X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=arch%2Fi386%2Fkernel%2Fentry.S;h=094b47426d0ce8d20800bc594d48ea6eae03587d;hb=refs%2Fheads%2Fvserver;hp=0e7e68be12759a7cf0e82375bf0661e1d04239cb;hpb=6a77f38946aaee1cd85eeec6cf4229b204c15071;p=linux-2.6.git diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S index 0e7e68be1..094b47426 100644 --- a/arch/i386/kernel/entry.S +++ b/arch/i386/kernel/entry.S @@ -30,42 +30,43 @@ * 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 + * 24(%esp) - %gs + * 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 #include #include +#include #include #include #include #include +#include +#include +#include #include "irq_vectors.h" -#define nr_syscalls ((syscall_table_size)/4) +/* + * 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. + */ -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 +#define nr_syscalls ((syscall_table_size)/4) CF_MASK = 0x00000001 TF_MASK = 0x00000100 @@ -75,77 +76,157 @@ NT_MASK = 0x00004000 VM_MASK = 0x00020000 #ifdef CONFIG_PREEMPT -#define preempt_stop cli +#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF #else -#define preempt_stop -#define resume_kernel restore_all +#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 %gs; \ + CFI_ADJUST_CFA_OFFSET 4;\ + /*CFI_REL_OFFSET gs, 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 %edx, %es; \ + movl $(__KERNEL_PDA), %edx; \ + movl %edx, %gs #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; \ - popl %eax + 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; \ -.section .fixup,"ax"; \ -3: movl $0,(%esp); \ - jmp 1b; \ + CFI_ADJUST_CFA_OFFSET -4;\ + /*CFI_RESTORE es;*/\ +3: popl %gs; \ + CFI_ADJUST_CFA_OFFSET -4;\ + /*CFI_RESTORE gs;*/\ +.pushsection .fixup,"ax"; \ 4: movl $0,(%esp); \ + jmp 1b; \ +5: movl $0,(%esp); \ jmp 2b; \ -.previous; \ -.section __ex_table,"a";\ - .align 4; \ - .long 1b,3b; \ - .long 2b,4b; \ -.previous - - -#define RESTORE_ALL \ - RESTORE_REGS \ - addl $4, %esp; \ -1: iret; \ -.section .fixup,"ax"; \ -2: sti; \ - movl $(__USER_DS), %edx; \ - movl %edx, %ds; \ - movl %edx, %es; \ - movl $11,%eax; \ - call do_exit; \ -.previous; \ +6: movl $0,(%esp); \ + jmp 3b; \ .section __ex_table,"a";\ .align 4; \ - .long 1b,2b; \ -.previous - + .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 /* * Return to user mode is not as complex as all this looks, @@ -156,16 +237,20 @@ ENTRY(ret_from_fork) # userspace resumption stub bypassing syscall exit tracing ALIGN + RING0_PTREGS_FRAME ret_from_exception: - preempt_stop + preempt_stop(CLBR_ANY) ret_from_intr: GET_THREAD_INFO(%ebp) - movl EFLAGS(%esp), %eax # mix EFLAGS and CS - movb CS(%esp), %al - testl $(VM_MASK | 3), %eax - jz resume_kernel # returning to kernel or vm86-space +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) - cli # make sure we don't miss an interrupt + 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 @@ -176,32 +261,59 @@ ENTRY(resume_userspace) #ifdef CONFIG_PREEMPT ENTRY(resume_kernel) - cli + DISABLE_INTERRUPTS(CLBR_ANY) cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? - jnz restore_all + 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) ? + testl $IF_MASK,PT_EFLAGS(%esp) # interrupts off (exception path) ? jz restore_all call preempt_schedule_irq jmp need_resched #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) - movl TSS_sysenter_esp0(%esp),%esp + CFI_STARTPROC simple + CFI_SIGNAL_FRAME + CFI_DEF_CFA esp, 0 + CFI_REGISTER esp, ebp + movl SYSENTER_stack_esp0(%esp),%esp sysenter_past_esp: - sti + /* + * 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*/ +#ifndef CONFIG_COMPAT_VDSO + /* + * 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) +#else pushl $SYSENTER_RETURN +#endif + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET eip, 0 /* * Load the potential sixth argument from user stack. @@ -216,60 +328,150 @@ sysenter_past_esp: .previous pushl %eax + CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL GET_THREAD_INFO(%ebp) - testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%ebp) + /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ + testw $(_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) - cli + movl %eax,PT_EAX(%esp) + DISABLE_INTERRUPTS(CLBR_ECX|CLBR_EDX) + 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 EIP(%esp), %edx - movl OLDESP(%esp), %ecx + movl PT_EIP(%esp), %edx + movl PT_OLDESP(%esp), %ecx xorl %ebp,%ebp - sti - sysexit - + TRACE_IRQS_ON +1: mov PT_GS(%esp), %gs + ENABLE_INTERRUPTS_SYSEXIT + CFI_ENDPROC +.pushsection .fixup,"ax" +2: movl $0,PT_GS(%esp) + jmp 1b +.section __ex_table,"a" + .align 4 + .long 1b,2b +.popsection # 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 - testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%ebp) + testl $TF_MASK,PT_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_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 + movl %eax,PT_EAX(%esp) # store the return value syscall_exit: - cli # make sure we don't miss an interrupt + 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 testw $_TIF_ALLWORK_MASK, %cx # current->work jne syscall_exit_work + restore_all: - 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 # 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 - cli # make sure we don't miss an interrupt + 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? @@ -279,32 +481,38 @@ work_resched: work_notifysig: # deal with pending signals and # notify-resume requests - testl $VM_MASK, EFLAGS(%esp) +#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 restore_all + 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 restore_all + jmp resume_userspace_sig # perform syscall exit tracing ALIGN syscall_trace_entry: - movl $-ENOSYS,EAX(%esp) + movl $-ENOSYS,PT_EAX(%esp) movl %esp, %eax xorl %edx,%edx call do_syscall_trace - movl ORIG_EAX(%esp), %eax + movl PT_ORIG_EAX(%esp), %eax cmpl $(nr_syscalls), %eax jnae syscall_call jmp syscall_exit @@ -314,25 +522,53 @@ syscall_trace_entry: syscall_exit_work: testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl jz work_pending - sti # could let do_syscall_trace() call + 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 + CFI_ENDPROC - ALIGN + 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,EAX(%esp) + movl $-EFAULT,PT_EAX(%esp) jmp resume_userspace - ALIGN syscall_badsys: - movl $-ENOSYS,EAX(%esp) + movl $-ENOSYS,PT_EAX(%esp) jmp resume_userspace + CFI_ENDPROC + +#define FIXUP_ESPFIX_STACK \ + /* since we are on a wrong stack, we cant make it a C code :( */ \ + movl %gs:PDA_cpu, %ebx; \ + PER_CPU(cpu_gdt_descr, %ebx); \ + movl GDS_address(%ebx), %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 @@ -344,9 +580,14 @@ ENTRY(interrupt) vector=0 ENTRY(irq_entries_start) + RING0_INT_FRAME .rept NR_IRQS ALIGN -1: pushl $vector-256 + .if vector + CFI_ADJUST_CFA_OFFSET -4 + .endif +1: pushl $~(vector) + CFI_ADJUST_CFA_OFFSET 4 jmp common_interrupt .data .long 1b @@ -354,83 +595,136 @@ ENTRY(irq_entries_start) vector=vector+1 .endr +/* + * 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 + CFI_ENDPROC #define BUILD_INTERRUPT(name, nr) \ ENTRY(name) \ - pushl $nr-256; \ - SAVE_ALL \ + 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; + jmp ret_from_intr; \ + CFI_ENDPROC /* The include is where all of the SMP etc. interrupts come from */ #include "entry_arch.h" -ENTRY(divide_error) - pushl $0 # no error code - pushl $do_divide_error +KPROBE_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 %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 - xorl %eax, %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 - decl %eax # eax = -1 + 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 %es, %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) + pushl %gs + CFI_ADJUST_CFA_OFFSET 4 + /*CFI_REL_OFFSET gs, 0*/ + movl $(__KERNEL_PDA), %ecx + movl %ecx, %gs + UNWIND_ESPFIX_STACK + popl %ecx + CFI_ADJUST_CFA_OFFSET -4 + /*CFI_REGISTER es, 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 + mov %ecx, PT_GS(%esp) + /*CFI_REL_OFFSET gs, 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 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 ENTRY(device_not_available) + RING0_INT_FRAME pushl $-1 # mark this as an int + CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL - movl %cr0, %eax + GET_CR0_INTO_EAX testl $0x4, %eax # EM (math emulation bit) jne device_not_available_emulate - preempt_stop + 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 /* * 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 + * "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. * @@ -442,24 +736,32 @@ device_not_available_emulate: cmpw $__KERNEL_CS,4(%esp); \ jne ok; \ label: \ - movl TSS_sysenter_esp0+offset(%esp),%esp; \ + movl SYSENTER_stack_esp0+offset(%esp),%esp; \ + CFI_DEF_CFA esp, 0; \ + CFI_UNDEFINED eip; \ pushfl; \ + CFI_ADJUST_CFA_OFFSET 4; \ pushl $__KERNEL_CS; \ - pushl $sysenter_past_esp + CFI_ADJUST_CFA_OFFSET 4; \ + pushl $sysenter_past_esp; \ + CFI_ADJUST_CFA_OFFSET 4; \ + CFI_REL_OFFSET eip, 0 -ENTRY(debug) +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 - testl %eax,%eax - jnz restore_all jmp ret_from_exception + CFI_ENDPROC +KPROBE_END(debug) /* * NMI is doubly nasty. It can happen _while_ we're handling @@ -469,10 +771,19 @@ debug_stack_correct: * check whether we got an NMI on the debug path where the debug * fault happened on the sysenter path. */ -ENTRY(nmi) +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. @@ -480,387 +791,209 @@ ENTRY(nmi) 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 - RESTORE_ALL + 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 - 1,(%esp) - jle nmi_stack_correct + cmpl $debug,(%esp) + jb nmi_stack_correct cmpl $debug_esp_fix_insn,(%esp) - jle nmi_debug_stack_fixup -nmi_debug_stack_fixup: + ja nmi_stack_correct FIX_STACK(24,nmi_stack_correct, 1) jmp nmi_stack_correct -ENTRY(int3) +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 + +ENTRY(native_irq_enable_sysexit) + sti + 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 - testl %eax,%eax - jnz restore_all 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 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 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 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 ENTRY(invalid_TSS) + RING0_EC_FRAME pushl $do_invalid_TSS + CFI_ADJUST_CFA_OFFSET 4 jmp error_code + CFI_ENDPROC ENTRY(segment_not_present) + RING0_EC_FRAME pushl $do_segment_not_present + CFI_ADJUST_CFA_OFFSET 4 jmp error_code + CFI_ENDPROC ENTRY(stack_segment) + RING0_EC_FRAME pushl $do_stack_segment + CFI_ADJUST_CFA_OFFSET 4 jmp error_code + CFI_ENDPROC -ENTRY(general_protection) +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 -ENTRY(page_fault) - pushl $do_page_fault +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 #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 #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 - -.data -ENTRY(sys_call_table) - .long sys_restart_syscall /* 0 - old "setup()" system call, used for restarting */ - .long sys_exit - .long sys_fork - .long sys_read - .long sys_write - .long sys_open /* 5 */ - .long sys_close - .long sys_waitpid - .long sys_creat - .long sys_link - .long sys_unlink /* 10 */ - .long sys_execve - .long sys_chdir - .long sys_time - .long sys_mknod - .long sys_chmod /* 15 */ - .long sys_lchown16 - .long sys_ni_syscall /* old break syscall holder */ - .long sys_stat - .long sys_lseek - .long sys_getpid /* 20 */ - .long sys_mount - .long sys_oldumount - .long sys_setuid16 - .long sys_getuid16 - .long sys_stime /* 25 */ - .long sys_ptrace - .long sys_alarm - .long sys_fstat - .long sys_pause - .long sys_utime /* 30 */ - .long sys_ni_syscall /* old stty syscall holder */ - .long sys_ni_syscall /* old gtty syscall holder */ - .long sys_access - .long sys_nice - .long sys_ni_syscall /* 35 - old ftime syscall holder */ - .long sys_sync - .long sys_kill - .long sys_rename - .long sys_mkdir - .long sys_rmdir /* 40 */ - .long sys_dup - .long sys_pipe - .long sys_times - .long sys_ni_syscall /* old prof syscall holder */ - .long sys_brk /* 45 */ - .long sys_setgid16 - .long sys_getgid16 - .long sys_signal - .long sys_geteuid16 - .long sys_getegid16 /* 50 */ - .long sys_acct - .long sys_umount /* recycled never used phys() */ - .long sys_ni_syscall /* old lock syscall holder */ - .long sys_ioctl - .long sys_fcntl /* 55 */ - .long sys_ni_syscall /* old mpx syscall holder */ - .long sys_setpgid - .long sys_ni_syscall /* old ulimit syscall holder */ - .long sys_olduname - .long sys_umask /* 60 */ - .long sys_chroot - .long sys_ustat - .long sys_dup2 - .long sys_getppid - .long sys_getpgrp /* 65 */ - .long sys_setsid - .long sys_sigaction - .long sys_sgetmask - .long sys_ssetmask - .long sys_setreuid16 /* 70 */ - .long sys_setregid16 - .long sys_sigsuspend - .long sys_sigpending - .long sys_sethostname - .long sys_setrlimit /* 75 */ - .long sys_old_getrlimit - .long sys_getrusage - .long sys_gettimeofday - .long sys_settimeofday - .long sys_getgroups16 /* 80 */ - .long sys_setgroups16 - .long old_select - .long sys_symlink - .long sys_lstat - .long sys_readlink /* 85 */ - .long sys_uselib - .long sys_swapon - .long sys_reboot - .long old_readdir - .long old_mmap /* 90 */ - .long sys_munmap - .long sys_truncate - .long sys_ftruncate - .long sys_fchmod - .long sys_fchown16 /* 95 */ - .long sys_getpriority - .long sys_setpriority - .long sys_ni_syscall /* old profil syscall holder */ - .long sys_statfs - .long sys_fstatfs /* 100 */ - .long sys_ioperm - .long sys_socketcall - .long sys_syslog - .long sys_setitimer - .long sys_getitimer /* 105 */ - .long sys_newstat - .long sys_newlstat - .long sys_newfstat - .long sys_uname - .long sys_iopl /* 110 */ - .long sys_vhangup - .long sys_ni_syscall /* old "idle" system call */ - .long sys_vm86old - .long sys_wait4 - .long sys_swapoff /* 115 */ - .long sys_sysinfo - .long sys_ipc - .long sys_fsync - .long sys_sigreturn - .long sys_clone /* 120 */ - .long sys_setdomainname - .long sys_newuname - .long sys_modify_ldt - .long sys_adjtimex - .long sys_mprotect /* 125 */ - .long sys_sigprocmask - .long sys_ni_syscall /* old "create_module" */ - .long sys_init_module - .long sys_delete_module - .long sys_ni_syscall /* 130: old "get_kernel_syms" */ - .long sys_quotactl - .long sys_getpgid - .long sys_fchdir - .long sys_bdflush - .long sys_sysfs /* 135 */ - .long sys_personality - .long sys_ni_syscall /* reserved for afs_syscall */ - .long sys_setfsuid16 - .long sys_setfsgid16 - .long sys_llseek /* 140 */ - .long sys_getdents - .long sys_select - .long sys_flock - .long sys_msync - .long sys_readv /* 145 */ - .long sys_writev - .long sys_getsid - .long sys_fdatasync - .long sys_sysctl - .long sys_mlock /* 150 */ - .long sys_munlock - .long sys_mlockall - .long sys_munlockall - .long sys_sched_setparam - .long sys_sched_getparam /* 155 */ - .long sys_sched_setscheduler - .long sys_sched_getscheduler - .long sys_sched_yield - .long sys_sched_get_priority_max - .long sys_sched_get_priority_min /* 160 */ - .long sys_sched_rr_get_interval - .long sys_nanosleep - .long sys_mremap - .long sys_setresuid16 - .long sys_getresuid16 /* 165 */ - .long sys_vm86 - .long sys_ni_syscall /* Old sys_query_module */ - .long sys_poll - .long sys_nfsservctl - .long sys_setresgid16 /* 170 */ - .long sys_getresgid16 - .long sys_prctl - .long sys_rt_sigreturn - .long sys_rt_sigaction - .long sys_rt_sigprocmask /* 175 */ - .long sys_rt_sigpending - .long sys_rt_sigtimedwait - .long sys_rt_sigqueueinfo - .long sys_rt_sigsuspend - .long sys_pread64 /* 180 */ - .long sys_pwrite64 - .long sys_chown16 - .long sys_getcwd - .long sys_capget - .long sys_capset /* 185 */ - .long sys_sigaltstack - .long sys_sendfile - .long sys_ni_syscall /* reserved for streams1 */ - .long sys_ni_syscall /* reserved for streams2 */ - .long sys_vfork /* 190 */ - .long sys_getrlimit - .long sys_mmap2 - .long sys_truncate64 - .long sys_ftruncate64 - .long sys_stat64 /* 195 */ - .long sys_lstat64 - .long sys_fstat64 - .long sys_lchown - .long sys_getuid - .long sys_getgid /* 200 */ - .long sys_geteuid - .long sys_getegid - .long sys_setreuid - .long sys_setregid - .long sys_getgroups /* 205 */ - .long sys_setgroups - .long sys_fchown - .long sys_setresuid - .long sys_getresuid - .long sys_setresgid /* 210 */ - .long sys_getresgid - .long sys_chown - .long sys_setuid - .long sys_setgid - .long sys_setfsuid /* 215 */ - .long sys_setfsgid - .long sys_pivot_root - .long sys_mincore - .long sys_madvise - .long sys_getdents64 /* 220 */ - .long sys_fcntl64 - .long sys_ni_syscall /* reserved for TUX */ - .long sys_ni_syscall - .long sys_gettid - .long sys_readahead /* 225 */ - .long sys_setxattr - .long sys_lsetxattr - .long sys_fsetxattr - .long sys_getxattr - .long sys_lgetxattr /* 230 */ - .long sys_fgetxattr - .long sys_listxattr - .long sys_llistxattr - .long sys_flistxattr - .long sys_removexattr /* 235 */ - .long sys_lremovexattr - .long sys_fremovexattr - .long sys_tkill - .long sys_sendfile64 - .long sys_futex /* 240 */ - .long sys_sched_setaffinity - .long sys_sched_getaffinity - .long sys_set_thread_area - .long sys_get_thread_area - .long sys_io_setup /* 245 */ - .long sys_io_destroy - .long sys_io_getevents - .long sys_io_submit - .long sys_io_cancel - .long sys_fadvise64 /* 250 */ - .long sys_ni_syscall - .long sys_exit_group - .long sys_lookup_dcookie - .long sys_epoll_create - .long sys_epoll_ctl /* 255 */ - .long sys_epoll_wait - .long sys_remap_file_pages - .long sys_set_tid_address - .long sys_timer_create - .long sys_timer_settime /* 260 */ - .long sys_timer_gettime - .long sys_timer_getoverrun - .long sys_timer_delete - .long sys_clock_settime - .long sys_clock_gettime /* 265 */ - .long sys_clock_getres - .long sys_clock_nanosleep - .long sys_statfs64 - .long sys_fstatfs64 - .long sys_tgkill /* 270 */ - .long sys_utimes - .long sys_fadvise64_64 - .long sys_vserver - .long sys_mbind - .long sys_get_mempolicy - .long sys_set_mempolicy - .long sys_mq_open - .long sys_mq_unlink - .long sys_mq_timedsend - .long sys_mq_timedreceive /* 280 */ - .long sys_mq_notify - .long sys_mq_getsetattr - .long sys_ni_syscall /* reserved for kexec */ - .long sys_waitid - .long sys_ni_syscall /* 285 */ /* available */ - .long sys_add_key - .long sys_request_key - .long sys_keyctl + CFI_ENDPROC + +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) + +.section .rodata,"a" +#include "syscall_table.S" syscall_table_size=(.-sys_call_table)