From:   Florian Weimer <fweimer@redhat.com>
To:     "Paul E. McKenney via Libc-alpha" <libc-alpha@sourceware.org>
Cc:     paulmck@kernel.org, Peter Zijlstra <peterz@infradead.org>,
        Boqun Feng <boqun.feng@gmail.com>,
        Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
        linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 2/5] nptl: Add rseq registration
References: <cover.1638798186.git.fweimer@redhat.com>
        <9c58724d604e160ebda5f667331fa41416c0d12b.1638798186.git.fweimer@redhat.com>
        <1780152866.15126.1638809966443.JavaMail.zimbra@efficios.com>
        <871r2podt9.fsf@oldenburg.str.redhat.com>
        <1614144911.15213.1638816753026.JavaMail.zimbra@efficios.com>
        <87ilw1mu81.fsf@oldenburg.str.redhat.com>
        <20211206201122.GE641268@paulmck-ThinkPad-P17-Gen-1>
Date:   Mon, 06 Dec 2021 21:26:51 +0100
In-Reply-To: <20211206201122.GE641268@paulmck-ThinkPad-P17-Gen-1> (Paul
        E. McKenney via Libc-alpha's message of "Mon, 6 Dec 2021 12:11:22
        -0800")
Message-ID: <87k0ghlbsk.fsf@oldenburg.str.redhat.com>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/27.2 (gnu/linux)
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

* Paul E. McKenney via Libc-alpha:

>> The C memory model is broken and does not prevent out-of-thin-air
>> values.  As far as I know, this breaks single-copy atomicity.  In
>> practice, compilers will not exercise the latitude offered by the memory
>> model.  volatile does not ensure absence of data races.
>
> Within the confines of the standard, agreed, use of the volatile keyword
> does not explicitly prevent data races.
>
> However, volatile accesses are (informally) defined to suffice for
> device-driver memory accesses that communicate with devices, whether via
> MMIO or DMA-style shared memory.  The device-driver firmware is often
> written in C or C++.  So doesn't this informal device-driver guarantee
> need to also do what is needed for userspace code that is communicating
> with kernel code?  If not, why not?

The informal guarantee is probably good enough here, too.  However, the
actual accesses are behind macros, and those macros use either
non-volatile plain reads or inline assembler (which use
single-instruction naturally aligned reads).

THanks,
Florian