git/entry.c

555 lines
14 KiB
C
Raw Normal View History

#include "cache.h"
#include "blob.h"
#include "object-store.h"
#include "dir.h"
#include "streaming.h"
#include "submodule.h"
#include "progress.h"
#include "fsmonitor.h"
#include "entry.h"
static void create_directories(const char *path, int path_len,
const struct checkout *state)
{
char *buf = xmallocz(path_len);
int len = 0;
while (len < path_len) {
do {
buf[len] = path[len];
len++;
} while (len < path_len && path[len] != '/');
if (len >= path_len)
break;
buf[len] = 0;
/*
* For 'checkout-index --prefix=<dir>', <dir> is
* allowed to be a symlink to an existing directory,
* and we set 'state->base_dir_len' below, such that
* we test the path components of the prefix with the
* stat() function instead of the lstat() function.
*/
if (has_dirs_only_path(buf, len, state->base_dir_len))
continue; /* ok, it is already a directory. */
/*
* If this mkdir() would fail, it could be that there
* is already a symlink or something else exists
* there, therefore we then try to unlink it and try
* one more time to create the directory.
*/
if (mkdir(buf, 0777)) {
if (errno == EEXIST && state->force &&
!unlink_or_warn(buf) && !mkdir(buf, 0777))
continue;
die_errno("cannot create directory at '%s'", buf);
}
}
free(buf);
}
static void remove_subtree(struct strbuf *path)
{
DIR *dir = opendir(path->buf);
struct dirent *de;
int origlen = path->len;
if (!dir)
die_errno("cannot opendir '%s'", path->buf);
while ((de = readdir(dir)) != NULL) {
struct stat st;
if (is_dot_or_dotdot(de->d_name))
continue;
strbuf_addch(path, '/');
strbuf_addstr(path, de->d_name);
if (lstat(path->buf, &st))
die_errno("cannot lstat '%s'", path->buf);
if (S_ISDIR(st.st_mode))
remove_subtree(path);
else if (unlink(path->buf))
die_errno("cannot unlink '%s'", path->buf);
strbuf_setlen(path, origlen);
}
closedir(dir);
if (rmdir(path->buf))
die_errno("cannot rmdir '%s'", path->buf);
}
static int create_file(const char *path, unsigned int mode)
{
mode = (mode & 0100) ? 0777 : 0666;
return open(path, O_WRONLY | O_CREAT | O_EXCL, mode);
}
void *read_blob_entry(const struct cache_entry *ce, unsigned long *size)
{
enum object_type type;
void *blob_data = read_object_file(&ce->oid, &type, size);
if (blob_data) {
if (type == OBJ_BLOB)
return blob_data;
free(blob_data);
}
return NULL;
}
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
static int open_output_fd(char *path, const struct cache_entry *ce, int to_tempfile)
{
int symlink = (ce->ce_mode & S_IFMT) != S_IFREG;
if (to_tempfile) {
xsnprintf(path, TEMPORARY_FILENAME_LENGTH, "%s",
symlink ? ".merge_link_XXXXXX" : ".merge_file_XXXXXX");
return mkstemp(path);
} else {
return create_file(path, !symlink ? ce->ce_mode : 0666);
}
}
int fstat_checkout_output(int fd, const struct checkout *state, struct stat *st)
{
/* use fstat() only when path == ce->name */
if (fstat_is_reliable() &&
state->refresh_cache && !state->base_dir_len) {
return !fstat(fd, st);
}
return 0;
}
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
static int streaming_write_entry(const struct cache_entry *ce, char *path,
struct stream_filter *filter,
const struct checkout *state, int to_tempfile,
int *fstat_done, struct stat *statbuf)
{
int result = 0;
int fd;
fd = open_output_fd(path, ce, to_tempfile);
if (fd < 0)
return -1;
result |= stream_blob_to_fd(fd, &ce->oid, filter, 1);
*fstat_done = fstat_checkout_output(fd, state, statbuf);
result |= close(fd);
if (result)
unlink(path);
return result;
}
void enable_delayed_checkout(struct checkout *state)
{
if (!state->delayed_checkout) {
state->delayed_checkout = xmalloc(sizeof(*state->delayed_checkout));
state->delayed_checkout->state = CE_CAN_DELAY;
string_list_init(&state->delayed_checkout->filters, 0);
string_list_init(&state->delayed_checkout->paths, 0);
}
}
static int remove_available_paths(struct string_list_item *item, void *cb_data)
{
struct string_list *available_paths = cb_data;
struct string_list_item *available;
available = string_list_lookup(available_paths, item->string);
if (available)
available->util = (void *)item->string;
return !available;
}
int finish_delayed_checkout(struct checkout *state, int *nr_checkouts)
{
int errs = 0;
unsigned delayed_object_count;
off_t filtered_bytes = 0;
struct string_list_item *filter, *path;
struct progress *progress;
struct delayed_checkout *dco = state->delayed_checkout;
if (!state->delayed_checkout)
return errs;
dco->state = CE_RETRY;
delayed_object_count = dco->paths.nr;
progress = start_delayed_progress(_("Filtering content"), delayed_object_count);
while (dco->filters.nr > 0) {
for_each_string_list_item(filter, &dco->filters) {
struct string_list available_paths = STRING_LIST_INIT_NODUP;
display_progress(progress, delayed_object_count - dco->paths.nr);
if (!async_query_available_blobs(filter->string, &available_paths)) {
/* Filter reported an error */
errs = 1;
filter->string = "";
continue;
}
if (available_paths.nr <= 0) {
/*
* Filter responded with no entries. That means
* the filter is done and we can remove the
* filter from the list (see
* "string_list_remove_empty_items" call below).
*/
filter->string = "";
continue;
}
/*
* In dco->paths we store a list of all delayed paths.
* The filter just send us a list of available paths.
* Remove them from the list.
*/
filter_string_list(&dco->paths, 0,
&remove_available_paths, &available_paths);
for_each_string_list_item(path, &available_paths) {
struct cache_entry* ce;
if (!path->util) {
error("external filter '%s' signaled that '%s' "
"is now available although it has not been "
"delayed earlier",
filter->string, path->string);
errs |= 1;
/*
* Do not ask the filter for available blobs,
* again, as the filter is likely buggy.
*/
filter->string = "";
continue;
}
ce = index_file_exists(state->istate, path->string,
strlen(path->string), 0);
if (ce) {
errs |= checkout_entry(ce, state, NULL, nr_checkouts);
filtered_bytes += ce->ce_stat_data.sd_size;
display_throughput(progress, filtered_bytes);
} else
errs = 1;
}
}
string_list_remove_empty_items(&dco->filters, 0);
}
stop_progress(&progress);
string_list_clear(&dco->filters, 0);
/* At this point we should not have any delayed paths anymore. */
errs |= dco->paths.nr;
for_each_string_list_item(path, &dco->paths) {
error("'%s' was not filtered properly", path->string);
}
string_list_clear(&dco->paths, 0);
free(dco);
state->delayed_checkout = NULL;
return errs;
}
void update_ce_after_write(const struct checkout *state, struct cache_entry *ce,
struct stat *st)
{
if (state->refresh_cache) {
assert(state->istate);
fill_stat_cache_info(state->istate, ce, st);
ce->ce_flags |= CE_UPDATE_IN_BASE;
mark_fsmonitor_invalid(state->istate, ce);
state->istate->cache_changed |= CE_ENTRY_CHANGED;
}
}
/* Note: ca is used (and required) iff the entry refers to a regular file. */
static int write_entry(struct cache_entry *ce, char *path, struct conv_attrs *ca,
const struct checkout *state, int to_tempfile)
{
unsigned int ce_mode_s_ifmt = ce->ce_mode & S_IFMT;
struct delayed_checkout *dco = state->delayed_checkout;
int fd, ret, fstat_done = 0;
char *new_blob;
struct strbuf buf = STRBUF_INIT;
unsigned long size;
ssize_t wrote;
size_t newsize = 0;
struct stat st;
const struct submodule *sub;
struct checkout_metadata meta;
clone_checkout_metadata(&meta, &state->meta, &ce->oid);
if (ce_mode_s_ifmt == S_IFREG) {
struct stream_filter *filter = get_stream_filter_ca(ca, &ce->oid);
if (filter &&
!streaming_write_entry(ce, path, filter,
state, to_tempfile,
&fstat_done, &st))
goto finish;
}
switch (ce_mode_s_ifmt) {
case S_IFLNK:
new_blob = read_blob_entry(ce, &size);
if (!new_blob)
return error("unable to read sha1 file of %s (%s)",
ce->name, oid_to_hex(&ce->oid));
/*
* We can't make a real symlink; write out a regular file entry
* with the symlink destination as its contents.
*/
if (!has_symlinks || to_tempfile)
goto write_file_entry;
ret = symlink(new_blob, path);
free(new_blob);
if (ret)
return error_errno("unable to create symlink %s", path);
break;
case S_IFREG:
/*
* We do not send the blob in case of a retry, so do not
* bother reading it at all.
*/
if (dco && dco->state == CE_RETRY) {
new_blob = NULL;
size = 0;
} else {
new_blob = read_blob_entry(ce, &size);
if (!new_blob)
return error("unable to read sha1 file of %s (%s)",
ce->name, oid_to_hex(&ce->oid));
}
/*
* Convert from git internal format to working tree format
*/
if (dco && dco->state != CE_NO_DELAY) {
ret = async_convert_to_working_tree_ca(ca, ce->name,
new_blob, size,
&buf, &meta, dco);
if (ret && string_list_has_string(&dco->paths, ce->name)) {
free(new_blob);
goto delayed;
}
} else {
ret = convert_to_working_tree_ca(ca, ce->name, new_blob,
size, &buf, &meta);
}
if (ret) {
free(new_blob);
new_blob = strbuf_detach(&buf, &newsize);
size = newsize;
}
/*
* No "else" here as errors from convert are OK at this
* point. If the error would have been fatal (e.g.
* filter is required), then we would have died already.
*/
write_file_entry:
fd = open_output_fd(path, ce, to_tempfile);
if (fd < 0) {
free(new_blob);
return error_errno("unable to create file %s", path);
}
Lazy man's auto-CRLF It currently does NOT know about file attributes, so it does its conversion purely based on content. Maybe that is more in the "git philosophy" anyway, since content is king, but I think we should try to do the file attributes to turn it off on demand. Anyway, BY DEFAULT it is off regardless, because it requires a [core] AutoCRLF = true in your config file to be enabled. We could make that the default for Windows, of course, the same way we do some other things (filemode etc). But you can actually enable it on UNIX, and it will cause: - "git update-index" will write blobs without CRLF - "git diff" will diff working tree files without CRLF - "git checkout" will write files to the working tree _with_ CRLF and things work fine. Funnily, it actually shows an odd file in git itself: git clone -n git test-crlf cd test-crlf git config core.autocrlf true git checkout git diff shows a diff for "Documentation/docbook-xsl.css". Why? Because we have actually checked in that file *with* CRLF! So when "core.autocrlf" is true, we'll always generate a *different* hash for it in the index, because the index hash will be for the content _without_ CRLF. Is this complete? I dunno. It seems to work for me. It doesn't use the filename at all right now, and that's probably a deficiency (we could certainly make the "is_binary()" heuristics also take standard filename heuristics into account). I don't pass in the filename at all for the "index_fd()" case (git-update-index), so that would need to be passed around, but this actually works fine. NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours truly. I will not guarantee that they work at all reasonable. Caveat emptor. But it _is_ simple, and it _is_ safe, since it's all off by default. The patch is pretty simple - the biggest part is the new "convert.c" file, but even that is really just basic stuff that anybody can write in "Teaching C 101" as a final project for their first class in programming. Not to say that it's bug-free, of course - but at least we're not talking about rocket surgery here. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-14 03:07:23 +08:00
wrote = write_in_full(fd, new_blob, size);
if (!to_tempfile)
fstat_done = fstat_checkout_output(fd, state, &st);
close(fd);
free(new_blob);
if (wrote < 0)
return error("unable to write file %s", path);
break;
case S_IFGITLINK:
if (to_tempfile)
return error("cannot create temporary submodule %s", ce->name);
if (mkdir(path, 0777) < 0)
return error("cannot create submodule directory %s", path);
sub = submodule_from_ce(ce);
if (sub)
return submodule_move_head(ce->name,
NULL, oid_to_hex(&ce->oid),
state->force ? SUBMODULE_MOVE_HEAD_FORCE : 0);
break;
default:
return error("unknown file mode for %s in index", ce->name);
}
finish:
if (state->refresh_cache) {
if (!fstat_done && lstat(ce->name, &st) < 0)
return error_errno("unable to stat just-written file %s",
ce->name);
update_ce_after_write(state, ce , &st);
}
delayed:
return 0;
}
/*
* This is like 'lstat()', except it refuses to follow symlinks
* in the path, after skipping "skiplen".
*/
static int check_path(const char *path, int len, struct stat *st, int skiplen)
{
const char *slash = path + len;
while (path < slash && *slash != '/')
slash--;
if (!has_dirs_only_path(path, slash - path, skiplen)) {
errno = ENOENT;
return -1;
}
return lstat(path, st);
}
static void mark_colliding_entries(const struct checkout *state,
struct cache_entry *ce, struct stat *st)
{
int i, trust_ino = check_stat;
clone: fix colliding file detection on APFS Commit b878579ae7 (clone: report duplicate entries on case-insensitive filesystems - 2018-08-17) adds a warning to user when cloning a repo with case-sensitive file names on a case-insensitive file system. The "find duplicate file" check was doing by comparing inode number (and only fall back to fspathcmp() when inode is known to be unreliable because fspathcmp() can't cover all case folding cases). The inode check is very simple, and wrong. It compares between a 32-bit number (sd_ino) and potentially a 64-bit number (st_ino). When an inode is larger than 2^32 (which seems to be the case for APFS), it will be truncated and stored in sd_ino, but comparing with itself will fail. As a result, instead of showing a pair of files that have the same name, we show just one file (marked before the beginning of the loop). We fail to find the original one. The fix could be just a simple type cast (*) dup->ce_stat_data.sd_ino == (unsigned int)st->st_ino but this is no longer a reliable test, there are 4G possible inodes that can match sd_ino because we only match the lower 32 bits instead of full 64 bits. There are two options to go. Either we ignore inode and go with fspathcmp() on Apple platform. This means we can't do accurate inode check on HFS anymore, or even on APFS when inode numbers are still below 2^32. Or we just to to reduce the odds of matching a wrong file by checking more attributes, counting mostly on st_size because st_xtime is likely the same. This patch goes with this direction, hoping that false positive chances are too small to be seen in practice. While at there, enable the test on Cygwin (verified working by Ramsay Jones) (*) this is also already done inside match_stat_data() Reported-by: Carlo Arenas <carenas@gmail.com> Helped-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-21 00:28:53 +08:00
#if defined(GIT_WINDOWS_NATIVE) || defined(__CYGWIN__)
trust_ino = 0;
#endif
ce->ce_flags |= CE_MATCHED;
for (i = 0; i < state->istate->cache_nr; i++) {
struct cache_entry *dup = state->istate->cache[i];
if (dup == ce)
break;
if (dup->ce_flags & (CE_MATCHED | CE_VALID | CE_SKIP_WORKTREE))
continue;
clone: fix colliding file detection on APFS Commit b878579ae7 (clone: report duplicate entries on case-insensitive filesystems - 2018-08-17) adds a warning to user when cloning a repo with case-sensitive file names on a case-insensitive file system. The "find duplicate file" check was doing by comparing inode number (and only fall back to fspathcmp() when inode is known to be unreliable because fspathcmp() can't cover all case folding cases). The inode check is very simple, and wrong. It compares between a 32-bit number (sd_ino) and potentially a 64-bit number (st_ino). When an inode is larger than 2^32 (which seems to be the case for APFS), it will be truncated and stored in sd_ino, but comparing with itself will fail. As a result, instead of showing a pair of files that have the same name, we show just one file (marked before the beginning of the loop). We fail to find the original one. The fix could be just a simple type cast (*) dup->ce_stat_data.sd_ino == (unsigned int)st->st_ino but this is no longer a reliable test, there are 4G possible inodes that can match sd_ino because we only match the lower 32 bits instead of full 64 bits. There are two options to go. Either we ignore inode and go with fspathcmp() on Apple platform. This means we can't do accurate inode check on HFS anymore, or even on APFS when inode numbers are still below 2^32. Or we just to to reduce the odds of matching a wrong file by checking more attributes, counting mostly on st_size because st_xtime is likely the same. This patch goes with this direction, hoping that false positive chances are too small to be seen in practice. While at there, enable the test on Cygwin (verified working by Ramsay Jones) (*) this is also already done inside match_stat_data() Reported-by: Carlo Arenas <carenas@gmail.com> Helped-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-21 00:28:53 +08:00
if ((trust_ino && !match_stat_data(&dup->ce_stat_data, st)) ||
(!trust_ino && !fspathcmp(ce->name, dup->name))) {
dup->ce_flags |= CE_MATCHED;
break;
}
}
}
int checkout_entry(struct cache_entry *ce, const struct checkout *state,
char *topath, int *nr_checkouts)
{
static struct strbuf path = STRBUF_INIT;
struct stat st;
struct conv_attrs ca_buf, *ca = NULL;
if (ce->ce_flags & CE_WT_REMOVE) {
if (topath)
/*
* No content and thus no path to create, so we have
* no pathname to return.
*/
BUG("Can't remove entry to a path");
unlink_entry(ce);
return 0;
}
if (topath) {
if (S_ISREG(ce->ce_mode)) {
convert_attrs(state->istate, &ca_buf, ce->name);
ca = &ca_buf;
}
return write_entry(ce, topath, ca, state, 1);
}
strbuf_reset(&path);
strbuf_add(&path, state->base_dir, state->base_dir_len);
strbuf_add(&path, ce->name, ce_namelen(ce));
if (!check_path(path.buf, path.len, &st, state->base_dir_len)) {
const struct submodule *sub;
unsigned changed = ie_match_stat(state->istate, ce, &st,
CE_MATCH_IGNORE_VALID | CE_MATCH_IGNORE_SKIP_WORKTREE);
/*
* Needs to be checked before !changed returns early,
* as the possibly empty directory was not changed
*/
sub = submodule_from_ce(ce);
if (sub) {
int err;
if (!is_submodule_populated_gently(ce->name, &err)) {
struct stat sb;
if (lstat(ce->name, &sb))
die(_("could not stat file '%s'"), ce->name);
if (!(st.st_mode & S_IFDIR))
unlink_or_warn(ce->name);
return submodule_move_head(ce->name,
NULL, oid_to_hex(&ce->oid), 0);
} else
return submodule_move_head(ce->name,
"HEAD", oid_to_hex(&ce->oid),
state->force ? SUBMODULE_MOVE_HEAD_FORCE : 0);
}
if (!changed)
return 0;
if (!state->force) {
if (!state->quiet)
fprintf(stderr,
"%s already exists, no checkout\n",
path.buf);
return -1;
}
if (state->clone)
mark_colliding_entries(state, ce, &st);
/*
* We unlink the old file, to get the new one with the
* right permissions (including umask, which is nasty
* to emulate by hand - much easier to let the system
* just do the right thing)
*/
if (S_ISDIR(st.st_mode)) {
/* If it is a gitlink, leave it alone! */
if (S_ISGITLINK(ce->ce_mode))
return 0;
remove_subtree(&path);
} else if (unlink(path.buf))
return error_errno("unable to unlink old '%s'", path.buf);
} else if (state->not_new)
return 0;
create_directories(path.buf, path.len, state);
if (nr_checkouts)
(*nr_checkouts)++;
if (S_ISREG(ce->ce_mode)) {
convert_attrs(state->istate, &ca_buf, ce->name);
ca = &ca_buf;
}
return write_entry(ce, path.buf, ca, state, 0);
}
void unlink_entry(const struct cache_entry *ce)
{
const struct submodule *sub = submodule_from_ce(ce);
if (sub) {
/* state.force is set at the caller. */
submodule_move_head(ce->name, "HEAD", NULL,
SUBMODULE_MOVE_HEAD_FORCE);
}
if (!check_leading_path(ce->name, ce_namelen(ce)))
return;
if (remove_or_warn(ce->ce_mode, ce->name))
return;
schedule_dir_for_removal(ce->name, ce_namelen(ce));
}