x86/ftrace: implement DYNAMIC_FTRACE_WITH_JMP

Implement the DYNAMIC_FTRACE_WITH_JMP for x86_64. In ftrace_call_replace,
we will use JMP32_INSN_OPCODE instead of CALL_INSN_OPCODE if the address
should use "jmp".

Meanwhile, adjust the direct call in the ftrace_regs_caller. The RSB is
balanced in the "jmp" mode. Take the function "foo" for example:

 original_caller:
 call foo -> foo:
         call fentry -> fentry:
                 [do ftrace callbacks ]
                 move tramp_addr to stack
                 RET -> tramp_addr
                         tramp_addr:
                         [..]
                         call foo_body -> foo_body:
                                 [..]
                                 RET -> back to tramp_addr
                         [..]
                         RET -> back to original_caller

Signed-off-by: Menglong Dong <[email protected]>

Author: image-dragon

arch/x86/Kconfig

@@ -230,6 +230,7 @@ config X86
 	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_DYNAMIC_FTRACE_WITH_JMP	if X86_64
 	select HAVE_SAMPLE_FTRACE_DIRECT	if X86_64
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64
 	select HAVE_EBPF_JIT

arch/x86/kernel/ftrace.c

@@ -74,7 +74,12 @@ static const char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	 * No need to translate into a callthunk. The trampoline does
 	 * the depth accounting itself.
 	 */
-	return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
+	if (ftrace_is_jmp(addr)) {
+		addr = ftrace_jmp_get(addr);
+		return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr);
+	} else {
+		return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
+	}
 }
 
 static int ftrace_verify_code(unsigned long ip, const char *old_code)

arch/x86/kernel/ftrace_64.S

@@ -285,8 +285,18 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	RET
 
+1:
+	testb	$1, %al
+	jz	2f
+	andq $0xfffffffffffffffe, %rax
+	movq %rax, MCOUNT_REG_SIZE+8(%rsp)
+	restore_mcount_regs
+	/* Restore flags */
+	popfq
+	RET
+
 	/* Swap the flags with orig_rax */
-1:	movq MCOUNT_REG_SIZE(%rsp), %rdi
+2:	movq MCOUNT_REG_SIZE(%rsp), %rdi
 	movq %rdi, MCOUNT_REG_SIZE-8(%rsp)
 	movq %rax, MCOUNT_REG_SIZE(%rsp)