内核源码阅读（五）进程ID

接着上一节我们继续学习进程ID。
在上一节中我们提到了node是一个散列表元素，对于这个散列表并未做过多解释，在这里我们给出更加详细的描述。

这个散列表是为了在给定的命名空间中查找对应与指定PID数值的pid数组的pid结构实例。
static struct hlist_head *pid_hash;
上面的hlist_head是一个内核的标准数据结构，用于建立双向散列表。
pid_hash是一个hlist_head数组，全局pid哈希表，桶数目介于16-4096之间，由系统可用内存决定 ，pidhash_init（）用于计算并分配合适的所需内存。

假如我们已经分配了一个新pid实例，并设置ID类型，可使用下面的函数将其和进程关联起来。

int fastcall attach_pid(struct task_struct *task, enum pid_type type,
        struct pid *pid)
{
    struct pid_link *link;

    /* 建立task_struct与pid的关联 */
    link = &task->pids[type];
    link->pid = pid;
    /* 建立pid与task_struct的关联 */
    hlist_add_head_rcu(&link->node, &pid->tasks[type]);

    return 0;
}

下面我们将关注如何通过上节的数据结构来获取局部的id,如task_pid，task_tgid等，以及命名空间局部数字ID和task_struct的相互转换过程。

struct task_struct *find_task_by_pid_type_ns(int type, int nr,
        struct pid_namespace *ns)
{
    return pid_task(find_pid_ns(nr, ns), type);
}

EXPORT_SYMBOL(find_task_by_pid_type_ns);

/**
 * 通过全局pid查找任务
 */
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);

/**
 * 在当前进程的命名空间中，查找特定进程号的进程
 */
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);

/**
 * 根据id在命名空间中查找进程
 */
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)
{
    struct pid *pid;
    rcu_read_lock();
    pid = get_pid(task->pids[type].pid);
    rcu_read_unlock();
    return pid;
}
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);
struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
{
    struct pid *pid;
    rcu_read_lock();
    pid = get_pid(task->pids[type].pid);
    rcu_read_unlock();
    return pid;
}

struct task_struct *fastcall 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;
}

下面将介绍如何生成唯一的PID。
内核采用了一个大的位图来对PID进行管理和跟踪，每个PID用一个比特来标识，空闲置0，反之置1即可。

在这里需要注意在进行pid分配建立一个新进程时，由于进程可能在多明敏空间中可见，则必须生成局部PID，这个需先在alloc_pid()中处理，然后才能调用alloc_pidmap()去分配pid，释放的时候同样。

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;

    pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
    if (!pid)
        goto out;

    tmp = ns;
    for (i = ns->level; i >= 0; i--) {
        nr = alloc_pidmap(tmp);
        if (nr < 0)
            goto out_free;

        pid->numbers[i].nr = nr;
        pid->numbers[i].ns = tmp;
        tmp = tmp->parent;
    }

    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]);

    spin_lock_irq(&pidmap_lock);
    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:
    return pid;

out_free:
    for (i++; i <= ns->level; i++)
        free_pidmap(pid->numbers[i].ns, pid->numbers[i].nr);

    kmem_cache_free(ns->pid_cachep, pid);
    pid = NULL;
    goto out;
}
/**
 * 在命名空间中，查找并分配一个可用的pid号
 */
static int alloc_pidmap(struct pid_namespace *pid_ns)
{
    int i, offset, max_scan, pid, last = pid_ns->last_pid;
    struct pidmap *map;

    pid = last + 1;
    if (pid >= pid_max)
        pid = RESERVED_PIDS;
    offset = pid & BITS_PER_PAGE_MASK;
    map = &pid_ns->pidmap[pid/BITS_PER_PAGE];
    max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset;
    for (i = 0; i <= max_scan; ++i) {
        if (unlikely(!map->page)) {
            void *page = kzalloc(PAGE_SIZE, GFP_KERNEL);
            /*
             * Free the page if someone raced with us
             * installing it:
             */
            spin_lock_irq(&pidmap_lock);
            if (map->page)
                kfree(page);
            else
                map->page = page;
            spin_unlock_irq(&pidmap_lock);
            if (unlikely(!map->page))
                break;
        }
        if (likely(atomic_read(&map->nr_free))) {
            do {
                if (!test_and_set_bit(offset, map->page)) {
                    atomic_dec(&map->nr_free);
                    pid_ns->last_pid = pid;
                    return pid;
                }
                offset = find_next_offset(map, offset);
                pid = mk_pid(pid_ns, map, offset);
            /*
             * find_next_offset() found a bit, the pid from it
             * is in-bounds, and if we fell back to the last
             * bitmap block and the final block was the same
             * as the starting point, pid is before last_pid.
             */
            } while (offset < BITS_PER_PAGE && pid < pid_max &&
                    (i != max_scan || pid < last ||
                        !((last+1) & BITS_PER_PAGE_MASK)));
        }
        if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
            ++map;
            offset = 0;
        } else {
            map = &pid_ns->pidmap[0];
            offset = RESERVED_PIDS;
            if (unlikely(last == offset))
                break;
        }
        pid = mk_pid(pid_ns, map, offset);
    }
    return -1;
}

fastcall 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++)
        hlist_del_rcu(&pid->numbers[i].pid_chain);
    spin_unlock_irqrestore(&pidmap_lock, flags);

    for (i = 0; i <= pid->level; i++)
        free_pidmap(pid->numbers[i].ns, pid->numbers[i].nr);

    call_rcu(&pid->rcu, delayed_put_pid);
}
/**
 * 在命名空间中，释放一个可用的pid号
 */
static fastcall void free_pidmap(struct pid_namespace *pid_ns, int pid)
{
    struct pidmap *map = pid_ns->pidmap + pid / BITS_PER_PAGE;
    int offset = pid & BITS_PER_PAGE_MASK;

    clear_bit(offset, map->page);
    atomic_inc(&map->nr_free);
}