aleksandr.fedorov_itglobal.com added inline comments.
INLINE COMMENTS
> v.maffione_gmail.com wrote in pci_virtio_net.c:407
> nmd->cur_tx_ring
>
> Why did you drop the iterating over all the possible tx rings?
I drop it to simplify the code under the assumption that current setup code
void
aleksandr.fedorov_itglobal.com updated this revision to Diff 58353.
aleksandr.fedorov_itglobal.com added a comment.
- Reuse vq_getchain() to handle various negotiated features (TSO, MRG_RXBUF,
INDIRECT descriptors).
- Add two helper functions vq_get_mrgrx_bufs() and vq_relchain_mrgrx() and
aleksandr.fedorov_itglobal.com marked 2 inline comments as done.
CHANGES SINCE LAST ACTION
https://reviews.freebsd.org/D20276/new/
REVISION DETAIL
https://reviews.freebsd.org/D20276
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreferences/
To:
aleksandr.fedorov_itglobal.com updated this revision to Diff 58357.
aleksandr.fedorov_itglobal.com added a comment.
Rename vq_get_mrgrx_bufs() to vq_getbufs_mrgrx() and vq_relchain_mrgrx() to
vq_relbufs_mrgrx() to to corresponding overall style.
CHANGES SINCE LAST UPDATE
aleksandr.fedorov_itglobal.com added a comment.
Vincenzo, you are right. I'm trying to rewrite the code to handle various
negotated features. But I need some more time to test it.
CHANGES SINCE LAST ACTION
https://reviews.freebsd.org/D20276/new/
REVISION DETAIL
aleksandr.fedorov_itglobal.com added inline comments.
INLINE COMMENTS
> v.maffione_gmail.com wrote in pci_virtio_net.c:407
> That's fine. But still you need to replace cur_rx_ring with cur_tx_ring, for
> consistency.
Vincenzo, do you have any other suggestion about netmap API usage?
CHANGES
aleksandr.fedorov_itglobal.com added a comment.
Vincenzo, thanks for the review.
The main motivation to write the custom method is optimization. Function
vq_getchain() returns virtio descriptors which chained using VRING_DESCR_F_NEXT
flag. But viritio-net guest drivers do not represent the
aleksandr.fedorov_itglobal.com updated this revision to Diff 57769.
aleksandr.fedorov_itglobal.com added a comment.
Change r->cur to r->head in RX path
CHANGES SINCE LAST UPDATE
https://reviews.freebsd.org/D20276?vs=57577=57769
CHANGES SINCE LAST ACTION
aleksandr.fedorov_itglobal.com marked 3 inline comments as done.
CHANGES SINCE LAST ACTION
https://reviews.freebsd.org/D20276/new/
REVISION DETAIL
https://reviews.freebsd.org/D20276
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreferences/
To:
aleksandr.fedorov_itglobal.com added inline comments.
INLINE COMMENTS
> v.maffione_gmail.com wrote in pci_virtio_net.c:496
> In theory this NIOCRXSYNC is not needed, because poll() or kqueue_wait()
> calls NIOCRXSYNC internally. This works perfectly with poll(), at least. As
> far as I know
aleksandr.fedorov_itglobal.com updated this revision to Diff 57577.
aleksandr.fedorov_itglobal.com added a comment.
Fix incorrect usage of 'cur_rx_ring' on TX path.
CHANGES SINCE LAST UPDATE
https://reviews.freebsd.org/D20276?vs=57439=57577
CHANGES SINCE LAST ACTION
aleksandr.fedorov_itglobal.com marked an inline comment as done.
CHANGES SINCE LAST ACTION
https://reviews.freebsd.org/D20276/new/
REVISION DETAIL
https://reviews.freebsd.org/D20276
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreferences/
To:
aleksandr.fedorov_itglobal.com created this revision.
aleksandr.fedorov_itglobal.com added reviewers: bhyve, jhb, rgrimes, krion,
v.maffione_gmail.com.
Herald added a subscriber: bcran.
REVISION SUMMARY
Сurrent implementation of the virtio-net backend doesn't allow to transfer of
packets
aleksandr.fedorov_itglobal.com abandoned this revision.
CHANGES SINCE LAST ACTION
https://reviews.freebsd.org/D20276/new/
REVISION DETAIL
https://reviews.freebsd.org/D20276
EMAIL PREFERENCES
https://reviews.freebsd.org/settings/panel/emailpreferences/
To: aleksandr.fedorov_itglobal.com,
14 matches
Mail list logo