arm64: ftrace: Add ftrace direct call support

Add ftrace direct support for arm64.

1. When there is custom trampoline only, replace the fentry nop to a
   jump instruction that jumps directly to the custom trampoline.

2. When ftrace trampoline and custom trampoline coexist, jump from
   fentry to ftrace trampoline first, then jump to custom trampoline
   when ftrace trampoline exits. The current unused register
   pt_regs->orig_x0 is used as an intermediary for jumping from ftrace
   trampoline to custom trampoline.

Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Acked-by: Song Liu <songliubraving@fb.com>

Author: Xu Kuohai

arch/arm64/Kconfig

@@ -177,6 +177,8 @@ config ARM64
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS \
 		if $(cc-option,-fpatchable-function-entry=2)
+	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS \
+		if DYNAMIC_FTRACE_WITH_REGS
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
 		if DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS

arch/arm64/include/asm/ftrace.h

@@ -78,6 +78,16 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	return addr;
 }
 
+static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs,
+						 unsigned long addr)
+{
+	/*
+	 * Place custom trampoline address in regs->orig_x0 to let ftrace
+	 * trampoline jump to it.
+	 */
+	regs->orig_x0 = addr;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 struct dyn_ftrace;
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);

arch/arm64/kernel/asm-offsets.c

@@ -80,6 +80,7 @@ int main(void)
   DEFINE(S_SDEI_TTBR1,		offsetof(struct pt_regs, sdei_ttbr1));
   DEFINE(S_PMR_SAVE,		offsetof(struct pt_regs, pmr_save));
   DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
+  DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(PT_REGS_SIZE,		sizeof(struct pt_regs));
   BLANK();
 #ifdef CONFIG_COMPAT

arch/arm64/kernel/entry-ftrace.S

@@ -60,6 +60,9 @@
 	str	x29, [sp, #S_FP]
 	.endif
 
+	/* Set orig_x0 to zero  */
+	str     xzr, [sp, #S_ORIG_X0]
+
 	/* Save the callsite's SP and LR */
 	add	x10, sp, #(PT_REGS_SIZE + 16)
 	stp	x9, x10, [sp, #S_LR]
@@ -119,12 +122,21 @@ ftrace_common_return:
 	/* Restore the callsite's FP, LR, PC */
 	ldr	x29, [sp, #S_FP]
 	ldr	x30, [sp, #S_LR]
-	ldr	x9, [sp, #S_PC]
-
+	ldr	x10, [sp, #S_PC]
+
+	ldr	x11, [sp, #S_ORIG_X0]
+	cbz	x11, 1f
+	/* Set x9 to parent ip before jump to custom trampoline */
+	mov	x9,  x30
+	/* Set lr to self ip */
+	ldr	x30, [sp, #S_PC]
+	/* Set x10 (used for return address) to custom trampoline */
+	mov	x10, x11
+1:
 	/* Restore the callsite's SP */
 	add	sp, sp, #PT_REGS_SIZE + 16
 
-	ret	x9
+	ret	x10
 SYM_CODE_END(ftrace_common)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER