1 files changed, 193 insertions, 120 deletions

diff --git a/kernel/pid.c b/kernel/pid.c
index 477691576b3..9b9a2669814 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -1,8 +1,8 @@
 /*
  * Generic pidhash and scalable, time-bounded PID allocator
  *
- * (C) 2002-2003 William Irwin, IBM
- * (C) 2004 William Irwin, Oracle
+ * (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
@@ -27,19 +27,22 @@
  */
 
 #include <linux/mm.h>
-#include <linux/module.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 int pidhash_shift;
+static unsigned int pidhash_shift = 4;
 struct pid init_struct_pid = INIT_STRUCT_PID;
 
 int pid_max = PID_MAX_DEFAULT;
@@ -49,9 +52,6 @@ int pid_max = PID_MAX_DEFAULT;
 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)
 {
@@ -75,26 +75,14 @@ struct pid_namespace init_pid_ns = {
 		[ 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,
+	.proc_inum = PROC_PID_INIT_INO,
 };
 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
  * interrupt might come in and do read_lock(&tasklist_lock).
@@ -111,15 +99,55 @@ EXPORT_SYMBOL(is_container_init);
 
 static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
 
-static void free_pidmap(struct pid_namespace *pid_ns, int pid)
+static void free_pidmap(struct upid *upid)
 {
-	struct pidmap *map = pid_ns->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);
 }
 
+/*
+ * 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;
@@ -130,7 +158,12 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
 		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;
+	/*
+	 * 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);
@@ -139,32 +172,29 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
 			 * installing it:
 			 */
 			spin_lock_irq(&pidmap_lock);
-			if (map->page)
-				kfree(page);
-			else
+			if (!map->page) {
 				map->page = page;
+				page = NULL;
+			}
 			spin_unlock_irq(&pidmap_lock);
+			kfree(page);
 			if (unlikely(!map->page))
 				break;
 		}
 		if (likely(atomic_read(&map->nr_free))) {
-			do {
+			for ( ; ; ) {
 				if (!test_and_set_bit(offset, map->page)) {
 					atomic_dec(&map->nr_free);
-					pid_ns->last_pid = pid;
+					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);
-			/*
-			 * 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 (pid >= pid_max)
+					break;
+			}
 		}
 		if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
 			++map;
@@ -180,11 +210,14 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
 	return -1;
 }
 
-int next_pidmap(struct pid_namespace *pid_ns, int last)
+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];
@@ -227,12 +260,33 @@ void free_pid(struct pid *pid)
 	unsigned long flags;
 
 	spin_lock_irqsave(&pidmap_lock, flags);
-	for (i = 0; i <= pid->level; i++)
-		hlist_del_rcu(&pid->numbers[i].pid_chain);
+	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].ns, pid->numbers[i].nr);
+		free_pidmap(pid->numbers + i);
 
 	call_rcu(&pid->rcu, delayed_put_pid);
 }
@@ -250,6 +304,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 		goto out;
 
 	tmp = ns;
+	pid->level = ns->level;
 	for (i = ns->level; i >= 0; i--) {
 		nr = alloc_pidmap(tmp);
 		if (nr < 0)
@@ -260,38 +315,53 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 		tmp = tmp->parent;
 	}
 
+	if (unlikely(is_child_reaper(pid))) {
+		if (pid_ns_prepare_proc(ns))
+			goto out_free;
+	}
+
 	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]);
 
+	upid = pid->numbers + ns->level;
 	spin_lock_irq(&pidmap_lock);
-	for (i = ns->level; i >= 0; i--) {
-		upid = &pid->numbers[i];
+	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);
 
 out:
 	return pid;
 
+out_unlock:
+	spin_unlock_irq(&pidmap_lock);
 out_free:
-	for (i++; i <= ns->level; i++)
-		free_pidmap(pid->numbers[i].ns, pid->numbers[i].nr);
+	while (++i <= ns->level)
+		free_pidmap(pid->numbers + i);
 
 	kmem_cache_free(ns->pid_cachep, pid);
 	pid = NULL;
 	goto out;
 }
 
+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 hlist_node *elem;
 	struct upid *pnr;
 
-	hlist_for_each_entry_rcu(pnr, elem,
+	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,
@@ -303,32 +373,21 @@ EXPORT_SYMBOL_GPL(find_pid_ns);
 
 struct pid *find_vpid(int nr)
 {
-	return find_pid_ns(nr, current->nsproxy->pid_ns);
+	return find_pid_ns(nr, task_active_pid_ns(current));
 }
 EXPORT_SYMBOL_GPL(find_vpid);
 
-struct pid *find_pid(int nr)
-{
-	return find_pid_ns(nr, &init_pid_ns);
-}
-EXPORT_SYMBOL_GPL(find_pid);
-
 /*
  * attach_pid() must be called with the tasklist_lock write-held.
  */
-int attach_pid(struct task_struct *task, enum pid_type type,
-		struct pid *pid)
+void attach_pid(struct task_struct *task, enum pid_type type)
 {
-	struct pid_link *link;
-
-	link = &task->pids[type];
-	link->pid = pid;
-	hlist_add_head_rcu(&link->node, &pid->tasks[type]);
-
-	return 0;
+	struct pid_link *link = &task->pids[type];
+	hlist_add_head_rcu(&link->node, &link->pid->tasks[type]);
 }
 
-void 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;
@@ -338,7 +397,7 @@ void detach_pid(struct task_struct *task, enum pid_type type)
 	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]))
@@ -347,13 +406,24 @@ void detach_pid(struct task_struct *task, enum pid_type type)
 	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);
-	old->pids[type].pid = NULL;
 }
 
 struct task_struct *pid_task(struct pid *pid, enum pid_type type)
@@ -361,7 +431,8 @@ 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);
+		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);
 	}
@@ -370,43 +441,32 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type)
 EXPORT_SYMBOL(pid_task);
 
 /*
- * Must be called under rcu_read_lock() or with tasklist_lock read-held.
+ * Must be called under rcu_read_lock().
  */
-struct task_struct *find_task_by_pid_type_ns(int type, int nr,
-		struct pid_namespace *ns)
-{
-	return pid_task(find_pid_ns(nr, ns), type);
-}
-
-EXPORT_SYMBOL(find_task_by_pid_type_ns);
-
-struct task_struct *find_task_by_pid(pid_t nr)
+struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
 {
-	return find_task_by_pid_type_ns(PIDTYPE_PID, nr, &init_pid_ns);
+	rcu_lockdep_assert(rcu_read_lock_held(),
+			   "find_task_by_pid_ns() needs rcu_read_lock()"
+			   " protection");
+	return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
 }
-EXPORT_SYMBOL(find_task_by_pid);
 
 struct task_struct *find_task_by_vpid(pid_t vnr)
 {
-	return find_task_by_pid_type_ns(PIDTYPE_PID, vnr,
-			current->nsproxy->pid_ns);
-}
-EXPORT_SYMBOL(find_task_by_vpid);
-
-struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
-{
-	return find_task_by_pid_type_ns(PIDTYPE_PID, nr, ns);
+	return find_task_by_pid_ns(vnr, task_active_pid_ns(current));
 }
-EXPORT_SYMBOL(find_task_by_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;
 }
+EXPORT_SYMBOL_GPL(get_task_pid);
 
 struct task_struct *get_pid_task(struct pid *pid, enum pid_type type)
 {
@@ -418,6 +478,7 @@ struct task_struct *get_pid_task(struct pid *pid, enum pid_type type)
 	rcu_read_unlock();
 	return result;
 }
+EXPORT_SYMBOL_GPL(get_pid_task);
 
 struct pid *find_get_pid(pid_t nr)
 {
@@ -429,6 +490,7 @@ struct pid *find_get_pid(pid_t nr)
 
 	return pid;
 }
+EXPORT_SYMBOL_GPL(find_get_pid);
 
 pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
 {
@@ -442,18 +504,32 @@ pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
 	}
 	return nr;
 }
+EXPORT_SYMBOL_GPL(pid_nr_ns);
 
 pid_t pid_vnr(struct pid *pid)
 {
-	return pid_nr_ns(pid, current->nsproxy->pid_ns);
+	return pid_nr_ns(pid, task_active_pid_ns(current));
 }
 EXPORT_SYMBOL_GPL(pid_vnr);
 
-pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
+			struct pid_namespace *ns)
 {
-	return pid_nr_ns(task_pid(tsk), ns);
+	pid_t nr = 0;
+
+	rcu_read_lock();
+	if (!ns)
+		ns = task_active_pid_ns(current);
+	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);
+EXPORT_SYMBOL(__task_pid_nr_ns);
 
 pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 {
@@ -461,22 +537,16 @@ pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 }
 EXPORT_SYMBOL(task_tgid_nr_ns);
 
-pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return pid_nr_ns(task_pgrp(tsk), ns);
-}
-EXPORT_SYMBOL(task_pgrp_nr_ns);
-
-pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
 {
-	return pid_nr_ns(task_session(tsk), ns);
+	return ns_of_pid(task_pid(tsk));
 }
-EXPORT_SYMBOL(task_session_nr_ns);
+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_namespace *ns)
 {
@@ -491,7 +561,6 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 
 	return pid;
 }
-EXPORT_SYMBOL_GPL(find_get_pid);
 
 /*
  * The pid hash table is scaled according to the amount of memory in the
@@ -500,26 +569,30 @@ EXPORT_SYMBOL_GPL(find_get_pid);
  */
 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;
+	unsigned int i, pidhash_size;
 
-	printk("PID hash table entries: %d (order: %d, %Zd bytes)\n",
-		pidhash_size, pidhash_shift,
-		pidhash_size * sizeof(struct hlist_head));
+	pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
+					   HASH_EARLY | HASH_SMALL,
+					   &pidhash_shift, NULL,
+					   0, 4096);
+	pidhash_size = 1U << pidhash_shift;
 
-	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)
 {
+	/* Veryify no one has done anything silly */
+	BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING);
+
+	/* bump default and minimum pid_max based on number of cpus */
+	pid_max = min(pid_max_max, max_t(int, pid_max,
+				PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
+	pid_max_min = max_t(int, pid_max_min,
+				PIDS_PER_CPU_MIN * num_possible_cpus());
+	pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min);
+
 	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);