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, 150 insertions, 0 deletions

diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
new file mode 100644
index 000000000..523c79f22
--- /dev/null
+++ b/tools/testing/radix-tree/benchmark.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * benchmark.c:
+ * Author: Konstantin Khlebnikov <koct9i@gmail.com>
+ */
+#include <linux/radix-tree.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <time.h>
+#include "test.h"
+
+#define NSEC_PER_SEC	1000000000L
+
+static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
+{
+	volatile unsigned long sink = 0;
+	struct radix_tree_iter iter;
+	struct timespec start, finish;
+	long long nsec;
+	int l, loops = 1;
+	void **slot;
+
+#ifdef BENCHMARK
+again:
+#endif
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	for (l = 0; l < loops; l++) {
+		if (tagged) {
+			radix_tree_for_each_tagged(slot, root, &iter, 0, 0)
+				sink ^= (unsigned long)slot;
+		} else {
+			radix_tree_for_each_slot(slot, root, &iter, 0)
+				sink ^= (unsigned long)slot;
+		}
+	}
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+#ifdef BENCHMARK
+	if (loops == 1 && nsec * 5 < NSEC_PER_SEC) {
+		loops = NSEC_PER_SEC / nsec / 4 + 1;
+		goto again;
+	}
+#endif
+
+	nsec /= loops;
+	return nsec;
+}
+
+static void benchmark_insert(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		item_insert(root, index);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, insertion: %15lld ns\n",
+		size, step, nsec);
+}
+
+static void benchmark_tagging(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		radix_tree_tag_set(root, index, 0);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, tagging: %17lld ns\n",
+		size, step, nsec);
+}
+
+static void benchmark_delete(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		item_delete(root, index);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, deletion: %16lld ns\n",
+		size, step, nsec);
+}
+
+static void benchmark_size(unsigned long size, unsigned long step)
+{
+	RADIX_TREE(tree, GFP_KERNEL);
+	long long normal, tagged;
+
+	benchmark_insert(&tree, size, step);
+	benchmark_tagging(&tree, size, step);
+
+	tagged = benchmark_iter(&tree, true);
+	normal = benchmark_iter(&tree, false);
+
+	printv(2, "Size: %8ld, step: %8ld, tagged iteration: %8lld ns\n",
+		size, step, tagged);
+	printv(2, "Size: %8ld, step: %8ld, normal iteration: %8lld ns\n",
+		size, step, normal);
+
+	benchmark_delete(&tree, size, step);
+
+	item_kill_tree(&tree);
+	rcu_barrier();
+}
+
+void benchmark(void)
+{
+	unsigned long size[] = {1 << 10, 1 << 20, 0};
+	unsigned long step[] = {1, 2, 7, 15, 63, 64, 65,
+				128, 256, 512, 12345, 0};
+	int c, s;
+
+	printv(1, "starting benchmarks\n");
+	printv(1, "RADIX_TREE_MAP_SHIFT = %d\n", RADIX_TREE_MAP_SHIFT);
+
+	for (c = 0; size[c]; c++)
+		for (s = 0; step[s]; s++)
+			benchmark_size(size[c], step[s]);
+}