x86: ptrace vs -ENOSYS

When we're stopped at syscall entry tracing, ptrace can change the %rax
value from -ENOSYS to something else.  If no system call is actually made
because the syscall number (now in orig_rax) is bad, then we now always
reset %rax to -ENOSYS again.

This changes it to leave the return value alone after entry tracing.
That way, the %rax value set by ptrace is there to be seen in user mode
(or in syscall exit tracing).  This is consistent with what the 32-bit
kernel does.

Signed-off-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index c20c9e7e08dd2a644860dabc206ae1fb843ea173..556a8df522a7adcf9583164be4cad60e29b00a97 100644 (file)
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -319,19 +319,17 @@ badsys:
        /* Do syscall tracing */
 tracesys:                       
        SAVE_REST
-       movq $-ENOSYS,RAX(%rsp)
+       movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
        FIXUP_TOP_OF_STACK %rdi
        movq %rsp,%rdi
        call syscall_trace_enter
        LOAD_ARGS ARGOFFSET  /* reload args from stack in case ptrace changed it */
        RESTORE_REST
        cmpq $__NR_syscall_max,%rax
-       movq $-ENOSYS,%rcx
-       cmova %rcx,%rax
-       ja  1f
+       ja   int_ret_from_sys_call      /* RAX(%rsp) set to -ENOSYS above */
        movq %r10,%rcx  /* fixup for C */
        call *sys_call_table(,%rax,8)
-1:     movq %rax,RAX-ARGOFFSET(%rsp)
+       movq %rax,RAX-ARGOFFSET(%rsp)
        /* Use IRET because user could have changed frame */
                
 /*