arm64/ftrace: Make function graph use ftrace directly

As we do in commit 0c0593b ("x86/ftrace: Make function graph
use ftrace directly"), we don't need special hook for graph tracer,
but instead we use graph_ops:func function to install return_hooker.

Since commit 3b23e49 ("arm64: implement ftrace with regs") add
implementation for FTRACE_WITH_REGS on arm64, we can easily adopt
the same cleanup on arm64.

And this cleanup only changes the FTRACE_WITH_REGS implementation,
so the mcount-based implementation is unaffected.

While in theory it would be possible to make a similar cleanup for
!FTRACE_WITH_REGS, this will require rework of the core code, and
so for now we only change the FTRACE_WITH_REGS implementation.

Tested-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Link: https://lore.kernel.org/r/20220420160006.17880-2-zhouchengming@bytedance.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

Author: Chengming Zhou

arch/arm64/include/asm/ftrace.h

@@ -80,8 +80,15 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 struct dyn_ftrace;
+struct ftrace_ops;
+struct ftrace_regs;
+
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
+
+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
 
 #define ftrace_return_address(n) return_address(n)

arch/arm64/kernel/entry-ftrace.S

@@ -97,12 +97,6 @@ SYM_CODE_START(ftrace_common)
 SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	bl	ftrace_stub
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
-	nop				// If enabled, this will be replaced
-					// "b ftrace_graph_caller"
-#endif
-
 /*
  * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved
  * x19-x29 per the AAPCS, and we created frame records upon entry, so we need
@@ -127,17 +121,6 @@ ftrace_common_return:
 	ret	x9
 SYM_CODE_END(ftrace_common)
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_CODE_START(ftrace_graph_caller)
-	ldr	x0, [sp, #S_PC]
-	sub	x0, x0, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
-	add	x1, sp, #S_LR			// parent_ip (callsite's LR)
-	ldr	x2, [sp, #PT_REGS_SIZE]	   	// parent fp (callsite's FP)
-	bl	prepare_ftrace_return
-	b	ftrace_common_return
-SYM_CODE_END(ftrace_graph_caller)
-#endif
-
 #else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
 /*

arch/arm64/kernel/ftrace.c

@@ -268,6 +268,22 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	/*
+	 * When DYNAMIC_FTRACE_WITH_REGS is selected, `fregs` can never be NULL
+	 * and arch_ftrace_get_regs(fregs) will always give a non-NULL pt_regs
+	 * in which we can safely modify the LR.
+	 */
+	struct pt_regs *regs = arch_ftrace_get_regs(fregs);
+	unsigned long *parent = (unsigned long *)&procedure_link_pointer(regs);
+
+	prepare_ftrace_return(ip, parent, frame_pointer(regs));
+}
+#else
 /*
  * Turn on/off the call to ftrace_graph_caller() in ftrace_caller()
  * depending on @enable.
@@ -297,5 +313,6 @@ int ftrace_disable_ftrace_graph_caller(void)
 {
 	return ftrace_modify_graph_caller(false);
 }
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */