Re: [patch] 'sticky pages' support in the VM, futex-2.5.38-C5

• Next message: Larry McVoy: "[offtopic] Linux Weekly News"
• Previous message: Rik van Riel: "Re: [PATCH][2.5] Single linked lists for Linux,v2"
• In reply to: Ingo Molnar: "[patch] 'sticky pages' support in the VM, futex-2.5.38-C5"
• Next in thread: Ingo Molnar: "Re: [patch] 'sticky pages' support in the VM, futex-2.5.38-C5"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

In article <Pine.LNX.4.44.0209261311070.11487-100000@localhost.localdomain>,
Ingo Molnar <mingo@elte.hu> wrote:
>
>while running fork() testcases with NPTL we found a number of futex
>related failures that i tracked down to the following conceptual bug in
>the futex code:

This patch seems trivially broken by having two futexes on the same
page. When the first futex removes itself, it will clear the sticky
bit, even though the other futex is still pinning the same page.

Trust me, you'll have to use the page list approach.

                Linus
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

• Next message: Larry McVoy: "[offtopic] Linux Weekly News"
• Previous message: Rik van Riel: "Re: [PATCH][2.5] Single linked lists for Linux,v2"
• In reply to: Ingo Molnar: "[patch] 'sticky pages' support in the VM, futex-2.5.38-C5"
• Next in thread: Ingo Molnar: "Re: [patch] 'sticky pages' support in the VM, futex-2.5.38-C5"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Mon Sep 30 2002 - 22:00:27 EST