diff --git a/Documentation/trace/fprobe.rst b/Documentation/trace/fprobe.rst
index 196f523..71cd404 100644
--- a/Documentation/trace/fprobe.rst
+++ b/Documentation/trace/fprobe.rst
@@ -9,9 +9,10 @@
 Introduction
 ============
 
-Fprobe is a function entry/exit probe mechanism based on ftrace.
-Instead of using ftrace full feature, if you only want to attach callbacks
-on function entry and exit, similar to the kprobes and kretprobes, you can
+Fprobe is a function entry/exit probe based on the function-graph tracing
+feature in ftrace.
+Instead of tracing all functions, if you want to attach callbacks on specific
+function entry and exit, similar to the kprobes and kretprobes, you can
 use fprobe. Compared with kprobes and kretprobes, fprobe gives faster
 instrumentation for multiple functions with single handler. This document
 describes how to use fprobe.
@@ -91,12 +92,14 @@
 
 .. code-block:: c
 
- int entry_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, void *entry_data);
+ int entry_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data);
 
- void exit_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, void *entry_data);
+ void exit_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data);
 
-Note that the @entry_ip is saved at function entry and passed to exit handler.
-If the entry callback function returns !0, the corresponding exit callback will be cancelled.
+Note that the @entry_ip is saved at function entry and passed to exit
+handler.
+If the entry callback function returns !0, the corresponding exit callback
+will be cancelled.
 
 @fp
         This is the address of `fprobe` data structure related to this handler.
@@ -112,12 +115,10 @@
         This is the return address that the traced function will return to,
         somewhere in the caller. This can be used at both entry and exit.
 
-@regs
-        This is the `pt_regs` data structure at the entry and exit. Note that
-        the instruction pointer of @regs may be different from the @entry_ip
-        in the entry_handler. If you need traced instruction pointer, you need
-        to use @entry_ip. On the other hand, in the exit_handler, the instruction
-        pointer of @regs is set to the current return address.
+@fregs
+        This is the `ftrace_regs` data structure at the entry and exit. This
+        includes the function parameters, or the return values. So user can
+        access thos values via appropriate `ftrace_regs_*` APIs.
 
 @entry_data
         This is a local storage to share the data between entry and exit handlers.
@@ -125,6 +126,17 @@
         and `entry_data_size` field when registering the fprobe, the storage is
         allocated and passed to both `entry_handler` and `exit_handler`.
 
+Entry data size and exit handlers on the same function
+======================================================
+
+Since the entry data is passed via per-task stack and it has limited size,
+the entry data size per probe is limited to `15 * sizeof(long)`. You also need
+to take care that the different fprobes are probing on the same function, this
+limit becomes smaller. The entry data size is aligned to `sizeof(long)` and
+each fprobe which has exit handler uses a `sizeof(long)` space on the stack,
+you should keep the number of fprobes on the same function as small as
+possible.
+
 Share the callbacks with kprobes
 ================================
 
@@ -165,8 +177,8 @@
  - fprobe fails to take ftrace_recursion lock. This usually means that a function
    which is traced by other ftrace users is called from the entry_handler.
 
- - fprobe fails to setup the function exit because of the shortage of rethook
-   (the shadow stack for hooking the function return.)
+ - fprobe fails to setup the function exit because of failing to allocate the
+   data buffer from the per-task shadow stack.
 
 The `fprobe::nmissed` field counts up in both cases. Therefore, the former
 skips both of entry and exit callback and the latter skips the exit
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 93c651b..8301775 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -217,9 +217,11 @@
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_GUP_FAST
+	select HAVE_FTRACE_GRAPH_FUNC
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_ERROR_INJECTION
+	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_RETVAL
 	select HAVE_GCC_PLUGINS
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 4e350df..d2ff8f6 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -8,6 +8,7 @@
 syscall-y += unistd_compat_32.h
 
 generic-y += early_ioremap.h
+generic-y += fprobe.h
 generic-y += mcs_spinlock.h
 generic-y += mmzone.h
 generic-y += qrwlock.h
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index 5ccff4d..bfe3ce9 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -52,6 +52,8 @@ extern unsigned long ftrace_graph_call;
 extern void return_to_handler(void);
 
 unsigned long ftrace_call_adjust(unsigned long addr);
+unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip);
+#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 #define HAVE_ARCH_FTRACE_REGS
@@ -129,6 +131,38 @@ ftrace_override_function_with_return(struct ftrace_regs *fregs)
 	arch_ftrace_regs(fregs)->pc = arch_ftrace_regs(fregs)->lr;
 }
 
+static __always_inline unsigned long
+ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->fp;
+}
+
+static __always_inline unsigned long
+ftrace_regs_get_return_address(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->lr;
+}
+
+static __always_inline struct pt_regs *
+ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs);
+
+	memcpy(regs->regs, afregs->regs, sizeof(afregs->regs));
+	regs->sp = afregs->sp;
+	regs->pc = afregs->pc;
+	regs->regs[29] = afregs->fp;
+	regs->regs[30] = afregs->lr;
+	return regs;
+}
+
+#define arch_ftrace_fill_perf_regs(fregs, _regs) do {		\
+		(_regs)->pc = arch_ftrace_regs(fregs)->pc;			\
+		(_regs)->regs[29] = arch_ftrace_regs(fregs)->fp;		\
+		(_regs)->sp = arch_ftrace_regs(fregs)->sp;			\
+		(_regs)->pstate = PSR_MODE_EL1h;		\
+	} while (0)
+
 int ftrace_regs_query_register_offset(const char *name);
 
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
@@ -186,23 +220,6 @@ static inline bool arch_syscall_match_sym_name(const char *sym,
 
 #ifndef __ASSEMBLY__
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-struct fgraph_ret_regs {
-	/* x0 - x7 */
-	unsigned long regs[8];
-
-	unsigned long fp;
-	unsigned long __unused;
-};
-
-static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->regs[0];
-}
-
-static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->fp;
-}
 
 void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 			   unsigned long frame_pointer);
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 29bf85d..eb1a840 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -179,18 +179,6 @@ int main(void)
   DEFINE(FTRACE_OPS_FUNC,		offsetof(struct ftrace_ops, func));
 #endif
   BLANK();
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-  DEFINE(FGRET_REGS_X0,			offsetof(struct fgraph_ret_regs, regs[0]));
-  DEFINE(FGRET_REGS_X1,			offsetof(struct fgraph_ret_regs, regs[1]));
-  DEFINE(FGRET_REGS_X2,			offsetof(struct fgraph_ret_regs, regs[2]));
-  DEFINE(FGRET_REGS_X3,			offsetof(struct fgraph_ret_regs, regs[3]));
-  DEFINE(FGRET_REGS_X4,			offsetof(struct fgraph_ret_regs, regs[4]));
-  DEFINE(FGRET_REGS_X5,			offsetof(struct fgraph_ret_regs, regs[5]));
-  DEFINE(FGRET_REGS_X6,			offsetof(struct fgraph_ret_regs, regs[6]));
-  DEFINE(FGRET_REGS_X7,			offsetof(struct fgraph_ret_regs, regs[7]));
-  DEFINE(FGRET_REGS_FP,			offsetof(struct fgraph_ret_regs, fp));
-  DEFINE(FGRET_REGS_SIZE,		sizeof(struct fgraph_ret_regs));
-#endif
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
   DEFINE(FTRACE_OPS_DIRECT_CALL,	offsetof(struct ftrace_ops, direct_call));
 #endif
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index f0c1664..169ccf6 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -329,24 +329,28 @@
  * @fp is checked against the value passed by ftrace_graph_caller().
  */
 SYM_CODE_START(return_to_handler)
-	/* save return value regs */
-	sub sp, sp, #FGRET_REGS_SIZE
-	stp x0, x1, [sp, #FGRET_REGS_X0]
-	stp x2, x3, [sp, #FGRET_REGS_X2]
-	stp x4, x5, [sp, #FGRET_REGS_X4]
-	stp x6, x7, [sp, #FGRET_REGS_X6]
-	str x29,    [sp, #FGRET_REGS_FP]	// parent's fp
+	/* Make room for ftrace_regs */
+	sub	sp, sp, #FREGS_SIZE
+
+	/* Save return value regs */
+	stp	x0, x1, [sp, #FREGS_X0]
+	stp	x2, x3, [sp, #FREGS_X2]
+	stp	x4, x5, [sp, #FREGS_X4]
+	stp	x6, x7, [sp, #FREGS_X6]
+
+	/* Save the callsite's FP */
+	str	x29, [sp, #FREGS_FP]
 
 	mov	x0, sp
-	bl	ftrace_return_to_handler	// addr = ftrace_return_to_hander(regs);
+	bl	ftrace_return_to_handler	// addr = ftrace_return_to_hander(fregs);
 	mov	x30, x0				// restore the original return address
 
-	/* restore return value regs */
-	ldp x0, x1, [sp, #FGRET_REGS_X0]
-	ldp x2, x3, [sp, #FGRET_REGS_X2]
-	ldp x4, x5, [sp, #FGRET_REGS_X4]
-	ldp x6, x7, [sp, #FGRET_REGS_X6]
-	add sp, sp, #FGRET_REGS_SIZE
+	/* Restore return value regs */
+	ldp	x0, x1, [sp, #FREGS_X0]
+	ldp	x2, x3, [sp, #FREGS_X2]
+	ldp	x4, x5, [sp, #FREGS_X4]
+	ldp	x6, x7, [sp, #FREGS_X6]
+	add	sp, sp, #FREGS_SIZE
 
 	ret
 SYM_CODE_END(return_to_handler)
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 245cb41..d7c0d023 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -143,6 +143,69 @@ unsigned long ftrace_call_adjust(unsigned long addr)
 	return addr;
 }
 
+/* Convert fentry_ip to the symbol address without kallsyms */
+unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
+{
+	u32 insn;
+
+	/*
+	 * When using patchable-function-entry without pre-function NOPS, ftrace
+	 * entry is the address of the first NOP after the function entry point.
+	 *
+	 * The compiler has either generated:
+	 *
+	 * func+00:	func:	NOP		// To be patched to MOV X9, LR
+	 * func+04:		NOP		// To be patched to BL <caller>
+	 *
+	 * Or:
+	 *
+	 * func-04:		BTI	C
+	 * func+00:	func:	NOP		// To be patched to MOV X9, LR
+	 * func+04:		NOP		// To be patched to BL <caller>
+	 *
+	 * The fentry_ip is the address of `BL <caller>` which is at `func + 4`
+	 * bytes in either case.
+	 */
+	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+		return fentry_ip - AARCH64_INSN_SIZE;
+
+	/*
+	 * When using patchable-function-entry with pre-function NOPs, BTI is
+	 * a bit different.
+	 *
+	 * func+00:	func:	NOP		// To be patched to MOV X9, LR
+	 * func+04:		NOP		// To be patched to BL <caller>
+	 *
+	 * Or:
+	 *
+	 * func+00:	func:	BTI	C
+	 * func+04:		NOP		// To be patched to MOV X9, LR
+	 * func+08:		NOP		// To be patched to BL <caller>
+	 *
+	 * The fentry_ip is the address of `BL <caller>` which is at either
+	 * `func + 4` or `func + 8` depends on whether there is a BTI.
+	 */
+
+	/* If there is no BTI, the func address should be one instruction before. */
+	if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+		return fentry_ip - AARCH64_INSN_SIZE;
+
+	/* We want to be extra safe in case entry ip is on the page edge,
+	 * but otherwise we need to avoid get_kernel_nofault()'s overhead.
+	 */
+	if ((fentry_ip & ~PAGE_MASK) < AARCH64_INSN_SIZE * 2) {
+		if (get_kernel_nofault(insn, (u32 *)(fentry_ip - AARCH64_INSN_SIZE * 2)))
+			return 0;
+	} else {
+		insn = *(u32 *)(fentry_ip - AARCH64_INSN_SIZE * 2);
+	}
+
+	if (aarch64_insn_is_bti(le32_to_cpu((__le32)insn)))
+		return fentry_ip - AARCH64_INSN_SIZE * 2;
+
+	return fentry_ip - AARCH64_INSN_SIZE;
+}
+
 /*
  * Replace a single instruction, which may be a branch or NOP.
  * If @validate == true, a replaced instruction is checked against 'old'.
@@ -481,7 +544,20 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	prepare_ftrace_return(ip, &arch_ftrace_regs(fregs)->lr, arch_ftrace_regs(fregs)->fp);
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long frame_pointer = arch_ftrace_regs(fregs)->fp;
+	unsigned long *parent = &arch_ftrace_regs(fregs)->lr;
+	unsigned long old;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	old = *parent;
+
+	if (!function_graph_enter_regs(old, ip, frame_pointer,
+				       (void *)frame_pointer, fregs)) {
+		*parent = return_hooker;
+	}
 }
 #else
 /*
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 28acd0b..28f0221 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -129,16 +129,18 @@
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS
+	select HAVE_FTRACE_REGS_HAVING_PT_REGS
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN
 	select HAVE_EXIT_THREAD
 	select HAVE_GUP_FAST
+	select HAVE_FTRACE_GRAPH_FUNC
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_ERROR_INJECTION
-	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
diff --git a/arch/loongarch/include/asm/fprobe.h b/arch/loongarch/include/asm/fprobe.h
new file mode 100644
index 0000000..7af3b31
--- /dev/null
+++ b/arch/loongarch/include/asm/fprobe.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_LOONGARCH_FPROBE_H
+#define _ASM_LOONGARCH_FPROBE_H
+
+/*
+ * Explicitly undef ARCH_DEFINE_ENCODE_FPROBE_HEADER, because loongarch does not
+ * have enough number of fixed MSBs of the address of kernel objects for
+ * encoding the size of data in fprobe_header. Use 2-entries encoding instead.
+ */
+#undef ARCH_DEFINE_ENCODE_FPROBE_HEADER
+
+#endif /* _ASM_LOONGARCH_FPROBE_H */
diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h
index 8f13eae..6e0a997 100644
--- a/arch/loongarch/include/asm/ftrace.h
+++ b/arch/loongarch/include/asm/ftrace.h
@@ -57,6 +57,16 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip)
 	instruction_pointer_set(&arch_ftrace_regs(fregs)->regs, ip);
 }
 
+#undef ftrace_regs_get_frame_pointer
+#define ftrace_regs_get_frame_pointer(fregs) \
+	(arch_ftrace_regs(fregs)->regs.regs[22])
+
+static __always_inline unsigned long
+ftrace_regs_get_return_address(struct ftrace_regs *fregs)
+{
+	return *(unsigned long *)(arch_ftrace_regs(fregs)->regs.regs[1]);
+}
+
 #define ftrace_graph_func ftrace_graph_func
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs);
@@ -78,26 +88,4 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
 
 #endif /* CONFIG_FUNCTION_TRACER */
 
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-struct fgraph_ret_regs {
-	/* a0 - a1 */
-	unsigned long regs[2];
-
-	unsigned long fp;
-	unsigned long __unused;
-};
-
-static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->regs[0];
-}
-
-static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->fp;
-}
-#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */
-#endif
-
 #endif /* _ASM_LOONGARCH_FTRACE_H */
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 049c5c3..8be1c38 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -280,18 +280,6 @@ static void __used output_pbe_defines(void)
 }
 #endif
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static void __used output_fgraph_ret_regs_defines(void)
-{
-	COMMENT("LoongArch fgraph_ret_regs offsets.");
-	OFFSET(FGRET_REGS_A0, fgraph_ret_regs, regs[0]);
-	OFFSET(FGRET_REGS_A1, fgraph_ret_regs, regs[1]);
-	OFFSET(FGRET_REGS_FP, fgraph_ret_regs, fp);
-	DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs));
-	BLANK();
-}
-#endif
-
 static void __used output_kvm_defines(void)
 {
 	COMMENT("KVM/LoongArch Specific offsets.");
diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c
index 1805622..25c9a4c 100644
--- a/arch/loongarch/kernel/ftrace_dyn.c
+++ b/arch/loongarch/kernel/ftrace_dyn.c
@@ -243,8 +243,16 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 {
 	struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs;
 	unsigned long *parent = (unsigned long *)&regs->regs[1];
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long old;
 
-	prepare_ftrace_return(ip, (unsigned long *)parent);
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	old = *parent;
+
+	if (!function_graph_enter_regs(old, ip, 0, parent, fregs))
+		*parent = return_hooker;
 }
 #else
 static int ftrace_modify_graph_caller(bool enable)
diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S
index 3015896..b685050 100644
--- a/arch/loongarch/kernel/mcount.S
+++ b/arch/loongarch/kernel/mcount.S
@@ -79,10 +79,11 @@
 SYM_FUNC_END(ftrace_graph_caller)
 
 SYM_FUNC_START(return_to_handler)
-	PTR_ADDI	sp, sp, -FGRET_REGS_SIZE
-	PTR_S		a0, sp, FGRET_REGS_A0
-	PTR_S		a1, sp, FGRET_REGS_A1
-	PTR_S		zero, sp, FGRET_REGS_FP
+	/* Save return value regs */
+	PTR_ADDI	sp, sp, -PT_SIZE
+	PTR_S		a0, sp, PT_R4
+	PTR_S		a1, sp, PT_R5
+	PTR_S		zero, sp, PT_R22
 
 	move		a0, sp
 	bl		ftrace_return_to_handler
@@ -90,9 +91,11 @@
 	/* Restore the real parent address: a0 -> ra */
 	move		ra, a0
 
-	PTR_L		a0, sp, FGRET_REGS_A0
-	PTR_L		a1, sp, FGRET_REGS_A1
-	PTR_ADDI	sp, sp, FGRET_REGS_SIZE
+	/* Restore return value regs */
+	PTR_L		a0, sp, PT_R4
+	PTR_L		a1, sp, PT_R5
+	PTR_ADDI	sp, sp, PT_SIZE
+
 	jr		ra
 SYM_FUNC_END(return_to_handler)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S
index 0c65cf0..d6b474a 100644
--- a/arch/loongarch/kernel/mcount_dyn.S
+++ b/arch/loongarch/kernel/mcount_dyn.S
@@ -140,19 +140,19 @@
 SYM_CODE_START(return_to_handler)
 	UNWIND_HINT_UNDEFINED
 	/* Save return value regs */
-	PTR_ADDI	sp, sp, -FGRET_REGS_SIZE
-	PTR_S		a0, sp, FGRET_REGS_A0
-	PTR_S		a1, sp, FGRET_REGS_A1
-	PTR_S		zero, sp, FGRET_REGS_FP
+	PTR_ADDI	sp, sp, -PT_SIZE
+	PTR_S		a0, sp, PT_R4
+	PTR_S		a1, sp, PT_R5
+	PTR_S		zero, sp, PT_R22
 
 	move		a0, sp
 	bl		ftrace_return_to_handler
 	move		ra, a0
 
 	/* Restore return value regs */
-	PTR_L		a0, sp, FGRET_REGS_A0
-	PTR_L		a1, sp, FGRET_REGS_A1
-	PTR_ADDI	sp, sp, FGRET_REGS_SIZE
+	PTR_L		a0, sp, PT_R4
+	PTR_L		a1, sp, PT_R5
+	PTR_ADDI	sp, sp, PT_SIZE
 
 	jr		ra
 SYM_CODE_END(return_to_handler)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index db9f7b2..34b965f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -241,6 +241,7 @@
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_GUP_FAST
+	select HAVE_FTRACE_GRAPH_FUNC
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_DESCRIPTORS	if PPC64_ELF_ABI_V1
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index db481b3..82da7c7 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -43,6 +43,13 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *
 	return arch_ftrace_regs(fregs)->regs.msr ? &arch_ftrace_regs(fregs)->regs : NULL;
 }
 
+#define arch_ftrace_fill_perf_regs(fregs, _regs) do {		\
+		(_regs)->result = 0;				\
+		(_regs)->nip = arch_ftrace_regs(fregs)->regs.nip;		\
+		(_regs)->gpr[1] = arch_ftrace_regs(fregs)->regs.gpr[1];		\
+		asm volatile("mfmsr %0" : "=r" ((_regs)->msr));	\
+	} while (0)
+
 static __always_inline void
 ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
 				    unsigned long ip)
@@ -50,6 +57,12 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
 	regs_set_return_ip(&arch_ftrace_regs(fregs)->regs, ip);
 }
 
+static __always_inline unsigned long
+ftrace_regs_get_return_address(struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->regs.link;
+}
+
 struct ftrace_ops;
 
 #define ftrace_graph_func ftrace_graph_func
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 5ccd791..2f776f1 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -658,7 +658,6 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	unsigned long sp = arch_ftrace_regs(fregs)->regs.gpr[1];
-	int bit;
 
 	if (unlikely(ftrace_graph_is_dead()))
 		goto out;
@@ -666,14 +665,9 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
 
-	bit = ftrace_test_recursion_trylock(ip, parent_ip);
-	if (bit < 0)
-		goto out;
-
-	if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp))
+	if (!function_graph_enter_regs(parent_ip, ip, 0, (unsigned long *)sp, fregs))
 		parent_ip = ppc_function_entry(return_to_handler);
 
-	ftrace_test_recursion_unlock(bit);
 out:
 	arch_ftrace_regs(fregs)->regs.link = parent_ip;
 }
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index 9878737..ac35015 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -787,10 +787,10 @@ int ftrace_disable_ftrace_graph_caller(void)
  * in current thread info. Return the address we want to divert to.
  */
 static unsigned long
-__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp)
+__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp,
+			struct ftrace_regs *fregs)
 {
 	unsigned long return_hooker;
-	int bit;
 
 	if (unlikely(ftrace_graph_is_dead()))
 		goto out;
@@ -798,16 +798,11 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
 
-	bit = ftrace_test_recursion_trylock(ip, parent);
-	if (bit < 0)
-		goto out;
-
 	return_hooker = ppc_function_entry(return_to_handler);
 
-	if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
+	if (!function_graph_enter_regs(parent, ip, 0, (unsigned long *)sp, fregs))
 		parent = return_hooker;
 
-	ftrace_test_recursion_unlock(bit);
 out:
 	return parent;
 }
@@ -816,13 +811,14 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip, arch_ftrace_regs(fregs)->regs.gpr[1]);
+	arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip,
+						arch_ftrace_regs(fregs)->regs.gpr[1], fregs);
 }
 #else
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
 				    unsigned long sp)
 {
-	return __prepare_ftrace_return(parent, ip, sp);
+	return __prepare_ftrace_return(parent, ip, sp, NULL);
 }
 #endif
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d4a7ca0..c736e34 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -146,9 +146,10 @@
 	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE)
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE
+	select HAVE_FTRACE_GRAPH_FUNC
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION
 	select HAVE_EBPF_JIT if MMU
 	select HAVE_GUP_FAST if MMU
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index de13d5a2..bd5fc94 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -4,6 +4,7 @@
 
 generic-y += early_ioremap.h
 generic-y += flat.h
+generic-y += fprobe.h
 generic-y += kvm_para.h
 generic-y += mmzone.h
 generic-y += mcs_spinlock.h
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 3d66437..c4721ce 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -168,6 +168,11 @@ static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct
 	return arch_ftrace_regs(fregs)->sp;
 }
 
+static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->s0;
+}
+
 static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs,
 							      unsigned int n)
 {
@@ -181,6 +186,11 @@ static __always_inline unsigned long ftrace_regs_get_return_value(const struct f
 	return arch_ftrace_regs(fregs)->a0;
 }
 
+static __always_inline unsigned long ftrace_regs_get_return_address(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->ra;
+}
+
 static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs,
 							 unsigned long ret)
 {
@@ -192,6 +202,20 @@ static __always_inline void ftrace_override_function_with_return(struct ftrace_r
 	arch_ftrace_regs(fregs)->epc = arch_ftrace_regs(fregs)->ra;
 }
 
+static __always_inline struct pt_regs *
+ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs);
+
+	memcpy(&regs->a0, afregs->args, sizeof(afregs->args));
+	regs->epc = afregs->epc;
+	regs->ra = afregs->ra;
+	regs->sp = afregs->sp;
+	regs->s0 = afregs->s0;
+	regs->t1 = afregs->t1;
+	return regs;
+}
+
 int ftrace_regs_query_register_offset(const char *name);
 
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
@@ -208,25 +232,4 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsi
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-struct fgraph_ret_regs {
-	unsigned long a1;
-	unsigned long a0;
-	unsigned long s0;
-	unsigned long ra;
-};
-
-static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->a0;
-}
-
-static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->s0;
-}
-#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */
-#endif
-
 #endif /* _ASM_RISCV_FTRACE_H */
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 8cb9b21..3524db5 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -214,7 +214,22 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	prepare_ftrace_return(&arch_ftrace_regs(fregs)->ra, ip, arch_ftrace_regs(fregs)->s0);
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long frame_pointer = arch_ftrace_regs(fregs)->s0;
+	unsigned long *parent = &arch_ftrace_regs(fregs)->ra;
+	unsigned long old;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/*
+	 * We don't suffer access faults, so no extra fault-recovery assembly
+	 * is needed here.
+	 */
+	old = *parent;
+
+	if (!function_graph_enter_regs(old, ip, frame_pointer, parent, fregs))
+		*parent = return_hooker;
 }
 #else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 extern void ftrace_graph_call(void);
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 3a42f62..0681680 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -12,6 +12,8 @@
 #include <asm/asm-offsets.h>
 #include <asm/ftrace.h>
 
+#define ABI_SIZE_ON_STACK	80
+
 	.text
 
 	.macro SAVE_ABI_STATE
@@ -26,12 +28,12 @@
 	 * register if a0 was not saved.
 	 */
 	.macro SAVE_RET_ABI_STATE
-	addi	sp, sp, -4*SZREG
-	REG_S	s0, 2*SZREG(sp)
-	REG_S	ra, 3*SZREG(sp)
-	REG_S	a0, 1*SZREG(sp)
-	REG_S	a1, 0*SZREG(sp)
-	addi	s0, sp, 4*SZREG
+	addi	sp, sp, -ABI_SIZE_ON_STACK
+	REG_S	ra, 1*SZREG(sp)
+	REG_S	s0, 8*SZREG(sp)
+	REG_S	a0, 10*SZREG(sp)
+	REG_S	a1, 11*SZREG(sp)
+	addi	s0, sp, ABI_SIZE_ON_STACK
 	.endm
 
 	.macro RESTORE_ABI_STATE
@@ -41,11 +43,11 @@
 	.endm
 
 	.macro RESTORE_RET_ABI_STATE
-	REG_L	ra, 3*SZREG(sp)
-	REG_L	s0, 2*SZREG(sp)
-	REG_L	a0, 1*SZREG(sp)
-	REG_L	a1, 0*SZREG(sp)
-	addi	sp, sp, 4*SZREG
+	REG_L	ra, 1*SZREG(sp)
+	REG_L	s0, 8*SZREG(sp)
+	REG_L	a0, 10*SZREG(sp)
+	REG_L	a1, 11*SZREG(sp)
+	addi	sp, sp, ABI_SIZE_ON_STACK
 	.endm
 
 SYM_TYPED_FUNC_START(ftrace_stub)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index e4931a3..5cbbb7d 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -183,16 +183,18 @@
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS
+	select HAVE_FTRACE_REGS_HAVING_PT_REGS
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EBPF_JIT if HAVE_MARCH_Z196_FEATURES
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_GUP_FAST
 	select HAVE_FENTRY
+	select HAVE_FTRACE_GRAPH_FUNC
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_ERROR_INJECTION
-	select HAVE_FUNCTION_GRAPH_RETVAL
+	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
diff --git a/arch/s390/include/asm/fprobe.h b/arch/s390/include/asm/fprobe.h
new file mode 100644
index 0000000..5ef600b
--- /dev/null
+++ b/arch/s390/include/asm/fprobe.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_FPROBE_H
+#define _ASM_S390_FPROBE_H
+
+#include <asm-generic/fprobe.h>
+
+#undef FPROBE_HEADER_MSB_PATTERN
+#define FPROBE_HEADER_MSB_PATTERN 0
+
+#endif /* _ASM_S390_FPROBE_H */
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index fc97d75..a3b73a4 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -39,6 +39,7 @@ struct dyn_arch_ftrace { };
 
 struct module;
 struct dyn_ftrace;
+struct ftrace_ops;
 
 bool ftrace_need_init_nop(void);
 #define ftrace_need_init_nop ftrace_need_init_nop
@@ -62,23 +63,6 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *
 	return NULL;
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-struct fgraph_ret_regs {
-	unsigned long gpr2;
-	unsigned long fp;
-};
-
-static __always_inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->gpr2;
-}
-
-static __always_inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->fp;
-}
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
 static __always_inline void
 ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
 				    unsigned long ip)
@@ -86,6 +70,25 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
 	arch_ftrace_regs(fregs)->regs.psw.addr = ip;
 }
 
+#undef ftrace_regs_get_frame_pointer
+static __always_inline unsigned long
+ftrace_regs_get_frame_pointer(struct ftrace_regs *fregs)
+{
+	return ftrace_regs_get_stack_pointer(fregs);
+}
+
+static __always_inline unsigned long
+ftrace_regs_get_return_address(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->regs.gprs[14];
+}
+
+#define arch_ftrace_fill_perf_regs(fregs, _regs)	 do {		\
+		(_regs)->psw.mask = 0;					\
+		(_regs)->psw.addr = arch_ftrace_regs(fregs)->regs.psw.addr;		\
+		(_regs)->gprs[15] = arch_ftrace_regs(fregs)->regs.gprs[15];		\
+	} while (0)
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 /*
  * When an ftrace registered caller is tracing a function that is
@@ -126,6 +129,10 @@ static inline bool arch_syscall_match_sym_name(const char *sym,
 	return !strcmp(sym + 7, name) || !strcmp(sym + 8, name);
 }
 
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+#define ftrace_graph_func ftrace_graph_func
+
 #endif /* __ASSEMBLY__ */
 
 #ifdef CONFIG_FUNCTION_TRACER
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 862a914..3670911 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -175,12 +175,6 @@ int main(void)
 	DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size));
 	DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line));
 	DEFINE(MAX_COMMAND_LINE_SIZE, PARMAREA + offsetof(struct parmarea, max_command_line_size));
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* function graph return value tracing */
-	OFFSET(__FGRAPH_RET_GPR2, fgraph_ret_regs, gpr2);
-	OFFSET(__FGRAPH_RET_FP, fgraph_ret_regs, fp);
-	DEFINE(__FGRAPH_RET_SIZE, sizeof(struct fgraph_ret_regs));
-#endif
 	OFFSET(__FTRACE_REGS_PT_REGS, __arch_ftrace_regs, regs);
 	DEFINE(__FTRACE_REGS_SIZE, sizeof(struct __arch_ftrace_regs));
 
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 2196952..a1f2887 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -41,7 +41,6 @@ void do_restart(void *arg);
 void __init startup_init(void);
 void die(struct pt_regs *regs, const char *str);
 int setup_profiling_timer(unsigned int multiplier);
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip);
 
 struct s390_mmap_arg_struct;
 struct fadvise64_64_args;
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 51439a7..c0b2c97 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -261,43 +261,23 @@ void ftrace_arch_code_modify_post_process(void)
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-/*
- * Hook the return address and push it in the stack of return addresses
- * in current thread info.
- */
-unsigned long prepare_ftrace_return(unsigned long ra, unsigned long sp,
-				    unsigned long ip)
+
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
+	unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14];
+	int bit;
+
 	if (unlikely(ftrace_graph_is_dead()))
-		goto out;
+		return;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
-		goto out;
-	ip -= MCOUNT_INSN_SIZE;
-	if (!function_graph_enter(ra, ip, 0, (void *) sp))
-		ra = (unsigned long) return_to_handler;
-out:
-	return ra;
-}
-NOKPROBE_SYMBOL(prepare_ftrace_return);
-
-/*
- * Patch the kernel code at ftrace_graph_caller location. The instruction
- * there is branch relative on condition. To enable the ftrace graph code
- * block, we simply patch the mask field of the instruction to zero and
- * turn the instruction into a nop.
- * To disable the ftrace graph code the mask field will be patched to
- * all ones, which turns the instruction into an unconditional branch.
- */
-int ftrace_enable_ftrace_graph_caller(void)
-{
-	/* Expect brc 0xf,... */
-	return ftrace_patch_branch_mask(ftrace_graph_caller, 0xa7f4, false);
-}
-
-int ftrace_disable_ftrace_graph_caller(void)
-{
-	/* Expect brc 0x0,... */
-	return ftrace_patch_branch_mask(ftrace_graph_caller, 0xa704, true);
+		return;
+	bit = ftrace_test_recursion_trylock(ip, *parent);
+	if (bit < 0)
+		return;
+	if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
+		*parent = (unsigned long)&return_to_handler;
+	ftrace_test_recursion_unlock(bit);
 }
 
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 7e267ef..1fec370 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -104,17 +104,6 @@
 	lgr	%r3,%r14
 	la	%r5,STACK_FREGS(%r15)
 	BASR_EX	%r14,%r1
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-# The j instruction gets runtime patched to a nop instruction.
-# See ftrace_enable_ftrace_graph_caller.
-SYM_INNER_LABEL(ftrace_graph_caller, SYM_L_GLOBAL)
-	j	.Lftrace_graph_caller_end
-	lmg	%r2,%r3,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15)
-	lg	%r4,(STACK_FREGS_PTREGS_PSW+8)(%r15)
-	brasl	%r14,prepare_ftrace_return
-	stg	%r2,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15)
-.Lftrace_graph_caller_end:
-#endif
 	lg	%r0,(STACK_FREGS_PTREGS_PSW+8)(%r15)
 #ifdef MARCH_HAS_Z196_FEATURES
 	ltg	%r1,STACK_FREGS_PTREGS_ORIG_GPR2(%r15)
@@ -134,14 +123,14 @@
 SYM_FUNC_START(return_to_handler)
 	stmg	%r2,%r5,32(%r15)
 	lgr	%r1,%r15
-	aghi	%r15,-(STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE)
+	# allocate ftrace_regs and stack frame for ftrace_return_to_handler
+	aghi	%r15,-STACK_FRAME_SIZE_FREGS
 	stg	%r1,__SF_BACKCHAIN(%r15)
-	la	%r3,STACK_FRAME_OVERHEAD(%r15)
-	stg	%r1,__FGRAPH_RET_FP(%r3)
-	stg	%r2,__FGRAPH_RET_GPR2(%r3)
-	lgr	%r2,%r3
+	stg	%r2,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15)
+	stg	%r1,(STACK_FREGS_PTREGS_GPRS+15*8)(%r15)
+	la	%r2,STACK_FRAME_OVERHEAD(%r15)
 	brasl	%r14,ftrace_return_to_handler
-	aghi	%r15,STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE
+	aghi	%r15,STACK_FRAME_SIZE_FREGS
 	lgr	%r14,%r2
 	lmg	%r2,%r5,32(%r15)
 	BR_EX	%r14
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b67f027..27c21c9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -224,6 +224,7 @@
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS	if X86_64
+	select HAVE_FTRACE_REGS_HAVING_PT_REGS	if X86_64
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_SAMPLE_FTRACE_DIRECT	if X86_64
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64
@@ -233,8 +234,9 @@
 	select HAVE_EXIT_THREAD
 	select HAVE_GUP_FAST
 	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE
+	select HAVE_FTRACE_GRAPH_FUNC		if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_FUNCTION_GRAPH_RETVAL	if HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_GRAPH_FREGS	if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER	if X86_32 || (X86_64 && DYNAMIC_FTRACE)
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 6c23d16..58f4dde 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -10,5 +10,6 @@
 generated-y += xen-hypercalls.h
 
 generic-y += early_ioremap.h
+generic-y += fprobe.h
 generic-y += mcs_spinlock.h
 generic-y += mmzone.h
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 6e8cf0f..f9cb4d0 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -34,6 +34,27 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	return addr;
 }
 
+static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
+{
+#ifdef CONFIG_X86_KERNEL_IBT
+	u32 instr;
+
+	/* We want to be extra safe in case entry ip is on the page edge,
+	 * but otherwise we need to avoid get_kernel_nofault()'s overhead.
+	 */
+	if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
+		if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
+			return fentry_ip;
+	} else {
+		instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
+	}
+	if (is_endbr(instr))
+		fentry_ip -= ENDBR_INSN_SIZE;
+#endif
+	return fentry_ip;
+}
+#define ftrace_get_symaddr(fentry_ip)	arch_ftrace_get_symaddr(fentry_ip)
+
 #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
 #include <linux/ftrace_regs.h>
@@ -47,10 +68,23 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
 	return &arch_ftrace_regs(fregs)->regs;
 }
 
+#define arch_ftrace_fill_perf_regs(fregs, _regs) do {	\
+		(_regs)->ip = arch_ftrace_regs(fregs)->regs.ip;		\
+		(_regs)->sp = arch_ftrace_regs(fregs)->regs.sp;		\
+		(_regs)->cs = __KERNEL_CS;		\
+		(_regs)->flags = 0;			\
+	} while (0)
+
 #define ftrace_regs_set_instruction_pointer(fregs, _ip)	\
 	do { arch_ftrace_regs(fregs)->regs.ip = (_ip); } while (0)
 
 
+static __always_inline unsigned long
+ftrace_regs_get_return_address(struct ftrace_regs *fregs)
+{
+	return *(unsigned long *)ftrace_regs_get_stack_pointer(fregs);
+}
+
 struct ftrace_ops;
 #define ftrace_graph_func ftrace_graph_func
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
@@ -134,24 +168,4 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
 #endif /* !COMPILE_OFFSETS */
 #endif /* !__ASSEMBLY__ */
 
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-struct fgraph_ret_regs {
-	unsigned long ax;
-	unsigned long dx;
-	unsigned long bp;
-};
-
-static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->ax;
-}
-
-static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->bp;
-}
-#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */
-#endif
-
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 4dd0ad6..166bc0e 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -607,16 +607,8 @@ int ftrace_disable_ftrace_graph_caller(void)
 }
 #endif /* CONFIG_DYNAMIC_FTRACE && !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 
-/*
- * Hook the return address and push it in the stack of return addrs
- * in current thread info.
- */
-void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
-			   unsigned long frame_pointer)
+static inline bool skip_ftrace_return(void)
 {
-	unsigned long return_hooker = (unsigned long)&return_to_handler;
-	int bit;
-
 	/*
 	 * When resuming from suspend-to-ram, this function can be indirectly
 	 * called from early CPU startup code while the CPU is in real mode,
@@ -626,23 +618,31 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 	 * This check isn't as accurate as virt_addr_valid(), but it should be
 	 * good enough for this purpose, and it's fast.
 	 */
-	if (unlikely((long)__builtin_frame_address(0) >= 0))
-		return;
+	if ((long)__builtin_frame_address(0) >= 0)
+		return true;
 
-	if (unlikely(ftrace_graph_is_dead()))
-		return;
+	if (ftrace_graph_is_dead())
+		return true;
 
-	if (unlikely(atomic_read(&current->tracing_graph_pause)))
-		return;
+	if (atomic_read(&current->tracing_graph_pause))
+		return true;
+	return false;
+}
 
-	bit = ftrace_test_recursion_trylock(ip, *parent);
-	if (bit < 0)
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+
+	if (unlikely(skip_ftrace_return()))
 		return;
 
 	if (!function_graph_enter(*parent, ip, frame_pointer, parent))
 		*parent = return_hooker;
-
-	ftrace_test_recursion_unlock(bit);
 }
 
 #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
@@ -651,8 +651,15 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 {
 	struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs;
 	unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs);
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long *parent = (unsigned long *)stack;
 
-	prepare_ftrace_return(ip, (unsigned long *)stack, 0);
+	if (unlikely(skip_ftrace_return()))
+		return;
+
+
+	if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
+		*parent = return_hooker;
 }
 #endif
 
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index 58d9ed5..f4e0c33 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -187,14 +187,15 @@
 
 .globl return_to_handler
 return_to_handler:
-	pushl	$0
-	pushl	%edx
-	pushl	%eax
+	subl	$(PTREGS_SIZE), %esp
+	movl	$0, PT_EBP(%esp)
+	movl	%edx, PT_EDX(%esp)
+	movl	%eax, PT_EAX(%esp)
 	movl	%esp, %eax
 	call	ftrace_return_to_handler
 	movl	%eax, %ecx
-	popl	%eax
-	popl	%edx
-	addl	$4, %esp		# skip ebp
+	movl	PT_EAX(%esp), %eax
+	movl	PT_EDX(%esp), %edx
+	addl	$(PTREGS_SIZE), %esp
 	JMP_NOSPEC ecx
 #endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 214f30e..d516472 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -348,21 +348,22 @@
 SYM_CODE_START(return_to_handler)
 	UNWIND_HINT_UNDEFINED
 	ANNOTATE_NOENDBR
-	subq  $24, %rsp
 
-	/* Save the return values */
-	movq %rax, (%rsp)
-	movq %rdx, 8(%rsp)
-	movq %rbp, 16(%rsp)
+	/* Save ftrace_regs for function exit context  */
+	subq $(FRAME_SIZE), %rsp
+
+	movq %rax, RAX(%rsp)
+	movq %rdx, RDX(%rsp)
+	movq %rbp, RBP(%rsp)
 	movq %rsp, %rdi
 
 	call ftrace_return_to_handler
 
 	movq %rax, %rdi
-	movq 8(%rsp), %rdx
-	movq (%rsp), %rax
+	movq RDX(%rsp), %rdx
+	movq RAX(%rsp), %rax
 
-	addq $24, %rsp
+	addq $(FRAME_SIZE), %rsp
 	/*
 	 * Jump back to the old return address. This cannot be JMP_NOSPEC rdi
 	 * since IBT would demand that contain ENDBR, which simply isn't so for
diff --git a/include/asm-generic/fprobe.h b/include/asm-generic/fprobe.h
new file mode 100644
index 0000000..8659a4d
--- /dev/null
+++ b/include/asm-generic/fprobe.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Generic arch dependent fprobe macros.
+ */
+#ifndef __ASM_GENERIC_FPROBE_H__
+#define __ASM_GENERIC_FPROBE_H__
+
+#include <linux/bits.h>
+
+#ifdef CONFIG_64BIT
+/*
+ * Encoding the size and the address of fprobe into one 64bit entry.
+ * The 32bit architectures should use 2 entries to store those info.
+ */
+
+#define ARCH_DEFINE_ENCODE_FPROBE_HEADER
+
+#define FPROBE_HEADER_MSB_SIZE_SHIFT (BITS_PER_LONG - FPROBE_DATA_SIZE_BITS)
+#define FPROBE_HEADER_MSB_MASK					\
+	GENMASK(FPROBE_HEADER_MSB_SIZE_SHIFT - 1, 0)
+
+/*
+ * By default, this expects the MSBs in the address of kprobe is 0xf.
+ * If any arch needs another fixed pattern (e.g. s390 is zero filled),
+ * override this.
+ */
+#define FPROBE_HEADER_MSB_PATTERN				\
+	GENMASK(BITS_PER_LONG - 1, FPROBE_HEADER_MSB_SIZE_SHIFT)
+
+#define arch_fprobe_header_encodable(fp)			\
+	(((unsigned long)(fp) & ~FPROBE_HEADER_MSB_MASK) ==	\
+	 FPROBE_HEADER_MSB_PATTERN)
+
+#define arch_encode_fprobe_header(fp, size)			\
+	(((unsigned long)(fp) & FPROBE_HEADER_MSB_MASK) |	\
+	 ((unsigned long)(size) << FPROBE_HEADER_MSB_SIZE_SHIFT))
+
+#define arch_decode_fprobe_header_size(val)			\
+	((unsigned long)(val) >> FPROBE_HEADER_MSB_SIZE_SHIFT)
+
+#define arch_decode_fprobe_header_fp(val)					\
+	((struct fprobe *)(((unsigned long)(val) & FPROBE_HEADER_MSB_MASK) |	\
+			   FPROBE_HEADER_MSB_PATTERN))
+#endif /* CONFIG_64BIT */
+
+#endif /* __ASM_GENERIC_FPROBE_H__ */
diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h
index f398695..702099f 100644
--- a/include/linux/fprobe.h
+++ b/include/linux/fprobe.h
@@ -5,47 +5,68 @@
 
 #include <linux/compiler.h>
 #include <linux/ftrace.h>
-#include <linux/rethook.h>
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
+#include <linux/slab.h>
 
 struct fprobe;
-
 typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip,
-			       unsigned long ret_ip, struct pt_regs *regs,
+			       unsigned long ret_ip, struct ftrace_regs *regs,
 			       void *entry_data);
 
 typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip,
-			       unsigned long ret_ip, struct pt_regs *regs,
+			       unsigned long ret_ip, struct ftrace_regs *regs,
 			       void *entry_data);
 
 /**
+ * struct fprobe_hlist_node - address based hash list node for fprobe.
+ *
+ * @hlist: The hlist node for address search hash table.
+ * @addr: One of the probing address of @fp.
+ * @fp: The fprobe which owns this.
+ */
+struct fprobe_hlist_node {
+	struct hlist_node	hlist;
+	unsigned long		addr;
+	struct fprobe		*fp;
+};
+
+/**
+ * struct fprobe_hlist - hash list nodes for fprobe.
+ *
+ * @hlist: The hlist node for existence checking hash table.
+ * @rcu: rcu_head for RCU deferred release.
+ * @fp: The fprobe which owns this fprobe_hlist.
+ * @size: The size of @array.
+ * @array: The fprobe_hlist_node for each address to probe.
+ */
+struct fprobe_hlist {
+	struct hlist_node		hlist;
+	struct rcu_head			rcu;
+	struct fprobe			*fp;
+	int				size;
+	struct fprobe_hlist_node	array[] __counted_by(size);
+};
+
+/**
  * struct fprobe - ftrace based probe.
- * @ops: The ftrace_ops.
+ *
  * @nmissed: The counter for missing events.
  * @flags: The status flag.
- * @rethook: The rethook data structure. (internal data)
  * @entry_data_size: The private data storage size.
- * @nr_maxactive: The max number of active functions.
  * @entry_handler: The callback function for function entry.
  * @exit_handler: The callback function for function exit.
+ * @hlist_array: The fprobe_hlist for fprobe search from IP hash table.
  */
 struct fprobe {
-#ifdef CONFIG_FUNCTION_TRACER
-	/*
-	 * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too.
-	 * But user of fprobe may keep embedding the struct fprobe on their own
-	 * code. To avoid build error, this will keep the fprobe data structure
-	 * defined here, but remove ftrace_ops data structure.
-	 */
-	struct ftrace_ops	ops;
-#endif
 	unsigned long		nmissed;
 	unsigned int		flags;
-	struct rethook		*rethook;
 	size_t			entry_data_size;
-	int			nr_maxactive;
 
 	fprobe_entry_cb entry_handler;
 	fprobe_exit_cb  exit_handler;
+
+	struct fprobe_hlist	*hlist_array;
 };
 
 /* This fprobe is soft-disabled. */
@@ -121,4 +142,9 @@ static inline void enable_fprobe(struct fprobe *fp)
 		fp->flags &= ~FPROBE_FL_DISABLED;
 }
 
+/* The entry data size is 4 bits (=16) * sizeof(long) in maximum */
+#define FPROBE_DATA_SIZE_BITS		4
+#define MAX_FPROBE_DATA_SIZE_WORD	((1L << FPROBE_DATA_SIZE_BITS) - 1)
+#define MAX_FPROBE_DATA_SIZE		(MAX_FPROBE_DATA_SIZE_WORD * sizeof(long))
+
 #endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index aa9ddd1..07092df 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -43,9 +43,8 @@ struct dyn_ftrace;
 
 char *arch_ftrace_match_adjust(char *str, const char *search);
 
-#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
-struct fgraph_ret_regs;
-unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs);
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS
+unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs);
 #else
 unsigned long ftrace_return_to_handler(unsigned long frame_pointer);
 #endif
@@ -134,6 +133,13 @@ extern int ftrace_enabled;
  * Also, architecture dependent fields can be used for internal process.
  * (e.g. orig_ax on x86_64)
  *
+ * Basically, ftrace_regs stores the registers related to the context.
+ * On function entry, registers for function parameters and hooking the
+ * function call are stored, and on function exit, registers for function
+ * return value and frame pointers are stored.
+ *
+ * And also, it dpends on the context that which registers are restored
+ * from the ftrace_regs.
  * On the function entry, those registers will be restored except for
  * the stack pointer, so that user can change the function parameters
  * and instruction pointer (e.g. live patching.)
@@ -170,6 +176,12 @@ static inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs)
 #define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0)
 #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 
+#ifdef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS
+
+static_assert(sizeof(struct pt_regs) == ftrace_regs_size());
+
+#endif /* CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */
+
 static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
 {
 	if (!fregs)
@@ -178,6 +190,54 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs
 	return arch_ftrace_get_regs(fregs);
 }
 
+#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) || \
+	defined(CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS)
+
+static __always_inline struct pt_regs *
+ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	/*
+	 * If CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS=y, ftrace_regs memory
+	 * layout is including pt_regs. So always returns that address.
+	 * Since arch_ftrace_get_regs() will check some members and may return
+	 * NULL, we can not use it.
+	 */
+	return &arch_ftrace_regs(fregs)->regs;
+}
+
+#endif /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS || CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */
+
+#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+
+/*
+ * Please define arch dependent pt_regs which compatible to the
+ * perf_arch_fetch_caller_regs() but based on ftrace_regs.
+ * This requires
+ *   - user_mode(_regs) returns false (always kernel mode).
+ *   - able to use the _regs for stack trace.
+ */
+#ifndef arch_ftrace_fill_perf_regs
+/* As same as perf_arch_fetch_caller_regs(), do nothing by default */
+#define arch_ftrace_fill_perf_regs(fregs, _regs) do {} while (0)
+#endif
+
+static __always_inline struct pt_regs *
+ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	arch_ftrace_fill_perf_regs(fregs, regs);
+	return regs;
+}
+
+#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
+
+static __always_inline struct pt_regs *
+ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	return &arch_ftrace_regs(fregs)->regs;
+}
+
+#endif
+
 /*
  * When true, the ftrace_regs_{get,set}_*() functions may be used on fregs.
  * Note: this can be true even when ftrace_get_regs() cannot provide a pt_regs.
@@ -190,6 +250,23 @@ static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs)
 	return ftrace_get_regs(fregs) != NULL;
 }
 
+#ifdef CONFIG_HAVE_REGS_AND_STACK_ACCESS_API
+static __always_inline unsigned long
+ftrace_regs_get_kernel_stack_nth(struct ftrace_regs *fregs, unsigned int nth)
+{
+	unsigned long *stackp;
+
+	stackp = (unsigned long *)ftrace_regs_get_stack_pointer(fregs);
+	if (((unsigned long)(stackp + nth) & ~(THREAD_SIZE - 1)) ==
+	    ((unsigned long)stackp & ~(THREAD_SIZE - 1)))
+		return *(stackp + nth);
+
+	return 0;
+}
+#else /* !CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */
+#define ftrace_regs_get_kernel_stack_nth(fregs, nth)	(0L)
+#endif /* CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */
+
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
 			      struct ftrace_ops *op, struct ftrace_regs *fregs);
 
@@ -545,6 +622,19 @@ enum {
 	FTRACE_MAY_SLEEP		= (1 << 5),
 };
 
+/* Arches can override ftrace_get_symaddr() to convert fentry_ip to symaddr. */
+#ifndef ftrace_get_symaddr
+/**
+ * ftrace_get_symaddr - return the symbol address from fentry_ip
+ * @fentry_ip: the address of ftrace location
+ *
+ * Get the symbol address from @fentry_ip (fast path). If there is no fast
+ * search path, this returns 0.
+ * User may need to use kallsyms API to find the symbol address.
+ */
+#define ftrace_get_symaddr(fentry_ip) (0)
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 void ftrace_arch_code_modify_prepare(void);
@@ -1069,12 +1159,15 @@ struct fgraph_ops;
 
 /* Type of the callback handlers for tracing function graph*/
 typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *,
-				       struct fgraph_ops *); /* return */
+				       struct fgraph_ops *,
+				       struct ftrace_regs *); /* return */
 typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *,
-				      struct fgraph_ops *); /* entry */
+				      struct fgraph_ops *,
+				      struct ftrace_regs *); /* entry */
 
 extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
-				   struct fgraph_ops *gops);
+				   struct fgraph_ops *gops,
+				   struct ftrace_regs *fregs);
 bool ftrace_pids_enabled(struct ftrace_ops *ops);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -1114,8 +1207,15 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 extern int
-function_graph_enter(unsigned long ret, unsigned long func,
-		     unsigned long frame_pointer, unsigned long *retp);
+function_graph_enter_regs(unsigned long ret, unsigned long func,
+			  unsigned long frame_pointer, unsigned long *retp,
+			  struct ftrace_regs *fregs);
+
+static inline int function_graph_enter(unsigned long ret, unsigned long func,
+				       unsigned long fp, unsigned long *retp)
+{
+	return function_graph_enter_regs(ret, func, fp, retp, NULL);
+}
 
 struct ftrace_ret_stack *
 ftrace_graph_get_ret_stack(struct task_struct *task, int skip);
diff --git a/include/linux/ftrace_regs.h b/include/linux/ftrace_regs.h
index be1ed0c..bbc1873 100644
--- a/include/linux/ftrace_regs.h
+++ b/include/linux/ftrace_regs.h
@@ -30,6 +30,8 @@ struct ftrace_regs;
 	override_function_with_return(&arch_ftrace_regs(fregs)->regs)
 #define ftrace_regs_query_register_offset(name) \
 	regs_query_register_offset(name)
+#define ftrace_regs_get_frame_pointer(fregs) \
+	frame_pointer(&arch_ftrace_regs(fregs)->regs)
 
 #endif /* HAVE_ARCH_FTRACE_REGS */
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 74c2b1d..d570b8b 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -31,9 +31,14 @@
 	help
 	  See Documentation/trace/ftrace-design.rst
 
-config HAVE_FUNCTION_GRAPH_RETVAL
+config HAVE_FUNCTION_GRAPH_FREGS
 	bool
 
+config HAVE_FTRACE_GRAPH_FUNC
+	bool
+	help
+	  True if ftrace_graph_func() is defined.
+
 config HAVE_DYNAMIC_FTRACE
 	bool
 	help
@@ -57,6 +62,12 @@
 	 This allows for use of ftrace_regs_get_argument() and
 	 ftrace_regs_get_stack_pointer().
 
+config HAVE_FTRACE_REGS_HAVING_PT_REGS
+	bool
+	help
+	 If this is set, ftrace_regs has pt_regs, thus it can convert to
+	 pt_regs without allocating memory.
+
 config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
 	bool
 	help
@@ -232,7 +243,7 @@
 
 config FUNCTION_GRAPH_RETVAL
 	bool "Kernel Function Graph Return Value"
-	depends on HAVE_FUNCTION_GRAPH_RETVAL
+	depends on HAVE_FUNCTION_GRAPH_FREGS
 	depends on FUNCTION_GRAPH_TRACER
 	default n
 	help
@@ -296,10 +307,9 @@
 
 config FPROBE
 	bool "Kernel Function Probe (fprobe)"
-	depends on FUNCTION_TRACER
-	depends on DYNAMIC_FTRACE_WITH_REGS
-	depends on HAVE_RETHOOK
-	select RETHOOK
+	depends on HAVE_FUNCTION_GRAPH_FREGS && HAVE_FTRACE_GRAPH_FUNC
+	depends on DYNAMIC_FTRACE_WITH_ARGS
+	select FUNCTION_GRAPH_TRACER
 	default n
 	help
 	  This option enables kernel function probe (fprobe) based on ftrace.
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9f2f657..c462aca 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2585,6 +2585,20 @@ struct user_syms {
 	char *buf;
 };
 
+#ifndef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS
+static DEFINE_PER_CPU(struct pt_regs, bpf_kprobe_multi_pt_regs);
+#define bpf_kprobe_multi_pt_regs_ptr()	this_cpu_ptr(&bpf_kprobe_multi_pt_regs)
+#else
+#define bpf_kprobe_multi_pt_regs_ptr()	(NULL)
+#endif
+
+static unsigned long ftrace_get_entry_ip(unsigned long fentry_ip)
+{
+	unsigned long ip = ftrace_get_symaddr(fentry_ip);
+
+	return ip ? : fentry_ip;
+}
+
 static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt)
 {
 	unsigned long __user usymbol;
@@ -2779,7 +2793,7 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
 
 static int
 kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
-			   unsigned long entry_ip, struct pt_regs *regs,
+			   unsigned long entry_ip, struct ftrace_regs *fregs,
 			   bool is_return, void *data)
 {
 	struct bpf_kprobe_multi_run_ctx run_ctx = {
@@ -2791,6 +2805,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
 		.entry_ip = entry_ip,
 	};
 	struct bpf_run_ctx *old_run_ctx;
+	struct pt_regs *regs;
 	int err;
 
 	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
@@ -2801,6 +2816,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
 
 	migrate_disable();
 	rcu_read_lock();
+	regs = ftrace_partial_regs(fregs, bpf_kprobe_multi_pt_regs_ptr());
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx);
 	err = bpf_prog_run(link->link.prog, regs);
 	bpf_reset_run_ctx(old_run_ctx);
@@ -2814,26 +2830,28 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
 
 static int
 kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip,
-			  unsigned long ret_ip, struct pt_regs *regs,
+			  unsigned long ret_ip, struct ftrace_regs *fregs,
 			  void *data)
 {
 	struct bpf_kprobe_multi_link *link;
 	int err;
 
 	link = container_of(fp, struct bpf_kprobe_multi_link, fp);
-	err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data);
+	err = kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip),
+					 fregs, false, data);
 	return is_kprobe_session(link->link.prog) ? err : 0;
 }
 
 static void
 kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip,
-			       unsigned long ret_ip, struct pt_regs *regs,
+			       unsigned long ret_ip, struct ftrace_regs *fregs,
 			       void *data)
 {
 	struct bpf_kprobe_multi_link *link;
 
 	link = container_of(fp, struct bpf_kprobe_multi_link, fp);
-	kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data);
+	kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip),
+				   fregs, true, data);
 }
 
 static int symbols_cmp_r(const void *a, const void *b, const void *priv)
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 30e3ddc..9e6b5a7 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -292,13 +292,15 @@ static inline unsigned long make_data_type_val(int idx, int size, int offset)
 }
 
 /* ftrace_graph_entry set to this to tell some archs to run function graph */
-static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops)
+static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops,
+		     struct ftrace_regs *fregs)
 {
 	return 0;
 }
 
 /* ftrace_graph_return set to this to tell some archs to run function graph */
-static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops)
+static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops,
+		       struct ftrace_regs *fregs)
 {
 }
 
@@ -520,13 +522,15 @@ int __weak ftrace_disable_ftrace_graph_caller(void)
 #endif
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
-			    struct fgraph_ops *gops)
+			    struct fgraph_ops *gops,
+			    struct ftrace_regs *fregs)
 {
 	return 0;
 }
 
 static void ftrace_graph_ret_stub(struct ftrace_graph_ret *trace,
-				  struct fgraph_ops *gops)
+				  struct fgraph_ops *gops,
+				  struct ftrace_regs *fregs)
 {
 }
 
@@ -644,14 +648,20 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 #endif
 
 /* If the caller does not use ftrace, call this function. */
-int function_graph_enter(unsigned long ret, unsigned long func,
-			 unsigned long frame_pointer, unsigned long *retp)
+int function_graph_enter_regs(unsigned long ret, unsigned long func,
+			      unsigned long frame_pointer, unsigned long *retp,
+			      struct ftrace_regs *fregs)
 {
 	struct ftrace_graph_ent trace;
 	unsigned long bitmap = 0;
 	int offset;
+	int bit;
 	int i;
 
+	bit = ftrace_test_recursion_trylock(func, ret);
+	if (bit < 0)
+		return -EBUSY;
+
 	trace.func = func;
 	trace.depth = ++current->curr_ret_depth;
 
@@ -663,7 +673,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	if (static_branch_likely(&fgraph_do_direct)) {
 		int save_curr_ret_stack = current->curr_ret_stack;
 
-		if (static_call(fgraph_func)(&trace, fgraph_direct_gops))
+		if (static_call(fgraph_func)(&trace, fgraph_direct_gops, fregs))
 			bitmap |= BIT(fgraph_direct_gops->idx);
 		else
 			/* Clear out any saved storage */
@@ -681,7 +691,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 
 			save_curr_ret_stack = current->curr_ret_stack;
 			if (ftrace_ops_test(&gops->ops, func, NULL) &&
-			    gops->entryfunc(&trace, gops))
+			    gops->entryfunc(&trace, gops, fregs))
 				bitmap |= BIT(i);
 			else
 				/* Clear out any saved storage */
@@ -697,12 +707,13 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	 * flag, set that bit always.
 	 */
 	set_bitmap(current, offset, bitmap | BIT(0));
-
+	ftrace_test_recursion_unlock(bit);
 	return 0;
  out_ret:
 	current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1;
  out:
 	current->curr_ret_depth--;
+	ftrace_test_recursion_unlock(bit);
 	return -EBUSY;
 }
 
@@ -792,15 +803,12 @@ static struct notifier_block ftrace_suspend_notifier = {
 	.notifier_call = ftrace_suspend_notifier_call,
 };
 
-/* fgraph_ret_regs is not defined without CONFIG_FUNCTION_GRAPH_RETVAL */
-struct fgraph_ret_regs;
-
 /*
  * Send the trace to the ring-buffer.
  * @return the original return address.
  */
-static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs,
-						unsigned long frame_pointer)
+static inline unsigned long
+__ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointer)
 {
 	struct ftrace_ret_stack *ret_stack;
 	struct ftrace_graph_ret trace;
@@ -819,8 +827,11 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 	}
 
 	trace.rettime = trace_clock_local();
+	if (fregs)
+		ftrace_regs_set_instruction_pointer(fregs, ret);
+
 #ifdef CONFIG_FUNCTION_GRAPH_RETVAL
-	trace.retval = fgraph_ret_regs_return_value(ret_regs);
+	trace.retval = ftrace_regs_get_return_value(fregs);
 #endif
 
 	bitmap = get_bitmap_bits(current, offset);
@@ -828,7 +839,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 #ifdef CONFIG_HAVE_STATIC_CALL
 	if (static_branch_likely(&fgraph_do_direct)) {
 		if (test_bit(fgraph_direct_gops->idx, &bitmap))
-			static_call(fgraph_retfunc)(&trace, fgraph_direct_gops);
+			static_call(fgraph_retfunc)(&trace, fgraph_direct_gops, fregs);
 	} else
 #endif
 	{
@@ -838,7 +849,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 			if (gops == &fgraph_stub)
 				continue;
 
-			gops->retfunc(&trace, gops);
+			gops->retfunc(&trace, gops, fregs);
 		}
 	}
 
@@ -855,14 +866,14 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 }
 
 /*
- * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can
- * leave only ftrace_return_to_handler(ret_regs).
+ * After all architecures have selected HAVE_FUNCTION_GRAPH_FREGS, we can
+ * leave only ftrace_return_to_handler(fregs).
  */
-#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
-unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs)
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS
+unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs)
 {
-	return __ftrace_return_to_handler(ret_regs,
-				fgraph_ret_regs_frame_pointer(ret_regs));
+	return __ftrace_return_to_handler(fregs,
+				ftrace_regs_get_frame_pointer(fregs));
 }
 #else
 unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
@@ -1010,7 +1021,8 @@ void ftrace_graph_sleep_time_control(bool enable)
  * Simply points to ftrace_stub, but with the proper protocol.
  * Defined by the linker script in linux/vmlinux.lds.h
  */
-void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops);
+void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops,
+		       struct ftrace_regs *fregs);
 
 /* The callbacks that hook a function */
 trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph;
@@ -1174,7 +1186,8 @@ void ftrace_graph_exit_task(struct task_struct *t)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 static int fgraph_pid_func(struct ftrace_graph_ent *trace,
-			   struct fgraph_ops *gops)
+			   struct fgraph_ops *gops,
+			   struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = gops->ops.private;
 	int pid;
@@ -1188,7 +1201,7 @@ static int fgraph_pid_func(struct ftrace_graph_ent *trace,
 			return 0;
 	}
 
-	return gops->saved_func(trace, gops);
+	return gops->saved_func(trace, gops, fregs);
 }
 
 void fgraph_update_pid_func(void)
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 9ff0182..2560b31 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -8,98 +8,224 @@
 #include <linux/fprobe.h>
 #include <linux/kallsyms.h>
 #include <linux/kprobes.h>
-#include <linux/rethook.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/sort.h>
 
+#include <asm/fprobe.h>
+
 #include "trace.h"
 
-struct fprobe_rethook_node {
-	struct rethook_node node;
-	unsigned long entry_ip;
-	unsigned long entry_parent_ip;
-	char data[];
-};
+#define FPROBE_IP_HASH_BITS 8
+#define FPROBE_IP_TABLE_SIZE (1 << FPROBE_IP_HASH_BITS)
 
-static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip,
-			struct ftrace_ops *ops, struct ftrace_regs *fregs)
+#define FPROBE_HASH_BITS 6
+#define FPROBE_TABLE_SIZE (1 << FPROBE_HASH_BITS)
+
+#define SIZE_IN_LONG(x) ((x + sizeof(long) - 1) >> (sizeof(long) == 8 ? 3 : 2))
+
+/*
+ * fprobe_table: hold 'fprobe_hlist::hlist' for checking the fprobe still
+ *   exists. The key is the address of fprobe instance.
+ * fprobe_ip_table: hold 'fprobe_hlist::array[*]' for searching the fprobe
+ *   instance related to the funciton address. The key is the ftrace IP
+ *   address.
+ *
+ * When unregistering the fprobe, fprobe_hlist::fp and fprobe_hlist::array[*].fp
+ * are set NULL and delete those from both hash tables (by hlist_del_rcu).
+ * After an RCU grace period, the fprobe_hlist itself will be released.
+ *
+ * fprobe_table and fprobe_ip_table can be accessed from either
+ *  - Normal hlist traversal and RCU add/del under 'fprobe_mutex' is held.
+ *  - RCU hlist traversal under disabling preempt
+ */
+static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE];
+static struct hlist_head fprobe_ip_table[FPROBE_IP_TABLE_SIZE];
+static DEFINE_MUTEX(fprobe_mutex);
+
+/*
+ * Find first fprobe in the hlist. It will be iterated twice in the entry
+ * probe, once for correcting the total required size, the second time is
+ * calling back the user handlers.
+ * Thus the hlist in the fprobe_table must be sorted and new probe needs to
+ * be added *before* the first fprobe.
+ */
+static struct fprobe_hlist_node *find_first_fprobe_node(unsigned long ip)
 {
-	struct fprobe_rethook_node *fpr;
-	struct rethook_node *rh = NULL;
-	struct fprobe *fp;
-	void *entry_data = NULL;
-	int ret = 0;
+	struct fprobe_hlist_node *node;
+	struct hlist_head *head;
 
-	fp = container_of(ops, struct fprobe, ops);
-
-	if (fp->exit_handler) {
-		rh = rethook_try_get(fp->rethook);
-		if (!rh) {
-			fp->nmissed++;
-			return;
-		}
-		fpr = container_of(rh, struct fprobe_rethook_node, node);
-		fpr->entry_ip = ip;
-		fpr->entry_parent_ip = parent_ip;
-		if (fp->entry_data_size)
-			entry_data = fpr->data;
+	head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)];
+	hlist_for_each_entry_rcu(node, head, hlist,
+				 lockdep_is_held(&fprobe_mutex)) {
+		if (node->addr == ip)
+			return node;
 	}
+	return NULL;
+}
+NOKPROBE_SYMBOL(find_first_fprobe_node);
 
-	if (fp->entry_handler)
-		ret = fp->entry_handler(fp, ip, parent_ip, ftrace_get_regs(fregs), entry_data);
+/* Node insertion and deletion requires the fprobe_mutex */
+static void insert_fprobe_node(struct fprobe_hlist_node *node)
+{
+	unsigned long ip = node->addr;
+	struct fprobe_hlist_node *next;
+	struct hlist_head *head;
 
-	/* If entry_handler returns !0, nmissed is not counted. */
-	if (rh) {
-		if (ret)
-			rethook_recycle(rh);
-		else
-			rethook_hook(rh, ftrace_get_regs(fregs), true);
+	lockdep_assert_held(&fprobe_mutex);
+
+	next = find_first_fprobe_node(ip);
+	if (next) {
+		hlist_add_before_rcu(&node->hlist, &next->hlist);
+		return;
 	}
+	head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)];
+	hlist_add_head_rcu(&node->hlist, head);
 }
 
-static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
-		struct ftrace_ops *ops, struct ftrace_regs *fregs)
+/* Return true if there are synonims */
+static bool delete_fprobe_node(struct fprobe_hlist_node *node)
 {
-	struct fprobe *fp;
-	int bit;
+	lockdep_assert_held(&fprobe_mutex);
 
-	fp = container_of(ops, struct fprobe, ops);
-	if (fprobe_disabled(fp))
-		return;
-
-	/* recursion detection has to go before any traceable function and
-	 * all functions before this point should be marked as notrace
-	 */
-	bit = ftrace_test_recursion_trylock(ip, parent_ip);
-	if (bit < 0) {
-		fp->nmissed++;
-		return;
-	}
-	__fprobe_handler(ip, parent_ip, ops, fregs);
-	ftrace_test_recursion_unlock(bit);
-
+	WRITE_ONCE(node->fp, NULL);
+	hlist_del_rcu(&node->hlist);
+	return !!find_first_fprobe_node(node->addr);
 }
-NOKPROBE_SYMBOL(fprobe_handler);
 
-static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
-				  struct ftrace_ops *ops, struct ftrace_regs *fregs)
+/* Check existence of the fprobe */
+static bool is_fprobe_still_exist(struct fprobe *fp)
 {
-	struct fprobe *fp;
-	int bit;
+	struct hlist_head *head;
+	struct fprobe_hlist *fph;
 
-	fp = container_of(ops, struct fprobe, ops);
-	if (fprobe_disabled(fp))
-		return;
-
-	/* recursion detection has to go before any traceable function and
-	 * all functions called before this point should be marked as notrace
-	 */
-	bit = ftrace_test_recursion_trylock(ip, parent_ip);
-	if (bit < 0) {
-		fp->nmissed++;
-		return;
+	head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)];
+	hlist_for_each_entry_rcu(fph, head, hlist,
+				 lockdep_is_held(&fprobe_mutex)) {
+		if (fph->fp == fp)
+			return true;
 	}
+	return false;
+}
+NOKPROBE_SYMBOL(is_fprobe_still_exist);
 
+static int add_fprobe_hash(struct fprobe *fp)
+{
+	struct fprobe_hlist *fph = fp->hlist_array;
+	struct hlist_head *head;
+
+	lockdep_assert_held(&fprobe_mutex);
+
+	if (WARN_ON_ONCE(!fph))
+		return -EINVAL;
+
+	if (is_fprobe_still_exist(fp))
+		return -EEXIST;
+
+	head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)];
+	hlist_add_head_rcu(&fp->hlist_array->hlist, head);
+	return 0;
+}
+
+static int del_fprobe_hash(struct fprobe *fp)
+{
+	struct fprobe_hlist *fph = fp->hlist_array;
+
+	lockdep_assert_held(&fprobe_mutex);
+
+	if (WARN_ON_ONCE(!fph))
+		return -EINVAL;
+
+	if (!is_fprobe_still_exist(fp))
+		return -ENOENT;
+
+	fph->fp = NULL;
+	hlist_del_rcu(&fph->hlist);
+	return 0;
+}
+
+#ifdef ARCH_DEFINE_ENCODE_FPROBE_HEADER
+
+/* The arch should encode fprobe_header info into one unsigned long */
+#define FPROBE_HEADER_SIZE_IN_LONG	1
+
+static inline bool write_fprobe_header(unsigned long *stack,
+					struct fprobe *fp, unsigned int size_words)
+{
+	if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD ||
+			 !arch_fprobe_header_encodable(fp)))
+		return false;
+
+	*stack = arch_encode_fprobe_header(fp, size_words);
+	return true;
+}
+
+static inline void read_fprobe_header(unsigned long *stack,
+					struct fprobe **fp, unsigned int *size_words)
+{
+	*fp = arch_decode_fprobe_header_fp(*stack);
+	*size_words = arch_decode_fprobe_header_size(*stack);
+}
+
+#else
+
+/* Generic fprobe_header */
+struct __fprobe_header {
+	struct fprobe *fp;
+	unsigned long size_words;
+} __packed;
+
+#define FPROBE_HEADER_SIZE_IN_LONG	SIZE_IN_LONG(sizeof(struct __fprobe_header))
+
+static inline bool write_fprobe_header(unsigned long *stack,
+					struct fprobe *fp, unsigned int size_words)
+{
+	struct __fprobe_header *fph = (struct __fprobe_header *)stack;
+
+	if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD))
+		return false;
+
+	fph->fp = fp;
+	fph->size_words = size_words;
+	return true;
+}
+
+static inline void read_fprobe_header(unsigned long *stack,
+					struct fprobe **fp, unsigned int *size_words)
+{
+	struct __fprobe_header *fph = (struct __fprobe_header *)stack;
+
+	*fp = fph->fp;
+	*size_words = fph->size_words;
+}
+
+#endif
+
+/*
+ * fprobe shadow stack management:
+ * Since fprobe shares a single fgraph_ops, it needs to share the stack entry
+ * among the probes on the same function exit. Note that a new probe can be
+ * registered before a target function is returning, we can not use the hash
+ * table to find the corresponding probes. Thus the probe address is stored on
+ * the shadow stack with its entry data size.
+ *
+ */
+static inline int __fprobe_handler(unsigned long ip, unsigned long parent_ip,
+				   struct fprobe *fp, struct ftrace_regs *fregs,
+				   void *data)
+{
+	if (!fp->entry_handler)
+		return 0;
+
+	return fp->entry_handler(fp, ip, parent_ip, fregs, data);
+}
+
+static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
+					  struct fprobe *fp, struct ftrace_regs *fregs,
+					  void *data)
+{
+	int ret;
 	/*
 	 * This user handler is shared with other kprobes and is not expected to be
 	 * called recursively. So if any other kprobe handler is running, this will
@@ -108,44 +234,183 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
 	 */
 	if (unlikely(kprobe_running())) {
 		fp->nmissed++;
-		goto recursion_unlock;
+		return 0;
 	}
 
 	kprobe_busy_begin();
-	__fprobe_handler(ip, parent_ip, ops, fregs);
+	ret = __fprobe_handler(ip, parent_ip, fp, fregs, data);
 	kprobe_busy_end();
-
-recursion_unlock:
-	ftrace_test_recursion_unlock(bit);
+	return ret;
 }
 
-static void fprobe_exit_handler(struct rethook_node *rh, void *data,
-				unsigned long ret_ip, struct pt_regs *regs)
+static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops,
+			struct ftrace_regs *fregs)
 {
-	struct fprobe *fp = (struct fprobe *)data;
-	struct fprobe_rethook_node *fpr;
-	int bit;
+	struct fprobe_hlist_node *node, *first;
+	unsigned long *fgraph_data = NULL;
+	unsigned long func = trace->func;
+	unsigned long ret_ip;
+	int reserved_words;
+	struct fprobe *fp;
+	int used, ret;
 
-	if (!fp || fprobe_disabled(fp))
-		return;
+	if (WARN_ON_ONCE(!fregs))
+		return 0;
 
-	fpr = container_of(rh, struct fprobe_rethook_node, node);
+	first = node = find_first_fprobe_node(func);
+	if (unlikely(!first))
+		return 0;
+
+	reserved_words = 0;
+	hlist_for_each_entry_from_rcu(node, hlist) {
+		if (node->addr != func)
+			break;
+		fp = READ_ONCE(node->fp);
+		if (!fp || !fp->exit_handler)
+			continue;
+		/*
+		 * Since fprobe can be enabled until the next loop, we ignore the
+		 * fprobe's disabled flag in this loop.
+		 */
+		reserved_words +=
+			FPROBE_HEADER_SIZE_IN_LONG + SIZE_IN_LONG(fp->entry_data_size);
+	}
+	node = first;
+	if (reserved_words) {
+		fgraph_data = fgraph_reserve_data(gops->idx, reserved_words * sizeof(long));
+		if (unlikely(!fgraph_data)) {
+			hlist_for_each_entry_from_rcu(node, hlist) {
+				if (node->addr != func)
+					break;
+				fp = READ_ONCE(node->fp);
+				if (fp && !fprobe_disabled(fp))
+					fp->nmissed++;
+			}
+			return 0;
+		}
+	}
 
 	/*
-	 * we need to assure no calls to traceable functions in-between the
-	 * end of fprobe_handler and the beginning of fprobe_exit_handler.
+	 * TODO: recursion detection has been done in the fgraph. Thus we need
+	 * to add a callback to increment missed counter.
 	 */
-	bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip);
-	if (bit < 0) {
-		fp->nmissed++;
+	ret_ip = ftrace_regs_get_return_address(fregs);
+	used = 0;
+	hlist_for_each_entry_from_rcu(node, hlist) {
+		int data_size;
+		void *data;
+
+		if (node->addr != func)
+			break;
+		fp = READ_ONCE(node->fp);
+		if (!fp || fprobe_disabled(fp))
+			continue;
+
+		data_size = fp->entry_data_size;
+		if (data_size && fp->exit_handler)
+			data = fgraph_data + used + FPROBE_HEADER_SIZE_IN_LONG;
+		else
+			data = NULL;
+
+		if (fprobe_shared_with_kprobes(fp))
+			ret = __fprobe_kprobe_handler(func, ret_ip, fp, fregs, data);
+		else
+			ret = __fprobe_handler(func, ret_ip, fp, fregs, data);
+
+		/* If entry_handler returns !0, nmissed is not counted but skips exit_handler. */
+		if (!ret && fp->exit_handler) {
+			int size_words = SIZE_IN_LONG(data_size);
+
+			if (write_fprobe_header(&fgraph_data[used], fp, size_words))
+				used += FPROBE_HEADER_SIZE_IN_LONG + size_words;
+		}
+	}
+	if (used < reserved_words)
+		memset(fgraph_data + used, 0, reserved_words - used);
+
+	/* If any exit_handler is set, data must be used. */
+	return used != 0;
+}
+NOKPROBE_SYMBOL(fprobe_entry);
+
+static void fprobe_return(struct ftrace_graph_ret *trace,
+			  struct fgraph_ops *gops,
+			  struct ftrace_regs *fregs)
+{
+	unsigned long *fgraph_data = NULL;
+	unsigned long ret_ip;
+	struct fprobe *fp;
+	int size, curr;
+	int size_words;
+
+	fgraph_data = (unsigned long *)fgraph_retrieve_data(gops->idx, &size);
+	if (WARN_ON_ONCE(!fgraph_data))
+		return;
+	size_words = SIZE_IN_LONG(size);
+	ret_ip = ftrace_regs_get_instruction_pointer(fregs);
+
+	preempt_disable();
+
+	curr = 0;
+	while (size_words > curr) {
+		read_fprobe_header(&fgraph_data[curr], &fp, &size);
+		if (!fp)
+			break;
+		curr += FPROBE_HEADER_SIZE_IN_LONG;
+		if (is_fprobe_still_exist(fp) && !fprobe_disabled(fp)) {
+			if (WARN_ON_ONCE(curr + size > size_words))
+				break;
+			fp->exit_handler(fp, trace->func, ret_ip, fregs,
+					 size ? fgraph_data + curr : NULL);
+		}
+		curr += size;
+	}
+	preempt_enable();
+}
+NOKPROBE_SYMBOL(fprobe_return);
+
+static struct fgraph_ops fprobe_graph_ops = {
+	.entryfunc	= fprobe_entry,
+	.retfunc	= fprobe_return,
+};
+static int fprobe_graph_active;
+
+/* Add @addrs to the ftrace filter and register fgraph if needed. */
+static int fprobe_graph_add_ips(unsigned long *addrs, int num)
+{
+	int ret;
+
+	lockdep_assert_held(&fprobe_mutex);
+
+	ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0);
+	if (ret)
+		return ret;
+
+	if (!fprobe_graph_active) {
+		ret = register_ftrace_graph(&fprobe_graph_ops);
+		if (WARN_ON_ONCE(ret)) {
+			ftrace_free_filter(&fprobe_graph_ops.ops);
+			return ret;
+		}
+	}
+	fprobe_graph_active++;
+	return 0;
+}
+
+/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */
+static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
+{
+	lockdep_assert_held(&fprobe_mutex);
+
+	fprobe_graph_active--;
+	if (!fprobe_graph_active) {
+		/* Q: should we unregister it ? */
+		unregister_ftrace_graph(&fprobe_graph_ops);
 		return;
 	}
 
-	fp->exit_handler(fp, fpr->entry_ip, ret_ip, regs,
-			 fp->entry_data_size ? (void *)fpr->data : NULL);
-	ftrace_test_recursion_unlock(bit);
+	ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
 }
-NOKPROBE_SYMBOL(fprobe_exit_handler);
 
 static int symbols_cmp(const void *a, const void *b)
 {
@@ -175,53 +440,97 @@ static unsigned long *get_ftrace_locations(const char **syms, int num)
 	return ERR_PTR(-ENOENT);
 }
 
-static void fprobe_init(struct fprobe *fp)
+struct filter_match_data {
+	const char *filter;
+	const char *notfilter;
+	size_t index;
+	size_t size;
+	unsigned long *addrs;
+};
+
+static int filter_match_callback(void *data, const char *name, unsigned long addr)
 {
-	fp->nmissed = 0;
-	if (fprobe_shared_with_kprobes(fp))
-		fp->ops.func = fprobe_kprobe_handler;
-	else
-		fp->ops.func = fprobe_handler;
-	fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS;
+	struct filter_match_data *match = data;
+
+	if (!glob_match(match->filter, name) ||
+	    (match->notfilter && glob_match(match->notfilter, name)))
+		return 0;
+
+	if (!ftrace_location(addr))
+		return 0;
+
+	if (match->addrs)
+		match->addrs[match->index] = addr;
+
+	match->index++;
+	return match->index == match->size;
 }
 
-static int fprobe_init_rethook(struct fprobe *fp, int num)
+/*
+ * Make IP list from the filter/no-filter glob patterns.
+ * Return the number of matched symbols, or -ENOENT.
+ */
+static int ip_list_from_filter(const char *filter, const char *notfilter,
+			       unsigned long *addrs, size_t size)
 {
-	int size;
+	struct filter_match_data match = { .filter = filter, .notfilter = notfilter,
+		.index = 0, .size = size, .addrs = addrs};
+	int ret;
 
-	if (!fp->exit_handler) {
-		fp->rethook = NULL;
-		return 0;
-	}
+	ret = kallsyms_on_each_symbol(filter_match_callback, &match);
+	if (ret < 0)
+		return ret;
+	ret = module_kallsyms_on_each_symbol(NULL, filter_match_callback, &match);
+	if (ret < 0)
+		return ret;
 
-	/* Initialize rethook if needed */
-	if (fp->nr_maxactive)
-		num = fp->nr_maxactive;
-	else
-		num *= num_possible_cpus() * 2;
-	if (num <= 0)
-		return -EINVAL;
-
-	size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size;
-
-	/* Initialize rethook */
-	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num);
-	if (IS_ERR(fp->rethook))
-		return PTR_ERR(fp->rethook);
-
-	return 0;
+	return match.index ?: -ENOENT;
 }
 
 static void fprobe_fail_cleanup(struct fprobe *fp)
 {
-	if (!IS_ERR_OR_NULL(fp->rethook)) {
-		/* Don't need to cleanup rethook->handler because this is not used. */
-		rethook_free(fp->rethook);
-		fp->rethook = NULL;
-	}
-	ftrace_free_filter(&fp->ops);
+	kfree(fp->hlist_array);
+	fp->hlist_array = NULL;
 }
 
+/* Initialize the fprobe data structure. */
+static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num)
+{
+	struct fprobe_hlist *hlist_array;
+	unsigned long addr;
+	int size, i;
+
+	if (!fp || !addrs || num <= 0)
+		return -EINVAL;
+
+	size = ALIGN(fp->entry_data_size, sizeof(long));
+	if (size > MAX_FPROBE_DATA_SIZE)
+		return -E2BIG;
+	fp->entry_data_size = size;
+
+	hlist_array = kzalloc(struct_size(hlist_array, array, num), GFP_KERNEL);
+	if (!hlist_array)
+		return -ENOMEM;
+
+	fp->nmissed = 0;
+
+	hlist_array->size = num;
+	fp->hlist_array = hlist_array;
+	hlist_array->fp = fp;
+	for (i = 0; i < num; i++) {
+		hlist_array->array[i].fp = fp;
+		addr = ftrace_location(addrs[i]);
+		if (!addr) {
+			fprobe_fail_cleanup(fp);
+			return -ENOENT;
+		}
+		hlist_array->array[i].addr = addr;
+	}
+	return 0;
+}
+
+#define FPROBE_IPS_MAX	INT_MAX
+
 /**
  * register_fprobe() - Register fprobe to ftrace by pattern.
  * @fp: A fprobe data structure to be registered.
@@ -235,46 +544,24 @@ static void fprobe_fail_cleanup(struct fprobe *fp)
  */
 int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter)
 {
-	struct ftrace_hash *hash;
-	unsigned char *str;
-	int ret, len;
+	unsigned long *addrs;
+	int ret;
 
 	if (!fp || !filter)
 		return -EINVAL;
 
-	fprobe_init(fp);
-
-	len = strlen(filter);
-	str = kstrdup(filter, GFP_KERNEL);
-	ret = ftrace_set_filter(&fp->ops, str, len, 0);
-	kfree(str);
-	if (ret)
+	ret = ip_list_from_filter(filter, notfilter, NULL, FPROBE_IPS_MAX);
+	if (ret < 0)
 		return ret;
 
-	if (notfilter) {
-		len = strlen(notfilter);
-		str = kstrdup(notfilter, GFP_KERNEL);
-		ret = ftrace_set_notrace(&fp->ops, str, len, 0);
-		kfree(str);
-		if (ret)
-			goto out;
-	}
+	addrs = kcalloc(ret, sizeof(unsigned long), GFP_KERNEL);
+	if (!addrs)
+		return -ENOMEM;
+	ret = ip_list_from_filter(filter, notfilter, addrs, ret);
+	if (ret > 0)
+		ret = register_fprobe_ips(fp, addrs, ret);
 
-	/* TODO:
-	 * correctly calculate the total number of filtered symbols
-	 * from both filter and notfilter.
-	 */
-	hash = rcu_access_pointer(fp->ops.local_hash.filter_hash);
-	if (WARN_ON_ONCE(!hash))
-		goto out;
-
-	ret = fprobe_init_rethook(fp, (int)hash->count);
-	if (!ret)
-		ret = register_ftrace_function(&fp->ops);
-
-out:
-	if (ret)
-		fprobe_fail_cleanup(fp);
+	kfree(addrs);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(register_fprobe);
@@ -282,7 +569,7 @@ EXPORT_SYMBOL_GPL(register_fprobe);
 /**
  * register_fprobe_ips() - Register fprobe to ftrace by address.
  * @fp: A fprobe data structure to be registered.
- * @addrs: An array of target ftrace location addresses.
+ * @addrs: An array of target function address.
  * @num: The number of entries of @addrs.
  *
  * Register @fp to ftrace for enabling the probe on the address given by @addrs.
@@ -294,23 +581,27 @@ EXPORT_SYMBOL_GPL(register_fprobe);
  */
 int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num)
 {
-	int ret;
+	struct fprobe_hlist *hlist_array;
+	int ret, i;
 
-	if (!fp || !addrs || num <= 0)
-		return -EINVAL;
-
-	fprobe_init(fp);
-
-	ret = ftrace_set_filter_ips(&fp->ops, addrs, num, 0, 0);
+	ret = fprobe_init(fp, addrs, num);
 	if (ret)
 		return ret;
 
-	ret = fprobe_init_rethook(fp, num);
-	if (!ret)
-		ret = register_ftrace_function(&fp->ops);
+	mutex_lock(&fprobe_mutex);
+
+	hlist_array = fp->hlist_array;
+	ret = fprobe_graph_add_ips(addrs, num);
+	if (!ret) {
+		add_fprobe_hash(fp);
+		for (i = 0; i < hlist_array->size; i++)
+			insert_fprobe_node(&hlist_array->array[i]);
+	}
+	mutex_unlock(&fprobe_mutex);
 
 	if (ret)
 		fprobe_fail_cleanup(fp);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(register_fprobe_ips);
@@ -348,14 +639,13 @@ EXPORT_SYMBOL_GPL(register_fprobe_syms);
 
 bool fprobe_is_registered(struct fprobe *fp)
 {
-	if (!fp || (fp->ops.saved_func != fprobe_handler &&
-		    fp->ops.saved_func != fprobe_kprobe_handler))
+	if (!fp || !fp->hlist_array)
 		return false;
 	return true;
 }
 
 /**
- * unregister_fprobe() - Unregister fprobe from ftrace
+ * unregister_fprobe() - Unregister fprobe.
  * @fp: A fprobe data structure to be unregistered.
  *
  * Unregister fprobe (and remove ftrace hooks from the function entries).
@@ -364,23 +654,41 @@ bool fprobe_is_registered(struct fprobe *fp)
  */
 int unregister_fprobe(struct fprobe *fp)
 {
-	int ret;
+	struct fprobe_hlist *hlist_array;
+	unsigned long *addrs = NULL;
+	int ret = 0, i, count;
 
-	if (!fprobe_is_registered(fp))
-		return -EINVAL;
+	mutex_lock(&fprobe_mutex);
+	if (!fp || !is_fprobe_still_exist(fp)) {
+		ret = -EINVAL;
+		goto out;
+	}
 
-	if (!IS_ERR_OR_NULL(fp->rethook))
-		rethook_stop(fp->rethook);
+	hlist_array = fp->hlist_array;
+	addrs = kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL);
+	if (!addrs) {
+		ret = -ENOMEM;	/* TODO: Fallback to one-by-one loop */
+		goto out;
+	}
 
-	ret = unregister_ftrace_function(&fp->ops);
-	if (ret < 0)
-		return ret;
+	/* Remove non-synonim ips from table and hash */
+	count = 0;
+	for (i = 0; i < hlist_array->size; i++) {
+		if (!delete_fprobe_node(&hlist_array->array[i]))
+			addrs[count++] = hlist_array->array[i].addr;
+	}
+	del_fprobe_hash(fp);
 
-	if (!IS_ERR_OR_NULL(fp->rethook))
-		rethook_free(fp->rethook);
+	if (count)
+		fprobe_graph_remove_ips(addrs, count);
 
-	ftrace_free_filter(&fp->ops);
+	kfree_rcu(hlist_array, rcu);
+	fp->hlist_array = NULL;
 
+out:
+	mutex_unlock(&fprobe_mutex);
+
+	kfree(addrs);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(unregister_fprobe);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2e113f8..b2955e5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -536,24 +536,21 @@ static int function_stat_show(struct seq_file *m, void *v)
 {
 	struct ftrace_profile *rec = v;
 	char str[KSYM_SYMBOL_LEN];
-	int ret = 0;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	static struct trace_seq s;
 	unsigned long long avg;
 	unsigned long long stddev;
 #endif
-	mutex_lock(&ftrace_profile_lock);
+	guard(mutex)(&ftrace_profile_lock);
 
 	/* we raced with function_profile_reset() */
-	if (unlikely(rec->counter == 0)) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (unlikely(rec->counter == 0))
+		return -EBUSY;
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	avg = div64_ul(rec->time, rec->counter);
 	if (tracing_thresh && (avg < tracing_thresh))
-		goto out;
+		return 0;
 #endif
 
 	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
@@ -590,10 +587,8 @@ static int function_stat_show(struct seq_file *m, void *v)
 	trace_print_seq(m, &s);
 #endif
 	seq_putc(m, '\n');
-out:
-	mutex_unlock(&ftrace_profile_lock);
 
-	return ret;
+	return 0;
 }
 
 static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
@@ -789,27 +784,24 @@ function_profile_call(unsigned long ip, unsigned long parent_ip,
 {
 	struct ftrace_profile_stat *stat;
 	struct ftrace_profile *rec;
-	unsigned long flags;
 
 	if (!ftrace_profile_enabled)
 		return;
 
-	local_irq_save(flags);
+	guard(preempt_notrace)();
 
 	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
-		goto out;
+		return;
 
 	rec = ftrace_find_profiled_func(stat, ip);
 	if (!rec) {
 		rec = ftrace_profile_alloc(stat, ip);
 		if (!rec)
-			goto out;
+			return;
 	}
 
 	rec->counter++;
- out:
-	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -827,7 +819,8 @@ struct profile_fgraph_data {
 };
 
 static int profile_graph_entry(struct ftrace_graph_ent *trace,
-			       struct fgraph_ops *gops)
+			       struct fgraph_ops *gops,
+			       struct ftrace_regs *fregs)
 {
 	struct profile_fgraph_data *profile_data;
 
@@ -849,26 +842,27 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 }
 
 static void profile_graph_return(struct ftrace_graph_ret *trace,
-				 struct fgraph_ops *gops)
+				 struct fgraph_ops *gops,
+				 struct ftrace_regs *fregs)
 {
 	struct profile_fgraph_data *profile_data;
 	struct ftrace_profile_stat *stat;
 	unsigned long long calltime;
 	unsigned long long rettime = trace_clock_local();
 	struct ftrace_profile *rec;
-	unsigned long flags;
 	int size;
 
-	local_irq_save(flags);
+	guard(preempt_notrace)();
+
 	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
-		goto out;
+		return;
 
 	profile_data = fgraph_retrieve_data(gops->idx, &size);
 
 	/* If the calltime was zero'd ignore it */
 	if (!profile_data || !profile_data->calltime)
-		goto out;
+		return;
 
 	calltime = rettime - profile_data->calltime;
 
@@ -896,9 +890,6 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 		rec->time += calltime;
 		rec->time_squared += calltime * calltime;
 	}
-
- out:
-	local_irq_restore(flags);
 }
 
 static struct fgraph_ops fprofiler_ops = {
@@ -946,20 +937,16 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
 
 	val = !!val;
 
-	mutex_lock(&ftrace_profile_lock);
+	guard(mutex)(&ftrace_profile_lock);
 	if (ftrace_profile_enabled ^ val) {
 		if (val) {
 			ret = ftrace_profile_init();
-			if (ret < 0) {
-				cnt = ret;
-				goto out;
-			}
+			if (ret < 0)
+				return ret;
 
 			ret = register_ftrace_profiler();
-			if (ret < 0) {
-				cnt = ret;
-				goto out;
-			}
+			if (ret < 0)
+				return ret;
 			ftrace_profile_enabled = 1;
 		} else {
 			ftrace_profile_enabled = 0;
@@ -970,8 +957,6 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
 			unregister_ftrace_profiler();
 		}
 	}
- out:
-	mutex_unlock(&ftrace_profile_lock);
 
 	*ppos += cnt;
 
@@ -1671,14 +1656,12 @@ unsigned long ftrace_location(unsigned long ip)
 	loc = ftrace_location_range(ip, ip);
 	if (!loc) {
 		if (!kallsyms_lookup_size_offset(ip, &size, &offset))
-			goto out;
+			return 0;
 
 		/* map sym+0 to __fentry__ */
 		if (!offset)
 			loc = ftrace_location_range(ip, ip + size - 1);
 	}
-
-out:
 	return loc;
 }
 
@@ -2073,7 +2056,7 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops,
 			continue;
 
 		if (rec == end)
-			goto err_out;
+			return -EBUSY;
 
 		in_old = !!ftrace_lookup_ip(old_hash, rec->ip);
 		in_new = !!ftrace_lookup_ip(new_hash, rec->ip);
@@ -2086,7 +2069,6 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops,
 			rec->flags |= FTRACE_FL_IPMODIFY;
 	} while_for_each_ftrace_rec();
 
-err_out:
 	return -EBUSY;
 }
 
@@ -4982,10 +4964,6 @@ static int cache_mod(struct trace_array *tr,
 	return ftrace_add_mod(tr, func, module, enable);
 }
 
-static int
-ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
-		 int reset, int enable);
-
 #ifdef CONFIG_MODULES
 static void process_mod_list(struct list_head *head, struct ftrace_ops *ops,
 			     char *mod, bool enable)
@@ -5615,20 +5593,15 @@ static DEFINE_MUTEX(ftrace_cmd_mutex);
 __init int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	struct ftrace_func_command *p;
-	int ret = 0;
 
-	mutex_lock(&ftrace_cmd_mutex);
+	guard(mutex)(&ftrace_cmd_mutex);
 	list_for_each_entry(p, &ftrace_commands, list) {
-		if (strcmp(cmd->name, p->name) == 0) {
-			ret = -EBUSY;
-			goto out_unlock;
-		}
+		if (strcmp(cmd->name, p->name) == 0)
+			return -EBUSY;
 	}
 	list_add(&cmd->list, &ftrace_commands);
- out_unlock:
-	mutex_unlock(&ftrace_cmd_mutex);
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -5638,20 +5611,17 @@ __init int register_ftrace_command(struct ftrace_func_command *cmd)
 __init int unregister_ftrace_command(struct ftrace_func_command *cmd)
 {
 	struct ftrace_func_command *p, *n;
-	int ret = -ENODEV;
 
-	mutex_lock(&ftrace_cmd_mutex);
+	guard(mutex)(&ftrace_cmd_mutex);
+
 	list_for_each_entry_safe(p, n, &ftrace_commands, list) {
 		if (strcmp(cmd->name, p->name) == 0) {
-			ret = 0;
 			list_del_init(&p->list);
-			goto out_unlock;
+			return 0;
 		}
 	}
- out_unlock:
-	mutex_unlock(&ftrace_cmd_mutex);
 
-	return ret;
+	return -ENODEV;
 }
 
 static int ftrace_process_regex(struct ftrace_iterator *iter,
@@ -5661,7 +5631,7 @@ static int ftrace_process_regex(struct ftrace_iterator *iter,
 	struct trace_array *tr = iter->ops->private;
 	char *func, *command, *next = buff;
 	struct ftrace_func_command *p;
-	int ret = -EINVAL;
+	int ret;
 
 	func = strsep(&next, ":");
 
@@ -5678,17 +5648,14 @@ static int ftrace_process_regex(struct ftrace_iterator *iter,
 
 	command = strsep(&next, ":");
 
-	mutex_lock(&ftrace_cmd_mutex);
-	list_for_each_entry(p, &ftrace_commands, list) {
-		if (strcmp(p->name, command) == 0) {
-			ret = p->func(tr, hash, func, command, next, enable);
-			goto out_unlock;
-		}
-	}
- out_unlock:
-	mutex_unlock(&ftrace_cmd_mutex);
+	guard(mutex)(&ftrace_cmd_mutex);
 
-	return ret;
+	list_for_each_entry(p, &ftrace_commands, list) {
+		if (strcmp(p->name, command) == 0)
+			return p->func(tr, hash, func, command, next, enable);
+	}
+
+	return -EINVAL;
 }
 
 static ssize_t
@@ -5722,12 +5689,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 					   parser->idx, enable);
 		trace_parser_clear(parser);
 		if (ret < 0)
-			goto out;
+			return ret;
 	}
 
-	ret = read;
- out:
-	return ret;
+	return read;
 }
 
 ssize_t
@@ -5788,7 +5753,7 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long *ips,
 static int
 ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 		unsigned long *ips, unsigned int cnt,
-		int remove, int reset, int enable)
+		int remove, int reset, int enable, char *mod)
 {
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *hash;
@@ -5814,7 +5779,15 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 		goto out_regex_unlock;
 	}
 
-	if (buf && !ftrace_match_records(hash, buf, len)) {
+	if (buf && !match_records(hash, buf, len, mod)) {
+		/* If this was for a module and nothing was enabled, flag it */
+		if (mod)
+			(*orig_hash)->flags |= FTRACE_HASH_FL_MOD;
+
+		/*
+		 * Even if it is a mod, return error to let caller know
+		 * nothing was added
+		 */
 		ret = -EINVAL;
 		goto out_regex_unlock;
 	}
@@ -5839,7 +5812,7 @@ static int
 ftrace_set_addr(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt,
 		int remove, int reset, int enable)
 {
-	return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable);
+	return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable, NULL);
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
@@ -6217,7 +6190,38 @@ static int
 ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 		 int reset, int enable)
 {
-	return ftrace_set_hash(ops, buf, len, NULL, 0, 0, reset, enable);
+	char *mod = NULL, *func, *command, *next = buf;
+	char *tmp __free(kfree) = NULL;
+	struct trace_array *tr = ops->private;
+	int ret;
+
+	func = strsep(&next, ":");
+
+	/* This can also handle :mod: parsing */
+	if (next) {
+		if (!tr)
+			return -EINVAL;
+
+		command = strsep(&next, ":");
+		if (strcmp(command, "mod") != 0)
+			return -EINVAL;
+
+		mod = next;
+		len = command - func;
+		/* Save the original func as ftrace_set_hash() can modify it */
+		tmp = kstrdup(func, GFP_KERNEL);
+	}
+
+	ret = ftrace_set_hash(ops, func, len, NULL, 0, 0, reset, enable, mod);
+
+	if (tr && mod && ret < 0) {
+		/* Did tmp fail to allocate? */
+		if (!tmp)
+			return -ENOMEM;
+		ret = cache_mod(tr, tmp, mod, enable);
+	}
+
+	return ret;
 }
 
 /**
@@ -6381,6 +6385,14 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable)
 
 	ftrace_ops_init(ops);
 
+	/* The trace_array is needed for caching module function filters */
+	if (!ops->private) {
+		struct trace_array *tr = trace_get_global_array();
+
+		ops->private = tr;
+		ftrace_init_trace_array(tr);
+	}
+
 	while (buf) {
 		func = strsep(&buf, ",");
 		ftrace_set_regex(ops, func, strlen(func), 0, enable);
@@ -7814,9 +7826,14 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
 
 void ftrace_init_trace_array(struct trace_array *tr)
 {
+	if (tr->flags & TRACE_ARRAY_FL_MOD_INIT)
+		return;
+
 	INIT_LIST_HEAD(&tr->func_probes);
 	INIT_LIST_HEAD(&tr->mod_trace);
 	INIT_LIST_HEAD(&tr->mod_notrace);
+
+	tr->flags |= TRACE_ARRAY_FL_MOD_INIT;
 }
 #else
 
@@ -7845,7 +7862,8 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
 __init void ftrace_init_global_array_ops(struct trace_array *tr)
 {
 	tr->ops = &global_ops;
-	tr->ops->private = tr;
+	if (!global_ops.private)
+		global_ops.private = tr;
 	ftrace_init_trace_array(tr);
 	init_array_fgraph_ops(tr, tr->ops);
 }
@@ -8287,7 +8305,7 @@ pid_write(struct file *filp, const char __user *ubuf,
 	if (!cnt)
 		return 0;
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
 	switch (type) {
 	case TRACE_PIDS:
@@ -8303,14 +8321,13 @@ pid_write(struct file *filp, const char __user *ubuf,
 					     lockdep_is_held(&ftrace_lock));
 		break;
 	default:
-		ret = -EINVAL;
 		WARN_ON_ONCE(1);
-		goto out;
+		return -EINVAL;
 	}
 
 	ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	switch (type) {
 	case TRACE_PIDS:
@@ -8339,11 +8356,8 @@ pid_write(struct file *filp, const char __user *ubuf,
 
 	ftrace_update_pid_func();
 	ftrace_startup_all(0);
- out:
-	mutex_unlock(&ftrace_lock);
 
-	if (ret > 0)
-		*ppos += ret;
+	*ppos += ret;
 
 	return ret;
 }
@@ -8746,17 +8760,17 @@ static int
 ftrace_enable_sysctl(const struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos)
 {
-	int ret = -ENODEV;
+	int ret;
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
 	if (unlikely(ftrace_disabled))
-		goto out;
+		return -ENODEV;
 
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
-		goto out;
+		return ret;
 
 	if (ftrace_enabled) {
 
@@ -8770,8 +8784,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write,
 	} else {
 		if (is_permanent_ops_registered()) {
 			ftrace_enabled = true;
-			ret = -EBUSY;
-			goto out;
+			return -EBUSY;
 		}
 
 		/* stopping ftrace calls (just send to ftrace_stub) */
@@ -8781,9 +8794,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write,
 	}
 
 	last_ftrace_enabled = !!ftrace_enabled;
- out:
-	mutex_unlock(&ftrace_lock);
-	return ret;
+	return 0;
 }
 
 static struct ctl_table ftrace_sysctls[] = {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b6e40e8..2542ec3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -10661,6 +10661,14 @@ __init static int tracer_alloc_buffers(void)
 	return ret;
 }
 
+#ifdef CONFIG_FUNCTION_TRACER
+/* Used to set module cached ftrace filtering at boot up */
+__init struct trace_array *trace_get_global_array(void)
+{
+	return &global_trace;
+}
+#endif
+
 void __init ftrace_boot_snapshot(void)
 {
 #ifdef CONFIG_TRACER_MAX_TRACE
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 179676d..04058a9 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -432,6 +432,7 @@ struct trace_array {
 enum {
 	TRACE_ARRAY_FL_GLOBAL	= BIT(0),
 	TRACE_ARRAY_FL_BOOT	= BIT(1),
+	TRACE_ARRAY_FL_MOD_INIT	= BIT(2),
 };
 
 extern struct list_head ftrace_trace_arrays;
@@ -693,8 +694,10 @@ void trace_latency_header(struct seq_file *m);
 void trace_default_header(struct seq_file *m);
 void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
 
-void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops);
-int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops);
+void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops,
+			struct ftrace_regs *fregs);
+int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops,
+		      struct ftrace_regs *fregs);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
@@ -1112,6 +1115,7 @@ void ftrace_destroy_function_files(struct trace_array *tr);
 int ftrace_allocate_ftrace_ops(struct trace_array *tr);
 void ftrace_free_ftrace_ops(struct trace_array *tr);
 void ftrace_init_global_array_ops(struct trace_array *tr);
+struct trace_array *trace_get_global_array(void);
 void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func);
 void ftrace_reset_array_ops(struct trace_array *tr);
 void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index c62d162..b8f3c4b 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -134,7 +134,7 @@ static int
 process_fetch_insn(struct fetch_insn *code, void *rec, void *edata,
 		   void *dest, void *base)
 {
-	struct pt_regs *regs = rec;
+	struct ftrace_regs *fregs = rec;
 	unsigned long val;
 	int ret;
 
@@ -142,17 +142,17 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *edata,
 	/* 1st stage: get value from context */
 	switch (code->op) {
 	case FETCH_OP_STACK:
-		val = regs_get_kernel_stack_nth(regs, code->param);
+		val = ftrace_regs_get_kernel_stack_nth(fregs, code->param);
 		break;
 	case FETCH_OP_STACKP:
-		val = kernel_stack_pointer(regs);
+		val = ftrace_regs_get_stack_pointer(fregs);
 		break;
 	case FETCH_OP_RETVAL:
-		val = regs_return_value(regs);
+		val = ftrace_regs_get_return_value(fregs);
 		break;
 #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
 	case FETCH_OP_ARG:
-		val = regs_get_kernel_argument(regs, code->param);
+		val = ftrace_regs_get_argument(fregs, code->param);
 		break;
 	case FETCH_OP_EDATA:
 		val = *(unsigned long *)((unsigned long)edata + code->offset);
@@ -175,7 +175,7 @@ NOKPROBE_SYMBOL(process_fetch_insn)
 /* function entry handler */
 static nokprobe_inline void
 __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
-		    struct pt_regs *regs,
+		    struct ftrace_regs *fregs,
 		    struct trace_event_file *trace_file)
 {
 	struct fentry_trace_entry_head *entry;
@@ -189,41 +189,71 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
-	dsize = __get_data_size(&tf->tp, regs, NULL);
+	dsize = __get_data_size(&tf->tp, fregs, NULL);
 
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
 					   sizeof(*entry) + tf->tp.size + dsize);
 	if (!entry)
 		return;
 
-	fbuffer.regs = regs;
+	fbuffer.regs = ftrace_get_regs(fregs);
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
 	entry->ip = entry_ip;
-	store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
 }
 
 static void
 fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
-		  struct pt_regs *regs)
+		  struct ftrace_regs *fregs)
 {
 	struct event_file_link *link;
 
 	trace_probe_for_each_link_rcu(link, &tf->tp)
-		__fentry_trace_func(tf, entry_ip, regs, link->file);
+		__fentry_trace_func(tf, entry_ip, fregs, link->file);
 }
 NOKPROBE_SYMBOL(fentry_trace_func);
 
+static nokprobe_inline
+void store_fprobe_entry_data(void *edata, struct trace_probe *tp, struct ftrace_regs *fregs)
+{
+	struct probe_entry_arg *earg = tp->entry_arg;
+	unsigned long val = 0;
+	int i;
+
+	if (!earg)
+		return;
+
+	for (i = 0; i < earg->size; i++) {
+		struct fetch_insn *code = &earg->code[i];
+
+		switch (code->op) {
+		case FETCH_OP_ARG:
+			val = ftrace_regs_get_argument(fregs, code->param);
+			break;
+		case FETCH_OP_ST_EDATA:
+			*(unsigned long *)((unsigned long)edata + code->offset) = val;
+			break;
+		case FETCH_OP_END:
+			goto end;
+		default:
+			break;
+		}
+	}
+end:
+	return;
+}
+
 /* function exit handler */
 static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip,
-				unsigned long ret_ip, struct pt_regs *regs,
+				unsigned long ret_ip, struct ftrace_regs *fregs,
 				void *entry_data)
 {
 	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
 
 	if (tf->tp.entry_arg)
-		store_trace_entry_data(entry_data, &tf->tp, regs);
+		store_fprobe_entry_data(entry_data, &tf->tp, fregs);
 
 	return 0;
 }
@@ -231,7 +261,7 @@ NOKPROBE_SYMBOL(trace_fprobe_entry_handler)
 
 static nokprobe_inline void
 __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
-		   unsigned long ret_ip, struct pt_regs *regs,
+		   unsigned long ret_ip, struct ftrace_regs *fregs,
 		   void *entry_data, struct trace_event_file *trace_file)
 {
 	struct fexit_trace_entry_head *entry;
@@ -245,60 +275,63 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
-	dsize = __get_data_size(&tf->tp, regs, entry_data);
+	dsize = __get_data_size(&tf->tp, fregs, entry_data);
 
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
 					   sizeof(*entry) + tf->tp.size + dsize);
 	if (!entry)
 		return;
 
-	fbuffer.regs = regs;
+	fbuffer.regs = ftrace_get_regs(fregs);
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
 	entry->func = entry_ip;
 	entry->ret_ip = ret_ip;
-	store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
 }
 
 static void
 fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
-		 unsigned long ret_ip, struct pt_regs *regs, void *entry_data)
+		 unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data)
 {
 	struct event_file_link *link;
 
 	trace_probe_for_each_link_rcu(link, &tf->tp)
-		__fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data, link->file);
+		__fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data, link->file);
 }
 NOKPROBE_SYMBOL(fexit_trace_func);
 
 #ifdef CONFIG_PERF_EVENTS
 
 static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip,
-			    struct pt_regs *regs)
+			    struct ftrace_regs *fregs)
 {
 	struct trace_event_call *call = trace_probe_event_call(&tf->tp);
 	struct fentry_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
+	struct pt_regs *regs;
 	int rctx;
 
 	head = this_cpu_ptr(call->perf_events);
 	if (hlist_empty(head))
 		return 0;
 
-	dsize = __get_data_size(&tf->tp, regs, NULL);
+	dsize = __get_data_size(&tf->tp, fregs, NULL);
 	__size = sizeof(*entry) + tf->tp.size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	entry = perf_trace_buf_alloc(size, NULL, &rctx);
+	entry = perf_trace_buf_alloc(size, &regs, &rctx);
 	if (!entry)
 		return 0;
 
+	regs = ftrace_fill_perf_regs(fregs, regs);
+
 	entry->ip = entry_ip;
 	memset(&entry[1], 0, dsize);
-	store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL);
 	return 0;
@@ -307,31 +340,34 @@ NOKPROBE_SYMBOL(fentry_perf_func);
 
 static void
 fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip,
-		unsigned long ret_ip, struct pt_regs *regs,
+		unsigned long ret_ip, struct ftrace_regs *fregs,
 		void *entry_data)
 {
 	struct trace_event_call *call = trace_probe_event_call(&tf->tp);
 	struct fexit_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
+	struct pt_regs *regs;
 	int rctx;
 
 	head = this_cpu_ptr(call->perf_events);
 	if (hlist_empty(head))
 		return;
 
-	dsize = __get_data_size(&tf->tp, regs, entry_data);
+	dsize = __get_data_size(&tf->tp, fregs, entry_data);
 	__size = sizeof(*entry) + tf->tp.size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	entry = perf_trace_buf_alloc(size, NULL, &rctx);
+	entry = perf_trace_buf_alloc(size, &regs, &rctx);
 	if (!entry)
 		return;
 
+	regs = ftrace_fill_perf_regs(fregs, regs);
+
 	entry->func = entry_ip;
 	entry->ret_ip = ret_ip;
-	store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL);
 }
@@ -339,33 +375,34 @@ NOKPROBE_SYMBOL(fexit_perf_func);
 #endif	/* CONFIG_PERF_EVENTS */
 
 static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip,
-			     unsigned long ret_ip, struct pt_regs *regs,
+			     unsigned long ret_ip, struct ftrace_regs *fregs,
 			     void *entry_data)
 {
 	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
 	int ret = 0;
 
 	if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
-		fentry_trace_func(tf, entry_ip, regs);
+		fentry_trace_func(tf, entry_ip, fregs);
+
 #ifdef CONFIG_PERF_EVENTS
 	if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE))
-		ret = fentry_perf_func(tf, entry_ip, regs);
+		ret = fentry_perf_func(tf, entry_ip, fregs);
 #endif
 	return ret;
 }
 NOKPROBE_SYMBOL(fentry_dispatcher);
 
 static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip,
-			     unsigned long ret_ip, struct pt_regs *regs,
+			     unsigned long ret_ip, struct ftrace_regs *fregs,
 			     void *entry_data)
 {
 	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
 
 	if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
-		fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data);
+		fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data);
 #ifdef CONFIG_PERF_EVENTS
 	if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE))
-		fexit_perf_func(tf, entry_ip, ret_ip, regs, entry_data);
+		fexit_perf_func(tf, entry_ip, ret_ip, fregs, entry_data);
 #endif
 }
 NOKPROBE_SYMBOL(fexit_dispatcher);
@@ -379,6 +416,9 @@ static void free_trace_fprobe(struct trace_fprobe *tf)
 	}
 }
 
+/* Since alloc_trace_fprobe() can return error, check the pointer is ERR too. */
+DEFINE_FREE(free_trace_fprobe, struct trace_fprobe *, if (!IS_ERR_OR_NULL(_T)) free_trace_fprobe(_T))
+
 /*
  * Allocate new trace_probe and initialize it (including fprobe).
  */
@@ -387,10 +427,9 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 					       const char *symbol,
 					       struct tracepoint *tpoint,
 					       struct module *mod,
-					       int maxactive,
 					       int nargs, bool is_return)
 {
-	struct trace_fprobe *tf;
+	struct trace_fprobe *tf __free(free_trace_fprobe) = NULL;
 	int ret = -ENOMEM;
 
 	tf = kzalloc(struct_size(tf, tp.args, nargs), GFP_KERNEL);
@@ -399,7 +438,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 
 	tf->symbol = kstrdup(symbol, GFP_KERNEL);
 	if (!tf->symbol)
-		goto error;
+		return ERR_PTR(-ENOMEM);
 
 	if (is_return)
 		tf->fp.exit_handler = fexit_dispatcher;
@@ -408,17 +447,13 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 
 	tf->tpoint = tpoint;
 	tf->mod = mod;
-	tf->fp.nr_maxactive = maxactive;
 
 	ret = trace_probe_init(&tf->tp, event, group, false, nargs);
 	if (ret < 0)
-		goto error;
+		return ERR_PTR(ret);
 
 	dyn_event_init(&tf->devent, &trace_fprobe_ops);
-	return tf;
-error:
-	free_trace_fprobe(tf);
-	return ERR_PTR(ret);
+	return_ptr(tf);
 }
 
 static struct trace_fprobe *find_trace_fprobe(const char *event,
@@ -845,14 +880,12 @@ static int register_trace_fprobe(struct trace_fprobe *tf)
 	struct trace_fprobe *old_tf;
 	int ret;
 
-	mutex_lock(&event_mutex);
+	guard(mutex)(&event_mutex);
 
 	old_tf = find_trace_fprobe(trace_probe_name(&tf->tp),
 				   trace_probe_group_name(&tf->tp));
-	if (old_tf) {
-		ret = append_trace_fprobe(tf, old_tf);
-		goto end;
-	}
+	if (old_tf)
+		return append_trace_fprobe(tf, old_tf);
 
 	/* Register new event */
 	ret = register_fprobe_event(tf);
@@ -862,7 +895,7 @@ static int register_trace_fprobe(struct trace_fprobe *tf)
 			trace_probe_log_err(0, EVENT_EXIST);
 		} else
 			pr_warn("Failed to register probe event(%d)\n", ret);
-		goto end;
+		return ret;
 	}
 
 	/* Register fprobe */
@@ -872,8 +905,6 @@ static int register_trace_fprobe(struct trace_fprobe *tf)
 	else
 		dyn_event_add(&tf->devent, trace_probe_event_call(&tf->tp));
 
-end:
-	mutex_unlock(&event_mutex);
 	return ret;
 }
 
@@ -1034,7 +1065,10 @@ static int parse_symbol_and_return(int argc, const char *argv[],
 	return 0;
 }
 
-static int __trace_fprobe_create(int argc, const char *argv[])
+DEFINE_FREE(module_put, struct module *, if (_T) module_put(_T))
+
+static int trace_fprobe_create_internal(int argc, const char *argv[],
+					struct traceprobe_parse_context *ctx)
 {
 	/*
 	 * Argument syntax:
@@ -1060,24 +1094,20 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	 * Type of args:
 	 *  FETCHARG:TYPE : use TYPE instead of unsigned long.
 	 */
-	struct trace_fprobe *tf = NULL;
-	int i, len, new_argc = 0, ret = 0;
+	struct trace_fprobe *tf __free(free_trace_fprobe) = NULL;
+	int i, new_argc = 0, ret = 0;
 	bool is_return = false;
-	char *symbol = NULL;
+	char *symbol __free(kfree) = NULL;
 	const char *event = NULL, *group = FPROBE_EVENT_SYSTEM;
-	const char **new_argv = NULL;
-	int maxactive = 0;
+	const char **new_argv __free(kfree) = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
 	char gbuf[MAX_EVENT_NAME_LEN];
 	char sbuf[KSYM_NAME_LEN];
 	char abuf[MAX_BTF_ARGS_LEN];
-	char *dbuf = NULL;
+	char *dbuf __free(kfree) = NULL;
 	bool is_tracepoint = false;
-	struct module *tp_mod = NULL;
+	struct module *tp_mod __free(module_put) = NULL;
 	struct tracepoint *tpoint = NULL;
-	struct traceprobe_parse_context ctx = {
-		.flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE,
-	};
 
 	if ((argv[0][0] != 'f' && argv[0][0] != 't') || argc < 2)
 		return -ECANCELED;
@@ -1087,35 +1117,13 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 		group = TRACEPOINT_EVENT_SYSTEM;
 	}
 
-	trace_probe_log_init("trace_fprobe", argc, argv);
-
-	event = strchr(&argv[0][1], ':');
-	if (event)
-		event++;
-
-	if (isdigit(argv[0][1])) {
-		if (event)
-			len = event - &argv[0][1] - 1;
-		else
-			len = strlen(&argv[0][1]);
-		if (len > MAX_EVENT_NAME_LEN - 1) {
+	if (argv[0][1] != '\0') {
+		if (argv[0][1] != ':') {
+			trace_probe_log_set_index(0);
 			trace_probe_log_err(1, BAD_MAXACT);
-			goto parse_error;
+			return -EINVAL;
 		}
-		memcpy(buf, &argv[0][1], len);
-		buf[len] = '\0';
-		ret = kstrtouint(buf, 0, &maxactive);
-		if (ret || !maxactive) {
-			trace_probe_log_err(1, BAD_MAXACT);
-			goto parse_error;
-		}
-		/* fprobe rethook instances are iterated over via a list. The
-		 * maximum should stay reasonable.
-		 */
-		if (maxactive > RETHOOK_MAXACTIVE_MAX) {
-			trace_probe_log_err(1, MAXACT_TOO_BIG);
-			goto parse_error;
-		}
+		event = &argv[0][2];
 	}
 
 	trace_probe_log_set_index(1);
@@ -1123,20 +1131,14 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	/* a symbol(or tracepoint) must be specified */
 	ret = parse_symbol_and_return(argc, argv, &symbol, &is_return, is_tracepoint);
 	if (ret < 0)
-		goto parse_error;
-
-	if (!is_return && maxactive) {
-		trace_probe_log_set_index(0);
-		trace_probe_log_err(1, BAD_MAXACT_TYPE);
-		goto parse_error;
-	}
+		return -EINVAL;
 
 	trace_probe_log_set_index(0);
 	if (event) {
 		ret = traceprobe_parse_event_name(&event, &group, gbuf,
 						  event - argv[0]);
 		if (ret)
-			goto parse_error;
+			return -EINVAL;
 	}
 
 	if (!event) {
@@ -1152,67 +1154,62 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	}
 
 	if (is_return)
-		ctx.flags |= TPARG_FL_RETURN;
+		ctx->flags |= TPARG_FL_RETURN;
 	else
-		ctx.flags |= TPARG_FL_FENTRY;
+		ctx->flags |= TPARG_FL_FENTRY;
 
 	if (is_tracepoint) {
-		ctx.flags |= TPARG_FL_TPOINT;
+		ctx->flags |= TPARG_FL_TPOINT;
 		tpoint = find_tracepoint(symbol, &tp_mod);
 		if (tpoint) {
-			ctx.funcname = kallsyms_lookup(
+			ctx->funcname = kallsyms_lookup(
 				(unsigned long)tpoint->probestub,
 				NULL, NULL, NULL, sbuf);
 		} else if (IS_ENABLED(CONFIG_MODULES)) {
 				/* This *may* be loaded afterwards */
 				tpoint = TRACEPOINT_STUB;
-				ctx.funcname = symbol;
+				ctx->funcname = symbol;
 		} else {
 			trace_probe_log_set_index(1);
 			trace_probe_log_err(0, NO_TRACEPOINT);
-			goto parse_error;
+			return -EINVAL;
 		}
 	} else
-		ctx.funcname = symbol;
+		ctx->funcname = symbol;
 
 	argc -= 2; argv += 2;
 	new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc,
-					       abuf, MAX_BTF_ARGS_LEN, &ctx);
-	if (IS_ERR(new_argv)) {
-		ret = PTR_ERR(new_argv);
-		new_argv = NULL;
-		goto out;
-	}
+					       abuf, MAX_BTF_ARGS_LEN, ctx);
+	if (IS_ERR(new_argv))
+		return PTR_ERR(new_argv);
 	if (new_argv) {
 		argc = new_argc;
 		argv = new_argv;
 	}
-	if (argc > MAX_TRACE_ARGS) {
-		ret = -E2BIG;
-		goto out;
-	}
+	if (argc > MAX_TRACE_ARGS)
+		return -E2BIG;
 
 	ret = traceprobe_expand_dentry_args(argc, argv, &dbuf);
 	if (ret)
-		goto out;
+		return ret;
 
 	/* setup a probe */
 	tf = alloc_trace_fprobe(group, event, symbol, tpoint, tp_mod,
-				maxactive, argc, is_return);
+				argc, is_return);
 	if (IS_ERR(tf)) {
 		ret = PTR_ERR(tf);
 		/* This must return -ENOMEM, else there is a bug */
 		WARN_ON_ONCE(ret != -ENOMEM);
-		goto out;	/* We know tf is not allocated */
+		return ret;
 	}
 
 	/* parse arguments */
 	for (i = 0; i < argc; i++) {
 		trace_probe_log_set_index(i + 2);
-		ctx.offset = 0;
-		ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx);
+		ctx->offset = 0;
+		ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], ctx);
 		if (ret)
-			goto error;	/* This can be -ENOMEM */
+			return ret;	/* This can be -ENOMEM */
 	}
 
 	if (is_return && tf->tp.entry_arg) {
@@ -1223,7 +1220,7 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	ret = traceprobe_set_print_fmt(&tf->tp,
 			is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL);
 	if (ret < 0)
-		goto error;
+		return ret;
 
 	ret = register_trace_fprobe(tf);
 	if (ret) {
@@ -1234,29 +1231,32 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 			trace_probe_log_err(0, BAD_PROBE_ADDR);
 		else if (ret != -ENOMEM && ret != -EEXIST)
 			trace_probe_log_err(0, FAIL_REG_PROBE);
-		goto error;
+		return -EINVAL;
 	}
 
-out:
-	if (tp_mod)
-		module_put(tp_mod);
+	/* 'tf' is successfully registered. To avoid freeing, assign NULL. */
+	tf = NULL;
+
+	return 0;
+}
+
+static int trace_fprobe_create_cb(int argc, const char *argv[])
+{
+	struct traceprobe_parse_context ctx = {
+		.flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE,
+	};
+	int ret;
+
+	trace_probe_log_init("trace_fprobe", argc, argv);
+	ret = trace_fprobe_create_internal(argc, argv, &ctx);
 	traceprobe_finish_parse(&ctx);
 	trace_probe_log_clear();
-	kfree(new_argv);
-	kfree(symbol);
-	kfree(dbuf);
 	return ret;
-
-parse_error:
-	ret = -EINVAL;
-error:
-	free_trace_fprobe(tf);
-	goto out;
 }
 
 static int trace_fprobe_create(const char *raw_command)
 {
-	return trace_probe_create(raw_command, __trace_fprobe_create);
+	return trace_probe_create(raw_command, trace_fprobe_create_cb);
 }
 
 static int trace_fprobe_release(struct dyn_event *ev)
@@ -1278,8 +1278,6 @@ static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev)
 		seq_putc(m, 't');
 	else
 		seq_putc(m, 'f');
-	if (trace_fprobe_is_return(tf) && tf->fp.nr_maxactive)
-		seq_printf(m, "%d", tf->fp.nr_maxactive);
 	seq_printf(m, ":%s/%s", trace_probe_group_name(&tf->tp),
 				trace_probe_name(&tf->tp));
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 5504b5e..dc62eb9 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -175,16 +175,16 @@ struct fgraph_times {
 };
 
 int trace_graph_entry(struct ftrace_graph_ent *trace,
-		      struct fgraph_ops *gops)
+		      struct fgraph_ops *gops,
+		      struct ftrace_regs *fregs)
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
 	struct trace_array_cpu *data;
 	struct fgraph_times *ftimes;
-	unsigned long flags;
 	unsigned int trace_ctx;
 	long disabled;
-	int ret;
+	int ret = 0;
 	int cpu;
 
 	if (*task_var & TRACE_GRAPH_NOTRACE)
@@ -235,25 +235,21 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
 	if (tracing_thresh)
 		return 1;
 
-	local_irq_save(flags);
+	preempt_disable_notrace();
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&data->disabled);
-	if (likely(disabled == 1)) {
-		trace_ctx = tracing_gen_ctx_flags(flags);
-		if (unlikely(IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) &&
-			tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR))) {
+	disabled = atomic_read(&data->disabled);
+	if (likely(!disabled)) {
+		trace_ctx = tracing_gen_ctx();
+		if (IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) &&
+		    tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR)) {
 			unsigned long retaddr = ftrace_graph_top_ret_addr(current);
-
 			ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx, retaddr);
-		} else
+		} else {
 			ret = __trace_graph_entry(tr, trace, trace_ctx);
-	} else {
-		ret = 0;
+		}
 	}
-
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
+	preempt_enable_notrace();
 
 	return ret;
 }
@@ -314,13 +310,12 @@ static void handle_nosleeptime(struct ftrace_graph_ret *trace,
 }
 
 void trace_graph_return(struct ftrace_graph_ret *trace,
-			struct fgraph_ops *gops)
+			struct fgraph_ops *gops, struct ftrace_regs *fregs)
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
 	struct trace_array_cpu *data;
 	struct fgraph_times *ftimes;
-	unsigned long flags;
 	unsigned int trace_ctx;
 	long disabled;
 	int size;
@@ -341,20 +336,20 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 
 	trace->calltime = ftimes->calltime;
 
-	local_irq_save(flags);
+	preempt_disable_notrace();
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&data->disabled);
-	if (likely(disabled == 1)) {
-		trace_ctx = tracing_gen_ctx_flags(flags);
+	disabled = atomic_read(&data->disabled);
+	if (likely(!disabled)) {
+		trace_ctx = tracing_gen_ctx();
 		__trace_graph_return(tr, trace, trace_ctx);
 	}
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
+	preempt_enable_notrace();
 }
 
 static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
-				      struct fgraph_ops *gops)
+				      struct fgraph_ops *gops,
+				      struct ftrace_regs *fregs)
 {
 	struct fgraph_times *ftimes;
 	int size;
@@ -378,7 +373,7 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 	    (trace->rettime - ftimes->calltime < tracing_thresh))
 		return;
 	else
-		trace_graph_return(trace, gops);
+		trace_graph_return(trace, gops, fregs);
 }
 
 static struct fgraph_ops funcgraph_ops = {
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index a4e799c..08786c5 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -176,7 +176,8 @@ static int irqsoff_display_graph(struct trace_array *tr, int set)
 }
 
 static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
-			       struct fgraph_ops *gops)
+			       struct fgraph_ops *gops,
+			       struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
@@ -214,7 +215,8 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
 }
 
 static void irqsoff_graph_return(struct ftrace_graph_ret *trace,
-				 struct fgraph_ops *gops)
+				 struct fgraph_ops *gops,
+				 struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index 2caf0d2..f39b37f 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -232,7 +232,7 @@ process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val,
 
 /* Sum up total data length for dynamic arrays (strings) */
 static nokprobe_inline int
-__get_data_size(struct trace_probe *tp, struct pt_regs *regs, void *edata)
+__get_data_size(struct trace_probe *tp, void *regs, void *edata)
 {
 	struct probe_arg *arg;
 	int i, len, ret = 0;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index c58292e..f372252 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -113,7 +113,8 @@ static int wakeup_display_graph(struct trace_array *tr, int set)
 }
 
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
-			      struct fgraph_ops *gops)
+			      struct fgraph_ops *gops,
+			      struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
@@ -150,7 +151,8 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
 }
 
 static void wakeup_graph_return(struct ftrace_graph_ret *trace,
-				struct fgraph_ops *gops)
+				struct fgraph_ops *gops,
+				struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 38b5754..d88c44f 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -774,7 +774,8 @@ struct fgraph_fixture {
 };
 
 static __init int store_entry(struct ftrace_graph_ent *trace,
-			      struct fgraph_ops *gops)
+			      struct fgraph_ops *gops,
+			      struct ftrace_regs *fregs)
 {
 	struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops);
 	const char *type = fixture->store_type_name;
@@ -807,7 +808,8 @@ static __init int store_entry(struct ftrace_graph_ent *trace,
 }
 
 static __init void store_return(struct ftrace_graph_ret *trace,
-				struct fgraph_ops *gops)
+				struct fgraph_ops *gops,
+				struct ftrace_regs *fregs)
 {
 	struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops);
 	const char *type = fixture->store_type_name;
@@ -1025,7 +1027,8 @@ static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
 static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace,
-				      struct fgraph_ops *gops)
+				      struct fgraph_ops *gops,
+				      struct ftrace_regs *fregs)
 {
 	/* This is harmlessly racy, we want to approximately detect a hang */
 	if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
@@ -1039,7 +1042,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace,
 		return 0;
 	}
 
-	return trace_graph_entry(trace, gops);
+	return trace_graph_entry(trace, gops, fregs);
 }
 
 static struct fgraph_ops fgraph_ops __initdata  = {
diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c
index 24de0e5..cf92111 100644
--- a/lib/test_fprobe.c
+++ b/lib/test_fprobe.c
@@ -17,10 +17,8 @@ static u32 rand1, entry_val, exit_val;
 /* Use indirect calls to avoid inlining the target functions */
 static u32 (*target)(u32 value);
 static u32 (*target2)(u32 value);
-static u32 (*target_nest)(u32 value, u32 (*nest)(u32));
 static unsigned long target_ip;
 static unsigned long target2_ip;
-static unsigned long target_nest_ip;
 static int entry_return_value;
 
 static noinline u32 fprobe_selftest_target(u32 value)
@@ -33,14 +31,9 @@ static noinline u32 fprobe_selftest_target2(u32 value)
 	return (value / div_factor) + 1;
 }
 
-static noinline u32 fprobe_selftest_nest_target(u32 value, u32 (*nest)(u32))
-{
-	return nest(value + 2);
-}
-
 static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip,
 				    unsigned long ret_ip,
-				    struct pt_regs *regs, void *data)
+				    struct ftrace_regs *fregs, void *data)
 {
 	KUNIT_EXPECT_FALSE(current_test, preemptible());
 	/* This can be called on the fprobe_selftest_target and the fprobe_selftest_target2 */
@@ -59,9 +52,9 @@ static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip,
 
 static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip,
 				    unsigned long ret_ip,
-				    struct pt_regs *regs, void *data)
+				    struct ftrace_regs *fregs, void *data)
 {
-	unsigned long ret = regs_return_value(regs);
+	unsigned long ret = ftrace_regs_get_return_value(fregs);
 
 	KUNIT_EXPECT_FALSE(current_test, preemptible());
 	if (ip != target_ip) {
@@ -79,22 +72,6 @@ static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip,
 		KUNIT_EXPECT_NULL(current_test, data);
 }
 
-static notrace int nest_entry_handler(struct fprobe *fp, unsigned long ip,
-				      unsigned long ret_ip,
-				      struct pt_regs *regs, void *data)
-{
-	KUNIT_EXPECT_FALSE(current_test, preemptible());
-	return 0;
-}
-
-static notrace void nest_exit_handler(struct fprobe *fp, unsigned long ip,
-				      unsigned long ret_ip,
-				      struct pt_regs *regs, void *data)
-{
-	KUNIT_EXPECT_FALSE(current_test, preemptible());
-	KUNIT_EXPECT_EQ(current_test, ip, target_nest_ip);
-}
-
 /* Test entry only (no rethook) */
 static void test_fprobe_entry(struct kunit *test)
 {
@@ -191,25 +168,6 @@ static void test_fprobe_data(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp));
 }
 
-/* Test nr_maxactive */
-static void test_fprobe_nest(struct kunit *test)
-{
-	static const char *syms[] = {"fprobe_selftest_target", "fprobe_selftest_nest_target"};
-	struct fprobe fp = {
-		.entry_handler = nest_entry_handler,
-		.exit_handler = nest_exit_handler,
-		.nr_maxactive = 1,
-	};
-
-	current_test = test;
-	KUNIT_EXPECT_EQ(test, 0, register_fprobe_syms(&fp, syms, 2));
-
-	target_nest(rand1, target);
-	KUNIT_EXPECT_EQ(test, 1, fp.nmissed);
-
-	KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp));
-}
-
 static void test_fprobe_skip(struct kunit *test)
 {
 	struct fprobe fp = {
@@ -247,10 +205,8 @@ static int fprobe_test_init(struct kunit *test)
 	rand1 = get_random_u32_above(div_factor);
 	target = fprobe_selftest_target;
 	target2 = fprobe_selftest_target2;
-	target_nest = fprobe_selftest_nest_target;
 	target_ip = get_ftrace_location(target);
 	target2_ip = get_ftrace_location(target2);
-	target_nest_ip = get_ftrace_location(target_nest);
 
 	return 0;
 }
@@ -260,7 +216,6 @@ static struct kunit_case fprobe_testcases[] = {
 	KUNIT_CASE(test_fprobe),
 	KUNIT_CASE(test_fprobe_syms),
 	KUNIT_CASE(test_fprobe_data),
-	KUNIT_CASE(test_fprobe_nest),
 	KUNIT_CASE(test_fprobe_skip),
 	{}
 };
diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c
index 0a50b05..bfe98ce 100644
--- a/samples/fprobe/fprobe_example.c
+++ b/samples/fprobe/fprobe_example.c
@@ -50,7 +50,7 @@ static void show_backtrace(void)
 
 static int sample_entry_handler(struct fprobe *fp, unsigned long ip,
 				unsigned long ret_ip,
-				struct pt_regs *regs, void *data)
+				struct ftrace_regs *fregs, void *data)
 {
 	if (use_trace)
 		/*
@@ -67,7 +67,7 @@ static int sample_entry_handler(struct fprobe *fp, unsigned long ip,
 }
 
 static void sample_exit_handler(struct fprobe *fp, unsigned long ip,
-				unsigned long ret_ip, struct pt_regs *regs,
+				unsigned long ret_ip, struct ftrace_regs *regs,
 				void *data)
 {
 	unsigned long rip = ret_ip;
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_repeat.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_repeat.tc
new file mode 100644
index 0000000..b4ad092
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_repeat.tc
@@ -0,0 +1,19 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Generic dynamic event - Repeating add/remove fprobe events
+# requires: dynamic_events "f[:[<group>/][<event>]] <func-name>[%return] [<args>]":README
+
+echo 0 > events/enable
+echo > dynamic_events
+
+PLACE=$FUNCTION_FORK
+REPEAT_TIMES=64
+
+for i in `seq 1 $REPEAT_TIMES`; do
+  echo "f:myevent $PLACE" >> dynamic_events
+  grep -q myevent dynamic_events
+  test -d events/fprobes/myevent
+  echo > dynamic_events
+done
+
+clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc
index 61877d1..c9425a34 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc
@@ -16,9 +16,7 @@
   REG=%r0 ;;
 esac
 
-check_error 'f^100 vfs_read'		# MAXACT_NO_KPROBE
-check_error 'f^1a111 vfs_read'		# BAD_MAXACT
-check_error 'f^100000 vfs_read'		# MAXACT_TOO_BIG
+check_error 'f^100 vfs_read'		# BAD_MAXACT
 
 check_error 'f ^non_exist_func'		# BAD_PROBE_ADDR (enoent)
 check_error 'f ^vfs_read+10'		# BAD_PROBE_ADDR