DPDK logo

Elixir Cross Referencer

  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
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2014 Intel Corporation
 */

#ifndef _VHOST_NET_CDEV_H_
#define _VHOST_NET_CDEV_H_
#include <stdint.h>
#include <stdio.h>
#include <sys/types.h>
#include <sys/queue.h>
#include <unistd.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h>
#include <sys/socket.h>
#include <linux/if.h>

#include <rte_log.h>
#include <rte_ether.h>
#include <rte_rwlock.h>

#include "rte_vhost.h"

/* Used to indicate that the device is running on a data core */
#define VIRTIO_DEV_RUNNING 1
/* Used to indicate that the device is ready to operate */
#define VIRTIO_DEV_READY 2
/* Used to indicate that the built-in vhost net device backend is enabled */
#define VIRTIO_DEV_BUILTIN_VIRTIO_NET 4

/* Backend value set by guest. */
#define VIRTIO_DEV_STOPPED -1

#define BUF_VECTOR_MAX 256

/**
 * Structure contains buffer address, length and descriptor index
 * from vring to do scatter RX.
 */
struct buf_vector {
	uint64_t buf_addr;
	uint32_t buf_len;
	uint32_t desc_idx;
};

/*
 * A structure to hold some fields needed in zero copy code path,
 * mainly for associating an mbuf with the right desc_idx.
 */
struct zcopy_mbuf {
	struct rte_mbuf *mbuf;
	uint32_t desc_idx;
	uint16_t in_use;

	TAILQ_ENTRY(zcopy_mbuf) next;
};
TAILQ_HEAD(zcopy_mbuf_list, zcopy_mbuf);

/*
 * Structure contains the info for each batched memory copy.
 */
struct batch_copy_elem {
	void *dst;
	void *src;
	uint32_t len;
	uint64_t log_addr;
};

/**
 * Structure contains variables relevant to RX/TX virtqueues.
 */
struct vhost_virtqueue {
	struct vring_desc	*desc;
	struct vring_avail	*avail;
	struct vring_used	*used;
	uint32_t		size;

	uint16_t		last_avail_idx;
	uint16_t		last_used_idx;
	/* Last used index we notify to front end. */
	uint16_t		signalled_used;
#define VIRTIO_INVALID_EVENTFD		(-1)
#define VIRTIO_UNINITIALIZED_EVENTFD	(-2)

	/* Backend value to determine if device should started/stopped */
	int			backend;
	int			enabled;
	int			access_ok;
	rte_spinlock_t		access_lock;

	/* Used to notify the guest (trigger interrupt) */
	int			callfd;
	/* Currently unused as polling mode is enabled */
	int			kickfd;

	/* Physical address of used ring, for logging */
	uint64_t		log_guest_addr;

	uint16_t		nr_zmbuf;
	uint16_t		zmbuf_size;
	uint16_t		last_zmbuf_idx;
	struct zcopy_mbuf	*zmbufs;
	struct zcopy_mbuf_list	zmbuf_list;

	struct vring_used_elem  *shadow_used_ring;
	uint16_t                shadow_used_idx;
	struct vhost_vring_addr ring_addrs;

	struct batch_copy_elem	*batch_copy_elems;
	uint16_t		batch_copy_nb_elems;

	rte_rwlock_t	iotlb_lock;
	rte_rwlock_t	iotlb_pending_lock;
	struct rte_mempool *iotlb_pool;
	TAILQ_HEAD(, vhost_iotlb_entry) iotlb_list;
	int				iotlb_cache_nr;
	TAILQ_HEAD(, vhost_iotlb_entry) iotlb_pending_list;
} __rte_cache_aligned;

/* Old kernels have no such macros defined */
#ifndef VIRTIO_NET_F_GUEST_ANNOUNCE
 #define VIRTIO_NET_F_GUEST_ANNOUNCE 21
#endif

#ifndef VIRTIO_NET_F_MQ
 #define VIRTIO_NET_F_MQ		22
#endif

#define VHOST_MAX_VRING			0x100
#define VHOST_MAX_QUEUE_PAIRS		0x80

#ifndef VIRTIO_NET_F_MTU
 #define VIRTIO_NET_F_MTU 3
#endif

#ifndef VIRTIO_F_ANY_LAYOUT
 #define VIRTIO_F_ANY_LAYOUT		27
#endif

/* Declare IOMMU related bits for older kernels */
#ifndef VIRTIO_F_IOMMU_PLATFORM

#define VIRTIO_F_IOMMU_PLATFORM 33

struct vhost_iotlb_msg {
	__u64 iova;
	__u64 size;
	__u64 uaddr;
#define VHOST_ACCESS_RO      0x1
#define VHOST_ACCESS_WO      0x2
#define VHOST_ACCESS_RW      0x3
	__u8 perm;
#define VHOST_IOTLB_MISS           1
#define VHOST_IOTLB_UPDATE         2
#define VHOST_IOTLB_INVALIDATE     3
#define VHOST_IOTLB_ACCESS_FAIL    4
	__u8 type;
};

#define VHOST_IOTLB_MSG 0x1

struct vhost_msg {
	int type;
	union {
		struct vhost_iotlb_msg iotlb;
		__u8 padding[64];
	};
};
#endif

/*
 * Define virtio 1.0 for older kernels
 */
#ifndef VIRTIO_F_VERSION_1
 #define VIRTIO_F_VERSION_1 32
#endif

#define VHOST_USER_F_PROTOCOL_FEATURES	30

/* Features supported by this builtin vhost-user net driver. */
#define VIRTIO_NET_SUPPORTED_FEATURES ((1ULL << VIRTIO_NET_F_MRG_RXBUF) | \
				(1ULL << VIRTIO_F_ANY_LAYOUT) | \
				(1ULL << VIRTIO_NET_F_CTRL_VQ) | \
				(1ULL << VIRTIO_NET_F_CTRL_RX) | \
				(1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE) | \
				(1ULL << VIRTIO_NET_F_MQ)      | \
				(1ULL << VIRTIO_F_VERSION_1)   | \
				(1ULL << VHOST_F_LOG_ALL)      | \
				(1ULL << VHOST_USER_F_PROTOCOL_FEATURES) | \
				(1ULL << VIRTIO_NET_F_GSO) | \
				(1ULL << VIRTIO_NET_F_HOST_TSO4) | \
				(1ULL << VIRTIO_NET_F_HOST_TSO6) | \
				(1ULL << VIRTIO_NET_F_HOST_UFO) | \
				(1ULL << VIRTIO_NET_F_HOST_ECN) | \
				(1ULL << VIRTIO_NET_F_CSUM)    | \
				(1ULL << VIRTIO_NET_F_GUEST_CSUM) | \
				(1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
				(1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
				(1ULL << VIRTIO_NET_F_GUEST_UFO) | \
				(1ULL << VIRTIO_NET_F_GUEST_ECN) | \
				(1ULL << VIRTIO_RING_F_INDIRECT_DESC) | \
				(1ULL << VIRTIO_RING_F_EVENT_IDX) | \
				(1ULL << VIRTIO_NET_F_MTU) | \
				(1ULL << VIRTIO_F_IOMMU_PLATFORM))


struct guest_page {
	uint64_t guest_phys_addr;
	uint64_t host_phys_addr;
	uint64_t size;
};

/**
 * Device structure contains all configuration information relating
 * to the device.
 */
struct virtio_net {
	/* Frontend (QEMU) memory and memory region information */
	struct rte_vhost_memory	*mem;
	uint64_t		features;
	uint64_t		protocol_features;
	int			vid;
	uint32_t		flags;
	uint16_t		vhost_hlen;
	/* to tell if we need broadcast rarp packet */
	rte_atomic16_t		broadcast_rarp;
	uint32_t		nr_vring;
	int			dequeue_zero_copy;
	struct vhost_virtqueue	*virtqueue[VHOST_MAX_QUEUE_PAIRS * 2];
#define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ)
	char			ifname[IF_NAME_SZ];
	uint64_t		log_size;
	uint64_t		log_base;
	uint64_t		log_addr;
	struct ether_addr	mac;
	uint16_t		mtu;

	struct vhost_device_ops const *notify_ops;

	uint32_t		nr_guest_pages;
	uint32_t		max_guest_pages;
	struct guest_page       *guest_pages;

	int			slave_req_fd;
} __rte_cache_aligned;


#define VHOST_LOG_PAGE	4096

/*
 * Atomically set a bit in memory.
 */
static __rte_always_inline void
vhost_set_bit(unsigned int nr, volatile uint8_t *addr)
{
	__sync_fetch_and_or_8(addr, (1U << nr));
}

static __rte_always_inline void
vhost_log_page(uint8_t *log_base, uint64_t page)
{
	vhost_set_bit(page % 8, &log_base[page / 8]);
}

static __rte_always_inline void
vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len)
{
	uint64_t page;

	if (likely(((dev->features & (1ULL << VHOST_F_LOG_ALL)) == 0) ||
		   !dev->log_base || !len))
		return;

	if (unlikely(dev->log_size <= ((addr + len - 1) / VHOST_LOG_PAGE / 8)))
		return;

	/* To make sure guest memory updates are committed before logging */
	rte_smp_wmb();

	page = addr / VHOST_LOG_PAGE;
	while (page * VHOST_LOG_PAGE < addr + len) {
		vhost_log_page((uint8_t *)(uintptr_t)dev->log_base, page);
		page += 1;
	}
}

static __rte_always_inline void
vhost_log_used_vring(struct virtio_net *dev, struct vhost_virtqueue *vq,
		     uint64_t offset, uint64_t len)
{
	vhost_log_write(dev, vq->log_guest_addr + offset, len);
}

/* Macros for printing using RTE_LOG */
#define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1
#define RTE_LOGTYPE_VHOST_DATA   RTE_LOGTYPE_USER1

#ifdef RTE_LIBRTE_VHOST_DEBUG
#define VHOST_MAX_PRINT_BUFF 6072
#define LOG_LEVEL RTE_LOG_DEBUG
#define LOG_DEBUG(log_type, fmt, args...) RTE_LOG(DEBUG, log_type, fmt, ##args)
#define PRINT_PACKET(device, addr, size, header) do { \
	char *pkt_addr = (char *)(addr); \
	unsigned int index; \
	char packet[VHOST_MAX_PRINT_BUFF]; \
	\
	if ((header)) \
		snprintf(packet, VHOST_MAX_PRINT_BUFF, "(%d) Header size %d: ", (device->vid), (size)); \
	else \
		snprintf(packet, VHOST_MAX_PRINT_BUFF, "(%d) Packet size %d: ", (device->vid), (size)); \
	for (index = 0; index < (size); index++) { \
		snprintf(packet + strnlen(packet, VHOST_MAX_PRINT_BUFF), VHOST_MAX_PRINT_BUFF - strnlen(packet, VHOST_MAX_PRINT_BUFF), \
			"%02hhx ", pkt_addr[index]); \
	} \
	snprintf(packet + strnlen(packet, VHOST_MAX_PRINT_BUFF), VHOST_MAX_PRINT_BUFF - strnlen(packet, VHOST_MAX_PRINT_BUFF), "\n"); \
	\
	LOG_DEBUG(VHOST_DATA, "%s", packet); \
} while (0)
#else
#define LOG_LEVEL RTE_LOG_INFO
#define LOG_DEBUG(log_type, fmt, args...) do {} while (0)
#define PRINT_PACKET(device, addr, size, header) do {} while (0)
#endif

extern uint64_t VHOST_FEATURES;
#define MAX_VHOST_DEVICE	1024
extern struct virtio_net *vhost_devices[MAX_VHOST_DEVICE];

/* Convert guest physical address to host physical address */
static __rte_always_inline rte_iova_t
gpa_to_hpa(struct virtio_net *dev, uint64_t gpa, uint64_t size)
{
	uint32_t i;
	struct guest_page *page;

	for (i = 0; i < dev->nr_guest_pages; i++) {
		page = &dev->guest_pages[i];

		if (gpa >= page->guest_phys_addr &&
		    gpa + size < page->guest_phys_addr + page->size) {
			return gpa - page->guest_phys_addr +
			       page->host_phys_addr;
		}
	}

	return 0;
}

struct virtio_net *get_device(int vid);

int vhost_new_device(void);
void cleanup_device(struct virtio_net *dev, int destroy);
void reset_device(struct virtio_net *dev);
void vhost_destroy_device(int);

void cleanup_vq(struct vhost_virtqueue *vq, int destroy);
void free_vq(struct vhost_virtqueue *vq);

int alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx);

void vhost_set_ifname(int, const char *if_name, unsigned int if_len);
void vhost_enable_dequeue_zero_copy(int vid);
void vhost_set_builtin_virtio_net(int vid, bool enable);

struct vhost_device_ops const *vhost_driver_callback_get(const char *path);

/*
 * Backend-specific cleanup.
 *
 * TODO: fix it; we have one backend now
 */
void vhost_backend_cleanup(struct virtio_net *dev);

uint64_t __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
			uint64_t iova, uint64_t size, uint8_t perm);
int vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq);
void vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq);

static __rte_always_inline uint64_t
vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
			uint64_t iova, uint64_t size, uint8_t perm)
{
	if (!(dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
		return rte_vhost_gpa_to_vva(dev->mem, iova);

	return __vhost_iova_to_vva(dev, vq, iova, size, perm);
}

#define vhost_used_event(vr) \
	(*(volatile uint16_t*)&(vr)->avail->ring[(vr)->size])

/*
 * The following is used with VIRTIO_RING_F_EVENT_IDX.
 * Assuming a given event_idx value from the other size, if we have
 * just incremented index from old to new_idx, should we trigger an
 * event?
 */
static __rte_always_inline int
vhost_need_event(uint16_t event_idx, uint16_t new_idx, uint16_t old)
{
	return (uint16_t)(new_idx - event_idx - 1) < (uint16_t)(new_idx - old);
}

static __rte_always_inline void
vhost_vring_call(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
	/* Flush used->idx update before we read avail->flags. */
	rte_mb();

	/* Don't kick guest if we don't reach index specified by guest. */
	if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX)) {
		uint16_t old = vq->signalled_used;
		uint16_t new = vq->last_used_idx;

		LOG_DEBUG(VHOST_DATA, "%s: used_event_idx=%d, old=%d, new=%d\n",
			__func__,
			vhost_used_event(vq),
			old, new);
		if (vhost_need_event(vhost_used_event(vq), new, old)
			&& (vq->callfd >= 0)) {
			vq->signalled_used = vq->last_used_idx;
			eventfd_write(vq->callfd, (eventfd_t) 1);
		}
	} else {
		/* Kick the guest if necessary. */
		if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
				&& (vq->callfd >= 0))
			eventfd_write(vq->callfd, (eventfd_t)1);
	}
}

#endif /* _VHOST_NET_CDEV_H_ */