summaryrefslogtreecommitdiffstats
path: root/fs/netfs/buffered_read.c
blob: 8742d22dfd2b240ee9695af5c284b5b4b44cbb3c (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
// SPDX-License-Identifier: GPL-2.0-or-later
/* Network filesystem high-level buffered read support.
 *
 * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */

#include <linux/export.h>
#include <linux/task_io_accounting_ops.h>
#include "internal.h"

/*
 * Unlock the folios in a read operation.  We need to set PG_fscache on any
 * folios we're going to write back before we unlock them.
 */
void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
{
	struct netfs_io_subrequest *subreq;
	struct folio *folio;
	unsigned int iopos, account = 0;
	pgoff_t start_page = rreq->start / PAGE_SIZE;
	pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
	bool subreq_failed = false;

	XA_STATE(xas, &rreq->mapping->i_pages, start_page);

	if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) {
		__clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags);
		list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
			__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
		}
	}

	/* Walk through the pagecache and the I/O request lists simultaneously.
	 * We may have a mixture of cached and uncached sections and we only
	 * really want to write out the uncached sections.  This is slightly
	 * complicated by the possibility that we might have huge pages with a
	 * mixture inside.
	 */
	subreq = list_first_entry(&rreq->subrequests,
				  struct netfs_io_subrequest, rreq_link);
	iopos = 0;
	subreq_failed = (subreq->error < 0);

	trace_netfs_rreq(rreq, netfs_rreq_trace_unlock);

	rcu_read_lock();
	xas_for_each(&xas, folio, last_page) {
		unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE;
		unsigned int pgend = pgpos + folio_size(folio);
		bool pg_failed = false;

		for (;;) {
			if (!subreq) {
				pg_failed = true;
				break;
			}
			if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags))
				folio_start_fscache(folio);
			pg_failed |= subreq_failed;
			if (pgend < iopos + subreq->len)
				break;

			account += subreq->transferred;
			iopos += subreq->len;
			if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
				subreq = list_next_entry(subreq, rreq_link);
				subreq_failed = (subreq->error < 0);
			} else {
				subreq = NULL;
				subreq_failed = false;
			}
			if (pgend == iopos)
				break;
		}

		if (!pg_failed) {
			flush_dcache_folio(folio);
			folio_mark_uptodate(folio);
		}

		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
			if (folio_index(folio) == rreq->no_unlock_folio &&
			    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
				_debug("no unlock");
			else
				folio_unlock(folio);
		}
	}
	rcu_read_unlock();

	task_io_account_read(account);
	if (rreq->netfs_ops->done)
		rreq->netfs_ops->done(rreq);
}

static void netfs_cache_expand_readahead(struct netfs_io_request *rreq,
					 loff_t *_start, size_t *_len, loff_t i_size)
{
	struct netfs_cache_resources *cres = &rreq->cache_resources;

	if (cres->ops && cres->ops->expand_readahead)
		cres->ops->expand_readahead(cres, _start, _len, i_size);
}

static void netfs_rreq_expand(struct netfs_io_request *rreq,
			      struct readahead_control *ractl)
{
	/* Give the cache a chance to change the request parameters.  The
	 * resultant request must contain the original region.
	 */
	netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size);

	/* Give the netfs a chance to change the request parameters.  The
	 * resultant request must contain the original region.
	 */
	if (rreq->netfs_ops->expand_readahead)
		rreq->netfs_ops->expand_readahead(rreq);

	/* Expand the request if the cache wants it to start earlier.  Note
	 * that the expansion may get further extended if the VM wishes to
	 * insert THPs and the preferred start and/or end wind up in the middle
	 * of THPs.
	 *
	 * If this is the case, however, the THP size should be an integer
	 * multiple of the cache granule size, so we get a whole number of
	 * granules to deal with.
	 */
	if (rreq->start  != readahead_pos(ractl) ||
	    rreq->len != readahead_length(ractl)) {
		readahead_expand(ractl, rreq->start, rreq->len);
		rreq->start  = readahead_pos(ractl);
		rreq->len = readahead_length(ractl);

		trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl),
				 netfs_read_trace_expanded);
	}
}

/**
 * netfs_readahead - Helper to manage a read request
 * @ractl: The description of the readahead request
 *
 * Fulfil a readahead request by drawing data from the cache if possible, or
 * the netfs if not.  Space beyond the EOF is zero-filled.  Multiple I/O
 * requests from different sources will get munged together.  If necessary, the
 * readahead window can be expanded in either direction to a more convenient
 * alighment for RPC efficiency or to make storage in the cache feasible.
 *
 * The calling netfs must initialise a netfs context contiguous to the vfs
 * inode before calling this.
 *
 * This is usable whether or not caching is enabled.
 */
void netfs_readahead(struct readahead_control *ractl)
{
	struct netfs_io_request *rreq;
	struct netfs_i_context *ctx = netfs_i_context(ractl->mapping->host);
	int ret;

	_enter("%lx,%x", readahead_index(ractl), readahead_count(ractl));

	if (readahead_count(ractl) == 0)
		return;

	rreq = netfs_alloc_request(ractl->mapping, ractl->file,
				   readahead_pos(ractl),
				   readahead_length(ractl),
				   NETFS_READAHEAD);
	if (IS_ERR(rreq))
		return;

	if (ctx->ops->begin_cache_operation) {
		ret = ctx->ops->begin_cache_operation(rreq);
		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
			goto cleanup_free;
	}

	netfs_stat(&netfs_n_rh_readahead);
	trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl),
			 netfs_read_trace_readahead);

	netfs_rreq_expand(rreq, ractl);

	/* Drop the refs on the folios here rather than in the cache or
	 * filesystem.  The locks will be dropped in netfs_rreq_unlock().
	 */
	while (readahead_folio(ractl))
		;

	netfs_begin_read(rreq, false);
	return;

cleanup_free:
	netfs_put_request(rreq, false, netfs_rreq_trace_put_failed);
	return;
}
EXPORT_SYMBOL(netfs_readahead);

/**
 * netfs_read_folio - Helper to manage a read_folio request
 * @file: The file to read from
 * @folio: The folio to read
 *
 * Fulfil a read_folio request by drawing data from the cache if
 * possible, or the netfs if not.  Space beyond the EOF is zero-filled.
 * Multiple I/O requests from different sources will get munged together.
 *
 * The calling netfs must initialise a netfs context contiguous to the vfs
 * inode before calling this.
 *
 * This is usable whether or not caching is enabled.
 */
int netfs_read_folio(struct file *file, struct folio *folio)
{
	struct address_space *mapping = folio_file_mapping(folio);
	struct netfs_io_request *rreq;
	struct netfs_i_context *ctx = netfs_i_context(mapping->host);
	int ret;

	_enter("%lx", folio_index(folio));

	rreq = netfs_alloc_request(mapping, file,
				   folio_file_pos(folio), folio_size(folio),
				   NETFS_READPAGE);
	if (IS_ERR(rreq)) {
		ret = PTR_ERR(rreq);
		goto alloc_error;
	}

	if (ctx->ops->begin_cache_operation) {
		ret = ctx->ops->begin_cache_operation(rreq);
		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
			goto discard;
	}

	netfs_stat(&netfs_n_rh_readpage);
	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
	return netfs_begin_read(rreq, true);

discard:
	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
alloc_error:
	folio_unlock(folio);
	return ret;
}
EXPORT_SYMBOL(netfs_read_folio);

/*
 * Prepare a folio for writing without reading first
 * @folio: The folio being prepared
 * @pos: starting position for the write
 * @len: length of write
 * @always_fill: T if the folio should always be completely filled/cleared
 *
 * In some cases, write_begin doesn't need to read at all:
 * - full folio write
 * - write that lies in a folio that is completely beyond EOF
 * - write that covers the folio from start to EOF or beyond it
 *
 * If any of these criteria are met, then zero out the unwritten parts
 * of the folio and return true. Otherwise, return false.
 */
static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len,
				 bool always_fill)
{
	struct inode *inode = folio_inode(folio);
	loff_t i_size = i_size_read(inode);
	size_t offset = offset_in_folio(folio, pos);
	size_t plen = folio_size(folio);

	if (unlikely(always_fill)) {
		if (pos - offset + len <= i_size)
			return false; /* Page entirely before EOF */
		zero_user_segment(&folio->page, 0, plen);
		folio_mark_uptodate(folio);
		return true;
	}

	/* Full folio write */
	if (offset == 0 && len >= plen)
		return true;

	/* Page entirely beyond the end of the file */
	if (pos - offset >= i_size)
		goto zero_out;

	/* Write that covers from the start of the folio to EOF or beyond */
	if (offset == 0 && (pos + len) >= i_size)
		goto zero_out;

	return false;
zero_out:
	zero_user_segments(&folio->page, 0, offset, offset + len, plen);
	return true;
}

/**
 * netfs_write_begin - Helper to prepare for writing
 * @file: The file to read from
 * @mapping: The mapping to read from
 * @pos: File position at which the write will begin
 * @len: The length of the write (may extend beyond the end of the folio chosen)
 * @_folio: Where to put the resultant folio
 * @_fsdata: Place for the netfs to store a cookie
 *
 * Pre-read data for a write-begin request by drawing data from the cache if
 * possible, or the netfs if not.  Space beyond the EOF is zero-filled.
 * Multiple I/O requests from different sources will get munged together.  If
 * necessary, the readahead window can be expanded in either direction to a
 * more convenient alighment for RPC efficiency or to make storage in the cache
 * feasible.
 *
 * The calling netfs must provide a table of operations, only one of which,
 * issue_op, is mandatory.
 *
 * The check_write_begin() operation can be provided to check for and flush
 * conflicting writes once the folio is grabbed and locked.  It is passed a
 * pointer to the fsdata cookie that gets returned to the VM to be passed to
 * write_end.  It is permitted to sleep.  It should return 0 if the request
 * should go ahead; unlock the folio and return -EAGAIN to cause the folio to
 * be regot; or return an error.
 *
 * The calling netfs must initialise a netfs context contiguous to the vfs
 * inode before calling this.
 *
 * This is usable whether or not caching is enabled.
 */
int netfs_write_begin(struct file *file, struct address_space *mapping,
		      loff_t pos, unsigned int len, struct folio **_folio,
		      void **_fsdata)
{
	struct netfs_io_request *rreq;
	struct netfs_i_context *ctx = netfs_i_context(file_inode(file ));
	struct folio *folio;
	unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
	pgoff_t index = pos >> PAGE_SHIFT;
	int ret;

	DEFINE_READAHEAD(ractl, file, NULL, mapping, index);

retry:
	folio = __filemap_get_folio(mapping, index, fgp_flags,
				    mapping_gfp_mask(mapping));
	if (!folio)
		return -ENOMEM;

	if (ctx->ops->check_write_begin) {
		/* Allow the netfs (eg. ceph) to flush conflicts. */
		ret = ctx->ops->check_write_begin(file, pos, len, folio, _fsdata);
		if (ret < 0) {
			trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin);
			if (ret == -EAGAIN)
				goto retry;
			goto error;
		}
	}

	if (folio_test_uptodate(folio))
		goto have_folio;

	/* If the page is beyond the EOF, we want to clear it - unless it's
	 * within the cache granule containing the EOF, in which case we need
	 * to preload the granule.
	 */
	if (!netfs_is_cache_enabled(ctx) &&
	    netfs_skip_folio_read(folio, pos, len, false)) {
		netfs_stat(&netfs_n_rh_write_zskip);
		goto have_folio_no_wait;
	}

	rreq = netfs_alloc_request(mapping, file,
				   folio_file_pos(folio), folio_size(folio),
				   NETFS_READ_FOR_WRITE);
	if (IS_ERR(rreq)) {
		ret = PTR_ERR(rreq);
		goto error;
	}
	rreq->no_unlock_folio	= folio_index(folio);
	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);

	if (ctx->ops->begin_cache_operation) {
		ret = ctx->ops->begin_cache_operation(rreq);
		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
			goto error_put;
	}

	netfs_stat(&netfs_n_rh_write_begin);
	trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin);

	/* Expand the request to meet caching requirements and download
	 * preferences.
	 */
	ractl._nr_pages = folio_nr_pages(folio);
	netfs_rreq_expand(rreq, &ractl);

	/* We hold the folio locks, so we can drop the references */
	folio_get(folio);
	while (readahead_folio(&ractl))
		;

	ret = netfs_begin_read(rreq, true);
	if (ret < 0)
		goto error;

have_folio:
	ret = folio_wait_fscache_killable(folio);
	if (ret < 0)
		goto error;
have_folio_no_wait:
	*_folio = folio;
	_leave(" = 0");
	return 0;

error_put:
	netfs_put_request(rreq, false, netfs_rreq_trace_put_failed);
error:
	folio_unlock(folio);
	folio_put(folio);
	_leave(" = %d", ret);
	return ret;
}
EXPORT_SYMBOL(netfs_write_begin);