[PATCH v8 2/6] arm64: ptrace: allow tracer to skip a system call

[AKASHI Takahiro]

If tracer specifies -1 as a syscall number, this traced system call should
be skipped with a return value specified in x0.
This patch implements this semantics, but there is one restriction here:

    syscall(-1) always return ENOSYS whatever value is stored in x0
    (a return value) at syscall entry.

Normally, with ptrace off, syscall(-1) returns -ENOSYS. With ptrace on,
however, if a tracer didn't pay any attention to user-issued syscall(-1)
and just let it go, it would return a value in x0 as in other system call
cases. This means that this system call might succeed and yet see any bogus
return value. This should be definitely avoided.

Please also note:
* syscall entry tracing and syscall exit tracing (ftrace tracepoint and
  audit) are always executed, if enabled, even when skipping a system call
  (that is, -1).
  In this way, we can avoid a potential bug where audit_syscall_entry()
  might be called without audit_syscall_exit() at the previous system call
  being called, that would cause OOPs in audit_syscall_entry().

Signed-off-by: AKASHI Takahiro <takahiro.akashi at linaro.org>
---
 arch/arm64/kernel/entry.S  |    3 +++
 arch/arm64/kernel/ptrace.c |   18 ++++++++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 726b910..01118b1 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -670,6 +670,8 @@ ENDPROC(el0_svc)
 __sys_trace:
 	mov	x0, sp
 	bl	syscall_trace_enter
+	cmp	w0, #-1				// skip the syscall?
+	b.eq	__sys_trace_return_skipped
 	adr	lr, __sys_trace_return		// return address
 	uxtw	scno, w0			// syscall number (possibly new)
 	mov	x1, sp				// pointer to regs
@@ -684,6 +686,7 @@ __sys_trace:
 
 __sys_trace_return:
 	str	x0, [sp]			// save returned x0
+__sys_trace_return_skipped:
 	mov	x0, sp
 	bl	syscall_trace_exit
 	b	ret_to_user
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 8b98781..34b1e85 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1149,6 +1149,8 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 
 asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 {
+	int orig_syscallno = regs->syscallno;
+
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
 
@@ -1158,6 +1160,22 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 	audit_syscall_entry(regs->syscallno, regs->orig_x0, regs->regs[1],
 			    regs->regs[2], regs->regs[3]);
 
+	if (((int)regs->syscallno == -1) && (orig_syscallno == -1)) {
+		/*
+		 * user-issued syscall(-1):
+		 * RESTRICTION: We always return ENOSYS whatever value is
+		 *   stored in x0 (a return value) at this point.
+		 * Normally, with ptrace off, syscall(-1) returns -ENOSYS.
+		 * With ptrace on, however, if a tracer didn't pay any
+		 * attention to user-issued syscall(-1) and just let it go
+		 * without a hack here, it would return a value in x0 as in
+		 * other system call cases. This means that this system call
+		 * might succeed and see any bogus return value.
+		 * This should be definitely avoided.
+		 */
+		regs->regs[0] = -ENOSYS;
+	}
+
 	return regs->syscallno;
 }
 
-- 
1.7.9.5