Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755329AbbK0Uwl (ORCPT ); Fri, 27 Nov 2015 15:52:41 -0500 Received: from h2.hallyn.com ([78.46.35.8]:38160 "EHLO h2.hallyn.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755214AbbK0Uwe (ORCPT ); Fri, 27 Nov 2015 15:52:34 -0500 From: serge.hallyn@ubuntu.com To: linux-kernel@vger.kernel.org Cc: adityakali@google.com, tj@kernel.org, linux-api@vger.kernel.org, containers@lists.linux-foundation.org, cgroups@vger.kernel.org, lxc-devel@lists.linuxcontainers.org, akpm@linux-foundation.org, ebiederm@xmission.com, gregkh@linuxfoundation.org, lizefan@huawei.com, hannes@cmpxchg.org Subject: [PATCH 5/7] cgroup: mount cgroupns-root when inside non-init cgroupns Date: Fri, 27 Nov 2015 14:52:23 -0600 Message-Id: <1448657545-531-6-git-send-email-serge.hallyn@ubuntu.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1448657545-531-1-git-send-email-serge.hallyn@ubuntu.com> References: <1448657545-531-1-git-send-email-serge.hallyn@ubuntu.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5369 Lines: 183 From: Aditya Kali This patch enables cgroup mounting inside userns when a process as appropriate privileges. The cgroup filesystem mounted is rooted at the cgroupns-root. Thus, in a container-setup, only the hierarchy under the cgroupns-root is exposed inside the container. This allows container management tools to run inside the containers without depending on any global state. In order to support this, a new kernfs api is added to lookup the dentry for the cgroupns-root. Changelog: 20151116 - Don't allow user namespaces to bind new subsystems 20151118 - postpone the FS_USERNS_MOUNT flag until the last patch, until we can convince ourselves it is safe. Signed-off-by: Aditya Kali Acked-by: Serge E. Hallyn --- fs/kernfs/mount.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/kernfs.h | 2 ++ kernel/cgroup.c | 39 ++++++++++++++++++++++++++++++++++++- 3 files changed, 90 insertions(+), 1 deletion(-) diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 8eaf417..cc41fe1 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -62,6 +62,56 @@ struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) return NULL; } +/** + * kernfs_obtain_root - get a dentry for the given kernfs_node + * @sb: the kernfs super_block + * @kn: kernfs_node for which a dentry is needed + * + * This can be used by callers which want to mount only a part of the kernfs + * as root of the filesystem. + */ +struct dentry *kernfs_obtain_root(struct super_block *sb, + struct kernfs_node *kn) +{ + struct dentry *dentry; + struct inode *inode; + + BUG_ON(sb->s_op != &kernfs_sops); + + /* inode for the given kernfs_node should already exist. */ + inode = kernfs_get_inode(sb, kn); + if (!inode) { + pr_debug("kernfs: could not get inode for '"); + pr_cont_kernfs_path(kn); + pr_cont("'.\n"); + return ERR_PTR(-EINVAL); + } + + /* instantiate and link root dentry */ + dentry = d_obtain_root(inode); + if (!dentry) { + pr_debug("kernfs: could not get dentry for '"); + pr_cont_kernfs_path(kn); + pr_cont("'.\n"); + return ERR_PTR(-ENOMEM); + } + + /* + * If this is a new dentry, set it up. We need kernfs_mutex because + * this may be called by callers other than kernfs_fill_super. + */ + mutex_lock(&kernfs_mutex); + if (!dentry->d_fsdata) { + kernfs_get(kn); + dentry->d_fsdata = kn; + } else { + WARN_ON(dentry->d_fsdata != kn); + } + mutex_unlock(&kernfs_mutex); + + return dentry; +} + static int kernfs_fill_super(struct super_block *sb, unsigned long magic) { struct kernfs_super_info *info = kernfs_info(sb); diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index d025ebd..1903777 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -284,6 +284,8 @@ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry); struct kernfs_root *kernfs_root_from_sb(struct super_block *sb); struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); +struct dentry *kernfs_obtain_root(struct super_block *sb, + struct kernfs_node *kn); struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0afed6b..2f487a4 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2005,6 +2005,15 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, int ret; int i; bool new_sb; + struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; + + get_cgroup_ns(ns); + + /* Check if the caller has permission to mount. */ + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) { + put_cgroup_ns(ns); + return ERR_PTR(-EPERM); + } /* * The first time anyone tries to mount a cgroup, enable the list @@ -2121,6 +2130,11 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, goto out_unlock; } + if (!opts.none && !capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_unlock; + } + root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) { ret = -ENOMEM; @@ -2139,12 +2153,34 @@ out_free: kfree(opts.release_agent); kfree(opts.name); - if (ret) + if (ret) { + put_cgroup_ns(ns); return ERR_PTR(ret); + } + out_mount: dentry = kernfs_mount(fs_type, flags, root->kf_root, is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC, &new_sb); + + if (!IS_ERR(dentry)) { + /* + * In non-init cgroup namespace, instead of root cgroup's + * dentry, we return the dentry corresponding to the + * cgroupns->root_cgrp. + */ + if (ns != &init_cgroup_ns) { + struct dentry *nsdentry; + struct cgroup *cgrp; + + cgrp = cset_cgroup_from_root(ns->root_cset, root); + nsdentry = kernfs_obtain_root(dentry->d_sb, + cgrp->kn); + dput(dentry); + dentry = nsdentry; + } + } + if (IS_ERR(dentry) || !new_sb) cgroup_put(&root->cgrp); @@ -2157,6 +2193,7 @@ out_mount: deactivate_super(pinned_sb); } + put_cgroup_ns(ns); return dentry; } -- 1.7.9.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/