[PATCH 2/3] riscv: Introduce HEST HEE notification handlers for APEI

[Ruidong Tian <tianruidong@linux.alibaba.com>]

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@linux.alibaba.com>
---
 arch/riscv/include/asm/fixmap.h |  3 ++
 drivers/acpi/apei/Kconfig       | 12 ++++++
 drivers/acpi/apei/ghes.c        | 68 ++++++++++++++++++++++++++++++++-
 include/acpi/ghes.h             |  6 +++
 4 files changed, 87 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h
index e874fd952286..9b3d5bbfda24 100644
--- a/arch/riscv/include/asm/fixmap.h
+++ b/arch/riscv/include/asm/fixmap.h
@@ -45,6 +45,9 @@ enum fixed_addresses {
 	FIX_APEI_GHES_SSE_LOW_PRIORITY,
 	FIX_APEI_GHES_SSE_HIGH_PRIORITY,
 #endif /* CONFIG_RISCV_SBI_SSE */
+#ifdef CONFIG_ACPI_APEI_HEE
+	FIX_APEI_GHES_HEE,
+#endif /* CONFIG_ACPI_APEI_HEE */
 #endif /* CONFIG_ACPI_APEI_GHES */
 	__end_of_permanent_fixed_addresses,
 	/*
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 895a843d0e36..ff487ab28a65 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -51,6 +51,18 @@ config ACPI_APEI_SSE
 	depends on RISCV && RISCV_SBI_SSE && 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 f228640d3f25..e0a5db80e554 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -125,7 +125,8 @@ static inline bool is_hest_sync_notify(struct ghes *ghes)
 {
 	u8 notify_type = ghes->generic->notify.type;
 
-	return notify_type == ACPI_HEST_NOTIFY_SEA;
+	return notify_type == ACPI_HEST_NOTIFY_SEA ||
+		   notify_type == ACPI_HEST_NOTIFY_HEE;
 }
 
 /*
@@ -1404,7 +1405,8 @@ static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
 	return rc;
 }
 
-#if defined(CONFIG_HAVE_ACPI_APEI_NMI) || defined(CONFIG_ACPI_APEI_SEA)
+#if defined(CONFIG_HAVE_ACPI_APEI_NMI) || defined(CONFIG_ACPI_APEI_SEA) || \
+	defined(CONFIG_ACPI_APEI_HEE)
 static int ghes_in_nmi_spool_from_list(struct list_head *rcu_list,
 				       enum fixed_addresses fixmap_idx)
 {
@@ -1540,6 +1542,53 @@ static inline int ghes_sea_add(struct ghes *ghes) { return -EINVAL; }
 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 int ghes_hee_add(struct ghes *ghes)
+{
+	int rc;
+
+	rc = ghes_map_error_status(ghes);
+	if (rc)
+		return rc;
+
+	mutex_lock(&ghes_list_mutex);
+	list_add_rcu(&ghes->list, &ghes_hee);
+	mutex_unlock(&ghes_list_mutex);
+
+	return 0;
+}
+
+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
@@ -1754,6 +1803,13 @@ 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);
+			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",
@@ -1837,6 +1893,11 @@ static int ghes_probe(struct platform_device *ghes_dev)
 		if (rc)
 			goto err;
 		break;
+	case ACPI_HEST_NOTIFY_HEE:
+		rc = ghes_hee_add(ghes);
+		if (rc)
+			goto err;
+		break;
 	case ACPI_HEST_NOTIFY_NMI:
 		rc = ghes_nmi_add(ghes);
 		if (rc)
@@ -1917,6 +1978,9 @@ 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 8d7e5caef3f1..bf4f6077ca39 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -140,6 +140,12 @@ 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);
-- 
2.51.2.612.gdc70283dfc


_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv