1 files changed, 114 insertions, 65 deletions

diff --git a/kernel/pid.c b/kernel/pid.c
index a31771bc89c1..fd5c2d4aa349 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -43,7 +43,6 @@
 #include <linux/sched/task.h>
 #include <linux/idr.h>
 #include <linux/pidfs.h>
-#include <linux/seqlock.h>
 #include <net/sock.h>
 #include <uapi/linux/pidfd.h>
 
@@ -85,7 +84,6 @@ struct pid_namespace init_pid_ns = {
 EXPORT_SYMBOL_GPL(init_pid_ns);
 
 static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
-seqcount_spinlock_t pidmap_lock_seq = SEQCNT_SPINLOCK_ZERO(pidmap_lock_seq, &pidmap_lock);
 
 void put_pid(struct pid *pid)
 {
@@ -130,20 +128,19 @@ void free_pid(struct pid *pid)
 			 * is the reaper wake up the reaper.  The reaper
 			 * may be sleeping in zap_pid_ns_processes().
 			 */
-			wake_up_process(ns->child_reaper);
+			wake_up_process(READ_ONCE(ns->child_reaper));
 			break;
 		case PIDNS_ADDING:
-			/* Handle a fork failure of the first process */
-			WARN_ON(ns->child_reaper);
-			ns->pid_allocated = 0;
+			/* Only possible if the 1st fork fails */
+			WARN_ON(READ_ONCE(ns->child_reaper));
 			break;
 		}
 
 		idr_remove(&ns->idr, upid->nr);
 	}
-	pidfs_remove_pid(pid);
 	spin_unlock(&pidmap_lock);
 
+	pidfs_remove_pid(pid);
 	call_rcu(&pid->rcu, delayed_put_pid);
 }
 
@@ -159,58 +156,85 @@ void free_pids(struct pid **pids)
 			free_pid(pids[tmp]);
 }
 
-struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
-		      size_t set_tid_size)
+struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid,
+		      size_t arg_set_tid_size)
 {
+	int set_tid[MAX_PID_NS_LEVEL + 1] = {};
+	int pid_max[MAX_PID_NS_LEVEL + 1] = {};
 	struct pid *pid;
 	enum pid_type type;
 	int i, nr;
 	struct pid_namespace *tmp;
 	struct upid *upid;
 	int retval = -ENOMEM;
+	bool retried_preload;
 
 	/*
-	 * set_tid_size contains the size of the set_tid array. Starting at
+	 * arg_set_tid_size contains the size of the arg_set_tid array. Starting at
 	 * the most nested currently active PID namespace it tells alloc_pid()
 	 * which PID to set for a process in that most nested PID namespace
-	 * up to set_tid_size PID namespaces. It does not have to set the PID
-	 * for a process in all nested PID namespaces but set_tid_size must
+	 * up to arg_set_tid_size PID namespaces. It does not have to set the PID
+	 * for a process in all nested PID namespaces but arg_set_tid_size must
 	 * never be greater than the current ns->level + 1.
 	 */
-	if (set_tid_size > ns->level + 1)
+	if (arg_set_tid_size > ns->level + 1)
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * Prep before we take locks:
+	 *
+	 * 1. allocate and fill in pid struct
+	 */
 	pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
 	if (!pid)
 		return ERR_PTR(retval);
 
-	tmp = ns;
+	get_pid_ns(ns);
 	pid->level = ns->level;
+	refcount_set(&pid->count, 1);
+	spin_lock_init(&pid->lock);
+	for (type = 0; type < PIDTYPE_MAX; ++type)
+		INIT_HLIST_HEAD(&pid->tasks[type]);
+	init_waitqueue_head(&pid->wait_pidfd);
+	INIT_HLIST_HEAD(&pid->inodes);
+	pidfs_prepare_pid(pid);
 
-	for (i = ns->level; i >= 0; i--) {
-		int tid = 0;
-		int pid_max = READ_ONCE(tmp->pid_max);
+	/*
+	 * 2. perm check checkpoint_restore_ns_capable()
+	 *
+	 * This stores found pid_max to make sure the used value is the same should
+	 * later code need it.
+	 */
+	for (tmp = ns, i = ns->level; i >= 0; i--) {
+		pid_max[ns->level - i] = READ_ONCE(tmp->pid_max);
 
-		if (set_tid_size) {
-			tid = set_tid[ns->level - i];
+		if (arg_set_tid_size) {
+			int tid = set_tid[ns->level - i] = arg_set_tid[ns->level - i];
 
 			retval = -EINVAL;
-			if (tid < 1 || tid >= pid_max)
-				goto out_free;
-			/*
-			 * Also fail if a PID != 1 is requested and
-			 * no PID 1 exists.
-			 */
-			if (tid != 1 && !tmp->child_reaper)
-				goto out_free;
+			if (tid < 1 || tid >= pid_max[ns->level - i])
+				goto out_abort;
 			retval = -EPERM;
 			if (!checkpoint_restore_ns_capable(tmp->user_ns))
-				goto out_free;
-			set_tid_size--;
+				goto out_abort;
+			arg_set_tid_size--;
 		}
 
-		idr_preload(GFP_KERNEL);
-		spin_lock(&pidmap_lock);
+		tmp = tmp->parent;
+	}
+
+	/*
+	 * Prep is done, id allocation goes here:
+	 */
+	retried_preload = false;
+	idr_preload(GFP_KERNEL);
+	spin_lock(&pidmap_lock);
+	/* For the case when the previous attempt to create init failed */
+	if (ns->pid_allocated == PIDNS_ADDING)
+		idr_set_cursor(&ns->idr, 0);
+
+	for (tmp = ns, i = ns->level; i >= 0;) {
+		int tid = set_tid[ns->level - i];
 
 		if (tid) {
 			nr = idr_alloc(&tmp->idr, NULL, tid,
@@ -220,6 +244,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 			 * alreay in use. Return EEXIST in that case.
 			 */
 			if (nr == -ENOSPC)
+
 				nr = -EEXIST;
 		} else {
 			int pid_min = 1;
@@ -235,18 +260,50 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 			 * a partially initialized PID (see below).
 			 */
 			nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
-					      pid_max, GFP_ATOMIC);
+					      pid_max[ns->level - i], GFP_ATOMIC);
+			if (nr == -ENOSPC)
+				nr = -EAGAIN;
 		}
-		spin_unlock(&pidmap_lock);
-		idr_preload_end();
 
-		if (nr < 0) {
-			retval = (nr == -ENOSPC) ? -EAGAIN : nr;
+		if (unlikely(nr < 0)) {
+			/*
+			 * Preload more memory if idr_alloc{,cyclic} failed with -ENOMEM.
+			 *
+			 * The IDR API only allows us to preload memory for one call, while we may end
+			 * up doing several under pidmap_lock with GFP_ATOMIC. The situation may be
+			 * salvageable with GFP_KERNEL. But make sure to not loop indefinitely if preload
+			 * did not help (the routine unfortunately returns void, so we have no idea
+			 * if it got anywhere).
+			 *
+			 * The lock can be safely dropped and picked up as historically pid allocation
+			 * for different namespaces was *not* atomic -- we try to hold on to it the
+			 * entire time only for performance reasons.
+			 */
+			if (nr == -ENOMEM && !retried_preload) {
+				spin_unlock(&pidmap_lock);
+				idr_preload_end();
+				retried_preload = true;
+				idr_preload(GFP_KERNEL);
+				spin_lock(&pidmap_lock);
+				continue;
+			}
+			retval = nr;
 			goto out_free;
 		}
 
 		pid->numbers[i].nr = nr;
 		pid->numbers[i].ns = tmp;
+		i--;
+		retried_preload = false;
+
+		/*
+		 * PID 1 (init) must be created first.
+		 */
+		if (!READ_ONCE(tmp->child_reaper) && nr != 1) {
+			retval = -EINVAL;
+			goto out_free;
+		}
+
 		tmp = tmp->parent;
 	}
 
@@ -257,25 +314,19 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	 * is what we have exposed to userspace for a long time and it is
 	 * documented behavior for pid namespaces. So we can't easily
 	 * change it even if there were an error code better suited.
+	 *
+	 * This can't be done earlier because we need to preserve other
+	 * error conditions.
+	 *
+	 * We need this even if copy_process() does the same check. If two
+	 * or more tasks from parent namespace try to inject a child into a
+	 * dead namespace, one of free_pid() calls from the copy_process()
+	 * error path may try to wakeup the possibly freed ns->child_reaper.
 	 */
 	retval = -ENOMEM;
-
-	get_pid_ns(ns);
-	refcount_set(&pid->count, 1);
-	spin_lock_init(&pid->lock);
-	for (type = 0; type < PIDTYPE_MAX; ++type)
-		INIT_HLIST_HEAD(&pid->tasks[type]);
-
-	init_waitqueue_head(&pid->wait_pidfd);
-	INIT_HLIST_HEAD(&pid->inodes);
-
-	upid = pid->numbers + ns->level;
-	idr_preload(GFP_KERNEL);
-	spin_lock(&pidmap_lock);
-	if (!(ns->pid_allocated & PIDNS_ADDING))
-		goto out_unlock;
-	pidfs_add_pid(pid);
-	for ( ; upid >= pid->numbers; --upid) {
+	if (unlikely(!(ns->pid_allocated & PIDNS_ADDING)))
+		goto out_free;
+	for (upid = pid->numbers + ns->level; upid >= pid->numbers; --upid) {
 		/* Make the PID visible to find_pid_ns. */
 		idr_replace(&upid->ns->idr, pid, upid->nr);
 		upid->ns->pid_allocated++;
@@ -284,26 +335,25 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	idr_preload_end();
 	ns_ref_active_get(ns);
 
-	return pid;
+	retval = pidfs_add_pid(pid);
+	if (unlikely(retval)) {
+		free_pid(pid);
+		pid = ERR_PTR(-ENOMEM);
+	}
 
-out_unlock:
-	spin_unlock(&pidmap_lock);
-	idr_preload_end();
-	put_pid_ns(ns);
+	return pid;
 
 out_free:
-	spin_lock(&pidmap_lock);
 	while (++i <= ns->level) {
 		upid = pid->numbers + i;
 		idr_remove(&upid->ns->idr, upid->nr);
 	}
 
-	/* On failure to allocate the first pid, reset the state */
-	if (ns->pid_allocated == PIDNS_ADDING)
-		idr_set_cursor(&ns->idr, 0);
-
 	spin_unlock(&pidmap_lock);
+	idr_preload_end();
 
+out_abort:
+	put_pid_ns(ns);
 	kmem_cache_free(ns->pid_cachep, pid);
 	return ERR_PTR(retval);
 }
@@ -515,8 +565,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 	rcu_read_lock();
 	if (!ns)
 		ns = task_active_pid_ns(current);
-	if (ns)
-		nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
+	nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
 	rcu_read_unlock();
 
 	return nr;