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, 233 insertions, 0 deletions

diff --git a/tools/include/nolibc/arch-powerpc.h b/tools/include/nolibc/arch-powerpc.h
new file mode 100644
index 000000000..dbe2e5205
--- /dev/null
+++ b/tools/include/nolibc/arch-powerpc.h
@@ -0,0 +1,233 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * PowerPC specific definitions for NOLIBC
+ * Copyright (C) 2023 Zhangjin Wu <falcon@tinylab.org>
+ */
+
+#ifndef _NOLIBC_ARCH_POWERPC_H
+#define _NOLIBC_ARCH_POWERPC_H
+
+#include <linux/unistd.h>
+
+#include "compiler.h"
+#include "crt.h"
+#include "std.h"
+
+/* Syscalls for PowerPC :
+ *   - stack is 16-byte aligned
+ *   - syscall number is passed in r0
+ *   - arguments are in r3, r4, r5, r6, r7, r8, r9
+ *   - the system call is performed by calling "sc"
+ *   - syscall return comes in r3, and the summary overflow bit is checked
+ *     to know if an error occurred, in which case errno is in r3.
+ *   - the arguments are cast to long and assigned into the target
+ *     registers which are then simply passed as registers to the asm code,
+ *     so that we don't have to experience issues with register constraints.
+ */
+
+#define _NOLIBC_SYSCALL_CLOBBERLIST \
+	"memory", "cr0", "ctr", "xer", "r12", "r11", "r10", "r9"
+
+#define __nolibc_syscall0(num)                                               \
+({                                                                           \
+	register long _ret  __asm__ ("r3");                                  \
+	register long _num  __asm__ ("r0") = (num);                          \
+									     \
+	__asm__ volatile (                                                   \
+		"	sc\n"                                                \
+		"	bns+ 1f\n"                                           \
+		"	neg  %0, %0\n"                                       \
+		"1:\n"                                                       \
+		: "=r"(_ret), "+r"(_num)                                     \
+		:                                                            \
+		: _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6", "r5", "r4"  \
+	);                                                                   \
+	_ret;                                                                \
+})
+
+#define __nolibc_syscall1(num, arg1)                                         \
+({                                                                           \
+	register long _ret  __asm__ ("r3");                                  \
+	register long _num  __asm__ ("r0") = (num);                          \
+	register long _arg1 __asm__ ("r3") = (long)(arg1);                   \
+									     \
+	__asm__ volatile (                                                   \
+		"	sc\n"                                                \
+		"	bns+ 1f\n"                                           \
+		"	neg  %0, %0\n"                                       \
+		"1:\n"                                                       \
+		: "=r"(_ret), "+r"(_num)                                     \
+		: "0"(_arg1)                                                 \
+		: _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6", "r5", "r4"  \
+	);                                                                   \
+	_ret;                                                                \
+})
+
+
+#define __nolibc_syscall2(num, arg1, arg2)                                   \
+({                                                                           \
+	register long _ret  __asm__ ("r3");                                  \
+	register long _num  __asm__ ("r0") = (num);                          \
+	register long _arg1 __asm__ ("r3") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("r4") = (long)(arg2);                   \
+									     \
+	__asm__ volatile (                                                   \
+		"	sc\n"                                                \
+		"	bns+ 1f\n"                                           \
+		"	neg  %0, %0\n"                                       \
+		"1:\n"                                                       \
+		: "=r"(_ret), "+r"(_num), "+r"(_arg2)                        \
+		: "0"(_arg1)                                                 \
+		: _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6", "r5"        \
+	);                                                                   \
+	_ret;                                                                \
+})
+
+
+#define __nolibc_syscall3(num, arg1, arg2, arg3)                             \
+({                                                                           \
+	register long _ret  __asm__ ("r3");                                  \
+	register long _num  __asm__ ("r0") = (num);                          \
+	register long _arg1 __asm__ ("r3") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("r4") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("r5") = (long)(arg3);                   \
+									     \
+	__asm__ volatile (                                                   \
+		"	sc\n"                                                \
+		"	bns+ 1f\n"                                           \
+		"	neg  %0, %0\n"                                       \
+		"1:\n"                                                       \
+		: "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3)           \
+		: "0"(_arg1)                                                 \
+		: _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6"              \
+	);                                                                   \
+	_ret;                                                                \
+})
+
+
+#define __nolibc_syscall4(num, arg1, arg2, arg3, arg4)                       \
+({                                                                           \
+	register long _ret  __asm__ ("r3");                                  \
+	register long _num  __asm__ ("r0") = (num);                          \
+	register long _arg1 __asm__ ("r3") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("r4") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("r5") = (long)(arg3);                   \
+	register long _arg4 __asm__ ("r6") = (long)(arg4);                   \
+									     \
+	__asm__ volatile (                                                   \
+		"	sc\n"                                                \
+		"	bns+ 1f\n"                                           \
+		"	neg  %0, %0\n"                                       \
+		"1:\n"                                                       \
+		: "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3),          \
+		  "+r"(_arg4)                                                \
+		: "0"(_arg1)                                                 \
+		: _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7"                    \
+	);                                                                   \
+	_ret;                                                                \
+})
+
+
+#define __nolibc_syscall5(num, arg1, arg2, arg3, arg4, arg5)                 \
+({                                                                           \
+	register long _ret  __asm__ ("r3");                                  \
+	register long _num  __asm__ ("r0") = (num);                          \
+	register long _arg1 __asm__ ("r3") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("r4") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("r5") = (long)(arg3);                   \
+	register long _arg4 __asm__ ("r6") = (long)(arg4);                   \
+	register long _arg5 __asm__ ("r7") = (long)(arg5);                   \
+									     \
+	__asm__ volatile (                                                   \
+		"	sc\n"                                                \
+		"	bns+ 1f\n"                                           \
+		"	neg  %0, %0\n"                                       \
+		"1:\n"                                                       \
+		: "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3),          \
+		  "+r"(_arg4), "+r"(_arg5)                                   \
+		: "0"(_arg1)                                                 \
+		: _NOLIBC_SYSCALL_CLOBBERLIST, "r8"                          \
+	);                                                                   \
+	_ret;                                                                \
+})
+
+#define __nolibc_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)           \
+({                                                                           \
+	register long _ret  __asm__ ("r3");                                  \
+	register long _num  __asm__ ("r0") = (num);                          \
+	register long _arg1 __asm__ ("r3") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("r4") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("r5") = (long)(arg3);                   \
+	register long _arg4 __asm__ ("r6") = (long)(arg4);                   \
+	register long _arg5 __asm__ ("r7") = (long)(arg5);                   \
+	register long _arg6 __asm__ ("r8") = (long)(arg6);                   \
+									     \
+	__asm__ volatile (                                                   \
+		"	sc\n"                                                \
+		"	bns+ 1f\n"                                           \
+		"	neg  %0, %0\n"                                       \
+		"1:\n"                                                       \
+		: "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3),          \
+		  "+r"(_arg4), "+r"(_arg5), "+r"(_arg6)                      \
+		: "0"(_arg1)                                                 \
+		: _NOLIBC_SYSCALL_CLOBBERLIST                                \
+	);                                                                   \
+	_ret;                                                                \
+})
+
+#if !defined(__powerpc64__) && !defined(__clang__)
+/* FIXME: For 32-bit PowerPC, with newer gcc compilers (e.g. gcc 13.1.0),
+ * "omit-frame-pointer" fails with __attribute__((no_stack_protector)) but
+ * works with __attribute__((__optimize__("-fno-stack-protector")))
+ */
+#ifdef __nolibc_no_stack_protector
+#undef __nolibc_no_stack_protector
+#define __nolibc_no_stack_protector __attribute__((__optimize__("-fno-stack-protector")))
+#endif
+#endif /* !__powerpc64__ */
+
+#ifndef NOLIBC_NO_RUNTIME
+/* startup code */
+void __attribute__((weak, noreturn)) __nolibc_entrypoint __nolibc_no_stack_protector _start(void)
+{
+#ifdef __powerpc64__
+#if _CALL_ELF == 2
+	/* with -mabi=elfv2, save TOC/GOT pointer to r2
+	 * r12 is global entry pointer, we use it to compute TOC from r12
+	 * https://www.llvm.org/devmtg/2014-04/PDFs/Talks/Euro-LLVM-2014-Weigand.pdf
+	 * https://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi.pdf
+	 */
+	__asm__ volatile (
+		"addis  2, 12, .TOC. - _start@ha\n"
+		"addi   2,  2, .TOC. - _start@l\n"
+	);
+#endif /* _CALL_ELF == 2 */
+
+	__asm__ volatile (
+		"mr     3, 1\n"         /* save stack pointer to r3, as arg1 of _start_c */
+		"li     0, 0\n"         /* zero the frame pointer                        */
+		"stdu   1, -32(1)\n"    /* the initial stack frame                       */
+		"bl     _start_c\n"     /* transfer to c runtime                         */
+	);
+#else
+	__asm__ volatile (
+		"mr     3, 1\n"         /* save stack pointer to r3, as arg1 of _start_c */
+		"li     0, 0\n"         /* zero the frame pointer                        */
+		"stwu   1, -16(1)\n"    /* the initial stack frame                       */
+		"bl     _start_c\n"     /* transfer to c runtime                         */
+	);
+#endif
+	__nolibc_entrypoint_epilogue();
+}
+#endif /* NOLIBC_NO_RUNTIME */
+
+#if !defined(__powerpc64__)
+static __attribute__((unused))
+int _sys_ftruncate64(int fd, uint32_t length0, uint32_t length1)
+{
+	return __nolibc_syscall4(__NR_ftruncate64, fd, 0, length0, length1);
+}
+#define _sys_ftruncate64 _sys_ftruncate64
+#endif
+
+#endif /* _NOLIBC_ARCH_POWERPC_H */