MIT_6.S081_xv6.Information 6:File System

#define BSIZE 1024  // block size
struct buf {
  int valid;   // has data been read from disk?
  int disk;    // does disk "own" buf?
  uint dev;
  uint blockno;
  struct sleeplock lock;
  uint refcnt;
  struct buf *prev; // LRU cache list
  struct buf *next;
  uchar data[BSIZE];
};

struct buf {
  int valid;   // has data been read from disk?
  int disk;    // does disk "own" buf?
  uint dev;
  uint blockno;
  struct sleeplock lock;
  uint refcnt;
  struct buf *prev; // LRU cache list
  struct buf *next;
  uchar data[BSIZE];
};

struct {
  struct spinlock lock;
  struct buf buf[NBUF];

  // Linked list of all buffers, through prev/next.
  // Sorted by how recently the buffer was used.
  // head.next is most recent, head.prev is least.
  struct buf head;
} bcache;

void
binit(void)
{
  struct buf *b;

  initlock(&bcache.lock, "bcache");

  // Create linked list of buffers
  bcache.head.prev = &bcache.head;
  bcache.head.next = &bcache.head;
  for(b = bcache.buf; b < bcache.buf+NBUF; b++){
    b->next = bcache.head.next;
    b->prev = &bcache.head;
    initsleeplock(&b->lock, "buffer");
    bcache.head.next->prev = b;
    bcache.head.next = b;
  }
}

// Look through buffer cache for block on device dev.
// If not found, allocate a buffer.
// In either case, return locked buffer.
static struct buf*
bget(uint dev, uint blockno)
{
  struct buf *b;

  acquire(&bcache.lock);

  // Is the block already cached?
  for(b = bcache.head.next; b != &bcache.head; b = b->next){
    if(b->dev == dev && b->blockno == blockno){
      b->refcnt++;
      release(&bcache.lock);
      acquiresleep(&b->lock);
      return b;
    }
  }

  // Not cached.
  // Recycle the least recently used (LRU) unused buffer.
  for(b = bcache.head.prev; b != &bcache.head; b = b->prev){
    if(b->refcnt == 0) {
      b->dev = dev;
      b->blockno = blockno;
      b->valid = 0;
      b->refcnt = 1;
      release(&bcache.lock);
      acquiresleep(&b->lock);
      return b;
    }
  }
  panic("bget: no buffers");
}

// Return a locked buf with the contents of the indicated block.
struct buf*
bread(uint dev, uint blockno)
{
  struct buf *b;

  b = bget(dev, blockno);
  if(!b->valid) {
    virtio_disk_rw(b, 0);
    b->valid = 1;
  }
  return b;
}

// Write b's contents to disk.  Must be locked.
void
bwrite(struct buf *b)
{
  if(!holdingsleep(&b->lock))
    panic("bwrite");
  virtio_disk_rw(b, 1);
}

// Release a locked buffer.
// Move to the head of the most-recently-used list.
void
brelse(struct buf *b)
{
  if(!holdingsleep(&b->lock))
    panic("brelse");

  releasesleep(&b->lock);

  acquire(&bcache.lock);
  b->refcnt--;
  if (b->refcnt == 0) {
    // no one is waiting for it.
    b->next->prev = b->prev;
    b->prev->next = b->next;
    b->next = bcache.head.next;
    b->prev = &bcache.head;
    bcache.head.next->prev = b;
    bcache.head.next = b;
  }
  
  release(&bcache.lock);
}

void
bpin(struct buf *b) {
  acquire(&bcache.lock);
  b->refcnt++;
  release(&bcache.lock);
}

void
bunpin(struct buf *b) {
  acquire(&bcache.lock);
  b->refcnt--;
  release(&bcache.lock);
}

// Disk layout:
// [ boot block | super block | log | inode blocks |
//                                          free bit map | data blocks]
//
// mkfs computes the super block and builds an initial file system. The
// super block describes the disk layout:
struct superblock {
  uint magic;        // Must be FSMAGIC
  uint size;         // Size of file system image (blocks)
  uint nblocks;      // Number of data blocks
  uint ninodes;      // Number of inodes.
  uint nlog;         // Number of log blocks
  uint logstart;     // Block number of first log block
  uint inodestart;   // Block number of first inode block
  uint bmapstart;    // Block number of first free map block
};

// Contents of the header block, used for both the on-disk header block
// and to keep track in memory of logged block# before commit.
struct logheader {
  int n;
  int block[LOGSIZE];
};

struct log {
  struct spinlock lock;
  int start;
  int size;
  int outstanding; // how many FS sys calls are executing.
  int committing;  // in commit(), please wait.
  int dev;
  struct logheader lh;
};

void
initlog(int dev, struct superblock *sb)
{
  if (sizeof(struct logheader) >= BSIZE)
    panic("initlog: too big logheader");

  initlock(&log.lock, "log");
  log.start = sb->logstart;
  log.size = sb->nlog;
  log.dev = dev;
  recover_from_log();
}

static void
recover_from_log(void)
{
  read_head();
  install_trans(1); // if committed, copy from log to disk
  log.lh.n = 0;
  write_head(); // clear the log
}

// Read the log header from disk into the in-memory log header
static void
read_head(void)
{
  struct buf *buf = bread(log.dev, log.start);
  struct logheader *lh = (struct logheader *) (buf->data);
  int i;
  log.lh.n = lh->n;
  for (i = 0; i < log.lh.n; i++) {
    log.lh.block[i] = lh->block[i];
  }
  brelse(buf);
}

// Copy committed blocks from log to their home location
static void
install_trans(int recovering)
{
  int tail;

  for (tail = 0; tail < log.lh.n; tail++) {
    struct buf *lbuf = bread(log.dev, log.start+tail+1); // read log block
    struct buf *dbuf = bread(log.dev, log.lh.block[tail]); // read dst
    memmove(dbuf->data, lbuf->data, BSIZE);  // copy block to dst
    bwrite(dbuf);  // write dst to disk
    if(recovering == 0)
      bunpin(dbuf);
    brelse(lbuf);
    brelse(dbuf);
  }
}

// called at the start of each FS system call.
void
begin_op(void)
{
  acquire(&log.lock);
  while(1){
    if(log.committing){
      sleep(&log, &log.lock);
    } else if(log.lh.n + (log.outstanding+1)*MAXOPBLOCKS > LOGSIZE){
      // this op might exhaust log space; wait for commit.
      sleep(&log, &log.lock);
    } else {
      log.outstanding += 1;
      release(&log.lock);
      break;
    }
  }
}

// called at the end of each FS system call.
// commits if this was the last outstanding operation.
void
end_op(void)
{
  int do_commit = 0;

  acquire(&log.lock);
  log.outstanding -= 1;
  if(log.committing)
    panic("log.committing");
  if(log.outstanding == 0){
    do_commit = 1;
    log.committing = 1;
  } else {
    // begin_op() may be waiting for log space,
    // and decrementing log.outstanding has decreased
    // the amount of reserved space.
    wakeup(&log);
  }
  release(&log.lock);

  if(do_commit){
    // call commit w/o holding locks, since not allowed
    // to sleep with locks.
    commit();
    acquire(&log.lock);
    log.committing = 0;
    wakeup(&log);
    release(&log.lock);
  }
}

void
log_write(struct buf *b)
{
  int i;

  acquire(&log.lock);
  if (log.lh.n >= LOGSIZE || log.lh.n >= log.size - 1)
    panic("too big a transaction");
  if (log.outstanding < 1)
    panic("log_write outside of trans");

  for (i = 0; i < log.lh.n; i++) {
    if (log.lh.block[i] == b->blockno)   // log absorption
      break;
  }
  log.lh.block[i] = b->blockno;
  if (i == log.lh.n) {  // Add new block to log?
    bpin(b);
    log.lh.n++;
  }
  release(&log.lock);
}

static void
commit()
{
  if (log.lh.n > 0) {
    write_log();     // Write modified blocks from cache to log
    write_head();    // Write header to disk -- the real commit
    install_trans(0); // Now install writes to home locations
    log.lh.n = 0;
    write_head();    // Erase the transaction from the log
  }
}

// Copy modified blocks from cache to log.
static void
write_log(void)
{
  int tail;

  for (tail = 0; tail < log.lh.n; tail++) {
    struct buf *to = bread(log.dev, log.start+tail+1); // log block
    struct buf *from = bread(log.dev, log.lh.block[tail]); // cache block
    memmove(to->data, from->data, BSIZE);
    bwrite(to);  // write the log
    brelse(from);
    brelse(to);
  }
}

// Allocate a zeroed disk block.
static uint
balloc(uint dev)
{
  int b, bi, m;
  struct buf *bp;

  bp = 0;
  for(b = 0; b < sb.size; b += BPB){
    bp = bread(dev, BBLOCK(b, sb));
    for(bi = 0; bi < BPB && b + bi < sb.size; bi++){
      m = 1 << (bi % 8);
      if((bp->data[bi/8] & m) == 0){  // Is block free?
        bp->data[bi/8] |= m;  // Mark block in use.
        log_write(bp);
        brelse(bp);
        bzero(dev, b + bi);
        return b + bi;
      }
    }
    brelse(bp);
  }
  panic("balloc: out of blocks");
}

// Free a disk block.
static void
bfree(int dev, uint b)
{
  struct buf *bp;
  int bi, m;

  bp = bread(dev, BBLOCK(b, sb));
  bi = b % BPB;
  m = 1 << (bi % 8);
  if((bp->data[bi/8] & m) == 0)
    panic("freeing free block");
  bp->data[bi/8] &= ~m;
  log_write(bp);
  brelse(bp);
}

// 下面的宏定义用于type字段，type = 0表示该dinode尚未分配
#define T_DIR     1
#define T_FILE    2
#define T_DEVICE  3
// On-disk inode structure
struct dinode {
  short type;           // File type
  short major;          // Major device number (T_DEVICE only)
  short minor;          // Minor device number (T_DEVICE only)
  short nlink;          // Number of links to inode in file system
  uint size;            // Size of file (bytes)
  uint addrs[NDIRECT+1];   // Data block addresses
};

// in-memory copy of an inode
struct inode {
  uint dev;           // Device number
  uint inum;          // Inode number
  int ref;            // Reference count
  struct sleeplock lock; // protects everything below here
  int valid;          // inode has been read from disk?

  short type;         // copy of disk inode
  short major;
  short minor;
  short nlink;
  uint size;
  uint addrs[NDIRECT+1];
};

struct {
  struct spinlock lock;
  struct inode inode[NINODE];
} itable;
// Find the inode with number inum on device dev
// and return the in-memory copy. Does not lock
// the inode and does not read it from disk.
static struct inode*
iget(uint dev, uint inum)
{
  struct inode *ip, *empty;

  acquire(&itable.lock);

  // Is the inode already in the table?
  empty = 0;
  for(ip = &itable.inode[0]; ip < &itable.inode[NINODE]; ip++){
    if(ip->ref > 0 && ip->dev == dev && ip->inum == inum){
      ip->ref++;
      release(&itable.lock);
      return ip;
    }
    if(empty == 0 && ip->ref == 0)    // Remember empty slot.
      empty = ip;
  }

  // Recycle an inode entry.
  if(empty == 0)
    panic("iget: no inodes");

  ip = empty;
  ip->dev = dev;
  ip->inum = inum;
  ip->ref = 1;
  ip->valid = 0;
  release(&itable.lock);

  return ip;
}

// Inodes per block.
#define IPB           (BSIZE / sizeof(struct dinode))

// Block containing inode i
#define IBLOCK(i, sb)     ((i) / IPB + sb.inodestart)

// Lock the given inode.
// Reads the inode from disk if necessary.
void
ilock(struct inode *ip)
{
  struct buf *bp;
  struct dinode *dip;

  if(ip == 0 || ip->ref < 1)
    panic("ilock");

  acquiresleep(&ip->lock);

  if(ip->valid == 0){
    bp = bread(ip->dev, IBLOCK(ip->inum, sb));
    dip = (struct dinode*)bp->data + ip->inum%IPB;
    ip->type = dip->type;
    ip->major = dip->major;
    ip->minor = dip->minor;
    ip->nlink = dip->nlink;
    ip->size = dip->size;
    memmove(ip->addrs, dip->addrs, sizeof(ip->addrs));
    brelse(bp);
    ip->valid = 1;
    if(ip->type == 0)
      panic("ilock: no type");
  }
}

// Unlock the given inode.
void
iunlock(struct inode *ip)
{
  if(ip == 0 || !holdingsleep(&ip->lock) || ip->ref < 1)
    panic("iunlock");

  releasesleep(&ip->lock);
}

// Increment reference count for ip.
// Returns ip to enable ip = idup(ip1) idiom.
struct inode*
idup(struct inode *ip)
{
  acquire(&itable.lock);
  ip->ref++;
  release(&itable.lock);
  return ip;
}
// Drop a reference to an in-memory inode.
// If that was the last reference, the inode table entry can
// be recycled.
// If that was the last reference and the inode has no links
// to it, free the inode (and its content) on disk.
// All calls to iput() must be inside a transaction in
// case it has to free the inode.
void
iput(struct inode *ip)
{
  acquire(&itable.lock);

  if(ip->ref == 1 && ip->valid && ip->nlink == 0){
    // inode has no links and no other references: truncate and free.

    // ip->ref == 1 means no other process can have ip locked,
    // so this acquiresleep() won't block (or deadlock).
    acquiresleep(&ip->lock);

    release(&itable.lock);

    itrunc(ip);
    ip->type = 0;
    iupdate(ip);
    ip->valid = 0;

    releasesleep(&ip->lock);

    acquire(&itable.lock);
  }

  ip->ref--;
  release(&itable.lock);
}

// Truncate(截断) inode (discard contents).
// Caller must hold ip->lock.
void
itrunc(struct inode *ip)
{
  int i, j;
  struct buf *bp;
  uint *a;
  // 遍历前面NDIRECT个直接块，并进行释放块操作
  for(i = 0; i < NDIRECT; i++){
    if(ip->addrs[i]){
      bfree(ip->dev, ip->addrs[i]);
      ip->addrs[i] = 0;
    }
  }

  if(ip->addrs[NDIRECT]){
    bp = bread(ip->dev, ip->addrs[NDIRECT]);
    a = (uint*)bp->data;
    // 遍历后面NINDIRECT个间接块，进行释放操作
    for(j = 0; j < NINDIRECT; j++){
      if(a[j])
        bfree(ip->dev, a[j]);
    }
    brelse(bp);
    bfree(ip->dev, ip->addrs[NDIRECT]);
    ip->addrs[NDIRECT] = 0;
  }

  ip->size = 0;
  iupdate(ip);
}

static uint
bmap(struct inode *ip, uint bn)
{
  uint addr, *a;
  struct buf *bp;
  // 判断是否为直接块
  if(bn < NDIRECT){
    if((addr = ip->addrs[bn]) == 0)
      ip->addrs[bn] = addr = balloc(ip->dev);
    return addr;
  }
  bn -= NDIRECT;
  // 判断是否是间接块
  if(bn < NINDIRECT){
    // Load indirect block, allocating if necessary.
    if((addr = ip->addrs[NDIRECT]) == 0)
      ip->addrs[NDIRECT] = addr = balloc(ip->dev);
    bp = bread(ip->dev, addr);
    a = (uint*)bp->data;
    if((addr = a[bn]) == 0){
      a[bn] = addr = balloc(ip->dev);
      log_write(bp);
    }
    brelse(bp);
    return addr;
  }

  panic("bmap: out of range");
}

// Write data to inode.
// Caller must hold ip->lock.
// If user_src==1, then src is a user virtual address;
// otherwise, src is a kernel address.
// Returns the number of bytes successfully written.
// If the return value is less than the requested n,
// there was an error of some kind.
int
writei(struct inode *ip, int user_src, uint64 src, uint off, uint n)
{
  uint tot, m;
  struct buf *bp;

  if(off > ip->size || off + n < off)
    return -1;
  if(off + n > MAXFILE*BSIZE)
    return -1;

  for(tot=0; tot<n; tot+=m, off+=m, src+=m){
    bp = bread(ip->dev, bmap(ip, off/BSIZE));
    m = min(n - tot, BSIZE - off%BSIZE);
    if(either_copyin(bp->data + (off % BSIZE), user_src, src, m) == -1) {
      brelse(bp);
      break;
    }
    log_write(bp);
    brelse(bp);
  }

  if(off > ip->size)
    ip->size = off;

  // write the i-node back to disk even if the size didn't change
  // because the loop above might have called bmap() and added a new
  // block to ip->addrs[].
  iupdate(ip);

  return tot;
}

int
readi(struct inode *ip, int user_dst, uint64 dst, uint off, uint n)
{
  uint tot, m;
  struct buf *bp;

  if(off > ip->size || off + n < off)
    return 0;
  if(off + n > ip->size)
    n = ip->size - off;

  for(tot=0; tot<n; tot+=m, off+=m, dst+=m){
    bp = bread(ip->dev, bmap(ip, off/BSIZE));
    m = min(n - tot, BSIZE - off%BSIZE);
    if(either_copyout(user_dst, dst, bp->data + (off % BSIZE), m) == -1) {
      brelse(bp);
      tot = -1;
      break;
    }
    brelse(bp);
  }
  return tot;
}

struct dirent {
  ushort inum;
  char name[DIRSIZ];
};

// Look for a directory entry in a directory.
// If found, set *poff to byte offset of entry.
struct inode*
dirlookup(struct inode *dp, char *name, uint *poff)
{
  uint off, inum;
  struct dirent de;

  if(dp->type != T_DIR)
    panic("dirlookup not DIR");

  for(off = 0; off < dp->size; off += sizeof(de)){
    if(readi(dp, 0, (uint64)&de, off, sizeof(de)) != sizeof(de))
      panic("dirlookup read");
    if(de.inum == 0)
      continue;
    if(namecmp(name, de.name) == 0){
      // entry matches path element
      if(poff)
        *poff = off;
      inum = de.inum;
      return iget(dp->dev, inum);
    }
  }

  return 0;
}

// Look up and return the inode for a path name.
// If parent != 0, return the inode for the parent and copy the final
// path element into name, which must have room for DIRSIZ bytes.
// Must be called inside a transaction since it calls iput().
static struct inode*
namex(char *path, int nameiparent, char *name)
{
  struct inode *ip, *next;

  if(*path == '/')
    ip = iget(ROOTDEV, ROOTINO);
  else
    ip = idup(myproc()->cwd);

  while((path = skipelem(path, name)) != 0){
    ilock(ip);
    if(ip->type != T_DIR){
      iunlockput(ip);
      return 0;
    }
    if(nameiparent && *path == '\0'){
      // Stop one level early.
      iunlock(ip);
      return ip;
    }
    if((next = dirlookup(ip, name, 0)) == 0){
      iunlockput(ip);
      return 0;
    }
    iunlockput(ip);
    ip = next;
  }
  if(nameiparent){
    iput(ip);
    return 0;
  }
  return ip;
}
// Paths

// Copy the next path element from path into name.
// Return a pointer to the element following the copied one.
// The returned path has no leading slashes,
// so the caller can check *path=='\0' to see if the name is the last one.
// If no name to remove, return 0.
//
// Examples:
//   skipelem("a/bb/c", name) = "bb/c", setting name = "a"
//   skipelem("///a//bb", name) = "bb", setting name = "a"
//   skipelem("a", name) = "", setting name = "a"
//   skipelem("", name) = skipelem("////", name) = 0
//
static char*
skipelem(char *path, char *name)
{
  char *s;
  int len;
  // 过滤路径字符串开头所有的'/'
  while(*path == '/')
    path++;
  if(*path == 0)
    return 0;
  s = path;
  while(*path != '/' && *path != 0)
    path++;
  len = path - s;
  if(len >= DIRSIZ)
    memmove(name, s, DIRSIZ);
  else {
    memmove(name, s, len);
    name[len] = 0;
  }
  while(*path == '/')
    path++;
  return path;
}

// Write a new directory entry (name, inum) into the directory dp.
int
dirlink(struct inode *dp, char *name, uint inum)
{
  int off;
  struct dirent de;
  struct inode *ip;

  // Check that name is not present.
  if((ip = dirlookup(dp, name, 0)) != 0){
    iput(ip);
    return -1;
  }

  // Look for an empty dirent.
  for(off = 0; off < dp->size; off += sizeof(de)){
    if(readi(dp, 0, (uint64)&de, off, sizeof(de)) != sizeof(de))
      panic("dirlink read");
    if(de.inum == 0)
      break;
  }

  strncpy(de.name, name, DIRSIZ);
  de.inum = inum;
  if(writei(dp, 0, (uint64)&de, off, sizeof(de)) != sizeof(de))
    panic("dirlink");

  return 0;
}

struct file {
  enum { FD_NONE, FD_PIPE, FD_INODE, FD_DEVICE } type;
  int ref; // reference count
  char readable;
  char writable;
  struct pipe *pipe; // FD_PIPE
  struct inode *ip;  // FD_INODE and FD_DEVICE
  uint off;          // FD_INODE
  short major;       // FD_DEVICE
};

struct {
  struct spinlock lock;
  struct file file[NFILE];
} ftable;

// Allocate a file structure.
struct file*
filealloc(void)
{
  struct file *f;

  acquire(&ftable.lock);
  for(f = ftable.file; f < ftable.file + NFILE; f++){
    if(f->ref == 0){
      f->ref = 1;
      release(&ftable.lock);
      return f;
    }
  }
  release(&ftable.lock);
  return 0;
}

// Increment ref count for file f.
struct file*
filedup(struct file *f)
{
  acquire(&ftable.lock);
  if(f->ref < 1)
    panic("filedup");
  f->ref++;
  release(&ftable.lock);
  return f;
}

// Close file f.  (Decrement ref count, close when reaches 0.)
void
fileclose(struct file *f)
{
  struct file ff;

  acquire(&ftable.lock);
  if(f->ref < 1)
    panic("fileclose");
  if(--f->ref > 0){
    release(&ftable.lock);
    return;
  }
  ff = *f;
  f->ref = 0;
  f->type = FD_NONE;
  release(&ftable.lock);

  if(ff.type == FD_PIPE){
    pipeclose(ff.pipe, ff.writable);
  } else if(ff.type == FD_INODE || ff.type == FD_DEVICE){
    begin_op();
    iput(ff.ip);
    end_op();
  }
}

// Get metadata about file f.
// addr is a user virtual address, pointing to a struct stat.
int
filestat(struct file *f, uint64 addr)
{
  struct proc *p = myproc();
  struct stat st;
  
  if(f->type == FD_INODE || f->type == FD_DEVICE){
    ilock(f->ip);
    stati(f->ip, &st);
    iunlock(f->ip);
    if(copyout(p->pagetable, addr, (char *)&st, sizeof(st)) < 0)
      return -1;
    return 0;
  }
  return -1;
}

// Read from file f.
// addr is a user virtual address.
int
fileread(struct file *f, uint64 addr, int n)
{
  int r = 0;

  if(f->readable == 0)
    return -1;

  if(f->type == FD_PIPE){
    r = piperead(f->pipe, addr, n);
  } else if(f->type == FD_DEVICE){
    if(f->major < 0 || f->major >= NDEV || !devsw[f->major].read)
      return -1;
    r = devsw[f->major].read(1, addr, n);
  } else if(f->type == FD_INODE){
    ilock(f->ip);
    if((r = readi(f->ip, 1, addr, f->off, n)) > 0)
      f->off += r;
    iunlock(f->ip);
  } else {
    panic("fileread");
  }

  return r;
}

// Write to file f.
// addr is a user virtual address.
int
filewrite(struct file *f, uint64 addr, int n)
{
  int r, ret = 0;

  if(f->writable == 0)
    return -1;

  if(f->type == FD_PIPE){
    ret = pipewrite(f->pipe, addr, n);
  } else if(f->type == FD_DEVICE){
    if(f->major < 0 || f->major >= NDEV || !devsw[f->major].write)
      return -1;
    ret = devsw[f->major].write(1, addr, n);
  } else if(f->type == FD_INODE){
    // write a few blocks at a time to avoid exceeding
    // the maximum log transaction size, including
    // i-node, indirect block, allocation blocks,
    // and 2 blocks of slop for non-aligned writes.
    // this really belongs lower down, since writei()
    // might be writing a device like the console.
    int max = ((MAXOPBLOCKS-1-1-2) / 2) * BSIZE;
    int i = 0;
    while(i < n){
      int n1 = n - i;
      if(n1 > max)
        n1 = max;

      begin_op();
      ilock(f->ip);
      if ((r = writei(f->ip, 1, addr + i, f->off, n1)) > 0)
        f->off += r;
      iunlock(f->ip);
      end_op();

      if(r != n1){
        // error from writei
        break;
      }
      i += r;
    }
    ret = (i == n ? n : -1);
  } else {
    panic("filewrite");
  }

  return ret;
}

// Create the path new as a link to the same inode as old.
uint64
sys_link(void)
{
  char name[DIRSIZ], new[MAXPATH], old[MAXPATH];
  struct inode *dp, *ip;

  if(argstr(0, old, MAXPATH) < 0 || argstr(1, new, MAXPATH) < 0)
    return -1;

  begin_op();
  if((ip = namei(old)) == 0){
    end_op();
    return -1;
  }

  ilock(ip);
  if(ip->type == T_DIR){
    iunlockput(ip);
    end_op();
    return -1;
  }

  ip->nlink++;
  iupdate(ip);
  iunlock(ip);

  if((dp = nameiparent(new, name)) == 0)
    goto bad;
  ilock(dp);
  if(dp->dev != ip->dev || dirlink(dp, name, ip->inum) < 0){
    iunlockput(dp);
    goto bad;
  }
  iunlockput(dp);
  iput(ip);

  end_op();

  return 0;

bad:
  ilock(ip);
  ip->nlink--;
  iupdate(ip);
  iunlockput(ip);
  end_op();
  return -1;
}

// map major device number to device functions.
struct devsw {
  int (*read)(int, uint64, int);
  int (*write)(int, uint64, int);
};

struct devsw devsw[NDEV];	// 其中NDEV = 10，xv6最多支持10种不同的驱动
#define CONSOLE 1	// xv6只实现了Console的读写

void
consoleinit(void)
{
  initlock(&cons.lock, "cons");

  uartinit();

  // connect read and write system calls
  // to consoleread and consolewrite.
  devsw[CONSOLE].read = consoleread;
  devsw[CONSOLE].write = consolewrite;
}

  if(open("console", O_RDWR) < 0){
    mknod("console", CONSOLE, 0);
    open("console", O_RDWR);
  }
  dup(0);  // stdout
  dup(0);  // stderr