arm64: ftrace: Add direct call trampoline samples support

The ftrace samples need per-architecture trampoline implementations
to save and restore argument registers around the calls to
my_direct_func* and to restore polluted registers (eg: x30).

These samples also include <asm/asm-offsets.h> which, on arm64, is not
necessary and redefines previously defined macros (resulting in
warnings) so these includes are guarded by !CONFIG_ARM64.

Link: https://lkml.kernel.org/r/20230427140700.625241-3-revest@chromium.orgReviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

arch/arm64/Kconfig

@@ -197,6 +197,8 @@ config ARM64
 		    !CC_OPTIMIZE_FOR_SIZE)
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
 		if DYNAMIC_FTRACE_WITH_ARGS
+	select HAVE_SAMPLE_FTRACE_DIRECT
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD

samples/ftrace/ftrace-direct-modify.c

@@ -2,7 +2,9 @@
 #include <linux/module.h>
 #include <linux/kthread.h>
 #include <linux/ftrace.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
 extern void my_direct_func1(void);
 extern void my_direct_func2(void);
@@ -96,6 +98,38 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:"
+"	bti	c\n"
+"	sub	sp, sp, #16\n"
+"	stp	x9, x30, [sp]\n"
+"	bl	my_direct_func1\n"
+"	ldp	x30, x9, [sp]\n"
+"	add	sp, sp, #16\n"
+"	ret	x9\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+"   my_tramp2:"
+"	bti	c\n"
+"	sub	sp, sp, #16\n"
+"	stp	x9, x30, [sp]\n"
+"	bl	my_direct_func2\n"
+"	ldp	x30, x9, [sp]\n"
+"	add	sp, sp, #16\n"
+"	ret	x9\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 
 asm (

samples/ftrace/ftrace-direct-multi-modify.c

@@ -2,7 +2,9 @@
 #include <linux/module.h>
 #include <linux/kthread.h>
 #include <linux/ftrace.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
 extern void my_direct_func1(unsigned long ip);
 extern void my_direct_func2(unsigned long ip);
@@ -103,6 +105,44 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:"
+"	bti	c\n"
+"	sub	sp, sp, #32\n"
+"	stp	x9, x30, [sp]\n"
+"	str	x0, [sp, #16]\n"
+"	mov	x0, x30\n"
+"	bl	my_direct_func1\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldr	x0, [sp, #16]\n"
+"	add	sp, sp, #32\n"
+"	ret	x9\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+"   my_tramp2:"
+"	bti	c\n"
+"	sub	sp, sp, #32\n"
+"	stp	x9, x30, [sp]\n"
+"	str	x0, [sp, #16]\n"
+"	mov	x0, x30\n"
+"	bl	my_direct_func2\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldr	x0, [sp, #16]\n"
+"	add	sp, sp, #32\n"
+"	ret	x9\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 #include <asm/asm.h>
 

samples/ftrace/ftrace-direct-multi.c

@@ -4,7 +4,9 @@
 #include <linux/mm.h> /* for handle_mm_fault() */
 #include <linux/ftrace.h>
 #include <linux/sched/stat.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
 extern void my_direct_func(unsigned long ip);
 
@@ -66,6 +68,29 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:"
+"	bti	c\n"
+"	sub	sp, sp, #32\n"
+"	stp	x9, x30, [sp]\n"
+"	str	x0, [sp, #16]\n"
+"	mov	x0, x30\n"
+"	bl	my_direct_func\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldr	x0, [sp, #16]\n"
+"	add	sp, sp, #32\n"
+"	ret	x9\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 
 #include <asm/asm.h>

samples/ftrace/ftrace-direct-too.c

@@ -3,7 +3,9 @@
 
 #include <linux/mm.h> /* for handle_mm_fault() */
 #include <linux/ftrace.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
 extern void my_direct_func(struct vm_area_struct *vma, unsigned long address,
 			   unsigned int flags, struct pt_regs *regs);
@@ -72,6 +74,30 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:"
+"	bti	c\n"
+"	sub	sp, sp, #48\n"
+"	stp	x9, x30, [sp]\n"
+"	stp	x0, x1, [sp, #16]\n"
+"	stp	x2, x3, [sp, #32]\n"
+"	bl	my_direct_func\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldp	x0, x1, [sp, #16]\n"
+"	ldp	x2, x3, [sp, #32]\n"
+"	add	sp, sp, #48\n"
+"	ret	x9\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 
 asm (

samples/ftrace/ftrace-direct.c

@@ -3,7 +3,9 @@
 
 #include <linux/sched.h> /* for wake_up_process() */
 #include <linux/ftrace.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
 extern void my_direct_func(struct task_struct *p);
 
@@ -63,6 +65,28 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:"
+"	bti	c\n"
+"	sub	sp, sp, #32\n"
+"	stp	x9, x30, [sp]\n"
+"	str	x0, [sp, #16]\n"
+"	bl	my_direct_func\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldr	x0, [sp, #16]\n"
+"	add	sp, sp, #32\n"
+"	ret	x9\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 
 asm (