From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934684Ab2C3Um2 (ORCPT ); Fri, 30 Mar 2012 16:42:28 -0400 Received: from mail-gy0-f174.google.com ([209.85.160.174]:35211 "EHLO mail-gy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934656Ab2C3UmW (ORCPT ); Fri, 30 Mar 2012 16:42:22 -0400 Date: Fri, 30 Mar 2012 13:42:16 -0700 From: Tejun Heo To: glommer@parallels.com, lizf@cn.fujitsu.com, containers@lists.linux-foundation.org, cgroups@vger.kernel.org Cc: linux-kernel@vger.kernel.org, fweisbec@gmail.com, rni@google.com, ctalbott@google.com Subject: [PATCH UPDATED 11/12] cgroup: introduce struct cfent Message-ID: <20120330204216.GH28934@google.com> References: <1332368265-21586-1-git-send-email-tj@kernel.org> <1332368265-21586-12-git-send-email-tj@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1332368265-21586-12-git-send-email-tj@kernel.org> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This patch adds cfent (cgroup file entry) which is the association between a cgroup and a file. This is in-cgroup representation of files under a cgroup directory. This simplifies walking walking cgroup files and thus cgroup_clear_directory(), which is now implemented in two parts - cgroup_rm_file() and a loop around it. cgroup_rm_file() will be used to implement cftype removal and cfent is scheduled to serve cgroup specific per-file data (e.g. for sysfs-like "sever" semantics). v2: - cfe was freed from cgroup_rm_file() which led to use-after-free if the file had openers at the time of removal. Moved to cgroup_diput(). - cgroup_clear_directory() triggered WARN_ON_ONCE() if d_subdirs wasn't empty after removing all files. This triggered spuriously if some files were open during directory clearing. Removed. v3: - In cgroup_diput(), WARN_ONCE(!list_empty(&cfe->node)) could be spuriously triggered for root cgroups because they don't go through cgroup_clear_directory() on unmount. Don't trigger WARN for root cgroups. Signed-off-by: Tejun Heo Cc: Glauber Costa --- cgroup_diput() may trigger WARN_ONCE() spuriously on unmount. Fixed. include/linux/cgroup.h | 1 kernel/cgroup.c | 109 +++++++++++++++++++++++++++++++++---------------- 2 files changed, 76 insertions(+), 34 deletions(-) Index: work/include/linux/cgroup.h =================================================================== --- work.orig/include/linux/cgroup.h +++ work/include/linux/cgroup.h @@ -175,6 +175,7 @@ struct cgroup { */ struct list_head sibling; /* my parent's children */ struct list_head children; /* my children */ + struct list_head files; /* my files */ struct cgroup *parent; /* my parent */ struct dentry __rcu *dentry; /* cgroup fs entry, RCU protected */ Index: work/kernel/cgroup.c =================================================================== --- work.orig/kernel/cgroup.c +++ work/kernel/cgroup.c @@ -148,6 +148,15 @@ struct cgroupfs_root { static struct cgroupfs_root rootnode; /* + * cgroupfs file entry, pointed to from leaf dentry->d_fsdata. + */ +struct cfent { + struct list_head node; + struct dentry *dentry; + struct cftype *type; +}; + +/* * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when * cgroup_subsys->use_id != 0. */ @@ -287,11 +296,16 @@ static inline struct cgroup *__d_cgrp(st return dentry->d_fsdata; } -static inline struct cftype *__d_cft(struct dentry *dentry) +static inline struct cfent *__d_cfe(struct dentry *dentry) { return dentry->d_fsdata; } +static inline struct cftype *__d_cft(struct dentry *dentry) +{ + return __d_cfe(dentry)->type; +} + /* the list of cgroups eligible for automatic release. Protected by * release_list_lock */ static LIST_HEAD(release_list); @@ -877,6 +891,14 @@ static void cgroup_diput(struct dentry * BUG_ON(!list_empty(&cgrp->pidlists)); kfree_rcu(cgrp, rcu_head); + } else { + struct cfent *cfe = __d_cfe(dentry); + struct cgroup *cgrp = dentry->d_parent->d_fsdata; + + WARN_ONCE(!list_empty(&cfe->node) && + cgrp != &cgrp->root->top_cgroup, + "cfe still linked for %s\n", cfe->type->name); + kfree(cfe); } iput(inode); } @@ -895,34 +917,36 @@ static void remove_dir(struct dentry *d) dput(parent); } -static void cgroup_clear_directory(struct dentry *dentry) +static int cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { - struct list_head *node; + struct cfent *cfe; + + lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex); + lockdep_assert_held(&cgroup_mutex); + + list_for_each_entry(cfe, &cgrp->files, node) { + struct dentry *d = cfe->dentry; - BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); - spin_lock(&dentry->d_lock); - node = dentry->d_subdirs.next; - while (node != &dentry->d_subdirs) { - struct dentry *d = list_entry(node, struct dentry, d_u.d_child); - - spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); - list_del_init(node); - if (d->d_inode) { - /* This should never be called on a cgroup - * directory with child cgroups */ - BUG_ON(d->d_inode->i_mode & S_IFDIR); - dget_dlock(d); - spin_unlock(&d->d_lock); - spin_unlock(&dentry->d_lock); - d_delete(d); - simple_unlink(dentry->d_inode, d); - dput(d); - spin_lock(&dentry->d_lock); - } else - spin_unlock(&d->d_lock); - node = dentry->d_subdirs.next; + if (cft && cfe->type != cft) + continue; + + dget(d); + d_delete(d); + simple_unlink(d->d_inode, d); + list_del_init(&cfe->node); + dput(d); + + return 0; } - spin_unlock(&dentry->d_lock); + return -ENOENT; +} + +static void cgroup_clear_directory(struct dentry *dir) +{ + struct cgroup *cgrp = __d_cgrp(dir); + + while (!list_empty(&cgrp->files)) + cgroup_rm_file(cgrp, NULL); } /* @@ -1352,6 +1376,7 @@ static void init_cgroup_housekeeping(str { INIT_LIST_HEAD(&cgrp->sibling); INIT_LIST_HEAD(&cgrp->children); + INIT_LIST_HEAD(&cgrp->files); INIT_LIST_HEAD(&cgrp->css_sets); INIT_LIST_HEAD(&cgrp->release_list); INIT_LIST_HEAD(&cgrp->pidlists); @@ -2623,7 +2648,9 @@ static int cgroup_add_file(struct cgroup const struct cftype *cft) { struct dentry *dir = cgrp->dentry; + struct cgroup *parent = __d_cgrp(dir); struct dentry *dentry; + struct cfent *cfe; int error; umode_t mode; char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; @@ -2639,17 +2666,31 @@ static int cgroup_add_file(struct cgroup strcat(name, "."); } strcat(name, cft->name); + BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex)); + + cfe = kzalloc(sizeof(*cfe), GFP_KERNEL); + if (!cfe) + return -ENOMEM; + dentry = lookup_one_len(name, dir, strlen(name)); - if (!IS_ERR(dentry)) { - mode = cgroup_file_mode(cft); - error = cgroup_create_file(dentry, mode | S_IFREG, - cgrp->root->sb); - if (!error) - dentry->d_fsdata = (void *)cft; - dput(dentry); - } else + if (IS_ERR(dentry)) { error = PTR_ERR(dentry); + goto out; + } + + mode = cgroup_file_mode(cft); + error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb); + if (!error) { + cfe->type = (void *)cft; + cfe->dentry = dentry; + dentry->d_fsdata = cfe; + list_add_tail(&cfe->node, &parent->files); + cfe = NULL; + } + dput(dentry); +out: + kfree(cfe); return error; }