pstree: Make pstree_item::pid pointer and move virt and node to array

So, after the patch struct pid will look as:

struct pid {
        struct pstree_item *item;
        pid_t real;
        int state;
        struct {
                pid_t virt;
                struct rb_node node;
        } ns[1];
};

travis-ci: success for Make pstree_item::pid allocated dynamically
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>

criu/action-scripts.c

@@ -70,7 +70,7 @@ static int run_shell_scripts(const char *action)
 		int pid;
 		char root_item_pid[16];
 
-		pid = root_item->pid.real;
+		pid = root_item->pid->real;
 		if (pid != -1) {
 			snprintf(root_item_pid, sizeof(root_item_pid), "%d", pid);
 			if (setenv("CRTOOLS_INIT_PID", root_item_pid, 1)) {

criu/autofs.c

@@ -579,12 +579,12 @@ static int autofs_dup_pipe(struct pstree_item *task,
 
 	if (dup_fle(task, ple, new_fd, flags) < 0) {
 		pr_err("Failed to add fd %d to process %d\n",
-				new_fd, task->pid.virt);
+				new_fd, task->pid->ns[0].virt);
 		return -1;
 	}
 
 	pr_info("autofs: added pipe fd %d, flags %#x to %d\n",
-			new_fd, flags, task->pid.virt);
+			new_fd, flags, task->pid->ns[0].virt);
 	return new_fd;
 }
 
@@ -851,12 +851,12 @@ static struct fdinfo_list_entry *autofs_pipe_le(struct pstree_item *master,
 	ple = find_fle_by_fd(&rsti(master)->fds, pipe_fd);
 	if (!ple) {
 		pr_err("Failed to find pipe fd %d in process %d\n",
-				pipe_fd, master->pid.virt);
+				pipe_fd, master->pid->ns[0].virt);
 		return NULL;
 	}
 	if (ple->fe->type != FD_TYPES__PIPE) {
 		pr_err("Fd %d in process %d is not a pipe: %d\n", pipe_fd,
-				master->pid.virt, ple->fe->type);
+				master->pid->ns[0].virt, ple->fe->type);
 		return NULL;
 	}
 	return ple;
@@ -874,7 +874,7 @@ static int autofs_create_fle(struct pstree_item *task, FdinfoEntry *fe,
 	le = (void *)ALIGN((long)le, sizeof(int));
 
 	futex_init(&le->real_pid);
-	le->pid = task->pid.virt;
+	le->pid = task->pid->ns[0].virt;
 	le->fe = fe;
 
 	collect_gen_fd(le, rst_info);
@@ -955,7 +955,7 @@ static int autofs_add_mount_info(void *data)
 		entry->fd = autofs_dup_pipe(master, ple, entry->fd);
 		if (entry->fd < 0) {
 			pr_err("Failed to find free fd in process %d\n",
-					master->pid.virt);
+					master->pid->ns[0].virt);
 			return -1;
 		}
 	}

criu/cgroup.c

@@ -640,7 +640,7 @@ int dump_task_cgroup(struct pstree_item *item, u32 *cg_id, struct parasite_dump_
 	struct cg_set *cs;
 
 	if (item)
-		pid = item->pid.real;
+		pid = item->pid->real;
 	else
 		pid = getpid();
 

criu/cr-check.c

@@ -1095,7 +1095,7 @@ int cr_check(void)
 	if (root_item == NULL)
 		return -1;
 
-	root_item->pid.real = getpid();
+	root_item->pid->real = getpid();
 
 	if (collect_pstree_ids())
 		return -1;

criu/cr-dump.c

@@ -591,7 +591,7 @@ static int dump_task_kobj_ids(struct pstree_item *item)
 {
 	int new;
 	struct kid_elem elem;
-	int pid = item->pid.real;
+	int pid = item->pid->real;
 	TaskKobjIdsEntry *ids = item->ids;
 
 	elem.pid = pid;
@@ -639,7 +639,7 @@ int get_task_ids(struct pstree_item *item)
 
 	task_kobj_ids_entry__init(item->ids);
 
-	if (item->pid.state != TASK_DEAD) {
+	if (item->pid->state != TASK_DEAD) {
 		ret = dump_task_kobj_ids(item);
 		if (ret)
 			goto err_free;
@@ -694,7 +694,7 @@ static int dump_task_core_all(struct parasite_ctl *ctl,
 {
 	struct cr_img *img;
 	CoreEntry *core = item->core[0];
-	pid_t pid = item->pid.real;
+	pid_t pid = item->pid->real;
 	int ret = -1;
 	struct proc_status_creds *creds;
 	struct parasite_dump_cgroup_args cgroup_args, *info = NULL;
@@ -709,7 +709,7 @@ static int dump_task_core_all(struct parasite_ctl *ctl,
 
 	creds = dmpi(item)->pi_creds;
 	if (creds->seccomp_mode != SECCOMP_MODE_DISABLED) {
-		pr_info("got seccomp mode %d for %d\n", creds->seccomp_mode, item->pid.virt);
+		pr_info("got seccomp mode %d for %d\n", creds->seccomp_mode, item->pid->ns[0].virt);
 		core->tc->has_seccomp_mode = true;
 		core->tc->seccomp_mode = creds->seccomp_mode;
 
@@ -721,7 +721,7 @@ static int dump_task_core_all(struct parasite_ctl *ctl,
 
 	strlcpy((char *)core->tc->comm, stat->comm, TASK_COMM_LEN);
 	core->tc->flags = stat->flags;
-	core->tc->task_state = item->pid.state;
+	core->tc->task_state = item->pid->state;
 	core->tc->exit_code = 0;
 
 	ret = parasite_dump_thread_leader_seized(ctl, pid, core);
@@ -766,24 +766,25 @@ err:
 static int collect_pstree_ids_predump(void)
 {
 	struct pstree_item *item;
+	struct pid pid;
 	struct {
 		struct pstree_item i;
 		struct dmp_info d;
-	} crt = { };
+	} crt = { .i.pid = &pid, };
 
 	/*
 	 * This thing is normally done inside
 	 * write_img_inventory().
 	 */
 
-	crt.i.pid.state = TASK_ALIVE;
-	crt.i.pid.real = getpid();
+	crt.i.pid->state = TASK_ALIVE;
+	crt.i.pid->real = getpid();
 
 	if (predump_task_ns_ids(&crt.i))
 		return -1;
 
 	for_each_pstree_item(item) {
-		if (item->pid.state == TASK_DEAD)
+		if (item->pid->state == TASK_DEAD)
 			continue;
 
 		if (predump_task_ns_ids(item))
@@ -827,9 +828,9 @@ static int dump_task_thread(struct parasite_ctl *parasite_ctl,
 		pr_err("Can't dump thread for pid %d\n", pid);
 		goto err;
 	}
-	pstree_insert_pid(tid->virt, tid);
+	pstree_insert_pid(tid->ns[0].virt, tid);
 
-	img = open_image(CR_FD_CORE, O_DUMP, tid->virt);
+	img = open_image(CR_FD_CORE, O_DUMP, tid->ns[0].virt);
 	if (!img)
 		goto err;
 
@@ -856,7 +857,7 @@ static int dump_one_zombie(const struct pstree_item *item,
 	core->tc->task_state = TASK_DEAD;
 	core->tc->exit_code = pps->exit_code;
 
-	img = open_image(CR_FD_CORE, O_DUMP, item->pid.virt);
+	img = open_image(CR_FD_CORE, O_DUMP, item->pid->ns[0].virt);
 	if (!img)
 		goto err;
 
@@ -980,8 +981,8 @@ static int dump_task_threads(struct parasite_ctl *parasite_ctl,
 
 	for (i = 0; i < item->nr_threads; i++) {
 		/* Leader is already dumped */
-		if (item->pid.real == item->threads[i].real) {
-			item->threads[i].virt = item->pid.virt;
+		if (item->pid->real == item->threads[i].real) {
+			item->threads[i].ns[0].virt = item->pid->ns[0].virt;
 			continue;
 		}
 		if (dump_task_thread(parasite_ctl, item, i))
@@ -1011,17 +1012,17 @@ static int fill_zombies_pids(struct pstree_item *item)
 	 * Pids read here are virtual -- caller has set up
 	 * the proc of target pid namespace.
 	 */
-	if (parse_children(item->pid.virt, &ch, &nr) < 0)
+	if (parse_children(item->pid->ns[0].virt, &ch, &nr) < 0)
 		return -1;
 
 	/*
 	 * Step 1 -- filter our ch's pid of alive tasks
 	 */
 	list_for_each_entry(child, &item->children, sibling) {
-		if (child->pid.virt < 0)
+		if (child->pid->ns[0].virt < 0)
 			continue;
 		for (i = 0; i < nr; i++) {
-			if (ch[i] == child->pid.virt) {
+			if (ch[i] == child->pid->ns[0].virt) {
 				ch[i] = -1;
 				break;
 			}
@@ -1036,12 +1037,12 @@ static int fill_zombies_pids(struct pstree_item *item)
 	 */
 	i = 0;
 	list_for_each_entry(child, &item->children, sibling) {
-		if (child->pid.virt > 0)
+		if (child->pid->ns[0].virt > 0)
 			continue;
 		for (; i < nr; i++) {
 			if (ch[i] < 0)
 				continue;
-			child->pid.virt = ch[i];
+			child->pid->ns[0].virt = ch[i];
 			ch[i] = -1;
 			break;
 		}
@@ -1069,12 +1070,12 @@ static int dump_zombies(void)
 	 */
 
 	for_each_pstree_item(item) {
-		if (item->pid.state != TASK_DEAD)
+		if (item->pid->state != TASK_DEAD)
 			continue;
 
-		if (item->pid.virt < 0) {
+		if (item->pid->ns[0].virt < 0) {
 			if (!pidns)
-				item->pid.virt = item->pid.real;
+				item->pid->ns[0].virt = item->pid->real;
 			else if (root_item == item) {
 				pr_err("A root task is dead\n");
 				goto err;
@@ -1083,7 +1084,7 @@ static int dump_zombies(void)
 		}
 
 		pr_info("Obtaining zombie stat ... \n");
-		if (parse_pid_stat(item->pid.virt, &pps_buf) < 0)
+		if (parse_pid_stat(item->pid->ns[0].virt, &pps_buf) < 0)
 			goto err;
 
 		item->sid = pps_buf.sid;
@@ -1104,7 +1105,7 @@ err:
 
 static int pre_dump_one_task(struct pstree_item *item)
 {
-	pid_t pid = item->pid.real;
+	pid_t pid = item->pid->real;
 	struct vm_area_list vmas;
 	struct parasite_ctl *parasite_ctl;
 	int ret = -1;
@@ -1118,12 +1119,12 @@ static int pre_dump_one_task(struct pstree_item *item)
 	pr_info("Pre-dumping task (pid: %d)\n", pid);
 	pr_info("========================================\n");
 
-	if (item->pid.state == TASK_STOPPED) {
+	if (item->pid->state == TASK_STOPPED) {
 		pr_warn("Stopped tasks are not supported\n");
 		return 0;
 	}
 
-	if (item->pid.state == TASK_DEAD)
+	if (item->pid->state == TASK_DEAD)
 		return 0;
 
 	ret = collect_mappings(pid, &vmas, NULL);
@@ -1157,7 +1158,7 @@ static int pre_dump_one_task(struct pstree_item *item)
 		goto err_cure;
 	}
 
-	item->pid.virt = misc.pid;
+	item->pid->ns[0].virt = misc.pid;
 
 	mdc.pre_dump = true;
 
@@ -1180,7 +1181,7 @@ err_cure:
 
 static int dump_one_task(struct pstree_item *item)
 {
-	pid_t pid = item->pid.real;
+	pid_t pid = item->pid->real;
 	struct vm_area_list vmas;
 	struct parasite_ctl *parasite_ctl;
 	int ret, exit_code = -1;
@@ -1197,7 +1198,7 @@ static int dump_one_task(struct pstree_item *item)
 	pr_info("Dumping task (pid: %d)\n", pid);
 	pr_info("========================================\n");
 
-	if (item->pid.state == TASK_DEAD)
+	if (item->pid->state == TASK_DEAD)
 		/*
 		 * zombies are dumped separately in dump_zombies()
 		 */
@@ -1286,21 +1287,21 @@ static int dump_one_task(struct pstree_item *item)
 		goto err_cure_imgset;
 	}
 
-	item->pid.virt = misc.pid;
-	pstree_insert_pid(item->pid.virt, &item->pid);
+	item->pid->ns[0].virt = misc.pid;
+	pstree_insert_pid(item->pid->ns[0].virt, item->pid);
 	item->sid = misc.sid;
 	item->pgid = misc.pgid;
 
 	pr_info("sid=%d pgid=%d pid=%d\n",
-		item->sid, item->pgid, item->pid.virt);
+		item->sid, item->pgid, item->pid->ns[0].virt);
 
 	if (item->sid == 0) {
 		pr_err("A session leader of %d(%d) is outside of its pid namespace\n",
-			item->pid.real, item->pid.virt);
+			item->pid->real, item->pid->ns[0].virt);
 		goto err_cure;
 	}
 
-	cr_imgset = cr_task_imgset_open(item->pid.virt, O_DUMP);
+	cr_imgset = cr_task_imgset_open(item->pid->ns[0].virt, O_DUMP);
 	if (!cr_imgset)
 		goto err_cure;
 
@@ -1449,9 +1450,9 @@ static int cr_pre_dump_finish(int ret)
 		if (!ctl)
 			continue;
 
-		pr_info("\tPre-dumping %d\n", item->pid.virt);
+		pr_info("\tPre-dumping %d\n", item->pid->ns[0].virt);
 		timing_start(TIME_MEMWRITE);
-		ret = open_page_xfer(&xfer, CR_FD_PAGEMAP, item->pid.virt);
+		ret = open_page_xfer(&xfer, CR_FD_PAGEMAP, item->pid->ns[0].virt);
 		if (ret < 0)
 			goto err;
 
@@ -1500,7 +1501,7 @@ int cr_pre_dump_tasks(pid_t pid)
 	root_item = alloc_pstree_item();
 	if (!root_item)
 		goto err;
-	root_item->pid.real = pid;
+	root_item->pid->real = pid;
 
 	if (!opts.track_mem) {
 		pr_info("Enforcing memory tracking for pre-dump.\n");
@@ -1655,7 +1656,7 @@ int cr_dump_tasks(pid_t pid)
 	root_item = alloc_pstree_item();
 	if (!root_item)
 		goto err;
-	root_item->pid.real = pid;
+	root_item->pid->real = pid;
 
 	pre_dump_ret = run_scripts(ACT_PRE_DUMP);
 	if (pre_dump_ret != 0) {

criu/cr-service.c

@@ -195,7 +195,7 @@ int send_criu_rpc_script(enum script_actions act, char *name, int fd)
 		 * checking this.
 		 */
 		cn.has_pid = true;
-		cn.pid = root_item->pid.real;
+		cn.pid = root_item->pid->real;
 		break;
 	default:
 		break;
@@ -568,7 +568,7 @@ static int restore_using_req(int sk, CriuOpts *req)
 	success = true;
 exit:
 	if (send_criu_restore_resp(sk, success,
-				   root_item ? root_item->pid.real : -1) == -1) {
+				   root_item ? root_item->pid->real : -1) == -1) {
 		pr_perror("Can't send response");
 		success = false;
 	}

criu/file-lock.c

@@ -318,11 +318,11 @@ int note_file_lock(struct pid *pid, int fd, int lfd, struct fd_parms *p)
 				continue;
 		}
 
-		fl->real_owner = pid->virt;
+		fl->real_owner = pid->ns[0].virt;
 		fl->owners_fd = fd;
 
 		pr_info("Found lock entry %d.%d %d vs %d\n",
-				pid->real, pid->virt, fd,
+				pid->real, pid->ns[0].virt, fd,
 				fl->fl_owner);
 	}
 

criu/files-reg.c

@@ -383,7 +383,7 @@ static int open_remap_dead_process(struct reg_file_info *rfi,
 	if (!helper)
 		return -1;
 
-	if (helper->pid.state != TASK_UNDEF) {
+	if (helper->pid->state != TASK_UNDEF) {
 		pr_info("Skipping helper for restoring /proc/%d; pid exists\n", rfe->remap_id);
 		return 0;
 	}
@@ -392,11 +392,11 @@ static int open_remap_dead_process(struct reg_file_info *rfi,
 
 	helper->sid = root_item->sid;
 	helper->pgid = root_item->pgid;
-	helper->pid.virt = rfe->remap_id;
+	helper->pid->ns[0].virt = rfe->remap_id;
 	helper->parent = root_item;
 	list_add_tail(&helper->sibling, &root_item->children);
 
-	pr_info("Added a helper for restoring /proc/%d\n", helper->pid.virt);
+	pr_info("Added a helper for restoring /proc/%d\n", helper->pid->ns[0].virt);
 
 	return 0;
 }
@@ -822,14 +822,14 @@ int dead_pid_conflict(void)
 			 * If the dead PID was given to a main thread of another
 			 * process, this is handled during restore.
 			 */
-			item = container_of(node, struct pstree_item, pid);
-			if (item->pid.real == item->threads[i].real ||
-			    item->threads[i].virt != pid)
+			item = node->item;
+			if (item->pid->real == item->threads[i].real ||
+			    item->threads[i].ns[0].virt != pid)
 				continue;
 		}
 
 		pr_err("Conflict with a dead task with the same PID as of this thread (virt %d, real %d).\n",
-			node->virt, node->real);
+			node->ns[0].virt, node->real);
 		return -1;
 	}
 

criu/files.c

@@ -322,7 +322,7 @@ static int fill_fd_params(struct pid *owner_pid, int fd, int lfd,
 {
 	int ret;
 	struct statfs fsbuf;
-	struct fdinfo_common fdinfo = { .mnt_id = -1, .owner = owner_pid->virt };
+	struct fdinfo_common fdinfo = { .mnt_id = -1, .owner = owner_pid->ns[0].virt };
 
 	if (fstat(lfd, &p->stat) < 0) {
 		pr_perror("Can't stat fd %d", lfd);
@@ -529,7 +529,7 @@ int dump_task_files_seized(struct parasite_ctl *ctl, struct pstree_item *item,
 	int off, nr_fds = min((int) PARASITE_MAX_FDS, dfds->nr_fds);
 
 	pr_info("\n");
-	pr_info("Dumping opened files (pid: %d)\n", item->pid.real);
+	pr_info("Dumping opened files (pid: %d)\n", item->pid->real);
 	pr_info("----------------------------------------\n");
 
 	lfds = xmalloc(nr_fds * sizeof(int));
@@ -555,7 +555,7 @@ int dump_task_files_seized(struct parasite_ctl *ctl, struct pstree_item *item,
 			goto err;
 
 		for (i = 0; i < nr_fds; i++) {
-			ret = dump_one_file(&item->pid, dfds->fds[i + off],
+			ret = dump_one_file(item->pid, dfds->fds[i + off],
 						lfds[i], opts + i, img, ctl);
 			close(lfds[i]);
 			if (ret)
@@ -747,7 +747,7 @@ int dup_fle(struct pstree_item *task, struct fdinfo_list_entry *ple,
 	if (!e)
 		return -1;
 
-	return collect_fd(task->pid.virt, e, rsti(task));
+	return collect_fd(task->pid->ns[0].virt, e, rsti(task));
 }
 
 int prepare_ctl_tty(int pid, struct rst_info *rst_info, u32 ctl_tty_id)
@@ -781,7 +781,7 @@ int prepare_fd_pid(struct pstree_item *item)
 {
 	int ret = 0;
 	struct cr_img *img;
-	pid_t pid = item->pid.virt;
+	pid_t pid = item->pid->ns[0].virt;
 	struct rst_info *rst_info = rsti(item);
 
 	INIT_LIST_HEAD(&rst_info->used);
@@ -793,7 +793,7 @@ int prepare_fd_pid(struct pstree_item *item)
 	if (item->ids == NULL) /* zombie */
 		return 0;
 
-	if (rsti(item)->fdt && rsti(item)->fdt->pid != item->pid.virt)
+	if (rsti(item)->fdt && rsti(item)->fdt->pid != item->pid->ns[0].virt)
 		return 0;
 
 	img = open_image(CR_FD_FDINFO, O_RSTR, item->ids->files_id);
@@ -1176,7 +1176,7 @@ int prepare_fds(struct pstree_item *me)
 		futex_inc_and_wake(&fdt->fdt_lock);
 		futex_wait_while_lt(&fdt->fdt_lock, fdt->nr);
 
-		if (fdt->pid != me->pid.virt) {
+		if (fdt->pid != me->pid->ns[0].virt) {
 			pr_info("File descriptor table is shared with %d\n", fdt->pid);
 			futex_wait_until(&fdt->fdt_lock, fdt->nr + 1);
 			goto out;
@@ -1189,7 +1189,7 @@ int prepare_fds(struct pstree_item *me)
 			continue;
 		}
 
-		ret = open_fdinfos(me->pid.virt, &rsti(me)->fds, state);
+		ret = open_fdinfos(me->pid->ns[0].virt, &rsti(me)->fds, state);
 		if (ret)
 			break;
 
@@ -1197,7 +1197,7 @@ int prepare_fds(struct pstree_item *me)
 		 * Now handle TTYs. Slaves are delayed to be sure masters
 		 * are already opened.
 		 */
-		ret = open_fdinfos(me->pid.virt, &rsti(me)->tty_slaves, state);
+		ret = open_fdinfos(me->pid->ns[0].virt, &rsti(me)->tty_slaves, state);
 		if (ret)
 			break;
 
@@ -1206,7 +1206,7 @@ int prepare_fds(struct pstree_item *me)
 		 * to be already restored, thus we store them in a separate
 		 * list and restore at the very end.
 		 */
-		ret = open_fdinfos(me->pid.virt, &rsti(me)->eventpoll, state);
+		ret = open_fdinfos(me->pid->ns[0].virt, &rsti(me)->eventpoll, state);
 		if (ret)
 			break;
 	}
@@ -1224,7 +1224,7 @@ int prepare_fds(struct pstree_item *me)
 		 * Opening current TTYs require session to be already set up,
 		 * thus slave peers already handled now it's time for cttys,
 		 */
-		ret = open_fdinfos(me->pid.virt, &rsti(me)->tty_ctty, state);
+		ret = open_fdinfos(me->pid->ns[0].virt, &rsti(me)->tty_ctty, state);
 		if (ret)
 			break;
 	}
@@ -1310,7 +1310,7 @@ out:
 
 int prepare_fs_pid(struct pstree_item *item)
 {
-	pid_t pid = item->pid.virt;
+	pid_t pid = item->pid->ns[0].virt;
 	struct rst_info *ri = rsti(item);
 	struct cr_img *img;
 	FsEntry *fe;
@@ -1361,15 +1361,15 @@ int shared_fdt_prepare(struct pstree_item *item)
 
 		futex_init(&fdt->fdt_lock);
 		fdt->nr = 1;
-		fdt->pid = parent->pid.virt;
+		fdt->pid = parent->pid->ns[0].virt;
 	} else
 		fdt = rsti(parent)->fdt;
 
 	rsti(item)->fdt = fdt;
 	rsti(item)->service_fd_id = fdt->nr;
 	fdt->nr++;
-	if (pid_rst_prio(item->pid.virt, fdt->pid))
-		fdt->pid = item->pid.virt;
+	if (pid_rst_prio(item->pid->ns[0].virt, fdt->pid))
+		fdt->pid = item->pid->ns[0].virt;
 
 	return 0;
 }
@@ -1667,7 +1667,7 @@ int inherit_fd_fini()
 int open_transport_socket(void)
 {
 	struct fdt *fdt = rsti(current)->fdt;
-	pid_t pid = current->pid.virt;
+	pid_t pid = current->pid->ns[0].virt;
 	struct sockaddr_un saddr;
 	int sock, slen;
 

criu/filesystems.c

@@ -407,7 +407,7 @@ static int tmpfs_dump(struct mount_info *pm)
 	sprintf(tmpfs_path, "/proc/self/fd/%d", fd);
 
 	if (root_ns_mask & CLONE_NEWUSER)
-		userns_pid = root_item->pid.real;
+		userns_pid = root_item->pid->real;
 
 	ret = cr_system_userns(-1, img_raw_fd(img), -1, "tar", (char *[])
 			{ "tar", "--create",

criu/image.c

@@ -107,10 +107,11 @@ int write_img_inventory(InventoryEntry *he)
 
 int prepare_inventory(InventoryEntry *he)
 {
+	struct pid pid;
 	struct {
 		struct pstree_item i;
 		struct dmp_info d;
-	} crt = { };
+	} crt = { .i.pid = &pid };
 
 	pr_info("Perparing image inventory (version %u)\n", CRTOOLS_IMAGES_V1);
 
@@ -122,8 +123,8 @@ int prepare_inventory(InventoryEntry *he)
 	he->has_lsmtype = true;
 	he->lsmtype = host_lsm_type();
 
-	crt.i.pid.state = TASK_ALIVE;
-	crt.i.pid.real = getpid();
+	crt.i.pid->state = TASK_ALIVE;
+	crt.i.pid->real = getpid();
 	if (get_task_ids(&crt.i))
 		return -1;
 

criu/include/pid.h

@@ -13,16 +13,17 @@ struct pid {
 	 */
 	pid_t real;
 
+	int state;	/* TASK_XXX constants */
+
 	/*
 	 * The @virt pid is one which used in the image itself and keeps
 	 * the pid value to be restored. This pid fetched from the
 	 * dumpee context, because the dumpee might have own pid namespace.
 	 */
-	pid_t virt;
-
-	int state;	/* TASK_XXX constants */
-
-	struct rb_node node;
+	struct {
+		pid_t virt;
+		struct rb_node node;
+	} ns[1]; /* Must be at the end of struct pid */
 };
 
 #define TASK_UNDEF		0x0

criu/include/pstree.h

@@ -15,7 +15,7 @@ struct pstree_item {
 	struct list_head	children;	/* list of my children */
 	struct list_head	sibling;	/* linkage in my parent's children list */
 
-	struct pid		pid;
+	struct pid		*pid;
 	pid_t			pgid;
 	pid_t			sid;
 	pid_t			born_sid;
@@ -66,7 +66,7 @@ static inline bool is_alive_state(int state)
 
 static inline bool task_alive(struct pstree_item *i)
 {
-	return is_alive_state(i->pid.state);
+	return is_alive_state(i->pid->state);
 }
 
 extern void free_pstree(struct pstree_item *root_item);

criu/irmap.c

@@ -237,7 +237,7 @@ char *irmap_lookup(unsigned int s_dev, unsigned long i_ino)
 	 * irmap_predump_prep, so we just go ahead and scan.
 	 */
 	if (!doing_predump &&
-			__mntns_get_root_fd(root_item->pid.real) < 0)
+			__mntns_get_root_fd(root_item->pid->real) < 0)
 		goto out;
 
 	timing_start(TIME_IRMAP_RESOLVE);
@@ -333,7 +333,7 @@ int irmap_predump_prep(void)
 	 */
 
 	doing_predump = true;
-	return __mntns_get_root_fd(root_item->pid.real) < 0 ? -1 : 0;
+	return __mntns_get_root_fd(root_item->pid->real) < 0 ? -1 : 0;
 }
 
 int irmap_predump_run(void)

criu/mem.c

@@ -278,7 +278,7 @@ static int __parasite_dump_pages_seized(struct pstree_item *item,
 	unsigned long pmc_size;
 
 	pr_info("\n");
-	pr_info("Dumping pages (type: %d pid: %d)\n", CR_FD_PAGES, item->pid.real);
+	pr_info("Dumping pages (type: %d pid: %d)\n", CR_FD_PAGES, item->pid->real);
 	pr_info("----------------------------------------\n");
 
 	timing_start(TIME_MEMDUMP);
@@ -292,7 +292,7 @@ static int __parasite_dump_pages_seized(struct pstree_item *item,
 
 	pmc_size = max(vma_area_list->priv_longest,
 		vma_area_list->shared_longest);
-	if (pmc_init(&pmc, item->pid.real, &vma_area_list->h,
+	if (pmc_init(&pmc, item->pid->real, &vma_area_list->h,
 			 pmc_size * PAGE_SIZE))
 		return -1;
 
@@ -315,11 +315,11 @@ static int __parasite_dump_pages_seized(struct pstree_item *item,
 		 * right here. For pre-dumps the pp will be taken by the
 		 * caller and handled later.
 		 */
-		ret = open_page_xfer(&xfer, CR_FD_PAGEMAP, item->pid.virt);
+		ret = open_page_xfer(&xfer, CR_FD_PAGEMAP, item->pid->ns[0].virt);
 		if (ret < 0)
 			goto out_pp;
 	} else {
-		ret = check_parent_page_xfer(CR_FD_PAGEMAP, item->pid.virt);
+		ret = check_parent_page_xfer(CR_FD_PAGEMAP, item->pid->ns[0].virt);
 		if (ret < 0)
 			goto out_pp;
 
@@ -349,7 +349,7 @@ static int __parasite_dump_pages_seized(struct pstree_item *item,
 		if (!map)
 			goto out_xfer;
 		if (vma_area_is(vma_area, VMA_ANON_SHARED))
-			ret = add_shmem_area(item->pid.real, vma_area->e, map);
+			ret = add_shmem_area(item->pid->real, vma_area->e, map);
 		else {
 again:
 			ret = generate_iovs(vma_area, pp, map, &off,
@@ -382,7 +382,7 @@ again:
 	 * Step 4 -- clean up
 	 */
 
-	ret = task_reset_dirty_track(item->pid.real);
+	ret = task_reset_dirty_track(item->pid->real);
 out_xfer:
 	if (!mdc->pre_dump)
 		xfer.close(&xfer);
@@ -445,7 +445,7 @@ int parasite_dump_pages_seized(struct pstree_item *item,
 
 int prepare_mm_pid(struct pstree_item *i)
 {
-	pid_t pid = i->pid.virt;
+	pid_t pid = i->pid->ns[0].virt;
 	int ret = -1, vn = 0;
 	struct cr_img *img;
 	struct rst_info *ri = rsti(i);
@@ -531,7 +531,7 @@ static int map_private_vma(struct pstree_item *t,
 	struct vma_area *p = *pvma;
 
 	if (vma_area_is(vma, VMA_FILE_PRIVATE)) {
-		ret = vma->vm_open(t->pid.virt, vma);
+		ret = vma->vm_open(t->pid->ns[0].virt, vma);
 		if (ret < 0) {
 			pr_err("Can't fixup VMA's fd\n");
 			return -1;
@@ -695,7 +695,7 @@ static int restore_priv_vma_content(struct pstree_item *t)
 
 	vma = list_first_entry(vmas, struct vma_area, list);
 
-	ret = open_page_read(t->pid.virt, &pr, PR_TASK);
+	ret = open_page_read(t->pid->ns[0].virt, &pr, PR_TASK);
 	if (ret <= 0)
 		return -1;
 
@@ -913,7 +913,7 @@ int unmap_guard_pages(struct pstree_item *t)
 
 int open_vmas(struct pstree_item *t)
 {
-	int pid = t->pid.virt;
+	int pid = t->pid->ns[0].virt;
 	struct vma_area *vma;
 	struct vm_area_list *vmas = &rsti(t)->vmas;
 

criu/mount.c

@@ -150,9 +150,9 @@ static struct mount_info *__lookup_overlayfs(struct mount_info *list, char *rpat
 		 * to make sure we stat the correct file
 		 */
 		if (mntns_root == -1) {
-			mntns_root = __mntns_get_root_fd(root_item->pid.real);
+			mntns_root = __mntns_get_root_fd(root_item->pid->real);
 			if (mntns_root < 0) {
-				pr_err("Unable to get the root file descriptor of pid %d\n", root_item->pid.real);
+				pr_err("Unable to get the root file descriptor of pid %d\n", root_item->pid->real);
 				return ERR_PTR(-ENOENT);
 			}
 		}
@@ -2679,7 +2679,7 @@ static int do_restore_task_mnt_ns(struct ns_id *nsid, struct pstree_item *curren
 {
 	int fd;
 
-	fd = open_proc(root_item->pid.virt, "fd/%d", nsid->mnt.ns_fd);
+	fd = open_proc(root_item->pid->ns[0].virt, "fd/%d", nsid->mnt.ns_fd);
 	if (fd < 0)
 		return -1;
 
@@ -3196,7 +3196,7 @@ int mntns_get_root_fd(struct ns_id *mntns)
 	if (!mntns->ns_populated) {
 		int fd;
 
-		fd = open_proc(root_item->pid.virt, "fd/%d", mntns->mnt.root_fd);
+		fd = open_proc(root_item->pid->ns[0].virt, "fd/%d", mntns->mnt.root_fd);
 		if (fd < 0)
 			return -1;
 

criu/namespaces.c

@@ -309,7 +309,7 @@ struct ns_id *rst_new_ns_id(unsigned int id, pid_t pid,
 
 int rst_add_ns_id(unsigned int id, struct pstree_item *i, struct ns_desc *nd)
 {
-	pid_t pid = i->pid.virt;
+	pid_t pid = i->pid->ns[0].virt;
 	struct ns_id *nsid;
 
 	nsid = lookup_ns_by_id(id, nd);
@@ -401,7 +401,7 @@ static unsigned int generate_ns_id(int pid, unsigned int kid, struct ns_desc *nd
 
 	if (pid != getpid()) {
 		type = NS_OTHER;
-		if (pid == root_item->pid.real) {
+		if (pid == root_item->pid->real) {
 			BUG_ON(root_ns_mask & nd->cflag);
 			pr_info("Will take %s namespace in the image\n", nd->str);
 			root_ns_mask |= nd->cflag;
@@ -549,7 +549,7 @@ static int open_ns_fd(struct file_desc *d)
 		return -1;
 	}
 
-	snprintf(path, sizeof(path) - 1, "/proc/%d/ns/%s", item->pid.virt, nd->str);
+	snprintf(path, sizeof(path) - 1, "/proc/%d/ns/%s", item->pid->ns[0].virt, nd->str);
 	path[sizeof(path) - 1] = '\0';
 
 	fd = open(path, nfi->nfe->flags);
@@ -593,7 +593,7 @@ struct collect_image_info nsfile_cinfo = {
 
 int predump_task_ns_ids(struct pstree_item *item)
 {
-	int pid = item->pid.real;
+	int pid = item->pid->real;
 
 	if (!__get_ns_id(pid, &net_ns_desc, NULL, &dmpi(item)->netns))
 		return -1;
@@ -606,7 +606,7 @@ int predump_task_ns_ids(struct pstree_item *item)
 
 int dump_task_ns_ids(struct pstree_item *item)
 {
-	int pid = item->pid.real;
+	int pid = item->pid->real;
 	TaskKobjIdsEntry *ids = item->ids;
 
 	ids->has_pid_ns_id = true;
@@ -790,7 +790,7 @@ int collect_user_ns(struct ns_id *ns, void *oarg)
 	 * mappings, which are used for convirting local id-s to
 	 * userns id-s (userns_uid(), userns_gid())
 	 */
-	if (dump_user_ns(root_item->pid.real, root_item->ids->user_ns_id))
+	if (dump_user_ns(root_item->pid->real, root_item->ids->user_ns_id))
 		return -1;
 
 	return 0;
@@ -994,7 +994,7 @@ static int do_dump_namespaces(struct ns_id *ns)
 
 int dump_namespaces(struct pstree_item *item, unsigned int ns_flags)
 {
-	struct pid *ns_pid = &item->pid;
+	struct pid *ns_pid = item->pid;
 	struct ns_id *ns;
 	int pid, nr = 0;
 	int ret = 0;
@@ -1010,9 +1010,9 @@ int dump_namespaces(struct pstree_item *item, unsigned int ns_flags)
 	 * net namespace with this is still open
 	 */
 
-	pr_info("Dumping %d(%d)'s namespaces\n", ns_pid->virt, ns_pid->real);
+	pr_info("Dumping %d(%d)'s namespaces\n", ns_pid->ns[0].virt, ns_pid->real);
 
-	if ((ns_flags & CLONE_NEWPID) && ns_pid->virt != 1) {
+	if ((ns_flags & CLONE_NEWPID) && ns_pid->ns[0].virt != 1) {
 		pr_err("Can't dump a pid namespace without the process init\n");
 		return -1;
 	}
@@ -1472,10 +1472,10 @@ int prepare_userns(struct pstree_item *item)
 	if (ret < 0)
 		return -1;
 
-	if (write_id_map(item->pid.real, e->uid_map, e->n_uid_map, "uid_map"))
+	if (write_id_map(item->pid->real, e->uid_map, e->n_uid_map, "uid_map"))
 		return -1;
 
-	if (write_id_map(item->pid.real, e->gid_map, e->n_gid_map, "gid_map"))
+	if (write_id_map(item->pid->real, e->gid_map, e->n_gid_map, "gid_map"))
 		return -1;
 
 	return 0;
@@ -1644,11 +1644,11 @@ err_out:
 
 int prepare_namespace(struct pstree_item *item, unsigned long clone_flags)
 {
-	pid_t pid = item->pid.virt;
+	pid_t pid = item->pid->ns[0].virt;
 	int id;
 
 	pr_info("Restoring namespaces %d flags 0x%lx\n",
-			item->pid.virt, clone_flags);
+			item->pid->ns[0].virt, clone_flags);
 
 	if ((clone_flags & CLONE_NEWUSER) && prepare_userns_creds())
 		return -1;

criu/net.c

@@ -1774,7 +1774,7 @@ int network_lock_internal()
 				"COMMIT\n";
 	int ret = 0, nsret;
 
-	if (switch_ns(root_item->pid.real, &net_ns_desc, &nsret))
+	if (switch_ns(root_item->pid->real, &net_ns_desc, &nsret))
 		return -1;
 
 
@@ -1798,7 +1798,7 @@ static int network_unlock_internal()
 			"COMMIT\n";
 	int ret = 0, nsret;
 
-	if (switch_ns(root_item->pid.real, &net_ns_desc, &nsret))
+	if (switch_ns(root_item->pid->real, &net_ns_desc, &nsret))
 		return -1;
 
 

criu/parasite-syscall.c

@@ -652,7 +652,7 @@ int parasite_dump_thread_seized(struct parasite_ctl *ctl, int id,
 		return -1;
 	}
 
-	tid->virt = args->tid;
+	tid->ns[0].virt = args->tid;
 	return dump_thread_core(pid, core, args);
 }
 

criu/proc_parse.c

@@ -2220,7 +2220,7 @@ int parse_threads(int pid, struct pid **_t, int *_n)
 				return -1;
 			}
 			t = tmp;
-			t[nr - 1].virt = -1;
+			t[nr - 1].ns[0].virt = -1;
 		}
 		t[nr - 1].real = atoi(de->d_name);
 		t[nr - 1].state = TASK_THREAD;

criu/seccomp.c

@@ -49,7 +49,7 @@ static int collect_filter_for_pstree(struct pstree_item *item)
 	struct sock_filter buf[BPF_MAXINSNS];
 	void *m;
 
-	if (item->pid.state == TASK_DEAD ||
+	if (item->pid->state == TASK_DEAD ||
 	    dmpi(item)->pi_creds->seccomp_mode != SECCOMP_MODE_FILTER)
 		return 0;
 
@@ -57,7 +57,7 @@ static int collect_filter_for_pstree(struct pstree_item *item)
 		int len;
 		struct seccomp_info *info, *inherited = NULL;
 
-		len = ptrace(PTRACE_SECCOMP_GET_FILTER, item->pid.real, i, buf);
+		len = ptrace(PTRACE_SECCOMP_GET_FILTER, item->pid->real, i, buf);
 		if (len < 0) {
 			if (errno == ENOENT) {
 				/* end of the search */

criu/seize.c

@@ -437,7 +437,7 @@ static inline bool child_collected(struct pstree_item *i, pid_t pid)
 	struct pstree_item *c;
 
 	list_for_each_entry(c, &i->children, sibling)
-		if (c->pid.real == pid)
+		if (c->pid->real == pid)
 			return true;
 
 	return false;
@@ -449,7 +449,7 @@ static int collect_children(struct pstree_item *item)
 	pid_t *ch;
 	int ret, i, nr_children, nr_inprogress;
 
-	ret = parse_children(item->pid.real, &ch, &nr_children);
+	ret = parse_children(item->pid->real, &ch, &nr_children);
 	if (ret < 0)
 		return ret;
 
@@ -488,7 +488,7 @@ static int collect_children(struct pstree_item *item)
 			goto free;
 		}
 
-		ret = seize_wait_task(pid, item->pid.real, creds);
+		ret = seize_wait_task(pid, item->pid->real, creds);
 		if (ret < 0) {
 			/*
 			 * Here is a race window between parse_children() and seize(),
@@ -509,9 +509,9 @@ static int collect_children(struct pstree_item *item)
 			processes_to_wait--;
 
 		dmpi(c)->pi_creds = creds;
-		c->pid.real = pid;
+		c->pid->real = pid;
 		c->parent = item;
-		c->pid.state = ret;
+		c->pid->state = ret;
 		list_add_tail(&c->sibling, &item->children);
 
 		/* Here is a recursive call (Depth-first search) */
@@ -528,7 +528,7 @@ static void unseize_task_and_threads(const struct pstree_item *item, int st)
 {
 	int i;
 
-	if (item->pid.state == TASK_DEAD)
+	if (item->pid->state == TASK_DEAD)
 		return;
 
 	/*
@@ -536,7 +536,7 @@ static void unseize_task_and_threads(const struct pstree_item *item, int st)
 	 * the item->state is the state task was in when we seized one.
 	 */
 
-	unseize_task(item->pid.real, item->pid.state, st);
+	unseize_task(item->pid->real, item->pid->state, st);
 
 	if (st == TASK_DEAD)
 		return;
@@ -553,7 +553,7 @@ static void pstree_wait(struct pstree_item *root_item)
 
 	for_each_pstree_item(item) {
 
-		if (item->pid.state == TASK_DEAD)
+		if (item->pid->state == TASK_DEAD)
 			continue;
 
 		for (i = 0; i < item->nr_threads; i++) {
@@ -607,14 +607,14 @@ void pstree_switch_state(struct pstree_item *root_item, int st)
 static pid_t item_ppid(const struct pstree_item *item)
 {
 	item = item->parent;
-	return item ? item->pid.real : -1;
+	return item ? item->pid->real : -1;
 }
 
 static inline bool thread_collected(struct pstree_item *i, pid_t tid)
 {
 	int t;
 
-	if (i->pid.real == tid) /* thread leader is collected as task */
+	if (i->pid->real == tid) /* thread leader is collected as task */
 		return true;
 
 	for (t = 0; t < i->nr_threads; t++)
@@ -678,11 +678,11 @@ static int collect_threads(struct pstree_item *item)
 	struct pid *threads = NULL;
 	int nr_threads = 0, i = 0, ret, nr_inprogress, nr_stopped = 0;
 
-	ret = parse_threads(item->pid.real, &threads, &nr_threads);
+	ret = parse_threads(item->pid->real, &threads, &nr_threads);
 	if (ret < 0)
 		goto err;
 
-	if ((item->pid.state == TASK_DEAD) && (nr_threads > 1)) {
+	if ((item->pid->state == TASK_DEAD) && (nr_threads > 1)) {
 		pr_err("Zombies with threads are not supported\n");
 		goto err;
 	}
@@ -693,7 +693,7 @@ static int collect_threads(struct pstree_item *item)
 		return -1;
 
 	if (item->nr_threads == 0) {
-		item->threads[0].real = item->pid.real;
+		item->threads[0].real = item->pid->real;
 		item->nr_threads = 1;
 		item->threads[0].item = NULL;
 	}
@@ -709,7 +709,7 @@ static int collect_threads(struct pstree_item *item)
 		nr_inprogress++;
 
 		pr_info("\tSeizing %d's %d thread\n",
-				item->pid.real, pid);
+				item->pid->real, pid);
 
 		if (!opts.freeze_cgroup && seize_catch_task(pid))
 			continue;
@@ -810,7 +810,7 @@ static int collect_task(struct pstree_item *item)
 	if (ret < 0)
 		goto err_close;
 
-	if ((item->pid.state == TASK_DEAD) && !list_empty(&item->children)) {
+	if ((item->pid->state == TASK_DEAD) && !list_empty(&item->children)) {
 		pr_err("Zombie with children?! O_o Run, run, run!\n");
 		goto err_close;
 	}
@@ -818,7 +818,7 @@ static int collect_task(struct pstree_item *item)
 	if (pstree_alloc_cores(item))
 		goto err_close;
 
-	pr_info("Collected %d in %d state\n", item->pid.real, item->pid.state);
+	pr_info("Collected %d in %d state\n", item->pid->real, item->pid->state);
 	return 0;
 
 err_close:
@@ -828,7 +828,7 @@ err_close:
 
 int collect_pstree(void)
 {
-	pid_t pid = root_item->pid.real;
+	pid_t pid = root_item->pid->real;
 	int ret = -1;
 	struct proc_status_creds *creds;
 
@@ -863,7 +863,7 @@ int collect_pstree(void)
 		processes_to_wait--;
 
 	pr_info("Seized task %d, state %d\n", pid, ret);
-	root_item->pid.state = ret;
+	root_item->pid->state = ret;
 	dmpi(root_item)->pi_creds = creds;
 
 	ret = collect_task(root_item);

criu/tty.c

@@ -1001,7 +1001,7 @@ static int pty_open_unpaired_slave(struct file_desc *d, struct tty_info *slave)
 		 * checkpoint complete process tree together with
 		 * the process which keeps the master peer.
 		 */
-		if (root_item->sid != root_item->pid.virt) {
+		if (root_item->sid != root_item->pid->ns[0].virt) {
 			pr_debug("Restore inherited group %d\n",
 				 getpgid(getppid()));
 			if (tty_set_prgp(fd, getpgid(getppid())))
@@ -1242,10 +1242,10 @@ static int tty_find_restoring_task(struct tty_info *info)
 		 * for us.
 		 */
 		item = find_first_sid(info->tie->sid);
-		if (item && item->pid.virt == item->sid) {
+		if (item && item->pid->ns[0].virt == item->sid) {
 			pr_info("Set a control terminal %#x to %d\n",
 				info->tfe->id, info->tie->sid);
-			return prepare_ctl_tty(item->pid.virt,
+			return prepare_ctl_tty(item->pid->ns[0].virt,
 					       rsti(item),
 					       info->tfe->id);
 		}
@@ -1651,7 +1651,7 @@ int dump_verify_tty_sids(void)
 		if (!ret && dinfo->sid) {
 			struct pstree_item *item = find_first_sid(dinfo->sid);
 
-			if (!item || item->pid.virt != dinfo->sid) {
+			if (!item || item->pid->ns[0].virt != dinfo->sid) {
 				if (!opts.shell_job) {
 					pr_err("Found dangling tty with sid %d pgid %d (%s) on peer fd %d.\n",
 					       dinfo->sid, dinfo->pgrp,