summaryrefslogtreecommitdiffstats
path: root/fs/exofs/ios.c
blob: 3cc0dd3f0eb261c537db1aee49cfdf46c9aa5642 (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
/*
 * Copyright (C) 2005, 2006
 * Avishay Traeger (avishay@gmail.com)
 * Copyright (C) 2008, 2009
 * Boaz Harrosh <bharrosh@panasas.com>
 *
 * This file is part of exofs.
 *
 * exofs 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.  Since it is based on ext2, and the only
 * valid version of GPL for the Linux kernel is version 2, the only valid
 * version of GPL for exofs is version 2.
 *
 * exofs 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 exofs; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */

#include <scsi/scsi_device.h>

#include "exofs.h"

#define EXOFS_DBGMSG2(M...) do {} while (0)
/* #define EXOFS_DBGMSG2 EXOFS_DBGMSG */

void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], const struct osd_obj_id *obj)
{
	osd_sec_init_nosec_doall_caps(cred_a, obj, false, true);
}

int exofs_read_kern(struct osd_dev *od, u8 *cred, struct osd_obj_id *obj,
		    u64 offset, void *p, unsigned length)
{
	struct osd_request *or = osd_start_request(od, GFP_KERNEL);
/*	struct osd_sense_info osi = {.key = 0};*/
	int ret;

	if (unlikely(!or)) {
		EXOFS_DBGMSG("%s: osd_start_request failed.\n", __func__);
		return -ENOMEM;
	}
	ret = osd_req_read_kern(or, obj, offset, p, length);
	if (unlikely(ret)) {
		EXOFS_DBGMSG("%s: osd_req_read_kern failed.\n", __func__);
		goto out;
	}

	ret = osd_finalize_request(or, 0, cred, NULL);
	if (unlikely(ret)) {
		EXOFS_DBGMSG("Faild to osd_finalize_request() => %d\n", ret);
		goto out;
	}

	ret = osd_execute_request(or);
	if (unlikely(ret))
		EXOFS_DBGMSG("osd_execute_request() => %d\n", ret);
	/* osd_req_decode_sense(or, ret); */

out:
	osd_end_request(or);
	return ret;
}

int exofs_get_io_state(struct exofs_sb_info *sbi, struct exofs_io_state** pios)
{
	struct exofs_io_state *ios;

	/*TODO: Maybe use kmem_cach per sbi of size
	 * exofs_io_state_size(sbi->s_numdevs)
	 */
	ios = kzalloc(exofs_io_state_size(sbi->s_numdevs), GFP_KERNEL);
	if (unlikely(!ios)) {
		EXOFS_DBGMSG("Faild kzalloc bytes=%d\n",
			     exofs_io_state_size(sbi->s_numdevs));
		*pios = NULL;
		return -ENOMEM;
	}

	ios->sbi = sbi;
	ios->obj.partition = sbi->s_pid;
	*pios = ios;
	return 0;
}

void exofs_put_io_state(struct exofs_io_state *ios)
{
	if (ios) {
		unsigned i;

		for (i = 0; i < ios->numdevs; i++) {
			struct exofs_per_dev_state *per_dev = &ios->per_dev[i];

			if (per_dev->or)
				osd_end_request(per_dev->or);
			if (per_dev->bio)
				bio_put(per_dev->bio);
		}

		kfree(ios);
	}
}

static void _sync_done(struct exofs_io_state *ios, void *p)
{
	struct completion *waiting = p;

	complete(waiting);
}

static void _last_io(struct kref *kref)
{
	struct exofs_io_state *ios = container_of(
					kref, struct exofs_io_state, kref);

	ios->done(ios, ios->private);
}

static void _done_io(struct osd_request *or, void *p)
{
	struct exofs_io_state *ios = p;

	kref_put(&ios->kref, _last_io);
}

static int exofs_io_execute(struct exofs_io_state *ios)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	bool sync = (ios->done == NULL);
	int i, ret;

	if (sync) {
		ios->done = _sync_done;
		ios->private = &wait;
	}

	for (i = 0; i < ios->numdevs; i++) {
		struct osd_request *or = ios->per_dev[i].or;
		if (unlikely(!or))
			continue;

		ret = osd_finalize_request(or, 0, ios->cred, NULL);
		if (unlikely(ret)) {
			EXOFS_DBGMSG("Faild to osd_finalize_request() => %d\n",
				     ret);
			return ret;
		}
	}

	kref_init(&ios->kref);

	for (i = 0; i < ios->numdevs; i++) {
		struct osd_request *or = ios->per_dev[i].or;
		if (unlikely(!or))
			continue;

		kref_get(&ios->kref);
		osd_execute_request_async(or, _done_io, ios);
	}

	kref_put(&ios->kref, _last_io);
	ret = 0;

	if (sync) {
		wait_for_completion(&wait);
		ret = exofs_check_io(ios, NULL);
	}
	return ret;
}

int exofs_check_io(struct exofs_io_state *ios, u64 *resid)
{
	enum osd_err_priority acumulated_osd_err = 0;
	int acumulated_lin_err = 0;
	int i;

	for (i = 0; i < ios->numdevs; i++) {
		struct osd_sense_info osi;
		int ret = osd_req_decode_sense(ios->per_dev[i].or, &osi);

		if (likely(!ret))
			continue;

		if (unlikely(ret == -EFAULT)) {
			EXOFS_DBGMSG("%s: EFAULT Need page clear\n", __func__);
			/*FIXME: All the pages in this device range should:
			 *	clear_highpage(page);
			 */
		}

		if (osi.osd_err_pri >= acumulated_osd_err) {
			acumulated_osd_err = osi.osd_err_pri;
			acumulated_lin_err = ret;
		}
	}

	/* TODO: raid specific residual calculations */
	if (resid) {
		if (likely(!acumulated_lin_err))
			*resid = 0;
		else
			*resid = ios->length;
	}

	return acumulated_lin_err;
}

int exofs_sbi_create(struct exofs_io_state *ios)
{
	int i, ret;

	for (i = 0; i < ios->sbi->s_numdevs; i++) {
		struct osd_request *or;

		or = osd_start_request(ios->sbi->s_ods[i], GFP_KERNEL);
		if (unlikely(!or)) {
			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
			ret = -ENOMEM;
			goto out;
		}
		ios->per_dev[i].or = or;
		ios->numdevs++;

		osd_req_create_object(or, &ios->obj);
	}
	ret = exofs_io_execute(ios);

out:
	return ret;
}

int exofs_sbi_remove(struct exofs_io_state *ios)
{
	int i, ret;

	for (i = 0; i < ios->sbi->s_numdevs; i++) {
		struct osd_request *or;

		or = osd_start_request(ios->sbi->s_ods[i], GFP_KERNEL);
		if (unlikely(!or)) {
			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
			ret = -ENOMEM;
			goto out;
		}
		ios->per_dev[i].or = or;
		ios->numdevs++;

		osd_req_remove_object(or, &ios->obj);
	}
	ret = exofs_io_execute(ios);

out:
	return ret;
}

int exofs_sbi_write(struct exofs_io_state *ios)
{
	int i, ret;

	for (i = 0; i < ios->sbi->s_numdevs; i++) {
		struct osd_request *or;

		or = osd_start_request(ios->sbi->s_ods[i], GFP_KERNEL);
		if (unlikely(!or)) {
			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
			ret = -ENOMEM;
			goto out;
		}
		ios->per_dev[i].or = or;
		ios->numdevs++;

		if (ios->bio) {
			struct bio *bio;

			if (i != 0) {
				bio = bio_kmalloc(GFP_KERNEL,
						  ios->bio->bi_max_vecs);
				if (unlikely(!bio)) {
					EXOFS_DBGMSG(
					      "Faild to allocate BIO size=%u\n",
					      ios->bio->bi_max_vecs);
					ret = -ENOMEM;
					goto out;
				}

				__bio_clone(bio, ios->bio);
				bio->bi_bdev = NULL;
				bio->bi_next = NULL;
				ios->per_dev[i].bio =  bio;
			} else {
				bio = ios->bio;
			}

			osd_req_write(or, &ios->obj, ios->offset, bio,
				      ios->length);
			EXOFS_DBGMSG("write(0x%llx) offset=0x%llx "
				      "length=0x%llx dev=%d\n",
				     _LLU(ios->obj.id), _LLU(ios->offset),
				     _LLU(ios->length), i);
		} else if (ios->kern_buff) {
			osd_req_write_kern(or, &ios->obj, ios->offset,
					   ios->kern_buff, ios->length);
			EXOFS_DBGMSG2("write_kern(0x%llx) offset=0x%llx "
				      "length=0x%llx dev=%d\n",
				     _LLU(ios->obj.id), _LLU(ios->offset),
				     _LLU(ios->length), i);
		} else {
			osd_req_set_attributes(or, &ios->obj);
			EXOFS_DBGMSG2("obj(0x%llx) set_attributes=%d dev=%d\n",
				     _LLU(ios->obj.id), ios->out_attr_len, i);
		}

		if (ios->out_attr)
			osd_req_add_set_attr_list(or, ios->out_attr,
						  ios->out_attr_len);

		if (ios->in_attr)
			osd_req_add_get_attr_list(or, ios->in_attr,
						  ios->in_attr_len);
	}
	ret = exofs_io_execute(ios);

out:
	return ret;
}

int exofs_sbi_read(struct exofs_io_state *ios)
{
	int i, ret;

	for (i = 0; i < 1; i++) {
		struct osd_request *or;
		unsigned first_dev = (unsigned)ios->obj.id;

		first_dev %= ios->sbi->s_numdevs;
		or = osd_start_request(ios->sbi->s_ods[first_dev], GFP_KERNEL);
		if (unlikely(!or)) {
			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
			ret = -ENOMEM;
			goto out;
		}
		ios->per_dev[i].or = or;
		ios->numdevs++;

		if (ios->bio) {
			osd_req_read(or, &ios->obj, ios->offset, ios->bio,
				     ios->length);
			EXOFS_DBGMSG("read(0x%llx) offset=0x%llx length=0x%llx"
				      " dev=%d\n", _LLU(ios->obj.id),
				     _LLU(ios->offset),
				     _LLU(ios->length),
				     first_dev);
		} else if (ios->kern_buff) {
			osd_req_read_kern(or, &ios->obj, ios->offset,
					   ios->kern_buff, ios->length);
			EXOFS_DBGMSG2("read_kern(0x%llx) offset=0x%llx "
				      "length=0x%llx dev=%d\n",
				     _LLU(ios->obj.id),
				     _LLU(ios->offset),
				     _LLU(ios->length),
				     first_dev);
		} else {
			osd_req_get_attributes(or, &ios->obj);
			EXOFS_DBGMSG2("obj(0x%llx) get_attributes=%d dev=%d\n",
				     _LLU(ios->obj.id), ios->in_attr_len,
				     first_dev);
		}

		if (ios->out_attr)
			osd_req_add_set_attr_list(or, ios->out_attr,
						  ios->out_attr_len);

		if (ios->in_attr)
			osd_req_add_get_attr_list(or, ios->in_attr,
						  ios->in_attr_len);
	}
	ret = exofs_io_execute(ios);

out:
	return ret;
}

int extract_attr_from_ios(struct exofs_io_state *ios, struct osd_attr *attr)
{
	struct osd_attr cur_attr = {.attr_page = 0}; /* start with zeros */
	void *iter = NULL;
	int nelem;

	do {
		nelem = 1;
		osd_req_decode_get_attr_list(ios->per_dev[0].or,
					     &cur_attr, &nelem, &iter);
		if ((cur_attr.attr_page == attr->attr_page) &&
		    (cur_attr.attr_id == attr->attr_id)) {
			attr->len = cur_attr.len;
			attr->val_ptr = cur_attr.val_ptr;
			return 0;
		}
	} while (iter);

	return -EIO;
}

int exofs_oi_truncate(struct exofs_i_info *oi, u64 size)
{
	struct exofs_sb_info *sbi = oi->vfs_inode.i_sb->s_fs_info;
	struct exofs_io_state *ios;
	struct osd_attr attr;
	__be64 newsize;
	int i, ret;

	if (exofs_get_io_state(sbi, &ios))
		return -ENOMEM;

	ios->obj.id = exofs_oi_objno(oi);
	ios->cred = oi->i_cred;

	newsize = cpu_to_be64(size);
	attr = g_attr_logical_length;
	attr.val_ptr = &newsize;

	for (i = 0; i < sbi->s_numdevs; i++) {
		struct osd_request *or;

		or = osd_start_request(sbi->s_ods[i], GFP_KERNEL);
		if (unlikely(!or)) {
			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
			ret = -ENOMEM;
			goto out;
		}
		ios->per_dev[i].or = or;
		ios->numdevs++;

		osd_req_set_attributes(or, &ios->obj);
		osd_req_add_set_attr_list(or, &attr, 1);
	}
	ret = exofs_io_execute(ios);

out:
	exofs_put_io_state(ios);
	return ret;
}
OpenPOWER on IntegriCloud