All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: David Vrabel <david.vrabel@citrix.com>, <konrad@kernel.org>,
	<boris.ostrovsky@oracle.com>, <linux-kernel@vger.kernel.org>,
	<xen-devel@lists.xenproject.org>
Subject: Re: [Xen-devel] [PATCH v3 1/7] xen-pciback: Document the various parameters and attributes in SysFS
Date: Wed, 9 Jul 2014 15:22:30 +0100	[thread overview]
Message-ID: <53BD5026.2030908@citrix.com> (raw)
In-Reply-To: <20140709141354.GG21837@laptop.dumpdata.com>

On 09/07/14 15:13, Konrad Rzeszutek Wilk wrote:
> On Wed, Jul 09, 2014 at 03:05:56PM +0100, Andrew Cooper wrote:
>> On 09/07/14 14:59, Konrad Rzeszutek Wilk wrote:
>>>>> +What:           /sys/bus/pci/drivers/pciback/irq_handler_state
>>>>> +Date:           Oct 2011
>>>>> +KernelVersion:  3.1
>>>>> +Contact:        xen-devel@lists.xenproject.org
>>>>> +Description:
>>>>> +                An option to toggle Xen PCI back to acknowledge (or stop)
>>>>> +                interrupts for the specific device regardless of whether the
>>>>> +                device is shared, enabled, or on a level interrupt line.
>>>>> +                Writing a string of DDDD:BB:DD.F will toggle the state.
>>>>> +                This is Domain:Bus:Device.Function where domain is optional.
>>>> I do not understand under what circumstances this should be used in.
>>> So that dom0 does not disable the IRQ line as it would be getting the IRQs
>>> for the guest as well (because the IRQ line is level and another guest
>>> uses an PCI device that is using the same line).
>> Why is this relevant?  Xen (and Xen alone) actually controls this aspect
>> of interrupts.  Xen manages passing line level interrupts to any domain
>> which might have a device hanging off a particular line, and has to wait
>> until all domains have EOI'd the line until it can clear the interrupt
>> at the IO-APIC.
> Because Linux will think there is an IRQ storm as the event->IRQ points
> to the default one. And then it will mask the event, which means dom0
> will mask the PIRQ, and Xen will then also mask the IRQ.

Xen will (and by this I mean 'should', and this was the behaviour last
time I delved in there) only mask the IRQ if dom0 is the only consumer
of these interrupts.

For any PCIPassthrough, dom0 will get line interrupts for passed-through
devices, but in this case pci-back should always handle the line
interrupts so Linux doesn't block them as an IRQ storm.

~Andrew

  reply	other threads:[~2014-07-09 14:23 UTC|newest]

Thread overview: 65+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-08 18:58 [PATCH] Xen PCIbackend support for slot and bus reset (v3) konrad
2014-07-08 18:58 ` [PATCH v3 1/7] xen-pciback: Document the various parameters and attributes in SysFS konrad
2014-07-08 18:18   ` [Xen-devel] " Andrew Cooper
2014-07-08 18:18   ` Andrew Cooper
2014-07-09 12:17   ` David Vrabel
2014-07-09 12:17   ` [Xen-devel] " David Vrabel
2014-07-09 13:59     ` Konrad Rzeszutek Wilk
2014-07-09 13:59     ` [Xen-devel] " Konrad Rzeszutek Wilk
2014-07-09 14:05       ` Andrew Cooper
2014-07-09 14:13         ` Konrad Rzeszutek Wilk
2014-07-09 14:13         ` [Xen-devel] " Konrad Rzeszutek Wilk
2014-07-09 14:22           ` Andrew Cooper [this message]
2014-07-09 14:25             ` Konrad Rzeszutek Wilk
2014-07-09 14:25             ` [Xen-devel] " Konrad Rzeszutek Wilk
2014-07-09 14:45               ` David Vrabel
2014-07-09 14:47                 ` Konrad Rzeszutek Wilk
2014-07-09 14:47                 ` [Xen-devel] " Konrad Rzeszutek Wilk
2014-07-09 14:57                   ` David Vrabel
2014-07-09 14:57                   ` [Xen-devel] " David Vrabel
2014-07-09 15:11                     ` Konrad Rzeszutek Wilk
2014-07-09 15:11                     ` Konrad Rzeszutek Wilk
2014-07-09 14:45               ` David Vrabel
2014-07-09 14:22           ` Andrew Cooper
2014-07-09 14:05       ` Andrew Cooper
2014-07-08 18:58 ` konrad
2014-07-08 18:58 ` [PATCH v3 2/7] xen/pciback: Don't deadlock when unbinding konrad
2014-07-08 18:58 ` konrad
2014-07-09 12:21   ` David Vrabel
2014-07-09 14:01     ` Konrad Rzeszutek Wilk
2014-07-09 14:01     ` Konrad Rzeszutek Wilk
2014-07-09 12:21   ` David Vrabel
2014-07-08 18:58 ` [PATCH v3 3/7] xen/pciback: Move the FLR code to a function konrad
2014-07-08 18:58   ` konrad
2014-07-08 18:58 ` [PATCH v3 4/7] xen/pciback: Implement PCI reset slot or bus with 'do_flr' SysFS attribute konrad
2014-07-08 18:58   ` konrad
2014-07-08 18:02   ` David Vrabel
2014-07-08 18:02   ` David Vrabel
2014-07-08 18:46     ` Konrad Rzeszutek Wilk
2014-07-08 18:46     ` Konrad Rzeszutek Wilk
2014-07-08 19:28       ` Konrad Rzeszutek Wilk
2014-07-08 19:28       ` Konrad Rzeszutek Wilk
2014-07-09 12:32       ` David Vrabel
2014-07-09 14:11         ` [Xen-devel] " David Vrabel
2014-07-09 14:11         ` David Vrabel
2014-07-09 14:12         ` Konrad Rzeszutek Wilk
2014-07-09 14:26           ` David Vrabel
2014-07-09 15:07             ` Konrad Rzeszutek Wilk
2014-07-09 15:07               ` Konrad Rzeszutek Wilk
2014-07-09 14:26           ` David Vrabel
2014-07-09 14:12         ` Konrad Rzeszutek Wilk
2014-07-09 12:32       ` David Vrabel
2014-07-08 18:17   ` Andrew Cooper
2014-07-08 18:17   ` [Xen-devel] " Andrew Cooper
2014-07-08 18:58 ` [PATCH v3 5/7] xen/pciback: Include the domain id if removing the device whilst still in use konrad
2014-07-08 18:58 ` konrad
2014-07-09 12:34   ` David Vrabel
2014-07-09 12:34   ` David Vrabel
2014-07-08 18:58 ` [PATCH v3 6/7] xen/pciback: Print out the domain owning the device konrad
2014-07-08 18:58 ` konrad
2014-07-09 13:04   ` David Vrabel
2014-07-09 13:04   ` David Vrabel
2014-07-08 18:58 ` [PATCH v3 7/7] xen/pciback: Remove tons of dereferences konrad
2014-07-08 18:58 ` konrad
2014-07-08 19:15 ` [Xen-devel] [PATCH] Xen PCIbackend support for slot and bus reset (v3) Sander Eikelenboom
2014-07-08 19:15 ` Sander Eikelenboom

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=53BD5026.2030908@citrix.com \
    --to=andrew.cooper3@citrix.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=david.vrabel@citrix.com \
    --cc=konrad.wilk@oracle.com \
    --cc=konrad@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.