X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fpid.c;h=f815455431bff3c95855a674086e6c1d8322a7c4;hb=ca77b555c0aafa3070fbb67592abaaa1b8d31913;hp=6eb14841b7346cbbc4387f5e81ba1689375fdc3d;hpb=7af5729474b5b8ad385adadab78d6e723e7655a3;p=linux-2.6-omap-h63xx.git diff --git a/kernel/pid.c b/kernel/pid.c index 6eb14841b73..f815455431b 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -18,6 +18,12 @@ * allocation scenario when all but one out of 1 million PIDs possible are * allocated already: the scanning of 32 list entries and at most PAGE_SIZE * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). + * + * Pid namespaces: + * (C) 2007 Pavel Emelyanov , OpenVZ, SWsoft Inc. + * (C) 2007 Sukadev Bhattiprolu , IBM + * Many thanks to Oleg Nesterov for comments and help + * */ #include @@ -28,12 +34,14 @@ #include #include #include +#include #define pid_hashfn(nr, ns) \ hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift) static struct hlist_head *pid_hash; static int pidhash_shift; struct pid init_struct_pid = INIT_STRUCT_PID; +static struct kmem_cache *pid_ns_cachep; int pid_max = PID_MAX_DEFAULT; @@ -71,11 +79,22 @@ struct pid_namespace init_pid_ns = { .level = 0, .child_reaper = &init_task, }; +EXPORT_SYMBOL_GPL(init_pid_ns); -int is_global_init(struct task_struct *tsk) +int is_container_init(struct task_struct *tsk) { - return tsk == init_pid_ns.child_reaper; + int ret = 0; + struct pid *pid; + + rcu_read_lock(); + pid = task_pid(tsk); + if (pid != NULL && pid->numbers[pid->level].nr == 1) + ret = 1; + rcu_read_unlock(); + + return ret; } +EXPORT_SYMBOL(is_container_init); /* * Note: disable interrupts while the pidmap_lock is held as an @@ -191,8 +210,7 @@ fastcall void put_pid(struct pid *pid) if ((atomic_read(&pid->count) == 1) || atomic_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); - if (ns != &init_pid_ns) - put_pid_ns(ns); + put_pid_ns(ns); } } EXPORT_SYMBOL_GPL(put_pid); @@ -210,7 +228,8 @@ fastcall void free_pid(struct pid *pid) unsigned long flags; spin_lock_irqsave(&pidmap_lock, flags); - hlist_del_rcu(&pid->pid_chain); + for (i = 0; i <= pid->level; i++) + hlist_del_rcu(&pid->numbers[i].pid_chain); spin_unlock_irqrestore(&pidmap_lock, flags); for (i = 0; i <= pid->level; i++) @@ -225,6 +244,7 @@ struct pid *alloc_pid(struct pid_namespace *ns) enum pid_type type; int i, nr; struct pid_namespace *tmp; + struct upid *upid; pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) @@ -241,17 +261,18 @@ struct pid *alloc_pid(struct pid_namespace *ns) tmp = tmp->parent; } - if (ns != &init_pid_ns) - get_pid_ns(ns); - + get_pid_ns(ns); pid->level = ns->level; - pid->nr = pid->numbers[0].nr; atomic_set(&pid->count, 1); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); spin_lock_irq(&pidmap_lock); - hlist_add_head_rcu(&pid->pid_chain, &pid_hash[pid_hashfn(pid->nr, ns)]); + for (i = ns->level; i >= 0; i--) { + upid = &pid->numbers[i]; + hlist_add_head_rcu(&upid->pid_chain, + &pid_hash[pid_hashfn(upid->nr, upid->ns)]); + } spin_unlock_irq(&pidmap_lock); out: @@ -266,18 +287,31 @@ out_free: goto out; } -struct pid * fastcall find_pid(int nr) +struct pid * fastcall find_pid_ns(int nr, struct pid_namespace *ns) { struct hlist_node *elem; - struct pid *pid; + struct upid *pnr; + + hlist_for_each_entry_rcu(pnr, elem, + &pid_hash[pid_hashfn(nr, ns)], pid_chain) + if (pnr->nr == nr && pnr->ns == ns) + return container_of(pnr, struct pid, + numbers[ns->level]); - hlist_for_each_entry_rcu(pid, elem, - &pid_hash[pid_hashfn(nr, &init_pid_ns)], pid_chain) { - if (pid->nr == nr) - return pid; - } return NULL; } +EXPORT_SYMBOL_GPL(find_pid_ns); + +struct pid *find_vpid(int nr) +{ + return find_pid_ns(nr, current->nsproxy->pid_ns); +} +EXPORT_SYMBOL_GPL(find_vpid); + +struct pid *find_pid(int nr) +{ + return find_pid_ns(nr, &init_pid_ns); +} EXPORT_SYMBOL_GPL(find_pid); /* @@ -338,12 +372,32 @@ struct task_struct * fastcall pid_task(struct pid *pid, enum pid_type type) /* * Must be called under rcu_read_lock() or with tasklist_lock read-held. */ -struct task_struct *find_task_by_pid_type(int type, int nr) +struct task_struct *find_task_by_pid_type_ns(int type, int nr, + struct pid_namespace *ns) { - return pid_task(find_pid(nr), type); + return pid_task(find_pid_ns(nr, ns), type); } -EXPORT_SYMBOL(find_task_by_pid_type); +EXPORT_SYMBOL(find_task_by_pid_type_ns); + +struct task_struct *find_task_by_pid(pid_t nr) +{ + return find_task_by_pid_type_ns(PIDTYPE_PID, nr, &init_pid_ns); +} +EXPORT_SYMBOL(find_task_by_pid); + +struct task_struct *find_task_by_vpid(pid_t vnr) +{ + return find_task_by_pid_type_ns(PIDTYPE_PID, vnr, + current->nsproxy->pid_ns); +} +EXPORT_SYMBOL(find_task_by_vpid); + +struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) +{ + return find_task_by_pid_type_ns(PIDTYPE_PID, nr, ns); +} +EXPORT_SYMBOL(find_task_by_pid_ns); struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { @@ -370,7 +424,7 @@ struct pid *find_get_pid(pid_t nr) struct pid *pid; rcu_read_lock(); - pid = get_pid(find_pid(nr)); + pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; @@ -389,20 +443,44 @@ pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) return nr; } +pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return pid_nr_ns(task_pid(tsk), ns); +} +EXPORT_SYMBOL(task_pid_nr_ns); + +pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return pid_nr_ns(task_tgid(tsk), ns); +} +EXPORT_SYMBOL(task_tgid_nr_ns); + +pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return pid_nr_ns(task_pgrp(tsk), ns); +} +EXPORT_SYMBOL(task_pgrp_nr_ns); + +pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return pid_nr_ns(task_session(tsk), ns); +} +EXPORT_SYMBOL(task_session_nr_ns); + /* * Used by proc to find the first pid that is greater then or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid. */ -struct pid *find_ge_pid(int nr) +struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { struct pid *pid; do { - pid = find_pid(nr); + pid = find_pid_ns(nr, ns); if (pid) break; - nr = next_pidmap(task_active_pid_ns(current), nr); + nr = next_pidmap(ns, nr); } while (nr > 0); return pid; @@ -440,8 +518,8 @@ static struct kmem_cache *create_pid_cachep(int nr_ids) snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids); cachep = kmem_cache_create(pcache->name, - /* FIXME add numerical ids here */ - sizeof(struct pid), 0, SLAB_HWCACHE_ALIGN, NULL); + sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid), + 0, SLAB_HWCACHE_ALIGN, NULL); if (cachep == NULL) goto err_cachep; @@ -459,19 +537,128 @@ err_alloc: return NULL; } +#ifdef CONFIG_PID_NS +static struct pid_namespace *create_pid_namespace(int level) +{ + struct pid_namespace *ns; + int i; + + ns = kmem_cache_alloc(pid_ns_cachep, GFP_KERNEL); + if (ns == NULL) + goto out; + + ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!ns->pidmap[0].page) + goto out_free; + + ns->pid_cachep = create_pid_cachep(level + 1); + if (ns->pid_cachep == NULL) + goto out_free_map; + + kref_init(&ns->kref); + ns->last_pid = 0; + ns->child_reaper = NULL; + ns->level = level; + + set_bit(0, ns->pidmap[0].page); + atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1); + + for (i = 1; i < PIDMAP_ENTRIES; i++) { + ns->pidmap[i].page = 0; + atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE); + } + + return ns; + +out_free_map: + kfree(ns->pidmap[0].page); +out_free: + kmem_cache_free(pid_ns_cachep, ns); +out: + return ERR_PTR(-ENOMEM); +} + +static void destroy_pid_namespace(struct pid_namespace *ns) +{ + int i; + + for (i = 0; i < PIDMAP_ENTRIES; i++) + kfree(ns->pidmap[i].page); + kmem_cache_free(pid_ns_cachep, ns); +} + struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns) { + struct pid_namespace *new_ns; + BUG_ON(!old_ns); - get_pid_ns(old_ns); - return old_ns; + new_ns = get_pid_ns(old_ns); + if (!(flags & CLONE_NEWPID)) + goto out; + + new_ns = ERR_PTR(-EINVAL); + if (flags & CLONE_THREAD) + goto out_put; + + new_ns = create_pid_namespace(old_ns->level + 1); + if (!IS_ERR(new_ns)) + new_ns->parent = get_pid_ns(old_ns); + +out_put: + put_pid_ns(old_ns); +out: + return new_ns; } void free_pid_ns(struct kref *kref) { - struct pid_namespace *ns; + struct pid_namespace *ns, *parent; ns = container_of(kref, struct pid_namespace, kref); - kfree(ns); + + parent = ns->parent; + destroy_pid_namespace(ns); + + if (parent != NULL) + put_pid_ns(parent); +} +#endif /* CONFIG_PID_NS */ + +void zap_pid_ns_processes(struct pid_namespace *pid_ns) +{ + int nr; + int rc; + + /* + * The last thread in the cgroup-init thread group is terminating. + * Find remaining pid_ts in the namespace, signal and wait for them + * to exit. + * + * Note: This signals each threads in the namespace - even those that + * belong to the same thread group, To avoid this, we would have + * to walk the entire tasklist looking a processes in this + * namespace, but that could be unnecessarily expensive if the + * pid namespace has just a few processes. Or we need to + * maintain a tasklist for each pid namespace. + * + */ + read_lock(&tasklist_lock); + nr = next_pidmap(pid_ns, 1); + while (nr > 0) { + kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr); + nr = next_pidmap(pid_ns, nr); + } + read_unlock(&tasklist_lock); + + do { + clear_thread_flag(TIF_SIGPENDING); + rc = sys_wait4(-1, NULL, __WALL, NULL); + } while (rc != -ECHILD); + + + /* Child reaper for the pid namespace is going away */ + pid_ns->child_reaper = NULL; + return; } /* @@ -509,4 +696,6 @@ void __init pidmap_init(void) init_pid_ns.pid_cachep = create_pid_cachep(1); if (init_pid_ns.pid_cachep == NULL) panic("Can't create pid_1 cachep\n"); + + pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC); }