ftrace: Synchronize the initialization of ftrace_opsgrafted

There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.

Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

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