X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=arch%2Fi386%2Fkernel%2Fentry-xen.S;fp=arch%2Fi386%2Fkernel%2Fentry-xen.S;h=1f3c30ae116572790ea9993c6eee4dfb25bd9945;hb=1db395853d4f30d6120458bd279ede1f882a8525;hp=0000000000000000000000000000000000000000;hpb=34a75f0025b9cf803b6a88db032e6ad6950c9313;p=linux-2.6.git diff --git a/arch/i386/kernel/entry-xen.S b/arch/i386/kernel/entry-xen.S new file mode 100644 index 000000000..1f3c30ae1 --- /dev/null +++ b/arch/i386/kernel/entry-xen.S @@ -0,0 +1,907 @@ +/* + * 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 'ret_from_system_call': + * 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) - orig_eax + * 28(%esp) - %eip + * 2C(%esp) - %cs + * 30(%esp) - %eflags + * 34(%esp) - %oldesp + * 38(%esp) - %oldss + * + * "current" is in register %ebx during any slow entries. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "irq_vectors.h" +#include + +#define nr_syscalls ((syscall_table_size)/4) + +EBX = 0x00 +ECX = 0x04 +EDX = 0x08 +ESI = 0x0C +EDI = 0x10 +EBP = 0x14 +EAX = 0x18 +DS = 0x1C +ES = 0x20 +ORIG_EAX = 0x24 +EIP = 0x28 +CS = 0x2C +EFLAGS = 0x30 +OLDESP = 0x34 +OLDSS = 0x38 + +CF_MASK = 0x00000001 +TF_MASK = 0x00000100 +IF_MASK = 0x00000200 +DF_MASK = 0x00000400 +NT_MASK = 0x00004000 +VM_MASK = 0x00020000 +/* Pseudo-eflags. */ +NMI_MASK = 0x80000000 + +#ifndef CONFIG_XEN +#define DISABLE_INTERRUPTS cli +#define ENABLE_INTERRUPTS sti +#else +/* Offsets into shared_info_t. */ +#define evtchn_upcall_pending /* 0 */ +#define evtchn_upcall_mask 1 + +#define sizeof_vcpu_shift 6 + +#ifdef CONFIG_SMP +#define GET_VCPU_INFO movl TI_cpu(%ebp),%esi ; \ + shl $sizeof_vcpu_shift,%esi ; \ + addl HYPERVISOR_shared_info,%esi +#else +#define GET_VCPU_INFO movl HYPERVISOR_shared_info,%esi +#endif + +#define __DISABLE_INTERRUPTS movb $1,evtchn_upcall_mask(%esi) +#define __ENABLE_INTERRUPTS movb $0,evtchn_upcall_mask(%esi) +#define DISABLE_INTERRUPTS GET_VCPU_INFO ; \ + __DISABLE_INTERRUPTS +#define ENABLE_INTERRUPTS GET_VCPU_INFO ; \ + __ENABLE_INTERRUPTS +#define __TEST_PENDING testb $0xFF,evtchn_upcall_pending(%esi) +#endif + +#ifdef CONFIG_PREEMPT +#define preempt_stop cli +#else +#define preempt_stop +#define resume_kernel restore_nocheck +#endif + +#define SAVE_ALL \ + cld; \ + pushl %es; \ + pushl %ds; \ + pushl %eax; \ + pushl %ebp; \ + pushl %edi; \ + pushl %esi; \ + pushl %edx; \ + pushl %ecx; \ + pushl %ebx; \ + movl $(__USER_DS), %edx; \ + movl %edx, %ds; \ + movl %edx, %es; + +#define RESTORE_INT_REGS \ + popl %ebx; \ + popl %ecx; \ + popl %edx; \ + popl %esi; \ + popl %edi; \ + popl %ebp; \ + popl %eax + +#define RESTORE_REGS \ + RESTORE_INT_REGS; \ +1: popl %ds; \ +2: popl %es; \ +.section .fixup,"ax"; \ +3: movl $0,(%esp); \ + jmp 1b; \ +4: movl $0,(%esp); \ + jmp 2b; \ +.previous; \ +.section __ex_table,"a";\ + .align 4; \ + .long 1b,3b; \ + .long 2b,4b; \ +.previous + + +ENTRY(ret_from_fork) + pushl %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl %eax + jmp syscall_exit + +/* + * 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 +ret_from_exception: + preempt_stop +ret_from_intr: + GET_THREAD_INFO(%ebp) + movl EFLAGS(%esp), %eax # mix EFLAGS and CS + movb CS(%esp), %al + testl $(VM_MASK | 2), %eax + jz resume_kernel +ENTRY(resume_userspace) + DISABLE_INTERRUPTS # 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 + +#ifdef CONFIG_PREEMPT +ENTRY(resume_kernel) + cli + 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,EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all + call preempt_schedule_irq + jmp need_resched +#endif + +/* 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) + movl SYSENTER_stack_esp0(%esp),%esp +sysenter_past_esp: + sti + pushl $(__USER_DS) + pushl %ebp + pushfl + pushl $(__USER_CS) + /* + * 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) +/* + * 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 + 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,EAX(%esp) + DISABLE_INTERRUPTS + movl TI_flags(%ebp), %ecx + testw $_TIF_ALLWORK_MASK, %cx + jne syscall_exit_work +/* if something modifies registers it must also disable sysexit */ + movl EIP(%esp), %edx + movl OLDESP(%esp), %ecx + xorl %ebp,%ebp +#ifdef CONFIG_XEN + __ENABLE_INTERRUPTS +sysexit_scrit: /**** START OF SYSEXIT CRITICAL REGION ****/ + __TEST_PENDING + jnz 14f # process more events if necessary... + movl ESI(%esp), %esi + sysexit +14: __DISABLE_INTERRUPTS +sysexit_ecrit: /**** END OF SYSEXIT CRITICAL REGION ****/ + push %esp + call evtchn_do_upcall + add $4,%esp + jmp ret_from_intr +#else + sti + sysexit +#endif /* !CONFIG_XEN */ + + + # system call handler stub +ENTRY(system_call) + pushl %eax # save orig_eax + SAVE_ALL + GET_THREAD_INFO(%ebp) + testl $TF_MASK,EFLAGS(%esp) + jz no_singlestep + orl $_TIF_SINGLESTEP,TI_flags(%ebp) +no_singlestep: + # 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,EAX(%esp) # store the return value +syscall_exit: + DISABLE_INTERRUPTS # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + movl TI_flags(%ebp), %ecx + testw $_TIF_ALLWORK_MASK, %cx # current->work + jne syscall_exit_work + +restore_all: +#ifndef CONFIG_XEN + movl EFLAGS(%esp), %eax # mix EFLAGS, SS and CS + # Warning: OLDSS(%esp) contains the wrong/random values if we + # are returning to the kernel. + # See comments in process.c:copy_thread() for details. + movb OLDSS(%esp), %ah + movb CS(%esp), %al + andl $(VM_MASK | (4 << 8) | 3), %eax + cmpl $((4 << 8) | 3), %eax + je ldt_ss # returning to user-space with LDT SS +restore_nocheck: +#else +restore_nocheck: + movl EFLAGS(%esp), %eax + testl $(VM_MASK|NMI_MASK), %eax + jnz hypervisor_iret + shr $9, %eax # EAX[0] == IRET_EFLAGS.IF + GET_VCPU_INFO + andb evtchn_upcall_mask(%esi),%al + andb $1,%al # EAX[0] == IRET_EFLAGS.IF & event_mask + jnz restore_all_enable_events # != 0 => enable event delivery +#endif + RESTORE_REGS + addl $4, %esp +1: iret +.section .fixup,"ax" +iret_exc: +#ifndef CONFIG_XEN + sti +#endif + pushl $0 # no error code + pushl $do_iret_error + jmp error_code +.previous +.section __ex_table,"a" + .align 4 + .long 1b,iret_exc +.previous + +#ifndef CONFIG_XEN +ldt_ss: + larl OLDSS(%esp), %eax + jnz restore_nocheck + testl $0x00400000, %eax # returning to 32bit stack? + jnz restore_nocheck # allright, normal return + /* 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. */ + subl $8, %esp # reserve space for switch16 pointer + cli + movl %esp, %eax + /* Set up the 16bit stack frame with switch32 pointer on top, + * and a switch16 pointer on top of the current frame. */ + call setup_x86_bogus_stack + RESTORE_REGS + lss 20+4(%esp), %esp # switch to 16bit stack +1: iret +.section __ex_table,"a" + .align 4 + .long 1b,iret_exc +.previous +#else +hypervisor_iret: + andl $~NMI_MASK, EFLAGS(%esp) + RESTORE_REGS + addl $4, %esp + jmp hypercall_page + (__HYPERVISOR_iret * 32) +#endif + + # perform work that needs to be done immediately before resumption + ALIGN +work_pending: + testb $_TIF_NEED_RESCHED, %cl + jz work_notifysig +work_resched: + call schedule + DISABLE_INTERRUPTS # 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 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 + testl $VM_MASK, 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 + + ALIGN +work_notifysig_v86: +#ifdef CONFIG_VM86 + pushl %ecx # save ti_flags for do_notify_resume + call save_v86_state # %eax contains pt_regs pointer + popl %ecx + movl %eax, %esp + xorl %edx, %edx + call do_notify_resume + jmp resume_userspace +#endif + + # perform syscall exit tracing + ALIGN +syscall_trace_entry: + movl $-ENOSYS,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 ORIG_EAX(%esp), %eax + cmpl $(nr_syscalls), %eax + jnae syscall_call + jmp syscall_exit + + # perform syscall exit tracing + ALIGN +syscall_exit_work: + testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl + jz work_pending + ENABLE_INTERRUPTS # could let do_syscall_trace() call + # schedule() instead + movl %esp, %eax + movl $1, %edx + call do_syscall_trace + jmp resume_userspace + + ALIGN +syscall_fault: + pushl %eax # save orig_eax + SAVE_ALL + GET_THREAD_INFO(%ebp) + movl $-EFAULT,EAX(%esp) + jmp resume_userspace + + ALIGN +syscall_badsys: + movl $-ENOSYS,EAX(%esp) + jmp resume_userspace + +#ifndef CONFIG_XEN +#define FIXUP_ESPFIX_STACK \ + movl %esp, %eax; \ + /* switch to 32bit stack using the pointer on top of 16bit stack */ \ + lss %ss:CPU_16BIT_STACK_SIZE-8, %esp; \ + /* copy data from 16bit stack to 32bit stack */ \ + call fixup_x86_bogus_stack; \ + /* put ESP to the proper location */ \ + movl %eax, %esp; +#define UNWIND_ESPFIX_STACK \ + pushl %eax; \ + movl %ss, %eax; \ + /* see if on 16bit stack */ \ + cmpw $__ESPFIX_SS, %ax; \ + jne 28f; \ + movl $__KERNEL_DS, %edx; \ + movl %edx, %ds; \ + movl %edx, %es; \ + /* switch to 32bit stack */ \ + FIXUP_ESPFIX_STACK \ +28: popl %eax; + +/* + * Build the entry stubs and pointer table with + * some assembler magic. + */ +.data +ENTRY(interrupt) +.text + +vector=0 +ENTRY(irq_entries_start) +.rept NR_IRQS + ALIGN +1: pushl $~(vector) + jmp common_interrupt +.data + .long 1b +.text +vector=vector+1 +.endr + + ALIGN +common_interrupt: + SAVE_ALL + movl %esp,%eax + call do_IRQ + jmp ret_from_intr + +#define BUILD_INTERRUPT(name, nr) \ +ENTRY(name) \ + pushl $~(nr); \ + SAVE_ALL \ + movl %esp,%eax; \ + call smp_/**/name; \ + jmp ret_from_intr; + +/* The include is where all of the SMP etc. interrupts come from */ +#include "entry_arch.h" +#else +#define UNWIND_ESPFIX_STACK +#endif + +ENTRY(divide_error) + pushl $0 # no error code + pushl $do_divide_error + ALIGN +error_code: + pushl %ds + pushl %eax + xorl %eax, %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + decl %eax # eax = -1 + pushl %ecx + pushl %ebx + cld + pushl %es + UNWIND_ESPFIX_STACK + popl %ecx + movl ES(%esp), %edi # get the function address + movl ORIG_EAX(%esp), %edx # get the error code + movl %eax, ORIG_EAX(%esp) + movl %ecx, ES(%esp) + movl $(__USER_DS), %ecx + movl %ecx, %ds + movl %ecx, %es + movl %esp,%eax # pt_regs pointer + call *%edi + jmp ret_from_exception + +#ifdef CONFIG_XEN +# A note on the "critical region" in our callback handler. +# We want to avoid stacking callback handlers due to events occurring +# during handling of the last event. To do this, we keep events disabled +# until we've done all processing. HOWEVER, we must enable events before +# popping the stack frame (can't be done atomically) and so it would still +# be possible to get enough handler activations to overflow the stack. +# Although unlikely, bugs of that kind are hard to track down, so we'd +# like to avoid the possibility. +# So, on entry to the handler we detect whether we interrupted an +# existing activation in its critical region -- if so, we pop the current +# activation and restart the handler using the previous one. +# +# The sysexit critical region is slightly different. sysexit +# atomically removes the entire stack frame. If we interrupt in the +# critical region we know that the entire frame is present and correct +# so we can simply throw away the new one. +ENTRY(hypervisor_callback) + pushl %eax + SAVE_ALL + movl EIP(%esp),%eax + cmpl $scrit,%eax + jb 11f + cmpl $ecrit,%eax + jb critical_region_fixup + cmpl $sysexit_scrit,%eax + jb 11f + cmpl $sysexit_ecrit,%eax + ja 11f + addl $0x34,%esp # Remove cs...ebx from stack frame. +11: push %esp + call evtchn_do_upcall + add $4,%esp + jmp ret_from_intr + + ALIGN +restore_all_enable_events: + __ENABLE_INTERRUPTS +scrit: /**** START OF CRITICAL REGION ****/ + __TEST_PENDING + jnz 14f # process more events if necessary... + RESTORE_REGS + addl $4, %esp +1: iret +.section __ex_table,"a" + .align 4 + .long 1b,iret_exc +.previous +14: __DISABLE_INTERRUPTS + jmp 11b +ecrit: /**** END OF CRITICAL REGION ****/ +# [How we do the fixup]. We want to merge the current stack frame with the +# just-interrupted frame. How we do this depends on where in the critical +# region the interrupted handler was executing, and so how many saved +# registers are in each frame. We do this quickly using the lookup table +# 'critical_fixup_table'. For each byte offset in the critical region, it +# provides the number of bytes which have already been popped from the +# interrupted stack frame. +critical_region_fixup: + addl $critical_fixup_table-scrit,%eax + movzbl (%eax),%eax # %eax contains num bytes popped + cmpb $0xff,%al # 0xff => vcpu_info critical region + jne 15f + GET_THREAD_INFO(%ebp) + xorl %eax,%eax +15: mov %esp,%esi + add %eax,%esi # %esi points at end of src region + mov %esp,%edi + add $0x34,%edi # %edi points at end of dst region + mov %eax,%ecx + shr $2,%ecx # convert words to bytes + je 17f # skip loop if nothing to copy +16: subl $4,%esi # pre-decrementing copy loop + subl $4,%edi + movl (%esi),%eax + movl %eax,(%edi) + loop 16b +17: movl %edi,%esp # final %edi is top of merged stack + jmp 11b + +critical_fixup_table: + .byte 0xff,0xff,0xff # testb $0xff,(%esi) = __TEST_PENDING + .byte 0xff,0xff # jnz 14f + .byte 0x00 # pop %ebx + .byte 0x04 # pop %ecx + .byte 0x08 # pop %edx + .byte 0x0c # pop %esi + .byte 0x10 # pop %edi + .byte 0x14 # pop %ebp + .byte 0x18 # pop %eax + .byte 0x1c # pop %ds + .byte 0x20 # pop %es + .byte 0x24,0x24,0x24 # add $4,%esp + .byte 0x28 # iret + .byte 0xff,0xff,0xff,0xff # movb $1,1(%esi) + .byte 0x00,0x00 # jmp 11b + +# 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(failsafe_callback) + pushl %eax + 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 + jz 5f + addl $16,%esp # EAX != 0 => Category 2 (Bad IRET) + jmp iret_exc +5: addl $16,%esp # EAX == 0 => Category 1 (Bad segment) + pushl $0 + SAVE_ALL + jmp ret_from_exception +.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 +#endif + +ENTRY(coprocessor_error) + pushl $0 + pushl $do_coprocessor_error + jmp error_code + +ENTRY(simd_coprocessor_error) + pushl $0 + pushl $do_simd_coprocessor_error + jmp error_code + +ENTRY(device_not_available) + pushl $-1 # mark this as an int + SAVE_ALL +#ifndef CONFIG_XEN + movl %cr0, %eax + testl $0x4, %eax # EM (math emulation bit) + je device_available_emulate + pushl $0 # temporary storage for ORIG_EIP + call math_emulate + addl $4, %esp + jmp ret_from_exception +device_available_emulate: +#endif + preempt_stop + call math_state_restore + jmp ret_from_exception + +#ifndef CONFIG_XEN +/* + * 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. + * + * "SYSENTER_stack_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 SYSENTER_stack_esp0+offset(%esp),%esp; \ + pushfl; \ + pushl $__KERNEL_CS; \ + pushl $sysenter_past_esp +#endif /* CONFIG_XEN */ + +KPROBE_ENTRY(debug) +#ifndef CONFIG_XEN + cmpl $sysenter_entry,(%esp) + jne debug_stack_correct + FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn) +debug_stack_correct: +#endif /* !CONFIG_XEN */ + pushl $-1 # mark this as an int + SAVE_ALL + xorl %edx,%edx # error code 0 + movl %esp,%eax # pt_regs pointer + call do_debug + jmp ret_from_exception + .previous .text + +#ifndef CONFIG_XEN +/* + * 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) + pushl %eax + movl %ss, %eax + cmpw $__ESPFIX_SS, %ax + popl %eax + je nmi_16bit_stack + cmpl $sysenter_entry,(%esp) + je nmi_stack_fixup + pushl %eax + 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 + jae nmi_stack_correct + cmpl $sysenter_entry,12(%esp) + je nmi_debug_stack_check +nmi_stack_correct: + pushl %eax + SAVE_ALL + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_nmi + jmp restore_all + +nmi_stack_fixup: + FIX_STACK(12,nmi_stack_correct, 1) + jmp nmi_stack_correct +nmi_debug_stack_check: + 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_16bit_stack: + /* create the pointer to lss back */ + pushl %ss + pushl %esp + movzwl %sp, %esp + addw $4, (%esp) + /* copy the iret frame of 12 bytes */ + .rept 3 + pushl 16(%esp) + .endr + pushl %eax + 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 16bit stack +1: iret +.section __ex_table,"a" + .align 4 + .long 1b,iret_exc +.previous +#else +ENTRY(nmi) + pushl %eax + SAVE_ALL + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_nmi + orl $NMI_MASK, EFLAGS(%esp) + jmp restore_all +#endif + +KPROBE_ENTRY(int3) + pushl $-1 # mark this as an int + SAVE_ALL + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_int3 + jmp ret_from_exception + .previous .text + +ENTRY(overflow) + pushl $0 + pushl $do_overflow + jmp error_code + +ENTRY(bounds) + pushl $0 + pushl $do_bounds + jmp error_code + +ENTRY(invalid_op) + pushl $0 + pushl $do_invalid_op + jmp error_code + +ENTRY(coprocessor_segment_overrun) + pushl $0 + pushl $do_coprocessor_segment_overrun + jmp error_code + +ENTRY(invalid_TSS) + pushl $do_invalid_TSS + jmp error_code + +ENTRY(segment_not_present) + pushl $do_segment_not_present + jmp error_code + +ENTRY(stack_segment) + pushl $do_stack_segment + jmp error_code + +KPROBE_ENTRY(general_protection) + pushl $do_general_protection + jmp error_code + .previous .text + +ENTRY(alignment_check) + pushl $do_alignment_check + jmp error_code + +KPROBE_ENTRY(page_fault) + pushl $do_page_fault + jmp error_code + .previous .text + +#ifdef CONFIG_X86_MCE +ENTRY(machine_check) + pushl $0 + pushl machine_check_vector + jmp error_code +#endif + +ENTRY(fixup_4gb_segment) + pushl $do_fixup_4gb_segment + jmp error_code + +.section .rodata,"a" +#include "syscall_table.S" + +syscall_table_size=(.-sys_call_table)