linux-kernel - softirq.c: tasklet

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <20061006205435.GA19190@rhlx01.fht-esslingen.de>
Date:	Fri, 6 Oct 2006 22:54:35 +0200
From:	Andreas Mohr <andi@...x01.fht-esslingen.de>
To:	linux-kernel@...r.kernel.org
Subject: softirq.c: tasklet_action() question

Hello all,

ok, possibly stupid question, but what the heck is THAT?:

static void tasklet_action(struct softirq_action *a)
{
        struct tasklet_struct *list;

        local_irq_disable();
        list = __get_cpu_var(tasklet_vec).list;
        __get_cpu_var(tasklet_vec).list = NULL;
        local_irq_enable();

	while (list) {

(same in tasklet_hi_action())

My gut reaction to this would be something similar to:

static void tasklet_action(struct softirq_action *a)
{
        struct tasklet_struct *list = NULL;

	super_cool_n_fast_atomic_xchg(&__get_cpu_var(tasklet_vec).list, &list);

	while (list) {

I'm sure it's obviously not quite as simple as that (maybe requires
atomic xchg extension of the cpu var API?), but would something like that be
possible (at least optionally or for non-SMP?) to avoid the IRQ masking
latency penalty, especially on x86?
(still hacking on a measly P3/700, and am bloody determined to keep it
that way for a looong time ;)

I'm sure that I'm missing something, so what is it? ;)

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