pid namespaces: add support for pid namespaces hierarchy

[linux-2.6-block.git] / kernel / pid.c

/*
 * Generic pidhash and scalable, time-bounded PID allocator
 *
 * (C) 2002-2003 William Irwin, IBM
 * (C) 2004 William Irwin, Oracle
 * (C) 2002-2004 Ingo Molnar, Red Hat
 *
 * pid-structures are backing objects for tasks sharing a given ID to chain
 * against. There is very little to them aside from hashing them and
 * parking tasks using given ID's on a list.
 *
 * The hash is always changed with the tasklist_lock write-acquired,
 * and the hash is only accessed with the tasklist_lock at least
 * read-acquired, so there's no additional SMP locking needed here.
 *
 * We have a list of bitmap pages, which bitmaps represent the PID space.
 * Allocating and freeing PIDs is completely lockless. The worst-case
 * allocation scenario when all but one out of 1 million PIDs possible are
 * allocated already: the scanning of 32 list entries and at most PAGE_SIZE
 * bytes. The typical fastpath is a single successful setbit. Freeing is O(1).
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/hash.h>
#include <linux/pid_namespace.h>
#include <linux/init_task.h>

#define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift)
static struct hlist_head *pid_hash;
static int pidhash_shift;
struct pid init_struct_pid = INIT_STRUCT_PID;

int pid_max = PID_MAX_DEFAULT;

#define RESERVED_PIDS		300

int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT;

#define BITS_PER_PAGE		(PAGE_SIZE*8)
#define BITS_PER_PAGE_MASK	(BITS_PER_PAGE-1)

static inline int mk_pid(struct pid_namespace *pid_ns,
		struct pidmap *map, int off)
{
	return (map - pid_ns->pidmap)*BITS_PER_PAGE + off;
}

#define find_next_offset(map, off)					\
		find_next_zero_bit((map)->page, BITS_PER_PAGE, off)

/*
 * PID-map pages start out as NULL, they get allocated upon
 * first use and are never deallocated. This way a low pid_max
 * value does not cause lots of bitmaps to be allocated, but
 * the scheme scales to up to 4 million PIDs, runtime.
 */
struct pid_namespace init_pid_ns = {
	.kref = {
		.refcount       = ATOMIC_INIT(2),
	},
	.pidmap = {
		[ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
	},
	.last_pid = 0,
	.level = 0,
	.child_reaper = &init_task,
};

int is_global_init(struct task_struct *tsk)
{
	return tsk == init_pid_ns.child_reaper;
}

/*
 * Note: disable interrupts while the pidmap_lock is held as an
 * interrupt might come in and do read_lock(&tasklist_lock).
 *
 * If we don't disable interrupts there is a nasty deadlock between
 * detach_pid()->free_pid() and another cpu that does
 * spin_lock(&pidmap_lock) followed by an interrupt routine that does
 * read_lock(&tasklist_lock);
 *
 * After we clean up the tasklist_lock and know there are no
 * irq handlers that take it we can leave the interrupts enabled.
 * For now it is easier to be safe than to prove it can't happen.
 */

static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);

static fastcall void free_pidmap(struct pid_namespace *pid_ns, int pid)
{
	struct pidmap *map = pid_ns->pidmap + pid / BITS_PER_PAGE;
	int offset = pid & BITS_PER_PAGE_MASK;

	clear_bit(offset, map->page);
	atomic_inc(&map->nr_free);
}

static int alloc_pidmap(struct pid_namespace *pid_ns)
{
	int i, offset, max_scan, pid, last = pid_ns->last_pid;
	struct pidmap *map;

	pid = last + 1;
	if (pid >= pid_max)
		pid = RESERVED_PIDS;
	offset = pid & BITS_PER_PAGE_MASK;
	map = &pid_ns->pidmap[pid/BITS_PER_PAGE];
	max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset;
	for (i = 0; i <= max_scan; ++i) {
		if (unlikely(!map->page)) {
			void *page = kzalloc(PAGE_SIZE, GFP_KERNEL);
			/*
			 * Free the page if someone raced with us
			 * installing it:
			 */
			spin_lock_irq(&pidmap_lock);
			if (map->page)
				kfree(page);
			else
				map->page = page;
			spin_unlock_irq(&pidmap_lock);
			if (unlikely(!map->page))
				break;
		}
		if (likely(atomic_read(&map->nr_free))) {
			do {
				if (!test_and_set_bit(offset, map->page)) {
					atomic_dec(&map->nr_free);
					pid_ns->last_pid = pid;
					return pid;
				}
				offset = find_next_offset(map, offset);
				pid = mk_pid(pid_ns, map, offset);
			/*
			 * find_next_offset() found a bit, the pid from it
			 * is in-bounds, and if we fell back to the last
			 * bitmap block and the final block was the same
			 * as the starting point, pid is before last_pid.
			 */
			} while (offset < BITS_PER_PAGE && pid < pid_max &&
					(i != max_scan || pid < last ||
					    !((last+1) & BITS_PER_PAGE_MASK)));
		}
		if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
			++map;
			offset = 0;
		} else {
			map = &pid_ns->pidmap[0];
			offset = RESERVED_PIDS;
			if (unlikely(last == offset))
				break;
		}
		pid = mk_pid(pid_ns, map, offset);
	}
	return -1;
}

static int next_pidmap(struct pid_namespace *pid_ns, int last)
{
	int offset;
	struct pidmap *map, *end;

	offset = (last + 1) & BITS_PER_PAGE_MASK;
	map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE];
	end = &pid_ns->pidmap[PIDMAP_ENTRIES];
	for (; map < end; map++, offset = 0) {
		if (unlikely(!map->page))
			continue;
		offset = find_next_bit((map)->page, BITS_PER_PAGE, offset);
		if (offset < BITS_PER_PAGE)
			return mk_pid(pid_ns, map, offset);
	}
	return -1;
}

fastcall void put_pid(struct pid *pid)
{
	struct pid_namespace *ns;

	if (!pid)
		return;

	/* FIXME - this must be the namespace this pid lives in */
	ns = &init_pid_ns;
	if ((atomic_read(&pid->count) == 1) ||
	     atomic_dec_and_test(&pid->count))
		kmem_cache_free(ns->pid_cachep, pid);
}
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);
}

fastcall void free_pid(struct pid *pid)
{
	/* We can be called with write_lock_irq(&tasklist_lock) held */
	unsigned long flags;

	spin_lock_irqsave(&pidmap_lock, flags);
	hlist_del_rcu(&pid->pid_chain);
	spin_unlock_irqrestore(&pidmap_lock, flags);

	free_pidmap(&init_pid_ns, pid->nr);
	call_rcu(&pid->rcu, delayed_put_pid);
}

struct pid *alloc_pid(void)
{
	struct pid *pid;
	enum pid_type type;
	int nr = -1;
	struct pid_namespace *ns;

	ns = task_active_pid_ns(current);
	pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
	if (!pid)
		goto out;

	nr = alloc_pidmap(ns);
	if (nr < 0)
		goto out_free;

	atomic_set(&pid->count, 1);
	pid->nr = nr;
	for (type = 0; type < PIDTYPE_MAX; ++type)
		INIT_HLIST_HEAD(&pid->tasks[type]);

	spin_lock_irq(&pidmap_lock);
	hlist_add_head_rcu(&pid->pid_chain, &pid_hash[pid_hashfn(pid->nr)]);
	spin_unlock_irq(&pidmap_lock);

out:
	return pid;

out_free:
	kmem_cache_free(ns->pid_cachep, pid);
	pid = NULL;
	goto out;
}

struct pid * fastcall find_pid(int nr)
{
	struct hlist_node *elem;
	struct pid *pid;

	hlist_for_each_entry_rcu(pid, elem,
			&pid_hash[pid_hashfn(nr)], pid_chain) {
		if (pid->nr == nr)
			return pid;
	}
	return NULL;
}
EXPORT_SYMBOL_GPL(find_pid);

/*
 * attach_pid() must be called with the tasklist_lock write-held.
 */
int fastcall attach_pid(struct task_struct *task, enum pid_type type,
		struct pid *pid)
{
	struct pid_link *link;

	link = &task->pids[type];
	link->pid = pid;
	hlist_add_head_rcu(&link->node, &pid->tasks[type]);

	return 0;
}

void fastcall detach_pid(struct task_struct *task, enum pid_type type)
{
	struct pid_link *link;
	struct pid *pid;
	int tmp;

	link = &task->pids[type];
	pid = link->pid;

	hlist_del_rcu(&link->node);
	link->pid = NULL;

	for (tmp = PIDTYPE_MAX; --tmp >= 0; )
		if (!hlist_empty(&pid->tasks[tmp]))
			return;

	free_pid(pid);
}

/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */
void fastcall transfer_pid(struct task_struct *old, struct task_struct *new,
			   enum pid_type type)
{
	new->pids[type].pid = old->pids[type].pid;
	hlist_replace_rcu(&old->pids[type].node, &new->pids[type].node);
	old->pids[type].pid = NULL;
}

struct task_struct * fastcall pid_task(struct pid *pid, enum pid_type type)
{
	struct task_struct *result = NULL;
	if (pid) {
		struct hlist_node *first;
		first = rcu_dereference(pid->tasks[type].first);
		if (first)
			result = hlist_entry(first, struct task_struct, pids[(type)].node);
	}
	return result;
}

/*
 * Must be called under rcu_read_lock() or with tasklist_lock read-held.
 */
struct task_struct *find_task_by_pid_type(int type, int nr)
{
	return pid_task(find_pid(nr), type);
}

EXPORT_SYMBOL(find_task_by_pid_type);

struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
{
	struct pid *pid;
	rcu_read_lock();
	pid = get_pid(task->pids[type].pid);
	rcu_read_unlock();
	return pid;
}

struct task_struct *fastcall 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;
}

struct pid *find_get_pid(pid_t nr)
{
	struct pid *pid;

	rcu_read_lock();
	pid = get_pid(find_pid(nr));
	rcu_read_unlock();

	return pid;
}

/*
 * Used by proc to find the first pid that is greater then or equal to nr.
 *
 * If there is a pid at nr this function is exactly the same as find_pid.
 */
struct pid *find_ge_pid(int nr)
{
	struct pid *pid;

	do {
		pid = find_pid(nr);
		if (pid)
			break;
		nr = next_pidmap(task_active_pid_ns(current), nr);
	} while (nr > 0);

	return pid;
}
EXPORT_SYMBOL_GPL(find_get_pid);

struct pid_cache {
	int nr_ids;
	char name[16];
	struct kmem_cache *cachep;
	struct list_head list;
};

static LIST_HEAD(pid_caches_lh);
static DEFINE_MUTEX(pid_caches_mutex);

/*
 * creates the kmem cache to allocate pids from.
 * @nr_ids: the number of numerical ids this pid will have to carry
 */

static struct kmem_cache *create_pid_cachep(int nr_ids)
{
	struct pid_cache *pcache;
	struct kmem_cache *cachep;

	mutex_lock(&pid_caches_mutex);
	list_for_each_entry (pcache, &pid_caches_lh, list)
		if (pcache->nr_ids == nr_ids)
			goto out;

	pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL);
	if (pcache == NULL)
		goto err_alloc;

	snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids);
	cachep = kmem_cache_create(pcache->name,
			/* FIXME add numerical ids here */
			sizeof(struct pid), 0, SLAB_HWCACHE_ALIGN, NULL);
	if (cachep == NULL)
		goto err_cachep;

	pcache->nr_ids = nr_ids;
	pcache->cachep = cachep;
	list_add(&pcache->list, &pid_caches_lh);
out:
	mutex_unlock(&pid_caches_mutex);
	return pcache->cachep;

err_cachep:
	kfree(pcache);
err_alloc:
	mutex_unlock(&pid_caches_mutex);
	return NULL;
}

struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns)
{
	BUG_ON(!old_ns);
	get_pid_ns(old_ns);
	return old_ns;
}

void free_pid_ns(struct kref *kref)
{
	struct pid_namespace *ns;

	ns = container_of(kref, struct pid_namespace, kref);
	kfree(ns);
}

/*
 * The pid hash table is scaled according to the amount of memory in the
 * machine.  From a minimum of 16 slots up to 4096 slots at one gigabyte or
 * more.
 */
void __init pidhash_init(void)
{
	int i, pidhash_size;
	unsigned long megabytes = nr_kernel_pages >> (20 - PAGE_SHIFT);

	pidhash_shift = max(4, fls(megabytes * 4));
	pidhash_shift = min(12, pidhash_shift);
	pidhash_size = 1 << pidhash_shift;

	printk("PID hash table entries: %d (order: %d, %Zd bytes)\n",
		pidhash_size, pidhash_shift,
		pidhash_size * sizeof(struct hlist_head));

	pid_hash = alloc_bootmem(pidhash_size *	sizeof(*(pid_hash)));
	if (!pid_hash)
		panic("Could not alloc pidhash!\n");
	for (i = 0; i < pidhash_size; i++)
		INIT_HLIST_HEAD(&pid_hash[i]);
}

void __init pidmap_init(void)
{
	init_pid_ns.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
	/* Reserve PID 0. We never call free_pidmap(0) */
	set_bit(0, init_pid_ns.pidmap[0].page);
	atomic_dec(&init_pid_ns.pidmap[0].nr_free);

	init_pid_ns.pid_cachep = create_pid_cachep(1);
	if (init_pid_ns.pid_cachep == NULL)
		panic("Can't create pid_1 cachep\n");
}