diff options
Diffstat (limited to 'bloom.c')
-rw-r--r-- | bloom.c | 58 |
1 files changed, 46 insertions, 12 deletions
@@ -2,10 +2,10 @@ #include "bloom.h" #include "diff.h" #include "diffcore.h" -#include "revision.h" #include "hashmap.h" #include "commit-graph.h" #include "commit.h" +#include "commit-slab.h" define_commit_slab(bloom_filter_slab, struct bloom_filter); @@ -28,12 +28,31 @@ 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, - struct commit *c) + uint32_t graph_pos) { uint32_t lex_pos, start_index, end_index; - uint32_t graph_pos = commit_graph_position(c); while (graph_pos < g->num_commits_in_base) g = g->base_graph; @@ -51,6 +70,20 @@ static int load_bloom_filter_from_graph(struct commit_graph *g, 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 + @@ -164,10 +197,10 @@ void init_bloom_filters(void) init_bloom_filter_slab(&bloom_filters); } -static int pathmap_cmp(const void *hashmap_cmp_fn_data, +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) + const void *keydata UNUSED) { const struct pathmap_hash_entry *e1, *e2; @@ -203,9 +236,10 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r, filter = bloom_filter_slab_at(&bloom_filters, c); if (!filter->data) { - load_commit_graph_info(r, c); - if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH) - load_bloom_filter_from_graph(r->objects->commit_graph, filter, c); + 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) @@ -229,10 +263,9 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r, diffcore_std(&diffopt); if (diff_queued_diff.nr <= settings->max_changed_paths) { - struct hashmap pathmap; + struct hashmap pathmap = HASHMAP_INIT(pathmap_cmp, NULL); struct pathmap_hash_entry *e; struct hashmap_iter iter; - hashmap_init(&pathmap, pathmap_cmp, NULL, 0); for (i = 0; i < diff_queued_diff.nr; i++) { const char *path = diff_queued_diff.queue[i]->two->path; @@ -278,16 +311,17 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r, *computed |= BLOOM_TRUNC_EMPTY; filter->len = 1; } - filter->data = xcalloc(filter->len, sizeof(unsigned char)); + 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_free_entries(&pathmap, struct pathmap_hash_entry, entry); + 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]); |