summaryrefslogtreecommitdiffstats
path: root/fs/afs/write.c
blob: 35db74627563f7465eacaab3e1f65bb1c7f2991e (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
// SPDX-License-Identifier: GPL-2.0-or-later
/* handling of writes to regular files and writing back to the server
 *
 * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */

#include <linux/backing-dev.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/netfs.h>
#include <trace/events/netfs.h>
#include "internal.h"

/*
 * completion of write to server
 */
static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len)
{
	_enter("{%llx:%llu},{%x @%llx}",
	       vnode->fid.vid, vnode->fid.vnode, len, start);

	afs_prune_wb_keys(vnode);
	_leave("");
}

/*
 * Find a key to use for the writeback.  We cached the keys used to author the
 * writes on the vnode.  *_wbk will contain the last writeback key used or NULL
 * and we need to start from there if it's set.
 */
static int afs_get_writeback_key(struct afs_vnode *vnode,
				 struct afs_wb_key **_wbk)
{
	struct afs_wb_key *wbk = NULL;
	struct list_head *p;
	int ret = -ENOKEY, ret2;

	spin_lock(&vnode->wb_lock);
	if (*_wbk)
		p = (*_wbk)->vnode_link.next;
	else
		p = vnode->wb_keys.next;

	while (p != &vnode->wb_keys) {
		wbk = list_entry(p, struct afs_wb_key, vnode_link);
		_debug("wbk %u", key_serial(wbk->key));
		ret2 = key_validate(wbk->key);
		if (ret2 == 0) {
			refcount_inc(&wbk->usage);
			_debug("USE WB KEY %u", key_serial(wbk->key));
			break;
		}

		wbk = NULL;
		if (ret == -ENOKEY)
			ret = ret2;
		p = p->next;
	}

	spin_unlock(&vnode->wb_lock);
	if (*_wbk)
		afs_put_wb_key(*_wbk);
	*_wbk = wbk;
	return 0;
}

static void afs_store_data_success(struct afs_operation *op)
{
	struct afs_vnode *vnode = op->file[0].vnode;

	op->ctime = op->file[0].scb.status.mtime_client;
	afs_vnode_commit_status(op, &op->file[0]);
	if (!afs_op_error(op)) {
		afs_pages_written_back(vnode, op->store.pos, op->store.size);
		afs_stat_v(vnode, n_stores);
		atomic_long_add(op->store.size, &afs_v2net(vnode)->n_store_bytes);
	}
}

static const struct afs_operation_ops afs_store_data_operation = {
	.issue_afs_rpc	= afs_fs_store_data,
	.issue_yfs_rpc	= yfs_fs_store_data,
	.success	= afs_store_data_success,
};

/*
 * write to a file
 */
static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t pos)
{
	struct afs_operation *op;
	struct afs_wb_key *wbk = NULL;
	loff_t size = iov_iter_count(iter);
	int ret = -ENOKEY;

	_enter("%s{%llx:%llu.%u},%llx,%llx",
	       vnode->volume->name,
	       vnode->fid.vid,
	       vnode->fid.vnode,
	       vnode->fid.unique,
	       size, pos);

	ret = afs_get_writeback_key(vnode, &wbk);
	if (ret) {
		_leave(" = %d [no keys]", ret);
		return ret;
	}

	op = afs_alloc_operation(wbk->key, vnode->volume);
	if (IS_ERR(op)) {
		afs_put_wb_key(wbk);
		return -ENOMEM;
	}

	afs_op_set_vnode(op, 0, vnode);
	op->file[0].dv_delta = 1;
	op->file[0].modification = true;
	op->store.pos = pos;
	op->store.size = size;
	op->flags |= AFS_OPERATION_UNINTR;
	op->ops = &afs_store_data_operation;

try_next_key:
	afs_begin_vnode_operation(op);

	op->store.write_iter = iter;
	op->store.i_size = max(pos + size, vnode->netfs.remote_i_size);
	op->mtime = inode_get_mtime(&vnode->netfs.inode);

	afs_wait_for_operation(op);

	switch (afs_op_error(op)) {
	case -EACCES:
	case -EPERM:
	case -ENOKEY:
	case -EKEYEXPIRED:
	case -EKEYREJECTED:
	case -EKEYREVOKED:
		_debug("next");

		ret = afs_get_writeback_key(vnode, &wbk);
		if (ret == 0) {
			key_put(op->key);
			op->key = key_get(wbk->key);
			goto try_next_key;
		}
		break;
	}

	afs_put_wb_key(wbk);
	_leave(" = %d", afs_op_error(op));
	return afs_put_operation(op);
}

#if 0 // TODO: Remove
static void afs_upload_to_server(struct netfs_io_subrequest *subreq)
{
	struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode);
	ssize_t ret;

	_enter("%x[%x],%zx",
	       subreq->rreq->debug_id, subreq->debug_index, subreq->io_iter.count);

	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
	ret = afs_store_data(vnode, &subreq->io_iter, subreq->start);
	netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len,
					  false);
}

static void afs_upload_to_server_worker(struct work_struct *work)
{
	struct netfs_io_subrequest *subreq =
		container_of(work, struct netfs_io_subrequest, work);

	afs_upload_to_server(subreq);
}

/*
 * Set up write requests for a writeback slice.  We need to add a write request
 * for each write we want to make.
 */
void afs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len)
{
	struct netfs_io_subrequest *subreq;

	_enter("%x,%llx-%llx", wreq->debug_id, start, start + len);

	subreq = netfs_create_write_request(wreq, NETFS_UPLOAD_TO_SERVER,
					    start, len, afs_upload_to_server_worker);
	if (subreq)
		netfs_queue_write_request(subreq);
}
#endif

/*
 * Writeback calls this when it finds a folio that needs uploading.  This isn't
 * called if writeback only has copy-to-cache to deal with.
 */
void afs_begin_writeback(struct netfs_io_request *wreq)
{
	wreq->io_streams[0].avail = true;
}

/*
 * Prepare a subrequest to write to the server.  This sets the max_len
 * parameter.
 */
void afs_prepare_write(struct netfs_io_subrequest *subreq)
{
	//if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags))
	//	subreq->max_len = 512 * 1024;
	//else
	subreq->max_len = 256 * 1024 * 1024;
}

/*
 * Issue a subrequest to write to the server.
 */
static void afs_issue_write_worker(struct work_struct *work)
{
	struct netfs_io_subrequest *subreq = container_of(work, struct netfs_io_subrequest, work);
	struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode);
	ssize_t ret;

	_enter("%x[%x],%zx",
	       subreq->rreq->debug_id, subreq->debug_index, subreq->io_iter.count);

#if 0 // Error injection
	if (subreq->debug_index == 3)
		return netfs_write_subrequest_terminated(subreq, -ENOANO, false);

	if (!test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) {
		set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
		return netfs_write_subrequest_terminated(subreq, -EAGAIN, false);
	}
#endif

	ret = afs_store_data(vnode, &subreq->io_iter, subreq->start);
	netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len, false);
}

void afs_issue_write(struct netfs_io_subrequest *subreq)
{
	subreq->work.func = afs_issue_write_worker;
	if (!queue_work(system_unbound_wq, &subreq->work))
		WARN_ON_ONCE(1);
}

/*
 * write some of the pending data back to the server
 */
int afs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
	int ret;

	/* We have to be careful as we can end up racing with setattr()
	 * truncating the pagecache since the caller doesn't take a lock here
	 * to prevent it.
	 */
	if (wbc->sync_mode == WB_SYNC_ALL)
		down_read(&vnode->validate_lock);
	else if (!down_read_trylock(&vnode->validate_lock))
		return 0;

	ret = netfs_writepages(mapping, wbc);
	up_read(&vnode->validate_lock);
	return ret;
}

/*
 * flush any dirty pages for this process, and check for write errors.
 * - the return status from this call provides a reliable indication of
 *   whether any write errors occurred for this process.
 */
int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
	struct afs_file *af = file->private_data;
	int ret;

	_enter("{%llx:%llu},{n=%pD},%d",
	       vnode->fid.vid, vnode->fid.vnode, file,
	       datasync);

	ret = afs_validate(vnode, af->key);
	if (ret < 0)
		return ret;

	return file_write_and_wait_range(file, start, end);
}

/*
 * notification that a previously read-only page is about to become writable
 * - if it returns an error, the caller will deliver a bus error signal
 */
vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
{
	struct file *file = vmf->vma->vm_file;

	if (afs_validate(AFS_FS_I(file_inode(file)), afs_file_key(file)) < 0)
		return VM_FAULT_SIGBUS;
	return netfs_page_mkwrite(vmf, NULL);
}

/*
 * Prune the keys cached for writeback.  The caller must hold vnode->wb_lock.
 */
void afs_prune_wb_keys(struct afs_vnode *vnode)
{
	LIST_HEAD(graveyard);
	struct afs_wb_key *wbk, *tmp;

	/* Discard unused keys */
	spin_lock(&vnode->wb_lock);

	if (!mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_WRITEBACK) &&
	    !mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_DIRTY)) {
		list_for_each_entry_safe(wbk, tmp, &vnode->wb_keys, vnode_link) {
			if (refcount_read(&wbk->usage) == 1)
				list_move(&wbk->vnode_link, &graveyard);
		}
	}

	spin_unlock(&vnode->wb_lock);

	while (!list_empty(&graveyard)) {
		wbk = list_entry(graveyard.next, struct afs_wb_key, vnode_link);
		list_del(&wbk->vnode_link);
		afs_put_wb_key(wbk);
	}
}