From 74bd59bb39eb08b4379e2590c5f160748d83f812 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 8 Feb 2008 04:18:24 -0800 Subject: namespaces: cleanup the code managed with PID_NS option Just like with the user namespaces, move the namespace management code into the separate .c file and mark the (already existing) PID_NS option as "depend on NAMESPACES" [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Pavel Emelyanov Acked-by: Serge Hallyn Cc: Cedric Le Goater Cc: "Eric W. Biederman" Cc: Herbert Poetzl Cc: Kirill Korotaev Cc: Sukadev Bhattiprolu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/Makefile | 1 + kernel/pid.c | 184 +-------------------------------------------- kernel/pid_namespace.c | 197 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 201 insertions(+), 181 deletions(-) create mode 100644 kernel/pid_namespace.c (limited to 'kernel') diff --git a/kernel/Makefile b/kernel/Makefile index 30a957a35c91..60cd39c84e6d 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_CPUSETS) += cpuset.o obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o obj-$(CONFIG_UTS_NS) += utsname.o obj-$(CONFIG_USER_NS) += user_namespace.o +obj-$(CONFIG_PID_NS) += pid_namespace.o obj-$(CONFIG_IKCONFIG) += configs.o obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o obj-$(CONFIG_STOP_MACHINE) += stop_machine.o diff --git a/kernel/pid.c b/kernel/pid.c index 3b30bccdfcdc..939746fb4ce7 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -41,7 +41,6 @@ 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; @@ -181,7 +180,7 @@ static int alloc_pidmap(struct pid_namespace *pid_ns) return -1; } -static int next_pidmap(struct pid_namespace *pid_ns, int last) +int next_pidmap(struct pid_namespace *pid_ns, int last) { int offset; struct pidmap *map, *end; @@ -488,180 +487,6 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) } EXPORT_SYMBOL_GPL(find_get_pid); -struct pid_cache { - int nr_ids; - char name[16]; - struct kmem_cache *cachep; - struct list_head list; -}; - -static LIST_HEAD(pid_caches_lh); -static DEFINE_MUTEX(pid_caches_mutex); - -/* - * creates the kmem cache to allocate pids from. - * @nr_ids: the number of numerical ids this pid will have to carry - */ - -static struct kmem_cache *create_pid_cachep(int nr_ids) -{ - struct pid_cache *pcache; - struct kmem_cache *cachep; - - mutex_lock(&pid_caches_mutex); - list_for_each_entry (pcache, &pid_caches_lh, list) - if (pcache->nr_ids == nr_ids) - goto out; - - pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL); - if (pcache == NULL) - goto err_alloc; - - snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids); - cachep = kmem_cache_create(pcache->name, - sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid), - 0, SLAB_HWCACHE_ALIGN, NULL); - if (cachep == NULL) - goto err_cachep; - - pcache->nr_ids = nr_ids; - pcache->cachep = cachep; - list_add(&pcache->list, &pid_caches_lh); -out: - mutex_unlock(&pid_caches_mutex); - return pcache->cachep; - -err_cachep: - kfree(pcache); -err_alloc: - mutex_unlock(&pid_caches_mutex); - 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); - 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, *parent; - - ns = container_of(kref, struct pid_namespace, kref); - - 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; -} - /* * The pid hash table is scaled according to the amount of memory in the * machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or @@ -694,9 +519,6 @@ void __init pidmap_init(void) set_bit(0, init_pid_ns.pidmap[0].page); atomic_dec(&init_pid_ns.pidmap[0].nr_free); - 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); + 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 new file mode 100644 index 000000000000..6d792b66d854 --- /dev/null +++ b/kernel/pid_namespace.c @@ -0,0 +1,197 @@ +/* + * Pid namespaces + * + * Authors: + * (C) 2007 Pavel Emelyanov , OpenVZ, SWsoft Inc. + * (C) 2007 Sukadev Bhattiprolu , IBM + * Many thanks to Oleg Nesterov for comments and help + * + */ + +#include +#include +#include +#include + +#define BITS_PER_PAGE (PAGE_SIZE*8) + +struct pid_cache { + int nr_ids; + char name[16]; + struct kmem_cache *cachep; + struct list_head list; +}; + +static LIST_HEAD(pid_caches_lh); +static DEFINE_MUTEX(pid_caches_mutex); +static struct kmem_cache *pid_ns_cachep; + +/* + * creates the kmem cache to allocate pids from. + * @nr_ids: the number of numerical ids this pid will have to carry + */ + +static struct kmem_cache *create_pid_cachep(int nr_ids) +{ + struct pid_cache *pcache; + struct kmem_cache *cachep; + + mutex_lock(&pid_caches_mutex); + list_for_each_entry(pcache, &pid_caches_lh, list) + if (pcache->nr_ids == nr_ids) + goto out; + + pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL); + if (pcache == NULL) + goto err_alloc; + + snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids); + cachep = kmem_cache_create(pcache->name, + sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid), + 0, SLAB_HWCACHE_ALIGN, NULL); + if (cachep == NULL) + goto err_cachep; + + pcache->nr_ids = nr_ids; + pcache->cachep = cachep; + list_add(&pcache->list, &pid_caches_lh); +out: + mutex_unlock(&pid_caches_mutex); + return pcache->cachep; + +err_cachep: + kfree(pcache); +err_alloc: + mutex_unlock(&pid_caches_mutex); + return NULL; +} + +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); + 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, *parent; + + ns = container_of(kref, struct pid_namespace, kref); + + parent = ns->parent; + destroy_pid_namespace(ns); + + if (parent != NULL) + put_pid_ns(parent); +} + +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; +} + +static __init int pid_namespaces_init(void) +{ + pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC); + return 0; +} + +__initcall(pid_namespaces_init); -- cgit v1.2.2