OpenCloudOS-Kernel/arch/x86/entry/entry_32.S

1349 lines
34 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 1991,1992 Linus Torvalds
*
* entry_32.S contains the system-call and low-level fault and trap handling routines.
*
* Stack layout while running C code:
* ptrace needs to have all registers 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
*/
#include <linux/linkage.h>
#include <linux/err.h>
#include <asm/thread_info.h>
#include <asm/irqflags.h>
#include <asm/errno.h>
#include <asm/segment.h>
#include <asm/smp.h>
#include <asm/percpu.h>
#include <asm/processor-flags.h>
#include <asm/irq_vectors.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/frame.h>
#include <asm/trapnr.h>
#include <asm/nospec-branch.h>
#include "calling.h"
.section .entry.text, "ax"
#define PTI_SWITCH_MASK (1 << PAGE_SHIFT)
/*
* 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
.endm
.macro POP_GS pop=0
addl $(4 + \pop), %esp
.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
.endm
.macro POP_GS pop=0
98: popl %gs
.if \pop <> 0
add $\pop, %esp
.endif
.endm
.macro POP_GS_EX
.pushsection .fixup, "ax"
99: movl $0, (%esp)
jmp 98b
.popsection
_ASM_EXTABLE(98b, 99b)
.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
.popsection
_ASM_EXTABLE(98b, 99b)
.endm
.macro GS_TO_REG reg
movl %gs, \reg
.endm
.macro REG_TO_PTGS reg
movl \reg, PT_GS(%esp)
.endm
.macro SET_KERNEL_GS reg
movl $(__KERNEL_STACK_CANARY), \reg
movl \reg, %gs
.endm
#endif /* CONFIG_X86_32_LAZY_GS */
/* Unconditionally switch to user cr3 */
.macro SWITCH_TO_USER_CR3 scratch_reg:req
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
movl %cr3, \scratch_reg
orl $PTI_SWITCH_MASK, \scratch_reg
movl \scratch_reg, %cr3
.Lend_\@:
.endm
.macro BUG_IF_WRONG_CR3 no_user_check=0
#ifdef CONFIG_DEBUG_ENTRY
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
.if \no_user_check == 0
/* coming from usermode? */
testl $USER_SEGMENT_RPL_MASK, PT_CS(%esp)
jz .Lend_\@
.endif
/* On user-cr3? */
movl %cr3, %eax
testl $PTI_SWITCH_MASK, %eax
jnz .Lend_\@
/* From userspace with kernel cr3 - BUG */
ud2
.Lend_\@:
#endif
.endm
/*
* Switch to kernel cr3 if not already loaded and return current cr3 in
* \scratch_reg
*/
.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
movl %cr3, \scratch_reg
/* Test if we are already on kernel CR3 */
testl $PTI_SWITCH_MASK, \scratch_reg
jz .Lend_\@
andl $(~PTI_SWITCH_MASK), \scratch_reg
movl \scratch_reg, %cr3
/* Return original CR3 in \scratch_reg */
orl $PTI_SWITCH_MASK, \scratch_reg
.Lend_\@:
.endm
#define CS_FROM_ENTRY_STACK (1 << 31)
#define CS_FROM_USER_CR3 (1 << 30)
#define CS_FROM_KERNEL (1 << 29)
#define CS_FROM_ESPFIX (1 << 28)
.macro FIXUP_FRAME
/*
* The high bits of the CS dword (__csh) are used for CS_FROM_*.
* Clear them in case hardware didn't do this for us.
*/
andl $0x0000ffff, 4*4(%esp)
#ifdef CONFIG_VM86
testl $X86_EFLAGS_VM, 5*4(%esp)
jnz .Lfrom_usermode_no_fixup_\@
#endif
testl $USER_SEGMENT_RPL_MASK, 4*4(%esp)
jnz .Lfrom_usermode_no_fixup_\@
orl $CS_FROM_KERNEL, 4*4(%esp)
/*
* When we're here from kernel mode; the (exception) stack looks like:
*
* 6*4(%esp) - <previous context>
* 5*4(%esp) - flags
* 4*4(%esp) - cs
* 3*4(%esp) - ip
* 2*4(%esp) - orig_eax
* 1*4(%esp) - gs / function
* 0*4(%esp) - fs
*
* Lets build a 5 entry IRET frame after that, such that struct pt_regs
* is complete and in particular regs->sp is correct. This gives us
* the original 6 enties as gap:
*
* 14*4(%esp) - <previous context>
* 13*4(%esp) - gap / flags
* 12*4(%esp) - gap / cs
* 11*4(%esp) - gap / ip
* 10*4(%esp) - gap / orig_eax
* 9*4(%esp) - gap / gs / function
* 8*4(%esp) - gap / fs
* 7*4(%esp) - ss
* 6*4(%esp) - sp
* 5*4(%esp) - flags
* 4*4(%esp) - cs
* 3*4(%esp) - ip
* 2*4(%esp) - orig_eax
* 1*4(%esp) - gs / function
* 0*4(%esp) - fs
*/
pushl %ss # ss
pushl %esp # sp (points at ss)
addl $7*4, (%esp) # point sp back at the previous context
pushl 7*4(%esp) # flags
pushl 7*4(%esp) # cs
pushl 7*4(%esp) # ip
pushl 7*4(%esp) # orig_eax
pushl 7*4(%esp) # gs / function
pushl 7*4(%esp) # fs
.Lfrom_usermode_no_fixup_\@:
.endm
.macro IRET_FRAME
/*
* We're called with %ds, %es, %fs, and %gs from the interrupted
* frame, so we shouldn't use them. Also, we may be in ESPFIX
* mode and therefore have a nonzero SS base and an offset ESP,
* so any attempt to access the stack needs to use SS. (except for
* accesses through %esp, which automatically use SS.)
*/
testl $CS_FROM_KERNEL, 1*4(%esp)
jz .Lfinished_frame_\@
/*
* Reconstruct the 3 entry IRET frame right after the (modified)
* regs->sp without lowering %esp in between, such that an NMI in the
* middle doesn't scribble our stack.
*/
pushl %eax
pushl %ecx
movl 5*4(%esp), %eax # (modified) regs->sp
movl 4*4(%esp), %ecx # flags
movl %ecx, %ss:-1*4(%eax)
movl 3*4(%esp), %ecx # cs
andl $0x0000ffff, %ecx
movl %ecx, %ss:-2*4(%eax)
movl 2*4(%esp), %ecx # ip
movl %ecx, %ss:-3*4(%eax)
movl 1*4(%esp), %ecx # eax
movl %ecx, %ss:-4*4(%eax)
popl %ecx
lea -4*4(%eax), %esp
popl %eax
.Lfinished_frame_\@:
.endm
.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 unwind_espfix=0
cld
.if \skip_gs == 0
PUSH_GS
.endif
pushl %fs
pushl %eax
movl $(__KERNEL_PERCPU), %eax
movl %eax, %fs
.if \unwind_espfix > 0
UNWIND_ESPFIX_STACK
.endif
popl %eax
FIXUP_FRAME
pushl %es
pushl %ds
pushl \pt_regs_ax
pushl %ebp
pushl %edi
pushl %esi
pushl %edx
pushl %ecx
pushl %ebx
movl $(__USER_DS), %edx
movl %edx, %ds
movl %edx, %es
.if \skip_gs == 0
SET_KERNEL_GS %edx
.endif
/* Switch to kernel stack if necessary */
.if \switch_stacks > 0
SWITCH_TO_KERNEL_STACK
.endif
.endm
.macro SAVE_ALL_NMI cr3_reg:req unwind_espfix=0
SAVE_ALL unwind_espfix=\unwind_espfix
BUG_IF_WRONG_CR3
/*
* Now switch the CR3 when PTI is enabled.
*
* We can enter with either user or kernel cr3, the code will
* store the old cr3 in \cr3_reg and switches to the kernel cr3
* if necessary.
*/
SWITCH_TO_KERNEL_CR3 scratch_reg=\cr3_reg
.Lend_\@:
.endm
.macro RESTORE_INT_REGS
popl %ebx
popl %ecx
popl %edx
popl %esi
popl %edi
popl %ebp
popl %eax
.endm
.macro RESTORE_REGS pop=0
RESTORE_INT_REGS
1: popl %ds
2: popl %es
3: popl %fs
POP_GS \pop
IRET_FRAME
.pushsection .fixup, "ax"
4: movl $0, (%esp)
jmp 1b
5: movl $0, (%esp)
jmp 2b
6: movl $0, (%esp)
jmp 3b
.popsection
_ASM_EXTABLE(1b, 4b)
_ASM_EXTABLE(2b, 5b)
_ASM_EXTABLE(3b, 6b)
POP_GS_EX
.endm
.macro RESTORE_ALL_NMI cr3_reg:req pop=0
/*
* Now switch the CR3 when PTI is enabled.
*
* We enter with kernel cr3 and switch the cr3 to the value
* stored on \cr3_reg, which is either a user or a kernel cr3.
*/
ALTERNATIVE "jmp .Lswitched_\@", "", X86_FEATURE_PTI
testl $PTI_SWITCH_MASK, \cr3_reg
jz .Lswitched_\@
/* User cr3 in \cr3_reg - write it to hardware cr3 */
movl \cr3_reg, %cr3
.Lswitched_\@:
BUG_IF_WRONG_CR3
RESTORE_REGS pop=\pop
.endm
.macro CHECK_AND_APPLY_ESPFIX
#ifdef CONFIG_X86_ESPFIX32
#define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8)
#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET
ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX
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
jne .Lend_\@ # returning to user-space with LDT SS
/*
* Setup and switch to ESPFIX stack
*
* We're returning to userspace with a 16 bit stack. The CPU will not
* restore the high word of ESP for us on executing iret... This is an
* "official" bug of all the x86-compatible CPUs, which we can work
* around to make dosemu and wine happy. We do this by preloading the
* high word of ESP with the high word of the userspace ESP while
* compensating for the offset by changing to the ESPFIX segment with
* a base address that matches for the difference.
*/
mov %esp, %edx /* load kernel esp */
mov PT_OLDESP(%esp), %eax /* load userspace esp */
mov %dx, %ax /* eax: new kernel esp */
sub %eax, %edx /* offset (low word is 0) */
shr $16, %edx
mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
pushl $__ESPFIX_SS
pushl %eax /* new kernel esp */
/*
* 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_ANY)
lss (%esp), %esp /* switch to espfix segment */
.Lend_\@:
#endif /* CONFIG_X86_ESPFIX32 */
.endm
/*
* Called with pt_regs fully populated and kernel segments loaded,
* so we can access PER_CPU and use the integer registers.
*
* We need to be very careful here with the %esp switch, because an NMI
* can happen everywhere. If the NMI handler finds itself on the
* entry-stack, it will overwrite the task-stack and everything we
* copied there. So allocate the stack-frame on the task-stack and
* switch to it before we do any copying.
*/
.macro SWITCH_TO_KERNEL_STACK
BUG_IF_WRONG_CR3
SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
/*
* %eax now contains the entry cr3 and we carry it forward in
* that register for the time this macro runs
*/
/* Are we on the entry stack? Bail out if not! */
movl PER_CPU_VAR(cpu_entry_area), %ecx
addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
subl %esp, %ecx /* ecx = (end of entry_stack) - esp */
cmpl $SIZEOF_entry_stack, %ecx
jae .Lend_\@
/* Load stack pointer into %esi and %edi */
movl %esp, %esi
movl %esi, %edi
/* Move %edi to the top of the entry stack */
andl $(MASK_entry_stack), %edi
addl $(SIZEOF_entry_stack), %edi
/* Load top of task-stack into %edi */
movl TSS_entry2task_stack(%edi), %edi
/* Special case - entry from kernel mode via entry stack */
#ifdef CONFIG_VM86
movl PT_EFLAGS(%esp), %ecx # mix EFLAGS and CS
movb PT_CS(%esp), %cl
andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %ecx
#else
movl PT_CS(%esp), %ecx
andl $SEGMENT_RPL_MASK, %ecx
#endif
cmpl $USER_RPL, %ecx
jb .Lentry_from_kernel_\@
/* Bytes to copy */
movl $PTREGS_SIZE, %ecx
#ifdef CONFIG_VM86
testl $X86_EFLAGS_VM, PT_EFLAGS(%esi)
jz .Lcopy_pt_regs_\@
/*
* Stack-frame contains 4 additional segment registers when
* coming from VM86 mode
*/
addl $(4 * 4), %ecx
#endif
.Lcopy_pt_regs_\@:
/* Allocate frame on task-stack */
subl %ecx, %edi
/* Switch to task-stack */
movl %edi, %esp
/*
* We are now on the task-stack and can safely copy over the
* stack-frame
*/
shrl $2, %ecx
cld
rep movsl
jmp .Lend_\@
.Lentry_from_kernel_\@:
/*
* This handles the case when we enter the kernel from
* kernel-mode and %esp points to the entry-stack. When this
* happens we need to switch to the task-stack to run C code,
* but switch back to the entry-stack again when we approach
* iret and return to the interrupted code-path. This usually
* happens when we hit an exception while restoring user-space
* segment registers on the way back to user-space or when the
* sysenter handler runs with eflags.tf set.
*
* When we switch to the task-stack here, we can't trust the
* contents of the entry-stack anymore, as the exception handler
* might be scheduled out or moved to another CPU. Therefore we
* copy the complete entry-stack to the task-stack and set a
* marker in the iret-frame (bit 31 of the CS dword) to detect
* what we've done on the iret path.
*
* On the iret path we copy everything back and switch to the
* entry-stack, so that the interrupted kernel code-path
* continues on the same stack it was interrupted with.
*
* Be aware that an NMI can happen anytime in this code.
*
* %esi: Entry-Stack pointer (same as %esp)
* %edi: Top of the task stack
* %eax: CR3 on kernel entry
*/
/* Calculate number of bytes on the entry stack in %ecx */
movl %esi, %ecx
/* %ecx to the top of entry-stack */
andl $(MASK_entry_stack), %ecx
addl $(SIZEOF_entry_stack), %ecx
/* Number of bytes on the entry stack to %ecx */
sub %esi, %ecx
/* Mark stackframe as coming from entry stack */
orl $CS_FROM_ENTRY_STACK, PT_CS(%esp)
/*
* Test the cr3 used to enter the kernel and add a marker
* so that we can switch back to it before iret.
*/
testl $PTI_SWITCH_MASK, %eax
jz .Lcopy_pt_regs_\@
orl $CS_FROM_USER_CR3, PT_CS(%esp)
/*
* %esi and %edi are unchanged, %ecx contains the number of
* bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate
* the stack-frame on task-stack and copy everything over
*/
jmp .Lcopy_pt_regs_\@
.Lend_\@:
.endm
/*
* Switch back from the kernel stack to the entry stack.
*
* The %esp register must point to pt_regs on the task stack. It will
* first calculate the size of the stack-frame to copy, depending on
* whether we return to VM86 mode or not. With that it uses 'rep movsl'
* to copy the contents of the stack over to the entry stack.
*
* We must be very careful here, as we can't trust the contents of the
* task-stack once we switched to the entry-stack. When an NMI happens
* while on the entry-stack, the NMI handler will switch back to the top
* of the task stack, overwriting our stack-frame we are about to copy.
* Therefore we switch the stack only after everything is copied over.
*/
.macro SWITCH_TO_ENTRY_STACK
/* Bytes to copy */
movl $PTREGS_SIZE, %ecx
#ifdef CONFIG_VM86
testl $(X86_EFLAGS_VM), PT_EFLAGS(%esp)
jz .Lcopy_pt_regs_\@
/* Additional 4 registers to copy when returning to VM86 mode */
addl $(4 * 4), %ecx
.Lcopy_pt_regs_\@:
#endif
/* Initialize source and destination for movsl */
movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
subl %ecx, %edi
movl %esp, %esi
/* Save future stack pointer in %ebx */
movl %edi, %ebx
/* Copy over the stack-frame */
shrl $2, %ecx
cld
rep movsl
/*
* Switch to entry-stack - needs to happen after everything is
* copied because the NMI handler will overwrite the task-stack
* when on entry-stack
*/
movl %ebx, %esp
.Lend_\@:
.endm
/*
* This macro handles the case when we return to kernel-mode on the iret
* path and have to switch back to the entry stack and/or user-cr3
*
* See the comments below the .Lentry_from_kernel_\@ label in the
* SWITCH_TO_KERNEL_STACK macro for more details.
*/
.macro PARANOID_EXIT_TO_KERNEL_MODE
/*
* Test if we entered the kernel with the entry-stack. Most
* likely we did not, because this code only runs on the
* return-to-kernel path.
*/
testl $CS_FROM_ENTRY_STACK, PT_CS(%esp)
jz .Lend_\@
/* Unlikely slow-path */
/* Clear marker from stack-frame */
andl $(~CS_FROM_ENTRY_STACK), PT_CS(%esp)
/* Copy the remaining task-stack contents to entry-stack */
movl %esp, %esi
movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
/* Bytes on the task-stack to ecx */
movl PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %ecx
subl %esi, %ecx
/* Allocate stack-frame on entry-stack */
subl %ecx, %edi
/*
* Save future stack-pointer, we must not switch until the
* copy is done, otherwise the NMI handler could destroy the
* contents of the task-stack we are about to copy.
*/
movl %edi, %ebx
/* Do the copy */
shrl $2, %ecx
cld
rep movsl
/* Safe to switch to entry-stack now */
movl %ebx, %esp
/*
* We came from entry-stack and need to check if we also need to
* switch back to user cr3.
*/
testl $CS_FROM_USER_CR3, PT_CS(%esp)
jz .Lend_\@
/* Clear marker from stack-frame */
andl $(~CS_FROM_USER_CR3), PT_CS(%esp)
SWITCH_TO_USER_CR3 scratch_reg=%eax
.Lend_\@:
.endm
/**
* idtentry - Macro to generate entry stubs for simple IDT entries
* @vector: Vector number
* @asmsym: ASM symbol for the entry point
* @cfunc: C function to be called
* @has_error_code: Hardware pushed error code on stack
*/
.macro idtentry vector asmsym cfunc has_error_code:req
SYM_CODE_START(\asmsym)
ASM_CLAC
cld
.if \has_error_code == 0
pushl $0 /* Clear the error code */
.endif
/* Push the C-function address into the GS slot */
pushl $\cfunc
/* Invoke the common exception entry */
jmp handle_exception
SYM_CODE_END(\asmsym)
.endm
.macro idtentry_irq vector cfunc
.p2align CONFIG_X86_L1_CACHE_SHIFT
SYM_CODE_START_LOCAL(asm_\cfunc)
ASM_CLAC
SAVE_ALL switch_stacks=1
ENCODE_FRAME_POINTER
movl %esp, %eax
movl PT_ORIG_EAX(%esp), %edx /* get the vector from stack */
movl $-1, PT_ORIG_EAX(%esp) /* no syscall to restart */
call \cfunc
jmp handle_exception_return
SYM_CODE_END(asm_\cfunc)
.endm
.macro idtentry_sysvec vector cfunc
idtentry \vector asm_\cfunc \cfunc has_error_code=0
.endm
/*
* Include the defines which emit the idt entries which are shared
* shared between 32 and 64 bit and emit the __irqentry_text_* markers
* so the stacktrace boundary checks work.
*/
.align 16
.globl __irqentry_text_start
__irqentry_text_start:
#include <asm/idtentry.h>
.align 16
.globl __irqentry_text_end
__irqentry_text_end:
/*
* %eax: prev task
* %edx: next task
*/
.pushsection .text, "ax"
SYM_CODE_START(__switch_to_asm)
/*
* Save callee-saved registers
* This must match the order in struct inactive_task_frame
*/
pushl %ebp
pushl %ebx
pushl %edi
pushl %esi
/*
* Flags are saved to prevent AC leakage. This could go
* away if objtool would have 32bit support to verify
* the STAC/CLAC correctness.
*/
pushfl
/* switch stack */
movl %esp, TASK_threadsp(%eax)
movl TASK_threadsp(%edx), %esp
#ifdef CONFIG_STACKPROTECTOR
movl TASK_stack_canary(%edx), %ebx
movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
#endif
#ifdef CONFIG_RETPOLINE
/*
* When switching from a shallower to a deeper call stack
* the RSB may either underflow or use entries populated
* with userspace addresses. On CPUs where those concerns
* exist, overwrite the RSB with entries which capture
* speculative execution to prevent attack.
*/
FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
#endif
/* Restore flags or the incoming task to restore AC state. */
popfl
/* restore callee-saved registers */
popl %esi
popl %edi
popl %ebx
popl %ebp
jmp __switch_to
SYM_CODE_END(__switch_to_asm)
.popsection
/*
* The unwinder expects the last frame on the stack to always be at the same
* offset from the end of the page, which allows it to validate the stack.
* Calling schedule_tail() directly would break that convention because its an
* asmlinkage function so its argument has to be pushed on the stack. This
* wrapper creates a proper "end of stack" frame header before the call.
*/
.pushsection .text, "ax"
SYM_FUNC_START(schedule_tail_wrapper)
FRAME_BEGIN
pushl %eax
call schedule_tail
popl %eax
FRAME_END
ret
SYM_FUNC_END(schedule_tail_wrapper)
.popsection
/*
* A newly forked process directly context switches into this address.
*
* eax: prev task we switched from
* ebx: kernel thread func (NULL for user thread)
* edi: kernel thread arg
*/
.pushsection .text, "ax"
SYM_CODE_START(ret_from_fork)
call schedule_tail_wrapper
testl %ebx, %ebx
jnz 1f /* kernel threads are uncommon */
2:
/* When we fork, we trace the syscall return in the child, too. */
movl %esp, %eax
call syscall_exit_to_user_mode
jmp .Lsyscall_32_done
/* kernel thread */
1: movl %edi, %eax
CALL_NOSPEC ebx
/*
* A kernel thread is allowed to return here after successfully
* calling kernel_execve(). Exit to userspace to complete the execve()
* syscall.
*/
movl $0, PT_EAX(%esp)
jmp 2b
SYM_CODE_END(ret_from_fork)
.popsection
SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE)
/*
* All code from here through __end_SYSENTER_singlestep_region is subject
* to being single-stepped if a user program sets TF and executes SYSENTER.
* There is absolutely nothing that we can do to prevent this from happening
* (thanks Intel!). To keep our handling of this situation as simple as
* possible, we handle TF just like AC and NT, except that our #DB handler
* will ignore all of the single-step traps generated in this range.
*/
/*
* 32-bit SYSENTER entry.
*
* 32-bit system calls through the vDSO's __kernel_vsyscall enter here
* if X86_FEATURE_SEP is available. This is the preferred system call
* entry on 32-bit systems.
*
* The SYSENTER instruction, in principle, should *only* occur in the
* vDSO. In practice, a small number of Android devices were shipped
* with a copy of Bionic that inlined a SYSENTER instruction. This
* never happened in any of Google's Bionic versions -- it only happened
* in a narrow range of Intel-provided versions.
*
* SYSENTER loads SS, ESP, CS, and EIP from previously programmed MSRs.
* IF and VM in RFLAGS are cleared (IOW: interrupts are off).
* SYSENTER does not save anything on the stack,
* and does not save old EIP (!!!), ESP, or EFLAGS.
*
* To avoid losing track of EFLAGS.VM (and thus potentially corrupting
* user and/or vm86 state), we explicitly disable the SYSENTER
* instruction in vm86 mode by reprogramming the MSRs.
*
* Arguments:
* eax system call number
* ebx arg1
* ecx arg2
* edx arg3
* esi arg4
* edi arg5
* ebp user stack
* 0(%ebp) arg6
*/
SYM_FUNC_START(entry_SYSENTER_32)
/*
* On entry-stack with all userspace-regs live - save and
* restore eflags and %eax to use it as scratch-reg for the cr3
* switch.
*/
pushfl
pushl %eax
BUG_IF_WRONG_CR3 no_user_check=1
SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
popl %eax
popfl
/* Stack empty again, switch to task stack */
movl TSS_entry2task_stack(%esp), %esp
.Lsysenter_past_esp:
pushl $__USER_DS /* pt_regs->ss */
pushl $0 /* pt_regs->sp (placeholder) */
pushfl /* pt_regs->flags (except IF = 0) */
pushl $__USER_CS /* pt_regs->cs */
pushl $0 /* pt_regs->ip = 0 (placeholder) */
pushl %eax /* pt_regs->orig_ax */
SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest, stack already switched */
/*
* SYSENTER doesn't filter flags, so we need to clear NT, AC
* and TF ourselves. To save a few cycles, we can check whether
* either was set instead of doing an unconditional popfq.
* This needs to happen before enabling interrupts so that
* we don't get preempted with NT set.
*
* If TF is set, we will single-step all the way to here -- do_debug
* will ignore all the traps. (Yes, this is slow, but so is
* single-stepping in general. This allows us to avoid having
* a more complicated code to handle the case where a user program
* forces us to single-step through the SYSENTER entry code.)
*
* NB.: .Lsysenter_fix_flags is a label with the code under it moved
* out-of-line as an optimization: NT is unlikely to be set in the
* majority of the cases and instead of polluting the I$ unnecessarily,
* we're keeping that code behind a branch which will predict as
* not-taken and therefore its instructions won't be fetched.
*/
testl $X86_EFLAGS_NT|X86_EFLAGS_AC|X86_EFLAGS_TF, PT_EFLAGS(%esp)
jnz .Lsysenter_fix_flags
.Lsysenter_flags_fixed:
movl %esp, %eax
call do_SYSENTER_32
testl %eax, %eax
jz .Lsyscall_32_done
STACKLEAK_ERASE
/* Opportunistic SYSEXIT */
/*
* Setup entry stack - we keep the pointer in %eax and do the
* switch after almost all user-state is restored.
*/
/* Load entry stack pointer and allocate frame for eflags/eax */
movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %eax
subl $(2*4), %eax
/* Copy eflags and eax to entry stack */
movl PT_EFLAGS(%esp), %edi
movl PT_EAX(%esp), %esi
movl %edi, (%eax)
movl %esi, 4(%eax)
/* Restore user registers and segments */
movl PT_EIP(%esp), %edx /* pt_regs->ip */
movl PT_OLDESP(%esp), %ecx /* pt_regs->sp */
1: mov PT_FS(%esp), %fs
PTGS_TO_GS
popl %ebx /* pt_regs->bx */
addl $2*4, %esp /* skip pt_regs->cx and pt_regs->dx */
popl %esi /* pt_regs->si */
popl %edi /* pt_regs->di */
popl %ebp /* pt_regs->bp */
/* Switch to entry stack */
movl %eax, %esp
/* Now ready to switch the cr3 */
SWITCH_TO_USER_CR3 scratch_reg=%eax
/*
* Restore all flags except IF. (We restore IF separately because
* STI gives a one-instruction window in which we won't be interrupted,
* whereas POPF does not.)
*/
btrl $X86_EFLAGS_IF_BIT, (%esp)
BUG_IF_WRONG_CR3 no_user_check=1
popfl
popl %eax
/*
* Return back to the vDSO, which will pop ecx and edx.
* Don't bother with DS and ES (they already contain __USER_DS).
*/
sti
sysexit
.pushsection .fixup, "ax"
2: movl $0, PT_FS(%esp)
jmp 1b
.popsection
_ASM_EXTABLE(1b, 2b)
PTGS_TO_GS_EX
.Lsysenter_fix_flags:
pushl $X86_EFLAGS_FIXED
popfl
jmp .Lsysenter_flags_fixed
SYM_ENTRY(__end_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE)
SYM_FUNC_END(entry_SYSENTER_32)
/*
* 32-bit legacy system call entry.
*
* 32-bit x86 Linux system calls traditionally used the INT $0x80
* instruction. INT $0x80 lands here.
*
* This entry point can be used by any 32-bit perform system calls.
* Instances of INT $0x80 can be found inline in various programs and
* libraries. It is also used by the vDSO's __kernel_vsyscall
* fallback for hardware that doesn't support a faster entry method.
* Restarted 32-bit system calls also fall back to INT $0x80
* regardless of what instruction was originally used to do the system
* call. (64-bit programs can use INT $0x80 as well, but they can
* only run on 64-bit kernels and therefore land in
* entry_INT80_compat.)
*
* This is considered a slow path. It is not used by most libc
* implementations on modern hardware except during process startup.
*
* Arguments:
* eax system call number
* ebx arg1
* ecx arg2
* edx arg3
* esi arg4
* edi arg5
* ebp arg6
*/
SYM_FUNC_START(entry_INT80_32)
ASM_CLAC
pushl %eax /* pt_regs->orig_ax */
SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1 /* save rest */
movl %esp, %eax
call do_int80_syscall_32
.Lsyscall_32_done:
STACKLEAK_ERASE
restore_all_switch_stack:
SWITCH_TO_ENTRY_STACK
CHECK_AND_APPLY_ESPFIX
/* Switch back to user CR3 */
SWITCH_TO_USER_CR3 scratch_reg=%eax
BUG_IF_WRONG_CR3
/* Restore user state */
RESTORE_REGS pop=4 # skip orig_eax/error_code
.Lirq_return:
/*
* ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
* when returning from IPI handler and when returning from
* scheduler to user-space.
*/
INTERRUPT_RETURN
.section .fixup, "ax"
SYM_CODE_START(asm_iret_error)
pushl $0 # no error code
pushl $iret_error
#ifdef CONFIG_DEBUG_ENTRY
/*
* The stack-frame here is the one that iret faulted on, so its a
* return-to-user frame. We are on kernel-cr3 because we come here from
* the fixup code. This confuses the CR3 checker, so switch to user-cr3
* as the checker expects it.
*/
pushl %eax
SWITCH_TO_USER_CR3 scratch_reg=%eax
popl %eax
#endif
jmp handle_exception
SYM_CODE_END(asm_iret_error)
.previous
_ASM_EXTABLE(.Lirq_return, asm_iret_error)
SYM_FUNC_END(entry_INT80_32)
.macro FIXUP_ESPFIX_STACK
/*
* Switch back for ESPFIX stack to the normal zerobased stack
*
* We can't call C functions using the ESPFIX stack. This code reads
* the high word of the segment base from the GDT and swiches to the
* normal stack and adjusts ESP with the matching offset.
*
* We might be on user CR3 here, so percpu data is not mapped and we can't
* access the GDT through the percpu segment. Instead, use SGDT to find
* the cpu_entry_area alias of the GDT.
*/
#ifdef CONFIG_X86_ESPFIX32
/* fixup the stack */
pushl %ecx
subl $2*4, %esp
sgdt (%esp)
movl 2(%esp), %ecx /* GDT address */
/*
* Careful: ECX is a linear pointer, so we need to force base
* zero. %cs is the only known-linear segment we have right now.
*/
mov %cs:GDT_ESPFIX_OFFSET + 4(%ecx), %al /* bits 16..23 */
mov %cs:GDT_ESPFIX_OFFSET + 7(%ecx), %ah /* bits 24..31 */
shl $16, %eax
addl $2*4, %esp
popl %ecx
addl %esp, %eax /* the adjusted stack pointer */
pushl $__KERNEL_DS
pushl %eax
lss (%esp), %esp /* switch to the normal stack segment */
#endif
.endm
.macro UNWIND_ESPFIX_STACK
/* It's safe to clobber %eax, all other regs need to be preserved */
#ifdef CONFIG_X86_ESPFIX32
movl %ss, %eax
/* see if on espfix stack */
cmpw $__ESPFIX_SS, %ax
jne .Lno_fixup_\@
/* switch to normal stack */
FIXUP_ESPFIX_STACK
.Lno_fixup_\@:
#endif
.endm
SYM_CODE_START_LOCAL_NOALIGN(handle_exception)
/* the function address is in %gs's slot on the stack */
SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
ENCODE_FRAME_POINTER
/* fixup %gs */
GS_TO_REG %ecx
movl PT_GS(%esp), %edi # get the function address
REG_TO_PTGS %ecx
SET_KERNEL_GS %ecx
/* fixup orig %eax */
movl PT_ORIG_EAX(%esp), %edx # get the error code
movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
movl %esp, %eax # pt_regs pointer
CALL_NOSPEC edi
handle_exception_return:
#ifdef CONFIG_VM86
movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
movb PT_CS(%esp), %al
andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
#else
/*
* We can be coming here from child spawned by kernel_thread().
*/
movl PT_CS(%esp), %eax
andl $SEGMENT_RPL_MASK, %eax
#endif
cmpl $USER_RPL, %eax # returning to v8086 or userspace ?
jnb ret_to_user
PARANOID_EXIT_TO_KERNEL_MODE
BUG_IF_WRONG_CR3
RESTORE_REGS 4
jmp .Lirq_return
ret_to_user:
movl %esp, %eax
jmp restore_all_switch_stack
SYM_CODE_END(handle_exception)
SYM_CODE_START(asm_exc_double_fault)
1:
/*
* This is a task gate handler, not an interrupt gate handler.
* The error code is on the stack, but the stack is otherwise
* empty. Interrupts are off. Our state is sane with the following
* exceptions:
*
* - CR0.TS is set. "TS" literally means "task switched".
* - EFLAGS.NT is set because we're a "nested task".
* - The doublefault TSS has back_link set and has been marked busy.
* - TR points to the doublefault TSS and the normal TSS is busy.
* - CR3 is the normal kernel PGD. This would be delightful, except
* that the CPU didn't bother to save the old CR3 anywhere. This
* would make it very awkward to return back to the context we came
* from.
*
* The rest of EFLAGS is sanitized for us, so we don't need to
* worry about AC or DF.
*
* Don't even bother popping the error code. It's always zero,
* and ignoring it makes us a bit more robust against buggy
* hypervisor task gate implementations.
*
* We will manually undo the task switch instead of doing a
* task-switching IRET.
*/
clts /* clear CR0.TS */
pushl $X86_EFLAGS_FIXED
popfl /* clear EFLAGS.NT */
call doublefault_shim
/* We don't support returning, so we have no IRET here. */
1:
hlt
jmp 1b
SYM_CODE_END(asm_exc_double_fault)
/*
* NMI is doubly nasty. It can happen on the first instruction of
* entry_SYSENTER_32 (just like #DB), but it can also interrupt the beginning
* of the #DB handler even if that #DB in turn hit before entry_SYSENTER_32
* switched stacks. We handle both conditions by simply checking whether we
* interrupted kernel code running on the SYSENTER stack.
*/
SYM_CODE_START(asm_exc_nmi)
ASM_CLAC
#ifdef CONFIG_X86_ESPFIX32
/*
* ESPFIX_SS is only ever set on the return to user path
* after we've switched to the entry stack.
*/
pushl %eax
movl %ss, %eax
cmpw $__ESPFIX_SS, %ax
popl %eax
je .Lnmi_espfix_stack
#endif
pushl %eax # pt_regs->orig_ax
SAVE_ALL_NMI cr3_reg=%edi
ENCODE_FRAME_POINTER
xorl %edx, %edx # zero error code
movl %esp, %eax # pt_regs pointer
/* Are we currently on the SYSENTER stack? */
movl PER_CPU_VAR(cpu_entry_area), %ecx
addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
subl %eax, %ecx /* ecx = (end of entry_stack) - esp */
cmpl $SIZEOF_entry_stack, %ecx
jb .Lnmi_from_sysenter_stack
/* Not on SYSENTER stack. */
call exc_nmi
jmp .Lnmi_return
.Lnmi_from_sysenter_stack:
/*
* We're on the SYSENTER stack. Switch off. No one (not even debug)
* is using the thread stack right now, so it's safe for us to use it.
*/
movl %esp, %ebx
movl PER_CPU_VAR(cpu_current_top_of_stack), %esp
call exc_nmi
movl %ebx, %esp
.Lnmi_return:
#ifdef CONFIG_X86_ESPFIX32
testl $CS_FROM_ESPFIX, PT_CS(%esp)
jnz .Lnmi_from_espfix
#endif
CHECK_AND_APPLY_ESPFIX
RESTORE_ALL_NMI cr3_reg=%edi pop=4
jmp .Lirq_return
#ifdef CONFIG_X86_ESPFIX32
.Lnmi_espfix_stack:
/*
* Create the pointer to LSS back
*/
pushl %ss
pushl %esp
addl $4, (%esp)
/* Copy the (short) IRET frame */
pushl 4*4(%esp) # flags
pushl 4*4(%esp) # cs
pushl 4*4(%esp) # ip
pushl %eax # orig_ax
SAVE_ALL_NMI cr3_reg=%edi unwind_espfix=1
ENCODE_FRAME_POINTER
/* clear CS_FROM_KERNEL, set CS_FROM_ESPFIX */
xorl $(CS_FROM_ESPFIX | CS_FROM_KERNEL), PT_CS(%esp)
xorl %edx, %edx # zero error code
movl %esp, %eax # pt_regs pointer
jmp .Lnmi_from_sysenter_stack
.Lnmi_from_espfix:
RESTORE_ALL_NMI cr3_reg=%edi
/*
* Because we cleared CS_FROM_KERNEL, IRET_FRAME 'forgot' to
* fix up the gap and long frame:
*
* 3 - original frame (exception)
* 2 - ESPFIX block (above)
* 6 - gap (FIXUP_FRAME)
* 5 - long frame (FIXUP_FRAME)
* 1 - orig_ax
*/
lss (1+5+6)*4(%esp), %esp # back to espfix stack
jmp .Lirq_return
#endif
SYM_CODE_END(asm_exc_nmi)
.pushsection .text, "ax"
SYM_CODE_START(rewind_stack_do_exit)
/* Prevent any naive code from trying to unwind to our caller. */
xorl %ebp, %ebp
movl PER_CPU_VAR(cpu_current_top_of_stack), %esi
leal -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
call do_exit
1: jmp 1b
SYM_CODE_END(rewind_stack_do_exit)
.popsection