Re: [PATCH 0/7] xen/events: bug fixes and some diagnostic aids

From: Julien Grall <julien@xen.org>
To: "Jürgen Groß" <jgross@suse.com>,
	xen-devel@lists.xenproject.org, linux-kernel@vger.kernel.org,
	linux-block@vger.kernel.org, netdev@vger.kernel.org,
	linux-scsi@vger.kernel.org
Cc: "Boris Ostrovsky" <boris.ostrovsky@oracle.com>,
	"Stefano Stabellini" <sstabellini@kernel.org>,
	stable@vger.kernel.org,
	"Konrad Rzeszutek Wilk" <konrad.wilk@oracle.com>,
	"Roger Pau Monné" <roger.pau@citrix.com>,
	"Jens Axboe" <axboe@kernel.dk>, "Wei Liu" <wei.liu@kernel.org>,
	"Paul Durrant" <paul@xen.org>,
	"David S. Miller" <davem@davemloft.net>,
	"Jakub Kicinski" <kuba@kernel.org>
Subject: Re: [PATCH 0/7] xen/events: bug fixes and some diagnostic aids
Date: Mon, 8 Feb 2021 12:16:41 +0000	[thread overview]
Message-ID: <e8c46e36-cf9e-fb30-21b5-fa662834a01a@xen.org> (raw)
In-Reply-To: <1831964f-185e-31bb-2446-778f2c18d71b@suse.com>

On 08/02/2021 12:14, Jürgen Groß wrote:
> On 08.02.21 11:40, Julien Grall wrote:
>> Hi Juergen,
>>
>> On 08/02/2021 10:22, Jürgen Groß wrote:
>>> On 08.02.21 10:54, Julien Grall wrote:
>>>> ... I don't really see how the difference matter here. The idea is 
>>>> to re-use what's already existing rather than trying to re-invent 
>>>> the wheel with an extra lock (or whatever we can come up).
>>>
>>> The difference is that the race is occurring _before_ any IRQ is
>>> involved. So I don't see how modification of IRQ handling would help.
>>
>> Roughly our current IRQ handling flow (handle_eoi_irq()) looks like:
>>
>> if ( irq in progress )
>> {
>>    set IRQS_PENDING
>>    return;
>> }
>>
>> do
>> {
>>    clear IRQS_PENDING
>>    handle_irq()
>> } while (IRQS_PENDING is set)
>>
>> IRQ handling flow like handle_fasteoi_irq() looks like:
>>
>> if ( irq in progress )
>>    return;
>>
>> handle_irq()
>>
>> The latter flow would catch "spurious" interrupt and ignore them. So 
>> it would handle nicely the race when changing the event affinity.
> 
> Sure? Isn't "irq in progress" being reset way before our "lateeoi" is
> issued, thus having the same problem again? 

Sorry I can't parse this.

And I think we want to keep
> the lateeoi behavior in order to be able to control event storms.

I didn't (yet) suggest to remove lateeoi. I only suggest to use a 
different workflow to handle the race with vCPU affinity.

Cheers,

-- 
Julien Grall