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
|
/*
*
* Copyright (c) 2009, Microsoft Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope 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, write to the Free Software Foundation, Inc., 59 Temple
* Place - Suite 330, Boston, MA 02111-1307 USA.
*
* Authors:
* Haiyang Zhang <haiyangz@microsoft.com>
* Hank Janssen <hjanssen@microsoft.com>
* K. Y. Srinivasan <kys@microsoft.com>
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/hyperv.h>
#include <linux/uio.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include "hyperv_vmbus.h"
void hv_begin_read(struct hv_ring_buffer_info *rbi)
{
rbi->ring_buffer->interrupt_mask = 1;
virt_mb();
}
u32 hv_end_read(struct hv_ring_buffer_info *rbi)
{
rbi->ring_buffer->interrupt_mask = 0;
virt_mb();
/*
* Now check to see if the ring buffer is still empty.
* If it is not, we raced and we need to process new
* incoming messages.
*/
return hv_get_bytes_to_read(rbi);
}
/*
* When we write to the ring buffer, check if the host needs to
* be signaled. Here is the details of this protocol:
*
* 1. The host guarantees that while it is draining the
* ring buffer, it will set the interrupt_mask to
* indicate it does not need to be interrupted when
* new data is placed.
*
* 2. The host guarantees that it will completely drain
* the ring buffer before exiting the read loop. Further,
* once the ring buffer is empty, it will clear the
* interrupt_mask and re-check to see if new data has
* arrived.
*
* KYS: Oct. 30, 2016:
* It looks like Windows hosts have logic to deal with DOS attacks that
* can be triggered if it receives interrupts when it is not expecting
* the interrupt. The host expects interrupts only when the ring
* transitions from empty to non-empty (or full to non full on the guest
* to host ring).
* So, base the signaling decision solely on the ring state until the
* host logic is fixed.
*/
static void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel,
bool kick_q)
{
struct hv_ring_buffer_info *rbi = &channel->outbound;
virt_mb();
if (READ_ONCE(rbi->ring_buffer->interrupt_mask))
return;
/* check interrupt_mask before read_index */
virt_rmb();
/*
* This is the only case we need to signal when the
* ring transitions from being empty to non-empty.
*/
if (old_write == READ_ONCE(rbi->ring_buffer->read_index))
vmbus_setevent(channel);
return;
}
/* Get the next write location for the specified ring buffer. */
static inline u32
hv_get_next_write_location(struct hv_ring_buffer_info *ring_info)
{
u32 next = ring_info->ring_buffer->write_index;
return next;
}
/* Set the next write location for the specified ring buffer. */
static inline void
hv_set_next_write_location(struct hv_ring_buffer_info *ring_info,
u32 next_write_location)
{
ring_info->ring_buffer->write_index = next_write_location;
}
/* Get the next read location for the specified ring buffer. */
static inline u32
hv_get_next_read_location(struct hv_ring_buffer_info *ring_info)
{
u32 next = ring_info->ring_buffer->read_index;
return next;
}
/*
* Get the next read location + offset for the specified ring buffer.
* This allows the caller to skip.
*/
static inline u32
hv_get_next_readlocation_withoffset(struct hv_ring_buffer_info *ring_info,
u32 offset)
{
u32 next = ring_info->ring_buffer->read_index;
next += offset;
next %= ring_info->ring_datasize;
return next;
}
/* Set the next read location for the specified ring buffer. */
static inline void
hv_set_next_read_location(struct hv_ring_buffer_info *ring_info,
u32 next_read_location)
{
ring_info->ring_buffer->read_index = next_read_location;
ring_info->priv_read_index = next_read_location;
}
/* Get the size of the ring buffer. */
static inline u32
hv_get_ring_buffersize(struct hv_ring_buffer_info *ring_info)
{
return ring_info->ring_datasize;
}
/* Get the read and write indices as u64 of the specified ring buffer. */
static inline u64
hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info)
{
return (u64)ring_info->ring_buffer->write_index << 32;
}
/*
* Helper routine to copy to source from ring buffer.
* Assume there is enough room. Handles wrap-around in src case only!!
*/
static u32 hv_copyfrom_ringbuffer(
struct hv_ring_buffer_info *ring_info,
void *dest,
u32 destlen,
u32 start_read_offset)
{
void *ring_buffer = hv_get_ring_buffer(ring_info);
u32 ring_buffer_size = hv_get_ring_buffersize(ring_info);
memcpy(dest, ring_buffer + start_read_offset, destlen);
start_read_offset += destlen;
start_read_offset %= ring_buffer_size;
return start_read_offset;
}
/*
* Helper routine to copy from source to ring buffer.
* Assume there is enough room. Handles wrap-around in dest case only!!
*/
static u32 hv_copyto_ringbuffer(
struct hv_ring_buffer_info *ring_info,
u32 start_write_offset,
void *src,
u32 srclen)
{
void *ring_buffer = hv_get_ring_buffer(ring_info);
u32 ring_buffer_size = hv_get_ring_buffersize(ring_info);
memcpy(ring_buffer + start_write_offset, src, srclen);
start_write_offset += srclen;
start_write_offset %= ring_buffer_size;
return start_write_offset;
}
/* Get various debug metrics for the specified ring buffer. */
void hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info,
struct hv_ring_buffer_debug_info *debug_info)
{
u32 bytes_avail_towrite;
u32 bytes_avail_toread;
if (ring_info->ring_buffer) {
hv_get_ringbuffer_availbytes(ring_info,
&bytes_avail_toread,
&bytes_avail_towrite);
debug_info->bytes_avail_toread = bytes_avail_toread;
debug_info->bytes_avail_towrite = bytes_avail_towrite;
debug_info->current_read_index =
ring_info->ring_buffer->read_index;
debug_info->current_write_index =
ring_info->ring_buffer->write_index;
debug_info->current_interrupt_mask =
ring_info->ring_buffer->interrupt_mask;
}
}
/* Initialize the ring buffer. */
int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
struct page *pages, u32 page_cnt)
{
int i;
struct page **pages_wraparound;
BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE));
memset(ring_info, 0, sizeof(struct hv_ring_buffer_info));
/*
* First page holds struct hv_ring_buffer, do wraparound mapping for
* the rest.
*/
pages_wraparound = kzalloc(sizeof(struct page *) * (page_cnt * 2 - 1),
GFP_KERNEL);
if (!pages_wraparound)
return -ENOMEM;
pages_wraparound[0] = pages;
for (i = 0; i < 2 * (page_cnt - 1); i++)
pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1];
ring_info->ring_buffer = (struct hv_ring_buffer *)
vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, PAGE_KERNEL);
kfree(pages_wraparound);
if (!ring_info->ring_buffer)
return -ENOMEM;
ring_info->ring_buffer->read_index =
ring_info->ring_buffer->write_index = 0;
/* Set the feature bit for enabling flow control. */
ring_info->ring_buffer->feature_bits.value = 1;
ring_info->ring_size = page_cnt << PAGE_SHIFT;
ring_info->ring_datasize = ring_info->ring_size -
sizeof(struct hv_ring_buffer);
spin_lock_init(&ring_info->ring_lock);
return 0;
}
/* Cleanup the ring buffer. */
void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
{
vunmap(ring_info->ring_buffer);
}
/* Write to the ring buffer. */
int hv_ringbuffer_write(struct vmbus_channel *channel,
struct kvec *kv_list, u32 kv_count, bool lock,
bool kick_q)
{
int i = 0;
u32 bytes_avail_towrite;
u32 totalbytes_towrite = 0;
u32 next_write_location;
u32 old_write;
u64 prev_indices = 0;
unsigned long flags = 0;
struct hv_ring_buffer_info *outring_info = &channel->outbound;
for (i = 0; i < kv_count; i++)
totalbytes_towrite += kv_list[i].iov_len;
totalbytes_towrite += sizeof(u64);
if (lock)
spin_lock_irqsave(&outring_info->ring_lock, flags);
bytes_avail_towrite = hv_get_bytes_to_write(outring_info);
/*
* If there is only room for the packet, assume it is full.
* Otherwise, the next time around, we think the ring buffer
* is empty since the read index == write index.
*/
if (bytes_avail_towrite <= totalbytes_towrite) {
if (lock)
spin_unlock_irqrestore(&outring_info->ring_lock, flags);
return -EAGAIN;
}
/* Write to the ring buffer */
next_write_location = hv_get_next_write_location(outring_info);
old_write = next_write_location;
for (i = 0; i < kv_count; i++) {
next_write_location = hv_copyto_ringbuffer(outring_info,
next_write_location,
kv_list[i].iov_base,
kv_list[i].iov_len);
}
/* Set previous packet start */
prev_indices = hv_get_ring_bufferindices(
|