linux-kernel - Re: Opinion on ordering of writel vs. stores to RAM

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

Message-Id: <20060909.023803.104047454.davem@davemloft.net>
Date:	Sat, 09 Sep 2006 02:38:03 -0700 (PDT)
From:	David Miller <davem@...emloft.net>
To:	benh@...nel.crashing.org
Cc:	torvalds@...l.org, paulus@...ba.org, linux-kernel@...r.kernel.org,
	akpm@...l.org, segher@...nel.crashing.org
Subject: Re: Opinion on ordering of writel vs. stores to RAM

From: Benjamin Herrenschmidt <benh@...nel.crashing.org>
Date: Sat, 09 Sep 2006 17:23:20 +1000

> I quite like mem_to_io_* (barrier/rb/wb) and io_to_mem_* in fact :) That
> is probably more talkative to device driver writers and would allow more
> fine grained barriers.

I firmly believe that the average driver person is not going
to be able to get these things right, even if you document it
in big bold letters in some Documentation/*.txt file.

This is like the Alpha OSF outb() interface for kernel drivers
that had something like 8 arguments.

And even if you define these things, and people start using it,
only PowerPC and a few other systems (I guess IA64) will ever
notice when this stuff is done wrong.  That's really not a good
plan from a testing coverage point of view.
-
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/