Inode Content

So far, we have been talking about how to allocate an inode, how to release an inode, how to get an inode, and locks around inode. In this section, we will look closely at the inode data.

Find data block address in inode

// The content (data) associated with each inode is stored
// in blocks on the disk. The first NDIRECT block numbers
// are listed in ip->addrs[].  The next NINDIRECT blocks are
// listed in block ip->addrs[NDIRECT].

// Return the disk block address of the nth block in inode ip.
// If there is no such block, bmap allocates one.
static uint
bmap(struct inode *ip, uint bn)
{
  uint addr, *a;
  struct buf *bp;

  if(bn < NDIRECT){
    if((addr = ip->addrs[bn]) == 0)
      ip->addrs[bn] = addr = balloc(ip->dev);
    return addr;
  }
  bn -= NDIRECT;

  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");
}

Given the inode, and the block number. Begin from Direct nodes, allocate (use balloc) if not existing. If block number is beyond direct nodes, search in indirect nodes, allocate if not existing. Return the address of the data block. (Aka the block index)

Read and write data for a file

Read

// Read data from inode.
// Caller must hold ip->lock.
// If user_dst==1, then dst is a user virtual address;
// otherwise, dst is a kernel address.
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 -1;
  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);
      break;
    }
    brelse(bp);
  }
  return n;
}

Starts by making sure that the offset and count are not beyond the end of the file. The main loop processes each block of the file, copying data from the buffer into dst.

Cool Stuff

off/BSIZE gets the data block’s index. bmap gets the actual address of that block. bread gets the buffer cache. The real data offset is bp->data + (off % BSIZE).

As you can see, X/Y for which block contains the data, X % Y for which position the data sits after finding the block.

Write

// 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.
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(n > 0){
    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 n;
}

Write is similar to read, except writing can grow the file size, so we might need to update inode's size.

Get stats of a file

stati is just copying inode metadata to user program via the stat system call.