diff options
Diffstat (limited to 'commit-graph.c')
-rw-r--r-- | commit-graph.c | 228 |
1 files changed, 107 insertions, 121 deletions
diff --git a/commit-graph.c b/commit-graph.c index ee66098e07..32583991f8 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -1,14 +1,13 @@ #include "git-compat-util.h" #include "config.h" +#include "csum-file.h" #include "gettext.h" #include "hex.h" #include "lockfile.h" -#include "pack.h" #include "packfile.h" #include "commit.h" #include "object.h" #include "refs.h" -#include "revision.h" #include "hash-lookup.h" #include "commit-graph.h" #include "object-file.h" @@ -275,103 +274,30 @@ struct commit_graph *load_commit_graph_one_fd_st(struct repository *r, return ret; } -static int verify_commit_graph_lite(struct commit_graph *g) +static int graph_read_oid_fanout(const unsigned char *chunk_start, + size_t chunk_size, void *data) { + struct commit_graph *g = data; int i; - /* - * Basic validation shared between parse_commit_graph() - * which'll be called every time the graph is used, and the - * much more expensive verify_commit_graph() used by - * "commit-graph verify". - * - * There should only be very basic checks here to ensure that - * we don't e.g. segfault in fill_commit_in_graph(), but - * because this is a very hot codepath nothing that e.g. loops - * over g->num_commits, or runs a checksum on the commit-graph - * itself. - */ - if (!g->chunk_oid_fanout) { - error("commit-graph is missing the OID Fanout chunk"); - return 1; - } - if (!g->chunk_oid_lookup) { - error("commit-graph is missing the OID Lookup chunk"); - return 1; - } - if (!g->chunk_commit_data) { - error("commit-graph is missing the Commit Data chunk"); - return 1; - } + if (chunk_size != 256 * sizeof(uint32_t)) + return error(_("commit-graph oid fanout chunk is wrong size")); + g->chunk_oid_fanout = (const uint32_t *)chunk_start; + g->num_commits = ntohl(g->chunk_oid_fanout[255]); for (i = 0; i < 255; i++) { uint32_t oid_fanout1 = ntohl(g->chunk_oid_fanout[i]); uint32_t oid_fanout2 = ntohl(g->chunk_oid_fanout[i + 1]); if (oid_fanout1 > oid_fanout2) { - error("commit-graph fanout values out of order"); + error(_("commit-graph fanout values out of order")); return 1; } } - if (ntohl(g->chunk_oid_fanout[255]) != g->num_commits) { - error("commit-graph oid table and fanout disagree on size"); - return 1; - } return 0; } -static int graph_read_oid_fanout(const unsigned char *chunk_start, - size_t chunk_size, void *data) -{ - struct commit_graph *g = data; - if (chunk_size != 256 * sizeof(uint32_t)) - return error("commit-graph oid fanout chunk is wrong size"); - g->chunk_oid_fanout = (const uint32_t *)chunk_start; - return 0; -} - -static int graph_read_oid_lookup(const unsigned char *chunk_start, - size_t chunk_size, void *data) -{ - struct commit_graph *g = data; - g->chunk_oid_lookup = chunk_start; - g->num_commits = chunk_size / g->hash_len; - return 0; -} - -static int graph_read_commit_data(const unsigned char *chunk_start, - size_t chunk_size, void *data) -{ - struct commit_graph *g = data; - if (chunk_size != g->num_commits * GRAPH_DATA_WIDTH) - return error("commit-graph commit data chunk is wrong size"); - g->chunk_commit_data = chunk_start; - return 0; -} - -static int graph_read_generation_data(const unsigned char *chunk_start, - size_t chunk_size, void *data) -{ - struct commit_graph *g = data; - if (chunk_size != g->num_commits * sizeof(uint32_t)) - return error("commit-graph generations chunk is wrong size"); - g->chunk_generation_data = chunk_start; - return 0; -} - -static int graph_read_bloom_index(const unsigned char *chunk_start, - size_t chunk_size, void *data) -{ - struct commit_graph *g = data; - if (chunk_size != g->num_commits * 4) { - warning("commit-graph changed-path index chunk is too small"); - return -1; - } - g->chunk_bloom_indexes = chunk_start; - return 0; -} - static int graph_read_bloom_data(const unsigned char *chunk_start, size_t chunk_size, void *data) { @@ -379,20 +305,17 @@ static int graph_read_bloom_data(const unsigned char *chunk_start, uint32_t hash_version; if (chunk_size < BLOOMDATA_CHUNK_HEADER_SIZE) { - warning("ignoring too-small changed-path chunk" - " (%"PRIuMAX" < %"PRIuMAX") in commit-graph file", + warning(_("ignoring too-small changed-path chunk" + " (%"PRIuMAX" < %"PRIuMAX") in commit-graph file"), (uintmax_t)chunk_size, (uintmax_t)BLOOMDATA_CHUNK_HEADER_SIZE); return -1; } - g->chunk_bloom_data = chunk_start; - g->chunk_bloom_data_size = chunk_size; hash_version = get_be32(chunk_start); - if (hash_version != 1) - return 0; - + g->chunk_bloom_data = chunk_start; + g->chunk_bloom_data_size = chunk_size; g->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings)); g->bloom_filter_settings->hash_version = hash_version; g->bloom_filter_settings->num_hashes = get_be32(chunk_start + 4); @@ -462,17 +385,33 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s, GRAPH_HEADER_SIZE, graph->num_chunks, 1)) goto free_and_return; - read_chunk(cf, GRAPH_CHUNKID_OIDFANOUT, graph_read_oid_fanout, graph); - read_chunk(cf, GRAPH_CHUNKID_OIDLOOKUP, graph_read_oid_lookup, graph); - read_chunk(cf, GRAPH_CHUNKID_DATA, graph_read_commit_data, graph); + if (read_chunk(cf, GRAPH_CHUNKID_OIDFANOUT, graph_read_oid_fanout, graph)) { + error(_("commit-graph required OID fanout chunk missing or corrupted")); + goto free_and_return; + } + if (pair_chunk_expect(cf, GRAPH_CHUNKID_OIDLOOKUP, + &graph->chunk_oid_lookup, graph->hash_len, + graph->num_commits)) { + error(_("commit-graph OID lookup chunk is the wrong size")); + goto free_and_return; + } + if (pair_chunk_expect(cf, GRAPH_CHUNKID_DATA, &graph->chunk_commit_data, + GRAPH_DATA_WIDTH, graph->num_commits)) { + error(_("commit-graph commit data chunk is wrong size")); + goto free_and_return; + } + pair_chunk(cf, GRAPH_CHUNKID_EXTRAEDGES, &graph->chunk_extra_edges, &graph->chunk_extra_edges_size); pair_chunk(cf, GRAPH_CHUNKID_BASE, &graph->chunk_base_graphs, &graph->chunk_base_graphs_size); if (s->commit_graph_generation_version >= 2) { - read_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA, - graph_read_generation_data, graph); + if (pair_chunk_expect(cf, GRAPH_CHUNKID_GENERATION_DATA, + &graph->chunk_generation_data, + sizeof(uint32_t), + graph->num_commits)) + error(_("commit-graph generations chunk is wrong size")); pair_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW, &graph->chunk_generation_data_overflow, &graph->chunk_generation_data_overflow_size); @@ -481,9 +420,12 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s, graph->read_generation_data = 1; } - if (s->commit_graph_read_changed_paths) { - read_chunk(cf, GRAPH_CHUNKID_BLOOMINDEXES, - graph_read_bloom_index, graph); + if (s->commit_graph_changed_paths_version) { + int res = pair_chunk_expect(cf, GRAPH_CHUNKID_BLOOMINDEXES, + &graph->chunk_bloom_indexes, + sizeof(uint32_t), graph->num_commits); + if (res && res != CHUNK_NOT_FOUND) + warning(_("commit-graph changed-path index chunk is too small")); read_chunk(cf, GRAPH_CHUNKID_BLOOMDATA, graph_read_bloom_data, graph); } @@ -499,9 +441,6 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s, oidread(&graph->oid, graph->data + graph->data_len - graph->hash_len); - if (verify_commit_graph_lite(graph)) - goto free_and_return; - free_chunkfile(cf); return graph; @@ -568,6 +507,31 @@ static int validate_mixed_generation_chain(struct commit_graph *g) return 0; } +static void validate_mixed_bloom_settings(struct commit_graph *g) +{ + struct bloom_filter_settings *settings = NULL; + for (; g; g = g->base_graph) { + if (!g->bloom_filter_settings) + continue; + if (!settings) { + settings = g->bloom_filter_settings; + continue; + } + + if (g->bloom_filter_settings->bits_per_entry != settings->bits_per_entry || + g->bloom_filter_settings->num_hashes != settings->num_hashes || + g->bloom_filter_settings->hash_version != settings->hash_version) { + g->chunk_bloom_indexes = NULL; + g->chunk_bloom_data = NULL; + FREE_AND_NULL(g->bloom_filter_settings); + + warning(_("disabling Bloom filters for commit-graph " + "layer '%s' due to incompatible settings"), + oid_to_hex(&g->oid)); + } + } +} + static int add_graph_to_chain(struct commit_graph *g, struct commit_graph *chain, struct object_id *oids, @@ -629,7 +593,7 @@ int open_commit_graph_chain(const char *chain_file, /* treat empty files the same as missing */ errno = ENOENT; } else { - warning("commit-graph chain file too small"); + warning(_("commit-graph chain file too small")); errno = EINVAL; } return 0; @@ -691,6 +655,7 @@ struct commit_graph *load_commit_graph_chain_fd_st(struct repository *r, } validate_mixed_generation_chain(graph_chain); + validate_mixed_bloom_settings(graph_chain); free(oids); fclose(fp); @@ -831,7 +796,11 @@ struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r) void close_commit_graph(struct raw_object_store *o) { + if (!o->commit_graph) + return; + clear_commit_graph_data_slab(&commit_graph_data_slab); + deinit_bloom_filters(); free_commit_graph(o->commit_graph); o->commit_graph = NULL; } @@ -970,7 +939,7 @@ static int fill_commit_in_graph(struct repository *r, parent_data_pos = edge_value & GRAPH_EDGE_LAST_MASK; do { if (g->chunk_extra_edges_size / sizeof(uint32_t) <= parent_data_pos) { - error("commit-graph extra-edges pointer out of bounds"); + error(_("commit-graph extra-edges pointer out of bounds")); free_commit_list(item->parents); item->parents = NULL; item->object.parsed = 0; @@ -1029,7 +998,7 @@ struct commit *lookup_commit_in_graph(struct repository *repo, const struct obje uint32_t pos; if (commit_graph_paranoia == -1) - commit_graph_paranoia = git_env_bool(GIT_COMMIT_GRAPH_PARANOIA, 1); + commit_graph_paranoia = git_env_bool(GIT_COMMIT_GRAPH_PARANOIA, 0); if (!prepare_commit_graph(repo)) return NULL; @@ -1169,6 +1138,7 @@ struct write_commit_graph_context { int count_bloom_filter_not_computed; int count_bloom_filter_trunc_empty; int count_bloom_filter_trunc_large; + int count_bloom_filter_upgraded; }; static int write_graph_chunk_fanout(struct hashfile *f, @@ -1776,6 +1746,8 @@ static void trace2_bloom_filter_write_statistics(struct write_commit_graph_conte ctx->count_bloom_filter_trunc_empty); trace2_data_intmax("commit-graph", ctx->r, "filter-trunc-large", ctx->count_bloom_filter_trunc_large); + trace2_data_intmax("commit-graph", ctx->r, "filter-upgraded", + ctx->count_bloom_filter_upgraded); } static void compute_bloom_filters(struct write_commit_graph_context *ctx) @@ -1817,6 +1789,8 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx) ctx->count_bloom_filter_trunc_empty++; if (computed & BLOOM_TRUNC_LARGE) ctx->count_bloom_filter_trunc_large++; + } else if (computed & BLOOM_UPGRADED) { + ctx->count_bloom_filter_upgraded++; } else if (computed & BLOOM_NOT_COMPUTED) ctx->count_bloom_filter_not_computed++; ctx->total_bloom_filter_data_size += filter @@ -2500,6 +2474,13 @@ int write_commit_graph(struct object_directory *odb, } if (!commit_graph_compatible(r)) return 0; + if (r->settings.commit_graph_changed_paths_version < -1 + || r->settings.commit_graph_changed_paths_version > 2) { + warning(_("attempting to write a commit-graph, but " + "'commitgraph.changedPathsVersion' (%d) is not supported"), + r->settings.commit_graph_changed_paths_version); + return 0; + } CALLOC_ARRAY(ctx, 1); ctx->r = r; @@ -2512,6 +2493,7 @@ int write_commit_graph(struct object_directory *odb, ctx->write_generation_data = (get_configured_generation_version(r) == 2); ctx->num_generation_data_overflows = 0; + bloom_settings.hash_version = r->settings.commit_graph_changed_paths_version; bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY", bloom_settings.bits_per_entry); bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES", @@ -2541,12 +2523,20 @@ int write_commit_graph(struct object_directory *odb, g = ctx->r->objects->commit_graph; /* We have changed-paths already. Keep them in the next graph */ - if (g && g->chunk_bloom_data) { + if (g && g->bloom_filter_settings) { ctx->changed_paths = 1; - ctx->bloom_settings = g->bloom_filter_settings; + + /* don't propagate the hash_version unless unspecified */ + if (bloom_settings.hash_version == -1) + bloom_settings.hash_version = g->bloom_filter_settings->hash_version; + bloom_settings.bits_per_entry = g->bloom_filter_settings->bits_per_entry; + bloom_settings.num_hashes = g->bloom_filter_settings->num_hashes; + bloom_settings.max_changed_paths = g->bloom_filter_settings->max_changed_paths; } } + bloom_settings.hash_version = bloom_settings.hash_version == 2 ? 2 : 1; + if (ctx->split) { struct commit_graph *g = ctx->r->objects->commit_graph; @@ -2629,6 +2619,9 @@ int write_commit_graph(struct object_directory *odb, res = write_commit_graph_file(ctx); + if (ctx->changed_paths) + deinit_bloom_filters(); + if (ctx->split) mark_commit_graphs(ctx); @@ -2641,19 +2634,16 @@ cleanup: oid_array_clear(&ctx->oids); clear_topo_level_slab(&topo_levels); - if (ctx->commit_graph_filenames_after) { - for (i = 0; i < ctx->num_commit_graphs_after; i++) { - free(ctx->commit_graph_filenames_after[i]); - free(ctx->commit_graph_hash_after[i]); - } - - for (i = 0; i < ctx->num_commit_graphs_before; i++) - free(ctx->commit_graph_filenames_before[i]); + for (i = 0; i < ctx->num_commit_graphs_before; i++) + free(ctx->commit_graph_filenames_before[i]); + free(ctx->commit_graph_filenames_before); - free(ctx->commit_graph_filenames_after); - free(ctx->commit_graph_filenames_before); - free(ctx->commit_graph_hash_after); + for (i = 0; i < ctx->num_commit_graphs_after; i++) { + free(ctx->commit_graph_filenames_after[i]); + free(ctx->commit_graph_hash_after[i]); } + free(ctx->commit_graph_filenames_after); + free(ctx->commit_graph_hash_after); free(ctx); @@ -2690,10 +2680,6 @@ static int verify_one_commit_graph(struct repository *r, struct commit *seen_gen_zero = NULL; struct commit *seen_gen_non_zero = NULL; - verify_commit_graph_error = verify_commit_graph_lite(g); - if (verify_commit_graph_error) - return verify_commit_graph_error; - if (!commit_graph_checksum_valid(g)) { graph_report(_("the commit-graph file has incorrect checksum and is likely corrupt")); verify_commit_graph_error = VERIFY_COMMIT_GRAPH_ERROR_HASH; |