#include "mru.h"
#include "list.h"
#include "mergesort.h"
-
-#ifndef O_NOATIME
-#if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
-#define O_NOATIME 01000000
-#else
-#define O_NOATIME 0
-#endif
-#endif
+#include "quote.h"
#define SZ_FMT PRIuMAX
static inline uintmax_t sz_fmt(size_t s) { return s; }
return buf->buf;
}
-/*
- * Return the name of the pack or index file with the specified sha1
- * in its filename. *base and *name are scratch space that must be
- * provided by the caller. which should be "pack" or "idx".
- */
-static char *sha1_get_pack_name(const unsigned char *sha1,
- struct strbuf *buf,
- const char *which)
+ char *odb_pack_name(struct strbuf *buf,
+ const unsigned char *sha1,
+ const char *ext)
{
strbuf_reset(buf);
strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(),
- sha1_to_hex(sha1), which);
+ sha1_to_hex(sha1), ext);
return buf->buf;
}
char *sha1_pack_name(const unsigned char *sha1)
{
static struct strbuf buf = STRBUF_INIT;
- return sha1_get_pack_name(sha1, &buf, "pack");
+ return odb_pack_name(&buf, sha1, "pack");
}
char *sha1_pack_index_name(const unsigned char *sha1)
{
static struct strbuf buf = STRBUF_INIT;
- return sha1_get_pack_name(sha1, &buf, "idx");
+ return odb_pack_name(&buf, sha1, "idx");
}
struct alternate_object_database *alt_odb_list;
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_addstr(&pathbuf, entry);
return 0;
}
+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 len, int sep,
const char *relative_base, int depth)
{
- struct string_list entries = STRING_LIST_INIT_NODUP;
- char *alt_copy;
- int i;
struct strbuf objdirbuf = STRBUF_INIT;
+ struct strbuf entry = STRBUF_INIT;
if (depth > 5) {
error("%s: ignoring alternate object stores, nesting too deep.",
die("unable to normalize object directory: %s",
objdirbuf.buf);
- alt_copy = xmemdupz(alt, len);
- string_list_split_in_place(&entries, alt_copy, sep, -1);
- for (i = 0; i < entries.nr; i++) {
- const char *entry = entries.items[i].string;
- if (entry[0] == '\0' || entry[0] == '#')
+ while (*alt) {
+ alt = parse_alt_odb_entry(alt, sep, &entry);
+ if (!entry.len)
continue;
- link_alt_odb_entry(entry, relative_base, depth, objdirbuf.buf);
+ link_alt_odb_entry(entry.buf, relative_base, depth, objdirbuf.buf);
}
- string_list_clear(&entries, 0);
- free(alt_copy);
+ strbuf_release(&entry);
strbuf_release(&objdirbuf);
}
int fd;
path = xstrfmt("%s/info/alternates", relative_base);
- fd = git_open_noatime(path);
+ fd = git_open(path);
free(path);
if (fd < 0)
return;
struct pack_idx_header *hdr;
size_t idx_size;
uint32_t version, nr, i, *index;
- int fd = git_open_noatime(path);
+ int fd = git_open(path);
struct stat st;
if (fd < 0)
while (pack_max_fds <= pack_open_fds && close_one_pack())
; /* nothing */
- p->pack_fd = git_open_noatime(p->pack_name);
+ p->pack_fd = git_open(p->pack_name);
if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
return -1;
pack_open_fds++;
strbuf_release(&path);
}
+static int approximate_object_count_valid;
+
+/*
+ * Give a fast, rough count of the number of objects in the repository. This
+ * ignores loose objects completely. If you have a lot of them, then either
+ * you should repack because your performance will be awful, or they are
+ * all unreachable objects about to be pruned, in which case they're not really
+ * interesting as a measure of repo size in the first place.
+ */
+unsigned long approximate_object_count(void)
+{
+ static unsigned long count;
+ if (!approximate_object_count_valid) {
+ struct packed_git *p;
+
+ prepare_packed_git();
+ count = 0;
+ for (p = packed_git; p; p = p->next) {
+ if (open_pack_index(p))
+ continue;
+ count += p->num_objects;
+ }
+ }
+ return count;
+}
+
static void *get_next_packed_git(const void *p)
{
return ((const struct packed_git *)p)->next;
void reprepare_packed_git(void)
{
+ approximate_object_count_valid = 0;
prepare_packed_git_run_once = 0;
prepare_packed_git();
}
return hashcmp(sha1, real_sha1) ? -1 : 0;
}
-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;
+ 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);
+ }
- errno = 0;
- fd = open(name, O_RDONLY | sha1_file_open_flag);
- if (fd >= 0)
- return fd;
+#if defined(F_GETFL) && defined(F_SETFL) && defined(FD_CLOEXEC)
+ {
+ static int fd_cloexec = FD_CLOEXEC;
- /* Might the failure be due to O_NOATIME? */
- if (errno != ENOENT && sha1_file_open_flag) {
- sha1_file_open_flag = 0;
- continue;
+ if (!o_cloexec && 0 <= fd && fd_cloexec) {
+ /* Opened w/o O_CLOEXEC? try with fcntl(2) to add it */
+ int flags = fcntl(fd, F_GETFL);
+ if (fcntl(fd, F_SETFL, flags | fd_cloexec))
+ fd_cloexec = 0;
}
-
- return -1;
}
+#endif
+ return fd;
}
-static int stat_sha1_file(const unsigned char *sha1, struct stat *st)
+/*
+ * 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;
- if (!lstat(sha1_file_name(sha1), st))
+ *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) {
- const char *path = alt_sha1_path(alt, sha1);
- if (!lstat(path, st))
+ *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;
struct alternate_object_database *alt;
int most_interesting_errno;
- fd = git_open_noatime(sha1_file_name(sha1));
+ *path = sha1_file_name(sha1);
+ fd = git_open(*path);
if (fd >= 0)
return fd;
most_interesting_errno = errno;
prepare_alt_odb();
for (alt = alt_odb_list; alt; alt = alt->next) {
- const char *path = alt_sha1_path(alt, sha1);
- fd = git_open_noatime(path);
+ *path = alt_sha1_path(alt, sha1);
+ fd = git_open(*path);
if (fd >= 0)
return fd;
if (most_interesting_errno == ENOENT)
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;
}
+void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
+{
+ return map_sha1_file_1(NULL, sha1, size);
+}
+
unsigned long unpack_object_header_buffer(const unsigned char *buf,
unsigned long len, enum object_type *type, unsigned long *sizep)
{
int parse_sha1_header(const char *hdr, unsigned long *sizep)
{
- struct object_info oi;
+ struct object_info oi = OBJECT_INFO_INIT;
oi.sizep = sizep;
- oi.typename = NULL;
- oi.typep = NULL;
return parse_sha1_header_extended(hdr, &oi, LOOKUP_REPLACE_OBJECT);
}
goto out;
}
-static int packed_object_info(struct packed_git *p, off_t obj_offset,
- struct object_info *oi)
+int packed_object_info(struct packed_git *p, off_t obj_offset,
+ struct object_info *oi)
{
struct pack_window *w_curs = NULL;
unsigned long size;
void clear_delta_base_cache(void)
{
- struct hashmap_iter iter;
- struct delta_base_cache_entry *entry;
- for (entry = hashmap_iter_first(&delta_base_cache, &iter);
- entry;
- entry = hashmap_iter_next(&iter)) {
+ struct list_head *lru, *tmp;
+ list_for_each_safe(lru, tmp, &delta_base_cache_lru) {
+ struct delta_base_cache_entry *entry =
+ list_entry(lru, struct delta_base_cache_entry, lru);
release_delta_base_cache(entry);
}
}
while (delta_stack_nr) {
void *delta_data;
void *base = data;
+ void *external_base = NULL;
unsigned long delta_size, base_size = size;
int i;
p->pack_name);
mark_bad_packed_object(p, base_sha1);
base = read_object(base_sha1, &type, &base_size);
+ external_base = base;
}
}
"at offset %"PRIuMAX" from %s",
(uintmax_t)curpos, p->pack_name);
data = NULL;
+ free(external_base);
continue;
}
error("failed to apply delta");
free(delta_data);
+ free(external_base);
}
*final_type = type;
* object even exists.
*/
if (!oi->typep && !oi->typename && !oi->sizep) {
+ const char *path;
struct stat st;
- if (stat_sha1_file(sha1, &st) < 0)
+ if (stat_sha1_file(sha1, &st, &path) < 0)
return -1;
if (oi->disk_sizep)
*oi->disk_sizep = st.st_size;
int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
{
enum object_type type;
- struct object_info oi = {NULL};
+ struct object_info oi = OBJECT_INFO_INIT;
oi.typep = &type;
oi.sizep = sizep;
{
void *data;
const struct packed_git *p;
+ const char *path;
+ struct stat st;
const unsigned char *repl = lookup_replace_object_extended(sha1, flag);
errno = 0;
die("replacement %s not found for %s",
sha1_to_hex(repl), sha1_to_hex(sha1));
- if (has_loose_object(repl)) {
- const char *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",
return has_sha1_file(oid->hash);
}
+int has_object_file_with_flags(const struct object_id *oid, int flags)
+{
+ return has_sha1_file_with_flags(oid->hash, flags);
+}
+
static void check_tree(const void *buf, size_t size)
{
struct tree_desc desc;
}
return r ? r : pack_errors;
}
+
+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_SHA1_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;
+ int fd = -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);
+ if (fd >= 0)
+ close(fd);
+ return ret;
+}