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, 107 insertions, 0 deletions

diff --git a/arch/powerpc/boot/div64.S b/arch/powerpc/boot/div64.S
new file mode 100644
index 000000000..4354928ed
--- /dev/null
+++ b/arch/powerpc/boot/div64.S
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Divide a 64-bit unsigned number by a 32-bit unsigned number.
+ * This routine assumes that the top 32 bits of the dividend are
+ * non-zero to start with.
+ * On entry, r3 points to the dividend, which get overwritten with
+ * the 64-bit quotient, and r4 contains the divisor.
+ * On exit, r3 contains the remainder.
+ *
+ * Copyright (C) 2002 Paul Mackerras, IBM Corp.
+ */
+#include "ppc_asm.h"
+
+	.globl __div64_32
+__div64_32:
+	lwz	r5,0(r3)	# get the dividend into r5/r6
+	lwz	r6,4(r3)
+	cmplw	r5,r4
+	li	r7,0
+	li	r8,0
+	blt	1f
+	divwu	r7,r5,r4	# if dividend.hi >= divisor,
+	mullw	r0,r7,r4	# quotient.hi = dividend.hi / divisor
+	subf.	r5,r0,r5	# dividend.hi %= divisor
+	beq	3f
+1:	mr	r11,r5		# here dividend.hi != 0
+	andis.	r0,r5,0xc000
+	bne	2f
+	cntlzw	r0,r5		# we are shifting the dividend right
+	li	r10,-1		# to make it < 2^32, and shifting
+	srw	r10,r10,r0	# the divisor right the same amount,
+	addc	r9,r4,r10	# rounding up (so the estimate cannot
+	andc	r11,r6,r10	# ever be too large, only too small)
+	andc	r9,r9,r10
+	addze	r9,r9
+	or	r11,r5,r11
+	rotlw	r9,r9,r0
+	rotlw	r11,r11,r0
+	divwu	r11,r11,r9	# then we divide the shifted quantities
+2:	mullw	r10,r11,r4	# to get an estimate of the quotient,
+	mulhwu	r9,r11,r4	# multiply the estimate by the divisor,
+	subfc	r6,r10,r6	# take the product from the divisor,
+	add	r8,r8,r11	# and add the estimate to the accumulated
+	subfe.	r5,r9,r5	# quotient
+	bne	1b
+3:	cmplw	r6,r4
+	blt	4f
+	divwu	r0,r6,r4	# perform the remaining 32-bit division
+	mullw	r10,r0,r4	# and get the remainder
+	add	r8,r8,r0
+	subf	r6,r10,r6
+4:	stw	r7,0(r3)	# return the quotient in *r3
+	stw	r8,4(r3)
+	mr	r3,r6		# return the remainder in r3
+	blr
+
+/*
+ * Extended precision shifts.
+ *
+ * Updated to be valid for shift counts from 0 to 63 inclusive.
+ * -- Gabriel
+ *
+ * R3/R4 has 64 bit value
+ * R5    has shift count
+ * result in R3/R4
+ *
+ *  ashrdi3: arithmetic right shift (sign propagation)	
+ *  lshrdi3: logical right shift
+ *  ashldi3: left shift
+ */
+	.globl __ashrdi3
+__ashrdi3:
+	subfic	r6,r5,32
+	srw	r4,r4,r5	# LSW = count > 31 ? 0 : LSW >> count
+	addi	r7,r5,32	# could be xori, or addi with -32
+	slw	r6,r3,r6	# t1 = count > 31 ? 0 : MSW << (32-count)
+	rlwinm	r8,r7,0,32	# t3 = (count < 32) ? 32 : 0
+	sraw	r7,r3,r7	# t2 = MSW >> (count-32)
+	or	r4,r4,r6	# LSW |= t1
+	slw	r7,r7,r8	# t2 = (count < 32) ? 0 : t2
+	sraw	r3,r3,r5	# MSW = MSW >> count
+	or	r4,r4,r7	# LSW |= t2
+	blr
+
+	.globl __ashldi3
+__ashldi3:
+	subfic	r6,r5,32
+	slw	r3,r3,r5	# MSW = count > 31 ? 0 : MSW << count
+	addi	r7,r5,32	# could be xori, or addi with -32
+	srw	r6,r4,r6	# t1 = count > 31 ? 0 : LSW >> (32-count)
+	slw	r7,r4,r7	# t2 = count < 32 ? 0 : LSW << (count-32)
+	or	r3,r3,r6	# MSW |= t1
+	slw	r4,r4,r5	# LSW = LSW << count
+	or	r3,r3,r7	# MSW |= t2
+	blr
+
+	.globl __lshrdi3
+__lshrdi3:
+	subfic	r6,r5,32
+	srw	r4,r4,r5	# LSW = count > 31 ? 0 : LSW >> count
+	addi	r7,r5,32	# could be xori, or addi with -32
+	slw	r6,r3,r6	# t1 = count > 31 ? 0 : MSW << (32-count)
+	srw	r7,r3,r7	# t2 = count < 32 ? 0 : MSW >> (count-32)
+	or	r4,r4,r6	# LSW |= t1
+	srw	r3,r3,r5	# MSW = MSW >> count
+	or	r4,r4,r7	# LSW |= t2
+	blr