Re: [Lse-tech] Re: RFC: patch to allow lock-free traversal of lists with insertion

From: Rusty Russell (
Date: Fri Oct 12 2001 - 00:06:06 EST

On Wed, 10 Oct 2001 17:25:22 +0000 (UTC) (Linus Torvalds) wrote:

> Absolutely. It's not that expensive an operation on sane hardware. And
> it's definitely conceptually the only right thing to do - we're saying
> that we're doing a read that depends on a previous read having seen
> previous memory. Ergo, "rmb()".

Accessing pointer contents after you dereference the pointer is "obvious":
we've been trying to get Richard to understand the problem for FIVE MONTHS,
and he's not stupid!

The PPC manual (thanks Paul M) clearly indicates rmbdd() is not neccessary.
That they mention it explicitly suggests it's going to happen on more
architectures: you are correct, we should sprinkle rmbdd() everywhere
(rmb() is heavy on current PPC) and I'll update the Kernel Locking Guide now
the rules have changed.[1]

[1] Aren't we lucky our documentation is so sparse noone can accuse us of being
    inconsistent? 8)
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at
Please read the FAQ at

This archive was generated by hypermail 2b29 : Mon Oct 15 2001 - 21:00:43 EST