cregit-Linux how code gets into the kernel

Release 4.15 kernel/pid.c

Directory: kernel
/*
 * Generic pidhash and scalable, time-bounded PID allocator
 *
 * (C) 2002-2003 Nadia Yvette Chambers, IBM
 * (C) 2004 Nadia Yvette Chambers, Oracle
 * (C) 2002-2004 Ingo Molnar, Red Hat
 *
 * pid-structures are backing objects for tasks sharing a given ID to chain
 * against. There is very little to them aside from hashing them and
 * parking tasks using given ID's on a list.
 *
 * The hash is always changed with the tasklist_lock write-acquired,
 * and the hash is only accessed with the tasklist_lock at least
 * read-acquired, so there's no additional SMP locking needed here.
 *
 * We have a list of bitmap pages, which bitmaps represent the PID space.
 * Allocating and freeing PIDs is completely lockless. The worst-case
 * 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 <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/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/bootmem.h>
#include <linux/hash.h>
#include <linux/pid_namespace.h>
#include <linux/init_task.h>
#include <linux/syscalls.h>
#include <linux/proc_ns.h>
#include <linux/proc_fs.h>
#include <linux/sched/task.h>
#include <linux/idr.h>


struct pid init_struct_pid = INIT_STRUCT_PID;


int pid_max = PID_MAX_DEFAULT;


#define RESERVED_PIDS		300


int pid_max_min = RESERVED_PIDS + 1;

int pid_max_max = PID_MAX_LIMIT;

/*
 * PID-map pages start out as NULL, they get allocated upon
 * first use and are never deallocated. This way a low pid_max
 * value does not cause lots of bitmaps to be allocated, but
 * the scheme scales to up to 4 million PIDs, runtime.
 */

struct pid_namespace init_pid_ns = {
	.kref = KREF_INIT(2),
	.idr = IDR_INIT,
	.pid_allocated = PIDNS_ADDING,
	.level = 0,
	.child_reaper = &init_task,
	.user_ns = &init_user_ns,
	.ns.inum = PROC_PID_INIT_INO,
#ifdef CONFIG_PID_NS
	.ns.ops = &pidns_operations,
#endif
};

EXPORT_SYMBOL_GPL(init_pid_ns);

/*
 * Note: disable interrupts while the pidmap_lock is held as an
 * interrupt might come in and do read_lock(&tasklist_lock).
 *
 * If we don't disable interrupts there is a nasty deadlock between
 * detach_pid()->free_pid() and another cpu that does
 * spin_lock(&pidmap_lock) followed by an interrupt routine that does
 * read_lock(&tasklist_lock);
 *
 * After we clean up the tasklist_lock and know there are no
 * irq handlers that take it we can leave the interrupts enabled.
 * For now it is easier to be safe than to prove it can't happen.
 */

static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);


void put_pid(struct pid *pid) { struct pid_namespace *ns; if (!pid) return; ns = pid->numbers[pid->level].ns; if ((atomic_read(&pid->count) == 1) || atomic_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann3143.06%120.00%
Pavel Emelyanov2737.50%240.00%
Ingo Molnar1318.06%120.00%
Nicholas Piggin11.39%120.00%
Total72100.00%5100.00%

EXPORT_SYMBOL_GPL(put_pid);
static void delayed_put_pid(struct rcu_head *rhp) { struct pid *pid = container_of(rhp, struct pid, rcu); put_pid(pid); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann1961.29%150.00%
Ingo Molnar1238.71%150.00%
Total31100.00%2100.00%


void free_pid(struct pid *pid) { /* We can be called with write_lock_irq(&tasklist_lock) held */ int i; unsigned long flags; spin_lock_irqsave(&pidmap_lock, flags); for (i = 0; i <= pid->level; i++) { struct upid *upid = pid->numbers + i; struct pid_namespace *ns = upid->ns; switch (--ns->pid_allocated) { case 2: case 1: /* When all that is left in the pid namespace * is the reaper wake up the reaper. The reaper * may be sleeping in zap_pid_ns_processes(). */ wake_up_process(ns->child_reaper); break; case PIDNS_ADDING: /* Handle a fork failure of the first process */ WARN_ON(ns->child_reaper); ns->pid_allocated = 0; /* fall through */ case 0: schedule_work(&ns->proc_work); break; } idr_remove(&ns->idr, upid->nr); } spin_unlock_irqrestore(&pidmap_lock, flags); call_rcu(&pid->rcu, delayed_put_pid); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann7953.74%538.46%
Pavel Emelyanov2013.61%215.38%
Oleg Nesterov1610.88%17.69%
Gargi Sharma1510.20%215.38%
Ingo Molnar138.84%215.38%
Kirill Korotaev42.72%17.69%
Total147100.00%13100.00%


struct pid *alloc_pid(struct pid_namespace *ns) { struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM; pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); tmp = ns; pid->level = ns->level; for (i = ns->level; i >= 0; i--) { int pid_min = 1; idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); /* * init really needs pid 1, but after reaching the maximum * wrap back to RESERVED_PIDS */ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). */ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, pid_max, GFP_ATOMIC); spin_unlock_irq(&pidmap_lock); idr_preload_end(); if (nr < 0) { retval = nr; goto out_free; } pid->numbers[i].nr = nr; pid->numbers[i].ns = tmp; tmp = tmp->parent; } if (unlikely(is_child_reaper(pid))) { if (pid_ns_prepare_proc(ns)) goto out_free; } get_pid_ns(ns); 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); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock_irq(&pidmap_lock); return pid; out_unlock: spin_unlock_irq(&pidmap_lock); put_pid_ns(ns); out_free: spin_lock_irq(&pidmap_lock); while (++i <= ns->level) idr_remove(&ns->idr, (pid->numbers + i)->nr); /* On failure to allocate the first pid, reset the state */ if (ns->pid_allocated == PIDNS_ADDING) idr_set_cursor(&ns->idr, 0); spin_unlock_irq(&pidmap_lock); kmem_cache_free(ns->pid_cachep, pid); return ERR_PTR(retval); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann13431.68%630.00%
Pavel Emelyanov10224.11%315.00%
Gargi Sharma9722.93%210.00%
Ingo Molnar276.38%210.00%
Michal Hocko245.67%15.00%
André Goddard Rosa153.55%15.00%
Kirill Korotaev112.60%15.00%
Oleg Nesterov92.13%210.00%
Arnd Bergmann20.47%15.00%
Sukadev Bhattiprolu20.47%15.00%
Total423100.00%20100.00%


void disable_pid_allocation(struct pid_namespace *ns) { spin_lock_irq(&pidmap_lock); ns->pid_allocated &= ~PIDNS_ADDING; spin_unlock_irq(&pidmap_lock); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann2793.10%150.00%
Gargi Sharma26.90%150.00%
Total29100.00%2100.00%


struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { return idr_find(&ns->idr, nr); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann1142.31%133.33%
Pavel Emelyanov1038.46%133.33%
Gargi Sharma519.23%133.33%
Total26100.00%3100.00%

EXPORT_SYMBOL_GPL(find_pid_ns);
struct pid *find_vpid(int nr) { return find_pid_ns(nr, task_active_pid_ns(current)); }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov1885.71%150.00%
Eric W. Biedermann314.29%150.00%
Total21100.00%2100.00%

EXPORT_SYMBOL_GPL(find_vpid); /* * attach_pid() must be called with the tasklist_lock write-held. */
void attach_pid(struct task_struct *task, enum pid_type type) { struct pid_link *link = &task->pids[type]; hlist_add_head_rcu(&link->node, &link->pid->tasks[type]); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann3782.22%120.00%
Oleg Nesterov511.11%240.00%
Ingo Molnar36.67%240.00%
Total45100.00%5100.00%


static void __change_pid(struct task_struct *task, enum pid_type type, struct pid *new) { struct pid_link *link; struct pid *pid; int tmp; link = &task->pids[type]; pid = link->pid; hlist_del_rcu(&link->node); link->pid = new; for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (!hlist_empty(&pid->tasks[tmp])) return; free_pid(pid); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann4446.32%114.29%
Ingo Molnar3233.68%342.86%
Oleg Nesterov1616.84%228.57%
Kirill Korotaev33.16%114.29%
Total95100.00%7100.00%


void detach_pid(struct task_struct *task, enum pid_type type) { __change_pid(task, type, NULL); }

Contributors

PersonTokensPropCommitsCommitProp
Oleg Nesterov23100.00%1100.00%
Total23100.00%1100.00%


void change_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { __change_pid(task, type, pid); attach_pid(task, type); }

Contributors

PersonTokensPropCommitsCommitProp
Oleg Nesterov35100.00%1100.00%
Total35100.00%1100.00%

/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */
void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { new->pids[type].pid = old->pids[type].pid; hlist_replace_rcu(&old->pids[type].node, &new->pids[type].node); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann60100.00%1100.00%
Total60100.00%1100.00%


struct task_struct *pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pids[(type)].node); } return result; }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann5265.82%116.67%
Ingo Molnar1316.46%116.67%
Kirill Korotaev67.59%116.67%
Paul E. McKenney45.06%233.33%
Arnd Bergmann45.06%116.67%
Total79100.00%6100.00%

EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */
struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); }

Contributors

PersonTokensPropCommitsCommitProp
Ingo Molnar924.32%225.00%
Eric W. Biedermann821.62%112.50%
Pavel Emelyanov821.62%112.50%
Tetsuo Handa513.51%112.50%
Paul E. McKenney410.81%225.00%
Christoph Hellwig38.11%112.50%
Total37100.00%8100.00%


struct task_struct *find_task_by_vpid(pid_t vnr) { return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov1780.95%133.33%
Eric W. Biedermann314.29%133.33%
Christoph Hellwig14.76%133.33%
Total21100.00%3100.00%


struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); if (type != PIDTYPE_PID) task = task->group_leader; pid = get_pid(rcu_dereference(task->pids[type].pid)); rcu_read_unlock(); return pid; }

Contributors

PersonTokensPropCommitsCommitProp
Oleg Nesterov5694.92%266.67%
Eric Dumazet35.08%133.33%
Total59100.00%3100.00%

EXPORT_SYMBOL_GPL(get_task_pid);
struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; rcu_read_lock(); result = pid_task(pid, type); if (result) get_task_struct(result); rcu_read_unlock(); return result; }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann48100.00%1100.00%
Total48100.00%1100.00%

EXPORT_SYMBOL_GPL(get_pid_task);
struct pid *find_get_pid(pid_t nr) { struct pid *pid; rcu_read_lock(); pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann3397.06%150.00%
Pavel Emelyanov12.94%150.00%
Total34100.00%2100.00%

EXPORT_SYMBOL_GPL(find_get_pid);
pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) { struct upid *upid; pid_t nr = 0; if (pid && ns->level <= pid->level) { upid = &pid->numbers[ns->level]; if (upid->ns == ns) nr = upid->nr; } return nr; }

Contributors

PersonTokensPropCommitsCommitProp
Pavel Emelyanov68100.00%1100.00%
Total68100.00%1100.00%

EXPORT_SYMBOL_GPL(pid_nr_ns);
pid_t pid_vnr(struct pid *pid) { return pid_nr_ns(pid, task_active_pid_ns(current)); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann21100.00%2100.00%
Total21100.00%2100.00%

EXPORT_SYMBOL_GPL(pid_vnr);
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns) { pid_t nr = 0; rcu_read_lock(); if (!ns) ns = task_active_pid_ns(current); if (likely(pid_alive(task))) { if (type != PIDTYPE_PID) { if (type == __PIDTYPE_TGID) type = PIDTYPE_PID; task = task->group_leader; } nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns); } rcu_read_unlock(); return nr; }

Contributors

PersonTokensPropCommitsCommitProp
Oleg Nesterov6767.00%240.00%
Pavel Emelyanov2727.00%120.00%
Eric W. Biedermann33.00%120.00%
Eric Dumazet33.00%120.00%
Total100100.00%5100.00%

EXPORT_SYMBOL(__task_pid_nr_ns);
struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann21100.00%1100.00%
Total21100.00%1100.00%

EXPORT_SYMBOL_GPL(task_active_pid_ns); /* * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */
struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { return idr_get_next(&ns->idr, &nr); }

Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann1555.56%250.00%
Gargi Sharma622.22%125.00%
Pavel Emelyanov622.22%125.00%
Total27100.00%4100.00%


void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ pid_max = min(pid_max_max, max_t(int, pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); idr_init(&init_pid_ns.idr); init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); }

Contributors

PersonTokensPropCommitsCommitProp
Hedi Berriche4352.44%16.67%
Pavel Emelyanov1113.41%320.00%
Eric W. Biedermann89.76%213.33%
Sukadev Bhattiprolu89.76%320.00%
Gargi Sharma44.88%213.33%
Andrew Morton44.88%16.67%
Vladimir Davydov22.44%16.67%
Zhen Lei11.22%16.67%
Ingo Molnar11.22%16.67%
Total82100.00%15100.00%


Overall Contributors

PersonTokensPropCommitsCommitProp
Eric W. Biedermann68938.09%1619.28%
Pavel Emelyanov33518.52%1113.25%
Oleg Nesterov22812.60%1012.05%
Gargi Sharma1769.73%22.41%
Ingo Molnar1508.29%56.02%
Hedi Berriche432.38%11.20%
Sukadev Bhattiprolu351.93%910.84%
Kirill Korotaev241.33%11.20%
Michal Hocko241.33%11.20%
André Goddard Rosa150.83%11.20%
William Lee Irwin III120.66%11.20%
Rik Van Riel100.55%11.20%
Paul E. McKenney80.44%44.82%
Andrew Morton70.39%11.20%
Cédric Le Goater70.39%11.20%
Arnd Bergmann60.33%22.41%
Eric Dumazet60.33%11.20%
Tetsuo Handa60.33%22.41%
David Sterba50.28%11.20%
Christoph Hellwig40.22%11.20%
David Howells30.17%11.20%
Raphael S. Carvalho30.17%11.20%
Franck Bui-Huu30.17%11.20%
Vladimir Davydov20.11%11.20%
Arnaldo Carvalho de Melo20.11%11.20%
Peter Zijlstra10.06%11.20%
Frederik Schwarzer10.06%11.20%
Zhen Lei10.06%11.20%
Paul Gortmaker10.06%11.20%
Nicholas Piggin10.06%11.20%
Nadia Yvette Chambers10.06%11.20%
Total1809100.00%83100.00%
Directory: kernel
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.