2011-10-29 05:48:40 +08:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2011, Google Inc.
|
|
|
|
*/
|
2014-09-14 15:40:45 +08:00
|
|
|
#include "cache.h"
|
2011-10-29 05:48:40 +08:00
|
|
|
#include "bulk-checkin.h"
|
|
|
|
#include "csum-file.h"
|
|
|
|
#include "pack.h"
|
2014-03-03 17:24:29 +08:00
|
|
|
#include "strbuf.h"
|
2017-08-19 06:20:26 +08:00
|
|
|
#include "packfile.h"
|
2011-10-29 05:48:40 +08:00
|
|
|
|
|
|
|
static struct bulk_checkin_state {
|
|
|
|
unsigned plugged:1;
|
|
|
|
|
|
|
|
char *pack_tmp_name;
|
2018-02-01 10:18:46 +08:00
|
|
|
struct hashfile *f;
|
2011-10-29 05:48:40 +08:00
|
|
|
off_t offset;
|
|
|
|
struct pack_idx_option pack_idx_opts;
|
|
|
|
|
|
|
|
struct pack_idx_entry **written;
|
|
|
|
uint32_t alloc_written;
|
|
|
|
uint32_t nr_written;
|
|
|
|
} state;
|
|
|
|
|
|
|
|
static void finish_bulk_checkin(struct bulk_checkin_state *state)
|
|
|
|
{
|
2015-03-14 07:39:32 +08:00
|
|
|
struct object_id oid;
|
2014-03-03 17:24:29 +08:00
|
|
|
struct strbuf packname = STRBUF_INIT;
|
2011-10-29 05:48:40 +08:00
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!state->f)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (state->nr_written == 0) {
|
|
|
|
close(state->f->fd);
|
|
|
|
unlink(state->pack_tmp_name);
|
|
|
|
goto clear_exit;
|
|
|
|
} else if (state->nr_written == 1) {
|
2018-02-01 10:18:46 +08:00
|
|
|
hashclose(state->f, oid.hash, CSUM_FSYNC);
|
2011-10-29 05:48:40 +08:00
|
|
|
} else {
|
2018-02-01 10:18:46 +08:00
|
|
|
int fd = hashclose(state->f, oid.hash, 0);
|
2015-03-14 07:39:32 +08:00
|
|
|
fixup_pack_header_footer(fd, oid.hash, state->pack_tmp_name,
|
|
|
|
state->nr_written, oid.hash,
|
2011-10-29 05:48:40 +08:00
|
|
|
state->offset);
|
|
|
|
close(fd);
|
|
|
|
}
|
|
|
|
|
2014-03-03 17:24:29 +08:00
|
|
|
strbuf_addf(&packname, "%s/pack/pack-", get_object_directory());
|
|
|
|
finish_tmp_packfile(&packname, state->pack_tmp_name,
|
2011-10-29 05:48:40 +08:00
|
|
|
state->written, state->nr_written,
|
2015-03-14 07:39:32 +08:00
|
|
|
&state->pack_idx_opts, oid.hash);
|
2011-10-29 05:48:40 +08:00
|
|
|
for (i = 0; i < state->nr_written; i++)
|
|
|
|
free(state->written[i]);
|
|
|
|
|
|
|
|
clear_exit:
|
|
|
|
free(state->written);
|
|
|
|
memset(state, 0, sizeof(*state));
|
|
|
|
|
2014-03-03 17:24:29 +08:00
|
|
|
strbuf_release(&packname);
|
2011-10-29 05:48:40 +08:00
|
|
|
/* Make objects we just wrote available to ourselves */
|
|
|
|
reprepare_packed_git();
|
|
|
|
}
|
|
|
|
|
|
|
|
static int already_written(struct bulk_checkin_state *state, unsigned char sha1[])
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
/* The object may already exist in the repository */
|
|
|
|
if (has_sha1_file(sha1))
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
/* Might want to keep the list sorted */
|
|
|
|
for (i = 0; i < state->nr_written; i++)
|
2017-05-07 06:10:11 +08:00
|
|
|
if (!hashcmp(state->written[i]->oid.hash, sha1))
|
2011-10-29 05:48:40 +08:00
|
|
|
return 1;
|
|
|
|
|
|
|
|
/* This is a new object we need to keep */
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Read the contents from fd for size bytes, streaming it to the
|
|
|
|
* packfile in state while updating the hash in ctx. Signal a failure
|
|
|
|
* by returning a negative value when the resulting pack would exceed
|
|
|
|
* the pack size limit and this is not the first object in the pack,
|
|
|
|
* so that the caller can discard what we wrote from the current pack
|
|
|
|
* by truncating it and opening a new one. The caller will then call
|
|
|
|
* us again after rewinding the input fd.
|
|
|
|
*
|
|
|
|
* The already_hashed_to pointer is kept untouched by the caller to
|
|
|
|
* make sure we do not hash the same byte when we are called
|
|
|
|
* again. This way, the caller does not have to checkpoint its hash
|
|
|
|
* status before calling us just in case we ask it to call us again
|
|
|
|
* with a new pack.
|
|
|
|
*/
|
|
|
|
static int stream_to_pack(struct bulk_checkin_state *state,
|
2018-02-01 10:18:48 +08:00
|
|
|
git_hash_ctx *ctx, off_t *already_hashed_to,
|
2011-10-29 05:48:40 +08:00
|
|
|
int fd, size_t size, enum object_type type,
|
|
|
|
const char *path, unsigned flags)
|
|
|
|
{
|
|
|
|
git_zstream s;
|
|
|
|
unsigned char obuf[16384];
|
|
|
|
unsigned hdrlen;
|
|
|
|
int status = Z_OK;
|
|
|
|
int write_object = (flags & HASH_WRITE_OBJECT);
|
|
|
|
off_t offset = 0;
|
|
|
|
|
|
|
|
git_deflate_init(&s, pack_compression_level);
|
|
|
|
|
encode_in_pack_object_header: respect output buffer length
The encode_in_pack_object_header() writes a variable-length
header to an output buffer, but it doesn't actually know
long the buffer is. At first glance, this looks like it
might be possible to overflow.
In practice, this is probably impossible. The smallest
buffer we use is 10 bytes, which would hold the header for
an object up to 2^67 bytes. Obviously we're not likely to
see such an object, but we might worry that an object could
lie about its size (causing us to overflow before we realize
it does not actually have that many bytes). But the argument
is passed as a uintmax_t. Even on systems that have __int128
available, uintmax_t is typically restricted to 64-bit by
the ABI.
So it's unlikely that a system exists where this could be
exploited. Still, it's easy enough to use a normal out/len
pair and make sure we don't write too far. That protects the
hypothetical 128-bit system, makes it harder for callers to
accidentally specify a too-small buffer, and makes the
resulting code easier to audit.
Note that the one caller in fast-import tried to catch such
a case, but did so _after_ the call (at which point we'd
have already overflowed!). This check can now go away.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-25 01:26:40 +08:00
|
|
|
hdrlen = encode_in_pack_object_header(obuf, sizeof(obuf), type, size);
|
2011-10-29 05:48:40 +08:00
|
|
|
s.next_out = obuf + hdrlen;
|
|
|
|
s.avail_out = sizeof(obuf) - hdrlen;
|
|
|
|
|
|
|
|
while (status != Z_STREAM_END) {
|
|
|
|
unsigned char ibuf[16384];
|
|
|
|
|
|
|
|
if (size && !s.avail_in) {
|
|
|
|
ssize_t rsize = size < sizeof(ibuf) ? size : sizeof(ibuf);
|
2017-09-27 14:02:11 +08:00
|
|
|
ssize_t read_result = read_in_full(fd, ibuf, rsize);
|
|
|
|
if (read_result < 0)
|
|
|
|
die_errno("failed to read from '%s'", path);
|
|
|
|
if (read_result != rsize)
|
2011-10-29 05:48:40 +08:00
|
|
|
die("failed to read %d bytes from '%s'",
|
|
|
|
(int)rsize, path);
|
|
|
|
offset += rsize;
|
|
|
|
if (*already_hashed_to < offset) {
|
|
|
|
size_t hsize = offset - *already_hashed_to;
|
|
|
|
if (rsize < hsize)
|
|
|
|
hsize = rsize;
|
|
|
|
if (hsize)
|
2018-02-01 10:18:48 +08:00
|
|
|
the_hash_algo->update_fn(ctx, ibuf, hsize);
|
2011-10-29 05:48:40 +08:00
|
|
|
*already_hashed_to = offset;
|
|
|
|
}
|
|
|
|
s.next_in = ibuf;
|
|
|
|
s.avail_in = rsize;
|
|
|
|
size -= rsize;
|
|
|
|
}
|
|
|
|
|
|
|
|
status = git_deflate(&s, size ? 0 : Z_FINISH);
|
|
|
|
|
|
|
|
if (!s.avail_out || status == Z_STREAM_END) {
|
|
|
|
if (write_object) {
|
|
|
|
size_t written = s.next_out - obuf;
|
|
|
|
|
|
|
|
/* would we bust the size limit? */
|
|
|
|
if (state->nr_written &&
|
|
|
|
pack_size_limit_cfg &&
|
|
|
|
pack_size_limit_cfg < state->offset + written) {
|
|
|
|
git_deflate_abort(&s);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2018-02-01 10:18:46 +08:00
|
|
|
hashwrite(state->f, obuf, written);
|
2011-10-29 05:48:40 +08:00
|
|
|
state->offset += written;
|
|
|
|
}
|
|
|
|
s.next_out = obuf;
|
|
|
|
s.avail_out = sizeof(obuf);
|
|
|
|
}
|
|
|
|
|
|
|
|
switch (status) {
|
|
|
|
case Z_OK:
|
|
|
|
case Z_BUF_ERROR:
|
|
|
|
case Z_STREAM_END:
|
|
|
|
continue;
|
|
|
|
default:
|
|
|
|
die("unexpected deflate failure: %d", status);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
git_deflate_end(&s);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Lazily create backing packfile for the state */
|
|
|
|
static void prepare_to_stream(struct bulk_checkin_state *state,
|
|
|
|
unsigned flags)
|
|
|
|
{
|
|
|
|
if (!(flags & HASH_WRITE_OBJECT) || state->f)
|
|
|
|
return;
|
|
|
|
|
|
|
|
state->f = create_tmp_packfile(&state->pack_tmp_name);
|
|
|
|
reset_pack_idx_option(&state->pack_idx_opts);
|
|
|
|
|
|
|
|
/* Pretend we are going to write only one object */
|
|
|
|
state->offset = write_pack_header(state->f, 1);
|
|
|
|
if (!state->offset)
|
|
|
|
die_errno("unable to write pack header");
|
|
|
|
}
|
|
|
|
|
|
|
|
static int deflate_to_pack(struct bulk_checkin_state *state,
|
|
|
|
unsigned char result_sha1[],
|
|
|
|
int fd, size_t size,
|
|
|
|
enum object_type type, const char *path,
|
|
|
|
unsigned flags)
|
|
|
|
{
|
|
|
|
off_t seekback, already_hashed_to;
|
2018-02-01 10:18:48 +08:00
|
|
|
git_hash_ctx ctx;
|
2011-10-29 05:48:40 +08:00
|
|
|
unsigned char obuf[16384];
|
|
|
|
unsigned header_len;
|
2018-02-01 10:18:46 +08:00
|
|
|
struct hashfile_checkpoint checkpoint;
|
2011-10-29 05:48:40 +08:00
|
|
|
struct pack_idx_entry *idx = NULL;
|
|
|
|
|
|
|
|
seekback = lseek(fd, 0, SEEK_CUR);
|
|
|
|
if (seekback == (off_t) -1)
|
|
|
|
return error("cannot find the current offset");
|
|
|
|
|
2015-09-25 05:06:42 +08:00
|
|
|
header_len = xsnprintf((char *)obuf, sizeof(obuf), "%s %" PRIuMAX,
|
|
|
|
typename(type), (uintmax_t)size) + 1;
|
2018-02-01 10:18:48 +08:00
|
|
|
the_hash_algo->init_fn(&ctx);
|
|
|
|
the_hash_algo->update_fn(&ctx, obuf, header_len);
|
2011-10-29 05:48:40 +08:00
|
|
|
|
|
|
|
/* Note: idx is non-NULL when we are writing */
|
|
|
|
if ((flags & HASH_WRITE_OBJECT) != 0)
|
|
|
|
idx = xcalloc(1, sizeof(*idx));
|
|
|
|
|
|
|
|
already_hashed_to = 0;
|
|
|
|
|
|
|
|
while (1) {
|
|
|
|
prepare_to_stream(state, flags);
|
|
|
|
if (idx) {
|
2018-02-01 10:18:46 +08:00
|
|
|
hashfile_checkpoint(state->f, &checkpoint);
|
2011-10-29 05:48:40 +08:00
|
|
|
idx->offset = state->offset;
|
|
|
|
crc32_begin(state->f);
|
|
|
|
}
|
|
|
|
if (!stream_to_pack(state, &ctx, &already_hashed_to,
|
|
|
|
fd, size, type, path, flags))
|
|
|
|
break;
|
|
|
|
/*
|
|
|
|
* Writing this object to the current pack will make
|
|
|
|
* it too big; we need to truncate it, start a new
|
|
|
|
* pack, and write into it.
|
|
|
|
*/
|
|
|
|
if (!idx)
|
|
|
|
die("BUG: should not happen");
|
2018-02-01 10:18:46 +08:00
|
|
|
hashfile_truncate(state->f, &checkpoint);
|
2011-10-29 05:48:40 +08:00
|
|
|
state->offset = checkpoint.offset;
|
|
|
|
finish_bulk_checkin(state);
|
|
|
|
if (lseek(fd, seekback, SEEK_SET) == (off_t) -1)
|
|
|
|
return error("cannot seek back");
|
|
|
|
}
|
2018-02-01 10:18:48 +08:00
|
|
|
the_hash_algo->final_fn(result_sha1, &ctx);
|
2011-10-29 05:48:40 +08:00
|
|
|
if (!idx)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
idx->crc32 = crc32_end(state->f);
|
|
|
|
if (already_written(state, result_sha1)) {
|
2018-02-01 10:18:46 +08:00
|
|
|
hashfile_truncate(state->f, &checkpoint);
|
2011-10-29 05:48:40 +08:00
|
|
|
state->offset = checkpoint.offset;
|
|
|
|
free(idx);
|
|
|
|
} else {
|
2017-05-07 06:10:11 +08:00
|
|
|
hashcpy(idx->oid.hash, result_sha1);
|
2011-10-29 05:48:40 +08:00
|
|
|
ALLOC_GROW(state->written,
|
|
|
|
state->nr_written + 1,
|
|
|
|
state->alloc_written);
|
|
|
|
state->written[state->nr_written++] = idx;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int index_bulk_checkin(unsigned char *sha1,
|
|
|
|
int fd, size_t size, enum object_type type,
|
|
|
|
const char *path, unsigned flags)
|
|
|
|
{
|
|
|
|
int status = deflate_to_pack(&state, sha1, fd, size, type,
|
|
|
|
path, flags);
|
|
|
|
if (!state.plugged)
|
|
|
|
finish_bulk_checkin(&state);
|
|
|
|
return status;
|
|
|
|
}
|
|
|
|
|
|
|
|
void plug_bulk_checkin(void)
|
|
|
|
{
|
|
|
|
state.plugged = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
void unplug_bulk_checkin(void)
|
|
|
|
{
|
|
|
|
state.plugged = 0;
|
|
|
|
if (state.f)
|
|
|
|
finish_bulk_checkin(&state);
|
|
|
|
}
|