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, 51 insertions, 0 deletions

diff --git a/arch/alpha/lib/ev67-strlen.S b/arch/alpha/lib/ev67-strlen.S
new file mode 100644
index 000000000..3d9078807
--- /dev/null
+++ b/arch/alpha/lib/ev67-strlen.S
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * arch/alpha/lib/ev67-strlen.S
+ * 21264 version by Rick Gorton <rick.gorton@alpha-processor.com>
+ *
+ * Finds length of a 0-terminated string.  Optimized for the
+ * Alpha architecture:
+ *
+ *	- memory accessed as aligned quadwords only
+ *	- uses bcmpge to compare 8 bytes in parallel
+ *
+ * Much of the information about 21264 scheduling/coding comes from:
+ *	Compiler Writer's Guide for the Alpha 21264
+ *	abbreviated as 'CWG' in other comments here
+ *	ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html
+ * Scheduling notation:
+ *	E	- either cluster
+ *	U	- upper subcluster; U0 - subcluster U0; U1 - subcluster U1
+ *	L	- lower subcluster; L0 - subcluster L0; L1 - subcluster L1
+ */
+#include <linux/export.h>
+	.set noreorder
+	.set noat
+
+	.globl	strlen
+	.ent	strlen
+	.align 4
+strlen:
+	ldq_u	$1, 0($16)	# L : load first quadword ($16  may be misaligned)
+	lda	$2, -1($31)	# E :
+	insqh	$2, $16, $2	# U :
+	andnot	$16, 7, $0	# E :
+
+	or	$2, $1, $1	# E :
+	cmpbge	$31, $1, $2	# E : $2  <- bitmask: bit i == 1 <==> i-th byte == 0
+	nop			# E :
+	bne	$2, $found	# U :
+
+$loop:	ldq	$1, 8($0)	# L :
+	addq	$0, 8, $0	# E : addr += 8
+	cmpbge	$31, $1, $2	# E :
+	beq	$2, $loop	# U :
+
+$found:
+	cttz	$2, $3		# U0 :
+	addq	$0, $3, $0	# E :
+	subq	$0, $16, $0	# E :
+	ret	$31, ($26)	# L0 :
+
+	.end	strlen
+	EXPORT_SYMBOL(strlen)