summaryrefslogtreecommitdiff
path: root/fs/orangefs/dir.c
blob: ba7dec40771e6d902e43551efcba9f528034faf1 (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
/*
 * (C) 2001 Clemson University and The University of Chicago
 *
 * See COPYING in top-level directory.
 */

#include "protocol.h"
#include "orangefs-kernel.h"
#include "orangefs-bufmap.h"

/*
 * decode routine used by kmod to deal with the blob sent from
 * userspace for readdirs. The blob contains zero or more of these
 * sub-blobs:
 *   __u32 - represents length of the character string that follows.
 *   string - between 1 and ORANGEFS_NAME_MAX bytes long.
 *   padding - (if needed) to cause the __u32 plus the string to be
 *             eight byte aligned.
 *   khandle - sizeof(khandle) bytes.
 */
static long decode_dirents(char *ptr, size_t size,
                           struct orangefs_readdir_response_s *readdir)
{
	int i;
	struct orangefs_readdir_response_s *rd =
		(struct orangefs_readdir_response_s *) ptr;
	char *buf = ptr;
	int khandle_size = sizeof(struct orangefs_khandle);
	size_t offset = offsetof(struct orangefs_readdir_response_s,
				dirent_array);
	/* 8 reflects eight byte alignment */
	int smallest_blob = khandle_size + 8;
	__u32 len;
	int aligned_len;
	int sizeof_u32 = sizeof(__u32);
	long ret;

	gossip_debug(GOSSIP_DIR_DEBUG, "%s: size:%zu:\n", __func__, size);

	/* size is = offset on empty dirs, > offset on non-empty dirs... */
	if (size < offset) {
		gossip_err("%s: size:%zu: offset:%zu:\n",
			   __func__,
			   size,
			   offset);
		ret = -EINVAL;
		goto out;
	}

        if ((size == offset) && (readdir->orangefs_dirent_outcount != 0)) {
		gossip_err("%s: size:%zu: dirent_outcount:%d:\n",
			   __func__,
			   size,
			   readdir->orangefs_dirent_outcount);
		ret = -EINVAL;
		goto out;
	}

	readdir->token = rd->token;
	readdir->orangefs_dirent_outcount = rd->orangefs_dirent_outcount;
	readdir->dirent_array = kcalloc(readdir->orangefs_dirent_outcount,
					sizeof(*readdir->dirent_array),
					GFP_KERNEL);
	if (readdir->dirent_array == NULL) {
		gossip_err("%s: kcalloc failed.\n", __func__);
		ret = -ENOMEM;
		goto out;
	}

	buf += offset;
	size -= offset;

	for (i = 0; i < readdir->orangefs_dirent_outcount; i++) {
		if (size < smallest_blob) {
			gossip_err("%s: size:%zu: smallest_blob:%d:\n",
				   __func__,
				   size,
				   smallest_blob);
			ret = -EINVAL;
			goto free;
		}

		len = *(__u32 *)buf;
		if ((len < 1) || (len > ORANGEFS_NAME_MAX)) {
			gossip_err("%s: len:%d:\n", __func__, len);
			ret = -EINVAL;
			goto free;
		}

		gossip_debug(GOSSIP_DIR_DEBUG,
			     "%s: size:%zu: len:%d:\n",
			     __func__,
			     size,
			     len);

		readdir->dirent_array[i].d_name = buf + sizeof_u32;
		readdir->dirent_array[i].d_length = len;

		/*
		 * Calculate "aligned" length of this string and its
		 * associated __u32 descriptor.
		 */
		aligned_len = ((sizeof_u32 + len + 1) + 7) & ~7;
		gossip_debug(GOSSIP_DIR_DEBUG,
			     "%s: aligned_len:%d:\n",
			     __func__,
			     aligned_len);

		/*
		 * The end of the blob should coincide with the end
		 * of the last sub-blob.
		 */
		if (size < aligned_len + khandle_size) {
			gossip_err("%s: ran off the end of the blob.\n",
				   __func__);
			ret = -EINVAL;
			goto free;
		}
		size -= aligned_len + khandle_size;

		buf += aligned_len;

		readdir->dirent_array[i].khandle =
			*(struct orangefs_khandle *) buf;
		buf += khandle_size;
	}
	ret = buf - ptr;
	gossip_debug(GOSSIP_DIR_DEBUG, "%s: returning:%ld:\n", __func__, ret);
	goto out;

free:
	kfree(readdir->dirent_array);
	readdir->dirent_array = NULL;

out:
	return ret;
}

/*
 * Read directory entries from an instance of an open directory.
 */
static int orangefs_readdir(struct file *file, struct dir_context *ctx)
{
	int ret = 0;
	int buffer_index;
	/*
	 * ptoken supports Orangefs' distributed directory logic, added
	 * in 2.9.2.
	 */
	__u64 *ptoken = file->private_data;
	__u64 pos = 0;
	ino_t ino = 0;
	struct dentry *dentry = file->f_path.dentry;
	struct orangefs_kernel_op_s *new_op = NULL;
	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(dentry->d_inode);
	int buffer_full = 0;
	struct orangefs_readdir_response_s readdir_response;
	void *dents_buf;
	int i = 0;
	int len = 0;
	ino_t current_ino = 0;
	char *current_entry = NULL;
	long bytes_decoded;

	gossip_debug(GOSSIP_DIR_DEBUG,
		     "%s: ctx->pos:%lld, ptoken = %llu\n",
		     __func__,
		     lld(ctx->pos),
		     llu(*ptoken));

	pos = (__u64) ctx->pos;

	/* are we done? */
	if (pos == ORANGEFS_READDIR_END) {
		gossip_debug(GOSSIP_DIR_DEBUG,
			     "Skipping to termination path\n");
		return 0;
	}

	gossip_debug(GOSSIP_DIR_DEBUG,
		     "orangefs_readdir called on %s (pos=%llu)\n",
		     dentry->d_name.name, llu(pos));

	memset(&readdir_response, 0, sizeof(readdir_response));

	new_op = op_alloc(ORANGEFS_VFS_OP_READDIR);
	if (!new_op)
		return -ENOMEM;

	/*
	 * Only the indices are shared. No memory is actually shared, but the
	 * mechanism is used.
	 */
	new_op->uses_shared_memory = 1;
	new_op->upcall.req.readdir.refn = orangefs_inode->refn;
	new_op->upcall.req.readdir.max_dirent_count =
	    ORANGEFS_MAX_DIRENT_COUNT_READDIR;

	gossip_debug(GOSSIP_DIR_DEBUG,
		     "%s: upcall.req.readdir.refn.khandle: %pU\n",
		     __func__,
		     &new_op->upcall.req.readdir.refn.khandle);

	new_op->upcall.req.readdir.token = *ptoken;

get_new_buffer_index:
	buffer_index = orangefs_readdir_index_get();
	if (buffer_index < 0) {
		ret = buffer_index;
		gossip_lerr("orangefs_readdir: orangefs_readdir_index_get() failure (%d)\n",
			    ret);
		goto out_free_op;
	}
	new_op->upcall.req.readdir.buf_index = buffer_index;

	ret = service_operation(new_op,
				"orangefs_readdir",
				get_interruptible_flag(dentry->d_inode));

	gossip_debug(GOSSIP_DIR_DEBUG,
		     "Readdir downcall status is %d.  ret:%d\n",
		     new_op->downcall.status,
		     ret);

	orangefs_readdir_index_put(buffer_index);

	if (ret == -EAGAIN && op_state_purged(new_op)) {
		/* Client-core indices are invalid after it restarted. */
		gossip_debug(GOSSIP_DIR_DEBUG,
			"%s: Getting new buffer_index for retry of readdir..\n",
			 __func__);
		goto get_new_buffer_index;
	}

	if (ret == -EIO && op_state_purged(new_op)) {
		gossip_err("%s: Client is down. Aborting readdir call.\n",
			__func__);
		goto out_free_op;
	}

	if (ret < 0 || new_op->downcall.status != 0) {
		gossip_debug(GOSSIP_DIR_DEBUG,
			     "Readdir request failed.  Status:%d\n",
			     new_op->downcall.status);
		if (ret >= 0)
			ret = new_op->downcall.status;
		goto out_free_op;
	}

	dents_buf = new_op->downcall.trailer_buf;
	if (dents_buf == NULL) {
		gossip_err("Invalid NULL buffer in readdir response\n");
		ret = -ENOMEM;
		goto out_free_op;
	}

	bytes_decoded = decode_dirents(dents_buf, new_op->downcall.trailer_size,
					&readdir_response);
	if (bytes_decoded < 0) {
		ret = bytes_decoded;
		gossip_err("Could not decode readdir from buffer %d\n", ret);
		goto out_vfree;
	}

	if (bytes_decoded != new_op->downcall.trailer_size) {
		gossip_err("orangefs_readdir: # bytes decoded (%ld) "
			   "!= trailer size (%ld)\n",
			   bytes_decoded,
			   (long)new_op->downcall.trailer_size);
		ret = -EINVAL;
		goto out_destroy_handle;
	}

	/*
	 *  orangefs doesn't actually store dot and dot-dot, but
	 *  we need to have them represented.
	 */
	if (pos == 0) {
		ino = get_ino_from_khandle(dentry->d_inode);
		gossip_debug(GOSSIP_DIR_DEBUG,
			     "%s: calling dir_emit of \".\" with pos = %llu\n",
			     __func__,
			     llu(pos));
		ret = dir_emit(ctx, ".", 1, ino, DT_DIR);
		pos += 1;
	}

	if (pos == 1) {
		ino = get_parent_ino_from_dentry(dentry);
		gossip_debug(GOSSIP_DIR_DEBUG,
			     "%s: calling dir_emit of \"..\" with pos = %llu\n",
			     __func__,
			     llu(pos));
		ret = dir_emit(ctx, "..", 2, ino, DT_DIR);
		pos += 1;
	}

	/*
	 * we stored ORANGEFS_ITERATE_NEXT in ctx->pos last time around
	 * to prevent "finding" dot and dot-dot on any iteration
	 * other than the first.
	 */
	if (ctx->pos == ORANGEFS_ITERATE_NEXT)
		ctx->pos = 0;

	gossip_debug(GOSSIP_DIR_DEBUG,
		     "%s: dirent_outcount:%d:\n",
		     __func__,
		     readdir_response.orangefs_dirent_outcount);
	for (i = ctx->pos;
	     i < readdir_response.orangefs_dirent_outcount;
	     i++) {
		len = readdir_response.dirent_array[i].d_length;
		current_entry = readdir_response.dirent_array[i].d_name;
		current_ino = orangefs_khandle_to_ino(
			&readdir_response.dirent_array[i].khandle);

		gossip_debug(GOSSIP_DIR_DEBUG,
			     "calling dir_emit for %s with len %d"
			     ", ctx->pos %ld\n",
			     current_entry,
			     len,
			     (unsigned long)ctx->pos);
		/*
		 * type is unknown. We don't return object type
		 * in the dirent_array. This leaves getdents
		 * clueless about type.
		 */
		ret =
		    dir_emit(ctx, current_entry, len, current_ino, DT_UNKNOWN);
		if (!ret)
			break;
		ctx->pos++;
		gossip_debug(GOSSIP_DIR_DEBUG,
			      "%s: ctx->pos:%lld\n",
			      __func__,
			      lld(ctx->pos));

	}

	/*
	 * we ran all the way through the last batch, set up for
	 * getting another batch...
	 */
	if (ret) {
		*ptoken = readdir_response.token;
		ctx->pos = ORANGEFS_ITERATE_NEXT;
	}

	/*
	 * Did we hit the end of the directory?
	 */
	if (readdir_response.token == ORANGEFS_READDIR_END &&
	    !buffer_full) {
		gossip_debug(GOSSIP_DIR_DEBUG,
		"End of dir detected; setting ctx->pos to ORANGEFS_READDIR_END.\n");
		ctx->pos = ORANGEFS_READDIR_END;
	}

out_destroy_handle:
	/* kfree(NULL) is safe */
	kfree(readdir_response.dirent_array);
out_vfree:
	gossip_debug(GOSSIP_DIR_DEBUG, "vfree %p\n", dents_buf);
	vfree(dents_buf);
out_free_op:
	op_release(new_op);
	gossip_debug(GOSSIP_DIR_DEBUG, "orangefs_readdir returning %d\n", ret);
	return ret;
}

static int orangefs_dir_open(struct inode *inode, struct file *file)
{
	__u64 *ptoken;

	file->private_data = kmalloc(sizeof(__u64), GFP_KERNEL);
	if (!file->private_data)
		return -ENOMEM;

	ptoken = file->private_data;
	*ptoken = ORANGEFS_READDIR_START;
	return 0;
}

static int orangefs_dir_release(struct inode *inode, struct file *file)
{
	orangefs_flush_inode(inode);
	kfree(file->private_data);
	return 0;
}

/** ORANGEFS implementation of VFS directory operations */
const struct file_operations orangefs_dir_operations = {
	.read = generic_read_dir,
	.iterate = orangefs_readdir,
	.open = orangefs_dir_open,
	.release = orangefs_dir_release,
};