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, 38 insertions, 0 deletions

diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h
new file mode 100644
index 000000000..fd2f6f29b
--- /dev/null
+++ b/io_uring/sqpoll.h
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+
+struct io_sq_data {
+	refcount_t		refs;
+	atomic_t		park_pending;
+	struct mutex		lock;
+
+	/* ctx's that are using this sqd */
+	struct list_head	ctx_list;
+
+	struct task_struct __rcu *thread;
+	struct wait_queue_head	wait;
+
+	unsigned		sq_thread_idle;
+	int			sq_cpu;
+	pid_t			task_pid;
+	pid_t			task_tgid;
+
+	u64			work_time;
+	unsigned long		state;
+	struct completion	exited;
+};
+
+int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_uring_params *p);
+void io_sq_thread_finish(struct io_ring_ctx *ctx);
+void io_sq_thread_stop(struct io_sq_data *sqd);
+void io_sq_thread_park(struct io_sq_data *sqd);
+void io_sq_thread_unpark(struct io_sq_data *sqd);
+void io_put_sq_data(struct io_sq_data *sqd);
+void io_sqpoll_wait_sq(struct io_ring_ctx *ctx);
+int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, cpumask_var_t mask);
+u64 io_sq_cpu_usec(struct task_struct *tsk);
+
+static inline struct task_struct *sqpoll_task_locked(struct io_sq_data *sqd)
+{
+	return rcu_dereference_protected(sqd->thread,
+					 lockdep_is_held(&sqd->lock));
+}