aboutsummaryrefslogtreecommitdiffstats
path: root/reftable/block.c
blob: 298e8c56b9e2085b798f50a05c136ad67c5cdbfe (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
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
/*
Copyright 2020 Google LLC

Use of this source code is governed by a BSD-style
license that can be found in the LICENSE file or at
https://developers.google.com/open-source/licenses/bsd
*/

#include "block.h"

#include "blocksource.h"
#include "constants.h"
#include "record.h"
#include "reftable-error.h"
#include "system.h"
#include <zlib.h>

int header_size(int version)
{
	switch (version) {
	case 1:
		return 24;
	case 2:
		return 28;
	}
	abort();
}

int footer_size(int version)
{
	switch (version) {
	case 1:
		return 68;
	case 2:
		return 72;
	}
	abort();
}

static int block_writer_register_restart(struct block_writer *w, int n,
					 int is_restart, struct strbuf *key)
{
	int rlen = w->restart_len;
	if (rlen >= MAX_RESTARTS) {
		is_restart = 0;
	}

	if (is_restart) {
		rlen++;
	}
	if (2 + 3 * rlen + n > w->block_size - w->next)
		return -1;
	if (is_restart) {
		REFTABLE_ALLOC_GROW(w->restarts, w->restart_len + 1, w->restart_cap);
		w->restarts[w->restart_len++] = w->next;
	}

	w->next += n;

	strbuf_reset(&w->last_key);
	strbuf_addbuf(&w->last_key, key);
	w->entries++;
	return 0;
}

void block_writer_init(struct block_writer *bw, uint8_t typ, uint8_t *buf,
		       uint32_t block_size, uint32_t header_off, int hash_size)
{
	bw->buf = buf;
	bw->hash_size = hash_size;
	bw->block_size = block_size;
	bw->header_off = header_off;
	bw->buf[header_off] = typ;
	bw->next = header_off + 4;
	bw->restart_interval = 16;
	bw->entries = 0;
	bw->restart_len = 0;
	bw->last_key.len = 0;
}

uint8_t block_writer_type(struct block_writer *bw)
{
	return bw->buf[bw->header_off];
}

/* Adds the reftable_record to the block. Returns -1 if it does not fit, 0 on
   success. Returns REFTABLE_API_ERROR if attempting to write a record with
   empty key. */
int block_writer_add(struct block_writer *w, struct reftable_record *rec)
{
	struct strbuf empty = STRBUF_INIT;
	struct strbuf last =
		w->entries % w->restart_interval == 0 ? empty : w->last_key;
	struct string_view out = {
		.buf = w->buf + w->next,
		.len = w->block_size - w->next,
	};

	struct string_view start = out;

	int is_restart = 0;
	struct strbuf key = STRBUF_INIT;
	int n = 0;
	int err = -1;

	reftable_record_key(rec, &key);
	if (!key.len) {
		err = REFTABLE_API_ERROR;
		goto done;
	}

	n = reftable_encode_key(&is_restart, out, last, key,
				reftable_record_val_type(rec));
	if (n < 0)
		goto done;
	string_view_consume(&out, n);

	n = reftable_record_encode(rec, out, w->hash_size);
	if (n < 0)
		goto done;
	string_view_consume(&out, n);

	err = block_writer_register_restart(w, start.len - out.len, is_restart,
					    &key);
done:
	strbuf_release(&key);
	return err;
}

int block_writer_finish(struct block_writer *w)
{
	int i;
	for (i = 0; i < w->restart_len; i++) {
		put_be24(w->buf + w->next, w->restarts[i]);
		w->next += 3;
	}

	put_be16(w->buf + w->next, w->restart_len);
	w->next += 2;
	put_be24(w->buf + 1 + w->header_off, w->next);

	if (block_writer_type(w) == BLOCK_TYPE_LOG) {
		int block_header_skip = 4 + w->header_off;
		uLongf src_len = w->next - block_header_skip;
		uLongf dest_cap = src_len * 1.001 + 12;
		uint8_t *compressed;

		REFTABLE_ALLOC_ARRAY(compressed, dest_cap);

		while (1) {
			uLongf out_dest_len = dest_cap;
			int zresult = compress2(compressed, &out_dest_len,
						w->buf + block_header_skip,
						src_len, 9);
			if (zresult == Z_BUF_ERROR && dest_cap < LONG_MAX) {
				dest_cap *= 2;
				compressed =
					reftable_realloc(compressed, dest_cap);
				if (compressed)
					continue;
			}

			if (Z_OK != zresult) {
				reftable_free(compressed);
				return REFTABLE_ZLIB_ERROR;
			}

			memcpy(w->buf + block_header_skip, compressed,
			       out_dest_len);
			w->next = out_dest_len + block_header_skip;
			reftable_free(compressed);
			break;
		}
	}
	return w->next;
}

uint8_t block_reader_type(struct block_reader *r)
{
	return r->block.data[r->header_off];
}

int block_reader_init(struct block_reader *br, struct reftable_block *block,
		      uint32_t header_off, uint32_t table_block_size,
		      int hash_size)
{
	uint32_t full_block_size = table_block_size;
	uint8_t typ = block->data[header_off];
	uint32_t sz = get_be24(block->data + header_off + 1);
	int err = 0;
	uint16_t restart_count = 0;
	uint32_t restart_start = 0;
	uint8_t *restart_bytes = NULL;
	uint8_t *uncompressed = NULL;

	if (!reftable_is_block_type(typ)) {
		err =  REFTABLE_FORMAT_ERROR;
		goto done;
	}

	if (typ == BLOCK_TYPE_LOG) {
		int block_header_skip = 4 + header_off;
		uLongf dst_len = sz - block_header_skip; /* total size of dest
							    buffer. */
		uLongf src_len = block->len - block_header_skip;

		/* Log blocks specify the *uncompressed* size in their header. */
		REFTABLE_ALLOC_ARRAY(uncompressed, sz);

		/* Copy over the block header verbatim. It's not compressed. */
		memcpy(uncompressed, block->data, block_header_skip);

		/* Uncompress */
		if (Z_OK !=
		    uncompress2(uncompressed + block_header_skip, &dst_len,
				block->data + block_header_skip, &src_len)) {
			err = REFTABLE_ZLIB_ERROR;
			goto done;
		}

		if (dst_len + block_header_skip != sz) {
			err = REFTABLE_FORMAT_ERROR;
			goto done;
		}

		/* We're done with the input data. */
		reftable_block_done(block);
		block->data = uncompressed;
		uncompressed = NULL;
		block->len = sz;
		block->source = malloc_block_source();
		full_block_size = src_len + block_header_skip;
	} else if (full_block_size == 0) {
		full_block_size = sz;
	} else if (sz < full_block_size && sz < block->len &&
		   block->data[sz] != 0) {
		/* If the block is smaller than the full block size, it is
		   padded (data followed by '\0') or the next block is
		   unaligned. */
		full_block_size = sz;
	}

	restart_count = get_be16(block->data + sz - 2);
	restart_start = sz - 2 - 3 * restart_count;
	restart_bytes = block->data + restart_start;

	/* transfer ownership. */
	br->block = *block;
	block->data = NULL;
	block->len = 0;

	br->hash_size = hash_size;
	br->block_len = restart_start;
	br->full_block_size = full_block_size;
	br->header_off = header_off;
	br->restart_count = restart_count;
	br->restart_bytes = restart_bytes;

done:
	reftable_free(uncompressed);
	return err;
}

static uint32_t block_reader_restart_offset(struct block_reader *br, int i)
{
	return get_be24(br->restart_bytes + 3 * i);
}

void block_reader_start(struct block_reader *br, struct block_iter *it)
{
	it->br = br;
	strbuf_reset(&it->last_key);
	it->next_off = br->header_off + 4;
}

struct restart_needle_less_args {
	int error;
	struct strbuf needle;
	struct block_reader *reader;
};

static int restart_needle_less(size_t idx, void *_args)
{
	struct restart_needle_less_args *args = _args;
	uint32_t off = block_reader_restart_offset(args->reader, idx);
	struct string_view in = {
		.buf = args->reader->block.data + off,
		.len = args->reader->block_len - off,
	};
	uint64_t prefix_len, suffix_len;
	uint8_t extra;
	int n;

	/*
	 * Records at restart points are stored without prefix compression, so
	 * there is no need to fully decode the record key here. This removes
	 * the need for allocating memory.
	 */
	n = reftable_decode_keylen(in, &prefix_len, &suffix_len, &extra);
	if (n < 0 || prefix_len) {
		args->error = 1;
		return -1;
	}

	string_view_consume(&in, n);
	if (suffix_len > in.len) {
		args->error = 1;
		return -1;
	}

	n = memcmp(args->needle.buf, in.buf,
		   args->needle.len < suffix_len ? args->needle.len : suffix_len);
	if (n)
		return n < 0;
	return args->needle.len < suffix_len;
}

void block_iter_copy_from(struct block_iter *dest, struct block_iter *src)
{
	dest->br = src->br;
	dest->next_off = src->next_off;
	strbuf_reset(&dest->last_key);
	strbuf_addbuf(&dest->last_key, &src->last_key);
}

int block_iter_next(struct block_iter *it, struct reftable_record *rec)
{
	struct string_view in = {
		.buf = it->br->block.data + it->next_off,
		.len = it->br->block_len - it->next_off,
	};
	struct string_view start = in;
	uint8_t extra = 0;
	int n = 0;

	if (it->next_off >= it->br->block_len)
		return 1;

	n = reftable_decode_key(&it->last_key, &extra, in);
	if (n < 0)
		return -1;
	if (!it->last_key.len)
		return REFTABLE_FORMAT_ERROR;

	string_view_consume(&in, n);
	n = reftable_record_decode(rec, it->last_key, extra, in, it->br->hash_size,
				   &it->scratch);
	if (n < 0)
		return -1;
	string_view_consume(&in, n);

	it->next_off += start.len - in.len;
	return 0;
}

int block_reader_first_key(struct block_reader *br, struct strbuf *key)
{
	int off = br->header_off + 4, n;
	struct string_view in = {
		.buf = br->block.data + off,
		.len = br->block_len - off,
	};
	uint8_t extra = 0;

	strbuf_reset(key);

	n = reftable_decode_key(key, &extra, in);
	if (n < 0)
		return n;
	if (!key->len)
		return REFTABLE_FORMAT_ERROR;

	return 0;
}

int block_iter_seek(struct block_iter *it, struct strbuf *want)
{
	return block_reader_seek(it->br, it, want);
}

void block_iter_close(struct block_iter *it)
{
	strbuf_release(&it->last_key);
	strbuf_release(&it->scratch);
}

int block_reader_seek(struct block_reader *br, struct block_iter *it,
		      struct strbuf *want)
{
	struct restart_needle_less_args args = {
		.needle = *want,
		.reader = br,
	};
	struct block_iter next = BLOCK_ITER_INIT;
	struct reftable_record rec;
	int err = 0;
	size_t i;

	/*
	 * Perform a binary search over the block's restart points, which
	 * avoids doing a linear scan over the whole block. Like this, we
	 * identify the section of the block that should contain our key.
	 *
	 * Note that we explicitly search for the first restart point _greater_
	 * than the sought-after record, not _greater or equal_ to it. In case
	 * the sought-after record is located directly at the restart point we
	 * would otherwise start doing the linear search at the preceding
	 * restart point. While that works alright, we would end up scanning
	 * too many record.
	 */
	i = binsearch(br->restart_count, &restart_needle_less, &args);
	if (args.error) {
		err = REFTABLE_FORMAT_ERROR;
		goto done;
	}

	/*
	 * Now there are multiple cases:
	 *
	 *   - `i == 0`: The wanted record is smaller than the record found at
	 *     the first restart point. As the first restart point is the first
	 *     record in the block, our wanted record cannot be located in this
	 *     block at all. We still need to position the iterator so that the
	 *     next call to `block_iter_next()` will yield an end-of-iterator
	 *     signal.
	 *
	 *   - `i == restart_count`: The wanted record was not found at any of
	 *     the restart points. As there is no restart point at the end of
	 *     the section the record may thus be contained in the last block.
	 *
	 *   - `i > 0`: The wanted record must be contained in the section
	 *     before the found restart point. We thus do a linear search
	 *     starting from the preceding restart point.
	 */
	if (i > 0)
		it->next_off = block_reader_restart_offset(br, i - 1);
	else
		it->next_off = br->header_off + 4;
	it->br = br;

	reftable_record_init(&rec, block_reader_type(br));

	/*
	 * We're looking for the last entry less than the wanted key so that
	 * the next call to `block_reader_next()` would yield the wanted
	 * record. We thus don't want to position our reader at the sought
	 * after record, but one before. To do so, we have to go one entry too
	 * far and then back up.
	 */
	while (1) {
		block_iter_copy_from(&next, it);
		err = block_iter_next(&next, &rec);
		if (err < 0)
			goto done;
		if (err > 0) {
			err = 0;
			goto done;
		}

		/*
		 * Check whether the current key is greater or equal to the
		 * sought-after key. In case it is greater we know that the
		 * record does not exist in the block and can thus abort early.
		 * In case it is equal to the sought-after key we have found
		 * the desired record.
		 */
		reftable_record_key(&rec, &it->last_key);
		if (strbuf_cmp(&it->last_key, want) >= 0)
			goto done;

		block_iter_copy_from(it, &next);
	}

done:
	block_iter_close(&next);
	reftable_record_release(&rec);

	return err;
}

void block_writer_release(struct block_writer *bw)
{
	FREE_AND_NULL(bw->restarts);
	strbuf_release(&bw->last_key);
	/* the block is not owned. */
}

void reftable_block_done(struct reftable_block *blockp)
{
	struct reftable_block_source source = blockp->source;
	if (blockp && source.ops)
		source.ops->return_block(source.arg, blockp);
	blockp->data = NULL;
	blockp->len = 0;
	blockp->source.ops = NULL;
	blockp->source.arg = NULL;
}