From 17e80398782b4e8746a389604aaaf9744fd6900a Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 18 Nov 2024 16:33:52 +0100 Subject: [PATCH 1/7] reftable/system: move "dir.h" to its only user We still include "dir.h" in "reftable/system.h" even though it is not used by anything but by a single unit test. Move it over into that unit test so that we don't accidentally use any functionality provided by it in the reftable codebase. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/system.h | 1 - t/unit-tests/t-reftable-stack.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/reftable/system.h b/reftable/system.h index 5ec8583343..8564213475 100644 --- a/reftable/system.h +++ b/reftable/system.h @@ -15,7 +15,6 @@ https://developers.google.com/open-source/licenses/bsd #include "lockfile.h" #include "tempfile.h" #include "hash.h" /* hash ID, sizes.*/ -#include "dir.h" /* remove_dir_recursively, for tests.*/ int hash_size(uint32_t id); diff --git a/t/unit-tests/t-reftable-stack.c b/t/unit-tests/t-reftable-stack.c index 72f6747064..1b4363a58f 100644 --- a/t/unit-tests/t-reftable-stack.c +++ b/t/unit-tests/t-reftable-stack.c @@ -8,6 +8,7 @@ https://developers.google.com/open-source/licenses/bsd #include "test-lib.h" #include "lib-reftable.h" +#include "dir.h" #include "reftable/merged.h" #include "reftable/reader.h" #include "reftable/reftable-error.h" From 88e297275b94f2fbbc60b770f37654796799b907 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 18 Nov 2024 16:33:55 +0100 Subject: [PATCH 2/7] reftable: explicitly handle hash format IDs The hash format IDs are used for two different things across the reftable codebase: - They are used as a 32 bit unsigned integer when reading and writing the header in order to identify the hash function. - They are used internally to identify which hash function is in use. When one only considers the second usecase one might think that one can easily change the representation of those hash IDs. But because those IDs end up in the reftable header and footer on disk it is important that those never change. Create separate constants `REFTABLE_FORMAT_ID_*` and use them in contexts where we read or write reftable headers. This serves multiple purposes: - It allows us to more easily discern cases where we actually use those constants for the on-disk format. - It detangles us from the same constants that are defined in libgit.a, which is another required step to convert the reftable library to become standalone. - It makes the next step easier where we stop using `GIT_*_FORMAT_ID` constants in favor of a custom enum. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/basics.h | 8 ++++++++ reftable/reader.c | 10 ++++++---- reftable/writer.c | 16 +++++++++++++++- 3 files changed, 29 insertions(+), 5 deletions(-) diff --git a/reftable/basics.h b/reftable/basics.h index 7aa46d7c30..bcab0b529b 100644 --- a/reftable/basics.h +++ b/reftable/basics.h @@ -150,4 +150,12 @@ int common_prefix_size(struct reftable_buf *a, struct reftable_buf *b); int hash_size(uint32_t id); +/* + * Format IDs that identify the hash function used by a reftable. Note that + * these constants end up on disk and thus mustn't change. The format IDs are + * "sha1" and "s256" in big endian, respectively. + */ +#define REFTABLE_FORMAT_ID_SHA1 ((uint32_t) 0x73686131) +#define REFTABLE_FORMAT_ID_SHA256 ((uint32_t) 0x73323536) + #endif diff --git a/reftable/reader.c b/reftable/reader.c index 90dc950b57..64eb6938ef 100644 --- a/reftable/reader.c +++ b/reftable/reader.c @@ -109,16 +109,18 @@ static int parse_footer(struct reftable_reader *r, uint8_t *footer, if (r->version == 1) { r->hash_id = GIT_SHA1_FORMAT_ID; } else { - r->hash_id = get_be32(f); - switch (r->hash_id) { - case GIT_SHA1_FORMAT_ID: + switch (get_be32(f)) { + case REFTABLE_FORMAT_ID_SHA1: + r->hash_id = GIT_SHA1_FORMAT_ID; break; - case GIT_SHA256_FORMAT_ID: + case REFTABLE_FORMAT_ID_SHA256: + r->hash_id = GIT_SHA256_FORMAT_ID; break; default: err = REFTABLE_FORMAT_ERROR; goto done; } + f += 4; } diff --git a/reftable/writer.c b/reftable/writer.c index fd136794d5..9aa45de634 100644 --- a/reftable/writer.c +++ b/reftable/writer.c @@ -103,8 +103,22 @@ static int writer_write_header(struct reftable_writer *w, uint8_t *dest) put_be64(dest + 8, w->min_update_index); put_be64(dest + 16, w->max_update_index); if (writer_version(w) == 2) { - put_be32(dest + 24, w->opts.hash_id); + uint32_t hash_id; + + switch (w->opts.hash_id) { + case GIT_SHA1_FORMAT_ID: + hash_id = REFTABLE_FORMAT_ID_SHA1; + break; + case GIT_SHA256_FORMAT_ID: + hash_id = REFTABLE_FORMAT_ID_SHA256; + break; + default: + return -1; + } + + put_be32(dest + 24, hash_id); } + return header_size(writer_version(w)); } From c2f08236ed786a48e50af33ecc5c0f951c14761b Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 18 Nov 2024 16:33:57 +0100 Subject: [PATCH 3/7] reftable/system: stop depending on "hash.h" We include "hash.h" in "reftable/system.h" such that we can use hash format IDs as well as the raw size of SHA1 and SHA256. As we are in the process of converting the reftable library to become standalone we of course cannot rely on those constants anymore. Introduce a new `enum reftable_hash` to replace internal uses of the hash format IDs and new constants that replace internal uses of the hash size. Adapt the reftable backend to set up the correct hash function. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- refs/reftable-backend.c | 12 +++++- reftable/basics.c | 13 ++++--- reftable/basics.h | 2 +- reftable/merged.c | 4 +- reftable/merged.h | 3 +- reftable/reader.c | 8 ++-- reftable/reader.h | 4 +- reftable/reftable-basics.h | 13 +++++++ reftable/reftable-merged.h | 4 +- reftable/reftable-reader.h | 2 +- reftable/reftable-record.h | 12 +++--- reftable/reftable-writer.h | 2 +- reftable/stack.c | 4 +- reftable/system.h | 3 -- reftable/writer.c | 8 ++-- t/helper/test-reftable.c | 4 +- t/unit-tests/lib-reftable.c | 4 +- t/unit-tests/lib-reftable.h | 2 +- t/unit-tests/t-reftable-block.c | 40 +++++++++---------- t/unit-tests/t-reftable-merged.c | 26 ++++++------- t/unit-tests/t-reftable-pq.c | 2 +- t/unit-tests/t-reftable-reader.c | 4 +- t/unit-tests/t-reftable-readwrite.c | 40 +++++++++---------- t/unit-tests/t-reftable-record.c | 59 +++++++++++++++-------------- t/unit-tests/t-reftable-stack.c | 34 ++++++++--------- 25 files changed, 166 insertions(+), 143 deletions(-) diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index 3c6107c7ce..7d86d92097 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -15,6 +15,7 @@ #include "../object.h" #include "../path.h" #include "../refs.h" +#include "../reftable/reftable-basics.h" #include "../reftable/reftable-stack.h" #include "../reftable/reftable-record.h" #include "../reftable/reftable-error.h" @@ -289,7 +290,16 @@ static struct ref_store *reftable_be_init(struct repository *repo, refs->store_flags = store_flags; refs->log_all_ref_updates = repo_settings_get_log_all_ref_updates(repo); - refs->write_options.hash_id = repo->hash_algo->format_id; + switch (repo->hash_algo->format_id) { + case GIT_SHA1_FORMAT_ID: + refs->write_options.hash_id = REFTABLE_HASH_SHA1; + break; + case GIT_SHA256_FORMAT_ID: + refs->write_options.hash_id = REFTABLE_HASH_SHA256; + break; + default: + BUG("unknown hash algorithm %d", repo->hash_algo->format_id); + } refs->write_options.default_permissions = calc_shared_perm(0666 & ~mask); refs->write_options.disable_auto_compact = !git_env_bool("GIT_TEST_REFTABLE_AUTOCOMPACTION", 1); diff --git a/reftable/basics.c b/reftable/basics.c index bc4fcc9144..7d84a5d62d 100644 --- a/reftable/basics.c +++ b/reftable/basics.c @@ -271,14 +271,15 @@ int common_prefix_size(struct reftable_buf *a, struct reftable_buf *b) return p; } -int hash_size(uint32_t id) +int hash_size(enum reftable_hash id) { + if (!id) + return REFTABLE_HASH_SIZE_SHA1; switch (id) { - case 0: - case GIT_SHA1_FORMAT_ID: - return GIT_SHA1_RAWSZ; - case GIT_SHA256_FORMAT_ID: - return GIT_SHA256_RAWSZ; + case REFTABLE_HASH_SHA1: + return REFTABLE_HASH_SIZE_SHA1; + case REFTABLE_HASH_SHA256: + return REFTABLE_HASH_SIZE_SHA256; } abort(); } diff --git a/reftable/basics.h b/reftable/basics.h index bcab0b529b..36beda2c25 100644 --- a/reftable/basics.h +++ b/reftable/basics.h @@ -148,7 +148,7 @@ char *reftable_strdup(const char *str); /* Find the longest shared prefix size of `a` and `b` */ int common_prefix_size(struct reftable_buf *a, struct reftable_buf *b); -int hash_size(uint32_t id); +int hash_size(enum reftable_hash id); /* * Format IDs that identify the hash function used by a reftable. Note that diff --git a/reftable/merged.c b/reftable/merged.c index 514d6facf4..5b93e20f42 100644 --- a/reftable/merged.c +++ b/reftable/merged.c @@ -181,7 +181,7 @@ static void iterator_from_merged_iter(struct reftable_iterator *it, int reftable_merged_table_new(struct reftable_merged_table **dest, struct reftable_reader **readers, size_t n, - uint32_t hash_id) + enum reftable_hash hash_id) { struct reftable_merged_table *m = NULL; uint64_t last_max = 0; @@ -293,7 +293,7 @@ int reftable_merged_table_init_log_iterator(struct reftable_merged_table *mt, return merged_table_init_iter(mt, it, BLOCK_TYPE_LOG); } -uint32_t reftable_merged_table_hash_id(struct reftable_merged_table *mt) +enum reftable_hash reftable_merged_table_hash_id(struct reftable_merged_table *mt) { return mt->hash_id; } diff --git a/reftable/merged.h b/reftable/merged.h index 89bd0c4b35..0b7d939e92 100644 --- a/reftable/merged.h +++ b/reftable/merged.h @@ -10,11 +10,12 @@ https://developers.google.com/open-source/licenses/bsd #define MERGED_H #include "system.h" +#include "reftable-basics.h" struct reftable_merged_table { struct reftable_reader **readers; size_t readers_len; - uint32_t hash_id; + enum reftable_hash hash_id; /* If unset, produce deletions. This is useful for compaction. For the * full stack, deletions should be produced. */ diff --git a/reftable/reader.c b/reftable/reader.c index 64eb6938ef..ea82955c9b 100644 --- a/reftable/reader.c +++ b/reftable/reader.c @@ -67,7 +67,7 @@ static int reader_get_block(struct reftable_reader *r, return block_source_read_block(&r->source, dest, off, sz); } -uint32_t reftable_reader_hash_id(struct reftable_reader *r) +enum reftable_hash reftable_reader_hash_id(struct reftable_reader *r) { return r->hash_id; } @@ -107,14 +107,14 @@ static int parse_footer(struct reftable_reader *r, uint8_t *footer, f += 8; if (r->version == 1) { - r->hash_id = GIT_SHA1_FORMAT_ID; + r->hash_id = REFTABLE_HASH_SHA1; } else { switch (get_be32(f)) { case REFTABLE_FORMAT_ID_SHA1: - r->hash_id = GIT_SHA1_FORMAT_ID; + r->hash_id = REFTABLE_HASH_SHA1; break; case REFTABLE_FORMAT_ID_SHA256: - r->hash_id = GIT_SHA256_FORMAT_ID; + r->hash_id = REFTABLE_HASH_SHA256; break; default: err = REFTABLE_FORMAT_ERROR; diff --git a/reftable/reader.h b/reftable/reader.h index 010fbfe851..d2b48a4849 100644 --- a/reftable/reader.h +++ b/reftable/reader.h @@ -37,8 +37,8 @@ struct reftable_reader { /* Size of the file, excluding the footer. */ uint64_t size; - /* 'sha1' for SHA1, 's256' for SHA-256 */ - uint32_t hash_id; + /* The hash function used for ref records. */ + enum reftable_hash hash_id; uint32_t block_size; uint64_t min_update_index; diff --git a/reftable/reftable-basics.h b/reftable/reftable-basics.h index 6e8e636b71..e0397ed583 100644 --- a/reftable/reftable-basics.h +++ b/reftable/reftable-basics.h @@ -11,6 +11,19 @@ #include +/* + * Hash functions understood by the reftable library. Note that the values are + * arbitrary and somewhat random such that we can easily detect cases where the + * hash hasn't been properly set up. + */ +enum reftable_hash { + REFTABLE_HASH_SHA1 = 89, + REFTABLE_HASH_SHA256 = 247, +}; +#define REFTABLE_HASH_SIZE_SHA1 20 +#define REFTABLE_HASH_SIZE_SHA256 32 +#define REFTABLE_HASH_SIZE_MAX REFTABLE_HASH_SIZE_SHA256 + /* Overrides the functions to use for memory management. */ void reftable_set_alloc(void *(*malloc)(size_t), void *(*realloc)(void *, size_t), void (*free)(void *)); diff --git a/reftable/reftable-merged.h b/reftable/reftable-merged.h index a970d5dd89..f2d01c3ef8 100644 --- a/reftable/reftable-merged.h +++ b/reftable/reftable-merged.h @@ -34,7 +34,7 @@ struct reftable_reader; */ int reftable_merged_table_new(struct reftable_merged_table **dest, struct reftable_reader **readers, size_t n, - uint32_t hash_id); + enum reftable_hash hash_id); /* Initialize a merged table iterator for reading refs. */ int reftable_merged_table_init_ref_iterator(struct reftable_merged_table *mt, @@ -56,6 +56,6 @@ reftable_merged_table_min_update_index(struct reftable_merged_table *mt); void reftable_merged_table_free(struct reftable_merged_table *m); /* return the hash ID of the merged table. */ -uint32_t reftable_merged_table_hash_id(struct reftable_merged_table *m); +enum reftable_hash reftable_merged_table_hash_id(struct reftable_merged_table *m); #endif diff --git a/reftable/reftable-reader.h b/reftable/reftable-reader.h index 6a2d0b693f..0085fbb903 100644 --- a/reftable/reftable-reader.h +++ b/reftable/reftable-reader.h @@ -54,7 +54,7 @@ int reftable_reader_init_log_iterator(struct reftable_reader *r, struct reftable_iterator *it); /* returns the hash ID used in this table. */ -uint32_t reftable_reader_hash_id(struct reftable_reader *r); +enum reftable_hash reftable_reader_hash_id(struct reftable_reader *r); /* return an iterator for the refs pointing to `oid`. */ int reftable_reader_refs_for(struct reftable_reader *r, diff --git a/reftable/reftable-record.h b/reftable/reftable-record.h index 2d42463c58..ddd48eb579 100644 --- a/reftable/reftable-record.h +++ b/reftable/reftable-record.h @@ -9,7 +9,7 @@ https://developers.google.com/open-source/licenses/bsd #ifndef REFTABLE_RECORD_H #define REFTABLE_RECORD_H -#include "hash.h" +#include "reftable-basics.h" #include /* @@ -40,10 +40,10 @@ struct reftable_ref_record { #define REFTABLE_NR_REF_VALUETYPES 4 } value_type; union { - unsigned char val1[GIT_MAX_RAWSZ]; + unsigned char val1[REFTABLE_HASH_SIZE_MAX]; struct { - unsigned char value[GIT_MAX_RAWSZ]; /* first hash */ - unsigned char target_value[GIT_MAX_RAWSZ]; /* second hash */ + unsigned char value[REFTABLE_HASH_SIZE_MAX]; /* first hash */ + unsigned char target_value[REFTABLE_HASH_SIZE_MAX]; /* second hash */ } val2; char *symref; /* referent, malloced 0-terminated string */ } value; @@ -85,8 +85,8 @@ struct reftable_log_record { union { struct { - unsigned char new_hash[GIT_MAX_RAWSZ]; - unsigned char old_hash[GIT_MAX_RAWSZ]; + unsigned char new_hash[REFTABLE_HASH_SIZE_MAX]; + unsigned char old_hash[REFTABLE_HASH_SIZE_MAX]; char *name; char *email; uint64_t time; diff --git a/reftable/reftable-writer.h b/reftable/reftable-writer.h index e4fc953788..211860d08a 100644 --- a/reftable/reftable-writer.h +++ b/reftable/reftable-writer.h @@ -33,7 +33,7 @@ struct reftable_write_options { /* 4-byte identifier ("sha1", "s256") of the hash. * Defaults to SHA1 if unset */ - uint32_t hash_id; + enum reftable_hash hash_id; /* Default mode for creating files. If unset, use 0666 (+umask) */ unsigned int default_permissions; diff --git a/reftable/stack.c b/reftable/stack.c index c33979536e..9ae716ff37 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -73,7 +73,7 @@ int reftable_new_stack(struct reftable_stack **dest, const char *dir, if (_opts) opts = *_opts; if (opts.hash_id == 0) - opts.hash_id = GIT_SHA1_FORMAT_ID; + opts.hash_id = REFTABLE_HASH_SHA1; *dest = NULL; @@ -1603,7 +1603,7 @@ struct segment suggest_compaction_segment(uint64_t *sizes, size_t n, static uint64_t *stack_table_sizes_for_compaction(struct reftable_stack *st) { - int version = (st->opts.hash_id == GIT_SHA1_FORMAT_ID) ? 1 : 2; + int version = (st->opts.hash_id == REFTABLE_HASH_SHA1) ? 1 : 2; int overhead = header_size(version) - 1; uint64_t *sizes; diff --git a/reftable/system.h b/reftable/system.h index 8564213475..38d3534620 100644 --- a/reftable/system.h +++ b/reftable/system.h @@ -14,8 +14,5 @@ https://developers.google.com/open-source/licenses/bsd #include "git-compat-util.h" #include "lockfile.h" #include "tempfile.h" -#include "hash.h" /* hash ID, sizes.*/ - -int hash_size(uint32_t id); #endif diff --git a/reftable/writer.c b/reftable/writer.c index 9aa45de634..ea2f831fc5 100644 --- a/reftable/writer.c +++ b/reftable/writer.c @@ -79,7 +79,7 @@ static void options_set_defaults(struct reftable_write_options *opts) } if (opts->hash_id == 0) { - opts->hash_id = GIT_SHA1_FORMAT_ID; + opts->hash_id = REFTABLE_HASH_SHA1; } if (opts->block_size == 0) { opts->block_size = DEFAULT_BLOCK_SIZE; @@ -88,7 +88,7 @@ static void options_set_defaults(struct reftable_write_options *opts) static int writer_version(struct reftable_writer *w) { - return (w->opts.hash_id == 0 || w->opts.hash_id == GIT_SHA1_FORMAT_ID) ? + return (w->opts.hash_id == 0 || w->opts.hash_id == REFTABLE_HASH_SHA1) ? 1 : 2; } @@ -106,10 +106,10 @@ static int writer_write_header(struct reftable_writer *w, uint8_t *dest) uint32_t hash_id; switch (w->opts.hash_id) { - case GIT_SHA1_FORMAT_ID: + case REFTABLE_HASH_SHA1: hash_id = REFTABLE_FORMAT_ID_SHA1; break; - case GIT_SHA256_FORMAT_ID: + case REFTABLE_HASH_SHA256: hash_id = REFTABLE_FORMAT_ID_SHA256; break; default: diff --git a/t/helper/test-reftable.c b/t/helper/test-reftable.c index 5c8849d115..3c72ed985b 100644 --- a/t/helper/test-reftable.c +++ b/t/helper/test-reftable.c @@ -156,7 +156,7 @@ int cmd__dump_reftable(int argc, const char **argv) int opt_dump_blocks = 0; int opt_dump_table = 0; int opt_dump_stack = 0; - uint32_t opt_hash_id = GIT_SHA1_FORMAT_ID; + uint32_t opt_hash_id = REFTABLE_HASH_SHA1; const char *arg = NULL, *argv0 = argv[0]; for (; argc > 1; argv++, argc--) @@ -167,7 +167,7 @@ int cmd__dump_reftable(int argc, const char **argv) else if (!strcmp("-t", argv[1])) opt_dump_table = 1; else if (!strcmp("-6", argv[1])) - opt_hash_id = GIT_SHA256_FORMAT_ID; + opt_hash_id = REFTABLE_HASH_SHA256; else if (!strcmp("-s", argv[1])) opt_dump_stack = 1; else if (!strcmp("-?", argv[1]) || !strcmp("-h", argv[1])) { diff --git a/t/unit-tests/lib-reftable.c b/t/unit-tests/lib-reftable.c index 2ddf480588..c1631f4527 100644 --- a/t/unit-tests/lib-reftable.c +++ b/t/unit-tests/lib-reftable.c @@ -3,7 +3,7 @@ #include "reftable/constants.h" #include "reftable/writer.h" -void t_reftable_set_hash(uint8_t *p, int i, uint32_t id) +void t_reftable_set_hash(uint8_t *p, int i, enum reftable_hash id) { memset(p, (uint8_t)i, hash_size(id)); } @@ -82,7 +82,7 @@ void t_reftable_write_to_buf(struct reftable_buf *buf, size_t off = i * (opts.block_size ? opts.block_size : DEFAULT_BLOCK_SIZE); if (!off) - off = header_size(opts.hash_id == GIT_SHA256_FORMAT_ID ? 2 : 1); + off = header_size(opts.hash_id == REFTABLE_HASH_SHA256 ? 2 : 1); check_char(buf->buf[off], ==, 'r'); } diff --git a/t/unit-tests/lib-reftable.h b/t/unit-tests/lib-reftable.h index d4950fed3d..e4c360fa7e 100644 --- a/t/unit-tests/lib-reftable.h +++ b/t/unit-tests/lib-reftable.h @@ -6,7 +6,7 @@ struct reftable_buf; -void t_reftable_set_hash(uint8_t *p, int i, uint32_t id); +void t_reftable_set_hash(uint8_t *p, int i, enum reftable_hash id); struct reftable_writer *t_reftable_strbuf_writer(struct reftable_buf *buf, struct reftable_write_options *opts); diff --git a/t/unit-tests/t-reftable-block.c b/t/unit-tests/t-reftable-block.c index f9af907117..13e10807da 100644 --- a/t/unit-tests/t-reftable-block.c +++ b/t/unit-tests/t-reftable-block.c @@ -36,7 +36,7 @@ static void t_ref_block_read_write(void) block.len = block_size; block_source_from_buf(&block.source ,&buf); ret = block_writer_init(&bw, BLOCK_TYPE_REF, block.data, block_size, - header_off, hash_size(GIT_SHA1_FORMAT_ID)); + header_off, hash_size(REFTABLE_HASH_SHA1)); check(!ret); rec.u.ref.refname = (char *) ""; @@ -47,7 +47,7 @@ static void t_ref_block_read_write(void) for (i = 0; i < N; i++) { rec.u.ref.refname = xstrfmt("branch%02"PRIuMAX, (uintmax_t)i); rec.u.ref.value_type = REFTABLE_REF_VAL1; - memset(rec.u.ref.value.val1, i, GIT_SHA1_RAWSZ); + memset(rec.u.ref.value.val1, i, REFTABLE_HASH_SIZE_SHA1); recs[i] = rec; ret = block_writer_add(&bw, &rec); @@ -61,7 +61,7 @@ static void t_ref_block_read_write(void) block_writer_release(&bw); - block_reader_init(&br, &block, header_off, block_size, GIT_SHA1_RAWSZ); + block_reader_init(&br, &block, header_off, block_size, REFTABLE_HASH_SIZE_SHA1); block_iter_seek_start(&it, &br); @@ -72,7 +72,7 @@ static void t_ref_block_read_write(void) check_int(i, ==, N); break; } - check(reftable_record_equal(&recs[i], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1)); } for (i = 0; i < N; i++) { @@ -85,7 +85,7 @@ static void t_ref_block_read_write(void) ret = block_iter_next(&it, &rec); check_int(ret, ==, 0); - check(reftable_record_equal(&recs[i], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1)); want.len--; ret = block_iter_seek_key(&it, &br, &want); @@ -93,7 +93,7 @@ static void t_ref_block_read_write(void) ret = block_iter_next(&it, &rec); check_int(ret, ==, 0); - check(reftable_record_equal(&recs[10 * (i / 10)], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[10 * (i / 10)], &rec, REFTABLE_HASH_SIZE_SHA1)); } block_reader_release(&br); @@ -130,7 +130,7 @@ static void t_log_block_read_write(void) block.len = block_size; block_source_from_buf(&block.source ,&buf); ret = block_writer_init(&bw, BLOCK_TYPE_LOG, block.data, block_size, - header_off, hash_size(GIT_SHA1_FORMAT_ID)); + header_off, hash_size(REFTABLE_HASH_SHA1)); check(!ret); for (i = 0; i < N; i++) { @@ -150,7 +150,7 @@ static void t_log_block_read_write(void) block_writer_release(&bw); - block_reader_init(&br, &block, header_off, block_size, GIT_SHA1_RAWSZ); + block_reader_init(&br, &block, header_off, block_size, REFTABLE_HASH_SIZE_SHA1); block_iter_seek_start(&it, &br); @@ -161,7 +161,7 @@ static void t_log_block_read_write(void) check_int(i, ==, N); break; } - check(reftable_record_equal(&recs[i], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1)); } for (i = 0; i < N; i++) { @@ -175,7 +175,7 @@ static void t_log_block_read_write(void) ret = block_iter_next(&it, &rec); check_int(ret, ==, 0); - check(reftable_record_equal(&recs[i], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1)); want.len--; ret = block_iter_seek_key(&it, &br, &want); @@ -183,7 +183,7 @@ static void t_log_block_read_write(void) ret = block_iter_next(&it, &rec); check_int(ret, ==, 0); - check(reftable_record_equal(&recs[10 * (i / 10)], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[10 * (i / 10)], &rec, REFTABLE_HASH_SIZE_SHA1)); } block_reader_release(&br); @@ -220,7 +220,7 @@ static void t_obj_block_read_write(void) block.len = block_size; block_source_from_buf(&block.source, &buf); ret = block_writer_init(&bw, BLOCK_TYPE_OBJ, block.data, block_size, - header_off, hash_size(GIT_SHA1_FORMAT_ID)); + header_off, hash_size(REFTABLE_HASH_SHA1)); check(!ret); for (i = 0; i < N; i++) { @@ -242,7 +242,7 @@ static void t_obj_block_read_write(void) block_writer_release(&bw); - block_reader_init(&br, &block, header_off, block_size, GIT_SHA1_RAWSZ); + block_reader_init(&br, &block, header_off, block_size, REFTABLE_HASH_SIZE_SHA1); block_iter_seek_start(&it, &br); @@ -253,7 +253,7 @@ static void t_obj_block_read_write(void) check_int(i, ==, N); break; } - check(reftable_record_equal(&recs[i], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1)); } for (i = 0; i < N; i++) { @@ -266,7 +266,7 @@ static void t_obj_block_read_write(void) ret = block_iter_next(&it, &rec); check_int(ret, ==, 0); - check(reftable_record_equal(&recs[i], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1)); } block_reader_release(&br); @@ -304,7 +304,7 @@ static void t_index_block_read_write(void) block.len = block_size; block_source_from_buf(&block.source, &buf); ret = block_writer_init(&bw, BLOCK_TYPE_INDEX, block.data, block_size, - header_off, hash_size(GIT_SHA1_FORMAT_ID)); + header_off, hash_size(REFTABLE_HASH_SHA1)); check(!ret); for (i = 0; i < N; i++) { @@ -326,7 +326,7 @@ static void t_index_block_read_write(void) block_writer_release(&bw); - block_reader_init(&br, &block, header_off, block_size, GIT_SHA1_RAWSZ); + block_reader_init(&br, &block, header_off, block_size, REFTABLE_HASH_SIZE_SHA1); block_iter_seek_start(&it, &br); @@ -337,7 +337,7 @@ static void t_index_block_read_write(void) check_int(i, ==, N); break; } - check(reftable_record_equal(&recs[i], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1)); } for (i = 0; i < N; i++) { @@ -350,7 +350,7 @@ static void t_index_block_read_write(void) ret = block_iter_next(&it, &rec); check_int(ret, ==, 0); - check(reftable_record_equal(&recs[i], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1)); want.len--; ret = block_iter_seek_key(&it, &br, &want); @@ -358,7 +358,7 @@ static void t_index_block_read_write(void) ret = block_iter_next(&it, &rec); check_int(ret, ==, 0); - check(reftable_record_equal(&recs[10 * (i / 10)], &rec, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&recs[10 * (i / 10)], &rec, REFTABLE_HASH_SIZE_SHA1)); } block_reader_release(&br); diff --git a/t/unit-tests/t-reftable-merged.c b/t/unit-tests/t-reftable-merged.c index 484c18251f..0573d9470a 100644 --- a/t/unit-tests/t-reftable-merged.c +++ b/t/unit-tests/t-reftable-merged.c @@ -42,7 +42,7 @@ merged_table_from_records(struct reftable_ref_record **refs, check(!err); } - err = reftable_merged_table_new(&mt, *readers, n, GIT_SHA1_FORMAT_ID); + err = reftable_merged_table_new(&mt, *readers, n, REFTABLE_HASH_SHA1); check(!err); return mt; } @@ -91,7 +91,7 @@ static void t_merged_single_record(void) err = reftable_iterator_next_ref(&it, &ref); check(!err); - check(reftable_ref_record_equal(&r2[0], &ref, GIT_SHA1_RAWSZ)); + check(reftable_ref_record_equal(&r2[0], &ref, REFTABLE_HASH_SIZE_SHA1)); reftable_ref_record_release(&ref); reftable_iterator_destroy(&it); readers_destroy(readers, 3); @@ -168,7 +168,7 @@ static void t_merged_refs(void) check(!err); err = reftable_iterator_seek_ref(&it, "a"); check(!err); - check_int(reftable_merged_table_hash_id(mt), ==, GIT_SHA1_FORMAT_ID); + check_int(reftable_merged_table_hash_id(mt), ==, REFTABLE_HASH_SHA1); check_int(reftable_merged_table_min_update_index(mt), ==, 1); check_int(reftable_merged_table_max_update_index(mt), ==, 3); @@ -186,7 +186,7 @@ static void t_merged_refs(void) check_int(ARRAY_SIZE(want), ==, len); for (i = 0; i < len; i++) check(reftable_ref_record_equal(want[i], &out[i], - GIT_SHA1_RAWSZ)); + REFTABLE_HASH_SIZE_SHA1)); for (i = 0; i < len; i++) reftable_ref_record_release(&out[i]); reftable_free(out); @@ -252,12 +252,12 @@ static void t_merged_seek_multiple_times(void) err = reftable_iterator_next_ref(&it, &rec); check(!err); - err = reftable_ref_record_equal(&rec, &r1[1], GIT_SHA1_RAWSZ); + err = reftable_ref_record_equal(&rec, &r1[1], REFTABLE_HASH_SIZE_SHA1); check(err == 1); err = reftable_iterator_next_ref(&it, &rec); check(!err); - err = reftable_ref_record_equal(&rec, &r2[1], GIT_SHA1_RAWSZ); + err = reftable_ref_record_equal(&rec, &r2[1], REFTABLE_HASH_SIZE_SHA1); check(err == 1); err = reftable_iterator_next_ref(&it, &rec); @@ -300,7 +300,7 @@ merged_table_from_log_records(struct reftable_log_record **logs, check(!err); } - err = reftable_merged_table_new(&mt, *readers, n, GIT_SHA1_FORMAT_ID); + err = reftable_merged_table_new(&mt, *readers, n, REFTABLE_HASH_SHA1); check(!err); return mt; } @@ -377,7 +377,7 @@ static void t_merged_logs(void) check(!err); err = reftable_iterator_seek_log(&it, "a"); check(!err); - check_int(reftable_merged_table_hash_id(mt), ==, GIT_SHA1_FORMAT_ID); + check_int(reftable_merged_table_hash_id(mt), ==, REFTABLE_HASH_SHA1); check_int(reftable_merged_table_min_update_index(mt), ==, 1); check_int(reftable_merged_table_max_update_index(mt), ==, 3); @@ -395,7 +395,7 @@ static void t_merged_logs(void) check_int(ARRAY_SIZE(want), ==, len); for (i = 0; i < len; i++) check(reftable_log_record_equal(want[i], &out[i], - GIT_SHA1_RAWSZ)); + REFTABLE_HASH_SIZE_SHA1)); err = merged_table_init_iter(mt, &it, BLOCK_TYPE_LOG); check(!err); @@ -404,7 +404,7 @@ static void t_merged_logs(void) reftable_log_record_release(&out[0]); err = reftable_iterator_next_log(&it, &out[0]); check(!err); - check(reftable_log_record_equal(&out[0], &r3[0], GIT_SHA1_RAWSZ)); + check(reftable_log_record_equal(&out[0], &r3[0], REFTABLE_HASH_SIZE_SHA1)); reftable_iterator_destroy(&it); for (i = 0; i < len; i++) @@ -448,11 +448,11 @@ static void t_default_write_opts(void) check(!err); hash_id = reftable_reader_hash_id(rd); - check_int(hash_id, ==, GIT_SHA1_FORMAT_ID); + check_int(hash_id, ==, REFTABLE_HASH_SHA1); - err = reftable_merged_table_new(&merged, &rd, 1, GIT_SHA256_FORMAT_ID); + err = reftable_merged_table_new(&merged, &rd, 1, REFTABLE_HASH_SHA256); check_int(err, ==, REFTABLE_FORMAT_ERROR); - err = reftable_merged_table_new(&merged, &rd, 1, GIT_SHA1_FORMAT_ID); + err = reftable_merged_table_new(&merged, &rd, 1, REFTABLE_HASH_SHA1); check(!err); reftable_reader_decref(rd); diff --git a/t/unit-tests/t-reftable-pq.c b/t/unit-tests/t-reftable-pq.c index ada4c19f18..272da05bea 100644 --- a/t/unit-tests/t-reftable-pq.c +++ b/t/unit-tests/t-reftable-pq.c @@ -132,7 +132,7 @@ static void t_merged_iter_pqueue_top(void) merged_iter_pqueue_check(&pq); check(pq_entry_equal(&top, &e)); - check(reftable_record_equal(top.rec, &recs[i], GIT_SHA1_RAWSZ)); + check(reftable_record_equal(top.rec, &recs[i], REFTABLE_HASH_SIZE_SHA1)); for (size_t j = 0; i < pq.len; j++) { check(pq_less(&top, &pq.heap[j])); check_int(top.index, >, j); diff --git a/t/unit-tests/t-reftable-reader.c b/t/unit-tests/t-reftable-reader.c index 19cb53b641..546df6005e 100644 --- a/t/unit-tests/t-reftable-reader.c +++ b/t/unit-tests/t-reftable-reader.c @@ -31,7 +31,7 @@ static int t_reader_seek_once(void) ret = reftable_iterator_next_ref(&it, &ref); check(!ret); - ret = reftable_ref_record_equal(&ref, &records[0], GIT_SHA1_RAWSZ); + ret = reftable_ref_record_equal(&ref, &records[0], REFTABLE_HASH_SIZE_SHA1); check_int(ret, ==, 1); ret = reftable_iterator_next_ref(&it, &ref); @@ -74,7 +74,7 @@ static int t_reader_reseek(void) ret = reftable_iterator_next_ref(&it, &ref); check(!ret); - ret = reftable_ref_record_equal(&ref, &records[0], GIT_SHA1_RAWSZ); + ret = reftable_ref_record_equal(&ref, &records[0], REFTABLE_HASH_SIZE_SHA1); check_int(ret, ==, 1); ret = reftable_iterator_next_ref(&it, &ref); diff --git a/t/unit-tests/t-reftable-readwrite.c b/t/unit-tests/t-reftable-readwrite.c index d279b86df0..57896922eb 100644 --- a/t/unit-tests/t-reftable-readwrite.c +++ b/t/unit-tests/t-reftable-readwrite.c @@ -41,7 +41,7 @@ static void t_buffer(void) } static void write_table(char ***names, struct reftable_buf *buf, int N, - int block_size, uint32_t hash_id) + int block_size, enum reftable_hash hash_id) { struct reftable_write_options opts = { .block_size = block_size, @@ -62,7 +62,7 @@ static void write_table(char ***names, struct reftable_buf *buf, int N, refs[i].refname = (*names)[i] = xstrfmt("refs/heads/branch%02d", i); refs[i].update_index = update_index; refs[i].value_type = REFTABLE_REF_VAL1; - t_reftable_set_hash(refs[i].value.val1, i, GIT_SHA1_FORMAT_ID); + t_reftable_set_hash(refs[i].value.val1, i, REFTABLE_HASH_SHA1); } for (i = 0; i < N; i++) { @@ -70,7 +70,7 @@ static void write_table(char ***names, struct reftable_buf *buf, int N, logs[i].update_index = update_index; logs[i].value_type = REFTABLE_LOG_UPDATE; t_reftable_set_hash(logs[i].value.update.new_hash, i, - GIT_SHA1_FORMAT_ID); + REFTABLE_HASH_SHA1); logs[i].value.update.message = (char *) "message"; } @@ -104,7 +104,7 @@ static void t_log_buffer_size(void) /* This tests buffer extension for log compression. Must use a random hash, to ensure that the compressed part is larger than the original. */ - for (i = 0; i < GIT_SHA1_RAWSZ; i++) { + for (i = 0; i < REFTABLE_HASH_SIZE_SHA1; i++) { log.value.update.old_hash[i] = (uint8_t)(git_rand() % 256); log.value.update.new_hash[i] = (uint8_t)(git_rand() % 256); } @@ -191,9 +191,9 @@ static void t_log_write_read(void) log.update_index = i; log.value_type = REFTABLE_LOG_UPDATE; t_reftable_set_hash(log.value.update.old_hash, i, - GIT_SHA1_FORMAT_ID); + REFTABLE_HASH_SHA1); t_reftable_set_hash(log.value.update.new_hash, i + 1, - GIT_SHA1_FORMAT_ID); + REFTABLE_HASH_SHA1); err = reftable_writer_add_log(w, &log); check(!err); @@ -326,7 +326,7 @@ static void t_table_read_write_sequential(void) int err = 0; int j = 0; - write_table(&names, &buf, N, 256, GIT_SHA1_FORMAT_ID); + write_table(&names, &buf, N, 256, REFTABLE_HASH_SHA1); block_source_from_buf(&source, &buf); @@ -361,7 +361,7 @@ static void t_table_write_small_table(void) char **names; struct reftable_buf buf = REFTABLE_BUF_INIT; int N = 1; - write_table(&names, &buf, N, 4096, GIT_SHA1_FORMAT_ID); + write_table(&names, &buf, N, 4096, REFTABLE_HASH_SHA1); check_int(buf.len, <, 200); reftable_buf_release(&buf); free_names(names); @@ -378,7 +378,7 @@ static void t_table_read_api(void) struct reftable_log_record log = { 0 }; struct reftable_iterator it = { 0 }; - write_table(&names, &buf, N, 256, GIT_SHA1_FORMAT_ID); + write_table(&names, &buf, N, 256, REFTABLE_HASH_SHA1); block_source_from_buf(&source, &buf); @@ -400,7 +400,7 @@ static void t_table_read_api(void) reftable_buf_release(&buf); } -static void t_table_read_write_seek(int index, int hash_id) +static void t_table_read_write_seek(int index, enum reftable_hash hash_id) { char **names; struct reftable_buf buf = REFTABLE_BUF_INIT; @@ -467,24 +467,24 @@ static void t_table_read_write_seek(int index, int hash_id) static void t_table_read_write_seek_linear(void) { - t_table_read_write_seek(0, GIT_SHA1_FORMAT_ID); + t_table_read_write_seek(0, REFTABLE_HASH_SHA1); } static void t_table_read_write_seek_linear_sha256(void) { - t_table_read_write_seek(0, GIT_SHA256_FORMAT_ID); + t_table_read_write_seek(0, REFTABLE_HASH_SHA256); } static void t_table_read_write_seek_index(void) { - t_table_read_write_seek(1, GIT_SHA1_FORMAT_ID); + t_table_read_write_seek(1, REFTABLE_HASH_SHA1); } static void t_table_refs_for(int indexed) { char **want_names; int want_names_len = 0; - uint8_t want_hash[GIT_SHA1_RAWSZ]; + uint8_t want_hash[REFTABLE_HASH_SIZE_SHA1]; struct reftable_write_options opts = { .block_size = 256, @@ -500,10 +500,10 @@ static void t_table_refs_for(int indexed) want_names = reftable_calloc(N + 1, sizeof(*want_names)); check(want_names != NULL); - t_reftable_set_hash(want_hash, 4, GIT_SHA1_FORMAT_ID); + t_reftable_set_hash(want_hash, 4, REFTABLE_HASH_SHA1); for (i = 0; i < N; i++) { - uint8_t hash[GIT_SHA1_RAWSZ]; + uint8_t hash[REFTABLE_HASH_SIZE_SHA1]; char fill[51] = { 0 }; char name[100]; struct reftable_ref_record ref = { 0 }; @@ -517,9 +517,9 @@ static void t_table_refs_for(int indexed) ref.value_type = REFTABLE_REF_VAL2; t_reftable_set_hash(ref.value.val2.value, i / 4, - GIT_SHA1_FORMAT_ID); + REFTABLE_HASH_SHA1); t_reftable_set_hash(ref.value.val2.target_value, 3 + i / 4, - GIT_SHA1_FORMAT_ID); + REFTABLE_HASH_SHA1); /* 80 bytes / entry, so 3 entries per block. Yields 17 */ @@ -527,8 +527,8 @@ static void t_table_refs_for(int indexed) n = reftable_writer_add_ref(w, &ref); check_int(n, ==, 0); - if (!memcmp(ref.value.val2.value, want_hash, GIT_SHA1_RAWSZ) || - !memcmp(ref.value.val2.target_value, want_hash, GIT_SHA1_RAWSZ)) + if (!memcmp(ref.value.val2.value, want_hash, REFTABLE_HASH_SIZE_SHA1) || + !memcmp(ref.value.val2.target_value, want_hash, REFTABLE_HASH_SIZE_SHA1)) want_names[want_names_len++] = xstrdup(name); } diff --git a/t/unit-tests/t-reftable-record.c b/t/unit-tests/t-reftable-record.c index eb98bf2da9..42bc64cec8 100644 --- a/t/unit-tests/t-reftable-record.c +++ b/t/unit-tests/t-reftable-record.c @@ -7,6 +7,7 @@ */ #include "test-lib.h" +#include "reftable/basics.h" #include "reftable/constants.h" #include "reftable/record.h" @@ -17,10 +18,10 @@ static void t_copy(struct reftable_record *rec) typ = reftable_record_type(rec); reftable_record_init(©, typ); - reftable_record_copy_from(©, rec, GIT_SHA1_RAWSZ); + reftable_record_copy_from(©, rec, REFTABLE_HASH_SIZE_SHA1); /* do it twice to catch memory leaks */ - reftable_record_copy_from(©, rec, GIT_SHA1_RAWSZ); - check(reftable_record_equal(rec, ©, GIT_SHA1_RAWSZ)); + reftable_record_copy_from(©, rec, REFTABLE_HASH_SIZE_SHA1); + check(reftable_record_equal(rec, ©, REFTABLE_HASH_SIZE_SHA1)); reftable_record_release(©); } @@ -59,7 +60,7 @@ static void t_varint_roundtrip(void) static void set_hash(uint8_t *h, int j) { - for (int i = 0; i < hash_size(GIT_SHA1_FORMAT_ID); i++) + for (int i = 0; i < hash_size(REFTABLE_HASH_SHA1); i++) h[i] = (j >> i) & 0xff; } @@ -84,14 +85,14 @@ static void t_reftable_ref_record_comparison(void) }, }; - check(!reftable_record_equal(&in[0], &in[1], GIT_SHA1_RAWSZ)); + check(!reftable_record_equal(&in[0], &in[1], REFTABLE_HASH_SIZE_SHA1)); check(!reftable_record_cmp(&in[0], &in[1])); - check(!reftable_record_equal(&in[1], &in[2], GIT_SHA1_RAWSZ)); + check(!reftable_record_equal(&in[1], &in[2], REFTABLE_HASH_SIZE_SHA1)); check_int(reftable_record_cmp(&in[1], &in[2]), >, 0); in[1].u.ref.value_type = in[0].u.ref.value_type; - check(reftable_record_equal(&in[0], &in[1], GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&in[0], &in[1], REFTABLE_HASH_SIZE_SHA1)); check(!reftable_record_cmp(&in[0], &in[1])); } @@ -155,15 +156,15 @@ static void t_reftable_ref_record_roundtrip(void) check_int(reftable_record_is_deletion(&in), ==, i == REFTABLE_REF_DELETION); reftable_record_key(&in, &key); - n = reftable_record_encode(&in, dest, GIT_SHA1_RAWSZ); + n = reftable_record_encode(&in, dest, REFTABLE_HASH_SIZE_SHA1); check_int(n, >, 0); /* decode into a non-zero reftable_record to test for leaks. */ - m = reftable_record_decode(&out, key, i, dest, GIT_SHA1_RAWSZ, &scratch); + m = reftable_record_decode(&out, key, i, dest, REFTABLE_HASH_SIZE_SHA1, &scratch); check_int(n, ==, m); check(reftable_ref_record_equal(&in.u.ref, &out.u.ref, - GIT_SHA1_RAWSZ)); + REFTABLE_HASH_SIZE_SHA1)); reftable_record_release(&in); reftable_buf_release(&key); @@ -193,15 +194,15 @@ static void t_reftable_log_record_comparison(void) }, }; - check(!reftable_record_equal(&in[0], &in[1], GIT_SHA1_RAWSZ)); - check(!reftable_record_equal(&in[1], &in[2], GIT_SHA1_RAWSZ)); + check(!reftable_record_equal(&in[0], &in[1], REFTABLE_HASH_SIZE_SHA1)); + check(!reftable_record_equal(&in[1], &in[2], REFTABLE_HASH_SIZE_SHA1)); check_int(reftable_record_cmp(&in[1], &in[2]), >, 0); /* comparison should be reversed for equal keys, because * comparison is now performed on the basis of update indices */ check_int(reftable_record_cmp(&in[0], &in[1]), <, 0); in[1].u.log.update_index = in[0].u.log.update_index; - check(reftable_record_equal(&in[0], &in[1], GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&in[0], &in[1], REFTABLE_HASH_SIZE_SHA1)); check(!reftable_record_cmp(&in[0], &in[1])); } @@ -303,15 +304,15 @@ static void t_reftable_log_record_roundtrip(void) reftable_record_key(&rec, &key); - n = reftable_record_encode(&rec, dest, GIT_SHA1_RAWSZ); + n = reftable_record_encode(&rec, dest, REFTABLE_HASH_SIZE_SHA1); check_int(n, >=, 0); valtype = reftable_record_val_type(&rec); m = reftable_record_decode(&out, key, valtype, dest, - GIT_SHA1_RAWSZ, &scratch); + REFTABLE_HASH_SIZE_SHA1, &scratch); check_int(n, ==, m); check(reftable_log_record_equal(&in[i], &out.u.log, - GIT_SHA1_RAWSZ)); + REFTABLE_HASH_SIZE_SHA1)); reftable_log_record_release(&in[i]); reftable_buf_release(&key); reftable_record_release(&out); @@ -380,20 +381,20 @@ static void t_reftable_obj_record_comparison(void) }, }; - check(!reftable_record_equal(&in[0], &in[1], GIT_SHA1_RAWSZ)); + check(!reftable_record_equal(&in[0], &in[1], REFTABLE_HASH_SIZE_SHA1)); check(!reftable_record_cmp(&in[0], &in[1])); - check(!reftable_record_equal(&in[1], &in[2], GIT_SHA1_RAWSZ)); + check(!reftable_record_equal(&in[1], &in[2], REFTABLE_HASH_SIZE_SHA1)); check_int(reftable_record_cmp(&in[1], &in[2]), >, 0); in[1].u.obj.offset_len = in[0].u.obj.offset_len; - check(reftable_record_equal(&in[0], &in[1], GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&in[0], &in[1], REFTABLE_HASH_SIZE_SHA1)); check(!reftable_record_cmp(&in[0], &in[1])); } static void t_reftable_obj_record_roundtrip(void) { - uint8_t testHash1[GIT_SHA1_RAWSZ] = { 1, 2, 3, 4, 0 }; + uint8_t testHash1[REFTABLE_HASH_SIZE_SHA1] = { 1, 2, 3, 4, 0 }; uint64_t till9[] = { 1, 2, 3, 4, 500, 600, 700, 800, 9000 }; struct reftable_obj_record recs[3] = { { @@ -435,14 +436,14 @@ static void t_reftable_obj_record_roundtrip(void) check(!reftable_record_is_deletion(&in)); t_copy(&in); reftable_record_key(&in, &key); - n = reftable_record_encode(&in, dest, GIT_SHA1_RAWSZ); + n = reftable_record_encode(&in, dest, REFTABLE_HASH_SIZE_SHA1); check_int(n, >, 0); extra = reftable_record_val_type(&in); m = reftable_record_decode(&out, key, extra, dest, - GIT_SHA1_RAWSZ, &scratch); + REFTABLE_HASH_SIZE_SHA1, &scratch); check_int(n, ==, m); - check(reftable_record_equal(&in, &out, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&in, &out, REFTABLE_HASH_SIZE_SHA1)); reftable_buf_release(&key); reftable_record_release(&out); } @@ -473,14 +474,14 @@ static void t_reftable_index_record_comparison(void) check(!reftable_buf_addstr(&in[1].u.idx.last_key, "refs/heads/master")); check(!reftable_buf_addstr(&in[2].u.idx.last_key, "refs/heads/branch")); - check(!reftable_record_equal(&in[0], &in[1], GIT_SHA1_RAWSZ)); + check(!reftable_record_equal(&in[0], &in[1], REFTABLE_HASH_SIZE_SHA1)); check(!reftable_record_cmp(&in[0], &in[1])); - check(!reftable_record_equal(&in[1], &in[2], GIT_SHA1_RAWSZ)); + check(!reftable_record_equal(&in[1], &in[2], REFTABLE_HASH_SIZE_SHA1)); check_int(reftable_record_cmp(&in[1], &in[2]), >, 0); in[1].u.idx.offset = in[0].u.idx.offset; - check(reftable_record_equal(&in[0], &in[1], GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&in[0], &in[1], REFTABLE_HASH_SIZE_SHA1)); check(!reftable_record_cmp(&in[0], &in[1])); for (size_t i = 0; i < ARRAY_SIZE(in); i++) @@ -516,15 +517,15 @@ static void t_reftable_index_record_roundtrip(void) check(!reftable_record_is_deletion(&in)); check(!reftable_buf_cmp(&key, &in.u.idx.last_key)); - n = reftable_record_encode(&in, dest, GIT_SHA1_RAWSZ); + n = reftable_record_encode(&in, dest, REFTABLE_HASH_SIZE_SHA1); check_int(n, >, 0); extra = reftable_record_val_type(&in); - m = reftable_record_decode(&out, key, extra, dest, GIT_SHA1_RAWSZ, + m = reftable_record_decode(&out, key, extra, dest, REFTABLE_HASH_SIZE_SHA1, &scratch); check_int(m, ==, n); - check(reftable_record_equal(&in, &out, GIT_SHA1_RAWSZ)); + check(reftable_record_equal(&in, &out, REFTABLE_HASH_SIZE_SHA1)); reftable_record_release(&out); reftable_buf_release(&key); diff --git a/t/unit-tests/t-reftable-stack.c b/t/unit-tests/t-reftable-stack.c index 1b4363a58f..13fd8d8f94 100644 --- a/t/unit-tests/t-reftable-stack.c +++ b/t/unit-tests/t-reftable-stack.c @@ -121,7 +121,7 @@ static void write_n_ref_tables(struct reftable_stack *st, snprintf(buf, sizeof(buf), "refs/heads/branch-%04"PRIuMAX, (uintmax_t)i); ref.refname = buf; - t_reftable_set_hash(ref.value.val1, i, GIT_SHA1_FORMAT_ID); + t_reftable_set_hash(ref.value.val1, i, REFTABLE_HASH_SHA1); err = reftable_stack_add(st, &write_test_ref, &ref); check(!err); @@ -169,7 +169,7 @@ static void t_reftable_stack_add_one(void) err = reftable_stack_read_ref(st, ref.refname, &dest); check(!err); - check(reftable_ref_record_equal(&ref, &dest, GIT_SHA1_RAWSZ)); + check(reftable_ref_record_equal(&ref, &dest, REFTABLE_HASH_SIZE_SHA1)); check_int(st->readers_len, >, 0); #ifndef GIT_WINDOWS_NATIVE @@ -280,7 +280,7 @@ static void t_reftable_stack_transaction_api(void) err = reftable_stack_read_ref(st, ref.refname, &dest); check(!err); check_int(REFTABLE_REF_SYMREF, ==, dest.value_type); - check(reftable_ref_record_equal(&ref, &dest, GIT_SHA1_RAWSZ)); + check(reftable_ref_record_equal(&ref, &dest, REFTABLE_HASH_SIZE_SHA1)); reftable_ref_record_release(&dest); reftable_stack_destroy(st); @@ -340,7 +340,7 @@ static void t_reftable_stack_transaction_with_reload(void) for (size_t i = 0; i < ARRAY_SIZE(refs); i++) { err = reftable_stack_read_ref(st2, refs[i].refname, &ref); check(!err); - check(reftable_ref_record_equal(&refs[i], &ref, GIT_SHA1_RAWSZ)); + check(reftable_ref_record_equal(&refs[i], &ref, REFTABLE_HASH_SIZE_SHA1)); } reftable_ref_record_release(&ref); @@ -530,13 +530,13 @@ static void t_reftable_stack_add(void) refs[i].refname = xstrdup(buf); refs[i].update_index = i + 1; refs[i].value_type = REFTABLE_REF_VAL1; - t_reftable_set_hash(refs[i].value.val1, i, GIT_SHA1_FORMAT_ID); + t_reftable_set_hash(refs[i].value.val1, i, REFTABLE_HASH_SHA1); logs[i].refname = xstrdup(buf); logs[i].update_index = N + i + 1; logs[i].value_type = REFTABLE_LOG_UPDATE; logs[i].value.update.email = xstrdup("identity@invalid"); - t_reftable_set_hash(logs[i].value.update.new_hash, i, GIT_SHA1_FORMAT_ID); + t_reftable_set_hash(logs[i].value.update.new_hash, i, REFTABLE_HASH_SHA1); } for (i = 0; i < N; i++) { @@ -562,7 +562,7 @@ static void t_reftable_stack_add(void) int err = reftable_stack_read_ref(st, refs[i].refname, &dest); check(!err); check(reftable_ref_record_equal(&dest, refs + i, - GIT_SHA1_RAWSZ)); + REFTABLE_HASH_SIZE_SHA1)); reftable_ref_record_release(&dest); } @@ -571,7 +571,7 @@ static void t_reftable_stack_add(void) int err = reftable_stack_read_log(st, refs[i].refname, &dest); check(!err); check(reftable_log_record_equal(&dest, logs + i, - GIT_SHA1_RAWSZ)); + REFTABLE_HASH_SIZE_SHA1)); reftable_log_record_release(&dest); } @@ -622,14 +622,14 @@ static void t_reftable_stack_iterator(void) refs[i].refname = xstrfmt("branch%02"PRIuMAX, (uintmax_t)i); refs[i].update_index = i + 1; refs[i].value_type = REFTABLE_REF_VAL1; - t_reftable_set_hash(refs[i].value.val1, i, GIT_SHA1_FORMAT_ID); + t_reftable_set_hash(refs[i].value.val1, i, REFTABLE_HASH_SHA1); logs[i].refname = xstrfmt("branch%02"PRIuMAX, (uintmax_t)i); logs[i].update_index = i + 1; logs[i].value_type = REFTABLE_LOG_UPDATE; logs[i].value.update.email = xstrdup("johndoe@invalid"); logs[i].value.update.message = xstrdup("commit\n"); - t_reftable_set_hash(logs[i].value.update.new_hash, i, GIT_SHA1_FORMAT_ID); + t_reftable_set_hash(logs[i].value.update.new_hash, i, REFTABLE_HASH_SHA1); } for (i = 0; i < N; i++) { @@ -656,7 +656,7 @@ static void t_reftable_stack_iterator(void) if (err > 0) break; check(!err); - check(reftable_ref_record_equal(&ref, &refs[i], GIT_SHA1_RAWSZ)); + check(reftable_ref_record_equal(&ref, &refs[i], REFTABLE_HASH_SIZE_SHA1)); reftable_ref_record_release(&ref); } check_int(i, ==, N); @@ -674,7 +674,7 @@ static void t_reftable_stack_iterator(void) if (err > 0) break; check(!err); - check(reftable_log_record_equal(&log, &logs[i], GIT_SHA1_RAWSZ)); + check(reftable_log_record_equal(&log, &logs[i], REFTABLE_HASH_SIZE_SHA1)); reftable_log_record_release(&log); } check_int(i, ==, N); @@ -767,7 +767,7 @@ static void t_reftable_stack_tombstone(void) if (i % 2 == 0) { refs[i].value_type = REFTABLE_REF_VAL1; t_reftable_set_hash(refs[i].value.val1, i, - GIT_SHA1_FORMAT_ID); + REFTABLE_HASH_SHA1); } logs[i].refname = xstrdup(buf); @@ -776,7 +776,7 @@ static void t_reftable_stack_tombstone(void) if (i % 2 == 0) { logs[i].value_type = REFTABLE_LOG_UPDATE; t_reftable_set_hash(logs[i].value.update.new_hash, i, - GIT_SHA1_FORMAT_ID); + REFTABLE_HASH_SHA1); logs[i].value.update.email = xstrdup("identity@invalid"); } @@ -836,7 +836,7 @@ static void t_reftable_stack_hash_id(void) .value.symref = (char *) "target", .update_index = 1, }; - struct reftable_write_options opts32 = { .hash_id = GIT_SHA256_FORMAT_ID }; + struct reftable_write_options opts32 = { .hash_id = REFTABLE_HASH_SHA256 }; struct reftable_stack *st32 = NULL; struct reftable_write_options opts_default = { 0 }; struct reftable_stack *st_default = NULL; @@ -859,7 +859,7 @@ static void t_reftable_stack_hash_id(void) err = reftable_stack_read_ref(st_default, "master", &dest); check(!err); - check(reftable_ref_record_equal(&ref, &dest, GIT_SHA1_RAWSZ)); + check(reftable_ref_record_equal(&ref, &dest, REFTABLE_HASH_SIZE_SHA1)); reftable_ref_record_release(&dest); reftable_stack_destroy(st); reftable_stack_destroy(st_default); @@ -909,7 +909,7 @@ static void t_reflog_expire(void) logs[i].value.update.time = i; logs[i].value.update.email = xstrdup("identity@invalid"); t_reftable_set_hash(logs[i].value.update.new_hash, i, - GIT_SHA1_FORMAT_ID); + REFTABLE_HASH_SHA1); } for (i = 1; i <= N; i++) { From 86b770b0bbf1aba3c8e43401936258c58648703a Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 18 Nov 2024 16:34:00 +0100 Subject: [PATCH 4/7] reftable/stack: stop using `fsync_component()` directly We're executing `fsync_component()` directly in the reftable library so that we can fsync data to disk depending on "core.fsync". But as we're in the process of converting the reftable library to become standalone we cannot use that function in the library anymore. Refactor the code such that users of the library can inject a custom fsync function via the write options. This allows us to get rid of the dependency on "write-or-die.h". Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- refs/reftable-backend.c | 7 ++++++ reftable/reftable-writer.h | 6 +++++ reftable/stack.c | 51 ++++++++++++++++++++++++-------------- 3 files changed, 46 insertions(+), 18 deletions(-) diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index 7d86d92097..2e774176ed 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -24,6 +24,7 @@ #include "../setup.h" #include "../strmap.h" #include "../trace2.h" +#include "../write-or-die.h" #include "parse.h" #include "refs-internal.h" @@ -273,6 +274,11 @@ static int reftable_be_config(const char *var, const char *value, return 0; } +static int reftable_be_fsync(int fd) +{ + return fsync_component(FSYNC_COMPONENT_REFERENCE, fd); +} + static struct ref_store *reftable_be_init(struct repository *repo, const char *gitdir, unsigned int store_flags) @@ -304,6 +310,7 @@ static struct ref_store *reftable_be_init(struct repository *repo, refs->write_options.disable_auto_compact = !git_env_bool("GIT_TEST_REFTABLE_AUTOCOMPACTION", 1); refs->write_options.lock_timeout_ms = 100; + refs->write_options.fsync = reftable_be_fsync; git_config(reftable_be_config, &refs->write_options); diff --git a/reftable/reftable-writer.h b/reftable/reftable-writer.h index 211860d08a..c85ef5a5bd 100644 --- a/reftable/reftable-writer.h +++ b/reftable/reftable-writer.h @@ -62,6 +62,12 @@ struct reftable_write_options { * negative value will cause us to block indefinitely. */ long lock_timeout_ms; + + /* + * Optional callback used to fsync files to disk. Falls back to using + * fsync(3P) when unset. + */ + int (*fsync)(int fd); }; /* reftable_block_stats holds statistics for a single block type */ diff --git a/reftable/stack.c b/reftable/stack.c index 9ae716ff37..c67bdd952c 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -8,7 +8,6 @@ https://developers.google.com/open-source/licenses/bsd #include "stack.h" -#include "../write-or-die.h" #include "system.h" #include "constants.h" #include "merged.h" @@ -43,17 +42,28 @@ static int stack_filename(struct reftable_buf *dest, struct reftable_stack *st, return 0; } -static ssize_t reftable_fd_write(void *arg, const void *data, size_t sz) +static int stack_fsync(const struct reftable_write_options *opts, int fd) { - int *fdp = (int *)arg; - return write_in_full(*fdp, data, sz); + if (opts->fsync) + return opts->fsync(fd); + return fsync(fd); } -static int reftable_fd_flush(void *arg) -{ - int *fdp = (int *)arg; +struct fd_writer { + const struct reftable_write_options *opts; + int fd; +}; - return fsync_component(FSYNC_COMPONENT_REFERENCE, *fdp); +static ssize_t fd_writer_write(void *arg, const void *data, size_t sz) +{ + struct fd_writer *writer = arg; + return write_in_full(writer->fd, data, sz); +} + +static int fd_writer_flush(void *arg) +{ + struct fd_writer *writer = arg; + return stack_fsync(writer->opts, writer->fd); } int reftable_new_stack(struct reftable_stack **dest, const char *dir, @@ -765,7 +775,7 @@ int reftable_addition_commit(struct reftable_addition *add) goto done; } - err = fsync_component(FSYNC_COMPONENT_REFERENCE, lock_file_fd); + err = stack_fsync(&add->stack->opts, lock_file_fd); if (err < 0) { err = REFTABLE_IO_ERROR; goto done; @@ -858,8 +868,10 @@ int reftable_addition_add(struct reftable_addition *add, struct reftable_buf next_name = REFTABLE_BUF_INIT; struct reftable_writer *wr = NULL; struct tempfile *tab_file = NULL; + struct fd_writer writer = { + .opts = &add->stack->opts, + }; int err = 0; - int tab_fd; reftable_buf_reset(&next_name); @@ -887,10 +899,10 @@ int reftable_addition_add(struct reftable_addition *add, goto done; } } - tab_fd = get_tempfile_fd(tab_file); - err = reftable_writer_new(&wr, reftable_fd_write, reftable_fd_flush, - &tab_fd, &add->stack->opts); + writer.fd = get_tempfile_fd(tab_file); + err = reftable_writer_new(&wr, fd_writer_write, fd_writer_flush, + &writer, &add->stack->opts); if (err < 0) goto done; @@ -973,8 +985,11 @@ static int stack_compact_locked(struct reftable_stack *st, struct reftable_buf next_name = REFTABLE_BUF_INIT; struct reftable_buf tab_file_path = REFTABLE_BUF_INIT; struct reftable_writer *wr = NULL; + struct fd_writer writer= { + .opts = &st->opts, + }; struct tempfile *tab_file; - int tab_fd, err = 0; + int err = 0; err = format_name(&next_name, reftable_reader_min_update_index(st->readers[first]), reftable_reader_max_update_index(st->readers[last])); @@ -994,7 +1009,6 @@ static int stack_compact_locked(struct reftable_stack *st, err = REFTABLE_IO_ERROR; goto done; } - tab_fd = get_tempfile_fd(tab_file); if (st->opts.default_permissions && chmod(get_tempfile_path(tab_file), st->opts.default_permissions) < 0) { @@ -1002,8 +1016,9 @@ static int stack_compact_locked(struct reftable_stack *st, goto done; } - err = reftable_writer_new(&wr, reftable_fd_write, reftable_fd_flush, - &tab_fd, &st->opts); + writer.fd = get_tempfile_fd(tab_file); + err = reftable_writer_new(&wr, fd_writer_write, fd_writer_flush, + &writer, &st->opts); if (err < 0) goto done; @@ -1460,7 +1475,7 @@ static int stack_compact_range(struct reftable_stack *st, goto done; } - err = fsync_component(FSYNC_COMPONENT_REFERENCE, get_lock_file_fd(&tables_list_lock)); + err = stack_fsync(&st->opts, get_lock_file_fd(&tables_list_lock)); if (err < 0) { err = REFTABLE_IO_ERROR; unlink(new_table_path.buf); From 01e49941d6560dfebfac39a2ffe49d3d24b35069 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 18 Nov 2024 16:34:03 +0100 Subject: [PATCH 5/7] reftable/system: provide thin wrapper for tempfile subsystem We use the tempfile subsystem to write temporary tables, but given that we're in the process of converting the reftable library to become standalone we cannot use this subsystem directly anymore. While we could in theory convert the code to use mkstemp(3p) instead, we'd lose access to our infrastructure that automatically prunes tempfiles via atexit(3p) or signal handlers. Provide a thin wrapper for the tempfile subsystem instead. Like this, the compatibility shim is fully self-contained in "reftable/system.c". Downstream users of the reftable library would have to implement their own tempfile shims by replacing "system.c" with a custom version. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- Makefile | 1 + reftable/stack.c | 57 +++++++++++++++++++---------------------------- reftable/system.c | 49 ++++++++++++++++++++++++++++++++++++++++ reftable/system.h | 42 +++++++++++++++++++++++++++++++++- 4 files changed, 114 insertions(+), 35 deletions(-) create mode 100644 reftable/system.c diff --git a/Makefile b/Makefile index feeed6f932..50a79ad83f 100644 --- a/Makefile +++ b/Makefile @@ -2722,6 +2722,7 @@ REFTABLE_OBJS += reftable/pq.o REFTABLE_OBJS += reftable/reader.o REFTABLE_OBJS += reftable/record.o REFTABLE_OBJS += reftable/stack.o +REFTABLE_OBJS += reftable/system.o REFTABLE_OBJS += reftable/tree.o REFTABLE_OBJS += reftable/writer.o diff --git a/reftable/stack.c b/reftable/stack.c index c67bdd952c..2ac6a37151 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -16,7 +16,6 @@ https://developers.google.com/open-source/licenses/bsd #include "reftable-record.h" #include "reftable-merged.h" #include "writer.h" -#include "tempfile.h" static int stack_try_add(struct reftable_stack *st, int (*write_table)(struct reftable_writer *wr, @@ -867,7 +866,7 @@ int reftable_addition_add(struct reftable_addition *add, struct reftable_buf tab_file_name = REFTABLE_BUF_INIT; struct reftable_buf next_name = REFTABLE_BUF_INIT; struct reftable_writer *wr = NULL; - struct tempfile *tab_file = NULL; + struct reftable_tmpfile tab_file = REFTABLE_TMPFILE_INIT; struct fd_writer writer = { .opts = &add->stack->opts, }; @@ -887,20 +886,18 @@ int reftable_addition_add(struct reftable_addition *add, if (err < 0) goto done; - tab_file = mks_tempfile(temp_tab_file_name.buf); - if (!tab_file) { - err = REFTABLE_IO_ERROR; + err = tmpfile_from_pattern(&tab_file, temp_tab_file_name.buf); + if (err < 0) goto done; - } if (add->stack->opts.default_permissions) { - if (chmod(get_tempfile_path(tab_file), + if (chmod(tab_file.path, add->stack->opts.default_permissions)) { err = REFTABLE_IO_ERROR; goto done; } } - writer.fd = get_tempfile_fd(tab_file); + writer.fd = tab_file.fd; err = reftable_writer_new(&wr, fd_writer_write, fd_writer_flush, &writer, &add->stack->opts); if (err < 0) @@ -918,11 +915,9 @@ int reftable_addition_add(struct reftable_addition *add, if (err < 0) goto done; - err = close_tempfile_gently(tab_file); - if (err < 0) { - err = REFTABLE_IO_ERROR; + err = tmpfile_close(&tab_file); + if (err < 0) goto done; - } if (wr->min_update_index < add->next_update_index) { err = REFTABLE_API_ERROR; @@ -945,11 +940,9 @@ int reftable_addition_add(struct reftable_addition *add, On windows, this relies on rand() picking a unique destination name. Maybe we should do retry loop as well? */ - err = rename_tempfile(&tab_file, tab_file_name.buf); - if (err < 0) { - err = REFTABLE_IO_ERROR; + err = tmpfile_rename(&tab_file, tab_file_name.buf); + if (err < 0) goto done; - } REFTABLE_ALLOC_GROW(add->new_tables, add->new_tables_len + 1, add->new_tables_cap); @@ -960,7 +953,7 @@ int reftable_addition_add(struct reftable_addition *add, add->new_tables[add->new_tables_len++] = reftable_buf_detach(&next_name); done: - delete_tempfile(&tab_file); + tmpfile_delete(&tab_file); reftable_buf_release(&temp_tab_file_name); reftable_buf_release(&tab_file_name); reftable_buf_release(&next_name); @@ -980,7 +973,7 @@ uint64_t reftable_stack_next_update_index(struct reftable_stack *st) static int stack_compact_locked(struct reftable_stack *st, size_t first, size_t last, struct reftable_log_expiry_config *config, - struct tempfile **tab_file_out) + struct reftable_tmpfile *tab_file_out) { struct reftable_buf next_name = REFTABLE_BUF_INIT; struct reftable_buf tab_file_path = REFTABLE_BUF_INIT; @@ -988,7 +981,7 @@ static int stack_compact_locked(struct reftable_stack *st, struct fd_writer writer= { .opts = &st->opts, }; - struct tempfile *tab_file; + struct reftable_tmpfile tab_file = REFTABLE_TMPFILE_INIT; int err = 0; err = format_name(&next_name, reftable_reader_min_update_index(st->readers[first]), @@ -1004,19 +997,17 @@ static int stack_compact_locked(struct reftable_stack *st, if (err < 0) goto done; - tab_file = mks_tempfile(tab_file_path.buf); - if (!tab_file) { - err = REFTABLE_IO_ERROR; + err = tmpfile_from_pattern(&tab_file, tab_file_path.buf); + if (err < 0) goto done; - } if (st->opts.default_permissions && - chmod(get_tempfile_path(tab_file), st->opts.default_permissions) < 0) { + chmod(tab_file.path, st->opts.default_permissions) < 0) { err = REFTABLE_IO_ERROR; goto done; } - writer.fd = get_tempfile_fd(tab_file); + writer.fd = tab_file.fd; err = reftable_writer_new(&wr, fd_writer_write, fd_writer_flush, &writer, &st->opts); if (err < 0) @@ -1030,15 +1021,15 @@ static int stack_compact_locked(struct reftable_stack *st, if (err < 0) goto done; - err = close_tempfile_gently(tab_file); + err = tmpfile_close(&tab_file); if (err < 0) goto done; *tab_file_out = tab_file; - tab_file = NULL; + tab_file = REFTABLE_TMPFILE_INIT; done: - delete_tempfile(&tab_file); + tmpfile_delete(&tab_file); reftable_writer_free(wr); reftable_buf_release(&next_name); reftable_buf_release(&tab_file_path); @@ -1171,7 +1162,7 @@ static int stack_compact_range(struct reftable_stack *st, struct reftable_buf table_name = REFTABLE_BUF_INIT; struct lock_file tables_list_lock = LOCK_INIT; struct lock_file *table_locks = NULL; - struct tempfile *new_table = NULL; + struct reftable_tmpfile new_table = REFTABLE_TMPFILE_INIT; int is_empty_table = 0, err = 0; size_t first_to_replace, last_to_replace; size_t i, nlocks = 0; @@ -1439,11 +1430,9 @@ static int stack_compact_range(struct reftable_stack *st, if (err < 0) goto done; - err = rename_tempfile(&new_table, new_table_path.buf); - if (err < 0) { - err = REFTABLE_IO_ERROR; + err = tmpfile_rename(&new_table, new_table_path.buf); + if (err < 0) goto done; - } } /* @@ -1515,7 +1504,7 @@ done: rollback_lock_file(&table_locks[i]); reftable_free(table_locks); - delete_tempfile(&new_table); + tmpfile_delete(&new_table); reftable_buf_release(&new_table_name); reftable_buf_release(&new_table_path); reftable_buf_release(&tables_list_buf); diff --git a/reftable/system.c b/reftable/system.c new file mode 100644 index 0000000000..01f96f03d8 --- /dev/null +++ b/reftable/system.c @@ -0,0 +1,49 @@ +#include "system.h" +#include "basics.h" +#include "reftable-error.h" +#include "../tempfile.h" + +int tmpfile_from_pattern(struct reftable_tmpfile *out, const char *pattern) +{ + struct tempfile *tempfile; + + tempfile = mks_tempfile(pattern); + if (!tempfile) + return REFTABLE_IO_ERROR; + + out->path = tempfile->filename.buf; + out->fd = tempfile->fd; + out->priv = tempfile; + + return 0; +} + +int tmpfile_close(struct reftable_tmpfile *t) +{ + struct tempfile *tempfile = t->priv; + int ret = close_tempfile_gently(tempfile); + t->fd = -1; + if (ret < 0) + return REFTABLE_IO_ERROR; + return 0; +} + +int tmpfile_delete(struct reftable_tmpfile *t) +{ + struct tempfile *tempfile = t->priv; + int ret = delete_tempfile(&tempfile); + *t = REFTABLE_TMPFILE_INIT; + if (ret < 0) + return REFTABLE_IO_ERROR; + return 0; +} + +int tmpfile_rename(struct reftable_tmpfile *t, const char *path) +{ + struct tempfile *tempfile = t->priv; + int ret = rename_tempfile(&tempfile, path); + *t = REFTABLE_TMPFILE_INIT; + if (ret < 0) + return REFTABLE_IO_ERROR; + return 0; +} diff --git a/reftable/system.h b/reftable/system.h index 38d3534620..858189fd55 100644 --- a/reftable/system.h +++ b/reftable/system.h @@ -13,6 +13,46 @@ https://developers.google.com/open-source/licenses/bsd #include "git-compat-util.h" #include "lockfile.h" -#include "tempfile.h" + +/* + * An implementation-specific temporary file. By making this specific to the + * implementation it becomes possible to tie temporary files into any kind of + * signal or atexit handlers for cleanup on abnormal situations. + */ +struct reftable_tmpfile { + const char *path; + int fd; + void *priv; +}; +#define REFTABLE_TMPFILE_INIT ((struct reftable_tmpfile) { .fd = -1, }) + +/* + * Create a temporary file from a pattern similar to how mkstemp(3p) would. + * The `pattern` shall not be modified. On success, the structure at `out` has + * been initialized such that it is ready for use. Returns 0 on success, a + * reftable error code on error. + */ +int tmpfile_from_pattern(struct reftable_tmpfile *out, const char *pattern); + +/* + * Close the temporary file's file descriptor without removing the file itself. + * This is a no-op in case the file has already been closed beforehand. Returns + * 0 on success, a reftable error code on error. + */ +int tmpfile_close(struct reftable_tmpfile *t); + +/* + * Close the temporary file and delete it. This is a no-op in case the file has + * already been deleted or renamed beforehand. Returns 0 on success, a reftable + * error code on error. + */ +int tmpfile_delete(struct reftable_tmpfile *t); + +/* + * Rename the temporary file to the provided path. The temporary file must be + * active. Return 0 on success, a reftable error code on error. Deactivates the + * temporary file. + */ +int tmpfile_rename(struct reftable_tmpfile *t, const char *path); #endif From 6361226b79d24eb93a14e0b7d25f584269f9d5e6 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 18 Nov 2024 16:34:05 +0100 Subject: [PATCH 6/7] reftable/stack: drop only use of `get_locked_file_path()` We've got a single callsite where we call `get_locked_file_path()`. As we're about to convert our usage of the lockfile subsystem to instead be used via a compatibility shim we'd have to implement more logic for this single callsite. While that would be okay if Git was the only supposed user of the reftable library, it's a bit more awkward when considering that we have to reimplement this functionality for every user of the library eventually. Refactor the code such that we don't call `get_locked_file_path()` anymore. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/stack.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/reftable/stack.c b/reftable/stack.c index 2ac6a37151..223d7c622d 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -1493,9 +1493,15 @@ static int stack_compact_range(struct reftable_stack *st, */ for (i = 0; i < nlocks; i++) { struct lock_file *table_lock = &table_locks[i]; - char *table_path = get_locked_file_path(table_lock); - unlink(table_path); - reftable_free(table_path); + const char *lock_path = get_lock_file_path(table_lock); + + reftable_buf_reset(&table_name); + err = reftable_buf_add(&table_name, lock_path, + strlen(lock_path) - strlen(".lock")); + if (err) + continue; + + unlink(table_name.buf); } done: From 988e7f5e952bbb7b6ae885f4da744f536f22693f Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 18 Nov 2024 16:34:08 +0100 Subject: [PATCH 7/7] reftable/system: provide thin wrapper for lockfile subsystem We use the lockfile subsystem to write lockfiles for "tables.list". As with the tempfile subsystem, the lockfile subsystem also hooks into our infrastructure to prune stale locks via atexit(3p) or signal handlers. Furthermore, the lockfile subsystem also handles locking timeouts, which do add quite a bit of logic. Having to reimplement that in the context of Git wouldn't make a whole lot of sense, and it is quite likely that downstream users of the reftable library may have a better idea for how exactly to implement timeouts. So again, provide a thin wrapper for the lockfile subsystem instead such that the compatibility shim is fully self-contained. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- reftable/stack.c | 63 ++++++++++------------- reftable/system.c | 77 +++++++++++++++++++++++++++++ reftable/system.h | 45 ++++++++++++++++- t/unit-tests/lib-reftable.c | 1 + t/unit-tests/t-reftable-block.c | 1 + t/unit-tests/t-reftable-pq.c | 1 + t/unit-tests/t-reftable-readwrite.c | 1 + t/unit-tests/t-reftable-stack.c | 2 + 8 files changed, 154 insertions(+), 37 deletions(-) diff --git a/reftable/stack.c b/reftable/stack.c index 223d7c622d..10d45e89d0 100644 --- a/reftable/stack.c +++ b/reftable/stack.c @@ -657,7 +657,7 @@ static int format_name(struct reftable_buf *dest, uint64_t min, uint64_t max) } struct reftable_addition { - struct lock_file tables_list_lock; + struct reftable_flock tables_list_lock; struct reftable_stack *stack; char **new_tables; @@ -676,10 +676,8 @@ static int reftable_stack_init_addition(struct reftable_addition *add, add->stack = st; - err = hold_lock_file_for_update_timeout(&add->tables_list_lock, - st->list_file, - LOCK_NO_DEREF, - st->opts.lock_timeout_ms); + err = flock_acquire(&add->tables_list_lock, st->list_file, + st->opts.lock_timeout_ms); if (err < 0) { if (errno == EEXIST) { err = REFTABLE_LOCK_ERROR; @@ -689,7 +687,7 @@ static int reftable_stack_init_addition(struct reftable_addition *add, goto done; } if (st->opts.default_permissions) { - if (chmod(get_lock_file_path(&add->tables_list_lock), + if (chmod(add->tables_list_lock.path, st->opts.default_permissions) < 0) { err = REFTABLE_IO_ERROR; goto done; @@ -733,7 +731,7 @@ static void reftable_addition_close(struct reftable_addition *add) add->new_tables_len = 0; add->new_tables_cap = 0; - rollback_lock_file(&add->tables_list_lock); + flock_release(&add->tables_list_lock); reftable_buf_release(&nm); } @@ -749,7 +747,6 @@ void reftable_addition_destroy(struct reftable_addition *add) int reftable_addition_commit(struct reftable_addition *add) { struct reftable_buf table_list = REFTABLE_BUF_INIT; - int lock_file_fd = get_lock_file_fd(&add->tables_list_lock); int err = 0; size_t i; @@ -767,20 +764,20 @@ int reftable_addition_commit(struct reftable_addition *add) goto done; } - err = write_in_full(lock_file_fd, table_list.buf, table_list.len); + err = write_in_full(add->tables_list_lock.fd, table_list.buf, table_list.len); reftable_buf_release(&table_list); if (err < 0) { err = REFTABLE_IO_ERROR; goto done; } - err = stack_fsync(&add->stack->opts, lock_file_fd); + err = stack_fsync(&add->stack->opts, add->tables_list_lock.fd); if (err < 0) { err = REFTABLE_IO_ERROR; goto done; } - err = commit_lock_file(&add->tables_list_lock); + err = flock_commit(&add->tables_list_lock); if (err < 0) { err = REFTABLE_IO_ERROR; goto done; @@ -1160,8 +1157,8 @@ static int stack_compact_range(struct reftable_stack *st, struct reftable_buf new_table_name = REFTABLE_BUF_INIT; struct reftable_buf new_table_path = REFTABLE_BUF_INIT; struct reftable_buf table_name = REFTABLE_BUF_INIT; - struct lock_file tables_list_lock = LOCK_INIT; - struct lock_file *table_locks = NULL; + struct reftable_flock tables_list_lock = REFTABLE_FLOCK_INIT; + struct reftable_flock *table_locks = NULL; struct reftable_tmpfile new_table = REFTABLE_TMPFILE_INIT; int is_empty_table = 0, err = 0; size_t first_to_replace, last_to_replace; @@ -1179,10 +1176,7 @@ static int stack_compact_range(struct reftable_stack *st, * Hold the lock so that we can read "tables.list" and lock all tables * which are part of the user-specified range. */ - err = hold_lock_file_for_update_timeout(&tables_list_lock, - st->list_file, - LOCK_NO_DEREF, - st->opts.lock_timeout_ms); + err = flock_acquire(&tables_list_lock, st->list_file, st->opts.lock_timeout_ms); if (err < 0) { if (errno == EEXIST) err = REFTABLE_LOCK_ERROR; @@ -1205,19 +1199,20 @@ static int stack_compact_range(struct reftable_stack *st, * older process is still busy compacting tables which are preexisting * from the point of view of the newer process. */ - REFTABLE_CALLOC_ARRAY(table_locks, last - first + 1); + REFTABLE_ALLOC_ARRAY(table_locks, last - first + 1); if (!table_locks) { err = REFTABLE_OUT_OF_MEMORY_ERROR; goto done; } + for (i = 0; i < last - first + 1; i++) + table_locks[i] = REFTABLE_FLOCK_INIT; for (i = last + 1; i > first; i--) { err = stack_filename(&table_name, st, reader_name(st->readers[i - 1])); if (err < 0) goto done; - err = hold_lock_file_for_update(&table_locks[nlocks], - table_name.buf, LOCK_NO_DEREF); + err = flock_acquire(&table_locks[nlocks], table_name.buf, 0); if (err < 0) { /* * When the table is locked already we may do a @@ -1253,7 +1248,7 @@ static int stack_compact_range(struct reftable_stack *st, * run into file descriptor exhaustion when we compress a lot * of tables. */ - err = close_lock_file_gently(&table_locks[nlocks++]); + err = flock_close(&table_locks[nlocks++]); if (err < 0) { err = REFTABLE_IO_ERROR; goto done; @@ -1265,7 +1260,7 @@ static int stack_compact_range(struct reftable_stack *st, * "tables.list" lock while compacting the locked tables. This allows * concurrent updates to the stack to proceed. */ - err = rollback_lock_file(&tables_list_lock); + err = flock_release(&tables_list_lock); if (err < 0) { err = REFTABLE_IO_ERROR; goto done; @@ -1288,10 +1283,7 @@ static int stack_compact_range(struct reftable_stack *st, * "tables.list". We'll then replace the compacted range of tables with * the new table. */ - err = hold_lock_file_for_update_timeout(&tables_list_lock, - st->list_file, - LOCK_NO_DEREF, - st->opts.lock_timeout_ms); + err = flock_acquire(&tables_list_lock, st->list_file, st->opts.lock_timeout_ms); if (err < 0) { if (errno == EEXIST) err = REFTABLE_LOCK_ERROR; @@ -1301,7 +1293,7 @@ static int stack_compact_range(struct reftable_stack *st, } if (st->opts.default_permissions) { - if (chmod(get_lock_file_path(&tables_list_lock), + if (chmod(tables_list_lock.path, st->opts.default_permissions) < 0) { err = REFTABLE_IO_ERROR; goto done; @@ -1456,7 +1448,7 @@ static int stack_compact_range(struct reftable_stack *st, goto done; } - err = write_in_full(get_lock_file_fd(&tables_list_lock), + err = write_in_full(tables_list_lock.fd, tables_list_buf.buf, tables_list_buf.len); if (err < 0) { err = REFTABLE_IO_ERROR; @@ -1464,14 +1456,14 @@ static int stack_compact_range(struct reftable_stack *st, goto done; } - err = stack_fsync(&st->opts, get_lock_file_fd(&tables_list_lock)); + err = stack_fsync(&st->opts, tables_list_lock.fd); if (err < 0) { err = REFTABLE_IO_ERROR; unlink(new_table_path.buf); goto done; } - err = commit_lock_file(&tables_list_lock); + err = flock_commit(&tables_list_lock); if (err < 0) { err = REFTABLE_IO_ERROR; unlink(new_table_path.buf); @@ -1492,12 +1484,11 @@ static int stack_compact_range(struct reftable_stack *st, * readers, so it is expected that unlinking tables may fail. */ for (i = 0; i < nlocks; i++) { - struct lock_file *table_lock = &table_locks[i]; - const char *lock_path = get_lock_file_path(table_lock); + struct reftable_flock *table_lock = &table_locks[i]; reftable_buf_reset(&table_name); - err = reftable_buf_add(&table_name, lock_path, - strlen(lock_path) - strlen(".lock")); + err = reftable_buf_add(&table_name, table_lock->path, + strlen(table_lock->path) - strlen(".lock")); if (err) continue; @@ -1505,9 +1496,9 @@ static int stack_compact_range(struct reftable_stack *st, } done: - rollback_lock_file(&tables_list_lock); + flock_release(&tables_list_lock); for (i = 0; table_locks && i < nlocks; i++) - rollback_lock_file(&table_locks[i]); + flock_release(&table_locks[i]); reftable_free(table_locks); tmpfile_delete(&new_table); diff --git a/reftable/system.c b/reftable/system.c index 01f96f03d8..adf8e4d30b 100644 --- a/reftable/system.c +++ b/reftable/system.c @@ -1,6 +1,7 @@ #include "system.h" #include "basics.h" #include "reftable-error.h" +#include "../lockfile.h" #include "../tempfile.h" int tmpfile_from_pattern(struct reftable_tmpfile *out, const char *pattern) @@ -47,3 +48,79 @@ int tmpfile_rename(struct reftable_tmpfile *t, const char *path) return REFTABLE_IO_ERROR; return 0; } + +int flock_acquire(struct reftable_flock *l, const char *target_path, + long timeout_ms) +{ + struct lock_file *lockfile; + int err; + + lockfile = reftable_malloc(sizeof(*lockfile)); + if (!lockfile) + return REFTABLE_OUT_OF_MEMORY_ERROR; + + err = hold_lock_file_for_update_timeout(lockfile, target_path, LOCK_NO_DEREF, + timeout_ms); + if (err < 0) { + reftable_free(lockfile); + if (errno == EEXIST) + return REFTABLE_LOCK_ERROR; + return -1; + } + + l->fd = get_lock_file_fd(lockfile); + l->path = get_lock_file_path(lockfile); + l->priv = lockfile; + + return 0; +} + +int flock_close(struct reftable_flock *l) +{ + struct lock_file *lockfile = l->priv; + int ret; + + if (!lockfile) + return REFTABLE_API_ERROR; + + ret = close_lock_file_gently(lockfile); + l->fd = -1; + if (ret < 0) + return REFTABLE_IO_ERROR; + + return 0; +} + +int flock_release(struct reftable_flock *l) +{ + struct lock_file *lockfile = l->priv; + int ret; + + if (!lockfile) + return 0; + + ret = rollback_lock_file(lockfile); + reftable_free(lockfile); + *l = REFTABLE_FLOCK_INIT; + if (ret < 0) + return REFTABLE_IO_ERROR; + + return 0; +} + +int flock_commit(struct reftable_flock *l) +{ + struct lock_file *lockfile = l->priv; + int ret; + + if (!lockfile) + return REFTABLE_API_ERROR; + + ret = commit_lock_file(lockfile); + reftable_free(lockfile); + *l = REFTABLE_FLOCK_INIT; + if (ret < 0) + return REFTABLE_IO_ERROR; + + return 0; +} diff --git a/reftable/system.h b/reftable/system.h index 858189fd55..7d5f803eeb 100644 --- a/reftable/system.h +++ b/reftable/system.h @@ -12,7 +12,6 @@ https://developers.google.com/open-source/licenses/bsd /* This header glues the reftable library to the rest of Git */ #include "git-compat-util.h" -#include "lockfile.h" /* * An implementation-specific temporary file. By making this specific to the @@ -55,4 +54,48 @@ int tmpfile_delete(struct reftable_tmpfile *t); */ int tmpfile_rename(struct reftable_tmpfile *t, const char *path); +/* + * An implementation-specific file lock. Same as with `reftable_tmpfile`, + * making this specific to the implementation makes it possible to tie this + * into signal or atexit handlers such that we know to clean up stale locks on + * abnormal exits. + */ +struct reftable_flock { + const char *path; + int fd; + void *priv; +}; +#define REFTABLE_FLOCK_INIT ((struct reftable_flock){ .fd = -1, }) + +/* + * Acquire the lock for the given target path by exclusively creating a file + * with ".lock" appended to it. If that lock exists, we wait up to `timeout_ms` + * to acquire the lock. If `timeout_ms` is 0 we don't wait, if it is negative + * we block indefinitely. + * + * Retrun 0 on success, a reftable error code on error. + */ +int flock_acquire(struct reftable_flock *l, const char *target_path, + long timeout_ms); + +/* + * Close the lockfile's file descriptor without removing the lock itself. This + * is a no-op in case the lockfile has already been closed beforehand. Returns + * 0 on success, a reftable error code on error. + */ +int flock_close(struct reftable_flock *l); + +/* + * Release the lock by unlinking the lockfile. This is a no-op in case the + * lockfile has already been released or committed beforehand. Returns 0 on + * success, a reftable error code on error. + */ +int flock_release(struct reftable_flock *l); + +/* + * Commit the lock by renaming the lockfile into place. Returns 0 on success, a + * reftable error code on error. + */ +int flock_commit(struct reftable_flock *l); + #endif diff --git a/t/unit-tests/lib-reftable.c b/t/unit-tests/lib-reftable.c index c1631f4527..d795dfb7c9 100644 --- a/t/unit-tests/lib-reftable.c +++ b/t/unit-tests/lib-reftable.c @@ -2,6 +2,7 @@ #include "test-lib.h" #include "reftable/constants.h" #include "reftable/writer.h" +#include "strbuf.h" void t_reftable_set_hash(uint8_t *p, int i, enum reftable_hash id) { diff --git a/t/unit-tests/t-reftable-block.c b/t/unit-tests/t-reftable-block.c index 13e10807da..22040aeefa 100644 --- a/t/unit-tests/t-reftable-block.c +++ b/t/unit-tests/t-reftable-block.c @@ -11,6 +11,7 @@ https://developers.google.com/open-source/licenses/bsd #include "reftable/blocksource.h" #include "reftable/constants.h" #include "reftable/reftable-error.h" +#include "strbuf.h" static void t_ref_block_read_write(void) { diff --git a/t/unit-tests/t-reftable-pq.c b/t/unit-tests/t-reftable-pq.c index 272da05bea..f3f8a0cdf3 100644 --- a/t/unit-tests/t-reftable-pq.c +++ b/t/unit-tests/t-reftable-pq.c @@ -9,6 +9,7 @@ https://developers.google.com/open-source/licenses/bsd #include "test-lib.h" #include "reftable/constants.h" #include "reftable/pq.h" +#include "strbuf.h" static void merged_iter_pqueue_check(const struct merged_iter_pqueue *pq) { diff --git a/t/unit-tests/t-reftable-readwrite.c b/t/unit-tests/t-reftable-readwrite.c index 57896922eb..91c881aedf 100644 --- a/t/unit-tests/t-reftable-readwrite.c +++ b/t/unit-tests/t-reftable-readwrite.c @@ -13,6 +13,7 @@ https://developers.google.com/open-source/licenses/bsd #include "reftable/reader.h" #include "reftable/reftable-error.h" #include "reftable/reftable-writer.h" +#include "strbuf.h" static const int update_index = 5; diff --git a/t/unit-tests/t-reftable-stack.c b/t/unit-tests/t-reftable-stack.c index 13fd8d8f94..b2f6c1c37e 100644 --- a/t/unit-tests/t-reftable-stack.c +++ b/t/unit-tests/t-reftable-stack.c @@ -13,6 +13,8 @@ https://developers.google.com/open-source/licenses/bsd #include "reftable/reader.h" #include "reftable/reftable-error.h" #include "reftable/stack.h" +#include "strbuf.h" +#include "tempfile.h" #include static void clear_dir(const char *dirname)