From: Anshuman Khandual <khandual@linux.vnet.ibm.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: virtualization@lists.linux-foundation.org,
linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
aik@ozlabs.ru, robh@kernel.org, joe@perches.com,
elfring@users.sourceforge.net, david@gibson.dropbear.id.au,
jasowang@redhat.com, benh@kernel.crashing.org,
mpe@ellerman.id.au, hch@infradead.org, linuxram@us.ibm.com,
haren@linux.vnet.ibm.com, paulus@samba.org,
srikar@linux.vnet.ibm.com
Subject: Re: [RFC 2/4] virtio: Override device's DMA OPS with virtio_direct_dma_ops selectively
Date: Mon, 30 Jul 2018 09:45:11 +0530 [thread overview]
Message-ID: <1932ff74-dab8-853d-256c-40045e7ad2d9@linux.vnet.ibm.com> (raw)
In-Reply-To: <20180729001344-mutt-send-email-mst@kernel.org>
On 07/29/2018 02:46 AM, Michael S. Tsirkin wrote:
> On Sat, Jul 28, 2018 at 02:26:24PM +0530, Anshuman Khandual wrote:
>> On 07/20/2018 09:29 AM, Anshuman Khandual wrote:
>>> Now that virtio core always needs all virtio devices to have DMA OPS, we
>>> need to make sure that the structure it points is the right one. In the
>>> absence of VIRTIO_F_IOMMU_PLATFORM flag QEMU expects GPA from guest kernel.
>>> In such case, virtio device must use default virtio_direct_dma_ops DMA OPS
>>> structure which transforms scatter gather buffer addresses as GPA. This
>>> DMA OPS override must happen as early as possible during virtio device
>>> initializatin sequence before virtio core starts using given device's DMA
>>> OPS callbacks for I/O transactions. This change detects device's IOMMU flag
>>> and does the override in case the flag is cleared.
>>>
>>> Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
>>> ---
>>> drivers/virtio/virtio.c | 5 +++++
>>> 1 file changed, 5 insertions(+)
>>>
>>> diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
>>> index 7907ad3..6b13987 100644
>>> --- a/drivers/virtio/virtio.c
>>> +++ b/drivers/virtio/virtio.c
>>> @@ -166,6 +166,8 @@ void virtio_add_status(struct virtio_device *dev, unsigned int status)
>>> }
>>> EXPORT_SYMBOL_GPL(virtio_add_status);
>>>
>>> +const struct dma_map_ops virtio_direct_dma_ops;
>>> +
>>> int virtio_finalize_features(struct virtio_device *dev)
>>> {
>>> int ret = dev->config->finalize_features(dev);
>>> @@ -174,6 +176,9 @@ int virtio_finalize_features(struct virtio_device *dev)
>>> if (ret)
>>> return ret;
>>
>>
>> The previous patch removed the code block for XEN guests which forced
>> the use of DMA API all the time irrespective of VIRTIO_F_IOMMU_PLATFORM
>> flag on the device. Here is what I have removed with patch 2/4 which
>> breaks the existing semantics on XEN guests.
>>
>> -static bool vring_use_dma_api(struct virtio_device *vdev)
>> -{
>> - if (!virtio_has_iommu_quirk(vdev))
>> - return true;
>> -
>> - /* Otherwise, we are left to guess. */
>> - /*
>> - * In theory, it's possible to have a buggy QEMU-supposed
>> - * emulated Q35 IOMMU and Xen enabled at the same time. On
>> - * such a configuration, virtio has never worked and will
>> - * not work without an even larger kludge. Instead, enable
>> - * the DMA API if we're a Xen guest, which at least allows
>> - * all of the sensible Xen configurations to work correctly.
>> - */
>> - if (xen_domain())
>> - return true;
>> -
>> - return false;
>> -}
>>
>> XEN guests would not like override with virtio_direct_dma_ops in any
>> case irrespective of the flag VIRTIO_F_IOMMU_PLATFORM. So the existing
>> semantics can be preserved with something like this. It just assumes
>> that dev->dma_ops is non-NULL and a valid one set by the architecture.
>> If required we can add those tests here before skipping the override.
>>
>> diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
>> index 7907ad3..6b13987 100644
>> --- a/drivers/virtio/virtio.c
>> +++ b/drivers/virtio/virtio.c
>> @@ -166,6 +166,8 @@ void virtio_add_status(struct virtio_device *dev, unsigned int status)
>> }
>> EXPORT_SYMBOL_GPL(virtio_add_status);
>>
>> +const struct dma_map_ops virtio_direct_dma_ops;
>> +
>> int virtio_finalize_features(struct virtio_device *dev)
>> {
>> int ret = dev->config->finalize_features(dev);
>> @@ -174,6 +176,9 @@ int virtio_finalize_features(struct virtio_device *dev)
>> if (ret)
>> return ret;
>> +
>> + if (xen_domain())
>> + goto skip_override;
>> +
>> + if (virtio_has_iommu_quirk(dev))
>> + set_dma_ops(dev->dev.parent, &virtio_direct_dma_ops);
>> +
>> + skip_override:
>> +
>
> I prefer normal if scoping as opposed to goto spaghetti pls.
> Better yet move vring_use_dma_api here and use it.
> Less of a chance something will break.
Sure, will move vring_use_dma_api() function in here.
next prev parent reply other threads:[~2018-07-30 4:15 UTC|newest]
Thread overview: 119+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-20 3:59 [RFC 0/4] Virtio uses DMA API for all devices Anshuman Khandual
2018-07-20 3:59 ` [RFC 1/4] virtio: Define virtio_direct_dma_ops structure Anshuman Khandual
2018-07-30 9:24 ` Christoph Hellwig
2018-07-31 4:01 ` Anshuman Khandual
2018-07-20 3:59 ` [RFC 2/4] virtio: Override device's DMA OPS with virtio_direct_dma_ops selectively Anshuman Khandual
2018-07-28 8:56 ` Anshuman Khandual
2018-07-28 21:16 ` Michael S. Tsirkin
2018-07-30 4:15 ` Anshuman Khandual [this message]
2018-07-30 9:30 ` Christoph Hellwig
2018-07-31 6:39 ` Anshuman Khandual
2018-07-30 9:25 ` Christoph Hellwig
2018-07-31 7:00 ` Anshuman Khandual
2018-07-20 3:59 ` [RFC 3/4] virtio: Force virtio core to use DMA API callbacks for all virtio devices Anshuman Khandual
2018-07-20 3:59 ` [RFC 4/4] virtio: Add platform specific DMA API translation for virito devices Anshuman Khandual
2018-07-20 13:15 ` Michael S. Tsirkin
2018-07-23 2:16 ` Anshuman Khandual
2018-07-25 4:30 ` Anshuman Khandual
2018-07-25 13:31 ` Michael S. Tsirkin
2018-07-20 13:16 ` [RFC 0/4] Virtio uses DMA API for all devices Michael S. Tsirkin
2018-07-23 6:28 ` Anshuman Khandual
2018-07-23 9:08 ` Michael S. Tsirkin
2018-07-25 3:26 ` Anshuman Khandual
2018-07-27 11:31 ` Michael S. Tsirkin
2018-07-28 8:37 ` Anshuman Khandual
2018-07-27 9:58 ` Will Deacon
2018-07-27 10:58 ` Anshuman Khandual
2018-07-30 9:34 ` Christoph Hellwig
2018-07-30 10:28 ` Michael S. Tsirkin
2018-07-30 11:18 ` Christoph Hellwig
2018-07-30 13:26 ` Michael S. Tsirkin
2018-07-31 17:30 ` Christoph Hellwig
2018-07-31 20:36 ` Benjamin Herrenschmidt
2018-08-01 8:16 ` Will Deacon
2018-08-01 8:36 ` Christoph Hellwig
2018-08-01 9:05 ` Will Deacon
2018-08-01 22:41 ` Michael S. Tsirkin
2018-08-01 22:35 ` Michael S. Tsirkin
2018-08-02 15:24 ` Benjamin Herrenschmidt
2018-08-02 15:41 ` Michael S. Tsirkin
2018-08-02 16:01 ` Benjamin Herrenschmidt
2018-08-02 17:19 ` Michael S. Tsirkin
2018-08-02 17:53 ` Benjamin Herrenschmidt
2018-08-02 20:52 ` Michael S. Tsirkin
2018-08-02 21:13 ` Benjamin Herrenschmidt
2018-08-02 21:51 ` Michael S. Tsirkin
2018-08-03 7:05 ` Christoph Hellwig
2018-08-03 15:58 ` Benjamin Herrenschmidt
2018-08-03 16:02 ` Christoph Hellwig
2018-08-03 18:58 ` Benjamin Herrenschmidt
2018-08-04 8:21 ` Christoph Hellwig
2018-08-05 1:10 ` Benjamin Herrenschmidt
2018-08-05 7:29 ` Christoph Hellwig
2018-08-05 21:16 ` Benjamin Herrenschmidt
2018-08-05 21:30 ` Benjamin Herrenschmidt
2018-08-06 9:42 ` Christoph Hellwig
2018-08-06 19:52 ` Benjamin Herrenschmidt
2018-08-07 6:21 ` Christoph Hellwig
2018-08-07 6:42 ` Benjamin Herrenschmidt
2018-08-07 13:55 ` Christoph Hellwig
2018-08-07 20:32 ` Benjamin Herrenschmidt
2018-08-08 6:31 ` Christoph Hellwig
2018-08-08 10:07 ` Benjamin Herrenschmidt
2018-08-08 12:30 ` Christoph Hellwig
2018-08-08 13:18 ` Benjamin Herrenschmidt
2018-08-08 20:31 ` Michael S. Tsirkin
2018-08-08 22:13 ` Benjamin Herrenschmidt
2018-08-09 2:00 ` Benjamin Herrenschmidt
2018-08-09 5:40 ` Christoph Hellwig
2018-09-07 0:09 ` Jiandi An
2018-09-10 6:19 ` Christoph Hellwig
2018-09-10 8:53 ` Gerd Hoffmann
2018-08-03 19:07 ` Michael S. Tsirkin
2018-08-04 1:11 ` Benjamin Herrenschmidt
2018-08-04 1:16 ` Benjamin Herrenschmidt
2018-08-05 0:22 ` Michael S. Tsirkin
2018-08-05 4:52 ` Benjamin Herrenschmidt
2018-08-06 13:46 ` Michael S. Tsirkin
2018-08-06 19:56 ` Benjamin Herrenschmidt
2018-08-06 20:35 ` Michael S. Tsirkin
2018-08-06 21:26 ` Benjamin Herrenschmidt
2018-08-06 21:46 ` Michael S. Tsirkin
2018-08-06 22:13 ` Benjamin Herrenschmidt
2018-08-06 23:16 ` Benjamin Herrenschmidt
2018-08-06 23:45 ` Michael S. Tsirkin
2018-08-07 0:18 ` Benjamin Herrenschmidt
2018-08-07 6:32 ` Christoph Hellwig
2018-08-07 6:27 ` Christoph Hellwig
2018-08-07 6:44 ` Benjamin Herrenschmidt
2018-08-07 6:18 ` Christoph Hellwig
2018-08-07 6:16 ` Christoph Hellwig
2018-08-06 23:18 ` Benjamin Herrenschmidt
2018-08-07 6:12 ` Christoph Hellwig
2018-08-04 1:18 ` Benjamin Herrenschmidt
2018-08-04 1:22 ` Benjamin Herrenschmidt
2018-08-05 0:23 ` Michael S. Tsirkin
2018-08-03 19:17 ` Michael S. Tsirkin
2018-08-04 8:15 ` Christoph Hellwig
2018-08-05 0:09 ` Michael S. Tsirkin
2018-08-05 1:11 ` Benjamin Herrenschmidt
2018-08-05 7:25 ` Christoph Hellwig
2018-08-05 0:53 ` Benjamin Herrenschmidt
2018-08-05 0:27 ` Michael S. Tsirkin
2018-08-06 14:05 ` Will Deacon
2018-08-01 21:56 ` Michael S. Tsirkin
2018-08-02 15:33 ` Benjamin Herrenschmidt
2018-08-02 20:53 ` Michael S. Tsirkin
2018-08-03 7:06 ` Christoph Hellwig
2018-08-02 20:55 ` Michael S. Tsirkin
2018-08-03 2:41 ` Jason Wang
2018-08-03 19:08 ` Michael S. Tsirkin
2018-08-04 1:21 ` Benjamin Herrenschmidt
2018-08-05 0:24 ` Michael S. Tsirkin
2018-08-06 9:02 ` Anshuman Khandual
2018-08-06 13:36 ` Michael S. Tsirkin
2018-08-06 15:24 ` Christoph Hellwig
2018-08-06 16:06 ` Michael S. Tsirkin
2018-08-06 16:10 ` Christoph Hellwig
2018-08-06 16:13 ` Michael S. Tsirkin
2018-08-06 16:34 ` Christoph Hellwig
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=1932ff74-dab8-853d-256c-40045e7ad2d9@linux.vnet.ibm.com \
--to=khandual@linux.vnet.ibm.com \
--cc=aik@ozlabs.ru \
--cc=benh@kernel.crashing.org \
--cc=david@gibson.dropbear.id.au \
--cc=elfring@users.sourceforge.net \
--cc=haren@linux.vnet.ibm.com \
--cc=hch@infradead.org \
--cc=jasowang@redhat.com \
--cc=joe@perches.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=linuxram@us.ibm.com \
--cc=mpe@ellerman.id.au \
--cc=mst@redhat.com \
--cc=paulus@samba.org \
--cc=robh@kernel.org \
--cc=srikar@linux.vnet.ibm.com \
--cc=virtualization@lists.linux-foundation.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).