int do_getitimer(int which, struct itimerval *value)
{
struct task_struct *tsk = current;
cputime_t cinterval, cval;
switch (which) {
case ITIMER_REAL:
spin_lock_irq(&tsk->sighand->siglock);
value->it_value = itimer_get_remtime(&tsk->signal->real_timer);
value->it_interval =
ktime_to_timeval(tsk->signal->it_real_incr);
spin_unlock_irq(&tsk->sighand->siglock);
break;
case ITIMER_VIRTUAL:
spin_lock_irq(&tsk->sighand->siglock);
cval = tsk->signal->it_virt_expires;
cinterval = tsk->signal->it_virt_incr;
if (!cputime_eq(cval, cputime_zero)) {
struct task_cputime cputime;
cputime_t utime;
thread_group_cputimer(tsk, &cputime);
utime = cputime.utime;
if (cputime_le(cval, utime)) { /* about to fire */
cval = jiffies_to_cputime(1);
} else {
cval = cputime_sub(cval, utime);
}
}
spin_unlock_irq(&tsk->sighand->siglock);
cputime_to_timeval(cval, &value->it_value);
cputime_to_timeval(cinterval, &value->it_interval);
break;
case ITIMER_PROF:
spin_lock_irq(&tsk->sighand->siglock);
cval = tsk->signal->it_prof_expires;
cinterval = tsk->signal->it_prof_incr;
if (!cputime_eq(cval, cputime_zero)) {
struct task_cputime times;
cputime_t ptime;
thread_group_cputimer(tsk, ×);
ptime = cputime_add(times.utime, times.stime);
if (cputime_le(cval, ptime)) { /* about to fire */
cval = jiffies_to_cputime(1);
} else {
cval = cputime_sub(cval, ptime);
}
}
spin_unlock_irq(&tsk->sighand->siglock);
cputime_to_timeval(cval, &value->it_value);
cputime_to_timeval(cinterval, &value->it_interval);
break;
default:
return(-EINVAL);
}
return 0;
}
static inline void check_for_tasks(int cpu)
{
struct task_struct *p;
write_lock_irq(&tasklist_lock);
for_each_process(p) {
if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&
(!cputime_eq(p->utime, cputime_zero) ||
!cputime_eq(p->stime, cputime_zero)))
printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d "
"(state = %ld, flags = %x)\n",
p->comm, task_pid_nr(p), cpu,
p->state, p->flags);
}
write_unlock_irq(&tasklist_lock);
}
static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
struct itimerval *const value)
{
cputime_t cval, cinterval;
struct cpu_itimer *it = &tsk->signal->it[clock_id];
spin_lock_irq(&tsk->sighand->siglock);
cval = it->expires;
cinterval = it->incr;
if (!cputime_eq(cval, cputime_zero)) {
struct task_cputime cputime;
cputime_t t;
thread_group_cputimer(tsk, &cputime);
if (clock_id == CPUCLOCK_PROF)
t = cputime_add(cputime.utime, cputime.stime);
else
/* CPUCLOCK_VIRT */
t = cputime.utime;
if (cputime_le(cval, t))
/* about to fire */
cval = cputime_one_jiffy;
else
cval = cputime_sub(cval, t);
}
spin_unlock_irq(&tsk->sighand->siglock);
cputime_to_timeval(cval, &value->it_value);
cputime_to_timeval(cinterval, &value->it_interval);
}
static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
const struct itimerval *const value,
struct itimerval *const ovalue)
{
cputime_t cval, nval, cinterval, ninterval;
s64 ns_ninterval, ns_nval;
u32 error, incr_error;
struct cpu_itimer *it = &tsk->signal->it[clock_id];
nval = timeval_to_cputime(&value->it_value);
ns_nval = timeval_to_ns(&value->it_value);
ninterval = timeval_to_cputime(&value->it_interval);
ns_ninterval = timeval_to_ns(&value->it_interval);
error = cputime_sub_ns(nval, ns_nval);
incr_error = cputime_sub_ns(ninterval, ns_ninterval);
spin_lock_irq(&tsk->sighand->siglock);
cval = it->expires;
cinterval = it->incr;
if (!cputime_eq(cval, cputime_zero) ||
!cputime_eq(nval, cputime_zero)) {
if (cputime_gt(nval, cputime_zero))
nval = cputime_add(nval, cputime_one_jiffy);
set_process_cpu_timer(tsk, clock_id, &nval, &cval);
}
it->expires = nval;
it->incr = ninterval;
it->error = error;
it->incr_error = incr_error;
trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
spin_unlock_irq(&tsk->sighand->siglock);
if (ovalue) {
cputime_to_timeval(cval, &ovalue->it_value);
cputime_to_timeval(cinterval, &ovalue->it_interval);
}
}
/*
* Called after updating RLIMIT_CPU to set timer expiration if necessary.
*/
void update_rlimit_cpu(unsigned long rlim_new)
{
cputime_t cputime;
cputime = secs_to_cputime(rlim_new);
if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
cputime_gt(current->signal->it_prof_expires, cputime)) {
spin_lock_irq(¤t->sighand->siglock);
set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
spin_unlock_irq(¤t->sighand->siglock);
}
}
/*
* Called after updating RLIMIT_CPU to set timer expiration if necessary.
*/
void update_rlimit_cpu(unsigned long rlim_new)
{
cputime_t cputime = secs_to_cputime(rlim_new);
struct signal_struct *const sig = current->signal;
if (cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) ||
cputime_lt(sig->it[CPUCLOCK_PROF].expires, cputime)) {
spin_lock_irq(¤t->sighand->siglock);
set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
spin_unlock_irq(¤t->sighand->siglock);
}
}
asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
{
struct rlimit new_rlim, *old_rlim;
int retval;
if (resource >= RLIM_NLIMITS)
return -EINVAL;
if(copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
return -EFAULT;
if (new_rlim.rlim_cur > new_rlim.rlim_max)
return -EINVAL;
old_rlim = current->signal->rlim + resource;
if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
!capable(CAP_SYS_RESOURCE))
return -EPERM;
if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > NR_OPEN)
return -EPERM;
retval = security_task_setrlimit(resource, &new_rlim);
if (retval)
return retval;
task_lock(current->group_leader);
*old_rlim = new_rlim;
task_unlock(current->group_leader);
if (resource == RLIMIT_CPU && new_rlim.rlim_cur != RLIM_INFINITY &&
(cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
new_rlim.rlim_cur <= cputime_to_secs(
current->signal->it_prof_expires))) {
cputime_t cputime = secs_to_cputime(new_rlim.rlim_cur);
read_lock(&tasklist_lock);
spin_lock_irq(¤t->sighand->siglock);
set_process_cpu_timer(current, CPUCLOCK_PROF,
&cputime, NULL);
spin_unlock_irq(¤t->sighand->siglock);
read_unlock(&tasklist_lock);
}
return 0;
}
/*
* 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->user->processes) >=
p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->user != current->nsproxy->user_ns->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);
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;
#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);
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->real_start_time = p->start_time;
monotonic_to_bootbased(&p->real_start_time);
#ifdef CONFIG_SECURITY
p->security = NULL;
#endif
p->cap_bset = current->cap_bset;
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
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
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;
if ((retval = copy_io(clone_flags, p)))
goto bad_fork_cleanup_namespaces;
retval = copy_thread(0, 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(task_active_pid_ns(p));
if (!pid)
goto bad_fork_cleanup_io;
if (clone_flags & CLONE_NEWPID) {
retval = pid_ns_prepare_proc(task_active_pid_ns(p));
if (retval < 0)
goto bad_fork_free_pid;
}
}
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_pid;
}
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;
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_pid;
}
if (clone_flags & CLONE_THREAD) {
atomic_inc(¤t->signal->count);
atomic_inc(¤t->signal->live);
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)) {
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;
p->signal->tty = current->signal->tty;
set_task_pgrp(p, task_pgrp_nr(current));
set_task_session(p, task_session_nr(current));
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++;
}
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_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_keys:
exit_keys(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
__cleanup_signal(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_security:
security_task_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:
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);
}
/*
* 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);
#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;
#ifdef CONFIG_LTT_USERSPACE_GENERIC
if (clone_flags & CLONE_THREAD)
memset(p->ltt_facilities, 0, sizeof(p->ltt_facilities));
else {
int i;
for(i=0; i<LTT_FAC_PER_PROCESS; i++) {
p->ltt_facilities[i] = current->ltt_facilities[i];
if(p->ltt_facilities[i] != 0)
ltt_facility_ref(p->ltt_facilities[i]);
}
}
#endif //CONFIG_LTT_USERSPACE_GENERIC
/* 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->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);
/*
* 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());
/*
* 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;
#if 1 /* put here by ltt patch */
goto bad_fork_cleanup_ltt_facilities;
#else
goto bad_fork_cleanup_namespace;
#endif
}
/* 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_ltt_facilities;
}
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);
}
/*
* inherit ioprio
*/
p->ioprio = current->ioprio;
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)++;
}
if (!current->signal->tty && p->signal->tty)
p->signal->tty = NULL;
nr_threads++;
total_forks++;
write_unlock_irq(&tasklist_lock);
retval = 0;
fork_out:
if (retval)
return ERR_PTR(retval);
return p;
bad_fork_cleanup_ltt_facilities:
#ifdef CONFIG_LTT_USERSPACE_GENERIC
{
int i;
for(i=0; i<LTT_FAC_PER_PROCESS; i++) {
if(p->ltt_facilities[i] == 0) break;
WARN_ON(ltt_facility_unregister(
p->ltt_facilities[i]));
}
}
#endif //CONFIG_LTT_USERSPACE_GENERIC
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;
}
int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
{
struct task_struct *tsk = current;
struct hrtimer *timer;
ktime_t expires;
cputime_t cval, cinterval, nval, ninterval;
/*
* Validate the timevals in value.
*/
if (!timeval_valid(&value->it_value) ||
!timeval_valid(&value->it_interval))
return -EINVAL;
switch (which) {
case ITIMER_REAL:
again:
spin_lock_irq(&tsk->sighand->siglock);
timer = &tsk->signal->real_timer;
if (ovalue) {
ovalue->it_value = itimer_get_remtime(timer);
ovalue->it_interval
= ktime_to_timeval(tsk->signal->it_real_incr);
}
/* We are sharing ->siglock with it_real_fn() */
if (hrtimer_try_to_cancel(timer) < 0) {
spin_unlock_irq(&tsk->sighand->siglock);
hrtimer_wait_for_timer(&tsk->signal->real_timer);
goto again;
}
expires = timeval_to_ktime(value->it_value);
if (expires.tv64 != 0) {
tsk->signal->it_real_incr =
timeval_to_ktime(value->it_interval);
hrtimer_start(timer, expires, HRTIMER_MODE_REL);
} else
tsk->signal->it_real_incr.tv64 = 0;
spin_unlock_irq(&tsk->sighand->siglock);
break;
case ITIMER_VIRTUAL:
nval = timeval_to_cputime(&value->it_value);
ninterval = timeval_to_cputime(&value->it_interval);
spin_lock_irq(&tsk->sighand->siglock);
cval = tsk->signal->it_virt_expires;
cinterval = tsk->signal->it_virt_incr;
if (!cputime_eq(cval, cputime_zero) ||
!cputime_eq(nval, cputime_zero)) {
if (cputime_gt(nval, cputime_zero))
nval = cputime_add(nval,
jiffies_to_cputime(1));
set_process_cpu_timer(tsk, CPUCLOCK_VIRT,
&nval, &cval);
}
tsk->signal->it_virt_expires = nval;
tsk->signal->it_virt_incr = ninterval;
spin_unlock_irq(&tsk->sighand->siglock);
if (ovalue) {
cputime_to_timeval(cval, &ovalue->it_value);
cputime_to_timeval(cinterval, &ovalue->it_interval);
}
break;
case ITIMER_PROF:
nval = timeval_to_cputime(&value->it_value);
ninterval = timeval_to_cputime(&value->it_interval);
spin_lock_irq(&tsk->sighand->siglock);
cval = tsk->signal->it_prof_expires;
cinterval = tsk->signal->it_prof_incr;
if (!cputime_eq(cval, cputime_zero) ||
!cputime_eq(nval, cputime_zero)) {
if (cputime_gt(nval, cputime_zero))
nval = cputime_add(nval,
jiffies_to_cputime(1));
set_process_cpu_timer(tsk, CPUCLOCK_PROF,
&nval, &cval);
}
tsk->signal->it_prof_expires = nval;
tsk->signal->it_prof_incr = ninterval;
spin_unlock_irq(&tsk->sighand->siglock);
if (ovalue) {
cputime_to_timeval(cval, &ovalue->it_value);
cputime_to_timeval(cinterval, &ovalue->it_interval);
}
break;
default:
return -EINVAL;
}
return 0;
}
int do_getitimer(int which, struct itimerval *value)
{
struct task_struct *tsk = current;
cputime_t cinterval, cval;
switch (which) {
case ITIMER_REAL:
spin_lock_irq(&tsk->sighand->siglock);
value->it_value = itimer_get_remtime(&tsk->signal->real_timer);
value->it_interval =
ktime_to_timeval(tsk->signal->it_real_incr);
spin_unlock_irq(&tsk->sighand->siglock);
break;
case ITIMER_VIRTUAL:
read_lock(&tasklist_lock);
spin_lock_irq(&tsk->sighand->siglock);
cval = tsk->signal->it_virt_expires;
cinterval = tsk->signal->it_virt_incr;
if (!cputime_eq(cval, cputime_zero)) {
struct task_struct *t = tsk;
cputime_t utime = tsk->signal->utime;
do {
utime = cputime_add(utime, t->utime);
t = next_thread(t);
} while (t != tsk);
if (cputime_le(cval, utime)) { /* about to fire */
cval = jiffies_to_cputime(1);
} else {
cval = cputime_sub(cval, utime);
}
}
spin_unlock_irq(&tsk->sighand->siglock);
read_unlock(&tasklist_lock);
cputime_to_timeval(cval, &value->it_value);
cputime_to_timeval(cinterval, &value->it_interval);
break;
case ITIMER_PROF:
read_lock(&tasklist_lock);
spin_lock_irq(&tsk->sighand->siglock);
cval = tsk->signal->it_prof_expires;
cinterval = tsk->signal->it_prof_incr;
if (!cputime_eq(cval, cputime_zero)) {
struct task_struct *t = tsk;
cputime_t ptime = cputime_add(tsk->signal->utime,
tsk->signal->stime);
do {
ptime = cputime_add(ptime,
cputime_add(t->utime,
t->stime));
t = next_thread(t);
} while (t != tsk);
if (cputime_le(cval, ptime)) { /* about to fire */
cval = jiffies_to_cputime(1);
} else {
cval = cputime_sub(cval, ptime);
}
}
spin_unlock_irq(&tsk->sighand->siglock);
read_unlock(&tasklist_lock);
cputime_to_timeval(cval, &value->it_value);
cputime_to_timeval(cinterval, &value->it_interval);
break;
default:
return(-EINVAL);
}
return 0;
}
int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
{
struct task_struct *tsk = current;
struct hrtimer *timer;
ktime_t expires;
cputime_t cval, cinterval, nval, ninterval;
/*
* Validate the timevals in value.
*
* Note: Although the spec requires that invalid values shall
* return -EINVAL, we just fixup the value and print a limited
* number of warnings in order not to break users of this
* historical misfeature.
*
* Scheduled for replacement in March 2007
*/
check_itimerval(value);
switch (which) {
case ITIMER_REAL:
again:
spin_lock_irq(&tsk->sighand->siglock);
timer = &tsk->signal->real_timer;
if (ovalue) {
ovalue->it_value = itimer_get_remtime(timer);
ovalue->it_interval
= ktime_to_timeval(tsk->signal->it_real_incr);
}
/* We are sharing ->siglock with it_real_fn() */
if (hrtimer_try_to_cancel(timer) < 0) {
spin_unlock_irq(&tsk->sighand->siglock);
goto again;
}
tsk->signal->it_real_incr =
timeval_to_ktime(value->it_interval);
expires = timeval_to_ktime(value->it_value);
if (expires.tv64 != 0)
hrtimer_start(timer, expires, HRTIMER_REL);
spin_unlock_irq(&tsk->sighand->siglock);
break;
case ITIMER_VIRTUAL:
nval = timeval_to_cputime(&value->it_value);
ninterval = timeval_to_cputime(&value->it_interval);
read_lock(&tasklist_lock);
spin_lock_irq(&tsk->sighand->siglock);
cval = tsk->signal->it_virt_expires;
cinterval = tsk->signal->it_virt_incr;
if (!cputime_eq(cval, cputime_zero) ||
!cputime_eq(nval, cputime_zero)) {
if (cputime_gt(nval, cputime_zero))
nval = cputime_add(nval,
jiffies_to_cputime(1));
set_process_cpu_timer(tsk, CPUCLOCK_VIRT,
&nval, &cval);
}
tsk->signal->it_virt_expires = nval;
tsk->signal->it_virt_incr = ninterval;
spin_unlock_irq(&tsk->sighand->siglock);
read_unlock(&tasklist_lock);
if (ovalue) {
cputime_to_timeval(cval, &ovalue->it_value);
cputime_to_timeval(cinterval, &ovalue->it_interval);
}
break;
case ITIMER_PROF:
nval = timeval_to_cputime(&value->it_value);
ninterval = timeval_to_cputime(&value->it_interval);
read_lock(&tasklist_lock);
spin_lock_irq(&tsk->sighand->siglock);
cval = tsk->signal->it_prof_expires;
cinterval = tsk->signal->it_prof_incr;
if (!cputime_eq(cval, cputime_zero) ||
!cputime_eq(nval, cputime_zero)) {
if (cputime_gt(nval, cputime_zero))
nval = cputime_add(nval,
jiffies_to_cputime(1));
set_process_cpu_timer(tsk, CPUCLOCK_PROF,
&nval, &cval);
}
tsk->signal->it_prof_expires = nval;
tsk->signal->it_prof_incr = ninterval;
spin_unlock_irq(&tsk->sighand->siglock);
read_unlock(&tasklist_lock);
if (ovalue) {
cputime_to_timeval(cval, &ovalue->it_value);
cputime_to_timeval(cinterval, &ovalue->it_interval);
}
break;
default:
return -EINVAL;
}
return 0;
}
