x86_64, entry: Treat regs->ax the same in fastpath and slowpath syscalls

For slowpath syscalls, we initialize regs->ax to -ENOSYS and stick
the syscall number into regs->orig_ax prior to any possible tracing
and syscall execution.  This is user-visible ABI used by ptrace
syscall emulation and seccomp.

For fastpath syscalls, there's no good reason not to do the same
thing.  It's even slightly simpler than what we're currently doing.
It probably has no measureable performance impact.  It should have
no user-visible effect.

The purpose of this patch is to prepare for two-phase syscall
tracing, in which the first phase might modify the saved RAX without
leaving the fast path.  This change is just subtle enough that I'm
keeping it separate.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Link: http://lkml.kernel.org/r/01218b493f12ae2f98034b78c9ae085e38e94350.1409954077.git.luto@amacapital.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index cb4c73b..76659b6 100644 (file)
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -85,7 +85,7 @@ For 32-bit we have the following conventions - kernel is built with
 #define ARGOFFSET      R11
 #define SWFRAME                ORIG_RAX
 
-       .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1
+       .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1, rax_enosys=0
        subq  $9*8+\addskip, %rsp
        CFI_ADJUST_CFA_OFFSET   9*8+\addskip
        movq_cfi rdi, 8*8
@@ -96,7 +96,11 @@ For 32-bit we have the following conventions - kernel is built with
        movq_cfi rcx, 5*8
        .endif
 
+       .if \rax_enosys
+       movq $-ENOSYS, 4*8(%rsp)
+       .else
        movq_cfi rax, 4*8
+       .endif
 
        .if \save_r891011
        movq_cfi r8,  3*8

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2fac134..0bd6d3c 100644 (file)
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -404,8 +404,8 @@ GLOBAL(system_call_after_swapgs)
         * and short:
         */
        ENABLE_INTERRUPTS(CLBR_NONE)
-       SAVE_ARGS 8,0
-       movq  %rax,ORIG_RAX-ARGOFFSET(%rsp)
+       SAVE_ARGS 8, 0, rax_enosys=1
+       movq_cfi rax,(ORIG_RAX-ARGOFFSET)
        movq  %rcx,RIP-ARGOFFSET(%rsp)
        CFI_REL_OFFSET rip,RIP-ARGOFFSET
        testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
@@ -417,7 +417,7 @@ system_call_fastpath:
        andl $__SYSCALL_MASK,%eax
        cmpl $__NR_syscall_max,%eax
 #endif
-       ja badsys
+       ja ret_from_sys_call  /* and return regs->ax */
        movq %r10,%rcx
        call *sys_call_table(,%rax,8)  # XXX:    rip relative
        movq %rax,RAX-ARGOFFSET(%rsp)
@@ -476,10 +476,6 @@ sysret_signal:
        FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
        jmp int_check_syscall_exit_work
 
-badsys:
-       movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
-       jmp ret_from_sys_call
-
 #ifdef CONFIG_AUDITSYSCALL
        /*
         * Fast path for syscall audit without full syscall trace.
@@ -519,7 +515,6 @@ tracesys:
        jz auditsys
 #endif
        SAVE_REST
-       movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
        FIXUP_TOP_OF_STACK %rdi
        movq %rsp,%rdi
        call syscall_trace_enter
@@ -536,7 +531,7 @@ tracesys:
        andl $__SYSCALL_MASK,%eax
        cmpl $__NR_syscall_max,%eax
 #endif
-       ja   int_ret_from_sys_call      /* RAX(%rsp) set to -ENOSYS above */
+       ja   int_ret_from_sys_call      /* RAX(%rsp) is already set */
        movq %r10,%rcx  /* fixup for C */
        call *sys_call_table(,%rax,8)
        movq %rax,RAX-ARGOFFSET(%rsp)