From 111c9f8f72d10bb375da1450e8f1fe6b5e85841e Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:26 +0100 Subject: [PATCH 1/8] midx-write: pass down repository to static functions In 'midx-write.c' there are a lot of static functions which use global variables `the_repository` or `the_hash_algo`. In a follow up commit, the repository variable will be added to `write_midx_context`, which some of the functions can use. But for functions which do not have access to this struct, pass down the required information from non-static functions `write_midx_file` and `write_midx_file_only`. This requires that the function `hash_to_hex` is also replaced with `hash_to_hex_algop` since the former internally accesses the `the_hash_algo` global variable. This ensures that the usage of global variables is limited to these non-static functions, which will be cleaned up in a follow up commit. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx-write.c | 57 ++++++++++++++++++++++++++++------------------------ 1 file changed, 31 insertions(+), 26 deletions(-) diff --git a/midx-write.c b/midx-write.c index c57726ef9475df..22b5233f51ec6c 100644 --- a/midx-write.c +++ b/midx-write.c @@ -35,13 +35,13 @@ extern void clear_incremental_midx_files_ext(const char *object_dir, extern int cmp_idx_or_pack_name(const char *idx_or_pack_name, const char *idx_name); -static size_t write_midx_header(struct hashfile *f, - unsigned char num_chunks, +static size_t write_midx_header(const struct git_hash_algo *hash_algo, + struct hashfile *f, unsigned char num_chunks, uint32_t num_packs) { hashwrite_be32(f, MIDX_SIGNATURE); hashwrite_u8(f, MIDX_VERSION); - hashwrite_u8(f, oid_version(the_hash_algo)); + hashwrite_u8(f, oid_version(hash_algo)); hashwrite_u8(f, num_chunks); hashwrite_u8(f, 0); /* unused */ hashwrite_be32(f, num_packs); @@ -702,7 +702,7 @@ static int add_ref_to_pending(const char *refname, const char *referent UNUSED, return 0; } - if (!peel_iterated_oid(the_repository, oid, &peeled)) + if (!peel_iterated_oid(revs->repo, oid, &peeled)) oid = &peeled; object = parse_object_or_die(oid, refname); @@ -827,7 +827,7 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr return cb.commits; } -static int write_midx_bitmap(const char *midx_name, +static int write_midx_bitmap(struct repository *r, const char *midx_name, const unsigned char *midx_hash, struct packing_data *pdata, struct commit **commits, @@ -840,9 +840,9 @@ static int write_midx_bitmap(const char *midx_name, struct bitmap_writer writer; struct pack_idx_entry **index; char *bitmap_name = xstrfmt("%s-%s.bitmap", midx_name, - hash_to_hex(midx_hash)); + hash_to_hex_algop(midx_hash, r->hash_algo)); - trace2_region_enter("midx", "write_midx_bitmap", the_repository); + trace2_region_enter("midx", "write_midx_bitmap", r); if (flags & MIDX_WRITE_BITMAP_HASH_CACHE) options |= BITMAP_OPT_HASH_CACHE; @@ -859,7 +859,7 @@ static int write_midx_bitmap(const char *midx_name, for (i = 0; i < pdata->nr_objects; i++) index[i] = &pdata->objects[i].idx; - bitmap_writer_init(&writer, the_repository, pdata); + bitmap_writer_init(&writer, r, pdata); bitmap_writer_show_progress(&writer, flags & MIDX_PROGRESS); bitmap_writer_build_type_index(&writer, index); @@ -892,7 +892,7 @@ static int write_midx_bitmap(const char *midx_name, free(bitmap_name); bitmap_writer_free(&writer); - trace2_region_leave("midx", "write_midx_bitmap", the_repository); + trace2_region_leave("midx", "write_midx_bitmap", r); return ret; } @@ -1049,7 +1049,7 @@ static void clear_midx_files(const char *object_dir, strbuf_release(&buf); } -static int write_midx_internal(const char *object_dir, +static int write_midx_internal(struct repository *r, const char *object_dir, struct string_list *packs_to_include, struct string_list *packs_to_drop, const char *preferred_pack_name, @@ -1070,7 +1070,8 @@ static int write_midx_internal(const char *object_dir, const char **keep_hashes = NULL; struct chunkfile *cf; - trace2_region_enter("midx", "write_midx_internal", the_repository); + trace2_region_enter("midx", "write_midx_internal", r); + ctx.incremental = !!(flags & MIDX_WRITE_INCREMENTAL); if (ctx.incremental && (flags & MIDX_WRITE_BITMAP)) @@ -1087,8 +1088,7 @@ static int write_midx_internal(const char *object_dir, midx_name.buf); if (!packs_to_include || ctx.incremental) { - struct multi_pack_index *m = lookup_multi_pack_index(the_repository, - object_dir); + struct multi_pack_index *m = lookup_multi_pack_index(r, object_dir); if (m && !midx_checksum_valid(m)) { warning(_("ignoring existing multi-pack-index; checksum mismatch")); m = NULL; @@ -1351,7 +1351,7 @@ static int write_midx_internal(const char *object_dir, add_chunk(cf, MIDX_CHUNKID_OIDFANOUT, MIDX_CHUNK_FANOUT_SIZE, write_midx_oid_fanout); add_chunk(cf, MIDX_CHUNKID_OIDLOOKUP, - st_mult(ctx.entries_nr, the_hash_algo->rawsz), + st_mult(ctx.entries_nr, r->hash_algo->rawsz), write_midx_oid_lookup); add_chunk(cf, MIDX_CHUNKID_OBJECTOFFSETS, st_mult(ctx.entries_nr, MIDX_CHUNK_OFFSET_WIDTH), @@ -1373,7 +1373,8 @@ static int write_midx_internal(const char *object_dir, write_midx_bitmapped_packs); } - write_midx_header(f, get_num_chunks(cf), ctx.nr - dropped_packs); + write_midx_header(r->hash_algo, f, get_num_chunks(cf), + ctx.nr - dropped_packs); write_chunkfile(cf, &ctx); finalize_hashfile(f, midx_hash, FSYNC_COMPONENT_PACK_METADATA, @@ -1405,7 +1406,7 @@ static int write_midx_internal(const char *object_dir, FREE_AND_NULL(ctx.entries); ctx.entries_nr = 0; - if (write_midx_bitmap(midx_name.buf, midx_hash, &pdata, + if (write_midx_bitmap(r, midx_name.buf, midx_hash, &pdata, commits, commits_nr, ctx.pack_order, flags) < 0) { error(_("could not write multi-pack bitmap")); @@ -1449,12 +1450,13 @@ static int write_midx_internal(const char *object_dir, strbuf_release(&final_midx_name); keep_hashes[ctx.num_multi_pack_indexes_before] = - xstrdup(hash_to_hex(midx_hash)); + xstrdup(hash_to_hex_algop(midx_hash, r->hash_algo)); for (i = 0; i < ctx.num_multi_pack_indexes_before; i++) { uint32_t j = ctx.num_multi_pack_indexes_before - i - 1; - keep_hashes[j] = xstrdup(hash_to_hex(get_midx_checksum(m))); + keep_hashes[j] = xstrdup(hash_to_hex_algop(get_midx_checksum(m), + r->hash_algo)); m = m->base_midx; } @@ -1462,7 +1464,7 @@ static int write_midx_internal(const char *object_dir, fprintf(get_lock_file_fp(&lk), "%s\n", keep_hashes[i]); } else { keep_hashes[ctx.num_multi_pack_indexes_before] = - xstrdup(hash_to_hex(midx_hash)); + xstrdup(hash_to_hex_algop(midx_hash, r->hash_algo)); } if (ctx.m || ctx.base_midx) @@ -1495,7 +1497,7 @@ static int write_midx_internal(const char *object_dir, } strbuf_release(&midx_name); - trace2_region_leave("midx", "write_midx_internal", the_repository); + trace2_region_leave("midx", "write_midx_internal", r); return result; } @@ -1505,8 +1507,8 @@ int write_midx_file(const char *object_dir, const char *refs_snapshot, unsigned flags) { - return write_midx_internal(object_dir, NULL, NULL, preferred_pack_name, - refs_snapshot, flags); + return write_midx_internal(the_repository, object_dir, NULL, NULL, + preferred_pack_name, refs_snapshot, flags); } int write_midx_file_only(const char *object_dir, @@ -1515,8 +1517,9 @@ int write_midx_file_only(const char *object_dir, const char *refs_snapshot, unsigned flags) { - return write_midx_internal(object_dir, packs_to_include, NULL, - preferred_pack_name, refs_snapshot, flags); + return write_midx_internal(the_repository, object_dir, packs_to_include, + NULL, preferred_pack_name, refs_snapshot, + flags); } int expire_midx_packs(struct repository *r, const char *object_dir, unsigned flags) @@ -1572,7 +1575,8 @@ int expire_midx_packs(struct repository *r, const char *object_dir, unsigned fla free(count); if (packs_to_drop.nr) - result = write_midx_internal(object_dir, NULL, &packs_to_drop, NULL, NULL, flags); + result = write_midx_internal(r, object_dir, NULL, + &packs_to_drop, NULL, NULL, flags); string_list_clear(&packs_to_drop, 0); @@ -1769,7 +1773,8 @@ int midx_repack(struct repository *r, const char *object_dir, size_t batch_size, goto cleanup; } - result = write_midx_internal(object_dir, NULL, NULL, NULL, NULL, flags); + result = write_midx_internal(r, object_dir, NULL, NULL, NULL, NULL, + flags); cleanup: free(include_pack); From eade1ddeb63176353a07adaefc16c874b7825b6f Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:27 +0100 Subject: [PATCH 2/8] midx-write: use `revs->repo` inside `read_refs_snapshot` The function `read_refs_snapshot()` uses `parse_oid_hex()`, which relies on the global `the_hash_algo` variable. Let's instead use `parse_oid_hex_algop()` and provide the hash algo via `revs->repo`. Also, while here, fix a missing newline after the function's definition. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx-write.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/midx-write.c b/midx-write.c index 22b5233f51ec6c..564438f616f59c 100644 --- a/midx-write.c +++ b/midx-write.c @@ -760,7 +760,7 @@ static int read_refs_snapshot(const char *refs_snapshot, hex = &buf.buf[1]; } - if (parse_oid_hex(hex, &oid, &end) < 0) + if (parse_oid_hex_algop(hex, &oid, &end, revs->repo->hash_algo) < 0) die(_("could not parse line: %s"), buf.buf); if (*end) die(_("malformed line: %s"), buf.buf); @@ -776,6 +776,7 @@ static int read_refs_snapshot(const char *refs_snapshot, strbuf_release(&buf); return 0; } + static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr_p, const char *refs_snapshot, struct write_midx_context *ctx) From 4261200c50050a61aeb1a1ad461100309d0866b9 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:28 +0100 Subject: [PATCH 3/8] write-midx: add repository field to `write_midx_context` The struct `write_midx_context` is used to pass context for creating MIDX files. Add the repository field here to ensure that most functions within `midx-write.c` have access to the field and can use that instead of the global `the_repository` variable. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx-write.c | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/midx-write.c b/midx-write.c index 564438f616f59c..1c355cdf8db4e9 100644 --- a/midx-write.c +++ b/midx-write.c @@ -110,6 +110,8 @@ struct write_midx_context { uint32_t num_multi_pack_indexes_before; struct string_list *to_include; + + struct repository *repo; }; static int should_include_pack(const struct write_midx_context *ctx, @@ -154,7 +156,7 @@ static void add_pack_to_midx(const char *full_path, size_t full_path_len, return; ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc); - p = add_packed_git(the_repository, full_path, full_path_len, 0); + p = add_packed_git(ctx->repo, full_path, full_path_len, 0); if (!p) { warning(_("failed to add packfile '%s'"), full_path); @@ -480,7 +482,7 @@ static int write_midx_oid_lookup(struct hashfile *f, void *data) { struct write_midx_context *ctx = data; - unsigned char hash_len = the_hash_algo->rawsz; + unsigned char hash_len = ctx->repo->hash_algo->rawsz; struct pack_midx_entry *list = ctx->entries; uint32_t i; @@ -605,7 +607,7 @@ static uint32_t *midx_pack_order(struct write_midx_context *ctx) uint32_t *pack_order, base_objects = 0; uint32_t i; - trace2_region_enter("midx", "midx_pack_order", the_repository); + trace2_region_enter("midx", "midx_pack_order", ctx->repo); if (ctx->incremental && ctx->base_midx) base_objects = ctx->base_midx->num_objects + @@ -640,7 +642,7 @@ static uint32_t *midx_pack_order(struct write_midx_context *ctx) } free(data); - trace2_region_leave("midx", "midx_pack_order", the_repository); + trace2_region_leave("midx", "midx_pack_order", ctx->repo); return pack_order; } @@ -651,9 +653,10 @@ static void write_midx_reverse_index(char *midx_name, unsigned char *midx_hash, struct strbuf buf = STRBUF_INIT; char *tmp_file; - trace2_region_enter("midx", "write_midx_reverse_index", the_repository); + trace2_region_enter("midx", "write_midx_reverse_index", ctx->repo); - strbuf_addf(&buf, "%s-%s.rev", midx_name, hash_to_hex(midx_hash)); + strbuf_addf(&buf, "%s-%s.rev", midx_name, hash_to_hex_algop(midx_hash, + ctx->repo->hash_algo)); tmp_file = write_rev_file_order(NULL, ctx->pack_order, ctx->entries_nr, midx_hash, WRITE_REV); @@ -664,7 +667,7 @@ static void write_midx_reverse_index(char *midx_name, unsigned char *midx_hash, strbuf_release(&buf); free(tmp_file); - trace2_region_leave("midx", "write_midx_reverse_index", the_repository); + trace2_region_leave("midx", "write_midx_reverse_index", ctx->repo); } static void prepare_midx_packing_data(struct packing_data *pdata, @@ -672,10 +675,10 @@ static void prepare_midx_packing_data(struct packing_data *pdata, { uint32_t i; - trace2_region_enter("midx", "prepare_midx_packing_data", the_repository); + trace2_region_enter("midx", "prepare_midx_packing_data", ctx->repo); memset(pdata, 0, sizeof(struct packing_data)); - prepare_packing_data(the_repository, pdata); + prepare_packing_data(ctx->repo, pdata); for (i = 0; i < ctx->entries_nr; i++) { uint32_t pos = ctx->pack_order[i]; @@ -686,7 +689,7 @@ static void prepare_midx_packing_data(struct packing_data *pdata, ctx->info[ctx->pack_perm[from->pack_int_id]].p); } - trace2_region_leave("midx", "prepare_midx_packing_data", the_repository); + trace2_region_leave("midx", "prepare_midx_packing_data", ctx->repo); } static int add_ref_to_pending(const char *refname, const char *referent UNUSED, @@ -784,17 +787,16 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr struct rev_info revs; struct bitmap_commit_cb cb = {0}; - trace2_region_enter("midx", "find_commits_for_midx_bitmap", - the_repository); + trace2_region_enter("midx", "find_commits_for_midx_bitmap", ctx->repo); cb.ctx = ctx; - repo_init_revisions(the_repository, &revs, NULL); + repo_init_revisions(ctx->repo, &revs, NULL); if (refs_snapshot) { read_refs_snapshot(refs_snapshot, &revs); } else { setup_revisions(0, NULL, &revs, NULL); - refs_for_each_ref(get_main_ref_store(the_repository), + refs_for_each_ref(get_main_ref_store(ctx->repo), add_ref_to_pending, &revs); } @@ -822,8 +824,7 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr release_revisions(&revs); - trace2_region_leave("midx", "find_commits_for_midx_bitmap", - the_repository); + trace2_region_leave("midx", "find_commits_for_midx_bitmap", ctx->repo); return cb.commits; } @@ -945,7 +946,7 @@ static int fill_packs_from_midx(struct write_midx_context *ctx, */ if (flags & MIDX_WRITE_REV_INDEX || preferred_pack_name) { - if (prepare_midx_pack(the_repository, m, + if (prepare_midx_pack(ctx->repo, m, m->num_packs_in_base + i)) { error(_("could not load pack")); return 1; @@ -1073,6 +1074,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir, trace2_region_enter("midx", "write_midx_internal", r); + ctx.repo = r; ctx.incremental = !!(flags & MIDX_WRITE_INCREMENTAL); if (ctx.incremental && (flags & MIDX_WRITE_BITMAP)) @@ -1469,7 +1471,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir, } if (ctx.m || ctx.base_midx) - close_object_store(the_repository->objects); + close_object_store(ctx.repo->objects); if (commit_lock_file(&lk) < 0) die_errno(_("could not write multi-pack-index")); From 3e238779c7d6aab7e9b92aff8cabfd1fea3941dd Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:29 +0100 Subject: [PATCH 4/8] midx-write: pass down repository to `write_midx_file[_only]` In a previous commit, we passed the repository field to all subcommands in the `builtin/` directory. Utilize this to pass the repository field down to the `write_midx_file[_only]` functions to remove the usage of `the_repository` global variables. With this, all usage of global variables in `midx-write.c` is removed, hence, remove the `USE_THE_REPOSITORY_VARIABLE` guard from the file. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- builtin/multi-pack-index.c | 6 +++--- builtin/repack.c | 2 +- midx-write.c | 22 +++++++++------------- midx.h | 10 ++++------ 4 files changed, 17 insertions(+), 23 deletions(-) diff --git a/builtin/multi-pack-index.c b/builtin/multi-pack-index.c index 85e40a4b6d3e47..2a938466f53aaa 100644 --- a/builtin/multi-pack-index.c +++ b/builtin/multi-pack-index.c @@ -120,7 +120,7 @@ static void read_packs_from_stdin(struct string_list *to) static int cmd_multi_pack_index_write(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { struct option *options; static struct option builtin_multi_pack_index_write_options[] = { @@ -165,7 +165,7 @@ static int cmd_multi_pack_index_write(int argc, const char **argv, read_packs_from_stdin(&packs); - ret = write_midx_file_only(opts.object_dir, &packs, + ret = write_midx_file_only(repo, opts.object_dir, &packs, opts.preferred_pack, opts.refs_snapshot, opts.flags); @@ -176,7 +176,7 @@ static int cmd_multi_pack_index_write(int argc, const char **argv, } - ret = write_midx_file(opts.object_dir, opts.preferred_pack, + ret = write_midx_file(repo, opts.object_dir, opts.preferred_pack, opts.refs_snapshot, opts.flags); free(opts.refs_snapshot); diff --git a/builtin/repack.c b/builtin/repack.c index 96a4fa234bddfd..9c21fc482dfb38 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -1569,7 +1569,7 @@ int cmd_repack(int argc, unsigned flags = 0; if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX_WRITE_INCREMENTAL, 0)) flags |= MIDX_WRITE_INCREMENTAL; - write_midx_file(repo_get_object_directory(the_repository), + write_midx_file(the_repository, repo_get_object_directory(the_repository), NULL, NULL, flags); } diff --git a/midx-write.c b/midx-write.c index 1c355cdf8db4e9..1bc2f5256916e6 100644 --- a/midx-write.c +++ b/midx-write.c @@ -1,5 +1,3 @@ -#define USE_THE_REPOSITORY_VARIABLE - #include "git-compat-util.h" #include "abspath.h" #include "config.h" @@ -1505,24 +1503,22 @@ static int write_midx_internal(struct repository *r, const char *object_dir, return result; } -int write_midx_file(const char *object_dir, +int write_midx_file(struct repository *r, const char *object_dir, const char *preferred_pack_name, - const char *refs_snapshot, - unsigned flags) + const char *refs_snapshot, unsigned flags) { - return write_midx_internal(the_repository, object_dir, NULL, NULL, - preferred_pack_name, refs_snapshot, flags); + return write_midx_internal(r, object_dir, NULL, NULL, + preferred_pack_name, refs_snapshot, + flags); } -int write_midx_file_only(const char *object_dir, +int write_midx_file_only(struct repository *r, const char *object_dir, struct string_list *packs_to_include, const char *preferred_pack_name, - const char *refs_snapshot, - unsigned flags) + const char *refs_snapshot, unsigned flags) { - return write_midx_internal(the_repository, object_dir, packs_to_include, - NULL, preferred_pack_name, refs_snapshot, - flags); + return write_midx_internal(r, object_dir, packs_to_include, NULL, + preferred_pack_name, refs_snapshot, flags); } int expire_midx_packs(struct repository *r, const char *object_dir, unsigned flags) diff --git a/midx.h b/midx.h index 3b0ac4d8788b37..c37ad5b5242b56 100644 --- a/midx.h +++ b/midx.h @@ -123,15 +123,13 @@ int prepare_multi_pack_index_one(struct repository *r, const char *object_dir, i * Variant of write_midx_file which writes a MIDX containing only the packs * specified in packs_to_include. */ -int write_midx_file(const char *object_dir, - const char *preferred_pack_name, - const char *refs_snapshot, +int write_midx_file(struct repository *r, const char *object_dir, + const char *preferred_pack_name, const char *refs_snapshot, unsigned flags); -int write_midx_file_only(const char *object_dir, +int write_midx_file_only(struct repository *r, const char *object_dir, struct string_list *packs_to_include, const char *preferred_pack_name, - const char *refs_snapshot, - unsigned flags); + const char *refs_snapshot, unsigned flags); void clear_midx_file(struct repository *r); int verify_midx_file(struct repository *r, const char *object_dir, unsigned flags); int expire_midx_packs(struct repository *r, const char *object_dir, unsigned flags); From 8fb569cefdf40e7d5555f06c575b9b7ffe1d2dbc Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:30 +0100 Subject: [PATCH 5/8] midx: cleanup internal usage of `the_repository` and `the_hash_algo` In the `midx.c` file, there are multiple usages of `the_repository` and `the_hash_algo` within static functions of the file. Some of the usages can be simply swapped out with the available `repository` struct. While some of them can be swapped out by passing the repository to the required functions. This leaves out only some other usages of `the_repository` and `the_hash_algo` in the file in non-static functions, which we'll tackle in upcoming commits. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx.c | 49 +++++++++++++++++++++++++++---------------------- 1 file changed, 27 insertions(+), 22 deletions(-) diff --git a/midx.c b/midx.c index 079c45a1aafb65..6f0fb8285af148 100644 --- a/midx.c +++ b/midx.c @@ -25,7 +25,7 @@ int cmp_idx_or_pack_name(const char *idx_or_pack_name, const unsigned char *get_midx_checksum(struct multi_pack_index *m) { - return m->data + m->data_len - the_hash_algo->rawsz; + return m->data + m->data_len - m->repo->hash_algo->rawsz; } void get_midx_filename(struct strbuf *out, const char *object_dir) @@ -94,7 +94,8 @@ static int midx_read_object_offsets(const unsigned char *chunk_start, #define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + the_hash_algo->rawsz) -static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir, +static struct multi_pack_index *load_multi_pack_index_one(struct repository *r, + const char *object_dir, const char *midx_name, int local) { @@ -131,7 +132,7 @@ static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir m->data = midx_map; m->data_len = midx_size; m->local = local; - m->repo = the_repository; + m->repo = r; m->signature = get_be32(m->data); if (m->signature != MIDX_SIGNATURE) @@ -144,12 +145,12 @@ static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir m->version); hash_version = m->data[MIDX_BYTE_HASH_VERSION]; - if (hash_version != oid_version(the_hash_algo)) { + if (hash_version != oid_version(r->hash_algo)) { error(_("multi-pack-index hash version %u does not match version %u"), - hash_version, oid_version(the_hash_algo)); + hash_version, oid_version(r->hash_algo)); goto cleanup_fail; } - m->hash_len = the_hash_algo->rawsz; + m->hash_len = r->hash_algo->rawsz; m->num_chunks = m->data[MIDX_BYTE_NUM_CHUNKS]; @@ -206,8 +207,8 @@ static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir m->pack_names[i]); } - trace2_data_intmax("midx", the_repository, "load/num_packs", m->num_packs); - trace2_data_intmax("midx", the_repository, "load/num_objects", m->num_objects); + trace2_data_intmax("midx", r, "load/num_packs", m->num_packs); + trace2_data_intmax("midx", r, "load/num_objects", m->num_objects); free_chunkfile(cf); return m; @@ -240,8 +241,9 @@ void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir, strbuf_addf(buf, "/multi-pack-index-%s.%s", hash_to_hex(hash), ext); } -static int open_multi_pack_index_chain(const char *chain_file, - int *fd, struct stat *st) +static int open_multi_pack_index_chain(const struct git_hash_algo *hash_algo, + const char *chain_file, int *fd, + struct stat *st) { *fd = git_open(chain_file); if (*fd < 0) @@ -250,7 +252,7 @@ static int open_multi_pack_index_chain(const char *chain_file, close(*fd); return 0; } - if (st->st_size < the_hash_algo->hexsz) { + if (st->st_size < hash_algo->hexsz) { close(*fd); if (!st->st_size) { /* treat empty files the same as missing */ @@ -292,7 +294,8 @@ static int add_midx_to_chain(struct multi_pack_index *midx, return 1; } -static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, +static struct multi_pack_index *load_midx_chain_fd_st(struct repository *r, + const char *object_dir, int local, int fd, struct stat *st, int *incomplete_chain) @@ -303,7 +306,7 @@ static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, uint32_t i, count; FILE *fp = xfdopen(fd, "r"); - count = st->st_size / (the_hash_algo->hexsz + 1); + count = st->st_size / (r->hash_algo->hexsz + 1); for (i = 0; i < count; i++) { struct multi_pack_index *m; @@ -312,7 +315,7 @@ static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, if (strbuf_getline_lf(&buf, fp) == EOF) break; - if (get_oid_hex(buf.buf, &layer)) { + if (get_oid_hex_algop(buf.buf, &layer, r->hash_algo)) { warning(_("invalid multi-pack-index chain: line '%s' " "not a hash"), buf.buf); @@ -325,7 +328,7 @@ static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, strbuf_reset(&buf); get_split_midx_filename_ext(&buf, object_dir, layer.hash, MIDX_EXT_MIDX); - m = load_multi_pack_index_one(object_dir, buf.buf, local); + m = load_multi_pack_index_one(r, object_dir, buf.buf, local); if (m) { if (add_midx_to_chain(m, midx_chain)) { @@ -348,7 +351,8 @@ static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, return midx_chain; } -static struct multi_pack_index *load_multi_pack_index_chain(const char *object_dir, +static struct multi_pack_index *load_multi_pack_index_chain(struct repository *r, + const char *object_dir, int local) { struct strbuf chain_file = STRBUF_INIT; @@ -357,10 +361,10 @@ static struct multi_pack_index *load_multi_pack_index_chain(const char *object_d struct multi_pack_index *m = NULL; get_midx_chain_filename(&chain_file, object_dir); - if (open_multi_pack_index_chain(chain_file.buf, &fd, &st)) { + if (open_multi_pack_index_chain(r->hash_algo, chain_file.buf, &fd, &st)) { int incomplete; /* ownership of fd is taken over by load function */ - m = load_midx_chain_fd_st(object_dir, local, fd, &st, + m = load_midx_chain_fd_st(r, object_dir, local, fd, &st, &incomplete); } @@ -376,9 +380,10 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, get_midx_filename(&midx_name, object_dir); - m = load_multi_pack_index_one(object_dir, midx_name.buf, local); + m = load_multi_pack_index_one(the_repository, object_dir, + midx_name.buf, local); if (!m) - m = load_multi_pack_index_chain(object_dir, local); + m = load_multi_pack_index_chain(the_repository, object_dir, local); strbuf_release(&midx_name); @@ -520,7 +525,7 @@ int bsearch_one_midx(const struct object_id *oid, struct multi_pack_index *m, uint32_t *result) { int ret = bsearch_hash(oid->hash, m->chunk_oid_fanout, - m->chunk_oid_lookup, the_hash_algo->rawsz, + m->chunk_oid_lookup, m->repo->hash_algo->rawsz, result); if (result) *result += m->num_objects_in_base; @@ -551,7 +556,7 @@ struct object_id *nth_midxed_object_oid(struct object_id *oid, n = midx_for_object(&m, n); oidread(oid, m->chunk_oid_lookup + st_mult(m->hash_len, n), - the_repository->hash_algo); + m->repo->hash_algo); return oid; } From 545702e276fdadd6f71cd11c8a9ef1bb56d223d3 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:31 +0100 Subject: [PATCH 6/8] midx: pass `repository` to `load_multi_pack_index` The `load_multi_pack_index` function in midx uses `the_repository` variable to access the `repository` struct. Modify the function and its callee's to send the `repository` field. This moves usage of `the_repository` to the `test-read-midx.c` file. While that is not optimal, it is okay, since the upcoming commits will slowly move the usage of `the_repository` up the layers and remove it eventually. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx.c | 11 ++++++----- midx.h | 4 +++- t/helper/test-read-midx.c | 8 ++++---- 3 files changed, 13 insertions(+), 10 deletions(-) diff --git a/midx.c b/midx.c index 6f0fb8285af148..98ee84d4a8bf38 100644 --- a/midx.c +++ b/midx.c @@ -372,7 +372,8 @@ static struct multi_pack_index *load_multi_pack_index_chain(struct repository *r return m; } -struct multi_pack_index *load_multi_pack_index(const char *object_dir, +struct multi_pack_index *load_multi_pack_index(struct repository *r, + const char *object_dir, int local) { struct strbuf midx_name = STRBUF_INIT; @@ -380,10 +381,10 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, get_midx_filename(&midx_name, object_dir); - m = load_multi_pack_index_one(the_repository, object_dir, + m = load_multi_pack_index_one(r, object_dir, midx_name.buf, local); if (!m) - m = load_multi_pack_index_chain(the_repository, object_dir, local); + m = load_multi_pack_index_chain(r, object_dir, local); strbuf_release(&midx_name); @@ -727,7 +728,7 @@ int prepare_multi_pack_index_one(struct repository *r, const char *object_dir, i if (!strcmp(object_dir, m_search->object_dir)) return 1; - m = load_multi_pack_index(object_dir, local); + m = load_multi_pack_index(r, object_dir, local); if (m) { struct multi_pack_index *mp = r->objects->multi_pack_index; @@ -881,7 +882,7 @@ int verify_midx_file(struct repository *r, const char *object_dir, unsigned flag struct pair_pos_vs_id *pairs = NULL; uint32_t i; struct progress *progress = NULL; - struct multi_pack_index *m = load_multi_pack_index(object_dir, 1); + struct multi_pack_index *m = load_multi_pack_index(r, object_dir, 1); struct multi_pack_index *curr; verify_midx_error = 0; diff --git a/midx.h b/midx.h index c37ad5b5242b56..78efa28d353717 100644 --- a/midx.h +++ b/midx.h @@ -97,7 +97,9 @@ void get_midx_chain_filename(struct strbuf *buf, const char *object_dir); void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir, const unsigned char *hash, const char *ext); -struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local); +struct multi_pack_index *load_multi_pack_index(struct repository *r, + const char *object_dir, + int local); int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, uint32_t pack_int_id); struct packed_git *nth_midxed_pack(struct multi_pack_index *m, uint32_t pack_int_id); diff --git a/t/helper/test-read-midx.c b/t/helper/test-read-midx.c index 438fb9fc6197fc..fc632369618917 100644 --- a/t/helper/test-read-midx.c +++ b/t/helper/test-read-midx.c @@ -18,7 +18,7 @@ static int read_midx_file(const char *object_dir, const char *checksum, struct multi_pack_index *m; setup_git_directory(); - m = load_multi_pack_index(object_dir, 1); + m = load_multi_pack_index(the_repository, object_dir, 1); if (!m) return 1; @@ -82,7 +82,7 @@ static int read_midx_checksum(const char *object_dir) struct multi_pack_index *m; setup_git_directory(); - m = load_multi_pack_index(object_dir, 1); + m = load_multi_pack_index(the_repository, object_dir, 1); if (!m) return 1; printf("%s\n", hash_to_hex(get_midx_checksum(m))); @@ -98,7 +98,7 @@ static int read_midx_preferred_pack(const char *object_dir) setup_git_directory(); - midx = load_multi_pack_index(object_dir, 1); + midx = load_multi_pack_index(the_repository, object_dir, 1); if (!midx) return 1; @@ -121,7 +121,7 @@ static int read_midx_bitmapped_packs(const char *object_dir) setup_git_directory(); - midx = load_multi_pack_index(object_dir, 1); + midx = load_multi_pack_index(the_repository, object_dir, 1); if (!midx) return 1; From e9b91eaad5bac821a24c927a09300bd4a80fa0f7 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:32 +0100 Subject: [PATCH 7/8] midx: pass down `hash_algo` to functions using global variables The functions `get_split_midx_filename_ext()`, `get_midx_filename()` and `get_midx_filename_ext()` use `hash_to_hex()` which internally uses the `the_hash_algo` global variable. Remove this dependency on global variables by passing down the `hash_algo` through to the functions mentioned and instead calling `hash_to_hex_algop()` along with the obtained `hash_algo`. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx-write.c | 22 +++++++++++----------- midx.c | 26 +++++++++++++++----------- midx.h | 10 +++++++--- pack-bitmap.c | 6 +++--- pack-revindex.c | 2 +- 5 files changed, 37 insertions(+), 29 deletions(-) diff --git a/midx-write.c b/midx-write.c index 1bc2f5256916e6..bcd1d50eb0f5c2 100644 --- a/midx-write.c +++ b/midx-write.c @@ -991,9 +991,10 @@ static int link_midx_to_chain(struct multi_pack_index *m) for (i = 0; i < ARRAY_SIZE(midx_exts); i++) { const unsigned char *hash = get_midx_checksum(m); - get_midx_filename_ext(&from, m->object_dir, hash, - midx_exts[i].non_split); - get_split_midx_filename_ext(&to, m->object_dir, hash, + get_midx_filename_ext(m->repo->hash_algo, &from, m->object_dir, + hash, midx_exts[i].non_split); + get_split_midx_filename_ext(m->repo->hash_algo, &to, + m->object_dir, hash, midx_exts[i].split); if (link(from.buf, to.buf) < 0 && errno != ENOENT) { @@ -1012,9 +1013,8 @@ static int link_midx_to_chain(struct multi_pack_index *m) return ret; } -static void clear_midx_files(const char *object_dir, - const char **hashes, - uint32_t hashes_nr, +static void clear_midx_files(struct repository *r, const char *object_dir, + const char **hashes, uint32_t hashes_nr, unsigned incremental) { /* @@ -1039,7 +1039,7 @@ static void clear_midx_files(const char *object_dir, } if (incremental) - get_midx_filename(&buf, object_dir); + get_midx_filename(r->hash_algo, &buf, object_dir); else get_midx_chain_filename(&buf, object_dir); @@ -1083,7 +1083,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir, "%s/pack/multi-pack-index.d/tmp_midx_XXXXXX", object_dir); else - get_midx_filename(&midx_name, object_dir); + get_midx_filename(r->hash_algo, &midx_name, object_dir); if (safe_create_leading_directories(midx_name.buf)) die_errno(_("unable to create leading directories of %s"), midx_name.buf); @@ -1440,8 +1440,8 @@ static int write_midx_internal(struct repository *r, const char *object_dir, if (link_midx_to_chain(ctx.base_midx) < 0) return -1; - get_split_midx_filename_ext(&final_midx_name, object_dir, - midx_hash, MIDX_EXT_MIDX); + get_split_midx_filename_ext(r->hash_algo, &final_midx_name, + object_dir, midx_hash, MIDX_EXT_MIDX); if (rename_tempfile(&incr, final_midx_name.buf) < 0) { error_errno(_("unable to rename new multi-pack-index layer")); @@ -1474,7 +1474,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir, if (commit_lock_file(&lk) < 0) die_errno(_("could not write multi-pack-index")); - clear_midx_files(object_dir, keep_hashes, + clear_midx_files(r, object_dir, keep_hashes, ctx.num_multi_pack_indexes_before + 1, ctx.incremental); diff --git a/midx.c b/midx.c index 98ee84d4a8bf38..f45ea842cd6eda 100644 --- a/midx.c +++ b/midx.c @@ -28,17 +28,19 @@ const unsigned char *get_midx_checksum(struct multi_pack_index *m) return m->data + m->data_len - m->repo->hash_algo->rawsz; } -void get_midx_filename(struct strbuf *out, const char *object_dir) +void get_midx_filename(const struct git_hash_algo *hash_algo, + struct strbuf *out, const char *object_dir) { - get_midx_filename_ext(out, object_dir, NULL, NULL); + get_midx_filename_ext(hash_algo, out, object_dir, NULL, NULL); } -void get_midx_filename_ext(struct strbuf *out, const char *object_dir, +void get_midx_filename_ext(const struct git_hash_algo *hash_algo, + struct strbuf *out, const char *object_dir, const unsigned char *hash, const char *ext) { strbuf_addf(out, "%s/pack/multi-pack-index", object_dir); if (ext) - strbuf_addf(out, "-%s.%s", hash_to_hex(hash), ext); + strbuf_addf(out, "-%s.%s", hash_to_hex_algop(hash, hash_algo), ext); } static int midx_read_oid_fanout(const unsigned char *chunk_start, @@ -234,11 +236,13 @@ void get_midx_chain_filename(struct strbuf *buf, const char *object_dir) strbuf_addstr(buf, "/multi-pack-index-chain"); } -void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir, +void get_split_midx_filename_ext(const struct git_hash_algo *hash_algo, + struct strbuf *buf, const char *object_dir, const unsigned char *hash, const char *ext) { get_midx_chain_dirname(buf, object_dir); - strbuf_addf(buf, "/multi-pack-index-%s.%s", hash_to_hex(hash), ext); + strbuf_addf(buf, "/multi-pack-index-%s.%s", + hash_to_hex_algop(hash, hash_algo), ext); } static int open_multi_pack_index_chain(const struct git_hash_algo *hash_algo, @@ -326,8 +330,8 @@ static struct multi_pack_index *load_midx_chain_fd_st(struct repository *r, valid = 0; strbuf_reset(&buf); - get_split_midx_filename_ext(&buf, object_dir, layer.hash, - MIDX_EXT_MIDX); + get_split_midx_filename_ext(r->hash_algo, &buf, object_dir, + layer.hash, MIDX_EXT_MIDX); m = load_multi_pack_index_one(r, object_dir, buf.buf, local); if (m) { @@ -379,7 +383,7 @@ struct multi_pack_index *load_multi_pack_index(struct repository *r, struct strbuf midx_name = STRBUF_INIT; struct multi_pack_index *m; - get_midx_filename(&midx_name, object_dir); + get_midx_filename(r->hash_algo, &midx_name, object_dir); m = load_multi_pack_index_one(r, object_dir, midx_name.buf, local); @@ -822,7 +826,7 @@ void clear_midx_file(struct repository *r) { struct strbuf midx = STRBUF_INIT; - get_midx_filename(&midx, r->objects->odb->path); + get_midx_filename(r->hash_algo, &midx, r->objects->odb->path); if (r->objects && r->objects->multi_pack_index) { close_midx(r->objects->multi_pack_index); @@ -891,7 +895,7 @@ int verify_midx_file(struct repository *r, const char *object_dir, unsigned flag struct stat sb; struct strbuf filename = STRBUF_INIT; - get_midx_filename(&filename, object_dir); + get_midx_filename(r->hash_algo, &filename, object_dir); if (!stat(filename.buf, &sb)) { error(_("multi-pack-index file exists, but failed to parse")); diff --git a/midx.h b/midx.h index 78efa28d353717..9d1374cbd58d01 100644 --- a/midx.h +++ b/midx.h @@ -7,6 +7,7 @@ struct object_id; struct pack_entry; struct repository; struct bitmapped_pack; +struct git_hash_algo; #define MIDX_SIGNATURE 0x4d494458 /* "MIDX" */ #define MIDX_VERSION 1 @@ -89,12 +90,15 @@ struct multi_pack_index { #define MIDX_EXT_MIDX "midx" const unsigned char *get_midx_checksum(struct multi_pack_index *m); -void get_midx_filename(struct strbuf *out, const char *object_dir); -void get_midx_filename_ext(struct strbuf *out, const char *object_dir, +void get_midx_filename(const struct git_hash_algo *hash_algo, + struct strbuf *out, const char *object_dir); +void get_midx_filename_ext(const struct git_hash_algo *hash_algo, + struct strbuf *out, const char *object_dir, const unsigned char *hash, const char *ext); void get_midx_chain_dirname(struct strbuf *buf, const char *object_dir); void get_midx_chain_filename(struct strbuf *buf, const char *object_dir); -void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir, +void get_split_midx_filename_ext(const struct git_hash_algo *hash_algo, + struct strbuf *buf, const char *object_dir, const unsigned char *hash, const char *ext); struct multi_pack_index *load_multi_pack_index(struct repository *r, diff --git a/pack-bitmap.c b/pack-bitmap.c index 0cb1b56c9d5a55..7b62d099cab572 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -375,8 +375,8 @@ static int load_bitmap_entries_v1(struct bitmap_index *index) char *midx_bitmap_filename(struct multi_pack_index *midx) { struct strbuf buf = STRBUF_INIT; - get_midx_filename_ext(&buf, midx->object_dir, get_midx_checksum(midx), - MIDX_EXT_BITMAP); + get_midx_filename_ext(midx->repo->hash_algo, &buf, midx->object_dir, + get_midx_checksum(midx), MIDX_EXT_BITMAP); return strbuf_detach(&buf, NULL); } @@ -415,7 +415,7 @@ static int open_midx_bitmap_1(struct bitmap_index *bitmap_git, if (bitmap_git->pack || bitmap_git->midx) { struct strbuf buf = STRBUF_INIT; - get_midx_filename(&buf, midx->object_dir); + get_midx_filename(midx->repo->hash_algo, &buf, midx->object_dir); trace2_data_string("bitmap", bitmap_repo(bitmap_git), "ignoring extra midx bitmap file", buf.buf); close(fd); diff --git a/pack-revindex.c b/pack-revindex.c index 22d3c2346488de..d3832478d99edf 100644 --- a/pack-revindex.c +++ b/pack-revindex.c @@ -383,7 +383,7 @@ int load_midx_revindex(struct multi_pack_index *m) trace2_data_string("load_midx_revindex", the_repository, "source", "rev"); - get_midx_filename_ext(&revindex_name, m->object_dir, + get_midx_filename_ext(m->repo->hash_algo, &revindex_name, m->object_dir, get_midx_checksum(m), MIDX_EXT_REV); ret = load_revindex_from_disk(revindex_name.buf, From 36a7b11389f405608f8a58f0c5ae12a8dec25016 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:33 +0100 Subject: [PATCH 8/8] midx: inline the `MIDX_MIN_SIZE` definition The `MIDX_MIN_SIZE` definition is used to check the midx_size in `local_multi_pack_index_one`. This definition relies on the `the_hash_algo` global variable. Inline this and remove the global variable usage. With this, remove `USE_THE_REPOSITORY_VARIABLE` usage from `midx.c`. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/midx.c b/midx.c index f45ea842cd6eda..e0eae1c25ec91f 100644 --- a/midx.c +++ b/midx.c @@ -1,5 +1,3 @@ -#define USE_THE_REPOSITORY_VARIABLE - #include "git-compat-util.h" #include "config.h" #include "dir.h" @@ -94,8 +92,6 @@ static int midx_read_object_offsets(const unsigned char *chunk_start, return 0; } -#define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + the_hash_algo->rawsz) - static struct multi_pack_index *load_multi_pack_index_one(struct repository *r, const char *object_dir, const char *midx_name, @@ -122,7 +118,7 @@ static struct multi_pack_index *load_multi_pack_index_one(struct repository *r, midx_size = xsize_t(st.st_size); - if (midx_size < MIDX_MIN_SIZE) { + if (midx_size < (MIDX_HEADER_SIZE + r->hash_algo->rawsz)) { error(_("multi-pack-index file %s is too small"), midx_name); goto cleanup_fail; }