linux/arch/m68k/kernel/entry.S
Michael Schmitz da89ce46f0 m68k: Fix spinlock race in kernel thread creation
Context switching does take care to retain the correct lock owner across
the switch from 'prev' to 'next' tasks.  This does rely on interrupts
remaining disabled for the entire duration of the switch.

This condition is guaranteed for normal process creation and context
switching between already running processes, because both 'prev' and
'next' already have interrupts disabled in their saved copies of the
status register.

The situation is different for newly created kernel threads.  The status
register is set to PS_S in copy_thread(), which does leave the IPL at 0.
Upon restoring the 'next' thread's status register in switch_to() aka
resume(), interrupts then become enabled prematurely.  resume() then
returns via ret_from_kernel_thread() and schedule_tail() where run queue
lock is released (see finish_task_switch() and finish_lock_switch()).

A timer interrupt calling scheduler_tick() before the lock is released
in finish_task_switch() will find the lock already taken, with the
current task as lock owner.  This causes a spinlock recursion warning as
reported by Guenter Roeck.

As far as I can ascertain, this race has been opened in commit
533e6903be ("m68k: split ret_from_fork(), simplify kernel_thread()")
but I haven't done a detailed study of kernel history so it may well
predate that commit.

Interrupts cannot be disabled in the saved status register copy for
kernel threads (init will complain about interrupts disabled when
finally starting user space).  Disable interrupts temporarily when
switching the tasks' register sets in resume().

Note that a simple oriw 0x700,%sr after restoring sr is not enough here
- this leaves enough of a race for the 'spinlock recursion' warning to
still be observed.

Tested on ARAnyM and qemu (Quadra 800 emulation).

Fixes: 533e6903be ("m68k: split ret_from_fork(), simplify kernel_thread()")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Closes: https://lore.kernel.org/all/07811b26-677c-4d05-aeb4-996cd880b789@roeck-us.net
Signed-off-by: Michael Schmitz <schmitzmic@gmail.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20240411033631.16335-1-schmitzmic@gmail.com
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2024-05-08 17:43:22 +02:00

440 lines
9.7 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0-or-later
* -*- mode: asm -*-
*
* linux/arch/m68k/kernel/entry.S
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Linux/m68k support by Hamish Macdonald
*
* 68060 fixes by Jesper Skov
*
*/
/*
* 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.
*
*/
/*
* 12/03/96 Jes: Currently we only support m68k single-cpu systems, so
* all pointers that used to be 'current' are now entry
* number 0 in the 'current_set' list.
*
* 6/05/00 RZ: addedd writeback completion after return from sighandler
* for 68040
*/
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/setup.h>
#include <asm/traps.h>
#include <asm/unistd.h>
#include <asm/asm-offsets.h>
#include <asm/entry.h>
.globl system_call, buserr, trap, resume
.globl sys_call_table
.globl __sys_fork, __sys_clone, __sys_vfork
.globl bad_interrupt
.globl auto_irqhandler_fixup
.globl user_irqvec_fixup
.text
ENTRY(__sys_fork)
SAVE_SWITCH_STACK
jbsr sys_fork
lea %sp@(24),%sp
rts
ENTRY(__sys_clone)
SAVE_SWITCH_STACK
pea %sp@(SWITCH_STACK_SIZE)
jbsr m68k_clone
lea %sp@(28),%sp
rts
ENTRY(__sys_vfork)
SAVE_SWITCH_STACK
jbsr sys_vfork
lea %sp@(24),%sp
rts
ENTRY(__sys_clone3)
SAVE_SWITCH_STACK
pea %sp@(SWITCH_STACK_SIZE)
jbsr m68k_clone3
lea %sp@(28),%sp
rts
ENTRY(sys_sigreturn)
SAVE_SWITCH_STACK
movel %sp,%a1 | switch_stack pointer
lea %sp@(SWITCH_STACK_SIZE),%a0 | pt_regs pointer
lea %sp@(-84),%sp | leave a gap
movel %a1,%sp@-
movel %a0,%sp@-
jbsr do_sigreturn
jra 1f | shared with rt_sigreturn()
ENTRY(sys_rt_sigreturn)
SAVE_SWITCH_STACK
movel %sp,%a1 | switch_stack pointer
lea %sp@(SWITCH_STACK_SIZE),%a0 | pt_regs pointer
lea %sp@(-84),%sp | leave a gap
movel %a1,%sp@-
movel %a0,%sp@-
| stack contents:
| [original pt_regs address] [original switch_stack address]
| [gap] [switch_stack] [pt_regs] [exception frame]
jbsr do_rt_sigreturn
1:
| stack contents now:
| [original pt_regs address] [original switch_stack address]
| [unused part of the gap] [moved switch_stack] [moved pt_regs]
| [replacement exception frame]
| return value of do_{rt_,}sigreturn() points to moved switch_stack.
movel %d0,%sp | discard the leftover junk
RESTORE_SWITCH_STACK
| stack contents now is just [syscall return address] [pt_regs] [frame]
| return pt_regs.d0
movel %sp@(PT_OFF_D0+4),%d0
rts
ENTRY(buserr)
SAVE_ALL_INT
GET_CURRENT(%d0)
movel %sp,%sp@- | stack frame pointer argument
jbsr buserr_c
addql #4,%sp
jra ret_from_exception
ENTRY(trap)
SAVE_ALL_INT
GET_CURRENT(%d0)
movel %sp,%sp@- | stack frame pointer argument
jbsr trap_c
addql #4,%sp
jra ret_from_exception
| After a fork we jump here directly from resume,
| so that %d1 contains the previous task
| schedule_tail now used regardless of CONFIG_SMP
ENTRY(ret_from_fork)
movel %d1,%sp@-
jsr schedule_tail
addql #4,%sp
jra ret_from_exception
ENTRY(ret_from_kernel_thread)
| a3 contains the kernel thread payload, d7 - its argument
movel %d1,%sp@-
jsr schedule_tail
movel %d7,(%sp)
jsr %a3@
addql #4,%sp
jra ret_from_exception
#if defined(CONFIG_COLDFIRE) || !defined(CONFIG_MMU)
#ifdef TRAP_DBG_INTERRUPT
.globl dbginterrupt
ENTRY(dbginterrupt)
SAVE_ALL_INT
GET_CURRENT(%d0)
movel %sp,%sp@- /* stack frame pointer argument */
jsr dbginterrupt_c
addql #4,%sp
jra ret_from_exception
#endif
ENTRY(reschedule)
/* save top of frame */
pea %sp@
jbsr set_esp0
addql #4,%sp
pea ret_from_exception
jmp schedule
ENTRY(ret_from_user_signal)
moveq #__NR_sigreturn,%d0
trap #0
ENTRY(ret_from_user_rt_signal)
movel #__NR_rt_sigreturn,%d0
trap #0
#else
do_trace_entry:
movel #-ENOSYS,%sp@(PT_OFF_D0)| needed for strace
subql #4,%sp
SAVE_SWITCH_STACK
jbsr syscall_trace_enter
RESTORE_SWITCH_STACK
addql #4,%sp
addql #1,%d0 | optimization for cmpil #-1,%d0
jeq ret_from_syscall
movel %sp@(PT_OFF_ORIG_D0),%d0
cmpl #NR_syscalls,%d0
jcs syscall
jra ret_from_syscall
badsys:
movel #-ENOSYS,%sp@(PT_OFF_D0)
jra ret_from_syscall
do_trace_exit:
subql #4,%sp
SAVE_SWITCH_STACK
jbsr syscall_trace_leave
RESTORE_SWITCH_STACK
addql #4,%sp
jra .Lret_from_exception
ENTRY(system_call)
SAVE_ALL_SYS
GET_CURRENT(%d1)
movel %d1,%a1
| save top of frame
movel %sp,%curptr@(TASK_THREAD+THREAD_ESP0)
| syscall trace?
tstb %a1@(TINFO_FLAGS+2)
jmi do_trace_entry
| seccomp filter active?
btst #5,%a1@(TINFO_FLAGS+2)
bnes do_trace_entry
cmpl #NR_syscalls,%d0
jcc badsys
syscall:
jbsr @(sys_call_table,%d0:l:4)@(0)
movel %d0,%sp@(PT_OFF_D0) | save the return value
ret_from_syscall:
|oriw #0x0700,%sr
movel %curptr@(TASK_STACK),%a1
movew %a1@(TINFO_FLAGS+2),%d0
jne syscall_exit_work
1: RESTORE_ALL
syscall_exit_work:
btst #5,%sp@(PT_OFF_SR) | check if returning to kernel
bnes 1b | if so, skip resched, signals
lslw #1,%d0
jcs do_trace_exit
jmi do_delayed_trace
lslw #8,%d0
jne do_signal_return
pea resume_userspace
jra schedule
ENTRY(ret_from_exception)
.Lret_from_exception:
btst #5,%sp@(PT_OFF_SR) | check if returning to kernel
bnes 1f | if so, skip resched, signals
| only allow interrupts when we are really the last one on the
| kernel stack, otherwise stack overflow can occur during
| heavy interrupt load
andw #ALLOWINT,%sr
resume_userspace:
movel %curptr@(TASK_STACK),%a1
moveb %a1@(TINFO_FLAGS+3),%d0
jne exit_work
1: RESTORE_ALL
exit_work:
| save top of frame
movel %sp,%curptr@(TASK_THREAD+THREAD_ESP0)
lslb #1,%d0
jne do_signal_return
pea resume_userspace
jra schedule
do_signal_return:
|andw #ALLOWINT,%sr
subql #4,%sp | dummy return address
SAVE_SWITCH_STACK
pea %sp@(SWITCH_STACK_SIZE)
bsrl do_notify_resume
addql #4,%sp
RESTORE_SWITCH_STACK
addql #4,%sp
jbra resume_userspace
do_delayed_trace:
bclr #7,%sp@(PT_OFF_SR) | clear trace bit in SR
pea 1 | send SIGTRAP
movel %curptr,%sp@-
pea LSIGTRAP
jbsr send_sig
addql #8,%sp
addql #4,%sp
jbra resume_userspace
/* This is the main interrupt handler for autovector interrupts */
ENTRY(auto_inthandler)
SAVE_ALL_INT
GET_CURRENT(%d0)
| put exception # in d0
bfextu %sp@(PT_OFF_FORMATVEC){#4,#10},%d0
subw #VEC_SPUR,%d0
movel %sp,%sp@-
movel %d0,%sp@- | put vector # on stack
auto_irqhandler_fixup = . + 2
jsr do_IRQ | process the IRQ
addql #8,%sp | pop parameters off stack
jra ret_from_exception
/* Handler for user defined interrupt vectors */
ENTRY(user_inthandler)
SAVE_ALL_INT
GET_CURRENT(%d0)
| put exception # in d0
bfextu %sp@(PT_OFF_FORMATVEC){#4,#10},%d0
user_irqvec_fixup = . + 2
subw #VEC_USER,%d0
movel %sp,%sp@-
movel %d0,%sp@- | put vector # on stack
jsr do_IRQ | process the IRQ
addql #8,%sp | pop parameters off stack
jra ret_from_exception
/* Handler for uninitialized and spurious interrupts */
ENTRY(bad_inthandler)
SAVE_ALL_INT
GET_CURRENT(%d0)
movel %sp,%sp@-
jsr handle_badint
addql #4,%sp
jra ret_from_exception
resume:
/*
* Beware - when entering resume, prev (the current task) is
* in a0, next (the new task) is in a1,so don't change these
* registers until their contents are no longer needed.
*/
/* save sr */
movew %sr,%a0@(TASK_THREAD+THREAD_SR)
/* save fs (sfc,%dfc) (may be pointing to kernel memory) */
movec %sfc,%d0
movew %d0,%a0@(TASK_THREAD+THREAD_FC)
/* save usp */
/* it is better to use a movel here instead of a movew 8*) */
movec %usp,%d0
movel %d0,%a0@(TASK_THREAD+THREAD_USP)
/* save non-scratch registers on stack */
SAVE_SWITCH_STACK
/* save current kernel stack pointer */
movel %sp,%a0@(TASK_THREAD+THREAD_KSP)
/* save floating point context */
#ifndef CONFIG_M68KFPU_EMU_ONLY
#ifdef CONFIG_M68KFPU_EMU
tstl m68k_fputype
jeq 3f
#endif
fsave %a0@(TASK_THREAD+THREAD_FPSTATE)
#if defined(CONFIG_M68060)
#if !defined(CPU_M68060_ONLY)
btst #3,m68k_cputype+3
beqs 1f
#endif
/* The 060 FPU keeps status in bits 15-8 of the first longword */
tstb %a0@(TASK_THREAD+THREAD_FPSTATE+2)
jeq 3f
#if !defined(CPU_M68060_ONLY)
jra 2f
#endif
#endif /* CONFIG_M68060 */
#if !defined(CPU_M68060_ONLY)
1: tstb %a0@(TASK_THREAD+THREAD_FPSTATE)
jeq 3f
#endif
2: fmovemx %fp0-%fp7,%a0@(TASK_THREAD+THREAD_FPREG)
fmoveml %fpcr/%fpsr/%fpiar,%a0@(TASK_THREAD+THREAD_FPCNTL)
3:
#endif /* CONFIG_M68KFPU_EMU_ONLY */
/* Return previous task in %d1 */
movel %curptr,%d1
/* switch to new task (a1 contains new task) */
movel %a1,%curptr
/* restore floating point context */
#ifndef CONFIG_M68KFPU_EMU_ONLY
#ifdef CONFIG_M68KFPU_EMU
tstl m68k_fputype
jeq 4f
#endif
#if defined(CONFIG_M68060)
#if !defined(CPU_M68060_ONLY)
btst #3,m68k_cputype+3
beqs 1f
#endif
/* The 060 FPU keeps status in bits 15-8 of the first longword */
tstb %a1@(TASK_THREAD+THREAD_FPSTATE+2)
jeq 3f
#if !defined(CPU_M68060_ONLY)
jra 2f
#endif
#endif /* CONFIG_M68060 */
#if !defined(CPU_M68060_ONLY)
1: tstb %a1@(TASK_THREAD+THREAD_FPSTATE)
jeq 3f
#endif
2: fmovemx %a1@(TASK_THREAD+THREAD_FPREG),%fp0-%fp7
fmoveml %a1@(TASK_THREAD+THREAD_FPCNTL),%fpcr/%fpsr/%fpiar
3: frestore %a1@(TASK_THREAD+THREAD_FPSTATE)
4:
#endif /* CONFIG_M68KFPU_EMU_ONLY */
/* restore the kernel stack pointer */
movel %a1@(TASK_THREAD+THREAD_KSP),%sp
/* restore non-scratch registers */
RESTORE_SWITCH_STACK
/* restore user stack pointer */
movel %a1@(TASK_THREAD+THREAD_USP),%a0
movel %a0,%usp
/* restore fs (sfc,%dfc) */
movew %a1@(TASK_THREAD+THREAD_FC),%a0
movec %a0,%sfc
movec %a0,%dfc
/* restore status register */
movew %a1@(TASK_THREAD+THREAD_SR),%d0
oriw #0x0700,%d0
movew %d0,%sr
rts
#endif /* CONFIG_MMU && !CONFIG_COLDFIRE */