On Sun, Oct 18, 1998 at 01:18:12PM +0200, David S. Miller wrote:
> Date: Sun, 18 Oct 1998 13:11:45 +0200
> From: Andi Kleen <[EMAIL PROTECTED]>
>
> Regarding sock_readers - TCP bh should always lock_sock before
> doing anything with a socket, with the only exception of one
> dubious case in tcp_v[46]_err(). Do you know of more?
>
> Not entirely true. Main tcp receive path only checks to make sure
> readers is zero, then it moves on. This is why lock_sock() performs a
> synchronize_bh() as part of it's implementation, on SMP this matters.
Then it moves on and calls lock_sock: see tcp_v4_do_rcv and tcp_v6_do_rcv.
-Andi
-
To unsubscribe from this list: send the line "unsubscribe linux-net" in
the body of a message to [EMAIL PROTECTED]
