1 files changed, 143 insertions, 45 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 63eff85f251f..6322b56529e9 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -55,6 +55,7 @@
 #include <linux/nsproxy.h>
 #include <linux/file.h>
 #include <linux/sched/cputime.h>
+#include <linux/cpu.h>
 #include <net/sock.h>
 
 #define CREATE_TRACE_POINTS
@@ -677,7 +678,8 @@ struct css_set init_css_set = {
 	.task_iters		= LIST_HEAD_INIT(init_css_set.task_iters),
 	.threaded_csets		= LIST_HEAD_INIT(init_css_set.threaded_csets),
 	.cgrp_links		= LIST_HEAD_INIT(init_css_set.cgrp_links),
-	.mg_preload_node	= LIST_HEAD_INIT(init_css_set.mg_preload_node),
+	.mg_src_preload_node	= LIST_HEAD_INIT(init_css_set.mg_src_preload_node),
+	.mg_dst_preload_node	= LIST_HEAD_INIT(init_css_set.mg_dst_preload_node),
 	.mg_node		= LIST_HEAD_INIT(init_css_set.mg_node),
 
 	/*
@@ -1151,7 +1153,8 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	INIT_LIST_HEAD(&cset->threaded_csets);
 	INIT_HLIST_NODE(&cset->hlist);
 	INIT_LIST_HEAD(&cset->cgrp_links);
-	INIT_LIST_HEAD(&cset->mg_preload_node);
+	INIT_LIST_HEAD(&cset->mg_src_preload_node);
+	INIT_LIST_HEAD(&cset->mg_dst_preload_node);
 	INIT_LIST_HEAD(&cset->mg_node);
 
 	/* Copy the set of subsystem state objects generated in
@@ -1649,7 +1652,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 {
 	struct cgroup *dcgrp = &dst_root->cgrp;
 	struct cgroup_subsys *ss;
-	int ssid, i, ret;
+	int ssid, ret;
 	u16 dfl_disable_ss_mask = 0;
 
 	lockdep_assert_held(&cgroup_mutex);
@@ -1693,7 +1696,8 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		struct cgroup_root *src_root = ss->root;
 		struct cgroup *scgrp = &src_root->cgrp;
 		struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
-		struct css_set *cset;
+		struct css_set *cset, *cset_pos;
+		struct css_task_iter *it;
 
 		WARN_ON(!css || cgroup_css(dcgrp, ss));
 
@@ -1711,9 +1715,22 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		css->cgroup = dcgrp;
 
 		spin_lock_irq(&css_set_lock);
-		hash_for_each(css_set_table, i, cset, hlist)
+		WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
+		list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
+					 e_cset_node[ss->id]) {
 			list_move_tail(&cset->e_cset_node[ss->id],
 				       &dcgrp->e_csets[ss->id]);
+			/*
+			 * all css_sets of scgrp together in same order to dcgrp,
+			 * patch in-flight iterators to preserve correct iteration.
+			 * since the iterator is always advanced right away and
+			 * finished when it->cset_pos meets it->cset_head, so only
+			 * update it->cset_head is enough here.
+			 */
+			list_for_each_entry(it, &cset->task_iters, iters_node)
+				if (it->cset_head == &scgrp->e_csets[ss->id])
+					it->cset_head = &dcgrp->e_csets[ss->id];
+		}
 		spin_unlock_irq(&css_set_lock);
 
 		/* default hierarchy doesn't enable controllers by default */
@@ -2208,6 +2225,45 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 EXPORT_SYMBOL_GPL(task_cgroup_path);
 
 /**
+ * cgroup_attach_lock - Lock for ->attach()
+ * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
+ *
+ * cgroup migration sometimes needs to stabilize threadgroups against forks and
+ * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach()
+ * implementations (e.g. cpuset), also need to disable CPU hotplug.
+ * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can
+ * lead to deadlocks.
+ *
+ * Bringing up a CPU may involve creating and destroying tasks which requires
+ * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
+ * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while
+ * write-locking threadgroup_rwsem, the locking order is reversed and we end up
+ * waiting for an on-going CPU hotplug operation which in turn is waiting for
+ * the threadgroup_rwsem to be released to create new tasks. For more details:
+ *
+ *   http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu
+ *
+ * Resolve the situation by always acquiring cpus_read_lock() before optionally
+ * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that
+ * CPU hotplug is disabled on entry.
+ */
+static void cgroup_attach_lock(void)
+{
+	get_online_cpus();
+	percpu_down_write(&cgroup_threadgroup_rwsem);
+}
+
+/**
+ * cgroup_attach_unlock - Undo cgroup_attach_lock()
+ * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem
+ */
+static void cgroup_attach_unlock(void)
+{
+	percpu_up_write(&cgroup_threadgroup_rwsem);
+	put_online_cpus();
+}
+
+/**
  * cgroup_migrate_add_task - add a migration target task to a migration context
  * @task: target task
  * @mgctx: target migration context
@@ -2455,21 +2511,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp)
  */
 void cgroup_migrate_finish(struct cgroup_mgctx *mgctx)
 {
-	LIST_HEAD(preloaded);
 	struct css_set *cset, *tmp_cset;
 
 	lockdep_assert_held(&cgroup_mutex);
 
 	spin_lock_irq(&css_set_lock);
 
-	list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded);
-	list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded);
+	list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets,
+				 mg_src_preload_node) {
+		cset->mg_src_cgrp = NULL;
+		cset->mg_dst_cgrp = NULL;
+		cset->mg_dst_cset = NULL;
+		list_del_init(&cset->mg_src_preload_node);
+		put_css_set_locked(cset);
+	}
 
-	list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) {
+	list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets,
+				 mg_dst_preload_node) {
 		cset->mg_src_cgrp = NULL;
 		cset->mg_dst_cgrp = NULL;
 		cset->mg_dst_cset = NULL;
-		list_del_init(&cset->mg_preload_node);
+		list_del_init(&cset->mg_dst_preload_node);
 		put_css_set_locked(cset);
 	}
 
@@ -2511,7 +2573,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
 
 	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
 
-	if (!list_empty(&src_cset->mg_preload_node))
+	if (!list_empty(&src_cset->mg_src_preload_node))
 		return;
 
 	WARN_ON(src_cset->mg_src_cgrp);
@@ -2522,7 +2584,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
 	src_cset->mg_src_cgrp = src_cgrp;
 	src_cset->mg_dst_cgrp = dst_cgrp;
 	get_css_set(src_cset);
-	list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets);
+	list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets);
 }
 
 /**
@@ -2547,7 +2609,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 
 	/* look up the dst cset for each src cset and link it to src */
 	list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
-				 mg_preload_node) {
+				 mg_src_preload_node) {
 		struct css_set *dst_cset;
 		struct cgroup_subsys *ss;
 		int ssid;
@@ -2566,7 +2628,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 		if (src_cset == dst_cset) {
 			src_cset->mg_src_cgrp = NULL;
 			src_cset->mg_dst_cgrp = NULL;
-			list_del_init(&src_cset->mg_preload_node);
+			list_del_init(&src_cset->mg_src_preload_node);
 			put_css_set(src_cset);
 			put_css_set(dst_cset);
 			continue;
@@ -2574,8 +2636,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
 
 		src_cset->mg_dst_cset = dst_cset;
 
-		if (list_empty(&dst_cset->mg_preload_node))
-			list_add_tail(&dst_cset->mg_preload_node,
+		if (list_empty(&dst_cset->mg_dst_preload_node))
+			list_add_tail(&dst_cset->mg_dst_preload_node,
 				      &mgctx->preloaded_dst_csets);
 		else
 			put_css_set(dst_cset);
@@ -2686,7 +2748,7 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup)
 	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
 		return ERR_PTR(-EINVAL);
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock();
 
 	rcu_read_lock();
 	if (pid) {
@@ -2717,7 +2779,7 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup)
 	goto out_unlock_rcu;
 
 out_unlock_threadgroup:
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock();
 out_unlock_rcu:
 	rcu_read_unlock();
 	return tsk;
@@ -2732,7 +2794,7 @@ void cgroup_procs_write_finish(struct task_struct *task)
 	/* release reference from cgroup_procs_write_start() */
 	put_task_struct(task);
 
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock();
 	for_each_subsys(ss, ssid)
 		if (ss->post_attach)
 			ss->post_attach();
@@ -2791,7 +2853,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock();
 
 	/* look up all csses currently attached to @cgrp's subtree */
 	spin_lock_irq(&css_set_lock);
@@ -2809,7 +2871,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 		goto out_finish;
 
 	spin_lock_irq(&css_set_lock);
-	list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) {
+	list_for_each_entry(src_cset, &mgctx.preloaded_src_csets,
+			    mg_src_preload_node) {
 		struct task_struct *task, *ntask;
 
 		/* all tasks in src_csets need to be migrated */
@@ -2821,7 +2884,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	ret = cgroup_migrate_execute(&mgctx);
 out_finish:
 	cgroup_migrate_finish(&mgctx);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock();
 	return ret;
 }
 
@@ -3451,24 +3514,43 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 static int cgroup_file_open(struct kernfs_open_file *of)
 {
 	struct cftype *cft = of->kn->priv;
+	struct cgroup_file_ctx *ctx;
+	int ret;
 
-	if (cft->open)
-		return cft->open(of);
-	return 0;
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->ns = current->nsproxy->cgroup_ns;
+	get_cgroup_ns(ctx->ns);
+	of->priv = ctx;
+
+	if (!cft->open)
+		return 0;
+
+	ret = cft->open(of);
+	if (ret) {
+		put_cgroup_ns(ctx->ns);
+		kfree(ctx);
+	}
+	return ret;
 }
 
 static void cgroup_file_release(struct kernfs_open_file *of)
 {
 	struct cftype *cft = of->kn->priv;
+	struct cgroup_file_ctx *ctx = of->priv;
 
 	if (cft->release)
 		cft->release(of);
+	put_cgroup_ns(ctx->ns);
+	kfree(ctx);
 }
 
 static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 				 size_t nbytes, loff_t off)
 {
-	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct cgroup *cgrp = of->kn->parent->priv;
 	struct cftype *cft = of->kn->priv;
 	struct cgroup_subsys_state *css;
@@ -3482,7 +3564,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	 */
 	if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) &&
 	    !(cft->flags & CFTYPE_NS_DELEGATABLE) &&
-	    ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp)
+	    ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp)
 		return -EPERM;
 
 	if (cft->write)
@@ -4376,21 +4458,21 @@ void css_task_iter_end(struct css_task_iter *it)
 
 static void cgroup_procs_release(struct kernfs_open_file *of)
 {
-	if (of->priv) {
-		css_task_iter_end(of->priv);
-		kfree(of->priv);
-	}
+	struct cgroup_file_ctx *ctx = of->priv;
+
+	if (ctx->procs.started)
+		css_task_iter_end(&ctx->procs.iter);
 }
 
 static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos)
 {
 	struct kernfs_open_file *of = s->private;
-	struct css_task_iter *it = of->priv;
+	struct cgroup_file_ctx *ctx = of->priv;
 
 	if (pos)
 		(*pos)++;
 
-	return css_task_iter_next(it);
+	return css_task_iter_next(&ctx->procs.iter);
 }
 
 static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
@@ -4398,21 +4480,18 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
 {
 	struct kernfs_open_file *of = s->private;
 	struct cgroup *cgrp = seq_css(s)->cgroup;
-	struct css_task_iter *it = of->priv;
+	struct cgroup_file_ctx *ctx = of->priv;
+	struct css_task_iter *it = &ctx->procs.iter;
 
 	/*
 	 * When a seq_file is seeked, it's always traversed sequentially
 	 * from position 0, so we can simply keep iterating on !0 *pos.
 	 */
-	if (!it) {
+	if (!ctx->procs.started) {
 		if (WARN_ON_ONCE((*pos)))
 			return ERR_PTR(-EINVAL);
-
-		it = kzalloc(sizeof(*it), GFP_KERNEL);
-		if (!it)
-			return ERR_PTR(-ENOMEM);
-		of->priv = it;
 		css_task_iter_start(&cgrp->self, iter_flags, it);
+		ctx->procs.started = true;
 	} else if (!(*pos)) {
 		css_task_iter_end(it);
 		css_task_iter_start(&cgrp->self, iter_flags, it);
@@ -4447,9 +4526,9 @@ static int cgroup_procs_show(struct seq_file *s, void *v)
 
 static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 					 struct cgroup *dst_cgrp,
-					 struct super_block *sb)
+					 struct super_block *sb,
+					 struct cgroup_namespace *ns)
 {
-	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
 	struct cgroup *com_cgrp = src_cgrp;
 	struct inode *inode;
 	int ret;
@@ -4485,8 +4564,10 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
 				  char *buf, size_t nbytes, loff_t off)
 {
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct cgroup *src_cgrp, *dst_cgrp;
 	struct task_struct *task;
+	const struct cred *saved_cred;
 	ssize_t ret;
 
 	dst_cgrp = cgroup_kn_lock_live(of->kn, false);
@@ -4503,8 +4584,16 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
 	src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
 	spin_unlock_irq(&css_set_lock);
 
+	/*
+	 * Process and thread migrations follow same delegation rule. Check
+	 * permissions using the credentials from file open to protect against
+	 * inherited fd attacks.
+	 */
+	saved_cred = override_creds(of->file->f_cred);
 	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp,
-					    of->file->f_path.dentry->d_sb);
+					    of->file->f_path.dentry->d_sb,
+					    ctx->ns);
+	revert_creds(saved_cred);
 	if (ret)
 		goto out_finish;
 
@@ -4526,8 +4615,10 @@ static void *cgroup_threads_start(struct seq_file *s, loff_t *pos)
 static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
 				    char *buf, size_t nbytes, loff_t off)
 {
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct cgroup *src_cgrp, *dst_cgrp;
 	struct task_struct *task;
+	const struct cred *saved_cred;
 	ssize_t ret;
 
 	buf = strstrip(buf);
@@ -4546,9 +4637,16 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
 	src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
 	spin_unlock_irq(&css_set_lock);
 
-	/* thread migrations follow the cgroup.procs delegation rule */
+	/*
+	 * Process and thread migrations follow same delegation rule. Check
+	 * permissions using the credentials from file open to protect against
+	 * inherited fd attacks.
+	 */
+	saved_cred = override_creds(of->file->f_cred);
 	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp,
-					    of->file->f_path.dentry->d_sb);
+					    of->file->f_path.dentry->d_sb,
+					    ctx->ns);
+	revert_creds(saved_cred);
 	if (ret)
 		goto out_finish;