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, 101 insertions, 0 deletions

diff --git a/include/net/fq.h b/include/net/fq.h
new file mode 100644
index 000000000..99fbe4127
--- /dev/null
+++ b/include/net/fq.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2016 Qualcomm Atheros, Inc
+ *
+ * Based on net/sched/sch_fq_codel.c
+ */
+#ifndef __NET_SCHED_FQ_H
+#define __NET_SCHED_FQ_H
+
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+struct fq_tin;
+
+/**
+ * struct fq_flow - per traffic flow queue
+ *
+ * @tin: owner of this flow. Used to manage collisions, i.e. when a packet
+ *	hashes to an index which points to a flow that is already owned by a
+ *	different tin the packet is destined to. In such case the implementer
+ *	must provide a fallback flow
+ * @flowchain: can be linked to fq_tin's new_flows or old_flows. Used for DRR++
+ *	(deficit round robin) based round robin queuing similar to the one
+ *	found in net/sched/sch_fq_codel.c
+ * @queue: sk_buff queue to hold packets
+ * @backlog: number of bytes pending in the queue. The number of packets can be
+ *	found in @queue.qlen
+ * @deficit: used for DRR++
+ */
+struct fq_flow {
+	struct fq_tin *tin;
+	struct list_head flowchain;
+	struct sk_buff_head queue;
+	u32 backlog;
+	int deficit;
+};
+
+/**
+ * struct fq_tin - a logical container of fq_flows
+ *
+ * Used to group fq_flows into a logical aggregate. DRR++ scheme is used to
+ * pull interleaved packets out of the associated flows.
+ *
+ * @new_flows: linked list of fq_flow
+ * @old_flows: linked list of fq_flow
+ */
+struct fq_tin {
+	struct list_head new_flows;
+	struct list_head old_flows;
+	struct list_head tin_list;
+	struct fq_flow default_flow;
+	u32 backlog_bytes;
+	u32 backlog_packets;
+	u32 overlimit;
+	u32 collisions;
+	u32 flows;
+	u32 tx_bytes;
+	u32 tx_packets;
+};
+
+/**
+ * struct fq - main container for fair queuing purposes
+ *
+ * @limit: max number of packets that can be queued across all flows
+ * @backlog: number of packets queued across all flows
+ */
+struct fq {
+	struct fq_flow *flows;
+	unsigned long *flows_bitmap;
+
+	struct list_head tin_backlog;
+	spinlock_t lock;
+	u32 flows_cnt;
+	u32 limit;
+	u32 memory_limit;
+	u32 memory_usage;
+	u32 quantum;
+	u32 backlog;
+	u32 overlimit;
+	u32 overmemory;
+	u32 collisions;
+};
+
+typedef struct sk_buff *fq_tin_dequeue_t(struct fq *,
+					 struct fq_tin *,
+					 struct fq_flow *flow);
+
+typedef void fq_skb_free_t(struct fq *,
+			   struct fq_tin *,
+			   struct fq_flow *,
+			   struct sk_buff *);
+
+/* Return %true to filter (drop) the frame. */
+typedef bool fq_skb_filter_t(struct fq *,
+			     struct fq_tin *,
+			     struct fq_flow *,
+			     struct sk_buff *,
+			     void *);
+
+#endif