From: David Wragg <dpw@doc.ic.ac.uk>
Date: 04 Nov 2000 22:16:18 +0000
Since f_pos of struct file is a loff_t, on 32-bit architectures it
needs a lock to make accesses atomic (or some more sophisticated form
of protection). But looking in 2.4.0-test10, there doesn't seem to be
any such lock.
The llseek op is called with the Big Kernel Lock, but unlike in 2.2,
the read and write ops are called without any locks held, and so
generic_file_{read|write} make unprotected accesses to f_pos (through
their ppos argument).
This looks like it's a bug to me.... although if you have multiple
threads hitting a file descriptor at the same time, you're pretty much
asking for trouble.
- Ted
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Wed Nov 15 2000 - 21:00:21 EST