#include <linux/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/memblock.h>
#include <linux/pid_namespace.h>
#include <linux/init_task.h>
#include <linux/syscalls.h>
#include <linux/proc_ns.h>
#include <linux/refcount.h>
#include <linux/anon_inodes.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/idr.h>
#include <net/sock.h>
#include <uapi/linux/pidfd.h>
struct pid init_struct_pid = {
.count = REFCOUNT_INIT(1),
.tasks = {
{ .first = NULL },
{ .first = NULL },
{ .first = NULL },
},
.level = 0,
.numbers = { {
.nr = 0,
.ns = &init_pid_ns,
}, }
};
int pid_max = PID_MAX_DEFAULT;
#define RESERVED_PIDS 300
int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT;
struct pid_namespace init_pid_ns = {
.ns.count = REFCOUNT_INIT(2),
.idr = IDR_INIT(init_pid_ns.idr),
.pid_allocated = PIDNS_ADDING,
.level = 0,
.child_reaper = &init_task,
.user_ns = &init_user_ns,
.ns.inum = PROC_PID_INIT_INO,
#ifdef CONFIG_PID_NS
.ns.ops = &pidns_operations,
#endif
#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
.memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC,
#endif
};
EXPORT_SYMBOL_GPL(init_pid_ns);
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
void put_pid(struct pid *pid)
{
struct pid_namespace *ns;
if (!pid)
return;
ns = pid->numbers[pid->level].ns;
if (refcount_dec_and_test(&pid->count)) {
kmem_cache_free(ns->pid_cachep, pid);
put_pid_ns(ns);
}
}
EXPORT_SYMBOL_GPL(put_pid);
static void delayed_put_pid(struct rcu_head *rhp)
{
struct pid *pid = container_of(rhp, struct pid, rcu);
put_pid(pid);
}
void free_pid(struct pid *pid)
{
int i;
unsigned long flags;
spin_lock_irqsave(&pidmap_lock, flags);
for (i = 0; i <= pid->level; i++) {
struct upid *upid = pid->numbers + i;
struct pid_namespace *ns = upid->ns;
switch (--ns->pid_allocated) {
case 2:
case 1:
wake_up_process(ns->child_reaper);
break;
case PIDNS_ADDING:
WARN_ON(ns->child_reaper);
ns->pid_allocated = 0;
break;
}
idr_remove(&ns->idr, upid->nr);
}
spin_unlock_irqrestore(&pidmap_lock, flags);
call_rcu(&pid->rcu, delayed_put_pid);
}
struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
size_t set_tid_size)
{
struct pid *pid;
enum pid_type type;
int i, nr;
struct pid_namespace *tmp;
struct upid *upid;
int retval = -ENOMEM;
if (set_tid_size > ns->level + 1)
return ERR_PTR(-EINVAL);
pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
if (!pid)
return ERR_PTR(retval);
tmp = ns;
pid->level = ns->level;
for (i = ns->level; i >= 0; i--) {
int tid = 0;
if (set_tid_size) {
tid = set_tid[ns->level - i];
retval = -EINVAL;
if (tid < 1 || tid >= pid_max)
goto out_free;
if (tid != 1 && !tmp->child_reaper)
goto out_free;
retval = -EPERM;
if (!checkpoint_restore_ns_capable(tmp->user_ns))
goto out_free;
set_tid_size--;
}
idr_preload(GFP_KERNEL);
spin_lock_irq(&pidmap_lock);
if (tid) {
nr = idr_alloc(&tmp->idr, NULL, tid,
tid + 1, GFP_ATOMIC);
if (nr == -ENOSPC)
nr = -EEXIST;
} else {
int pid_min = 1;
if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
pid_min = RESERVED_PIDS;
nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
pid_max, GFP_ATOMIC);
}
spin_unlock_irq(&pidmap_lock);
idr_preload_end();
if (nr < 0) {
retval = (nr == -ENOSPC) ? -EAGAIN : nr;
goto out_free;
}
pid->numbers[i].nr = nr;
pid->numbers[i].ns = tmp;
tmp = tmp->parent;
}
retval = -ENOMEM;
get_pid_ns(ns);
refcount_set(&pid->count, 1);
spin_lock_init(&pid->lock);
for (type = 0; type < PIDTYPE_MAX; ++type)
INIT_HLIST_HEAD(&pid->tasks[type]);
init_waitqueue_head(&pid->wait_pidfd);
INIT_HLIST_HEAD(&pid->inodes);
upid = pid->numbers + ns->level;
spin_lock_irq(&pidmap_lock);
if (!(ns->pid_allocated & PIDNS_ADDING))
goto out_unlock;
for ( ; upid >= pid->numbers; --upid) {
idr_replace(&upid->ns->idr, pid, upid->nr);
upid->ns->pid_allocated++;
}
spin_unlock_irq(&pidmap_lock);
return pid;
out_unlock:
spin_unlock_irq(&pidmap_lock);
put_pid_ns(ns);
out_free:
spin_lock_irq(&pidmap_lock);
while (++i <= ns->level) {
upid = pid->numbers + i;
idr_remove(&upid->ns->idr, upid->nr);
}
if (ns->pid_allocated == PIDNS_ADDING)
idr_set_cursor(&ns->idr, 0);
spin_unlock_irq(&pidmap_lock);
kmem_cache_free(ns->pid_cachep, pid);
return ERR_PTR(retval);
}
void disable_pid_allocation(struct pid_namespace *ns)
{
spin_lock_irq(&pidmap_lock);
ns->pid_allocated &= ~PIDNS_ADDING;
spin_unlock_irq(&pidmap_lock);
}
struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
return idr_find(&ns->idr, nr);
}
EXPORT_SYMBOL_GPL(find_pid_ns);
struct pid *find_vpid(int nr)
{
return find_pid_ns(nr, task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(find_vpid);
static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type)
{
return (type == PIDTYPE_PID) ?
&task->thread_pid :
&task->signal->pids[type];
}
void attach_pid(struct task_struct *task, enum pid_type type)
{
struct pid *pid = *task_pid_ptr(task, type);
hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]);
}
static void __change_pid(struct task_struct *task, enum pid_type type,
struct pid *new)
{
struct pid **pid_ptr = task_pid_ptr(task, type);
struct pid *pid;
int tmp;
pid = *pid_ptr;
hlist_del_rcu(&task->pid_links[type]);
*pid_ptr = new;
for (tmp = PIDTYPE_MAX; --tmp >= 0; )
if (pid_has_task(pid, tmp))
return;
free_pid(pid);
}
void detach_pid(struct task_struct *task, enum pid_type type)
{
__change_pid(task, type, NULL);
}
void change_pid(struct task_struct *task, enum pid_type type,
struct pid *pid)
{
__change_pid(task, type, pid);
attach_pid(task, type);
}
void exchange_tids(struct task_struct *left, struct task_struct *right)
{
struct pid *pid1 = left->thread_pid;
struct pid *pid2 = right->thread_pid;
struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID];
struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID];
hlists_swap_heads_rcu(head1, head2);
rcu_assign_pointer(left->thread_pid, pid2);
rcu_assign_pointer(right->thread_pid, pid1);
WRITE_ONCE(left->pid, pid_nr(pid2));
WRITE_ONCE(right->pid, pid_nr(pid1));
}
void transfer_pid(struct task_struct *old, struct task_struct *new,
enum pid_type type)
{
if (type == PIDTYPE_PID)
new->thread_pid = old->thread_pid;
hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]);
}
struct task_struct *pid_task(struct pid *pid, enum pid_type type)
{
struct task_struct *result = NULL;
if (pid) {
struct hlist_node *first;
first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]),
lockdep_tasklist_lock_is_held());
if (first)
result = hlist_entry(first, struct task_struct, pid_links[(type)]);
}
return result;
}
EXPORT_SYMBOL(pid_task);
struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
{
RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
"find_task_by_pid_ns() needs rcu_read_lock() protection");
return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
}
struct task_struct *find_task_by_vpid(pid_t vnr)
{
return find_task_by_pid_ns(vnr, task_active_pid_ns(current));
}
struct task_struct *find_get_task_by_vpid(pid_t nr)
{
struct task_struct *task;
rcu_read_lock();
task = find_task_by_vpid(nr);
if (task)
get_task_struct(task);
rcu_read_unlock();
return task;
}
struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
{
struct pid *pid;
rcu_read_lock();
pid = get_pid(rcu_dereference(*task_pid_ptr(task, type)));
rcu_read_unlock();
return pid;
}
EXPORT_SYMBOL_GPL(get_task_pid);
struct task_struct *get_pid_task(struct pid *pid, enum pid_type type)
{
struct task_struct *result;
rcu_read_lock();
result = pid_task(pid, type);
if (result)
get_task_struct(result);
rcu_read_unlock();
return result;
}
EXPORT_SYMBOL_GPL(get_pid_task);
struct pid *find_get_pid(pid_t nr)
{
struct pid *pid;
rcu_read_lock();
pid = get_pid(find_vpid(nr));
rcu_read_unlock();
return pid;
}
EXPORT_SYMBOL_GPL(find_get_pid);
pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
{
struct upid *upid;
pid_t nr = 0;
if (pid && ns->level <= pid->level) {
upid = &pid->numbers[ns->level];
if (upid->ns == ns)
nr = upid->nr;
}
return nr;
}
EXPORT_SYMBOL_GPL(pid_nr_ns);
pid_t pid_vnr(struct pid *pid)
{
return pid_nr_ns(pid, task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(pid_vnr);
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
struct pid_namespace *ns)
{
pid_t nr = 0;
rcu_read_lock();
if (!ns)
ns = task_active_pid_ns(current);
nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
rcu_read_unlock();
return nr;
}
EXPORT_SYMBOL(__task_pid_nr_ns);
struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
{
return ns_of_pid(task_pid(tsk));
}
EXPORT_SYMBOL_GPL(task_active_pid_ns);
struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
{
return idr_get_next(&ns->idr, &nr);
}
EXPORT_SYMBOL_GPL(find_ge_pid);
struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
{
struct fd f;
struct pid *pid;
f = fdget(fd);
if (!f.file)
return ERR_PTR(-EBADF);
pid = pidfd_pid(f.file);
if (!IS_ERR(pid)) {
get_pid(pid);
*flags = f.file->f_flags;
}
fdput(f);
return pid;
}
struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags)
{
unsigned int f_flags;
struct pid *pid;
struct task_struct *task;
pid = pidfd_get_pid(pidfd, &f_flags);
if (IS_ERR(pid))
return ERR_CAST(pid);
task = get_pid_task(pid, PIDTYPE_TGID);
put_pid(pid);
if (!task)
return ERR_PTR(-ESRCH);
*flags = f_flags;
return task;
}
int pidfd_create(struct pid *pid, unsigned int flags)
{
int pidfd;
struct file *pidfd_file;
pidfd = pidfd_prepare(pid, flags, &pidfd_file);
if (pidfd < 0)
return pidfd;
fd_install(pidfd, pidfd_file);
return pidfd;
}
SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
{
int fd;
struct pid *p;
if (flags & ~PIDFD_NONBLOCK)
return -EINVAL;
if (pid <= 0)
return -EINVAL;
p = find_get_pid(pid);
if (!p)
return -ESRCH;
fd = pidfd_create(p, flags);
put_pid(p);
return fd;
}
void __init pid_idr_init(void)
{
BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING);
pid_max = min(pid_max_max, max_t(int, pid_max,
PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
pid_max_min = max_t(int, pid_max_min,
PIDS_PER_CPU_MIN * num_possible_cpus());
pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min);
idr_init(&init_pid_ns.idr);
init_pid_ns.pid_cachep = kmem_cache_create("pid",
struct_size_t(struct pid, numbers, 1),
__alignof__(struct pid),
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT,
NULL);
}
static struct file *__pidfd_fget(struct task_struct *task, int fd)
{
struct file *file;
int ret;
ret = down_read_killable(&task->signal->exec_update_lock);
if (ret)
return ERR_PTR(ret);
if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
file = fget_task(task, fd);
else
file = ERR_PTR(-EPERM);
up_read(&task->signal->exec_update_lock);
return file ?: ERR_PTR(-EBADF);
}
static int pidfd_getfd(struct pid *pid, int fd)
{
struct task_struct *task;
struct file *file;
int ret;
task = get_pid_task(pid, PIDTYPE_PID);
if (!task)
return -ESRCH;
file = __pidfd_fget(task, fd);
put_task_struct(task);
if (IS_ERR(file))
return PTR_ERR(file);
ret = receive_fd(file, O_CLOEXEC);
fput(file);
return ret;
}
SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd,
unsigned int, flags)
{
struct pid *pid;
struct fd f;
int ret;
if (flags)
return -EINVAL;
f = fdget(pidfd);
if (!f.file)
return -EBADF;
pid = pidfd_pid(f.file);
if (IS_ERR(pid))
ret = PTR_ERR(pid);
else
ret = pidfd_getfd(pid, fd);
fdput(f);
return ret;
}