x86/asm/entry/32: Update -ENOSYS handling to match the 64-bit logic

Recently Andy changed the 64-bit syscall logic so that
pt_regs->ax is initially set to -ENOSYS, and on syscall exit,
it is updated with the actual return value. This simplified
the logic there.

This patch does the same for 32-bit syscall entry points.

The check for %rax being too big is moved to be just before
the call instruction which dispatches execution through the
syscall table.

There is no way to accidentally skip this check now by jumping
to a label after it. This allows us to remove redundant checks
after ptrace et al.

If %rax is too big, we just skip over the (call, write %rax to
pt_regs->ax) instruction pair. pt_regs->ax remains set to -ENOSYS,
and it gets returned to userspace.

Similar to 64-bit code, this eliminates the "ia32_badsys" code path.

Run-tested.

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Will Drewry <wad@chromium.org>
Link: http://lkml.kernel.org/r/1429632194-13445-2-git-send-email-dvlasenk@redhat.com
[ Changelog massage. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 3cdb9eafbf8cb5a371869dd4a83b01578d4ae577..56fd6dd2e342695a8538f7abe3a7a59c166862c4 100644 (file)
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -136,7 +136,7 @@ ENTRY(ia32_sysenter_target)
        pushq_cfi_reg   rsi                     /* pt_regs->si */
        pushq_cfi_reg   rdx                     /* pt_regs->dx */
        pushq_cfi_reg   rcx                     /* pt_regs->cx */
-       pushq_cfi_reg   rax                     /* pt_regs->ax */
+       pushq_cfi       $-ENOSYS                /* pt_regs->ax */
        cld
        sub     $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
        CFI_ADJUST_CFA_OFFSET 10*8
@@ -163,8 +163,6 @@ sysenter_flags_fixed:
        testl   $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
        CFI_REMEMBER_STATE
        jnz  sysenter_tracesys
-       cmpq    $(IA32_NR_syscalls-1),%rax
-       ja      ia32_badsys
 sysenter_do_call:
        /* 32bit syscall -> 64bit C ABI argument conversion */
        movl    %edi,%r8d       /* arg5 */
@@ -173,8 +171,11 @@ sysenter_do_call:
        movl    %ebx,%edi       /* arg1 */
        movl    %edx,%edx       /* arg3 (zero extension) */
 sysenter_dispatch:
+       cmpq    $(IA32_NR_syscalls-1),%rax
+       ja      1f
        call    *ia32_sys_call_table(,%rax,8)
        movq    %rax,RAX(%rsp)
+1:
        DISABLE_INTERRUPTS(CLBR_NONE)
        TRACE_IRQS_OFF
        testl   $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
@@ -241,9 +242,7 @@ sysexit_from_sys_call:
        movl %ebx,%esi                  /* 2nd arg: 1st syscall arg */
        movl %eax,%edi                  /* 1st arg: syscall number */
        call __audit_syscall_entry
-       movl RAX(%rsp),%eax     /* reload syscall number */
-       cmpq $(IA32_NR_syscalls-1),%rax
-       ja ia32_badsys
+       movl ORIG_RAX(%rsp),%eax        /* reload syscall number */
        movl %ebx,%edi                  /* reload 1st syscall arg */
        movl RCX(%rsp),%esi     /* reload 2nd syscall arg */
        movl RDX(%rsp),%edx     /* reload 3rd syscall arg */
@@ -294,13 +293,10 @@ sysenter_tracesys:
 #endif
        SAVE_EXTRA_REGS
        CLEAR_RREGS
-       movq    $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
        movq    %rsp,%rdi        /* &pt_regs -> arg1 */
        call    syscall_trace_enter
        LOAD_ARGS32  /* reload args from stack in case ptrace changed it */
        RESTORE_EXTRA_REGS
-       cmpq    $(IA32_NR_syscalls-1),%rax
-       ja      int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
        jmp     sysenter_do_call
        CFI_ENDPROC
 ENDPROC(ia32_sysenter_target)
@@ -370,7 +366,7 @@ ENTRY(ia32_cstar_target)
        pushq_cfi_reg   rdx                     /* pt_regs->dx */
        pushq_cfi_reg   rbp                     /* pt_regs->cx */
        movl    %ebp,%ecx
-       pushq_cfi_reg   rax                     /* pt_regs->ax */
+       pushq_cfi       $-ENOSYS                /* pt_regs->ax */
        sub     $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
        CFI_ADJUST_CFA_OFFSET 10*8
 
@@ -386,8 +382,6 @@ ENTRY(ia32_cstar_target)
        testl   $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
        CFI_REMEMBER_STATE
        jnz   cstar_tracesys
-       cmpq $IA32_NR_syscalls-1,%rax
-       ja  ia32_badsys
 cstar_do_call:
        /* 32bit syscall -> 64bit C ABI argument conversion */
        movl    %edi,%r8d       /* arg5 */
@@ -396,8 +390,11 @@ cstar_do_call:
        movl    %ebx,%edi       /* arg1 */
        movl    %edx,%edx       /* arg3 (zero extension) */
 cstar_dispatch:
+       cmpq    $(IA32_NR_syscalls-1),%rax
+       ja      1f
        call *ia32_sys_call_table(,%rax,8)
        movq %rax,RAX(%rsp)
+1:
        DISABLE_INTERRUPTS(CLBR_NONE)
        TRACE_IRQS_OFF
        testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
@@ -444,14 +441,11 @@ cstar_tracesys:
        xchgl %r9d,%ebp
        SAVE_EXTRA_REGS
        CLEAR_RREGS r9
-       movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
        movq %rsp,%rdi        /* &pt_regs -> arg1 */
        call syscall_trace_enter
        LOAD_ARGS32 1   /* reload args from stack in case ptrace changed it */
        RESTORE_EXTRA_REGS
        xchgl %ebp,%r9d
-       cmpq $(IA32_NR_syscalls-1),%rax
-       ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
        jmp cstar_do_call
 END(ia32_cstar_target)
                                
@@ -510,7 +504,7 @@ ENTRY(ia32_syscall)
        pushq_cfi_reg   rsi                     /* pt_regs->si */
        pushq_cfi_reg   rdx                     /* pt_regs->dx */
        pushq_cfi_reg   rcx                     /* pt_regs->cx */
-       pushq_cfi_reg   rax                     /* pt_regs->ax */
+       pushq_cfi       $-ENOSYS                /* pt_regs->ax */
        cld
        sub     $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
        CFI_ADJUST_CFA_OFFSET 10*8
@@ -518,8 +512,6 @@ ENTRY(ia32_syscall)
        orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
        testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
        jnz ia32_tracesys
-       cmpq $(IA32_NR_syscalls-1),%rax
-       ja ia32_badsys
 ia32_do_call:
        /* 32bit syscall -> 64bit C ABI argument conversion */
        movl %edi,%r8d  /* arg5 */
@@ -527,9 +519,12 @@ ia32_do_call:
        xchg %ecx,%esi  /* rsi:arg2, rcx:arg4 */
        movl %ebx,%edi  /* arg1 */
        movl %edx,%edx  /* arg3 (zero extension) */
+       cmpq    $(IA32_NR_syscalls-1),%rax
+       ja      1f
        call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
 ia32_sysret:
        movq %rax,RAX(%rsp)
+1:
 ia32_ret_from_sys_call:
        CLEAR_RREGS
        jmp int_ret_from_sys_call
@@ -537,23 +532,14 @@ ia32_ret_from_sys_call:
 ia32_tracesys:
        SAVE_EXTRA_REGS
        CLEAR_RREGS
-       movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
        movq %rsp,%rdi        /* &pt_regs -> arg1 */
        call syscall_trace_enter
        LOAD_ARGS32     /* reload args from stack in case ptrace changed it */
        RESTORE_EXTRA_REGS
-       cmpq $(IA32_NR_syscalls-1),%rax
-       ja  int_ret_from_sys_call       /* ia32_tracesys has set RAX(%rsp) */
        jmp ia32_do_call
+       CFI_ENDPROC
 END(ia32_syscall)
 
-ia32_badsys:
-       movq $0,ORIG_RAX(%rsp)
-       movq $-ENOSYS,%rax
-       jmp ia32_sysret
-
-       CFI_ENDPROC
-       
        .macro PTREGSCALL label, func
        ALIGN
 GLOBAL(\label)