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
|
/*
* 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.
*/
#include "hw.h"
#include "msix.h"
#include "pci.h"
/* Declaration from linux/pci_regs.h */
#define PCI_CAP_ID_MSIX 0x11 /* MSI-X */
#define PCI_MSIX_FLAGS 2 /* Table at lower 11 bits */
#define PCI_MSIX_FLAGS_QSIZE 0x7FF
#define PCI_MSIX_FLAGS_ENABLE (1 << 15)
#define PCI_MSIX_FLAGS_BIRMASK (7 << 0)
/* MSI-X capability structure */
#define MSIX_TABLE_OFFSET 4
#define MSIX_PBA_OFFSET 8
#define MSIX_CAP_LENGTH 12
/* MSI enable bit is in byte 1 in FLAGS register */
#define MSIX_ENABLE_OFFSET (PCI_MSIX_FLAGS + 1)
#define MSIX_ENABLE_MASK (PCI_MSIX_FLAGS_ENABLE >> 8)
/* MSI-X table format */
#define MSIX_MSG_ADDR 0
#define MSIX_MSG_UPPER_ADDR 4
#define MSIX_MSG_DATA 8
#define MSIX_VECTOR_CTRL 12
#define MSIX_ENTRY_SIZE 16
#define MSIX_VECTOR_MASK 0x1
/* How much space does an MSIX table need. */
/* The spec requires giving the table structure
* a 4K aligned region all by itself. Align it to
* target pages so that drivers can do passthrough
* on the rest of the region. */
#define MSIX_PAGE_SIZE TARGET_PAGE_ALIGN(0x1000)
/* Reserve second half of the page for pending bits */
#define MSIX_PAGE_PENDING (MSIX_PAGE_SIZE / 2)
#define MSIX_MAX_ENTRIES 32
#ifdef MSIX_DEBUG
#define DEBUG(fmt, ...) \
do { \
fprintf(stderr, "%s: " fmt, __func__ , __VA_ARGS__); \
} while (0)
#else
#define DEBUG(fmt, ...) do { } while(0)
#endif
/* Flag for interrupt controller to declare MSI-X support */
int msix_supported;
/* Add MSI-X capability to the config space for the device. */
/* Given a bar and its size, add MSI-X table on top of it
* and fill MSI-X capability in the config space.
* Original bar size must be a power of 2 or 0.
* New bar size is returned. */
static int msix_add_config(struct PCIDevice *pdev, unsigned short nentries,
unsigned bar_nr, unsigned bar_size)
{
int config_offset;
uint8_t *config;
uint32_t new_size;
if (nentries < 1 || nentries > PCI_MSIX_FLAGS_QSIZE + 1)
return -EINVAL;
if (bar_size > 0x80000000)
return -ENOSPC;
/* Add space for MSI-X structures */
if (!bar_size)
new_size = MSIX_PAGE_SIZE;
else if (bar_size < MSIX_PAGE_SIZE) {
bar_size = MSIX_PAGE_SIZE;
new_size = MSIX_PAGE_SIZE * 2;
} else
new_size = bar_size * 2;
pdev->msix_bar_size = new_size;
config_offset = pci_add_capability(pdev, PCI_CAP_ID_MSIX, MSIX_CAP_LENGTH);
if (config_offset < 0)
return config_offset;
config = pdev->config + config_offset;
pci_set_word(config + PCI_MSIX_FLAGS, nentries - 1);
/* Table on top of BAR */
pci_set_long(config + MSIX_TABLE_OFFSET, bar_size | bar_nr);
/* Pending bits on top of that */
pci_set_long(config + MSIX_PBA_OFFSET, (bar_size + MSIX_PAGE_PENDING) |
bar_nr);
pdev->msix_cap = config_offset;
/* Make flags bit writeable. */
pdev->wmask[config_offset + MSIX_ENABLE_OFFSET] |= MSIX_ENABLE_MASK;
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;
}
/* 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_ENABLE_OFFSET;
if (addr + len <= enable_pos || addr > enable_pos)
return;
if (msix_enabled(dev))
qemu_set_irq(dev->irq[0], 0);
}
static uint32_t msix_mmio_readl(void *opaque, target_phys_addr_t addr)
{
PCIDevice *dev = opaque;
unsigned int offset = addr & (MSIX_PAGE_SIZE - 1);
void *page = dev->msix_table_page;
uint32_t val = 0;
memcpy(&val, (void *)((char *)page + offset), 4);
return val;
}
static uint32_t msix_mmio_read_unallowed(void *opaque, target_phys_addr_t addr)
{
fprintf(stderr, "MSI-X: only dword read is allowed!\n");
return 0;
}
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_table_page + MSIX_PAGE_PENDING + 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 int msix_is_masked(PCIDevice *dev, int vector)
{
unsigned offset = vector * MSIX_ENTRY_SIZE + MSIX_VECTOR_CTRL;
return dev->msix_table_page[offset] & MSIX_VECTOR_MASK;
}
static void msix_mmio_writel(void *opaque, target_phys_addr_t addr,
uint32_t val)
{
PCIDevice *dev = opaque;
unsigned int offset = addr & (MSIX_PAGE_SIZE - 1);
int vector = offset / MSIX_ENTRY_SIZE;
memcpy(dev->msix_table_page + offset, &val, 4);
if (!msix_is_masked(dev, vector) && msix_is_pending(dev, vector)) {
msix_clr_pending(dev, vector);
msix_notify(dev, vector);
}
}
static void msix_mmio_write_unallowed(void *opaque, target_phys_addr_t addr,
uint32_t val)
{
fprintf(stderr, "MSI-X: only dword write is allowed!\n");
}
static CPUWriteMemoryFunc *msix_mmio_write[] = {
msix_mmio_write_unallowed, msix_mmio_write_unallowed, msix_mmio_writel
};
static CPUReadMemoryFunc *msix_mmio_read[] = {
msix_mmio_read_unallowed, msix_mmio_read_unallowed, msix_mmio_readl
};
/* Should be called from device's map method. */
void msix_mmio_map(PCIDevice *d, int region_num,
uint32_t addr, uint32_t size, int type)
{
uint8_t *config = d->config + d->msix_cap;
uint32_t table = pci_get_long(config + MSIX_TABLE_OFFSET);
uint32_t offset = table & ~(MSIX_PAGE_SIZE - 1);
/* TODO: for assigned devices, we'll want to make it possible to map
* pending bits separately in case they are in a separate bar. */
int table_bir = table & PCI_MSIX_FLAGS_BIRMASK;
if (table_bir != region_num)
return;
if (size <= offset)
return;
cpu_register_physical_memory(addr + offset, size - offset,
d->msix_mmio_index);
}
/* Initialize the MSI-X structures. Note: if MSI-X is supported, BAR size is
* modified, it should be retrieved with msix_bar_size. */
int msix_init(struct PCIDevice *dev, unsigned short nentries,
unsigned bar_nr, unsigned bar_size)
{
int ret;
/* Nothing to do if MSI is not supported by interrupt controller */
if (!msix_supported)
return -ENOTSUP;
if (nentries > MSIX_MAX_ENTRIES)
return -EINVAL;
dev->msix_entry_used = qemu_mallocz(MSIX_MAX_ENTRIES *
sizeof *dev->msix_entry_used);
dev->msix_table_page = qemu_mallocz(MSIX_PAGE_SIZE);
dev->msix_mmio_index = cpu_register_io_memory(msix_mmio_read,
msix_mmio_write, dev);
if (dev->msix_mmio_index == -1) {
ret = -EBUSY;
goto err_index;
}
dev->msix_entries_nr = nentries;
ret = msix_add_config(dev, nentries, bar_nr, bar_size);
if (ret)
goto err_config;
dev->cap_present |= QEMU_PCI_CAP_MSIX;
return 0;
err_config:
cpu_unregister_io_memory(dev->msix_mmio_index);
err_index:
qemu_free(dev->msix_table_page);
dev->msix_table_page = NULL;
qemu_free(dev->msix_entry_used);
dev->msix_entry_used = NULL;
return ret;
}
/* Clean up resources for the device. */
int msix_uninit(PCIDevice *dev)
{
if (!(dev->cap_present & QEMU_PCI_CAP_MSIX))
return 0;
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;
cpu_unregister_io_memory(dev->msix_mmio_index);
qemu_free(dev->msix_table_page);
dev->msix_table_page = NULL;
qemu_free(dev->msix_entry_used);
dev->msix_entry_used = NULL;
dev->cap_present &= ~QEMU_PCI_CAP_MSIX;
return 0;
}
void msix_save(PCIDevice *dev, QEMUFile *f)
{
unsigned nentries = (pci_get_word(dev->config + PCI_MSIX_FLAGS) &
PCI_MSIX_FLAGS_QSIZE) + 1;
qemu_put_buffer(f, dev->msix_table_page, nentries * MSIX_ENTRY_SIZE);
qemu_put_buffer(f, dev->msix_table_page + MSIX_PAGE_PENDING,
(nentries + 7) / 8);
}
/* Should be called after restoring the config space. */
void msix_load(PCIDevice *dev, QEMUFile *f)
{
unsigned n = dev->msix_entries_nr;
if (!dev->cap_present & QEMU_PCI_CAP_MSIX)
return;
qemu_get_buffer(f, dev->msix_table_page, n * MSIX_ENTRY_SIZE);
qemu_get_buffer(f, dev->msix_table_page + MSIX_PAGE_PENDING, (n + 7) / 8);
}
/* 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_ENABLE_OFFSET] &
MSIX_ENABLE_MASK);
}
/* Size of bar where MSI-X table resides, or 0 if MSI-X not supported. */
uint32_t msix_bar_size(PCIDevice *dev)
{
return (dev->cap_present & QEMU_PCI_CAP_MSIX) ?
dev->msix_bar_size : 0;
}
/* Send an MSI-X message */
void msix_notify(PCIDevice *dev, unsigned vector)
{
uint8_t *table_entry = dev->msix_table_page + vector * MSIX_ENTRY_SIZE;
uint64_t address;
uint32_t data;
if (vector >= dev->msix_entries_nr || !dev->msix_entry_used[vector])
return;
if (msix_is_masked(dev, vector)) {
msix_set_pending(dev, vector);
return;
}
address = pci_get_long(table_entry + MSIX_MSG_UPPER_ADDR);
address = (address << 32) | pci_get_long(table_entry + MSIX_MSG_ADDR);
data = pci_get_long(table_entry + MSIX_MSG_DATA);
stl_phys(address, data);
}
void msix_reset(PCIDevice *dev)
{
if (!(dev->cap_present & QEMU_PCI_CAP_MSIX))
return;
msix_free_irq_entries(dev);
dev->config[dev->msix_cap + MSIX_ENABLE_OFFSET] &= MSIX_ENABLE_MASK;
memset(dev->msix_table_page, 0, MSIX_PAGE_SIZE);
}
/* 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])
--dev->msix_entry_used[vector];
}
|