret;
}

-static void ghes_sea_add(struct ghes *ghes)
+static void ghes_abort_add(struct ghes *ghes)
{
- mutex_lock(&ghes_list_mutex);
- list_add_rcu(&ghes->list, &ghes_sea);
- mutex_unlock(&ghes_list_mutex);
+ struct list_head *head = NULL;
+ u8 notify_type = ghes->generic->notify.type;
+
+ if (notify_type == ACPI_HEST_NOTIFY_SEA)
+ head = &ghes_sea;
+ else if (notify_type == ACPI_HEST_NOTIFY_SEI)
+ head = &ghes_sei;
+
+ if (head) {
+ mutex_lock(&ghes_list_mutex);
+ list_add_rcu(&ghes->list, head);
+ mutex_unlock(&ghes_list_mutex);
+ }
}

-static void ghes_sea_remove(struct ghes *ghes)
+static void ghes_abort_remove(struct ghes *ghes)
{
mutex_lock(&ghes_list_mutex);
list_del_rcu(&ghes->list);
@@ -1093,6 +1112,13 @@ 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",
@@ -1162,7 +1188,8 @@ static int ghes_probe(struct platform_device *ghes_dev)
break;

case ACPI_HEST_NOTIFY_SEA:
- ghes_sea_add(ghes);
+ case ACPI_HEST_NOTIFY_SEI:
+ ghes_abort_add(ghes);
break;
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_add(ghes);
@@ -1215,7 +1242,8 @@ static int ghes_remove(struct platform_device *ghes_dev)
break;

case ACPI_HEST_NOTIFY_SEA:
- ghes_sea_remove(ghes);
+ case ACPI_HEST_NOTIFY_SEI:
+ ghes_abort_remove(ghes);
break;
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_remove(ghes);
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 9061c5c743b3..ec6f4bab1d1b 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -118,6 +118,6 @@ static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata)
(void *)section - (void *)(estatus + 1) < estatus->data_length; \
section = acpi_hest_get_next(section))

-int ghes_notify_sea(void);
+int ghes_notify_abort(u8 type);

#endif /* GHES_H */
--
2.14.1