x86/amd_node: Fix PCI device reference counting in amd_smn_init()grafted

The local "root" pointer is a temporary variable used during the device
search. Therefore, refcount related to the search iterators should be cleaned
up after the search is complete.

Use the __free() cleanup macro to ensure the refcount is decremented when the
temporary pointer goes out of scope.

Additionally, increment the refcount when caching a root pointer. This ensures
the in-use refcount is separate from the temporary search refcounting.

Finally, drop the redundant "root = NULL" before the second search loop. The
pci_get_class() iterator always decrements the refcount of its "from"
argument, so the first loop can only fall through with "root" already NULL.

Fixes: 0a4b61d9c2e4 ("x86/amd_node: Fix AMD root device caching")
Closes: https://sashiko.dev/#/patchset/20260806160159.230453-1-jason.andryuk%40amd.com
Reported-by: Sashiko <sashiko-bot@kernel.org>
Assisted-by: LLM
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Cc: <stable@kernel.org>
Link: https://patch.msgid.link/20260903154325.74343-1-yazen.ghannam@amd.com

1 files changed, 146 insertions, 0 deletions

diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
new file mode 100644
index 000000000..8d7e5caef
--- /dev/null
+++ b/include/acpi/ghes.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef GHES_H
+#define GHES_H
+
+#include <acpi/apei.h>
+#include <acpi/hed.h>
+
+/*
+ * One struct ghes is created for each generic hardware error source.
+ * It provides the context for APEI hardware error timer/IRQ/SCI/NMI
+ * handler.
+ *
+ * estatus: memory buffer for error status block, allocated during
+ * HEST parsing.
+ */
+#define GHES_EXITING		0x0002
+
+struct ghes {
+	union {
+		struct acpi_hest_generic *generic;
+		struct acpi_hest_generic_v2 *generic_v2;
+	};
+	struct acpi_hest_generic_status *estatus;
+	unsigned int estatus_length;
+	unsigned long flags;
+	union {
+		struct list_head list;
+		struct timer_list timer;
+		unsigned int irq;
+	};
+	struct device *dev;
+	struct list_head elist;
+	void __iomem *error_status_vaddr;
+};
+
+struct ghes_estatus_node {
+	struct llist_node llnode;
+	struct acpi_hest_generic *generic;
+	struct ghes *ghes;
+};
+
+struct ghes_estatus_cache {
+	u32 estatus_len;
+	atomic_t count;
+	struct acpi_hest_generic *generic;
+	unsigned long long time_in;
+	struct rcu_head rcu;
+};
+
+enum {
+	GHES_SEV_NO = 0x0,
+	GHES_SEV_CORRECTED = 0x1,
+	GHES_SEV_RECOVERABLE = 0x2,
+	GHES_SEV_PANIC = 0x3,
+};
+
+#ifdef CONFIG_ACPI_APEI_GHES
+/**
+ * ghes_register_vendor_record_notifier - register a notifier for vendor
+ * records that the kernel would otherwise ignore.
+ * @nb: pointer to the notifier_block structure of the event handler.
+ *
+ * return 0 : SUCCESS, non-zero : FAIL
+ */
+int ghes_register_vendor_record_notifier(struct notifier_block *nb);
+
+/**
+ * ghes_unregister_vendor_record_notifier - unregister the previously
+ * registered vendor record notifier.
+ * @nb: pointer to the notifier_block structure of the vendor record handler.
+ */
+void ghes_unregister_vendor_record_notifier(struct notifier_block *nb);
+
+/**
+ * devm_ghes_register_vendor_record_notifier - device-managed vendor
+ * record notifier registration.
+ * @dev: device that owns the notifier lifetime
+ * @nb: pointer to the notifier_block structure of the vendor record handler
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int devm_ghes_register_vendor_record_notifier(struct device *dev,
+					      struct notifier_block *nb);
+
+struct list_head *ghes_get_devices(void);
+
+void ghes_estatus_pool_region_free(unsigned long addr, u32 size);
+#else
+static inline struct list_head *ghes_get_devices(void) { return NULL; }
+
+static inline void ghes_estatus_pool_region_free(unsigned long addr, u32 size) { return; }
+#endif
+
+int ghes_estatus_pool_init(unsigned int num_ghes);
+
+static inline int acpi_hest_get_version(struct acpi_hest_generic_data *gdata)
+{
+	return gdata->revision >> 8;
+}
+
+static inline void *acpi_hest_get_payload(struct acpi_hest_generic_data *gdata)
+{
+	if (acpi_hest_get_version(gdata) >= 3)
+		return (void *)(((struct acpi_hest_generic_data_v300 *)(gdata)) + 1);
+
+	return gdata + 1;
+}
+
+static inline int acpi_hest_get_error_length(struct acpi_hest_generic_data *gdata)
+{
+	return ((struct acpi_hest_generic_data *)(gdata))->error_data_length;
+}
+
+static inline int acpi_hest_get_size(struct acpi_hest_generic_data *gdata)
+{
+	if (acpi_hest_get_version(gdata) >= 3)
+		return sizeof(struct acpi_hest_generic_data_v300);
+
+	return sizeof(struct acpi_hest_generic_data);
+}
+
+static inline int acpi_hest_get_record_size(struct acpi_hest_generic_data *gdata)
+{
+	return (acpi_hest_get_size(gdata) + acpi_hest_get_error_length(gdata));
+}
+
+static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata)
+{
+	return (void *)(gdata) + acpi_hest_get_record_size(gdata);
+}
+
+#define apei_estatus_for_each_section(estatus, section)			\
+	for (section = (struct acpi_hest_generic_data *)(estatus + 1);	\
+	     (void *)section - (void *)(estatus + 1) < estatus->data_length; \
+	     section = acpi_hest_get_next(section))
+
+#ifdef CONFIG_ACPI_APEI_SEA
+int ghes_notify_sea(void);
+#else
+static inline int ghes_notify_sea(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);
+#endif /* GHES_H */