/* * Generic pidhash and scalable, time-bounded PID allocator * * (C) 2002-2003 Nadia Yvette Chambers, IBM * (C) 2004 Nadia Yvette Chambers, 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). * * Pid namespaces: *    (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. *    (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM *     Many thanks to Oleg Nesterov for comments and help * */ #include <linux/mm.h>#include <linux/export.h>#include <linux/slab.h>#include <linux/init.h>#include <linux/rculist.h>#include <linux/bootmem.h>#include <linux/hash.h>#include <linux/pid_namespace.h>#include <linux/init_task.h>#include <linux/syscalls.h>#include <linux/proc_ns.h>#include <linux/proc_fs.h> #define pid_hashfn(nr, ns)	\	hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)static struct hlist_head *pid_hash;static unsigned int pidhash_shift = 4;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; 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,	.nr_hashed = PIDNS_HASH_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};EXPORT_SYMBOL_GPL(init_pid_ns); /* * 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 void free_pidmap(struct upid *upid){	int nr = upid->nr;	struct pidmap *map = upid->ns->pidmap + nr / BITS_PER_PAGE;	int offset = nr & BITS_PER_PAGE_MASK; 	clear_bit(offset, map->page);	atomic_inc(&map->nr_free);} /* * If we started walking pids at 'base', is 'a' seen before 'b'? */static int pid_before(int base, int a, int b){	/*	 * This is the same as saying	 *	 * (a - base + MAXUINT) % MAXUINT < (b - base + MAXUINT) % MAXUINT	 * and that mapping orders 'a' and 'b' with respect to 'base'.	 */	return (unsigned)(a - base) < (unsigned)(b - base);} /* * We might be racing with someone else trying to set pid_ns->last_pid * at the pid allocation time (there's also a sysctl for this, but racing * with this one is OK, see comment in kernel/pid_namespace.c about it). * We want the winner to have the "later" value, because if the * "earlier" value prevails, then a pid may get reused immediately. * * Since pids rollover, it is not sufficient to just pick the bigger * value.  We have to consider where we started counting from. * * 'base' is the value of pid_ns->last_pid that we observed when * we started looking for a pid. * * 'pid' is the pid that we eventually found. */static void set_last_pid(struct pid_namespace *pid_ns, int base, int pid){	int prev;	int last_write = base;	do {		prev = last_write;		last_write = cmpxchg(&pid_ns->last_pid, prev, pid);	} while ((prev != last_write) && (pid_before(base, last_write, pid)));} 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];	/*	 * If last_pid points into the middle of the map->page we	 * want to scan this bitmap block twice, the second time	 * we start with offset == 0 (or RESERVED_PIDS).	 */	max_scan = DIV_ROUND_UP(pid_max, 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) {				map->page = page;				page = NULL;			}			spin_unlock_irq(&pidmap_lock);			kfree(page);			if (unlikely(!map->page))				return -ENOMEM;		}		if (likely(atomic_read(&map->nr_free))) {			for ( ; ; ) {				if (!test_and_set_bit(offset, map->page)) {					atomic_dec(&map->nr_free);					set_last_pid(pid_ns, last, pid);					return pid;				}				offset = find_next_offset(map, offset);				if (offset >= BITS_PER_PAGE)					break;				pid = mk_pid(pid_ns, map, offset);				if (pid >= pid_max)					break;			}		}		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 -EAGAIN;} int next_pidmap(struct pid_namespace *pid_ns, unsigned int last){	int offset;	struct pidmap *map, *end; 	if (last >= PID_MAX_LIMIT)		return -1; 	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;} void put_pid(struct pid *pid){	struct pid_namespace *ns; 	if (!pid)		return; 	ns = pid->numbers[pid->level].ns;	if ((atomic_read(&pid->count) == 1) ||	     atomic_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){	/* We can be called with write_lock_irq(&tasklist_lock) held */	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;		hlist_del_rcu(&upid->pid_chain);		switch(--ns->nr_hashed) {		case 2:		case 1:			/* When all that is left in the pid namespace			 * is the reaper wake up the reaper.  The reaper			 * may be sleeping in zap_pid_ns_processes().			 */			wake_up_process(ns->child_reaper);			break;		case PIDNS_HASH_ADDING:			/* Handle a fork failure of the first process */			WARN_ON(ns->child_reaper);			ns->nr_hashed = 0;			/* fall through */		case 0:			schedule_work(&ns->proc_work);			break;		}	}	spin_unlock_irqrestore(&pidmap_lock, flags); 	for (i = 0; i <= pid->level; i++)		free_pidmap(pid->numbers + i); 	call_rcu(&pid->rcu, delayed_put_pid);} struct pid *alloc_pid(struct pid_namespace *ns){	struct pid *pid;	enum pid_type type;	int i, nr;	struct pid_namespace *tmp;	struct upid *upid;	int retval = -ENOMEM; 	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--) {		nr = alloc_pidmap(tmp);		if (IS_ERR_VALUE(nr)) {			retval = nr;			goto out_free;		} 		pid->numbers[i].nr = nr;		pid->numbers[i].ns = tmp;		tmp = tmp->parent;	} 	if (unlikely(is_child_reaper(pid))) {		if (pid_ns_prepare_proc(ns))			goto out_free;	} 	get_pid_ns(ns);	atomic_set(&pid->count, 1);	for (type = 0; type < PIDTYPE_MAX; ++type)		INIT_HLIST_HEAD(&pid->tasks[type]); 	upid = pid->numbers + ns->level;	spin_lock_irq(&pidmap_lock);	if (!(ns->nr_hashed & PIDNS_HASH_ADDING))		goto out_unlock;	for ( ; upid >= pid->numbers; --upid) {		hlist_add_head_rcu(&upid->pid_chain,				&pid_hash[pid_hashfn(upid->nr, upid->ns)]);		upid->ns->nr_hashed++;	}	spin_unlock_irq(&pidmap_lock); 	return pid; out_unlock:	spin_unlock_irq(&pidmap_lock);	put_pid_ns(ns); out_free:	while (++i <= ns->level)		free_pidmap(pid->numbers + i); 	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->nr_hashed &= ~PIDNS_HASH_ADDING;	spin_unlock_irq(&pidmap_lock);} struct pid *find_pid_ns(int nr, struct pid_namespace *ns){	struct upid *pnr; 	hlist_for_each_entry_rcu(pnr,			&pid_hash[pid_hashfn(nr, ns)], pid_chain)		if (pnr->nr == nr && pnr->ns == ns)			return container_of(pnr, struct pid,					numbers[ns->level]); 	return NULL;}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); /* * attach_pid() must be called with the tasklist_lock write-held. */void attach_pid(struct task_struct *task, enum pid_type type){	struct pid_link *link = &task->pids[type];	hlist_add_head_rcu(&link->node, &link->pid->tasks[type]);} static void __change_pid(struct task_struct *task, enum pid_type type,			struct pid *new){	struct pid_link *link;	struct pid *pid;	int tmp; 	link = &task->pids[type];	pid = link->pid; 	hlist_del_rcu(&link->node);	link->pid = new; 	for (tmp = PIDTYPE_MAX; --tmp >= 0; )		if (!hlist_empty(&pid->tasks[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);} /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */void 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);} 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, pids[(type)].node);	}	return result;}EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */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 pid *get_task_pid(struct task_struct *task, enum pid_type type){	struct pid *pid;	rcu_read_lock();	if (type != PIDTYPE_PID)		task = task->group_leader;	pid = get_pid(task->pids[type].pid);	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)

Lines 1–500 of 608. Load more