Unix管道的实现方式

我们在说啥啊？

$ echo hello | wc -c
6

传送带提供单向进程间通信通道。流水线具有一个输入（写端）和一个输出（读端）。可以读取写入管道输入的数据。

使用pipe(2)返回两个文件描述符的调用来创建管道：一个引用管道的输入，第二个引用输出。

$ strace -qf -e execve,pipe,dup2,read,write \
    sh -c 'echo hello | wc -c'

execve("/bin/sh", ["sh", "-c", "echo hello | wc -c"], …)
pipe([3, 4])                            = 0
[pid 2604795] dup2(4, 1)                = 1
[pid 2604795] write(1, "hello\n", 6)    = 6
[pid 2604796] dup2(3, 0)                = 0
[pid 2604796] execve("/usr/bin/wc", ["wc", "-c"], …)
[pid 2604796] read(0, "hello\n", 16384) = 6
[pid 2604796] write(1, "6\n", 2)        = 2

, read(2) , . , write(2) , .

我们在找什么？

我们在找什么

传统的Unix内核（1970–1974）

Unix的第三版是使用汇编语言编写的内核的最新版本，而第一版则使用管道。1973年，做了很多工作来改进第三版，用C重写了内核，因此出现了第四版Unix。

Unix, , , , - , , . , . , , , . ? «» , , -, : « !».

. , , ( ), . . . API , .

管道系统调用创建称为管道的输出输入机制。返回的文件描述符可用于读取和写入操作。将某些内容写入管道时，最多缓冲504字节的数据，此后暂停写入过程。从管道读取时，将获取缓冲的数据。

pipe , . . - , , r1 (. fildes[1]), 4096 , . , r0 (. fildes[0]), .

, ( ) ( fork) read write.

Shell具有用于定义通过管道连接的线性进程数组的语法。

从只有一端（所有写入文件描述符均已关闭）的空管道（不包含缓冲数据）进行的读取调用将返回“文件末尾”。在类似情况下的录音呼叫将被忽略。

第六版Unix（1975）

多年来，Lions是Bell实验室之外唯一可用的Unix核心文档。尽管第六版的许可证允许教师使用其源代码，但第七版的许可证排除了这种可能性，因此该书以非法打字副本的形式分发。

15 , Lions, . TUHS , . 1988- 9 , PDP11. , , /usr/src/, 1979- , . PWB, .

. , , += =+. - , - , .

/*
 * Max allowable buffering per pipe.
 * This is also the max size of the
 * file created to implement the pipe.
 * If this size is bigger than 4096,
 * pipes will be implemented in LARG
 * files, which is probably not good.
 */
#define    PIPSIZ    4096

/*
 * The sys-pipe entry.
 * Allocate an inode on the root device.
 * Allocate 2 file structures.
 * Put it all together with flags.
 */
pipe()
{
    register *ip, *rf, *wf;
    int r;

    ip = ialloc(rootdev);
    if(ip == NULL)
        return;
    rf = falloc();
    if(rf == NULL) {
        iput(ip);
        return;
    }
    r = u.u_ar0[R0];
    wf = falloc();
    if(wf == NULL) {
        rf->f_count = 0;
        u.u_ofile[r] = NULL;
        iput(ip);
        return;
    }
    u.u_ar0[R1] = u.u_ar0[R0]; /* wf's fd */
    u.u_ar0[R0] = r;           /* rf's fd */
    wf->f_flag = FWRITE|FPIPE;
    wf->f_inode = ip;
    rf->f_flag = FREAD|FPIPE;
    rf->f_inode = ip;
    ip->i_count = 2;
    ip->i_flag = IACC|IUPD;
    ip->i_mode = IALLOC;
}

/*
 * common code for read and write calls:
 * check permissions, set base, count, and offset,
 * and switch out to readi, writei, or pipe code.
 */
rdwr(mode)
{
    register *fp, m;

    m = mode;
    fp = getf(u.u_ar0[R0]);
        /* … */

    if(fp->f_flag&FPIPE) {
        if(m==FREAD)
            readp(fp); else
            writep(fp);
    }
        /* … */
}

writep(fp)
{
    register *rp, *ip, c;

    rp = fp;
    ip = rp->f_inode;
    c = u.u_count;

loop:
    /* If all done, return. */

    plock(ip);
    if(c == 0) {
        prele(ip);
        u.u_count = 0;
        return;
    }

    /*
     * If there are not both read and write sides of the
     * pipe active, return error and signal too.
     */

    if(ip->i_count < 2) {
        prele(ip);
        u.u_error = EPIPE;
        psignal(u.u_procp, SIGPIPE);
        return;
    }

    /*
     * If the pipe is full, wait for reads to deplete
     * and truncate it.
     */

    if(ip->i_size1 == PIPSIZ) {
        ip->i_mode =| IWRITE;
        prele(ip);
        sleep(ip+1, PPIPE);
        goto loop;
    }

    /* Write what is possible and loop back. */

    u.u_offset[0] = 0;
    u.u_offset[1] = ip->i_size1;
    u.u_count = min(c, PIPSIZ-u.u_offset[1]);
    c =- u.u_count;
    writei(ip);
    prele(ip);
    if(ip->i_mode&IREAD) {
        ip->i_mode =& ~IREAD;
        wakeup(ip+2);
    }
    goto loop;
}

/*
 * Give up the processor till a wakeup occurs
 * on chan, at which time the process
 * enters the scheduling queue at priority pri.
 * The most important effect of pri is that when
 * pri<0 a signal cannot disturb the sleep;
 * if pri>=0 signals will be processed.
 * Callers of this routine must be prepared for
 * premature return, and check that the reason for
 * sleeping has gone away.
 */
sleep(chan, pri) /* … */

/*
 * Wake up all processes sleeping on chan.
 */
wakeup(chan) /* … */

readp(fp)
int *fp;
{
    register *rp, *ip;

    rp = fp;
    ip = rp->f_inode;

loop:
    /* Very conservative locking. */

    plock(ip);

    /*
     * If the head (read) has caught up with
     * the tail (write), reset both to 0.
     */

    if(rp->f_offset[1] == ip->i_size1) {
        if(rp->f_offset[1] != 0) {
            rp->f_offset[1] = 0;
            ip->i_size1 = 0;
            if(ip->i_mode&IWRITE) {
                ip->i_mode =& ~IWRITE;
                wakeup(ip+1);
            }
        }

        /*
         * If there are not both reader and
         * writer active, return without
         * satisfying read.
         */

        prele(ip);
        if(ip->i_count < 2)
            return;
        ip->i_mode =| IREAD;
        sleep(ip+2, PPIPE);
        goto loop;
    }

    /* Read and return */

    u.u_offset[0] = 0;
    u.u_offset[1] = rp->f_offset[1];
    readi(ip);
    rp->f_offset[1] = u.u_offset[1];
    prele(ip);
}

/*
 * Read the file corresponding to
 * the inode pointed at by the argument.
 * The actual read arguments are found
 * in the variables:
 *    u_base        core address for destination
 *    u_offset    byte offset in file
 *    u_count        number of bytes to read
 *    u_segflg    read to kernel/user
 */
readi(aip)
struct inode *aip;
/* … */

/*
 * Write the file corresponding to
 * the inode pointed at by the argument.
 * The actual write arguments are found
 * in the variables:
 *    u_base        core address for source
 *    u_offset    byte offset in file
 *    u_count        number of bytes to write
 *    u_segflg    write to kernel/user
 */
writei(aip)
struct inode *aip;
/* … */

/*
 * Lock a pipe.
 * If its already locked, set the WANT bit and sleep.
 */
plock(ip)
int *ip;
{
    register *rp;

    rp = ip;
    while(rp->i_flag&ILOCK) {
        rp->i_flag =| IWANT;
        sleep(rp, PPIPE);
    }
    rp->i_flag =| ILOCK;
}

/*
 * Unlock a pipe.
 * If WANT bit is on, wakeup.
 * This routine is also used to unlock inodes in general.
 */
prele(ip)
int *ip;
{
    register *rp;

    rp = ip;
    rp->i_flag =& ~ILOCK;
    if(rp->i_flag&IWANT) {
        rp->i_flag =& ~IWANT;
        wakeup(rp);
    }
}

Xv6，一个简单的Unix形内核

#define PIPESIZE 512

struct pipe {
  struct spinlock lock;
  char data[PIPESIZE];
  uint nread;     // number of bytes read
  uint nwrite;    // number of bytes written
  int readopen;   // read fd is still open
  int writeopen;  // write fd is still open
};

int
pipealloc(struct file **f0, struct file **f1)
{
  struct pipe *p;

  p = 0;
  *f0 = *f1 = 0;
  if((*f0 = filealloc()) == 0 || (*f1 = filealloc()) == 0)
    goto bad;
  if((p = (struct pipe*)kalloc()) == 0)
    goto bad;
  p->readopen = 1;
  p->writeopen = 1;
  p->nwrite = 0;
  p->nread = 0;
  initlock(&p->lock, "pipe");
  (*f0)->type = FD_PIPE;
  (*f0)->readable = 1;
  (*f0)->writable = 0;
  (*f0)->pipe = p;
  (*f1)->type = FD_PIPE;
  (*f1)->readable = 0;
  (*f1)->writable = 1;
  (*f1)->pipe = p;
  return 0;

 bad:
  if(p)
    kfree((char*)p);
  if(*f0)
    fileclose(*f0);
  if(*f1)
    fileclose(*f1);
  return -1;
}

Linux 0.01

int write_pipe(struct m_inode * inode, char * buf, int count)
{
    char * b=buf;

    wake_up(&inode->i_wait);
    if (inode->i_count != 2) { /* no readers */
        current->signal |= (1<<(SIGPIPE-1));
        return -1;
    }
    while (count-->0) {
        while (PIPE_FULL(*inode)) {
            wake_up(&inode->i_wait);
            if (inode->i_count != 2) {
                current->signal |= (1<<(SIGPIPE-1));
                return b-buf;
            }
            sleep_on(&inode->i_wait);
        }
        ((char *)inode->i_size)[PIPE_HEAD(*inode)] =
            get_fs_byte(b++);
        INC_PIPE( PIPE_HEAD(*inode) );
        wake_up(&inode->i_wait);
    }
    wake_up(&inode->i_wait);
    return b-buf;
}

现代Linux，FreeBSD，NetBSD，OpenBSD内核