From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by passt.top (Postfix) with ESMTP id D372F5A031C for ; Fri, 12 Jul 2024 17:32:56 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1720798375; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=wQbA3dU/rBYkODlrVm8zkCqax8PQhCZK1p5/76P5pXo=; b=dj8dyttiQ64N6JEm0p0U1P40p5wPNlyi7vyQyGYaThRFK/EBUYn9Z6O7qn8+aeu1YZXwb9 VNtLCIxuWkw+Arb5Wk8YqorzR3VucfXHsXH5Axt6dyShTA2r+Cpc5V/N5M/lN6UyN6mxSJ gpqBfz5oAS+3CeBWuSecw7D1gAu949M= Received: from mx-prod-mc-05.mail-002.prod.us-west-2.aws.redhat.com (ec2-54-186-198-63.us-west-2.compute.amazonaws.com [54.186.198.63]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-329-d2TsiWsfOHKnf5bfR2DR-A-1; Fri, 12 Jul 2024 11:32:53 -0400 X-MC-Unique: d2TsiWsfOHKnf5bfR2DR-A-1 Received: from mx-prod-int-05.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-05.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.17]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mx-prod-mc-05.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id 23C4B1955F40 for ; Fri, 12 Jul 2024 15:32:53 +0000 (UTC) Received: from lenovo-t14s.redhat.com (unknown [10.39.192.244]) by mx-prod-int-05.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id 0EAD01955F40; Fri, 12 Jul 2024 15:32:51 +0000 (UTC) From: Laurent Vivier To: passt-dev@passt.top Subject: [PATCH v2 4/4] vhost-user: add vhost-user Date: Fri, 12 Jul 2024 17:32:44 +0200 Message-ID: <20240712153244.831436-5-lvivier@redhat.com> In-Reply-To: <20240712153244.831436-1-lvivier@redhat.com> References: <20240712153244.831436-1-lvivier@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.0 on 10.30.177.17 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="US-ASCII"; x-default=true Message-ID-Hash: LQBLZUCEQTVJ74JBUNGLPQXB4Y7YUCS2 X-Message-ID-Hash: LQBLZUCEQTVJ74JBUNGLPQXB4Y7YUCS2 X-MailFrom: lvivier@redhat.com 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: 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: add virtio and vhost-user functions to connect with QEMU. $ ./passt --vhost-user and # qemu-system-x86_64 ... -m 4G \ -object memory-backend-memfd,id=memfd0,share=on,size=4G \ -numa node,memdev=memfd0 \ -chardev socket,id=chr0,path=/tmp/passt_1.socket \ -netdev vhost-user,id=netdev0,chardev=chr0 \ -device virtio-net,mac=9a:2b:2c:2d:2e:2f,netdev=netdev0 \ ... Signed-off-by: Laurent Vivier --- Makefile | 4 +- checksum.c | 1 - conf.c | 24 ++- isolation.c | 15 +- packet.c | 13 ++ packet.h | 2 + passt.c | 16 +- passt.h | 10 + pcap.c | 1 - tap.c | 114 +++++++--- tap.h | 5 +- tcp.c | 17 +- tcp_vu.c | 560 +++++++++++++++++++++++++++++++++++++++++++++++++ tcp_vu.h | 12 ++ udp.c | 54 ++--- udp_internal.h | 39 ++++ udp_vu.c | 240 +++++++++++++++++++++ udp_vu.h | 11 + vhost_user.c | 28 ++- virtio.c | 1 - 20 files changed, 1084 insertions(+), 83 deletions(-) create mode 100644 tcp_vu.c create mode 100644 tcp_vu.h create mode 100644 udp_internal.h create mode 100644 udp_vu.c create mode 100644 udp_vu.h diff --git a/Makefile b/Makefile index b2da6ad62103..d22388726099 100644 --- a/Makefile +++ b/Makefile @@ -47,7 +47,7 @@ FLAGS += -DDUAL_STACK_SOCKETS=$(DUAL_STACK_SOCKETS) PASST_SRCS = arch.c arp.c checksum.c conf.c dhcp.c dhcpv6.c flow.c fwd.c \ icmp.c igmp.c inany.c iov.c ip.c isolation.c lineread.c log.c mld.c \ ndp.c netlink.c packet.c passt.c pasta.c pcap.c pif.c tap.c tcp.c \ - tcp_buf.c tcp_splice.c udp.c util.c vhost_user.c virtio.c + tcp_buf.c tcp_splice.c tcp_vu.c udp.c udp_vu.c util.c vhost_user.c virtio.c QRAP_SRCS = qrap.c SRCS = $(PASST_SRCS) $(QRAP_SRCS) @@ -57,7 +57,7 @@ PASST_HEADERS = arch.h arp.h checksum.h conf.h dhcp.h dhcpv6.h flow.h fwd.h \ flow_table.h icmp.h icmp_flow.h inany.h iov.h ip.h isolation.h \ lineread.h log.h ndp.h netlink.h packet.h passt.h pasta.h pcap.h pif.h \ siphash.h tap.h tcp.h tcp_buf.h tcp_conn.h tcp_internal.h tcp_splice.h \ - udp.h util.h vhost_user.h virtio.h + tcp_vu.h udp.h udp_internal.h udp_vu.h util.h vhost_user.h virtio.h HEADERS = $(PASST_HEADERS) seccomp.h C := \#include \nstruct tcp_info x = { .tcpi_snd_wnd = 0 }; diff --git a/checksum.c b/checksum.c index 006614fcbb28..aa5b7ae1cb66 100644 --- a/checksum.c +++ b/checksum.c @@ -501,7 +501,6 @@ uint16_t csum(const void *buf, size_t len, uint32_t init) * * Return: 16-bit folded, complemented checksum */ -/* cppcheck-suppress unusedFunction */ uint16_t csum_iov(const struct iovec *iov, size_t n, uint32_t init) { unsigned int i; diff --git a/conf.c b/conf.c index 3c38cebcbd69..3eb5ba56df88 100644 --- a/conf.c +++ b/conf.c @@ -45,6 +45,7 @@ #include "lineread.h" #include "isolation.h" #include "log.h" +#include "vhost_user.h" /** * next_chunk - Return the next piece of a string delimited by a character @@ -744,9 +745,14 @@ static void usage(const char *name, FILE *f, int status) " default: same interface name as external one\n"); } else { fprintf(f, - " -s, --socket PATH UNIX domain socket path\n" + " -s, --socket, --socket-path PATH UNIX domain socket path\n" " default: probe free path starting from " UNIX_SOCK_PATH "\n", 1); + fprintf(f, + " --vhost-user Enable vhost-user mode\n" + " UNIX domain socket is provided by -s option\n" + " --print-capabilities print back-end capabilities in JSON format,\n" + " only meaningful for vhost-user mode\n"); } fprintf(f, @@ -1215,6 +1221,10 @@ void conf(struct ctx *c, int argc, char **argv) {"no-copy-routes", no_argument, NULL, 18 }, {"no-copy-addrs", no_argument, NULL, 19 }, {"netns-only", no_argument, NULL, 20 }, + {"vhost-user", no_argument, NULL, 21 }, + /* vhost-user backend program convention */ + {"print-capabilities", no_argument, NULL, 22 }, + {"socket-path", required_argument, NULL, 's' }, { 0 }, }; const char *logname = (c->mode == MODE_PASTA) ? "pasta" : "passt"; @@ -1344,14 +1354,12 @@ void conf(struct ctx *c, int argc, char **argv) sizeof(c->ip4.ifname_out), "%s", optarg); if (ret <= 0 || ret >= (int)sizeof(c->ip4.ifname_out)) die("Invalid interface name: %s", optarg); - break; case 16: ret = snprintf(c->ip6.ifname_out, sizeof(c->ip6.ifname_out), "%s", optarg); if (ret <= 0 || ret >= (int)sizeof(c->ip6.ifname_out)) die("Invalid interface name: %s", optarg); - break; case 17: if (c->mode != MODE_PASTA) @@ -1380,6 +1388,16 @@ void conf(struct ctx *c, int argc, char **argv) netns_only = 1; *userns = 0; break; + case 21: + if (c->mode == MODE_PASTA) { + err("--vhost-user is for passt mode only"); + usage(argv[0], stdout, EXIT_SUCCESS); + } + c->mode = MODE_VU; + break; + case 22: + vu_print_capabilities(); + break; case 'd': c->debug = 1; c->quiet = 0; diff --git a/isolation.c b/isolation.c index 4956d7e6f331..1a27f066c2ba 100644 --- a/isolation.c +++ b/isolation.c @@ -373,12 +373,19 @@ void isolate_postfork(const struct ctx *c) prctl(PR_SET_DUMPABLE, 0); - if (c->mode == MODE_PASTA) { - prog.len = (unsigned short)ARRAY_SIZE(filter_pasta); - prog.filter = filter_pasta; - } else { + switch (c->mode) { + case MODE_PASST: prog.len = (unsigned short)ARRAY_SIZE(filter_passt); prog.filter = filter_passt; + break; + case MODE_PASTA: + prog.len = (unsigned short)ARRAY_SIZE(filter_pasta); + prog.filter = filter_pasta; + break; + case MODE_VU: + prog.len = (unsigned short)ARRAY_SIZE(filter_vu); + prog.filter = filter_vu; + break; } if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) || diff --git a/packet.c b/packet.c index f7bb523c4ffa..a95d525f97f2 100644 --- a/packet.c +++ b/packet.c @@ -36,6 +36,19 @@ static int packet_check_range(const struct pool *p, size_t offset, size_t len, const char *start, const char *func, int line) { + ASSERT(p->buf); + + if (p->buf_size == 0) { + int ret; + + ret = vu_packet_check_range((void *)p->buf, offset, len, start); + + if (ret == -1 && func) + trace("cannot find region, %s:%i", func, line); + + return ret; + } + if (start < p->buf) { if (func) { trace("add packet start %p before buffer start %p, " diff --git a/packet.h b/packet.h index 8377dcf678bb..d32688d8a0a4 100644 --- a/packet.h +++ b/packet.h @@ -22,6 +22,8 @@ struct pool { struct iovec pkt[1]; }; +int vu_packet_check_range(void *buf, size_t offset, size_t len, + const char *start); void packet_add_do(struct pool *p, size_t len, const char *start, const char *func, int line); void *packet_get_do(const struct pool *p, const size_t idx, diff --git a/passt.c b/passt.c index e4d45daab011..6f3df4026c83 100644 --- a/passt.c +++ b/passt.c @@ -73,6 +73,8 @@ char *epoll_type_str[] = { [EPOLL_TYPE_TAP_PASTA] = "/dev/net/tun device", [EPOLL_TYPE_TAP_PASST] = "connected qemu socket", [EPOLL_TYPE_TAP_LISTEN] = "listening qemu socket", + [EPOLL_TYPE_VHOST_CMD] = "vhost-user command socket", + [EPOLL_TYPE_VHOST_KICK] = "vhost-user kick socket", }; static_assert(ARRAY_SIZE(epoll_type_str) == EPOLL_NUM_TYPES, "epoll_type_str[] doesn't match enum epoll_type"); @@ -205,6 +207,7 @@ int main(int argc, char **argv) struct rlimit limit; struct timespec now; struct sigaction sa; + struct vu_dev vdev; arch_avx2_exec(argv); @@ -259,6 +262,8 @@ int main(int argc, char **argv) pasta_netns_quit_init(&c); tap_sock_init(&c); + if (c.mode == MODE_VU) + vu_init(&c, &vdev); secret_init(&c); @@ -347,11 +352,20 @@ loop: tcp_timer_handler(&c, ref); break; case EPOLL_TYPE_UDP: - udp_buf_sock_handler(&c, ref, eventmask, &now); + if (c.mode == MODE_VU) + udp_vu_sock_handler(&c, ref, eventmask, &now); + else + udp_buf_sock_handler(&c, ref, eventmask, &now); break; case EPOLL_TYPE_PING: icmp_sock_handler(&c, ref); break; + case EPOLL_TYPE_VHOST_CMD: + tap_handler_vu(&vdev, c.fd_tap, eventmask); + break; + case EPOLL_TYPE_VHOST_KICK: + vu_kick_cb(&vdev, ref); + break; default: /* Can't happen */ ASSERT(0); diff --git a/passt.h b/passt.h index 21cf4c15c921..7dce022505b4 100644 --- a/passt.h +++ b/passt.h @@ -22,6 +22,8 @@ union epoll_ref; #include "fwd.h" #include "tcp.h" #include "udp.h" +#include "udp_vu.h" +#include "vhost_user.h" /** * enum epoll_type - Different types of fds we poll over @@ -51,6 +53,10 @@ enum epoll_type { EPOLL_TYPE_TAP_PASST, /* socket listening for qemu socket connections */ EPOLL_TYPE_TAP_LISTEN, + /* vhost-user command socket */ + EPOLL_TYPE_VHOST_CMD, + /* vhost-user kick event socket */ + EPOLL_TYPE_VHOST_KICK, EPOLL_NUM_TYPES, }; @@ -117,6 +123,7 @@ struct fqdn { enum passt_modes { MODE_PASST, MODE_PASTA, + MODE_VU, }; /** @@ -223,6 +230,7 @@ struct ip6_ctx { * @no_map_gw: Don't map connections, untracked UDP to gateway to host * @low_wmem: Low probed net.core.wmem_max * @low_rmem: Low probed net.core.rmem_max + * @vdev: vhost-user device */ struct ctx { enum passt_modes mode; @@ -286,6 +294,8 @@ struct ctx { int low_wmem; int low_rmem; + + struct vu_dev *vdev; }; void proto_update_l2_buf(const unsigned char *eth_d, diff --git a/pcap.c b/pcap.c index 46cc4b0d72b6..7e9c56090041 100644 --- a/pcap.c +++ b/pcap.c @@ -140,7 +140,6 @@ void pcap_multiple(const struct iovec *iov, size_t frame_parts, unsigned int n, * containing packet data to write, including L2 header * @iovcnt: Number of buffers (@iov entries) */ -/* cppcheck-suppress unusedFunction */ void pcap_iov(const struct iovec *iov, size_t iovcnt) { struct timespec now; diff --git a/tap.c b/tap.c index ec994a2ed4ed..56506a45e4dd 100644 --- a/tap.c +++ b/tap.c @@ -58,6 +58,7 @@ #include "packet.h" #include "tap.h" #include "log.h" +#include "vhost_user.h" /* IPv4 (plus ARP) and IPv6 message batches from tap/guest to IP handlers */ static PACKET_POOL_NOINIT(pool_tap4, TAP_MSGS, pkt_buf); @@ -78,16 +79,22 @@ void tap_send_single(const struct ctx *c, const void *data, size_t l2len) struct iovec iov[2]; size_t iovcnt = 0; - if (c->mode == MODE_PASST) { + switch (c->mode) { + case MODE_PASST: iov[iovcnt] = IOV_OF_LVALUE(vnet_len); iovcnt++; - } - - iov[iovcnt].iov_base = (void *)data; - iov[iovcnt].iov_len = l2len; - iovcnt++; + /* fall through */ + case MODE_PASTA: + iov[iovcnt].iov_base = (void *)data; + iov[iovcnt].iov_len = l2len; + iovcnt++; - tap_send_frames(c, iov, iovcnt, 1); + tap_send_frames(c, iov, iovcnt, 1); + break; + case MODE_VU: + vu_send(c->vdev, data, l2len); + break; + } } /** @@ -416,10 +423,18 @@ size_t tap_send_frames(const struct ctx *c, const struct iovec *iov, if (!nframes) return 0; - if (c->mode == MODE_PASTA) + switch (c->mode) { + case MODE_PASTA: m = tap_send_frames_pasta(c, iov, bufs_per_frame, nframes); - else + break; + case MODE_PASST: m = tap_send_frames_passt(c, iov, bufs_per_frame, nframes); + break; + case MODE_VU: + /* fall through */ + default: + ASSERT(0); + } if (m < nframes) debug("tap: failed to send %zu frames of %zu", @@ -977,7 +992,7 @@ void tap_add_packet(struct ctx *c, ssize_t l2len, char *p) * tap_sock_reset() - Handle closing or failure of connect AF_UNIX socket * @c: Execution context */ -static void tap_sock_reset(struct ctx *c) +void tap_sock_reset(struct ctx *c) { if (c->one_off) { info("Client closed connection, exiting"); @@ -988,6 +1003,8 @@ static void tap_sock_reset(struct ctx *c) epoll_ctl(c->epollfd, EPOLL_CTL_DEL, c->fd_tap, NULL); close(c->fd_tap); c->fd_tap = -1; + if (c->mode == MODE_VU) + vu_cleanup(c->vdev); } /** @@ -1180,11 +1197,17 @@ static void tap_sock_unix_init(struct ctx *c) ev.data.u64 = ref.u64; epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap_listen, &ev); - info("\nYou can now start qemu (>= 7.2, with commit 13c6be96618c):"); - info(" kvm ... -device virtio-net-pci,netdev=s -netdev stream,id=s,server=off,addr.type=unix,addr.path=%s", - c->sock_path); - info("or qrap, for earlier qemu versions:"); - info(" ./qrap 5 kvm ... -net socket,fd=5 -net nic,model=virtio"); + if (c->mode == MODE_VU) { + info("You can start qemu with:"); + info(" kvm ... -chardev socket,id=chr0,path=%s -netdev vhost-user,id=netdev0,chardev=chr0 -device virtio-net,netdev=netdev0 -object memory-backend-memfd,id=memfd0,share=on,size=$RAMSIZE -numa node,memdev=memfd0\n", + c->sock_path); + } else { + info("\nYou can now start qemu (>= 7.2, with commit 13c6be96618c):"); + info(" kvm ... -device virtio-net-pci,netdev=s -netdev stream,id=s,server=off,addr.type=unix,addr.path=%s", + c->sock_path); + info("or qrap, for earlier qemu versions:"); + info(" ./qrap 5 kvm ... -net socket,fd=5 -net nic,model=virtio"); + } } /** @@ -1194,8 +1217,8 @@ static void tap_sock_unix_init(struct ctx *c) */ void tap_listen_handler(struct ctx *c, uint32_t events) { - union epoll_ref ref = { .type = EPOLL_TYPE_TAP_PASST }; struct epoll_event ev = { 0 }; + union epoll_ref ref; int v = INT_MAX / 2; struct ucred ucred; socklen_t len; @@ -1235,7 +1258,13 @@ void tap_listen_handler(struct ctx *c, uint32_t events) trace("tap: failed to set SO_SNDBUF to %i", v); ref.fd = c->fd_tap; - ev.events = EPOLLIN | EPOLLET | EPOLLRDHUP; + if (c->mode == MODE_VU) { + ref.type = EPOLL_TYPE_VHOST_CMD; + ev.events = EPOLLIN | EPOLLRDHUP; + } else { + ref.type = EPOLL_TYPE_TAP_PASST; + ev.events = EPOLLIN | EPOLLRDHUP | EPOLLET; + } ev.data.u64 = ref.u64; epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap, &ev); } @@ -1296,21 +1325,47 @@ static void tap_sock_tun_init(struct ctx *c) epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap, &ev); } +void tap_sock_update_buf(void *base, size_t size) +{ + int i; + + pool_tap4_storage.buf = base; + pool_tap4_storage.buf_size = size; + pool_tap6_storage.buf = base; + pool_tap6_storage.buf_size = size; + + for (i = 0; i < TAP_SEQS; i++) { + tap4_l4[i].p.buf = base; + tap4_l4[i].p.buf_size = size; + tap6_l4[i].p.buf = base; + tap6_l4[i].p.buf_size = size; + } +} + /** * tap_sock_init() - Create and set up AF_UNIX socket or tuntap file descriptor * @c: Execution context */ void tap_sock_init(struct ctx *c) { - size_t sz = sizeof(pkt_buf); + size_t sz; + char *buf; int i; - pool_tap4_storage = PACKET_INIT(pool_tap4, TAP_MSGS, pkt_buf, sz); - pool_tap6_storage = PACKET_INIT(pool_tap6, TAP_MSGS, pkt_buf, sz); + if (c->mode == MODE_VU) { + buf = NULL; + sz = 0; + } else { + buf = pkt_buf; + sz = sizeof(pkt_buf); + } + + pool_tap4_storage = PACKET_INIT(pool_tap4, TAP_MSGS, buf, sz); + pool_tap6_storage = PACKET_INIT(pool_tap6, TAP_MSGS, buf, sz); for (i = 0; i < TAP_SEQS; i++) { - tap4_l4[i].p = PACKET_INIT(pool_l4, UIO_MAXIOV, pkt_buf, sz); - tap6_l4[i].p = PACKET_INIT(pool_l4, UIO_MAXIOV, pkt_buf, sz); + tap4_l4[i].p = PACKET_INIT(pool_l4, UIO_MAXIOV, buf, sz); + tap6_l4[i].p = PACKET_INIT(pool_l4, UIO_MAXIOV, buf, sz); } if (c->fd_tap != -1) { /* Passed as --fd */ @@ -1319,12 +1374,21 @@ void tap_sock_init(struct ctx *c) ASSERT(c->one_off); ref.fd = c->fd_tap; - if (c->mode == MODE_PASST) + switch (c->mode) { + case MODE_PASST: ref.type = EPOLL_TYPE_TAP_PASST; - else + ev.events = EPOLLIN | EPOLLET | EPOLLRDHUP; + break; + case MODE_PASTA: ref.type = EPOLL_TYPE_TAP_PASTA; + ev.events = EPOLLIN | EPOLLET | EPOLLRDHUP; + break; + case MODE_VU: + ref.type = EPOLL_TYPE_VHOST_CMD; + ev.events = EPOLLIN | EPOLLRDHUP; + break; + } - ev.events = EPOLLIN | EPOLLET | EPOLLRDHUP; ev.data.u64 = ref.u64; epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap, &ev); return; diff --git a/tap.h b/tap.h index d496bd0e4b99..d9c6d4f57093 100644 --- a/tap.h +++ b/tap.h @@ -40,7 +40,8 @@ static inline struct iovec tap_hdr_iov(const struct ctx *c, */ static inline void tap_hdr_update(struct tap_hdr *thdr, size_t l2len) { - thdr->vnet_len = htonl(l2len); + if (thdr) + thdr->vnet_len = htonl(l2len); } struct in_addr tap_ip4_daddr(const struct ctx *c); @@ -69,6 +70,8 @@ void tap_handler_pasta(struct ctx *c, uint32_t events, void tap_handler_passt(struct ctx *c, uint32_t events, const struct timespec *now); int tap_sock_unix_open(char *sock_path); +void tap_sock_reset(struct ctx *c); +void tap_sock_update_buf(void *base, size_t size); void tap_sock_init(struct ctx *c); void tap_flush_pools(void); void tap_handler(struct ctx *c, const struct timespec *now); diff --git a/tcp.c b/tcp.c index 698e7ecb821a..424486ff73be 100644 --- a/tcp.c +++ b/tcp.c @@ -304,6 +304,7 @@ #include "flow_table.h" #include "tcp_internal.h" #include "tcp_buf.h" +#include "tcp_vu.h" #define TCP_HASH_TABLE_LOAD 70 /* % */ #define TCP_HASH_TABLE_SIZE (FLOW_MAX * 100 / TCP_HASH_TABLE_LOAD) @@ -1049,7 +1050,10 @@ static size_t tcp_fill_headers4(const struct ctx *c, tcp_fill_header(th, conn, seq); - tcp_update_check_tcp4(iph, th); + if (c->mode != MODE_VU) + tcp_update_check_tcp4(iph, th); + else + th->check = 0; tap_hdr_update(taph, l3len + sizeof(struct ethhdr)); @@ -1094,7 +1098,10 @@ static size_t tcp_fill_headers6(const struct ctx *c, tcp_fill_header(th, conn, seq); - tcp_update_check_tcp6(ip6h, th); + if (c->mode != MODE_VU) + tcp_update_check_tcp6(ip6h, th); + else + th->check = 0; tap_hdr_update(taph, l4len + sizeof(*ip6h) + sizeof(struct ethhdr)); @@ -1362,6 +1369,9 @@ int tcp_prepare_flags(struct ctx *c, struct tcp_tap_conn *conn, */ int tcp_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags) { + if (c->mode == MODE_VU) + return tcp_vu_send_flag(c, conn, flags); + return tcp_buf_send_flag(c, conn, flags); } @@ -1814,6 +1824,9 @@ static int tcp_sock_consume(const struct tcp_tap_conn *conn, uint32_t ack_seq) */ static int tcp_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn) { + if (c->mode == MODE_VU) + return tcp_vu_data_from_sock(c, conn); + return tcp_buf_data_from_sock(c, conn); } diff --git a/tcp_vu.c b/tcp_vu.c new file mode 100644 index 000000000000..24fee3f63278 --- /dev/null +++ b/tcp_vu.c @@ -0,0 +1,560 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * Copyright Red Hat + * Author: Laurent Vivier + * + * tcp_vu.c - TCP L2 vhost-user management functions + */ + +#include +#include +#include + +#include + +#include + +#include +#include + +#include "util.h" +#include "ip.h" +#include "passt.h" +#include "siphash.h" +#include "inany.h" +#include "vhost_user.h" +#include "tcp.h" +#include "pcap.h" +#include "flow.h" +#include "tcp_conn.h" +#include "flow_table.h" +#include "tcp_vu.h" +#include "tcp_internal.h" +#include "checksum.h" + +#define CONN_V4(conn) (!!inany_v4(&(conn)->faddr)) +#define CONN_V6(conn) (!CONN_V4(conn)) + +/** + * struct tcp_payload_t - TCP header and data to send segments with payload + * @th: TCP header + * @data: TCP data + */ +struct tcp_payload_t { + struct tcphdr th; + uint8_t data[IP_MAX_MTU - sizeof(struct tcphdr)]; +}; + +/** + * struct tcp_flags_t - TCP header and data to send zero-length + * segments (flags) + * @th: TCP header + * @opts TCP options + */ +struct tcp_flags_t { + struct tcphdr th; + char opts[OPT_MSS_LEN + OPT_WS_LEN + 1]; +}; + +/* vhost-user */ +static const struct virtio_net_hdr vu_header = { + .flags = VIRTIO_NET_HDR_F_DATA_VALID, + .gso_type = VIRTIO_NET_HDR_GSO_NONE, +}; + +int tcp_vu_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags) +{ + struct vu_dev *vdev = c->vdev; + struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE]; + size_t l2len, vnet_hdrlen, l4len, optlen; + struct virtio_net_hdr_mrg_rxbuf *vh; + struct iovec l2_iov[TCP_NUM_IOVS]; + struct vu_virtq_element elem; + struct iovec in_sg; + struct ethhdr *eh; + int nb_ack; + int ret; + + elem.out_num = 0; + elem.out_sg = NULL; + elem.in_num = 1; + elem.in_sg = &in_sg; + ret = vu_queue_pop(vdev, vq, &elem); + if (ret < 0) + return 0; + + if (elem.in_num < 1) { + err("virtio-net receive queue contains no in buffers"); + vu_queue_rewind(vdev, vq, 1); + return 0; + } + + vh = elem.in_sg[0].iov_base; + + vh->hdr = vu_header; + if (vu_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) { + vnet_hdrlen = sizeof(*vh); + vh->num_buffers = htole16(1); + } else { + vnet_hdrlen = sizeof(vh->hdr); + } + + l2_iov[TCP_IOV_TAP].iov_base = NULL; + l2_iov[TCP_IOV_TAP].iov_len = 0; + l2_iov[TCP_IOV_ETH].iov_base = (char *)elem.in_sg[0].iov_base + vnet_hdrlen; + l2_iov[TCP_IOV_ETH].iov_len = sizeof(struct ethhdr); + + eh = l2_iov[TCP_IOV_ETH].iov_base; + + memcpy(eh->h_dest, c->mac_guest, sizeof(eh->h_dest)); + memcpy(eh->h_source, c->mac, sizeof(eh->h_source)); + + if (CONN_V4(conn)) { + struct tcp_flags_t *payload; + struct iphdr *iph; + uint32_t seq; + + l2_iov[TCP_IOV_IP].iov_base = (char *)l2_iov[TCP_IOV_ETH].iov_base + + l2_iov[TCP_IOV_ETH].iov_len; + l2_iov[TCP_IOV_IP].iov_len = sizeof(struct iphdr); + l2_iov[TCP_IOV_PAYLOAD].iov_base = (char *)l2_iov[TCP_IOV_IP].iov_base + + l2_iov[TCP_IOV_IP].iov_len; + + eh->h_proto = htons(ETH_P_IP); + + iph = l2_iov[TCP_IOV_IP].iov_base; + *iph = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); + + payload = l2_iov[TCP_IOV_PAYLOAD].iov_base; + payload->th = (struct tcphdr){ + .doff = offsetof(struct tcp_flags_t, opts) / 4, + .ack = 1 + }; + + seq = conn->seq_to_tap; + ret = tcp_prepare_flags(c, conn, flags, &payload->th, payload->opts, &optlen); + if (ret <= 0) { + vu_queue_rewind(vdev, vq, 1); + return ret; + } + + l4len = tcp_l2_buf_fill_headers(c, conn, l2_iov, optlen, NULL, + seq); + /* cppcheck-suppress unreadVariable */ + l2_iov[TCP_IOV_PAYLOAD].iov_len = l4len; + + l2len = l4len + sizeof(*iph) + sizeof(struct ethhdr); + + if (*c->pcap) { + struct in_addr saddr, daddr; + uint32_t sum; + + saddr.s_addr = iph->saddr; + daddr.s_addr = iph->daddr; + sum = proto_ipv4_header_psum(l4len, + IPPROTO_TCP, + saddr, daddr); + + payload->th.check = 0; + payload->th.check = csum(&payload->th, optlen + sizeof(struct tcphdr), sum); + } + } else { + struct tcp_flags_t *payload; + struct ipv6hdr *ip6h; + uint32_t seq; + + l2_iov[TCP_IOV_IP].iov_base = (char *)l2_iov[TCP_IOV_ETH].iov_base + + l2_iov[TCP_IOV_ETH].iov_len; + l2_iov[TCP_IOV_IP].iov_len = sizeof(struct ipv6hdr); + l2_iov[TCP_IOV_PAYLOAD].iov_base = (char *)l2_iov[TCP_IOV_IP].iov_base + + l2_iov[TCP_IOV_IP].iov_len; + + eh->h_proto = htons(ETH_P_IPV6); + + ip6h = l2_iov[TCP_IOV_IP].iov_base; + *ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP); + + payload = l2_iov[TCP_IOV_PAYLOAD].iov_base; + payload->th = (struct tcphdr){ + .doff = offsetof(struct tcp_flags_t, opts) / 4, + .ack = 1 + }; + + seq = conn->seq_to_tap; + ret = tcp_prepare_flags(c, conn, flags, &payload->th, payload->opts, &optlen); + if (ret <= 0) { + vu_queue_rewind(vdev, vq, 1); + return ret; + } + + l4len = tcp_l2_buf_fill_headers(c, conn, l2_iov, optlen, NULL, + seq); + /* cppcheck-suppress unreadVariable */ + l2_iov[TCP_IOV_PAYLOAD].iov_len = l4len; + + l2len = l4len + sizeof(*ip6h) + sizeof(struct ethhdr); + + if (*c->pcap) { + uint32_t sum = proto_ipv6_header_psum(l4len, + IPPROTO_TCP, + &ip6h->saddr, + &ip6h->daddr); + + payload->th.check = 0; + payload->th.check = csum(&payload->th, optlen + sizeof(struct tcphdr), sum); + } + } + + pcap((void *)eh, l2len); + + l2len += vnet_hdrlen; + ASSERT(l2len <= elem.in_sg[0].iov_len); + + vu_queue_fill(vq, &elem, l2len, 0); + nb_ack = 1; + + if (flags & DUP_ACK) { + struct vu_virtq_element elem_dup; + struct iovec in_sg_dup; + + elem_dup.out_num = 0; + elem_dup.out_sg = NULL; + elem_dup.in_num = 1; + elem_dup.in_sg = &in_sg_dup; + ret = vu_queue_pop(vdev, vq, &elem_dup); + if (ret == 0) { + if (elem_dup.in_num < 1 || elem_dup.in_sg[0].iov_len < l2len) { + vu_queue_rewind(vdev, vq, 1); + } else { + memcpy(elem_dup.in_sg[0].iov_base, vh, l2len); + nb_ack++; + } + } + } + + vu_queue_flush(vq, nb_ack); + vu_queue_notify(vdev, vq); + + return 0; +} + +int tcp_vu_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn) +{ + uint32_t wnd_scaled = conn->wnd_from_tap << conn->ws_from_tap; + static struct iovec iov_vu[VIRTQUEUE_MAX_SIZE]; + static struct vu_virtq_element elem[VIRTQUEUE_MAX_SIZE]; + static struct iovec in_sg[VIRTQUEUE_MAX_SIZE]; + struct vu_dev *vdev = c->vdev; + struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE]; + size_t l2_hdrlen, vnet_hdrlen, fillsize; + int s = conn->sock, v4 = CONN_V4(conn); + struct iovec l2_iov[TCP_NUM_IOVS]; + int i, ret, iov_cnt, iov_used; + struct msghdr mh_sock = { 0 }; + uint16_t mss = MSS_GET(conn); + static int in_sg_count; + uint32_t already_sent; + const uint16_t *check; + struct iovec *first; + bool has_mrg_rxbuf; + int segment_size; + int num_buffers; + ssize_t len; + + if (!vu_queue_enabled(vq) || !vu_queue_started(vq)) { + flow_err(conn, + "Got packet, but no available descriptors on RX virtq."); + return 0; + } + + already_sent = conn->seq_to_tap - conn->seq_ack_from_tap; + + if (SEQ_LT(already_sent, 0)) { + /* RFC 761, section 2.1. */ + flow_trace(conn, "ACK sequence gap: ACK for %u, sent: %u", + conn->seq_ack_from_tap, conn->seq_to_tap); + conn->seq_to_tap = conn->seq_ack_from_tap; + already_sent = 0; + } + + if (!wnd_scaled || already_sent >= wnd_scaled) { + conn_flag(c, conn, STALLED); + conn_flag(c, conn, ACK_FROM_TAP_DUE); + return 0; + } + + /* Set up buffer descriptors we'll fill completely and partially. */ + + fillsize = wnd_scaled; + + iov_vu[0].iov_base = tcp_buf_discard; + iov_vu[0].iov_len = already_sent; + fillsize -= already_sent; + + has_mrg_rxbuf = vu_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF); + if (has_mrg_rxbuf) + vnet_hdrlen = sizeof(struct virtio_net_hdr_mrg_rxbuf); + else + vnet_hdrlen = sizeof(struct virtio_net_hdr); + l2_hdrlen = vnet_hdrlen + sizeof(struct ethhdr) + sizeof(struct tcphdr); + if (v4) + l2_hdrlen += sizeof(struct iphdr); + else + l2_hdrlen += sizeof(struct ipv6hdr); + + iov_cnt = 0; + in_sg_count = 0; + segment_size = 0; + while (fillsize > 0 && iov_cnt < VIRTQUEUE_MAX_SIZE - 1 && + in_sg_count < ARRAY_SIZE(in_sg)) { + + elem[iov_cnt].out_num = 0; + elem[iov_cnt].out_sg = NULL; + elem[iov_cnt].in_num = ARRAY_SIZE(in_sg) - in_sg_count; + elem[iov_cnt].in_sg = &in_sg[in_sg_count]; + ret = vu_queue_pop(vdev, vq, &elem[iov_cnt]); + if (ret < 0) + break; + + if (elem[iov_cnt].in_num < 1) { + err("virtio-net receive queue contains no in buffers"); + goto err; + } + in_sg_count += elem[iov_cnt].in_num; + + ASSERT(elem[iov_cnt].in_num == 1); + ASSERT(elem[iov_cnt].in_sg[0].iov_len >= l2_hdrlen); + + if (segment_size == 0) { + iov_vu[iov_cnt + 1].iov_base = + (char *)elem[iov_cnt].in_sg[0].iov_base + l2_hdrlen; + iov_vu[iov_cnt + 1].iov_len = + elem[iov_cnt].in_sg[0].iov_len - l2_hdrlen; + } else { + iov_vu[iov_cnt + 1].iov_base = elem[iov_cnt].in_sg[0].iov_base; + iov_vu[iov_cnt + 1].iov_len = elem[iov_cnt].in_sg[0].iov_len; + } + + if (iov_vu[iov_cnt + 1].iov_len > fillsize) + iov_vu[iov_cnt + 1].iov_len = fillsize; + + segment_size += iov_vu[iov_cnt + 1].iov_len; + if (!has_mrg_rxbuf) { + segment_size = 0; + } else if (segment_size >= mss) { + iov_vu[iov_cnt + 1].iov_len -= segment_size - mss; + segment_size = 0; + } + fillsize -= iov_vu[iov_cnt + 1].iov_len; + + iov_cnt++; + } + if (iov_cnt == 0) + return 0; + + ret = 0; + mh_sock.msg_iov = iov_vu; + mh_sock.msg_iovlen = iov_cnt + 1; + + do + len = recvmsg(s, &mh_sock, MSG_PEEK); + while (len < 0 && errno == EINTR); + + if (len < 0) + goto err; + + if (!len) { + vu_queue_rewind(vdev, vq, iov_cnt); + if ((conn->events & (SOCK_FIN_RCVD | TAP_FIN_SENT)) == SOCK_FIN_RCVD) { + ret = tcp_vu_send_flag(c, conn, FIN | ACK); + if (ret) { + tcp_rst(c, conn); + return ret; + } + + conn_event(c, conn, TAP_FIN_SENT); + } + + return 0; + } + + len -= already_sent; + if (len <= 0) { + conn_flag(c, conn, STALLED); + vu_queue_rewind(vdev, vq, iov_cnt); + return 0; + } + + conn_flag(c, conn, ~STALLED); + + /* Likely, some new data was acked too. */ + tcp_update_seqack_wnd(c, conn, 0, NULL); + + /* initialize headers */ + iov_used = 0; + num_buffers = 0; + check = NULL; + segment_size = 0; + for (i = 0; i < iov_cnt && len; i++) { + + if (segment_size == 0) + first = &iov_vu[i + 1]; + + if (iov_vu[i + 1].iov_len > (size_t)len) + iov_vu[i + 1].iov_len = len; + + len -= iov_vu[i + 1].iov_len; + iov_used++; + + segment_size += iov_vu[i + 1].iov_len; + num_buffers++; + + if (segment_size >= mss || len == 0 || + i + 1 == iov_cnt || !has_mrg_rxbuf) { + char *base = (char *)first->iov_base - l2_hdrlen; + size_t size = first->iov_len + l2_hdrlen; + struct virtio_net_hdr_mrg_rxbuf *vh; + struct ethhdr *eh; + size_t l4len; + + vh = (struct virtio_net_hdr_mrg_rxbuf *)base; + + vh->hdr = vu_header; + if (has_mrg_rxbuf) + vh->num_buffers = htole16(num_buffers); + + l2_iov[TCP_IOV_TAP].iov_base = NULL; + l2_iov[TCP_IOV_TAP].iov_len = 0; + l2_iov[TCP_IOV_ETH].iov_base = base + vnet_hdrlen; + l2_iov[TCP_IOV_ETH].iov_len = sizeof(struct ethhdr); + + eh = l2_iov[TCP_IOV_ETH].iov_base; + + memcpy(eh->h_dest, c->mac_guest, sizeof(eh->h_dest)); + memcpy(eh->h_source, c->mac, sizeof(eh->h_source)); + + /* initialize header */ + if (v4) { + struct tcp_payload_t *payload; + struct iphdr *iph; + + l2_iov[TCP_IOV_IP].iov_base = (char *)l2_iov[TCP_IOV_ETH].iov_base + + l2_iov[TCP_IOV_ETH].iov_len; + l2_iov[TCP_IOV_IP].iov_len = sizeof(struct iphdr); + l2_iov[TCP_IOV_PAYLOAD].iov_base = (char *)l2_iov[TCP_IOV_IP].iov_base + + l2_iov[TCP_IOV_IP].iov_len; + + + eh->h_proto = htons(ETH_P_IP); + + iph = l2_iov[TCP_IOV_IP].iov_base; + *iph = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP); + payload = l2_iov[TCP_IOV_PAYLOAD].iov_base; + payload->th = (struct tcphdr){ + .doff = offsetof(struct tcp_payload_t, data) / 4, + .ack = 1 + }; + + l4len = tcp_l2_buf_fill_headers(c, conn, l2_iov, + segment_size, + len ? check : NULL, + conn->seq_to_tap); + l2_iov[TCP_IOV_PAYLOAD].iov_len = l4len; + + if (*c->pcap) { + struct in_addr saddr, daddr; + uint32_t sum; + + saddr.s_addr = iph->saddr; + daddr.s_addr = iph->daddr; + sum = proto_ipv4_header_psum(l4len, + IPPROTO_TCP, + saddr, daddr); + first->iov_base = &payload->th; + first->iov_len = size - l2_hdrlen + sizeof(struct tcphdr); + payload->th.check = 0; + payload->th.check = csum_iov(first, num_buffers, sum); + } + + check = &iph->check; + } else { + struct tcp_payload_t *payload; + struct ipv6hdr *ip6h; + + l2_iov[TCP_IOV_IP].iov_base = (char *)l2_iov[TCP_IOV_ETH].iov_base + + l2_iov[TCP_IOV_ETH].iov_len; + l2_iov[TCP_IOV_IP].iov_len = sizeof(struct ipv6hdr); + l2_iov[TCP_IOV_PAYLOAD].iov_base = (char *)l2_iov[TCP_IOV_IP].iov_base + + l2_iov[TCP_IOV_IP].iov_len; + + + eh->h_proto = htons(ETH_P_IPV6); + + ip6h = l2_iov[TCP_IOV_IP].iov_base; + *ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP); + + payload = l2_iov[TCP_IOV_PAYLOAD].iov_base; + payload->th = (struct tcphdr){ + .doff = offsetof(struct tcp_payload_t, data) / 4, + .ack = 1 + }; +; + l4len = tcp_l2_buf_fill_headers(c, conn, l2_iov, + segment_size, + NULL, conn->seq_to_tap); + l2_iov[TCP_IOV_PAYLOAD].iov_len = l4len; + + if (*c->pcap) { + uint32_t sum = proto_ipv6_header_psum(l4len, + IPPROTO_TCP, + &ip6h->saddr, + &ip6h->daddr); + + first->iov_base = &payload->th; + first->iov_len = size - l2_hdrlen + sizeof(struct tcphdr); + + payload->th.check = 0; + payload->th.check = csum_iov(first, num_buffers, sum); + } + } + + /* set iov for pcap logging */ + first->iov_base = eh; + first->iov_len = size - vnet_hdrlen; + + pcap_iov(first, num_buffers); + + /* set iov_len for vu_queue_fill_by_index(); */ + + first->iov_base = base; + first->iov_len = size; + + conn->seq_to_tap += segment_size; + + segment_size = 0; + num_buffers = 0; + } + } + + /* release unused buffers */ + vu_queue_rewind(vdev, vq, iov_cnt - iov_used); + + /* send packets */ + for (i = 0; i < iov_used; i++) + vu_queue_fill(vq, &elem[i], iov_vu[i + 1].iov_len, i); + + vu_queue_flush(vq, iov_used); + vu_queue_notify(vdev, vq); + + conn_flag(c, conn, ACK_FROM_TAP_DUE); + + return 0; +err: + vu_queue_rewind(vdev, vq, iov_cnt); + + if (errno != EAGAIN && errno != EWOULDBLOCK) { + ret = -errno; + tcp_rst(c, conn); + } + + return ret; +} diff --git a/tcp_vu.h b/tcp_vu.h new file mode 100644 index 000000000000..99daba5b34ed --- /dev/null +++ b/tcp_vu.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * Copyright Red Hat + * Author: Laurent Vivier + */ + +#ifndef TCP_VU_H +#define TCP_VU_H + +int tcp_vu_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags); +int tcp_vu_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn); + +#endif /*TCP_VU_H */ diff --git a/udp.c b/udp.c index e089ef952b8a..2560094d4c21 100644 --- a/udp.c +++ b/udp.c @@ -121,9 +121,7 @@ #include "tap.h" #include "pcap.h" #include "log.h" - -#define UDP_CONN_TIMEOUT 180 /* s, timeout for ephemeral or local bind */ -#define UDP_MAX_FRAMES 32 /* max # of frames to receive at once */ +#include "udp_internal.h" /** * struct udp_tap_port - Port tracking based on tap-facing source port @@ -171,20 +169,8 @@ static uint8_t udp_act[IP_VERSIONS][UDP_ACT_TYPE_MAX][DIV_ROUND_UP(NUM_PORTS, 8) /* Static buffers */ -/** - * struct udp_payload_t - UDP header and data for inbound messages - * @uh: UDP header - * @data: UDP data - */ -static struct udp_payload_t { - struct udphdr uh; - char data[USHRT_MAX - sizeof(struct udphdr)]; -#ifdef __AVX2__ -} __attribute__ ((packed, aligned(32))) -#else -} __attribute__ ((packed, aligned(__alignof__(unsigned int)))) -#endif -udp_payload[UDP_MAX_FRAMES]; +/* UDP header and data for inbound messages */ +static struct udp_payload_t udp_payload[UDP_MAX_FRAMES]; /* Ethernet header for IPv4 frames */ static struct ethhdr udp4_eth_hdr; @@ -241,11 +227,11 @@ static struct mmsghdr udp6_l2_mh_sock [UDP_MAX_FRAMES]; /* recvmmsg()/sendmmsg() data for "spliced" connections */ static struct iovec udp_iov_splice [UDP_MAX_FRAMES]; -static struct sockaddr_in udp4_localname = { +struct sockaddr_in udp4_localname = { .sin_family = AF_INET, .sin_addr = IN4ADDR_LOOPBACK_INIT, }; -static struct sockaddr_in6 udp6_localname = { +struct sockaddr_in6 udp6_localname = { .sin6_family = AF_INET6, .sin6_addr = IN6ADDR_LOOPBACK_INIT, }; @@ -594,11 +580,11 @@ out: * * Return: size of IPv4 payload (UDP header + data) */ -static size_t udp_update_hdr4(const struct ctx *c, - struct iphdr *ip4h, const struct sockaddr_in *s_in, - struct udp_payload_t *bp, - in_port_t dstport, size_t dlen, - const struct timespec *now) +size_t udp_update_hdr4(const struct ctx *c, + struct iphdr *ip4h, const struct sockaddr_in *s_in, + struct udp_payload_t *bp, + in_port_t dstport, size_t dlen, + const struct timespec *now) { const struct in_addr dst = c->ip4.addr_seen; in_port_t srcport = ntohs(s_in->sin_port); @@ -633,7 +619,10 @@ static size_t udp_update_hdr4(const struct ctx *c, bp->uh.source = s_in->sin_port; bp->uh.dest = htons(dstport); bp->uh.len = htons(l4len); - csum_udp4(&bp->uh, src, dst, bp->data, dlen); + if (c->mode != MODE_VU) + csum_udp4(&bp->uh, src, dst, bp->data, dlen); + else + bp->uh.check = 0; return l4len; } @@ -650,11 +639,11 @@ static size_t udp_update_hdr4(const struct ctx *c, * * Return: size of IPv6 payload (UDP header + data) */ -static size_t udp_update_hdr6(const struct ctx *c, - struct ipv6hdr *ip6h, struct sockaddr_in6 *s_in6, - struct udp_payload_t *bp, - in_port_t dstport, size_t dlen, - const struct timespec *now) +size_t udp_update_hdr6(const struct ctx *c, + struct ipv6hdr *ip6h, struct sockaddr_in6 *s_in6, + struct udp_payload_t *bp, + in_port_t dstport, size_t dlen, + const struct timespec *now) { const struct in6_addr *src = &s_in6->sin6_addr; const struct in6_addr *dst = &c->ip6.addr_seen; @@ -705,7 +694,10 @@ static size_t udp_update_hdr6(const struct ctx *c, bp->uh.source = s_in6->sin6_port; bp->uh.dest = htons(dstport); bp->uh.len = ip6h->payload_len; - csum_udp6(&bp->uh, src, dst, bp->data, dlen); + if (c->mode != MODE_VU) + csum_udp6(&bp->uh, src, dst, bp->data, dlen); + else + bp->uh.check = 0xffff; /* zero checksum is invalid with IPv6 */ return l4len; } diff --git a/udp_internal.h b/udp_internal.h new file mode 100644 index 000000000000..898d1e103cb8 --- /dev/null +++ b/udp_internal.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * Copyright (c) 2021 Red Hat GmbH + * Author: Stefano Brivio + */ + +#ifndef UDP_INTERNAL_H +#define UDP_INTERNAL_H + +#define UDP_CONN_TIMEOUT 180 /* s, timeout for ephemeral or local bind */ +#define UDP_MAX_FRAMES 32 /* max # of frames to receive at once */ + +extern struct sockaddr_in udp4_localname; +extern struct sockaddr_in6 udp6_localname; + +/** + * struct udp_payload_t - UDP header and data for inbound messages + * @uh: UDP header + * @data: UDP data + */ +struct udp_payload_t { + struct udphdr uh; + char data[USHRT_MAX - sizeof(struct udphdr)]; +#ifdef __AVX2__ +} __attribute__ ((packed, aligned(32))); +#else +} __attribute__ ((packed, aligned(__alignof__(unsigned int)))); +#endif + +size_t udp_update_hdr4(const struct ctx *c, + struct iphdr *ip4h, const struct sockaddr_in *s_in, + struct udp_payload_t *bp, + in_port_t dstport, size_t dlen, + const struct timespec *now); +size_t udp_update_hdr6(const struct ctx *c, + struct ipv6hdr *ip6h, struct sockaddr_in6 *s_in6, + struct udp_payload_t *bp, + in_port_t dstport, size_t dlen, + const struct timespec *now); +#endif /* UDP_INTERNAL_H */ diff --git a/udp_vu.c b/udp_vu.c new file mode 100644 index 000000000000..22b9fbf53807 --- /dev/null +++ b/udp_vu.c @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * Copyright Red Hat + * Author: Laurent Vivier + * + * udp_vu.c - UDP L2 vhost-user management functions + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "checksum.h" +#include "util.h" +#include "ip.h" +#include "passt.h" +#include "pcap.h" +#include "log.h" +#include "vhost_user.h" +#include "udp_internal.h" +#include "udp_vu.h" + +/* vhost-user */ +static const struct virtio_net_hdr vu_header = { + .flags = VIRTIO_NET_HDR_F_DATA_VALID, + .gso_type = VIRTIO_NET_HDR_GSO_NONE, +}; + +static struct iovec iov_vu [VIRTQUEUE_MAX_SIZE]; +static struct vu_virtq_element elem [VIRTQUEUE_MAX_SIZE]; +static struct iovec in_sg[VIRTQUEUE_MAX_SIZE]; +static int in_sg_count; + +void udp_vu_sock_handler(const struct ctx *c, union epoll_ref ref, + uint32_t events, const struct timespec *now) +{ + struct vu_dev *vdev = c->vdev; + struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE]; + bool has_mrg_rxbuf, v6 = ref.udp.v6; + in_port_t dstport = ref.udp.port; + size_t l2_hdrlen, vnet_hdrlen; + struct msghdr msg; + int i, virtqueue_max; + + if (c->no_udp || !(events & EPOLLIN)) + return; + + has_mrg_rxbuf = vu_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF); + if (has_mrg_rxbuf) { + vnet_hdrlen = sizeof(struct virtio_net_hdr_mrg_rxbuf); + virtqueue_max = VIRTQUEUE_MAX_SIZE; + } else { + vnet_hdrlen = sizeof(struct virtio_net_hdr); + virtqueue_max = 1; + } + l2_hdrlen = vnet_hdrlen + sizeof(struct ethhdr) + sizeof(struct udphdr); + + if (v6) { + l2_hdrlen += sizeof(struct ipv6hdr); + + udp6_localname.sin6_port = htons(dstport); + msg.msg_name = &udp6_localname; + msg.msg_namelen = sizeof(udp6_localname); + } else { + l2_hdrlen += sizeof(struct iphdr); + + udp4_localname.sin_port = htons(dstport); + msg.msg_name = &udp4_localname; + msg.msg_namelen = sizeof(udp4_localname); + } + + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + for (i = 0; i < UDP_MAX_FRAMES; i++) { + struct virtio_net_hdr_mrg_rxbuf *vh; + size_t size, fillsize, off; + int iov_cnt, iov_used, idx; + struct ethhdr *eh; + ssize_t data_len; + size_t l4len; + char *base; + + fillsize = USHRT_MAX; + iov_cnt = 0; + in_sg_count = 0; + while (fillsize && iov_cnt < virtqueue_max && + in_sg_count < ARRAY_SIZE(in_sg)) { + int ret; + + elem[iov_cnt].out_num = 0; + elem[iov_cnt].out_sg = NULL; + elem[iov_cnt].in_num = ARRAY_SIZE(in_sg) - in_sg_count; + elem[iov_cnt].in_sg = &in_sg[in_sg_count]; + ret = vu_queue_pop(vdev, vq, &elem[iov_cnt]); + if (ret < 0) + break; + in_sg_count += elem[iov_cnt].in_num; + + if (elem[iov_cnt].in_num < 1) { + err("virtio-net receive queue contains no in buffers"); + vu_queue_rewind(vdev, vq, iov_cnt); + return; + } + ASSERT(elem[iov_cnt].in_num == 1); + ASSERT(elem[iov_cnt].in_sg[0].iov_len >= l2_hdrlen); + + if (iov_cnt == 0) { + base = elem[iov_cnt].in_sg[0].iov_base; + size = elem[iov_cnt].in_sg[0].iov_len; + + /* keep space for the headers */ + iov_vu[0].iov_base = base + l2_hdrlen; + iov_vu[0].iov_len = size - l2_hdrlen; + } else { + iov_vu[iov_cnt].iov_base = elem[iov_cnt].in_sg[0].iov_base; + iov_vu[iov_cnt].iov_len = elem[iov_cnt].in_sg[0].iov_len; + } + + if (iov_vu[iov_cnt].iov_len > fillsize) + iov_vu[iov_cnt].iov_len = fillsize; + + fillsize -= iov_vu[iov_cnt].iov_len; + + iov_cnt++; + } + if (iov_cnt == 0) + break; + + msg.msg_iov = iov_vu; + msg.msg_iovlen = iov_cnt; + + data_len = recvmsg(ref.fd, &msg, 0); + if (data_len < 0) { + vu_queue_rewind(vdev, vq, iov_cnt); + return; + } + + /* restore original values */ + iov_vu[0].iov_base = base; + iov_vu[0].iov_len = size; + + /* count the numbers of buffer filled by recvmsg() */ + idx = iov_skip_bytes(iov_vu, iov_cnt, l2_hdrlen + data_len, + &off); + /* adjust last iov length */ + if (idx < iov_cnt) + iov_vu[idx].iov_len = off; + iov_used = idx + !!off; + if (idx == 0) + size = iov_vu[0].iov_len; + + /* release unused buffers */ + vu_queue_rewind(vdev, vq, iov_cnt - iov_used); + + /* vnet_header */ + vh = (struct virtio_net_hdr_mrg_rxbuf *)base; + vh->hdr = vu_header; + if (has_mrg_rxbuf) + vh->num_buffers = htole16(iov_used); + + /* ethernet header */ + eh = (struct ethhdr *)(base + vnet_hdrlen); + + memcpy(eh->h_dest, c->mac_guest, sizeof(eh->h_dest)); + memcpy(eh->h_source, c->mac, sizeof(eh->h_source)); + + /* initialize header */ + if (v6) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(eh + 1); + struct udp_payload_t *bp = (struct udp_payload_t *)(ip6h + 1); + + eh->h_proto = htons(ETH_P_IPV6); + + *ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_UDP); + + l4len = udp_update_hdr6(c, ip6h, &udp6_localname, bp, + dstport, data_len, now); + if (*c->pcap) { + uint32_t sum; + + sum = proto_ipv6_header_psum(l4len, IPPROTO_UDP, + &ip6h->saddr, + &ip6h->daddr); + + iov_vu[0].iov_base = &bp->uh; + iov_vu[0].iov_len = size - l2_hdrlen + + sizeof(bp->uh); + bp->uh.check = 0; /* by default, set to 0xffff */ + bp->uh.check = csum_iov(iov_vu, iov_used, sum); + } + } else { + struct iphdr *iph = (struct iphdr *)(eh + 1); + struct udp_payload_t *bp = (struct udp_payload_t *)(iph + 1); + + eh->h_proto = htons(ETH_P_IP); + + *iph = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_UDP); + + l4len = udp_update_hdr4(c, iph, &udp4_localname, bp, + dstport, data_len, now); + if (*c->pcap) { + uint32_t sum; + + sum = proto_ipv4_header_psum(l4len, IPPROTO_UDP, + /* cppcheck-suppress unknownEvaluationOrder */ + (struct in_addr){ .s_addr = iph->saddr }, + (struct in_addr){ .s_addr = iph->daddr }); + + iov_vu[0].iov_base = &bp->uh; + iov_vu[0].iov_len = size - l2_hdrlen + + sizeof(bp->uh); + bp->uh.check = csum_iov(iov_vu, iov_used, sum); + } + } + + /* set iov for pcap logging */ + iov_vu[0].iov_base = base + vnet_hdrlen; + iov_vu[0].iov_len = size - vnet_hdrlen; + pcap_iov(iov_vu, iov_used); + + /* set iov_len for vu_queue_fill_by_index(); */ + iov_vu[0].iov_base = base; + iov_vu[0].iov_len = size; + + /* send packets */ + for (i = 0; i < iov_used; i++) + vu_queue_fill(vq, &elem[i], iov_vu[i].iov_len, i); + + vu_queue_flush(vq, iov_used); + vu_queue_notify(vdev, vq); + } +} diff --git a/udp_vu.h b/udp_vu.h new file mode 100644 index 000000000000..d402980c21c1 --- /dev/null +++ b/udp_vu.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * Copyright Red Hat + * Author: Laurent Vivier + */ + +#ifndef UDP_VU_H +#define UDP_VU_H + +void udp_vu_sock_handler(const struct ctx *c, union epoll_ref ref, + uint32_t events, const struct timespec *now); +#endif /* UDP_VU_H */ diff --git a/vhost_user.c b/vhost_user.c index 23ec4326995d..496d9c1088ad 100644 --- a/vhost_user.c +++ b/vhost_user.c @@ -38,7 +38,6 @@ * this is part of the vhost-user backend * convention. */ -/* cppcheck-suppress unusedFunction */ void vu_print_capabilities(void) { printf("{\n"); @@ -149,8 +148,7 @@ static void vmsg_close_fds(const struct vhost_user_msg *vmsg) */ static void vu_remove_watch(const struct vu_dev *vdev, int fd) { - (void)vdev; - (void)fd; + epoll_ctl(vdev->context->epollfd, EPOLL_CTL_DEL, fd, NULL); } /** @@ -412,7 +410,6 @@ static bool map_ring(struct vu_dev *vdev, struct vu_virtq *vq) * * Return: 0 if the zone in a mapped memory region, -1 otherwise */ -/* cppcheck-suppress unusedFunction */ int vu_packet_check_range(void *buf, size_t offset, size_t len, const char *start) { @@ -503,6 +500,14 @@ static bool vu_set_mem_table_exec(struct vu_dev *vdev, } } + /* As vu_packet_check_range() has no access to the number of + * memory regions, mark the end of the array with mmap_addr = 0 + */ + ASSERT(vdev->nregions < VHOST_USER_MAX_RAM_SLOTS - 1); + vdev->regions[vdev->nregions].mmap_addr = 0; + + tap_sock_update_buf(vdev->regions, 0); + return false; } @@ -623,8 +628,12 @@ static bool vu_get_vring_base_exec(struct vu_dev *vdev, */ static void vu_set_watch(const struct vu_dev *vdev, int fd) { - (void)vdev; - (void)fd; + union epoll_ref ref = { .type = EPOLL_TYPE_VHOST_KICK, .fd = fd }; + struct epoll_event ev = { 0 }; + + ev.data.u64 = ref.u64; + ev.events = EPOLLIN; + epoll_ctl(vdev->context->epollfd, EPOLL_CTL_ADD, fd, &ev); } /** @@ -660,7 +669,6 @@ static int vu_wait_queue(const struct vu_virtq *vq) * * Return: number of bytes sent, -1 if there is an error */ -/* cppcheck-suppress unusedFunction */ int vu_send(struct vu_dev *vdev, const void *buf, size_t size) { size_t hdrlen = vdev->hdrlen; @@ -854,7 +862,6 @@ static void vu_handle_tx(struct vu_dev *vdev, int index) * @vdev: vhost-user device * @ref: epoll reference information */ -/* cppcheck-suppress unusedFunction */ void vu_kick_cb(struct vu_dev *vdev, union epoll_ref ref) { eventfd_t kick_data; @@ -1097,11 +1104,11 @@ static bool vu_set_vring_enable_exec(struct vu_dev *vdev, * @c: execution context * @vdev: vhost-user device */ -/* cppcheck-suppress unusedFunction */ void vu_init(struct ctx *c, struct vu_dev *vdev) { int i; + c->vdev = vdev; vdev->context = c; vdev->hdrlen = 0; for (i = 0; i < VHOST_USER_MAX_QUEUES; i++) @@ -1164,7 +1171,7 @@ void vu_cleanup(struct vu_dev *vdev) */ static void vu_sock_reset(struct vu_dev *vdev) { - (void)vdev; + tap_sock_reset(vdev->context); } /** @@ -1173,7 +1180,6 @@ static void vu_sock_reset(struct vu_dev *vdev) * @fd: vhost-user message socket * @events: epoll events */ -/* cppcheck-suppress unusedFunction */ void tap_handler_vu(struct vu_dev *vdev, int fd, uint32_t events) { struct vhost_user_msg msg = { 0 }; diff --git a/virtio.c b/virtio.c index d712f30cc33d..9e6e79382e2c 100644 --- a/virtio.c +++ b/virtio.c @@ -507,7 +507,6 @@ void vu_queue_unpop(struct vu_dev *dev, struct vu_virtq *vq, unsigned int index, * @vq: Virtqueue * @num: Number of element to unpop */ -/* cppcheck-suppress unusedFunction */ bool vu_queue_rewind(struct vu_dev *dev, struct vu_virtq *vq, unsigned int num) { (void)dev; -- 2.45.2