summaryrefslogtreecommitdiff
path: root/builtin/index-pack.c
diff options
context:
space:
mode:
Diffstat (limited to 'builtin/index-pack.c')
-rw-r--r--builtin/index-pack.c511
1 files changed, 368 insertions, 143 deletions
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 0d03cb442d..60a8ee05db 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -1,6 +1,12 @@
+#define USE_THE_REPOSITORY_VARIABLE
+#define DISABLE_SIGN_COMPARE_WARNINGS
+
#include "builtin.h"
#include "config.h"
#include "delta.h"
+#include "environment.h"
+#include "gettext.h"
+#include "hex.h"
#include "pack.h"
#include "csum-file.h"
#include "blob.h"
@@ -9,15 +15,25 @@
#include "tree.h"
#include "progress.h"
#include "fsck.h"
-#include "exec-cmd.h"
+#include "strbuf.h"
#include "streaming.h"
#include "thread-utils.h"
#include "packfile.h"
+#include "pack-revindex.h"
+#include "object-file.h"
#include "object-store.h"
+#include "oid-array.h"
+#include "oidset.h"
+#include "path.h"
+#include "replace-object.h"
+#include "tree-walk.h"
#include "promisor-remote.h"
+#include "run-command.h"
+#include "setup.h"
+#include "strvec.h"
static const char index_pack_usage[] =
-"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
+"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--[no-]rev-index] [--verify] [--strict[=<msg-id>=<severity>...]] [--fsck-objects[=<msg-id>=<severity>...]] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
struct object_entry {
struct pack_idx_entry idx;
@@ -86,7 +102,7 @@ static LIST_HEAD(done_head);
static size_t base_cache_used;
static size_t base_cache_limit;
-struct thread_local {
+struct thread_local_data {
pthread_t thread;
int pack_fd;
};
@@ -109,7 +125,7 @@ static struct object_entry *objects;
static struct object_stat *obj_stat;
static struct ofs_delta_entry *ofs_deltas;
static struct ref_delta_entry *ref_deltas;
-static struct thread_local nothread_data;
+static struct thread_local_data nothread_data;
static int nr_objects;
static int nr_ofs_deltas;
static int nr_ref_deltas;
@@ -120,8 +136,9 @@ static int nr_threads;
static int from_stdin;
static int strict;
static int do_fsck_object;
-static struct fsck_options fsck_options = FSCK_OPTIONS_STRICT;
+static struct fsck_options fsck_options = FSCK_OPTIONS_MISSING_GITMODULES;
static int verbose;
+static const char *progress_title;
static int show_resolving_progress;
static int show_stat;
static int check_self_contained_and_connected;
@@ -134,12 +151,19 @@ static unsigned int input_offset, input_len;
static off_t consumed_bytes;
static off_t max_input_size;
static unsigned deepest_delta;
-static git_hash_ctx input_ctx;
+static struct git_hash_ctx input_ctx;
static uint32_t input_crc32;
static int input_fd, output_fd;
static const char *curr_pack;
-static struct thread_local *thread_data;
+/*
+ * outgoing_links is guarded by read_mutex, and record_outgoing_links is
+ * read-only in a thread.
+ */
+static struct oidset outgoing_links = OIDSET_INIT;
+static int record_outgoing_links;
+
+static struct thread_local_data *thread_data;
static int nr_dispatched;
static int threads_active;
@@ -185,11 +209,9 @@ static void init_thread(void)
if (show_stat)
pthread_mutex_init(&deepest_delta_mutex, NULL);
pthread_key_create(&key, NULL);
- thread_data = xcalloc(nr_threads, sizeof(*thread_data));
+ CALLOC_ARRAY(thread_data, nr_threads);
for (i = 0; i < nr_threads; i++) {
- thread_data[i].pack_fd = open(curr_pack, O_RDONLY);
- if (thread_data[i].pack_fd == -1)
- die_errno(_("unable to open %s"), curr_pack);
+ thread_data[i].pack_fd = xopen(curr_pack, O_RDONLY);
}
threads_active = 1;
@@ -212,7 +234,9 @@ static void cleanup_thread(void)
free(thread_data);
}
-static int mark_link(struct object *obj, int type, void *data, struct fsck_options *options)
+static int mark_link(struct object *obj, enum object_type type,
+ void *data UNUSED,
+ struct fsck_options *options UNUSED)
{
if (!obj)
return -1;
@@ -255,13 +279,14 @@ static unsigned check_objects(void)
{
unsigned i, max, foreign_nr = 0;
- max = get_max_object_index();
+ max = get_max_object_index(the_repository);
if (verbose)
- progress = start_delayed_progress(_("Checking objects"), max);
+ progress = start_delayed_progress(the_repository,
+ _("Checking objects"), max);
for (i = 0; i < max; i++) {
- foreign_nr += check_object(get_indexed_object(i));
+ foreign_nr += check_object(get_indexed_object(the_repository, i));
display_progress(progress, i + 1);
}
@@ -276,7 +301,7 @@ static void flush(void)
if (input_offset) {
if (output_fd >= 0)
write_or_die(output_fd, input_buffer, input_offset);
- the_hash_algo->update_fn(&input_ctx, input_buffer, input_offset);
+ git_hash_update(&input_ctx, input_buffer, input_offset);
memmove(input_buffer, input_buffer + input_offset, input_len);
input_offset = 0;
}
@@ -323,8 +348,12 @@ static void use(int bytes)
if (signed_add_overflows(consumed_bytes, bytes))
die(_("pack too large for current definition of off_t"));
consumed_bytes += bytes;
- if (max_input_size && consumed_bytes > max_input_size)
- die(_("pack exceeds maximum allowed size"));
+ if (max_input_size && consumed_bytes > max_input_size) {
+ struct strbuf size_limit = STRBUF_INIT;
+ strbuf_humanise_bytes(&size_limit, max_input_size);
+ die(_("pack exceeds maximum allowed size (%s)"),
+ size_limit.buf);
+ }
}
static const char *open_pack_file(const char *pack_name)
@@ -337,15 +366,11 @@ static const char *open_pack_file(const char *pack_name)
"pack/tmp_pack_XXXXXX");
pack_name = strbuf_detach(&tmp_file, NULL);
} else {
- output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
- if (output_fd < 0)
- die_errno(_("unable to create '%s'"), pack_name);
+ output_fd = xopen(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
}
nothread_data.pack_fd = output_fd;
} else {
- input_fd = open(pack_name, O_RDONLY);
- if (input_fd < 0)
- die_errno(_("cannot open packfile '%s'"), pack_name);
+ input_fd = xopen(pack_name, O_RDONLY);
output_fd = -1;
nothread_data.pack_fd = input_fd;
}
@@ -355,22 +380,22 @@ static const char *open_pack_file(const char *pack_name)
static void parse_pack_header(void)
{
- struct pack_header *hdr = fill(sizeof(struct pack_header));
+ unsigned char *hdr = fill(sizeof(struct pack_header));
/* Header consistency check */
- if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
+ if (get_be32(hdr) != PACK_SIGNATURE)
die(_("pack signature mismatch"));
- if (!pack_version_ok(hdr->hdr_version))
+ hdr += 4;
+ if (!pack_version_ok_native(get_be32(hdr)))
die(_("pack version %"PRIu32" unsupported"),
- ntohl(hdr->hdr_version));
+ get_be32(hdr));
+ hdr += 4;
- nr_objects = ntohl(hdr->hdr_entries);
+ nr_objects = get_be32(hdr);
use(sizeof(struct pack_header));
}
-static NORETURN void bad_object(off_t offset, const char *format,
- ...) __attribute__((format (printf, 2, 3)));
-
+__attribute__((format (printf, 2, 3)))
static NORETURN void bad_object(off_t offset, const char *format, ...)
{
va_list params;
@@ -383,7 +408,7 @@ static NORETURN void bad_object(off_t offset, const char *format, ...)
(uintmax_t)offset, buf);
}
-static inline struct thread_local *get_thread_data(void)
+static inline struct thread_local_data *get_thread_data(void)
{
if (HAVE_THREADS) {
if (threads_active)
@@ -394,7 +419,7 @@ static inline struct thread_local *get_thread_data(void)
return &nothread_data;
}
-static void set_thread_data(struct thread_local *data)
+static void set_thread_data(struct thread_local_data *data)
{
if (threads_active)
pthread_setspecific(key, data);
@@ -450,18 +475,18 @@ static void *unpack_entry_data(off_t offset, unsigned long size,
int status;
git_zstream stream;
void *buf;
- git_hash_ctx c;
+ struct git_hash_ctx c;
char hdr[32];
int hdrlen;
if (!is_delta_type(type)) {
- hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %"PRIuMAX,
- type_name(type),(uintmax_t)size) + 1;
+ hdrlen = format_object_header(hdr, sizeof(hdr), type, size);
the_hash_algo->init_fn(&c);
- the_hash_algo->update_fn(&c, hdr, hdrlen);
+ git_hash_update(&c, hdr, hdrlen);
} else
oid = NULL;
- if (type == OBJ_BLOB && size > big_file_threshold)
+ if (type == OBJ_BLOB &&
+ size > repo_settings_get_big_file_threshold(the_repository))
buf = fixed_buf;
else
buf = xmallocz(size);
@@ -478,7 +503,7 @@ static void *unpack_entry_data(off_t offset, unsigned long size,
status = git_inflate(&stream, 0);
use(input_len - stream.avail_in);
if (oid)
- the_hash_algo->update_fn(&c, last_out, stream.next_out - last_out);
+ git_hash_update(&c, last_out, stream.next_out - last_out);
if (buf == fixed_buf) {
stream.next_out = buf;
stream.avail_out = sizeof(fixed_buf);
@@ -488,7 +513,7 @@ static void *unpack_entry_data(off_t offset, unsigned long size,
bad_object(offset, _("inflate returned %d"), status);
git_inflate_end(&stream);
if (oid)
- the_hash_algo->final_fn(oid->hash, &c);
+ git_hash_final_oid(oid, &c);
return buf == fixed_buf ? NULL : buf;
}
@@ -523,7 +548,8 @@ static void *unpack_raw_entry(struct object_entry *obj,
switch (obj->type) {
case OBJ_REF_DELTA:
- hashcpy(ref_oid->hash, fill(the_hash_algo->rawsz));
+ oidread(ref_oid, fill(the_hash_algo->rawsz),
+ the_repository->hash_algo);
use(the_hash_algo->rawsz);
break;
case OBJ_OFS_DELTA:
@@ -585,7 +611,7 @@ static void *unpack_data(struct object_entry *obj,
if (!n)
die(Q_("premature end of pack file, %"PRIuMAX" byte missing",
"premature end of pack file, %"PRIuMAX" bytes missing",
- (unsigned int)len),
+ len),
(uintmax_t)len);
from += n;
len -= n;
@@ -774,7 +800,8 @@ static int check_collison(struct object_entry *entry)
enum object_type type;
unsigned long size;
- if (entry->size <= big_file_threshold || entry->type != OBJ_BLOB)
+ if (entry->size <= repo_settings_get_big_file_threshold(the_repository) ||
+ entry->type != OBJ_BLOB)
return -1;
memset(&data, 0, sizeof(data));
@@ -792,6 +819,68 @@ static int check_collison(struct object_entry *entry)
return 0;
}
+static void record_outgoing_link(const struct object_id *oid)
+{
+ oidset_insert(&outgoing_links, oid);
+}
+
+static void maybe_record_name_entry(const struct name_entry *entry)
+{
+ /*
+ * Checking only trees here results in a significantly faster packfile
+ * indexing, but the drawback is that if the packfile to be indexed
+ * references a local blob only directly (that is, never through a
+ * local tree), that local blob is in danger of being garbage
+ * collected. Such a situation may arise if we push local commits,
+ * including one with a change to a blob in the root tree, and then the
+ * server incorporates them into its main branch through a "rebase" or
+ * "squash" merge strategy, and then we fetch the new main branch from
+ * the server.
+ *
+ * This situation has not been observed yet - we have only noticed
+ * missing commits, not missing trees or blobs. (In fact, if it were
+ * believed that only missing commits are problematic, one could argue
+ * that we should also exclude trees during the outgoing link check;
+ * but it is safer to include them.)
+ *
+ * Due to the rarity of the situation (it has not been observed to
+ * happen in real life), and because the "penalty" in such a situation
+ * is merely to refetch the missing blob when it's needed (and this
+ * happens only once - when refetched, the blob goes into a promisor
+ * pack, so it won't be GC-ed, the tradeoff seems worth it.
+ */
+ if (S_ISDIR(entry->mode))
+ record_outgoing_link(&entry->oid);
+}
+
+static void do_record_outgoing_links(struct object *obj)
+{
+ if (obj->type == OBJ_TREE) {
+ struct tree *tree = (struct tree *)obj;
+ struct tree_desc desc;
+ struct name_entry entry;
+ if (init_tree_desc_gently(&desc, &tree->object.oid,
+ tree->buffer, tree->size, 0))
+ /*
+ * Error messages are given when packs are
+ * verified, so do not print any here.
+ */
+ return;
+ while (tree_entry_gently(&desc, &entry))
+ maybe_record_name_entry(&entry);
+ } else if (obj->type == OBJ_COMMIT) {
+ struct commit *commit = (struct commit *) obj;
+ struct commit_list *parents = commit->parents;
+
+ record_outgoing_link(get_commit_tree_oid(commit));
+ for (; parents; parents = parents->next)
+ record_outgoing_link(&parents->item->object.oid);
+ } else if (obj->type == OBJ_TAG) {
+ struct tag *tag = (struct tag *) obj;
+ record_outgoing_link(get_tagged_oid(tag));
+ }
+}
+
static void sha1_object(const void *data, struct object_entry *obj_entry,
unsigned long size, enum object_type type,
const struct object_id *oid)
@@ -804,7 +893,8 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
if (startup_info->have_repository) {
read_lock();
collision_test_needed =
- has_object_file_with_flags(oid, OBJECT_INFO_QUICK);
+ repo_has_object_file_with_flags(the_repository, oid,
+ OBJECT_INFO_QUICK);
read_unlock();
}
@@ -824,7 +914,8 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
die(_("cannot read existing object info %s"), oid_to_hex(oid));
if (has_type != type || has_size != size)
die(_("SHA1 COLLISION FOUND WITH %s !"), oid_to_hex(oid));
- has_data = read_object_file(oid, &has_type, &has_size);
+ has_data = repo_read_object_file(the_repository, oid,
+ &has_type, &has_size);
read_unlock();
if (!data)
data = new_data = get_data_from_pack(obj_entry);
@@ -836,7 +927,7 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
free(has_data);
}
- if (strict || do_fsck_object) {
+ if (strict || do_fsck_object || record_outgoing_links) {
read_lock();
if (type == OBJ_BLOB) {
struct blob *blob = lookup_blob(the_repository, oid);
@@ -868,6 +959,8 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
die(_("fsck error in packed object"));
if (strict && fsck_walk(obj, NULL, &fsck_options))
die(_("Not all child objects of %s are reachable"), oid_to_hex(&obj->oid));
+ if (record_outgoing_links)
+ do_record_outgoing_links(obj);
if (obj->type == OBJ_TREE) {
struct tree *item = (struct tree *) obj;
@@ -977,7 +1070,7 @@ static struct base_data *resolve_delta(struct object_entry *delta_obj,
if (!result_data)
bad_object(delta_obj->idx.offset, _("failed to apply delta"));
hash_object_file(the_hash_algo, result_data, result_size,
- type_name(delta_obj->real_type), &delta_obj->idx.oid);
+ delta_obj->real_type, &delta_obj->idx.oid);
sha1_object(result_data, NULL, result_size, delta_obj->real_type,
&delta_obj->idx.oid);
@@ -1115,6 +1208,7 @@ static void *threaded_second_pass(void *data)
list_add(&child->list, &work_head);
base_cache_used += child->size;
prune_base_data(NULL);
+ free_base_data(child);
} else {
/*
* This child does not have its own children. It may be
@@ -1137,6 +1231,7 @@ static void *threaded_second_pass(void *data)
p = next_p;
}
+ FREE_AND_NULL(child);
}
work_unlock();
}
@@ -1155,9 +1250,12 @@ static void parse_pack_objects(unsigned char *hash)
struct ofs_delta_entry *ofs_delta = ofs_deltas;
struct object_id ref_delta_oid;
struct stat st;
+ struct git_hash_ctx tmp_ctx;
if (verbose)
progress = start_progress(
+ the_repository,
+ progress_title ? progress_title :
from_stdin ? _("Receiving objects") : _("Indexing objects"),
nr_objects);
for (i = 0; i < nr_objects; i++) {
@@ -1190,8 +1288,10 @@ static void parse_pack_objects(unsigned char *hash)
/* Check pack integrity */
flush();
- the_hash_algo->final_fn(hash, &input_ctx);
- if (!hasheq(fill(the_hash_algo->rawsz), hash))
+ the_hash_algo->init_fn(&tmp_ctx);
+ git_hash_clone(&tmp_ctx, &input_ctx);
+ git_hash_final(hash, &tmp_ctx);
+ if (!hasheq(fill(the_hash_algo->rawsz), hash, the_repository->hash_algo))
die(_("pack is corrupted (SHA1 mismatch)"));
use(the_hash_algo->rawsz);
@@ -1223,7 +1323,7 @@ static void parse_pack_objects(unsigned char *hash)
* recursively checking if the resulting object is used as a base
* for some more deltas.
*/
-static void resolve_deltas(void)
+static void resolve_deltas(struct pack_idx_option *opts)
{
int i;
@@ -1235,11 +1335,12 @@ static void resolve_deltas(void)
QSORT(ref_deltas, nr_ref_deltas, compare_ref_delta_entry);
if (verbose || show_resolving_progress)
- progress = start_progress(_("Resolving deltas"),
+ progress = start_progress(the_repository,
+ _("Resolving deltas"),
nr_ref_deltas + nr_ofs_deltas);
nr_dispatched = 0;
- base_cache_limit = delta_base_cache_limit * nr_threads;
+ base_cache_limit = opts->delta_base_cache_limit * nr_threads;
if (nr_threads > 1 || getenv("GIT_FORCE_THREADS")) {
init_thread();
for (i = 0; i < nr_threads; i++) {
@@ -1283,7 +1384,7 @@ static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned cha
REALLOC_ARRAY(objects, nr_objects + nr_unresolved + 1);
memset(objects + nr_objects + 1, 0,
nr_unresolved * sizeof(*objects));
- f = hashfd(output_fd, curr_pack);
+ f = hashfd(the_repository->hash_algo, output_fd, curr_pack);
fix_unresolved_deltas(f);
strbuf_addf(&msg, Q_("completed with %d local object",
"completed with %d local objects",
@@ -1291,12 +1392,12 @@ static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned cha
nr_objects - nr_objects_initial);
stop_progress_msg(&progress, msg.buf);
strbuf_release(&msg);
- finalize_hashfile(f, tail_hash, 0);
- hashcpy(read_hash, pack_hash);
- fixup_pack_header_footer(output_fd, pack_hash,
+ finalize_hashfile(f, tail_hash, FSYNC_COMPONENT_PACK, 0);
+ hashcpy(read_hash, pack_hash, the_repository->hash_algo);
+ fixup_pack_header_footer(the_hash_algo, output_fd, pack_hash,
curr_pack, nr_objects,
read_hash, consumed_bytes-the_hash_algo->rawsz);
- if (!hasheq(read_hash, tail_hash))
+ if (!hasheq(read_hash, tail_hash, the_repository->hash_algo))
die(_("Unexpected tail checksum for %s "
"(disk corruption?)"), curr_pack);
}
@@ -1357,7 +1458,7 @@ static struct object_entry *append_obj_to_pack(struct hashfile *f,
obj[1].idx.offset += write_compressed(f, buf, size);
obj[0].idx.crc32 = crc32_end(f);
hashflush(f);
- hashcpy(obj->idx.oid.hash, sha1);
+ oidread(&obj->idx.oid, sha1, the_repository->hash_algo);
return obj;
}
@@ -1388,7 +1489,7 @@ static void fix_unresolved_deltas(struct hashfile *f)
sorted_by_pos[i] = &ref_deltas[i];
QSORT(sorted_by_pos, nr_ref_deltas, delta_pos_compare);
- if (has_promisor_remote()) {
+ if (repo_has_promisor_remote(the_repository)) {
/*
* Prefetch the delta bases.
*/
@@ -1414,13 +1515,13 @@ static void fix_unresolved_deltas(struct hashfile *f)
if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
continue;
- data = read_object_file(&d->oid, &type, &size);
+ data = repo_read_object_file(the_repository, &d->oid, &type,
+ &size);
if (!data)
continue;
- if (check_object_signature(the_repository, &d->oid,
- data, size,
- type_name(type)))
+ if (check_object_signature(the_repository, &d->oid, data, size,
+ type) < 0)
die(_("local object %s is corrupt"), oid_to_hex(&d->oid));
/*
@@ -1429,6 +1530,7 @@ static void fix_unresolved_deltas(struct hashfile *f)
* object).
*/
append_obj_to_pack(f, d->oid.hash, data, size, type);
+ free(data);
threaded_second_pass(NULL);
display_progress(progress, nr_resolved_deltas);
@@ -1436,15 +1538,15 @@ static void fix_unresolved_deltas(struct hashfile *f)
free(sorted_by_pos);
}
-static const char *derive_filename(const char *pack_name, const char *suffix,
- struct strbuf *buf)
+static const char *derive_filename(const char *pack_name, const char *strip,
+ const char *suffix, struct strbuf *buf)
{
size_t len;
- if (!strip_suffix(pack_name, ".pack", &len))
- die(_("packfile name '%s' does not end with '.pack'"),
- pack_name);
+ if (!strip_suffix(pack_name, strip, &len) || !len ||
+ pack_name[len - 1] != '.')
+ die(_("packfile name '%s' does not end with '.%s'"),
+ pack_name, strip);
strbuf_add(buf, pack_name, len);
- strbuf_addch(buf, '.');
strbuf_addstr(buf, suffix);
return buf->buf;
}
@@ -1459,9 +1561,9 @@ static void write_special_file(const char *suffix, const char *msg,
int msg_len = strlen(msg);
if (pack_name)
- filename = derive_filename(pack_name, suffix, &name_buf);
+ filename = derive_filename(pack_name, "pack", suffix, &name_buf);
else
- filename = odb_pack_name(&name_buf, hash, suffix);
+ filename = odb_pack_name(the_repository, &name_buf, hash, suffix);
fd = odb_pack_keep(filename);
if (fd < 0) {
@@ -1482,22 +1584,38 @@ static void write_special_file(const char *suffix, const char *msg,
strbuf_release(&name_buf);
}
+static void rename_tmp_packfile(const char **final_name,
+ const char *curr_name,
+ struct strbuf *name, unsigned char *hash,
+ const char *ext, int make_read_only_if_same)
+{
+ if (!*final_name || strcmp(*final_name, curr_name)) {
+ if (!*final_name)
+ *final_name = odb_pack_name(the_repository, name, hash, ext);
+ if (finalize_object_file(curr_name, *final_name))
+ die(_("unable to rename temporary '*.%s' file to '%s'"),
+ ext, *final_name);
+ } else if (make_read_only_if_same) {
+ chmod(*final_name, 0444);
+ }
+}
+
static void final(const char *final_pack_name, const char *curr_pack_name,
const char *final_index_name, const char *curr_index_name,
+ const char *final_rev_index_name, const char *curr_rev_index_name,
const char *keep_msg, const char *promisor_msg,
unsigned char *hash)
{
const char *report = "pack";
struct strbuf pack_name = STRBUF_INIT;
struct strbuf index_name = STRBUF_INIT;
- int err;
+ struct strbuf rev_index_name = STRBUF_INIT;
if (!from_stdin) {
close(input_fd);
} else {
- fsync_or_die(output_fd, curr_pack_name);
- err = close(output_fd);
- if (err)
+ fsync_component_or_die(FSYNC_COMPONENT_PACK, output_fd, curr_pack_name);
+ if (close(output_fd))
die_errno(_("error while closing pack file"));
}
@@ -1508,25 +1626,18 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
write_special_file("promisor", promisor_msg, final_pack_name,
hash, NULL);
- if (final_pack_name != curr_pack_name) {
- if (!final_pack_name)
- final_pack_name = odb_pack_name(&pack_name, hash, "pack");
- if (finalize_object_file(curr_pack_name, final_pack_name))
- die(_("cannot store pack file"));
- } else if (from_stdin)
- chmod(final_pack_name, 0444);
-
- if (final_index_name != curr_index_name) {
- if (!final_index_name)
- final_index_name = odb_pack_name(&index_name, hash, "idx");
- if (finalize_object_file(curr_index_name, final_index_name))
- die(_("cannot store index file"));
- } else
- chmod(final_index_name, 0444);
+ rename_tmp_packfile(&final_pack_name, curr_pack_name, &pack_name,
+ hash, "pack", from_stdin);
+ if (curr_rev_index_name)
+ rename_tmp_packfile(&final_rev_index_name, curr_rev_index_name,
+ &rev_index_name, hash, "rev", 1);
+ rename_tmp_packfile(&final_index_name, curr_index_name, &index_name,
+ hash, "idx", 1);
if (do_fsck_object) {
struct packed_git *p;
- p = add_packed_git(final_index_name, strlen(final_index_name), 0);
+ p = add_packed_git(the_repository, final_index_name,
+ strlen(final_index_name), 0);
if (p)
install_packed_git(the_repository, p);
}
@@ -1540,35 +1651,28 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
write_or_die(1, buf.buf, buf.len);
strbuf_release(&buf);
- /*
- * Let's just mimic git-unpack-objects here and write
- * the last part of the input buffer to stdout.
- */
- while (input_len) {
- err = xwrite(1, input_buffer + input_offset, input_len);
- if (err <= 0)
- break;
- input_len -= err;
- input_offset += err;
- }
+ /* Write the last part of the buffer to stdout */
+ write_in_full(1, input_buffer + input_offset, input_len);
}
+ strbuf_release(&rev_index_name);
strbuf_release(&index_name);
strbuf_release(&pack_name);
}
-static int git_index_pack_config(const char *k, const char *v, void *cb)
+static int git_index_pack_config(const char *k, const char *v,
+ const struct config_context *ctx, void *cb)
{
struct pack_idx_option *opts = cb;
if (!strcmp(k, "pack.indexversion")) {
- opts->version = git_config_int(k, v);
+ opts->version = git_config_int(k, v, ctx->kvi);
if (opts->version > 2)
- die(_("bad pack.indexversion=%"PRIu32), opts->version);
+ die(_("bad pack.indexVersion=%"PRIu32), opts->version);
return 0;
}
if (!strcmp(k, "pack.threads")) {
- nr_threads = git_config_int(k, v);
+ nr_threads = git_config_int(k, v, ctx->kvi);
if (nr_threads < 0)
die(_("invalid number of threads specified (%d)"),
nr_threads);
@@ -1578,7 +1682,17 @@ static int git_index_pack_config(const char *k, const char *v, void *cb)
}
return 0;
}
- return git_default_config(k, v, cb);
+ if (!strcmp(k, "pack.writereverseindex")) {
+ if (git_config_bool(k, v))
+ opts->flags |= WRITE_REV;
+ else
+ opts->flags &= ~WRITE_REV;
+ }
+ if (!strcmp(k, "core.deltabasecachelimit")) {
+ opts->delta_base_cache_limit = git_config_ulong(k, v, ctx->kvi);
+ return 0;
+ }
+ return git_default_config(k, v, ctx, cb);
}
static int cmp_uint32(const void *a_, const void *b_)
@@ -1597,7 +1711,7 @@ static void read_v2_anomalous_offsets(struct packed_git *p,
/* The address of the 4-byte offset table */
idx1 = (((const uint32_t *)((const uint8_t *)p->index_data + p->crc_offset))
- + p->num_objects /* CRC32 table */
+ + (size_t)p->num_objects /* CRC32 table */
);
/* The address of the 8-byte offset table */
@@ -1625,7 +1739,8 @@ static void read_v2_anomalous_offsets(struct packed_git *p,
static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)
{
- struct packed_git *p = add_packed_git(pack_name, strlen(pack_name), 1);
+ struct packed_git *p = add_packed_git(the_repository, pack_name,
+ strlen(pack_name), 1);
if (!p)
die(_("Cannot open existing pack file '%s'"), pack_name);
@@ -1641,7 +1756,7 @@ static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)
/*
* Get rid of the idx file as we do not need it anymore.
* NEEDSWORK: extract this bit from free_pack_by_name() in
- * sha1-file.c, perhaps? It shouldn't matter very much as we
+ * object-file.c, perhaps? It shouldn't matter very much as we
* know we haven't installed this pack (hence we never have
* read anything from it).
*/
@@ -1655,7 +1770,7 @@ static void show_pack_info(int stat_only)
unsigned long *chain_histogram = NULL;
if (deepest_delta)
- chain_histogram = xcalloc(deepest_delta, sizeof(unsigned long));
+ CALLOC_ARRAY(chain_histogram, deepest_delta);
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
@@ -1691,16 +1806,89 @@ static void show_pack_info(int stat_only)
i + 1,
chain_histogram[i]);
}
+ free(chain_histogram);
}
-int cmd_index_pack(int argc, const char **argv, const char *prefix)
+static void repack_local_links(void)
{
- int i, fix_thin_pack = 0, verify = 0, stat_only = 0;
+ struct child_process cmd = CHILD_PROCESS_INIT;
+ FILE *out;
+ struct strbuf line = STRBUF_INIT;
+ struct oidset_iter iter;
+ struct object_id *oid;
+ char *base_name = NULL;
+
+ if (!oidset_size(&outgoing_links))
+ return;
+
+ oidset_iter_init(&outgoing_links, &iter);
+ while ((oid = oidset_iter_next(&iter))) {
+ struct object_info info = OBJECT_INFO_INIT;
+ if (oid_object_info_extended(the_repository, oid, &info, 0))
+ /* Missing; assume it is a promisor object */
+ continue;
+ if (info.whence == OI_PACKED && info.u.packed.pack->pack_promisor)
+ continue;
+
+ if (!cmd.args.nr) {
+ base_name = mkpathdup(
+ "%s/pack/pack",
+ repo_get_object_directory(the_repository));
+ strvec_push(&cmd.args, "pack-objects");
+ strvec_push(&cmd.args,
+ "--exclude-promisor-objects-best-effort");
+ strvec_push(&cmd.args, base_name);
+ cmd.git_cmd = 1;
+ cmd.in = -1;
+ cmd.out = -1;
+ if (start_command(&cmd))
+ die(_("could not start pack-objects to repack local links"));
+ }
+
+ if (write_in_full(cmd.in, oid_to_hex(oid), the_hash_algo->hexsz) < 0 ||
+ write_in_full(cmd.in, "\n", 1) < 0)
+ die(_("failed to feed local object to pack-objects"));
+ }
+
+ if (!cmd.args.nr)
+ return;
+
+ close(cmd.in);
+
+ out = xfdopen(cmd.out, "r");
+ while (strbuf_getline_lf(&line, out) != EOF) {
+ unsigned char binary[GIT_MAX_RAWSZ];
+ if (line.len != the_hash_algo->hexsz ||
+ !hex_to_bytes(binary, line.buf, line.len))
+ die(_("index-pack: Expecting full hex object ID lines only from pack-objects."));
+
+ /*
+ * pack-objects creates the .pack and .idx files, but not the
+ * .promisor file. Create the .promisor file, which is empty.
+ */
+ write_special_file("promisor", "", NULL, binary, NULL);
+ }
+
+ fclose(out);
+ if (finish_command(&cmd))
+ die(_("could not finish pack-objects to repack local links"));
+ strbuf_release(&line);
+ free(base_name);
+}
+
+int cmd_index_pack(int argc,
+ const char **argv,
+ const char *prefix,
+ struct repository *repo UNUSED)
+{
+ int i, fix_thin_pack = 0, verify = 0, stat_only = 0, rev_index;
const char *curr_index;
- const char *index_name = NULL, *pack_name = NULL;
+ char *curr_rev_index = NULL;
+ const char *index_name = NULL, *pack_name = NULL, *rev_index_name = NULL;
const char *keep_msg = NULL;
const char *promisor_msg = NULL;
struct strbuf index_name_buf = STRBUF_INIT;
+ struct strbuf rev_index_name_buf = STRBUF_INIT;
struct pack_idx_entry **idx_objects;
struct pack_idx_option opts;
unsigned char pack_hash[GIT_MAX_RAWSZ];
@@ -1716,17 +1904,22 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
*/
fetch_if_missing = 0;
- if (argc == 2 && !strcmp(argv[1], "-h"))
- usage(index_pack_usage);
+ show_usage_if_asked(argc, argv, index_pack_usage);
- read_replace_refs = 0;
+ disable_replace_refs();
fsck_options.walk = mark_link;
reset_pack_idx_option(&opts);
+ opts.flags |= WRITE_REV;
git_config(git_index_pack_config, &opts);
if (prefix && chdir(prefix))
die(_("Cannot come back to cwd"));
+ if (git_env_bool(GIT_TEST_NO_WRITE_REV_INDEX, 0))
+ rev_index = 0;
+ else
+ rev_index = !!(opts.flags & (WRITE_REV_VERIFY | WRITE_REV));
+
for (i = 1; i < argc; i++) {
const char *arg = argv[i];
@@ -1742,8 +1935,9 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
} else if (!strcmp(arg, "--check-self-contained-and-connected")) {
strict = 1;
check_self_contained_and_connected = 1;
- } else if (!strcmp(arg, "--fsck-objects")) {
+ } else if (skip_to_optional_arg(arg, "--fsck-objects", &arg)) {
do_fsck_object = 1;
+ fsck_set_msg_types(&fsck_options, arg);
} else if (!strcmp(arg, "--verify")) {
verify = 1;
} else if (!strcmp(arg, "--verify-stat")) {
@@ -1756,7 +1950,7 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
} else if (skip_to_optional_arg(arg, "--keep", &keep_msg)) {
; /* nothing to do */
} else if (skip_to_optional_arg(arg, "--promisor", &promisor_msg)) {
- ; /* already parsed */
+ record_outgoing_links = 1;
} else if (starts_with(arg, "--threads=")) {
char *end;
nr_threads = strtoul(arg+10, &end, 0);
@@ -1766,21 +1960,17 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
warning(_("no threads support, ignoring %s"), arg);
nr_threads = 1;
}
- } else if (starts_with(arg, "--pack_header=")) {
- struct pack_header *hdr;
- char *c;
-
- hdr = (struct pack_header *)input_buffer;
- hdr->hdr_signature = htonl(PACK_SIGNATURE);
- hdr->hdr_version = htonl(strtoul(arg + 14, &c, 10));
- if (*c != ',')
- die(_("bad %s"), arg);
- hdr->hdr_entries = htonl(strtoul(c + 1, &c, 10));
- if (*c)
- die(_("bad %s"), arg);
- input_len = sizeof(*hdr);
+ } else if (skip_prefix(arg, "--pack_header=", &arg)) {
+ if (parse_pack_header_option(arg,
+ input_buffer,
+ &input_len) < 0)
+ die(_("bad --pack_header: %s"), arg);
} else if (!strcmp(arg, "-v")) {
verbose = 1;
+ } else if (!strcmp(arg, "--progress-title")) {
+ if (progress_title || (i+1) >= argc)
+ usage(index_pack_usage);
+ progress_title = argv[++i];
} else if (!strcmp(arg, "--show-resolving-progress")) {
show_resolving_progress = 1;
} else if (!strcmp(arg, "--report-end-of-input")) {
@@ -1805,6 +1995,10 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
if (hash_algo == GIT_HASH_UNKNOWN)
die(_("unknown hash algorithm '%s'"), arg);
repo_set_hash_algo(the_repository, hash_algo);
+ } else if (!strcmp(arg, "--rev-index")) {
+ rev_index = 1;
+ } else if (!strcmp(arg, "--no-rev-index")) {
+ rev_index = 0;
} else
usage(index_pack_usage);
continue;
@@ -1818,13 +2012,33 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
if (!pack_name && !from_stdin)
usage(index_pack_usage);
if (fix_thin_pack && !from_stdin)
- die(_("--fix-thin cannot be used without --stdin"));
+ die(_("the option '%s' requires '%s'"), "--fix-thin", "--stdin");
+ if (promisor_msg && pack_name)
+ die(_("--promisor cannot be used with a pack name"));
if (from_stdin && !startup_info->have_repository)
die(_("--stdin requires a git repository"));
if (from_stdin && hash_algo)
- die(_("--object-format cannot be used with --stdin"));
+ die(_("options '%s' and '%s' cannot be used together"), "--object-format", "--stdin");
if (!index_name && pack_name)
- index_name = derive_filename(pack_name, "idx", &index_name_buf);
+ index_name = derive_filename(pack_name, "pack", "idx", &index_name_buf);
+
+ /*
+ * Packfiles and indices do not carry enough information to be able to
+ * identify their object hash. So when we are neither in a repository
+ * nor has the user told us which object hash to use we have no other
+ * choice but to guess the object hash.
+ */
+ if (!the_repository->hash_algo)
+ repo_set_hash_algo(the_repository, GIT_HASH_SHA1);
+
+ opts.flags &= ~(WRITE_REV | WRITE_REV_VERIFY);
+ if (rev_index) {
+ opts.flags |= verify ? WRITE_REV_VERIFY : WRITE_REV;
+ if (index_name)
+ rev_index_name = derive_filename(index_name,
+ "idx", "rev",
+ &rev_index_name_buf);
+ }
if (verify) {
if (!index_name)
@@ -1857,14 +2071,14 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
curr_pack = open_pack_file(pack_name);
parse_pack_header();
- objects = xcalloc(st_add(nr_objects, 1), sizeof(struct object_entry));
+ CALLOC_ARRAY(objects, st_add(nr_objects, 1));
if (show_stat)
- obj_stat = xcalloc(st_add(nr_objects, 1), sizeof(struct object_stat));
- ofs_deltas = xcalloc(nr_objects, sizeof(struct ofs_delta_entry));
+ CALLOC_ARRAY(obj_stat, st_add(nr_objects, 1));
+ CALLOC_ARRAY(ofs_deltas, nr_objects);
parse_pack_objects(pack_hash);
if (report_end_of_input)
write_in_full(2, "\0", 1);
- resolve_deltas();
+ resolve_deltas(&opts);
conclude_pack(fix_thin_pack, curr_pack, pack_hash);
free(ofs_deltas);
free(ref_deltas);
@@ -1877,12 +2091,18 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
ALLOC_ARRAY(idx_objects, nr_objects);
for (i = 0; i < nr_objects; i++)
idx_objects[i] = &objects[i].idx;
- curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_hash);
+ curr_index = write_idx_file(the_repository, index_name, idx_objects,
+ nr_objects, &opts, pack_hash);
+ if (rev_index)
+ curr_rev_index = write_rev_file(the_repository, rev_index_name,
+ idx_objects, nr_objects,
+ pack_hash, opts.flags);
free(idx_objects);
if (!verify)
final(pack_name, curr_pack,
index_name, curr_index,
+ rev_index_name, curr_rev_index,
keep_msg, promisor_msg,
pack_hash);
else
@@ -1891,12 +2111,17 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
if (do_fsck_object && fsck_finish(&fsck_options))
die(_("fsck error in pack objects"));
+ free(opts.anomaly);
free(objects);
strbuf_release(&index_name_buf);
- if (pack_name == NULL)
+ strbuf_release(&rev_index_name_buf);
+ if (!pack_name)
free((void *) curr_pack);
- if (index_name == NULL)
+ if (!index_name)
free((void *) curr_index);
+ free(curr_rev_index);
+
+ repack_local_links();
/*
* Let the caller know this pack is not self contained
generated by cgit v1.2.3 (git 2.46.0) at 2025-11-30 13:03:02 +0000