public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
blob 41235101b69eef7efa5ad75c161421d4e5848242 8685 bytes (raw)

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
 
// SPDX-License-Identifier: GPL-2.0-or-later
/* udp_vu.c - UDP L2 vhost-user management functions
 *
 * Copyright Red Hat
 * Author: Laurent Vivier <lvivier@redhat.com>
 */

#include <unistd.h>
#include <assert.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <netinet/in.h>
#include <netinet/ip.h>
#include <netinet/udp.h>
#include <stdint.h>
#include <stddef.h>
#include <sys/uio.h>
#include <linux/virtio_net.h>

#include "checksum.h"
#include "util.h"
#include "ip.h"
#include "siphash.h"
#include "inany.h"
#include "passt.h"
#include "pcap.h"
#include "log.h"
#include "vhost_user.h"
#include "udp_internal.h"
#include "flow.h"
#include "flow_table.h"
#include "udp_flow.h"
#include "udp_vu.h"
#include "vu_common.h"

static struct iovec     iov_vu		[VIRTQUEUE_MAX_SIZE];
static struct vu_virtq_element	elem		[VIRTQUEUE_MAX_SIZE];

/**
 * udp_vu_hdrlen() - return the size of the header in level 2 frame (UDP)
 * @v6:		Set for IPv6 packet
 *
 * Return: Return the size of the header
 */
static size_t udp_vu_hdrlen(bool v6)
{
	size_t hdrlen;

	hdrlen = sizeof(struct virtio_net_hdr_mrg_rxbuf) +
		 sizeof(struct ethhdr) + sizeof(struct udphdr);

	if (v6)
		hdrlen += sizeof(struct ipv6hdr);
	else
		hdrlen += sizeof(struct iphdr);

	return hdrlen;
}

/**
 * udp_vu_sock_info() - get socket information
 * @s:		Socket to get information from
 * @s_in:	Socket address (output)
 *
 * Return: 0 if socket address can be read, -1 otherwise
 */
static int udp_vu_sock_info(int s, union sockaddr_inany *s_in)
{
	struct msghdr msg = {
		.msg_name = s_in,
		.msg_namelen = sizeof(union sockaddr_inany),
	};

	return recvmsg(s, &msg, MSG_PEEK | MSG_DONTWAIT);
}

/**
 * udp_vu_sock_recv() - Receive datagrams from socket into vhost-user buffers
 * @c:		Execution context
 * @s:		Socket to receive from
 * @events:	epoll events bitmap
 * @v6:		Set for IPv6 connections
 * @dlen:	Size of received data (output)
 *
 * Return: Number of iov entries used to store the datagram
 */
static int udp_vu_sock_recv(const struct ctx *c, int s, uint32_t events,
			    bool v6, ssize_t *dlen)
{
	struct vu_dev *vdev = c->vdev;
	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
	int iov_cnt, idx, iov_used;
	struct msghdr msg  = { 0 };
	size_t off, hdrlen;

	ASSERT(!c->no_udp);

	if (!(events & EPOLLIN))
		return 0;

	/* compute L2 header length */
	hdrlen = udp_vu_hdrlen(v6);

	vu_init_elem(elem, iov_vu, VIRTQUEUE_MAX_SIZE);

	iov_cnt = vu_collect(vdev, vq, elem, VIRTQUEUE_MAX_SIZE,
			     IP_MAX_MTU + ETH_HLEN +
			     sizeof(struct virtio_net_hdr_mrg_rxbuf),
			     NULL);
	if (iov_cnt == 0)
		return 0;

	/* reserve space for the headers */
	ASSERT(iov_vu[0].iov_len >= hdrlen);
	iov_vu[0].iov_base = (char *)iov_vu[0].iov_base + hdrlen;
	iov_vu[0].iov_len -= hdrlen;

	/* read data from the socket */
	msg.msg_iov = iov_vu;
	msg.msg_iovlen = iov_cnt;

	*dlen = recvmsg(s, &msg, 0);
	if (*dlen < 0) {
		vu_queue_rewind(vq, iov_cnt);
		return 0;
	}

	/* restore the pointer to the headers address */
	iov_vu[0].iov_base = (char *)iov_vu[0].iov_base - hdrlen;
	iov_vu[0].iov_len += hdrlen;

	/* count the numbers of buffer filled by recvmsg() */
	idx = iov_skip_bytes(iov_vu, iov_cnt, *dlen + hdrlen, &off);

	/* adjust last iov length */
	if (idx < iov_cnt)
		iov_vu[idx].iov_len = off;
	iov_used = idx + !!off;

	vu_set_vnethdr(vdev, iov_vu[0].iov_base, iov_used);

	/* release unused buffers */
	vu_queue_rewind(vq, iov_cnt - iov_used);

	return iov_used;
}

/**
 * udp_vu_prepare() - Prepare the packet header
 * @c:		Execution context
 * @toside:	Address information for one side of the flow
 * @dlen:	Packet data length
 *
 * Return: Layer-4 length
 */
static size_t udp_vu_prepare(const struct ctx *c,
			     const struct flowside *toside, ssize_t dlen)
{
	struct ethhdr *eh;
	size_t l4len;

	/* ethernet header */
	eh = vu_eth(iov_vu[0].iov_base);

	memcpy(eh->h_dest, c->guest_mac, sizeof(eh->h_dest));
	memcpy(eh->h_source, c->our_tap_mac, sizeof(eh->h_source));

	/* initialize header */
	if (inany_v4(&toside->eaddr) && inany_v4(&toside->oaddr)) {
		struct iphdr *iph = vu_ip(iov_vu[0].iov_base);
		struct udp_payload_t *bp = vu_payloadv4(iov_vu[0].iov_base);

		eh->h_proto = htons(ETH_P_IP);

		*iph = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_UDP);

		l4len = udp_update_hdr4(iph, bp, toside, dlen, true);
	} else {
		struct ipv6hdr *ip6h = vu_ip(iov_vu[0].iov_base);
		struct udp_payload_t *bp = vu_payloadv6(iov_vu[0].iov_base);

		eh->h_proto = htons(ETH_P_IPV6);

		*ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_UDP);

		l4len = udp_update_hdr6(ip6h, bp, toside, dlen, true);
	}

	return l4len;
}

/**
 * udp_vu_csum() - Calculate and set checksum for a UDP packet
 * @toside:	Address information for one side of the flow
 * @iov_used:	Number of used iov_vu items
 */
static void udp_vu_csum(const struct flowside *toside, int iov_used)
{
	const struct in_addr *src4 = inany_v4(&toside->oaddr);
	const struct in_addr *dst4 = inany_v4(&toside->eaddr);
	char *base = iov_vu[0].iov_base;
	struct udp_payload_t *bp;
	struct iov_tail data;

	if (src4 && dst4) {
		bp = vu_payloadv4(base);
		data = IOV_TAIL(iov_vu, iov_used, (char *)&bp->data - base);
		csum_udp4(&bp->uh, *src4, *dst4, &data);
	} else {
		bp = vu_payloadv6(base);
		data = IOV_TAIL(iov_vu, iov_used, (char *)&bp->data - base);
		csum_udp6(&bp->uh, &toside->oaddr.a6, &toside->eaddr.a6, &data);
	}
}

/**
 * udp_vu_listen_sock_handler() - Handle new data from socket
 * @c:		Execution context
 * @ref:	epoll reference
 * @events:	epoll events bitmap
 * @now:	Current timestamp
 */
void udp_vu_listen_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];
	int i;

	if (udp_sock_errs(c, ref.fd, events) < 0) {
		err("UDP: Unrecoverable error on listening socket:"
		    " (%s port %hu)", pif_name(ref.udp.pif), ref.udp.port);
		return;
	}

	for (i = 0; i < UDP_MAX_FRAMES; i++) {
		const struct flowside *toside;
		union sockaddr_inany s_in;
		flow_sidx_t sidx;
		uint8_t pif;
		ssize_t dlen;
		int iov_used;
		bool v6;

		if (udp_vu_sock_info(ref.fd, &s_in) < 0)
			break;

		sidx = udp_flow_from_sock(c, ref, &s_in, now);
		pif = pif_at_sidx(sidx);

		if (pif != PIF_TAP) {
			if (flow_sidx_valid(sidx)) {
				flow_sidx_t fromsidx = flow_sidx_opposite(sidx);
				struct udp_flow *uflow = udp_at_sidx(sidx);

				flow_err(uflow,
					"No support for forwarding UDP from %s to %s",
					pif_name(pif_at_sidx(fromsidx)),
					pif_name(pif));
			} else {
				debug("Discarding 1 datagram without flow");
			}

			continue;
		}

		toside = flowside_at_sidx(sidx);

		v6 = !(inany_v4(&toside->eaddr) && inany_v4(&toside->oaddr));

		iov_used = udp_vu_sock_recv(c, ref.fd, events, v6, &dlen);
		if (iov_used <= 0)
			break;

		udp_vu_prepare(c, toside, dlen);
		if (*c->pcap) {
			udp_vu_csum(toside, iov_used);
			pcap_iov(iov_vu, iov_used,
				 sizeof(struct virtio_net_hdr_mrg_rxbuf));
		}
		vu_flush(vdev, vq, elem, iov_used);
	}
}

/**
 * udp_vu_reply_sock_handler() - Handle new data from flow specific socket
 * @c:		Execution context
 * @ref:	epoll reference
 * @events:	epoll events bitmap
 * @now:	Current timestamp
 */
void udp_vu_reply_sock_handler(const struct ctx *c, union epoll_ref ref,
			        uint32_t events, const struct timespec *now)
{
	flow_sidx_t tosidx = flow_sidx_opposite(ref.flowside);
	const struct flowside *toside = flowside_at_sidx(tosidx);
	struct udp_flow *uflow = udp_at_sidx(ref.flowside);
	int from_s = uflow->s[ref.flowside.sidei];
	struct vu_dev *vdev = c->vdev;
	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
	int i;

	ASSERT(!c->no_udp);

	if (udp_sock_errs(c, from_s, events) < 0) {
		flow_err(uflow, "Unrecoverable error on reply socket");
		flow_err_details(uflow);
		udp_flow_close(c, uflow);
		return;
	}

	for (i = 0; i < UDP_MAX_FRAMES; i++) {
		uint8_t topif = pif_at_sidx(tosidx);
		ssize_t dlen;
		int iov_used;
		bool v6;

		ASSERT(uflow);

		if (topif != PIF_TAP) {
			uint8_t frompif = pif_at_sidx(ref.flowside);

			flow_err(uflow,
				 "No support for forwarding UDP from %s to %s",
				 pif_name(frompif), pif_name(topif));
			continue;
		}

		v6 = !(inany_v4(&toside->eaddr) && inany_v4(&toside->oaddr));

		iov_used = udp_vu_sock_recv(c, from_s, events, v6, &dlen);
		if (iov_used <= 0)
			break;
		flow_trace(uflow, "Received 1 datagram on reply socket");
		uflow->ts = now->tv_sec;

		udp_vu_prepare(c, toside, dlen);
		if (*c->pcap) {
			udp_vu_csum(toside, iov_used);
			pcap_iov(iov_vu, iov_used,
				 sizeof(struct virtio_net_hdr_mrg_rxbuf));
		}
		vu_flush(vdev, vq, elem, iov_used);
	}
}

debug log:

solving 41235101b69e ...
found 41235101b69e in https://passt.top/passt

Code repositories for project(s) associated with this public inbox

	https://passt.top/passt

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 IMAP folder(s).