summaryrefslogtreecommitdiff
path: root/hw/block/dataplane/virtio-blk.c
blob: f8716bc73ef54308e3ebf24a613b52a0d2bda1ec (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
/*
 * Dedicated thread for virtio-blk I/O processing
 *
 * Copyright 2012 IBM, Corp.
 * Copyright 2012 Red Hat, Inc. and/or its affiliates
 *
 * Authors:
 *   Stefan Hajnoczi <stefanha@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#include "trace.h"
#include "qemu/iov.h"
#include "qemu/thread.h"
#include "qemu/error-report.h"
#include "hw/virtio/virtio-access.h"
#include "hw/virtio/dataplane/vring.h"
#include "hw/virtio/dataplane/vring-accessors.h"
#include "sysemu/block-backend.h"
#include "hw/virtio/virtio-blk.h"
#include "virtio-blk.h"
#include "block/aio.h"
#include "hw/virtio/virtio-bus.h"
#include "qom/object_interfaces.h"

struct VirtIOBlockDataPlane {
    bool started;
    bool starting;
    bool stopping;
    bool disabled;

    VirtIOBlkConf *conf;

    VirtIODevice *vdev;
    Vring vring;                    /* virtqueue vring */
    EventNotifier *guest_notifier;  /* irq */
    QEMUBH *bh;                     /* bh for guest notification */

    /* Note that these EventNotifiers are assigned by value.  This is
     * fine as long as you do not call event_notifier_cleanup on them
     * (because you don't own the file descriptor or handle; you just
     * use it).
     */
    IOThread *iothread;
    IOThread internal_iothread_obj;
    AioContext *ctx;
    EventNotifier host_notifier;    /* doorbell */

    /* Operation blocker on BDS */
    Error *blocker;
    void (*saved_complete_request)(struct VirtIOBlockReq *req,
                                   unsigned char status);
};

/* Raise an interrupt to signal guest, if necessary */
static void notify_guest(VirtIOBlockDataPlane *s)
{
    if (!vring_should_notify(s->vdev, &s->vring)) {
        return;
    }

    event_notifier_set(s->guest_notifier);
}

static void notify_guest_bh(void *opaque)
{
    VirtIOBlockDataPlane *s = opaque;

    notify_guest(s);
}

static void complete_request_vring(VirtIOBlockReq *req, unsigned char status)
{
    VirtIOBlockDataPlane *s = req->dev->dataplane;
    stb_p(&req->in->status, status);

    vring_push(s->vdev, &req->dev->dataplane->vring, &req->elem, req->in_len);

    /* Suppress notification to guest by BH and its scheduled
     * flag because requests are completed as a batch after io
     * plug & unplug is introduced, and the BH can still be
     * executed in dataplane aio context even after it is
     * stopped, so needn't worry about notification loss with BH.
     */
    qemu_bh_schedule(s->bh);
}

static void handle_notify(EventNotifier *e)
{
    VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane,
                                           host_notifier);
    VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);

    event_notifier_test_and_clear(&s->host_notifier);
    blk_io_plug(s->conf->conf.blk);
    for (;;) {
        MultiReqBuffer mrb = {};
        int ret;

        /* Disable guest->host notifies to avoid unnecessary vmexits */
        vring_disable_notification(s->vdev, &s->vring);

        for (;;) {
            VirtIOBlockReq *req = virtio_blk_alloc_request(vblk);

            ret = vring_pop(s->vdev, &s->vring, &req->elem);
            if (ret < 0) {
                virtio_blk_free_request(req);
                break; /* no more requests */
            }

            trace_virtio_blk_data_plane_process_request(s, req->elem.out_num,
                                                        req->elem.in_num,
                                                        req->elem.index);

            virtio_blk_handle_request(req, &mrb);
        }

        if (mrb.num_reqs) {
            virtio_blk_submit_multireq(s->conf->conf.blk, &mrb);
        }

        if (likely(ret == -EAGAIN)) { /* vring emptied */
            /* Re-enable guest->host notifies and stop processing the vring.
             * But if the guest has snuck in more descriptors, keep processing.
             */
            if (vring_enable_notification(s->vdev, &s->vring)) {
                break;
            }
        } else { /* fatal error */
            break;
        }
    }
    blk_io_unplug(s->conf->conf.blk);
}

/* Context: QEMU global mutex held */
void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
                                  VirtIOBlockDataPlane **dataplane,
                                  Error **errp)
{
    VirtIOBlockDataPlane *s;
    Error *local_err = NULL;
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);

    *dataplane = NULL;

    if (!conf->data_plane && !conf->iothread) {
        return;
    }

    /* Don't try if transport does not support notifiers. */
    if (!k->set_guest_notifiers || !k->set_host_notifier) {
        error_setg(errp,
                   "device is incompatible with x-data-plane "
                   "(transport does not support notifiers)");
        return;
    }

    /* If dataplane is (re-)enabled while the guest is running there could be
     * block jobs that can conflict.
     */
    if (blk_op_is_blocked(conf->conf.blk, BLOCK_OP_TYPE_DATAPLANE,
                          &local_err)) {
        error_setg(errp, "cannot start dataplane thread: %s",
                   error_get_pretty(local_err));
        error_free(local_err);
        return;
    }

    s = g_new0(VirtIOBlockDataPlane, 1);
    s->vdev = vdev;
    s->conf = conf;

    if (conf->iothread) {
        s->iothread = conf->iothread;
        object_ref(OBJECT(s->iothread));
    } else {
        /* Create per-device IOThread if none specified.  This is for
         * x-data-plane option compatibility.  If x-data-plane is removed we
         * can drop this.
         */
        object_initialize(&s->internal_iothread_obj,
                          sizeof(s->internal_iothread_obj),
                          TYPE_IOTHREAD);
        user_creatable_complete(OBJECT(&s->internal_iothread_obj), &error_abort);
        s->iothread = &s->internal_iothread_obj;
    }
    s->ctx = iothread_get_aio_context(s->iothread);
    s->bh = aio_bh_new(s->ctx, notify_guest_bh, s);

    error_setg(&s->blocker, "block device is in use by data plane");
    blk_op_block_all(conf->conf.blk, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_RESIZE, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_DRIVE_DEL, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_BACKUP_SOURCE, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_CHANGE, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_COMMIT_SOURCE, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_COMMIT_TARGET, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_EJECT, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_EXTERNAL_SNAPSHOT, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_INTERNAL_SNAPSHOT, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_INTERNAL_SNAPSHOT_DELETE,
                   s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_MIRROR, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_STREAM, s->blocker);
    blk_op_unblock(conf->conf.blk, BLOCK_OP_TYPE_REPLACE, s->blocker);

    *dataplane = s;
}

/* Context: QEMU global mutex held */
void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
{
    if (!s) {
        return;
    }

    virtio_blk_data_plane_stop(s);
    blk_op_unblock_all(s->conf->conf.blk, s->blocker);
    error_free(s->blocker);
    qemu_bh_delete(s->bh);
    object_unref(OBJECT(s->iothread));
    g_free(s);
}

/* Context: QEMU global mutex held */
void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
{
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
    VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
    VirtQueue *vq;
    int r;

    if (s->started || s->disabled) {
        return;
    }

    if (s->starting) {
        return;
    }

    s->starting = true;

    vq = virtio_get_queue(s->vdev, 0);
    if (!vring_setup(&s->vring, s->vdev, 0)) {
        goto fail_vring;
    }

    /* Set up guest notifier (irq) */
    r = k->set_guest_notifiers(qbus->parent, 1, true);
    if (r != 0) {
        fprintf(stderr, "virtio-blk failed to set guest notifier (%d), "
                "ensure -enable-kvm is set\n", r);
        goto fail_guest_notifiers;
    }
    s->guest_notifier = virtio_queue_get_guest_notifier(vq);

    /* Set up virtqueue notify */
    r = k->set_host_notifier(qbus->parent, 0, true);
    if (r != 0) {
        fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r);
        goto fail_host_notifier;
    }
    s->host_notifier = *virtio_queue_get_host_notifier(vq);

    s->saved_complete_request = vblk->complete_request;
    vblk->complete_request = complete_request_vring;

    s->starting = false;
    s->started = true;
    trace_virtio_blk_data_plane_start(s);

    blk_set_aio_context(s->conf->conf.blk, s->ctx);

    /* Kick right away to begin processing requests already in vring */
    event_notifier_set(virtio_queue_get_host_notifier(vq));

    /* Get this show started by hooking up our callbacks */
    aio_context_acquire(s->ctx);
    aio_set_event_notifier(s->ctx, &s->host_notifier, false,
                           handle_notify);
    aio_context_release(s->ctx);
    return;

  fail_host_notifier:
    k->set_guest_notifiers(qbus->parent, 1, false);
  fail_guest_notifiers:
    vring_teardown(&s->vring, s->vdev, 0);
    s->disabled = true;
  fail_vring:
    s->starting = false;
}

/* Context: QEMU global mutex held */
void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
{
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
    VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);


    /* Better luck next time. */
    if (s->disabled) {
        s->disabled = false;
        return;
    }
    if (!s->started || s->stopping) {
        return;
    }
    s->stopping = true;
    vblk->complete_request = s->saved_complete_request;
    trace_virtio_blk_data_plane_stop(s);

    aio_context_acquire(s->ctx);

    /* Stop notifications for new requests from guest */
    aio_set_event_notifier(s->ctx, &s->host_notifier, false,
                           NULL);

    /* Drain and switch bs back to the QEMU main loop */
    blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context());

    aio_context_release(s->ctx);

    /* Sync vring state back to virtqueue so that non-dataplane request
     * processing can continue when we disable the host notifier below.
     */
    vring_teardown(&s->vring, s->vdev, 0);

    k->set_host_notifier(qbus->parent, 0, false);

    /* Clean up guest notifier (irq) */
    k->set_guest_notifiers(qbus->parent, 1, false);

    s->started = false;
    s->stopping = false;
}