#include "refs.h"
#include "pack-revindex.h"
#include "sha1-lookup.h"
+#include "bulk-checkin.h"
+#include "streaming.h"
#ifndef O_NOATIME
#if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
0
};
+static struct packed_git *last_found_pack;
+
static struct cached_object *find_cached_object(const unsigned char *sha1)
{
int i;
struct alternate_object_database *alt_odb_list;
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);
/*
const char *objdir = get_object_directory();
struct alternate_object_database *ent;
struct alternate_object_database *alt;
- /* 43 = 40-byte + 2 '/' + terminating NUL */
- int pfxlen = len;
- int entlen = pfxlen + 43;
- int base_len = -1;
+ int pfxlen, entlen;
+ struct strbuf pathbuf = STRBUF_INIT;
if (!is_absolute_path(entry) && relative_base) {
- /* Relative alt-odb */
- if (base_len < 0)
- base_len = strlen(relative_base) + 1;
- entlen += base_len;
- pfxlen += base_len;
+ strbuf_addstr(&pathbuf, real_path(relative_base));
+ strbuf_addch(&pathbuf, '/');
}
- ent = xmalloc(sizeof(*ent) + entlen);
+ strbuf_add(&pathbuf, entry, len);
- if (!is_absolute_path(entry) && relative_base) {
- memcpy(ent->base, relative_base, base_len - 1);
- ent->base[base_len - 1] = '/';
- memcpy(ent->base + base_len, entry, len);
- }
- else
- memcpy(ent->base, entry, pfxlen);
+ normalize_path_copy(pathbuf.buf, pathbuf.buf);
+
+ pfxlen = strlen(pathbuf.buf);
+
+ /*
+ * 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] = '/';
return -1;
}
}
- if (!memcmp(ent->base, objdir, pfxlen)) {
+ if (!strcmp(ent->base, objdir)) {
free(ent);
return -1;
}
}
}
-static void read_info_alternates(const char * relative_base, int depth)
+void read_info_alternates(const char * relative_base, int depth)
{
char *map;
size_t mapsz;
close_pack_index(p);
free(p->bad_object_sha1);
*pp = p->next;
+ if (last_found_pack == p)
+ last_found_pack = NULL;
free(p);
return;
}
}
}
+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.
return error("packfile %s index unavailable", p->pack_name);
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;
+ unsigned int max_fds = get_max_fd_limit();
/* Save 3 for stdin/stdout/stderr, 22 for work */
if (25 < max_fds)
return NULL;
}
-int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type)
+/*
+ * With an in-core object data in "map", rehash it to make sure the
+ * object name actually matches "sha1" to detect object corruption.
+ * With "map" == NULL, try reading the object named with "sha1" using
+ * the streaming interface and rehash it to do the same.
+ */
+int check_sha1_signature(const unsigned char *sha1, void *map,
+ unsigned long size, const char *type)
{
unsigned char real_sha1[20];
- hash_sha1_file(map, size, type, real_sha1);
+ enum object_type obj_type;
+ struct git_istream *st;
+ git_SHA_CTX c;
+ char hdr[32];
+ int hdrlen;
+
+ if (map) {
+ hash_sha1_file(map, size, type, real_sha1);
+ return hashcmp(sha1, real_sha1) ? -1 : 0;
+ }
+
+ st = open_istream(sha1, &obj_type, &size, NULL);
+ if (!st)
+ return -1;
+
+ /* Generate the header */
+ hdrlen = sprintf(hdr, "%s %lu", typename(obj_type), size) + 1;
+
+ /* Sha1.. */
+ git_SHA1_Init(&c);
+ git_SHA1_Update(&c, hdr, hdrlen);
+ for (;;) {
+ char buf[1024 * 16];
+ ssize_t readlen = read_istream(st, buf, sizeof(buf));
+
+ if (!readlen)
+ break;
+ git_SHA1_Update(&c, buf, readlen);
+ }
+ git_SHA1_Final(real_sha1, &c);
+ close_istream(st);
return hashcmp(sha1, real_sha1) ? -1 : 0;
}
return -1;
}
-static void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
+void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
{
void *map;
int fd;
if (!fstat(fd, &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));
+ return NULL;
+ }
map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0);
}
close(fd);
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. If so,
- * we are looking at the official format, not the experimental
- * one.
+ * 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] == 0x78 && !(word % 31))
+ if ((map[0] & 0x8F) == 0x08 && !(word % 31))
return 0;
else
return 1;
while (c & 0x80) {
if (len <= used || bitsizeof(long) <= shift) {
error("bad object header");
- return 0;
+ size = used = 0;
+ break;
}
c = buf[used++];
size += (c & 0x7f) << shift;
return used;
}
-static int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
+int unpack_sha1_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] = {
* too permissive for what we want to check. So do an anal
* object header parse by hand.
*/
-static int parse_sha1_header(const char *hdr, unsigned long *sizep)
+int parse_sha1_header(const char *hdr, unsigned long *sizep)
{
char type[10];
int i;
/* forward declaration for a mutually recursive function */
static int packed_object_info(struct packed_git *p, off_t offset,
- unsigned long *sizep);
+ unsigned long *sizep, int *rtype);
static int packed_delta_info(struct packed_git *p,
struct pack_window **w_curs,
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);
+ type = packed_object_info(p, base_offset, NULL, NULL);
if (type <= OBJ_NONE) {
struct revindex_entry *revidx;
const unsigned char *base_sha1;
return type;
}
-static int unpack_object_header(struct packed_git *p,
- struct pack_window **w_curs,
- off_t *curpos,
- unsigned long *sizep)
+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;
return type;
}
-const char *packed_object_info_detail(struct packed_git *p,
- off_t obj_offset,
- unsigned long *size,
- unsigned long *store_size,
- unsigned int *delta_chain_length,
- unsigned char *base_sha1)
-{
- struct pack_window *w_curs = NULL;
- off_t curpos;
- unsigned long dummy;
- unsigned char *next_sha1;
- enum object_type type;
- struct revindex_entry *revidx;
-
- *delta_chain_length = 0;
- curpos = obj_offset;
- type = unpack_object_header(p, &w_curs, &curpos, size);
-
- revidx = find_pack_revindex(p, obj_offset);
- *store_size = revidx[1].offset - obj_offset;
-
- for (;;) {
- switch (type) {
- default:
- die("pack %s contains unknown object type %d",
- p->pack_name, type);
- case OBJ_COMMIT:
- case OBJ_TREE:
- case OBJ_BLOB:
- case OBJ_TAG:
- unuse_pack(&w_curs);
- return typename(type);
- case OBJ_OFS_DELTA:
- obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
- if (!obj_offset)
- die("pack %s contains bad delta base reference of type %s",
- p->pack_name, typename(type));
- if (*delta_chain_length == 0) {
- revidx = find_pack_revindex(p, obj_offset);
- hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr));
- }
- break;
- case OBJ_REF_DELTA:
- next_sha1 = use_pack(p, &w_curs, curpos, NULL);
- if (*delta_chain_length == 0)
- hashcpy(base_sha1, next_sha1);
- obj_offset = find_pack_entry_one(next_sha1, p);
- break;
- }
- (*delta_chain_length)++;
- curpos = obj_offset;
- type = unpack_object_header(p, &w_curs, &curpos, &dummy);
- }
-}
-
static int packed_object_info(struct packed_git *p, off_t obj_offset,
- unsigned long *sizep)
+ unsigned long *sizep, int *rtype)
{
struct pack_window *w_curs = NULL;
unsigned long size;
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:
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)
{
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,
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;
return 0;
}
-static int is_pack_valid(struct packed_git *p)
+int is_pack_valid(struct packed_git *p)
{
/* An already open pack is known to be valid. */
if (p->pack_fd != -1)
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;
+ }
+
+ offset = find_pack_entry_one(sha1, p);
+ if (!offset)
+ return 0;
+
+ /*
+ * 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!
+ */
+ 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)
{
- static struct packed_git *last_found = (void *)1;
struct packed_git *p;
- off_t offset;
prepare_packed_git();
if (!packed_git)
return 0;
- p = (last_found == (void *)1) ? packed_git : last_found;
- do {
- 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))
- goto next;
- }
+ if (last_found_pack && fill_pack_entry(sha1, e, last_found_pack))
+ return 1;
- offset = find_pack_entry_one(sha1, p);
- if (offset) {
- /*
- * 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!
- */
- if (!is_pack_valid(p)) {
- error("packfile %s cannot be accessed", p->pack_name);
- goto next;
- }
- e->offset = offset;
- e->p = p;
- hashcpy(e->sha1, sha1);
- last_found = p;
- return 1;
- }
+ for (p = packed_git; p; p = p->next) {
+ if (p == last_found_pack || !fill_pack_entry(sha1, e, p))
+ continue;
- next:
- if (p == last_found)
- p = packed_git;
- else
- p = p->next;
- if (p == last_found)
- p = p->next;
- } while (p);
+ last_found_pack = p;
+ return 1;
+ }
return 0;
}
return status;
}
-int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+/* returns enum object_type or negative */
+int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi)
{
struct cached_object *co;
struct pack_entry e;
- int status;
+ int status, rtype;
co = find_cached_object(sha1);
if (co) {
- if (sizep)
- *sizep = co->size;
+ if (oi->sizep)
+ *(oi->sizep) = co->size;
+ oi->whence = OI_CACHED;
return co->type;
}
if (!find_pack_entry(sha1, &e)) {
/* Most likely it's a loose object. */
- status = sha1_loose_object_info(sha1, sizep);
- if (status >= 0)
+ status = sha1_loose_object_info(sha1, oi->sizep);
+ if (status >= 0) {
+ oi->whence = OI_LOOSE;
return status;
+ }
/* Not a loose object; someone else may have just packed it. */
reprepare_packed_git();
return status;
}
- status = packed_object_info(e.p, e.offset, sizep);
+ 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(sha1, sizep);
+ 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;
+ 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;
}
+int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+{
+ struct object_info oi;
+
+ oi.sizep = sizep;
+ return sha1_object_info_extended(sha1, &oi);
+}
+
static void *read_packed_sha1(const unsigned char *sha1,
enum object_type *type, unsigned long *size)
{
unlink_or_warn(tmpfile);
if (ret) {
if (ret != EEXIST) {
- return error("unable to write sha1 filename %s: %s\n", filename, strerror(ret));
+ return error("unable to write sha1 filename %s: %s", filename, strerror(ret));
}
/* FIXME!!! Collision check here ? */
}
git_SHA_CTX c;
unsigned char parano_sha1[20];
char *filename;
- static char tmpfile[PATH_MAX];
+ static char tmp_file[PATH_MAX];
filename = sha1_file_name(sha1);
- fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
+ fd = create_tmpfile(tmp_file, sizeof(tmp_file), filename);
if (fd < 0) {
if (errno == EACCES)
- return error("insufficient permission for adding an object to repository database %s\n", get_object_directory());
+ return error("insufficient permission for adding an object to repository database %s", get_object_directory());
else
- return error("unable to create temporary sha1 filename %s: %s\n", tmpfile, strerror(errno));
+ return error("unable to create temporary file: %s", strerror(errno));
}
/* Set it up */
struct utimbuf utb;
utb.actime = mtime;
utb.modtime = mtime;
- if (utime(tmpfile, &utb) < 0)
+ if (utime(tmp_file, &utb) < 0)
warning("failed utime() on %s: %s",
- tmpfile, strerror(errno));
+ tmp_file, strerror(errno));
}
- return move_temp_to_file(tmpfile, filename);
+ return move_temp_to_file(tmp_file, filename);
}
int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
if ((type == OBJ_BLOB) && path) {
struct strbuf nbuf = STRBUF_INIT;
if (convert_to_git(path, buf, size, &nbuf,
- write_object ? safe_crlf : 0)) {
+ write_object ? safe_crlf : SAFE_CRLF_FALSE)) {
buf = strbuf_detach(&nbuf, &size);
re_allocated = 1;
}
}
/*
- * 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 creates one packfile per large blob unless bulk-checkin
+ * machinery is "plugged".
*
* 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.
+ * (or equivalent in-core API described above). However, that is
+ * somewhat complicated, as we do not know the size of the filter
+ * result, which we need to know beforehand when writing a git object.
+ * Since 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, 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,
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;
+ return index_bulk_checkin(sha1, fd, size, type, path, flags);
}
int index_fd(unsigned char *sha1, int fd, struct stat *st,
if (!S_ISREG(st->st_mode))
ret = index_pipe(sha1, fd, type, path, flags);
- else if (size <= big_file_threshold || type != OBJ_BLOB)
+ 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);
else
ret = index_stream(sha1, fd, size, type, path, flags);