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, 218 insertions, 0 deletions

diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c
new file mode 100644
index 000000000..05305e655
--- /dev/null
+++ b/lib/find_bit_benchmark.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Test for find_*_bit functions.
+ *
+ * Copyright (c) 2017 Cavium.
+ */
+
+/*
+ * find_bit functions are widely used in kernel, so the successful boot
+ * is good enough test for correctness.
+ *
+ * This test is focused on performance of traversing bitmaps. Two typical
+ * scenarios are reproduced:
+ * - randomly filled bitmap with approximately equal number of set and
+ *   cleared bits;
+ * - sparse bitmap with few set bits at random positions.
+ */
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+
+#define BITMAP_LEN	(4096UL * 8 * 10)
+#define SPARSE		500
+
+static DECLARE_BITMAP(bitmap, BITMAP_LEN) __initdata;
+static DECLARE_BITMAP(bitmap2, BITMAP_LEN) __initdata;
+
+/*
+ * This is Schlemiel the Painter's algorithm.
+ */
+static int __init test_find_first_bit(const void *bitmap, unsigned long len)
+{
+	static DECLARE_BITMAP(cp, BITMAP_LEN) __initdata;
+	unsigned long i, cnt;
+	ktime_t time;
+
+	bitmap_copy(cp, bitmap, BITMAP_LEN);
+
+	time = ktime_get();
+	for (cnt = i = 0; i < len; cnt++) {
+		i = find_first_bit(cp, len);
+		__clear_bit(i, cp);
+	}
+	time = ktime_get() - time;
+	pr_err("find_first_bit:     %18llu ns, %6ld iterations\n", time, cnt);
+
+	return 0;
+}
+
+static int __init test_find_first_and_bit(const void *bitmap, const void *bitmap2,
+		unsigned long len)
+{
+	static DECLARE_BITMAP(cp, BITMAP_LEN) __initdata;
+	unsigned long i, cnt;
+	ktime_t time;
+
+	bitmap_copy(cp, bitmap, BITMAP_LEN);
+
+	time = ktime_get();
+	for (cnt = i = 0; i < len; cnt++) {
+		i = find_first_and_bit(cp, bitmap2, len);
+		__clear_bit(i, cp);
+	}
+	time = ktime_get() - time;
+	pr_err("find_first_and_bit: %18llu ns, %6ld iterations\n", time, cnt);
+
+	return 0;
+}
+
+static int __init test_find_next_bit(const void *bitmap, unsigned long len)
+{
+	unsigned long i, cnt;
+	ktime_t time;
+
+	time = ktime_get();
+	for (cnt = i = 0; i < BITMAP_LEN; cnt++)
+		i = find_next_bit(bitmap, BITMAP_LEN, i) + 1;
+	time = ktime_get() - time;
+	pr_err("find_next_bit:      %18llu ns, %6ld iterations\n", time, cnt);
+
+	return 0;
+}
+
+static int __init test_find_next_zero_bit(const void *bitmap, unsigned long len)
+{
+	unsigned long i, cnt;
+	ktime_t time;
+
+	time = ktime_get();
+	for (cnt = i = 0; i < BITMAP_LEN; cnt++)
+		i = find_next_zero_bit(bitmap, len, i) + 1;
+	time = ktime_get() - time;
+	pr_err("find_next_zero_bit: %18llu ns, %6ld iterations\n", time, cnt);
+
+	return 0;
+}
+
+static int __init test_find_last_bit(const void *bitmap, unsigned long len)
+{
+	unsigned long l, cnt = 0;
+	ktime_t time;
+
+	time = ktime_get();
+	do {
+		cnt++;
+		l = find_last_bit(bitmap, len);
+		if (l >= len)
+			break;
+		len = l;
+	} while (len);
+	time = ktime_get() - time;
+	pr_err("find_last_bit:      %18llu ns, %6ld iterations\n", time, cnt);
+
+	return 0;
+}
+
+static int __init test_find_nth_bit(const unsigned long *bitmap, unsigned long len)
+{
+	unsigned long l, n, w = bitmap_weight(bitmap, len);
+	ktime_t time;
+
+	time = ktime_get();
+	for (n = 0; n < w; n++) {
+		l = find_nth_bit(bitmap, len, n);
+		WARN_ON(l >= len);
+	}
+	time = ktime_get() - time;
+	pr_err("find_nth_bit:       %18llu ns, %6ld iterations\n", time, w);
+
+	return 0;
+}
+
+static int __init test_find_next_and_bit(const void *bitmap,
+		const void *bitmap2, unsigned long len)
+{
+	unsigned long i, cnt;
+	ktime_t time;
+
+	time = ktime_get();
+	for (cnt = i = 0; i < BITMAP_LEN; cnt++)
+		i = find_next_and_bit(bitmap, bitmap2, BITMAP_LEN, i + 1);
+	time = ktime_get() - time;
+	pr_err("find_next_and_bit:  %18llu ns, %6ld iterations\n", time, cnt);
+
+	return 0;
+}
+
+static int __init
+test_bitmap_find_next_zero_area_off(unsigned long *bitmap, unsigned long len)
+{
+	unsigned long i, cnt;
+	ktime_t time;
+
+	time = ktime_get();
+	for (cnt = i = 0; i < BITMAP_LEN; cnt++)
+		i = bitmap_find_next_zero_area_off(bitmap, BITMAP_LEN, i, 8, 0, 0) + 1;
+	time = ktime_get() - time;
+	pr_err("bitmap_find_next_zero_area_off:%7llu ns, %6ld iterations\n", time, cnt);
+
+	return 0;
+}
+
+static int __init find_bit_test(void)
+{
+	unsigned long nbits = BITMAP_LEN / SPARSE;
+
+	pr_err("\nStart testing find_bit() with random-filled bitmap\n");
+
+	get_random_bytes(bitmap, sizeof(bitmap));
+	get_random_bytes(bitmap2, sizeof(bitmap2));
+
+	test_bitmap_find_next_zero_area_off(bitmap, BITMAP_LEN);
+	test_find_next_bit(bitmap, BITMAP_LEN);
+	test_find_next_zero_bit(bitmap, BITMAP_LEN);
+	test_find_last_bit(bitmap, BITMAP_LEN);
+	test_find_nth_bit(bitmap, BITMAP_LEN / 10);
+
+	/*
+	 * test_find_first_bit() may take some time, so
+	 * traverse only part of bitmap to avoid soft lockup.
+	 */
+	test_find_first_bit(bitmap, BITMAP_LEN / 10);
+	test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN / 2);
+	test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN);
+
+	pr_err("\nStart testing find_bit() with sparse bitmap\n");
+
+	bitmap_zero(bitmap, BITMAP_LEN);
+	bitmap_zero(bitmap2, BITMAP_LEN);
+
+	while (nbits--) {
+		__set_bit(get_random_u32_below(BITMAP_LEN), bitmap);
+		__set_bit(get_random_u32_below(BITMAP_LEN), bitmap2);
+	}
+
+	test_bitmap_find_next_zero_area_off(bitmap, BITMAP_LEN);
+	test_find_next_bit(bitmap, BITMAP_LEN);
+	test_find_next_zero_bit(bitmap, BITMAP_LEN);
+	test_find_last_bit(bitmap, BITMAP_LEN);
+	test_find_nth_bit(bitmap, BITMAP_LEN);
+	test_find_first_bit(bitmap, BITMAP_LEN);
+	test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN);
+	test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN);
+
+	/*
+	 * Everything is OK. Return error just to let user run benchmark
+	 * again without annoying rmmod.
+	 */
+	return -EINVAL;
+}
+module_init(find_bit_test);
+
+MODULE_DESCRIPTION("Test for find_*_bit functions");
+MODULE_LICENSE("GPL");