linux-kernel - Re: [PATCH v1 2/3] locking/pvqspinlock, hv: Enable PV qspinlock for Hyper-V

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Fri, 14 Sep 2018 12:42:33 +0200 (CEST)
From:   Thomas Gleixner <tglx@...utronix.de>
To:     Yi Sun <yi.y.sun@...ux.intel.com>
cc:     linux-kernel@...r.kernel.org, x86@...nel.org,
        chao.p.peng@...el.com, chao.gao@...el.com,
        isaku.yamahata@...el.com, michael.h.kelly@...rosoft.com,
        tianyu.lan@...rosoft.com, "K. Y. Srinivasan" <kys@...rosoft.com>,
        Haiyang Zhang <haiyangz@...rosoft.com>,
        Stephen Hemminger <sthemmin@...rosoft.com>
Subject: Re: [PATCH v1 2/3] locking/pvqspinlock, hv: Enable PV qspinlock for
 Hyper-V

On Fri, 14 Sep 2018, Yi Sun wrote:
> > > +static void hv_notify_long_spin_wait(void)
> > > +{
> > > +	u64 input = spin_wait_info | 0x00000000ffffffff;
> > 
> > What? The result is always 0x00000000ffffffff .....
> > 
> Oh, sorry for such error.
> 
> > > +	spin_wait_info++;
> > > +	hv_do_fast_hypercall8(HVCALL_NOTIFY_LONG_SPIN_WAIT, input);
> > > +}
> > > +
> > > +static void hv_qlock_kick(int cpu)
> > > +{
> > > +	spin_wait_info--;
> > 
> > Looking at the above this is completely pointless and I have no idea what
> > that variable is supposed to do.
> > 
> Per Microsoft Hypervisor Top Level Functional Specification, the input
> parameter of HVCALL_NOTIFY_LONG_SPIN_WAIT is defined as below:
> 
> SpinwaitInfo – Specifies the accumulated count the guest was spinning.
> 
> So, it is increased when guest is spinning and reduced when spinlock is
> released.

But that's a global variable, so it might be incremented and decremented by
several CPUs at once. I don't have the spec and have no time to study it
either, but global does not make any sense to me. The spin wait info comes
from a single guest CPU and the wakeup is targeted at that guest CPU as
well. So why global? It might be defined that way, but then you really want
to explain it proper.

Thanks,

	tglx