linux/arch/x86/kernel/entry_32.S
Alexander van Heukelum 2e04bc7656 i386: fix return to 16-bit stack from NMI handler
Returning to a task with a 16-bit stack requires special care: the iret
instruction does not restore the high word of esp in that case. The
espfix code fixes this, but currently is not invoked on NMIs. This means
that a running task gets the upper word of esp clobbered due intervening
NMIs. To reproduce, compile and run the following program with the nmi
watchdog enabled (nmi_watchdog=2 on the command line). Using gdb you can
see that the high bits of esp contain garbage, while the low bits are
still correct.

This patch puts the espfix code back into the NMI code path.

The patch is slightly complicated due to the irqtrace infrastructure not
being NMI-safe. The NMI return path cannot call TRACE_IRQS_IRET.
Otherwise, the tail of the normal iret-code is correct for the nmi code
path too. To be able to share this code-path, the TRACE_IRQS_IRET was
move up a bit. The espfix code exists after the TRACE_IRQS_IRET, but
this code explicitly disables interrupts. This short interrupts-off
section is now not traced anymore. The return-to-kernel path now always
includes the preliminary test to decide if the espfix code should be
called. This is never the case, but doing it this way keeps the patch as
simple as possible and the few extra instructions should not affect
timing in any significant way.

 #define _GNU_SOURCE
 #include <stdio.h>
 #include <sys/types.h>
 #include <sys/mman.h>
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <asm/ldt.h>

int modify_ldt(int func, void *ptr, unsigned long bytecount)
{
        return syscall(SYS_modify_ldt, func, ptr, bytecount);
}

/* this is assumed to be usable */
 #define SEGBASEADDR 0x10000
 #define SEGLIMIT 0x20000

/* 16-bit segment */
struct user_desc desc = {
        .entry_number = 0,
        .base_addr = SEGBASEADDR,
        .limit = SEGLIMIT,
        .seg_32bit = 0,
        .contents = 0, /* ??? */
        .read_exec_only = 0,
        .limit_in_pages = 0,
        .seg_not_present = 0,
        .useable = 1
};

int main(void)
{
        setvbuf(stdout, NULL, _IONBF, 0);

        /* map a 64 kb segment */
        char *pointer = mmap((void *)SEGBASEADDR, SEGLIMIT+1,
                        PROT_EXEC|PROT_READ|PROT_WRITE,
                        MAP_SHARED|MAP_ANONYMOUS, -1, 0);
        if (pointer == NULL) {
                printf("could not map space\n");
                return 0;
        }

        /* write ldt, new mode */
        int err = modify_ldt(0x11, &desc, sizeof(desc));
        if (err) {
                printf("error modifying ldt: %i\n", err);
                return 0;
        }

        for (int i=0; i<1000; i++) {
        asm volatile (
                "pusha\n\t"
                "mov %ss, %eax\n\t" /* preserve ss:esp */
                "mov %esp, %ebp\n\t"
                "push $7\n\t" /* index 0, ldt, user mode */
                "push $65536-4096\n\t" /* esp */
                "lss (%esp), %esp\n\t" /* switch to new stack */
                "push %eax\n\t" /* save old ss:esp on new stack */
                "push %ebp\n\t"
                "add $17*65536, %esp\n\t" /* set high bits */
                "mov %esp, %edx\n\t"

                "mov $10000000, %ecx\n\t" /* wait... */
                "1: loop 1b\n\t" /* ... a bit */

                "cmp %esp, %edx\n\t"
                "je 1f\n\t"
                "ud2\n\t" /* esp changed inexplicably! */
                "1:\n\t"
                "sub $17*65536, %esp\n\t" /* restore high bits */
                "lss (%esp), %esp\n\t" /* restore old ss:esp */
                "popa\n\t");

                printf("\rx%ix", i);
        }

        return 0;
}

Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Acked-by: Stas Sergeev <stsp@aknet.ru>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-17 21:35:09 -07:00

1406 lines
31 KiB
ArmAsm

/*
*
* 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) - %gs saved iff !CONFIG_X86_32_LAZY_GS
* 2C(%esp) - orig_eax
* 30(%esp) - %eip
* 34(%esp) - %cs
* 38(%esp) - %eflags
* 3C(%esp) - %oldesp
* 40(%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_types.h>
#include <asm/desc.h>
#include <asm/percpu.h>
#include <asm/dwarf2.h>
#include <asm/processor-flags.h>
#include <asm/ftrace.h>
#include <asm/irq_vectors.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
#define __AUDIT_ARCH_LE 0x40000000
#ifndef CONFIG_AUDITSYSCALL
#define sysenter_audit syscall_trace_entry
#define sysexit_audit syscall_exit_work
#endif
/*
* 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)
#ifdef CONFIG_PREEMPT
#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
#else
#define preempt_stop(clobbers)
#define resume_kernel restore_all
#endif
.macro TRACE_IRQS_IRET
#ifdef CONFIG_TRACE_IRQFLAGS
testl $X86_EFLAGS_IF,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
/*
* User gs save/restore
*
* %gs is used for userland TLS and kernel only uses it for stack
* canary which is required to be at %gs:20 by gcc. Read the comment
* at the top of stackprotector.h for more info.
*
* Local labels 98 and 99 are used.
*/
#ifdef CONFIG_X86_32_LAZY_GS
/* unfortunately push/pop can't be no-op */
.macro PUSH_GS
pushl $0
CFI_ADJUST_CFA_OFFSET 4
.endm
.macro POP_GS pop=0
addl $(4 + \pop), %esp
CFI_ADJUST_CFA_OFFSET -(4 + \pop)
.endm
.macro POP_GS_EX
.endm
/* all the rest are no-op */
.macro PTGS_TO_GS
.endm
.macro PTGS_TO_GS_EX
.endm
.macro GS_TO_REG reg
.endm
.macro REG_TO_PTGS reg
.endm
.macro SET_KERNEL_GS reg
.endm
#else /* CONFIG_X86_32_LAZY_GS */
.macro PUSH_GS
pushl %gs
CFI_ADJUST_CFA_OFFSET 4
/*CFI_REL_OFFSET gs, 0*/
.endm
.macro POP_GS pop=0
98: popl %gs
CFI_ADJUST_CFA_OFFSET -4
/*CFI_RESTORE gs*/
.if \pop <> 0
add $\pop, %esp
CFI_ADJUST_CFA_OFFSET -\pop
.endif
.endm
.macro POP_GS_EX
.pushsection .fixup, "ax"
99: movl $0, (%esp)
jmp 98b
.section __ex_table, "a"
.align 4
.long 98b, 99b
.popsection
.endm
.macro PTGS_TO_GS
98: mov PT_GS(%esp), %gs
.endm
.macro PTGS_TO_GS_EX
.pushsection .fixup, "ax"
99: movl $0, PT_GS(%esp)
jmp 98b
.section __ex_table, "a"
.align 4
.long 98b, 99b
.popsection
.endm
.macro GS_TO_REG reg
movl %gs, \reg
/*CFI_REGISTER gs, \reg*/
.endm
.macro REG_TO_PTGS reg
movl \reg, PT_GS(%esp)
/*CFI_REL_OFFSET gs, PT_GS*/
.endm
.macro SET_KERNEL_GS reg
movl $(__KERNEL_STACK_CANARY), \reg
movl \reg, %gs
.endm
#endif /* CONFIG_X86_32_LAZY_GS */
.macro SAVE_ALL
cld
PUSH_GS
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
SET_KERNEL_GS %edx
.endm
.macro 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
.endm
.macro RESTORE_REGS pop=0
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;*/
POP_GS \pop
.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
POP_GS_EX
.endm
.macro 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
.endm
.macro 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
.endm
.macro 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
.endm
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 $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
cmpl $USER_RPL, %eax
jb resume_kernel # not returning to v8086 or userspace
ENTRY(resume_userspace)
LOCKDEP_SYS_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
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_all
need_resched:
movl TI_flags(%ebp), %ecx # need_resched set ?
testb $_TIF_NEED_RESCHED, %cl
jz restore_all
testl $X86_EFLAGS_IF,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(ia32_sysenter_target)
CFI_STARTPROC simple
CFI_SIGNAL_FRAME
CFI_DEF_CFA esp, 0
CFI_REGISTER esp, ebp
movl TSS_sysenter_sp0(%esp),%esp
sysenter_past_esp:
/*
* Interrupts are disabled here, but we can't trace it until
* enough kernel state to call TRACE_IRQS_OFF can be called - but
* we immediately enable interrupts at that point anyway.
*/
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
orl $X86_EFLAGS_IF, (%esp)
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
pushl %eax
CFI_ADJUST_CFA_OFFSET 4
SAVE_ALL
ENABLE_INTERRUPTS(CLBR_NONE)
/*
* Load the potential sixth argument from user stack.
* Careful about security.
*/
cmpl $__PAGE_OFFSET-3,%ebp
jae syscall_fault
1: movl (%ebp),%ebp
movl %ebp,PT_EBP(%esp)
.section __ex_table,"a"
.align 4
.long 1b,syscall_fault
.previous
GET_THREAD_INFO(%ebp)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
jnz sysenter_audit
sysenter_do_call:
cmpl $(nr_syscalls), %eax
jae syscall_badsys
call *sys_call_table(,%eax,4)
movl %eax,PT_EAX(%esp)
LOCKDEP_SYS_EXIT
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
testl $_TIF_ALLWORK_MASK, %ecx
jne sysexit_audit
sysenter_exit:
/* 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
PTGS_TO_GS
ENABLE_INTERRUPTS_SYSEXIT
#ifdef CONFIG_AUDITSYSCALL
sysenter_audit:
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
jnz syscall_trace_entry
addl $4,%esp
CFI_ADJUST_CFA_OFFSET -4
/* %esi already in 8(%esp) 6th arg: 4th syscall arg */
/* %edx already in 4(%esp) 5th arg: 3rd syscall arg */
/* %ecx already in 0(%esp) 4th arg: 2nd syscall arg */
movl %ebx,%ecx /* 3rd arg: 1st syscall arg */
movl %eax,%edx /* 2nd arg: syscall number */
movl $AUDIT_ARCH_I386,%eax /* 1st arg: audit arch */
call audit_syscall_entry
pushl %ebx
CFI_ADJUST_CFA_OFFSET 4
movl PT_EAX(%esp),%eax /* reload syscall number */
jmp sysenter_do_call
sysexit_audit:
testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
jne syscall_exit_work
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_ANY)
movl %eax,%edx /* second arg, syscall return value */
cmpl $0,%eax /* is it < 0? */
setl %al /* 1 if so, 0 if not */
movzbl %al,%eax /* zero-extend that */
inc %eax /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
call audit_syscall_exit
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
jne syscall_exit_work
movl PT_EAX(%esp),%eax /* reload syscall return value */
jmp sysenter_exit
#endif
CFI_ENDPROC
.pushsection .fixup,"ax"
2: movl $0,PT_FS(%esp)
jmp 1b
.section __ex_table,"a"
.align 4
.long 1b,2b
.popsection
PTGS_TO_GS_EX
ENDPROC(ia32_sysenter_target)
# 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
testl $_TIF_WORK_SYSCALL_ENTRY,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:
LOCKDEP_SYS_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
movl TI_flags(%ebp), %ecx
testl $_TIF_ALLWORK_MASK, %ecx # current->work
jne syscall_exit_work
restore_all:
TRACE_IRQS_IRET
restore_all_notrace:
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 $(X86_EFLAGS_VM | (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:
RESTORE_REGS 4 # skip orig_eax/error_code
CFI_ADJUST_CFA_OFFSET -4
irq_return:
INTERRUPT_RETURN
.section .fixup,"ax"
ENTRY(iret_exc)
pushl $0 # no error code
pushl $do_iret_error
jmp error_code
.previous
.section __ex_table,"a"
.align 4
.long irq_return,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, pv_info+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, but do not irqtrace this section: we
* will soon execute iret and the tracer was already set to
* the irqstate after the iret */
DISABLE_INTERRUPTS(CLBR_EAX)
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
LOCKDEP_SYS_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
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 $X86_EFLAGS_VM, 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
call syscall_trace_enter
/* What it returned is what we'll actually use. */
cmpl $(nr_syscalls), %eax
jnae syscall_call
jmp syscall_exit
END(syscall_trace_entry)
# perform syscall exit tracing
ALIGN
syscall_exit_work:
testl $_TIF_WORK_SYSCALL_EXIT, %ecx
jz work_pending
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call
# schedule() instead
movl %esp, %eax
call syscall_trace_leave
jmp resume_userspace
END(syscall_exit_work)
CFI_ENDPROC
RING0_INT_FRAME # can't unwind into user space anyway
syscall_fault:
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
/*
* System calls that need a pt_regs pointer.
*/
#define PTREGSCALL(name) \
ALIGN; \
ptregs_##name: \
leal 4(%esp),%eax; \
jmp sys_##name;
PTREGSCALL(iopl)
PTREGSCALL(fork)
PTREGSCALL(clone)
PTREGSCALL(vfork)
PTREGSCALL(execve)
PTREGSCALL(sigaltstack)
PTREGSCALL(sigreturn)
PTREGSCALL(rt_sigreturn)
PTREGSCALL(vm86)
PTREGSCALL(vm86old)
.macro 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
.endm
.macro 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:
.endm
/*
* Build the entry stubs and pointer table with some assembler magic.
* We pack 7 stubs into a single 32-byte chunk, which will fit in a
* single cache line on all modern x86 implementations.
*/
.section .init.rodata,"a"
ENTRY(interrupt)
.text
.p2align 5
.p2align CONFIG_X86_L1_CACHE_SHIFT
ENTRY(irq_entries_start)
RING0_INT_FRAME
vector=FIRST_EXTERNAL_VECTOR
.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
.balign 32
.rept 7
.if vector < NR_VECTORS
.if vector <> FIRST_EXTERNAL_VECTOR
CFI_ADJUST_CFA_OFFSET -4
.endif
1: pushl $(~vector+0x80) /* Note: always in signed byte range */
CFI_ADJUST_CFA_OFFSET 4
.if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
jmp 2f
.endif
.previous
.long 1b
.text
vector=vector+1
.endif
.endr
2: jmp common_interrupt
.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:
*/
.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */
SAVE_ALL
TRACE_IRQS_OFF
movl %esp,%eax
call do_IRQ
jmp ret_from_intr
ENDPROC(common_interrupt)
CFI_ENDPROC
#define BUILD_INTERRUPT3(name, nr, fn) \
ENTRY(name) \
RING0_INT_FRAME; \
pushl $~(nr); \
CFI_ADJUST_CFA_OFFSET 4; \
SAVE_ALL; \
TRACE_IRQS_OFF \
movl %esp,%eax; \
call fn; \
jmp ret_from_intr; \
CFI_ENDPROC; \
ENDPROC(name)
#define BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(name, nr, smp_##name)
/* The include is where all of the SMP etc. interrupts come from */
#include <asm/entry_arch.h>
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
pushl $do_device_not_available
CFI_ADJUST_CFA_OFFSET 4
jmp error_code
CFI_ENDPROC
END(device_not_available)
#ifdef CONFIG_PARAVIRT
ENTRY(native_iret)
iret
.section __ex_table,"a"
.align 4
.long native_iret, iret_exc
.previous
END(native_iret)
ENTRY(native_irq_enable_sysexit)
sti
sysexit
END(native_irq_enable_sysexit)
#endif
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)
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
ud2 # padding for call trace
CFI_ENDPROC
ENDPROC(kernel_thread_helper)
#ifdef CONFIG_XEN
/* Xen doesn't set %esp to be precisely what the normal sysenter
entrypoint expects, so fix it up before using the normal path. */
ENTRY(xen_sysenter_target)
RING0_INT_FRAME
addl $5*4, %esp /* remove xen-provided frame */
CFI_ADJUST_CFA_OFFSET -5*4
jmp sysenter_past_esp
CFI_ENDPROC
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
jmp xen_iret_crit_fixup
ENTRY(xen_do_upcall)
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 */
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(mcount)
ret
END(mcount)
ENTRY(ftrace_caller)
cmpl $0, function_trace_stop
jne ftrace_stub
pushl %eax
pushl %ecx
pushl %edx
movl 0xc(%esp), %eax
movl 0x4(%ebp), %edx
subl $MCOUNT_INSN_SIZE, %eax
.globl ftrace_call
ftrace_call:
call ftrace_stub
popl %edx
popl %ecx
popl %eax
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.globl ftrace_graph_call
ftrace_graph_call:
jmp ftrace_stub
#endif
.globl ftrace_stub
ftrace_stub:
ret
END(ftrace_caller)
#else /* ! CONFIG_DYNAMIC_FTRACE */
ENTRY(mcount)
cmpl $0, function_trace_stop
jne ftrace_stub
cmpl $ftrace_stub, ftrace_trace_function
jnz trace
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
cmpl $ftrace_stub, ftrace_graph_return
jnz ftrace_graph_caller
cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
jnz ftrace_graph_caller
#endif
.globl ftrace_stub
ftrace_stub:
ret
/* taken from glibc */
trace:
pushl %eax
pushl %ecx
pushl %edx
movl 0xc(%esp), %eax
movl 0x4(%ebp), %edx
subl $MCOUNT_INSN_SIZE, %eax
call *ftrace_trace_function
popl %edx
popl %ecx
popl %eax
jmp ftrace_stub
END(mcount)
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
cmpl $0, function_trace_stop
jne ftrace_stub
pushl %eax
pushl %ecx
pushl %edx
movl 0xc(%esp), %edx
lea 0x4(%ebp), %eax
subl $MCOUNT_INSN_SIZE, %edx
call prepare_ftrace_return
popl %edx
popl %ecx
popl %eax
ret
END(ftrace_graph_caller)
.globl return_to_handler
return_to_handler:
pushl $0
pushl %eax
pushl %ecx
pushl %edx
call ftrace_return_to_handler
movl %eax, 0xc(%esp)
popl %edx
popl %ecx
popl %eax
ret
#endif
.section .rodata,"a"
#include "syscall_table_32.S"
syscall_table_size=(.-sys_call_table)
/*
* Some functions should be protected against kprobes
*/
.pushsection .kprobes.text, "ax"
ENTRY(page_fault)
RING0_EC_FRAME
pushl $do_page_fault
CFI_ADJUST_CFA_OFFSET 4
ALIGN
error_code:
/* the function address is in %gs's slot on the stack */
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
cld
movl $(__KERNEL_PERCPU), %ecx
movl %ecx, %fs
UNWIND_ESPFIX_STACK
GS_TO_REG %ecx
movl PT_GS(%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
REG_TO_PTGS %ecx
SET_KERNEL_GS %ecx
movl $(__USER_DS), %ecx
movl %ecx, %ds
movl %ecx, %es
TRACE_IRQS_OFF
movl %esp,%eax # pt_regs pointer
call *%edi
jmp ret_from_exception
CFI_ENDPROC
END(page_fault)
/*
* 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_sp0+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.
*/
.macro FIX_STACK offset ok label
cmpw $__KERNEL_CS, 4(%esp)
jne \ok
\label:
movl TSS_sysenter_sp0 + \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
.endm
ENTRY(debug)
RING0_INT_FRAME
cmpl $ia32_sysenter_target,(%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
TRACE_IRQS_OFF
xorl %edx,%edx # error code 0
movl %esp,%eax # pt_regs pointer
call do_debug
jmp ret_from_exception
CFI_ENDPROC
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.
*/
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 $ia32_sysenter_target,(%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 $ia32_sysenter_target,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_all_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
addl $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
jmp irq_return
CFI_ENDPROC
END(nmi)
ENTRY(int3)
RING0_INT_FRAME
pushl $-1 # mark this as an int
CFI_ADJUST_CFA_OFFSET 4
SAVE_ALL
TRACE_IRQS_OFF
xorl %edx,%edx # zero error code
movl %esp,%eax # pt_regs pointer
call do_int3
jmp ret_from_exception
CFI_ENDPROC
END(int3)
ENTRY(general_protection)
RING0_EC_FRAME
pushl $do_general_protection
CFI_ADJUST_CFA_OFFSET 4
jmp error_code
CFI_ENDPROC
END(general_protection)
/*
* End of kprobes section
*/
.popsection