The ns_cgroup is an annoying cgroup at the namespace / cgroup frontier. For example, a single process can not handle a big amount of namespaces without interacting with this cgroup and falling in an exponential creation time due to the nested cgroup directory depth (eg. /cgroup/<pid>/.../<pid>/...).
That was spotted when creating a single process using multiple network namespaces, the objective was 4096 network namespaces, but at 820 netns, the creation time was dramatically slow and the creation time for a namespace increased from 10msec to 10sec. After five hours, the expected numbers of netns was not reached. Without the ns_cgroup interaction, 4K netns are created after 2 minutes. In order to solve that, we have to mount the cgroup with all the subsystems except the ns_cgroup, it's a little weird and hard to manage from an administration pov because we have to know what are the cgroup available on the system and we can't do a simple 'mount -t cgroup cgroup /cgroup'. With the previous patch which adds a 'clone_child' parameter to a cgroup, we should be able to remove the ns_cgroup and manage manually the creation + adding a task to the cgroup consistenly with the rest of the subsystems. This patch removes the ns_cgroup as suggested in the following thread: https://lists.linux-foundation.org/pipermail/containers/2009-June/018616.html The 'cgroup_clone' function is removed because it is no longer used. All the ns_cgroup.c code is removed, so we don't have the rules for attaching a task to a cgroup, but I am not sure it's really relevant. Because we must have the CAP_SYS_ADMIN for unsharing a namespace or to create a cgroup. Concerning cgroup hierarchy vs process attachment I am not sure to understand what is the goal of these checks and what are they for. Signed-off-by: Daniel Lezcano <[email protected]> Cc: Eric W. Biederman <[email protected]> Cc: Paul Menage <[email protected]> Cc: Serge E. Hallyn <[email protected]> Cc: Jamal Hadi Salim <[email protected]> --- include/linux/cgroup.h | 3 - include/linux/cgroup_subsys.h | 6 -- init/Kconfig | 9 --- kernel/Makefile | 1 kernel/cgroup.c | 116 ------------------------------------------ kernel/fork.c | 6 -- kernel/ns_cgroup.c | 110 --------------------------------------- kernel/nsproxy.c | 15 +---- 8 files changed, 3 insertions(+), 263 deletions(-) Index: linux-2.6/include/linux/cgroup.h =================================================================== --- linux-2.6.orig/include/linux/cgroup.h +++ linux-2.6/include/linux/cgroup.h @@ -499,9 +499,6 @@ static inline struct cgroup* task_cgroup return task_subsys_state(task, subsys_id)->cgroup; } -int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *ss, - char *nodename); - /* A cgroup_iter should be treated as an opaque object */ struct cgroup_iter { struct list_head *cg_link; Index: linux-2.6/init/Kconfig =================================================================== --- linux-2.6.orig/init/Kconfig +++ linux-2.6/init/Kconfig @@ -512,15 +512,6 @@ config CGROUP_DEBUG Say N if unsure. -config CGROUP_NS - bool "Namespace cgroup subsystem" - depends on CGROUPS - help - Provides a simple namespace cgroup subsystem to - provide hierarchical naming of sets of namespaces, - for instance virtual servers and checkpoint/restart - jobs. - config CGROUP_FREEZER bool "Freezer cgroup subsystem" depends on CGROUPS Index: linux-2.6/kernel/Makefile =================================================================== --- linux-2.6.orig/kernel/Makefile +++ linux-2.6/kernel/Makefile @@ -61,7 +61,6 @@ obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CGROUPS) += cgroup.o obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o obj-$(CONFIG_CPUSETS) += cpuset.o -obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o obj-$(CONFIG_UTS_NS) += utsname.o obj-$(CONFIG_USER_NS) += user_namespace.o obj-$(CONFIG_PID_NS) += pid_namespace.o Index: linux-2.6/kernel/cgroup.c =================================================================== --- linux-2.6.orig/kernel/cgroup.c +++ linux-2.6/kernel/cgroup.c @@ -3564,122 +3564,6 @@ void cgroup_exit(struct task_struct *tsk } /** - * cgroup_clone - clone the cgroup the given subsystem is attached to - * @tsk: the task to be moved - * @subsys: the given subsystem - * @nodename: the name for the new cgroup - * - * Duplicate the current cgroup in the hierarchy that the given - * subsystem is attached to, and move this task into the new - * child. - */ -int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, - char *nodename) -{ - struct dentry *dentry; - int ret = 0; - struct cgroup *parent, *child; - struct inode *inode; - struct css_set *cg; - struct cgroupfs_root *root; - struct cgroup_subsys *ss; - - /* We shouldn't be called by an unregistered subsystem */ - BUG_ON(!subsys->active); - - /* First figure out what hierarchy and cgroup we're dealing - * with, and pin them so we can drop cgroup_mutex */ - mutex_lock(&cgroup_mutex); - again: - root = subsys->root; - if (root == &rootnode) { - mutex_unlock(&cgroup_mutex); - return 0; - } - - /* Pin the hierarchy */ - if (!atomic_inc_not_zero(&root->sb->s_active)) { - /* We race with the final deactivate_super() */ - mutex_unlock(&cgroup_mutex); - return 0; - } - - /* Keep the cgroup alive */ - task_lock(tsk); - parent = task_cgroup(tsk, subsys->subsys_id); - cg = tsk->cgroups; - get_css_set(cg); - task_unlock(tsk); - - mutex_unlock(&cgroup_mutex); - - /* Now do the VFS work to create a cgroup */ - inode = parent->dentry->d_inode; - - /* Hold the parent directory mutex across this operation to - * stop anyone else deleting the new cgroup */ - mutex_lock(&inode->i_mutex); - dentry = lookup_one_len(nodename, parent->dentry, strlen(nodename)); - if (IS_ERR(dentry)) { - printk(KERN_INFO - "cgroup: Couldn't allocate dentry for %s: %ld\n", nodename, - PTR_ERR(dentry)); - ret = PTR_ERR(dentry); - goto out_release; - } - - /* Create the cgroup directory, which also creates the cgroup */ - ret = vfs_mkdir(inode, dentry, 0755); - child = __d_cgrp(dentry); - dput(dentry); - if (ret) { - printk(KERN_INFO - "Failed to create cgroup %s: %d\n", nodename, - ret); - goto out_release; - } - - /* The cgroup now exists. Retake cgroup_mutex and check - * that we're still in the same state that we thought we - * were. */ - mutex_lock(&cgroup_mutex); - if ((root != subsys->root) || - (parent != task_cgroup(tsk, subsys->subsys_id))) { - /* Aargh, we raced ... */ - mutex_unlock(&inode->i_mutex); - put_css_set(cg); - - deactivate_super(root->sb); - /* The cgroup is still accessible in the VFS, but - * we're not going to try to rmdir() it at this - * point. */ - printk(KERN_INFO - "Race in cgroup_clone() - leaking cgroup %s\n", - nodename); - goto again; - } - - /* do any required auto-setup */ - for_each_subsys(root, ss) { - if (ss->post_clone) - ss->post_clone(ss, child); - } - - /* All seems fine. Finish by moving the task into the new cgroup */ - ret = cgroup_attach_task(child, tsk); - mutex_unlock(&cgroup_mutex); - - out_release: - mutex_unlock(&inode->i_mutex); - - mutex_lock(&cgroup_mutex); - put_css_set(cg); - mutex_unlock(&cgroup_mutex); - deactivate_super(root->sb); - return ret; -} - -/** * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp * @cgrp: the cgroup in question * @task: the task in question Index: linux-2.6/kernel/fork.c =================================================================== --- linux-2.6.orig/kernel/fork.c +++ linux-2.6/kernel/fork.c @@ -1184,12 +1184,6 @@ static struct task_struct *copy_process( if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; - if (current->nsproxy != p->nsproxy) { - retval = ns_cgroup_clone(p, pid); - if (retval) - goto bad_fork_free_pid; - } - p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? Index: linux-2.6/kernel/ns_cgroup.c =================================================================== --- linux-2.6.orig/kernel/ns_cgroup.c +++ /dev/null @@ -1,110 +0,0 @@ -/* - * ns_cgroup.c - namespace cgroup subsystem - * - * Copyright 2006, 2007 IBM Corp - */ - -#include <linux/module.h> -#include <linux/cgroup.h> -#include <linux/fs.h> -#include <linux/proc_fs.h> -#include <linux/slab.h> -#include <linux/nsproxy.h> - -struct ns_cgroup { - struct cgroup_subsys_state css; -}; - -struct cgroup_subsys ns_subsys; - -static inline struct ns_cgroup *cgroup_to_ns( - struct cgroup *cgroup) -{ - return container_of(cgroup_subsys_state(cgroup, ns_subsys_id), - struct ns_cgroup, css); -} - -int ns_cgroup_clone(struct task_struct *task, struct pid *pid) -{ - char name[PROC_NUMBUF]; - - snprintf(name, PROC_NUMBUF, "%d", pid_vnr(pid)); - return cgroup_clone(task, &ns_subsys, name); -} - -/* - * Rules: - * 1. you can only enter a cgroup which is a descendant of your current - * cgroup - * 2. you can only place another process into a cgroup if - * a. you have CAP_SYS_ADMIN - * b. your cgroup is an ancestor of task's destination cgroup - * (hence either you are in the same cgroup as task, or in an - * ancestor cgroup thereof) - */ -static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup, - struct task_struct *task, bool threadgroup) -{ - if (current != task) { - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (!cgroup_is_descendant(new_cgroup, current)) - return -EPERM; - } - - if (!cgroup_is_descendant(new_cgroup, task)) - return -EPERM; - - if (threadgroup) { - struct task_struct *c; - rcu_read_lock(); - list_for_each_entry_rcu(c, &task->thread_group, thread_group) { - if (!cgroup_is_descendant(new_cgroup, c)) { - rcu_read_unlock(); - return -EPERM; - } - } - rcu_read_unlock(); - } - - return 0; -} - -/* - * Rules: you can only create a cgroup if - * 1. you are capable(CAP_SYS_ADMIN) - * 2. the target cgroup is a descendant of your own cgroup - */ -static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss, - struct cgroup *cgroup) -{ - struct ns_cgroup *ns_cgroup; - - if (!capable(CAP_SYS_ADMIN)) - return ERR_PTR(-EPERM); - if (!cgroup_is_descendant(cgroup, current)) - return ERR_PTR(-EPERM); - - ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL); - if (!ns_cgroup) - return ERR_PTR(-ENOMEM); - return &ns_cgroup->css; -} - -static void ns_destroy(struct cgroup_subsys *ss, - struct cgroup *cgroup) -{ - struct ns_cgroup *ns_cgroup; - - ns_cgroup = cgroup_to_ns(cgroup); - kfree(ns_cgroup); -} - -struct cgroup_subsys ns_subsys = { - .name = "ns", - .can_attach = ns_can_attach, - .create = ns_create, - .destroy = ns_destroy, - .subsys_id = ns_subsys_id, -}; Index: linux-2.6/kernel/nsproxy.c =================================================================== --- linux-2.6.orig/kernel/nsproxy.c +++ linux-2.6/kernel/nsproxy.c @@ -170,8 +170,6 @@ void free_nsproxy(struct nsproxy *ns) int unshare_nsproxy_namespaces(unsigned long unshare_flags, struct nsproxy **new_nsp, struct fs_struct *new_fs) { - int err = 0; - if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWNET))) return 0; @@ -181,17 +179,10 @@ int unshare_nsproxy_namespaces(unsigned *new_nsp = create_new_namespaces(unshare_flags, current, new_fs ? new_fs : current->fs); - if (IS_ERR(*new_nsp)) { - err = PTR_ERR(*new_nsp); - goto out; - } + if (IS_ERR(*new_nsp)) + return PTR_ERR(*new_nsp); - err = ns_cgroup_clone(current, task_pid(current)); - if (err) - put_nsproxy(*new_nsp); - -out: - return err; + return 0; } void switch_task_namespaces(struct task_struct *p, struct nsproxy *new) Index: linux-2.6/include/linux/cgroup_subsys.h =================================================================== --- linux-2.6.orig/include/linux/cgroup_subsys.h +++ linux-2.6/include/linux/cgroup_subsys.h @@ -19,12 +19,6 @@ SUBSYS(debug) /* */ -#ifdef CONFIG_CGROUP_NS -SUBSYS(ns) -#endif - -/* */ - #ifdef CONFIG_CGROUP_SCHED SUBSYS(cpu_cgroup) #endif _______________________________________________ Containers mailing list [email protected] https://lists.linux-foundation.org/mailman/listinfo/containers _______________________________________________ Devel mailing list [email protected] https://openvz.org/mailman/listinfo/devel
