* 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/module.h>
#include <linux/slab.h>
#include <linux/init.h>
+#include <linux/rculist.h>
#include <linux/bootmem.h>
#include <linux/hash.h>
-#include <linux/pspace.h>
+#include <linux/pid_namespace.h>
+#include <linux/init_task.h>
+#include <linux/syscalls.h>
-#define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift)
+#define pid_hashfn(nr, ns) \
+ hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
static struct hlist_head *pid_hash;
static int pidhash_shift;
-static kmem_cache_t *pid_cachep;
+struct pid init_struct_pid = INIT_STRUCT_PID;
int pid_max = PID_MAX_DEFAULT;
#define BITS_PER_PAGE (PAGE_SIZE*8)
#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1)
-static inline int mk_pid(struct pspace *pspace, struct pidmap *map, int off)
+static inline int mk_pid(struct pid_namespace *pid_ns,
+ struct pidmap *map, int off)
{
- return (map - pspace->pidmap)*BITS_PER_PAGE + off;
+ return (map - pid_ns->pidmap)*BITS_PER_PAGE + off;
}
#define find_next_offset(map, off) \
* value does not cause lots of bitmaps to be allocated, but
* the scheme scales to up to 4 million PIDs, runtime.
*/
-struct pspace init_pspace = {
+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
+ .last_pid = 0,
+ .level = 0,
+ .child_reaper = &init_task,
};
+EXPORT_SYMBOL_GPL(init_pid_ns);
+
+int is_container_init(struct task_struct *tsk)
+{
+ int ret = 0;
+ struct pid *pid;
+
+ rcu_read_lock();
+ pid = task_pid(tsk);
+ if (pid != NULL && pid->numbers[pid->level].nr == 1)
+ ret = 1;
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(is_container_init);
/*
* Note: disable interrupts while the pidmap_lock is held as an
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
-static fastcall void free_pidmap(struct pspace *pspace, int pid)
+static void free_pidmap(struct upid *upid)
{
- struct pidmap *map = pspace->pidmap + pid / BITS_PER_PAGE;
- int offset = pid & BITS_PER_PAGE_MASK;
+ 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);
}
-static int alloc_pidmap(struct pspace *pspace)
+static int alloc_pidmap(struct pid_namespace *pid_ns)
{
- int i, offset, max_scan, pid, last = pspace->last_pid;
+ 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 = &pspace->pidmap[pid/BITS_PER_PAGE];
+ 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)) {
do {
if (!test_and_set_bit(offset, map->page)) {
atomic_dec(&map->nr_free);
- pspace->last_pid = pid;
+ pid_ns->last_pid = pid;
return pid;
}
offset = find_next_offset(map, offset);
- pid = mk_pid(pspace, 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
(i != max_scan || pid < last ||
!((last+1) & BITS_PER_PAGE_MASK)));
}
- if (map < &pspace->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
+ if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
++map;
offset = 0;
} else {
- map = &pspace->pidmap[0];
+ map = &pid_ns->pidmap[0];
offset = RESERVED_PIDS;
if (unlikely(last == offset))
break;
}
- pid = mk_pid(pspace, map, offset);
+ pid = mk_pid(pid_ns, map, offset);
}
return -1;
}
-static int next_pidmap(struct pspace *pspace, int last)
+int next_pidmap(struct pid_namespace *pid_ns, int last)
{
int offset;
struct pidmap *map, *end;
offset = (last + 1) & BITS_PER_PAGE_MASK;
- map = &pspace->pidmap[(last + 1)/BITS_PER_PAGE];
- end = &pspace->pidmap[PIDMAP_ENTRIES];
+ 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(pspace, map, offset);
+ return mk_pid(pid_ns, map, offset);
}
return -1;
}
-fastcall void put_pid(struct pid *pid)
+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(pid_cachep, pid);
+ atomic_dec_and_test(&pid->count)) {
+ kmem_cache_free(ns->pid_cachep, pid);
+ put_pid_ns(ns);
+ }
}
EXPORT_SYMBOL_GPL(put_pid);
put_pid(pid);
}
-fastcall void free_pid(struct 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);
- hlist_del_rcu(&pid->pid_chain);
+ for (i = 0; i <= pid->level; i++)
+ hlist_del_rcu(&pid->numbers[i].pid_chain);
spin_unlock_irqrestore(&pidmap_lock, flags);
- free_pidmap(&init_pspace, pid->nr);
+ for (i = 0; i <= pid->level; i++)
+ free_pidmap(pid->numbers + i);
+
call_rcu(&pid->rcu, delayed_put_pid);
}
-struct pid *alloc_pid(void)
+struct pid *alloc_pid(struct pid_namespace *ns)
{
struct pid *pid;
enum pid_type type;
- int nr = -1;
+ int i, nr;
+ struct pid_namespace *tmp;
+ struct upid *upid;
- pid = kmem_cache_alloc(pid_cachep, GFP_KERNEL);
+ pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
if (!pid)
goto out;
- nr = alloc_pidmap(&init_pspace);
- if (nr < 0)
- goto out_free;
+ tmp = ns;
+ for (i = ns->level; i >= 0; i--) {
+ nr = alloc_pidmap(tmp);
+ if (nr < 0)
+ goto out_free;
+ pid->numbers[i].nr = nr;
+ pid->numbers[i].ns = tmp;
+ tmp = tmp->parent;
+ }
+
+ get_pid_ns(ns);
+ pid->level = ns->level;
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)]);
+ for (i = ns->level; i >= 0; i--) {
+ upid = &pid->numbers[i];
+ hlist_add_head_rcu(&upid->pid_chain,
+ &pid_hash[pid_hashfn(upid->nr, upid->ns)]);
+ }
spin_unlock_irq(&pidmap_lock);
out:
return pid;
out_free:
- kmem_cache_free(pid_cachep, pid);
+ while (++i <= ns->level)
+ free_pidmap(pid->numbers + i);
+
+ kmem_cache_free(ns->pid_cachep, pid);
pid = NULL;
goto out;
}
-struct pid * fastcall find_pid(int nr)
+struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
struct hlist_node *elem;
- struct pid *pid;
+ struct upid *pnr;
+
+ hlist_for_each_entry_rcu(pnr, elem,
+ &pid_hash[pid_hashfn(nr, ns)], pid_chain)
+ if (pnr->nr == nr && pnr->ns == ns)
+ return container_of(pnr, struct pid,
+ numbers[ns->level]);
- 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);
+EXPORT_SYMBOL_GPL(find_pid_ns);
-int fastcall attach_pid(struct task_struct *task, enum pid_type type, int nr)
+struct pid *find_vpid(int nr)
+{
+ return find_pid_ns(nr, current->nsproxy->pid_ns);
+}
+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 *pid)
{
struct pid_link *link;
- struct pid *pid;
link = &task->pids[type];
- link->pid = pid = find_pid(nr);
+ 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)
+static void __change_pid(struct task_struct *task, enum pid_type type,
+ struct pid *new)
{
struct pid_link *link;
struct pid *pid;
pid = link->pid;
hlist_del_rcu(&link->node);
- link->pid = NULL;
+ link->pid = new;
for (tmp = PIDTYPE_MAX; --tmp >= 0; )
if (!hlist_empty(&pid->tasks[tmp]))
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, 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,
+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);
- old->pids[type].pid = NULL;
}
-struct task_struct * fastcall pid_task(struct pid *pid, enum pid_type type)
+struct task_struct *pid_task(struct pid *pid, enum pid_type type)
{
struct task_struct *result = NULL;
if (pid) {
}
return result;
}
+EXPORT_SYMBOL(pid_task);
/*
* 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)
+struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
{
- return pid_task(find_pid(nr), type);
+ return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
}
-EXPORT_SYMBOL(find_task_by_pid_type);
+struct task_struct *find_task_by_vpid(pid_t vnr)
+{
+ return find_task_by_pid_ns(vnr, current->nsproxy->pid_ns);
+}
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;
}
-struct task_struct *fastcall get_pid_task(struct pid *pid, enum pid_type type)
+struct task_struct *get_pid_task(struct pid *pid, enum pid_type type)
{
struct task_struct *result;
rcu_read_lock();
struct pid *pid;
rcu_read_lock();
- pid = get_pid(find_pid(nr));
+ 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;
+}
+
+pid_t pid_vnr(struct pid *pid)
+{
+ return pid_nr_ns(pid, current->nsproxy->pid_ns);
+}
+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 = current->nsproxy->pid_ns;
+ if (likely(pid_alive(task))) {
+ if (type != PIDTYPE_PID)
+ task = task->group_leader;
+ nr = pid_nr_ns(task->pids[type].pid, ns);
+ }
+ rcu_read_unlock();
+
+ return nr;
+}
+EXPORT_SYMBOL(__task_pid_nr_ns);
+
+pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+ return pid_nr_ns(task_tgid(tsk), ns);
+}
+EXPORT_SYMBOL(task_tgid_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);
/*
- * Used by proc to find the first pid that is greater then or equal to nr.
+ * Used by proc to find the first pid that is greater than or equal to nr.
*
- * If there is a pid at nr this function is exactly the same as find_pid.
+ * If there is a pid at nr this function is exactly the same as find_pid_ns.
*/
-struct pid *find_ge_pid(int nr)
+struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
{
struct pid *pid;
do {
- pid = find_pid(nr);
+ pid = find_pid_ns(nr, ns);
if (pid)
break;
- nr = next_pidmap(&init_pspace, nr);
+ nr = next_pidmap(ns, nr);
} while (nr > 0);
return pid;
}
-EXPORT_SYMBOL_GPL(find_get_pid);
/*
* The pid hash table is scaled according to the amount of memory in the
void __init pidmap_init(void)
{
- init_pspace.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+ init_pid_ns.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
/* Reserve PID 0. We never call free_pidmap(0) */
- set_bit(0, init_pspace.pidmap[0].page);
- atomic_dec(&init_pspace.pidmap[0].nr_free);
+ set_bit(0, init_pid_ns.pidmap[0].page);
+ atomic_dec(&init_pid_ns.pidmap[0].nr_free);
- pid_cachep = kmem_cache_create("pid", sizeof(struct pid),
- __alignof__(struct pid),
- SLAB_PANIC, NULL, NULL);
+ init_pid_ns.pid_cachep = KMEM_CACHE(pid,
+ SLAB_HWCACHE_ALIGN | SLAB_PANIC);
}