X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fpid.c;h=d3f722d20f9c6e8d849693a1754b616d3ba74bea;hb=608221fdf9a2170962295dcfbea53dc5c50d1a74;hp=7781d9999058337f12618910b81cea8c0ee1c0f0;hpb=d73d65293e3e2de7e916a89c8da30be0948afab7;p=safe%2Fjmp%2Flinux-2.6

diff --git a/kernel/pid.c b/kernel/pid.c
index 7781d99..d3f722d 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -18,31 +18,47 @@
  * 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/pid_namespace.h>
+#include <linux/init_task.h>
+#include <linux/syscalls.h>
 
-#define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift)
-static struct hlist_head *pid_hash[PIDTYPE_MAX];
-static int pidhash_shift;
+#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;
-int last_pid;
 
 #define RESERVED_PIDS		300
 
 int pid_max_min = RESERVED_PIDS + 1;
 int pid_max_max = PID_MAX_LIMIT;
 
-#define PIDMAP_ENTRIES		((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8)
 #define BITS_PER_PAGE		(PAGE_SIZE*8)
 #define BITS_PER_PAGE_MASK	(BITS_PER_PAGE-1)
-#define mk_pid(map, off)	(((map) - pidmap_array)*BITS_PER_PAGE + (off))
+
+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)
 
@@ -52,49 +68,84 @@ int pid_max_max = PID_MAX_LIMIT;
  * value does not cause lots of bitmaps to be allocated, but
  * the scheme scales to up to 4 million PIDs, runtime.
  */
-typedef struct pidmap {
-	atomic_t nr_free;
-	void *page;
-} pidmap_t;
+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,
+};
+EXPORT_SYMBOL_GPL(init_pid_ns);
+
+int is_container_init(struct task_struct *tsk)
+{
+	int ret = 0;
+	struct pid *pid;
 
-static pidmap_t pidmap_array[PIDMAP_ENTRIES] =
-	 { [ 0 ... PIDMAP_ENTRIES-1 ] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } };
+	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
+ * 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);
 
-fastcall void free_pidmap(int pid)
+static void free_pidmap(struct upid *upid)
 {
-	pidmap_t *map = pidmap_array + 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);
 }
 
-int alloc_pidmap(void)
+static int alloc_pidmap(struct pid_namespace *pid_ns)
 {
-	int i, offset, max_scan, pid, last = last_pid;
-	pidmap_t *map;
+	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 = &pidmap_array[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)) {
-			unsigned long page = get_zeroed_page(GFP_KERNEL);
+			void *page = kzalloc(PAGE_SIZE, GFP_KERNEL);
 			/*
 			 * Free the page if someone raced with us
 			 * installing it:
 			 */
-			spin_lock(&pidmap_lock);
+			spin_lock_irq(&pidmap_lock);
 			if (map->page)
-				free_page(page);
+				kfree(page);
 			else
-				map->page = (void *)page;
-			spin_unlock(&pidmap_lock);
+				map->page = page;
+			spin_unlock_irq(&pidmap_lock);
 			if (unlikely(!map->page))
 				break;
 		}
@@ -102,11 +153,11 @@ int alloc_pidmap(void)
 			do {
 				if (!test_and_set_bit(offset, map->page)) {
 					atomic_dec(&map->nr_free);
-					last_pid = pid;
+					pid_ns->last_pid = pid;
 					return pid;
 				}
 				offset = find_next_offset(map, offset);
-				pid = mk_pid(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
@@ -117,105 +168,328 @@ int alloc_pidmap(void)
 					(i != max_scan || pid < last ||
 					    !((last+1) & BITS_PER_PAGE_MASK)));
 		}
-		if (map < &pidmap_array[(pid_max-1)/BITS_PER_PAGE]) {
+		if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
 			++map;
 			offset = 0;
 		} else {
-			map = &pidmap_array[0];
+			map = &pid_ns->pidmap[0];
 			offset = RESERVED_PIDS;
 			if (unlikely(last == offset))
 				break;
 		}
-		pid = mk_pid(map, offset);
+		pid = mk_pid(pid_ns, map, offset);
 	}
 	return -1;
 }
 
-struct pid * fastcall find_pid(enum pid_type type, int nr)
+int next_pidmap(struct pid_namespace *pid_ns, int last)
 {
-	struct hlist_node *elem;
-	struct pid *pid;
-
-	hlist_for_each_entry_rcu(pid, elem,
-			&pid_hash[type][pid_hashfn(nr)], pid_chain) {
-		if (pid->nr == nr)
-			return pid;
+	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 NULL;
+	return -1;
 }
 
-int fastcall attach_pid(task_t *task, enum pid_type type, int nr)
+void put_pid(struct pid *pid)
 {
-	struct pid *pid, *task_pid;
-
-	task_pid = &task->pids[type];
-	pid = find_pid(type, nr);
-	task_pid->nr = nr;
-	if (pid == NULL) {
-		INIT_LIST_HEAD(&task_pid->pid_list);
-		hlist_add_head_rcu(&task_pid->pid_chain,
-				   &pid_hash[type][pid_hashfn(nr)]);
-	} else {
-		INIT_HLIST_NODE(&task_pid->pid_chain);
-		list_add_tail_rcu(&task_pid->pid_list, &pid->pid_list);
+	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);
 
-	return 0;
+static void delayed_put_pid(struct rcu_head *rhp)
+{
+	struct pid *pid = container_of(rhp, struct pid, rcu);
+	put_pid(pid);
 }
 
-static fastcall int __detach_pid(task_t *task, enum pid_type type)
+void free_pid(struct pid *pid)
 {
-	struct pid *pid, *pid_next;
-	int nr = 0;
+	/* We can be called with write_lock_irq(&tasklist_lock) held */
+	int i;
+	unsigned long flags;
 
-	pid = &task->pids[type];
-	if (!hlist_unhashed(&pid->pid_chain)) {
+	spin_lock_irqsave(&pidmap_lock, flags);
+	for (i = 0; i <= pid->level; i++)
+		hlist_del_rcu(&pid->numbers[i].pid_chain);
+	spin_unlock_irqrestore(&pidmap_lock, flags);
 
-		if (list_empty(&pid->pid_list)) {
-			nr = pid->nr;
-			hlist_del_rcu(&pid->pid_chain);
-		} else {
-			pid_next = list_entry(pid->pid_list.next,
-						struct pid, pid_list);
-			/* insert next pid from pid_list to hash */
-			hlist_replace_rcu(&pid->pid_chain,
-					  &pid_next->pid_chain);
-		}
+	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;
+
+	pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
+	if (!pid)
+		goto out;
+
+	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);
+	for (type = 0; type < PIDTYPE_MAX; ++type)
+		INIT_HLIST_HEAD(&pid->tasks[type]);
+
+	spin_lock_irq(&pidmap_lock);
+	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);
 
-	list_del_rcu(&pid->pid_list);
-	pid->nr = 0;
+out:
+	return pid;
 
-	return nr;
+out_free:
+	while (++i <= ns->level)
+		free_pidmap(pid->numbers + i);
+
+	kmem_cache_free(ns->pid_cachep, pid);
+	pid = NULL;
+	goto out;
 }
 
-void fastcall detach_pid(task_t *task, enum pid_type type)
+struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
 {
-	int tmp, nr;
+	struct hlist_node *elem;
+	struct upid *pnr;
 
-	nr = __detach_pid(task, type);
-	if (!nr)
-		return;
+	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]);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(find_pid_ns);
+
+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;
+
+	link = &task->pids[type];
+	link->pid = pid;
+	hlist_add_head_rcu(&link->node, &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 (tmp != type && find_pid(tmp, nr))
+		if (!hlist_empty(&pid->tasks[tmp]))
 			return;
 
-	free_pidmap(nr);
+	free_pid(pid);
 }
 
-task_t *find_task_by_pid_type(int type, int nr)
+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 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(pid->tasks[type].first);
+		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() or with tasklist_lock read-held.
+ */
+struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
+{
+	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, 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;
+}
 
-	pid = find_pid(type, nr);
-	if (!pid)
-		return NULL;
+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;
+}
 
-	return pid_task(&pid->pid_list, type);
+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);
 
-EXPORT_SYMBOL(find_task_by_pid_type);
+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 than or equal to nr.
+ *
+ * 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_namespace *ns)
+{
+	struct pid *pid;
+
+	do {
+		pid = find_pid_ns(nr, ns);
+		if (pid)
+			break;
+		nr = next_pidmap(ns, nr);
+	} while (nr > 0);
+
+	return pid;
+}
 
 /*
  * The pid hash table is scaled according to the amount of memory in the
@@ -224,39 +498,24 @@ EXPORT_SYMBOL(find_task_by_pid_type);
  */
 void __init pidhash_init(void)
 {
-	int i, j, pidhash_size;
-	unsigned long megabytes = nr_kernel_pages >> (20 - PAGE_SHIFT);
+	int i, pidhash_size;
 
-	pidhash_shift = max(4, fls(megabytes * 4));
-	pidhash_shift = min(12, pidhash_shift);
+	pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
+					   HASH_EARLY | HASH_SMALL,
+					   &pidhash_shift, NULL, 4096);
 	pidhash_size = 1 << pidhash_shift;
 
-	printk("PID hash table entries: %d (order: %d, %Zd bytes)\n",
-		pidhash_size, pidhash_shift,
-		PIDTYPE_MAX * pidhash_size * sizeof(struct hlist_head));
-
-	for (i = 0; i < PIDTYPE_MAX; i++) {
-		pid_hash[i] = alloc_bootmem(pidhash_size *
-					sizeof(*(pid_hash[i])));
-		if (!pid_hash[i])
-			panic("Could not alloc pidhash!\n");
-		for (j = 0; j < pidhash_size; j++)
-			INIT_HLIST_HEAD(&pid_hash[i][j]);
-	}
+	for (i = 0; i < pidhash_size; i++)
+		INIT_HLIST_HEAD(&pid_hash[i]);
 }
 
 void __init pidmap_init(void)
 {
-	int i;
-
-	pidmap_array->page = (void *)get_zeroed_page(GFP_KERNEL);
-	set_bit(0, pidmap_array->page);
-	atomic_dec(&pidmap_array->nr_free);
-
-	/*
-	 * Allocate PID 0, and hash it via all PID types:
-	 */
+	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);
 
-	for (i = 0; i < PIDTYPE_MAX; i++)
-		attach_pid(current, i, 0);
+	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
+			SLAB_HWCACHE_ALIGN | SLAB_PANIC);
 }