Network Block Device (TCP version)
                                       
   Note: Network Block Device is now experimental, which approximately
   means, that it works on my computer, and it worked on one of school
   computers.
   
   What is it: With this think compiled in kernel, linux can use remote
   server as one of its block devices. So every time client computer
   wants to read /dev/nd0, it will send request over TCP to server, which
   will reply with data readed. This can be used for stations with
   low-disk space (or even disklesses - if you boot from floppy) to
   borrow disk space from other computer. Unlike NFS, it is possible to
   put any filesystem on it etc. It is impossible to use NBD as root
   filesystem, since it requires user-level program to start. It also
   allows you to run block-device in user land (making server and client
   physicaly same computer, communicating using loopback).
   
   Current state: It currently works. Network block device looks like
   being pretty stable. I originaly thought that it is impossible to swap
   over TCP. It turned out not to be true - swapping over TCP now works
   and seems to be deadlock-free, but it requires heavy patches into
   Linux's network layer.
   
   Devices: Network block device uses major 43, minors 0..n (where n is
   configurable in nbd.h). Create these files by mknod when needed. After
   that, your ls -l /dev/ should look like:

brw-rw-rw-   1 root     root      43,   0 Apr 11 00:28 nd0
brw-rw-rw-   1 root     root      43,   1 Apr 11 00:28 nd1
...

   Protocol: Userland program passes file handle with connected TCP
   socket to actuall kernel driver. This way, kernel does not have to
   care about connecting etc. Protocol is rather simple: If driver is
   asked to read from block device, it sends packet of following form
   "request" (all data are in network byte order):
   
  __u32 magic;        must be equal to 0x12560953
  __u32 from;         position in bytes to read from / write at
  __u32 len;          number of bytes to be read / written
  __u64 handle;       handle of operation
  __u32 type;         0 = read
                      1 = write
  ...                 in case of write operation, this is
                      immediately followed len bytes of data

   When operation is completed, server responds with packet of following
   structure "reply":
   
  __u32 magic;        must be equal to
  __u64 handle;       handle copyied from request
  __u32 error;        0 = operation completed successfully,
                      else error code
  ...                 in case of read operation with no error,
                      this is immediately followed len bytes of data

   For more information, look at http://atrey.karlin.mff.cuni.cz/~pavel.