Add functions to register a ghes entry with HEE, allowing the OS
to receive hardware error notifications from firmware through
standardized ACPI interfaces.
Signed-off-by: Ruidong Tian <tianruidong@xxxxxxxxxxxxxxxxx>
---
arch/riscv/Kconfig | 1 +
arch/riscv/include/asm/fixmap.h | 6 ++++
drivers/acpi/apei/Kconfig | 12 +++++++
drivers/acpi/apei/ghes.c | 58 +++++++++++++++++++++++++++++++++
include/acpi/ghes.h | 6 ++++
5 files changed, 83 insertions(+)
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index a4b233a0659e..b085e172b355 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -23,6 +23,7 @@ config RISCV
select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG
select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
+ select HAVE_ACPI_APEI if (ACPI && EFI)
select ARCH_HAS_BINFMT_FLAT
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL if MMU
diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h
index 0a55099bb734..07421edc9daa 100644
--- a/arch/riscv/include/asm/fixmap.h
+++ b/arch/riscv/include/asm/fixmap.h
@@ -38,6 +38,12 @@ enum fixed_addresses {
FIX_TEXT_POKE0,
FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_ACPI_APEI_HEE
+ /* Used for GHES mapping from assorted contexts */
+ FIX_APEI_GHES_IRQ,
+ FIX_APEI_GHES_HEE,
+#endif /* CONFIG_ACPI_APEI_GHES */
+
__end_of_permanent_fixed_addresses,
/*
* Temporary boot-time mappings, used by early_ioremap(),
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 070c07d68dfb..d54a295cfc8d 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -46,6 +46,18 @@ config ACPI_APEI_SEA
depends on ARM64 && ACPI_APEI_GHES
default y
+config ACPI_APEI_HEE
+ bool "APEI Hardware Error Exception support"
+ depends on RISCV && ACPI_APEI_GHES
+ default y
+ help
+ Enable support for RISC-V Hardware Error Exception (HEE) notification
+ in ACPI Platform Error Interface (APEI). This allows firmware
+ to report hardware errors through RISC-V exception mechanism.
+
+ Say Y if you want to support firmware-first error handling
+ on RISC-V platforms with ACPI.
+
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 a0d54993edb3..1011e28091dc 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -97,6 +97,11 @@
#define FIX_APEI_GHES_SDEI_CRITICAL __end_of_fixed_addresses
#endif
+#if !defined(CONFIG_X86) && !defined(CONFIG_ARM64)
+#define FIX_APEI_GHES_NMI __end_of_fixed_addresses
+#define FIX_APEI_GHES_SEA __end_of_fixed_addresses
+#endif
+
static ATOMIC_NOTIFIER_HEAD(ghes_report_chain);
static inline bool is_hest_type_generic_v2(struct ghes *ghes)
@@ -1415,6 +1420,45 @@ 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_HEE
+static LIST_HEAD(ghes_hee);
+
+/*
+ * Return 0 only if one of the HEE error sources successfully reported an error
+ * record sent from the firmware.
+ */
+int ghes_notify_hee(void)
+{
+ static DEFINE_RAW_SPINLOCK(ghes_notify_lock_hee);
+ int rv;
+
+ raw_spin_lock(&ghes_notify_lock_hee);
+ rv = ghes_in_nmi_spool_from_list(&ghes_hee, FIX_APEI_GHES_HEE);
+ raw_spin_unlock(&ghes_notify_lock_hee);
+
+ return rv;
+}
+EXPORT_SYMBOL_GPL(ghes_notify_hee);
+
+static void ghes_hee_add(struct ghes *ghes)
+{
+ mutex_lock(&ghes_list_mutex);
+ list_add_rcu(&ghes->list, &ghes_hee);
+ mutex_unlock(&ghes_list_mutex);
+}
+
+static void ghes_hee_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_HEE */
+static inline void ghes_hee_add(struct ghes *ghes) { }
+static inline void ghes_hee_remove(struct ghes *ghes) { }
+#endif /* CONFIG_ACPI_APEI_HEE */
+
#ifdef CONFIG_HAVE_ACPI_APEI_NMI
/*
* NMI may be triggered on any CPU, so ghes_in_nmi is used for
@@ -1558,6 +1602,14 @@ static int ghes_probe(struct platform_device *ghes_dev)
goto err;
}
break;
+ case ACPI_HEST_NOTIFY_HEE:
+ if (!IS_ENABLED(CONFIG_ACPI_APEI_HEE)) {
+ pr_warn(GHES_PFX "Generic hardware error source: %d notified via HEE is not supported\n",
+ generic->header.source_id);
+ rc = -ENOTSUPP;
+ 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",
@@ -1631,6 +1683,9 @@ static int ghes_probe(struct platform_device *ghes_dev)
case ACPI_HEST_NOTIFY_SEA:
ghes_sea_add(ghes);
break;
+ case ACPI_HEST_NOTIFY_HEE:
+ ghes_hee_add(ghes);
+ break;
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_add(ghes);
break;
@@ -1698,6 +1753,9 @@ static void ghes_remove(struct platform_device *ghes_dev)
case ACPI_HEST_NOTIFY_SEA:
ghes_sea_remove(ghes);
break;
+ case ACPI_HEST_NOTIFY_HEE:
+ ghes_hee_remove(ghes);
+ break;
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_remove(ghes);
break;
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index ebd21b05fe6e..8046e1b30c21 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -127,6 +127,12 @@ int ghes_notify_sea(void);
static inline int ghes_notify_sea(void) { return -ENOENT; }
#endif
+#ifdef CONFIG_ACPI_APEI_HEE
+int ghes_notify_hee(void);
+#else
+static inline int ghes_notify_hee(void) { return -ENOENT; }
+#endif
+
struct notifier_block;
extern void ghes_register_report_chain(struct notifier_block *nb);
extern void ghes_unregister_report_chain(struct notifier_block *nb);
--
2.43.7
