1、 处于某个线程组（在一个进程中，以标志CLONE_THREAD来调用clone建立的该进程的不同的执行上下文，我们在后文会看到）中的所有进程都有统一的线程组ID（ TGID）。如果进程没有使用线程，则其PID和TGID相同。线程组中的主进程被称作组长（ group leader）。通过clone创建的所有线程的task_struct的group_leader成员，会指向组长的task_struct实例。
/* * What is struct pid? * * A struct pid is the kernel's internal notion of a process identifier. * It refers to inpidual tasks, process groups, and sessions. While * there are processes attached to it the struct pid lives in a hash * table, so it and then the processes that it refers to can be found * quickly from the numeric pid value. The attached processes may be * quickly accessed by following pointers from struct pid. * * Storing pid_t values in the kernel and referring to them later has a * problem. The process originally with that pid may have exited and the * pid allocator wrapped, and another process could have come along * and been assigned that pid. * * Referring to user space processes by holding a reference to struct * task_struct has a problem. When the user space process exits * the now useless task_struct is still kept. A task_struct plus a * stack consumes around 10K of low kernel memory. More precisely * this is THREAD_SIZE + sizeof(struct task_struct). By comparison * a struct pid is about 64 bytes. * * Holding a reference to struct pid solves both of these problems. * It is small so holding a reference does not consume a lot of * resources, and since a new struct pid is allocated when the numeric pid * value is reused (when pids wrap around) we don't mistakenly refer to new * processes. *//* * struct upid is used to get the id of the struct pid, as it is * seen in particular namespace. Later the struct pid is found with * find_pid_ns() using the int nr and struct pid_namespace *ns. */struct upid { int nr; struct pid_namespace *ns;};struct pid{ refcount_t count; unsigned int level; spinlock_t lock; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; /* wait queue for pidfd notifications */ wait_queue_head_t wait_pidfd; struct rcu_head rcu; struct upid numbers[1];}; 对于struct upid， nr表示ID的数值， ns是指向该ID所属的命名空间的指针。所有的upid实例都保存在一个散列表中。 pid_chain用内核的标准方法实现了散列溢出链表。struct pid的定义首先是一个引用计数器count。 tasks是一个数组，每个数组项都是一个散列表头，对应于一个ID类型。这样做是必要的，因为一个ID可能用于几个进程。所有共享同一给定ID的task_struct实例，都通过该列表连接起来。 PIDTYPE_MAX表示ID类型的数目：
struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size){ struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM;
/* * set_tid_size contains the size of the set_tid array. Starting at * the most nested currently active PID namespace it tells alloc_pid() * which PID to set for a process in that most nested PID namespace * up to set_tid_size PID namespaces. It does not have to set the PID * for a process in all nested PID namespaces but set_tid_size must * never be greater than the current ns->level + 1. */ if (set_tid_size > ns->level + 1) return ERR_PTR(-EINVAL);
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 tid = 0;
if (set_tid_size) { tid = set_tid[ns->level - i];
retval = -EINVAL; if (tid < 1 || tid >= pid_max) goto out_free; /* * Also fail if a PID != 1 is requested and * no PID 1 exists. */ if (tid != 1 && !tmp->child_reaper) goto out_free; retval = -EPERM; if (!checkpoint_restore_ns_capable(tmp->user_ns)) goto out_free; set_tid_size--; }
if (tid) { nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* * If ENOSPC is returned it means that the PID is * alreay in use. Return EEXIST in that case. */ if (nr == -ENOSPC) nr = -EEXIST; } else { int pid_min = 1; /* * 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();
