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
|
/*
* linux/fs/nfs/blocklayout/blocklayoutdev.c
*
* Device operations for the pnfs nfs4 file layout driver.
*
* Copyright (c) 2006 The Regents of the University of Michigan.
* All rights reserved.
*
* Andy Adamson <andros@citi.umich.edu>
* Fred Isaman <iisaman@umich.edu>
*
* permission is granted to use, copy, create derivative works and
* redistribute this software and such derivative works for any purpose,
* so long as the name of the university of michigan is not used in
* any advertising or publicity pertaining to the use or distribution
* of this software without specific, written prior authorization. if
* the above copyright notice or any other identification of the
* university of michigan is included in any copy of any portion of
* this software, then the disclaimer below must also be included.
*
* this software is provided as is, without representation from the
* university of michigan as to its fitness for any purpose, and without
* warranty by the university of michigan of any kind, either express
* or implied, including without limitation the implied warranties of
* merchantability and fitness for a particular purpose. the regents
* of the university of michigan shall not be liable for any damages,
* including special, indirect, incidental, or consequential damages,
* with respect to any claim arising out or in connection with the use
* of the software, even if it has been or is hereafter advised of the
* possibility of such damages.
*/
#include <linux/module.h>
#include <linux/buffer_head.h> /* __bread */
#include <linux/genhd.h>
#include <linux/blkdev.h>
#include <linux/hash.h>
#include "blocklayout.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
static int decode_sector_number(__be32 **rp, sector_t *sp)
{
uint64_t s;
*rp = xdr_decode_hyper(*rp, &s);
if (s & 0x1ff) {
printk(KERN_WARNING "%s: sector not aligned\n", __func__);
return -1;
}
*sp = s >> SECTOR_SHIFT;
return 0;
}
/* Open a block_device by device number. */
struct block_device *nfs4_blkdev_get(dev_t dev)
{
struct block_device *bd;
dprintk("%s enter\n", __func__);
bd = blkdev_get_by_dev(dev, FMODE_READ, NULL);
if (IS_ERR(bd))
goto fail;
return bd;
fail:
dprintk("%s failed to open device : %ld\n",
__func__, PTR_ERR(bd));
return NULL;
}
/*
* Release the block device
*/
int nfs4_blkdev_put(struct block_device *bdev)
{
dprintk("%s for device %d:%d\n", __func__, MAJOR(bdev->bd_dev),
MINOR(bdev->bd_dev));
return blkdev_put(bdev, FMODE_READ);
}
static struct bl_dev_msg bl_mount_reply;
ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
size_t mlen)
{
if (mlen != sizeof (struct bl_dev_msg))
return -EINVAL;
if (copy_from_user(&bl_mount_reply, src, mlen) != 0)
return -EFAULT;
wake_up(&bl_wq);
return mlen;
}
void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
{
if (msg->errno >= 0)
return;
wake_up(&bl_wq);
}
/*
* Decodes pnfs_block_deviceaddr4 which is XDR encoded in dev->dev_addr_buf.
*/
struct pnfs_block_dev *
nfs4_blk_decode_device(struct nfs_server *server,
struct pnfs_device *dev)
{
struct pnfs_block_dev *rv;
struct block_device *bd = NULL;
struct rpc_pipe_msg msg;
struct bl_msg_hdr bl_msg = {
.type = BL_DEVICE_MOUNT,
.totallen = dev->mincount,
};
uint8_t *dataptr;
DECLARE_WAITQUEUE(wq, current);
struct bl_dev_msg *reply = &bl_mount_reply;
int offset, len, i, rc;
dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
dev->mincount);
memset(&msg, 0, sizeof(msg));
msg.data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
if (!msg.data) {
rv = ERR_PTR(-ENOMEM);
goto out;
}
memcpy(msg.data, &bl_msg, sizeof(bl_msg));
dataptr = (uint8_t *) msg.data;
len = dev->mincount;
offset = sizeof(bl_msg);
for (i = 0; len > 0; i++) {
memcpy(&dataptr[offset], page_address(dev->pages[i]),
len < PAGE_CACHE_SIZE ? len : PAGE_CACHE_SIZE);
len -= PAGE_CACHE_SIZE;
offset += PAGE_CACHE_SIZE;
}
msg.len = sizeof(bl_msg) + dev->mincount;
dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
add_wait_queue(&bl_wq, &wq);
rc = rpc_queue_upcall(bl_device_pipe->d_inode, &msg);
if (rc < 0) {
remove_wait_queue(&bl_wq, &wq);
rv = ERR_PTR(rc);
goto out;
}
set_current_state(TASK_UNINTERRUPTIBLE);
schedule();
__set_current_state(TASK_RUNNING);
remove_wait_queue(&bl_wq, &wq);
if (reply->status != BL_DEVICE_REQUEST_PROC) {
dprintk("%s failed to open device: %d\n",
__func__, reply->status);
rv = ERR_PTR(-EINVAL);
goto out;
}
bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor));
if (IS_ERR(bd)) {
rc = PTR_ERR(bd);
dprintk("%s failed to open device : %d\n", __func__, rc);
rv = ERR_PTR(rc);
goto out;
}
rv = kzalloc(sizeof(*rv), GFP_NOFS);
if (!rv) {
rv = ERR_PTR(-ENOMEM);
goto out;
}
rv->bm_mdev = bd;
memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid));
dprintk("%s Created device %s with bd_block_size %u\n",
__func__,
bd->bd_disk->disk_name,
bd->bd_block_size);
out:
kfree(msg.data);
return rv;
}
/* Map deviceid returned by the server to constructed block_device */
static struct block_device *translate_devid(struct pnfs_layout_hdr *lo,
struct nfs4_deviceid *id)
{
struct block_device *rv = NULL;
struct block_mount_id *mid;
struct pnfs_block_dev *dev;
dprintk("%s enter, lo=%p, id=%p\n", __func__, lo, id);
mid = BLK_ID(lo);
spin_lock(&mid->bm_lock);
list_for_each_entry(dev, &mid->bm_devlist, bm_node) {
if (memcmp(id->data, dev->bm_mdevid.data,
NFS4_DEVICEID4_SIZE) == 0) {
rv = dev->bm_mdev;
goto out;
}
}
out:
spin_unlock(&mid->bm_lock);
dprintk("%s returning %p\n", __func__, rv);
return rv;
}
/* Tracks info needed to ensure extents in layout obey constraints of spec */
struct layout_verification {
u32 mode; /* R or RW */
u64 start; /* Expected start of next non-COW extent */
u64 inval; /* Start of INVAL coverage */
u64 cowread; /* End of COW read coverage */
};
/* Verify the extent meets the layout requirements of the pnfs-block draft,
* section 2.3.1.
*/
static int verify_extent(struct pnfs_block_extent *be,
struct layout_verification *lv)
{
if (lv->mode == IOMODE_READ) {
if (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
be->be_state == PNFS_BLOCK_INVALID_DATA)
return -EIO;
if (be->be_f_offset != lv->start)
return -EIO;
lv->start += be->be_length;
return 0;
}
/* lv->mode == IOMODE_RW */
if (be->be_state == PNFS_BLOCK_READWRITE_DATA) {
if (be->be_f_offset != lv->start)
return -EIO;
if (lv->cowread > lv->start)
return -EIO;
lv->start += be->be_length;
lv->inval = lv->start;
return 0;
} else if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
if (be->be_f_offset != lv->start)
return -EIO;
lv->start += be->be_length;
return 0;
} else if (be->be_state == PNFS_BLOCK_READ_DATA) {
if (be->be_f_offset > lv->start)
|