static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
{
#ifdef CONFIG_BLOCK
struct io_context *ioc = current->io_context;
struct io_context *new_ioc;
if (!ioc)
return 0;
/*
* Share io context with parent, if CLONE_IO is set
*/
if (clone_flags & CLONE_IO) {
tsk->io_context = ioc_task_link(ioc);
if (unlikely(!tsk->io_context))
return -ENOMEM;
} else if (ioprio_valid(ioc->ioprio)) {
new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
if (unlikely(!new_ioc))
return -ENOMEM;
new_ioc->ioprio = ioc->ioprio;
put_io_context(new_ioc);
}
#endif
return 0;
}
int set_task_ioprio(struct task_struct *task, int ioprio)
{
int err;
struct io_context *ioc;
const struct cred *cred = current_cred(), *tcred;
rcu_read_lock();
tcred = __task_cred(task);
if (!uid_eq(tcred->uid, cred->euid) &&
!uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) {
rcu_read_unlock();
return -EPERM;
}
rcu_read_unlock();
err = security_task_setioprio(task, ioprio);
if (err)
return err;
ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
if (ioc) {
ioc->ioprio = ioprio;
put_io_context(ioc);
}
return err;
}
static int ioband_cgroup(struct bio *bio)
{
struct io_context *ioc = get_bio_cgroup_iocontext(bio);
int id = 0;
if (ioc) {
id = ioc->id;
put_io_context(ioc);
}
return id;
}
void copy_io_context(struct io_context **pdst, struct io_context **psrc)
{
struct io_context *src = *psrc;
struct io_context *dst = *pdst;
if (src) {
BUG_ON(atomic_long_read(&src->refcount) == 0);
atomic_long_inc(&src->refcount);
put_io_context(dst);
*pdst = src;
}
}
/* Called by the exiting task */
void exit_io_context(struct task_struct *task)
{
struct io_context *ioc;
task_lock(task);
ioc = task->io_context;
task->io_context = NULL;
task_unlock(task);
atomic_dec(&ioc->nr_tasks);
put_io_context(ioc, NULL);
}
/* Called by the exiting task */
void exit_io_context(struct task_struct *task)
{
struct io_context *ioc;
task_lock(task);
ioc = task->io_context;
task->io_context = NULL;
task_unlock(task);
if (atomic_dec_and_test(&ioc->nr_tasks))
hlist_sched_exit(ioc, &ioc->cic_list);
hlist_sched_exit(ioc, &ioc->bfq_cic_list);
put_io_context(ioc);
}
/* Called by the exiting task */
void exit_io_context(struct task_struct *task)
{
struct io_context *ioc;
task_lock(task);
ioc = task->io_context;
task->io_context = NULL;
task_unlock(task);
if (atomic_dec_and_test(&ioc->nr_tasks))
cfq_exit(ioc);
put_io_context(ioc);
}
/**
* __bfq_exit_single_io_context - deassociate @cic from any running task.
* @bfqd: bfq_data on which @cic is valid.
* @cic: the cic being exited.
*
* Whenever no more tasks are using @cic or @bfqd is deallocated we
* need to invalidate its entry in the radix tree hash table and to
* release the queues it refers to.
*
* Called under the queue lock.
*/
static void __bfq_exit_single_io_context(struct bfq_data *bfqd,
struct cfq_io_context *cic)
{
struct io_context *ioc = cic->ioc;
list_del_init(&cic->queue_list);
/*
* Make sure dead mark is seen for dead queues
*/
smp_wmb();
rcu_assign_pointer(cic->key, bfqd_dead_key(bfqd));
/*
* No write-side locking as no task is using @ioc (they're exited
* or bfqd is being deallocated.
*/
rcu_read_lock();
if (rcu_dereference(ioc->ioc_data) == cic) {
rcu_read_unlock();
spin_lock(&ioc->lock);
rcu_assign_pointer(ioc->ioc_data, NULL);
spin_unlock(&ioc->lock);
} else
rcu_read_unlock();
if (cic->cfqq[BLK_RW_ASYNC] != NULL) {
bfq_exit_bfqq(bfqd, cic->cfqq[BLK_RW_ASYNC]);
cic->cfqq[BLK_RW_ASYNC] = NULL;
}
spin_lock(&bfqd->eqm_lock);
if (cic->cfqq[BLK_RW_SYNC] != NULL) {
/*
* If the bic is using a shared queue, put the reference
* taken on the io_context when the bic started using a
* shared bfq_queue.
*/
if (bfq_bfqq_coop(cic->cfqq[BLK_RW_SYNC]))
put_io_context(ioc);
bfq_exit_bfqq(bfqd, cic->cfqq[BLK_RW_SYNC]);
cic->cfqq[BLK_RW_SYNC] = NULL;
}
spin_unlock(&bfqd->eqm_lock);
}
/* Called by the exitting task */
void exit_io_context(void)
{
struct io_context *ioc;
task_lock(current);
ioc = current->io_context;
current->io_context = NULL;
task_unlock(current);
if (atomic_dec_and_test(&ioc->nr_tasks)) {
if (ioc->aic && ioc->aic->exit)
ioc->aic->exit(ioc->aic);
// cfq_exit(ioc);
hlist_sched_exit(ioc, &ioc->cic_list);
hlist_sched_exit(ioc, &ioc->bfq_cic_list);
put_io_context(ioc);
}
}
/**
* bfq_get_io_context - return the @cic associated to @bfqd in @ioc.
* @bfqd: the search key.
* @gfp_mask: the mask to use for cic allocation.
*
* Setup general io context and cfq io context. There can be several cfq
* io contexts per general io context, if this process is doing io to more
* than one device managed by cfq.
*/
static struct cfq_io_context *bfq_get_io_context(struct bfq_data *bfqd,
gfp_t gfp_mask)
{
struct io_context *ioc = NULL;
struct cfq_io_context *cic;
might_sleep_if(gfp_mask & __GFP_WAIT);
ioc = get_io_context(gfp_mask, bfqd->queue->node);
if (ioc == NULL)
return NULL;
/* Lookup for an existing cic. */
cic = bfq_cic_lookup(bfqd, ioc);
if (cic != NULL)
goto out;
/* Alloc one if needed. */
cic = bfq_alloc_io_context(bfqd, gfp_mask);
if (cic == NULL)
goto err;
/* Link it into the ioc's radix tree and cic list. */
if (bfq_cic_link(bfqd, ioc, cic, gfp_mask) != 0)
goto err_free;
out:
/*
* test_and_clear_bit() implies a memory barrier, paired with
* the wmb() in fs/ioprio.c, so the value seen for ioprio is the
* new one.
*/
if (unlikely(test_and_clear_bit(IOC_BFQ_IOPRIO_CHANGED,
ioc->ioprio_changed)))
bfq_ioc_set_ioprio(ioc);
return cic;
err_free:
bfq_cic_free(cic);
err:
put_io_context(ioc);
return NULL;
}
static inline int is_rt(struct fuse_conn *fc)
{
/*
* Returns 1 if a process is RT class.
*/
struct io_context *ioc = NULL;
int ret = 0;
if (!fc)
return 0;
if (!(fc->flags & FUSE_HANDLE_RT_CLASS)) /* Don't handle RT class */
return 0;
get_io_context(ioc);
if(!ioc)
return 0;
if(IOPRIO_PRIO_CLASS(ioc->ioprio) == IOPRIO_CLASS_RT)
ret = 1;
put_io_context(ioc);
return ret;
}
static inline int is_rt(struct fuse_conn *fc)
{
/* Returns 1 if request is RT class */
/* && FUSE_HANDLE_RT_CLASS bit of fc->flags is set. */
/* FUSE_HANDLE_RT_CLASS bit is set by 'handle_rt_class' */
struct io_context *ioc;
int ret = 0;
if (!fc)
return 0;
if (!(fc->flags & FUSE_HANDLE_RT_CLASS)) /* Don't handle RT class */
return 0;
ioc = get_io_context(GFP_NOWAIT, 0);
if (!ioc)
return 0;
if (IOPRIO_PRIO_CLASS(ioc->ioprio) == IOPRIO_CLASS_RT)
ret = 1;
put_io_context(ioc);
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 *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) >=
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;
#ifdef CONFIG_SECURITY_ANOUBIS
anoubis_task_create(p);
#endif
/*
* 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;
p->prev_utime = cputime_zero;
p->prev_stime = cputime_zero;
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->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
p->bts = NULL;
p->stack_start = stack_start;
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
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;
if (clone_flags & CLONE_NEWPID) {
retval = pid_ns_prepare_proc(p->nsproxy->pid_ns);
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;
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_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 (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++;
}
total_forks++;
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
perf_event_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_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_policy:
perf_event_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
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);
anoubis_task_destroy(p);
exit_creds(p);
bad_fork_free:
free_task(p);
fork_out:
return ERR_PTR(retval);
}
