Date: Mon, 19 Feb 2024 07:00:27 GMT From: Warner Losh <imp@FreeBSD.org> To: src-committers@FreeBSD.org, dev-commits-src-all@FreeBSD.org, dev-commits-src-branches@FreeBSD.org Subject: git: fbbfcab6b850 - releng/13.3 - vtnet: Adjust for ethernet alignment. Message-ID: <202402190700.41J70R7o006551@gitrepo.freebsd.org>
next in thread | raw e-mail | index | archive | help
The branch releng/13.3 has been updated by imp: URL: https://cgit.FreeBSD.org/src/commit/?id=fbbfcab6b850fd0125633cc87575b54f0929c1a8 commit fbbfcab6b850fd0125633cc87575b54f0929c1a8 Author: Warner Losh <imp@FreeBSD.org> AuthorDate: 2024-01-29 05:08:55 +0000 Commit: Warner Losh <imp@FreeBSD.org> CommitDate: 2024-02-19 06:59:40 +0000 vtnet: Adjust for ethernet alignment. If the header that we add to the packet's size is 0 % 4 and we're strictly aligning, then we need to adjust where we store the header so the packet that follows will have it's struct ip header properly aligned. We do this on allocation (and when we check the length of the mbufs in the lro_nomrg case). We can't just adjust the clustersz in the softc, because it's also used to allocate the mbufs and it needs to be the proper size for that. Since we otherwise use the size of the mbuf (or sometimes the smaller size of the received packet) to compute how much we can buffer, this ensures no overflows. The 2 byte adjustment also does not affect how many packets we can receive in the lro_nomrg case. PR: 271288 Sponsored by: Netflix Reviewed by: bryanv Differential Revision: https://reviews.freebsd.org/D43224 (cherry picked from commit 3be59adbb5a2ae7600d46432d3bc82286e507e95) (cherry picked from commit 778eb6e1f6668864a6eddd2f6f9bcc2aa26344f3) Approved-by: re (cperciva) --- sys/dev/virtio/network/if_vtnet.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/sys/dev/virtio/network/if_vtnet.c b/sys/dev/virtio/network/if_vtnet.c index 9737e964a591..3945826f91a0 100644 --- a/sys/dev/virtio/network/if_vtnet.c +++ b/sys/dev/virtio/network/if_vtnet.c @@ -1545,6 +1545,15 @@ vtnet_rx_alloc_buf(struct vtnet_softc *sc, int nbufs, struct mbuf **m_tailp) } m->m_len = size; +#ifndef __NO_STRICT_ALIGNMENT + /* + * Need to offset the mbuf if the header we're going to add + * will misalign. + */ + if (sc->vtnet_hdr_size % 4 == 0) { + m_adj(m, ETHER_ALIGN); + } +#endif if (m_head != NULL) { m_tail->m_next = m; m_tail = m; @@ -1571,6 +1580,14 @@ vtnet_rxq_replace_lro_nomrg_buf(struct vtnet_rxq *rxq, struct mbuf *m0, sc = rxq->vtnrx_sc; clustersz = sc->vtnet_rx_clustersz; +#ifndef __NO_STRICT_ALIGNMENT + /* + * Need to offset the mbuf if the header we're going to add will + * misalign, account for that here. + */ + if (sc->vtnet_hdr_size % 4 == 0) + clustersz -= ETHER_ALIGN; +#endif m_prev = NULL; m_tail = NULL; @@ -1694,6 +1711,10 @@ vtnet_rxq_enqueue_buf(struct vtnet_rxq *rxq, struct mbuf *m) header_inlined = vtnet_modern(sc) || (sc->vtnet_flags & VTNET_FLAG_MRG_RXBUFS) != 0; /* TODO: ANY_LAYOUT */ + /* + * Note: The mbuf has been already adjusted when we allocate it if we + * have to do strict alignment. + */ if (header_inlined) error = sglist_append_mbuf(sg, m); else {
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?202402190700.41J70R7o006551>