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, 115 insertions, 0 deletions

diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
new file mode 100644
index 000000000..f069d1b23
--- /dev/null
+++ b/arch/arm/lib/bitops.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/assembler.h>
+#include <asm/unwind.h>
+
+#if __LINUX_ARM_ARCH__ >= 6
+	.macro	bitop, name, instr
+ENTRY(	\name		)
+UNWIND(	.fnstart	)
+	ands	ip, r1, #3
+	strbne	r1, [ip]		@ assert word-aligned
+	mov	r2, #1
+	and	r3, r0, #31		@ Get bit offset
+	mov	r0, r0, lsr #5
+	add	r1, r1, r0, lsl #2	@ Get word offset
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+	.arch_extension	mp
+	ALT_SMP(W(pldw)	[r1])
+	ALT_UP(W(nop))
+#endif
+	mov	r3, r2, lsl r3
+1:	ldrex	r2, [r1]
+	\instr	r2, r2, r3
+	strex	r0, r2, [r1]
+	cmp	r0, #0
+	bne	1b
+	bx	lr
+UNWIND(	.fnend		)
+ENDPROC(\name		)
+	.endm
+
+	.macro	__testop, name, instr, store, barrier
+ENTRY(	\name		)
+UNWIND(	.fnstart	)
+	ands	ip, r1, #3
+	strbne	r1, [ip]		@ assert word-aligned
+	mov	r2, #1
+	and	r3, r0, #31		@ Get bit offset
+	mov	r0, r0, lsr #5
+	add	r1, r1, r0, lsl #2	@ Get word offset
+	mov	r3, r2, lsl r3		@ create mask
+	\barrier
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+	.arch_extension	mp
+	ALT_SMP(W(pldw)	[r1])
+	ALT_UP(W(nop))
+#endif
+1:	ldrex	r2, [r1]
+	ands	r0, r2, r3		@ save old value of bit
+	\instr	r2, r2, r3		@ toggle bit
+	strex	ip, r2, [r1]
+	cmp	ip, #0
+	bne	1b
+	\barrier
+	cmp	r0, #0
+	movne	r0, #1
+2:	bx	lr
+UNWIND(	.fnend		)
+ENDPROC(\name		)
+	.endm
+
+	.macro	testop, name, instr, store
+	__testop \name, \instr, \store, smp_dmb
+	.endm
+
+	.macro	sync_testop, name, instr, store
+	__testop \name, \instr, \store, __smp_dmb
+	.endm
+#else
+	.macro	bitop, name, instr
+ENTRY(	\name		)
+UNWIND(	.fnstart	)
+	ands	ip, r1, #3
+	strbne	r1, [ip]		@ assert word-aligned
+	and	r2, r0, #31
+	mov	r0, r0, lsr #5
+	mov	r3, #1
+	mov	r3, r3, lsl r2
+	save_and_disable_irqs ip
+	ldr	r2, [r1, r0, lsl #2]
+	\instr	r2, r2, r3
+	str	r2, [r1, r0, lsl #2]
+	restore_irqs ip
+	ret	lr
+UNWIND(	.fnend		)
+ENDPROC(\name		)
+	.endm
+
+/**
+ * testop - implement a test_and_xxx_bit operation.
+ * @instr: operational instruction
+ * @store: store instruction
+ *
+ * Note: we can trivially conditionalise the store instruction
+ * to avoid dirtying the data cache.
+ */
+	.macro	testop, name, instr, store
+ENTRY(	\name		)
+UNWIND(	.fnstart	)
+	ands	ip, r1, #3
+	strbne	r1, [ip]		@ assert word-aligned
+	and	r3, r0, #31
+	mov	r0, r0, lsr #5
+	save_and_disable_irqs ip
+	ldr	r2, [r1, r0, lsl #2]!
+	mov	r0, #1
+	tst	r2, r0, lsl r3
+	\instr	r2, r2, r0, lsl r3
+	\store	r2, [r1]
+	moveq	r0, #0
+	restore_irqs ip
+	ret	lr
+UNWIND(	.fnend		)
+ENDPROC(\name		)
+	.endm
+#endif