本文部分内容截取自《深入理解Linux内核》，版权属于原作者。笔记代码参考2.6.11。小弟看ULK断断续续，一直都没坚持下来，如有错误，还请各位老大指正~
CONTENTS
pidhash介绍
\include\linux\pid.h
#ifndef _LINUX_PID_H
#define _LINUX_PID_H
/*
pid的hashmap一共有4个，分别对应下面的4中类型。
同样，在进程描述符中task_struct中，有一个变量
struct pid pids[PIDTYPE_MAX];
该数组的每一个元素都分别的添加到对应的这4个hashmap中
*/
enum pid_type
{
PIDTYPE_PID,
PIDTYPE_TGID,
PIDTYPE_PGID,
PIDTYPE_SID,
PIDTYPE_MAX
};
/*
放在pidhashmap中的单个元素。
由于是hashmap方式存储，因此必定会有冲突，然后用链表串起来
如果是因为pid号码hash导致的，就使用pid_chain串起来，
如果是因为pid号码相同导致的，就使用pid_list串起来。
*/
struct pid
{
/* Try to keep pid_chain in the same cacheline as nr for find_pid */
int nr; /* 该pid结构体中存储的pid号码 */
struct hlist_node pid_chain; /* 当pid号码hash冲突时，使用该元素来链 */
/* list of pids with the same nr, only one of them is in the hash */
struct list_head pid_list;/* 当pid号码相同时，使用该元素链 */
};
/* hashmap中存储的是task_struct中pid数组的对应元素，因此这里可以根据hashmap中
对应的pid指针来反向获取它所在的task_struct的指针。
*/
#define pid_task(elem, type) \
list_entry(elem, struct task_struct, pids[type].pid_list)
/*
* attach_pid() and detach_pid() must be called with the tasklist_lock
* write-held.
*/
extern int FASTCALL(attach_pid(struct task_struct *task, enum pid_type type, int nr));
extern void FASTCALL(detach_pid(struct task_struct *task, enum pid_type));
/*
* look up a PID in the hash table. Must be called with the tasklist_lock
* held.
*/
extern struct pid *FASTCALL(find_pid(enum pid_type, int));
extern int alloc_pidmap(void);
extern void FASTCALL(free_pidmap(int));
extern void switch_exec_pids(struct task_struct *leader, struct task_struct *thread);
#define do_each_task_pid(who, type, task) \
if ((task = find_task_by_pid_type(type, who))) { \
prefetch((task)->pids[type].pid_list.next); \
do {
#define while_each_task_pid(who, type, task) \
} while (task = pid_task((task)->pids[type].pid_list.next,\
type), \
prefetch((task)->pids[type].pid_list.next), \
hlist_unhashed(&(task)->pids[type].pid_chain)); \
} \
#endif /* _LINUX_PID_H */
\kernel\pid.c
/*
* Generic pidhash and scalable, time-bounded PID allocator
*
* (C) 2002-2003 William Irwin, IBM
* (C) 2004 William Irwin, 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).
*/
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/hash.h>
/*
pid号码hash函数
*/
#define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift)
/* 内核中的hashmap数组，每个数组都是一个链表头数组，
因此对于该pid_hash的一次解引用可以获得指定的链表头数组，
第二次解引用可以获得指定的链表头
*/
static struct hlist_head *pid_hash[PIDTYPE_MAX];
static int pidhash_shift;
int pid_max = PID_MAX_DEFAULT;
int last_pid;
#define RESERVED_PIDS 300
int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT;
#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8)
#define BITS_PER_PAGE (PAGE_SIZE*8)
#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1)
#define mk_pid(map, off) (((map) - pidmap_array)*BITS_PER_PAGE + (off))
#define find_next_offset(map, off) \
find_next_zero_bit((map)->page, BITS_PER_PAGE, off)
/*
* 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.
*/
typedef struct pidmap {
atomic_t nr_free;/* 当前还剩下的可用的pid号码*/
void *page;
} pidmap_t;
static pidmap_t pidmap_array[PIDMAP_ENTRIES] =
{ [ 0 ... PIDMAP_ENTRIES-1 ] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } };
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
/*
回收不用的pid号码
*/
fastcall void free_pidmap(int pid)
{
/*
首先找到该pid号码对应的pidmap指针
*/
pidmap_t *map = pidmap_array + pid / BITS_PER_PAGE;
int offset = pid & BITS_PER_PAGE_MASK;
/*
将该pid号码对应的bit清了，同时增加可用数目
*/
clear_bit(offset, map->page);
atomic_inc(&map->nr_free);
}
/*
分配一个pid号码
*/
int alloc_pidmap(void)
{
int i, offset, max_scan, pid, last = last_pid;
pidmap_t *map;
pid = last + 1;
if (pid >= pid_max)
pid = RESERVED_PIDS;
offset = pid & BITS_PER_PAGE_MASK;
map = &pidmap_array[pid/BITS_PER_PAGE];
max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset;
for (i = 0; i <= max_scan; ++i) {
/*
如果当前内存不够了，就申请一块新的内存
*/
if (unlikely(!map->page)) {
unsigned long page = get_zeroed_page(GFP_KERNEL);
/*
* Free the page if someone raced with us
* installing it:
*/
spin_lock(&pidmap_lock);
if (map->page)
free_page(page);
else
map->page = (void *)page;
spin_unlock(&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);
last_pid = pid;
return pid;
}
/* 查找空余为0的bit位，其实就是可用的pid号码 */
offset = find_next_offset(map, offset);
pid = mk_pid(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 < &pidmap_array[(pid_max-1)/BITS_PER_PAGE]) {
++map;
offset = 0;
} else {
map = &pidmap_array[0];
offset = RESERVED_PIDS;
if (unlikely(last == offset))
break;
}
pid = mk_pid(map, offset);
}
return -1;
}
/*
在hashmap中查找指定的pid号码对应的pid元素结构体指针。
*/
struct pid * fastcall find_pid(enum pid_type type, int nr)
{
struct hlist_node *elem;
struct pid *pid;
/*
首先可以根据type确定是哪一个hashmap，然后根据hash函数可以获取是哪一个链表头，
由于该链表头链起来的是pid号码hash相同的元素，因此需要在这个链表头上开始一个一个寻找，通过简单的判断pid号码是否相同*/
hlist_for_each_entry(pid, elem,
&pid_hash[type][pid_hashfn(nr)], pid_chain) {
if (pid->nr == nr)
return pid;
}
return NULL;
}
/*
将某一个task指定一个特定的类别上的pid号码
*/
int fastcall attach_pid(task_t *task, enum pid_type type, int nr)
{
struct pid *pid, *task_pid;
task_pid = &task->pids[type];
pid = find_pid(type, nr);
/*
首先通过find函数来看下当前hash中是否已经有相同的pid号码的pid元素了，
如果有，那么就通过pid_list加到最后，
如果没有，说明当前pidhash还没有出现冲突，可以直接挂到hashmap对应的链表头上。
*/
if (pid == NULL) {
hlist_add_head(&task_pid->pid_chain,//挂链表头用pid_chain
&pid_hash[type][pid_hashfn(nr)]);
INIT_LIST_HEAD(&task_pid->pid_list);
} else {
INIT_HLIST_NODE(&task_pid->pid_chain);
list_add_tail(&task_pid->pid_list, &pid->pid_list);//挂相同pid号用pid_list
}
/*
将task对应的pid号码存储起来
*/
task_pid->nr = nr;
return 0;
}
/*
将某一个task从对应的hashmap上解下来
*/
static fastcall int __detach_pid(task_t *task, enum pid_type type)
{
struct pid *pid, *pid_next;
int nr = 0;
pid = &task->pids[type];
/*
如果当前task就没有在对应的hashmap上，就很简单了
*/
if (!hlist_unhashed(&pid->pid_chain)) {
hlist_del(&pid->pid_chain);
/*
如果没有相同的pid号码，也很好处理
*/
if (list_empty(&pid->pid_list))
nr = pid->nr;
else {
/*
如果有相同的pid号码，就要维护好以前的链表，即pid_list链表
*/
pid_next = list_entry(pid->pid_list.next,
struct pid, pid_list);
/* insert next pid from pid_list to hash */
hlist_add_head(&pid_next->pid_chain,
&pid_hash[type][pid_hashfn(pid_next->nr)]);
}
}
list_del(&pid->pid_list);
pid->nr = 0;
return nr;
}
void fastcall detach_pid(task_t *task, enum pid_type type)
{
int tmp, nr;
nr = __detach_pid(task, type);
if (!nr)
return;
for (tmp = PIDTYPE_MAX; --tmp >= 0; )
if (tmp != type && find_pid(tmp, nr))
return;
free_pidmap(nr);
}
/*
根据pid号码和类型查找对应的task
*/
task_t *find_task_by_pid_type(int type, int nr)
{
struct pid *pid;
pid = find_pid(type, nr);
if (!pid)
return NULL;
return pid_task(&pid->pid_list, type);
}
EXPORT_SYMBOL(find_task_by_pid_type);
/*
* This function switches the PIDs if a non-leader thread calls
* sys_execve() - this must be done without releasing the PID.
* (which a detach_pid() would eventually do.)
*/
void switch_exec_pids(task_t *leader, task_t *thread)
{
__detach_pid(leader, PIDTYPE_PID);
__detach_pid(leader, PIDTYPE_TGID);
__detach_pid(leader, PIDTYPE_PGID);
__detach_pid(leader, PIDTYPE_SID);
__detach_pid(thread, PIDTYPE_PID);
__detach_pid(thread, PIDTYPE_TGID);
leader->pid = leader->tgid = thread->pid;
thread->pid = thread->tgid;
attach_pid(thread, PIDTYPE_PID, thread->pid);
attach_pid(thread, PIDTYPE_TGID, thread->tgid);
attach_pid(thread, PIDTYPE_PGID, thread->signal->pgrp);
attach_pid(thread, PIDTYPE_SID, thread->signal->session);
list_add_tail(&thread->tasks, &init_task.tasks);
attach_pid(leader, PIDTYPE_PID, leader->pid);
attach_pid(leader, PIDTYPE_TGID, leader->tgid);
attach_pid(leader, PIDTYPE_PGID, leader->signal->pgrp);
attach_pid(leader, PIDTYPE_SID, leader->signal->session);
}
/*
* 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
* more.
*/
void __init pidhash_init(void)
{
int i, j, pidhash_size;
unsigned long megabytes = nr_kernel_pages >> (20 - PAGE_SHIFT);
pidhash_shift = max(4, fls(megabytes * 4));
pidhash_shift = min(12, pidhash_shift);
pidhash_size = 1 << pidhash_shift;
printk("PID hash table entries: %d (order: %d, %Zd bytes)\n",
pidhash_size, pidhash_shift,
PIDTYPE_MAX * pidhash_size * sizeof(struct hlist_head));
for (i = 0; i < PIDTYPE_MAX; i++) {
pid_hash[i] = alloc_bootmem(pidhash_size *
sizeof(*(pid_hash[i])));
if (!pid_hash[i])
panic("Could not alloc pidhash!\n");
for (j = 0; j < pidhash_size; j++)
INIT_HLIST_HEAD(&pid_hash[i][j]);
}
}
void __init pidmap_init(void)
{
int i;
pidmap_array->page = (void *)get_zeroed_page(GFP_KERNEL);
set_bit(0, pidmap_array->page);
atomic_dec(&pidmap_array->nr_free);
/*
* Allocate PID 0, and hash it via all PID types:
*/
for (i = 0; i < PIDTYPE_MAX; i++)
attach_pid(current, i, 0);
}
发表评论