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_children' 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. Changelog: Jul 29 (seh): remove references to ns_cgroup_clone(), fix up some documentation, and remove CONFIG_CGROUP_NS references. Signed-off-by: Daniel Lezcano <[email protected]> Signed-off-by: Serge E. Hallyn <[email protected]> Cc: Eric W. Biederman <[email protected]> Cc: Paul Menage <[email protected]> Cc: Jamal Hadi Salim <[email protected]> --- Documentation/cgroups/cgroups.txt | 2 +- arch/ia64/configs/generic_defconfig | 1 - arch/mips/configs/bcm47xx_defconfig | 1 - arch/mips/configs/ip27_defconfig | 1 - arch/mips/configs/sb1250-swarm_defconfig | 1 - arch/powerpc/configs/cell_defconfig | 1 - arch/powerpc/configs/ppc64_defconfig | 1 - arch/powerpc/configs/ppc64e_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/powerpc/configs/pseries_defconfig | 1 - arch/s390/defconfig | 1 - arch/sh/configs/sdk7786_defconfig | 1 - arch/sh/configs/se7206_defconfig | 1 - arch/sh/configs/sh7724_generic_defconfig | 1 - arch/sh/configs/sh7770_generic_defconfig | 1 - arch/sh/configs/shx3_defconfig | 1 - arch/sh/configs/urquell_defconfig | 1 - arch/x86/configs/i386_defconfig | 1 - arch/x86/configs/x86_64_defconfig | 1 - include/linux/cgroup.h | 3 - include/linux/cgroup_subsys.h | 6 -- include/linux/nsproxy.h | 9 --- init/Kconfig | 9 --- kernel/Makefile | 1 - kernel/cgroup.c | 116 ------------------------------ kernel/cpuset.c | 7 +- kernel/fork.c | 6 -- kernel/ns_cgroup.c | 110 ---------------------------- kernel/nsproxy.c | 4 - 29 files changed, 4 insertions(+), 287 deletions(-) delete mode 100644 kernel/ns_cgroup.c diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 190018b..6a5ba63 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -618,7 +618,7 @@ always handled well. void post_clone(struct cgroup_subsys *ss, struct cgroup *cgrp) (cgroup_mutex held by caller) -Called at the end of cgroup_clone() to do any parameter +Called during cgroup_create() to do any parameter initialization which might be required before a task could attach. For example in cpusets, no task may attach before 'cpus' and 'mems' are set up. diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig index 6a4cc50..d257546 100644 --- a/arch/ia64/configs/generic_defconfig +++ b/arch/ia64/configs/generic_defconfig @@ -25,7 +25,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=20 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -# CONFIG_CGROUP_NS is not set # CONFIG_CGROUP_FREEZER is not set # CONFIG_CGROUP_DEVICE is not set CONFIG_CPUSETS=y diff --git a/arch/mips/configs/bcm47xx_defconfig b/arch/mips/configs/bcm47xx_defconfig index bbd826b..cb75ade 100644 --- a/arch/mips/configs/bcm47xx_defconfig +++ b/arch/mips/configs/bcm47xx_defconfig @@ -199,7 +199,6 @@ CONFIG_TINY_RCU=y CONFIG_LOG_BUF_SHIFT=17 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -CONFIG_CGROUP_NS=y # CONFIG_CGROUP_FREEZER is not set # CONFIG_CGROUP_DEVICE is not set # CONFIG_CPUSETS is not set diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index 84b6503..036ad3e 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -209,7 +209,6 @@ CONFIG_LOG_BUF_SHIFT=15 # CONFIG_GROUP_SCHED is not set CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -# CONFIG_CGROUP_NS is not set # CONFIG_CGROUP_FREEZER is not set # CONFIG_CGROUP_DEVICE is not set CONFIG_CPUSETS=y diff --git a/arch/mips/configs/sb1250-swarm_defconfig b/arch/mips/configs/sb1250-swarm_defconfig index 7f07bf0..0f059f2 100644 --- a/arch/mips/configs/sb1250-swarm_defconfig +++ b/arch/mips/configs/sb1250-swarm_defconfig @@ -197,7 +197,6 @@ CONFIG_SYSVIPC_SYSCTL=y CONFIG_LOG_BUF_SHIFT=15 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -# CONFIG_CGROUP_NS is not set CONFIG_CPUSETS=y CONFIG_GROUP_SCHED=y CONFIG_FAIR_GROUP_SCHED=y diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index 9433719..cfa9177 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -76,7 +76,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=15 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -# CONFIG_CGROUP_NS is not set CONFIG_CPUSETS=y # CONFIG_GROUP_SCHED is not set # CONFIG_USER_SCHED is not set diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 369f4e0..2bc8f44 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -86,7 +86,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=17 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -# CONFIG_CGROUP_NS is not set # CONFIG_CGROUP_FREEZER is not set # CONFIG_CGROUP_DEVICE is not set CONFIG_CPUSETS=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 403e82e..ac0f13d 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -100,7 +100,6 @@ CONFIG_LOG_BUF_SHIFT=17 # CONFIG_GROUP_SCHED is not set CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -# CONFIG_CGROUP_NS is not set # CONFIG_CGROUP_FREEZER is not set # CONFIG_CGROUP_DEVICE is not set CONFIG_CPUSETS=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 12dc7c4..8175eba 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -88,7 +88,6 @@ CONFIG_AUDIT_TREE=y CONFIG_LOG_BUF_SHIFT=17 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -CONFIG_CGROUP_NS=y # CONFIG_CGROUP_FREEZER is not set CONFIG_CGROUP_DEVICE=y CONFIG_GROUP_SCHED=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 16ae717..6d96b61 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -85,7 +85,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=17 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -CONFIG_CGROUP_NS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 253f158..08e9f82 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -72,7 +72,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=17 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -CONFIG_CGROUP_NS=y # CONFIG_CGROUP_FREEZER is not set # CONFIG_CGROUP_DEVICE is not set # CONFIG_CPUSETS is not set diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index 2698245..0f6894e 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -84,7 +84,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=17 CONFIG_CGROUPS=y CONFIG_CGROUP_DEBUG=y -CONFIG_CGROUP_NS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig index 910eaec..d2c0fc8 100644 --- a/arch/sh/configs/se7206_defconfig +++ b/arch/sh/configs/se7206_defconfig @@ -77,7 +77,6 @@ CONFIG_TREE_RCU_TRACE=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_CGROUPS=y CONFIG_CGROUP_DEBUG=y -CONFIG_CGROUP_NS=y # CONFIG_CGROUP_FREEZER is not set CONFIG_CGROUP_DEVICE=y # CONFIG_CPUSETS is not set diff --git a/arch/sh/configs/sh7724_generic_defconfig b/arch/sh/configs/sh7724_generic_defconfig index a6a9e68..c3a2f67 100644 --- a/arch/sh/configs/sh7724_generic_defconfig +++ b/arch/sh/configs/sh7724_generic_defconfig @@ -70,7 +70,6 @@ CONFIG_RCU_FANOUT=32 CONFIG_LOG_BUF_SHIFT=17 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -# CONFIG_CGROUP_NS is not set # CONFIG_CGROUP_FREEZER is not set # CONFIG_CGROUP_DEVICE is not set # CONFIG_CPUSETS is not set diff --git a/arch/sh/configs/sh7770_generic_defconfig b/arch/sh/configs/sh7770_generic_defconfig index 4327f89..ce2357f 100644 --- a/arch/sh/configs/sh7770_generic_defconfig +++ b/arch/sh/configs/sh7770_generic_defconfig @@ -69,7 +69,6 @@ CONFIG_RCU_FANOUT=32 CONFIG_LOG_BUF_SHIFT=17 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -# CONFIG_CGROUP_NS is not set # CONFIG_CGROUP_FREEZER is not set # CONFIG_CGROUP_DEVICE is not set # CONFIG_CPUSETS is not set diff --git a/arch/sh/configs/shx3_defconfig b/arch/sh/configs/shx3_defconfig index 42f6bd3..05ced6a 100644 --- a/arch/sh/configs/shx3_defconfig +++ b/arch/sh/configs/shx3_defconfig @@ -84,7 +84,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -CONFIG_CGROUP_NS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y # CONFIG_CPUSETS is not set diff --git a/arch/sh/configs/urquell_defconfig b/arch/sh/configs/urquell_defconfig index 28bb19d..e698dff 100644 --- a/arch/sh/configs/urquell_defconfig +++ b/arch/sh/configs/urquell_defconfig @@ -82,7 +82,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_CGROUPS=y CONFIG_CGROUP_DEBUG=y -CONFIG_CGROUP_NS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index d28fad1..4428d5c 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -105,7 +105,6 @@ CONFIG_FAIR_GROUP_SCHED=y CONFIG_CGROUP_SCHED=y CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -CONFIG_CGROUP_NS=y CONFIG_CGROUP_FREEZER=y # CONFIG_CGROUP_DEVICE is not set CONFIG_CPUSETS=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 6c86acd..2ff947f 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -105,7 +105,6 @@ CONFIG_FAIR_GROUP_SCHED=y CONFIG_CGROUP_SCHED=y CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set -CONFIG_CGROUP_NS=y CONFIG_CGROUP_FREEZER=y # CONFIG_CGROUP_DEVICE is not set CONFIG_CPUSETS=y diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f3cbd73..ddbdb77 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -552,9 +552,6 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, 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; diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index ccefff0..4ba5259 100644 --- a/include/linux/cgroup_subsys.h +++ b/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 diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 7b370c7..50d20ab 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -81,13 +81,4 @@ static inline void get_nsproxy(struct nsproxy *ns) atomic_inc(&ns->count); } -#ifdef CONFIG_CGROUP_NS -int ns_cgroup_clone(struct task_struct *tsk, struct pid *pid); -#else -static inline int ns_cgroup_clone(struct task_struct *tsk, struct pid *pid) -{ - return 0; -} -#endif - #endif diff --git a/init/Kconfig b/init/Kconfig index 5cff9a9..1124656 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -496,15 +496,6 @@ 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 diff --git a/kernel/Makefile b/kernel/Makefile index 057472f..a7ee5f4 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -62,7 +62,6 @@ 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 diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 09fb6f9..7ec5bad 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4212,122 +4212,6 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) } /** - * 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 diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 02b9611..4613840 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1829,10 +1829,9 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont) } /* - * post_clone() is called at the end of cgroup_clone(). - * 'cgroup' was just created automatically as a result of - * a cgroup_clone(), and the current task is about to - * be moved into 'cgroup'. + * post_clone() is called during cgroup_create() when the + * clone_children mount argument was specified. The cgroup + * can not yet have any tasks. * * Currently we refuse to set up the cgroup - thereby * refusing the task to be entered, and as a result refusing diff --git a/kernel/fork.c b/kernel/fork.c index b6cce14..c391b1d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1167,12 +1167,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, 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()? diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c deleted file mode 100644 index 2a5dfec..0000000 --- a/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, -}; diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index f74e6c0..014a90d 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -198,10 +198,6 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags, goto out; } - err = ns_cgroup_clone(current, task_pid(current)); - if (err) - put_nsproxy(*new_nsp); - out: return err; } -- 1.7.0.4 _______________________________________________ Containers mailing list [email protected] https://lists.linux-foundation.org/mailman/listinfo/containers _______________________________________________ Devel mailing list [email protected] https://openvz.org/mailman/listinfo/devel
