From mboxrd@z Thu Jan 1 00:00:00 1970 Received: by passt.top (Postfix, from userid 1000) id 894B35A095E; Fri, 05 Dec 2025 01:51:57 +0100 (CET) From: Stefano Brivio To: passt-dev@passt.top Subject: [PATCH v2 5/5] tcp, udp: Pad batched frames for vhost-user modes to 60 bytes (802.3 minimum) Date: Fri, 5 Dec 2025 01:51:57 +0100 Message-ID: <20251205005157.2577523-6-sbrivio@redhat.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20251205005157.2577523-1-sbrivio@redhat.com> References: <20251205005157.2577523-1-sbrivio@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Message-ID-Hash: XU6WDAWEP5MYOYP7X3K7B4SZZNRMQX7S X-Message-ID-Hash: XU6WDAWEP5MYOYP7X3K7B4SZZNRMQX7S X-MailFrom: sbrivio@passt.top X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header CC: David Gibson , Laurent Vivier X-Mailman-Version: 3.3.8 Precedence: list List-Id: Development discussion and patches for passt Archived-At: Archived-At: List-Archive: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: For both TCP and UDP, we request vhost-user buffers that are large enough to reach ETH_ZLEN (60 bytes), so padding is just a matter of increasing the appropriate iov_len and clearing bytes in the buffer as needed. Link: https://bugs.passt.top/show_bug.cgi?id=166 Signed-off-by: Stefano Brivio --- tcp.c | 2 -- tcp_internal.h | 1 + tcp_vu.c | 32 ++++++++++++++++++++++++++++---- udp_vu.c | 13 ++++++++++++- 4 files changed, 41 insertions(+), 7 deletions(-) diff --git a/tcp.c b/tcp.c index c5486bc..8cd062f 100644 --- a/tcp.c +++ b/tcp.c @@ -341,8 +341,6 @@ enum { }; #endif -/* MSS rounding: see SET_MSS() */ -#define MSS_DEFAULT 536 #define WINDOW_DEFAULT 14600 /* RFC 6928 */ #define RTO_INIT 1 /* s, RFC 6298 */ diff --git a/tcp_internal.h b/tcp_internal.h index 5f8fb35..d2295c9 100644 --- a/tcp_internal.h +++ b/tcp_internal.h @@ -12,6 +12,7 @@ #define BUF_DISCARD_SIZE (1 << 20) #define DISCARD_IOV_NUM DIV_ROUND_UP(MAX_WINDOW, BUF_DISCARD_SIZE) +#define MSS_DEFAULT /* and minimum */ 536 /* as it comes from minimum MTU */ #define MSS4 ROUND_DOWN(IP_MAX_MTU - \ sizeof(struct tcphdr) - \ sizeof(struct iphdr), \ diff --git a/tcp_vu.c b/tcp_vu.c index 1c81ce3..638813c 100644 --- a/tcp_vu.c +++ b/tcp_vu.c @@ -60,6 +60,26 @@ static size_t tcp_vu_hdrlen(bool v6) return hdrlen; } +/** + * tcp_vu_pad() - Pad 802.3 frame to minimum length (60 bytes) if needed + * @iov: iovec array storing 802.3 frame with TCP segment inside + * @cnt: Number of entries in @iov + */ +static void tcp_vu_pad(struct iovec *iov, size_t cnt) +{ + size_t l2len, pad; + + ASSERT(iov_size(iov, cnt) >= sizeof(struct virtio_net_hdr_mrg_rxbuf)); + l2len = iov_size(iov, cnt) - sizeof(struct virtio_net_hdr_mrg_rxbuf); + if (l2len >= ETH_ZLEN) + return; + + pad = ETH_ZLEN - l2len; + + memset((char *)iov[cnt - 1].iov_base + iov[cnt - 1].iov_len, 0, pad); + iov[cnt - 1].iov_len += pad; +} + /** * tcp_vu_send_flag() - Send segment with flags to vhost-user (no payload) * @c: Execution context @@ -91,12 +111,11 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags) vu_set_element(&flags_elem[0], NULL, &flags_iov[0]); elem_cnt = vu_collect(vdev, vq, &flags_elem[0], 1, - hdrlen + sizeof(struct tcp_syn_opts), NULL); + MAX(hdrlen + sizeof(*opts), ETH_ZLEN), NULL); if (elem_cnt != 1) return -1; - ASSERT(flags_elem[0].in_sg[0].iov_len >= - hdrlen + sizeof(struct tcp_syn_opts)); + ASSERT(flags_elem[0].in_sg[0].iov_len >= hdrlen + sizeof(*opts)); vu_set_vnethdr(vdev, flags_elem[0].in_sg[0].iov_base, 1); @@ -138,6 +157,8 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags) tcp_fill_headers(c, conn, NULL, eh, ip4h, ip6h, th, &payload, NULL, seq, !*c->pcap); + tcp_vu_pad(&flags_elem[0].in_sg[0], 1); + if (*c->pcap) { pcap_iov(&flags_elem[0].in_sg[0], 1, sizeof(struct virtio_net_hdr_mrg_rxbuf)); @@ -211,7 +232,8 @@ static ssize_t tcp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, cnt = vu_collect(vdev, vq, &elem[elem_cnt], VIRTQUEUE_MAX_SIZE - elem_cnt, - MIN(mss, fillsize) + hdrlen, &frame_size); + MAX(MIN(mss, fillsize) + hdrlen, ETH_ZLEN), + &frame_size); if (cnt == 0) break; @@ -456,6 +478,8 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn) tcp_vu_prepare(c, conn, iov, buf_cnt, &check, !*c->pcap, push); + tcp_vu_pad(iov, buf_cnt); + if (*c->pcap) { pcap_iov(iov, buf_cnt, sizeof(struct virtio_net_hdr_mrg_rxbuf)); diff --git a/udp_vu.c b/udp_vu.c index 099677f..33dbb9a 100644 --- a/udp_vu.c +++ b/udp_vu.c @@ -72,8 +72,8 @@ static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s, { const struct vu_dev *vdev = c->vdev; int iov_cnt, idx, iov_used; + size_t off, hdrlen, l2len; struct msghdr msg = { 0 }; - size_t off, hdrlen; ASSERT(!c->no_udp); @@ -116,6 +116,17 @@ static int udp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq, int s, iov_vu[idx].iov_len = off; iov_used = idx + !!off; + /* pad 802.3 frame to 60 bytes if needed */ + l2len = *dlen + hdrlen - sizeof(struct virtio_net_hdr_mrg_rxbuf); + if (l2len < ETH_ZLEN) { + size_t pad = ETH_ZLEN - l2len; + + memset((char *)iov_vu[idx].iov_base + iov_vu[idx].iov_len, + 0, pad); + + iov_vu[idx].iov_len += pad; + } + vu_set_vnethdr(vdev, iov_vu[0].iov_base, iov_used); /* release unused buffers */ -- 2.43.0