ARM: ftrace: enable the graph tracer with the EABI unwinder

Enable the function graph tracer in combination with the EABI unwinder,
so that Thumb2 builds or Clang ARM builds can make use of it.

This involves using the unwinder to locate the return address of an
instrumented function on the stack, so that it can be overridden and
made to refer to the ftrace handling routines that need to be called at
function return.

Given that for these builds, it is not guaranteed that the value of the
link register is stored on the stack, fall back to the stack slot that
will be used by the ftrace exit code to restore LR in the instrumented
function's execution context.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>

arch/arm/Kconfig

@@ -91,7 +91,7 @@ config ARM
 	select HAVE_EXIT_THREAD
 	select HAVE_FAST_GUP if ARM_LPAE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
-	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
+	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !(THUMB2_KERNEL && CC_IS_CLANG)
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GCC_PLUGINS

arch/arm/Kconfig.debug

@@ -65,7 +65,7 @@ config UNWINDER_FRAME_POINTER
 
 config UNWINDER_ARM
 	bool "ARM EABI stack unwinder"
-	depends on AEABI && !FUNCTION_GRAPH_TRACER
+	depends on AEABI
 	# https://github.com/ClangBuiltLinux/linux/issues/732
 	depends on !LD_IS_LLD || LLD_VERSION >= 110000
 	select ARM_UNWIND

arch/arm/include/asm/ftrace.h

@@ -35,26 +35,8 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 #ifndef __ASSEMBLY__
 
-#if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND)
-/*
- * return_address uses walk_stackframe to do it's work.  If both
- * CONFIG_FRAME_POINTER=y and CONFIG_ARM_UNWIND=y walk_stackframe uses unwind
- * information.  For this to work in the function tracer many functions would
- * have to be marked with __notrace.  So for now just depend on
- * !CONFIG_ARM_UNWIND.
- */
-
 void *return_address(unsigned int);
 
-#else
-
-static inline void *return_address(unsigned int level)
-{
-	return NULL;
-}
-
-#endif
-
 #define ftrace_return_address(n) return_address(n)
 
 #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME

arch/arm/kernel/Makefile

@@ -25,10 +25,7 @@ obj-y		:= elf.o entry-common.o irq.o opcodes.o \
 KASAN_SANITIZE_stacktrace.o := n
 KASAN_SANITIZE_traps.o := n
 
-ifneq ($(CONFIG_ARM_UNWIND),y)
+obj-y				+= return_address.o
-obj-$(CONFIG_FRAME_POINTER)	+= return_address.o
-endif
-
 obj-$(CONFIG_ATAGS)		+= atags_parse.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o

arch/arm/kernel/entry-ftrace.S

@@ -100,7 +100,8 @@ ftrace_regs_call:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	.globl ftrace_graph_regs_call
 ftrace_graph_regs_call:
-	mov	r0, r0
+ARM(	mov	r0, r0	)
+THUMB(	nop.w		)
 #endif
 
 	@ pop saved regs
@@ -112,13 +113,18 @@ ftrace_graph_regs_call:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 .macro __ftrace_graph_regs_caller
 
-	sub     r0, fp, #4              @ lr of instrumented routine (parent)
+#ifdef CONFIG_UNWINDER_FRAME_POINTER
+	sub	r0, fp, #4		@ lr of instrumented routine (parent)
+#else
+	add	r0, sp, #S_LR
+#endif
 
 	@ called from __ftrace_regs_caller
-	ldr     r1, [sp, #S_PC]		@ instrumented routine (func)
+	ldr	r1, [sp, #S_PC]		@ instrumented routine (func)
 	mcount_adjust_addr	r1, r1
 
-	mov	r2, fp			@ frame pointer
+	mov	r2, fpreg		@ frame pointer
+	add	r3, sp, #PT_REGS_SIZE
 	bl	prepare_ftrace_return
 
 	@ pop registers saved in ftrace_regs_caller
@@ -149,14 +155,19 @@ ftrace_call\suffix:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	.globl ftrace_graph_call\suffix
 ftrace_graph_call\suffix:
-	mov	r0, r0
+ARM(	mov	r0, r0	)
+THUMB(	nop.w		)
 #endif
 
 	mcount_exit
 .endm
 
 .macro __ftrace_graph_caller
+#ifdef CONFIG_UNWINDER_FRAME_POINTER
 	sub	r0, fp, #4		@ &lr of instrumented routine (&parent)
+#else
+	add	r0, sp, #20
+#endif
 #ifdef CONFIG_DYNAMIC_FTRACE
 	@ called from __ftrace_caller, saved in mcount_enter
 	ldr	r1, [sp, #16]		@ instrumented routine (func)
@@ -165,7 +176,8 @@ ftrace_graph_call\suffix:
 	@ called from __mcount, untouched in lr
 	mcount_adjust_addr	r1, lr	@ instrumented routine (func)
 #endif
-	mov	r2, fp			@ frame pointer
+	mov	r2, fpreg		@ frame pointer
+	add	r3, sp, #24
 	bl	prepare_ftrace_return
 	mcount_exit
 .endm
@@ -244,14 +256,14 @@ ENDPROC(ftrace_graph_regs_caller)
 .purgem mcount_exit
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	.globl return_to_handler
+ENTRY(return_to_handler)
-return_to_handler:
 	stmdb	sp!, {r0-r3}
 	add	r0, sp, #16		@ sp at exit of instrumented routine
 	bl	ftrace_return_to_handler
 	mov	lr, r0			@ r0 has real ret addr
 	ldmia	sp!, {r0-r3}
 	ret	lr
+ENDPROC(return_to_handler)
 #endif
 
 ENTRY(ftrace_stub)

arch/arm/kernel/ftrace.c

@@ -22,6 +22,7 @@
 #include <asm/ftrace.h>
 #include <asm/insn.h>
 #include <asm/set_memory.h>
+#include <asm/stacktrace.h>
 #include <asm/patch.h>
 
 /*
@@ -224,8 +225,10 @@ int ftrace_make_nop(struct module *mod,
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
+asmlinkage
 void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
-			   unsigned long frame_pointer)
+			   unsigned long frame_pointer,
+			   unsigned long stack_pointer)
 {
 	unsigned long return_hooker = (unsigned long) &return_to_handler;
 	unsigned long old;
@@ -236,6 +239,18 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	if (IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER)) {
 		/* FP points one word below parent's top of stack */
 		frame_pointer += 4;
+	} else {
+		struct stackframe frame = {
+			.fp = frame_pointer,
+			.sp = stack_pointer,
+			.lr = self_addr,
+			.pc = self_addr,
+		};
+		if (unwind_frame(&frame) < 0)
+			return;
+		if (frame.lr != self_addr)
+			parent = frame.lr_addr;
+		frame_pointer = frame.sp;
 	}
 
 	old = *parent;
@@ -258,7 +273,7 @@ static int __ftrace_modify_caller(unsigned long *callsite,
 	unsigned long caller_fn = (unsigned long) func;
 	unsigned long pc = (unsigned long) callsite;
 	unsigned long branch = arm_gen_branch(pc, caller_fn);
-	unsigned long nop = 0xe1a00000;	/* mov r0, r0 */
+	unsigned long nop = arm_gen_nop();
 	unsigned long old = enable ? nop : branch;
 	unsigned long new = enable ? branch : nop;