From 0a01f2cc390e10633a54f72c608cc3fe19a50c3d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 1 Aug 2012 10:33:47 -0700 Subject: [PATCH] pidns: Make the pidns proc mount/umount logic obvious. Track the number of pids in the proc hash table. When the number of pids goes to 0 schedule work to unmount the kernel mount of proc. Move the mount of proc into alloc_pid when we allocate the pid for init. Remove the surprising calls of pid_ns_release proc in fork and proc_flush_task. Those code paths really shouldn't know about proc namespace implementation details and people have demonstrated several times that finding and understanding those code paths is difficult and non-obvious. Because of the call path detach pid is alwasy called with the rtnl_lock held free_pid is not allowed to sleep, so the work to unmounting proc is moved to a work queue. This has the side benefit of not blocking the entire world waiting for the unnecessary rcu_barrier in deactivate_locked_super. In the process of making the code clear and obvious this fixes a bug reported by Gao feng where we would leak a mount of proc during clone(CLONE_NEWPID|CLONE_NEWNET) if copy_pid_ns succeeded and copy_net_ns failed. Acked-by: "Serge E. Hallyn" Signed-off-by: "Eric W. Biederman" --- fs/proc/base.c | 4 ---- fs/proc/root.c | 5 ----- include/linux/pid_namespace.h | 2 ++ kernel/fork.c | 2 -- kernel/pid.c | 21 +++++++++++++++++---- kernel/pid_namespace.c | 14 +++++++------- 6 files changed, 26 insertions(+), 22 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 6177fc238fdb..7621dc51cff8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2590,10 +2590,6 @@ void proc_flush_task(struct task_struct *task) proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr, tgid->numbers[i].nr); } - - upid = &pid->numbers[pid->level]; - if (upid->nr == 1) - pid_ns_release_proc(upid->ns); } static struct dentry *proc_pid_instantiate(struct inode *dir, diff --git a/fs/proc/root.c b/fs/proc/root.c index fc1609321a78..f2f251158d35 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -155,11 +155,6 @@ void __init proc_root_init(void) err = register_filesystem(&proc_fs_type); if (err) return; - err = pid_ns_prepare_proc(&init_pid_ns); - if (err) { - unregister_filesystem(&proc_fs_type); - return; - } proc_self_init(); proc_symlink("mounts", NULL, "self/mounts"); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index c89c9cfcd247..4c96acdb2489 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -21,6 +21,7 @@ struct pid_namespace { struct kref kref; struct pidmap pidmap[PIDMAP_ENTRIES]; int last_pid; + int nr_hashed; struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; @@ -32,6 +33,7 @@ struct pid_namespace { struct bsd_acct_struct *bacct; #endif struct user_namespace *user_ns; + struct work_struct proc_work; kgid_t pid_gid; int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ diff --git a/kernel/fork.c b/kernel/fork.c index 7798c247f4b9..666dc8b06606 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1476,8 +1476,6 @@ bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: - if (unlikely(clone_flags & CLONE_NEWPID)) - pid_ns_release_proc(p->nsproxy->pid_ns); exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) diff --git a/kernel/pid.c b/kernel/pid.c index 3a5f238c1ca0..e957f8b09136 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -36,6 +36,7 @@ #include #include #include +#include #define pid_hashfn(nr, ns) \ hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift) @@ -270,8 +271,12 @@ void free_pid(struct pid *pid) unsigned long flags; spin_lock_irqsave(&pidmap_lock, flags); - for (i = 0; i <= pid->level; i++) - hlist_del_rcu(&pid->numbers[i].pid_chain); + for (i = 0; i <= pid->level; i++) { + struct upid *upid = pid->numbers + i; + hlist_del_rcu(&upid->pid_chain); + if (--upid->ns->nr_hashed == 0) + schedule_work(&upid->ns->proc_work); + } spin_unlock_irqrestore(&pidmap_lock, flags); for (i = 0; i <= pid->level; i++) @@ -293,6 +298,7 @@ struct pid *alloc_pid(struct pid_namespace *ns) goto out; tmp = ns; + pid->level = ns->level; for (i = ns->level; i >= 0; i--) { nr = alloc_pidmap(tmp); if (nr < 0) @@ -303,17 +309,23 @@ struct pid *alloc_pid(struct pid_namespace *ns) tmp = tmp->parent; } + if (unlikely(is_child_reaper(pid))) { + if (pid_ns_prepare_proc(ns)) + goto out_free; + } + get_pid_ns(ns); - pid->level = ns->level; atomic_set(&pid->count, 1); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); - for ( ; upid >= pid->numbers; --upid) + for ( ; upid >= pid->numbers; --upid) { hlist_add_head_rcu(&upid->pid_chain, &pid_hash[pid_hashfn(upid->nr, upid->ns)]); + upid->ns->nr_hashed++; + } spin_unlock_irq(&pidmap_lock); out: @@ -570,6 +582,7 @@ void __init pidmap_init(void) /* Reserve PID 0. We never call free_pidmap(0) */ set_bit(0, init_pid_ns.pidmap[0].page); atomic_dec(&init_pid_ns.pidmap[0].nr_free); + init_pid_ns.nr_hashed = 1; init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index b2604950aa50..84591cfeefc1 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -72,6 +72,12 @@ err_alloc: return NULL; } +static void proc_cleanup_work(struct work_struct *work) +{ + struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work); + pid_ns_release_proc(ns); +} + /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ #define MAX_PID_NS_LEVEL 32 @@ -105,6 +111,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ns->level = level; ns->parent = get_pid_ns(parent_pid_ns); ns->user_ns = get_user_ns(user_ns); + INIT_WORK(&ns->proc_work, proc_cleanup_work); set_bit(0, ns->pidmap[0].page); atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1); @@ -112,15 +119,8 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns for (i = 1; i < PIDMAP_ENTRIES; i++) atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE); - err = pid_ns_prepare_proc(ns); - if (err) - goto out_put_parent_pid_ns; - return ns; -out_put_parent_pid_ns: - put_pid_ns(parent_pid_ns); - put_user_ns(user_ns); out_free_map: kfree(ns->pidmap[0].page); out_free: