summaryrefslogtreecommitdiffstats
path: root/qemu/hw/virtio/dataplane/vring.c
blob: 07fd69c69eb8cdf9267f4c6955a75f616b625ed1 (plain)
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
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
/* Copyright 2012 Red Hat, Inc.
 * Copyright IBM, Corp. 2012
 *
 * Based on Linux 2.6.39 vhost code:
 * Copyright (C) 2009 Red Hat, Inc.
 * Copyright (C) 2006 Rusty Russell IBM Corporation
 *
 * Author: Michael S. Tsirkin <mst@redhat.com>
 *         Stefan Hajnoczi <stefanha@redhat.com>
 *
 * Inspiration, some code, and most witty comments come from
 * Documentation/virtual/lguest/lguest.c, by Rusty Russell
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 */

#include "trace.h"
#include "hw/hw.h"
#include "exec/memory.h"
#include "exec/address-spaces.h"
#include "hw/virtio/virtio-access.h"
#include "hw/virtio/dataplane/vring.h"
#include "hw/virtio/dataplane/vring-accessors.h"
#include "qemu/error-report.h"

/* vring_map can be coupled with vring_unmap or (if you still have the
 * value returned in *mr) memory_region_unref.
 */
static void *vring_map(MemoryRegion **mr, hwaddr phys, hwaddr len,
                       bool is_write)
{
    MemoryRegionSection section = memory_region_find(get_system_memory(), phys, len);

    if (!section.mr || int128_get64(section.size) < len) {
        goto out;
    }
    if (is_write && section.readonly) {
        goto out;
    }
    if (!memory_region_is_ram(section.mr)) {
        goto out;
    }

    /* Ignore regions with dirty logging, we cannot mark them dirty */
    if (memory_region_get_dirty_log_mask(section.mr)) {
        goto out;
    }

    *mr = section.mr;
    return memory_region_get_ram_ptr(section.mr) + section.offset_within_region;

out:
    memory_region_unref(section.mr);
    *mr = NULL;
    return NULL;
}

static void vring_unmap(void *buffer, bool is_write)
{
    ram_addr_t addr;
    MemoryRegion *mr;

    mr = qemu_ram_addr_from_host(buffer, &addr);
    memory_region_unref(mr);
}

/* Map the guest's vring to host memory */
bool vring_setup(Vring *vring, VirtIODevice *vdev, int n)
{
    hwaddr vring_addr = virtio_queue_get_ring_addr(vdev, n);
    hwaddr vring_size = virtio_queue_get_ring_size(vdev, n);
    void *vring_ptr;

    vring->broken = false;

    vring_ptr = vring_map(&vring->mr, vring_addr, vring_size, true);
    if (!vring_ptr) {
        error_report("Failed to map vring "
                     "addr %#" HWADDR_PRIx " size %" HWADDR_PRIu,
                     vring_addr, vring_size);
        vring->broken = true;
        return false;
    }

    vring_init(&vring->vr, virtio_queue_get_num(vdev, n), vring_ptr, 4096);

    vring->last_avail_idx = virtio_queue_get_last_avail_idx(vdev, n);
    vring->last_used_idx = vring_get_used_idx(vdev, vring);
    vring->signalled_used = 0;
    vring->signalled_used_valid = false;

    trace_vring_setup(virtio_queue_get_ring_addr(vdev, n),
                      vring->vr.desc, vring->vr.avail, vring->vr.used);
    return true;
}

void vring_teardown(Vring *vring, VirtIODevice *vdev, int n)
{
    virtio_queue_set_last_avail_idx(vdev, n, vring->last_avail_idx);
    virtio_queue_invalidate_signalled_used(vdev, n);

    memory_region_unref(vring->mr);
}

/* Disable guest->host notifies */
void vring_disable_notification(VirtIODevice *vdev, Vring *vring)
{
    if (!virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
        vring_set_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY);
    }
}

/* Enable guest->host notifies
 *
 * Return true if the vring is empty, false if there are more requests.
 */
bool vring_enable_notification(VirtIODevice *vdev, Vring *vring)
{
    if (virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
        vring_avail_event(&vring->vr) = vring->vr.avail->idx;
    } else {
        vring_clear_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY);
    }
    smp_mb(); /* ensure update is seen before reading avail_idx */
    return !vring_more_avail(vdev, vring);
}

/* This is stolen from linux/drivers/vhost/vhost.c:vhost_notify() */
bool vring_should_notify(VirtIODevice *vdev, Vring *vring)
{
    uint16_t old, new;
    bool v;
    /* Flush out used index updates. This is paired
     * with the barrier that the Guest executes when enabling
     * interrupts. */
    smp_mb();

    if (virtio_has_feature(vdev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
        unlikely(!vring_more_avail(vdev, vring))) {
        return true;
    }

    if (!virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
        return !(vring_get_avail_flags(vdev, vring) &
                 VRING_AVAIL_F_NO_INTERRUPT);
    }
    old = vring->signalled_used;
    v = vring->signalled_used_valid;
    new = vring->signalled_used = vring->last_used_idx;
    vring->signalled_used_valid = true;

    if (unlikely(!v)) {
        return true;
    }

    return vring_need_event(virtio_tswap16(vdev, vring_used_event(&vring->vr)),
                            new, old);
}


static int get_desc(Vring *vring, VirtQueueElement *elem,
                    struct vring_desc *desc)
{
    unsigned *num;
    struct iovec *iov;
    hwaddr *addr;
    MemoryRegion *mr;

    if (desc->flags & VRING_DESC_F_WRITE) {
        num = &elem->in_num;
        iov = &elem->in_sg[*num];
        addr = &elem->in_addr[*num];
    } else {
        num = &elem->out_num;
        iov = &elem->out_sg[*num];
        addr = &elem->out_addr[*num];

        /* If it's an output descriptor, they're all supposed
         * to come before any input descriptors. */
        if (unlikely(elem->in_num)) {
            error_report("Descriptor has out after in");
            return -EFAULT;
        }
    }

    /* Stop for now if there are not enough iovecs available. */
    if (*num >= VIRTQUEUE_MAX_SIZE) {
        error_report("Invalid SG num: %u", *num);
        return -EFAULT;
    }

    /* TODO handle non-contiguous memory across region boundaries */
    iov->iov_base = vring_map(&mr, desc->addr, desc->len,
                              desc->flags & VRING_DESC_F_WRITE);
    if (!iov->iov_base) {
        error_report("Failed to map descriptor addr %#" PRIx64 " len %u",
                     (uint64_t)desc->addr, desc->len);
        return -EFAULT;
    }

    /* The MemoryRegion is looked up again and unref'ed later, leave the
     * ref in place.  */
    iov->iov_len = desc->len;
    *addr = desc->addr;
    *num += 1;
    return 0;
}

static void copy_in_vring_desc(VirtIODevice *vdev,
                               const struct vring_desc *guest,
                               struct vring_desc *host)
{
    host->addr = virtio_ldq_p(vdev, &guest->addr);
    host->len = virtio_ldl_p(vdev, &guest->len);
    host->flags = virtio_lduw_p(vdev, &guest->flags);
    host->next = virtio_lduw_p(vdev, &guest->next);
}

/* This is stolen from linux/drivers/vhost/vhost.c. */
static int get_indirect(VirtIODevice *vdev, Vring *vring,
                        VirtQueueElement *elem, struct vring_desc *indirect)
{
    struct vring_desc desc;
    unsigned int i = 0, count, found = 0;
    int ret;

    /* Sanity check */
    if (unlikely(indirect->len % sizeof(desc))) {
        error_report("Invalid length in indirect descriptor: "
                     "len %#x not multiple of %#zx",
                     indirect->len, sizeof(desc));
        vring->broken = true;
        return -EFAULT;
    }

    count = indirect->len / sizeof(desc);
    /* Buffers are chained via a 16 bit next field, so
     * we can have at most 2^16 of these. */
    if (unlikely(count > USHRT_MAX + 1)) {
        error_report("Indirect buffer length too big: %d", indirect->len);
        vring->broken = true;
        return -EFAULT;
    }

    do {
        struct vring_desc *desc_ptr;
        MemoryRegion *mr;

        /* Translate indirect descriptor */
        desc_ptr = vring_map(&mr,
                             indirect->addr + found * sizeof(desc),
                             sizeof(desc), false);
        if (!desc_ptr) {
            error_report("Failed to map indirect descriptor "
                         "addr %#" PRIx64 " len %zu",
                         (uint64_t)indirect->addr + found * sizeof(desc),
                         sizeof(desc));
            vring->broken = true;
            return -EFAULT;
        }
        copy_in_vring_desc(vdev, desc_ptr, &desc);
        memory_region_unref(mr);

        /* Ensure descriptor has been loaded before accessing fields */
        barrier(); /* read_barrier_depends(); */

        if (unlikely(++found > count)) {
            error_report("Loop detected: last one at %u "
                         "indirect size %u", i, count);
            vring->broken = true;
            return -EFAULT;
        }

        if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) {
            error_report("Nested indirect descriptor");
            vring->broken = true;
            return -EFAULT;
        }

        ret = get_desc(vring, elem, &desc);
        if (ret < 0) {
            vring->broken |= (ret == -EFAULT);
            return ret;
        }
        i = desc.next;
    } while (desc.flags & VRING_DESC_F_NEXT);
    return 0;
}

static void vring_unmap_element(VirtQueueElement *elem)
{
    int i;

    /* This assumes that the iovecs, if changed, are never moved past
     * the end of the valid area.  This is true if iovec manipulations
     * are done with iov_discard_front and iov_discard_back.
     */
    for (i = 0; i < elem->out_num; i++) {
        vring_unmap(elem->out_sg[i].iov_base, false);
    }

    for (i = 0; i < elem->in_num; i++) {
        vring_unmap(elem->in_sg[i].iov_base, true);
    }
}

/* This looks in the virtqueue and for the first available buffer, and converts
 * it to an iovec for convenient access.  Since descriptors consist of some
 * number of output then some number of input descriptors, it's actually two
 * iovecs, but we pack them into one and note how many of each there were.
 *
 * This function returns the descriptor number found, or vq->num (which is
 * never a valid descriptor number) if none was found.  A negative code is
 * returned on error.
 *
 * Stolen from linux/drivers/vhost/vhost.c.
 */
int vring_pop(VirtIODevice *vdev, Vring *vring,
              VirtQueueElement *elem)
{
    struct vring_desc desc;
    unsigned int i, head, found = 0, num = vring->vr.num;
    uint16_t avail_idx, last_avail_idx;
    int ret;

    /* Initialize elem so it can be safely unmapped */
    elem->in_num = elem->out_num = 0;

    /* If there was a fatal error then refuse operation */
    if (vring->broken) {
        ret = -EFAULT;
        goto out;
    }

    /* Check it isn't doing very strange things with descriptor numbers. */
    last_avail_idx = vring->last_avail_idx;
    avail_idx = vring_get_avail_idx(vdev, vring);
    barrier(); /* load indices now and not again later */

    if (unlikely((uint16_t)(avail_idx - last_avail_idx) > num)) {
        error_report("Guest moved used index from %u to %u",
                     last_avail_idx, avail_idx);
        ret = -EFAULT;
        goto out;
    }

    /* If there's nothing new since last we looked. */
    if (avail_idx == last_avail_idx) {
        ret = -EAGAIN;
        goto out;
    }

    /* Only get avail ring entries after they have been exposed by guest. */
    smp_rmb();

    /* Grab the next descriptor number they're advertising, and increment
     * the index we've seen. */
    head = vring_get_avail_ring(vdev, vring, last_avail_idx % num);

    elem->index = head;

    /* If their number is silly, that's an error. */
    if (unlikely(head >= num)) {
        error_report("Guest says index %u > %u is available", head, num);
        ret = -EFAULT;
        goto out;
    }

    i = head;
    do {
        if (unlikely(i >= num)) {
            error_report("Desc index is %u > %u, head = %u", i, num, head);
            ret = -EFAULT;
            goto out;
        }
        if (unlikely(++found > num)) {
            error_report("Loop detected: last one at %u vq size %u head %u",
                         i, num, head);
            ret = -EFAULT;
            goto out;
        }
        copy_in_vring_desc(vdev, &vring->vr.desc[i], &desc);

        /* Ensure descriptor is loaded before accessing fields */
        barrier();

        if (desc.flags & VRING_DESC_F_INDIRECT) {
            ret = get_indirect(vdev, vring, elem, &desc);
            if (ret < 0) {
                goto out;
            }
            continue;
        }

        ret = get_desc(vring, elem, &desc);
        if (ret < 0) {
            goto out;
        }

        i = desc.next;
    } while (desc.flags & VRING_DESC_F_NEXT);

    /* On success, increment avail index. */
    vring->last_avail_idx++;
    if (virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
        vring_avail_event(&vring->vr) =
            virtio_tswap16(vdev, vring->last_avail_idx);
    }

    return head;

out:
    assert(ret < 0);
    if (ret == -EFAULT) {
        vring->broken = true;
    }
    vring_unmap_element(elem);
    return ret;
}

/* After we've used one of their buffers, we tell them about it.
 *
 * Stolen from linux/drivers/vhost/vhost.c.
 */
void vring_push(VirtIODevice *vdev, Vring *vring, VirtQueueElement *elem,
                int len)
{
    unsigned int head = elem->index;
    uint16_t new;

    vring_unmap_element(elem);

    /* Don't touch vring if a fatal error occurred */
    if (vring->broken) {
        return;
    }

    /* The virtqueue contains a ring of used buffers.  Get a pointer to the
     * next entry in that used ring. */
    vring_set_used_ring_id(vdev, vring, vring->last_used_idx % vring->vr.num,
                           head);
    vring_set_used_ring_len(vdev, vring, vring->last_used_idx % vring->vr.num,
                            len);

    /* Make sure buffer is written before we update index. */
    smp_wmb();

    new = ++vring->last_used_idx;
    vring_set_used_idx(vdev, vring, new);
    if (unlikely((int16_t)(new - vring->signalled_used) < (uint16_t)1)) {
        vring->signalled_used_valid = false;
    }
}