X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=kernel%2Fpid.c;h=07c5d91e1ab30aa80e9ac3c4833946bf185440b2;hb=refs%2Fheads%2Fvserver;hp=6ed44f56ca456f91d2e1a941043a8628091d8f98;hpb=5273a3df6485dc2ad6aa7ddd441b9a21970f003b;p=linux-2.6.git

diff --git a/kernel/pid.c b/kernel/pid.c
index 6ed44f56c..07c5d91e1 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -1,8 +1,9 @@
 /*
  * Generic pidhash and scalable, time-bounded PID allocator
  *
- * (C) 2002 William Irwin, IBM
- * (C) 2002 Ingo Molnar, Red Hat
+ * (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
@@ -25,242 +26,372 @@
 #include <linux/init.h>
 #include <linux/bootmem.h>
 #include <linux/hash.h>
+#include <linux/pid_namespace.h>
+#include <linux/vs_pid.h>
 
 #define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift)
-static struct list_head *pid_hash[PIDTYPE_MAX];
+static struct hlist_head *pid_hash;
 static int pidhash_shift;
+static struct kmem_cache *pid_cachep;
 
 int pid_max = PID_MAX_DEFAULT;
-int last_pid;
 
 #define RESERVED_PIDS		300
 
-#define PIDMAP_ENTRIES		(PID_MAX_LIMIT/PAGE_SIZE/8)
+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.
  */
-typedef struct pidmap {
-	atomic_t nr_free;
-	void *page;
-} pidmap_t;
-
-static pidmap_t pidmap_array[PIDMAP_ENTRIES] =
-	 { [ 0 ... PIDMAP_ENTRIES-1 ] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } };
+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,
+	.child_reaper = &init_task
+};
 
-static pidmap_t *map_limit = pidmap_array + PIDMAP_ENTRIES;
+/*
+ * 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 spinlock_t pidmap_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;
+static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
 
-fastcall void free_pidmap(int pid)
+static fastcall void free_pidmap(struct pid_namespace *pid_ns, int pid)
 {
-	pidmap_t *map = pidmap_array + pid / BITS_PER_PAGE;
+	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);
 }
 
-/*
- * Here we search for the next map that has free bits left.
- * Normally the next map has free PIDs.
- */
-static inline pidmap_t *next_free_map(pidmap_t *map, int *max_steps)
+static int alloc_pidmap(struct pid_namespace *pid_ns)
 {
-	while (--*max_steps) {
-		if (++map == map_limit)
-			map = pidmap_array;
+	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)) {
-			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);
-
-			if (!map->page)
+				map->page = page;
+			spin_unlock_irq(&pidmap_lock);
+			if (unlikely(!map->page))
 				break;
 		}
-		if (atomic_read(&map->nr_free))
-			return map;
+		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 NULL;
+	return -1;
 }
 
-int alloc_pidmap(void)
+static int next_pidmap(struct pid_namespace *pid_ns, int last)
 {
-	int pid, offset, max_steps = PIDMAP_ENTRIES + 1;
-	pidmap_t *map;
-
-	pid = last_pid + 1;
-	if (pid >= pid_max)
-		pid = RESERVED_PIDS;
-
-	offset = pid & BITS_PER_PAGE_MASK;
-	map = pidmap_array + pid / BITS_PER_PAGE;
-
-	if (likely(map->page && !test_and_set_bit(offset, map->page))) {
-		/*
-		 * There is a small window for last_pid updates to race,
-		 * but in that case the next allocation will go into the
-		 * slowpath and that fixes things up.
-		 */
-return_pid:
-		atomic_dec(&map->nr_free);
-		last_pid = pid;
-		return pid;
-	}
-	
-	if (!offset || !atomic_read(&map->nr_free)) {
-next_map:
-		map = next_free_map(map, &max_steps);
-		if (!map)
-			goto failure;
-		offset = 0;
+	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);
 	}
-	/*
-	 * Find the next zero bit:
-	 */
-scan_more:
-	offset = find_next_zero_bit(map->page, BITS_PER_PAGE, offset);
-	if (offset >= BITS_PER_PAGE)
-		goto next_map;
-	if (test_and_set_bit(offset, map->page))
-		goto scan_more;
-
-	/* we got the PID: */
-	pid = (map - pidmap_array) * BITS_PER_PAGE + offset;
-	goto return_pid;
-
-failure:
 	return -1;
 }
 
-fastcall struct pid *find_pid(enum pid_type type, int nr)
+fastcall void put_pid(struct pid *pid)
+{
+	if (!pid)
+		return;
+	if ((atomic_read(&pid->count) == 1) ||
+	     atomic_dec_and_test(&pid->count))
+		kmem_cache_free(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 list_head *elem, *bucket = &pid_hash[type][pid_hashfn(nr)];
 	struct pid *pid;
+	enum pid_type type;
+	int nr = -1;
+
+	pid = kmem_cache_alloc(pid_cachep, GFP_KERNEL);
+	if (!pid)
+		goto out;
+
+	nr = alloc_pidmap(current->nsproxy->pid_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(pid_cachep, pid);
+	pid = NULL;
+	goto out;
+}
 
-	__list_for_each(elem, bucket) {
-		pid = list_entry(elem, struct pid, hash_chain);
+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);
 
-void fastcall link_pid(task_t *task, struct pid_link *link, struct pid *pid)
+int fastcall attach_pid(struct task_struct *task, enum pid_type type, int nr)
 {
-	atomic_inc(&pid->count);
-	list_add_tail(&link->pid_chain, &pid->task_list);
-	link->pidptr = pid;
-}
+	struct pid_link *link;
+	struct pid *pid;
 
-int fastcall attach_pid(task_t *task, enum pid_type type, int nr)
-{
-	struct pid *pid = find_pid(type, nr);
-
-	if (pid)
-		atomic_inc(&pid->count);
-	else {
-		pid = &task->pids[type].pid;
-		pid->nr = nr;
-		atomic_set(&pid->count, 1);
-		INIT_LIST_HEAD(&pid->task_list);
-		pid->task = task;
-		get_task_struct(task);
-		list_add(&pid->hash_chain, &pid_hash[type][pid_hashfn(nr)]);
-	}
-	list_add_tail(&task->pids[type].pid_chain, &pid->task_list);
-	task->pids[type].pidptr = pid;
+	link = &task->pids[type];
+	link->pid = pid = find_pid(nr);
+	hlist_add_head_rcu(&link->node, &pid->tasks[type]);
 
 	return 0;
 }
 
-static inline int __detach_pid(task_t *task, enum pid_type type)
+void fastcall detach_pid(struct task_struct *task, enum pid_type type)
 {
-	struct pid_link *link = task->pids + type;
-	struct pid *pid = link->pidptr;
-	int nr;
+	struct pid_link *link;
+	struct pid *pid;
+	int tmp;
 
-	list_del(&link->pid_chain);
-	if (!atomic_dec_and_test(&pid->count))
-		return 0;
+	link = &task->pids[type];
+	pid = link->pid;
+
+	hlist_del_rcu(&link->node);
+	link->pid = NULL;
 
-	nr = pid->nr;
-	list_del(&pid->hash_chain);
-	put_task_struct(pid->task);
+	for (tmp = PIDTYPE_MAX; --tmp >= 0; )
+		if (!hlist_empty(&pid->tasks[tmp]))
+			return;
+
+	free_pid(pid);
+}
 
-	return nr;
+/* 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;
 }
 
-static void _detach_pid(task_t *task, enum pid_type type)
+struct task_struct * fastcall pid_task(struct pid *pid, enum pid_type type)
 {
-	__detach_pid(task, type);
+	struct task_struct *result = NULL;
+
+	if (type == PIDTYPE_REALPID)
+		type = PIDTYPE_PID;
+	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;
 }
 
-void fastcall detach_pid(task_t *task, enum pid_type type)
+/*
+ * 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)
 {
-	int nr = __detach_pid(task, type);
+	struct task_struct *task;
 
-	if (!nr)
-		return;
+	if (type == PIDTYPE_PID)
+		nr = vx_rmap_pid(nr);
 
-	for (type = 0; type < PIDTYPE_MAX; ++type)
-		if (find_pid(type, nr))
-			return;
-	free_pidmap(nr);
+	task = pid_task(find_pid(nr), type);
+	if (task && (type != PIDTYPE_REALPID) &&
+		/* maybe VS_WATCH_P in the future? */
+		!vx_check(task->xid, VS_WATCH|VS_IDENT))
+		return NULL;
+	return task;
 }
 
-task_t *find_task_by_pid(int nr)
+EXPORT_SYMBOL(find_task_by_pid_type);
+
+struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
 {
-	struct pid *pid = find_pid(PIDTYPE_PID, nr);
+	struct pid *pid;
+	rcu_read_lock();
+	pid = get_pid(task->pids[type].pid);
+	rcu_read_unlock();
+	return pid;
+}
 
-	if (!pid)
-		return NULL;
-	return pid_task(pid->task_list.next, PIDTYPE_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;
 }
 
-EXPORT_SYMBOL(find_task_by_pid);
+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;
+}
 
 /*
- * This function switches the PIDs if a non-leader thread calls
- * sys_execve() - this must be done without releasing the PID.
- * (which a detach_pid() would eventually do.)
+ * 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.
  */
-void switch_exec_pids(task_t *leader, task_t *thread)
+struct pid *find_ge_pid(int nr)
 {
-	_detach_pid(leader, PIDTYPE_PID);
-	_detach_pid(leader, PIDTYPE_TGID);
-	_detach_pid(leader, PIDTYPE_PGID);
-	_detach_pid(leader, PIDTYPE_SID);
-
-	_detach_pid(thread, PIDTYPE_PID);
-	_detach_pid(thread, PIDTYPE_TGID);
-
-	leader->pid = leader->tgid = thread->pid;
-	thread->pid = thread->tgid;
-
-	attach_pid(thread, PIDTYPE_PID, thread->pid);
-	attach_pid(thread, PIDTYPE_TGID, thread->tgid);
-	attach_pid(thread, PIDTYPE_PGID, thread->signal->pgrp);
-	attach_pid(thread, PIDTYPE_SID, thread->signal->session);
-	list_add_tail(&thread->tasks, &init_task.tasks);
-
-	attach_pid(leader, PIDTYPE_PID, leader->pid);
-	attach_pid(leader, PIDTYPE_TGID, leader->tgid);
-	attach_pid(leader, PIDTYPE_PGID, leader->signal->pgrp);
-	attach_pid(leader, PIDTYPE_SID, leader->signal->session);
+	struct pid *pid;
+
+	do {
+		pid = find_pid(nr);
+		if (pid)
+			break;
+		nr = next_pidmap(current->nsproxy->pid_ns, nr);
+	} while (nr > 0);
+
+	return pid;
+}
+EXPORT_SYMBOL_GPL(find_get_pid);
+
+int copy_pid_ns(int flags, struct task_struct *tsk)
+{
+	struct pid_namespace *old_ns = tsk->nsproxy->pid_ns;
+	int err = 0;
+
+	if (!old_ns)
+		return 0;
+
+	get_pid_ns(old_ns);
+	return err;
+}
+
+void free_pid_ns(struct kref *kref)
+{
+	struct pid_namespace *ns;
+
+	ns = container_of(kref, struct pid_namespace, kref);
+	kfree(ns);
 }
 
 /*
@@ -270,39 +401,32 @@ void switch_exec_pids(task_t *leader, task_t *thread)
  */
 void __init pidhash_init(void)
 {
-	int i, j, pidhash_size;
-	unsigned long megabytes = max_pfn >> (20 - PAGE_SHIFT);
+	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",
+	printk("PID hash table entries: %d (order: %d, %Zd bytes)\n",
 		pidhash_size, pidhash_shift,
-		pidhash_size * sizeof(struct list_head));
-
-	for (i = 0; i < PIDTYPE_MAX; i++) {
-		pid_hash[i] = alloc_bootmem(pidhash_size *
-					sizeof(struct list_head));
-		if (!pid_hash[i])
-			panic("Could not alloc pidhash!\n");
-		for (j = 0; j < pidhash_size; j++)
-			INIT_LIST_HEAD(&pid_hash[i][j]);
-	}
+		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)
 {
-	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:
-	 */
-
-	for (i = 0; i < PIDTYPE_MAX; i++)
-		attach_pid(current, i, 0);
+	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);
+
+	pid_cachep = kmem_cache_create("pid", sizeof(struct pid),
+					__alignof__(struct pid),
+					SLAB_PANIC, NULL, NULL);
 }