git/csum-file.c
Derrick Stolee 1687150b5d hashfile: allow skipping the hash function
The hashfile API is useful for generating files that include a trailing
hash of the file's contents up to that point. Using such a hash is
helpful for verifying the file for corruption-at-rest, such as a faulty
drive causing flipped bits.

Git's index file includes this trailing hash, so it uses a 'struct
hashfile' to handle the I/O to the file. This was very convenient to
allow using the hashfile methods during these operations.

However, hashing the file contents during write comes at a performance
penalty. It's slower to hash the bytes on their way to the disk than
without that step. This problem is made worse by the replacement of
hardware-accelerated SHA1 computations with the software-based sha1dc
computation.

This write cost is significant, and the checksum capability is likely
not worth that cost for such a short-lived file. The index is rewritten
frequently and the only time the checksum is checked is during 'git
fsck'. Thus, it would be helpful to allow a user to opt-out of the hash
computation.

We first need to allow Git to opt-out of the hash computation in the
hashfile API. The buffered writes of the API are still helpful, so it
makes sense to make the change here.

Introduce a new 'skip_hash' option to 'struct hashfile'. When set, the
update_fn and final_fn members of the_hash_algo are skipped. When
finalizing the hashfile, the trailing hash is replaced with the null
hash.

This use of a trailing null hash would be desireable in either case,
since we do not want to special case a file format to have a different
length depending on whether it was hashed or not. When the final bytes
of a file are all zero, we can infer that it was written without
hashing, and thus that verification is not available as a check for file
consistency. This also means that we could easily toggle hashing for any
file format we desire.

A version of this patch has existed in the microsoft/git fork since
2017 [1] (the linked commit was rebased in 2018, but the original dates
back to January 2017). Here, the change to make the index use this fast
path is delayed until a later change.

[1] 21fed2d914

Co-authored-by: Kevin Willford <kewillf@microsoft.com>
Signed-off-by: Kevin Willford <kewillf@microsoft.com>
Signed-off-by: Derrick Stolee <derrickstolee@github.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-01-07 07:46:14 +09:00

241 lines
5.4 KiB
C

/*
* csum-file.c
*
* Copyright (C) 2005 Linus Torvalds
*
* Simple file write infrastructure for writing SHA1-summed
* files. Useful when you write a file that you want to be
* able to verify hasn't been messed with afterwards.
*/
#include "cache.h"
#include "progress.h"
#include "csum-file.h"
static void verify_buffer_or_die(struct hashfile *f,
const void *buf,
unsigned int count)
{
ssize_t ret = read_in_full(f->check_fd, f->check_buffer, count);
if (ret < 0)
die_errno("%s: sha1 file read error", f->name);
if (ret != count)
die("%s: sha1 file truncated", f->name);
if (memcmp(buf, f->check_buffer, count))
die("sha1 file '%s' validation error", f->name);
}
static void flush(struct hashfile *f, const void *buf, unsigned int count)
{
if (0 <= f->check_fd && count)
verify_buffer_or_die(f, buf, count);
if (write_in_full(f->fd, buf, count) < 0) {
if (errno == ENOSPC)
die("sha1 file '%s' write error. Out of diskspace", f->name);
die_errno("sha1 file '%s' write error", f->name);
}
f->total += count;
display_throughput(f->tp, f->total);
}
void hashflush(struct hashfile *f)
{
unsigned offset = f->offset;
if (offset) {
if (!f->skip_hash)
the_hash_algo->update_fn(&f->ctx, f->buffer, offset);
flush(f, f->buffer, offset);
f->offset = 0;
}
}
static void free_hashfile(struct hashfile *f)
{
free(f->buffer);
free(f->check_buffer);
free(f);
}
int finalize_hashfile(struct hashfile *f, unsigned char *result,
enum fsync_component component, unsigned int flags)
{
int fd;
hashflush(f);
if (f->skip_hash)
hashclr(f->buffer);
else
the_hash_algo->final_fn(f->buffer, &f->ctx);
if (result)
hashcpy(result, f->buffer);
if (flags & CSUM_HASH_IN_STREAM)
flush(f, f->buffer, the_hash_algo->rawsz);
if (flags & CSUM_FSYNC)
fsync_component_or_die(component, f->fd, f->name);
if (flags & CSUM_CLOSE) {
if (close(f->fd))
die_errno("%s: sha1 file error on close", f->name);
fd = 0;
} else
fd = f->fd;
if (0 <= f->check_fd) {
char discard;
int cnt = read_in_full(f->check_fd, &discard, 1);
if (cnt < 0)
die_errno("%s: error when reading the tail of sha1 file",
f->name);
if (cnt)
die("%s: sha1 file has trailing garbage", f->name);
if (close(f->check_fd))
die_errno("%s: sha1 file error on close", f->name);
}
free_hashfile(f);
return fd;
}
void hashwrite(struct hashfile *f, const void *buf, unsigned int count)
{
while (count) {
unsigned left = f->buffer_len - f->offset;
unsigned nr = count > left ? left : count;
if (f->do_crc)
f->crc32 = crc32(f->crc32, buf, nr);
if (nr == f->buffer_len) {
/*
* Flush a full batch worth of data directly
* from the input, skipping the memcpy() to
* the hashfile's buffer. In this block,
* f->offset is necessarily zero.
*/
if (!f->skip_hash)
the_hash_algo->update_fn(&f->ctx, buf, nr);
flush(f, buf, nr);
} else {
/*
* Copy to the hashfile's buffer, flushing only
* if it became full.
*/
memcpy(f->buffer + f->offset, buf, nr);
f->offset += nr;
left -= nr;
if (!left)
hashflush(f);
}
count -= nr;
buf = (char *) buf + nr;
}
}
struct hashfile *hashfd_check(const char *name)
{
int sink, check;
struct hashfile *f;
sink = xopen("/dev/null", O_WRONLY);
check = xopen(name, O_RDONLY);
f = hashfd(sink, name);
f->check_fd = check;
f->check_buffer = xmalloc(f->buffer_len);
return f;
}
static struct hashfile *hashfd_internal(int fd, const char *name,
struct progress *tp,
size_t buffer_len)
{
struct hashfile *f = xmalloc(sizeof(*f));
f->fd = fd;
f->check_fd = -1;
f->offset = 0;
f->total = 0;
f->tp = tp;
f->name = name;
f->do_crc = 0;
f->skip_hash = 0;
the_hash_algo->init_fn(&f->ctx);
f->buffer_len = buffer_len;
f->buffer = xmalloc(buffer_len);
f->check_buffer = NULL;
return f;
}
struct hashfile *hashfd(int fd, const char *name)
{
/*
* Since we are not going to use a progress meter to
* measure the rate of data passing through this hashfile,
* use a larger buffer size to reduce fsync() calls.
*/
return hashfd_internal(fd, name, NULL, 128 * 1024);
}
struct hashfile *hashfd_throughput(int fd, const char *name, struct progress *tp)
{
/*
* Since we are expecting to report progress of the
* write into this hashfile, use a smaller buffer
* size so the progress indicators arrive at a more
* frequent rate.
*/
return hashfd_internal(fd, name, tp, 8 * 1024);
}
void hashfile_checkpoint(struct hashfile *f, struct hashfile_checkpoint *checkpoint)
{
hashflush(f);
checkpoint->offset = f->total;
the_hash_algo->clone_fn(&checkpoint->ctx, &f->ctx);
}
int hashfile_truncate(struct hashfile *f, struct hashfile_checkpoint *checkpoint)
{
off_t offset = checkpoint->offset;
if (ftruncate(f->fd, offset) ||
lseek(f->fd, offset, SEEK_SET) != offset)
return -1;
f->total = offset;
f->ctx = checkpoint->ctx;
f->offset = 0; /* hashflush() was called in checkpoint */
return 0;
}
void crc32_begin(struct hashfile *f)
{
f->crc32 = crc32(0, NULL, 0);
f->do_crc = 1;
}
uint32_t crc32_end(struct hashfile *f)
{
f->do_crc = 0;
return f->crc32;
}
int hashfile_checksum_valid(const unsigned char *data, size_t total_len)
{
unsigned char got[GIT_MAX_RAWSZ];
git_hash_ctx ctx;
size_t data_len = total_len - the_hash_algo->rawsz;
if (total_len < the_hash_algo->rawsz)
return 0; /* say "too short"? */
the_hash_algo->init_fn(&ctx);
the_hash_algo->update_fn(&ctx, data, data_len);
the_hash_algo->final_fn(got, &ctx);
return hasheq(got, data + data_len);
}