summaryrefslogtreecommitdiffstats
path: root/bloom.c
blob: e529f7605ca14d3fcb779412fc22e1e20d45ac20 (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
#include "git-compat-util.h"
#include "bloom.h"
#include "diff.h"
#include "diffcore.h"
#include "hashmap.h"
#include "commit-graph.h"
#include "commit.h"
#include "commit-slab.h"

define_commit_slab(bloom_filter_slab, struct bloom_filter);

static struct bloom_filter_slab bloom_filters;

struct pathmap_hash_entry {
    struct hashmap_entry entry;
    const char path[FLEX_ARRAY];
};

static uint32_t rotate_left(uint32_t value, int32_t count)
{
	uint32_t mask = 8 * sizeof(uint32_t) - 1;
	count &= mask;
	return ((value << count) | (value >> ((-count) & mask)));
}

static inline unsigned char get_bitmask(uint32_t pos)
{
	return ((unsigned char)1) << (pos & (BITS_PER_WORD - 1));
}

static int check_bloom_offset(struct commit_graph *g, uint32_t pos,
			      uint32_t offset)
{
	/*
	 * Note that we allow offsets equal to the data size, which would set
	 * our pointers at one past the end of the chunk memory. This is
	 * necessary because the on-disk index points to the end of the
	 * entries (so we can compute size by comparing adjacent ones). And
	 * naturally the final entry's end is one-past-the-end of the chunk.
	 */
	if (offset <= g->chunk_bloom_data_size - BLOOMDATA_CHUNK_HEADER_SIZE)
		return 0;

	warning("ignoring out-of-range offset (%"PRIuMAX") for changed-path"
		" filter at pos %"PRIuMAX" of %s (chunk size: %"PRIuMAX")",
		(uintmax_t)offset, (uintmax_t)pos,
		g->filename, (uintmax_t)g->chunk_bloom_data_size);
	return -1;
}

static int load_bloom_filter_from_graph(struct commit_graph *g,
					struct bloom_filter *filter,
					uint32_t graph_pos)
{
	uint32_t lex_pos, start_index, end_index;

	while (graph_pos < g->num_commits_in_base)
		g = g->base_graph;

	/* The commit graph commit 'c' lives in doesn't carry Bloom filters. */
	if (!g->chunk_bloom_indexes)
		return 0;

	lex_pos = graph_pos - g->num_commits_in_base;

	end_index = get_be32(g->chunk_bloom_indexes + 4 * lex_pos);

	if (lex_pos > 0)
		start_index = get_be32(g->chunk_bloom_indexes + 4 * (lex_pos - 1));
	else
		start_index = 0;

	if (check_bloom_offset(g, lex_pos, end_index) < 0 ||
	    check_bloom_offset(g, lex_pos - 1, start_index) < 0)
		return 0;

	if (end_index < start_index) {
		warning("ignoring decreasing changed-path index offsets"
			" (%"PRIuMAX" > %"PRIuMAX") for positions"
			" %"PRIuMAX" and %"PRIuMAX" of %s",
			(uintmax_t)start_index, (uintmax_t)end_index,
			(uintmax_t)(lex_pos-1), (uintmax_t)lex_pos,
			g->filename);
		return 0;
	}

	filter->len = end_index - start_index;
	filter->data = (unsigned char *)(g->chunk_bloom_data +
					sizeof(unsigned char) * start_index +
					BLOOMDATA_CHUNK_HEADER_SIZE);

	return 1;
}

/*
 * Calculate the murmur3 32-bit hash value for the given data
 * using the given seed.
 * Produces a uniformly distributed hash value.
 * Not considered to be cryptographically secure.
 * Implemented as described in https://en.wikipedia.org/wiki/MurmurHash#Algorithm
 */
uint32_t murmur3_seeded(uint32_t seed, const char *data, size_t len)
{
	const uint32_t c1 = 0xcc9e2d51;
	const uint32_t c2 = 0x1b873593;
	const uint32_t r1 = 15;
	const uint32_t r2 = 13;
	const uint32_t m = 5;
	const uint32_t n = 0xe6546b64;
	int i;
	uint32_t k1 = 0;
	const char *tail;

	int len4 = len / sizeof(uint32_t);

	uint32_t k;
	for (i = 0; i < len4; i++) {
		uint32_t byte1 = (uint32_t)data[4*i];
		uint32_t byte2 = ((uint32_t)data[4*i + 1]) << 8;
		uint32_t byte3 = ((uint32_t)data[4*i + 2]) << 16;
		uint32_t byte4 = ((uint32_t)data[4*i + 3]) << 24;
		k = byte1 | byte2 | byte3 | byte4;
		k *= c1;
		k = rotate_left(k, r1);
		k *= c2;

		seed ^= k;
		seed = rotate_left(seed, r2) * m + n;
	}

	tail = (data + len4 * sizeof(uint32_t));

	switch (len & (sizeof(uint32_t) - 1)) {
	case 3:
		k1 ^= ((uint32_t)tail[2]) << 16;
		/*-fallthrough*/
	case 2:
		k1 ^= ((uint32_t)tail[1]) << 8;
		/*-fallthrough*/
	case 1:
		k1 ^= ((uint32_t)tail[0]) << 0;
		k1 *= c1;
		k1 = rotate_left(k1, r1);
		k1 *= c2;
		seed ^= k1;
		break;
	}

	seed ^= (uint32_t)len;
	seed ^= (seed >> 16);
	seed *= 0x85ebca6b;
	seed ^= (seed >> 13);
	seed *= 0xc2b2ae35;
	seed ^= (seed >> 16);

	return seed;
}

void fill_bloom_key(const char *data,
		    size_t len,
		    struct bloom_key *key,
		    const struct bloom_filter_settings *settings)
{
	int i;
	const uint32_t seed0 = 0x293ae76f;
	const uint32_t seed1 = 0x7e646e2c;
	const uint32_t hash0 = murmur3_seeded(seed0, data, len);
	const uint32_t hash1 = murmur3_seeded(seed1, data, len);

	key->hashes = (uint32_t *)xcalloc(settings->num_hashes, sizeof(uint32_t));
	for (i = 0; i < settings->num_hashes; i++)
		key->hashes[i] = hash0 + i * hash1;
}

void clear_bloom_key(struct bloom_key *key)
{
	FREE_AND_NULL(key->hashes);
}

void add_key_to_filter(const struct bloom_key *key,
		       struct bloom_filter *filter,
		       const struct bloom_filter_settings *settings)
{
	int i;
	uint64_t mod = filter->len * BITS_PER_WORD;

	for (i = 0; i < settings->num_hashes; i++) {
		uint64_t hash_mod = key->hashes[i] % mod;
		uint64_t block_pos = hash_mod / BITS_PER_WORD;

		filter->data[block_pos] |= get_bitmask(hash_mod);
	}
}

void init_bloom_filters(void)
{
	init_bloom_filter_slab(&bloom_filters);
}

static int pathmap_cmp(const void *hashmap_cmp_fn_data UNUSED,
		       const struct hashmap_entry *eptr,
		       const struct hashmap_entry *entry_or_key,
		       const void *keydata UNUSED)
{
	const struct pathmap_hash_entry *e1, *e2;

	e1 = container_of(eptr, const struct pathmap_hash_entry, entry);
	e2 = container_of(entry_or_key, const struct pathmap_hash_entry, entry);

	return strcmp(e1->path, e2->path);
}

static void init_truncated_large_filter(struct bloom_filter *filter)
{
	filter->data = xmalloc(1);
	filter->data[0] = 0xFF;
	filter->len = 1;
}

struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
						 struct commit *c,
						 int compute_if_not_present,
						 const struct bloom_filter_settings *settings,
						 enum bloom_filter_computed *computed)
{
	struct bloom_filter *filter;
	int i;
	struct diff_options diffopt;

	if (computed)
		*computed = BLOOM_NOT_COMPUTED;

	if (!bloom_filters.slab_size)
		return NULL;

	filter = bloom_filter_slab_at(&bloom_filters, c);

	if (!filter->data) {
		uint32_t graph_pos;
		if (repo_find_commit_pos_in_graph(r, c, &graph_pos))
			load_bloom_filter_from_graph(r->objects->commit_graph,
						     filter, graph_pos);
	}

	if (filter->data && filter->len)
		return filter;
	if (!compute_if_not_present)
		return NULL;

	repo_diff_setup(r, &diffopt);
	diffopt.flags.recursive = 1;
	diffopt.detect_rename = 0;
	diffopt.max_changes = settings->max_changed_paths;
	diff_setup_done(&diffopt);

	/* ensure commit is parsed so we have parent information */
	repo_parse_commit(r, c);

	if (c->parents)
		diff_tree_oid(&c->parents->item->object.oid, &c->object.oid, "", &diffopt);
	else
		diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
	diffcore_std(&diffopt);

	if (diff_queued_diff.nr <= settings->max_changed_paths) {
		struct hashmap pathmap = HASHMAP_INIT(pathmap_cmp, NULL);
		struct pathmap_hash_entry *e;
		struct hashmap_iter iter;

		for (i = 0; i < diff_queued_diff.nr; i++) {
			const char *path = diff_queued_diff.queue[i]->two->path;

			/*
			 * Add each leading directory of the changed file, i.e. for
			 * 'dir/subdir/file' add 'dir' and 'dir/subdir' as well, so
			 * the Bloom filter could be used to speed up commands like
			 * 'git log dir/subdir', too.
			 *
			 * Note that directories are added without the trailing '/'.
			 */
			do {
				char *last_slash = strrchr(path, '/');

				FLEX_ALLOC_STR(e, path, path);
				hashmap_entry_init(&e->entry, strhash(path));

				if (!hashmap_get(&pathmap, &e->entry, NULL))
					hashmap_add(&pathmap, &e->entry);
				else
					free(e);

				if (!last_slash)
					last_slash = (char*)path;
				*last_slash = '\0';

			} while (*path);

			diff_free_filepair(diff_queued_diff.queue[i]);
		}

		if (hashmap_get_size(&pathmap) > settings->max_changed_paths) {
			init_truncated_large_filter(filter);
			if (computed)
				*computed |= BLOOM_TRUNC_LARGE;
			goto cleanup;
		}

		filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
		if (!filter->len) {
			if (computed)
				*computed |= BLOOM_TRUNC_EMPTY;
			filter->len = 1;
		}
		CALLOC_ARRAY(filter->data, filter->len);

		hashmap_for_each_entry(&pathmap, &iter, e, entry) {
			struct bloom_key key;
			fill_bloom_key(e->path, strlen(e->path), &key, settings);
			add_key_to_filter(&key, filter, settings);
			clear_bloom_key(&key);
		}

	cleanup:
		hashmap_clear_and_free(&pathmap, struct pathmap_hash_entry, entry);
	} else {
		for (i = 0; i < diff_queued_diff.nr; i++)
			diff_free_filepair(diff_queued_diff.queue[i]);
		init_truncated_large_filter(filter);

		if (computed)
			*computed |= BLOOM_TRUNC_LARGE;
	}

	if (computed)
		*computed |= BLOOM_COMPUTED;

	free(diff_queued_diff.queue);
	DIFF_QUEUE_CLEAR(&diff_queued_diff);

	return filter;
}

int bloom_filter_contains(const struct bloom_filter *filter,
			  const struct bloom_key *key,
			  const struct bloom_filter_settings *settings)
{
	int i;
	uint64_t mod = filter->len * BITS_PER_WORD;

	if (!mod)
		return -1;

	for (i = 0; i < settings->num_hashes; i++) {
		uint64_t hash_mod = key->hashes[i] % mod;
		uint64_t block_pos = hash_mod / BITS_PER_WORD;
		if (!(filter->data[block_pos] & get_bitmask(hash_mod)))
			return 0;
	}

	return 1;
}