public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
blob f9e7afcf4ddb5974dd263ff6da2978f76b5524aa 8622 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
 
/* SPDX-License-Identifier: GPL-2.0-or-later
 * Copyright Red Hat
 * Author: Laurent Vivier <lvivier@redhat.com>
 *
 * udp_vu.c - UDP L2 vhost-user management functions
 */

#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"

/* 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;

static size_t udp_vu_l2_hdrlen(const struct vu_dev *vdev, bool v6)
{
	size_t l2_hdrlen;

	l2_hdrlen = vdev->hdrlen + sizeof(struct ethhdr) +
		    sizeof(struct udphdr);

	if (v6)
		l2_hdrlen += sizeof(struct ipv6hdr);
	else
		l2_hdrlen += sizeof(struct iphdr);

	return l2_hdrlen;
}

static int udp_vu_sock_recv(const struct ctx *c, union sockaddr_inany *s_in,
			    int s, uint32_t events, bool v6, ssize_t *data_len)
{
	struct vu_dev *vdev = c->vdev;
	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
	int virtqueue_max, iov_cnt, idx, iov_used;
	size_t fillsize, size, off, l2_hdrlen;
	struct virtio_net_hdr_mrg_rxbuf *vh;
	struct msghdr msg  = { 0 };
	char *base;

	ASSERT(!c->no_udp);

	/* Clear any errors first */
	if (events & EPOLLERR) {
		while (udp_sock_recverr(s))
			;
	}

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

	/* compute L2 header length */

	if (vu_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
		virtqueue_max = VIRTQUEUE_MAX_SIZE;
	else
		virtqueue_max = 1;

	l2_hdrlen = udp_vu_l2_hdrlen(vdev, v6);

	msg.msg_name = s_in;
	msg.msg_namelen = sizeof(union sockaddr_inany);

	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(vq, iov_cnt);
			return 0;
		}
		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)
		return 0;

	msg.msg_iov = iov_vu;
	msg.msg_iovlen = iov_cnt;

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

	/* 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;

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

	vh = (struct virtio_net_hdr_mrg_rxbuf *)base;
	vh->hdr = vu_header;
	if (vdev->hdrlen == sizeof(struct virtio_net_hdr_mrg_rxbuf))
		vh->num_buffers = htole16(iov_used);

	return iov_used;
}

static size_t udp_vu_prepare(const struct ctx *c,
			     const struct flowside *toside, ssize_t data_len)
{
	const struct vu_dev *vdev = c->vdev;
	struct ethhdr *eh;
	size_t l4len;

	/* ethernet header */
	eh = vu_eth(vdev, iov_vu[0].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 (inany_v4(&toside->eaddr) && inany_v4(&toside->faddr)) {
		struct iphdr *iph = vu_ip(vdev, iov_vu[0].iov_base);
		struct udp_payload_t *bp = vu_payloadv4(vdev,
							    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(c, iph, bp, toside, data_len);
	} else {
		struct ipv6hdr *ip6h = vu_ip(vdev, iov_vu[0].iov_base);
		struct udp_payload_t *bp = vu_payloadv6(vdev,
							    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(c, ip6h, bp, toside, data_len);
	}

	return l4len;
}

static void udp_vu_pcap(const struct ctx *c, const struct flowside *toside,
			size_t l4len, int iov_used)
{
	const struct in_addr *src = inany_v4(&toside->faddr);
	const struct in_addr *dst = inany_v4(&toside->eaddr);
	const struct vu_dev *vdev = c->vdev;
	char *base = iov_vu[0].iov_base;
	size_t size = iov_vu[0].iov_len;
	struct udp_payload_t *bp;
	uint32_t sum;

	if (!*c->pcap)
		return;

	if (src && dst) {
		bp = vu_payloadv4(vdev, base);
		sum = proto_ipv4_header_psum(l4len, IPPROTO_UDP, *src, *dst);
	} else {
		bp = vu_payloadv6(vdev, base);
		sum = proto_ipv6_header_psum(l4len, IPPROTO_UDP,
					     &toside->faddr.a6,
					     &toside->eaddr.a6);
		bp->uh.check = 0; /* by default, set to 0xffff */
	}

	iov_vu[0].iov_base = &bp->uh;
	iov_vu[0].iov_len = size - ((char *)iov_vu[0].iov_base - base);

	bp->uh.check = csum_iov(iov_vu, iov_used, sum);

	/* set iov for pcap logging */
	iov_vu[0].iov_base = base + vdev->hdrlen;
	iov_vu[0].iov_len = size - vdev->hdrlen;
	pcap_iov(iov_vu, iov_used);

	/* restore iov_vu[0] */
	iov_vu[0].iov_base = base;
	iov_vu[0].iov_len = size;
}

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];
	bool v6 = ref.udp.v6;
	int i;

	for (i = 0; i < UDP_MAX_FRAMES; i++) {
		union sockaddr_inany s_in;
		flow_sidx_t batchsidx;
		uint8_t batchpif;
		ssize_t data_len;
		int iov_used;

		iov_used = udp_vu_sock_recv(c, &s_in, ref.fd,
					    events, v6, &data_len);
		if (iov_used <= 0)
			return;

		batchsidx = udp_flow_from_sock(c, ref, &s_in, now);
		batchpif = pif_at_sidx(batchsidx);

		if (batchpif == PIF_TAP) {
			size_t l4len;

			l4len = udp_vu_prepare(c, flowside_at_sidx(batchsidx),
					       data_len);
			udp_vu_pcap(c, flowside_at_sidx(batchsidx), l4len,
				    iov_used);
			vu_send_frame(vdev, vq, elem, iov_vu, iov_used);
		} else if (flow_sidx_valid(batchsidx)) {
			flow_sidx_t fromsidx = flow_sidx_opposite(batchsidx);
			struct udp_flow *uflow = udp_at_sidx(batchsidx);

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

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 vu_dev *vdev = c->vdev;
	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
	struct udp_flow *uflow = udp_at_sidx(ref.flowside);
	uint8_t topif = pif_at_sidx(tosidx);
	bool v6 = ref.udp.v6;
	int i;

	ASSERT(!c->no_udp && uflow);

	for (i = 0; i < UDP_MAX_FRAMES; i++) {
		union sockaddr_inany s_in;
		ssize_t data_len;
		int iov_used;

		iov_used = udp_vu_sock_recv(c, &s_in, ref.fd,
					    events, v6, &data_len);
		if (iov_used <= 0)
			return;
		flow_trace(uflow, "Received 1 datagram on reply socket");
		uflow->ts = now->tv_sec;

		if (topif == PIF_TAP) {
			size_t l4len;

			l4len = udp_vu_prepare(c, toside, data_len);
			udp_vu_pcap(c, toside, l4len, iov_used);
			vu_send_frame(vdev, vq, elem, iov_vu, iov_used);
		} else {
			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));
		}
	}
}

debug log:

solving f9e7afcf4ddb ...
found f9e7afcf4ddb in https://archives.passt.top/passt-dev/20240815155024.827956-5-lvivier@redhat.com/

applying [1/1] https://archives.passt.top/passt-dev/20240815155024.827956-5-lvivier@redhat.com/
diff --git a/udp_vu.c b/udp_vu.c
new file mode 100644
index 000000000000..f9e7afcf4ddb

Checking patch udp_vu.c...
Applied patch udp_vu.c cleanly.

index at:
100644 f9e7afcf4ddb5974dd263ff6da2978f76b5524aa	udp_vu.c

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).