From: Jason Wang <jasowang@redhat.com>
To: Stefano Garzarella <sgarzare@redhat.com>
Cc: virtualization@lists.linux-foundation.org,
Stefan Hajnoczi <stefanha@redhat.com>,
Laurent Vivier <lvivier@redhat.com>,
linux-kernel@vger.kernel.org, Eli Cohen <elic@nvidia.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
Max Gurtovoy <mgurtovoy@nvidia.com>
Subject: Re: [PATCH RFC 00/12] vdpa: generalize vdpa simulator and add block device
Date: Tue, 22 Dec 2020 10:44:48 +0800 [thread overview]
Message-ID: <856d53c2-82e2-e408-76e6-24c92010f973@redhat.com> (raw)
In-Reply-To: <20201221111423.sestfroiw2dgpluc@steredhat>
On 2020/12/21 下午7:14, Stefano Garzarella wrote:
> On Mon, Dec 21, 2020 at 11:16:54AM +0800, Jason Wang wrote:
>>
>> On 2020/12/18 下午7:38, Stefano Garzarella wrote:
>>> On Mon, Nov 16, 2020 at 11:37:48AM +0800, Jason Wang wrote:
>>>>
>>>> On 2020/11/13 下午9:47, Stefano Garzarella wrote:
>>>>> Thanks to Max that started this work!
>>>>> I took his patches, and extended the block simulator a bit.
>>>>>
>>>>> This series moves the network device simulator in a new module
>>>>> (vdpa_sim_net) and leaves the generic functions in the vdpa_sim core
>>>>> module, allowing the possibility to add new vDPA device simulators.
>>>>> Then we added a new vdpa_sim_blk module to simulate a block device.
>>>>>
>>>>> I'm not sure about patch 11 ("vringh: allow vringh_iov_xfer() to skip
>>>>> bytes when ptr is NULL"), maybe we can add a new functions instead of
>>>>> modify vringh_iov_xfer().
>>>>>
>>>>> As Max reported, I'm also seeing errors with vdpa_sim_blk related to
>>>>> iotlb and vringh when there is high load, these are some of the error
>>>>> messages I can see randomly:
>>>>>
>>>>> vringh: Failed to access avail idx at 00000000e8deb2cc
>>>>> vringh: Failed to read head: idx 6289 address 00000000e1ad1d50
>>>>> vringh: Failed to get flags at 000000006635d7a3
>>>>>
>>>>> virtio_vdpa vdpa0: vringh_iov_push_iotlb() error: -14 offset:
>>>>> 0x2840000 len: 0x20000
>>>>> virtio_vdpa vdpa0: vringh_iov_pull_iotlb() error: -14 offset:
>>>>> 0x58ee000 len: 0x3000
>>>>>
>>>>> These errors should all be related to the fact that iotlb_translate()
>>>>> fails with -EINVAL, so it seems that we miss some mapping.
>>>>
>>>>
>>>> Is this only reproducible when there's multiple co-current
>>>> accessing of IOTLB? If yes, it's probably a hint that some kind of
>>>> synchronization is still missed somewhere.
>>>>
>>>> It might be useful to log the dma_map/unmp in both virtio_ring and
>>>> vringh to see who is missing the map.
>>>>
>>>
>>> Just an update about these issues with vdpa-sim-blk.
>>> I've been focusing a little bit on these failures over the last few
>>> days and have found two issues related to the IOTLB/IOMMU:
>>>
>>> 1. Some requests coming from the block layer fills the SG list with
>>> multiple buffers that had the same physical address. This happens
>>> for example while using 'mkfs', at some points multiple sectors are
>>> zeroed so multiple SG elements point to the same physical page that
>>> is zeroed.
>>> Since we are using vhost_iotlb_del_range() in the
>>> vdpasim_unmap_page(), this removes all the overlapped ranges. I
>>> fixed removing a single map in vdpasim_unmap_page(), but has an
>>> alternative we can implement some kind of reference counts.
>>
>>
>> I think we need to do what hardware do. So using refcount is probably
>> not a good ida.
>
> Okay, so since we are using for simplicity an identical mapping, we
> are assigning the same dma_addr to multiple pages.
I think I get you now. That's the root cause for the failure.
Then I think we need an simple iova allocator for vdpa simulator, and it
might be useful for VDUSE as well.
Thanks
>
> So, it should be okay to remove a single mapping checking the others
> parameters (i.e. dir, size).
>
> I'll send a patch, so with the code it should be easier :-)
>
> Thanks,
> Stefano
>
>>
>>
>>>
>>> 2. There was a race between dma_map/unmap and the worker thread,
>>> since both are accessing the IOMMU. Taking the iommu_lock while
>>> using vhost_iotlb_* API in the worker thread fixes the "vringh:
>>> Failed to *" issues.
>>>
>>> Whit these issues fixed the vdpa-blk simulator seems to work well.
>>> I'll send the patches next week or after the break.
>>
>>
>> Good to know this.
>>
>> Thanks
>>
>>
>>>
>>> Thanks,
>>> Stefano
>>>
>>
>
next prev parent reply other threads:[~2020-12-22 2:46 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-13 13:47 [PATCH RFC 00/12] vdpa: generalize vdpa simulator and add block device Stefano Garzarella
2020-11-13 13:47 ` [PATCH RFC 01/12] vhost-vdpa: add support for vDPA blk devices Stefano Garzarella
2020-11-17 10:57 ` Stefan Hajnoczi
2020-11-17 15:05 ` Stefano Garzarella
2020-11-13 13:47 ` [PATCH RFC 02/12] vdpa: split vdpasim to core and net modules Stefano Garzarella
2020-11-16 4:00 ` Jason Wang
2020-11-16 9:39 ` Stefano Garzarella
2020-11-18 13:14 ` Stefano Garzarella
2020-11-19 6:16 ` Jason Wang
2020-11-13 13:47 ` [PATCH RFC 03/12] vdpa_sim: remove hard-coded virtq count Stefano Garzarella
2020-11-16 4:02 ` Jason Wang
2020-11-13 13:47 ` [PATCH RFC 04/12] vdpa: add vdpa simulator for block device Stefano Garzarella
2020-11-16 4:10 ` Jason Wang
2020-11-16 10:17 ` Stefano Garzarella
2020-11-17 11:11 ` Stefan Hajnoczi
2020-11-17 14:16 ` Stefano Garzarella
2020-11-17 16:43 ` Stefan Hajnoczi
2020-11-17 17:38 ` Stefano Garzarella
2020-11-18 11:23 ` Stefan Hajnoczi
2020-11-18 11:39 ` Stefano Garzarella
2020-11-13 13:47 ` [PATCH RFC 05/12] vdpa_sim: remove the limit of IOTLB entries Stefano Garzarella
2020-11-16 4:12 ` Jason Wang
2020-11-16 10:22 ` Stefano Garzarella
2020-11-13 13:47 ` [PATCH RFC 06/12] vdpa_sim: add struct vdpasim_device to store device properties Stefano Garzarella
2020-11-16 4:14 ` Jason Wang
2020-11-16 10:30 ` Stefano Garzarella
2020-11-17 11:23 ` Stefan Hajnoczi
2020-11-17 14:24 ` Stefano Garzarella
2020-11-13 13:47 ` [PATCH RFC 07/12] vdpa_sim: move config management outside of the core Stefano Garzarella
2020-11-16 4:18 ` Jason Wang
2020-11-16 10:42 ` Stefano Garzarella
2020-11-13 13:47 ` [PATCH RFC 08/12] vdpa_sim: use kvmalloc to allocate vdpasim->buffer Stefano Garzarella
2020-11-16 4:19 ` Jason Wang
2020-11-13 13:47 ` [PATCH RFC 09/12] vdpa_sim: make vdpasim->buffer size configurable Stefano Garzarella
2020-11-16 4:19 ` Jason Wang
2020-11-13 13:47 ` [PATCH RFC 10/12] vdpa_sim: split vdpasim_virtqueue's iov field in riov and wiov Stefano Garzarella
2020-11-16 4:21 ` Jason Wang
2020-11-17 11:27 ` Stefan Hajnoczi
2020-11-20 14:41 ` Stefano Garzarella
2020-11-13 13:47 ` [PATCH RFC 11/12] vringh: allow vringh_iov_xfer() to skip bytes when ptr is NULL Stefano Garzarella
2020-11-16 4:32 ` Jason Wang
2020-11-16 11:48 ` Stefano Garzarella
2020-11-13 13:47 ` [PATCH RFC 12/12] vdpa_sim_blk: implement ramdisk behaviour Stefano Garzarella
2020-11-16 5:25 ` Jason Wang
2020-11-16 11:08 ` Stefano Garzarella
2020-11-16 9:50 ` Michael S. Tsirkin
2020-11-16 11:23 ` Stefano Garzarella
2020-11-17 11:36 ` Stefan Hajnoczi
2020-11-17 14:32 ` Stefano Garzarella
2020-11-16 3:37 ` [PATCH RFC 00/12] vdpa: generalize vdpa simulator and add block device Jason Wang
2020-11-16 8:53 ` Stefano Garzarella
2020-12-18 11:38 ` Stefano Garzarella
2020-12-21 3:16 ` Jason Wang
2020-12-21 11:14 ` Stefano Garzarella
2020-12-22 2:44 ` Jason Wang [this message]
2020-12-22 10:57 ` Stefano Garzarella
2020-12-22 12:29 ` Jason Wang
2020-12-22 12:56 ` Jason Wang
2020-12-22 13:23 ` Stefano Garzarella
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=856d53c2-82e2-e408-76e6-24c92010f973@redhat.com \
--to=jasowang@redhat.com \
--cc=elic@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lvivier@redhat.com \
--cc=mgurtovoy@nvidia.com \
--cc=mst@redhat.com \
--cc=sgarzare@redhat.com \
--cc=stefanha@redhat.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).