summaryrefslogtreecommitdiff
path: root/dma-helpers.c
blob: 41ef24a63b6b077022fd329b528dac9cc19ead70 (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
/*
 * DMA helper functions
 *
 * Copyright (c) 2009 Red Hat
 *
 * This work is licensed under the terms of the GNU General Public License
 * (GNU GPL), version 2 or later.
 */

#include "qemu/osdep.h"
#include "sysemu/block-backend.h"
#include "sysemu/dma.h"
#include "trace/trace-root.h"
#include "qemu/thread.h"
#include "qemu/main-loop.h"
#include "sysemu/cpus.h"
#include "qemu/range.h"

/* #define DEBUG_IOMMU */

int dma_memory_set(AddressSpace *as, dma_addr_t addr, uint8_t c, dma_addr_t len)
{
    dma_barrier(as, DMA_DIRECTION_FROM_DEVICE);

#define FILLBUF_SIZE 512
    uint8_t fillbuf[FILLBUF_SIZE];
    int l;
    bool error = false;

    memset(fillbuf, c, FILLBUF_SIZE);
    while (len > 0) {
        l = len < FILLBUF_SIZE ? len : FILLBUF_SIZE;
        error |= address_space_write(as, addr, MEMTXATTRS_UNSPECIFIED,
                                     fillbuf, l);
        len -= l;
        addr += l;
    }

    return error;
}

void qemu_sglist_init(QEMUSGList *qsg, DeviceState *dev, int alloc_hint,
                      AddressSpace *as)
{
    qsg->sg = g_malloc(alloc_hint * sizeof(ScatterGatherEntry));
    qsg->nsg = 0;
    qsg->nalloc = alloc_hint;
    qsg->size = 0;
    qsg->as = as;
    qsg->dev = dev;
    object_ref(OBJECT(dev));
}

void qemu_sglist_add(QEMUSGList *qsg, dma_addr_t base, dma_addr_t len)
{
    if (qsg->nsg == qsg->nalloc) {
        qsg->nalloc = 2 * qsg->nalloc + 1;
        qsg->sg = g_realloc(qsg->sg, qsg->nalloc * sizeof(ScatterGatherEntry));
    }
    qsg->sg[qsg->nsg].base = base;
    qsg->sg[qsg->nsg].len = len;
    qsg->size += len;
    ++qsg->nsg;
}

void qemu_sglist_destroy(QEMUSGList *qsg)
{
    object_unref(OBJECT(qsg->dev));
    g_free(qsg->sg);
    memset(qsg, 0, sizeof(*qsg));
}

typedef struct {
    BlockAIOCB common;
    AioContext *ctx;
    BlockAIOCB *acb;
    QEMUSGList *sg;
    uint32_t align;
    uint64_t offset;
    DMADirection dir;
    int sg_cur_index;
    dma_addr_t sg_cur_byte;
    QEMUIOVector iov;
    QEMUBH *bh;
    DMAIOFunc *io_func;
    void *io_func_opaque;
} DMAAIOCB;

static void dma_blk_cb(void *opaque, int ret);

static void reschedule_dma(void *opaque)
{
    DMAAIOCB *dbs = (DMAAIOCB *)opaque;

    assert(!dbs->acb && dbs->bh);
    qemu_bh_delete(dbs->bh);
    dbs->bh = NULL;
    dma_blk_cb(dbs, 0);
}

static void dma_blk_unmap(DMAAIOCB *dbs)
{
    int i;

    for (i = 0; i < dbs->iov.niov; ++i) {
        dma_memory_unmap(dbs->sg->as, dbs->iov.iov[i].iov_base,
                         dbs->iov.iov[i].iov_len, dbs->dir,
                         dbs->iov.iov[i].iov_len);
    }
    qemu_iovec_reset(&dbs->iov);
}

static void dma_complete(DMAAIOCB *dbs, int ret)
{
    trace_dma_complete(dbs, ret, dbs->common.cb);

    assert(!dbs->acb && !dbs->bh);
    dma_blk_unmap(dbs);
    if (dbs->common.cb) {
        dbs->common.cb(dbs->common.opaque, ret);
    }
    qemu_iovec_destroy(&dbs->iov);
    qemu_aio_unref(dbs);
}

static void dma_blk_cb(void *opaque, int ret)
{
    DMAAIOCB *dbs = (DMAAIOCB *)opaque;
    dma_addr_t cur_addr, cur_len;
    void *mem;

    trace_dma_blk_cb(dbs, ret);

    dbs->acb = NULL;
    dbs->offset += dbs->iov.size;

    if (dbs->sg_cur_index == dbs->sg->nsg || ret < 0) {
        dma_complete(dbs, ret);
        return;
    }
    dma_blk_unmap(dbs);

    while (dbs->sg_cur_index < dbs->sg->nsg) {
        cur_addr = dbs->sg->sg[dbs->sg_cur_index].base + dbs->sg_cur_byte;
        cur_len = dbs->sg->sg[dbs->sg_cur_index].len - dbs->sg_cur_byte;
        mem = dma_memory_map(dbs->sg->as, cur_addr, &cur_len, dbs->dir);
        /*
         * Make reads deterministic in icount mode. Windows sometimes issues
         * disk read requests with overlapping SGs. It leads
         * to non-determinism, because resulting buffer contents may be mixed
         * from several sectors. This code splits all SGs into several
         * groups. SGs in every group do not overlap.
         */
        if (mem && use_icount && dbs->dir == DMA_DIRECTION_FROM_DEVICE) {
            int i;
            for (i = 0 ; i < dbs->iov.niov ; ++i) {
                if (ranges_overlap((intptr_t)dbs->iov.iov[i].iov_base,
                                   dbs->iov.iov[i].iov_len, (intptr_t)mem,
                                   cur_len)) {
                    dma_memory_unmap(dbs->sg->as, mem, cur_len,
                                     dbs->dir, cur_len);
                    mem = NULL;
                    break;
                }
            }
        }
        if (!mem)
            break;
        qemu_iovec_add(&dbs->iov, mem, cur_len);
        dbs->sg_cur_byte += cur_len;
        if (dbs->sg_cur_byte == dbs->sg->sg[dbs->sg_cur_index].len) {
            dbs->sg_cur_byte = 0;
            ++dbs->sg_cur_index;
        }
    }

    if (dbs->iov.size == 0) {
        trace_dma_map_wait(dbs);
        dbs->bh = aio_bh_new(dbs->ctx, reschedule_dma, dbs);
        cpu_register_map_client(dbs->bh);
        return;
    }

    if (!QEMU_IS_ALIGNED(dbs->iov.size, dbs->align)) {
        qemu_iovec_discard_back(&dbs->iov,
                                QEMU_ALIGN_DOWN(dbs->iov.size, dbs->align));
    }

    aio_context_acquire(dbs->ctx);
    dbs->acb = dbs->io_func(dbs->offset, &dbs->iov,
                            dma_blk_cb, dbs, dbs->io_func_opaque);
    aio_context_release(dbs->ctx);
    assert(dbs->acb);
}

static void dma_aio_cancel(BlockAIOCB *acb)
{
    DMAAIOCB *dbs = container_of(acb, DMAAIOCB, common);

    trace_dma_aio_cancel(dbs);

    assert(!(dbs->acb && dbs->bh));
    if (dbs->acb) {
        /* This will invoke dma_blk_cb.  */
        blk_aio_cancel_async(dbs->acb);
        return;
    }

    if (dbs->bh) {
        cpu_unregister_map_client(dbs->bh);
        qemu_bh_delete(dbs->bh);
        dbs->bh = NULL;
    }
    if (dbs->common.cb) {
        dbs->common.cb(dbs->common.opaque, -ECANCELED);
    }
}

static AioContext *dma_get_aio_context(BlockAIOCB *acb)
{
    DMAAIOCB *dbs = container_of(acb, DMAAIOCB, common);

    return dbs->ctx;
}

static const AIOCBInfo dma_aiocb_info = {
    .aiocb_size         = sizeof(DMAAIOCB),
    .cancel_async       = dma_aio_cancel,
    .get_aio_context    = dma_get_aio_context,
};

BlockAIOCB *dma_blk_io(AioContext *ctx,
    QEMUSGList *sg, uint64_t offset, uint32_t align,
    DMAIOFunc *io_func, void *io_func_opaque,
    BlockCompletionFunc *cb,
    void *opaque, DMADirection dir)
{
    DMAAIOCB *dbs = qemu_aio_get(&dma_aiocb_info, NULL, cb, opaque);

    trace_dma_blk_io(dbs, io_func_opaque, offset, (dir == DMA_DIRECTION_TO_DEVICE));

    dbs->acb = NULL;
    dbs->sg = sg;
    dbs->ctx = ctx;
    dbs->offset = offset;
    dbs->align = align;
    dbs->sg_cur_index = 0;
    dbs->sg_cur_byte = 0;
    dbs->dir = dir;
    dbs->io_func = io_func;
    dbs->io_func_opaque = io_func_opaque;
    dbs->bh = NULL;
    qemu_iovec_init(&dbs->iov, sg->nsg);
    dma_blk_cb(dbs, 0);
    return &dbs->common;
}


static
BlockAIOCB *dma_blk_read_io_func(int64_t offset, QEMUIOVector *iov,
                                 BlockCompletionFunc *cb, void *cb_opaque,
                                 void *opaque)
{
    BlockBackend *blk = opaque;
    return blk_aio_preadv(blk, offset, iov, 0, cb, cb_opaque);
}

BlockAIOCB *dma_blk_read(BlockBackend *blk,
                         QEMUSGList *sg, uint64_t offset, uint32_t align,
                         void (*cb)(void *opaque, int ret), void *opaque)
{
    return dma_blk_io(blk_get_aio_context(blk), sg, offset, align,
                      dma_blk_read_io_func, blk, cb, opaque,
                      DMA_DIRECTION_FROM_DEVICE);
}

static
BlockAIOCB *dma_blk_write_io_func(int64_t offset, QEMUIOVector *iov,
                                  BlockCompletionFunc *cb, void *cb_opaque,
                                  void *opaque)
{
    BlockBackend *blk = opaque;
    return blk_aio_pwritev(blk, offset, iov, 0, cb, cb_opaque);
}

BlockAIOCB *dma_blk_write(BlockBackend *blk,
                          QEMUSGList *sg, uint64_t offset, uint32_t align,
                          void (*cb)(void *opaque, int ret), void *opaque)
{
    return dma_blk_io(blk_get_aio_context(blk), sg, offset, align,
                      dma_blk_write_io_func, blk, cb, opaque,
                      DMA_DIRECTION_TO_DEVICE);
}


static uint64_t dma_buf_rw(uint8_t *ptr, int32_t len, QEMUSGList *sg,
                           DMADirection dir)
{
    uint64_t resid;
    int sg_cur_index;

    resid = sg->size;
    sg_cur_index = 0;
    len = MIN(len, resid);
    while (len > 0) {
        ScatterGatherEntry entry = sg->sg[sg_cur_index++];
        int32_t xfer = MIN(len, entry.len);
        dma_memory_rw(sg->as, entry.base, ptr, xfer, dir);
        ptr += xfer;
        len -= xfer;
        resid -= xfer;
    }

    return resid;
}

uint64_t dma_buf_read(uint8_t *ptr, int32_t len, QEMUSGList *sg)
{
    return dma_buf_rw(ptr, len, sg, DMA_DIRECTION_FROM_DEVICE);
}

uint64_t dma_buf_write(uint8_t *ptr, int32_t len, QEMUSGList *sg)
{
    return dma_buf_rw(ptr, len, sg, DMA_DIRECTION_TO_DEVICE);
}

void dma_acct_start(BlockBackend *blk, BlockAcctCookie *cookie,
                    QEMUSGList *sg, enum BlockAcctType type)
{
    block_acct_start(blk_get_stats(blk), cookie, sg->size, type);
}