* creation etc.
*/
#include "cache.h"
+#include "config.h"
+#include "string-list.h"
+#include "lockfile.h"
#include "delta.h"
#include "pack.h"
#include "blob.h"
#include "sha1-lookup.h"
#include "bulk-checkin.h"
#include "streaming.h"
+#include "dir.h"
+#include "mru.h"
+#include "list.h"
+#include "mergesort.h"
+#include "quote.h"
+#include "packfile.h"
+
+const unsigned char null_sha1[GIT_MAX_RAWSZ];
+const struct object_id null_oid;
+const struct object_id empty_tree_oid = {
+ EMPTY_TREE_SHA1_BIN_LITERAL
+};
+const struct object_id empty_blob_oid = {
+ EMPTY_BLOB_SHA1_BIN_LITERAL
+};
-#ifndef O_NOATIME
-#if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
-#define O_NOATIME 01000000
-#else
-#define O_NOATIME 0
-#endif
-#endif
+static void git_hash_sha1_init(void *ctx)
+{
+ git_SHA1_Init((git_SHA_CTX *)ctx);
+}
+
+static void git_hash_sha1_update(void *ctx, const void *data, size_t len)
+{
+ git_SHA1_Update((git_SHA_CTX *)ctx, data, len);
+}
+
+static void git_hash_sha1_final(unsigned char *hash, void *ctx)
+{
+ git_SHA1_Final(hash, (git_SHA_CTX *)ctx);
+}
+
+static void git_hash_unknown_init(void *ctx)
+{
+ die("trying to init unknown hash");
+}
+
+static void git_hash_unknown_update(void *ctx, const void *data, size_t len)
+{
+ die("trying to update unknown hash");
+}
-#define SZ_FMT PRIuMAX
-static inline uintmax_t sz_fmt(size_t s) { return s; }
+static void git_hash_unknown_final(unsigned char *hash, void *ctx)
+{
+ die("trying to finalize unknown hash");
+}
-const unsigned char null_sha1[20];
+const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
+ {
+ NULL,
+ 0x00000000,
+ 0,
+ 0,
+ 0,
+ git_hash_unknown_init,
+ git_hash_unknown_update,
+ git_hash_unknown_final,
+ NULL,
+ NULL,
+ },
+ {
+ "sha-1",
+ /* "sha1", big-endian */
+ 0x73686131,
+ sizeof(git_SHA_CTX),
+ GIT_SHA1_RAWSZ,
+ GIT_SHA1_HEXSZ,
+ git_hash_sha1_init,
+ git_hash_sha1_update,
+ git_hash_sha1_final,
+ &empty_tree_oid,
+ &empty_blob_oid,
+ },
+};
/*
* This is meant to hold a *small* number of objects that you would
0
};
-static struct packed_git *last_found_pack;
-
static struct cached_object *find_cached_object(const unsigned char *sha1)
{
int i;
return NULL;
}
+
+static enum safe_crlf get_safe_crlf(unsigned flags)
+{
+ if (flags & HASH_RENORMALIZE)
+ return SAFE_CRLF_RENORMALIZE;
+ else if (flags & HASH_WRITE_OBJECT)
+ return safe_crlf;
+ else
+ return SAFE_CRLF_FALSE;
+}
+
+
int mkdir_in_gitdir(const char *path)
{
if (mkdir(path, 0777)) {
return adjust_shared_perm(path);
}
-int safe_create_leading_directories(char *path)
+enum scld_error safe_create_leading_directories(char *path)
{
- char *pos = path + offset_1st_component(path);
- struct stat st;
+ char *next_component = path + offset_1st_component(path);
+ enum scld_error ret = SCLD_OK;
+
+ while (ret == SCLD_OK && next_component) {
+ struct stat st;
+ char *slash = next_component, slash_character;
+
+ while (*slash && !is_dir_sep(*slash))
+ slash++;
- while (pos) {
- pos = strchr(pos, '/');
- if (!pos)
+ if (!*slash)
break;
- while (*++pos == '/')
- ;
- if (!*pos)
+
+ next_component = slash + 1;
+ while (is_dir_sep(*next_component))
+ next_component++;
+ if (!*next_component)
break;
- *--pos = '\0';
+
+ slash_character = *slash;
+ *slash = '\0';
if (!stat(path, &st)) {
/* path exists */
if (!S_ISDIR(st.st_mode)) {
- *pos = '/';
- return -3;
+ errno = ENOTDIR;
+ ret = SCLD_EXISTS;
}
+ } else if (mkdir(path, 0777)) {
+ if (errno == EEXIST &&
+ !stat(path, &st) && S_ISDIR(st.st_mode))
+ ; /* somebody created it since we checked */
+ else if (errno == ENOENT)
+ /*
+ * Either mkdir() failed because
+ * somebody just pruned the containing
+ * directory, or stat() failed because
+ * the file that was in our way was
+ * just removed. Either way, inform
+ * the caller that it might be worth
+ * trying again:
+ */
+ ret = SCLD_VANISHED;
+ else
+ ret = SCLD_FAILED;
+ } else if (adjust_shared_perm(path)) {
+ ret = SCLD_PERMS;
}
- else if (mkdir(path, 0777)) {
- *pos = '/';
- return -1;
- }
- else if (adjust_shared_perm(path)) {
- *pos = '/';
- return -2;
- }
- *pos++ = '/';
+ *slash = slash_character;
}
- return 0;
+ return ret;
}
-int safe_create_leading_directories_const(const char *path)
+enum scld_error safe_create_leading_directories_const(const char *path)
{
+ int save_errno;
/* path points to cache entries, so xstrdup before messing with it */
char *buf = xstrdup(path);
- int result = safe_create_leading_directories(buf);
+ enum scld_error result = safe_create_leading_directories(buf);
+
+ save_errno = errno;
free(buf);
+ errno = save_errno;
return result;
}
-static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
+int raceproof_create_file(const char *path, create_file_fn fn, void *cb)
{
- int i;
- for (i = 0; i < 20; i++) {
- static char hex[] = "0123456789abcdef";
- unsigned int val = sha1[i];
- char *pos = pathbuf + i*2 + (i > 0);
- *pos++ = hex[val >> 4];
- *pos = hex[val & 0xf];
- }
-}
+ /*
+ * The number of times we will try to remove empty directories
+ * in the way of path. This is only 1 because if another
+ * process is racily creating directories that conflict with
+ * us, we don't want to fight against them.
+ */
+ int remove_directories_remaining = 1;
-/*
- * NOTE! This returns a statically allocated buffer, so you have to be
- * careful about using it. Do an "xstrdup()" if you need to save the
- * filename.
- *
- * Also note that this returns the location for creating. Reading
- * SHA1 file can happen from any alternate directory listed in the
- * DB_ENVIRONMENT environment variable if it is not found in
- * the primary object database.
- */
-char *sha1_file_name(const unsigned char *sha1)
-{
- static char buf[PATH_MAX];
- const char *objdir;
- int len;
+ /*
+ * The number of times that we will try to create the
+ * directories containing path. We are willing to attempt this
+ * more than once, because another process could be trying to
+ * clean up empty directories at the same time as we are
+ * trying to create them.
+ */
+ int create_directories_remaining = 3;
- objdir = get_object_directory();
- len = strlen(objdir);
+ /* A scratch copy of path, filled lazily if we need it: */
+ struct strbuf path_copy = STRBUF_INIT;
- /* '/' + sha1(2) + '/' + sha1(38) + '\0' */
- if (len + 43 > PATH_MAX)
- die("insanely long object directory %s", objdir);
- memcpy(buf, objdir, len);
- buf[len] = '/';
- buf[len+3] = '/';
- buf[len+42] = '\0';
- fill_sha1_path(buf + len + 1, sha1);
- return buf;
-}
+ int ret, save_errno;
-static char *sha1_get_pack_name(const unsigned char *sha1,
- char **name, char **base, const char *which)
-{
- static const char hex[] = "0123456789abcdef";
- char *buf;
- int i;
+ /* Sanity check: */
+ assert(*path);
+
+retry_fn:
+ ret = fn(path, cb);
+ save_errno = errno;
+ if (!ret)
+ goto out;
+
+ if (errno == EISDIR && remove_directories_remaining-- > 0) {
+ /*
+ * A directory is in the way. Maybe it is empty; try
+ * to remove it:
+ */
+ if (!path_copy.len)
+ strbuf_addstr(&path_copy, path);
+
+ if (!remove_dir_recursively(&path_copy, REMOVE_DIR_EMPTY_ONLY))
+ goto retry_fn;
+ } else if (errno == ENOENT && create_directories_remaining-- > 0) {
+ /*
+ * Maybe the containing directory didn't exist, or
+ * maybe it was just deleted by a process that is
+ * racing with us to clean up empty directories. Try
+ * to create it:
+ */
+ enum scld_error scld_result;
- if (!*base) {
- const char *sha1_file_directory = get_object_directory();
- int len = strlen(sha1_file_directory);
- *base = xmalloc(len + 60);
- sprintf(*base, "%s/pack/pack-1234567890123456789012345678901234567890.%s",
- sha1_file_directory, which);
- *name = *base + len + 11;
+ if (!path_copy.len)
+ strbuf_addstr(&path_copy, path);
+
+ do {
+ scld_result = safe_create_leading_directories(path_copy.buf);
+ if (scld_result == SCLD_OK)
+ goto retry_fn;
+ } while (scld_result == SCLD_VANISHED && create_directories_remaining-- > 0);
}
- buf = *name;
+out:
+ strbuf_release(&path_copy);
+ errno = save_errno;
+ return ret;
+}
+static void fill_sha1_path(struct strbuf *buf, const unsigned char *sha1)
+{
+ int i;
for (i = 0; i < 20; i++) {
- unsigned int val = *sha1++;
- *buf++ = hex[val >> 4];
- *buf++ = hex[val & 0xf];
+ static char hex[] = "0123456789abcdef";
+ unsigned int val = sha1[i];
+ strbuf_addch(buf, hex[val >> 4]);
+ strbuf_addch(buf, hex[val & 0xf]);
+ if (!i)
+ strbuf_addch(buf, '/');
}
-
- return *base;
}
-char *sha1_pack_name(const unsigned char *sha1)
+const char *sha1_file_name(const unsigned char *sha1)
{
- static char *name, *base;
+ static struct strbuf buf = STRBUF_INIT;
+
+ strbuf_reset(&buf);
+ strbuf_addf(&buf, "%s/", get_object_directory());
- return sha1_get_pack_name(sha1, &name, &base, "pack");
+ fill_sha1_path(&buf, sha1);
+ return buf.buf;
}
-char *sha1_pack_index_name(const unsigned char *sha1)
+struct strbuf *alt_scratch_buf(struct alternate_object_database *alt)
{
- static char *name, *base;
+ strbuf_setlen(&alt->scratch, alt->base_len);
+ return &alt->scratch;
+}
- return sha1_get_pack_name(sha1, &name, &base, "idx");
+static const char *alt_sha1_path(struct alternate_object_database *alt,
+ const unsigned char *sha1)
+{
+ struct strbuf *buf = alt_scratch_buf(alt);
+ fill_sha1_path(buf, sha1);
+ return buf->buf;
}
struct alternate_object_database *alt_odb_list;
static struct alternate_object_database **alt_odb_tail;
-static int git_open_noatime(const char *name);
+/*
+ * Return non-zero iff the path is usable as an alternate object database.
+ */
+static int alt_odb_usable(struct strbuf *path, const char *normalized_objdir)
+{
+ struct alternate_object_database *alt;
+
+ /* Detect cases where alternate disappeared */
+ if (!is_directory(path->buf)) {
+ error("object directory %s does not exist; "
+ "check .git/objects/info/alternates.",
+ path->buf);
+ return 0;
+ }
+
+ /*
+ * Prevent the common mistake of listing the same
+ * thing twice, or object directory itself.
+ */
+ for (alt = alt_odb_list; alt; alt = alt->next) {
+ if (!fspathcmp(path->buf, alt->path))
+ return 0;
+ }
+ if (!fspathcmp(path->buf, normalized_objdir))
+ return 0;
+
+ return 1;
+}
/*
* Prepare alternate object database registry.
* SHA1, an extra slash for the first level indirection, and the
* terminating NUL.
*/
-static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth)
+static void read_info_alternates(const char * relative_base, int depth);
+static int link_alt_odb_entry(const char *entry, const char *relative_base,
+ int depth, const char *normalized_objdir)
{
- const char *objdir = get_object_directory();
struct alternate_object_database *ent;
- struct alternate_object_database *alt;
- int pfxlen, entlen;
struct strbuf pathbuf = STRBUF_INIT;
if (!is_absolute_path(entry) && relative_base) {
- strbuf_addstr(&pathbuf, real_path(relative_base));
+ strbuf_realpath(&pathbuf, relative_base, 1);
strbuf_addch(&pathbuf, '/');
}
- strbuf_add(&pathbuf, entry, len);
+ strbuf_addstr(&pathbuf, entry);
- normalize_path_copy(pathbuf.buf, pathbuf.buf);
-
- pfxlen = strlen(pathbuf.buf);
+ if (strbuf_normalize_path(&pathbuf) < 0 && relative_base) {
+ error("unable to normalize alternate object path: %s",
+ pathbuf.buf);
+ strbuf_release(&pathbuf);
+ return -1;
+ }
/*
* The trailing slash after the directory name is given by
* this function at the end. Remove duplicates.
*/
- while (pfxlen && pathbuf.buf[pfxlen-1] == '/')
- pfxlen -= 1;
-
- entlen = pfxlen + 43; /* '/' + 2 hex + '/' + 38 hex + NUL */
- ent = xmalloc(sizeof(*ent) + entlen);
- memcpy(ent->base, pathbuf.buf, pfxlen);
- strbuf_release(&pathbuf);
-
- ent->name = ent->base + pfxlen + 1;
- ent->base[pfxlen + 3] = '/';
- ent->base[pfxlen] = ent->base[entlen-1] = 0;
+ while (pathbuf.len && pathbuf.buf[pathbuf.len - 1] == '/')
+ strbuf_setlen(&pathbuf, pathbuf.len - 1);
- /* Detect cases where alternate disappeared */
- if (!is_directory(ent->base)) {
- error("object directory %s does not exist; "
- "check .git/objects/info/alternates.",
- ent->base);
- free(ent);
+ if (!alt_odb_usable(&pathbuf, normalized_objdir)) {
+ strbuf_release(&pathbuf);
return -1;
}
- /* Prevent the common mistake of listing the same
- * thing twice, or object directory itself.
- */
- for (alt = alt_odb_list; alt; alt = alt->next) {
- if (!memcmp(ent->base, alt->base, pfxlen)) {
- free(ent);
- return -1;
- }
- }
- if (!strcmp(ent->base, objdir)) {
- free(ent);
- return -1;
- }
+ ent = alloc_alt_odb(pathbuf.buf);
/* add the alternate entry */
*alt_odb_tail = ent;
ent->next = NULL;
/* recursively add alternates */
- read_info_alternates(ent->base, depth + 1);
-
- ent->base[pfxlen] = '/';
+ read_info_alternates(pathbuf.buf, depth + 1);
+ strbuf_release(&pathbuf);
return 0;
}
-static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
+static const char *parse_alt_odb_entry(const char *string,
+ int sep,
+ struct strbuf *out)
+{
+ const char *end;
+
+ strbuf_reset(out);
+
+ if (*string == '#') {
+ /* comment; consume up to next separator */
+ end = strchrnul(string, sep);
+ } else if (*string == '"' && !unquote_c_style(out, string, &end)) {
+ /*
+ * quoted path; unquote_c_style has copied the
+ * data for us and set "end". Broken quoting (e.g.,
+ * an entry that doesn't end with a quote) falls
+ * back to the unquoted case below.
+ */
+ } else {
+ /* normal, unquoted path */
+ end = strchrnul(string, sep);
+ strbuf_add(out, string, end - string);
+ }
+
+ if (*end)
+ end++;
+ return end;
+}
+
+static void link_alt_odb_entries(const char *alt, int sep,
const char *relative_base, int depth)
{
- const char *cp, *last;
+ struct strbuf objdirbuf = STRBUF_INIT;
+ struct strbuf entry = STRBUF_INIT;
+
+ if (!alt || !*alt)
+ return;
if (depth > 5) {
error("%s: ignoring alternate object stores, nesting too deep.",
return;
}
- last = alt;
- while (last < ep) {
- cp = last;
- if (cp < ep && *cp == '#') {
- while (cp < ep && *cp != sep)
- cp++;
- last = cp + 1;
+ strbuf_add_absolute_path(&objdirbuf, get_object_directory());
+ if (strbuf_normalize_path(&objdirbuf) < 0)
+ die("unable to normalize object directory: %s",
+ objdirbuf.buf);
+
+ while (*alt) {
+ alt = parse_alt_odb_entry(alt, sep, &entry);
+ if (!entry.len)
continue;
- }
- while (cp < ep && *cp != sep)
- cp++;
- if (last != cp) {
- if (!is_absolute_path(last) && depth) {
- error("%s: ignoring relative alternate object store %s",
- relative_base, last);
- } else {
- link_alt_odb_entry(last, cp - last,
- relative_base, depth);
- }
- }
- while (cp < ep && *cp == sep)
- cp++;
- last = cp;
+ link_alt_odb_entry(entry.buf, relative_base, depth, objdirbuf.buf);
}
+ strbuf_release(&entry);
+ strbuf_release(&objdirbuf);
}
-void read_info_alternates(const char * relative_base, int depth)
+static void read_info_alternates(const char * relative_base, int depth)
{
- char *map;
- size_t mapsz;
- struct stat st;
- const char alt_file_name[] = "info/alternates";
- /* Given that relative_base is no longer than PATH_MAX,
- ensure that "path" has enough space to append "/", the
- file name, "info/alternates", and a trailing NUL. */
- char path[PATH_MAX + 1 + sizeof alt_file_name];
- int fd;
+ char *path;
+ struct strbuf buf = STRBUF_INIT;
- sprintf(path, "%s/%s", relative_base, alt_file_name);
- fd = git_open_noatime(path);
- if (fd < 0)
- return;
- if (fstat(fd, &st) || (st.st_size == 0)) {
- close(fd);
+ path = xstrfmt("%s/info/alternates", relative_base);
+ if (strbuf_read_file(&buf, path, 1024) < 0) {
+ warn_on_fopen_errors(path);
+ free(path);
return;
}
- mapsz = xsize_t(st.st_size);
- map = xmmap(NULL, mapsz, PROT_READ, MAP_PRIVATE, fd, 0);
- close(fd);
- link_alt_odb_entries(map, map + mapsz, '\n', relative_base, depth);
+ link_alt_odb_entries(buf.buf, '\n', relative_base, depth);
+ strbuf_release(&buf);
+ free(path);
+}
+
+struct alternate_object_database *alloc_alt_odb(const char *dir)
+{
+ struct alternate_object_database *ent;
+
+ FLEX_ALLOC_STR(ent, path, dir);
+ strbuf_init(&ent->scratch, 0);
+ strbuf_addf(&ent->scratch, "%s/", dir);
+ ent->base_len = ent->scratch.len;
- munmap(map, mapsz);
+ return ent;
}
void add_to_alternates_file(const char *reference)
{
- struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
- int fd = hold_lock_file_for_append(lock, git_path("objects/info/alternates"), LOCK_DIE_ON_ERROR);
- char *alt = mkpath("%s\n", reference);
- write_or_die(fd, alt, strlen(alt));
- if (commit_lock_file(lock))
- die("could not close alternates file");
- if (alt_odb_tail)
- link_alt_odb_entries(alt, alt + strlen(alt), '\n', NULL, 0);
+ struct lock_file lock = LOCK_INIT;
+ char *alts = git_pathdup("objects/info/alternates");
+ FILE *in, *out;
+ int found = 0;
+
+ hold_lock_file_for_update(&lock, alts, LOCK_DIE_ON_ERROR);
+ out = fdopen_lock_file(&lock, "w");
+ if (!out)
+ die_errno("unable to fdopen alternates lockfile");
+
+ in = fopen(alts, "r");
+ if (in) {
+ struct strbuf line = STRBUF_INIT;
+
+ while (strbuf_getline(&line, in) != EOF) {
+ if (!strcmp(reference, line.buf)) {
+ found = 1;
+ break;
+ }
+ fprintf_or_die(out, "%s\n", line.buf);
+ }
+
+ strbuf_release(&line);
+ fclose(in);
+ }
+ else if (errno != ENOENT)
+ die_errno("unable to read alternates file");
+
+ if (found) {
+ rollback_lock_file(&lock);
+ } else {
+ fprintf_or_die(out, "%s\n", reference);
+ if (commit_lock_file(&lock))
+ die_errno("unable to move new alternates file into place");
+ if (alt_odb_tail)
+ link_alt_odb_entries(reference, '\n', NULL, 0);
+ }
+ free(alts);
+}
+
+void add_to_alternates_memory(const char *reference)
+{
+ /*
+ * Make sure alternates are initialized, or else our entry may be
+ * overwritten when they are.
+ */
+ prepare_alt_odb();
+
+ link_alt_odb_entries(reference, '\n', NULL, 0);
+}
+
+/*
+ * Compute the exact path an alternate is at and returns it. In case of
+ * error NULL is returned and the human readable error is added to `err`
+ * `path` may be relative and should point to $GITDIR.
+ * `err` must not be null.
+ */
+char *compute_alternate_path(const char *path, struct strbuf *err)
+{
+ char *ref_git = NULL;
+ const char *repo, *ref_git_s;
+ int seen_error = 0;
+
+ ref_git_s = real_path_if_valid(path);
+ if (!ref_git_s) {
+ seen_error = 1;
+ strbuf_addf(err, _("path '%s' does not exist"), path);
+ goto out;
+ } else
+ /*
+ * Beware: read_gitfile(), real_path() and mkpath()
+ * return static buffer
+ */
+ ref_git = xstrdup(ref_git_s);
+
+ repo = read_gitfile(ref_git);
+ if (!repo)
+ repo = read_gitfile(mkpath("%s/.git", ref_git));
+ if (repo) {
+ free(ref_git);
+ ref_git = xstrdup(repo);
+ }
+
+ if (!repo && is_directory(mkpath("%s/.git/objects", ref_git))) {
+ char *ref_git_git = mkpathdup("%s/.git", ref_git);
+ free(ref_git);
+ ref_git = ref_git_git;
+ } else if (!is_directory(mkpath("%s/objects", ref_git))) {
+ struct strbuf sb = STRBUF_INIT;
+ seen_error = 1;
+ if (get_common_dir(&sb, ref_git)) {
+ strbuf_addf(err,
+ _("reference repository '%s' as a linked "
+ "checkout is not supported yet."),
+ path);
+ goto out;
+ }
+
+ strbuf_addf(err, _("reference repository '%s' is not a "
+ "local repository."), path);
+ goto out;
+ }
+
+ if (!access(mkpath("%s/shallow", ref_git), F_OK)) {
+ strbuf_addf(err, _("reference repository '%s' is shallow"),
+ path);
+ seen_error = 1;
+ goto out;
+ }
+
+ if (!access(mkpath("%s/info/grafts", ref_git), F_OK)) {
+ strbuf_addf(err,
+ _("reference repository '%s' is grafted"),
+ path);
+ seen_error = 1;
+ goto out;
+ }
+
+out:
+ if (seen_error) {
+ FREE_AND_NULL(ref_git);
+ }
+
+ return ref_git;
}
-void foreach_alt_odb(alt_odb_fn fn, void *cb)
+int foreach_alt_odb(alt_odb_fn fn, void *cb)
{
struct alternate_object_database *ent;
+ int r = 0;
prepare_alt_odb();
- for (ent = alt_odb_list; ent; ent = ent->next)
- if (fn(ent, cb))
- return;
+ for (ent = alt_odb_list; ent; ent = ent->next) {
+ r = fn(ent, cb);
+ if (r)
+ break;
+ }
+ return r;
}
void prepare_alt_odb(void)
return;
alt = getenv(ALTERNATE_DB_ENVIRONMENT);
- if (!alt) alt = "";
alt_odb_tail = &alt_odb_list;
- link_alt_odb_entries(alt, alt + strlen(alt), PATH_SEP, NULL, 0);
+ link_alt_odb_entries(alt, PATH_SEP, NULL, 0);
read_info_alternates(get_object_directory(), 0);
}
-static int has_loose_object_local(const unsigned char *sha1)
+/* Returns 1 if we have successfully freshened the file, 0 otherwise. */
+static int freshen_file(const char *fn)
{
- char *name = sha1_file_name(sha1);
- return !access(name, F_OK);
+ struct utimbuf t;
+ t.actime = t.modtime = time(NULL);
+ return !utime(fn, &t);
}
-int has_loose_object_nonlocal(const unsigned char *sha1)
+/*
+ * All of the check_and_freshen functions return 1 if the file exists and was
+ * freshened (if freshening was requested), 0 otherwise. If they return
+ * 0, you should not assume that it is safe to skip a write of the object (it
+ * either does not exist on disk, or has a stale mtime and may be subject to
+ * pruning).
+ */
+int check_and_freshen_file(const char *fn, int freshen)
+{
+ if (access(fn, F_OK))
+ return 0;
+ if (freshen && !freshen_file(fn))
+ return 0;
+ return 1;
+}
+
+static int check_and_freshen_local(const unsigned char *sha1, int freshen)
+{
+ return check_and_freshen_file(sha1_file_name(sha1), freshen);
+}
+
+static int check_and_freshen_nonlocal(const unsigned char *sha1, int freshen)
{
struct alternate_object_database *alt;
prepare_alt_odb();
for (alt = alt_odb_list; alt; alt = alt->next) {
- fill_sha1_path(alt->name, sha1);
- if (!access(alt->base, F_OK))
+ const char *path = alt_sha1_path(alt, sha1);
+ if (check_and_freshen_file(path, freshen))
return 1;
}
return 0;
}
-static int has_loose_object(const unsigned char *sha1)
+static int check_and_freshen(const unsigned char *sha1, int freshen)
{
- return has_loose_object_local(sha1) ||
- has_loose_object_nonlocal(sha1);
-}
-
-static unsigned int pack_used_ctr;
-static unsigned int pack_mmap_calls;
-static unsigned int peak_pack_open_windows;
-static unsigned int pack_open_windows;
-static unsigned int pack_open_fds;
-static unsigned int pack_max_fds;
-static size_t peak_pack_mapped;
-static size_t pack_mapped;
-struct packed_git *packed_git;
-
-void pack_report(void)
-{
- fprintf(stderr,
- "pack_report: getpagesize() = %10" SZ_FMT "\n"
- "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n"
- "pack_report: core.packedGitLimit = %10" SZ_FMT "\n",
- sz_fmt(getpagesize()),
- sz_fmt(packed_git_window_size),
- sz_fmt(packed_git_limit));
- fprintf(stderr,
- "pack_report: pack_used_ctr = %10u\n"
- "pack_report: pack_mmap_calls = %10u\n"
- "pack_report: pack_open_windows = %10u / %10u\n"
- "pack_report: pack_mapped = "
- "%10" SZ_FMT " / %10" SZ_FMT "\n",
- pack_used_ctr,
- pack_mmap_calls,
- pack_open_windows, peak_pack_open_windows,
- sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped));
-}
-
-static int check_packed_git_idx(const char *path, struct packed_git *p)
-{
- void *idx_map;
- struct pack_idx_header *hdr;
- size_t idx_size;
- uint32_t version, nr, i, *index;
- int fd = git_open_noatime(path);
- struct stat st;
-
- if (fd < 0)
- return -1;
- if (fstat(fd, &st)) {
- close(fd);
- return -1;
- }
- idx_size = xsize_t(st.st_size);
- if (idx_size < 4 * 256 + 20 + 20) {
- close(fd);
- return error("index file %s is too small", path);
- }
- idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0);
- close(fd);
-
- hdr = idx_map;
- if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) {
- version = ntohl(hdr->idx_version);
- if (version < 2 || version > 2) {
- munmap(idx_map, idx_size);
- return error("index file %s is version %"PRIu32
- " and is not supported by this binary"
- " (try upgrading GIT to a newer version)",
- path, version);
- }
- } else
- version = 1;
-
- nr = 0;
- index = idx_map;
- if (version > 1)
- index += 2; /* skip index header */
- for (i = 0; i < 256; i++) {
- uint32_t n = ntohl(index[i]);
- if (n < nr) {
- munmap(idx_map, idx_size);
- return error("non-monotonic index %s", path);
- }
- nr = n;
- }
-
- if (version == 1) {
- /*
- * Total size:
- * - 256 index entries 4 bytes each
- * - 24-byte entries * nr (20-byte sha1 + 4-byte offset)
- * - 20-byte SHA1 of the packfile
- * - 20-byte SHA1 file checksum
- */
- if (idx_size != 4*256 + nr * 24 + 20 + 20) {
- munmap(idx_map, idx_size);
- return error("wrong index v1 file size in %s", path);
- }
- } else if (version == 2) {
- /*
- * Minimum size:
- * - 8 bytes of header
- * - 256 index entries 4 bytes each
- * - 20-byte sha1 entry * nr
- * - 4-byte crc entry * nr
- * - 4-byte offset entry * nr
- * - 20-byte SHA1 of the packfile
- * - 20-byte SHA1 file checksum
- * And after the 4-byte offset table might be a
- * variable sized table containing 8-byte entries
- * for offsets larger than 2^31.
- */
- unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20;
- unsigned long max_size = min_size;
- if (nr)
- max_size += (nr - 1)*8;
- if (idx_size < min_size || idx_size > max_size) {
- munmap(idx_map, idx_size);
- return error("wrong index v2 file size in %s", path);
- }
- if (idx_size != min_size &&
- /*
- * make sure we can deal with large pack offsets.
- * 31-bit signed offset won't be enough, neither
- * 32-bit unsigned one will be.
- */
- (sizeof(off_t) <= 4)) {
- munmap(idx_map, idx_size);
- return error("pack too large for current definition of off_t in %s", path);
- }
- }
-
- p->index_version = version;
- p->index_data = idx_map;
- p->index_size = idx_size;
- p->num_objects = nr;
- return 0;
+ return check_and_freshen_local(sha1, freshen) ||
+ check_and_freshen_nonlocal(sha1, freshen);
}
-int open_pack_index(struct packed_git *p)
+int has_loose_object_nonlocal(const unsigned char *sha1)
{
- char *idx_name;
- int ret;
-
- if (p->index_data)
- return 0;
-
- idx_name = xstrdup(p->pack_name);
- strcpy(idx_name + strlen(idx_name) - strlen(".pack"), ".idx");
- ret = check_packed_git_idx(idx_name, p);
- free(idx_name);
- return ret;
+ return check_and_freshen_nonlocal(sha1, 0);
}
-static void scan_windows(struct packed_git *p,
- struct packed_git **lru_p,
- struct pack_window **lru_w,
- struct pack_window **lru_l)
+static int has_loose_object(const unsigned char *sha1)
{
- struct pack_window *w, *w_l;
-
- for (w_l = NULL, w = p->windows; w; w = w->next) {
- if (!w->inuse_cnt) {
- if (!*lru_w || w->last_used < (*lru_w)->last_used) {
- *lru_p = p;
- *lru_w = w;
- *lru_l = w_l;
- }
- }
- w_l = w;
- }
+ return check_and_freshen(sha1, 0);
}
-static int unuse_one_window(struct packed_git *current, int keep_fd)
+static void mmap_limit_check(size_t length)
{
- struct packed_git *p, *lru_p = NULL;
- struct pack_window *lru_w = NULL, *lru_l = NULL;
-
- if (current)
- scan_windows(current, &lru_p, &lru_w, &lru_l);
- for (p = packed_git; p; p = p->next)
- scan_windows(p, &lru_p, &lru_w, &lru_l);
- if (lru_p) {
- munmap(lru_w->base, lru_w->len);
- pack_mapped -= lru_w->len;
- if (lru_l)
- lru_l->next = lru_w->next;
- else {
- lru_p->windows = lru_w->next;
- if (!lru_p->windows && lru_p->pack_fd != -1
- && lru_p->pack_fd != keep_fd) {
- close(lru_p->pack_fd);
- pack_open_fds--;
- lru_p->pack_fd = -1;
- }
- }
- free(lru_w);
- pack_open_windows--;
- return 1;
+ static size_t limit = 0;
+ if (!limit) {
+ limit = git_env_ulong("GIT_MMAP_LIMIT", 0);
+ if (!limit)
+ limit = SIZE_MAX;
}
- return 0;
+ if (length > limit)
+ die("attempting to mmap %"PRIuMAX" over limit %"PRIuMAX,
+ (uintmax_t)length, (uintmax_t)limit);
}
-void release_pack_memory(size_t need, int fd)
+void *xmmap_gently(void *start, size_t length,
+ int prot, int flags, int fd, off_t offset)
{
- size_t cur = pack_mapped;
- while (need >= (cur - pack_mapped) && unuse_one_window(NULL, fd))
- ; /* nothing */
-}
+ void *ret;
-void *xmmap(void *start, size_t length,
- int prot, int flags, int fd, off_t offset)
-{
- void *ret = mmap(start, length, prot, flags, fd, offset);
+ mmap_limit_check(length);
+ ret = mmap(start, length, prot, flags, fd, offset);
if (ret == MAP_FAILED) {
if (!length)
return NULL;
- release_pack_memory(length, fd);
+ release_pack_memory(length);
ret = mmap(start, length, prot, flags, fd, offset);
- if (ret == MAP_FAILED)
- die_errno("Out of memory? mmap failed");
}
return ret;
}
-void close_pack_windows(struct packed_git *p)
+void *xmmap(void *start, size_t length,
+ int prot, int flags, int fd, off_t offset)
{
- while (p->windows) {
- struct pack_window *w = p->windows;
-
- if (w->inuse_cnt)
- die("pack '%s' still has open windows to it",
- p->pack_name);
- munmap(w->base, w->len);
- pack_mapped -= w->len;
- pack_open_windows--;
- p->windows = w->next;
- free(w);
- }
-}
-
-void unuse_pack(struct pack_window **w_cursor)
-{
- struct pack_window *w = *w_cursor;
- if (w) {
- w->inuse_cnt--;
- *w_cursor = NULL;
- }
-}
-
-void close_pack_index(struct packed_git *p)
-{
- if (p->index_data) {
- munmap((void *)p->index_data, p->index_size);
- p->index_data = NULL;
- }
-}
-
-/*
- * This is used by git-repack in case a newly created pack happens to
- * contain the same set of objects as an existing one. In that case
- * the resulting file might be different even if its name would be the
- * same. It is best to close any reference to the old pack before it is
- * replaced on disk. Of course no index pointers nor windows for given pack
- * must subsist at this point. If ever objects from this pack are requested
- * again, the new version of the pack will be reinitialized through
- * reprepare_packed_git().
- */
-void free_pack_by_name(const char *pack_name)
-{
- struct packed_git *p, **pp = &packed_git;
-
- while (*pp) {
- p = *pp;
- if (strcmp(pack_name, p->pack_name) == 0) {
- clear_delta_base_cache();
- close_pack_windows(p);
- if (p->pack_fd != -1) {
- close(p->pack_fd);
- pack_open_fds--;
- }
- close_pack_index(p);
- free(p->bad_object_sha1);
- *pp = p->next;
- if (last_found_pack == p)
- last_found_pack = NULL;
- free(p);
- return;
- }
- pp = &p->next;
- }
-}
-
-static unsigned int get_max_fd_limit(void)
-{
-#ifdef RLIMIT_NOFILE
- struct rlimit lim;
-
- if (getrlimit(RLIMIT_NOFILE, &lim))
- die_errno("cannot get RLIMIT_NOFILE");
-
- return lim.rlim_cur;
-#elif defined(_SC_OPEN_MAX)
- return sysconf(_SC_OPEN_MAX);
-#elif defined(OPEN_MAX)
- return OPEN_MAX;
-#else
- return 1; /* see the caller ;-) */
-#endif
-}
-
-/*
- * Do not call this directly as this leaks p->pack_fd on error return;
- * call open_packed_git() instead.
- */
-static int open_packed_git_1(struct packed_git *p)
-{
- struct stat st;
- struct pack_header hdr;
- unsigned char sha1[20];
- unsigned char *idx_sha1;
- long fd_flag;
-
- if (!p->index_data && open_pack_index(p))
- return error("packfile %s index unavailable", p->pack_name);
-
- if (!pack_max_fds) {
- unsigned int max_fds = get_max_fd_limit();
-
- /* Save 3 for stdin/stdout/stderr, 22 for work */
- if (25 < max_fds)
- pack_max_fds = max_fds - 25;
- else
- pack_max_fds = 1;
- }
-
- while (pack_max_fds <= pack_open_fds && unuse_one_window(NULL, -1))
- ; /* nothing */
-
- p->pack_fd = git_open_noatime(p->pack_name);
- if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
- return -1;
- pack_open_fds++;
-
- /* If we created the struct before we had the pack we lack size. */
- if (!p->pack_size) {
- if (!S_ISREG(st.st_mode))
- return error("packfile %s not a regular file", p->pack_name);
- p->pack_size = st.st_size;
- } else if (p->pack_size != st.st_size)
- return error("packfile %s size changed", p->pack_name);
-
- /* We leave these file descriptors open with sliding mmap;
- * there is no point keeping them open across exec(), though.
- */
- fd_flag = fcntl(p->pack_fd, F_GETFD, 0);
- if (fd_flag < 0)
- return error("cannot determine file descriptor flags");
- fd_flag |= FD_CLOEXEC;
- if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1)
- return error("cannot set FD_CLOEXEC");
-
- /* Verify we recognize this pack file format. */
- if (read_in_full(p->pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr))
- return error("file %s is far too short to be a packfile", p->pack_name);
- if (hdr.hdr_signature != htonl(PACK_SIGNATURE))
- return error("file %s is not a GIT packfile", p->pack_name);
- if (!pack_version_ok(hdr.hdr_version))
- return error("packfile %s is version %"PRIu32" and not"
- " supported (try upgrading GIT to a newer version)",
- p->pack_name, ntohl(hdr.hdr_version));
-
- /* Verify the pack matches its index. */
- if (p->num_objects != ntohl(hdr.hdr_entries))
- return error("packfile %s claims to have %"PRIu32" objects"
- " while index indicates %"PRIu32" objects",
- p->pack_name, ntohl(hdr.hdr_entries),
- p->num_objects);
- if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1)
- return error("end of packfile %s is unavailable", p->pack_name);
- if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1))
- return error("packfile %s signature is unavailable", p->pack_name);
- idx_sha1 = ((unsigned char *)p->index_data) + p->index_size - 40;
- if (hashcmp(sha1, idx_sha1))
- return error("packfile %s does not match index", p->pack_name);
- return 0;
-}
-
-static int open_packed_git(struct packed_git *p)
-{
- if (!open_packed_git_1(p))
- return 0;
- if (p->pack_fd != -1) {
- close(p->pack_fd);
- pack_open_fds--;
- p->pack_fd = -1;
- }
- return -1;
-}
-
-static int in_window(struct pack_window *win, off_t offset)
-{
- /* We must promise at least 20 bytes (one hash) after the
- * offset is available from this window, otherwise the offset
- * is not actually in this window and a different window (which
- * has that one hash excess) must be used. This is to support
- * the object header and delta base parsing routines below.
- */
- off_t win_off = win->offset;
- return win_off <= offset
- && (offset + 20) <= (win_off + win->len);
-}
-
-unsigned char *use_pack(struct packed_git *p,
- struct pack_window **w_cursor,
- off_t offset,
- unsigned long *left)
-{
- struct pack_window *win = *w_cursor;
-
- /* Since packfiles end in a hash of their content and it's
- * pointless to ask for an offset into the middle of that
- * hash, and the in_window function above wouldn't match
- * don't allow an offset too close to the end of the file.
- */
- if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p))
- die("packfile %s cannot be accessed", p->pack_name);
- if (offset > (p->pack_size - 20))
- die("offset beyond end of packfile (truncated pack?)");
-
- if (!win || !in_window(win, offset)) {
- if (win)
- win->inuse_cnt--;
- for (win = p->windows; win; win = win->next) {
- if (in_window(win, offset))
- break;
- }
- if (!win) {
- size_t window_align = packed_git_window_size / 2;
- off_t len;
-
- if (p->pack_fd == -1 && open_packed_git(p))
- die("packfile %s cannot be accessed", p->pack_name);
-
- win = xcalloc(1, sizeof(*win));
- win->offset = (offset / window_align) * window_align;
- len = p->pack_size - win->offset;
- if (len > packed_git_window_size)
- len = packed_git_window_size;
- win->len = (size_t)len;
- pack_mapped += win->len;
- while (packed_git_limit < pack_mapped
- && unuse_one_window(p, p->pack_fd))
- ; /* nothing */
- win->base = xmmap(NULL, win->len,
- PROT_READ, MAP_PRIVATE,
- p->pack_fd, win->offset);
- if (win->base == MAP_FAILED)
- die("packfile %s cannot be mapped: %s",
- p->pack_name,
- strerror(errno));
- if (!win->offset && win->len == p->pack_size
- && !p->do_not_close) {
- close(p->pack_fd);
- pack_open_fds--;
- p->pack_fd = -1;
- }
- pack_mmap_calls++;
- pack_open_windows++;
- if (pack_mapped > peak_pack_mapped)
- peak_pack_mapped = pack_mapped;
- if (pack_open_windows > peak_pack_open_windows)
- peak_pack_open_windows = pack_open_windows;
- win->next = p->windows;
- p->windows = win;
- }
- }
- if (win != *w_cursor) {
- win->last_used = pack_used_ctr++;
- win->inuse_cnt++;
- *w_cursor = win;
- }
- offset -= win->offset;
- if (left)
- *left = win->len - xsize_t(offset);
- return win->base + offset;
-}
-
-static struct packed_git *alloc_packed_git(int extra)
-{
- struct packed_git *p = xmalloc(sizeof(*p) + extra);
- memset(p, 0, sizeof(*p));
- p->pack_fd = -1;
- return p;
-}
-
-static void try_to_free_pack_memory(size_t size)
-{
- release_pack_memory(size, -1);
-}
-
-struct packed_git *add_packed_git(const char *path, int path_len, int local)
-{
- static int have_set_try_to_free_routine;
- struct stat st;
- struct packed_git *p = alloc_packed_git(path_len + 2);
-
- if (!have_set_try_to_free_routine) {
- have_set_try_to_free_routine = 1;
- set_try_to_free_routine(try_to_free_pack_memory);
- }
-
- /*
- * Make sure a corresponding .pack file exists and that
- * the index looks sane.
- */
- path_len -= strlen(".idx");
- if (path_len < 1) {
- free(p);
- return NULL;
- }
- memcpy(p->pack_name, path, path_len);
-
- strcpy(p->pack_name + path_len, ".keep");
- if (!access(p->pack_name, F_OK))
- p->pack_keep = 1;
-
- strcpy(p->pack_name + path_len, ".pack");
- if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
- free(p);
- return NULL;
- }
-
- /* ok, it looks sane as far as we can check without
- * actually mapping the pack file.
- */
- p->pack_size = st.st_size;
- p->pack_local = local;
- p->mtime = st.st_mtime;
- if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1))
- hashclr(p->sha1);
- return p;
-}
-
-struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
-{
- const char *path = sha1_pack_name(sha1);
- struct packed_git *p = alloc_packed_git(strlen(path) + 1);
-
- strcpy(p->pack_name, path);
- hashcpy(p->sha1, sha1);
- if (check_packed_git_idx(idx_path, p)) {
- free(p);
- return NULL;
- }
-
- return p;
-}
-
-void install_packed_git(struct packed_git *pack)
-{
- if (pack->pack_fd != -1)
- pack_open_fds++;
-
- pack->next = packed_git;
- packed_git = pack;
-}
-
-static void prepare_packed_git_one(char *objdir, int local)
-{
- /* Ensure that this buffer is large enough so that we can
- append "/pack/" without clobbering the stack even if
- strlen(objdir) were PATH_MAX. */
- char path[PATH_MAX + 1 + 4 + 1 + 1];
- int len;
- DIR *dir;
- struct dirent *de;
-
- sprintf(path, "%s/pack", objdir);
- len = strlen(path);
- dir = opendir(path);
- if (!dir) {
- if (errno != ENOENT)
- error("unable to open object pack directory: %s: %s",
- path, strerror(errno));
- return;
- }
- path[len++] = '/';
- while ((de = readdir(dir)) != NULL) {
- int namelen = strlen(de->d_name);
- struct packed_git *p;
-
- if (!has_extension(de->d_name, ".idx"))
- continue;
-
- if (len + namelen + 1 > sizeof(path))
- continue;
-
- /* Don't reopen a pack we already have. */
- strcpy(path + len, de->d_name);
- for (p = packed_git; p; p = p->next) {
- if (!memcmp(path, p->pack_name, len + namelen - 4))
- break;
- }
- if (p)
- continue;
- /* See if it really is a valid .idx file with corresponding
- * .pack file that we can map.
- */
- p = add_packed_git(path, len + namelen, local);
- if (!p)
- continue;
- install_packed_git(p);
- }
- closedir(dir);
-}
-
-static int sort_pack(const void *a_, const void *b_)
-{
- struct packed_git *a = *((struct packed_git **)a_);
- struct packed_git *b = *((struct packed_git **)b_);
- int st;
-
- /*
- * Local packs tend to contain objects specific to our
- * variant of the project than remote ones. In addition,
- * remote ones could be on a network mounted filesystem.
- * Favor local ones for these reasons.
- */
- st = a->pack_local - b->pack_local;
- if (st)
- return -st;
-
- /*
- * Younger packs tend to contain more recent objects,
- * and more recent objects tend to get accessed more
- * often.
- */
- if (a->mtime < b->mtime)
- return 1;
- else if (a->mtime == b->mtime)
- return 0;
- return -1;
-}
-
-static void rearrange_packed_git(void)
-{
- struct packed_git **ary, *p;
- int i, n;
-
- for (n = 0, p = packed_git; p; p = p->next)
- n++;
- if (n < 2)
- return;
-
- /* prepare an array of packed_git for easier sorting */
- ary = xcalloc(n, sizeof(struct packed_git *));
- for (n = 0, p = packed_git; p; p = p->next)
- ary[n++] = p;
-
- qsort(ary, n, sizeof(struct packed_git *), sort_pack);
-
- /* link them back again */
- for (i = 0; i < n - 1; i++)
- ary[i]->next = ary[i + 1];
- ary[n - 1]->next = NULL;
- packed_git = ary[0];
-
- free(ary);
-}
-
-static int prepare_packed_git_run_once = 0;
-void prepare_packed_git(void)
-{
- struct alternate_object_database *alt;
-
- if (prepare_packed_git_run_once)
- return;
- prepare_packed_git_one(get_object_directory(), 1);
- prepare_alt_odb();
- for (alt = alt_odb_list; alt; alt = alt->next) {
- alt->name[-1] = 0;
- prepare_packed_git_one(alt->base, 0);
- alt->name[-1] = '/';
- }
- rearrange_packed_git();
- prepare_packed_git_run_once = 1;
-}
-
-void reprepare_packed_git(void)
-{
- discard_revindex();
- prepare_packed_git_run_once = 0;
- prepare_packed_git();
-}
-
-static void mark_bad_packed_object(struct packed_git *p,
- const unsigned char *sha1)
-{
- unsigned i;
- for (i = 0; i < p->num_bad_objects; i++)
- if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
- return;
- p->bad_object_sha1 = xrealloc(p->bad_object_sha1, 20 * (p->num_bad_objects + 1));
- hashcpy(p->bad_object_sha1 + 20 * p->num_bad_objects, sha1);
- p->num_bad_objects++;
-}
-
-static const struct packed_git *has_packed_and_bad(const unsigned char *sha1)
-{
- struct packed_git *p;
- unsigned i;
-
- for (p = packed_git; p; p = p->next)
- for (i = 0; i < p->num_bad_objects; i++)
- if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
- return p;
- return NULL;
+ void *ret = xmmap_gently(start, length, prot, flags, fd, offset);
+ if (ret == MAP_FAILED)
+ die_errno("mmap failed");
+ return ret;
}
/*
return -1;
/* Generate the header */
- hdrlen = sprintf(hdr, "%s %lu", typename(obj_type), size) + 1;
+ hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(obj_type), size) + 1;
/* Sha1.. */
git_SHA1_Init(&c);
char buf[1024 * 16];
ssize_t readlen = read_istream(st, buf, sizeof(buf));
+ if (readlen < 0) {
+ close_istream(st);
+ return -1;
+ }
if (!readlen)
break;
git_SHA1_Update(&c, buf, readlen);
return hashcmp(sha1, real_sha1) ? -1 : 0;
}
-static int git_open_noatime(const char *name)
+int git_open_cloexec(const char *name, int flags)
{
- static int sha1_file_open_flag = O_NOATIME;
+ int fd;
+ static int o_cloexec = O_CLOEXEC;
- for (;;) {
- int fd = open(name, O_RDONLY | sha1_file_open_flag);
- if (fd >= 0)
- return fd;
+ fd = open(name, flags | o_cloexec);
+ if ((o_cloexec & O_CLOEXEC) && fd < 0 && errno == EINVAL) {
+ /* Try again w/o O_CLOEXEC: the kernel might not support it */
+ o_cloexec &= ~O_CLOEXEC;
+ fd = open(name, flags | o_cloexec);
+ }
- /* Might the failure be due to O_NOATIME? */
- if (errno != ENOENT && sha1_file_open_flag) {
- sha1_file_open_flag = 0;
- continue;
+#if defined(F_GETFD) && defined(F_SETFD) && defined(FD_CLOEXEC)
+ {
+ static int fd_cloexec = FD_CLOEXEC;
+
+ if (!o_cloexec && 0 <= fd && fd_cloexec) {
+ /* Opened w/o O_CLOEXEC? try with fcntl(2) to add it */
+ int flags = fcntl(fd, F_GETFD);
+ if (fcntl(fd, F_SETFD, flags | fd_cloexec))
+ fd_cloexec = 0;
}
+ }
+#endif
+ return fd;
+}
- return -1;
+/*
+ * Find "sha1" as a loose object in the local repository or in an alternate.
+ * Returns 0 on success, negative on failure.
+ *
+ * The "path" out-parameter will give the path of the object we found (if any).
+ * Note that it may point to static storage and is only valid until another
+ * call to sha1_file_name(), etc.
+ */
+static int stat_sha1_file(const unsigned char *sha1, struct stat *st,
+ const char **path)
+{
+ struct alternate_object_database *alt;
+
+ *path = sha1_file_name(sha1);
+ if (!lstat(*path, st))
+ return 0;
+
+ prepare_alt_odb();
+ errno = ENOENT;
+ for (alt = alt_odb_list; alt; alt = alt->next) {
+ *path = alt_sha1_path(alt, sha1);
+ if (!lstat(*path, st))
+ return 0;
}
+
+ return -1;
}
-static int open_sha1_file(const unsigned char *sha1)
+/*
+ * Like stat_sha1_file(), but actually open the object and return the
+ * descriptor. See the caveats on the "path" parameter above.
+ */
+static int open_sha1_file(const unsigned char *sha1, const char **path)
{
int fd;
- char *name = sha1_file_name(sha1);
struct alternate_object_database *alt;
+ int most_interesting_errno;
- fd = git_open_noatime(name);
+ *path = sha1_file_name(sha1);
+ fd = git_open(*path);
if (fd >= 0)
return fd;
+ most_interesting_errno = errno;
prepare_alt_odb();
- errno = ENOENT;
for (alt = alt_odb_list; alt; alt = alt->next) {
- name = alt->name;
- fill_sha1_path(name, sha1);
- fd = git_open_noatime(alt->base);
+ *path = alt_sha1_path(alt, sha1);
+ fd = git_open(*path);
if (fd >= 0)
return fd;
+ if (most_interesting_errno == ENOENT)
+ most_interesting_errno = errno;
}
+ errno = most_interesting_errno;
return -1;
}
-void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
+/*
+ * Map the loose object at "path" if it is not NULL, or the path found by
+ * searching for a loose object named "sha1".
+ */
+static void *map_sha1_file_1(const char *path,
+ const unsigned char *sha1,
+ unsigned long *size)
{
void *map;
int fd;
- fd = open_sha1_file(sha1);
+ if (path)
+ fd = git_open(path);
+ else
+ fd = open_sha1_file(sha1, &path);
map = NULL;
if (fd >= 0) {
struct stat st;
*size = xsize_t(st.st_size);
if (!*size) {
/* mmap() is forbidden on empty files */
- error("object file %s is empty", sha1_file_name(sha1));
+ error("object file %s is empty", path);
return NULL;
}
map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0);
return map;
}
-/*
- * There used to be a second loose object header format which
- * was meant to mimic the in-pack format, allowing for direct
- * copy of the object data. This format turned up not to be
- * really worth it and we no longer write loose objects in that
- * format.
- */
-static int experimental_loose_object(unsigned char *map)
-{
- unsigned int word;
-
- /*
- * We must determine if the buffer contains the standard
- * zlib-deflated stream or the experimental format based
- * on the in-pack object format. Compare the header byte
- * for each format:
- *
- * RFC1950 zlib w/ deflate : 0www1000 : 0 <= www <= 7
- * Experimental pack-based : Stttssss : ttt = 1,2,3,4
- *
- * If bit 7 is clear and bits 0-3 equal 8, the buffer MUST be
- * in standard loose-object format, UNLESS it is a Git-pack
- * format object *exactly* 8 bytes in size when inflated.
- *
- * However, RFC1950 also specifies that the 1st 16-bit word
- * must be divisible by 31 - this checksum tells us our buffer
- * is in the standard format, giving a false positive only if
- * the 1st word of the Git-pack format object happens to be
- * divisible by 31, ie:
- * ((byte0 * 256) + byte1) % 31 = 0
- * => 0ttt10000www1000 % 31 = 0
- *
- * As it happens, this case can only arise for www=3 & ttt=1
- * - ie, a Commit object, which would have to be 8 bytes in
- * size. As no Commit can be that small, we find that the
- * combination of these two criteria (bitmask & checksum)
- * can always correctly determine the buffer format.
- */
- word = (map[0] << 8) + map[1];
- if ((map[0] & 0x8F) == 0x08 && !(word % 31))
- return 0;
- else
- return 1;
-}
-
-unsigned long unpack_object_header_buffer(const unsigned char *buf,
- unsigned long len, enum object_type *type, unsigned long *sizep)
+void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
{
- unsigned shift;
- unsigned long size, c;
- unsigned long used = 0;
-
- c = buf[used++];
- *type = (c >> 4) & 7;
- size = c & 15;
- shift = 4;
- while (c & 0x80) {
- if (len <= used || bitsizeof(long) <= shift) {
- error("bad object header");
- size = used = 0;
- break;
- }
- c = buf[used++];
- size += (c & 0x7f) << shift;
- shift += 7;
- }
- *sizep = size;
- return used;
+ return map_sha1_file_1(NULL, sha1, size);
}
-int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
+static int unpack_sha1_short_header(git_zstream *stream,
+ unsigned char *map, unsigned long mapsize,
+ void *buffer, unsigned long bufsiz)
{
- unsigned long size, used;
- static const char valid_loose_object_type[8] = {
- 0, /* OBJ_EXT */
- 1, 1, 1, 1, /* "commit", "tree", "blob", "tag" */
- 0, /* "delta" and others are invalid in a loose object */
- };
- enum object_type type;
-
/* Get the data stream */
memset(stream, 0, sizeof(*stream));
stream->next_in = map;
stream->next_out = buffer;
stream->avail_out = bufsiz;
- if (experimental_loose_object(map)) {
- /*
- * The old experimental format we no longer produce;
- * we can still read it.
- */
- used = unpack_object_header_buffer(map, mapsize, &type, &size);
- if (!used || !valid_loose_object_type[type])
- return -1;
- map += used;
- mapsize -= used;
+ git_inflate_init(stream);
+ return git_inflate(stream, 0);
+}
- /* Set up the stream for the rest.. */
- stream->next_in = map;
- stream->avail_in = mapsize;
- git_inflate_init(stream);
+int unpack_sha1_header(git_zstream *stream,
+ unsigned char *map, unsigned long mapsize,
+ void *buffer, unsigned long bufsiz)
+{
+ int status = unpack_sha1_short_header(stream, map, mapsize,
+ buffer, bufsiz);
+
+ if (status < Z_OK)
+ return status;
- /* And generate the fake traditional header */
- stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
- typename(type), size);
+ /* Make sure we have the terminating NUL */
+ if (!memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
+ return -1;
+ return 0;
+}
+
+static int unpack_sha1_header_to_strbuf(git_zstream *stream, unsigned char *map,
+ unsigned long mapsize, void *buffer,
+ unsigned long bufsiz, struct strbuf *header)
+{
+ int status;
+
+ status = unpack_sha1_short_header(stream, map, mapsize, buffer, bufsiz);
+ if (status < Z_OK)
+ return -1;
+
+ /*
+ * Check if entire header is unpacked in the first iteration.
+ */
+ if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
return 0;
- }
- git_inflate_init(stream);
- return git_inflate(stream, 0);
+
+ /*
+ * buffer[0..bufsiz] was not large enough. Copy the partial
+ * result out to header, and then append the result of further
+ * reading the stream.
+ */
+ strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer);
+ stream->next_out = buffer;
+ stream->avail_out = bufsiz;
+
+ do {
+ status = git_inflate(stream, 0);
+ strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer);
+ if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
+ return 0;
+ stream->next_out = buffer;
+ stream->avail_out = bufsiz;
+ } while (status != Z_STREAM_END);
+ return -1;
}
static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
* too permissive for what we want to check. So do an anal
* object header parse by hand.
*/
-int parse_sha1_header(const char *hdr, unsigned long *sizep)
+static int parse_sha1_header_extended(const char *hdr, struct object_info *oi,
+ unsigned int flags)
{
- char type[10];
- int i;
+ const char *type_buf = hdr;
unsigned long size;
+ int type, type_len = 0;
/*
- * The type can be at most ten bytes (including the
- * terminating '\0' that we add), and is followed by
+ * The type can be of any size but is followed by
* a space.
*/
- i = 0;
for (;;) {
char c = *hdr++;
+ if (!c)
+ return -1;
if (c == ' ')
break;
- type[i++] = c;
- if (i >= sizeof(type))
- return -1;
+ type_len++;
}
- type[i] = 0;
+
+ type = type_from_string_gently(type_buf, type_len, 1);
+ if (oi->typename)
+ strbuf_add(oi->typename, type_buf, type_len);
+ /*
+ * Set type to 0 if its an unknown object and
+ * we're obtaining the type using '--allow-unknown-type'
+ * option.
+ */
+ if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE) && (type < 0))
+ type = 0;
+ else if (type < 0)
+ die("invalid object type");
+ if (oi->typep)
+ *oi->typep = type;
/*
* The length must follow immediately, and be in canonical
*/
size = *hdr++ - '0';
if (size > 9)
- return -1;
- if (size) {
- for (;;) {
- unsigned long c = *hdr - '0';
- if (c > 9)
- break;
- hdr++;
- size = size * 10 + c;
- }
- }
- *sizep = size;
-
- /*
- * The length must be followed by a zero byte
- */
- return *hdr ? -1 : type_from_string(type);
-}
-
-static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
-{
- int ret;
- git_zstream stream;
- char hdr[8192];
-
- ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
- if (ret < Z_OK || (*type = parse_sha1_header(hdr, size)) < 0)
- return NULL;
-
- return unpack_sha1_rest(&stream, hdr, *size, sha1);
-}
-
-unsigned long get_size_from_delta(struct packed_git *p,
- struct pack_window **w_curs,
- off_t curpos)
-{
- const unsigned char *data;
- unsigned char delta_head[20], *in;
- git_zstream stream;
- int st;
-
- memset(&stream, 0, sizeof(stream));
- stream.next_out = delta_head;
- stream.avail_out = sizeof(delta_head);
-
- git_inflate_init(&stream);
- do {
- in = use_pack(p, w_curs, curpos, &stream.avail_in);
- stream.next_in = in;
- st = git_inflate(&stream, Z_FINISH);
- curpos += stream.next_in - in;
- } while ((st == Z_OK || st == Z_BUF_ERROR) &&
- stream.total_out < sizeof(delta_head));
- git_inflate_end(&stream);
- if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) {
- error("delta data unpack-initial failed");
- return 0;
- }
-
- /* Examine the initial part of the delta to figure out
- * the result size.
- */
- data = delta_head;
-
- /* ignore base size */
- get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
-
- /* Read the result size */
- return get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
-}
-
-static off_t get_delta_base(struct packed_git *p,
- struct pack_window **w_curs,
- off_t *curpos,
- enum object_type type,
- off_t delta_obj_offset)
-{
- unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL);
- off_t base_offset;
-
- /* use_pack() assured us we have [base_info, base_info + 20)
- * as a range that we can look at without walking off the
- * end of the mapped window. Its actually the hash size
- * that is assured. An OFS_DELTA longer than the hash size
- * is stupid, as then a REF_DELTA would be smaller to store.
- */
- if (type == OBJ_OFS_DELTA) {
- unsigned used = 0;
- unsigned char c = base_info[used++];
- base_offset = c & 127;
- while (c & 128) {
- base_offset += 1;
- if (!base_offset || MSB(base_offset, 7))
- return 0; /* overflow */
- c = base_info[used++];
- base_offset = (base_offset << 7) + (c & 127);
- }
- base_offset = delta_obj_offset - base_offset;
- if (base_offset <= 0 || base_offset >= delta_obj_offset)
- return 0; /* out of bound */
- *curpos += used;
- } else if (type == OBJ_REF_DELTA) {
- /* The base entry _must_ be in the same pack */
- base_offset = find_pack_entry_one(base_info, p);
- *curpos += 20;
- } else
- die("I am totally screwed");
- return base_offset;
-}
-
-/* forward declaration for a mutually recursive function */
-static int packed_object_info(struct packed_git *p, off_t offset,
- unsigned long *sizep, int *rtype);
-
-static int packed_delta_info(struct packed_git *p,
- struct pack_window **w_curs,
- off_t curpos,
- enum object_type type,
- off_t obj_offset,
- unsigned long *sizep)
-{
- off_t base_offset;
-
- base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
- if (!base_offset)
- return OBJ_BAD;
- type = packed_object_info(p, base_offset, NULL, NULL);
- if (type <= OBJ_NONE) {
- struct revindex_entry *revidx;
- const unsigned char *base_sha1;
- revidx = find_pack_revindex(p, base_offset);
- if (!revidx)
- return OBJ_BAD;
- base_sha1 = nth_packed_object_sha1(p, revidx->nr);
- mark_bad_packed_object(p, base_sha1);
- type = sha1_object_info(base_sha1, NULL);
- if (type <= OBJ_NONE)
- return OBJ_BAD;
- }
-
- /* We choose to only get the type of the base object and
- * ignore potentially corrupt pack file that expects the delta
- * based on a base with a wrong size. This saves tons of
- * inflate() calls.
- */
- if (sizep) {
- *sizep = get_size_from_delta(p, w_curs, curpos);
- if (*sizep == 0)
- type = OBJ_BAD;
- }
-
- return type;
-}
-
-int unpack_object_header(struct packed_git *p,
- struct pack_window **w_curs,
- off_t *curpos,
- unsigned long *sizep)
-{
- unsigned char *base;
- unsigned long left;
- unsigned long used;
- enum object_type type;
-
- /* use_pack() assures us we have [base, base + 20) available
- * as a range that we can look at. (Its actually the hash
- * size that is assured.) With our object header encoding
- * the maximum deflated object size is 2^137, which is just
- * insane, so we know won't exceed what we have been given.
- */
- base = use_pack(p, w_curs, *curpos, &left);
- used = unpack_object_header_buffer(base, left, &type, sizep);
- if (!used) {
- type = OBJ_BAD;
- } else
- *curpos += used;
-
- return type;
-}
-
-static int packed_object_info(struct packed_git *p, off_t obj_offset,
- unsigned long *sizep, int *rtype)
-{
- struct pack_window *w_curs = NULL;
- unsigned long size;
- off_t curpos = obj_offset;
- enum object_type type;
-
- type = unpack_object_header(p, &w_curs, &curpos, &size);
- if (rtype)
- *rtype = type; /* representation type */
-
- switch (type) {
- case OBJ_OFS_DELTA:
- case OBJ_REF_DELTA:
- type = packed_delta_info(p, &w_curs, curpos,
- type, obj_offset, sizep);
- break;
- case OBJ_COMMIT:
- case OBJ_TREE:
- case OBJ_BLOB:
- case OBJ_TAG:
- if (sizep)
- *sizep = size;
- break;
- default:
- error("unknown object type %i at offset %"PRIuMAX" in %s",
- type, (uintmax_t)obj_offset, p->pack_name);
- type = OBJ_BAD;
- }
- unuse_pack(&w_curs);
- return type;
-}
-
-static void *unpack_compressed_entry(struct packed_git *p,
- struct pack_window **w_curs,
- off_t curpos,
- unsigned long size)
-{
- int st;
- git_zstream stream;
- unsigned char *buffer, *in;
-
- buffer = xmallocz(size);
- memset(&stream, 0, sizeof(stream));
- stream.next_out = buffer;
- stream.avail_out = size + 1;
-
- git_inflate_init(&stream);
- do {
- in = use_pack(p, w_curs, curpos, &stream.avail_in);
- stream.next_in = in;
- st = git_inflate(&stream, Z_FINISH);
- if (!stream.avail_out)
- break; /* the payload is larger than it should be */
- curpos += stream.next_in - in;
- } while (st == Z_OK || st == Z_BUF_ERROR);
- git_inflate_end(&stream);
- if ((st != Z_STREAM_END) || stream.total_out != size) {
- free(buffer);
- return NULL;
- }
-
- return buffer;
-}
-
-#define MAX_DELTA_CACHE (256)
-
-static size_t delta_base_cached;
-
-static struct delta_base_cache_lru_list {
- struct delta_base_cache_lru_list *prev;
- struct delta_base_cache_lru_list *next;
-} delta_base_cache_lru = { &delta_base_cache_lru, &delta_base_cache_lru };
-
-static struct delta_base_cache_entry {
- struct delta_base_cache_lru_list lru;
- void *data;
- struct packed_git *p;
- off_t base_offset;
- unsigned long size;
- enum object_type type;
-} delta_base_cache[MAX_DELTA_CACHE];
-
-static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset)
-{
- unsigned long hash;
-
- hash = (unsigned long)p + (unsigned long)base_offset;
- hash += (hash >> 8) + (hash >> 16);
- return hash % MAX_DELTA_CACHE;
-}
-
-static int in_delta_base_cache(struct packed_git *p, off_t base_offset)
-{
- unsigned long hash = pack_entry_hash(p, base_offset);
- struct delta_base_cache_entry *ent = delta_base_cache + hash;
- return (ent->data && ent->p == p && ent->base_offset == base_offset);
-}
-
-static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
- unsigned long *base_size, enum object_type *type, int keep_cache)
-{
- void *ret;
- unsigned long hash = pack_entry_hash(p, base_offset);
- struct delta_base_cache_entry *ent = delta_base_cache + hash;
-
- ret = ent->data;
- if (!ret || ent->p != p || ent->base_offset != base_offset)
- return unpack_entry(p, base_offset, type, base_size);
-
- if (!keep_cache) {
- ent->data = NULL;
- ent->lru.next->prev = ent->lru.prev;
- ent->lru.prev->next = ent->lru.next;
- delta_base_cached -= ent->size;
- } else {
- ret = xmemdupz(ent->data, ent->size);
- }
- *type = ent->type;
- *base_size = ent->size;
- return ret;
-}
-
-static inline void release_delta_base_cache(struct delta_base_cache_entry *ent)
-{
- if (ent->data) {
- free(ent->data);
- ent->data = NULL;
- ent->lru.next->prev = ent->lru.prev;
- ent->lru.prev->next = ent->lru.next;
- delta_base_cached -= ent->size;
- }
-}
-
-void clear_delta_base_cache(void)
-{
- unsigned long p;
- for (p = 0; p < MAX_DELTA_CACHE; p++)
- release_delta_base_cache(&delta_base_cache[p]);
-}
-
-static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
- void *base, unsigned long base_size, enum object_type type)
-{
- unsigned long hash = pack_entry_hash(p, base_offset);
- struct delta_base_cache_entry *ent = delta_base_cache + hash;
- struct delta_base_cache_lru_list *lru;
-
- release_delta_base_cache(ent);
- delta_base_cached += base_size;
-
- for (lru = delta_base_cache_lru.next;
- delta_base_cached > delta_base_cache_limit
- && lru != &delta_base_cache_lru;
- lru = lru->next) {
- struct delta_base_cache_entry *f = (void *)lru;
- if (f->type == OBJ_BLOB)
- release_delta_base_cache(f);
- }
- for (lru = delta_base_cache_lru.next;
- delta_base_cached > delta_base_cache_limit
- && lru != &delta_base_cache_lru;
- lru = lru->next) {
- struct delta_base_cache_entry *f = (void *)lru;
- release_delta_base_cache(f);
- }
-
- ent->p = p;
- ent->base_offset = base_offset;
- ent->type = type;
- ent->data = base;
- ent->size = base_size;
- ent->lru.next = &delta_base_cache_lru;
- ent->lru.prev = delta_base_cache_lru.prev;
- delta_base_cache_lru.prev->next = &ent->lru;
- delta_base_cache_lru.prev = &ent->lru;
-}
-
-static void *read_object(const unsigned char *sha1, enum object_type *type,
- unsigned long *size);
-
-static void *unpack_delta_entry(struct packed_git *p,
- struct pack_window **w_curs,
- off_t curpos,
- unsigned long delta_size,
- off_t obj_offset,
- enum object_type *type,
- unsigned long *sizep)
-{
- void *delta_data, *result, *base;
- unsigned long base_size;
- off_t base_offset;
-
- base_offset = get_delta_base(p, w_curs, &curpos, *type, obj_offset);
- if (!base_offset) {
- error("failed to validate delta base reference "
- "at offset %"PRIuMAX" from %s",
- (uintmax_t)curpos, p->pack_name);
- return NULL;
- }
- unuse_pack(w_curs);
- base = cache_or_unpack_entry(p, base_offset, &base_size, type, 0);
- if (!base) {
- /*
- * We're probably in deep shit, but let's try to fetch
- * the required base anyway from another pack or loose.
- * This is costly but should happen only in the presence
- * of a corrupted pack, and is better than failing outright.
- */
- struct revindex_entry *revidx;
- const unsigned char *base_sha1;
- revidx = find_pack_revindex(p, base_offset);
- if (!revidx)
- return NULL;
- base_sha1 = nth_packed_object_sha1(p, revidx->nr);
- error("failed to read delta base object %s"
- " at offset %"PRIuMAX" from %s",
- sha1_to_hex(base_sha1), (uintmax_t)base_offset,
- p->pack_name);
- mark_bad_packed_object(p, base_sha1);
- base = read_object(base_sha1, type, &base_size);
- if (!base)
- return NULL;
- }
-
- delta_data = unpack_compressed_entry(p, w_curs, curpos, delta_size);
- if (!delta_data) {
- error("failed to unpack compressed delta "
- "at offset %"PRIuMAX" from %s",
- (uintmax_t)curpos, p->pack_name);
- free(base);
- return NULL;
- }
- result = patch_delta(base, base_size,
- delta_data, delta_size,
- sizep);
- if (!result)
- die("failed to apply delta");
- free(delta_data);
- add_delta_base_cache(p, base_offset, base, base_size, *type);
- return result;
-}
-
-static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
-{
- static FILE *log_file;
-
- if (!log_file) {
- log_file = fopen(log_pack_access, "w");
- if (!log_file) {
- error("cannot open pack access log '%s' for writing: %s",
- log_pack_access, strerror(errno));
- log_pack_access = NULL;
- return;
- }
- }
- fprintf(log_file, "%s %"PRIuMAX"\n",
- p->pack_name, (uintmax_t)obj_offset);
- fflush(log_file);
-}
-
-int do_check_packed_object_crc;
-
-void *unpack_entry(struct packed_git *p, off_t obj_offset,
- enum object_type *type, unsigned long *sizep)
-{
- struct pack_window *w_curs = NULL;
- off_t curpos = obj_offset;
- void *data;
-
- if (log_pack_access)
- write_pack_access_log(p, obj_offset);
-
- if (do_check_packed_object_crc && p->index_version > 1) {
- struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
- unsigned long len = revidx[1].offset - obj_offset;
- if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) {
- const unsigned char *sha1 =
- nth_packed_object_sha1(p, revidx->nr);
- error("bad packed object CRC for %s",
- sha1_to_hex(sha1));
- mark_bad_packed_object(p, sha1);
- unuse_pack(&w_curs);
- return NULL;
- }
- }
-
- *type = unpack_object_header(p, &w_curs, &curpos, sizep);
- switch (*type) {
- case OBJ_OFS_DELTA:
- case OBJ_REF_DELTA:
- data = unpack_delta_entry(p, &w_curs, curpos, *sizep,
- obj_offset, type, sizep);
- break;
- case OBJ_COMMIT:
- case OBJ_TREE:
- case OBJ_BLOB:
- case OBJ_TAG:
- data = unpack_compressed_entry(p, &w_curs, curpos, *sizep);
- break;
- default:
- data = NULL;
- error("unknown object type %i at offset %"PRIuMAX" in %s",
- *type, (uintmax_t)obj_offset, p->pack_name);
- }
- unuse_pack(&w_curs);
- return data;
-}
-
-const unsigned char *nth_packed_object_sha1(struct packed_git *p,
- uint32_t n)
-{
- const unsigned char *index = p->index_data;
- if (!index) {
- if (open_pack_index(p))
- return NULL;
- index = p->index_data;
- }
- if (n >= p->num_objects)
- return NULL;
- index += 4 * 256;
- if (p->index_version == 1) {
- return index + 24 * n + 4;
- } else {
- index += 8;
- return index + 20 * n;
- }
-}
-
-off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
-{
- const unsigned char *index = p->index_data;
- index += 4 * 256;
- if (p->index_version == 1) {
- return ntohl(*((uint32_t *)(index + 24 * n)));
- } else {
- uint32_t off;
- index += 8 + p->num_objects * (20 + 4);
- off = ntohl(*((uint32_t *)(index + 4 * n)));
- if (!(off & 0x80000000))
- return off;
- index += p->num_objects * 4 + (off & 0x7fffffff) * 8;
- return (((uint64_t)ntohl(*((uint32_t *)(index + 0)))) << 32) |
- ntohl(*((uint32_t *)(index + 4)));
- }
-}
-
-off_t find_pack_entry_one(const unsigned char *sha1,
- struct packed_git *p)
-{
- const uint32_t *level1_ofs = p->index_data;
- const unsigned char *index = p->index_data;
- unsigned hi, lo, stride;
- static int use_lookup = -1;
- static int debug_lookup = -1;
-
- if (debug_lookup < 0)
- debug_lookup = !!getenv("GIT_DEBUG_LOOKUP");
-
- if (!index) {
- if (open_pack_index(p))
- return 0;
- level1_ofs = p->index_data;
- index = p->index_data;
- }
- if (p->index_version > 1) {
- level1_ofs += 2;
- index += 8;
- }
- index += 4 * 256;
- hi = ntohl(level1_ofs[*sha1]);
- lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
- if (p->index_version > 1) {
- stride = 20;
- } else {
- stride = 24;
- index += 4;
- }
-
- if (debug_lookup)
- printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n",
- sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects);
-
- if (use_lookup < 0)
- use_lookup = !!getenv("GIT_USE_LOOKUP");
- if (use_lookup) {
- int pos = sha1_entry_pos(index, stride, 0,
- lo, hi, p->num_objects, sha1);
- if (pos < 0)
- return 0;
- return nth_packed_object_offset(p, pos);
- }
-
- do {
- unsigned mi = (lo + hi) / 2;
- int cmp = hashcmp(index + mi * stride, sha1);
-
- if (debug_lookup)
- printf("lo %u hi %u rg %u mi %u\n",
- lo, hi, hi - lo, mi);
- if (!cmp)
- return nth_packed_object_offset(p, mi);
- if (cmp > 0)
- hi = mi;
- else
- lo = mi+1;
- } while (lo < hi);
- return 0;
-}
-
-int is_pack_valid(struct packed_git *p)
-{
- /* An already open pack is known to be valid. */
- if (p->pack_fd != -1)
- return 1;
-
- /* If the pack has one window completely covering the
- * file size, the pack is known to be valid even if
- * the descriptor is not currently open.
- */
- if (p->windows) {
- struct pack_window *w = p->windows;
-
- if (!w->offset && w->len == p->pack_size)
- return 1;
- }
-
- /* Force the pack to open to prove its valid. */
- return !open_packed_git(p);
-}
-
-static int fill_pack_entry(const unsigned char *sha1,
- struct pack_entry *e,
- struct packed_git *p)
-{
- off_t offset;
-
- if (p->num_bad_objects) {
- unsigned i;
- for (i = 0; i < p->num_bad_objects; i++)
- if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
- return 0;
+ return -1;
+ if (size) {
+ for (;;) {
+ unsigned long c = *hdr - '0';
+ if (c > 9)
+ break;
+ hdr++;
+ size = size * 10 + c;
+ }
}
- offset = find_pack_entry_one(sha1, p);
- if (!offset)
- return 0;
+ if (oi->sizep)
+ *oi->sizep = size;
/*
- * We are about to tell the caller where they can locate the
- * requested object. We better make sure the packfile is
- * still here and can be accessed before supplying that
- * answer, as it may have been deleted since the index was
- * loaded!
+ * The length must be followed by a zero byte
*/
- if (!is_pack_valid(p)) {
- warning("packfile %s cannot be accessed", p->pack_name);
- return 0;
- }
- e->offset = offset;
- e->p = p;
- hashcpy(e->sha1, sha1);
- return 1;
-}
-
-static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
-{
- struct packed_git *p;
-
- prepare_packed_git();
- if (!packed_git)
- return 0;
-
- if (last_found_pack && fill_pack_entry(sha1, e, last_found_pack))
- return 1;
-
- for (p = packed_git; p; p = p->next) {
- if (p == last_found_pack || !fill_pack_entry(sha1, e, p))
- continue;
-
- last_found_pack = p;
- return 1;
- }
- return 0;
+ return *hdr ? -1 : type;
}
-struct packed_git *find_sha1_pack(const unsigned char *sha1,
- struct packed_git *packs)
+int parse_sha1_header(const char *hdr, unsigned long *sizep)
{
- struct packed_git *p;
-
- for (p = packs; p; p = p->next) {
- if (find_pack_entry_one(sha1, p))
- return p;
- }
- return NULL;
+ struct object_info oi = OBJECT_INFO_INIT;
+ oi.sizep = sizep;
+ return parse_sha1_header_extended(hdr, &oi, 0);
}
-static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *sizep)
+static int sha1_loose_object_info(const unsigned char *sha1,
+ struct object_info *oi,
+ int flags)
{
- int status;
- unsigned long mapsize, size;
+ int status = 0;
+ unsigned long mapsize;
void *map;
git_zstream stream;
char hdr[32];
+ struct strbuf hdrbuf = STRBUF_INIT;
+ unsigned long size_scratch;
+
+ if (oi->delta_base_sha1)
+ hashclr(oi->delta_base_sha1);
+
+ /*
+ * If we don't care about type or size, then we don't
+ * need to look inside the object at all. Note that we
+ * do not optimize out the stat call, even if the
+ * caller doesn't care about the disk-size, since our
+ * return value implicitly indicates whether the
+ * object even exists.
+ */
+ if (!oi->typep && !oi->typename && !oi->sizep && !oi->contentp) {
+ const char *path;
+ struct stat st;
+ if (stat_sha1_file(sha1, &st, &path) < 0)
+ return -1;
+ if (oi->disk_sizep)
+ *oi->disk_sizep = st.st_size;
+ return 0;
+ }
map = map_sha1_file(sha1, &mapsize);
if (!map)
- return error("unable to find %s", sha1_to_hex(sha1));
- if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
+ return -1;
+
+ if (!oi->sizep)
+ oi->sizep = &size_scratch;
+
+ if (oi->disk_sizep)
+ *oi->disk_sizep = mapsize;
+ if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE)) {
+ if (unpack_sha1_header_to_strbuf(&stream, map, mapsize, hdr, sizeof(hdr), &hdrbuf) < 0)
+ status = error("unable to unpack %s header with --allow-unknown-type",
+ sha1_to_hex(sha1));
+ } else if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
status = error("unable to unpack %s header",
sha1_to_hex(sha1));
- else if ((status = parse_sha1_header(hdr, &size)) < 0)
+ if (status < 0)
+ ; /* Do nothing */
+ else if (hdrbuf.len) {
+ if ((status = parse_sha1_header_extended(hdrbuf.buf, oi, flags)) < 0)
+ status = error("unable to parse %s header with --allow-unknown-type",
+ sha1_to_hex(sha1));
+ } else if ((status = parse_sha1_header_extended(hdr, oi, flags)) < 0)
status = error("unable to parse %s header", sha1_to_hex(sha1));
- else if (sizep)
- *sizep = size;
- git_inflate_end(&stream);
+
+ if (status >= 0 && oi->contentp) {
+ *oi->contentp = unpack_sha1_rest(&stream, hdr,
+ *oi->sizep, sha1);
+ if (!*oi->contentp) {
+ git_inflate_end(&stream);
+ status = -1;
+ }
+ } else
+ git_inflate_end(&stream);
+
munmap(map, mapsize);
- return status;
+ if (status && oi->typep)
+ *oi->typep = status;
+ if (oi->sizep == &size_scratch)
+ oi->sizep = NULL;
+ strbuf_release(&hdrbuf);
+ oi->whence = OI_LOOSE;
+ return (status < 0) ? status : 0;
}
-/* returns enum object_type or negative */
-int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi)
+int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi, unsigned flags)
{
- struct cached_object *co;
+ static struct object_info blank_oi = OBJECT_INFO_INIT;
struct pack_entry e;
- int status, rtype;
-
- co = find_cached_object(sha1);
- if (co) {
- if (oi->sizep)
- *(oi->sizep) = co->size;
- oi->whence = OI_CACHED;
- return co->type;
+ int rtype;
+ const unsigned char *real = (flags & OBJECT_INFO_LOOKUP_REPLACE) ?
+ lookup_replace_object(sha1) :
+ sha1;
+
+ if (is_null_sha1(real))
+ return -1;
+
+ if (!oi)
+ oi = &blank_oi;
+
+ if (!(flags & OBJECT_INFO_SKIP_CACHED)) {
+ struct cached_object *co = find_cached_object(real);
+ if (co) {
+ if (oi->typep)
+ *(oi->typep) = co->type;
+ if (oi->sizep)
+ *(oi->sizep) = co->size;
+ if (oi->disk_sizep)
+ *(oi->disk_sizep) = 0;
+ if (oi->delta_base_sha1)
+ hashclr(oi->delta_base_sha1);
+ if (oi->typename)
+ strbuf_addstr(oi->typename, typename(co->type));
+ if (oi->contentp)
+ *oi->contentp = xmemdupz(co->buf, co->size);
+ oi->whence = OI_CACHED;
+ return 0;
+ }
}
- if (!find_pack_entry(sha1, &e)) {
+ if (!find_pack_entry(real, &e)) {
/* Most likely it's a loose object. */
- status = sha1_loose_object_info(sha1, oi->sizep);
- if (status >= 0) {
- oi->whence = OI_LOOSE;
- return status;
- }
+ if (!sha1_loose_object_info(real, oi, flags))
+ return 0;
/* Not a loose object; someone else may have just packed it. */
- reprepare_packed_git();
- if (!find_pack_entry(sha1, &e))
- return status;
+ if (flags & OBJECT_INFO_QUICK) {
+ return -1;
+ } else {
+ reprepare_packed_git();
+ if (!find_pack_entry(real, &e))
+ return -1;
+ }
}
- status = packed_object_info(e.p, e.offset, oi->sizep, &rtype);
- if (status < 0) {
- mark_bad_packed_object(e.p, sha1);
- status = sha1_object_info_extended(sha1, oi);
- } else if (in_delta_base_cache(e.p, e.offset)) {
- oi->whence = OI_DBCACHED;
- } else {
- oi->whence = OI_PACKED;
+ if (oi == &blank_oi)
+ /*
+ * We know that the caller doesn't actually need the
+ * information below, so return early.
+ */
+ return 0;
+
+ rtype = packed_object_info(e.p, e.offset, oi);
+ if (rtype < 0) {
+ mark_bad_packed_object(e.p, real);
+ return sha1_object_info_extended(real, oi, 0);
+ } else if (oi->whence == OI_PACKED) {
oi->u.packed.offset = e.offset;
oi->u.packed.pack = e.p;
oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
rtype == OBJ_OFS_DELTA);
}
- return status;
+ return 0;
}
+/* returns enum object_type or negative */
int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
{
- struct object_info oi;
+ enum object_type type;
+ struct object_info oi = OBJECT_INFO_INIT;
+ oi.typep = &type;
oi.sizep = sizep;
- return sha1_object_info_extended(sha1, &oi);
+ if (sha1_object_info_extended(sha1, &oi,
+ OBJECT_INFO_LOOKUP_REPLACE) < 0)
+ return -1;
+ return type;
}
-static void *read_packed_sha1(const unsigned char *sha1,
- enum object_type *type, unsigned long *size)
+static void *read_object(const unsigned char *sha1, enum object_type *type,
+ unsigned long *size)
{
- struct pack_entry e;
- void *data;
+ struct object_info oi = OBJECT_INFO_INIT;
+ void *content;
+ oi.typep = type;
+ oi.sizep = size;
+ oi.contentp = &content;
- if (!find_pack_entry(sha1, &e))
+ if (sha1_object_info_extended(sha1, &oi, 0) < 0)
return NULL;
- data = cache_or_unpack_entry(e.p, e.offset, size, type, 1);
- if (!data) {
- /*
- * We're probably in deep shit, but let's try to fetch
- * the required object anyway from another pack or loose.
- * This should happen only in the presence of a corrupted
- * pack, and is better than failing outright.
- */
- error("failed to read object %s at offset %"PRIuMAX" from %s",
- sha1_to_hex(sha1), (uintmax_t)e.offset, e.p->pack_name);
- mark_bad_packed_object(e.p, sha1);
- data = read_object(sha1, type, size);
- }
- return data;
+ return content;
}
int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
hash_sha1_file(buf, len, typename(type), sha1);
if (has_sha1_file(sha1) || find_cached_object(sha1))
return 0;
- if (cached_object_alloc <= cached_object_nr) {
- cached_object_alloc = alloc_nr(cached_object_alloc);
- cached_objects = xrealloc(cached_objects,
- sizeof(*cached_objects) *
- cached_object_alloc);
- }
+ ALLOC_GROW(cached_objects, cached_object_nr + 1, cached_object_alloc);
co = &cached_objects[cached_object_nr++];
co->size = len;
co->type = type;
return 0;
}
-static void *read_object(const unsigned char *sha1, enum object_type *type,
- unsigned long *size)
-{
- unsigned long mapsize;
- void *map, *buf;
- struct cached_object *co;
-
- co = find_cached_object(sha1);
- if (co) {
- *type = co->type;
- *size = co->size;
- return xmemdupz(co->buf, co->size);
- }
-
- buf = read_packed_sha1(sha1, type, size);
- if (buf)
- return buf;
- map = map_sha1_file(sha1, &mapsize);
- if (map) {
- buf = unpack_sha1_file(map, mapsize, type, size, sha1);
- munmap(map, mapsize);
- return buf;
- }
- reprepare_packed_git();
- return read_packed_sha1(sha1, type, size);
-}
-
/*
* This function dies on corrupt objects; the callers who want to
* deal with them should arrange to call read_object() and give error
void *read_sha1_file_extended(const unsigned char *sha1,
enum object_type *type,
unsigned long *size,
- unsigned flag)
+ int lookup_replace)
{
void *data;
- char *path;
const struct packed_git *p;
- const unsigned char *repl = (flag & READ_SHA1_FILE_REPLACE)
- ? lookup_replace_object(sha1) : sha1;
+ const char *path;
+ struct stat st;
+ const unsigned char *repl = lookup_replace ? lookup_replace_object(sha1)
+ : sha1;
errno = 0;
data = read_object(repl, type, size);
die("replacement %s not found for %s",
sha1_to_hex(repl), sha1_to_hex(sha1));
- if (has_loose_object(repl)) {
- path = sha1_file_name(sha1);
+ if (!stat_sha1_file(repl, &st, &path))
die("loose object %s (stored in %s) is corrupt",
sha1_to_hex(repl), path);
- }
if ((p = has_packed_and_bad(repl)) != NULL)
die("packed object %s (stored in %s) is corrupt",
git_SHA_CTX c;
/* Generate the header */
- *hdrlen = sprintf(hdr, "%s %lu", type, len)+1;
+ *hdrlen = xsnprintf(hdr, *hdrlen, "%s %lu", type, len)+1;
/* Sha1.. */
git_SHA1_Init(&c);
/*
* Move the just written object into its final resting place.
- * NEEDSWORK: this should be renamed to finalize_temp_file() as
- * "moving" is only a part of what it does, when no patch between
- * master to pu changes the call sites of this function.
*/
-int move_temp_to_file(const char *tmpfile, const char *filename)
+int finalize_object_file(const char *tmpfile, const char *filename)
{
int ret = 0;
unlink_or_warn(tmpfile);
if (ret) {
if (ret != EEXIST) {
- return error("unable to write sha1 filename %s: %s", filename, strerror(ret));
+ return error_errno("unable to write sha1 filename %s", filename);
}
/* FIXME!!! Collision check here ? */
}
static int write_buffer(int fd, const void *buf, size_t len)
{
if (write_in_full(fd, buf, len) < 0)
- return error("file write error (%s)", strerror(errno));
+ return error_errno("file write error");
return 0;
}
unsigned char *sha1)
{
char hdr[32];
- int hdrlen;
+ int hdrlen = sizeof(hdr);
write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);
return 0;
}
* We want to avoid cross-directory filename renames, because those
* can have problems on various filesystems (FAT, NFS, Coda).
*/
-static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename)
+static int create_tmpfile(struct strbuf *tmp, const char *filename)
{
int fd, dirlen = directory_size(filename);
- if (dirlen + 20 > bufsiz) {
- errno = ENAMETOOLONG;
- return -1;
- }
- memcpy(buffer, filename, dirlen);
- strcpy(buffer + dirlen, "tmp_obj_XXXXXX");
- fd = git_mkstemp_mode(buffer, 0444);
+ strbuf_reset(tmp);
+ strbuf_add(tmp, filename, dirlen);
+ strbuf_addstr(tmp, "tmp_obj_XXXXXX");
+ fd = git_mkstemp_mode(tmp->buf, 0444);
if (fd < 0 && dirlen && errno == ENOENT) {
- /* Make sure the directory exists */
- memcpy(buffer, filename, dirlen);
- buffer[dirlen-1] = 0;
- if (mkdir(buffer, 0777) || adjust_shared_perm(buffer))
+ /*
+ * Make sure the directory exists; note that the contents
+ * of the buffer are undefined after mkstemp returns an
+ * error, so we have to rewrite the whole buffer from
+ * scratch.
+ */
+ strbuf_reset(tmp);
+ strbuf_add(tmp, filename, dirlen - 1);
+ if (mkdir(tmp->buf, 0777) && errno != EEXIST)
+ return -1;
+ if (adjust_shared_perm(tmp->buf))
return -1;
/* Try again */
- strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX");
- fd = git_mkstemp_mode(buffer, 0444);
+ strbuf_addstr(tmp, "/tmp_obj_XXXXXX");
+ fd = git_mkstemp_mode(tmp->buf, 0444);
}
return fd;
}
git_zstream stream;
git_SHA_CTX c;
unsigned char parano_sha1[20];
- char *filename;
- static char tmp_file[PATH_MAX];
+ static struct strbuf tmp_file = STRBUF_INIT;
+ const char *filename = sha1_file_name(sha1);
- filename = sha1_file_name(sha1);
- fd = create_tmpfile(tmp_file, sizeof(tmp_file), filename);
+ fd = create_tmpfile(&tmp_file, filename);
if (fd < 0) {
if (errno == EACCES)
return error("insufficient permission for adding an object to repository database %s", get_object_directory());
else
- return error("unable to create temporary file: %s", strerror(errno));
+ return error_errno("unable to create temporary file");
}
/* Set it up */
- memset(&stream, 0, sizeof(stream));
git_deflate_init(&stream, zlib_compression_level);
stream.next_out = compressed;
stream.avail_out = sizeof(compressed);
struct utimbuf utb;
utb.actime = mtime;
utb.modtime = mtime;
- if (utime(tmp_file, &utb) < 0)
- warning("failed utime() on %s: %s",
- tmp_file, strerror(errno));
+ if (utime(tmp_file.buf, &utb) < 0)
+ warning_errno("failed utime() on %s", tmp_file.buf);
}
- return move_temp_to_file(tmp_file, filename);
+ return finalize_object_file(tmp_file.buf, filename);
}
-int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
+static int freshen_loose_object(const unsigned char *sha1)
+{
+ return check_and_freshen(sha1, 1);
+}
+
+static int freshen_packed_object(const unsigned char *sha1)
+{
+ struct pack_entry e;
+ if (!find_pack_entry(sha1, &e))
+ return 0;
+ if (e.p->freshened)
+ return 1;
+ if (!freshen_file(e.p->pack_name))
+ return 0;
+ e.p->freshened = 1;
+ return 1;
+}
+
+int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1)
{
- unsigned char sha1[20];
char hdr[32];
- int hdrlen;
+ int hdrlen = sizeof(hdr);
/* Normally if we have it in the pack then we do not bother writing
* it out into .git/objects/??/?{38} file.
*/
write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);
- if (returnsha1)
- hashcpy(returnsha1, sha1);
- if (has_sha1_file(sha1))
+ if (freshen_packed_object(sha1) || freshen_loose_object(sha1))
return 0;
return write_loose_object(sha1, hdr, hdrlen, buf, len, 0);
}
+int hash_sha1_file_literally(const void *buf, unsigned long len, const char *type,
+ struct object_id *oid, unsigned flags)
+{
+ char *header;
+ int hdrlen, status = 0;
+
+ /* type string, SP, %lu of the length plus NUL must fit this */
+ hdrlen = strlen(type) + 32;
+ header = xmalloc(hdrlen);
+ write_sha1_file_prepare(buf, len, type, oid->hash, header, &hdrlen);
+
+ if (!(flags & HASH_WRITE_OBJECT))
+ goto cleanup;
+ if (freshen_packed_object(oid->hash) || freshen_loose_object(oid->hash))
+ goto cleanup;
+ status = write_loose_object(oid->hash, header, hdrlen, buf, len, 0);
+
+cleanup:
+ free(header);
+ return status;
+}
+
int force_object_loose(const unsigned char *sha1, time_t mtime)
{
void *buf;
if (has_loose_object(sha1))
return 0;
- buf = read_packed_sha1(sha1, &type, &len);
+ buf = read_object(sha1, &type, &len);
if (!buf)
return error("cannot read sha1_file for %s", sha1_to_hex(sha1));
- hdrlen = sprintf(hdr, "%s %lu", typename(type), len) + 1;
+ hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(type), len) + 1;
ret = write_loose_object(sha1, hdr, hdrlen, buf, len, mtime);
free(buf);
return ret;
}
-int has_pack_index(const unsigned char *sha1)
+int has_sha1_file_with_flags(const unsigned char *sha1, int flags)
{
- struct stat st;
- if (stat(sha1_pack_index_name(sha1), &st))
+ if (!startup_info->have_repository)
return 0;
- return 1;
+ return sha1_object_info_extended(sha1, NULL,
+ flags | OBJECT_INFO_SKIP_CACHED) >= 0;
}
-int has_sha1_pack(const unsigned char *sha1)
+int has_object_file(const struct object_id *oid)
{
- struct pack_entry e;
- return find_pack_entry(sha1, &e);
+ return has_sha1_file(oid->hash);
}
-int has_sha1_file(const unsigned char *sha1)
+int has_object_file_with_flags(const struct object_id *oid, int flags)
{
- struct pack_entry e;
-
- if (find_pack_entry(sha1, &e))
- return 1;
- return has_loose_object(sha1);
+ return has_sha1_file_with_flags(oid->hash, flags);
}
static void check_tree(const void *buf, size_t size)
die("corrupt tag");
}
-static int index_mem(unsigned char *sha1, void *buf, size_t size,
+static int index_mem(struct object_id *oid, void *buf, size_t size,
enum object_type type,
const char *path, unsigned flags)
{
*/
if ((type == OBJ_BLOB) && path) {
struct strbuf nbuf = STRBUF_INIT;
- if (convert_to_git(path, buf, size, &nbuf,
- write_object ? safe_crlf : SAFE_CRLF_FALSE)) {
+ if (convert_to_git(&the_index, path, buf, size, &nbuf,
+ get_safe_crlf(flags))) {
buf = strbuf_detach(&nbuf, &size);
re_allocated = 1;
}
}
if (write_object)
- ret = write_sha1_file(buf, size, typename(type), sha1);
+ ret = write_sha1_file(buf, size, typename(type), oid->hash);
else
- ret = hash_sha1_file(buf, size, typename(type), sha1);
+ ret = hash_sha1_file(buf, size, typename(type), oid->hash);
if (re_allocated)
free(buf);
return ret;
}
-static int index_pipe(unsigned char *sha1, int fd, enum object_type type,
+static int index_stream_convert_blob(struct object_id *oid, int fd,
+ const char *path, unsigned flags)
+{
+ int ret;
+ const int write_object = flags & HASH_WRITE_OBJECT;
+ struct strbuf sbuf = STRBUF_INIT;
+
+ assert(path);
+ assert(would_convert_to_git_filter_fd(path));
+
+ convert_to_git_filter_fd(&the_index, path, fd, &sbuf,
+ get_safe_crlf(flags));
+
+ if (write_object)
+ ret = write_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+ oid->hash);
+ else
+ ret = hash_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+ oid->hash);
+ strbuf_release(&sbuf);
+ return ret;
+}
+
+static int index_pipe(struct object_id *oid, int fd, enum object_type type,
const char *path, unsigned flags)
{
struct strbuf sbuf = STRBUF_INIT;
int ret;
if (strbuf_read(&sbuf, fd, 4096) >= 0)
- ret = index_mem(sha1, sbuf.buf, sbuf.len, type, path, flags);
+ ret = index_mem(oid, sbuf.buf, sbuf.len, type, path, flags);
else
ret = -1;
strbuf_release(&sbuf);
#define SMALL_FILE_SIZE (32*1024)
-static int index_core(unsigned char *sha1, int fd, size_t size,
+static int index_core(struct object_id *oid, int fd, size_t size,
enum object_type type, const char *path,
unsigned flags)
{
int ret;
if (!size) {
- ret = index_mem(sha1, NULL, size, type, path, flags);
+ ret = index_mem(oid, "", size, type, path, flags);
} else if (size <= SMALL_FILE_SIZE) {
char *buf = xmalloc(size);
- if (size == read_in_full(fd, buf, size))
- ret = index_mem(sha1, buf, size, type, path, flags);
+ ssize_t read_result = read_in_full(fd, buf, size);
+ if (read_result < 0)
+ ret = error_errno("read error while indexing %s",
+ path ? path : "<unknown>");
+ else if (read_result != size)
+ ret = error("short read while indexing %s",
+ path ? path : "<unknown>");
else
- ret = error("short read %s", strerror(errno));
+ ret = index_mem(oid, buf, size, type, path, flags);
free(buf);
} else {
void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
- ret = index_mem(sha1, buf, size, type, path, flags);
+ ret = index_mem(oid, buf, size, type, path, flags);
munmap(buf, size);
}
return ret;
* binary blobs, they generally do not want to get any conversion, and
* callers should avoid this code path when filters are requested.
*/
-static int index_stream(unsigned char *sha1, int fd, size_t size,
+static int index_stream(struct object_id *oid, int fd, size_t size,
enum object_type type, const char *path,
unsigned flags)
{
- return index_bulk_checkin(sha1, fd, size, type, path, flags);
+ return index_bulk_checkin(oid->hash, fd, size, type, path, flags);
}
-int index_fd(unsigned char *sha1, int fd, struct stat *st,
+int index_fd(struct object_id *oid, int fd, struct stat *st,
enum object_type type, const char *path, unsigned flags)
{
int ret;
- size_t size = xsize_t(st->st_size);
- if (!S_ISREG(st->st_mode))
- ret = index_pipe(sha1, fd, type, path, flags);
- else if (size <= big_file_threshold || type != OBJ_BLOB ||
- (path && would_convert_to_git(path, NULL, 0, 0)))
- ret = index_core(sha1, fd, size, type, path, flags);
+ /*
+ * Call xsize_t() only when needed to avoid potentially unnecessary
+ * die() for large files.
+ */
+ if (type == OBJ_BLOB && path && would_convert_to_git_filter_fd(path))
+ ret = index_stream_convert_blob(oid, fd, path, flags);
+ else if (!S_ISREG(st->st_mode))
+ ret = index_pipe(oid, fd, type, path, flags);
+ else if (st->st_size <= big_file_threshold || type != OBJ_BLOB ||
+ (path && would_convert_to_git(&the_index, path)))
+ ret = index_core(oid, fd, xsize_t(st->st_size), type, path,
+ flags);
else
- ret = index_stream(sha1, fd, size, type, path, flags);
+ ret = index_stream(oid, fd, xsize_t(st->st_size), type, path,
+ flags);
close(fd);
return ret;
}
-int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags)
+int index_path(struct object_id *oid, const char *path, struct stat *st, unsigned flags)
{
int fd;
struct strbuf sb = STRBUF_INIT;
+ int rc = 0;
switch (st->st_mode & S_IFMT) {
case S_IFREG:
fd = open(path, O_RDONLY);
if (fd < 0)
- return error("open(\"%s\"): %s", path,
- strerror(errno));
- if (index_fd(sha1, fd, st, OBJ_BLOB, path, flags) < 0)
+ return error_errno("open(\"%s\")", path);
+ if (index_fd(oid, fd, st, OBJ_BLOB, path, flags) < 0)
return error("%s: failed to insert into database",
path);
break;
case S_IFLNK:
- if (strbuf_readlink(&sb, path, st->st_size)) {
- char *errstr = strerror(errno);
- return error("readlink(\"%s\"): %s", path,
- errstr);
- }
+ if (strbuf_readlink(&sb, path, st->st_size))
+ return error_errno("readlink(\"%s\")", path);
if (!(flags & HASH_WRITE_OBJECT))
- hash_sha1_file(sb.buf, sb.len, blob_type, sha1);
- else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1))
- return error("%s: failed to insert into database",
- path);
+ hash_sha1_file(sb.buf, sb.len, blob_type, oid->hash);
+ else if (write_sha1_file(sb.buf, sb.len, blob_type, oid->hash))
+ rc = error("%s: failed to insert into database", path);
strbuf_release(&sb);
break;
case S_IFDIR:
- return resolve_gitlink_ref(path, "HEAD", sha1);
+ return resolve_gitlink_ref(path, "HEAD", oid);
default:
return error("%s: unsupported file type", path);
}
- return 0;
+ return rc;
}
int read_pack_header(int fd, struct pack_header *header)
{
- if (read_in_full(fd, header, sizeof(*header)) < sizeof(*header))
+ if (read_in_full(fd, header, sizeof(*header)) != sizeof(*header))
/* "eof before pack header was fully read" */
return PH_ERROR_EOF;
die("%s is not a valid '%s' object", sha1_to_hex(sha1),
typename(expect));
}
+
+int for_each_file_in_obj_subdir(unsigned int subdir_nr,
+ struct strbuf *path,
+ each_loose_object_fn obj_cb,
+ each_loose_cruft_fn cruft_cb,
+ each_loose_subdir_fn subdir_cb,
+ void *data)
+{
+ size_t origlen, baselen;
+ DIR *dir;
+ struct dirent *de;
+ int r = 0;
+ struct object_id oid;
+
+ if (subdir_nr > 0xff)
+ BUG("invalid loose object subdirectory: %x", subdir_nr);
+
+ origlen = path->len;
+ strbuf_complete(path, '/');
+ strbuf_addf(path, "%02x", subdir_nr);
+
+ dir = opendir(path->buf);
+ if (!dir) {
+ if (errno != ENOENT)
+ r = error_errno("unable to open %s", path->buf);
+ strbuf_setlen(path, origlen);
+ return r;
+ }
+
+ oid.hash[0] = subdir_nr;
+ strbuf_addch(path, '/');
+ baselen = path->len;
+
+ while ((de = readdir(dir))) {
+ size_t namelen;
+ if (is_dot_or_dotdot(de->d_name))
+ continue;
+
+ namelen = strlen(de->d_name);
+ strbuf_setlen(path, baselen);
+ strbuf_add(path, de->d_name, namelen);
+ if (namelen == GIT_SHA1_HEXSZ - 2 &&
+ !hex_to_bytes(oid.hash + 1, de->d_name,
+ GIT_SHA1_RAWSZ - 1)) {
+ if (obj_cb) {
+ r = obj_cb(&oid, path->buf, data);
+ if (r)
+ break;
+ }
+ continue;
+ }
+
+ if (cruft_cb) {
+ r = cruft_cb(de->d_name, path->buf, data);
+ if (r)
+ break;
+ }
+ }
+ closedir(dir);
+
+ strbuf_setlen(path, baselen - 1);
+ if (!r && subdir_cb)
+ r = subdir_cb(subdir_nr, path->buf, data);
+
+ strbuf_setlen(path, origlen);
+
+ return r;
+}
+
+int for_each_loose_file_in_objdir_buf(struct strbuf *path,
+ each_loose_object_fn obj_cb,
+ each_loose_cruft_fn cruft_cb,
+ each_loose_subdir_fn subdir_cb,
+ void *data)
+{
+ int r = 0;
+ int i;
+
+ for (i = 0; i < 256; i++) {
+ r = for_each_file_in_obj_subdir(i, path, obj_cb, cruft_cb,
+ subdir_cb, data);
+ if (r)
+ break;
+ }
+
+ return r;
+}
+
+int for_each_loose_file_in_objdir(const char *path,
+ each_loose_object_fn obj_cb,
+ each_loose_cruft_fn cruft_cb,
+ each_loose_subdir_fn subdir_cb,
+ void *data)
+{
+ struct strbuf buf = STRBUF_INIT;
+ int r;
+
+ strbuf_addstr(&buf, path);
+ r = for_each_loose_file_in_objdir_buf(&buf, obj_cb, cruft_cb,
+ subdir_cb, data);
+ strbuf_release(&buf);
+
+ return r;
+}
+
+struct loose_alt_odb_data {
+ each_loose_object_fn *cb;
+ void *data;
+};
+
+static int loose_from_alt_odb(struct alternate_object_database *alt,
+ void *vdata)
+{
+ struct loose_alt_odb_data *data = vdata;
+ struct strbuf buf = STRBUF_INIT;
+ int r;
+
+ strbuf_addstr(&buf, alt->path);
+ r = for_each_loose_file_in_objdir_buf(&buf,
+ data->cb, NULL, NULL,
+ data->data);
+ strbuf_release(&buf);
+ return r;
+}
+
+int for_each_loose_object(each_loose_object_fn cb, void *data, unsigned flags)
+{
+ struct loose_alt_odb_data alt;
+ int r;
+
+ r = for_each_loose_file_in_objdir(get_object_directory(),
+ cb, NULL, NULL, data);
+ if (r)
+ return r;
+
+ if (flags & FOR_EACH_OBJECT_LOCAL_ONLY)
+ return 0;
+
+ alt.cb = cb;
+ alt.data = data;
+ return foreach_alt_odb(loose_from_alt_odb, &alt);
+}
+
+static int check_stream_sha1(git_zstream *stream,
+ const char *hdr,
+ unsigned long size,
+ const char *path,
+ const unsigned char *expected_sha1)
+{
+ git_SHA_CTX c;
+ unsigned char real_sha1[GIT_MAX_RAWSZ];
+ unsigned char buf[4096];
+ unsigned long total_read;
+ int status = Z_OK;
+
+ git_SHA1_Init(&c);
+ git_SHA1_Update(&c, hdr, stream->total_out);
+
+ /*
+ * We already read some bytes into hdr, but the ones up to the NUL
+ * do not count against the object's content size.
+ */
+ total_read = stream->total_out - strlen(hdr) - 1;
+
+ /*
+ * This size comparison must be "<=" to read the final zlib packets;
+ * see the comment in unpack_sha1_rest for details.
+ */
+ while (total_read <= size &&
+ (status == Z_OK || status == Z_BUF_ERROR)) {
+ stream->next_out = buf;
+ stream->avail_out = sizeof(buf);
+ if (size - total_read < stream->avail_out)
+ stream->avail_out = size - total_read;
+ status = git_inflate(stream, Z_FINISH);
+ git_SHA1_Update(&c, buf, stream->next_out - buf);
+ total_read += stream->next_out - buf;
+ }
+ git_inflate_end(stream);
+
+ if (status != Z_STREAM_END) {
+ error("corrupt loose object '%s'", sha1_to_hex(expected_sha1));
+ return -1;
+ }
+ if (stream->avail_in) {
+ error("garbage at end of loose object '%s'",
+ sha1_to_hex(expected_sha1));
+ return -1;
+ }
+
+ git_SHA1_Final(real_sha1, &c);
+ if (hashcmp(expected_sha1, real_sha1)) {
+ error("sha1 mismatch for %s (expected %s)", path,
+ sha1_to_hex(expected_sha1));
+ return -1;
+ }
+
+ return 0;
+}
+
+int read_loose_object(const char *path,
+ const unsigned char *expected_sha1,
+ enum object_type *type,
+ unsigned long *size,
+ void **contents)
+{
+ int ret = -1;
+ void *map = NULL;
+ unsigned long mapsize;
+ git_zstream stream;
+ char hdr[32];
+
+ *contents = NULL;
+
+ map = map_sha1_file_1(path, NULL, &mapsize);
+ if (!map) {
+ error_errno("unable to mmap %s", path);
+ goto out;
+ }
+
+ if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) {
+ error("unable to unpack header of %s", path);
+ goto out;
+ }
+
+ *type = parse_sha1_header(hdr, size);
+ if (*type < 0) {
+ error("unable to parse header of %s", path);
+ git_inflate_end(&stream);
+ goto out;
+ }
+
+ if (*type == OBJ_BLOB) {
+ if (check_stream_sha1(&stream, hdr, *size, path, expected_sha1) < 0)
+ goto out;
+ } else {
+ *contents = unpack_sha1_rest(&stream, hdr, *size, expected_sha1);
+ if (!*contents) {
+ error("unable to unpack contents of %s", path);
+ git_inflate_end(&stream);
+ goto out;
+ }
+ if (check_sha1_signature(expected_sha1, *contents,
+ *size, typename(*type))) {
+ error("sha1 mismatch for %s (expected %s)", path,
+ sha1_to_hex(expected_sha1));
+ free(*contents);
+ goto out;
+ }
+ }
+
+ ret = 0; /* everything checks out */
+
+out:
+ if (map)
+ munmap(map, mapsize);
+ return ret;
+}