/proc/pid/checkpointable

index e0af8a2..ed4fd3d 100644
@@ -226,13 +226,6 @@ static int cr_write_task(struct cr_ctx *ctx, struct task_struct *t)
 {
 	int ret;
 
-	/* TODO: verity that the task is frozen (unless self) */
-
-	if (t->state == TASK_DEAD) {
-		pr_warning("c/r: task may not be in state TASK_DEAD\n");
-		return -EAGAIN;
-	}
-
 	ret = cr_write_task_struct(ctx, t);
 	pr_debug("task_struct: ret %d\n", ret);
 	if (ret < 0)

@@ -255,6 +248,200 @@ static int cr_write_task(struct cr_ctx *ctx, struct task_struct *t)
 	return ret;
 }
 
+/* dump all tasks in ctx->tasks_arr[] */
+static int cr_write_all_tasks(struct cr_ctx *ctx)
+{
+	int n, ret = 0;
+
+	for (n = 0; n < ctx->tasks_nr; n++) {
+		pr_debug("dumping task #%d\n", n);
+		ret = cr_write_task(ctx, ctx->tasks_arr[n]);
+		if (ret < 0)
+			break;
+	}
+
+	return ret;
+}
+
+static int cr_may_checkpoint_task(struct task_struct *t, struct cr_ctx *ctx)
+{
+	pr_debug("check %d\n", task_pid_nr_ns(t, ctx->root_nsproxy->pid_ns));
+
+	if (t->state == TASK_DEAD) {
+		pr_warning("c/r: task %d is TASK_DEAD\n", task_pid_vnr(t));
+		return -EAGAIN;
+	}
+
+	if (!ptrace_may_access(t, PTRACE_MODE_READ))
+		return -EPERM;
+
+	/* FIXME: verify that the task is frozen (unless self) */
+
+	/* FIXME: change this for nested containers */
+	if (task_nsproxy(t) != ctx->root_nsproxy)
+		return -EPERM;
+
+	return 0;
+}
+
+#define CR_HDR_PIDS_CHUNK	256
+
+static int cr_write_pids(struct cr_ctx *ctx)
+{
+	struct cr_hdr_pids *hh;
+	struct pid_namespace *ns;
+	struct task_struct *task;
+	struct task_struct **tasks_arr;
+	int tasks_nr, n, ret = 0, pos = 0;
+
+	ns = ctx->root_nsproxy->pid_ns;
+	tasks_arr = ctx->tasks_arr;
+	tasks_nr = ctx->tasks_nr;
+
+	hh = cr_hbuf_get(ctx, sizeof(*hh) * CR_HDR_PIDS_CHUNK);
+
+	while (tasks_nr > 0) {
+		rcu_read_lock();
+		for (n = min(tasks_nr, CR_HDR_PIDS_CHUNK); n; n--) {
+			task = tasks_arr[pos];
+
+			/* is this task cool ? */
+			ret = cr_may_checkpoint_task(task, ctx);
+			if (ret < 0) {
+				rcu_read_unlock();
+				goto out;
+			}
+			hh[pos].vpid = task_pid_nr_ns(task, ns);
+			hh[pos].vtgid = task_tgid_nr_ns(task, ns);
+			hh[pos].vppid = task_tgid_nr_ns(task->real_parent, ns);
+			pr_debug("task[%d]: vpid %d vtgid %d parent %d\n", pos,
+				 hh[pos].vpid, hh[pos].vtgid, hh[pos].vppid);
+			pos++;
+		}
+		rcu_read_unlock();
+
+		n = min(tasks_nr, CR_HDR_PIDS_CHUNK);
+		ret = cr_kwrite(ctx, hh, n * sizeof(*hh));
+		if (ret < 0)
+			break;
+
+		tasks_nr -= n;
+	}
+ out:
+	cr_hbuf_put(ctx, sizeof(*hh));
+	return ret;
+}
+
+/* count number of tasks in tree (and optionally fill pid's in array) */
+static int cr_tree_count_tasks(struct cr_ctx *ctx)
+{
+	struct task_struct *root = ctx->root_task;
+	struct task_struct *task = root;
+	struct task_struct *parent = NULL;
+	struct task_struct **tasks_arr = ctx->tasks_arr;
+	int tasks_nr = ctx->tasks_nr;
+	int nr = 0;
+
+	read_lock(&tasklist_lock);
+
+	/* count tasks via DFS scan of the tree */
+	while (1) {
+		if (tasks_arr) {
+			/* unlikely, but ... */
+			if (nr == tasks_nr)
+				return -EBUSY;	/* cleanup in cr_ctx_free() */
+			tasks_arr[nr] = task;
+			get_task_struct(task);
+		}
+
+		nr++;
+
+		/* if has children - proceed with child */
+		if (!list_empty(&task->children)) {
+			parent = task;
+			task = list_entry(task->children.next,
+					  struct task_struct, sibling);
+			continue;
+		}
+
+		while (task != root) {
+			/* if has sibling - proceed with sibling */
+			if (!list_is_last(&task->sibling, &parent->children)) {
+				task = list_entry(task->sibling.next,
+						  struct task_struct, sibling);
+				break;
+			}
+
+			/* else, trace back to parent and proceed */
+			task = parent;
+			parent = parent->real_parent;
+		}
+
+		if (task == root)
+			break;
+	}
+
+	read_unlock(&tasklist_lock);
+	return nr;
+}
+
+/*
+ * cr_build_tree - scan the tasks tree in DFS order and fill in array
+ * @ctx: checkpoint context
+ *
+ * Using DFS order simplifies the restart logic to re-create the tasks.
+ *
+ * On success, ctx->tasks_arr will be allocated and populated with all
+ * tasks (reference taken), and ctx->tasks_nr will hold the total count.
+ * The array is cleaned up by cr_ctx_free().
+ */
+static int cr_build_tree(struct cr_ctx *ctx)
+{
+	int n, m;
+
+	/* count tasks (no side effects) */
+	n = cr_tree_count_tasks(ctx);
+
+	ctx->tasks_nr = n;
+	ctx->tasks_arr = kzalloc(n * sizeof(*ctx->tasks_arr), GFP_KERNEL);
+	if (!ctx->tasks_arr)
+		return -ENOMEM;
+
+	/* count again (now will fill array) */
+	m = cr_tree_count_tasks(ctx);
+
+	/* unlikely, but ... (cleanup in cr_ctx_free) */
+	if (m < 0)
+		return m;
+	else if (m != n)
+		return -EBUSY;
+
+	return 0;
+}
+
+/* dump the array that describes the tasks tree */
+static int cr_write_tree(struct cr_ctx *ctx)
+{
+	struct cr_hdr h;
+	struct cr_hdr_tree *hh;
+	int ret;
+
+	h.type = CR_HDR_TREE;
+	h.len = sizeof(*hh);
+	h.parent = 0;
+
+	hh = cr_hbuf_get(ctx, sizeof(*hh));
+	hh->tasks_nr = ctx->tasks_nr;
+
+	ret = cr_write_obj(ctx, &h, hh);
+	cr_hbuf_put(ctx, sizeof(*hh));
+	if (ret < 0)
+		return ret;
+
+	ret = cr_write_pids(ctx);
+	return ret;
+}
+
 static int cr_get_container(struct cr_ctx *ctx, pid_t pid)
 {
 	struct task_struct *task = NULL;

@@ -272,7 +459,7 @@ static int cr_get_container(struct cr_ctx *ctx, pid_t pid)
 	if (!task)
 		goto out;
 
-#if 0	/* enable to use containers */
+#if 0	/* enable with containers */
 	if (!is_container_init(task)) {
 		err = -EINVAL;
 		goto out;

@@ -294,7 +481,7 @@ static int cr_get_container(struct cr_ctx *ctx, pid_t pid)
 	if (!nsproxy)
 		goto out;
 
-	/* TODO: verify that the container is frozen */
+	/* FIXME: verify that the container is frozen */
 
 	ctx->root_task = task;
 	ctx->root_nsproxy = nsproxy;

@@ -342,12 +529,22 @@ int do_checkpoint(struct cr_ctx *ctx, pid_t pid)
 	ret = cr_ctx_checkpoint(ctx, pid);
 	if (ret < 0)
 		goto out;
+
+	ret = cr_build_tree(ctx);
+	if (ret < 0)
+		goto out;
+
 	ret = cr_write_head(ctx);
 	if (ret < 0)
 		goto out;
-	ret = cr_write_task(ctx, ctx->root_task);
+	ret = cr_write_tree(ctx);
 	if (ret < 0)
 		goto out;
+
+	ret = cr_write_all_tasks(ctx);
+	if (ret < 0)
+		goto out;
+
 	ret = cr_write_tail(ctx);
 	if (ret < 0)
 		goto out;

index 4a51ed3..0436ef3 100644
@@ -152,6 +152,19 @@ void cr_hbuf_put(struct cr_ctx *ctx, int n)
  * restart operation, and persists until the operation is completed.
  */
 
+static void cr_task_arr_free(struct cr_ctx *ctx)
+{
+	int n;
+
+	for (n = 0; n < ctx->tasks_nr; n++) {
+		if (ctx->tasks_arr[n]) {
+			put_task_struct(ctx->tasks_arr[n]);
+			ctx->tasks_arr[n] = NULL;
+		}
+	}
+	kfree(ctx->tasks_arr);
+}
+
 static void cr_ctx_free(struct cr_ctx *ctx)
 {
 	if (ctx->file)

@@ -164,6 +177,9 @@ static void cr_ctx_free(struct cr_ctx *ctx)
 	cr_pgarr_free(ctx);
 	cr_objhash_free(ctx);
 
+	if (ctx->tasks_arr)
+		cr_task_arr_free(ctx);
+
 	if (ctx->root_nsproxy)
 		put_nsproxy(ctx->root_nsproxy);
 	if (ctx->root_task)

index e77393f..6307511 100644
@@ -34,6 +34,9 @@ struct cr_ctx {
 	void *hbuf;		/* temporary buffer for headers */
 	int hpos;		/* position in headers buffer */
 
+	struct task_struct **tasks_arr;	/* array of all tasks in container */
+	int tasks_nr;			/* size of tasks array */
+
 	struct cr_objhash *objhash;	/* hash for shared objects */
 
 	struct list_head pgarr_list;	/* page array to dump VMA contents */

index 66313bd..0acf7c0 100644
@@ -45,7 +45,8 @@ enum {
 	CR_HDR_STRING,
 	CR_HDR_FNAME,
 
-	CR_HDR_TASK = 101,
+	CR_HDR_TREE = 101,
+	CR_HDR_TASK,
 	CR_HDR_THREAD,
 	CR_HDR_CPU,
 

@@ -81,6 +82,16 @@ struct cr_hdr_tail {
 	__u64 magic;
 } __attribute__((aligned(8)));
 
+struct cr_hdr_tree {
+	__u32 tasks_nr;
+} __attribute__((aligned(8)));
+
+struct cr_hdr_pids {
+	__s32 vpid;
+	__s32 vtgid;
+	__s32 vppid;
+} __attribute__((aligned(8)));
+
 struct cr_hdr_task {
 	__u32 state;
 	__u32 exit_state;

index 0c46abf..6b4cd75 100644
@@ -10,6 +10,7 @@
 
 #include <linux/version.h>
 #include <linux/sched.h>
+#include <linux/wait.h>
 #include <linux/file.h>
 #include <linux/magic.h>
 #include <linux/checkpoint.h>

@@ -276,30 +277,235 @@ static int cr_read_task(struct cr_ctx *ctx)
 	return ret;
 }
 
+/* cr_read_tree - read the tasks tree into the checkpoint context */
+static int cr_read_tree(struct cr_ctx *ctx)
+{
+	struct cr_hdr_tree *hh = cr_hbuf_get(ctx, sizeof(*hh));
+	int parent, size, ret = -EINVAL;
+
+	parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_TREE);
+	if (parent < 0) {
+		ret = parent;
+		goto out;
+	} else if (parent != 0)
+		goto out;
+
+	if (hh->tasks_nr < 0)
+		goto out;
+
+	ctx->pids_nr = hh->tasks_nr;
+	size = sizeof(*ctx->pids_arr) * ctx->pids_nr;
+	if (size < 0)		/* overflow ? */
+		goto out;
+
+	ctx->pids_arr = kmalloc(size, GFP_KERNEL);
+	if (!ctx->pids_arr) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	ret = cr_kread(ctx, ctx->pids_arr, size);
+ out:
+	cr_hbuf_put(ctx, sizeof(*hh));
+	return ret;
+}
+
+static int cr_wait_task(struct cr_ctx *ctx)
+{
+	pid_t pid = task_pid_vnr(current);
+
+	pr_debug("pid %d waiting\n", pid);
+	return wait_event_interruptible(ctx->waitq, ctx->pids_active == pid);
+}
+
+static int cr_next_task(struct cr_ctx *ctx)
+{
+	struct task_struct *tsk;
+
+	ctx->pids_pos++;
+
+	pr_debug("pids_pos %d %d\n", ctx->pids_pos, ctx->pids_nr);
+	if (ctx->pids_pos == ctx->pids_nr) {
+		complete(&ctx->complete);
+		return 0;
+	}
+
+	ctx->pids_active = ctx->pids_arr[ctx->pids_pos].vpid;
+
+	pr_debug("pids_next %d\n", ctx->pids_active);
+
+	rcu_read_lock();
+	tsk = find_task_by_pid_ns(ctx->pids_active, ctx->root_nsproxy->pid_ns);
+	if (tsk)
+		wake_up_process(tsk);
+	rcu_read_unlock();
+
+	if (!tsk) {
+		ctx->pids_err = -ESRCH;
+		complete(&ctx->complete);
+		return -ESRCH;
+	}
+
+	return 0;
+}
+
+/* FIXME: this should be per container */
+DECLARE_WAIT_QUEUE_HEAD(cr_restart_waitq);
+
+static int do_restart_task(struct cr_ctx *ctx, pid_t pid)
+{
+	struct task_struct *root_task;
+	int ret;
+
+	rcu_read_lock();
+	root_task = find_task_by_pid_ns(pid, current->nsproxy->pid_ns);
+	if (root_task)
+		get_task_struct(root_task);
+	rcu_read_unlock();
+
+	if (!root_task)
+		return -EINVAL;
+
+	/*
+	 * wait for container init to initialize the restart context, then
+	 * grab a reference to that context, and if we're the last task to
+	 * do it, notify the container init.
+	 */
+	ret = wait_event_interruptible(cr_restart_waitq,
+				       root_task->checkpoint_ctx);
+	if (ret < 0)
+		goto out;
+
+	task_lock(root_task);
+	ctx = root_task->checkpoint_ctx;
+	if (ctx)
+		cr_ctx_get(ctx);
+	task_unlock(root_task);
+
+	if (!ctx) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
+	if (atomic_dec_and_test(&ctx->tasks_count))
+		complete(&ctx->complete);
+
+	/* wait for our turn, do the restore, and tell next task in line */
+	ret = cr_wait_task(ctx);
+	if (ret < 0)
+		goto out;
+	ret = cr_read_task(ctx);
+	if (ret < 0)
+		goto out;
+	ret = cr_next_task(ctx);
+
+ out:
+	cr_ctx_put(ctx);
+	put_task_struct(root_task);
+	return ret;
+}
+
+static int cr_wait_all_tasks_start(struct cr_ctx *ctx)
+{
+	int ret;
+
+	if (ctx->pids_nr == 1)
+		return 0;
+
+	init_completion(&ctx->complete);
+	current->checkpoint_ctx = ctx;
+
+	wake_up_all(&cr_restart_waitq);
+
+	ret = wait_for_completion_interruptible(&ctx->complete);
+	if (ret < 0)
+		return ret;
+
+	task_lock(current);
+	current->checkpoint_ctx = NULL;
+	task_unlock(current);
+
+	return 0;
+}
+
+static int cr_wait_all_tasks_finish(struct cr_ctx *ctx)
+{
+	int ret;
+
+	if (ctx->pids_nr == 1)
+		return 0;
+
+	init_completion(&ctx->complete);
+
+	ret = cr_next_task(ctx);
+	if (ret < 0)
+		return ret;
+
+	ret = wait_for_completion_interruptible(&ctx->complete);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 /* setup restart-specific parts of ctx */
 static int cr_ctx_restart(struct cr_ctx *ctx, pid_t pid)
 {
+	ctx->root_pid = pid;
+	ctx->root_task = current;
+	ctx->root_nsproxy = current->nsproxy;
+
+	get_task_struct(ctx->root_task);
+	get_nsproxy(ctx->root_nsproxy);
+
+	atomic_set(&ctx->tasks_count, ctx->pids_nr - 1);
+
 	return 0;
 }
 
-int do_restart(struct cr_ctx *ctx, pid_t pid)
+static int do_restart_root(struct cr_ctx *ctx, pid_t pid)
 {
 	int ret;
 
+	ret = cr_read_head(ctx);
+	if (ret < 0)
+		goto out;
+	ret = cr_read_tree(ctx);
+	if (ret < 0)
+		goto out;
+
 	ret = cr_ctx_restart(ctx, pid);
 	if (ret < 0)
 		goto out;
-	ret = cr_read_head(ctx);
+
+	/* wait for all other tasks to enter do_restart_task() */
+	ret = cr_wait_all_tasks_start(ctx);
 	if (ret < 0)
 		goto out;
+
 	ret = cr_read_task(ctx);
 	if (ret < 0)
 		goto out;
-	ret = cr_read_tail(ctx);
+
+	/* wait for all other tasks to complete do_restart_task() */
+	ret = cr_wait_all_tasks_finish(ctx);
 	if (ret < 0)
 		goto out;
 
-	/* on success, adjust the return value if needed [TODO] */
+	ret = cr_read_tail(ctx);
+
  out:
 	return ret;
 }
+
+int do_restart(struct cr_ctx *ctx, pid_t pid)
+{
+	int ret;
+
+	if (ctx)
+		ret = do_restart_root(ctx, pid);
+	else
+		ret = do_restart_task(ctx, pid);
+
+	/* on success, adjust the return value if needed [TODO] */
+	return ret;
+}

index 0436ef3..f26b0c6 100644
@@ -167,6 +167,8 @@ static void cr_task_arr_free(struct cr_ctx *ctx)
 
 static void cr_ctx_free(struct cr_ctx *ctx)
 {
+	BUG_ON(atomic_read(&ctx->refcount));
+
 	if (ctx->file)
 		fput(ctx->file);
 

@@ -185,6 +187,8 @@ static void cr_ctx_free(struct cr_ctx *ctx)
 	if (ctx->root_task)
 		put_task_struct(ctx->root_task);
 
+	kfree(ctx->pids_arr);
+
 	kfree(ctx);
 }
 

@@ -199,8 +203,10 @@ static struct cr_ctx *cr_ctx_alloc(int fd, unsigned long flags)
 
 	ctx->flags = flags;
 
+	atomic_set(&ctx->refcount, 0);
 	INIT_LIST_HEAD(&ctx->pgarr_list);
 	INIT_LIST_HEAD(&ctx->pgarr_pool);
+	init_waitqueue_head(&ctx->waitq);
 
 	err = -EBADF;
 	ctx->file = fget(fd);

@@ -215,6 +221,7 @@ static struct cr_ctx *cr_ctx_alloc(int fd, unsigned long flags)
 	if (cr_objhash_alloc(ctx) < 0)
 		goto err;
 
+	atomic_inc(&ctx->refcount);
 	return ctx;
 
  err:

@@ -222,6 +229,17 @@ static struct cr_ctx *cr_ctx_alloc(int fd, unsigned long flags)
 	return ERR_PTR(err);
 }
 
+void cr_ctx_get(struct cr_ctx *ctx)
+{
+	atomic_inc(&ctx->refcount);
+}
+
+void cr_ctx_put(struct cr_ctx *ctx)
+{
+	if (ctx && atomic_dec_and_test(&ctx->refcount))
+		cr_ctx_free(ctx);
+}
+
 /**
  * sys_checkpoint - checkpoint a container
  * @pid: pid of the container init(1) process

@@ -249,7 +267,7 @@ asmlinkage long sys_checkpoint(pid_t pid, int fd, unsigned long flags)
 	if (!ret)
 		ret = ctx->crid;
 
-	cr_ctx_free(ctx);
+	cr_ctx_put(ctx);
 	return ret;
 }
 

@@ -264,7 +282,7 @@ asmlinkage long sys_checkpoint(pid_t pid, int fd, unsigned long flags)
  */
 asmlinkage long sys_restart(int crid, int fd, unsigned long flags)
 {
-	struct cr_ctx *ctx;
+	struct cr_ctx *ctx = NULL;
 	pid_t pid;
 	int ret;
 

@@ -272,15 +290,17 @@ asmlinkage long sys_restart(int crid, int fd, unsigned long flags)
 	if (flags)
 		return -EINVAL;
 
-	ctx = cr_ctx_alloc(fd, flags | CR_CTX_RSTR);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-
 	/* FIXME: for now, we use 'crid' as a pid */
 	pid = (pid_t) crid;
 
+	if (pid == task_pid_vnr(current))
+		ctx = cr_ctx_alloc(fd, flags | CR_CTX_RSTR);
+
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
 	ret = do_restart(ctx, pid);
 
-	cr_ctx_free(ctx);
+	cr_ctx_put(ctx);
 	return ret;
 }

index 6307511..484be56 100644
@@ -13,10 +13,13 @@
 #include <linux/path.h>
 #include <linux/fs.h>
 #include <linux/fdtable.h>
+#include <linux/path.h>
+#include <linux/sched.h>
+#include <asm/atomic.h>
 
 #ifdef CONFIG_CHECKPOINT_RESTART
 
-#define CR_VERSION  2
+#define CR_VERSION  3
 
 struct cr_ctx {
 	int crid;		/* unique checkpoint id */

@@ -34,8 +37,7 @@ struct cr_ctx {
 	void *hbuf;		/* temporary buffer for headers */
 	int hpos;		/* position in headers buffer */
 
-	struct task_struct **tasks_arr;	/* array of all tasks in container */
-	int tasks_nr;			/* size of tasks array */
+	atomic_t refcount;
 
 	struct cr_objhash *objhash;	/* hash for shared objects */
 

@@ -43,6 +45,20 @@ struct cr_ctx {
 	struct list_head pgarr_pool;	/* pool of empty page arrays chain */
 
 	struct path fs_mnt;	/* container root (FIXME) */
+
+	/* [multi-process checkpoint] */
+	struct task_struct **tasks_arr; /* array of all tasks [checkpoint] */
+	int tasks_nr;                   /* size of tasks array */
+
+	/* [multi-process restart] */
+	struct cr_hdr_pids *pids_arr;	/* array of all pids [restart] */
+	int pids_nr;			/* size of pids array */
+	int pids_pos;			/* position pids array */
+	int pids_err;			/* error occured ? */
+	pid_t pids_active;		/* pid of (next) active task */
+	atomic_t tasks_count;		/* sync of restarting tasks */
+	struct completion complete;	/* sync of restarting tasks */
+	wait_queue_head_t waitq;	/* sync of restarting tasks */
 };
 
 /* cr_ctx: flags */

@@ -55,6 +71,9 @@ extern int cr_kread(struct cr_ctx *ctx, void *buf, int count);
 extern void *cr_hbuf_get(struct cr_ctx *ctx, int n);
 extern void cr_hbuf_put(struct cr_ctx *ctx, int n);
 
+extern void cr_ctx_get(struct cr_ctx *ctx);
+extern void cr_ctx_put(struct cr_ctx *ctx);
+
 /* shared objects handling */
 
 enum {

index 8c216e0..c5d5987 100644
@@ -1416,6 +1416,9 @@ struct task_struct {
 #ifdef CONFIG_TRACING
 	/* state flags for use by tracers */
 	unsigned long trace;
+#endif 
+#ifdef CONFIG_CHECKPOINT_RESTART
+	struct cr_ctx *checkpoint_ctx;
 #endif
 };
 

index ed4fd3d..dae9b97 100644
@@ -341,11 +341,18 @@ static int cr_tree_count_tasks(struct cr_ctx *ctx)
 	struct task_struct **tasks_arr = ctx->tasks_arr;
 	int tasks_nr = ctx->tasks_nr;
 	int nr = 0;
+	int ret;
 
 	read_lock(&tasklist_lock);
 
 	/* count tasks via DFS scan of the tree */
 	while (1) {
+		ret = cr_may_checkpoint_task(task, ctx);
+		if (ret < 0) {
+			nr = ret;
+			break;
+		}
+
 		if (tasks_arr) {
 			/* unlikely, but ... */
 			if (nr == tasks_nr)

@@ -401,6 +408,8 @@ static int cr_build_tree(struct cr_ctx *ctx)
 
 	/* count tasks (no side effects) */
 	n = cr_tree_count_tasks(ctx);
+	if (n < 0)
+		return n;
 
 	ctx->tasks_nr = n;
 	ctx->tasks_arr = kzalloc(n * sizeof(*ctx->tasks_arr), GFP_KERNEL);

index dae9b97..c16f30c 100644
@@ -19,6 +19,7 @@
 #include <linux/mount.h>
 #include <linux/utsname.h>
 #include <linux/magic.h>
+#include <linux/freezer.h>
 #include <linux/checkpoint.h>
 #include <linux/checkpoint_hdr.h>
 

@@ -275,7 +276,9 @@ static int cr_may_checkpoint_task(struct task_struct *t, struct cr_ctx *ctx)
 	if (!ptrace_may_access(t, PTRACE_MODE_READ))
 		return -EPERM;
 
-	/* FIXME: verify that the task is frozen (unless self) */
+	/* verify that the task is frozen (unless self) */
+	if (t != current && !frozen(t))
+		return -EBUSY;
 
 	/* FIXME: change this for nested containers */
 	if (task_nsproxy(t) != ctx->root_nsproxy)

index c16f30c..ad0956c 100644
@@ -264,22 +264,31 @@ static int cr_write_all_tasks(struct cr_ctx *ctx)
 	return ret;
 }
 
+int task_checkpointable(struct task_struct *t)
+{
+	if (t->state == TASK_DEAD) {
+		pr_warning("c/r: task %d is TASK_DEAD\n", task_pid_vnr(t));
+		return 0;
+	}
+
+	/* Verify that task is frozen, unless it is self-checkpoint */
+	if (t != current && !frozen(t))
+		return 0;
+
+	return 1;
+}
+
 static int cr_may_checkpoint_task(struct task_struct *t, struct cr_ctx *ctx)
 {
 	pr_debug("check %d\n", task_pid_nr_ns(t, ctx->root_nsproxy->pid_ns));
 
-	if (t->state == TASK_DEAD) {
-		pr_warning("c/r: task %d is TASK_DEAD\n", task_pid_vnr(t));
+	/* verify that the task is checkpointable */
+	if (!task_checkpointable(t))
 		return -EAGAIN;
-	}
 
 	if (!ptrace_may_access(t, PTRACE_MODE_READ))
 		return -EPERM;
 
-	/* verify that the task is frozen (unless self) */
-	if (t != current && !frozen(t))
-		return -EBUSY;
-
 	/* FIXME: change this for nested containers */
 	if (task_nsproxy(t) != ctx->root_nsproxy)
 		return -EPERM;

index bde92c3..989ca93 100644
@@ -2501,6 +2501,13 @@ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
 	return 0;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTART
+static int proc_pid_checkpointable(struct task_struct *task, char *buffer)
+{
+	return sprintf(buffer, "%d\n", task_checkpointable(task));
+}
+#endif
+
 /*
  * Thread groups
  */

@@ -2580,6 +2587,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 	INF("io",	S_IRUGO, proc_tgid_io_accounting),
 #endif
+#ifdef CONFIG_CHECKPOINT_RESTART
+	INF("checkpointable", S_IRUGO, proc_pid_checkpointable),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file * filp,

@@ -2915,6 +2925,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 	INF("io",	S_IRUGO, proc_tid_io_accounting),
 #endif
+#ifdef CONFIG_CHECKPOINT_RESTART
+	INF("checkpointable", S_IRUGO, proc_pid_checkpointable),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file * filp,

index 484be56..d1f53a6 100644
@@ -142,6 +142,8 @@ static inline int cr_enabled(void)
 	return 1;
 }
 
+int task_checkpointable(struct task_struct *t);
+
 #else /* !CONFIG_CHECKPOINT_RESTART */
 
 static inline void files_deny_checkpointing(struct files_struct *files) {}

@@ -162,5 +164,10 @@ static inline int cr_enabled(void)
 	return 0;
 }
 
+static inline int task_checkpointable(struct task_struct *t)
+{
+	return 0;
+}
+
 #endif /* CONFIG_CHECKPOINT_RESTART */
 #endif /* _CHECKPOINT_CKPT_H_ */

index ad0956c..c8c377d 100644
@@ -264,18 +264,23 @@ static int cr_write_all_tasks(struct cr_ctx *ctx)
 	return ret;
 }
 
-int task_checkpointable(struct task_struct *t)
+int __task_checkpointable(struct task_struct *t)
 {
 	if (t->state == TASK_DEAD) {
 		pr_warning("c/r: task %d is TASK_DEAD\n", task_pid_vnr(t));
-		return 0;
+		return CR_DEAD;
 	}
 
 	/* Verify that task is frozen, unless it is self-checkpoint */
 	if (t != current && !frozen(t))
-		return 0;
+		return CR_NOT_FROZEN;
+
+	return CR_CHECKPOINTABLE;
+}
 
-	return 1;
+int task_checkpointable(struct task_struct *t)
+{
+	return __task_checkpointable(t) == CR_CHECKPOINTABLE;
 }
 
 static int cr_may_checkpoint_task(struct task_struct *t, struct cr_ctx *ctx)

index 989ca93..6e4c07c 100644
@@ -2502,9 +2502,26 @@ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
 }
 
 #ifdef CONFIG_CHECKPOINT_RESTART
+static char *explain_checkpointable(int reason)
+{
+	char *message;
+
+	switch(reason) {
+	case CR_CHECKPOINTABLE: message = "1"; break;
+	case CR_DEAD: 		message = "0 (dead)"; break;
+	case CR_NOT_FROZEN: 	message = "0 (not frozen)"; break;
+	default:		message = "0 (unknown)"; break;
+	}
+	return message;
+}
+
 static int proc_pid_checkpointable(struct task_struct *task, char *buffer)
 {
-	return sprintf(buffer, "%d\n", task_checkpointable(task));
+	int rc;
+
+	rc = __task_checkpointable(task);
+
+	return scnprintf(buffer, PAGE_SIZE, "%s\n", explain_checkpointable(rc));
 }
 #endif
 

index d1f53a6..a1eba73 100644
@@ -142,6 +142,13 @@ static inline int cr_enabled(void)
 	return 1;
 }
 
+enum cr_uncheckpointable_reason {
+	CR_CHECKPOINTABLE = 0,
+	CR_DEAD,
+	CR_NOT_FROZEN
+};
+
+int __task_checkpointable(struct task_struct *t);
 int task_checkpointable(struct task_struct *t);
 
 #else /* !CONFIG_CHECKPOINT_RESTART */