From c6b3d5bcd67c75961a1e8b9564d1475c0f194a84 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 4 Apr 2014 17:14:41 +0800 Subject: cgroup: fix top cgroup refcnt leak As mount() and kill_sb() is not a one-to-one match, If we mount the same cgroupfs in serveral mount points, and then umount all of them, kill_sb() will be called only once. Try: # mount -t cgroup -o cpuacct xxx /cgroup # mount -t cgroup -o cpuacct xxx /cgroup2 # cat /proc/cgroups | grep cpuacct cpuacct 2 1 1 # umount /cgroup # umount /cgroup2 # cat /proc/cgroups | grep cpuacct cpuacct 2 1 1 You'll see cgroupfs will never be freed. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- kernel/cgroup.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index fede3d3f28ff..0dfc7324c789 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1487,6 +1487,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, struct cgroup_sb_opts opts; struct dentry *dentry; int ret; + bool new_sb; /* * The first time anyone tries to mount a cgroup, enable the list @@ -1603,8 +1604,8 @@ out_unlock: if (ret) return ERR_PTR(ret); - dentry = kernfs_mount(fs_type, flags, root->kf_root, NULL); - if (IS_ERR(dentry)) + dentry = kernfs_mount(fs_type, flags, root->kf_root, &new_sb); + if (IS_ERR(dentry) || !new_sb) cgroup_put(&root->cgrp); return dentry; } -- cgit v1.2.2 From 49957f8e2a43035a97d05bddefa394492a969c0d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Apr 2014 16:44:47 -0400 Subject: cgroup: newly created dirs and files should be owned by the creator While converting cgroup to kernfs, 2bd59d48ebfb ("cgroup: convert to kernfs") accidentally dropped the logic which makes newly created cgroup dirs and files owned by the current uid / gid. This broke cases where cgroup subtree management is delegated to !root as the sub manager wouldn't be able to create more than single level of hierarchy or put tasks into child cgroups it created. Among other things, this breaks user session management in systemd and one of the symptoms was 90s hang during shutdown. User session systemd running as the user creates a sub-service to initiate shutdown and tries to put kill(1) into it but fails because cgroup.procs is owned by root. This leads to 90s hang during shutdown. Implement cgroup_kn_set_ugid() which sets a kn's uid and gid to those of the caller and use it from file and dir creation paths. Signed-off-by: Tejun Heo Reported-by: Linus Torvalds --- kernel/cgroup.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0dfc7324c789..9fcdaa705b6c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2346,11 +2346,26 @@ static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, return ret; } +/* set uid and gid of cgroup dirs and files to that of the creator */ +static int cgroup_kn_set_ugid(struct kernfs_node *kn) +{ + struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = current_fsuid(), + .ia_gid = current_fsgid(), }; + + if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && + gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) + return 0; + + return kernfs_setattr(kn, &iattr); +} + static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; struct kernfs_node *kn; struct lock_class_key *key = NULL; + int ret; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = &cft->lockdep_key; @@ -2358,7 +2373,13 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft) kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), 0, cft->kf_ops, cft, NULL, false, key); - return PTR_ERR_OR_ZERO(kn); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + ret = cgroup_kn_set_ugid(kn); + if (ret) + kernfs_remove(kn); + return ret; } /** @@ -3753,6 +3774,10 @@ static long cgroup_create(struct cgroup *parent, const char *name, */ idr_replace(&root->cgroup_idr, cgrp, cgrp->id); + err = cgroup_kn_set_ugid(kn); + if (err) + goto err_destroy; + err = cgroup_addrm_files(cgrp, cgroup_base_files, true); if (err) goto err_destroy; -- cgit v1.2.2