![Dmitry Safonov](/assets/img/avatar_default.png)
CRIU restores application mappings on the same place where they were before Checkpoint. That means, that we need to move vDSO and sigpage during restore on exactly the same place where they were before C/R. Make mremap() code update mm->context.{sigpage,vdso} pointers during VMA move. Sigpage is used for landing after handling a signal - if the pointer is not updated during moving, the application might crash on any signal after mremap(). vDSO pointer on ARM32 is used only for setting auxv at this moment, update it during mremap() in case of future usage. Without those updates, current work of CRIU on ARM32 is not reliable. Historically, we error Checkpointing if we find vDSO page on ARM32 and suggest user to disable CONFIG_VDSO. But that's not correct - it goes from x86 where signal processing is ended in vDSO blob. For arm32 it's sigpage, which is not disabled with `CONFIG_VDSO=n'. Looks like C/R was working by luck - because userspace on ARM32 at this moment always sets SA_RESTORER. Signed-off-by: Dmitry Safonov <dsafonov@virtuozzo.com> Acked-by: Andy Lutomirski <luto@amacapital.net> Cc: linux-arm-kernel@lists.infradead.org Cc: Will Deacon <will.deacon@arm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Christopher Covington <cov@codeaurora.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
468 lines
11 KiB
C
468 lines
11 KiB
C
/*
|
|
* linux/arch/arm/kernel/process.c
|
|
*
|
|
* Copyright (C) 1996-2000 Russell King - Converted to ARM.
|
|
* Original Copyright (C) 1995 Linus Torvalds
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
#include <stdarg.h>
|
|
|
|
#include <linux/export.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/debug.h>
|
|
#include <linux/sched/task.h>
|
|
#include <linux/sched/task_stack.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/stddef.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/user.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/kallsyms.h>
|
|
#include <linux/init.h>
|
|
#include <linux/elfcore.h>
|
|
#include <linux/pm.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/utsname.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/random.h>
|
|
#include <linux/hw_breakpoint.h>
|
|
#include <linux/leds.h>
|
|
|
|
#include <asm/processor.h>
|
|
#include <asm/thread_notify.h>
|
|
#include <asm/stacktrace.h>
|
|
#include <asm/system_misc.h>
|
|
#include <asm/mach/time.h>
|
|
#include <asm/tls.h>
|
|
#include <asm/vdso.h>
|
|
|
|
#ifdef CONFIG_CC_STACKPROTECTOR
|
|
#include <linux/stackprotector.h>
|
|
unsigned long __stack_chk_guard __read_mostly;
|
|
EXPORT_SYMBOL(__stack_chk_guard);
|
|
#endif
|
|
|
|
static const char *processor_modes[] __maybe_unused = {
|
|
"USER_26", "FIQ_26" , "IRQ_26" , "SVC_26" , "UK4_26" , "UK5_26" , "UK6_26" , "UK7_26" ,
|
|
"UK8_26" , "UK9_26" , "UK10_26", "UK11_26", "UK12_26", "UK13_26", "UK14_26", "UK15_26",
|
|
"USER_32", "FIQ_32" , "IRQ_32" , "SVC_32" , "UK4_32" , "UK5_32" , "MON_32" , "ABT_32" ,
|
|
"UK8_32" , "UK9_32" , "HYP_32", "UND_32" , "UK12_32", "UK13_32", "UK14_32", "SYS_32"
|
|
};
|
|
|
|
static const char *isa_modes[] __maybe_unused = {
|
|
"ARM" , "Thumb" , "Jazelle", "ThumbEE"
|
|
};
|
|
|
|
/*
|
|
* This is our default idle handler.
|
|
*/
|
|
|
|
void (*arm_pm_idle)(void);
|
|
|
|
/*
|
|
* Called from the core idle loop.
|
|
*/
|
|
|
|
void arch_cpu_idle(void)
|
|
{
|
|
if (arm_pm_idle)
|
|
arm_pm_idle();
|
|
else
|
|
cpu_do_idle();
|
|
local_irq_enable();
|
|
}
|
|
|
|
void arch_cpu_idle_prepare(void)
|
|
{
|
|
local_fiq_enable();
|
|
}
|
|
|
|
void arch_cpu_idle_enter(void)
|
|
{
|
|
ledtrig_cpu(CPU_LED_IDLE_START);
|
|
#ifdef CONFIG_PL310_ERRATA_769419
|
|
wmb();
|
|
#endif
|
|
}
|
|
|
|
void arch_cpu_idle_exit(void)
|
|
{
|
|
ledtrig_cpu(CPU_LED_IDLE_END);
|
|
}
|
|
|
|
void __show_regs(struct pt_regs *regs)
|
|
{
|
|
unsigned long flags;
|
|
char buf[64];
|
|
#ifndef CONFIG_CPU_V7M
|
|
unsigned int domain, fs;
|
|
#ifdef CONFIG_CPU_SW_DOMAIN_PAN
|
|
/*
|
|
* Get the domain register for the parent context. In user
|
|
* mode, we don't save the DACR, so lets use what it should
|
|
* be. For other modes, we place it after the pt_regs struct.
|
|
*/
|
|
if (user_mode(regs)) {
|
|
domain = DACR_UACCESS_ENABLE;
|
|
fs = get_fs();
|
|
} else {
|
|
domain = to_svc_pt_regs(regs)->dacr;
|
|
fs = to_svc_pt_regs(regs)->addr_limit;
|
|
}
|
|
#else
|
|
domain = get_domain();
|
|
fs = get_fs();
|
|
#endif
|
|
#endif
|
|
|
|
show_regs_print_info(KERN_DEFAULT);
|
|
|
|
print_symbol("PC is at %s\n", instruction_pointer(regs));
|
|
print_symbol("LR is at %s\n", regs->ARM_lr);
|
|
printk("pc : [<%08lx>] lr : [<%08lx>] psr: %08lx\n",
|
|
regs->ARM_pc, regs->ARM_lr, regs->ARM_cpsr);
|
|
printk("sp : %08lx ip : %08lx fp : %08lx\n",
|
|
regs->ARM_sp, regs->ARM_ip, regs->ARM_fp);
|
|
printk("r10: %08lx r9 : %08lx r8 : %08lx\n",
|
|
regs->ARM_r10, regs->ARM_r9,
|
|
regs->ARM_r8);
|
|
printk("r7 : %08lx r6 : %08lx r5 : %08lx r4 : %08lx\n",
|
|
regs->ARM_r7, regs->ARM_r6,
|
|
regs->ARM_r5, regs->ARM_r4);
|
|
printk("r3 : %08lx r2 : %08lx r1 : %08lx r0 : %08lx\n",
|
|
regs->ARM_r3, regs->ARM_r2,
|
|
regs->ARM_r1, regs->ARM_r0);
|
|
|
|
flags = regs->ARM_cpsr;
|
|
buf[0] = flags & PSR_N_BIT ? 'N' : 'n';
|
|
buf[1] = flags & PSR_Z_BIT ? 'Z' : 'z';
|
|
buf[2] = flags & PSR_C_BIT ? 'C' : 'c';
|
|
buf[3] = flags & PSR_V_BIT ? 'V' : 'v';
|
|
buf[4] = '\0';
|
|
|
|
#ifndef CONFIG_CPU_V7M
|
|
{
|
|
const char *segment;
|
|
|
|
if ((domain & domain_mask(DOMAIN_USER)) ==
|
|
domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
|
|
segment = "none";
|
|
else if (fs == get_ds())
|
|
segment = "kernel";
|
|
else
|
|
segment = "user";
|
|
|
|
printk("Flags: %s IRQs o%s FIQs o%s Mode %s ISA %s Segment %s\n",
|
|
buf, interrupts_enabled(regs) ? "n" : "ff",
|
|
fast_interrupts_enabled(regs) ? "n" : "ff",
|
|
processor_modes[processor_mode(regs)],
|
|
isa_modes[isa_mode(regs)], segment);
|
|
}
|
|
#else
|
|
printk("xPSR: %08lx\n", regs->ARM_cpsr);
|
|
#endif
|
|
|
|
#ifdef CONFIG_CPU_CP15
|
|
{
|
|
unsigned int ctrl;
|
|
|
|
buf[0] = '\0';
|
|
#ifdef CONFIG_CPU_CP15_MMU
|
|
{
|
|
unsigned int transbase;
|
|
asm("mrc p15, 0, %0, c2, c0\n\t"
|
|
: "=r" (transbase));
|
|
snprintf(buf, sizeof(buf), " Table: %08x DAC: %08x",
|
|
transbase, domain);
|
|
}
|
|
#endif
|
|
asm("mrc p15, 0, %0, c1, c0\n" : "=r" (ctrl));
|
|
|
|
printk("Control: %08x%s\n", ctrl, buf);
|
|
}
|
|
#endif
|
|
}
|
|
|
|
void show_regs(struct pt_regs * regs)
|
|
{
|
|
__show_regs(regs);
|
|
dump_stack();
|
|
}
|
|
|
|
ATOMIC_NOTIFIER_HEAD(thread_notify_head);
|
|
|
|
EXPORT_SYMBOL_GPL(thread_notify_head);
|
|
|
|
/*
|
|
* Free current thread data structures etc..
|
|
*/
|
|
void exit_thread(struct task_struct *tsk)
|
|
{
|
|
thread_notify(THREAD_NOTIFY_EXIT, task_thread_info(tsk));
|
|
}
|
|
|
|
void flush_thread(void)
|
|
{
|
|
struct thread_info *thread = current_thread_info();
|
|
struct task_struct *tsk = current;
|
|
|
|
flush_ptrace_hw_breakpoint(tsk);
|
|
|
|
memset(thread->used_cp, 0, sizeof(thread->used_cp));
|
|
memset(&tsk->thread.debug, 0, sizeof(struct debug_info));
|
|
memset(&thread->fpstate, 0, sizeof(union fp_state));
|
|
|
|
flush_tls();
|
|
|
|
thread_notify(THREAD_NOTIFY_FLUSH, thread);
|
|
}
|
|
|
|
void release_thread(struct task_struct *dead_task)
|
|
{
|
|
}
|
|
|
|
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
|
|
|
|
int
|
|
copy_thread(unsigned long clone_flags, unsigned long stack_start,
|
|
unsigned long stk_sz, struct task_struct *p)
|
|
{
|
|
struct thread_info *thread = task_thread_info(p);
|
|
struct pt_regs *childregs = task_pt_regs(p);
|
|
|
|
memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
|
|
|
|
#ifdef CONFIG_CPU_USE_DOMAINS
|
|
/*
|
|
* Copy the initial value of the domain access control register
|
|
* from the current thread: thread->addr_limit will have been
|
|
* copied from the current thread via setup_thread_stack() in
|
|
* kernel/fork.c
|
|
*/
|
|
thread->cpu_domain = get_domain();
|
|
#endif
|
|
|
|
if (likely(!(p->flags & PF_KTHREAD))) {
|
|
*childregs = *current_pt_regs();
|
|
childregs->ARM_r0 = 0;
|
|
if (stack_start)
|
|
childregs->ARM_sp = stack_start;
|
|
} else {
|
|
memset(childregs, 0, sizeof(struct pt_regs));
|
|
thread->cpu_context.r4 = stk_sz;
|
|
thread->cpu_context.r5 = stack_start;
|
|
childregs->ARM_cpsr = SVC_MODE;
|
|
}
|
|
thread->cpu_context.pc = (unsigned long)ret_from_fork;
|
|
thread->cpu_context.sp = (unsigned long)childregs;
|
|
|
|
clear_ptrace_hw_breakpoint(p);
|
|
|
|
if (clone_flags & CLONE_SETTLS)
|
|
thread->tp_value[0] = childregs->ARM_r3;
|
|
thread->tp_value[1] = get_tpuser();
|
|
|
|
thread_notify(THREAD_NOTIFY_COPY, thread);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Fill in the task's elfregs structure for a core dump.
|
|
*/
|
|
int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs)
|
|
{
|
|
elf_core_copy_regs(elfregs, task_pt_regs(t));
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* fill in the fpe structure for a core dump...
|
|
*/
|
|
int dump_fpu (struct pt_regs *regs, struct user_fp *fp)
|
|
{
|
|
struct thread_info *thread = current_thread_info();
|
|
int used_math = thread->used_cp[1] | thread->used_cp[2];
|
|
|
|
if (used_math)
|
|
memcpy(fp, &thread->fpstate.soft, sizeof (*fp));
|
|
|
|
return used_math != 0;
|
|
}
|
|
EXPORT_SYMBOL(dump_fpu);
|
|
|
|
unsigned long get_wchan(struct task_struct *p)
|
|
{
|
|
struct stackframe frame;
|
|
unsigned long stack_page;
|
|
int count = 0;
|
|
if (!p || p == current || p->state == TASK_RUNNING)
|
|
return 0;
|
|
|
|
frame.fp = thread_saved_fp(p);
|
|
frame.sp = thread_saved_sp(p);
|
|
frame.lr = 0; /* recovered from the stack */
|
|
frame.pc = thread_saved_pc(p);
|
|
stack_page = (unsigned long)task_stack_page(p);
|
|
do {
|
|
if (frame.sp < stack_page ||
|
|
frame.sp >= stack_page + THREAD_SIZE ||
|
|
unwind_frame(&frame) < 0)
|
|
return 0;
|
|
if (!in_sched_functions(frame.pc))
|
|
return frame.pc;
|
|
} while (count ++ < 16);
|
|
return 0;
|
|
}
|
|
|
|
unsigned long arch_randomize_brk(struct mm_struct *mm)
|
|
{
|
|
return randomize_page(mm->brk, 0x02000000);
|
|
}
|
|
|
|
#ifdef CONFIG_MMU
|
|
#ifdef CONFIG_KUSER_HELPERS
|
|
/*
|
|
* The vectors page is always readable from user space for the
|
|
* atomic helpers. Insert it into the gate_vma so that it is visible
|
|
* through ptrace and /proc/<pid>/mem.
|
|
*/
|
|
static struct vm_area_struct gate_vma = {
|
|
.vm_start = 0xffff0000,
|
|
.vm_end = 0xffff0000 + PAGE_SIZE,
|
|
.vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC,
|
|
};
|
|
|
|
static int __init gate_vma_init(void)
|
|
{
|
|
gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
|
|
return 0;
|
|
}
|
|
arch_initcall(gate_vma_init);
|
|
|
|
struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
|
|
{
|
|
return &gate_vma;
|
|
}
|
|
|
|
int in_gate_area(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
return (addr >= gate_vma.vm_start) && (addr < gate_vma.vm_end);
|
|
}
|
|
|
|
int in_gate_area_no_mm(unsigned long addr)
|
|
{
|
|
return in_gate_area(NULL, addr);
|
|
}
|
|
#define is_gate_vma(vma) ((vma) == &gate_vma)
|
|
#else
|
|
#define is_gate_vma(vma) 0
|
|
#endif
|
|
|
|
const char *arch_vma_name(struct vm_area_struct *vma)
|
|
{
|
|
return is_gate_vma(vma) ? "[vectors]" : NULL;
|
|
}
|
|
|
|
/* If possible, provide a placement hint at a random offset from the
|
|
* stack for the sigpage and vdso pages.
|
|
*/
|
|
static unsigned long sigpage_addr(const struct mm_struct *mm,
|
|
unsigned int npages)
|
|
{
|
|
unsigned long offset;
|
|
unsigned long first;
|
|
unsigned long last;
|
|
unsigned long addr;
|
|
unsigned int slots;
|
|
|
|
first = PAGE_ALIGN(mm->start_stack);
|
|
|
|
last = TASK_SIZE - (npages << PAGE_SHIFT);
|
|
|
|
/* No room after stack? */
|
|
if (first > last)
|
|
return 0;
|
|
|
|
/* Just enough room? */
|
|
if (first == last)
|
|
return first;
|
|
|
|
slots = ((last - first) >> PAGE_SHIFT) + 1;
|
|
|
|
offset = get_random_int() % slots;
|
|
|
|
addr = first + (offset << PAGE_SHIFT);
|
|
|
|
return addr;
|
|
}
|
|
|
|
static struct page *signal_page;
|
|
extern struct page *get_signal_page(void);
|
|
|
|
static int sigpage_mremap(const struct vm_special_mapping *sm,
|
|
struct vm_area_struct *new_vma)
|
|
{
|
|
current->mm->context.sigpage = new_vma->vm_start;
|
|
return 0;
|
|
}
|
|
|
|
static const struct vm_special_mapping sigpage_mapping = {
|
|
.name = "[sigpage]",
|
|
.pages = &signal_page,
|
|
.mremap = sigpage_mremap,
|
|
};
|
|
|
|
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
struct vm_area_struct *vma;
|
|
unsigned long npages;
|
|
unsigned long addr;
|
|
unsigned long hint;
|
|
int ret = 0;
|
|
|
|
if (!signal_page)
|
|
signal_page = get_signal_page();
|
|
if (!signal_page)
|
|
return -ENOMEM;
|
|
|
|
npages = 1; /* for sigpage */
|
|
npages += vdso_total_pages;
|
|
|
|
if (down_write_killable(&mm->mmap_sem))
|
|
return -EINTR;
|
|
hint = sigpage_addr(mm, npages);
|
|
addr = get_unmapped_area(NULL, hint, npages << PAGE_SHIFT, 0, 0);
|
|
if (IS_ERR_VALUE(addr)) {
|
|
ret = addr;
|
|
goto up_fail;
|
|
}
|
|
|
|
vma = _install_special_mapping(mm, addr, PAGE_SIZE,
|
|
VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
|
|
&sigpage_mapping);
|
|
|
|
if (IS_ERR(vma)) {
|
|
ret = PTR_ERR(vma);
|
|
goto up_fail;
|
|
}
|
|
|
|
mm->context.sigpage = addr;
|
|
|
|
/* Unlike the sigpage, failure to install the vdso is unlikely
|
|
* to be fatal to the process, so no error check needed
|
|
* here.
|
|
*/
|
|
arm_install_vdso(mm, addr + PAGE_SIZE);
|
|
|
|
up_fail:
|
|
up_write(&mm->mmap_sem);
|
|
return ret;
|
|
}
|
|
#endif
|