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, 88 insertions, 0 deletions

diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
new file mode 100644
index 000000000..0beede3dd
--- /dev/null
+++ b/include/drm/drm_ras.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef __DRM_RAS_H__
+#define __DRM_RAS_H__
+
+#include <linux/types.h>
+
+#include <uapi/drm/drm_ras.h>
+
+/**
+ * struct drm_ras_node - A DRM RAS Node
+ */
+struct drm_ras_node {
+	/** @id: Unique identifier for the node. Dynamically assigned. */
+	u32 id;
+	/**
+	 * @device_name: Human-readable name of the device. Given by the driver.
+	 */
+	const char *device_name;
+	/** @node_name: Human-readable name of the node. Given by the driver. */
+	const char *node_name;
+	/** @type: Type of the node (enum drm_ras_node_type). */
+	enum drm_ras_node_type type;
+
+	/* Error-Counter Related Callback and Variables */
+
+	/** @error_counter_range: Range of valid Error IDs for this node. */
+	struct {
+		/** @first: First valid Error ID. */
+		u32 first;
+		/** @last: Last valid Error ID. Mandatory entry. */
+		u32 last;
+	} error_counter_range;
+
+	/**
+	 * @query_error_counter:
+	 *
+	 * This callback is used by drm-ras to query a specific error counter.
+	 * Used for input check and to iterate all error counters in a node.
+	 *
+	 * Driver should expect query_error_counter() to be called with
+	 * error_id from `error_counter_range.first` to
+	 * `error_counter_range.last`.
+	 *
+	 * The @query_error_counter is a mandatory callback for
+	 * error_counter_node.
+	 *
+	 * Returns: 0 on success,
+	 *          -ENOENT when error_id is not supported as an indication that
+	 *                  drm_ras should silently skip this entry. Used for
+	 *                  supporting non-contiguous error ranges.
+	 *                  Driver is responsible for maintaining the list of
+	 *                  supported error IDs in the range of first to last.
+	 *          Other negative values on errors that should terminate the
+	 *          netlink query.
+	 */
+	int (*query_error_counter)(struct drm_ras_node *node, u32 error_id,
+				   const char **name, u32 *val);
+
+	/**
+	 * @clear_error_counter:
+	 *
+	 * This callback is used by drm_ras to clear a specific error counter.
+	 * Driver should implement this callback to support clearing error counters
+	 * of a node.
+	 *
+	 * Returns: 0 on success, negative error code on failure.
+	 */
+	int (*clear_error_counter)(struct drm_ras_node *node, u32 error_id);
+
+	/** @priv: Driver private data */
+	void *priv;
+};
+
+struct drm_device;
+
+#if IS_ENABLED(CONFIG_DRM_RAS)
+int drm_ras_node_register(struct drm_ras_node *node);
+void drm_ras_node_unregister(struct drm_ras_node *node);
+#else
+static inline int drm_ras_node_register(struct drm_ras_node *node) { return 0; }
+static inline void drm_ras_node_unregister(struct drm_ras_node *node) { }
+#endif
+
+#endif