summaryrefslogtreecommitdiffstats
path: root/hw/msix.c
blob: 800fc32f0b0e54a05637a8b51510aed7c1a9b236 (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
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
/*
 * MSI-X device support
 *
 * This module includes support for MSI-X in pci devices.
 *
 * Author: Michael S. Tsirkin <mst@redhat.com>
 *
 *  Copyright (c) 2009, Red Hat Inc, Michael S. Tsirkin (mst@redhat.com)
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 */

#include "hw.h"
#include "msi.h"
#include "msix.h"
#include "pci.h"
#include "range.h"

#define MSIX_CAP_LENGTH 12

/* MSI enable bit and maskall bit are in byte 1 in FLAGS register */
#define MSIX_CONTROL_OFFSET (PCI_MSIX_FLAGS + 1)
#define MSIX_ENABLE_MASK (PCI_MSIX_FLAGS_ENABLE >> 8)
#define MSIX_MASKALL_MASK (PCI_MSIX_FLAGS_MASKALL >> 8)

static MSIMessage msix_get_message(PCIDevice *dev, unsigned vector)
{
    uint8_t *table_entry = dev->msix_table + vector * PCI_MSIX_ENTRY_SIZE;
    MSIMessage msg;

    msg.address = pci_get_quad(table_entry + PCI_MSIX_ENTRY_LOWER_ADDR);
    msg.data = pci_get_long(table_entry + PCI_MSIX_ENTRY_DATA);
    return msg;
}

/*
 * Special API for POWER to configure the vectors through
 * a side channel. Should never be used by devices.
 */
void msix_set_message(PCIDevice *dev, int vector, struct MSIMessage msg)
{
    uint8_t *table_entry = dev->msix_table + vector * PCI_MSIX_ENTRY_SIZE;

    pci_set_quad(table_entry + PCI_MSIX_ENTRY_LOWER_ADDR, msg.address);
    pci_set_long(table_entry + PCI_MSIX_ENTRY_DATA, msg.data);
    table_entry[PCI_MSIX_ENTRY_VECTOR_CTRL] &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
}

static uint8_t msix_pending_mask(int vector)
{
    return 1 << (vector % 8);
}

static uint8_t *msix_pending_byte(PCIDevice *dev, int vector)
{
    return dev->msix_pba + vector / 8;
}

static int msix_is_pending(PCIDevice *dev, int vector)
{
    return *msix_pending_byte(dev, vector) & msix_pending_mask(vector);
}

static void msix_set_pending(PCIDevice *dev, int vector)
{
    *msix_pending_byte(dev, vector) |= msix_pending_mask(vector);
}

static void msix_clr_pending(PCIDevice *dev, int vector)
{
    *msix_pending_byte(dev, vector) &= ~msix_pending_mask(vector);
}

static bool msix_vector_masked(PCIDevice *dev, int vector, bool fmask)
{
    unsigned offset = vector * PCI_MSIX_ENTRY_SIZE + PCI_MSIX_ENTRY_VECTOR_CTRL;
    return fmask || dev->msix_table[offset] & PCI_MSIX_ENTRY_CTRL_MASKBIT;
}

static bool msix_is_masked(PCIDevice *dev, int vector)
{
    return msix_vector_masked(dev, vector, dev->msix_function_masked);
}

static void msix_fire_vector_notifier(PCIDevice *dev,
                                      unsigned int vector, bool is_masked)
{
    MSIMessage msg;
    int ret;

    if (!dev->msix_vector_use_notifier) {
        return;
    }
    if (is_masked) {
        dev->msix_vector_release_notifier(dev, vector);
    } else {
        msg = msix_get_message(dev, vector);
        ret = dev->msix_vector_use_notifier(dev, vector, msg);
        assert(ret >= 0);
    }
}

static void msix_handle_mask_update(PCIDevice *dev, int vector, bool was_masked)
{
    bool is_masked = msix_is_masked(dev, vector);

    if (is_masked == was_masked) {
        return;
    }

    msix_fire_vector_notifier(dev, vector, is_masked);

    if (!is_masked && msix_is_pending(dev, vector)) {
        msix_clr_pending(dev, vector);
        msix_notify(dev, vector);
    }
}

static void msix_update_function_masked(PCIDevice *dev)
{
    dev->msix_function_masked = !msix_enabled(dev) ||
        (dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] & MSIX_MASKALL_MASK);
}

/* Handle MSI-X capability config write. */
void msix_write_config(PCIDevice *dev, uint32_t addr,
                       uint32_t val, int len)
{
    unsigned enable_pos = dev->msix_cap + MSIX_CONTROL_OFFSET;
    int vector;
    bool was_masked;

    if (!msix_present(dev) || !range_covers_byte(addr, len, enable_pos)) {
        return;
    }

    was_masked = dev->msix_function_masked;
    msix_update_function_masked(dev);

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

    pci_device_deassert_intx(dev);

    if (dev->msix_function_masked == was_masked) {
        return;
    }

    for (vector = 0; vector < dev->msix_entries_nr; ++vector) {
        msix_handle_mask_update(dev, vector,
                                msix_vector_masked(dev, vector, was_masked));
    }
}

static uint64_t msix_table_mmio_read(void *opaque, target_phys_addr_t addr,
                                     unsigned size)
{
    PCIDevice *dev = opaque;

    return pci_get_long(dev->msix_table + addr);
}

static void msix_table_mmio_write(void *opaque, target_phys_addr_t addr,
                                  uint64_t val, unsigned size)
{
    PCIDevice *dev = opaque;
    int vector = addr / PCI_MSIX_ENTRY_SIZE;
    bool was_masked;

    was_masked = msix_is_masked(dev, vector);
    pci_set_long(dev->msix_table + addr, val);
    msix_handle_mask_update(dev, vector, was_masked);
}

static const MemoryRegionOps msix_table_mmio_ops = {
    .read = msix_table_mmio_read,
    .write = msix_table_mmio_write,
    /* TODO: MSIX should be LITTLE_ENDIAN. */
    .endianness = DEVICE_NATIVE_ENDIAN,
    .valid = {
        .min_access_size = 4,
        .max_access_size = 4,
    },
};

static uint64_t msix_pba_mmio_read(void *opaque, target_phys_addr_t addr,
                                   unsigned size)
{
    PCIDevice *dev = opaque;

    return pci_get_long(dev->msix_pba + addr);
}

static const MemoryRegionOps msix_pba_mmio_ops = {
    .read = msix_pba_mmio_read,
    /* TODO: MSIX should be LITTLE_ENDIAN. */
    .endianness = DEVICE_NATIVE_ENDIAN,
    .valid = {
        .min_access_size = 4,
        .max_access_size = 4,
    },
};

static void msix_mask_all(struct PCIDevice *dev, unsigned nentries)
{
    int vector;

    for (vector = 0; vector < nentries; ++vector) {
        unsigned offset =
            vector * PCI_MSIX_ENTRY_SIZE + PCI_MSIX_ENTRY_VECTOR_CTRL;
        bool was_masked = msix_is_masked(dev, vector);

        dev->msix_table[offset] |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
        msix_handle_mask_update(dev, vector, was_masked);
    }
}

/* Initialize the MSI-X structures */
int msix_init(struct PCIDevice *dev, unsigned short nentries,
              MemoryRegion *table_bar, uint8_t table_bar_nr,
              unsigned table_offset, MemoryRegion *pba_bar,
              uint8_t pba_bar_nr, unsigned pba_offset, uint8_t cap_pos)
{
    int cap;
    unsigned table_size, pba_size;
    uint8_t *config;

    /* Nothing to do if MSI is not supported by interrupt controller */
    if (!msi_supported) {
        return -ENOTSUP;
    }

    if (nentries < 1 || nentries > PCI_MSIX_FLAGS_QSIZE + 1) {
        return -EINVAL;
    }

    table_size = nentries * PCI_MSIX_ENTRY_SIZE;
    pba_size = QEMU_ALIGN_UP(nentries, 64) / 8;

    /* Sanity test: table & pba don't overlap, fit within BARs, min aligned */
    if ((table_bar_nr == pba_bar_nr &&
         ranges_overlap(table_offset, table_size, pba_offset, pba_size)) ||
        table_offset + table_size > memory_region_size(table_bar) ||
        pba_offset + pba_size > memory_region_size(pba_bar) ||
        (table_offset | pba_offset) & PCI_MSIX_FLAGS_BIRMASK) {
        return -EINVAL;
    }

    cap = pci_add_capability(dev, PCI_CAP_ID_MSIX, cap_pos, MSIX_CAP_LENGTH);
    if (cap < 0) {
        return cap;
    }

    dev->msix_cap = cap;
    dev->cap_present |= QEMU_PCI_CAP_MSIX;
    config = dev->config + cap;

    pci_set_word(config + PCI_MSIX_FLAGS, nentries - 1);
    dev->msix_entries_nr = nentries;
    dev->msix_function_masked = true;

    pci_set_long(config + PCI_MSIX_TABLE, table_offset | table_bar_nr);
    pci_set_long(config + PCI_MSIX_PBA, pba_offset | pba_bar_nr);

    /* Make flags bit writable. */
    dev->wmask[cap + MSIX_CONTROL_OFFSET] |= MSIX_ENABLE_MASK |
                                             MSIX_MASKALL_MASK;

    dev->msix_table = g_malloc0(table_size);
    dev->msix_pba = g_malloc0(pba_size);
    dev->msix_entry_used = g_malloc0(nentries * sizeof *dev->msix_entry_used);

    msix_mask_all(dev, nentries);

    memory_region_init_io(&dev->msix_table_mmio, &msix_table_mmio_ops, dev,
                          "msix-table", table_size);
    memory_region_add_subregion(table_bar, table_offset, &dev->msix_table_mmio);
    memory_region_init_io(&dev->msix_pba_mmio, &msix_pba_mmio_ops, dev,
                          "msix-pba", pba_size);
    memory_region_add_subregion(pba_bar, pba_offset, &dev->msix_pba_mmio);

    return 0;
}

int msix_init_exclusive_bar(PCIDevice *dev, unsigned short nentries,
                            uint8_t bar_nr)
{
    int ret;
    char *name;

    /*
     * Migration compatibility dictates that this remains a 4k
     * BAR with the vector table in the lower half and PBA in
     * the upper half.  Do not use these elsewhere!
     */
#define MSIX_EXCLUSIVE_BAR_SIZE 4096
#define MSIX_EXCLUSIVE_BAR_TABLE_OFFSET 0
#define MSIX_EXCLUSIVE_BAR_PBA_OFFSET (MSIX_EXCLUSIVE_BAR_SIZE / 2)
#define MSIX_EXCLUSIVE_CAP_OFFSET 0

    if (nentries * PCI_MSIX_ENTRY_SIZE > MSIX_EXCLUSIVE_BAR_PBA_OFFSET) {
        return -EINVAL;
    }

    if (asprintf(&name, "%s-msix", dev->name) == -1) {
        return -ENOMEM;
    }

    memory_region_init(&dev->msix_exclusive_bar, name, MSIX_EXCLUSIVE_BAR_SIZE);

    free(name);

    ret = msix_init(dev, nentries, &dev->msix_exclusive_bar, bar_nr,
                    MSIX_EXCLUSIVE_BAR_TABLE_OFFSET, &dev->msix_exclusive_bar,
                    bar_nr, MSIX_EXCLUSIVE_BAR_PBA_OFFSET,
                    MSIX_EXCLUSIVE_CAP_OFFSET);
    if (ret) {
        memory_region_destroy(&dev->msix_exclusive_bar);
        return ret;
    }

    pci_register_bar(dev, bar_nr, PCI_BASE_ADDRESS_SPACE_MEMORY,
                     &dev->msix_exclusive_bar);

    return 0;
}

static void msix_free_irq_entries(PCIDevice *dev)
{
    int vector;

    for (vector = 0; vector < dev->msix_entries_nr; ++vector) {
        dev->msix_entry_used[vector] = 0;
        msix_clr_pending(dev, vector);
    }
}

/* Clean up resources for the device. */
void msix_uninit(PCIDevice *dev, MemoryRegion *table_bar, MemoryRegion *pba_bar)
{
    if (!msix_present(dev)) {
        return;
    }
    pci_del_capability(dev, PCI_CAP_ID_MSIX, MSIX_CAP_LENGTH);
    dev->msix_cap = 0;
    msix_free_irq_entries(dev);
    dev->msix_entries_nr = 0;
    memory_region_del_subregion(pba_bar, &dev->msix_pba_mmio);
    memory_region_destroy(&dev->msix_pba_mmio);
    g_free(dev->msix_pba);
    dev->msix_pba = NULL;
    memory_region_del_subregion(table_bar, &dev->msix_table_mmio);
    memory_region_destroy(&dev->msix_table_mmio);
    g_free(dev->msix_table);
    dev->msix_table = NULL;
    g_free(dev->msix_entry_used);
    dev->msix_entry_used = NULL;
    dev->cap_present &= ~QEMU_PCI_CAP_MSIX;
    return;
}

void msix_uninit_exclusive_bar(PCIDevice *dev)
{
    if (msix_present(dev)) {
        msix_uninit(dev, &dev->msix_exclusive_bar, &dev->msix_exclusive_bar);
        memory_region_destroy(&dev->msix_exclusive_bar);
    }
}

void msix_save(PCIDevice *dev, QEMUFile *f)
{
    unsigned n = dev->msix_entries_nr;

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

    qemu_put_buffer(f, dev->msix_table, n * PCI_MSIX_ENTRY_SIZE);
    qemu_put_buffer(f, dev->msix_pba, (n + 7) / 8);
}

/* Should be called after restoring the config space. */
void msix_load(PCIDevice *dev, QEMUFile *f)
{
    unsigned n = dev->msix_entries_nr;
    unsigned int vector;

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

    msix_free_irq_entries(dev);
    qemu_get_buffer(f, dev->msix_table, n * PCI_MSIX_ENTRY_SIZE);
    qemu_get_buffer(f, dev->msix_pba, (n + 7) / 8);
    msix_update_function_masked(dev);

    for (vector = 0; vector < n; vector++) {
        msix_handle_mask_update(dev, vector, true);
    }
}

/* Does device support MSI-X? */
int msix_present(PCIDevice *dev)
{
    return dev->cap_present & QEMU_PCI_CAP_MSIX;
}

/* Is MSI-X enabled? */
int msix_enabled(PCIDevice *dev)
{
    return (dev->cap_present & QEMU_PCI_CAP_MSIX) &&
        (dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &
         MSIX_ENABLE_MASK);
}

/* Send an MSI-X message */
void msix_notify(PCIDevice *dev, unsigned vector)
{
    MSIMessage msg;

    if (vector >= dev->msix_entries_nr || !dev->msix_entry_used[vector])
        return;
    if (msix_is_masked(dev, vector)) {
        msix_set_pending(dev, vector);
        return;
    }

    msg = msix_get_message(dev, vector);

    stl_le_phys(msg.address, msg.data);
}

void msix_reset(PCIDevice *dev)
{
    if (!msix_present(dev)) {
        return;
    }
    msix_free_irq_entries(dev);
    dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &=
	    ~dev->wmask[dev->msix_cap + MSIX_CONTROL_OFFSET];
    memset(dev->msix_table, 0, dev->msix_entries_nr * PCI_MSIX_ENTRY_SIZE);
    memset(dev->msix_pba, 0, QEMU_ALIGN_UP(dev->msix_entries_nr, 64) / 8);
    msix_mask_all(dev, dev->msix_entries_nr);
}

/* PCI spec suggests that devices make it possible for software to configure
 * less vectors than supported by the device, but does not specify a standard
 * mechanism for devices to do so.
 *
 * We support this by asking devices to declare vectors software is going to
 * actually use, and checking this on the notification path. Devices that
 * don't want to follow the spec suggestion can declare all vectors as used. */

/* Mark vector as used. */
int msix_vector_use(PCIDevice *dev, unsigned vector)
{
    if (vector >= dev->msix_entries_nr)
        return -EINVAL;
    dev->msix_entry_used[vector]++;
    return 0;
}

/* Mark vector as unused. */
void msix_vector_unuse(PCIDevice *dev, unsigned vector)
{
    if (vector >= dev->msix_entries_nr || !dev->msix_entry_used[vector]) {
        return;
    }
    if (--dev->msix_entry_used[vector]) {
        return;
    }
    msix_clr_pending(dev, vector);
}

void msix_unuse_all_vectors(PCIDevice *dev)
{
    if (!msix_present(dev)) {
        return;
    }
    msix_free_irq_entries(dev);
}

unsigned int msix_nr_vectors_allocated(const PCIDevice *dev)
{
    return dev->msix_entries_nr;
}

static int msix_set_notifier_for_vector(PCIDevice *dev, unsigned int vector)
{
    MSIMessage msg;

    if (msix_is_masked(dev, vector)) {
        return 0;
    }
    msg = msix_get_message(dev, vector);
    return dev->msix_vector_use_notifier(dev, vector, msg);
}

static void msix_unset_notifier_for_vector(PCIDevice *dev, unsigned int vector)
{
    if (msix_is_masked(dev, vector)) {
        return;
    }
    dev->msix_vector_release_notifier(dev, vector);
}

int msix_set_vector_notifiers(PCIDevice *dev,
                              MSIVectorUseNotifier use_notifier,
                              MSIVectorReleaseNotifier release_notifier)
{
    int vector, ret;

    assert(use_notifier && release_notifier);

    dev->msix_vector_use_notifier = use_notifier;
    dev->msix_vector_release_notifier = release_notifier;

    if ((dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &
        (MSIX_ENABLE_MASK | MSIX_MASKALL_MASK)) == MSIX_ENABLE_MASK) {
        for (vector = 0; vector < dev->msix_entries_nr; vector++) {
            ret = msix_set_notifier_for_vector(dev, vector);
            if (ret < 0) {
                goto undo;
            }
        }
    }
    return 0;

undo:
    while (--vector >= 0) {
        msix_unset_notifier_for_vector(dev, vector);
    }
    dev->msix_vector_use_notifier = NULL;
    dev->msix_vector_release_notifier = NULL;
    return ret;
}

void msix_unset_vector_notifiers(PCIDevice *dev)
{
    int vector;

    assert(dev->msix_vector_use_notifier &&
           dev->msix_vector_release_notifier);

    if ((dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &
        (MSIX_ENABLE_MASK | MSIX_MASKALL_MASK)) == MSIX_ENABLE_MASK) {
        for (vector = 0; vector < dev->msix_entries_nr; vector++) {
            msix_unset_notifier_for_vector(dev, vector);
        }
    }
    dev->msix_vector_use_notifier = NULL;
    dev->msix_vector_release_notifier = NULL;
}
OpenPOWER on IntegriCloud