long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
unsigned long tmp;
int ret;
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA: {
int copied;
ret = -EIO;
if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0)
break;
copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
if (copied != sizeof(tmp))
break;
ret = put_user(tmp,(unsigned long *) data);
break;
}
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
tmp = 0;
ret = -EIO;
if ((addr & 3) || addr < 0)
break;
ret = 0;
switch (addr >> 2) {
case 0 ... PT__END - 1:
tmp = get_reg(child, addr >> 2);
break;
case PT__END + 0:
tmp = child->mm->end_code - child->mm->start_code;
break;
case PT__END + 1:
tmp = child->mm->end_data - child->mm->start_data;
break;
case PT__END + 2:
tmp = child->mm->start_stack - child->mm->start_brk;
break;
case PT__END + 3:
tmp = child->mm->start_code;
break;
case PT__END + 4:
tmp = child->mm->start_stack;
break;
default:
ret = -EIO;
break;
}
if (ret == 0)
ret = put_user(tmp, (unsigned long *) data);
break;
}
/* when I and D space are separate, this will have to be fixed. */
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
ret = -EIO;
if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0)
break;
if (access_process_vm(child, addr, &data, sizeof(data), 1) != sizeof(data))
break;
ret = 0;
break;
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
ret = -EIO;
if ((addr & 3) || addr < 0)
break;
ret = 0;
switch (addr >> 2) {
case 0 ... PT__END-1:
ret = put_reg(child, addr >> 2, data);
break;
default:
ret = -EIO;
break;
}
break;
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT: /* restart after signal. */
ret = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSCALL)
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->exit_code = data;
ptrace_disable(child);
wake_up_process(child);
ret = 0;
break;
/* make the child exit. Best I can do is send it a sigkill.
* perhaps it should be put in the status that it wants to
* exit.
*/
case PTRACE_KILL:
ret = 0;
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
break;
child->exit_code = SIGKILL;
clear_tsk_thread_flag(child, TIF_SINGLESTEP);
ptrace_disable(child);
wake_up_process(child);
break;
case PTRACE_SINGLESTEP: /* set the trap flag. */
ret = -EIO;
if (!valid_signal(data))
break;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
ptrace_enable(child);
child->exit_code = data;
wake_up_process(child);
ret = 0;
break;
case PTRACE_DETACH: /* detach a process that was attached. */
ret = ptrace_detach(child, data);
break;
case PTRACE_GETREGS: { /* Get all integer regs from the child. */
int i;
for (i = 0; i < PT__GPEND; i++) {
tmp = get_reg(child, i);
if (put_user(tmp, (unsigned long *) data)) {
ret = -EFAULT;
break;
}
data += sizeof(long);
}
ret = 0;
break;
}
case PTRACE_SETREGS: { /* Set all integer regs in the child. */
int i;
for (i = 0; i < PT__GPEND; i++) {
if (get_user(tmp, (unsigned long *) data)) {
ret = -EFAULT;
break;
}
put_reg(child, i, tmp);
data += sizeof(long);
}
ret = 0;
break;
}
case PTRACE_GETFPREGS: { /* Get the child FP/Media state. */
ret = 0;
if (copy_to_user((void *) data,
&child->thread.user->f,
sizeof(child->thread.user->f)))
ret = -EFAULT;
break;
}
case PTRACE_SETFPREGS: { /* Set the child FP/Media state. */
ret = 0;
if (copy_from_user(&child->thread.user->f,
(void *) data,
sizeof(child->thread.user->f)))
ret = -EFAULT;
break;
}
case PTRACE_GETFDPIC:
tmp = 0;
switch (addr) {
case PTRACE_GETFDPIC_EXEC:
tmp = child->mm->context.exec_fdpic_loadmap;
break;
case PTRACE_GETFDPIC_INTERP:
tmp = child->mm->context.interp_fdpic_loadmap;
break;
default:
break;
}
ret = 0;
if (put_user(tmp, (unsigned long *) data)) {
ret = -EFAULT;
break;
}
break;
default:
ret = -EIO;
break;
}
return ret;
}
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
*
* It copies the registers, and all the appropriate
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
static struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
int __user *child_tidptr,
struct pid *pid,
int trace)
{
int retval;
struct task_struct *p;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
*/
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
/*
* Shared signal handlers imply shared VM. By way of the above,
* thread groups also imply shared VM. Blocking this case allows
* for various simplifications in other code.
*/
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
/*
* Siblings of global init remain as zombies on exit since they are
* not reaped by their parent (swapper). To solve this and to avoid
* multi-rooted process trees, prevent global and container-inits
* from creating siblings.
*/
if ((clone_flags & CLONE_PARENT) &&
current->signal->flags & SIGNAL_UNKILLABLE)
return ERR_PTR(-EINVAL);
/*
* If the new process will be in a different pid or user namespace
* do not allow it to share a thread group or signal handlers or
* parent with the forking task.
*/
if (clone_flags & CLONE_SIGHAND) {
if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
(task_active_pid_ns(current) !=
current->nsproxy->pid_ns_for_children))
return ERR_PTR(-EINVAL);
}
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
ftrace_graph_init_task(p);
rt_mutex_init_task(p);
#ifdef CONFIG_PROVE_LOCKING
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
retval = -EAGAIN;
if (atomic_read(&p->real_cred->user->processes) >=
task_rlimit(p, RLIMIT_NPROC)) {
if (p->real_cred->user != INIT_USER &&
!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
goto bad_fork_free;
}
current->flags &= ~PF_NPROC_EXCEEDED;
retval = copy_creds(p, clone_flags);
if (retval < 0)
goto bad_fork_free;
/*
* If multiple threads are within copy_process(), then this check
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
retval = -EAGAIN;
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
p->flags |= PF_FORKNOEXEC;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
rcu_copy_process(p);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
init_sigpending(&p->pending);
p->utime = p->stime = p->gtime = 0;
p->utimescaled = p->stimescaled = 0;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
p->prev_cputime.utime = p->prev_cputime.stime = 0;
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
seqlock_init(&p->vtime_seqlock);
p->vtime_snap = 0;
p->vtime_snap_whence = VTIME_SLEEPING;
#endif
#if defined(SPLIT_RSS_COUNTING)
memset(&p->rss_stat, 0, sizeof(p->rss_stat));
#endif
p->default_timer_slack_ns = current->timer_slack_ns;
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
posix_cpu_timers_init(p);
p->start_time = ktime_get_ns();
p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
if (clone_flags & CLONE_THREAD)
threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup_threadgroup_lock;
}
#endif
#ifdef CONFIG_CPUSETS
p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
seqcount_init(&p->mems_allowed_seq);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
p->hardirqs_enabled = 0;
p->hardirq_enable_ip = 0;
p->hardirq_enable_event = 0;
p->hardirq_disable_ip = _THIS_IP_;
p->hardirq_disable_event = 0;
p->softirqs_enabled = 1;
p->softirq_enable_ip = _THIS_IP_;
p->softirq_enable_event = 0;
p->softirq_disable_ip = 0;
p->softirq_disable_event = 0;
p->hardirq_context = 0;
p->softirq_context = 0;
#endif
#ifdef CONFIG_LOCKDEP
p->lockdep_depth = 0; /* no locks held yet */
p->curr_chain_key = 0;
p->lockdep_recursion = 0;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
#ifdef CONFIG_BCACHE
p->sequential_io = 0;
p->sequential_io_avg = 0;
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
retval = sched_fork(clone_flags, p);
if (retval)
goto bad_fork_cleanup_policy;
retval = perf_event_init_task(p);
if (retval)
goto bad_fork_cleanup_policy;
retval = audit_alloc(p);
if (retval)
goto bad_fork_cleanup_perf;
/* copy all the process information */
shm_init_task(p);
retval = copy_semundo(clone_flags, p);
if (retval)
goto bad_fork_cleanup_audit;
retval = copy_files(clone_flags, p);
if (retval)
goto bad_fork_cleanup_semundo;
retval = copy_fs(clone_flags, p);
if (retval)
goto bad_fork_cleanup_files;
retval = copy_sighand(clone_flags, p);
if (retval)
goto bad_fork_cleanup_fs;
retval = copy_signal(clone_flags, p);
if (retval)
goto bad_fork_cleanup_sighand;
retval = copy_mm(clone_flags, p);
if (retval)
goto bad_fork_cleanup_signal;
retval = copy_namespaces(clone_flags, p);
if (retval)
goto bad_fork_cleanup_mm;
retval = copy_io(clone_flags, p);
if (retval)
goto bad_fork_cleanup_namespaces;
retval = copy_thread(clone_flags, stack_start, stack_size, p);
if (retval)
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(p->nsproxy->pid_ns_for_children);
if (!pid)
goto bad_fork_cleanup_io;
}
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
/*
* Clear TID on mm_release()?
*/
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
#ifdef CONFIG_FUTEX
p->robust_list = NULL;
#ifdef CONFIG_COMPAT
p->compat_robust_list = NULL;
#endif
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
#endif
/*
* sigaltstack should be cleared when sharing the same VM
*/
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
p->sas_ss_sp = p->sas_ss_size = 0;
/*
* Syscall tracing and stepping should be turned off in the
* child regardless of CLONE_PTRACE.
*/
user_disable_single_step(p);
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
clear_all_latency_tracing(p);
/* ok, now we should be set up.. */
p->pid = pid_nr(pid);
if (clone_flags & CLONE_THREAD) {
p->exit_signal = -1;
p->group_leader = current->group_leader;
p->tgid = current->tgid;
} else {
if (clone_flags & CLONE_PARENT)
p->exit_signal = current->group_leader->exit_signal;
else
p->exit_signal = (clone_flags & CSIGNAL);
p->group_leader = p;
p->tgid = p->pid;
}
p->nr_dirtied = 0;
p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
p->dirty_paused_when = 0;
p->pdeath_signal = 0;
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
/*
* Make it visible to the rest of the system, but dont wake it up yet.
* Need tasklist lock for parent etc handling!
*/
write_lock_irq(&tasklist_lock);
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
p->real_parent = current->real_parent;
p->parent_exec_id = current->parent_exec_id;
} else {
p->real_parent = current;
p->parent_exec_id = current->self_exec_id;
}
spin_lock(¤t->sighand->siglock);
/*
* Copy seccomp details explicitly here, in case they were changed
* before holding sighand lock.
*/
copy_seccomp(p);
/*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
* fork. Restart if a signal comes in before we add the new process to
* it's process group.
* A fatal signal pending means that current will exit, so the new
* thread can't slip out of an OOM kill (or normal SIGKILL).
*/
recalc_sigpending();
if (signal_pending(current)) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_free_pid;
}
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
init_task_pid(p, PIDTYPE_PID, pid);
if (thread_group_leader(p)) {
init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
init_task_pid(p, PIDTYPE_SID, task_session(current));
if (is_child_reaper(pid)) {
ns_of_pid(pid)->child_reaper = p;
p->signal->flags |= SIGNAL_UNKILLABLE;
}
p->signal->leader_pid = pid;
p->signal->tty = tty_kref_get(current->signal->tty);
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
attach_pid(p, PIDTYPE_PGID);
attach_pid(p, PIDTYPE_SID);
__this_cpu_inc(process_counts);
} else {
current->signal->nr_threads++;
atomic_inc(¤t->signal->live);
atomic_inc(¤t->signal->sigcnt);
list_add_tail_rcu(&p->thread_group,
&p->group_leader->thread_group);
list_add_tail_rcu(&p->thread_node,
&p->signal->thread_head);
}
attach_pid(p, PIDTYPE_PID);
nr_threads++;
}
total_forks++;
spin_unlock(¤t->sighand->siglock);
syscall_tracepoint_update(p);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
perf_event_fork(p);
trace_task_newtask(p, clone_flags);
uprobe_copy_process(p, clone_flags);
return p;
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_io:
if (p->io_context)
exit_io_context(p);
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
free_signal_struct(p->signal);
bad_fork_cleanup_sighand:
__cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_perf:
perf_event_free_task(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
delayacct_tsk_free(p);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
exit_creds(p);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
long ret;
#ifdef DEBUG_PTRACE
long oaddr=addr, odata=data;
#endif
switch (request) {
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA: {
#ifdef CONFIG_64BIT
if (__is_compat_task(child)) {
int copied;
unsigned int tmp;
addr &= 0xffffffffL;
copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
ret = -EIO;
if (copied != sizeof(tmp))
goto out_tsk;
ret = put_user(tmp,(unsigned int *) data);
DBG("sys_ptrace(PEEK%s, %d, %lx, %lx) returning %ld, data %x\n",
request == PTRACE_PEEKTEXT ? "TEXT" : "DATA",
pid, oaddr, odata, ret, tmp);
}
else
#endif
ret = generic_ptrace_peekdata(child, addr, data);
goto out_tsk;
}
/* when I and D space are separate, this will have to be fixed. */
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
ret = 0;
#ifdef CONFIG_64BIT
if (__is_compat_task(child)) {
unsigned int tmp = (unsigned int)data;
DBG("sys_ptrace(POKE%s, %d, %lx, %lx)\n",
request == PTRACE_POKETEXT ? "TEXT" : "DATA",
pid, oaddr, odata);
addr &= 0xffffffffL;
if (access_process_vm(child, addr, &tmp, sizeof(tmp), 1) == sizeof(tmp))
goto out_tsk;
}
else
#endif
{
if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
goto out_tsk;
}
ret = -EIO;
goto out_tsk;
/* Read the word at location addr in the USER area. For ptraced
processes, the kernel saves all regs on a syscall. */
case PTRACE_PEEKUSR: {
ret = -EIO;
#ifdef CONFIG_64BIT
if (__is_compat_task(child)) {
unsigned int tmp;
if (addr & (sizeof(int)-1))
goto out_tsk;
if ((addr = translate_usr_offset(addr)) < 0)
goto out_tsk;
tmp = *(unsigned int *) ((char *) task_regs(child) + addr);
ret = put_user(tmp, (unsigned int *) data);
DBG("sys_ptrace(PEEKUSR, %d, %lx, %lx) returning %ld, addr %lx, data %x\n",
pid, oaddr, odata, ret, addr, tmp);
}
else
#endif
{
unsigned long tmp;
if ((addr & (sizeof(long)-1)) || (unsigned long) addr >= sizeof(struct pt_regs))
goto out_tsk;
tmp = *(unsigned long *) ((char *) task_regs(child) + addr);
ret = put_user(tmp, (unsigned long *) data);
}
goto out_tsk;
}
/* Write the word at location addr in the USER area. This will need
to change when the kernel no longer saves all regs on a syscall.
FIXME. There is a problem at the moment in that r3-r18 are only
saved if the process is ptraced on syscall entry, and even then
those values are overwritten by actual register values on syscall
exit. */
case PTRACE_POKEUSR:
ret = -EIO;
/* Some register values written here may be ignored in
* entry.S:syscall_restore_rfi; e.g. iaoq is written with
* r31/r31+4, and not with the values in pt_regs.
*/
/* PT_PSW=0, so this is valid for 32 bit processes under 64
* bit kernels.
*/
if (addr == PT_PSW) {
/* PT_PSW=0, so this is valid for 32 bit processes
* under 64 bit kernels.
*
* Allow writing to Nullify, Divide-step-correction,
* and carry/borrow bits.
* BEWARE, if you set N, and then single step, it won't
* stop on the nullified instruction.
*/
DBG("sys_ptrace(POKEUSR, %d, %lx, %lx)\n",
pid, oaddr, odata);
data &= USER_PSW_BITS;
task_regs(child)->gr[0] &= ~USER_PSW_BITS;
task_regs(child)->gr[0] |= data;
ret = 0;
goto out_tsk;
}
#ifdef CONFIG_64BIT
if (__is_compat_task(child)) {
if (addr & (sizeof(int)-1))
goto out_tsk;
if ((addr = translate_usr_offset(addr)) < 0)
goto out_tsk;
DBG("sys_ptrace(POKEUSR, %d, %lx, %lx) addr %lx\n",
pid, oaddr, odata, addr);
if (addr >= PT_FR0 && addr <= PT_FR31 + 4) {
/* Special case, fp regs are 64 bits anyway */
*(unsigned int *) ((char *) task_regs(child) + addr) = data;
ret = 0;
}
else if ((addr >= PT_GR1+4 && addr <= PT_GR31+4) ||
addr == PT_IAOQ0+4 || addr == PT_IAOQ1+4 ||
addr == PT_SAR+4) {
/* Zero the top 32 bits */
*(unsigned int *) ((char *) task_regs(child) + addr - 4) = 0;
*(unsigned int *) ((char *) task_regs(child) + addr) = data;
ret = 0;
}
goto out_tsk;
}
else
#endif
{
if ((addr & (sizeof(long)-1)) || (unsigned long) addr >= sizeof(struct pt_regs))
goto out_tsk;
if ((addr >= PT_GR1 && addr <= PT_GR31) ||
addr == PT_IAOQ0 || addr == PT_IAOQ1 ||
(addr >= PT_FR0 && addr <= PT_FR31 + 4) ||
addr == PT_SAR) {
*(unsigned long *) ((char *) task_regs(child) + addr) = data;
ret = 0;
}
goto out_tsk;
}
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT:
ret = -EIO;
DBG("sys_ptrace(%s)\n",
request == PTRACE_SYSCALL ? "SYSCALL" : "CONT");
if (!valid_signal(data))
goto out_tsk;
child->ptrace &= ~(PT_SINGLESTEP|PT_BLOCKSTEP);
if (request == PTRACE_SYSCALL) {
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
} else {
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
}
child->exit_code = data;
goto out_wake_notrap;
case PTRACE_KILL:
/*
* make the child exit. Best I can do is send it a
* sigkill. perhaps it should be put in the status
* that it wants to exit.
*/
ret = 0;
DBG("sys_ptrace(KILL)\n");
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
goto out_tsk;
child->exit_code = SIGKILL;
goto out_wake_notrap;
case PTRACE_SINGLEBLOCK:
DBG("sys_ptrace(SINGLEBLOCK)\n");
ret = -EIO;
if (!valid_signal(data))
goto out_tsk;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->ptrace &= ~PT_SINGLESTEP;
child->ptrace |= PT_BLOCKSTEP;
child->exit_code = data;
/* Enable taken branch trap. */
pa_psw(child)->r = 0;
pa_psw(child)->t = 1;
pa_psw(child)->h = 0;
pa_psw(child)->l = 0;
goto out_wake;
case PTRACE_SINGLESTEP:
DBG("sys_ptrace(SINGLESTEP)\n");
ret = -EIO;
if (!valid_signal(data))
goto out_tsk;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->ptrace &= ~PT_BLOCKSTEP;
child->ptrace |= PT_SINGLESTEP;
child->exit_code = data;
if (pa_psw(child)->n) {
struct siginfo si;
/* Nullified, just crank over the queue. */
task_regs(child)->iaoq[0] = task_regs(child)->iaoq[1];
task_regs(child)->iasq[0] = task_regs(child)->iasq[1];
task_regs(child)->iaoq[1] = task_regs(child)->iaoq[0] + 4;
pa_psw(child)->n = 0;
pa_psw(child)->x = 0;
pa_psw(child)->y = 0;
pa_psw(child)->z = 0;
pa_psw(child)->b = 0;
ptrace_disable(child);
/* Don't wake up the child, but let the
parent know something happened. */
si.si_code = TRAP_TRACE;
si.si_addr = (void __user *) (task_regs(child)->iaoq[0] & ~3);
si.si_signo = SIGTRAP;
si.si_errno = 0;
force_sig_info(SIGTRAP, &si, child);
//notify_parent(child, SIGCHLD);
//ret = 0;
goto out_wake;
}
/* Enable recovery counter traps. The recovery counter
* itself will be set to zero on a task switch. If the
* task is suspended on a syscall then the syscall return
* path will overwrite the recovery counter with a suitable
* value such that it traps once back in user space. We
* disable interrupts in the childs PSW here also, to avoid
* interrupts while the recovery counter is decrementing.
*/
pa_psw(child)->r = 1;
pa_psw(child)->t = 0;
pa_psw(child)->h = 0;
pa_psw(child)->l = 0;
/* give it a chance to run. */
goto out_wake;
case PTRACE_GETEVENTMSG:
ret = put_user(child->ptrace_message, (unsigned int __user *) data);
goto out_tsk;
default:
ret = ptrace_request(child, request, addr, data);
goto out_tsk;
}
out_wake_notrap:
ptrace_disable(child);
out_wake:
wake_up_process(child);
ret = 0;
out_tsk:
DBG("arch_ptrace(%ld, %d, %lx, %lx) returning %ld\n",
request, pid, oaddr, odata, ret);
return ret;
}
asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
{
struct task_struct *child;
int ret;
lock_kernel();
ret = -EPERM;
if (request == PTRACE_TRACEME) {
/* are we already being traced? */
if (current->ptrace & PT_PTRACED)
goto out;
/* set the ptrace bit in the process flags. */
current->ptrace |= PT_PTRACED;
ret = 0;
goto out;
}
ret = -ESRCH;
read_lock(&tasklist_lock);
child = find_task_by_pid(pid);
if (child)
get_task_struct(child);
read_unlock(&tasklist_lock);
if (!child)
goto out;
ret = -EPERM;
if (pid == 1) /* you may not mess with init */
goto out_tsk;
if (request == PTRACE_ATTACH) {
ret = ptrace_attach(child);
goto out_tsk;
}
ret = ptrace_check_attach(child, request == PTRACE_KILL);
if (ret < 0)
goto out_tsk;
switch (request) {
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA: {
unsigned long tmp;
ret = read_long(child, addr, &tmp);
if (ret < 0)
break ;
ret = put_user(tmp, (unsigned long *) data);
break ;
}
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
unsigned long tmp = 0;
if ((addr & 3) || addr < 0 || addr >= sizeof(struct user)) {
ret = -EIO;
break ;
}
ret = 0; /* Default return condition */
addr = addr >> 2; /* temporary hack. */
if (addr < H8300_REGS_NO)
tmp = h8300_get_reg(child, addr);
else {
switch(addr) {
case 49:
tmp = child->mm->start_code;
break ;
case 50:
tmp = child->mm->start_data;
break ;
case 51:
tmp = child->mm->end_code;
break ;
case 52:
tmp = child->mm->end_data;
break ;
default:
ret = -EIO;
}
}
if (!ret)
ret = put_user(tmp,(unsigned long *) data);
break ;
}
/* when I and D space are separate, this will have to be fixed. */
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
ret = 0;
if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
break;
ret = -EIO;
break;
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
if ((addr & 3) || addr < 0 || addr >= sizeof(struct user)) {
ret = -EIO;
break ;
}
addr = addr >> 2; /* temporary hack. */
if (addr == PT_ORIG_ER0) {
ret = -EIO;
break ;
}
if (addr < H8300_REGS_NO) {
ret = h8300_put_reg(child, addr, data);
break ;
}
ret = -EIO;
break ;
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT: { /* restart after signal. */
ret = -EIO;
if ((unsigned long) data >= _NSIG)
break ;
if (request == PTRACE_SYSCALL)
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->exit_code = data;
wake_up_process(child);
/* make sure the single step bit is not set. */
h8300_disable_trace(child);
ret = 0;
}
/*
* make the child exit. Best I can do is send it a sigkill.
* perhaps it should be put in the status that it wants to
* exit.
*/
case PTRACE_KILL: {
ret = 0;
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
break;
child->exit_code = SIGKILL;
h8300_disable_trace(child);
wake_up_process(child);
break;
}
case PTRACE_SINGLESTEP: { /* set the trap flag. */
ret = -EIO;
if ((unsigned long) data > _NSIG)
break;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->exit_code = data;
h8300_enable_trace(child);
wake_up_process(child);
ret = 0;
break;
}
case PTRACE_DETACH: /* detach a process that was attached. */
ret = ptrace_detach(child, data);
break;
case PTRACE_GETREGS: { /* Get all gp regs from the child. */
int i;
unsigned long tmp;
for (i = 0; i < H8300_REGS_NO; i++) {
tmp = h8300_get_reg(child, i);
if (put_user(tmp, (unsigned long *) data)) {
ret = -EFAULT;
break;
}
data += sizeof(long);
}
ret = 0;
break;
}
case PTRACE_SETREGS: { /* Set all gp regs in the child. */
int i;
unsigned long tmp;
for (i = 0; i < H8300_REGS_NO; i++) {
if (get_user(tmp, (unsigned long *) data)) {
ret = -EFAULT;
break;
}
h8300_put_reg(child, i, tmp);
data += sizeof(long);
}
ret = 0;
break;
}
default:
ret = -EIO;
break;
}
out_tsk:
put_task_struct(child);
out:
unlock_kernel();
return ret;
}
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
*
* It copies the registers, and all the appropriate
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
int retval;
struct task_struct *p = NULL;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
*/
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
/*
* Shared signal handlers imply shared VM. By way of the above,
* thread groups also imply shared VM. Blocking this case allows
* for various simplifications in other code.
*/
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
retval = -EAGAIN;
if (atomic_read(&p->user->processes) >=
p->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->user != &root_user)
goto bad_fork_free;
}
atomic_inc(&p->user->__count);
atomic_inc(&p->user->processes);
get_group_info(p->group_info);
/*
* If multiple threads are within copy_process(), then this check
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
if (!try_module_get(p->thread_info->exec_domain->module))
goto bad_fork_cleanup_count;
if (p->binfmt && !try_module_get(p->binfmt->module))
goto bad_fork_cleanup_put_domain;
p->did_exec = 0;
copy_flags(clone_flags, p);
if (clone_flags & CLONE_IDLETASK)
p->pid = 0;
else {
p->pid = alloc_pidmap();
if (p->pid == -1)
goto bad_fork_cleanup;
}
retval = -EFAULT;
if (clone_flags & CLONE_PARENT_SETTID)
if (put_user(p->pid, parent_tidptr))
goto bad_fork_cleanup;
p->proc_dentry = NULL;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
init_waitqueue_head(&p->wait_chldexit);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
spin_lock_init(&p->proc_lock);
clear_tsk_thread_flag(p, TIF_SIGPENDING);
init_sigpending(&p->pending);
p->it_real_value = p->it_virt_value = p->it_prof_value = 0;
p->it_real_incr = p->it_virt_incr = p->it_prof_incr = 0;
init_timer(&p->real_timer);
p->real_timer.data = (unsigned long) p;
p->utime = p->stime = 0;
p->cutime = p->cstime = 0;
p->lock_depth = -1; /* -1 = no lock */
p->start_time = get_jiffies_64();
p->security = NULL;
p->io_context = NULL;
p->audit_context = NULL;
#ifdef CONFIG_NUMA
p->mempolicy = mpol_copy(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup;
}
#endif
retval = -ENOMEM;
if ((retval = security_task_alloc(p)))
goto bad_fork_cleanup_policy;
if ((retval = audit_alloc(p)))
goto bad_fork_cleanup_security;
/* copy all the process information */
if ((retval = copy_semundo(clone_flags, p)))
goto bad_fork_cleanup_audit;
if ((retval = copy_files(clone_flags, p)))
goto bad_fork_cleanup_semundo;
if ((retval = copy_fs(clone_flags, p)))
goto bad_fork_cleanup_files;
if ((retval = copy_sighand(clone_flags, p)))
goto bad_fork_cleanup_fs;
if ((retval = copy_signal(clone_flags, p)))
goto bad_fork_cleanup_sighand;
if ((retval = copy_mm(clone_flags, p)))
goto bad_fork_cleanup_signal;
if ((retval = copy_namespace(clone_flags, p)))
goto bad_fork_cleanup_mm;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_namespace;
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
/*
* Clear TID on mm_release()?
*/
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
/*
* Syscall tracing should be turned off in the child regardless
* of CLONE_PTRACE.
*/
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
p->parent_exec_id = p->self_exec_id;
/* ok, now we should be set up.. */
p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
/* Perform scheduler related setup */
sched_fork(p);
/*
* Ok, make it visible to the rest of the system.
* We dont wake it up yet.
*/
p->tgid = p->pid;
p->group_leader = p;
INIT_LIST_HEAD(&p->ptrace_children);
INIT_LIST_HEAD(&p->ptrace_list);
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/*
* Check for pending SIGKILL! The new thread should not be allowed
* to slip out of an OOM kill. (or normal SIGKILL.)
*/
if (sigismember(¤t->pending.signal, SIGKILL)) {
write_unlock_irq(&tasklist_lock);
retval = -EINTR;
goto bad_fork_cleanup_namespace;
}
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & CLONE_PARENT)
p->real_parent = current->real_parent;
else
p->real_parent = current;
p->parent = p->real_parent;
if (clone_flags & CLONE_THREAD) {
spin_lock(¤t->sighand->siglock);
/*
* Important: if an exit-all has been started then
* do not create this new thread - the whole thread
* group is supposed to exit anyway.
*/
if (current->signal->group_exit) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -EAGAIN;
goto bad_fork_cleanup_namespace;
}
p->tgid = current->tgid;
p->group_leader = current->group_leader;
if (current->signal->group_stop_count > 0) {
/*
* There is an all-stop in progress for the group.
* We ourselves will stop as soon as we check signals.
* Make the new thread part of that group stop too.
*/
current->signal->group_stop_count++;
set_tsk_thread_flag(p, TIF_SIGPENDING);
}
spin_unlock(¤t->sighand->siglock);
}
SET_LINKS(p);
if (p->ptrace & PT_PTRACED)
__ptrace_link(p, current->parent);
attach_pid(p, PIDTYPE_PID, p->pid);
if (thread_group_leader(p)) {
attach_pid(p, PIDTYPE_TGID, p->tgid);
attach_pid(p, PIDTYPE_PGID, process_group(p));
attach_pid(p, PIDTYPE_SID, p->signal->session);
if (p->pid)
__get_cpu_var(process_counts)++;
} else
link_pid(p, p->pids + PIDTYPE_TGID, &p->group_leader->pids[PIDTYPE_TGID].pid);
nr_threads++;
write_unlock_irq(&tasklist_lock);
retval = 0;
fork_out:
if (retval)
return ERR_PTR(retval);
return p;
bad_fork_cleanup_namespace:
exit_namespace(p);
bad_fork_cleanup_mm:
exit_mm(p);
if (p->active_mm)
mmdrop(p->active_mm);
bad_fork_cleanup_signal:
exit_signal(p);
bad_fork_cleanup_sighand:
exit_sighand(p);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_security:
security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_free(p->mempolicy);
#endif
bad_fork_cleanup:
if (p->pid > 0)
free_pidmap(p->pid);
if (p->binfmt)
module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
module_put(p->thread_info->exec_domain->module);
bad_fork_cleanup_count:
put_group_info(p->group_info);
atomic_dec(&p->user->processes);
free_uid(p->user);
bad_fork_free:
free_task(p);
goto fork_out;
}
/*
* Copy architecture-specific thread state
*/
int copy_thread(unsigned long clone_flags, unsigned long usp,
unsigned long kthread_arg, struct task_struct *p)
{
struct thread_info *ti = task_thread_info(p);
struct pt_regs *childregs, *regs = current_pt_regs();
unsigned long childksp;
p->set_child_tid = p->clear_child_tid = NULL;
childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
/* set up new TSS. */
childregs = (struct pt_regs *) childksp - 1;
/* Put the stack after the struct pt_regs. */
childksp = (unsigned long) childregs;
p->thread.cp0_status = read_c0_status() & ~(ST0_CU2|ST0_CU1);
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
unsigned long status = p->thread.cp0_status;
memset(childregs, 0, sizeof(struct pt_regs));
ti->addr_limit = KERNEL_DS;
p->thread.reg16 = usp; /* fn */
p->thread.reg17 = kthread_arg;
p->thread.reg29 = childksp;
p->thread.reg31 = (unsigned long) ret_from_kernel_thread;
#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
status = (status & ~(ST0_KUP | ST0_IEP | ST0_IEC)) |
((status & (ST0_KUC | ST0_IEC)) << 2);
#else
status |= ST0_EXL;
#endif
childregs->cp0_status = status;
return 0;
}
/* user thread */
*childregs = *regs;
childregs->regs[7] = 0; /* Clear error flag */
childregs->regs[2] = 0; /* Child gets zero as return value */
if (usp)
childregs->regs[29] = usp;
ti->addr_limit = USER_DS;
p->thread.reg29 = (unsigned long) childregs;
p->thread.reg31 = (unsigned long) ret_from_fork;
/*
* New tasks lose permission to use the fpu. This accelerates context
* switching for most programs since they don't use the fpu.
*/
childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
clear_tsk_thread_flag(p, TIF_USEDFPU);
clear_tsk_thread_flag(p, TIF_USEDMSA);
clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE);
#ifdef CONFIG_MIPS_MT_FPAFF
clear_tsk_thread_flag(p, TIF_FPUBOUND);
#endif /* CONFIG_MIPS_MT_FPAFF */
if (clone_flags & CLONE_SETTLS)
ti->tp_value = regs->regs[7];
return 0;
}
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
int ret;
unsigned long __user *datap = (unsigned long __user *)data;
switch (request) {
/* Read word at location address. */
case PTRACE_PEEKTEXT:
case PTRACE_PEEKDATA: {
unsigned long tmp;
int copied;
ret = -EIO;
/* The signal trampoline page is outside the normal user-addressable
* space but still accessible. This is hack to make it possible to
* access the signal handler code in GDB.
*/
if ((addr & PAGE_MASK) == cris_signal_return_page) {
/* The trampoline page is globally mapped, no page table to traverse.*/
tmp = *(unsigned long*)addr;
} else {
copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
if (copied != sizeof(tmp))
break;
}
ret = put_user(tmp,datap);
break;
}
/* Read the word at location address in the USER area. */
case PTRACE_PEEKUSR: {
unsigned long tmp;
ret = -EIO;
if ((addr & 3) || addr < 0 || addr > PT_MAX << 2)
break;
tmp = get_reg(child, addr >> 2);
ret = put_user(tmp, datap);
break;
}
/* Write the word at location address. */
case PTRACE_POKETEXT:
case PTRACE_POKEDATA:
ret = 0;
if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
break;
ret = -EIO;
break;
/* Write the word at location address in the USER area. */
case PTRACE_POKEUSR:
ret = -EIO;
if ((addr & 3) || addr < 0 || addr > PT_MAX << 2)
break;
addr >>= 2;
if (addr == PT_CCS) {
/* don't allow the tracing process to change stuff like
* interrupt enable, kernel/user bit, dma enables etc.
*/
data &= CCS_MASK;
data |= get_reg(child, PT_CCS) & ~CCS_MASK;
}
if (put_reg(child, addr, data))
break;
ret = 0;
break;
case PTRACE_SYSCALL:
case PTRACE_CONT:
ret = -EIO;
if (!valid_signal(data))
break;
/* Continue means no single-step. */
put_reg(child, PT_SPC, 0);
if (!get_debugreg(child->pid, PT_BP_CTRL)) {
unsigned long tmp;
/* If no h/w bp configured, disable S bit. */
tmp = get_reg(child, PT_CCS) & ~SBIT_USER;
put_reg(child, PT_CCS, tmp);
}
if (request == PTRACE_SYSCALL) {
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
}
else {
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
}
child->exit_code = data;
/* TODO: make sure any pending breakpoint is killed */
wake_up_process(child);
ret = 0;
break;
/* Make the child exit by sending it a sigkill. */
case PTRACE_KILL:
ret = 0;
if (child->exit_state == EXIT_ZOMBIE)
break;
child->exit_code = SIGKILL;
/* Deconfigure single-step and h/w bp. */
ptrace_disable(child);
/* TODO: make sure any pending breakpoint is killed */
wake_up_process(child);
break;
/* Set the trap flag. */
case PTRACE_SINGLESTEP: {
unsigned long tmp;
ret = -EIO;
/* Set up SPC if not set already (in which case we have
no other choice but to trust it). */
if (!get_reg(child, PT_SPC)) {
/* In case we're stopped in a delay slot. */
tmp = get_reg(child, PT_ERP) & ~1;
put_reg(child, PT_SPC, tmp);
}
tmp = get_reg(child, PT_CCS) | SBIT_USER;
put_reg(child, PT_CCS, tmp);
if (!valid_signal(data))
break;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
/* TODO: set some clever breakpoint mechanism... */
child->exit_code = data;
wake_up_process(child);
ret = 0;
break;
}
case PTRACE_DETACH:
ret = ptrace_detach(child, data);
break;
/* Get all GP registers from the child. */
case PTRACE_GETREGS: {
int i;
unsigned long tmp;
for (i = 0; i <= PT_MAX; i++) {
tmp = get_reg(child, i);
if (put_user(tmp, datap)) {
ret = -EFAULT;
goto out_tsk;
}
datap++;
}
ret = 0;
break;
}
/* Set all GP registers in the child. */
case PTRACE_SETREGS: {
int i;
unsigned long tmp;
for (i = 0; i <= PT_MAX; i++) {
if (get_user(tmp, datap)) {
ret = -EFAULT;
goto out_tsk;
}
if (i == PT_CCS) {
tmp &= CCS_MASK;
tmp |= get_reg(child, PT_CCS) & ~CCS_MASK;
}
put_reg(child, i, tmp);
datap++;
}
ret = 0;
break;
}
default:
ret = ptrace_request(child, request, addr, data);
break;
}
return ret;
}
/*
* Called by kernel/ptrace.c when detaching..
*
* Make sure single step bits etc are not set.
*/
void ptrace_disable(struct task_struct *child)
{
/* Don't load the watchpoint registers for the ex-child. */
clear_tsk_thread_flag(child, TIF_LOAD_WATCH);
}
static struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *child_tidptr,
struct pid *pid,
int trace)
{
int retval;
struct task_struct *p;
int cgroup_callbacks_done = 0;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
if ((clone_flags & CLONE_PARENT) &&
current->signal->flags & SIGNAL_UNKILLABLE)
return ERR_PTR(-EINVAL);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
ftrace_graph_init_task(p);
rt_mutex_init_task(p);
#ifdef CONFIG_PROVE_LOCKING
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
retval = -EAGAIN;
if (atomic_read(&p->real_cred->user->processes) >=
task_rlimit(p, RLIMIT_NPROC)) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->real_cred->user != INIT_USER)
goto bad_fork_free;
}
current->flags &= ~PF_NPROC_EXCEEDED;
retval = copy_creds(p, clone_flags);
if (retval < 0)
goto bad_fork_free;
retval = -EAGAIN;
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
p->did_exec = 0;
delayacct_tsk_init(p);
copy_flags(clone_flags, p);
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
rcu_copy_process(p);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
init_sigpending(&p->pending);
p->utime = p->stime = p->gtime = 0;
p->utimescaled = p->stimescaled = 0;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
p->prev_utime = p->prev_stime = 0;
#endif
#if defined(SPLIT_RSS_COUNTING)
memset(&p->rss_stat, 0, sizeof(p->rss_stat));
#endif
p->default_timer_slack_ns = current->timer_slack_ns;
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
posix_cpu_timers_init(p);
do_posix_clock_monotonic_gettime(&p->start_time);
p->real_start_time = p->start_time;
monotonic_to_bootbased(&p->real_start_time);
p->io_context = NULL;
p->audit_context = NULL;
if (clone_flags & CLONE_THREAD)
threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup_cgroup;
}
mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_CPUSETS
p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
seqcount_init(&p->mems_allowed_seq);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
p->hardirqs_enabled = 1;
#else
p->hardirqs_enabled = 0;
#endif
p->hardirq_enable_ip = 0;
p->hardirq_enable_event = 0;
p->hardirq_disable_ip = _THIS_IP_;
p->hardirq_disable_event = 0;
p->softirqs_enabled = 1;
p->softirq_enable_ip = _THIS_IP_;
p->softirq_enable_event = 0;
p->softirq_disable_ip = 0;
p->softirq_disable_event = 0;
p->hardirq_context = 0;
p->softirq_context = 0;
#endif
#ifdef CONFIG_LOCKDEP
p->lockdep_depth = 0;
p->curr_chain_key = 0;
p->lockdep_recursion = 0;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL;
p->blocked_by = NULL;
p->blocked_since = 0;
#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
p->memcg_batch.do_batch = 0;
p->memcg_batch.memcg = NULL;
#endif
sched_fork(p);
retval = perf_event_init_task(p);
if (retval)
goto bad_fork_cleanup_policy;
retval = audit_alloc(p);
if (retval)
goto bad_fork_cleanup_policy;
retval = copy_semundo(clone_flags, p);
if (retval)
goto bad_fork_cleanup_audit;
retval = copy_files(clone_flags, p);
if (retval)
goto bad_fork_cleanup_semundo;
retval = copy_fs(clone_flags, p);
if (retval)
goto bad_fork_cleanup_files;
retval = copy_sighand(clone_flags, p);
if (retval)
goto bad_fork_cleanup_fs;
retval = copy_signal(clone_flags, p);
if (retval)
goto bad_fork_cleanup_sighand;
retval = copy_mm(clone_flags, p);
if (retval)
goto bad_fork_cleanup_signal;
retval = copy_namespaces(clone_flags, p);
if (retval)
goto bad_fork_cleanup_mm;
retval = copy_io(clone_flags, p);
if (retval)
goto bad_fork_cleanup_namespaces;
retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(p->nsproxy->pid_ns);
if (!pid)
goto bad_fork_cleanup_io;
}
p->pid = pid_nr(pid);
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
#ifdef CONFIG_FUTEX
p->robust_list = NULL;
#ifdef CONFIG_COMPAT
p->compat_robust_list = NULL;
#endif
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
#endif
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
p->sas_ss_sp = p->sas_ss_size = 0;
user_disable_single_step(p);
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
clear_all_latency_tracing(p);
if (clone_flags & CLONE_THREAD)
p->exit_signal = -1;
else if (clone_flags & CLONE_PARENT)
p->exit_signal = current->group_leader->exit_signal;
else
p->exit_signal = (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
p->exit_state = 0;
p->nr_dirtied = 0;
p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
p->dirty_paused_when = 0;
p->group_leader = p;
INIT_LIST_HEAD(&p->thread_group);
cgroup_fork_callbacks(p);
cgroup_callbacks_done = 1;
write_lock_irq(&tasklist_lock);
if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
p->real_parent = current->real_parent;
p->parent_exec_id = current->parent_exec_id;
} else {
p->real_parent = current;
p->parent_exec_id = current->self_exec_id;
}
spin_lock(¤t->sighand->siglock);
recalc_sigpending();
if (signal_pending(current)) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_free_pid;
}
if (clone_flags & CLONE_THREAD) {
current->signal->nr_threads++;
atomic_inc(¤t->signal->live);
atomic_inc(¤t->signal->sigcnt);
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
}
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
if (thread_group_leader(p)) {
if (is_child_reaper(pid))
p->nsproxy->pid_ns->child_reaper = p;
p->signal->leader_pid = pid;
p->signal->tty = tty_kref_get(current->signal->tty);
attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
attach_pid(p, PIDTYPE_SID, task_session(current));
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
__this_cpu_inc(process_counts);
}
attach_pid(p, PIDTYPE_PID, pid);
nr_threads++;
}
total_forks++;
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
perf_event_fork(p);
trace_task_newtask(p, clone_flags);
return p;
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_io:
if (p->io_context)
exit_io_context(p);
bad_fork_cleanup_namespaces:
if (unlikely(clone_flags & CLONE_NEWPID))
pid_ns_release_proc(p->nsproxy->pid_ns);
exit_task_namespaces(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
free_signal_struct(p->signal);
bad_fork_cleanup_sighand:
__cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
exit_fs(p);
bad_fork_cleanup_files:
exit_files(p);
bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_policy:
perf_event_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
exit_creds(p);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
unsigned long unused, struct task_struct *p, struct pt_regs *regs)
{
struct thread_info *ti = task_thread_info(p);
struct pt_regs *childregs;
long childksp;
p->set_child_tid = p->clear_child_tid = NULL;
childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
preempt_disable();
if (is_fpu_owner())
save_fp(p);
if (cpu_has_dsp)
save_dsp(p);
preempt_enable();
/* set up new TSS. */
childregs = (struct pt_regs *) childksp - 1;
*childregs = *regs;
childregs->regs[7] = 0; /* Clear error flag */
#if defined(CONFIG_BINFMT_IRIX)
if (current->personality != PER_LINUX) {
/* Under IRIX things are a little different. */
childregs->regs[3] = 1;
regs->regs[3] = 0;
}
#endif
childregs->regs[2] = 0; /* Child gets zero as return value */
regs->regs[2] = p->pid;
if (childregs->cp0_status & ST0_CU0) {
childregs->regs[28] = (unsigned long) ti;
childregs->regs[29] = childksp;
ti->addr_limit = KERNEL_DS;
} else {
childregs->regs[29] = usp;
ti->addr_limit = USER_DS;
}
p->thread.reg29 = (unsigned long) childregs;
p->thread.reg31 = (unsigned long) ret_from_fork;
/*
* New tasks lose permission to use the fpu. This accelerates context
* switching for most programs since they don't use the fpu.
*/
p->thread.cp0_status = read_c0_status() & ~(ST0_CU2|ST0_CU1);
childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
clear_tsk_thread_flag(p, TIF_USEDFPU);
#ifdef CONFIG_MIPS_MT_FPAFF
/*
* FPU affinity support is cleaner if we track the
* user-visible CPU affinity from the very beginning.
* The generic cpus_allowed mask will already have
* been copied from the parent before copy_thread
* is invoked.
*/
p->thread.user_cpus_allowed = p->cpus_allowed;
#endif /* CONFIG_MIPS_MT_FPAFF */
if (clone_flags & CLONE_SETTLS)
ti->tp_value = regs->regs[7];
return 0;
}
int copy_thread(unsigned long clone_flags, unsigned long stack_start,
unsigned long stk_sz, struct task_struct *p)
{
struct pt_regs *childregs = task_pt_regs(p);
memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
/*
* Unalias p->thread.sve_state (if any) from the parent task
* and disable discard SVE state for p:
*/
clear_tsk_thread_flag(p, TIF_SVE);
p->thread.sve_state = NULL;
/*
* In case p was allocated the same task_struct pointer as some
* other recently-exited task, make sure p is disassociated from
* any cpu that may have run that now-exited task recently.
* Otherwise we could erroneously skip reloading the FPSIMD
* registers for p.
*/
fpsimd_flush_task_state(p);
if (likely(!(p->flags & PF_KTHREAD))) {
*childregs = *current_pt_regs();
childregs->regs[0] = 0;
/*
* Read the current TLS pointer from tpidr_el0 as it may be
* out-of-sync with the saved value.
*/
*task_user_tls(p) = read_sysreg(tpidr_el0);
if (stack_start) {
if (is_compat_thread(task_thread_info(p)))
childregs->compat_sp = stack_start;
else
childregs->sp = stack_start;
}
/*
* If a TLS pointer was passed to clone (4th argument), use it
* for the new thread.
*/
if (clone_flags & CLONE_SETTLS)
p->thread.uw.tp_value = childregs->regs[3];
} else {
memset(childregs, 0, sizeof(struct pt_regs));
childregs->pstate = PSR_MODE_EL1h;
if (IS_ENABLED(CONFIG_ARM64_UAO) &&
cpus_have_const_cap(ARM64_HAS_UAO))
childregs->pstate |= PSR_UAO_BIT;
if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
childregs->pstate |= PSR_SSBS_BIT;
if (system_uses_irq_prio_masking())
childregs->pmr_save = GIC_PRIO_IRQON;
p->thread.cpu_context.x19 = stack_start;
p->thread.cpu_context.x20 = stk_sz;
}
p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
p->thread.cpu_context.sp = (unsigned long)childregs;
ptrace_hw_copy_thread(p);
return 0;
}
/*
* Note that this implementation of ptrace behaves differently from vanilla
* ptrace. Contrary to what the man page says, in the PTRACE_PEEKTEXT,
* PTRACE_PEEKDATA, and PTRACE_PEEKUSER requests the data variable is not
* ignored. Instead, the data variable is expected to point at a location
* (in user space) where the result of the ptrace call is written (instead of
* being returned).
*/
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
int ret;
unsigned long __user *datap = (unsigned long __user *)data;
switch (request) {
/* Read word at location address. */
case PTRACE_PEEKTEXT:
case PTRACE_PEEKDATA:
ret = generic_ptrace_peekdata(child, addr, data);
break;
/* Read the word at location address in the USER area. */
case PTRACE_PEEKUSR: {
unsigned long tmp;
ret = -EIO;
if ((addr & 3) || addr < 0 || addr > PT_MAX << 2)
break;
tmp = get_reg(child, addr >> 2);
ret = put_user(tmp, datap);
break;
}
/* Write the word at location address. */
case PTRACE_POKETEXT:
case PTRACE_POKEDATA:
ret = generic_ptrace_pokedata(child, addr, data);
break;
/* Write the word at location address in the USER area. */
case PTRACE_POKEUSR:
ret = -EIO;
if ((addr & 3) || addr < 0 || addr > PT_MAX << 2)
break;
addr >>= 2;
if (addr == PT_DCCR) {
/* don't allow the tracing process to change stuff like
* interrupt enable, kernel/user bit, dma enables etc.
*/
data &= DCCR_MASK;
data |= get_reg(child, PT_DCCR) & ~DCCR_MASK;
}
if (put_reg(child, addr, data))
break;
ret = 0;
break;
case PTRACE_SYSCALL:
case PTRACE_CONT:
ret = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSCALL) {
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
}
else {
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
}
child->exit_code = data;
/* TODO: make sure any pending breakpoint is killed */
wake_up_process(child);
ret = 0;
break;
/* Make the child exit by sending it a sigkill. */
case PTRACE_KILL:
ret = 0;
if (child->exit_state == EXIT_ZOMBIE)
break;
child->exit_code = SIGKILL;
/* TODO: make sure any pending breakpoint is killed */
wake_up_process(child);
break;
/* Set the trap flag. */
case PTRACE_SINGLESTEP:
ret = -EIO;
if (!valid_signal(data))
break;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
/* TODO: set some clever breakpoint mechanism... */
child->exit_code = data;
wake_up_process(child);
ret = 0;
break;
/* Get all GP registers from the child. */
case PTRACE_GETREGS: {
int i;
unsigned long tmp;
ret = 0;
for (i = 0; i <= PT_MAX; i++) {
tmp = get_reg(child, i);
if (put_user(tmp, datap)) {
ret = -EFAULT;
break;
}
data += sizeof(long);
}
break;
}
/* Set all GP registers in the child. */
case PTRACE_SETREGS: {
int i;
unsigned long tmp;
ret = 0;
for (i = 0; i <= PT_MAX; i++) {
if (get_user(tmp, datap)) {
ret = -EFAULT;
break;
}
if (i == PT_DCCR) {
tmp &= DCCR_MASK;
tmp |= get_reg(child, PT_DCCR) & ~DCCR_MASK;
}
put_reg(child, i, tmp);
data += sizeof(long);
}
break;
}
default:
ret = ptrace_request(child, request, addr, data);
break;
}
return ret;
}
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
*
* It copies the registers, and all the appropriate
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
static task_t *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr,
int pid)
{
int retval;
struct task_struct *p = NULL;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
*/
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
/*
* Shared signal handlers imply shared VM. By way of the above,
* thread groups also imply shared VM. Blocking this case allows
* for various simplifications in other code.
*/
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
retval = -EAGAIN;
if (atomic_read(&p->user->processes) >=
p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->user != &root_user)
goto bad_fork_free;
}
atomic_inc(&p->user->__count);
atomic_inc(&p->user->processes);
get_group_info(p->group_info);
/*
* If multiple threads are within copy_process(), then this check
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
if (!try_module_get(p->thread_info->exec_domain->module))
goto bad_fork_cleanup_count;
if (p->binfmt && !try_module_get(p->binfmt->module))
goto bad_fork_cleanup_put_domain;
p->did_exec = 0;
copy_flags(clone_flags, p);
p->pid = pid;
retval = -EFAULT;
if (clone_flags & CLONE_PARENT_SETTID)
if (put_user(p->pid, parent_tidptr))
goto bad_fork_cleanup;
p->proc_dentry = NULL;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
spin_lock_init(&p->proc_lock);
clear_tsk_thread_flag(p, TIF_SIGPENDING);
init_sigpending(&p->pending);
p->utime = cputime_zero;
p->stime = cputime_zero;
p->sched_time = 0;
p->rchar = 0; /* I/O counter: bytes read */
p->wchar = 0; /* I/O counter: bytes written */
p->syscr = 0; /* I/O counter: read syscalls */
p->syscw = 0; /* I/O counter: write syscalls */
acct_clear_integrals(p);
p->it_virt_expires = cputime_zero;
p->it_prof_expires = cputime_zero;
p->it_sched_expires = 0;
INIT_LIST_HEAD(&p->cpu_timers[0]);
INIT_LIST_HEAD(&p->cpu_timers[1]);
INIT_LIST_HEAD(&p->cpu_timers[2]);
p->lock_depth = -1; /* -1 = no lock */
do_posix_clock_monotonic_gettime(&p->start_time);
p->security = NULL;
p->io_context = NULL;
p->io_wait = NULL;
p->audit_context = NULL;
#ifdef CONFIG_NUMA
p->mempolicy = mpol_copy(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup;
}
#endif
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
if ((retval = security_task_alloc(p)))
goto bad_fork_cleanup_policy;
if ((retval = audit_alloc(p)))
goto bad_fork_cleanup_security;
/* copy all the process information */
if ((retval = copy_semundo(clone_flags, p)))
goto bad_fork_cleanup_audit;
if ((retval = copy_files(clone_flags, p)))
goto bad_fork_cleanup_semundo;
if ((retval = copy_fs(clone_flags, p)))
goto bad_fork_cleanup_files;
if ((retval = copy_sighand(clone_flags, p)))
goto bad_fork_cleanup_fs;
if ((retval = copy_signal(clone_flags, p)))
goto bad_fork_cleanup_sighand;
if ((retval = copy_mm(clone_flags, p)))
goto bad_fork_cleanup_signal;
if ((retval = copy_keys(clone_flags, p)))
goto bad_fork_cleanup_mm;
if ((retval = copy_namespace(clone_flags, p)))
goto bad_fork_cleanup_keys;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_namespace;
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
/*
* Clear TID on mm_release()?
*/
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
/*
* Syscall tracing should be turned off in the child regardless
* of CLONE_PTRACE.
*/
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
p->parent_exec_id = p->self_exec_id;
/* ok, now we should be set up.. */
p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
p->exit_state = 0;
/* Perform scheduler related setup */
sched_fork(p);
/*
* Ok, make it visible to the rest of the system.
* We dont wake it up yet.
*/
p->group_leader = p;
INIT_LIST_HEAD(&p->ptrace_children);
INIT_LIST_HEAD(&p->ptrace_list);
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/*
* The task hasn't been attached yet, so cpus_allowed mask cannot
* have changed. The cpus_allowed mask of the parent may have
* changed after it was copied first time, and it may then move to
* another CPU - so we re-copy it here and set the child's CPU to
* the parent's CPU. This avoids alot of nasty races.
*/
p->cpus_allowed = current->cpus_allowed;
set_task_cpu(p, smp_processor_id());
/*
* Check for pending SIGKILL! The new thread should not be allowed
* to slip out of an OOM kill. (or normal SIGKILL.)
*/
if (sigismember(¤t->pending.signal, SIGKILL)) {
write_unlock_irq(&tasklist_lock);
retval = -EINTR;
goto bad_fork_cleanup_namespace;
}
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
p->real_parent = current->real_parent;
else
p->real_parent = current;
p->parent = p->real_parent;
if (clone_flags & CLONE_THREAD) {
spin_lock(¤t->sighand->siglock);
/*
* Important: if an exit-all has been started then
* do not create this new thread - the whole thread
* group is supposed to exit anyway.
*/
if (current->signal->flags & SIGNAL_GROUP_EXIT) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -EAGAIN;
goto bad_fork_cleanup_namespace;
}
p->group_leader = current->group_leader;
if (current->signal->group_stop_count > 0) {
/*
* There is an all-stop in progress for the group.
* We ourselves will stop as soon as we check signals.
* Make the new thread part of that group stop too.
*/
current->signal->group_stop_count++;
set_tsk_thread_flag(p, TIF_SIGPENDING);
}
if (!cputime_eq(current->signal->it_virt_expires,
cputime_zero) ||
!cputime_eq(current->signal->it_prof_expires,
cputime_zero) ||
current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
!list_empty(¤t->signal->cpu_timers[0]) ||
!list_empty(¤t->signal->cpu_timers[1]) ||
!list_empty(¤t->signal->cpu_timers[2])) {
/*
* Have child wake up on its first tick to check
* for process CPU timers.
*/
p->it_prof_expires = jiffies_to_cputime(1);
}
spin_unlock(¤t->sighand->siglock);
}
SET_LINKS(p);
if (unlikely(p->ptrace & PT_PTRACED))
__ptrace_link(p, current->parent);
cpuset_fork(p);
attach_pid(p, PIDTYPE_PID, p->pid);
attach_pid(p, PIDTYPE_TGID, p->tgid);
if (thread_group_leader(p)) {
attach_pid(p, PIDTYPE_PGID, process_group(p));
attach_pid(p, PIDTYPE_SID, p->signal->session);
if (p->pid)
__get_cpu_var(process_counts)++;
}
nr_threads++;
total_forks++;
write_unlock_irq(&tasklist_lock);
retval = 0;
fork_out:
if (retval)
return ERR_PTR(retval);
return p;
bad_fork_cleanup_namespace:
exit_namespace(p);
bad_fork_cleanup_keys:
exit_keys(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
exit_signal(p);
bad_fork_cleanup_sighand:
exit_sighand(p);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_security:
security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_free(p->mempolicy);
#endif
bad_fork_cleanup:
if (p->binfmt)
module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
module_put(p->thread_info->exec_domain->module);
bad_fork_cleanup_count:
put_group_info(p->group_info);
atomic_dec(&p->user->processes);
free_uid(p->user);
bad_fork_free:
free_task(p);
goto fork_out;
}
void user_disable_single_step(struct task_struct *child)
{
clear_tsk_thread_flag(child, TIF_SINGLESTEP);
}
int sys_ptrace(long request, long pid, long addr, long data)
{
struct task_struct *child;
int ret = -EPERM;
lock_kernel();
if (request == PTRACE_TRACEME) {
/* are we already being traced? */
if (current->ptrace & PT_PTRACED)
goto out;
ret = security_ptrace(current->parent, current);
if (ret)
goto out;
/* set the ptrace bit in the process flags. */
current->ptrace |= PT_PTRACED;
ret = 0;
goto out;
}
ret = -ESRCH;
read_lock(&tasklist_lock);
child = find_task_by_pid(pid);
if (child)
get_task_struct(child);
read_unlock(&tasklist_lock);
if (!child)
goto out;
ret = -EPERM;
if (pid == 1) /* you may not mess with init */
goto out_tsk;
if (request == PTRACE_ATTACH) {
ret = ptrace_attach(child);
goto out_tsk;
}
ret = ptrace_check_attach(child, request == PTRACE_KILL);
if (ret < 0)
goto out_tsk;
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA: {
unsigned long tmp;
int copied;
copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
ret = -EIO;
if (copied != sizeof(tmp))
break;
ret = put_user(tmp,(unsigned long __user *) data);
break;
}
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
unsigned long index;
unsigned long tmp;
ret = -EIO;
/* convert to index and check */
index = (unsigned long) addr >> 3;
if ((addr & 7) || (index > PT_FPSCR))
break;
if (index < PT_FPR0) {
tmp = get_reg(child, (int)index);
} else {
flush_fp_to_thread(child);
tmp = ((unsigned long *)child->thread.fpr)[index - PT_FPR0];
}
ret = put_user(tmp,(unsigned long __user *) data);
break;
}
/* If I and D space are separate, this will have to be fixed. */
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
ret = 0;
if (access_process_vm(child, addr, &data, sizeof(data), 1)
== sizeof(data))
break;
ret = -EIO;
break;
/* write the word at location addr in the USER area */
case PTRACE_POKEUSR: {
unsigned long index;
ret = -EIO;
/* convert to index and check */
index = (unsigned long) addr >> 3;
if ((addr & 7) || (index > PT_FPSCR))
break;
if (index == PT_ORIG_R3)
break;
if (index < PT_FPR0) {
ret = put_reg(child, index, data);
} else {
flush_fp_to_thread(child);
((unsigned long *)child->thread.fpr)[index - PT_FPR0] = data;
ret = 0;
}
break;
}
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT: { /* restart after signal. */
ret = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSCALL)
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->exit_code = data;
/* make sure the single step bit is not set. */
clear_single_step(child);
wake_up_process(child);
ret = 0;
break;
}
/*
* make the child exit. Best I can do is send it a sigkill.
* perhaps it should be put in the status that it wants to
* exit.
*/
case PTRACE_KILL: {
ret = 0;
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
break;
child->exit_code = SIGKILL;
/* make sure the single step bit is not set. */
clear_single_step(child);
wake_up_process(child);
break;
}
case PTRACE_SINGLESTEP: { /* set the trap flag. */
ret = -EIO;
if (!valid_signal(data))
break;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
set_single_step(child);
child->exit_code = data;
/* give it a chance to run. */
wake_up_process(child);
ret = 0;
break;
}
case PTRACE_GET_DEBUGREG: {
ret = -EINVAL;
/* We only support one DABR and no IABRS at the moment */
if (addr > 0)
break;
ret = put_user(child->thread.dabr,
(unsigned long __user *)data);
break;
}
case PTRACE_SET_DEBUGREG:
ret = ptrace_set_debugreg(child, addr, data);
break;
case PTRACE_DETACH:
ret = ptrace_detach(child, data);
break;
case PPC_PTRACE_GETREGS: { /* Get GPRs 0 - 31. */
int i;
unsigned long *reg = &((unsigned long *)child->thread.regs)[0];
unsigned long __user *tmp = (unsigned long __user *)addr;
for (i = 0; i < 32; i++) {
ret = put_user(*reg, tmp);
if (ret)
break;
reg++;
tmp++;
}
break;
}
case PPC_PTRACE_SETREGS: { /* Set GPRs 0 - 31. */
int i;
unsigned long *reg = &((unsigned long *)child->thread.regs)[0];
unsigned long __user *tmp = (unsigned long __user *)addr;
for (i = 0; i < 32; i++) {
ret = get_user(*reg, tmp);
if (ret)
break;
reg++;
tmp++;
}
break;
}
case PPC_PTRACE_GETFPREGS: { /* Get FPRs 0 - 31. */
int i;
unsigned long *reg = &((unsigned long *)child->thread.fpr)[0];
unsigned long __user *tmp = (unsigned long __user *)addr;
flush_fp_to_thread(child);
for (i = 0; i < 32; i++) {
ret = put_user(*reg, tmp);
if (ret)
break;
reg++;
tmp++;
}
break;
}
case PPC_PTRACE_SETFPREGS: { /* Get FPRs 0 - 31. */
int i;
unsigned long *reg = &((unsigned long *)child->thread.fpr)[0];
unsigned long __user *tmp = (unsigned long __user *)addr;
flush_fp_to_thread(child);
for (i = 0; i < 32; i++) {
ret = get_user(*reg, tmp);
if (ret)
break;
reg++;
tmp++;
}
break;
}
#ifdef CONFIG_ALTIVEC
case PTRACE_GETVRREGS:
/* Get the child altivec register state. */
flush_altivec_to_thread(child);
ret = get_vrregs((unsigned long __user *)data, child);
break;
case PTRACE_SETVRREGS:
/* Set the child altivec register state. */
flush_altivec_to_thread(child);
ret = set_vrregs(child, (unsigned long __user *)data);
break;
#endif
default:
ret = ptrace_request(child, request, addr, data);
break;
}
out_tsk:
put_task_struct(child);
out:
unlock_kernel();
return ret;
}
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
int ret;
unsigned long __user *datap = (unsigned long __user *)data;
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKDATA:
pr_debug("ptrace: PEEKDATA\n");
/* fall through */
case PTRACE_PEEKTEXT: /* read word at location addr. */
{
unsigned long tmp = 0;
int copied;
ret = -EIO;
pr_debug("ptrace: PEEKTEXT at addr 0x%08lx + %ld\n", addr, sizeof(data));
if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0)
break;
pr_debug("ptrace: user address is valid\n");
if (L1_CODE_LENGTH != 0 && addr >= get_l1_code_start()
&& addr + sizeof(tmp) <= get_l1_code_start() + L1_CODE_LENGTH) {
safe_dma_memcpy (&tmp, (const void *)(addr), sizeof(tmp));
copied = sizeof(tmp);
} else if (L1_DATA_A_LENGTH != 0 && addr >= L1_DATA_A_START
&& addr + sizeof(tmp) <= L1_DATA_A_START + L1_DATA_A_LENGTH) {
memcpy(&tmp, (const void *)(addr), sizeof(tmp));
copied = sizeof(tmp);
} else if (L1_DATA_B_LENGTH != 0 && addr >= L1_DATA_B_START
&& addr + sizeof(tmp) <= L1_DATA_B_START + L1_DATA_B_LENGTH) {
memcpy(&tmp, (const void *)(addr), sizeof(tmp));
copied = sizeof(tmp);
} else if (addr >= FIXED_CODE_START
&& addr + sizeof(tmp) <= FIXED_CODE_END) {
copy_from_user_page(0, 0, 0, &tmp, (const void *)(addr), sizeof(tmp));
copied = sizeof(tmp);
} else
copied = access_process_vm(child, addr, &tmp,
sizeof(tmp), 0);
pr_debug("ptrace: copied size %d [0x%08lx]\n", copied, tmp);
if (copied != sizeof(tmp))
break;
ret = put_user(tmp, datap);
break;
}
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR:
{
unsigned long tmp;
ret = -EIO;
tmp = 0;
if ((addr & 3) || (addr > (sizeof(struct pt_regs) + 16))) {
printk(KERN_WARNING "ptrace error : PEEKUSR : temporarily returning "
"0 - %x sizeof(pt_regs) is %lx\n",
(int)addr, sizeof(struct pt_regs));
break;
}
if (addr == sizeof(struct pt_regs)) {
/* PT_TEXT_ADDR */
tmp = child->mm->start_code + TEXT_OFFSET;
} else if (addr == (sizeof(struct pt_regs) + 4)) {
/* PT_TEXT_END_ADDR */
tmp = child->mm->end_code;
} else if (addr == (sizeof(struct pt_regs) + 8)) {
/* PT_DATA_ADDR */
tmp = child->mm->start_data;
#ifdef CONFIG_BINFMT_ELF_FDPIC
} else if (addr == (sizeof(struct pt_regs) + 12)) {
tmp = child->mm->context.exec_fdpic_loadmap;
} else if (addr == (sizeof(struct pt_regs) + 16)) {
tmp = child->mm->context.interp_fdpic_loadmap;
#endif
} else {
tmp = get_reg(child, addr);
}
ret = put_user(tmp, datap);
break;
}
/* when I and D space are separate, this will have to be fixed. */
case PTRACE_POKEDATA:
pr_debug("ptrace: PTRACE_PEEKDATA\n");
/* fall through */
case PTRACE_POKETEXT: /* write the word at location addr. */
{
int copied;
ret = -EIO;
pr_debug("ptrace: POKETEXT at addr 0x%08lx + %ld bytes %lx\n",
addr, sizeof(data), data);
if (is_user_addr_valid(child, addr, sizeof(data)) < 0)
break;
pr_debug("ptrace: user address is valid\n");
if (L1_CODE_LENGTH != 0 && addr >= get_l1_code_start()
&& addr + sizeof(data) <= get_l1_code_start() + L1_CODE_LENGTH) {
safe_dma_memcpy ((void *)(addr), &data, sizeof(data));
copied = sizeof(data);
} else if (L1_DATA_A_LENGTH != 0 && addr >= L1_DATA_A_START
&& addr + sizeof(data) <= L1_DATA_A_START + L1_DATA_A_LENGTH) {
memcpy((void *)(addr), &data, sizeof(data));
copied = sizeof(data);
} else if (L1_DATA_B_LENGTH != 0 && addr >= L1_DATA_B_START
&& addr + sizeof(data) <= L1_DATA_B_START + L1_DATA_B_LENGTH) {
memcpy((void *)(addr), &data, sizeof(data));
copied = sizeof(data);
} else if (addr >= FIXED_CODE_START
&& addr + sizeof(data) <= FIXED_CODE_END) {
copy_to_user_page(0, 0, 0, (void *)(addr), &data, sizeof(data));
copied = sizeof(data);
} else
copied = access_process_vm(child, addr, &data,
sizeof(data), 1);
pr_debug("ptrace: copied size %d\n", copied);
if (copied != sizeof(data))
break;
ret = 0;
break;
}
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
ret = -EIO;
if ((addr & 3) || (addr > (sizeof(struct pt_regs) + 16))) {
printk(KERN_WARNING "ptrace error : POKEUSR: temporarily returning 0\n");
break;
}
if (addr >= (sizeof(struct pt_regs))) {
ret = 0;
break;
}
if (addr == PT_SYSCFG) {
data &= SYSCFG_MASK;
data |= get_reg(child, PT_SYSCFG);
}
ret = put_reg(child, addr, data);
break;
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT: /* restart after signal. */
pr_debug("ptrace: syscall/cont\n");
ret = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSCALL)
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->exit_code = data;
ptrace_disable(child);
pr_debug("ptrace: before wake_up_process\n");
wake_up_process(child);
ret = 0;
break;
/*
* make the child exit. Best I can do is send it a sigkill.
* perhaps it should be put in the status that it wants to
* exit.
*/
case PTRACE_KILL:
ret = 0;
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
break;
child->exit_code = SIGKILL;
ptrace_disable(child);
wake_up_process(child);
break;
case PTRACE_SINGLESTEP: /* set the trap flag. */
pr_debug("ptrace: single step\n");
ret = -EIO;
if (!valid_signal(data))
break;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
ptrace_enable(child);
child->exit_code = data;
wake_up_process(child);
ret = 0;
break;
case PTRACE_GETREGS:
/* Get all gp regs from the child. */
ret = ptrace_getregs(child, datap);
break;
case PTRACE_SETREGS:
printk(KERN_WARNING "ptrace: SETREGS: **** NOT IMPLEMENTED ***\n");
/* Set all gp regs in the child. */
ret = 0;
break;
default:
ret = ptrace_request(child, request, addr, data);
break;
}
return ret;
}
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
int rval;
unsigned long val = 0;
unsigned long copied;
switch (request) {
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA:
pr_debug("PEEKTEXT/PEEKDATA at %08lX\n", addr);
copied = access_process_vm(child, addr, &val, sizeof(val), 0);
rval = -EIO;
if (copied != sizeof(val))
break;
rval = put_user(val, (unsigned long *)data);
break;
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
pr_debug("POKETEXT/POKEDATA to %08lX\n", addr);
rval = 0;
if (access_process_vm(child, addr, &data, sizeof(data), 1)
== sizeof(data))
break;
rval = -EIO;
break;
/* Read/write the word at location ADDR in the registers. */
case PTRACE_PEEKUSR:
case PTRACE_POKEUSR:
pr_debug("PEEKUSR/POKEUSR : 0x%08lx\n", addr);
rval = 0;
if (addr >= PT_SIZE && request == PTRACE_PEEKUSR) {
/*
* Special requests that don't actually correspond
* to offsets in struct pt_regs.
*/
if (addr == PT_TEXT_ADDR) {
val = child->mm->start_code;
} else if (addr == PT_DATA_ADDR) {
val = child->mm->start_data;
} else if (addr == PT_TEXT_LEN) {
val = child->mm->end_code
- child->mm->start_code;
} else {
rval = -EIO;
}
} else if (addr >= 0 && addr < PT_SIZE && (addr & 0x3) == 0) {
microblaze_reg_t *reg_addr = reg_save_addr(addr, child);
if (request == PTRACE_PEEKUSR)
val = *reg_addr;
else
*reg_addr = data;
} else
rval = -EIO;
if (rval == 0 && request == PTRACE_PEEKUSR)
rval = put_user(val, (unsigned long *)data);
break;
/* Continue and stop at next (return from) syscall */
case PTRACE_SYSCALL:
pr_debug("PTRACE_SYSCALL\n");
case PTRACE_SINGLESTEP:
pr_debug("PTRACE_SINGLESTEP\n");
/* Restart after a signal. */
case PTRACE_CONT:
pr_debug("PTRACE_CONT\n");
rval = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSCALL)
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->exit_code = data;
pr_debug("wakeup_process\n");
wake_up_process(child);
rval = 0;
break;
/*
* make the child exit. Best I can do is send it a sigkill.
* perhaps it should be put in the status that it wants to
* exit.
*/
case PTRACE_KILL:
pr_debug("PTRACE_KILL\n");
rval = 0;
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
break;
child->exit_code = SIGKILL;
wake_up_process(child);
break;
case PTRACE_DETACH: /* detach a process that was attached. */
pr_debug("PTRACE_DETACH\n");
rval = ptrace_detach(child, data);
break;
default:
/* rval = ptrace_request(child, request, addr, data); noMMU */
rval = -EIO;
}
return rval;
}
/*
* Called by kernel/ptrace.c when detaching.
*
* Make sure the single step bit is not set.
*/
void
ptrace_disable(struct task_struct *child)
{
/* Todo - pending singlesteps? */
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
}
int copy_thread(unsigned long clone_flags, unsigned long usp,
unsigned long unused, struct task_struct *p, struct pt_regs *regs)
{
struct thread_info *ti = task_thread_info(p);
struct pt_regs *childregs;
unsigned long childksp;
p->set_child_tid = p->clear_child_tid = NULL;
childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
preempt_disable();
if (is_fpu_owner())
save_fp(p);
if (cpu_has_dsp)
save_dsp(p);
preempt_enable();
/* set up new TSS. */
childregs = (struct pt_regs *) childksp - 1;
/* Put the stack after the struct pt_regs. */
childksp = (unsigned long) childregs;
*childregs = *regs;
childregs->regs[7] = 0; /* Clear error flag */
childregs->regs[2] = 0; /* Child gets zero as return value */
if (childregs->cp0_status & ST0_CU0) {
childregs->regs[28] = (unsigned long) ti;
childregs->regs[29] = childksp;
ti->addr_limit = KERNEL_DS;
} else {
childregs->regs[29] = usp;
ti->addr_limit = USER_DS;
}
p->thread.reg29 = (unsigned long) childregs;
p->thread.reg31 = (unsigned long) ret_from_fork;
/*
* New tasks lose permission to use the fpu. This accelerates context
* switching for most programs since they don't use the fpu.
*/
p->thread.cp0_status = read_c0_status() & ~(ST0_CU2|ST0_CU1);
childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
#ifdef CONFIG_MIPS_MT_SMTC
/*
* SMTC restores TCStatus after Status, and the CU bits
* are aliased there.
*/
childregs->cp0_tcstatus &= ~(ST0_CU2|ST0_CU1);
#endif
clear_tsk_thread_flag(p, TIF_USEDFPU);
#ifdef CONFIG_MIPS_MT_FPAFF
clear_tsk_thread_flag(p, TIF_FPUBOUND);
#endif /* CONFIG_MIPS_MT_FPAFF */
if (clone_flags & CLONE_SETTLS)
ti->tp_value = regs->regs[7];
return 0;
}
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
int ret = -EPERM;
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA:
ret = generic_ptrace_peekdata(child, addr, data);
break;
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
unsigned long index, tmp;
ret = -EIO;
/* convert to index and check */
#ifdef CONFIG_PPC32
index = (unsigned long) addr >> 2;
if ((addr & 3) || (index > PT_FPSCR)
|| (child->thread.regs == NULL))
#else
index = (unsigned long) addr >> 3;
if ((addr & 7) || (index > PT_FPSCR))
#endif
break;
CHECK_FULL_REGS(child->thread.regs);
if (index < PT_FPR0) {
tmp = ptrace_get_reg(child, (int) index);
} else {
flush_fp_to_thread(child);
tmp = ((unsigned long *)child->thread.fpr)[index - PT_FPR0];
}
ret = put_user(tmp,(unsigned long __user *) data);
break;
}
/* If I and D space are separate, this will have to be fixed. */
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
ret = generic_ptrace_pokedata(child, addr, data);
break;
/* write the word at location addr in the USER area */
case PTRACE_POKEUSR: {
unsigned long index;
ret = -EIO;
/* convert to index and check */
#ifdef CONFIG_PPC32
index = (unsigned long) addr >> 2;
if ((addr & 3) || (index > PT_FPSCR)
|| (child->thread.regs == NULL))
#else
index = (unsigned long) addr >> 3;
if ((addr & 7) || (index > PT_FPSCR))
#endif
break;
CHECK_FULL_REGS(child->thread.regs);
if (index < PT_FPR0) {
ret = ptrace_put_reg(child, index, data);
} else {
flush_fp_to_thread(child);
((unsigned long *)child->thread.fpr)[index - PT_FPR0] = data;
ret = 0;
}
break;
}
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT: { /* restart after signal. */
ret = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSCALL)
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->exit_code = data;
/* make sure the single step bit is not set. */
clear_single_step(child);
wake_up_process(child);
ret = 0;
break;
}
/*
* make the child exit. Best I can do is send it a sigkill.
* perhaps it should be put in the status that it wants to
* exit.
*/
case PTRACE_KILL: {
ret = 0;
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
break;
child->exit_code = SIGKILL;
/* make sure the single step bit is not set. */
clear_single_step(child);
wake_up_process(child);
break;
}
case PTRACE_SINGLESTEP: { /* set the trap flag. */
ret = -EIO;
if (!valid_signal(data))
break;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
set_single_step(child);
child->exit_code = data;
/* give it a chance to run. */
wake_up_process(child);
ret = 0;
break;
}
case PTRACE_GET_DEBUGREG: {
ret = -EINVAL;
/* We only support one DABR and no IABRS at the moment */
if (addr > 0)
break;
ret = put_user(child->thread.dabr,
(unsigned long __user *)data);
break;
}
case PTRACE_SET_DEBUGREG:
ret = ptrace_set_debugreg(child, addr, data);
break;
#ifdef CONFIG_PPC64
case PTRACE_GETREGS64:
#endif
case PTRACE_GETREGS: { /* Get all pt_regs from the child. */
int ui;
if (!access_ok(VERIFY_WRITE, (void __user *)data,
sizeof(struct pt_regs))) {
ret = -EIO;
break;
}
CHECK_FULL_REGS(child->thread.regs);
ret = 0;
for (ui = 0; ui < PT_REGS_COUNT; ui ++) {
ret |= __put_user(ptrace_get_reg(child, ui),
(unsigned long __user *) data);
data += sizeof(long);
}
break;
}
#ifdef CONFIG_PPC64
case PTRACE_SETREGS64:
#endif
case PTRACE_SETREGS: { /* Set all gp regs in the child. */
unsigned long tmp;
int ui;
if (!access_ok(VERIFY_READ, (void __user *)data,
sizeof(struct pt_regs))) {
ret = -EIO;
break;
}
CHECK_FULL_REGS(child->thread.regs);
ret = 0;
for (ui = 0; ui < PT_REGS_COUNT; ui ++) {
ret = __get_user(tmp, (unsigned long __user *) data);
if (ret)
break;
ptrace_put_reg(child, ui, tmp);
data += sizeof(long);
}
break;
}
case PTRACE_GETFPREGS: { /* Get the child FPU state (FPR0...31 + FPSCR) */
flush_fp_to_thread(child);
ret = get_fpregs((void __user *)data, child, 1);
break;
}
case PTRACE_SETFPREGS: { /* Set the child FPU state (FPR0...31 + FPSCR) */
flush_fp_to_thread(child);
ret = set_fpregs((void __user *)data, child, 1);
break;
}
#ifdef CONFIG_ALTIVEC
case PTRACE_GETVRREGS:
/* Get the child altivec register state. */
flush_altivec_to_thread(child);
ret = get_vrregs((unsigned long __user *)data, child);
break;
case PTRACE_SETVRREGS:
/* Set the child altivec register state. */
flush_altivec_to_thread(child);
ret = set_vrregs(child, (unsigned long __user *)data);
break;
#endif
#ifdef CONFIG_SPE
case PTRACE_GETEVRREGS:
/* Get the child spe register state. */
flush_spe_to_thread(child);
ret = get_evrregs((unsigned long __user *)data, child);
break;
case PTRACE_SETEVRREGS:
/* Set the child spe register state. */
/* this is to clear the MSR_SPE bit to force a reload
* of register state from memory */
flush_spe_to_thread(child);
ret = set_evrregs(child, (unsigned long __user *)data);
break;
#endif
/* Old reverse args ptrace callss */
case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */
case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */
case PPC_PTRACE_GETFPREGS: /* Get FPRs 0 - 31. */
case PPC_PTRACE_SETFPREGS: /* Get FPRs 0 - 31. */
ret = arch_ptrace_old(child, request, addr, data);
break;
default:
ret = ptrace_request(child, request, addr, data);
break;
}
return ret;
}
/*
* arch_ptrace()
* architecture specific ptrace routine.
*/
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
int ret;
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA:
ret = generic_ptrace_peekdata(child, addr, data);
break;
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
unsigned long tmp;
ret = -EIO;
if (((unsigned long) addr > PT_INTERP_FDPIC_LOADMAP)
|| (addr & 3))
break;
tmp = 0; /* Default return condition */
ret = -EIO;
if (addr < sizeof(struct pt_regs)) {
tmp = ptrace_get_reg(child, addr);
} else if (addr == PT_TEXT_ADDR) {
tmp = child->mm->start_code;
} else if (addr == PT_TEXT_END_ADDR) {
tmp = child->mm->end_code;
} else if (addr == PT_DATA_ADDR) {
tmp = child->mm->start_data;
} else if (addr == PT_EXEC_FDPIC_LOADMAP) {
#ifdef CONFIG_BINFMT_ELF_FDPIC
tmp = child->mm->context.exec_fdpic_loadmap;
#endif
} else if (addr == PT_INTERP_FDPIC_LOADMAP) {
#ifdef CONFIG_BINFMT_ELF_FDPIC
tmp = child->mm->context.interp_fdpic_loadmap;
#endif
} else {
break;
}
ret = put_user(tmp, (unsigned long *)data);
break;
}
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
ret = generic_ptrace_pokedata(child, addr, data);
/*
* If we just changed some code so we need to
* correct the caches
*/
if (request == PTRACE_POKETEXT && ret == 0) {
flush_icache_range(addr, addr + 4);
}
break;
case PTRACE_POKEUSR: /* write the word at location addr
* in the USER area */
ret = -EIO;
if (((unsigned long) addr > PT_DATA_ADDR) || (addr & 3))
break;
if (addr < sizeof(struct pt_regs)) {
ret = ptrace_put_reg(child, addr, data);
}
break;
case PTRACE_SYSCALL: /* continue and stop at next (return from)
* syscall */
case PTRACE_CONT: { /* restart after signal. */
ret = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSCALL)
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->exit_code = data;
/* make sure the single step bit is not set. */
ptrace_disable_single_step(child);
wake_up_process(child);
ret = 0;
break;
}
/*
* make the child exit. Best I can do is send it a sigkill.
* perhaps it should be put in the status that it wants to exit.
*/
case PTRACE_KILL: {
ret = 0;
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
break;
child->exit_code = SIGKILL;
/* make sure the single step bit is not set. */
ptrace_disable_single_step(child);
wake_up_process(child);
break;
}
case PTRACE_DETACH: /* detach a process that was attached. */
ret = ptrace_detach(child, data);
break;
case PTRACE_GETREGS: /* Get all gp regs from the child. */
ptrace_getregs(child, (unsigned long *)data);
ret = 0;
break;
case PTRACE_SETREGS: { /* Set all gp regs in the child. */
int i;
unsigned long tmp;
int count = sizeof(struct pt_regs) / sizeof(unsigned long);
for (i = 0; i < count; i++) {
if (get_user(tmp, (unsigned long *) data)) {
ret = -EFAULT;
break;
}
ptrace_put_reg(child, sizeof(unsigned long) * i, tmp);
data += sizeof(long);
}
ret = 0;
break;
}
default:
return ptrace_request(child, request, addr, data);
break;
}
return ret;
}
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
*
* It copies the registers, and all the appropriate
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
static struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr,
int pid)
{
int retval;
struct task_struct *p = NULL;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
*/
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
/*
* Shared signal handlers imply shared VM. By way of the above,
* thread groups also imply shared VM. Blocking this case allows
* for various simplifications in other code.
*/
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
rt_mutex_init_task(p);
#ifdef CONFIG_TRACE_IRQFLAGS
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
retval = -EAGAIN;
if (atomic_read(&p->user->processes) >=
p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->user != &root_user)
goto bad_fork_free;
}
atomic_inc(&p->user->__count);
atomic_inc(&p->user->processes);
get_group_info(p->group_info);
/*
* If multiple threads are within copy_process(), then this check
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
if (p->binfmt && !try_module_get(p->binfmt->module))
goto bad_fork_cleanup_put_domain;
p->did_exec = 0;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
copy_flags(clone_flags, p);
p->pid = pid;
retval = -EFAULT;
if (clone_flags & CLONE_PARENT_SETTID)
if (put_user(p->pid, parent_tidptr))
goto bad_fork_cleanup_delays_binfmt;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
clear_tsk_thread_flag(p, TIF_SIGPENDING);
init_sigpending(&p->pending);
p->utime = cputime_zero;
p->stime = cputime_zero;
#ifdef CONFIG_TASK_XACCT
p->rchar = 0; /* I/O counter: bytes read */
p->wchar = 0; /* I/O counter: bytes written */
p->syscr = 0; /* I/O counter: read syscalls */
p->syscw = 0; /* I/O counter: write syscalls */
#endif
task_io_accounting_init(p);
acct_clear_integrals(p);
p->it_virt_expires = cputime_zero;
p->it_prof_expires = cputime_zero;
p->it_sched_expires = 0;
INIT_LIST_HEAD(&p->cpu_timers[0]);
INIT_LIST_HEAD(&p->cpu_timers[1]);
INIT_LIST_HEAD(&p->cpu_timers[2]);
p->lock_depth = -1; /* -1 = no lock */
do_posix_clock_monotonic_gettime(&p->start_time);
p->security = NULL;
p->io_context = NULL;
p->io_wait = NULL;
p->audit_context = NULL;
cpuset_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_copy(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup_cpuset;
}
mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
p->hardirqs_enabled = 1;
#else
p->hardirqs_enabled = 0;
#endif
p->hardirq_enable_ip = 0;
p->hardirq_enable_event = 0;
p->hardirq_disable_ip = _THIS_IP_;
p->hardirq_disable_event = 0;
p->softirqs_enabled = 1;
p->softirq_enable_ip = _THIS_IP_;
p->softirq_enable_event = 0;
p->softirq_disable_ip = 0;
p->softirq_disable_event = 0;
p->hardirq_context = 0;
p->softirq_context = 0;
#endif
#ifdef CONFIG_LOCKDEP
p->lockdep_depth = 0; /* no locks held yet */
p->curr_chain_key = 0;
p->lockdep_recursion = 0;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
if ((retval = security_task_alloc(p)))
goto bad_fork_cleanup_policy;
if ((retval = audit_alloc(p)))
goto bad_fork_cleanup_security;
/* copy all the process information */
if ((retval = copy_semundo(clone_flags, p)))
goto bad_fork_cleanup_audit;
if ((retval = copy_files(clone_flags, p)))
goto bad_fork_cleanup_semundo;
if ((retval = copy_fs(clone_flags, p)))
goto bad_fork_cleanup_files;
if ((retval = copy_sighand(clone_flags, p)))
goto bad_fork_cleanup_fs;
if ((retval = copy_signal(clone_flags, p)))
goto bad_fork_cleanup_sighand;
if ((retval = copy_mm(clone_flags, p)))
goto bad_fork_cleanup_signal;
if ((retval = copy_keys(clone_flags, p)))
goto bad_fork_cleanup_mm;
if ((retval = copy_namespaces(clone_flags, p)))
goto bad_fork_cleanup_keys;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_namespaces;
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
/*
* Clear TID on mm_release()?
*/
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
p->robust_list = NULL;
#ifdef CONFIG_COMPAT
p->compat_robust_list = NULL;
#endif
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
/*
* sigaltstack should be cleared when sharing the same VM
*/
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
p->sas_ss_sp = p->sas_ss_size = 0;
/*
* Syscall tracing should be turned off in the child regardless
* of CLONE_PTRACE.
*/
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
p->parent_exec_id = p->self_exec_id;
/* ok, now we should be set up.. */
p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
p->exit_state = 0;
/*
* Ok, make it visible to the rest of the system.
* We dont wake it up yet.
*/
p->group_leader = p;
INIT_LIST_HEAD(&p->thread_group);
INIT_LIST_HEAD(&p->ptrace_children);
INIT_LIST_HEAD(&p->ptrace_list);
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/* for sys_ioprio_set(IOPRIO_WHO_PGRP) */
p->ioprio = current->ioprio;
/*
* The task hasn't been attached yet, so its cpus_allowed mask will
* not be changed, nor will its assigned CPU.
*
* The cpus_allowed mask of the parent may have changed after it was
* copied first time - so re-copy it here, then check the child's CPU
* to ensure it is on a valid CPU (and if not, just force it back to
* parent's CPU). This avoids alot of nasty races.
*/
p->cpus_allowed = current->cpus_allowed;
if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
!cpu_online(task_cpu(p))))
set_task_cpu(p, smp_processor_id());
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
p->real_parent = current->real_parent;
else
p->real_parent = current;
p->parent = p->real_parent;
spin_lock(¤t->sighand->siglock);
/*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
* fork. Restart if a signal comes in before we add the new process to
* it's process group.
* A fatal signal pending means that current will exit, so the new
* thread can't slip out of an OOM kill (or normal SIGKILL).
*/
recalc_sigpending();
if (signal_pending(current)) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_cleanup_namespaces;
}
if (clone_flags & CLONE_THREAD) {
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
if (!cputime_eq(current->signal->it_virt_expires,
cputime_zero) ||
!cputime_eq(current->signal->it_prof_expires,
cputime_zero) ||
current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
!list_empty(¤t->signal->cpu_timers[0]) ||
!list_empty(¤t->signal->cpu_timers[1]) ||
!list_empty(¤t->signal->cpu_timers[2])) {
/*
* Have child wake up on its first tick to check
* for process CPU timers.
*/
p->it_prof_expires = jiffies_to_cputime(1);
}
}
if (likely(p->pid)) {
add_parent(p);
if (unlikely(p->ptrace & PT_PTRACED))
__ptrace_link(p, current->parent);
if (thread_group_leader(p)) {
p->signal->tty = current->signal->tty;
p->signal->pgrp = process_group(current);
set_signal_session(p->signal, process_session(current));
attach_pid(p, PIDTYPE_PGID, process_group(p));
attach_pid(p, PIDTYPE_SID, process_session(p));
list_add_tail_rcu(&p->tasks, &init_task.tasks);
__get_cpu_var(process_counts)++;
}
attach_pid(p, PIDTYPE_PID, p->pid);
nr_threads++;
}
total_forks++;
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
return p;
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_keys:
exit_keys(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
cleanup_signal(p);
bad_fork_cleanup_sighand:
__cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_security:
security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_free(p->mempolicy);
bad_fork_cleanup_cpuset:
#endif
cpuset_exit(p);
bad_fork_cleanup_delays_binfmt:
delayacct_tsk_free(p);
if (p->binfmt)
module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
put_group_info(p->group_info);
atomic_dec(&p->user->processes);
free_uid(p->user);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
/*
* Our handling of the processor debug registers is non-trivial.
* We do not clear them on entry and exit from the kernel. Therefore
* it is possible to get a watchpoint trap here from inside the kernel.
* However, the code in ./ptrace.c has ensured that the user can
* only set watchpoints on userspace addresses. Therefore the in-kernel
* watchpoint trap can only occur in code which is reading/writing
* from user space. Such code must not hold kernel locks (since it
* can equally take a page fault), therefore it is safe to call
* force_sig_info even though that claims and releases locks.
*
* Code in ./signal.c ensures that the debug control register
* is restored before we deliver any signal, and therefore that
* user code runs with the correct debug control register even though
* we clear it here.
*
* Being careful here means that we don't have to be as careful in a
* lot of more complicated places (task switching can be a bit lazy
* about restoring all the debug state, and ptrace doesn't have to
* find every occurrence of the TF bit that could be saved away even
* by user code)
*
* May run on IST stack.
*/
dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk = current;
unsigned long condition;
int si_code;
get_debugreg(condition, 6);
/*
* The processor cleared BTF, so don't mark that we need it set.
*/
clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR);
tsk->thread.debugctlmsr = 0;
if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
SIGTRAP) == NOTIFY_STOP)
return;
/* It's safe to allow irq's after DR6 has been saved */
preempt_conditional_sti(regs);
/* Mask out spurious debug traps due to lazy DR7 setting */
if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
if (!tsk->thread.debugreg7)
goto clear_dr7;
}
#ifdef CONFIG_X86_32
if (v8086_mode(regs))
goto debug_vm86;
#endif
/* Save debug status register where ptrace can see it */
tsk->thread.debugreg6 = condition;
/*
* Single-stepping through TF: make sure we ignore any events in
* kernel space (but re-enable TF when returning to user mode).
*/
if (condition & DR_STEP) {
if (!user_mode_novm(regs))
goto clear_TF_reenable;
}
si_code = get_si_code(condition);
/* Ok, finally something we can handle */
send_sigtrap(tsk, regs, error_code, si_code);
/*
* Disable additional traps. They'll be re-enabled when
* the signal is delivered.
*/
clear_dr7:
set_debugreg(0, 7);
preempt_conditional_cli(regs);
return;
#ifdef CONFIG_X86_32
debug_vm86:
/* reenable preemption: handle_vm86_trap() might sleep */
dec_preempt_count();
handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
conditional_cli(regs);
return;
#endif
clear_TF_reenable:
set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
regs->flags &= ~X86_EFLAGS_TF;
preempt_conditional_cli(regs);
return;
}
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*
* error_code:
* 04 Protection -> Write-Protection (suprression)
* 10 Segment translation -> Not present (nullification)
* 11 Page translation -> Not present (nullification)
* 3b Region third trans. -> Not present (nullification)
*/
extern inline void
do_exception(struct pt_regs *regs, unsigned long error_code, int is_protection)
{
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct * vma;
unsigned long address;
int user_address;
const struct exception_table_entry *fixup;
int si_code = SEGV_MAPERR;
tsk = current;
mm = tsk->mm;
/*
* Check for low-address protection. This needs to be treated
* as a special case because the translation exception code
* field is not guaranteed to contain valid data in this case.
*/
if (is_protection && !(S390_lowcore.trans_exc_code & 4)) {
/* Low-address protection hit in kernel mode means
NULL pointer write access in kernel mode. */
if (!(regs->psw.mask & PSW_MASK_PSTATE)) {
address = 0;
user_address = 0;
goto no_context;
}
/* Low-address protection hit in user mode 'cannot happen'. */
die ("Low-address protection", regs, error_code);
do_exit(SIGKILL);
}
/*
* get the failing address
* more specific the segment and page table portion of
* the address
*/
address = S390_lowcore.trans_exc_code & __FAIL_ADDR_MASK;
user_address = check_user_space(regs, error_code);
/*
* Verify that the fault happened in user space, that
* we are not in an interrupt and that there is a
* user context.
*/
if (user_address == 0 || in_atomic() || !mm)
goto no_context;
/*
* When we get here, the fault happened in the current
* task's user address space, so we can switch on the
* interrupts again and then search the VMAs
*/
local_irq_enable();
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
if (vma->vm_start <= address)
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (expand_stack(vma, address))
goto bad_area;
/*
* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
good_area:
si_code = SEGV_ACCERR;
if (!is_protection) {
/* page not present, check vm flags */
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
goto bad_area;
} else {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
}
survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
switch (handle_mm_fault(mm, vma, address, is_protection)) {
case VM_FAULT_MINOR:
tsk->min_flt++;
break;
case VM_FAULT_MAJOR:
tsk->maj_flt++;
break;
case VM_FAULT_SIGBUS:
goto do_sigbus;
case VM_FAULT_OOM:
goto out_of_memory;
default:
BUG();
}
up_read(&mm->mmap_sem);
/*
* The instruction that caused the program check will
* be repeated. Don't signal single step via SIGTRAP.
*/
clear_tsk_thread_flag(current, TIF_SINGLE_STEP);
return;
/*
* Something tried to access memory that isn't in our memory map..
* Fix it, but check if it's kernel or user first..
*/
bad_area:
up_read(&mm->mmap_sem);
/* User mode accesses just cause a SIGSEGV */
if (regs->psw.mask & PSW_MASK_PSTATE) {
tsk->thread.prot_addr = address;
tsk->thread.trap_no = error_code;
do_sigsegv(regs, error_code, si_code, address);
return;
}
no_context:
/* Are we prepared to handle this kernel fault? */
fixup = search_exception_tables(regs->psw.addr & __FIXUP_MASK);
if (fixup) {
regs->psw.addr = fixup->fixup | PSW_ADDR_AMODE;
return;
}
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
if (user_address == 0)
printk(KERN_ALERT "Unable to handle kernel pointer dereference"
" at virtual kernel address %p\n", (void *)address);
else
printk(KERN_ALERT "Unable to handle kernel paging request"
" at virtual user address %p\n", (void *)address);
die("Oops", regs, error_code);
do_exit(SIGKILL);
/*
* We ran out of memory, or some other thing happened to us that made
* us unable to handle the page fault gracefully.
*/
out_of_memory:
up_read(&mm->mmap_sem);
if (tsk->pid == 1) {
yield();
goto survive;
}
printk("VM: killing process %s\n", tsk->comm);
if (regs->psw.mask & PSW_MASK_PSTATE)
do_exit(SIGKILL);
goto no_context;
do_sigbus:
up_read(&mm->mmap_sem);
/*
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
tsk->thread.prot_addr = address;
tsk->thread.trap_no = error_code;
force_sig(SIGBUS, tsk);
/* Kernel mode? Handle exceptions or die */
if (!(regs->psw.mask & PSW_MASK_PSTATE))
goto no_context;
}
static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
struct core_state *core_state, int exit_code)
{
struct task_struct *g, *p;
unsigned long flags;
int nr = -EAGAIN;
spin_lock_irq(&tsk->sighand->siglock);
if (!signal_group_exit(tsk->signal)) {
mm->core_state = core_state;
nr = zap_process(tsk, exit_code);
tsk->signal->group_exit_task = tsk;
/* ignore all signals except SIGKILL, see prepare_signal() */
tsk->signal->flags = SIGNAL_GROUP_COREDUMP;
clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
}
spin_unlock_irq(&tsk->sighand->siglock);
if (unlikely(nr < 0))
return nr;
tsk->flags |= PF_DUMPCORE;
if (atomic_read(&mm->mm_users) == nr + 1)
goto done;
/*
* We should find and kill all tasks which use this mm, and we should
* count them correctly into ->nr_threads. We don't take tasklist
* lock, but this is safe wrt:
*
* fork:
* None of sub-threads can fork after zap_process(leader). All
* processes which were created before this point should be
* visible to zap_threads() because copy_process() adds the new
* process to the tail of init_task.tasks list, and lock/unlock
* of ->siglock provides a memory barrier.
*
* do_exit:
* The caller holds mm->mmap_sem. This means that the task which
* uses this mm can't pass exit_mm(), so it can't exit or clear
* its ->mm.
*
* de_thread:
* It does list_replace_rcu(&leader->tasks, ¤t->tasks),
* we must see either old or new leader, this does not matter.
* However, it can change p->sighand, so lock_task_sighand(p)
* must be used. Since p->mm != NULL and we hold ->mmap_sem
* it can't fail.
*
* Note also that "g" can be the old leader with ->mm == NULL
* and already unhashed and thus removed from ->thread_group.
* This is OK, __unhash_process()->list_del_rcu() does not
* clear the ->next pointer, we will find the new leader via
* next_thread().
*/
rcu_read_lock();
for_each_process(g) {
if (g == tsk->group_leader)
continue;
if (g->flags & PF_KTHREAD)
continue;
p = g;
do {
if (p->mm) {
if (unlikely(p->mm == mm)) {
lock_task_sighand(p, &flags);
nr += zap_process(p, exit_code);
p->signal->flags = SIGNAL_GROUP_EXIT;
unlock_task_sighand(p, &flags);
}
break;
}
} while_each_thread(g, p);
}
rcu_read_unlock();
done:
atomic_set(&core_state->nr_threads, nr);
return nr;
}
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
*
* It copies the registers, and all the appropriate
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
static struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *child_tidptr,
struct pid *pid,
int trace)
{
int retval;
struct task_struct *p;
int cgroup_callbacks_done = 0;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
*/
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
/*
* Shared signal handlers imply shared VM. By way of the above,
* thread groups also imply shared VM. Blocking this case allows
* for various simplifications in other code.
*/
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
rt_mutex_init_task(p);
#ifdef CONFIG_PROVE_LOCKING
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
retval = -EAGAIN;
if (atomic_read(&p->real_cred->user->processes) >=
p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->real_cred->user != INIT_USER)
goto bad_fork_free;
}
retval = copy_creds(p, clone_flags);
if (retval < 0)
goto bad_fork_free;
/*
* If multiple threads are within copy_process(), then this check
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
retval = -EAGAIN;
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
if (p->binfmt && !try_module_get(p->binfmt->module))
goto bad_fork_cleanup_put_domain;
p->did_exec = 0;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
copy_flags(clone_flags, p);
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
#ifdef CONFIG_PREEMPT_RCU
p->rcu_read_lock_nesting = 0;
p->rcu_flipctr_idx = 0;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
clear_tsk_thread_flag(p, TIF_SIGPENDING);
init_sigpending(&p->pending);
p->utime = cputime_zero;
p->stime = cputime_zero;
p->gtime = cputime_zero;
p->utimescaled = cputime_zero;
p->stimescaled = cputime_zero;
p->prev_utime = cputime_zero;
p->prev_stime = cputime_zero;
p->default_timer_slack_ns = current->timer_slack_ns;
#ifdef CONFIG_DETECT_SOFTLOCKUP
p->last_switch_count = 0;
p->last_switch_timestamp = 0;
#endif
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
posix_cpu_timers_init(p);
p->lock_depth = -1; /* -1 = no lock */
do_posix_clock_monotonic_gettime(&p->start_time);
p->real_start_time = p->start_time;
monotonic_to_bootbased(&p->real_start_time);
p->io_context = NULL;
p->audit_context = NULL;
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup_cgroup;
}
mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
p->hardirqs_enabled = 1;
#else
p->hardirqs_enabled = 0;
#endif
p->hardirq_enable_ip = 0;
p->hardirq_enable_event = 0;
p->hardirq_disable_ip = _THIS_IP_;
p->hardirq_disable_event = 0;
p->softirqs_enabled = 1;
p->softirq_enable_ip = _THIS_IP_;
p->softirq_enable_event = 0;
p->softirq_disable_ip = 0;
p->softirq_disable_event = 0;
p->hardirq_context = 0;
p->softirq_context = 0;
#endif
#ifdef CONFIG_LOCKDEP
p->lockdep_depth = 0; /* no locks held yet */
p->curr_chain_key = 0;
p->lockdep_recursion = 0;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
if (unlikely(current->ptrace))
ptrace_fork(p, clone_flags);
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
if ((retval = audit_alloc(p)))
goto bad_fork_cleanup_policy;
/* copy all the process information */
if ((retval = copy_semundo(clone_flags, p)))
goto bad_fork_cleanup_audit;
if ((retval = copy_files(clone_flags, p)))
goto bad_fork_cleanup_semundo;
if ((retval = copy_fs(clone_flags, p)))
goto bad_fork_cleanup_files;
if ((retval = copy_sighand(clone_flags, p)))
goto bad_fork_cleanup_fs;
if ((retval = copy_signal(clone_flags, p)))
goto bad_fork_cleanup_sighand;
if ((retval = copy_mm(clone_flags, p)))
goto bad_fork_cleanup_signal;
if ((retval = copy_namespaces(clone_flags, p)))
goto bad_fork_cleanup_mm;
if ((retval = copy_io(clone_flags, p)))
goto bad_fork_cleanup_namespaces;
retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(p->nsproxy->pid_ns);
if (!pid)
goto bad_fork_cleanup_io;
if (clone_flags & CLONE_NEWPID) {
retval = pid_ns_prepare_proc(p->nsproxy->pid_ns);
if (retval < 0)
goto bad_fork_free_pid;
}
}
ftrace_graph_init_task(p);
p->pid = pid_nr(pid);
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
if (current->nsproxy != p->nsproxy) {
retval = ns_cgroup_clone(p, pid);
if (retval)
goto bad_fork_free_graph;
}
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
/*
* Clear TID on mm_release()?
*/
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
#ifdef CONFIG_FUTEX
p->robust_list = NULL;
#ifdef CONFIG_COMPAT
p->compat_robust_list = NULL;
#endif
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
#endif
/*
* sigaltstack should be cleared when sharing the same VM
*/
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
p->sas_ss_sp = p->sas_ss_size = 0;
/*
* Syscall tracing should be turned off in the child regardless
* of CLONE_PTRACE.
*/
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
clear_all_latency_tracing(p);
/* ok, now we should be set up.. */
p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
p->exit_state = 0;
/*
* Ok, make it visible to the rest of the system.
* We dont wake it up yet.
*/
p->group_leader = p;
INIT_LIST_HEAD(&p->thread_group);
/* Now that the task is set up, run cgroup callbacks if
* necessary. We need to run them before the task is visible
* on the tasklist. */
cgroup_fork_callbacks(p);
cgroup_callbacks_done = 1;
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/*
* The task hasn't been attached yet, so its cpus_allowed mask will
* not be changed, nor will its assigned CPU.
*
* The cpus_allowed mask of the parent may have changed after it was
* copied first time - so re-copy it here, then check the child's CPU
* to ensure it is on a valid CPU (and if not, just force it back to
* parent's CPU). This avoids alot of nasty races.
*/
p->cpus_allowed = current->cpus_allowed;
p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed;
if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
!cpu_online(task_cpu(p))))
set_task_cpu(p, smp_processor_id());
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
p->real_parent = current->real_parent;
p->parent_exec_id = current->parent_exec_id;
} else {
p->real_parent = current;
p->parent_exec_id = current->self_exec_id;
}
spin_lock(¤t->sighand->siglock);
/*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
* fork. Restart if a signal comes in before we add the new process to
* it's process group.
* A fatal signal pending means that current will exit, so the new
* thread can't slip out of an OOM kill (or normal SIGKILL).
*/
recalc_sigpending();
if (signal_pending(current)) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_free_graph;
}
if (clone_flags & CLONE_THREAD) {
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
}
if (likely(p->pid)) {
list_add_tail(&p->sibling, &p->real_parent->children);
tracehook_finish_clone(p, clone_flags, trace);
if (thread_group_leader(p)) {
if (clone_flags & CLONE_NEWPID)
p->nsproxy->pid_ns->child_reaper = p;
p->signal->leader_pid = pid;
tty_kref_put(p->signal->tty);
p->signal->tty = tty_kref_get(current->signal->tty);
attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
attach_pid(p, PIDTYPE_SID, task_session(current));
list_add_tail_rcu(&p->tasks, &init_task.tasks);
__get_cpu_var(process_counts)++;
}
attach_pid(p, PIDTYPE_PID, pid);
nr_threads++;
}
#ifdef CONFIG_LTT_LITE
ltt_lite_ev_process(LTT_LITE_EV_PROCESS_FORK, p);
#endif
total_forks++;
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
return p;
bad_fork_free_graph:
ftrace_graph_exit_task(p);
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_io:
put_io_context(p->io_context);
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
cleanup_signal(p);
bad_fork_cleanup_sighand:
__cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
if (p->binfmt)
module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
put_cred(p->real_cred);
put_cred(p->cred);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
/**
* __context_tracking_task_switch - context switch the syscall callbacks
* @prev: the task that is being switched out
* @next: the task that is being switched in
*
* The context tracking uses the syscall slow path to implement its user-kernel
* boundaries probes on syscalls. This way it doesn't impact the syscall fast
* path on CPUs that don't do context tracking.
*
* But we need to clear the flag on the previous task because it may later
* migrate to some CPU that doesn't do the context tracking. As such the TIF
* flag may not be desired there.
*/
void __context_tracking_task_switch(struct task_struct *prev,
struct task_struct *next)
{
clear_tsk_thread_flag(prev, TIF_NOHZ);
set_tsk_thread_flag(next, TIF_NOHZ);
}
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*
* interruption code (int_code):
* 04 Protection -> Write-Protection (suprression)
* 10 Segment translation -> Not present (nullification)
* 11 Page translation -> Not present (nullification)
* 3b Region third trans. -> Not present (nullification)
*/
static inline int do_exception(struct pt_regs *regs, int access)
{
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
unsigned long trans_exc_code;
unsigned long address;
unsigned int flags;
int fault;
if (notify_page_fault(regs))
return 0;
tsk = current;
mm = tsk->mm;
trans_exc_code = regs->int_parm_long;
/*
* Verify that the fault happened in user space, that
* we are not in an interrupt and that there is a
* user context.
*/
fault = VM_FAULT_BADCONTEXT;
if (unlikely(!user_space_fault(trans_exc_code) ||
!mm || pagefault_disabled()))
goto out;
address = trans_exc_code & __FAIL_ADDR_MASK;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
flags = FAULT_FLAG_ALLOW_RETRY;
if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
flags |= FAULT_FLAG_WRITE;
down_read(&mm->mmap_sem);
#ifdef CONFIG_PGSTE
if (test_tsk_thread_flag(current, TIF_SIE) && S390_lowcore.gmap) {
address = __gmap_fault(address,
(struct gmap *) S390_lowcore.gmap);
if (address == -EFAULT) {
fault = VM_FAULT_BADMAP;
goto out_up;
}
if (address == -ENOMEM) {
fault = VM_FAULT_OOM;
goto out_up;
}
}
#endif
retry:
fault = VM_FAULT_BADMAP;
vma = find_vma(mm, address);
if (!vma)
goto out_up;
if (unlikely(vma->vm_start > address)) {
if (!(vma->vm_flags & VM_GROWSDOWN))
goto out_up;
if (expand_stack(vma, address))
goto out_up;
}
/*
* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
fault = VM_FAULT_BADACCESS;
if (unlikely(!(vma->vm_flags & access)))
goto out_up;
if (is_vm_hugetlb_page(vma))
address &= HPAGE_MASK;
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
fault = handle_mm_fault(mm, vma, address, flags);
if (unlikely(fault & VM_FAULT_ERROR))
goto out_up;
/*
* Major/minor page fault accounting is only done on the
* initial attempt. If we go through a retry, it is extremely
* likely that the page will be found in page cache at that point.
*/
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR) {
tsk->maj_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
regs, address);
} else {
tsk->min_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
regs, address);
}
if (fault & VM_FAULT_RETRY) {
/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
* of starvation. */
flags &= ~FAULT_FLAG_ALLOW_RETRY;
down_read(&mm->mmap_sem);
goto retry;
}
}
/*
* The instruction that caused the program check will
* be repeated. Don't signal single step via SIGTRAP.
*/
clear_tsk_thread_flag(tsk, TIF_PER_TRAP);
fault = 0;
out_up:
up_read(&mm->mmap_sem);
out:
return fault;
}
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
*
* It copies the registers, and all the appropriate
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
static struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *child_tidptr,
struct pid *pid,
int trace)
{
int retval;
struct task_struct *p;
int cgroup_callbacks_done = 0;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
*/
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
/*
* Shared signal handlers imply shared VM. By way of the above,
* thread groups also imply shared VM. Blocking this case allows
* for various simplifications in other code.
*/
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
/*
* Siblings of global init remain as zombies on exit since they are
* not reaped by their parent (swapper). To solve this and to avoid
* multi-rooted process trees, prevent global and container-inits
* from creating siblings.
*/
if ((clone_flags & CLONE_PARENT) &&
current->signal->flags & SIGNAL_UNKILLABLE)
return ERR_PTR(-EINVAL);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
ftrace_graph_init_task(p);
rt_mutex_init_task(p);
#ifdef CONFIG_PROVE_LOCKING
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
retval = -EAGAIN;
if (atomic_read(&p->real_cred->user->processes) >=
task_rlimit(p, RLIMIT_NPROC)) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->real_cred->user != INIT_USER)
goto bad_fork_free;
}
retval = copy_creds(p, clone_flags);
if (retval < 0)
goto bad_fork_free;
/*
* If multiple threads are within copy_process(), then this check
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
retval = -EAGAIN;
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
p->did_exec = 0;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
copy_flags(clone_flags, p);
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
rcu_copy_process(p);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
init_sigpending(&p->pending);
p->utime = cputime_zero;
p->stime = cputime_zero;
p->gtime = cputime_zero;
p->utimescaled = cputime_zero;
p->stimescaled = cputime_zero;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
p->prev_utime = cputime_zero;
p->prev_stime = cputime_zero;
#endif
#if defined(SPLIT_RSS_COUNTING)
memset(&p->rss_stat, 0, sizeof(p->rss_stat));
#endif
p->default_timer_slack_ns = current->timer_slack_ns;
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
posix_cpu_timers_init(p);
do_posix_clock_monotonic_gettime(&p->start_time);
p->real_start_time = p->start_time;
monotonic_to_bootbased(&p->real_start_time);
p->io_context = NULL;
p->audit_context = NULL;
if (clone_flags & CLONE_THREAD)
threadgroup_fork_read_lock(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup_cgroup;
}
mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
p->hardirqs_enabled = 1;
#else
p->hardirqs_enabled = 0;
#endif
p->hardirq_enable_ip = 0;
p->hardirq_enable_event = 0;
p->hardirq_disable_ip = _THIS_IP_;
p->hardirq_disable_event = 0;
p->softirqs_enabled = 1;
p->softirq_enable_ip = _THIS_IP_;
p->softirq_enable_event = 0;
p->softirq_disable_ip = 0;
p->softirq_disable_event = 0;
p->hardirq_context = 0;
p->softirq_context = 0;
#endif
#ifdef CONFIG_LOCKDEP
p->lockdep_depth = 0; /* no locks held yet */
p->curr_chain_key = 0;
p->lockdep_recursion = 0;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
p->memcg_batch.do_batch = 0;
p->memcg_batch.memcg = NULL;
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p);
retval = perf_event_init_task(p);
if (retval)
goto bad_fork_cleanup_policy;
if ((retval = audit_alloc(p)))
goto bad_fork_cleanup_policy;
/* copy all the process information */
if ((retval = copy_semundo(clone_flags, p)))
goto bad_fork_cleanup_audit;
if ((retval = copy_files(clone_flags, p)))
goto bad_fork_cleanup_semundo;
if ((retval = copy_fs(clone_flags, p)))
goto bad_fork_cleanup_files;
if ((retval = copy_sighand(clone_flags, p)))
goto bad_fork_cleanup_fs;
if ((retval = copy_signal(clone_flags, p)))
goto bad_fork_cleanup_sighand;
if ((retval = copy_mm(clone_flags, p)))
goto bad_fork_cleanup_signal;
if ((retval = copy_namespaces(clone_flags, p)))
goto bad_fork_cleanup_mm;
if ((retval = copy_io(clone_flags, p)))
goto bad_fork_cleanup_namespaces;
retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(p->nsproxy->pid_ns);
if (!pid)
goto bad_fork_cleanup_io;
}
p->pid = pid_nr(pid);
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
p->tgid = current->tgid;
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
/*
* Clear TID on mm_release()?
*/
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
#ifdef CONFIG_FUTEX
p->robust_list = NULL;
#ifdef CONFIG_COMPAT
p->compat_robust_list = NULL;
#endif
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
#endif
/*
* sigaltstack should be cleared when sharing the same VM
*/
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
p->sas_ss_sp = p->sas_ss_size = 0;
/*
* Syscall tracing and stepping should be turned off in the
* child regardless of CLONE_PTRACE.
*/
user_disable_single_step(p);
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
clear_all_latency_tracing(p);
/* ok, now we should be set up.. */
p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
p->exit_state = 0;
/*
* Ok, make it visible to the rest of the system.
* We dont wake it up yet.
*/
p->group_leader = p;
INIT_LIST_HEAD(&p->thread_group);
/* Now that the task is set up, run cgroup callbacks if
* necessary. We need to run them before the task is visible
* on the tasklist. */
cgroup_fork_callbacks(p);
cgroup_callbacks_done = 1;
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
p->real_parent = current->real_parent;
p->parent_exec_id = current->parent_exec_id;
} else {
p->real_parent = current;
p->parent_exec_id = current->self_exec_id;
}
spin_lock(¤t->sighand->siglock);
/*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
* fork. Restart if a signal comes in before we add the new process to
* it's process group.
* A fatal signal pending means that current will exit, so the new
* thread can't slip out of an OOM kill (or normal SIGKILL).
*/
recalc_sigpending();
if (signal_pending(current)) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_free_pid;
}
if (clone_flags & CLONE_THREAD) {
current->signal->nr_threads++;
atomic_inc(¤t->signal->live);
atomic_inc(¤t->signal->sigcnt);
p->group_leader = current->group_leader;
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
}
if (likely(p->pid)) {
tracehook_finish_clone(p, clone_flags, trace);
if (thread_group_leader(p)) {
if (is_child_reaper(pid))
p->nsproxy->pid_ns->child_reaper = p;
p->signal->leader_pid = pid;
p->signal->tty = tty_kref_get(current->signal->tty);
attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
attach_pid(p, PIDTYPE_SID, task_session(current));
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
__this_cpu_inc(process_counts);
}
attach_pid(p, PIDTYPE_PID, pid);
nr_threads++;
}
total_forks++;
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
if (clone_flags & CLONE_THREAD)
threadgroup_fork_read_unlock(current);
perf_event_fork(p);
return p;
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_io:
if (p->io_context)
exit_io_context(p);
bad_fork_cleanup_namespaces:
if (unlikely(clone_flags & CLONE_NEWPID))
pid_ns_release_proc(p->nsproxy->pid_ns);
exit_task_namespaces(p);
bad_fork_cleanup_mm:
if (p->mm) {
task_lock(p);
if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
atomic_dec(&p->mm->oom_disable_count);
task_unlock(p);
mmput(p->mm);
}
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
free_signal_struct(p->signal);
bad_fork_cleanup_sighand:
__cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_policy:
perf_event_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
if (clone_flags & CLONE_THREAD)
threadgroup_fork_read_unlock(current);
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
exit_creds(p);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
/*
* Called by kernel/ptrace.c when detaching
*
* Make sure any single step bits, etc. are not set
*/
void ptrace_disable(struct task_struct *child)
{
clear_tsk_thread_flag(child, TIF_SINGLE_STEP);
clear_tsk_thread_flag(child, TIF_BREAKPOINT);
ocd_disable(child);
}
