mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-15 23:14:31 +08:00
cf00764747
Since commit4e57a4ddf6
("ARM: 9107/1: syscall: always store thread_info->abi_syscall"), the seccomp selftests "syscall_restart" has been broken. This was caused by the restart syscall not being stored to "abi_syscall" during restart setup before branching to the "local_restart" label. Tracers would see the wrong syscall, and scno would get overwritten while returning from the TIF_WORK path. Add the missing store. Cc: Russell King <linux@armlinux.org.uk> Cc: Arnd Bergmann <arnd@kernel.org> Cc: Lecopzer Chen <lecopzer.chen@mediatek.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: linux-arm-kernel@lists.infradead.org Fixes:4e57a4ddf6
("ARM: 9107/1: syscall: always store thread_info->abi_syscall") Reviewed-by: Arnd Bergmann <arnd@arndb.de> Link: https://lore.kernel.org/r/20230810195422.2304827-1-keescook@chromium.org Signed-off-by: Kees Cook <keescook@chromium.org>
462 lines
11 KiB
ArmAsm
462 lines
11 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* linux/arch/arm/kernel/entry-common.S
|
|
*
|
|
* Copyright (C) 2000 Russell King
|
|
*/
|
|
|
|
#include <asm/assembler.h>
|
|
#include <asm/unistd.h>
|
|
#include <asm/ftrace.h>
|
|
#include <asm/unwind.h>
|
|
#include <asm/page.h>
|
|
#ifdef CONFIG_AEABI
|
|
#include <asm/unistd-oabi.h>
|
|
#endif
|
|
|
|
.equ NR_syscalls, __NR_syscalls
|
|
|
|
#include "entry-header.S"
|
|
|
|
saved_psr .req r8
|
|
#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING_USER)
|
|
saved_pc .req r9
|
|
#define TRACE(x...) x
|
|
#else
|
|
saved_pc .req lr
|
|
#define TRACE(x...)
|
|
#endif
|
|
|
|
.section .entry.text,"ax",%progbits
|
|
.align 5
|
|
#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING_USER) || \
|
|
IS_ENABLED(CONFIG_DEBUG_RSEQ))
|
|
/*
|
|
* This is the fast syscall return path. We do as little as possible here,
|
|
* such as avoiding writing r0 to the stack. We only use this path if we
|
|
* have tracing, context tracking and rseq debug disabled - the overheads
|
|
* from those features make this path too inefficient.
|
|
*/
|
|
ret_fast_syscall:
|
|
__ret_fast_syscall:
|
|
UNWIND(.fnstart )
|
|
UNWIND(.cantunwind )
|
|
disable_irq_notrace @ disable interrupts
|
|
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
|
|
movs r1, r1, lsl #16
|
|
bne fast_work_pending
|
|
|
|
restore_user_regs fast = 1, offset = S_OFF
|
|
UNWIND(.fnend )
|
|
ENDPROC(ret_fast_syscall)
|
|
|
|
/* Ok, we need to do extra processing, enter the slow path. */
|
|
fast_work_pending:
|
|
str r0, [sp, #S_R0+S_OFF]! @ returned r0
|
|
/* fall through to work_pending */
|
|
#else
|
|
/*
|
|
* The "replacement" ret_fast_syscall for when tracing, context tracking,
|
|
* or rseq debug is enabled. As we will need to call out to some C functions,
|
|
* we save r0 first to avoid needing to save registers around each C function
|
|
* call.
|
|
*/
|
|
ret_fast_syscall:
|
|
__ret_fast_syscall:
|
|
UNWIND(.fnstart )
|
|
UNWIND(.cantunwind )
|
|
str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
|
|
#if IS_ENABLED(CONFIG_DEBUG_RSEQ)
|
|
/* do_rseq_syscall needs interrupts enabled. */
|
|
mov r0, sp @ 'regs'
|
|
bl do_rseq_syscall
|
|
#endif
|
|
disable_irq_notrace @ disable interrupts
|
|
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
|
|
movs r1, r1, lsl #16
|
|
beq no_work_pending
|
|
UNWIND(.fnend )
|
|
ENDPROC(ret_fast_syscall)
|
|
|
|
/* Slower path - fall through to work_pending */
|
|
#endif
|
|
|
|
tst r1, #_TIF_SYSCALL_WORK
|
|
bne __sys_trace_return_nosave
|
|
slow_work_pending:
|
|
mov r0, sp @ 'regs'
|
|
mov r2, why @ 'syscall'
|
|
bl do_work_pending
|
|
cmp r0, #0
|
|
beq no_work_pending
|
|
movlt scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE)
|
|
str scno, [tsk, #TI_ABI_SYSCALL] @ make sure tracers see update
|
|
ldmia sp, {r0 - r6} @ have to reload r0 - r6
|
|
b local_restart @ ... and off we go
|
|
ENDPROC(ret_fast_syscall)
|
|
|
|
/*
|
|
* "slow" syscall return path. "why" tells us if this was a real syscall.
|
|
* IRQs may be enabled here, so always disable them. Note that we use the
|
|
* "notrace" version to avoid calling into the tracing code unnecessarily.
|
|
* do_work_pending() will update this state if necessary.
|
|
*/
|
|
ENTRY(ret_to_user)
|
|
ret_slow_syscall:
|
|
#if IS_ENABLED(CONFIG_DEBUG_RSEQ)
|
|
/* do_rseq_syscall needs interrupts enabled. */
|
|
enable_irq_notrace @ enable interrupts
|
|
mov r0, sp @ 'regs'
|
|
bl do_rseq_syscall
|
|
#endif
|
|
disable_irq_notrace @ disable interrupts
|
|
ENTRY(ret_to_user_from_irq)
|
|
ldr r1, [tsk, #TI_FLAGS]
|
|
movs r1, r1, lsl #16
|
|
bne slow_work_pending
|
|
no_work_pending:
|
|
asm_trace_hardirqs_on save = 0
|
|
|
|
ct_user_enter save = 0
|
|
|
|
restore_user_regs fast = 0, offset = 0
|
|
ENDPROC(ret_to_user_from_irq)
|
|
ENDPROC(ret_to_user)
|
|
|
|
/*
|
|
* This is how we return from a fork.
|
|
*/
|
|
ENTRY(ret_from_fork)
|
|
bl schedule_tail
|
|
cmp r5, #0
|
|
movne r0, r4
|
|
badrne lr, 1f
|
|
retne r5
|
|
1: get_thread_info tsk
|
|
b ret_slow_syscall
|
|
ENDPROC(ret_from_fork)
|
|
|
|
/*=============================================================================
|
|
* SWI handler
|
|
*-----------------------------------------------------------------------------
|
|
*/
|
|
|
|
.align 5
|
|
#ifdef CONFIG_HARDEN_BRANCH_HISTORY
|
|
ENTRY(vector_bhb_loop8_swi)
|
|
sub sp, sp, #PT_REGS_SIZE
|
|
stmia sp, {r0 - r12}
|
|
mov r8, #8
|
|
1: b 2f
|
|
2: subs r8, r8, #1
|
|
bne 1b
|
|
dsb nsh
|
|
isb
|
|
b 3f
|
|
ENDPROC(vector_bhb_loop8_swi)
|
|
|
|
.align 5
|
|
ENTRY(vector_bhb_bpiall_swi)
|
|
sub sp, sp, #PT_REGS_SIZE
|
|
stmia sp, {r0 - r12}
|
|
mcr p15, 0, r8, c7, c5, 6 @ BPIALL
|
|
isb
|
|
b 3f
|
|
ENDPROC(vector_bhb_bpiall_swi)
|
|
#endif
|
|
.align 5
|
|
ENTRY(vector_swi)
|
|
#ifdef CONFIG_CPU_V7M
|
|
v7m_exception_entry
|
|
#else
|
|
sub sp, sp, #PT_REGS_SIZE
|
|
stmia sp, {r0 - r12} @ Calling r0 - r12
|
|
3:
|
|
ARM( add r8, sp, #S_PC )
|
|
ARM( stmdb r8, {sp, lr}^ ) @ Calling sp, lr
|
|
THUMB( mov r8, sp )
|
|
THUMB( store_user_sp_lr r8, r10, S_SP ) @ calling sp, lr
|
|
mrs saved_psr, spsr @ called from non-FIQ mode, so ok.
|
|
TRACE( mov saved_pc, lr )
|
|
str saved_pc, [sp, #S_PC] @ Save calling PC
|
|
str saved_psr, [sp, #S_PSR] @ Save CPSR
|
|
str r0, [sp, #S_OLD_R0] @ Save OLD_R0
|
|
#endif
|
|
reload_current r10, ip
|
|
zero_fp
|
|
alignment_trap r10, ip, cr_alignment
|
|
asm_trace_hardirqs_on save=0
|
|
enable_irq_notrace
|
|
ct_user_exit save=0
|
|
|
|
/*
|
|
* Get the system call number.
|
|
*/
|
|
|
|
#if defined(CONFIG_OABI_COMPAT)
|
|
|
|
/*
|
|
* If we have CONFIG_OABI_COMPAT then we need to look at the swi
|
|
* value to determine if it is an EABI or an old ABI call.
|
|
*/
|
|
#ifdef CONFIG_ARM_THUMB
|
|
tst saved_psr, #PSR_T_BIT
|
|
movne r10, #0 @ no thumb OABI emulation
|
|
USER( ldreq r10, [saved_pc, #-4] ) @ get SWI instruction
|
|
#else
|
|
USER( ldr r10, [saved_pc, #-4] ) @ get SWI instruction
|
|
#endif
|
|
ARM_BE8(rev r10, r10) @ little endian instruction
|
|
|
|
#elif defined(CONFIG_AEABI)
|
|
|
|
/*
|
|
* Pure EABI user space always put syscall number into scno (r7).
|
|
*/
|
|
#elif defined(CONFIG_ARM_THUMB)
|
|
/* Legacy ABI only, possibly thumb mode. */
|
|
tst saved_psr, #PSR_T_BIT @ this is SPSR from save_user_regs
|
|
addne scno, r7, #__NR_SYSCALL_BASE @ put OS number in
|
|
USER( ldreq scno, [saved_pc, #-4] )
|
|
|
|
#else
|
|
/* Legacy ABI only. */
|
|
USER( ldr scno, [saved_pc, #-4] ) @ get SWI instruction
|
|
#endif
|
|
|
|
/* saved_psr and saved_pc are now dead */
|
|
|
|
uaccess_disable tbl
|
|
get_thread_info tsk
|
|
|
|
adr tbl, sys_call_table @ load syscall table pointer
|
|
|
|
#if defined(CONFIG_OABI_COMPAT)
|
|
/*
|
|
* If the swi argument is zero, this is an EABI call and we do nothing.
|
|
*
|
|
* If this is an old ABI call, get the syscall number into scno and
|
|
* get the old ABI syscall table address.
|
|
*/
|
|
bics r10, r10, #0xff000000
|
|
strne r10, [tsk, #TI_ABI_SYSCALL]
|
|
streq scno, [tsk, #TI_ABI_SYSCALL]
|
|
eorne scno, r10, #__NR_OABI_SYSCALL_BASE
|
|
ldrne tbl, =sys_oabi_call_table
|
|
#elif !defined(CONFIG_AEABI)
|
|
bic scno, scno, #0xff000000 @ mask off SWI op-code
|
|
str scno, [tsk, #TI_ABI_SYSCALL]
|
|
eor scno, scno, #__NR_SYSCALL_BASE @ check OS number
|
|
#else
|
|
str scno, [tsk, #TI_ABI_SYSCALL]
|
|
#endif
|
|
/*
|
|
* Reload the registers that may have been corrupted on entry to
|
|
* the syscall assembly (by tracing or context tracking.)
|
|
*/
|
|
TRACE( ldmia sp, {r0 - r3} )
|
|
|
|
local_restart:
|
|
ldr r10, [tsk, #TI_FLAGS] @ check for syscall tracing
|
|
stmdb sp!, {r4, r5} @ push fifth and sixth args
|
|
|
|
tst r10, #_TIF_SYSCALL_WORK @ are we tracing syscalls?
|
|
bne __sys_trace
|
|
|
|
invoke_syscall tbl, scno, r10, __ret_fast_syscall
|
|
|
|
add r1, sp, #S_OFF
|
|
2: cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
|
|
eor r0, scno, #__NR_SYSCALL_BASE @ put OS number back
|
|
bcs arm_syscall
|
|
mov why, #0 @ no longer a real syscall
|
|
b sys_ni_syscall @ not private func
|
|
|
|
#if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)
|
|
/*
|
|
* We failed to handle a fault trying to access the page
|
|
* containing the swi instruction, but we're not really in a
|
|
* position to return -EFAULT. Instead, return back to the
|
|
* instruction and re-enter the user fault handling path trying
|
|
* to page it in. This will likely result in sending SEGV to the
|
|
* current task.
|
|
*/
|
|
9001:
|
|
sub lr, saved_pc, #4
|
|
str lr, [sp, #S_PC]
|
|
get_thread_info tsk
|
|
b ret_fast_syscall
|
|
#endif
|
|
ENDPROC(vector_swi)
|
|
.ltorg
|
|
|
|
/*
|
|
* This is the really slow path. We're going to be doing
|
|
* context switches, and waiting for our parent to respond.
|
|
*/
|
|
__sys_trace:
|
|
add r0, sp, #S_OFF
|
|
bl syscall_trace_enter
|
|
mov scno, r0
|
|
invoke_syscall tbl, scno, r10, __sys_trace_return, reload=1
|
|
cmp scno, #-1 @ skip the syscall?
|
|
bne 2b
|
|
add sp, sp, #S_OFF @ restore stack
|
|
|
|
__sys_trace_return_nosave:
|
|
enable_irq_notrace
|
|
mov r0, sp
|
|
bl syscall_trace_exit
|
|
b ret_slow_syscall
|
|
|
|
__sys_trace_return:
|
|
str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
|
|
mov r0, sp
|
|
bl syscall_trace_exit
|
|
b ret_slow_syscall
|
|
|
|
.macro syscall_table_start, sym
|
|
.equ __sys_nr, 0
|
|
.type \sym, #object
|
|
ENTRY(\sym)
|
|
.endm
|
|
|
|
.macro syscall, nr, func
|
|
.ifgt __sys_nr - \nr
|
|
.error "Duplicated/unorded system call entry"
|
|
.endif
|
|
.rept \nr - __sys_nr
|
|
.long sys_ni_syscall
|
|
.endr
|
|
.long \func
|
|
.equ __sys_nr, \nr + 1
|
|
.endm
|
|
|
|
.macro syscall_table_end, sym
|
|
.ifgt __sys_nr - __NR_syscalls
|
|
.error "System call table too big"
|
|
.endif
|
|
.rept __NR_syscalls - __sys_nr
|
|
.long sys_ni_syscall
|
|
.endr
|
|
.size \sym, . - \sym
|
|
.endm
|
|
|
|
#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native)
|
|
#define __SYSCALL(nr, func) syscall nr, func
|
|
|
|
/*
|
|
* This is the syscall table declaration for native ABI syscalls.
|
|
* With EABI a couple syscalls are obsolete and defined as sys_ni_syscall.
|
|
*/
|
|
syscall_table_start sys_call_table
|
|
#ifdef CONFIG_AEABI
|
|
#include <calls-eabi.S>
|
|
#else
|
|
#include <calls-oabi.S>
|
|
#endif
|
|
syscall_table_end sys_call_table
|
|
|
|
/*============================================================================
|
|
* Special system call wrappers
|
|
*/
|
|
@ r0 = syscall number
|
|
@ r8 = syscall table
|
|
sys_syscall:
|
|
bic scno, r0, #__NR_OABI_SYSCALL_BASE
|
|
cmp scno, #__NR_syscall - __NR_SYSCALL_BASE
|
|
cmpne scno, #NR_syscalls @ check range
|
|
#ifdef CONFIG_CPU_SPECTRE
|
|
movhs scno, #0
|
|
csdb
|
|
#endif
|
|
stmialo sp, {r5, r6} @ shuffle args
|
|
movlo r0, r1
|
|
movlo r1, r2
|
|
movlo r2, r3
|
|
movlo r3, r4
|
|
ldrlo pc, [tbl, scno, lsl #2]
|
|
b sys_ni_syscall
|
|
ENDPROC(sys_syscall)
|
|
|
|
sys_sigreturn_wrapper:
|
|
add r0, sp, #S_OFF
|
|
mov why, #0 @ prevent syscall restart handling
|
|
b sys_sigreturn
|
|
ENDPROC(sys_sigreturn_wrapper)
|
|
|
|
sys_rt_sigreturn_wrapper:
|
|
add r0, sp, #S_OFF
|
|
mov why, #0 @ prevent syscall restart handling
|
|
b sys_rt_sigreturn
|
|
ENDPROC(sys_rt_sigreturn_wrapper)
|
|
|
|
sys_statfs64_wrapper:
|
|
teq r1, #88
|
|
moveq r1, #84
|
|
b sys_statfs64
|
|
ENDPROC(sys_statfs64_wrapper)
|
|
|
|
sys_fstatfs64_wrapper:
|
|
teq r1, #88
|
|
moveq r1, #84
|
|
b sys_fstatfs64
|
|
ENDPROC(sys_fstatfs64_wrapper)
|
|
|
|
/*
|
|
* Note: off_4k (r5) is always units of 4K. If we can't do the requested
|
|
* offset, we return EINVAL.
|
|
*/
|
|
sys_mmap2:
|
|
str r5, [sp, #4]
|
|
b sys_mmap_pgoff
|
|
ENDPROC(sys_mmap2)
|
|
|
|
#ifdef CONFIG_OABI_COMPAT
|
|
|
|
/*
|
|
* These are syscalls with argument register differences
|
|
*/
|
|
|
|
sys_oabi_pread64:
|
|
stmia sp, {r3, r4}
|
|
b sys_pread64
|
|
ENDPROC(sys_oabi_pread64)
|
|
|
|
sys_oabi_pwrite64:
|
|
stmia sp, {r3, r4}
|
|
b sys_pwrite64
|
|
ENDPROC(sys_oabi_pwrite64)
|
|
|
|
sys_oabi_truncate64:
|
|
mov r3, r2
|
|
mov r2, r1
|
|
b sys_truncate64
|
|
ENDPROC(sys_oabi_truncate64)
|
|
|
|
sys_oabi_ftruncate64:
|
|
mov r3, r2
|
|
mov r2, r1
|
|
b sys_ftruncate64
|
|
ENDPROC(sys_oabi_ftruncate64)
|
|
|
|
sys_oabi_readahead:
|
|
str r3, [sp]
|
|
mov r3, r2
|
|
mov r2, r1
|
|
b sys_readahead
|
|
ENDPROC(sys_oabi_readahead)
|
|
|
|
/*
|
|
* Let's declare a second syscall table for old ABI binaries
|
|
* using the compatibility syscall entries.
|
|
*/
|
|
syscall_table_start sys_oabi_call_table
|
|
#undef __SYSCALL_WITH_COMPAT
|
|
#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat)
|
|
#include <calls-oabi.S>
|
|
syscall_table_end sys_oabi_call_table
|
|
|
|
#endif
|
|
|