[PATCH v2 16/36] x86/entry/64/compat: Remove most of the fast system call machinery

From: Andy Lutomirski
Date: Mon Oct 05 2015 - 20:55:08 EST


We now have only one code path that calls through the compat syscall
table. This will make it much more pleasant to change the pt_regs
vs register calling convention, which we need to do to move the call
into C.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
arch/x86/entry/entry_64_compat.S | 246 +--------------------------------------
1 file changed, 4 insertions(+), 242 deletions(-)

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 8f847722ce72..3216e6072312 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -101,119 +101,13 @@ sysenter_flags_fixed:
movl $11, %edi
call do_exit

- /*
- * Re-enable interrupts. IRQ tracing already thinks that IRQs are
- * on (since we treat user mode as having IRQs on), and the
- * prologue above is too short for it to be worth adding a
- * tracing round trip.
- */
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /*
- * no need to do an access_ok check here because rbp has been
- * 32-bit zero extended
- */
- ASM_STAC
-1: movl (%rbp), %ebp
- _ASM_EXTABLE(1b, ia32_badarg)
- ASM_CLAC
-
- 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 sysenter_tracesys
-
-sysenter_do_call:
- /* 32-bit syscall -> 64-bit C ABI argument conversion */
- movl %edi, %r8d /* arg5 */
- movl %ebp, %r9d /* arg6 */
- xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
- 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)
- jnz ia32_ret_from_sys_call_irqs_off
-sysexit_from_sys_call:
- /*
- * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
- * NMI between STI and SYSEXIT has poorly specified behavior,
- * and and NMI followed by an IRQ with usergs is fatal. So
- * we just pretend we're using SYSEXIT but we really use
- * SYSRETL instead.
- *
- * This code path is still called 'sysexit' because it pairs
- * with 'sysenter' and it uses the SYSENTER calling convention.
- */
- andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- movl RIP(%rsp), %ecx /* User %eip */
- movq RAX(%rsp), %rax
- movl RSI(%rsp), %esi
- movl RDI(%rsp), %edi
- xorl %edx, %edx /* Do not leak kernel information */
- xorq %r8, %r8
- xorq %r9, %r9
- xorq %r10, %r10
- movl EFLAGS(%rsp), %r11d /* User eflags */
- TRACE_IRQS_ON
-
- /*
- * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT,
- * since it avoids a dicey window with interrupts enabled.
- */
- movl RSP(%rsp), %esp
-
- /*
- * USERGS_SYSRET32 does:
- * gsbase = user's gs base
- * eip = ecx
- * rflags = r11
- * cs = __USER32_CS
- * ss = __USER_DS
- *
- * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
- *
- * pop %ebp
- * pop %edx
- * pop %ecx
- *
- * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
- * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's
- * address (already known to user code), and R12-R15 are
- * callee-saved and therefore don't contain any interesting
- * kernel data.
- */
- USERGS_SYSRET32
+ /* Unreachable. */
+ ud2

sysenter_fix_flags:
pushq $X86_EFLAGS_FIXED
popfq
jmp sysenter_flags_fixed
-
-sysenter_tracesys:
- SAVE_EXTRA_REGS
- xorl %eax, %eax /* Do not leak kernel information */
- movq %rax, R11(%rsp)
- movq %rax, R10(%rsp)
- movq %rax, R9(%rsp)
- movq %rax, R8(%rsp)
- movq %rsp, %rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
-
- /* Reload arg registers from stack. (see sysenter_tracesys) */
- movl RCX(%rsp), %ecx
- movl RDX(%rsp), %edx
- movl RSI(%rsp), %esi
- movl RDI(%rsp), %edi
- movl %eax, %eax /* zero extension */
-
- RESTORE_EXTRA_REGS
- jmp sysenter_do_call
ENDPROC(entry_SYSENTER_compat)

/*
@@ -280,142 +174,10 @@ ENTRY(entry_SYSCALL_compat)
pushq $-ENOSYS /* pt_regs->ax */
sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */

- /*
- * No need to do an access_ok check here because r8 has been
- * 32-bit zero extended:
- */
- ASM_STAC
-1: movl (%r8), %r9d
- _ASM_EXTABLE(1b, ia32_badarg)
- ASM_CLAC
- 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 cstar_tracesys
-
-cstar_do_call:
- /* 32-bit syscall -> 64-bit C ABI argument conversion */
- movl %edi, %r8d /* arg5 */
- /* r9 already loaded */ /* arg6 */
- xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
- 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)
- jnz ia32_ret_from_sys_call_irqs_off
-
-sysretl_from_sys_call:
- andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- movl RDX(%rsp), %edx
- movl RSI(%rsp), %esi
- movl RDI(%rsp), %edi
- movl RIP(%rsp), %ecx
- movl EFLAGS(%rsp), %r11d
- movq RAX(%rsp), %rax
- xorq %r10, %r10
- xorq %r9, %r9
- xorq %r8, %r8
- TRACE_IRQS_ON
- movl RSP(%rsp), %esp
- /*
- * 64-bit->32-bit SYSRET restores eip from ecx,
- * eflags from r11 (but RF and VM bits are forced to 0),
- * cs and ss are loaded from MSRs.
- * (Note: 32-bit->32-bit SYSRET is different: since r11
- * does not exist, it merely sets eflags.IF=1).
- *
- * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
- * descriptor is not reinitialized. This means that we must
- * avoid SYSRET with SS == NULL, which could happen if we schedule,
- * exit the kernel, and re-enter using an interrupt vector. (All
- * interrupt entries on x86_64 set SS to NULL.) We prevent that
- * from happening by reloading SS in __switch_to.
- */
- USERGS_SYSRET32
-
-cstar_tracesys:
- xchgl %r9d, %ebp
- SAVE_EXTRA_REGS
- xorl %eax, %eax /* Do not leak kernel information */
- movq %rax, R11(%rsp)
- movq %rax, R10(%rsp)
- movq %r9, R9(%rsp)
- movq %rax, R8(%rsp)
- movq %rsp, %rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- movl R9(%rsp), %r9d
-
- /* Reload arg registers from stack. (see sysenter_tracesys) */
- movl RCX(%rsp), %ecx
- movl RDX(%rsp), %edx
- movl RSI(%rsp), %esi
- movl RDI(%rsp), %edi
- movl %eax, %eax /* zero extension */
-
- RESTORE_EXTRA_REGS
- xchgl %ebp, %r9d
- jmp cstar_do_call
+ /* Unreachable. */
+ ud2
END(entry_SYSCALL_compat)

-ia32_badarg:
- /*
- * So far, we've entered kernel mode, set AC, turned on IRQs, and
- * saved C regs except r8-r11. We haven't done any of the other
- * standard entry work, though. We want to bail, but we shouldn't
- * treat this as a syscall entry since we don't even know what the
- * args are. Instead, treat this as a non-syscall entry, finish
- * the entry work, and immediately exit after setting AX = -EFAULT.
- *
- * We're really just being polite here. Killing the task outright
- * would be a reasonable action, too. Given that the only valid
- * way to have gotten here is through the vDSO, and we already know
- * that the stack pointer is bad, the task isn't going to survive
- * for long no matter what we do.
- */
-
- ASM_CLAC /* undo STAC */
- movq $-EFAULT, RAX(%rsp) /* return -EFAULT if possible */
-
- /* Fill in the rest of pt_regs */
- xorl %eax, %eax
- movq %rax, R11(%rsp)
- movq %rax, R10(%rsp)
- movq %rax, R9(%rsp)
- movq %rax, R8(%rsp)
- SAVE_EXTRA_REGS
-
- /* Turn IRQs back off. */
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
-
- /* Now finish entering normal kernel mode. */
-#ifdef CONFIG_CONTEXT_TRACKING
- call enter_from_user_mode
-#endif
-
- /* And exit again. */
- jmp retint_user
-
-ia32_ret_from_sys_call_irqs_off:
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
-
-ia32_ret_from_sys_call:
- xorl %eax, %eax /* Do not leak kernel information */
- movq %rax, R11(%rsp)
- movq %rax, R10(%rsp)
- movq %rax, R9(%rsp)
- movq %rax, R8(%rsp)
- jmp int_ret_from_sys_call
-
/*
* Emulated IA32 system calls via int 0x80.
*
--
2.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/