This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
Home Products Support Community News


[Xen-devel] Re: Question about x86/mm/gup.c's use of disabled interrupts

To: Avi Kivity <avi@xxxxxxxxxx>
Subject: [Xen-devel] Re: Question about x86/mm/gup.c's use of disabled interrupts
From: Jeremy Fitzhardinge <jeremy@xxxxxxxx>
Date: Wed, 18 Mar 2009 15:55:20 -0700
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>, Xen-devel <xen-devel@xxxxxxxxxxxxxxxxxxx>, Linux Kernel Mailing List <linux-kernel@xxxxxxxxxxxxxxx>, Linux Memory Management List <linux-mm@xxxxxxxxx>, Ingo Molnar <mingo@xxxxxxx>
Delivery-date: Wed, 18 Mar 2009 15:55:55 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to: <49C17880.7080109@xxxxxxxxxx>
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
References: <49C148AF.5050601@xxxxxxxx> <49C16411.2040705@xxxxxxxxxx> <49C1665A.4080707@xxxxxxxx> <49C16A48.4090303@xxxxxxxxxx> <49C17230.20109@xxxxxxxx> <49C17880.7080109@xxxxxxxxxx>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
User-agent: Thunderbird (X11/20090105)
Avi Kivity wrote:
Hm, awkward if flush_tlb_others doesn't IPI...

How can it avoid flushing the tlb on cpu [01]? It's it's gup_fast()ing a pte, it may as well load it into the tlb.

xen_flush_tlb_others uses a hypercall rather than an IPI, so none of the logic which depends on there being an IPI will work.

Simplest fix is to make gup_get_pte() a pvop, but that does seem like putting a red flag in front of an inner-loop hotspot, or something...

The per-cpu tlb-flush exclusion flag might really be the way to go.

I don't see how it will work, without changing Xen to look at the flag?

local_irq_disable() is used here to lock out a remote cpu, I don't see why deferring the flush helps.

Well, no, not deferring. Making xen_flush_tlb_others() spin waiting for "doing_gup" to clear on the target cpu. Or add an explicit notion of a "pte update barrier" rather than implicitly relying on the tlb IPI (which is extremely convenient when available...).


Xen-devel mailing list

<Prev in Thread] Current Thread [Next in Thread>