[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20170926144118.GA70381@devbig577.frc2.facebook.com>
Date: Tue, 26 Sep 2017 07:41:18 -0700
From: Tejun Heo <tj@...nel.org>
To: Mark Rutland <mark.rutland@....com>
Cc: linux-kernel@...r.kernel.org, Arnd Bergmann <arnd@...db.de>,
Christoph Lameter <cl@...ux.com>,
Peter Zijlstra <peterz@...radead.org>,
Pranith Kumar <bobby.prani@...il.com>,
Thomas Gleixner <tglx@...utronix.de>,
linux-arch@...r.kernel.org
Subject: Re: [PATCHv2] percpu: make this_cpu_generic_read() atomic w.r.t.
interrupts
On Tue, Sep 26, 2017 at 12:41:52PM +0100, Mark Rutland wrote:
> As raw_cpu_generic_read() is a plain read from a raw_cpu_ptr() address,
> it's possible (albeit unlikely) that the compiler will split the access
> across multiple instructions.
>
> In this_cpu_generic_read() we disable preemption but not interrupts
> before calling raw_cpu_generic_read(). Thus, an interrupt could be taken
> in the middle of the split load instructions. If a this_cpu_write() or
> RMW this_cpu_*() op is made to the same variable in the interrupt
> handling path, this_cpu_read() will return a torn value.
>
> For native word types, we can avoid tearing using READ_ONCE(), but this
> won't work in all cases (e.g. 64-bit types on most 32-bit platforms).
> This patch reworks this_cpu_generic_read() to use READ_ONCE() where
> possible, otherwise falling back to disabling interrupts.
>
> Signed-off-by: Mark Rutland <mark.rutland@....com>
> Cc: Arnd Bergmann <arnd@...db.de>
> Cc: Christoph Lameter <cl@...ux.com>
> Cc: Peter Zijlstra <peterz@...radead.org>
> Cc: Pranith Kumar <bobby.prani@...il.com>
> Cc: Tejun Heo <tj@...nel.org>
> Cc: Thomas Gleixner <tglx@...utronix.de>
> Cc: linux-arch@...r.kernel.org
Applied to percpu/for-4.14-fixes.
Thanks.
--
tejun
Powered by blists - more mailing lists