NetBSD-Bugs archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: kern/57199 (Pure PVH i386 guests hang on disk activity)



The following reply was made to PR kern/57199; it has been noted by GNATS.

From: Manuel Bouyer <bouyer%antioche.eu.org@localhost>
To: Taylor R Campbell <riastradh%NetBSD.org@localhost>
Cc: gnats-bugs%netbsd.org@localhost, kern-bug-people%netbsd.org@localhost, netbsd-bugs%netbsd.org@localhost,
        gnats-admin%netbsd.org@localhost, brad%anduin.eldar.org@localhost
Subject: Re: kern/57199 (Pure PVH i386 guests hang on disk activity)
Date: Wed, 17 Jul 2024 08:49:40 +0200

 On Tue, Jul 16, 2024 at 11:33:39PM +0000, Taylor R Campbell wrote:
 > > Date: Wed, 17 Jul 2024 01:15:12 +0200
 > > From: Manuel Bouyer <bouyer%antioche.eu.org@localhost>
 > > 
 > > On Tue, Jul 16, 2024 at 10:49:32PM +0000, riastradh%NetBSD.org@localhost wrote:
 > > > fixed in HEAD, needs pullup-10 and pullup-9
 > > 
 > > AFAIK it's not needed in netbsd-9, PVH is not supported before -10
 > 
 > Don't XEN3_DOM0 and XEN3_DOMU kernels have, e.g., xennet(4)?  If they
 > rely on xen_mb to enforce store-before-load ordering with respect to
 > the hypervisor (possibly on another physical CPU), they may need this
 > fix.
 > 
 > That said, by accident, it looks like this will only be relevant for
 > very old 32-bit x86 CPUs -- those without SSE2.  On CPUs with SSE2,
 > netbsd-9 hotpatches membar_sync to use MFENCE.  And all amd64 CPUs
 > have SSE2.
 
 AFAIK hotpatch is disabled for XEN PV kernels.
 
 -- 
 Manuel Bouyer <bouyer%antioche.eu.org@localhost>
      NetBSD: 26 ans d'experience feront toujours la difference
 --
 


Home | Main Index | Thread Index | Old Index