In current code logic, the two functions ghes_sea_add() and
ghes_sea_remove() are only called when CONFIG_ACPI_APEI_SEA
is defined. If not, it will return errors in the ghes_probe()
and not continue. If the probe is failed, the ghes_sea_remove()
also has no chance to be called. Hence, remove the unnecessary
handling when CONFIG_ACPI_APEI_SEA is not defined.
In the firmware-first RAS solution, the IPA fault address recorded
by hpfar_el2 may be UNKNOWN, and also current code does not use it,
so remove it.
Cc: Stephen Boyd <[email protected]>
Cc: James Morse <[email protected]>
Cc: Tyler Baicar <[email protected]>
Signed-off-by: Dongjiu Geng <[email protected]>
---
v2->v3:
1. remove the fault_ipa address
If ESR_ELx.DFSC is Synchronous External Abort on memory access(0b010000),
the hpfar_el2's value will be UNKNOWN, so this value is not accurate.
It is ever discussed here:
https://lkml.org/lkml/2017/9/8/623
---
arch/arm/include/asm/system_misc.h | 2 +-
arch/arm64/include/asm/system_misc.h | 2 +-
arch/arm64/mm/fault.c | 2 +-
drivers/acpi/apei/ghes.c | 14 --------------
virt/kvm/arm/mmu.c | 2 +-
5 files changed, 4 insertions(+), 18 deletions(-)
diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
index 8c4a89f..5b53a1c 100644
--- a/arch/arm/include/asm/system_misc.h
+++ b/arch/arm/include/asm/system_misc.h
@@ -22,7 +22,7 @@ extern void (*arm_pm_idle)(void);
extern unsigned int user_debug;
-static inline int handle_guest_sea(phys_addr_t addr, unsigned int esr)
+static inline int handle_guest_sea(unsigned int esr)
{
return -1;
}
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 07aa8e3..3f0d0a8 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -56,7 +56,7 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
__show_ratelimited; \
})
-int handle_guest_sea(phys_addr_t addr, unsigned int esr);
+int handle_guest_sea(unsigned int esr);
#endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2509e4f..13391f4 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -677,7 +677,7 @@ static const struct fault_info fault_info[] = {
* and non-zero if there was an error processing the error or there was
* no error to process.
*/
-int handle_guest_sea(phys_addr_t addr, unsigned int esr)
+int handle_guest_sea(unsigned int esr)
{
int ret = -ENOENT;
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index d661d45..c15a08d 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -813,7 +813,6 @@ static struct notifier_block ghes_notifier_hed = {
.notifier_call = ghes_notify_hed,
};
-#ifdef CONFIG_ACPI_APEI_SEA
static LIST_HEAD(ghes_sea);
/*
@@ -848,19 +847,6 @@ static void ghes_sea_remove(struct ghes *ghes)
mutex_unlock(&ghes_list_mutex);
synchronize_rcu();
}
-#else /* CONFIG_ACPI_APEI_SEA */
-static inline void ghes_sea_add(struct ghes *ghes)
-{
- pr_err(GHES_PFX "ID: %d, trying to add SEA notification which is not supported\n",
- ghes->generic->header.source_id);
-}
-
-static inline void ghes_sea_remove(struct ghes *ghes)
-{
- pr_err(GHES_PFX "ID: %d, trying to remove SEA notification which is not supported\n",
- ghes->generic->header.source_id);
-}
-#endif /* CONFIG_ACPI_APEI_SEA */
#ifdef CONFIG_HAVE_ACPI_APEI_NMI
/*
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 2ea21da..07636c2 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1504,7 +1504,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
* is no need to pass the error into the guest.
*/
if (is_abort_sea(fault_status)) {
- if (!handle_guest_sea(fault_ipa, kvm_vcpu_get_hsr(vcpu)))
+ if (!handle_guest_sea(kvm_vcpu_get_hsr(vcpu)))
return 1;
}
--
2.10.1
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.
Cc: Stephen Boyd <[email protected]>
Cc: James Morse <[email protected]>
Signed-off-by: Dongjiu Geng <[email protected]>
Tested-by: Tyler Baicar <[email protected]>
---
change since v2:
1. remove the dependency to ACPI_APEI_SEA/ACPI_APEI_SEI for NMI
---
arch/arm64/mm/fault.c | 4 ++--
drivers/acpi/apei/Kconfig | 15 ++++++++++++
drivers/acpi/apei/ghes.c | 58 +++++++++++++++++++++++++++++++++++------------
include/acpi/ghes.h | 2 +-
4 files changed, 61 insertions(+), 18 deletions(-)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 13391f4..0c6b3b2 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(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 de14d49..47fcb0c 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 c15a08d..903af70 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
- * record sent from the firmware.
+ * 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 9061c5c..ec6f4ba 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 */
--
2.10.1