This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: BZ 20822 :powerpc: race condition in __lll_unlock_elision
- From: Torvald Riegel <triegel at redhat dot com>
- To: Florian Weimer <fweimer at redhat dot com>
- Cc: munroesj at linux dot vnet dot ibm dot com, Rajalakshmi Srinivasaraghavan <raji at linux dot vnet dot ibm dot com>, libc-alpha at sourceware dot org, aaron Sawdey <acsawdey at linux dot vnet dot ibm dot com>, Ulrich Weigand <Ulrich dot Weigand at de dot ibm dot com>, Steve Munroe <sjmunroe at us dot ibm dot co>, carlos at redhat dot com, adhemerval dot zanella at linaro dot org, adconrad at ubuntu dot com, wschmidt at linux dot vnet dot ibm dot com
- Date: Tue, 22 Nov 2016 17:58:08 +0100
- Subject: Re: BZ 20822 :powerpc: race condition in __lll_unlock_elision
- Authentication-results: sourceware.org; auth=none
- References: <f777eebe-4a7b-87d2-1281-ab605c7fce8b@linux.vnet.ibm.com> <1479394010.7146.1154.camel@localhost.localdomain> <1479771736.9880.42.camel@oc7878010663> <1479804279.7146.1280.camel@localhost.localdomain> <a5e57060-b0e0-3156-5fdd-da24a4447a5d@redhat.com> <1479807670.7146.1295.camel@localhost.localdomain> <e649d9d8-1711-fa6b-b075-7dfdaf0c18d4@redhat.com> <1479822346.7146.1313.camel@localhost.localdomain> <19d846f3-3362-f4a4-6c22-466dbdbf1d60@redhat.com>
On Tue, 2016-11-22 at 16:02 +0100, Florian Weimer wrote:
> On 11/22/2016 02:45 PM, Torvald Riegel wrote:
>
> > Lock elision relies on this kind of mixed access. While it would be
> > nice to have a common formal model for the various HTMs out there from
> > the perspective of a C11/C++11 memory model setting, I don't think it's
> > a big problem right now that we don't (AFAIK) have such a formal model.
> > Lock elision should be well understood, so I'm not worried about any
> > surprises regarding this use case.
>
> You are the expert. I'm just surprised we embrace a wild-west approach
> to P&C again, while trying to convince others to argue from the
> definitions instead based on gut feeling.
To avoid misunderstandings: I'm not arguing in favor of embracing any
wild-west approach. It would be great if we had a formal model that can
cover more than one architecture's semantics. Nonetheless, we don't
have it, and I don't see this as a big enough problem to prevent us from
trying to use lock elision. Once someone comes up with a model, I
suppose we'd certainly try to use it if possible.