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, 86 insertions, 0 deletions

diff --git a/arch/alpha/lib/strncat.S b/arch/alpha/lib/strncat.S
new file mode 100644
index 000000000..a913a7c84
--- /dev/null
+++ b/arch/alpha/lib/strncat.S
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * arch/alpha/lib/strncat.S
+ * Contributed by Richard Henderson (rth@tamu.edu)
+ *
+ * Append no more than COUNT characters from the null-terminated string SRC
+ * to the null-terminated string DST.  Always null-terminate the new DST.
+ *
+ * This differs slightly from the semantics in libc in that we never write
+ * past count, whereas libc may write to count+1.  This follows the generic
+ * implementation in lib/string.c and is, IMHO, more sensible.
+ */
+#include <linux/export.h>
+	.text
+
+	.align 3
+	.globl strncat
+	.ent strncat
+strncat:
+	.frame $30, 0, $26
+	.prologue 0
+
+	mov	$16, $0		# set up return value
+	beq	$18, $zerocount
+
+	/* Find the end of the string.  */
+
+	ldq_u   $1, 0($16)	# load first quadword ($16 may be misaligned)
+	lda     $2, -1($31)
+	insqh   $2, $16, $2
+	andnot  $16, 7, $16
+	or      $2, $1, $1
+	cmpbge  $31, $1, $2	# bits set iff byte == 0
+	bne     $2, $found
+
+$loop:	ldq     $1, 8($16)
+	addq    $16, 8, $16
+	cmpbge  $31, $1, $2
+	beq     $2, $loop
+
+$found:	negq    $2, $3		# clear all but least set bit
+	and     $2, $3, $2
+
+	and     $2, 0xf0, $3	# binary search for that set bit
+	and	$2, 0xcc, $4
+	and	$2, 0xaa, $5
+	cmovne	$3, 4, $3
+	cmovne	$4, 2, $4
+	cmovne	$5, 1, $5
+	addq	$3, $4, $3
+	addq	$16, $5, $16
+	addq	$16, $3, $16
+
+	/* Now do the append.  */
+
+	bsr	$23, __stxncpy
+
+	/* Worry about the null termination.  */
+
+	zapnot	$1, $27, $2	# was last byte a null?
+	bne	$2, 0f
+	ret
+
+0:	cmplt	$27, $24, $2	# did we fill the buffer completely?
+	or	$2, $18, $2
+	bne	$2, 2f
+
+	and	$24, 0x80, $2	# no zero next byte
+	bne	$2, 1f
+
+	/* Here there are bytes left in the current word.  Clear one.  */
+	addq	$24, $24, $24	# end-of-count bit <<= 1
+2:	zap	$1, $24, $1
+	stq_u	$1, 0($16)
+	ret
+
+1:	/* Here we must read the next DST word and clear the first byte.  */
+	ldq_u	$1, 8($16)
+	zap	$1, 1, $1
+	stq_u	$1, 8($16)
+
+$zerocount:
+	ret
+
+	.end strncat
+	EXPORT_SYMBOL(strncat)