summaryrefslogtreecommitdiffstats
path: root/qemu/hw/pci/msi.c
blob: e0e64c2d9e060603e738ff570456fe5d903be4ee (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
/*
 * msi.c
 *
 * Copyright (c) 2010 Isaku Yamahata <yamahata at valinux co jp>
 *                    VA Linux Systems Japan K.K.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.

 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.

 * You should have received a copy of the GNU General Public License along
 * with this program; if not, see <http://www.gnu.org/licenses/>.
 */

#include "qemu/osdep.h"
#include "hw/pci/msi.h"
#include "hw/xen/xen.h"
#include "qemu/range.h"

/* PCI_MSI_ADDRESS_LO */
#define PCI_MSI_ADDRESS_LO_MASK         (~0x3)

/* If we get rid of cap allocator, we won't need those. */
#define PCI_MSI_32_SIZEOF       0x0a
#define PCI_MSI_64_SIZEOF       0x0e
#define PCI_MSI_32M_SIZEOF      0x14
#define PCI_MSI_64M_SIZEOF      0x18

#define PCI_MSI_VECTORS_MAX     32

/*
 * Flag for interrupt controllers to declare broken MSI/MSI-X support.
 * values: false - broken; true - non-broken.
 *
 * Setting this flag to false will remove MSI/MSI-X capability from all devices.
 *
 * It is preferrable for controllers to set this to true (non-broken) even if
 * they do not actually support MSI/MSI-X: guests normally probe the controller
 * type and do not attempt to enable MSI/MSI-X with interrupt controllers not
 * supporting such, so removing the capability is not required, and
 * it seems cleaner to have a given device look the same for all boards.
 *
 * TODO: some existing controllers violate the above rule. Identify and fix them.
 */
bool msi_nonbroken;

/* If we get rid of cap allocator, we won't need this. */
static inline uint8_t msi_cap_sizeof(uint16_t flags)
{
    switch (flags & (PCI_MSI_FLAGS_MASKBIT | PCI_MSI_FLAGS_64BIT)) {
    case PCI_MSI_FLAGS_MASKBIT | PCI_MSI_FLAGS_64BIT:
        return PCI_MSI_64M_SIZEOF;
    case PCI_MSI_FLAGS_64BIT:
        return PCI_MSI_64_SIZEOF;
    case PCI_MSI_FLAGS_MASKBIT:
        return PCI_MSI_32M_SIZEOF;
    case 0:
        return PCI_MSI_32_SIZEOF;
    default:
        abort();
        break;
    }
    return 0;
}

//#define MSI_DEBUG

#ifdef MSI_DEBUG
# define MSI_DPRINTF(fmt, ...)                                          \
    fprintf(stderr, "%s:%d " fmt, __func__, __LINE__, ## __VA_ARGS__)
#else
# define MSI_DPRINTF(fmt, ...)  do { } while (0)
#endif
#define MSI_DEV_PRINTF(dev, fmt, ...)                                   \
    MSI_DPRINTF("%s:%x " fmt, (dev)->name, (dev)->devfn, ## __VA_ARGS__)

static inline unsigned int msi_nr_vectors(uint16_t flags)
{
    return 1U <<
        ((flags & PCI_MSI_FLAGS_QSIZE) >> ctz32(PCI_MSI_FLAGS_QSIZE));
}

static inline uint8_t msi_flags_off(const PCIDevice* dev)
{
    return dev->msi_cap + PCI_MSI_FLAGS;
}

static inline uint8_t msi_address_lo_off(const PCIDevice* dev)
{
    return dev->msi_cap + PCI_MSI_ADDRESS_LO;
}

static inline uint8_t msi_address_hi_off(const PCIDevice* dev)
{
    return dev->msi_cap + PCI_MSI_ADDRESS_HI;
}

static inline uint8_t msi_data_off(const PCIDevice* dev, bool msi64bit)
{
    return dev->msi_cap + (msi64bit ? PCI_MSI_DATA_64 : PCI_MSI_DATA_32);
}

static inline uint8_t msi_mask_off(const PCIDevice* dev, bool msi64bit)
{
    return dev->msi_cap + (msi64bit ? PCI_MSI_MASK_64 : PCI_MSI_MASK_32);
}

static inline uint8_t msi_pending_off(const PCIDevice* dev, bool msi64bit)
{
    return dev->msi_cap + (msi64bit ? PCI_MSI_PENDING_64 : PCI_MSI_PENDING_32);
}

/*
 * Special API for POWER to configure the vectors through
 * a side channel. Should never be used by devices.
 */
void msi_set_message(PCIDevice *dev, MSIMessage msg)
{
    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;

    if (msi64bit) {
        pci_set_quad(dev->config + msi_address_lo_off(dev), msg.address);
    } else {
        pci_set_long(dev->config + msi_address_lo_off(dev), msg.address);
    }
    pci_set_word(dev->config + msi_data_off(dev, msi64bit), msg.data);
}

MSIMessage msi_get_message(PCIDevice *dev, unsigned int vector)
{
    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
    unsigned int nr_vectors = msi_nr_vectors(flags);
    MSIMessage msg;

    assert(vector < nr_vectors);

    if (msi64bit) {
        msg.address = pci_get_quad(dev->config + msi_address_lo_off(dev));
    } else {
        msg.address = pci_get_long(dev->config + msi_address_lo_off(dev));
    }

    /* upper bit 31:16 is zero */
    msg.data = pci_get_word(dev->config + msi_data_off(dev, msi64bit));
    if (nr_vectors > 1) {
        msg.data &= ~(nr_vectors - 1);
        msg.data |= vector;
    }

    return msg;
}

bool msi_enabled(const PCIDevice *dev)
{
    return msi_present(dev) &&
        (pci_get_word(dev->config + msi_flags_off(dev)) &
         PCI_MSI_FLAGS_ENABLE);
}

int msi_init(struct PCIDevice *dev, uint8_t offset,
             unsigned int nr_vectors, bool msi64bit, bool msi_per_vector_mask)
{
    unsigned int vectors_order;
    uint16_t flags;
    uint8_t cap_size;
    int config_offset;

    if (!msi_nonbroken) {
        return -ENOTSUP;
    }

    MSI_DEV_PRINTF(dev,
                   "init offset: 0x%"PRIx8" vector: %"PRId8
                   " 64bit %d mask %d\n",
                   offset, nr_vectors, msi64bit, msi_per_vector_mask);

    assert(!(nr_vectors & (nr_vectors - 1)));   /* power of 2 */
    assert(nr_vectors > 0);
    assert(nr_vectors <= PCI_MSI_VECTORS_MAX);
    /* the nr of MSI vectors is up to 32 */
    vectors_order = ctz32(nr_vectors);

    flags = vectors_order << ctz32(PCI_MSI_FLAGS_QMASK);
    if (msi64bit) {
        flags |= PCI_MSI_FLAGS_64BIT;
    }
    if (msi_per_vector_mask) {
        flags |= PCI_MSI_FLAGS_MASKBIT;
    }

    cap_size = msi_cap_sizeof(flags);
    config_offset = pci_add_capability(dev, PCI_CAP_ID_MSI, offset, cap_size);
    if (config_offset < 0) {
        return config_offset;
    }

    dev->msi_cap = config_offset;
    dev->cap_present |= QEMU_PCI_CAP_MSI;

    pci_set_word(dev->config + msi_flags_off(dev), flags);
    pci_set_word(dev->wmask + msi_flags_off(dev),
                 PCI_MSI_FLAGS_QSIZE | PCI_MSI_FLAGS_ENABLE);
    pci_set_long(dev->wmask + msi_address_lo_off(dev),
                 PCI_MSI_ADDRESS_LO_MASK);
    if (msi64bit) {
        pci_set_long(dev->wmask + msi_address_hi_off(dev), 0xffffffff);
    }
    pci_set_word(dev->wmask + msi_data_off(dev, msi64bit), 0xffff);

    if (msi_per_vector_mask) {
        /* Make mask bits 0 to nr_vectors - 1 writable. */
        pci_set_long(dev->wmask + msi_mask_off(dev, msi64bit),
                     0xffffffff >> (PCI_MSI_VECTORS_MAX - nr_vectors));
    }
    return config_offset;
}

void msi_uninit(struct PCIDevice *dev)
{
    uint16_t flags;
    uint8_t cap_size;

    if (!msi_present(dev)) {
        return;
    }
    flags = pci_get_word(dev->config + msi_flags_off(dev));
    cap_size = msi_cap_sizeof(flags);
    pci_del_capability(dev, PCI_CAP_ID_MSI, cap_size);
    dev->cap_present &= ~QEMU_PCI_CAP_MSI;

    MSI_DEV_PRINTF(dev, "uninit\n");
}

void msi_reset(PCIDevice *dev)
{
    uint16_t flags;
    bool msi64bit;

    if (!msi_present(dev)) {
        return;
    }

    flags = pci_get_word(dev->config + msi_flags_off(dev));
    flags &= ~(PCI_MSI_FLAGS_QSIZE | PCI_MSI_FLAGS_ENABLE);
    msi64bit = flags & PCI_MSI_FLAGS_64BIT;

    pci_set_word(dev->config + msi_flags_off(dev), flags);
    pci_set_long(dev->config + msi_address_lo_off(dev), 0);
    if (msi64bit) {
        pci_set_long(dev->config + msi_address_hi_off(dev), 0);
    }
    pci_set_word(dev->config + msi_data_off(dev, msi64bit), 0);
    if (flags & PCI_MSI_FLAGS_MASKBIT) {
        pci_set_long(dev->config + msi_mask_off(dev, msi64bit), 0);
        pci_set_long(dev->config + msi_pending_off(dev, msi64bit), 0);
    }
    MSI_DEV_PRINTF(dev, "reset\n");
}

static bool msi_is_masked(const PCIDevice *dev, unsigned int vector)
{
    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
    uint32_t mask, data;
    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
    assert(vector < PCI_MSI_VECTORS_MAX);

    if (!(flags & PCI_MSI_FLAGS_MASKBIT)) {
        return false;
    }

    data = pci_get_word(dev->config + msi_data_off(dev, msi64bit));
    if (xen_is_pirq_msi(data)) {
        return false;
    }

    mask = pci_get_long(dev->config +
                        msi_mask_off(dev, flags & PCI_MSI_FLAGS_64BIT));
    return mask & (1U << vector);
}

void msi_notify(PCIDevice *dev, unsigned int vector)
{
    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
    unsigned int nr_vectors = msi_nr_vectors(flags);
    MSIMessage msg;

    assert(vector < nr_vectors);
    if (msi_is_masked(dev, vector)) {
        assert(flags & PCI_MSI_FLAGS_MASKBIT);
        pci_long_test_and_set_mask(
            dev->config + msi_pending_off(dev, msi64bit), 1U << vector);
        MSI_DEV_PRINTF(dev, "pending vector 0x%x\n", vector);
        return;
    }

    msg = msi_get_message(dev, vector);

    MSI_DEV_PRINTF(dev,
                   "notify vector 0x%x"
                   " address: 0x%"PRIx64" data: 0x%"PRIx32"\n",
                   vector, msg.address, msg.data);
    msi_send_message(dev, msg);
}

void msi_send_message(PCIDevice *dev, MSIMessage msg)
{
    MemTxAttrs attrs = {};

    attrs.requester_id = pci_requester_id(dev);
    address_space_stl_le(&dev->bus_master_as, msg.address, msg.data,
                         attrs, NULL);
}

/* Normally called by pci_default_write_config(). */
void msi_write_config(PCIDevice *dev, uint32_t addr, uint32_t val, int len)
{
    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
    bool msi_per_vector_mask = flags & PCI_MSI_FLAGS_MASKBIT;
    unsigned int nr_vectors;
    uint8_t log_num_vecs;
    uint8_t log_max_vecs;
    unsigned int vector;
    uint32_t pending;

    if (!msi_present(dev) ||
        !ranges_overlap(addr, len, dev->msi_cap, msi_cap_sizeof(flags))) {
        return;
    }

#ifdef MSI_DEBUG
    MSI_DEV_PRINTF(dev, "addr 0x%"PRIx32" val 0x%"PRIx32" len %d\n",
                   addr, val, len);
    MSI_DEV_PRINTF(dev, "ctrl: 0x%"PRIx16" address: 0x%"PRIx32,
                   flags,
                   pci_get_long(dev->config + msi_address_lo_off(dev)));
    if (msi64bit) {
        fprintf(stderr, " address-hi: 0x%"PRIx32,
                pci_get_long(dev->config + msi_address_hi_off(dev)));
    }
    fprintf(stderr, " data: 0x%"PRIx16,
            pci_get_word(dev->config + msi_data_off(dev, msi64bit)));
    if (flags & PCI_MSI_FLAGS_MASKBIT) {
        fprintf(stderr, " mask 0x%"PRIx32" pending 0x%"PRIx32,
                pci_get_long(dev->config + msi_mask_off(dev, msi64bit)),
                pci_get_long(dev->config + msi_pending_off(dev, msi64bit)));
    }
    fprintf(stderr, "\n");
#endif

    if (!(flags & PCI_MSI_FLAGS_ENABLE)) {
        return;
    }

    /*
     * Now MSI is enabled, clear INTx# interrupts.
     * the driver is prohibited from writing enable bit to mask
     * a service request. But the guest OS could do this.
     * So we just discard the interrupts as moderate fallback.
     *
     * 6.8.3.3. Enabling Operation
     *   While enabled for MSI or MSI-X operation, a function is prohibited
     *   from using its INTx# pin (if implemented) to request
     *   service (MSI, MSI-X, and INTx# are mutually exclusive).
     */
    pci_device_deassert_intx(dev);

    /*
     * nr_vectors might be set bigger than capable. So clamp it.
     * This is not legal by spec, so we can do anything we like,
     * just don't crash the host
     */
    log_num_vecs =
        (flags & PCI_MSI_FLAGS_QSIZE) >> ctz32(PCI_MSI_FLAGS_QSIZE);
    log_max_vecs =
        (flags & PCI_MSI_FLAGS_QMASK) >> ctz32(PCI_MSI_FLAGS_QMASK);
    if (log_num_vecs > log_max_vecs) {
        flags &= ~PCI_MSI_FLAGS_QSIZE;
        flags |= log_max_vecs << ctz32(PCI_MSI_FLAGS_QSIZE);
        pci_set_word(dev->config + msi_flags_off(dev), flags);
    }

    if (!msi_per_vector_mask) {
        /* if per vector masking isn't supported,
           there is no pending interrupt. */
        return;
    }

    nr_vectors = msi_nr_vectors(flags);

    /* This will discard pending interrupts, if any. */
    pending = pci_get_long(dev->config + msi_pending_off(dev, msi64bit));
    pending &= 0xffffffff >> (PCI_MSI_VECTORS_MAX - nr_vectors);
    pci_set_long(dev->config + msi_pending_off(dev, msi64bit), pending);

    /* deliver pending interrupts which are unmasked */
    for (vector = 0; vector < nr_vectors; ++vector) {
        if (msi_is_masked(dev, vector) || !(pending & (1U << vector))) {
            continue;
        }

        pci_long_test_and_clear_mask(
            dev->config + msi_pending_off(dev, msi64bit), 1U << vector);
        msi_notify(dev, vector);
    }
}

unsigned int msi_nr_vectors_allocated(const PCIDevice *dev)
{
    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
    return msi_nr_vectors(flags);
}