RE: Add memory barrier when waiting on futex

[Ma, Xindong]

> -----Original Message-----
> From: Peter Zijlstra [mailto:peterz@xxxxxxxxxxxxx]
> Sent: Tuesday, November 26, 2013 4:26 PM
> To: Ma, Xindong
> Cc: stable@xxxxxxxxxxxxxxx; stable-commits@xxxxxxxxxxxxxxx; Wysocki, Rafael
> J; ccross@xxxxxxxxxx; tglx@xxxxxxxxxxxxx; dvhart@xxxxxxxxxxxxxxx;
> mingo@xxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx; gregkh@xxxxxxxxxxxxxxxxxxx;
> Tu, Xiaobing
> Subject: Re: Add memory barrier when waiting on futex
> 
> On Tue, Nov 26, 2013 at 01:07:25AM +0000, Ma, Xindong wrote:
> > I've already aware that they've protected by spinlock, this is why I adding a
> memory barrier to fix it.
> 
> That doesn't make sense.. the spinlocks should provide the required
> serialization, there's nothing to fix.
> 
> > I reproduced this issue several times on android which running on IA dual
> core.
> 
> I think you need to be more specific, in particular, if spinlocks do not provide
> serialization on your IA32 device, I'd call that thing broken.
> Adding random memory barriers is _WRONG_.
> 
I agree with you. Thanks, Peter.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/