#include "pack.h"
#include "blob.h"
#include "commit.h"
+#include "run-command.h"
#include "tag.h"
#include "tree.h"
+#include "tree-walk.h"
#include "refs.h"
#include "pack-revindex.h"
#include "sha1-lookup.h"
#endif
#endif
-#ifdef NO_C99_FORMAT
-#define SZ_FMT "lu"
-static unsigned long sz_fmt(size_t s) { return (unsigned long)s; }
-#else
-#define SZ_FMT "zu"
-static size_t sz_fmt(size_t s) { return s; }
-#endif
+#define SZ_FMT PRIuMAX
+static inline uintmax_t sz_fmt(size_t s) { return s; }
const unsigned char null_sha1[20];
-static int git_open_noatime(const char *name, struct packed_git *p);
+/*
+ * This is meant to hold a *small* number of objects that you would
+ * want read_sha1_file() to be able to return, but yet you do not want
+ * to write them into the object store (e.g. a browse-only
+ * application).
+ */
+static struct cached_object {
+ unsigned char sha1[20];
+ enum object_type type;
+ void *buf;
+ unsigned long size;
+} *cached_objects;
+static int cached_object_nr, cached_object_alloc;
+
+static struct cached_object empty_tree = {
+ EMPTY_TREE_SHA1_BIN_LITERAL,
+ OBJ_TREE,
+ "",
+ 0
+};
+
+static struct cached_object *find_cached_object(const unsigned char *sha1)
+{
+ int i;
+ struct cached_object *co = cached_objects;
+
+ for (i = 0; i < cached_object_nr; i++, co++) {
+ if (!hashcmp(co->sha1, sha1))
+ return co;
+ }
+ if (!hashcmp(sha1, empty_tree.sha1))
+ return &empty_tree;
+ return NULL;
+}
+
+int mkdir_in_gitdir(const char *path)
+{
+ if (mkdir(path, 0777)) {
+ int saved_errno = errno;
+ struct stat st;
+ struct strbuf sb = STRBUF_INIT;
+
+ if (errno != EEXIST)
+ return -1;
+ /*
+ * Are we looking at a path in a symlinked worktree
+ * whose original repository does not yet have it?
+ * e.g. .git/rr-cache pointing at its original
+ * repository in which the user hasn't performed any
+ * conflict resolution yet?
+ */
+ if (lstat(path, &st) || !S_ISLNK(st.st_mode) ||
+ strbuf_readlink(&sb, path, st.st_size) ||
+ !is_absolute_path(sb.buf) ||
+ mkdir(sb.buf, 0777)) {
+ strbuf_release(&sb);
+ errno = saved_errno;
+ return -1;
+ }
+ strbuf_release(&sb);
+ }
+ return adjust_shared_perm(path);
+}
int safe_create_leading_directories(char *path)
{
static struct alternate_object_database **alt_odb_tail;
static void read_info_alternates(const char * alternates, int depth);
+static int git_open_noatime(const char *name);
/*
* Prepare alternate object database registry.
int fd;
sprintf(path, "%s/%s", relative_base, alt_file_name);
- fd = git_open_noatime(path, NULL);
+ fd = git_open_noatime(path);
if (fd < 0)
return;
if (fstat(fd, &st) || (st.st_size == 0)) {
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;
struct pack_idx_header *hdr;
size_t idx_size;
uint32_t version, nr, i, *index;
- int fd = git_open_noatime(path, p);
+ int fd = git_open_noatime(path);
struct stat st;
if (fd < 0)
lru_l->next = lru_w->next;
else {
lru_p->windows = lru_w->next;
- if (!lru_p->windows && lru_p->pack_fd != keep_fd) {
+ 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;
}
}
if (strcmp(pack_name, p->pack_name) == 0) {
clear_delta_base_cache();
close_pack_windows(p);
- if (p->pack_fd != -1)
+ 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 (!p->index_data && open_pack_index(p))
return error("packfile %s index unavailable", p->pack_name);
- p->pack_fd = git_open_noatime(p->pack_name, p);
+ if (!pack_max_fds) {
+ struct rlimit lim;
+ unsigned int max_fds;
+
+ if (getrlimit(RLIMIT_NOFILE, &lim))
+ die_errno("cannot get RLIMIT_NOFILE");
+
+ max_fds = lim.rlim_cur;
+
+ /* 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) {
return 0;
if (p->pack_fd != -1) {
close(p->pack_fd);
+ pack_open_fds--;
p->pack_fd = -1;
}
return -1;
{
struct pack_window *win = *w_cursor;
- if (p->pack_fd == -1 && open_packed_git(p))
- die("packfile %s cannot be accessed", p->pack_name);
-
/* 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) {
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;
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)
void install_packed_git(struct packed_git *pack)
{
+ if (pack->pack_fd != -1)
+ pack_open_fds++;
+
pack->next = packed_git;
packed_git = pack;
}
sprintf(path, "%s/pack", objdir);
len = strlen(path);
dir = opendir(path);
- while (!dir && errno == EMFILE && unuse_one_window(NULL, -1))
- dir = opendir(path);
if (!dir) {
if (errno != ENOENT)
error("unable to open object pack directory: %s: %s",
return hashcmp(sha1, real_sha1) ? -1 : 0;
}
-static int git_open_noatime(const char *name, struct packed_git *p)
+static int git_open_noatime(const char *name)
{
static int sha1_file_open_flag = O_NOATIME;
if (fd >= 0)
return fd;
- /* Might the failure be insufficient file descriptors? */
- if (errno == EMFILE) {
- if (unuse_one_window(p, -1))
- continue;
- else
- return -1;
- }
-
/* Might the failure be due to O_NOATIME? */
if (errno != ENOENT && sha1_file_open_flag) {
sha1_file_open_flag = 0;
char *name = sha1_file_name(sha1);
struct alternate_object_database *alt;
- fd = git_open_noatime(name, NULL);
+ fd = git_open_noatime(name);
if (fd >= 0)
return fd;
for (alt = alt_odb_list; alt; alt = alt->next) {
name = alt->name;
fill_sha1_path(name, sha1);
- fd = git_open_noatime(alt->base, NULL);
+ fd = git_open_noatime(alt->base);
if (fd >= 0)
return fd;
}
return map;
}
-static int legacy_loose_object(unsigned char *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;
/*
* Is it a zlib-compressed buffer? If so, the first byte
* must be 0x78 (15-bit window size, deflated), and the
- * first 16-bit word is evenly divisible by 31
+ * first 16-bit word is evenly divisible by 31. If so,
+ * we are looking at the official format, not the experimental
+ * one.
*/
word = (map[0] << 8) + map[1];
if (map[0] == 0x78 && !(word % 31))
- return 1;
- else
return 0;
+ else
+ return 1;
}
unsigned long unpack_object_header_buffer(const unsigned char *buf,
stream->next_out = buffer;
stream->avail_out = bufsiz;
- if (legacy_loose_object(map)) {
- git_inflate_init(stream);
- return git_inflate(stream, 0);
- }
-
+ 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;
- /*
- * 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 don't write it any longer. But 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;
+ /* Set up the stream for the rest.. */
+ stream->next_in = map;
+ stream->avail_in = mapsize;
+ git_inflate_init(stream);
- /* Set up the stream for the rest.. */
- stream->next_in = map;
- stream->avail_in = mapsize;
+ /* And generate the fake traditional header */
+ stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
+ typename(type), size);
+ return 0;
+ }
git_inflate_init(stream);
-
- /* And generate the fake traditional header */
- stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
- typename(type), size);
- return 0;
+ return git_inflate(stream, 0);
}
static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
/*
* The above condition must be (bytes <= size), not
* (bytes < size). In other words, even though we
- * expect no more output and set avail_out to zer0,
+ * expect no more output and set avail_out to zero,
* the input zlib stream may have bytes that express
* "this concludes the stream", and we *do* want to
* eat that input.
enum object_type type;
/* use_pack() assures us we have [base, base + 20) available
- * as a range that we can look at at. (Its actually the hash
+ * 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.
return 0;
}
+static 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 find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
{
static struct packed_git *last_found = (void *)1;
* it may have been deleted since the index
* was loaded!
*/
- if (p->pack_fd == -1 && open_packed_git(p)) {
+ if (!is_pack_valid(p)) {
error("packfile %s cannot be accessed", p->pack_name);
goto next;
}
int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
{
+ struct cached_object *co;
struct pack_entry e;
int status;
+ co = find_cached_object(sha1);
+ if (co) {
+ if (sizep)
+ *sizep = co->size;
+ return co->type;
+ }
+
if (!find_pack_entry(sha1, &e)) {
/* Most likely it's a loose object. */
status = sha1_loose_object_info(sha1, sizep);
return data;
}
-/*
- * This is meant to hold a *small* number of objects that you would
- * want read_sha1_file() to be able to return, but yet you do not want
- * to write them into the object store (e.g. a browse-only
- * application).
- */
-static struct cached_object {
- unsigned char sha1[20];
- enum object_type type;
- void *buf;
- unsigned long size;
-} *cached_objects;
-static int cached_object_nr, cached_object_alloc;
-
-static struct cached_object empty_tree = {
- EMPTY_TREE_SHA1_BIN,
- OBJ_TREE,
- "",
- 0
-};
-
-static struct cached_object *find_cached_object(const unsigned char *sha1)
-{
- int i;
- struct cached_object *co = cached_objects;
-
- for (i = 0; i < cached_object_nr; i++, co++) {
- if (!hashcmp(co->sha1, sha1))
- return co;
- }
- if (!hashcmp(sha1, empty_tree.sha1))
- return &empty_tree;
- return NULL;
-}
-
int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
unsigned char *sha1)
{
* deal with them should arrange to call read_object() and give error
* messages themselves.
*/
-void *read_sha1_file_repl(const unsigned char *sha1,
- enum object_type *type,
- unsigned long *size,
- const unsigned char **replacement)
+void *read_sha1_file_extended(const unsigned char *sha1,
+ enum object_type *type,
+ unsigned long *size,
+ unsigned flag)
{
- const unsigned char *repl = lookup_replace_object(sha1);
void *data;
char *path;
const struct packed_git *p;
+ const unsigned char *repl = (flag & READ_SHA1_FILE_REPLACE)
+ ? lookup_replace_object(sha1) : sha1;
errno = 0;
data = read_object(repl, type, size);
- if (data) {
- if (replacement)
- *replacement = repl;
+ if (data)
return data;
- }
if (errno && errno != ENOENT)
die_errno("failed to read object %s", sha1_to_hex(sha1));
filename = sha1_file_name(sha1);
fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
- while (fd < 0 && errno == EMFILE && unuse_one_window(NULL, -1))
- fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
if (fd < 0) {
if (errno == EACCES)
return error("insufficient permission for adding an object to repository database %s\n", get_object_directory());
return has_loose_object(sha1);
}
+static void check_tree(const void *buf, size_t size)
+{
+ struct tree_desc desc;
+ struct name_entry entry;
+
+ init_tree_desc(&desc, buf, size);
+ while (tree_entry(&desc, &entry))
+ /* do nothing
+ * tree_entry() will die() on malformed entries */
+ ;
+}
+
+static void check_commit(const void *buf, size_t size)
+{
+ struct commit c;
+ memset(&c, 0, sizeof(c));
+ if (parse_commit_buffer(&c, buf, size))
+ die("corrupt commit");
+}
+
+static void check_tag(const void *buf, size_t size)
+{
+ struct tag t;
+ memset(&t, 0, sizeof(t));
+ if (parse_tag_buffer(&t, buf, size))
+ die("corrupt tag");
+}
+
static int index_mem(unsigned char *sha1, void *buf, size_t size,
- int write_object, enum object_type type, const char *path)
+ enum object_type type,
+ const char *path, unsigned flags)
{
int ret, re_allocated = 0;
+ int write_object = flags & HASH_WRITE_OBJECT;
if (!type)
type = OBJ_BLOB;
re_allocated = 1;
}
}
+ if (flags & HASH_FORMAT_CHECK) {
+ if (type == OBJ_TREE)
+ check_tree(buf, size);
+ if (type == OBJ_COMMIT)
+ check_commit(buf, size);
+ if (type == OBJ_TAG)
+ check_tag(buf, size);
+ }
if (write_object)
ret = write_sha1_file(buf, size, typename(type), sha1);
return ret;
}
+static int index_pipe(unsigned char *sha1, 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);
+ else
+ ret = -1;
+ strbuf_release(&sbuf);
+ return ret;
+}
+
#define SMALL_FILE_SIZE (32*1024)
-int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
- enum object_type type, const char *path)
+static int index_core(unsigned char *sha1, int fd, size_t size,
+ 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)) {
- struct strbuf sbuf = STRBUF_INIT;
- if (strbuf_read(&sbuf, fd, 4096) >= 0)
- ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
- type, path);
- else
- ret = -1;
- strbuf_release(&sbuf);
- } else if (!size) {
- ret = index_mem(sha1, NULL, size, write_object, type, path);
+ if (!size) {
+ ret = index_mem(sha1, NULL, 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, write_object, type,
- path);
+ ret = index_mem(sha1, buf, size, type, path, flags);
else
ret = error("short read %s", strerror(errno));
free(buf);
} else {
void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
- ret = index_mem(sha1, buf, size, write_object, type, path);
+ ret = index_mem(sha1, buf, size, type, path, flags);
munmap(buf, size);
}
+ return ret;
+}
+
+/*
+ * This creates one packfile per large blob, because the caller
+ * immediately wants the result sha1, and fast-import can report the
+ * object name via marks mechanism only by closing the created
+ * packfile.
+ *
+ * This also bypasses the usual "convert-to-git" dance, and that is on
+ * purpose. We could write a streaming version of the converting
+ * functions and insert that before feeding the data to fast-import
+ * (or equivalent in-core API described above), but the primary
+ * motivation for trying to stream from the working tree file and to
+ * avoid mmaping it in core is to deal with large binary blobs, and
+ * by definition they do _not_ want to get any conversion.
+ */
+static int index_stream(unsigned char *sha1, int fd, size_t size,
+ enum object_type type, const char *path,
+ unsigned flags)
+{
+ struct child_process fast_import;
+ char export_marks[512];
+ const char *argv[] = { "fast-import", "--quiet", export_marks, NULL };
+ char tmpfile[512];
+ char fast_import_cmd[512];
+ char buf[512];
+ int len, tmpfd;
+
+ strcpy(tmpfile, git_path("hashstream_XXXXXX"));
+ tmpfd = git_mkstemp_mode(tmpfile, 0600);
+ if (tmpfd < 0)
+ die_errno("cannot create tempfile: %s", tmpfile);
+ if (close(tmpfd))
+ die_errno("cannot close tempfile: %s", tmpfile);
+ sprintf(export_marks, "--export-marks=%s", tmpfile);
+
+ memset(&fast_import, 0, sizeof(fast_import));
+ fast_import.in = -1;
+ fast_import.argv = argv;
+ fast_import.git_cmd = 1;
+ if (start_command(&fast_import))
+ die_errno("index-stream: git fast-import failed");
+
+ len = sprintf(fast_import_cmd, "blob\nmark :1\ndata %lu\n",
+ (unsigned long) size);
+ write_or_whine(fast_import.in, fast_import_cmd, len,
+ "index-stream: feeding fast-import");
+ while (size) {
+ char buf[10240];
+ size_t sz = size < sizeof(buf) ? size : sizeof(buf);
+ size_t actual;
+
+ actual = read_in_full(fd, buf, sz);
+ if (actual < 0)
+ die_errno("index-stream: reading input");
+ if (write_in_full(fast_import.in, buf, actual) != actual)
+ die_errno("index-stream: feeding fast-import");
+ size -= actual;
+ }
+ if (close(fast_import.in))
+ die_errno("index-stream: closing fast-import");
+ if (finish_command(&fast_import))
+ die_errno("index-stream: finishing fast-import");
+
+ tmpfd = open(tmpfile, O_RDONLY);
+ if (tmpfd < 0)
+ die_errno("index-stream: cannot open fast-import mark");
+ len = read(tmpfd, buf, sizeof(buf));
+ if (len < 0)
+ die_errno("index-stream: reading fast-import mark");
+ if (close(tmpfd) < 0)
+ die_errno("index-stream: closing fast-import mark");
+ if (unlink(tmpfile))
+ die_errno("index-stream: unlinking fast-import mark");
+ if (len != 44 ||
+ memcmp(":1 ", buf, 3) ||
+ get_sha1_hex(buf + 3, sha1))
+ die_errno("index-stream: unexpected fast-import mark: <%s>", buf);
+ return 0;
+}
+
+int index_fd(unsigned char *sha1, 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)
+ ret = index_core(sha1, fd, size, type, path, flags);
+ else
+ ret = index_stream(sha1, fd, size, type, path, flags);
close(fd);
return ret;
}
-int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object)
+int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags)
{
int fd;
struct strbuf sb = STRBUF_INIT;
if (fd < 0)
return error("open(\"%s\"): %s", path,
strerror(errno));
- if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path) < 0)
+ if (index_fd(sha1, fd, st, OBJ_BLOB, path, flags) < 0)
return error("%s: failed to insert into database",
path);
break;
return error("readlink(\"%s\"): %s", path,
errstr);
}
- if (!write_object)
+ 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",