cregit-Linux how code gets into the kernel

Release 4.13 kernel/pid_namespace.c

Directory: kernel
/*
 * Pid namespaces
 *
 * Authors:
 *    (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc.
 *    (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM
 *     Many thanks to Oleg Nesterov for comments and help
 *
 */

#include <linux/pid.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/syscalls.h>
#include <linux/cred.h>
#include <linux/err.h>
#include <linux/acct.h>
#include <linux/slab.h>
#include <linux/proc_ns.h>
#include <linux/reboot.h>
#include <linux/export.h>
#include <linux/sched/task.h>
#include <linux/sched/signal.h>


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; }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov182100.00%1100.00%
Total182100.00%1100.00%


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); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann31100.00%1100.00%
Total31100.00%1100.00%

/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ #define MAX_PID_NS_LEVEL 32
static struct ucounts *inc_pid_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann24100.00%1100.00%
Total24100.00%1100.00%


static void dec_pid_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_PID_NAMESPACES); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann18100.00%1100.00%
Total18100.00%1100.00%


static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns, struct pid_namespace *parent_pid_ns) { struct pid_namespace *ns; unsigned int level = parent_pid_ns->level + 1; struct ucounts *ucounts; int i; int err; err = -ENOSPC; if (level > MAX_PID_NS_LEVEL) goto out; ucounts = inc_pid_namespaces(user_ns); if (!ucounts) goto out; err = -ENOMEM; ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL); if (ns == NULL) goto out_dec; 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; err = ns_alloc_inum(&ns->ns); if (err) goto out_free_map; ns->ns.ops = &pidns_operations; kref_init(&ns->kref); ns->level = level; ns->parent = get_pid_ns(parent_pid_ns); ns->user_ns = get_user_ns(user_ns); ns->ucounts = ucounts; ns->nr_hashed = PIDNS_HASH_ADDING; 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); for (i = 1; i < PIDMAP_ENTRIES; i++) 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_dec: dec_pid_namespaces(ucounts); out: return ERR_PTR(err); }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov19258.36%214.29%
Eric W. Biedermann8626.14%750.00%
Alexey Dobriyan236.99%17.14%
Andrey Vagin175.17%17.14%
Al Viro113.34%321.43%
Total329100.00%14100.00%


static void delayed_free_pidns(struct rcu_head *p) { struct pid_namespace *ns = container_of(p, struct pid_namespace, rcu); dec_pid_namespaces(ns->ucounts); put_user_ns(ns->user_ns); kmem_cache_free(pid_ns_cachep, ns); }

Contributors

PersonTokensPropCommitsCommitProp
Andrey Vagin2553.19%150.00%
Al Viro2246.81%150.00%
Total47100.00%2100.00%


static void destroy_pid_namespace(struct pid_namespace *ns) { int i; ns_free_inum(&ns->ns); for (i = 0; i < PIDMAP_ENTRIES; i++) kfree(ns->pidmap[i].page); call_rcu(&ns->rcu, delayed_free_pidns); }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov4375.44%120.00%
Al Viro915.79%360.00%
Eric W. Biedermann58.77%120.00%
Total57100.00%5100.00%


struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *old_ns) { if (!(flags & CLONE_NEWPID)) return get_pid_ns(old_ns); if (task_active_pid_ns(current) != old_ns) return ERR_PTR(-EINVAL); return create_pid_namespace(user_ns, old_ns); }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov3355.00%125.00%
Eric W. Biedermann2135.00%250.00%
Alexey Dobriyan610.00%125.00%
Total60100.00%4100.00%


static void free_pid_ns(struct kref *kref) { struct pid_namespace *ns; ns = container_of(kref, struct pid_namespace, kref); destroy_pid_namespace(ns); }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov2678.79%150.00%
Cyrill V. Gorcunov721.21%150.00%
Total33100.00%2100.00%


void put_pid_ns(struct pid_namespace *ns) { struct pid_namespace *parent; while (ns != &init_pid_ns) { parent = ns->parent; if (!kref_put(&ns->kref, free_pid_ns)) break; ns = parent; } }

Contributors

PersonTokensPropCommitsCommitProp
Cyrill V. Gorcunov3572.92%150.00%
Pavel Emelyanov1327.08%150.00%
Total48100.00%2100.00%

EXPORT_SYMBOL_GPL(put_pid_ns);
void zap_pid_ns_processes(struct pid_namespace *pid_ns) { int nr; int rc; struct task_struct *task, *me = current; int init_pids = thread_group_leader(me) ? 1 : 2; /* Don't allow any more processes into the pid namespace */ disable_pid_allocation(pid_ns); /* * Ignore SIGCHLD causing any terminated children to autoreap. * This speeds up the namespace shutdown, plus see the comment * below. */ spin_lock_irq(&me->sighand->siglock); me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN; spin_unlock_irq(&me->sighand->siglock); /* * 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) { rcu_read_lock(); task = pid_task(find_vpid(nr), PIDTYPE_PID); if (task && !__fatal_signal_pending(task)) send_sig_info(SIGKILL, SEND_SIG_FORCED, task); rcu_read_unlock(); nr = next_pidmap(pid_ns, nr); } read_unlock(&tasklist_lock); /* * Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD. * sys_wait4() will also block until our children traced from the * parent namespace are detached and become EXIT_DEAD. */ do { clear_thread_flag(TIF_SIGPENDING); rc = sys_wait4(-1, NULL, __WALL, NULL); } while (rc != -ECHILD); /* * sys_wait4() above can't reap the EXIT_DEAD children but we do not * really care, we could reparent them to the global init. We could * exit and reap ->child_reaper even if it is not the last thread in * this pid_ns, free_pid(nr_hashed == 0) calls proc_cleanup_work(), * pid_ns can not go away until proc_kill_sb() drops the reference. * * But this ns can also have other tasks injected by setns()+fork(). * Again, ignoring the user visible semantics we do not really need * to wait until they are all reaped, but they can be reparented to * us and thus we need to ensure that pid->child_reaper stays valid * until they all go away. See free_pid()->wake_up_process(). * * We rely on ignored SIGCHLD, an injected zombie must be autoreaped * if reparented. */ for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (pid_ns->nr_hashed == init_pids) break; schedule(); } __set_current_state(TASK_RUNNING); if (pid_ns->reboot) current->signal->group_exit_code = pid_ns->reboot; acct_exit_ns(pid_ns); return; }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov9639.83%215.38%
Eric W. Biedermann8936.93%646.15%
Sukadev Bhattiprolu2811.62%17.69%
Daniel Lezcano166.64%17.69%
Oleg Nesterov124.98%323.08%
Total241100.00%13100.00%

#ifdef CONFIG_CHECKPOINT_RESTORE
static int pid_ns_ctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct pid_namespace *pid_ns = task_active_pid_ns(current); struct ctl_table tmp = *table; if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* * Writing directly to ns' last_pid field is OK, since this field * is volatile in a living namespace anyway and a code writing to * it should synchronize its usage with external means. */ tmp.data = &pid_ns->last_pid; return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov7181.61%133.33%
Eric W. Biedermann1517.24%133.33%
Andrey Vagin11.15%133.33%
Total87100.00%3100.00%

extern int pid_max; static int zero = 0; static struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", .maxlen = sizeof(int), .mode = 0666, /* permissions are checked in the handler */ .proc_handler = pid_ns_ctl_handler, .extra1 = &zero, .extra2 = &pid_max, }, { } }; static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } }; #endif /* CONFIG_CHECKPOINT_RESTORE */
int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) { if (pid_ns == &init_pid_ns) return 0; switch (cmd) { case LINUX_REBOOT_CMD_RESTART2: case LINUX_REBOOT_CMD_RESTART: pid_ns->reboot = SIGHUP; break; case LINUX_REBOOT_CMD_POWER_OFF: case LINUX_REBOOT_CMD_HALT: pid_ns->reboot = SIGINT; break; default: return -EINVAL; } read_lock(&tasklist_lock); force_sig(SIGKILL, pid_ns->child_reaper); read_unlock(&tasklist_lock); do_exit(0); /* Not reached */ return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Daniel Lezcano90100.00%1100.00%
Total90100.00%1100.00%


static inline struct pid_namespace *to_pid_ns(struct ns_common *ns) { return container_of(ns, struct pid_namespace, ns); }

Contributors

PersonTokensPropCommitsCommitProp
Al Viro25100.00%1100.00%
Total25100.00%1100.00%


static struct ns_common *pidns_get(struct task_struct *task) { struct pid_namespace *ns; rcu_read_lock(); ns = task_active_pid_ns(task); if (ns) get_pid_ns(ns); rcu_read_unlock(); return ns ? &ns->ns : NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann3366.00%125.00%
Al Viro918.00%250.00%
Oleg Nesterov816.00%125.00%
Total50100.00%4100.00%


static struct ns_common *pidns_for_children_get(struct task_struct *task) { struct pid_namespace *ns = NULL; task_lock(task); if (task->nsproxy) { ns = task->nsproxy->pid_ns_for_children; get_pid_ns(ns); } task_unlock(task); if (ns) { read_lock(&tasklist_lock); if (!ns->child_reaper) { put_pid_ns(ns); ns = NULL; } read_unlock(&tasklist_lock); } return ns ? &ns->ns : NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Kirill Tkhai97100.00%1100.00%
Total97100.00%1100.00%


static void pidns_put(struct ns_common *ns) { put_pid_ns(to_pid_ns(ns)); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann1473.68%133.33%
Al Viro526.32%266.67%
Total19100.00%3100.00%


static int pidns_install(struct nsproxy *nsproxy, struct ns_common *ns) { struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *ancestor, *new = to_pid_ns(ns); if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) || !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) return -EPERM; /* * Only allow entering the current active pid namespace * or a child of the current active pid namespace. * * This is required for fork to return a usable pid value and * this maintains the property that processes and their * children can not escape their current pid namespace. */ if (new->level < active->level) return -EINVAL; ancestor = new; while (ancestor->level > active->level) ancestor = ancestor->parent; if (ancestor != active) return -EINVAL; put_pid_ns(nsproxy->pid_ns_for_children); nsproxy->pid_ns_for_children = get_pid_ns(new); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann12194.53%350.00%
Al Viro53.91%233.33%
Andrew Lutomirski21.56%116.67%
Total128100.00%6100.00%


static struct ns_common *pidns_get_parent(struct ns_common *ns) { struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *pid_ns, *p; /* See if the parent is in the current namespace */ pid_ns = p = to_pid_ns(ns)->parent; for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == active) break; p = p->parent; } return &get_pid_ns(pid_ns)->ns; }

Contributors

PersonTokensPropCommitsCommitProp
Andrey Vagin84100.00%1100.00%
Total84100.00%1100.00%


static struct user_namespace *pidns_owner(struct ns_common *ns) { return to_pid_ns(ns)->user_ns; }

Contributors

PersonTokensPropCommitsCommitProp
Andrey Vagin21100.00%1100.00%
Total21100.00%1100.00%

const struct proc_ns_operations pidns_operations = { .name = "pid", .type = CLONE_NEWPID, .get = pidns_get, .put = pidns_put, .install = pidns_install, .owner = pidns_owner, .get_parent = pidns_get_parent, }; const struct proc_ns_operations pidns_for_children_operations = { .name = "pid_for_children", .real_ns_name = "pid", .type = CLONE_NEWPID, .get = pidns_for_children_get, .put = pidns_put, .install = pidns_install, .owner = pidns_owner, .get_parent = pidns_get_parent, };
static __init int pid_namespaces_init(void) { pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC); #ifdef CONFIG_CHECKPOINT_RESTORE register_sysctl_paths(kern_path, pid_ns_ctl_table); #endif return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov2884.85%266.67%
Cyrill V. Gorcunov515.15%133.33%
Total33100.00%3100.00%

__initcall(pid_namespaces_init);

Overall Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov80040.59%48.16%
Eric W. Biedermann50125.42%1734.69%
Andrey Vagin1859.39%510.20%
Kirill Tkhai1447.31%12.04%
Daniel Lezcano1095.53%12.04%
Al Viro864.36%612.24%
Cyrill V. Gorcunov542.74%24.08%
Alexey Dobriyan291.47%24.08%
Sukadev Bhattiprolu281.42%12.04%
Oleg Nesterov201.01%48.16%
Ingo Molnar90.46%36.12%
Tejun Heo30.15%12.04%
Andrew Lutomirski20.10%12.04%
David Howells10.05%12.04%
Total1971100.00%49100.00%
Directory: kernel
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.