mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-16 08:44:21 +08:00
8169aff611
This is conceptually simpler. More importantly, it eliminates the PTREGSCALL and execve stubs, which were not compatible with the C ABI. This means that C code can call through the compat syscall table. The execve stubs are a bit subtle. They did two things: they cleared some registers and they forced slow-path return. Neither is necessary any more: elf_common_init clears the extra registers and start_thread calls force_iret(). Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/f95b7f7dfaacf88a8cae85bb06226cae53769287.1444091584.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
284 lines
8.1 KiB
ArmAsm
284 lines
8.1 KiB
ArmAsm
/*
|
|
* Compatibility mode system call entry point for x86-64.
|
|
*
|
|
* Copyright 2000-2002 Andi Kleen, SuSE Labs.
|
|
*/
|
|
#include "calling.h"
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/current.h>
|
|
#include <asm/errno.h>
|
|
#include <asm/ia32_unistd.h>
|
|
#include <asm/thread_info.h>
|
|
#include <asm/segment.h>
|
|
#include <asm/irqflags.h>
|
|
#include <asm/asm.h>
|
|
#include <asm/smap.h>
|
|
#include <linux/linkage.h>
|
|
#include <linux/err.h>
|
|
|
|
.section .entry.text, "ax"
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
ENTRY(native_usergs_sysret32)
|
|
swapgs
|
|
sysretl
|
|
ENDPROC(native_usergs_sysret32)
|
|
#endif
|
|
|
|
/*
|
|
* 32-bit SYSENTER instruction entry.
|
|
*
|
|
* SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
|
|
* IF and VM in rflags are cleared (IOW: interrupts are off).
|
|
* SYSENTER does not save anything on the stack,
|
|
* and does not save old rip (!!!) and rflags.
|
|
*
|
|
* Arguments:
|
|
* eax system call number
|
|
* ebx arg1
|
|
* ecx arg2
|
|
* edx arg3
|
|
* esi arg4
|
|
* edi arg5
|
|
* ebp user stack
|
|
* 0(%ebp) arg6
|
|
*
|
|
* This is purely a fast path. For anything complicated we use the int 0x80
|
|
* path below. We set up a complete hardware stack frame to share code
|
|
* with the int 0x80 path.
|
|
*/
|
|
ENTRY(entry_SYSENTER_compat)
|
|
/* Interrupts are off on entry. */
|
|
SWAPGS_UNSAFE_STACK
|
|
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
|
|
|
|
/* Zero-extending 32-bit regs, do not remove */
|
|
movl %ebp, %ebp
|
|
movl %eax, %eax
|
|
|
|
movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
|
|
|
|
/* Construct struct pt_regs on stack */
|
|
pushq $__USER32_DS /* pt_regs->ss */
|
|
pushq %rbp /* pt_regs->sp */
|
|
|
|
/*
|
|
* Push flags. This is nasty. First, interrupts are currently
|
|
* off, but we need pt_regs->flags to have IF set. Second, even
|
|
* if TF was set when SYSENTER started, it's clear by now. We fix
|
|
* that later using TIF_SINGLESTEP.
|
|
*/
|
|
pushfq /* pt_regs->flags (except IF = 0) */
|
|
orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */
|
|
|
|
pushq $__USER32_CS /* pt_regs->cs */
|
|
pushq %r10 /* pt_regs->ip = thread_info->sysenter_return */
|
|
pushq %rax /* pt_regs->orig_ax */
|
|
pushq %rdi /* pt_regs->di */
|
|
pushq %rsi /* pt_regs->si */
|
|
pushq %rdx /* pt_regs->dx */
|
|
pushq %rcx /* pt_regs->cx */
|
|
pushq $-ENOSYS /* pt_regs->ax */
|
|
cld
|
|
sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
|
|
|
|
/*
|
|
* Sysenter doesn't filter flags, so we need to clear NT
|
|
* ourselves. To save a few cycles, we can check whether
|
|
* NT was set instead of doing an unconditional popfq.
|
|
* This needs to happen before enabling interrupts so that
|
|
* we don't get preempted with NT set.
|
|
*/
|
|
testl $X86_EFLAGS_NT, EFLAGS(%rsp)
|
|
jnz sysenter_fix_flags
|
|
sysenter_flags_fixed:
|
|
|
|
/* Temporary: SYSENTER is disabled. */
|
|
#ifdef CONFIG_CONTEXT_TRACKING
|
|
call enter_from_user_mode
|
|
#endif
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
movl $11, %edi
|
|
call do_exit
|
|
|
|
/* Unreachable. */
|
|
ud2
|
|
|
|
sysenter_fix_flags:
|
|
pushq $X86_EFLAGS_FIXED
|
|
popfq
|
|
jmp sysenter_flags_fixed
|
|
ENDPROC(entry_SYSENTER_compat)
|
|
|
|
/*
|
|
* 32-bit SYSCALL instruction entry.
|
|
*
|
|
* 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
|
|
* then loads new ss, cs, and rip from previously programmed MSRs.
|
|
* rflags gets masked by a value from another MSR (so CLD and CLAC
|
|
* are not needed). SYSCALL does not save anything on the stack
|
|
* and does not change rsp.
|
|
*
|
|
* Note: rflags saving+masking-with-MSR happens only in Long mode
|
|
* (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it).
|
|
* Don't get confused: rflags saving+masking depends on Long Mode Active bit
|
|
* (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
|
|
* or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
|
|
*
|
|
* Arguments:
|
|
* eax system call number
|
|
* ecx return address
|
|
* ebx arg1
|
|
* ebp arg2 (note: not saved in the stack frame, should not be touched)
|
|
* edx arg3
|
|
* esi arg4
|
|
* edi arg5
|
|
* esp user stack
|
|
* 0(%esp) arg6
|
|
*
|
|
* This is purely a fast path. For anything complicated we use the int 0x80
|
|
* path below. We set up a complete hardware stack frame to share code
|
|
* with the int 0x80 path.
|
|
*/
|
|
ENTRY(entry_SYSCALL_compat)
|
|
/*
|
|
* Interrupts are off on entry.
|
|
* We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
|
|
* it is too small to ever cause noticeable irq latency.
|
|
*/
|
|
SWAPGS_UNSAFE_STACK
|
|
|
|
/* Temporary: SYSCALL32 is disabled. */
|
|
movl $-ENOSYS, %eax
|
|
USERGS_SYSRET32
|
|
|
|
movl %esp, %r8d
|
|
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
|
|
/* Zero-extending 32-bit regs, do not remove */
|
|
movl %eax, %eax
|
|
|
|
/* Construct struct pt_regs on stack */
|
|
pushq $__USER32_DS /* pt_regs->ss */
|
|
pushq %r8 /* pt_regs->sp */
|
|
pushq %r11 /* pt_regs->flags */
|
|
pushq $__USER32_CS /* pt_regs->cs */
|
|
pushq %rcx /* pt_regs->ip */
|
|
pushq %rax /* pt_regs->orig_ax */
|
|
pushq %rdi /* pt_regs->di */
|
|
pushq %rsi /* pt_regs->si */
|
|
pushq %rdx /* pt_regs->dx */
|
|
pushq %rbp /* pt_regs->cx */
|
|
movl %ebp, %ecx
|
|
pushq $-ENOSYS /* pt_regs->ax */
|
|
sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
|
|
|
|
/* Unreachable. */
|
|
ud2
|
|
END(entry_SYSCALL_compat)
|
|
|
|
/*
|
|
* Emulated IA32 system calls via int 0x80.
|
|
*
|
|
* Arguments:
|
|
* eax system call number
|
|
* ebx arg1
|
|
* ecx arg2
|
|
* edx arg3
|
|
* esi arg4
|
|
* edi arg5
|
|
* ebp arg6 (note: not saved in the stack frame, should not be touched)
|
|
*
|
|
* Notes:
|
|
* Uses the same stack frame as the x86-64 version.
|
|
* All registers except eax must be saved (but ptrace may violate that).
|
|
* Arguments are zero extended. For system calls that want sign extension and
|
|
* take long arguments a wrapper is needed. Most calls can just be called
|
|
* directly.
|
|
* Assumes it is only called from user space and entered with interrupts off.
|
|
*/
|
|
|
|
ENTRY(entry_INT80_compat)
|
|
/*
|
|
* Interrupts are off on entry.
|
|
* We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
|
|
* it is too small to ever cause noticeable irq latency.
|
|
*/
|
|
PARAVIRT_ADJUST_EXCEPTION_FRAME
|
|
SWAPGS
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
|
|
/* Zero-extending 32-bit regs, do not remove */
|
|
movl %eax, %eax
|
|
|
|
/* Construct struct pt_regs on stack (iret frame is already on stack) */
|
|
pushq %rax /* pt_regs->orig_ax */
|
|
pushq %rdi /* pt_regs->di */
|
|
pushq %rsi /* pt_regs->si */
|
|
pushq %rdx /* pt_regs->dx */
|
|
pushq %rcx /* pt_regs->cx */
|
|
pushq $-ENOSYS /* pt_regs->ax */
|
|
xorq %r8,%r8
|
|
pushq %r8 /* pt_regs->r8 = 0 */
|
|
pushq %r8 /* pt_regs->r9 = 0 */
|
|
pushq %r8 /* pt_regs->r10 = 0 */
|
|
pushq %r8 /* pt_regs->r11 = 0 */
|
|
pushq %rbx /* pt_regs->rbx */
|
|
pushq %rbp /* pt_regs->rbp */
|
|
pushq %r12 /* pt_regs->r12 */
|
|
pushq %r13 /* pt_regs->r13 */
|
|
pushq %r14 /* pt_regs->r14 */
|
|
pushq %r15 /* pt_regs->r15 */
|
|
cld
|
|
|
|
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
|
|
|
|
ia32_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) */
|
|
cmpq $(IA32_NR_syscalls-1), %rax
|
|
ja 1f
|
|
|
|
call *ia32_sys_call_table(, %rax, 8)
|
|
movq %rax, RAX(%rsp)
|
|
1:
|
|
RESTORE_EXTRA_REGS
|
|
jmp int_ret_from_sys_call
|
|
|
|
ia32_tracesys:
|
|
movq %rsp, %rdi /* &pt_regs -> arg1 */
|
|
call syscall_trace_enter
|
|
/*
|
|
* Reload arg registers from stack in case ptrace changed them.
|
|
* Don't reload %eax because syscall_trace_enter() returned
|
|
* the %rax value we should see. But do truncate it to 32 bits.
|
|
* If it's -1 to make us punt the syscall, then (u32)-1 is still
|
|
* an appropriately invalid value.
|
|
*/
|
|
movl RCX(%rsp), %ecx
|
|
movl RDX(%rsp), %edx
|
|
movl RSI(%rsp), %esi
|
|
movl RDI(%rsp), %edi
|
|
movl %eax, %eax /* zero extension */
|
|
jmp ia32_do_call
|
|
END(entry_INT80_compat)
|
|
|
|
ALIGN
|
|
GLOBAL(stub32_clone)
|
|
/*
|
|
* The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
|
|
* The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
|
|
*
|
|
* The native 64-bit kernel's sys_clone() implements the latter,
|
|
* so we need to swap arguments here before calling it:
|
|
*/
|
|
xchg %r8, %rcx
|
|
jmp sys_clone
|