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, 54 insertions, 0 deletions

diff --git a/lib/bucket_locks.c b/lib/bucket_locks.c
new file mode 100644
index 000000000..d29516ca0
--- /dev/null
+++ b/lib/bucket_locks.c
@@ -0,0 +1,54 @@
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+/* Allocate an array of spinlocks to be accessed by a hash. Two arguments
+ * indicate the number of elements to allocate in the array. max_size
+ * gives the maximum number of elements to allocate. cpu_mult gives
+ * the number of locks per CPU to allocate. The size is rounded up
+ * to a power of 2 to be suitable as a hash table.
+ */
+
+int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *locks_mask,
+			     size_t max_size, unsigned int cpu_mult, gfp_t gfp,
+			     const char *name, struct lock_class_key *key)
+{
+	spinlock_t *tlocks = NULL;
+	unsigned int i, size;
+#if defined(CONFIG_PROVE_LOCKING)
+	unsigned int nr_pcpus = 2;
+#else
+	unsigned int nr_pcpus = num_possible_cpus();
+#endif
+
+	if (cpu_mult) {
+		nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL);
+		size = min_t(unsigned int, nr_pcpus * cpu_mult, max_size);
+	} else {
+		size = max_size;
+	}
+
+	if (sizeof(spinlock_t) != 0) {
+		tlocks = kvmalloc_objs(spinlock_t, size, gfp);
+		if (!tlocks)
+			return -ENOMEM;
+		for (i = 0; i < size; i++) {
+			spin_lock_init(&tlocks[i]);
+			lockdep_init_map(&tlocks[i].dep_map, name, key, 0);
+		}
+	}
+
+	*locks = tlocks;
+	*locks_mask = size - 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(__alloc_bucket_spinlocks);
+
+void free_bucket_spinlocks(spinlock_t *locks)
+{
+	kvfree(locks);
+}
+EXPORT_SYMBOL(free_bucket_spinlocks);