samples/ftrace: Adjust LoongArch register restore order in direct calls

Ensure that in the ftrace direct call logic, the CPU register state
(with ra = parent return address) is restored to the correct state after
the execution of the custom trampoline function and before returning to
the traced function. Additionally, guarantee the correctness of the jump
logic for jr t0 (traced function address).

Cc: stable@vger.kernel.org
Fixes: 9cdc3b6 ("LoongArch: ftrace: Add direct call support")
Reported-by: Youling Tang <tangyouling@kylinos.cn>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Chenghao Duan <duanchenghao@kylinos.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

Author: Chenghao Duan

samples/ftrace/ftrace-direct-modify.c

@@ -176,8 +176,8 @@ asm (
 "	st.d	$t0, $sp, 0\n"
 "	st.d	$ra, $sp, 8\n"
 "	bl	my_direct_func1\n"
-"	ld.d	$t0, $sp, 0\n"
-"	ld.d	$ra, $sp, 8\n"
+"	ld.d	$ra, $sp, 0\n"
+"	ld.d	$t0, $sp, 8\n"
 "	addi.d	$sp, $sp, 16\n"
 "	jr	$t0\n"
 "	.size		my_tramp1, .-my_tramp1\n"
@@ -189,8 +189,8 @@ asm (
 "	st.d	$t0, $sp, 0\n"
 "	st.d	$ra, $sp, 8\n"
 "	bl	my_direct_func2\n"
-"	ld.d	$t0, $sp, 0\n"
-"	ld.d	$ra, $sp, 8\n"
+"	ld.d	$ra, $sp, 0\n"
+"	ld.d	$t0, $sp, 8\n"
 "	addi.d	$sp, $sp, 16\n"
 "	jr	$t0\n"
 "	.size		my_tramp2, .-my_tramp2\n"

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

@@ -199,8 +199,8 @@ asm (
 "	move	$a0, $t0\n"
 "	bl	my_direct_func1\n"
 "	ld.d	$a0, $sp, 0\n"
-"	ld.d	$t0, $sp, 8\n"
-"	ld.d	$ra, $sp, 16\n"
+"	ld.d	$ra, $sp, 8\n"
+"	ld.d	$t0, $sp, 16\n"
 "	addi.d	$sp, $sp, 32\n"
 "	jr	$t0\n"
 "	.size		my_tramp1, .-my_tramp1\n"
@@ -215,8 +215,8 @@ asm (
 "	move	$a0, $t0\n"
 "	bl	my_direct_func2\n"
 "	ld.d	$a0, $sp, 0\n"
-"	ld.d	$t0, $sp, 8\n"
-"	ld.d	$ra, $sp, 16\n"
+"	ld.d	$ra, $sp, 8\n"
+"	ld.d	$t0, $sp, 16\n"
 "	addi.d	$sp, $sp, 32\n"
 "	jr	$t0\n"
 "	.size		my_tramp2, .-my_tramp2\n"

samples/ftrace/ftrace-direct-multi.c

@@ -131,8 +131,8 @@ asm (
 "	move	$a0, $t0\n"
 "	bl	my_direct_func\n"
 "	ld.d	$a0, $sp, 0\n"
-"	ld.d	$t0, $sp, 8\n"
-"	ld.d	$ra, $sp, 16\n"
+"	ld.d	$ra, $sp, 8\n"
+"	ld.d	$t0, $sp, 16\n"
 "	addi.d	$sp, $sp, 32\n"
 "	jr	$t0\n"
 "	.size		my_tramp, .-my_tramp\n"

samples/ftrace/ftrace-direct-too.c

@@ -143,8 +143,8 @@ asm (
 "	ld.d	$a0, $sp, 0\n"
 "	ld.d	$a1, $sp, 8\n"
 "	ld.d	$a2, $sp, 16\n"
-"	ld.d	$t0, $sp, 24\n"
-"	ld.d	$ra, $sp, 32\n"
+"	ld.d	$ra, $sp, 24\n"
+"	ld.d	$t0, $sp, 32\n"
 "	addi.d	$sp, $sp, 48\n"
 "	jr	$t0\n"
 "	.size		my_tramp, .-my_tramp\n"

samples/ftrace/ftrace-direct.c

@@ -124,8 +124,8 @@ asm (
 "	st.d	$ra, $sp, 16\n"
 "	bl	my_direct_func\n"
 "	ld.d	$a0, $sp, 0\n"
-"	ld.d	$t0, $sp, 8\n"
-"	ld.d	$ra, $sp, 16\n"
+"	ld.d	$ra, $sp, 8\n"
+"	ld.d	$t0, $sp, 16\n"
 "	addi.d	$sp, $sp, 32\n"
 "	jr	$t0\n"
 "	.size		my_tramp, .-my_tramp\n"