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, 82 insertions, 0 deletions

diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c
new file mode 100644
index 000000000..8c7c398fd
--- /dev/null
+++ b/lib/dec_and_lock.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
+
+/*
+ * This is an implementation of the notion of "decrement a
+ * reference count, and return locked if it decremented to zero".
+ *
+ * NOTE NOTE NOTE! This is _not_ equivalent to
+ *
+ *	if (atomic_dec_and_test(&atomic)) {
+ *		spin_lock(&lock);
+ *		return 1;
+ *	}
+ *	return 0;
+ *
+ * because the spin-lock and the decrement must be
+ * "atomic".
+ */
+int atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
+{
+	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+	if (atomic_add_unless(atomic, -1, 1))
+		return 0;
+
+	/* Otherwise do it the slow way */
+	spin_lock(lock);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	spin_unlock(lock);
+	return 0;
+}
+
+EXPORT_SYMBOL(atomic_dec_and_lock);
+
+int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+				 unsigned long *flags)
+{
+	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+	if (atomic_add_unless(atomic, -1, 1))
+		return 0;
+
+	/* Otherwise do it the slow way */
+	spin_lock_irqsave(lock, *flags);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	spin_unlock_irqrestore(lock, *flags);
+	return 0;
+}
+EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave);
+
+int atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock)
+{
+	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+	if (atomic_add_unless(atomic, -1, 1))
+		return 0;
+
+	/* Otherwise do it the slow way */
+	raw_spin_lock(lock);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	raw_spin_unlock(lock);
+	return 0;
+}
+EXPORT_SYMBOL(atomic_dec_and_raw_lock);
+
+int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock,
+				     unsigned long *flags)
+{
+	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+	if (atomic_add_unless(atomic, -1, 1))
+		return 0;
+
+	/* Otherwise do it the slow way */
+	raw_spin_lock_irqsave(lock, *flags);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	raw_spin_unlock_irqrestore(lock, *flags);
+	return 0;
+}
+EXPORT_SYMBOL(_atomic_dec_and_raw_lock_irqsave);