9ec2b804e0
Most of the time we can simply use the iret instruction to exit the kernel, rather than having to use the iret hypercall - the only exception is if we're returning into vm86 mode, or from delivering an NMI (which we don't support yet). When running native, iret has the behaviour of testing for a pending interrupt atomically with re-enabling interrupts. Unfortunately there's no way to do this with Xen, so there's a window in which we could get a recursive exception after enabling events but before actually returning to userspace. This causes a problem: if the nested interrupt causes one of the task's TIF_WORK_MASK flags to be set, they will not be checked again before returning to userspace. This means that pending work may be left pending indefinitely, until the process enters and leaves the kernel again. The net effect is that a pending signal or reschedule event could be delayed for an unbounded amount of time. To deal with this, the xen event upcall handler checks to see if the EIP is within the critical section of the iret code, after events are (potentially) enabled up to the iret itself. If its within this range, it calls the iret critical section fixup, which adjusts the stack to deal with any unrestored registers, and then shifts the stack frame up to replace the previous invocation. Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
1115 lines
26 KiB
ArmAsm
1115 lines
26 KiB
ArmAsm
/*
|
|
* linux/arch/i386/entry.S
|
|
*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
*/
|
|
|
|
/*
|
|
* entry.S contains the system-call and fault low-level handling routines.
|
|
* This also contains the timer-interrupt handler, as well as all interrupts
|
|
* and faults that can result in a task-switch.
|
|
*
|
|
* NOTE: This code handles signal-recognition, which happens every time
|
|
* after a timer-interrupt and after each system call.
|
|
*
|
|
* I changed all the .align's to 4 (16 byte alignment), as that's faster
|
|
* on a 486.
|
|
*
|
|
* Stack layout in 'syscall_exit':
|
|
* ptrace needs to have all regs on the stack.
|
|
* if the order here is changed, it needs to be
|
|
* updated in fork.c:copy_process, signal.c:do_signal,
|
|
* ptrace.c and ptrace.h
|
|
*
|
|
* 0(%esp) - %ebx
|
|
* 4(%esp) - %ecx
|
|
* 8(%esp) - %edx
|
|
* C(%esp) - %esi
|
|
* 10(%esp) - %edi
|
|
* 14(%esp) - %ebp
|
|
* 18(%esp) - %eax
|
|
* 1C(%esp) - %ds
|
|
* 20(%esp) - %es
|
|
* 24(%esp) - %fs
|
|
* 28(%esp) - orig_eax
|
|
* 2C(%esp) - %eip
|
|
* 30(%esp) - %cs
|
|
* 34(%esp) - %eflags
|
|
* 38(%esp) - %oldesp
|
|
* 3C(%esp) - %oldss
|
|
*
|
|
* "current" is in register %ebx during any slow entries.
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
#include <asm/thread_info.h>
|
|
#include <asm/irqflags.h>
|
|
#include <asm/errno.h>
|
|
#include <asm/segment.h>
|
|
#include <asm/smp.h>
|
|
#include <asm/page.h>
|
|
#include <asm/desc.h>
|
|
#include <asm/percpu.h>
|
|
#include <asm/dwarf2.h>
|
|
#include "irq_vectors.h"
|
|
|
|
/*
|
|
* We use macros for low-level operations which need to be overridden
|
|
* for paravirtualization. The following will never clobber any registers:
|
|
* INTERRUPT_RETURN (aka. "iret")
|
|
* GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
|
|
* ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
|
|
*
|
|
* For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
|
|
* specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
|
|
* Allowing a register to be clobbered can shrink the paravirt replacement
|
|
* enough to patch inline, increasing performance.
|
|
*/
|
|
|
|
#define nr_syscalls ((syscall_table_size)/4)
|
|
|
|
CF_MASK = 0x00000001
|
|
TF_MASK = 0x00000100
|
|
IF_MASK = 0x00000200
|
|
DF_MASK = 0x00000400
|
|
NT_MASK = 0x00004000
|
|
VM_MASK = 0x00020000
|
|
|
|
#ifdef CONFIG_PREEMPT
|
|
#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
|
|
#else
|
|
#define preempt_stop(clobbers)
|
|
#define resume_kernel restore_nocheck
|
|
#endif
|
|
|
|
.macro TRACE_IRQS_IRET
|
|
#ifdef CONFIG_TRACE_IRQFLAGS
|
|
testl $IF_MASK,PT_EFLAGS(%esp) # interrupts off?
|
|
jz 1f
|
|
TRACE_IRQS_ON
|
|
1:
|
|
#endif
|
|
.endm
|
|
|
|
#ifdef CONFIG_VM86
|
|
#define resume_userspace_sig check_userspace
|
|
#else
|
|
#define resume_userspace_sig resume_userspace
|
|
#endif
|
|
|
|
#define SAVE_ALL \
|
|
cld; \
|
|
pushl %fs; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
/*CFI_REL_OFFSET fs, 0;*/\
|
|
pushl %es; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
/*CFI_REL_OFFSET es, 0;*/\
|
|
pushl %ds; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
/*CFI_REL_OFFSET ds, 0;*/\
|
|
pushl %eax; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
CFI_REL_OFFSET eax, 0;\
|
|
pushl %ebp; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
CFI_REL_OFFSET ebp, 0;\
|
|
pushl %edi; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
CFI_REL_OFFSET edi, 0;\
|
|
pushl %esi; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
CFI_REL_OFFSET esi, 0;\
|
|
pushl %edx; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
CFI_REL_OFFSET edx, 0;\
|
|
pushl %ecx; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
CFI_REL_OFFSET ecx, 0;\
|
|
pushl %ebx; \
|
|
CFI_ADJUST_CFA_OFFSET 4;\
|
|
CFI_REL_OFFSET ebx, 0;\
|
|
movl $(__USER_DS), %edx; \
|
|
movl %edx, %ds; \
|
|
movl %edx, %es; \
|
|
movl $(__KERNEL_PERCPU), %edx; \
|
|
movl %edx, %fs
|
|
|
|
#define RESTORE_INT_REGS \
|
|
popl %ebx; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
CFI_RESTORE ebx;\
|
|
popl %ecx; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
CFI_RESTORE ecx;\
|
|
popl %edx; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
CFI_RESTORE edx;\
|
|
popl %esi; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
CFI_RESTORE esi;\
|
|
popl %edi; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
CFI_RESTORE edi;\
|
|
popl %ebp; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
CFI_RESTORE ebp;\
|
|
popl %eax; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
CFI_RESTORE eax
|
|
|
|
#define RESTORE_REGS \
|
|
RESTORE_INT_REGS; \
|
|
1: popl %ds; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
/*CFI_RESTORE ds;*/\
|
|
2: popl %es; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
/*CFI_RESTORE es;*/\
|
|
3: popl %fs; \
|
|
CFI_ADJUST_CFA_OFFSET -4;\
|
|
/*CFI_RESTORE fs;*/\
|
|
.pushsection .fixup,"ax"; \
|
|
4: movl $0,(%esp); \
|
|
jmp 1b; \
|
|
5: movl $0,(%esp); \
|
|
jmp 2b; \
|
|
6: movl $0,(%esp); \
|
|
jmp 3b; \
|
|
.section __ex_table,"a";\
|
|
.align 4; \
|
|
.long 1b,4b; \
|
|
.long 2b,5b; \
|
|
.long 3b,6b; \
|
|
.popsection
|
|
|
|
#define RING0_INT_FRAME \
|
|
CFI_STARTPROC simple;\
|
|
CFI_SIGNAL_FRAME;\
|
|
CFI_DEF_CFA esp, 3*4;\
|
|
/*CFI_OFFSET cs, -2*4;*/\
|
|
CFI_OFFSET eip, -3*4
|
|
|
|
#define RING0_EC_FRAME \
|
|
CFI_STARTPROC simple;\
|
|
CFI_SIGNAL_FRAME;\
|
|
CFI_DEF_CFA esp, 4*4;\
|
|
/*CFI_OFFSET cs, -2*4;*/\
|
|
CFI_OFFSET eip, -3*4
|
|
|
|
#define RING0_PTREGS_FRAME \
|
|
CFI_STARTPROC simple;\
|
|
CFI_SIGNAL_FRAME;\
|
|
CFI_DEF_CFA esp, PT_OLDESP-PT_EBX;\
|
|
/*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/\
|
|
CFI_OFFSET eip, PT_EIP-PT_OLDESP;\
|
|
/*CFI_OFFSET es, PT_ES-PT_OLDESP;*/\
|
|
/*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/\
|
|
CFI_OFFSET eax, PT_EAX-PT_OLDESP;\
|
|
CFI_OFFSET ebp, PT_EBP-PT_OLDESP;\
|
|
CFI_OFFSET edi, PT_EDI-PT_OLDESP;\
|
|
CFI_OFFSET esi, PT_ESI-PT_OLDESP;\
|
|
CFI_OFFSET edx, PT_EDX-PT_OLDESP;\
|
|
CFI_OFFSET ecx, PT_ECX-PT_OLDESP;\
|
|
CFI_OFFSET ebx, PT_EBX-PT_OLDESP
|
|
|
|
ENTRY(ret_from_fork)
|
|
CFI_STARTPROC
|
|
pushl %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
call schedule_tail
|
|
GET_THREAD_INFO(%ebp)
|
|
popl %eax
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
pushl $0x0202 # Reset kernel eflags
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
popfl
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
jmp syscall_exit
|
|
CFI_ENDPROC
|
|
END(ret_from_fork)
|
|
|
|
/*
|
|
* Return to user mode is not as complex as all this looks,
|
|
* but we want the default path for a system call return to
|
|
* go as quickly as possible which is why some of this is
|
|
* less clear than it otherwise should be.
|
|
*/
|
|
|
|
# userspace resumption stub bypassing syscall exit tracing
|
|
ALIGN
|
|
RING0_PTREGS_FRAME
|
|
ret_from_exception:
|
|
preempt_stop(CLBR_ANY)
|
|
ret_from_intr:
|
|
GET_THREAD_INFO(%ebp)
|
|
check_userspace:
|
|
movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
|
|
movb PT_CS(%esp), %al
|
|
andl $(VM_MASK | SEGMENT_RPL_MASK), %eax
|
|
cmpl $USER_RPL, %eax
|
|
jb resume_kernel # not returning to v8086 or userspace
|
|
|
|
ENTRY(resume_userspace)
|
|
DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
|
|
# setting need_resched or sigpending
|
|
# between sampling and the iret
|
|
movl TI_flags(%ebp), %ecx
|
|
andl $_TIF_WORK_MASK, %ecx # is there any work to be done on
|
|
# int/exception return?
|
|
jne work_pending
|
|
jmp restore_all
|
|
END(ret_from_exception)
|
|
|
|
#ifdef CONFIG_PREEMPT
|
|
ENTRY(resume_kernel)
|
|
DISABLE_INTERRUPTS(CLBR_ANY)
|
|
cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ?
|
|
jnz restore_nocheck
|
|
need_resched:
|
|
movl TI_flags(%ebp), %ecx # need_resched set ?
|
|
testb $_TIF_NEED_RESCHED, %cl
|
|
jz restore_all
|
|
testl $IF_MASK,PT_EFLAGS(%esp) # interrupts off (exception path) ?
|
|
jz restore_all
|
|
call preempt_schedule_irq
|
|
jmp need_resched
|
|
END(resume_kernel)
|
|
#endif
|
|
CFI_ENDPROC
|
|
|
|
/* SYSENTER_RETURN points to after the "sysenter" instruction in
|
|
the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */
|
|
|
|
# sysenter call handler stub
|
|
ENTRY(sysenter_entry)
|
|
CFI_STARTPROC simple
|
|
CFI_SIGNAL_FRAME
|
|
CFI_DEF_CFA esp, 0
|
|
CFI_REGISTER esp, ebp
|
|
movl TSS_sysenter_esp0(%esp),%esp
|
|
sysenter_past_esp:
|
|
/*
|
|
* No need to follow this irqs on/off section: the syscall
|
|
* disabled irqs and here we enable it straight after entry:
|
|
*/
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
pushl $(__USER_DS)
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
/*CFI_REL_OFFSET ss, 0*/
|
|
pushl %ebp
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
CFI_REL_OFFSET esp, 0
|
|
pushfl
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl $(__USER_CS)
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
/*CFI_REL_OFFSET cs, 0*/
|
|
/*
|
|
* Push current_thread_info()->sysenter_return to the stack.
|
|
* A tiny bit of offset fixup is necessary - 4*4 means the 4 words
|
|
* pushed above; +8 corresponds to copy_thread's esp0 setting.
|
|
*/
|
|
pushl (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
CFI_REL_OFFSET eip, 0
|
|
|
|
/*
|
|
* Load the potential sixth argument from user stack.
|
|
* Careful about security.
|
|
*/
|
|
cmpl $__PAGE_OFFSET-3,%ebp
|
|
jae syscall_fault
|
|
1: movl (%ebp),%ebp
|
|
.section __ex_table,"a"
|
|
.align 4
|
|
.long 1b,syscall_fault
|
|
.previous
|
|
|
|
pushl %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
GET_THREAD_INFO(%ebp)
|
|
|
|
/* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */
|
|
testw $(_TIF_SYSCALL_EMU|_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
|
|
jnz syscall_trace_entry
|
|
cmpl $(nr_syscalls), %eax
|
|
jae syscall_badsys
|
|
call *sys_call_table(,%eax,4)
|
|
movl %eax,PT_EAX(%esp)
|
|
DISABLE_INTERRUPTS(CLBR_ANY)
|
|
TRACE_IRQS_OFF
|
|
movl TI_flags(%ebp), %ecx
|
|
testw $_TIF_ALLWORK_MASK, %cx
|
|
jne syscall_exit_work
|
|
/* if something modifies registers it must also disable sysexit */
|
|
movl PT_EIP(%esp), %edx
|
|
movl PT_OLDESP(%esp), %ecx
|
|
xorl %ebp,%ebp
|
|
TRACE_IRQS_ON
|
|
1: mov PT_FS(%esp), %fs
|
|
ENABLE_INTERRUPTS_SYSEXIT
|
|
CFI_ENDPROC
|
|
.pushsection .fixup,"ax"
|
|
2: movl $0,PT_FS(%esp)
|
|
jmp 1b
|
|
.section __ex_table,"a"
|
|
.align 4
|
|
.long 1b,2b
|
|
.popsection
|
|
ENDPROC(sysenter_entry)
|
|
|
|
# system call handler stub
|
|
ENTRY(system_call)
|
|
RING0_INT_FRAME # can't unwind into user space anyway
|
|
pushl %eax # save orig_eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
GET_THREAD_INFO(%ebp)
|
|
# system call tracing in operation / emulation
|
|
/* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */
|
|
testw $(_TIF_SYSCALL_EMU|_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
|
|
jnz syscall_trace_entry
|
|
cmpl $(nr_syscalls), %eax
|
|
jae syscall_badsys
|
|
syscall_call:
|
|
call *sys_call_table(,%eax,4)
|
|
movl %eax,PT_EAX(%esp) # store the return value
|
|
syscall_exit:
|
|
DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
|
|
# setting need_resched or sigpending
|
|
# between sampling and the iret
|
|
TRACE_IRQS_OFF
|
|
testl $TF_MASK,PT_EFLAGS(%esp) # If tracing set singlestep flag on exit
|
|
jz no_singlestep
|
|
orl $_TIF_SINGLESTEP,TI_flags(%ebp)
|
|
no_singlestep:
|
|
movl TI_flags(%ebp), %ecx
|
|
testw $_TIF_ALLWORK_MASK, %cx # current->work
|
|
jne syscall_exit_work
|
|
|
|
restore_all:
|
|
movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
|
|
# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
|
|
# are returning to the kernel.
|
|
# See comments in process.c:copy_thread() for details.
|
|
movb PT_OLDSS(%esp), %ah
|
|
movb PT_CS(%esp), %al
|
|
andl $(VM_MASK | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
|
|
cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
|
|
CFI_REMEMBER_STATE
|
|
je ldt_ss # returning to user-space with LDT SS
|
|
restore_nocheck:
|
|
TRACE_IRQS_IRET
|
|
restore_nocheck_notrace:
|
|
RESTORE_REGS
|
|
addl $4, %esp # skip orig_eax/error_code
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
1: INTERRUPT_RETURN
|
|
.section .fixup,"ax"
|
|
iret_exc:
|
|
TRACE_IRQS_ON
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
pushl $0 # no error code
|
|
pushl $do_iret_error
|
|
jmp error_code
|
|
.previous
|
|
.section __ex_table,"a"
|
|
.align 4
|
|
.long 1b,iret_exc
|
|
.previous
|
|
|
|
CFI_RESTORE_STATE
|
|
ldt_ss:
|
|
larl PT_OLDSS(%esp), %eax
|
|
jnz restore_nocheck
|
|
testl $0x00400000, %eax # returning to 32bit stack?
|
|
jnz restore_nocheck # allright, normal return
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
/*
|
|
* The kernel can't run on a non-flat stack if paravirt mode
|
|
* is active. Rather than try to fixup the high bits of
|
|
* ESP, bypass this code entirely. This may break DOSemu
|
|
* and/or Wine support in a paravirt VM, although the option
|
|
* is still available to implement the setting of the high
|
|
* 16-bits in the INTERRUPT_RETURN paravirt-op.
|
|
*/
|
|
cmpl $0, paravirt_ops+PARAVIRT_enabled
|
|
jne restore_nocheck
|
|
#endif
|
|
|
|
/* If returning to userspace with 16bit stack,
|
|
* try to fix the higher word of ESP, as the CPU
|
|
* won't restore it.
|
|
* This is an "official" bug of all the x86-compatible
|
|
* CPUs, which we can try to work around to make
|
|
* dosemu and wine happy. */
|
|
movl PT_OLDESP(%esp), %eax
|
|
movl %esp, %edx
|
|
call patch_espfix_desc
|
|
pushl $__ESPFIX_SS
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
DISABLE_INTERRUPTS(CLBR_EAX)
|
|
TRACE_IRQS_OFF
|
|
lss (%esp), %esp
|
|
CFI_ADJUST_CFA_OFFSET -8
|
|
jmp restore_nocheck
|
|
CFI_ENDPROC
|
|
ENDPROC(system_call)
|
|
|
|
# perform work that needs to be done immediately before resumption
|
|
ALIGN
|
|
RING0_PTREGS_FRAME # can't unwind into user space anyway
|
|
work_pending:
|
|
testb $_TIF_NEED_RESCHED, %cl
|
|
jz work_notifysig
|
|
work_resched:
|
|
call schedule
|
|
DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
|
|
# setting need_resched or sigpending
|
|
# between sampling and the iret
|
|
TRACE_IRQS_OFF
|
|
movl TI_flags(%ebp), %ecx
|
|
andl $_TIF_WORK_MASK, %ecx # is there any work to be done other
|
|
# than syscall tracing?
|
|
jz restore_all
|
|
testb $_TIF_NEED_RESCHED, %cl
|
|
jnz work_resched
|
|
|
|
work_notifysig: # deal with pending signals and
|
|
# notify-resume requests
|
|
#ifdef CONFIG_VM86
|
|
testl $VM_MASK, PT_EFLAGS(%esp)
|
|
movl %esp, %eax
|
|
jne work_notifysig_v86 # returning to kernel-space or
|
|
# vm86-space
|
|
xorl %edx, %edx
|
|
call do_notify_resume
|
|
jmp resume_userspace_sig
|
|
|
|
ALIGN
|
|
work_notifysig_v86:
|
|
pushl %ecx # save ti_flags for do_notify_resume
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
call save_v86_state # %eax contains pt_regs pointer
|
|
popl %ecx
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
movl %eax, %esp
|
|
#else
|
|
movl %esp, %eax
|
|
#endif
|
|
xorl %edx, %edx
|
|
call do_notify_resume
|
|
jmp resume_userspace_sig
|
|
END(work_pending)
|
|
|
|
# perform syscall exit tracing
|
|
ALIGN
|
|
syscall_trace_entry:
|
|
movl $-ENOSYS,PT_EAX(%esp)
|
|
movl %esp, %eax
|
|
xorl %edx,%edx
|
|
call do_syscall_trace
|
|
cmpl $0, %eax
|
|
jne resume_userspace # ret != 0 -> running under PTRACE_SYSEMU,
|
|
# so must skip actual syscall
|
|
movl PT_ORIG_EAX(%esp), %eax
|
|
cmpl $(nr_syscalls), %eax
|
|
jnae syscall_call
|
|
jmp syscall_exit
|
|
END(syscall_trace_entry)
|
|
|
|
# perform syscall exit tracing
|
|
ALIGN
|
|
syscall_exit_work:
|
|
testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl
|
|
jz work_pending
|
|
TRACE_IRQS_ON
|
|
ENABLE_INTERRUPTS(CLBR_ANY) # could let do_syscall_trace() call
|
|
# schedule() instead
|
|
movl %esp, %eax
|
|
movl $1, %edx
|
|
call do_syscall_trace
|
|
jmp resume_userspace
|
|
END(syscall_exit_work)
|
|
CFI_ENDPROC
|
|
|
|
RING0_INT_FRAME # can't unwind into user space anyway
|
|
syscall_fault:
|
|
pushl %eax # save orig_eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
GET_THREAD_INFO(%ebp)
|
|
movl $-EFAULT,PT_EAX(%esp)
|
|
jmp resume_userspace
|
|
END(syscall_fault)
|
|
|
|
syscall_badsys:
|
|
movl $-ENOSYS,PT_EAX(%esp)
|
|
jmp resume_userspace
|
|
END(syscall_badsys)
|
|
CFI_ENDPROC
|
|
|
|
#define FIXUP_ESPFIX_STACK \
|
|
/* since we are on a wrong stack, we cant make it a C code :( */ \
|
|
PER_CPU(gdt_page, %ebx); \
|
|
GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah); \
|
|
addl %esp, %eax; \
|
|
pushl $__KERNEL_DS; \
|
|
CFI_ADJUST_CFA_OFFSET 4; \
|
|
pushl %eax; \
|
|
CFI_ADJUST_CFA_OFFSET 4; \
|
|
lss (%esp), %esp; \
|
|
CFI_ADJUST_CFA_OFFSET -8;
|
|
#define UNWIND_ESPFIX_STACK \
|
|
movl %ss, %eax; \
|
|
/* see if on espfix stack */ \
|
|
cmpw $__ESPFIX_SS, %ax; \
|
|
jne 27f; \
|
|
movl $__KERNEL_DS, %eax; \
|
|
movl %eax, %ds; \
|
|
movl %eax, %es; \
|
|
/* switch to normal stack */ \
|
|
FIXUP_ESPFIX_STACK; \
|
|
27:;
|
|
|
|
/*
|
|
* Build the entry stubs and pointer table with
|
|
* some assembler magic.
|
|
*/
|
|
.data
|
|
ENTRY(interrupt)
|
|
.text
|
|
|
|
ENTRY(irq_entries_start)
|
|
RING0_INT_FRAME
|
|
vector=0
|
|
.rept NR_IRQS
|
|
ALIGN
|
|
.if vector
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
.endif
|
|
1: pushl $~(vector)
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp common_interrupt
|
|
.previous
|
|
.long 1b
|
|
.text
|
|
vector=vector+1
|
|
.endr
|
|
END(irq_entries_start)
|
|
|
|
.previous
|
|
END(interrupt)
|
|
.previous
|
|
|
|
/*
|
|
* the CPU automatically disables interrupts when executing an IRQ vector,
|
|
* so IRQ-flags tracing has to follow that:
|
|
*/
|
|
ALIGN
|
|
common_interrupt:
|
|
SAVE_ALL
|
|
TRACE_IRQS_OFF
|
|
movl %esp,%eax
|
|
call do_IRQ
|
|
jmp ret_from_intr
|
|
ENDPROC(common_interrupt)
|
|
CFI_ENDPROC
|
|
|
|
#define BUILD_INTERRUPT(name, nr) \
|
|
ENTRY(name) \
|
|
RING0_INT_FRAME; \
|
|
pushl $~(nr); \
|
|
CFI_ADJUST_CFA_OFFSET 4; \
|
|
SAVE_ALL; \
|
|
TRACE_IRQS_OFF \
|
|
movl %esp,%eax; \
|
|
call smp_##name; \
|
|
jmp ret_from_intr; \
|
|
CFI_ENDPROC; \
|
|
ENDPROC(name)
|
|
|
|
/* The include is where all of the SMP etc. interrupts come from */
|
|
#include "entry_arch.h"
|
|
|
|
KPROBE_ENTRY(page_fault)
|
|
RING0_EC_FRAME
|
|
pushl $do_page_fault
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
ALIGN
|
|
error_code:
|
|
/* the function address is in %fs's slot on the stack */
|
|
pushl %es
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
/*CFI_REL_OFFSET es, 0*/
|
|
pushl %ds
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
/*CFI_REL_OFFSET ds, 0*/
|
|
pushl %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
CFI_REL_OFFSET eax, 0
|
|
pushl %ebp
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
CFI_REL_OFFSET ebp, 0
|
|
pushl %edi
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
CFI_REL_OFFSET edi, 0
|
|
pushl %esi
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
CFI_REL_OFFSET esi, 0
|
|
pushl %edx
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
CFI_REL_OFFSET edx, 0
|
|
pushl %ecx
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
CFI_REL_OFFSET ecx, 0
|
|
pushl %ebx
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
CFI_REL_OFFSET ebx, 0
|
|
cld
|
|
pushl %fs
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
/*CFI_REL_OFFSET fs, 0*/
|
|
movl $(__KERNEL_PERCPU), %ecx
|
|
movl %ecx, %fs
|
|
UNWIND_ESPFIX_STACK
|
|
popl %ecx
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
/*CFI_REGISTER es, ecx*/
|
|
movl PT_FS(%esp), %edi # get the function address
|
|
movl PT_ORIG_EAX(%esp), %edx # get the error code
|
|
movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
|
|
mov %ecx, PT_FS(%esp)
|
|
/*CFI_REL_OFFSET fs, ES*/
|
|
movl $(__USER_DS), %ecx
|
|
movl %ecx, %ds
|
|
movl %ecx, %es
|
|
movl %esp,%eax # pt_regs pointer
|
|
call *%edi
|
|
jmp ret_from_exception
|
|
CFI_ENDPROC
|
|
KPROBE_END(page_fault)
|
|
|
|
ENTRY(coprocessor_error)
|
|
RING0_INT_FRAME
|
|
pushl $0
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl $do_coprocessor_error
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(coprocessor_error)
|
|
|
|
ENTRY(simd_coprocessor_error)
|
|
RING0_INT_FRAME
|
|
pushl $0
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl $do_simd_coprocessor_error
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(simd_coprocessor_error)
|
|
|
|
ENTRY(device_not_available)
|
|
RING0_INT_FRAME
|
|
pushl $-1 # mark this as an int
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
GET_CR0_INTO_EAX
|
|
testl $0x4, %eax # EM (math emulation bit)
|
|
jne device_not_available_emulate
|
|
preempt_stop(CLBR_ANY)
|
|
call math_state_restore
|
|
jmp ret_from_exception
|
|
device_not_available_emulate:
|
|
pushl $0 # temporary storage for ORIG_EIP
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
call math_emulate
|
|
addl $4, %esp
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
jmp ret_from_exception
|
|
CFI_ENDPROC
|
|
END(device_not_available)
|
|
|
|
/*
|
|
* Debug traps and NMI can happen at the one SYSENTER instruction
|
|
* that sets up the real kernel stack. Check here, since we can't
|
|
* allow the wrong stack to be used.
|
|
*
|
|
* "TSS_sysenter_esp0+12" is because the NMI/debug handler will have
|
|
* already pushed 3 words if it hits on the sysenter instruction:
|
|
* eflags, cs and eip.
|
|
*
|
|
* We just load the right stack, and push the three (known) values
|
|
* by hand onto the new stack - while updating the return eip past
|
|
* the instruction that would have done it for sysenter.
|
|
*/
|
|
#define FIX_STACK(offset, ok, label) \
|
|
cmpw $__KERNEL_CS,4(%esp); \
|
|
jne ok; \
|
|
label: \
|
|
movl TSS_sysenter_esp0+offset(%esp),%esp; \
|
|
CFI_DEF_CFA esp, 0; \
|
|
CFI_UNDEFINED eip; \
|
|
pushfl; \
|
|
CFI_ADJUST_CFA_OFFSET 4; \
|
|
pushl $__KERNEL_CS; \
|
|
CFI_ADJUST_CFA_OFFSET 4; \
|
|
pushl $sysenter_past_esp; \
|
|
CFI_ADJUST_CFA_OFFSET 4; \
|
|
CFI_REL_OFFSET eip, 0
|
|
|
|
KPROBE_ENTRY(debug)
|
|
RING0_INT_FRAME
|
|
cmpl $sysenter_entry,(%esp)
|
|
jne debug_stack_correct
|
|
FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn)
|
|
debug_stack_correct:
|
|
pushl $-1 # mark this as an int
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
xorl %edx,%edx # error code 0
|
|
movl %esp,%eax # pt_regs pointer
|
|
call do_debug
|
|
jmp ret_from_exception
|
|
CFI_ENDPROC
|
|
KPROBE_END(debug)
|
|
|
|
/*
|
|
* NMI is doubly nasty. It can happen _while_ we're handling
|
|
* a debug fault, and the debug fault hasn't yet been able to
|
|
* clear up the stack. So we first check whether we got an
|
|
* NMI on the sysenter entry path, but after that we need to
|
|
* check whether we got an NMI on the debug path where the debug
|
|
* fault happened on the sysenter path.
|
|
*/
|
|
KPROBE_ENTRY(nmi)
|
|
RING0_INT_FRAME
|
|
pushl %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
movl %ss, %eax
|
|
cmpw $__ESPFIX_SS, %ax
|
|
popl %eax
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
je nmi_espfix_stack
|
|
cmpl $sysenter_entry,(%esp)
|
|
je nmi_stack_fixup
|
|
pushl %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
movl %esp,%eax
|
|
/* Do not access memory above the end of our stack page,
|
|
* it might not exist.
|
|
*/
|
|
andl $(THREAD_SIZE-1),%eax
|
|
cmpl $(THREAD_SIZE-20),%eax
|
|
popl %eax
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
jae nmi_stack_correct
|
|
cmpl $sysenter_entry,12(%esp)
|
|
je nmi_debug_stack_check
|
|
nmi_stack_correct:
|
|
/* We have a RING0_INT_FRAME here */
|
|
pushl %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
xorl %edx,%edx # zero error code
|
|
movl %esp,%eax # pt_regs pointer
|
|
call do_nmi
|
|
jmp restore_nocheck_notrace
|
|
CFI_ENDPROC
|
|
|
|
nmi_stack_fixup:
|
|
RING0_INT_FRAME
|
|
FIX_STACK(12,nmi_stack_correct, 1)
|
|
jmp nmi_stack_correct
|
|
|
|
nmi_debug_stack_check:
|
|
/* We have a RING0_INT_FRAME here */
|
|
cmpw $__KERNEL_CS,16(%esp)
|
|
jne nmi_stack_correct
|
|
cmpl $debug,(%esp)
|
|
jb nmi_stack_correct
|
|
cmpl $debug_esp_fix_insn,(%esp)
|
|
ja nmi_stack_correct
|
|
FIX_STACK(24,nmi_stack_correct, 1)
|
|
jmp nmi_stack_correct
|
|
|
|
nmi_espfix_stack:
|
|
/* We have a RING0_INT_FRAME here.
|
|
*
|
|
* create the pointer to lss back
|
|
*/
|
|
pushl %ss
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl %esp
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
addw $4, (%esp)
|
|
/* copy the iret frame of 12 bytes */
|
|
.rept 3
|
|
pushl 16(%esp)
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
.endr
|
|
pushl %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
FIXUP_ESPFIX_STACK # %eax == %esp
|
|
xorl %edx,%edx # zero error code
|
|
call do_nmi
|
|
RESTORE_REGS
|
|
lss 12+4(%esp), %esp # back to espfix stack
|
|
CFI_ADJUST_CFA_OFFSET -24
|
|
1: INTERRUPT_RETURN
|
|
CFI_ENDPROC
|
|
.section __ex_table,"a"
|
|
.align 4
|
|
.long 1b,iret_exc
|
|
.previous
|
|
KPROBE_END(nmi)
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
ENTRY(native_iret)
|
|
1: iret
|
|
.section __ex_table,"a"
|
|
.align 4
|
|
.long 1b,iret_exc
|
|
.previous
|
|
END(native_iret)
|
|
|
|
ENTRY(native_irq_enable_sysexit)
|
|
sti
|
|
sysexit
|
|
END(native_irq_enable_sysexit)
|
|
#endif
|
|
|
|
KPROBE_ENTRY(int3)
|
|
RING0_INT_FRAME
|
|
pushl $-1 # mark this as an int
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
xorl %edx,%edx # zero error code
|
|
movl %esp,%eax # pt_regs pointer
|
|
call do_int3
|
|
jmp ret_from_exception
|
|
CFI_ENDPROC
|
|
KPROBE_END(int3)
|
|
|
|
ENTRY(overflow)
|
|
RING0_INT_FRAME
|
|
pushl $0
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl $do_overflow
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(overflow)
|
|
|
|
ENTRY(bounds)
|
|
RING0_INT_FRAME
|
|
pushl $0
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl $do_bounds
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(bounds)
|
|
|
|
ENTRY(invalid_op)
|
|
RING0_INT_FRAME
|
|
pushl $0
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl $do_invalid_op
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(invalid_op)
|
|
|
|
ENTRY(coprocessor_segment_overrun)
|
|
RING0_INT_FRAME
|
|
pushl $0
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl $do_coprocessor_segment_overrun
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(coprocessor_segment_overrun)
|
|
|
|
ENTRY(invalid_TSS)
|
|
RING0_EC_FRAME
|
|
pushl $do_invalid_TSS
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(invalid_TSS)
|
|
|
|
ENTRY(segment_not_present)
|
|
RING0_EC_FRAME
|
|
pushl $do_segment_not_present
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(segment_not_present)
|
|
|
|
ENTRY(stack_segment)
|
|
RING0_EC_FRAME
|
|
pushl $do_stack_segment
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(stack_segment)
|
|
|
|
KPROBE_ENTRY(general_protection)
|
|
RING0_EC_FRAME
|
|
pushl $do_general_protection
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
KPROBE_END(general_protection)
|
|
|
|
ENTRY(alignment_check)
|
|
RING0_EC_FRAME
|
|
pushl $do_alignment_check
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(alignment_check)
|
|
|
|
ENTRY(divide_error)
|
|
RING0_INT_FRAME
|
|
pushl $0 # no error code
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl $do_divide_error
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(divide_error)
|
|
|
|
#ifdef CONFIG_X86_MCE
|
|
ENTRY(machine_check)
|
|
RING0_INT_FRAME
|
|
pushl $0
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl machine_check_vector
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(machine_check)
|
|
#endif
|
|
|
|
ENTRY(spurious_interrupt_bug)
|
|
RING0_INT_FRAME
|
|
pushl $0
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
pushl $do_spurious_interrupt_bug
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
jmp error_code
|
|
CFI_ENDPROC
|
|
END(spurious_interrupt_bug)
|
|
|
|
ENTRY(kernel_thread_helper)
|
|
pushl $0 # fake return address for unwinder
|
|
CFI_STARTPROC
|
|
movl %edx,%eax
|
|
push %edx
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
call *%ebx
|
|
push %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
call do_exit
|
|
CFI_ENDPROC
|
|
ENDPROC(kernel_thread_helper)
|
|
|
|
#ifdef CONFIG_XEN
|
|
ENTRY(xen_hypervisor_callback)
|
|
CFI_STARTPROC
|
|
pushl $0
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
TRACE_IRQS_OFF
|
|
|
|
/* Check to see if we got the event in the critical
|
|
region in xen_iret_direct, after we've reenabled
|
|
events and checked for pending events. This simulates
|
|
iret instruction's behaviour where it delivers a
|
|
pending interrupt when enabling interrupts. */
|
|
movl PT_EIP(%esp),%eax
|
|
cmpl $xen_iret_start_crit,%eax
|
|
jb 1f
|
|
cmpl $xen_iret_end_crit,%eax
|
|
jae 1f
|
|
|
|
call xen_iret_crit_fixup
|
|
|
|
1: mov %esp, %eax
|
|
call xen_evtchn_do_upcall
|
|
jmp ret_from_intr
|
|
CFI_ENDPROC
|
|
ENDPROC(xen_hypervisor_callback)
|
|
|
|
# Hypervisor uses this for application faults while it executes.
|
|
# We get here for two reasons:
|
|
# 1. Fault while reloading DS, ES, FS or GS
|
|
# 2. Fault while executing IRET
|
|
# Category 1 we fix up by reattempting the load, and zeroing the segment
|
|
# register if the load fails.
|
|
# Category 2 we fix up by jumping to do_iret_error. We cannot use the
|
|
# normal Linux return path in this case because if we use the IRET hypercall
|
|
# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
|
|
# We distinguish between categories by maintaining a status value in EAX.
|
|
ENTRY(xen_failsafe_callback)
|
|
CFI_STARTPROC
|
|
pushl %eax
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
movl $1,%eax
|
|
1: mov 4(%esp),%ds
|
|
2: mov 8(%esp),%es
|
|
3: mov 12(%esp),%fs
|
|
4: mov 16(%esp),%gs
|
|
testl %eax,%eax
|
|
popl %eax
|
|
CFI_ADJUST_CFA_OFFSET -4
|
|
lea 16(%esp),%esp
|
|
CFI_ADJUST_CFA_OFFSET -16
|
|
jz 5f
|
|
addl $16,%esp
|
|
jmp iret_exc # EAX != 0 => Category 2 (Bad IRET)
|
|
5: pushl $0 # EAX == 0 => Category 1 (Bad segment)
|
|
CFI_ADJUST_CFA_OFFSET 4
|
|
SAVE_ALL
|
|
jmp ret_from_exception
|
|
CFI_ENDPROC
|
|
|
|
.section .fixup,"ax"
|
|
6: xorl %eax,%eax
|
|
movl %eax,4(%esp)
|
|
jmp 1b
|
|
7: xorl %eax,%eax
|
|
movl %eax,8(%esp)
|
|
jmp 2b
|
|
8: xorl %eax,%eax
|
|
movl %eax,12(%esp)
|
|
jmp 3b
|
|
9: xorl %eax,%eax
|
|
movl %eax,16(%esp)
|
|
jmp 4b
|
|
.previous
|
|
.section __ex_table,"a"
|
|
.align 4
|
|
.long 1b,6b
|
|
.long 2b,7b
|
|
.long 3b,8b
|
|
.long 4b,9b
|
|
.previous
|
|
ENDPROC(xen_failsafe_callback)
|
|
|
|
#endif /* CONFIG_XEN */
|
|
|
|
.section .rodata,"a"
|
|
#include "syscall_table.S"
|
|
|
|
syscall_table_size=(.-sys_call_table)
|