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, 122 insertions, 0 deletions

diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
new file mode 100644
index 000000000..ef3f841c6
--- /dev/null
+++ b/include/asm-generic/word-at-a-time.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+#include <linux/bitops.h>
+#include <linux/wordpart.h>
+#include <asm/byteorder.h>
+
+#ifdef __BIG_ENDIAN
+
+struct word_at_a_time {
+	const unsigned long high_bits, low_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0xfe) + 1, REPEAT_BYTE(0x7f) }
+
+/* Bit set in the bytes that have a zero */
+static inline long prep_zero_mask(unsigned long val, unsigned long rhs, const struct word_at_a_time *c)
+{
+	unsigned long mask = (val & c->low_bits) + c->low_bits;
+	return ~(mask | rhs);
+}
+
+#define create_zero_mask(mask) (mask)
+
+static inline long find_zero(unsigned long mask)
+{
+	long byte = 0;
+#ifdef CONFIG_64BIT
+	if (mask >> 32)
+		mask >>= 32;
+	else
+		byte = 4;
+#endif
+	if (mask >> 16)
+		mask >>= 16;
+	else
+		byte += 2;
+	return (mask >> 8) ? byte : byte + 1;
+}
+
+static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
+{
+	unsigned long rhs = val | c->low_bits;
+	*data = rhs;
+	return (val + c->high_bits) & ~rhs;
+}
+
+#ifndef zero_bytemask
+#define zero_bytemask(mask) (~1ul << __fls(mask))
+#endif
+
+#else
+
+/*
+ * The optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+	return mask*0x0001020304050608ul >> 56;
+}
+
+#else	/* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	long a = (0x0ff0001+mask) >> 23;
+	/* Fix the 1 for 00 case */
+	return a & mask;
+}
+
+#endif
+
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	return count_masked_bytes(mask);
+}
+
+#endif /* __BIG_ENDIAN */
+
+#endif /* _ASM_WORD_AT_A_TIME_H */