From: catalin.marinas@arm•com (Catalin Marinas)
To: linux-arm-kernel@lists•infradead.org
Subject: [PATCH 0/4] ABI updates
Date: Mon, 7 Jul 2014 14:52:59 +0100 [thread overview]
Message-ID: <20140707135259.GB32578@arm.com> (raw)
In-Reply-To: <20140704195134.GJ21766@n2100.arm.linux.org.uk>
On Fri, Jul 04, 2014 at 08:51:34PM +0100, Russell King - ARM Linux wrote:
> As a result of the recent discussions about android, several issues
> have been identified with existing kernels:
>
> 1. HWCAP_SWP does not properly reflect whether the SWP instruction
> should be used. Turn HWCAP_SWP off on ARMv6+ where the exclusives
> are available.
>
> 2. SWP is unsafe when running on a SMP CPU; there is no bus locking
> between the read and write parts of the instruction execution.
> Force SWP emulation on ARMv7+ where we can disable the SWP
> instruction.
>
> 3. Reporting of alignment faults - kernel mode faults are silent due to
> the requirements of the network stack, but we can note where the
> last one occurs.
>
> Testing reveals that at least my OMAP4430 userspace (supplied from TI)
> executes lots of SWP instructions, which is something that wasn't known
> before this patch.
>
> Many systems today are not configured with SWP emulation enabled on SMP.
> This means that the SWP instruction is available, but unsafe.
The patches look fine to me (we are still discussing patch 4 but even if
it needs changing for TLS, it can be done separately from this series).
Question - should we go a step further and change the pr_debug() in
swp_emulate.c to something like pr_warn()?
Another deprecated feature is CP15 barriers (disable bit coming with the
virtualisation extensions). I think we should start emulating these soon
as well and print warnings.
--
Catalin
prev parent reply other threads:[~2014-07-07 13:52 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-04 19:51 [PATCH 0/4] ABI updates Russell King - ARM Linux
2014-07-04 19:52 ` [PATCH 1/4] ARM: alignment: save last kernel aligned fault location Russell King
2014-07-04 19:52 ` [PATCH 2/4] ARM: SWP emulation: always enable when SMP is enabled Russell King
2014-07-04 19:52 ` [PATCH 3/4] ARM: SWP emulation: only initialise on ARMv7 CPUs Russell King
2014-07-04 19:52 ` [PATCH 4/4] ARM: hwcap: disable HWCAP_SWP if the CPU advertises it has exclusives Russell King
2014-07-04 20:11 ` Arnd Bergmann
2014-07-04 20:51 ` Russell King - ARM Linux
2014-07-04 20:58 ` Arnd Bergmann
2014-07-04 21:48 ` Russell King - ARM Linux
2014-07-05 18:46 ` Arnd Bergmann
2014-07-07 11:02 ` Catalin Marinas
2014-07-07 11:17 ` Russell King - ARM Linux
2014-07-07 12:05 ` Catalin Marinas
2014-07-07 13:13 ` Russell King - ARM Linux
2014-07-07 13:46 ` Catalin Marinas
2014-07-07 15:31 ` Russell King - ARM Linux
2014-07-07 15:59 ` Catalin Marinas
2014-07-07 16:31 ` Russell King - ARM Linux
2014-07-07 17:50 ` Catalin Marinas
2014-07-07 9:34 ` Will Deacon
2014-07-07 9:41 ` Russell King - ARM Linux
2014-07-07 9:51 ` Will Deacon
2014-07-04 20:12 ` [PATCH 0/4] ABI updates Arnd Bergmann
2014-07-07 11:19 ` Tony Lindgren
2014-07-07 11:23 ` Russell King - ARM Linux
2014-07-07 13:23 ` Tony Lindgren
2014-07-07 13:52 ` Catalin Marinas [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20140707135259.GB32578@arm.com \
--to=catalin.marinas@arm$(echo .)com \
--cc=linux-arm-kernel@lists$(echo .)infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox