x86/ftrace: Make function graph use ftrace directly

We don't need special hook for graph tracer entry point,
but instead we can use graph_ops::func function to install
the return_hooker.

This moves the graph tracing setup _before_ the direct
trampoline prepares the stack, so the return_hooker will
be called when the direct trampoline is finished.

This simplifies the code, because we don't need to take into
account the direct trampoline setup when preparing the graph
tracer hooker and we can allow function graph tracer on entries
registered with direct trampoline.

Link: https://lkml.kernel.org/r/[e-mail]

[fixed compile error reported by kernel test robot <[e-mail]>]
Signed-off-by: Steven Rostedt (VMware) <[e-mail]>
Signed-off-by: Jiri Olsa <[e-mail]>
Signed-off-by: Steven Rostedt (VMware) <[e-mail]>

arch/x86/include/asm/ftrace.h

···
 
 #define ftrace_instruction_pointer_set(fregs, _ip)	\
 	do { (fregs)->regs.ip = (_ip); } while (0)
+
+struct ftrace_ops;
+#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);
+#else
+#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
···
 struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
-
-#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
 
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */

arch/x86/kernel/ftrace.c

···
 	return ptr + CALL_INSN_SIZE + call.disp;
 }
 
-void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
+void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer);
 
 /*
···
 	void *ptr;
 
 	if (ops && ops->trampoline) {
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) && \
+	defined(CONFIG_FUNCTION_GRAPH_TRACER)
 		/*
 		 * We only know about function graph tracer setting as static
 		 * trampoline.
···
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-extern void ftrace_graph_call(void);
 
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+extern void ftrace_graph_call(void);
 static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
 	return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr);
···
 
 	return ftrace_mod_jmp(ip, &ftrace_stub);
 }
+#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return 0;
+}
 
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return 0;
+}
+#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 #endif /* !CONFIG_DYNAMIC_FTRACE */
 
 /*
···
 			   unsigned long frame_pointer)
 {
 	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	int bit;
 
 	/*
 	 * When resuming from suspend-to-ram, this function can be indirectly
···
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
+	bit = ftrace_test_recursion_trylock(ip, *parent);
+	if (bit < 0)
+		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
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	struct pt_regs *regs = &fregs->regs;
+	unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs);
+
+	prepare_ftrace_return(ip, (unsigned long *)stack, 0);
+}
+#endif
+
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */

arch/x86/kernel/ftrace_64.S

···
 SYM_FUNC_END(ftrace_caller);
 
 SYM_FUNC_START(ftrace_epilogue)
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
-	jmp ftrace_stub
-#endif
-
 /*
  * This is weak to keep gas from relaxing the jumps.
  * It is also used to copy the retq for trampolines.
···
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
 
-fgraph_trace:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	cmpq $ftrace_stub, ftrace_graph_return
-	jnz ftrace_graph_caller
-
-	cmpq $ftrace_graph_entry_stub, ftrace_graph_entry
-	jnz ftrace_graph_caller
-#endif
-
 SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
 	retq
 
···
 	CALL_NOSPEC r8
 	restore_mcount_regs
 
-	jmp fgraph_trace
+	jmp ftrace_stub
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_FUNC_START(ftrace_graph_caller)
-	/* Saves rbp into %rdx and fills first parameter  */
-	save_mcount_regs
-
-	leaq MCOUNT_REG_SIZE+8(%rsp), %rsi
-	movq $0, %rdx	/* No framepointers needed */
-	call	prepare_ftrace_return
-
-	restore_mcount_regs
-
-	retq
-SYM_FUNC_END(ftrace_graph_caller)
-
 SYM_FUNC_START(return_to_handler)
 	subq  $24, %rsp
 

include/linux/ftrace.h

···
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#ifndef ftrace_graph_func
+#define ftrace_graph_func ftrace_stub
+#define FTRACE_OPS_GRAPH_STUB FTRACE_OPS_FL_STUB
+#else
+#define FTRACE_OPS_GRAPH_STUB 0
+#endif
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 /* totally disable ftrace - can not re-enable after this */
 void ftrace_kill(void);
 

kernel/trace/fgraph.c

···
 {
 	struct ftrace_graph_ent trace;
 
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	/*
 	 * Skip graph tracing if the return location is served by direct trampoline,
 	 * since call sequence and return addresses are unpredictable anyway.
···
 	if (ftrace_direct_func_count &&
 	    ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE))
 		return -EBUSY;
+#endif
 	trace.func = func;
 	trace.depth = ++current->curr_ret_depth;
 
···
 #endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
 
 static struct ftrace_ops graph_ops = {
-	.func			= ftrace_stub,
+	.func			= ftrace_graph_func,
 	.flags			= FTRACE_OPS_FL_INITIALIZED |
 				   FTRACE_OPS_FL_PID |
-				   FTRACE_OPS_FL_STUB,
+				   FTRACE_OPS_GRAPH_STUB,
 #ifdef FTRACE_GRAPH_TRAMP_ADDR
 	.trampoline		= FTRACE_GRAPH_TRAMP_ADDR,
 	/* trampoline_size is only needed for dynamically allocated tramps */