1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-04-28 12:05:28 +02:00
git/tempfile.c
Jeff King 24d82185d2 tempfile: use list.h for linked list
The tempfile API keeps to-be-cleaned tempfiles in a
singly-linked list and never removes items from the list.  A
future patch would like to start removing items, but removal
from a singly linked list is O(n), as we have to walk the
list to find the predecessor element. This means that a
process which takes "n" simultaneous lockfiles (for example,
an atomic transaction on "n" refs) may end up quadratic in
"n".

Before we start allowing items to be removed, it would be
nice to have a way to cover this case in linear time.

The simplest solution is to make an assumption about the
order in which tempfiles are added and removed from the
list. If both operations iterate over the tempfiles in the
same order, then by putting new items at the end of the list
our removal search will always find its items at the
beginning of the list. And indeed, that would work for the
case of refs. But it creates a hidden dependency between
unrelated parts of the code. If anybody changes the ref code
(or if we add a new caller that opens multiple simultaneous
tempfiles) they may unknowingly introduce a performance
regression.

Another solution is to use a better data structure. A
doubly-linked list works fine, and we already have an
implementation in list.h. But there's one snag: the elements
of "struct tempfile" are all marked as "volatile", since a
signal handler may interrupt us and iterate over the list at
any moment (even if we were in the middle of adding a new
entry).

We can declare a "volatile struct list_head", but we can't
actually use it with the normal list functions. The compiler
complains about passing a pointer-to-volatile via a regular
pointer argument. And rightfully so, as the sub-function
would potentially need different code to deal with the
volatile case.

That leaves us with a few options:

  1. Drop the "volatile" modifier for the list items.

     This is probably a bad idea. I checked the assembly
     output from "gcc -O2", and the "volatile" really does
     impact the order in which it updates memory.

  2. Use macros instead of inline functions. The irony here
     is that list.h is entirely implemented as trivial
     inline functions. So we basically are already
     generating custom code for each call. But sadly there's no
     way in C to declare the inline function to take a more
     generic type.

     We could do so by switching the inline functions to
     macros, but it does make the end result harder to read.
     And it doesn't fully solve the problem (for instance,
     the declaration of list_head needs to change so that
     its "prev" and "next" pointers point to other volatile
     structs).

  3. Don't use list.h, and just make our own ad-hoc
     doubly-linked list. It's not that much code to
     implement the basics that we need here. But if we're
     going to do so, why not add the few extra lines
     required to model it after the actual list.h interface?
     We can even reuse a few of the macro helpers.

So this patch takes option 3, but actually implements a
parallel "volatile list" interface in list.h, where it could
potentially be reused by other code. This implements just
enough for tempfile.c's use, though we could easily port
other functions later if need be.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-06 17:19:54 +09:00

320 lines
8.4 KiB
C

/*
* State diagram and cleanup
* -------------------------
*
* If the program exits while a temporary file is active, we want to
* make sure that we remove it. This is done by remembering the active
* temporary files in a linked list, `tempfile_list`. An `atexit(3)`
* handler and a signal handler are registered, to clean up any active
* temporary files.
*
* Because the signal handler can run at any time, `tempfile_list` and
* the `tempfile` objects that comprise it must be kept in
* self-consistent states at all times.
*
* The possible states of a `tempfile` object are as follows:
*
* - Uninitialized. In this state the object's `on_list` field must be
* zero but the rest of its contents need not be initialized. As
* soon as the object is used in any way, it is irrevocably
* registered in `tempfile_list`, and `on_list` is set.
*
* - Active, file open (after `create_tempfile()` or
* `reopen_tempfile()`). In this state:
*
* - the temporary file exists
* - `active` is set
* - `filename` holds the filename of the temporary file
* - `fd` holds a file descriptor open for writing to it
* - `fp` holds a pointer to an open `FILE` object if and only if
* `fdopen_tempfile()` has been called on the object
* - `owner` holds the PID of the process that created the file
*
* - Active, file closed (after `close_tempfile_gently()`). Same
* as the previous state, except that the temporary file is closed,
* `fd` is -1, and `fp` is `NULL`.
*
* - Inactive (after `delete_tempfile()`, `rename_tempfile()`, or a
* failed attempt to create a temporary file). In this state:
*
* - `active` is unset
* - `filename` is empty (usually, though there are transitory
* states in which this condition doesn't hold). Client code should
* *not* rely on the filename being empty in this state.
* - `fd` is -1 and `fp` is `NULL`
* - the object is left registered in the `tempfile_list`, and
* `on_list` is set.
*
* A temporary file is owned by the process that created it. The
* `tempfile` has an `owner` field that records the owner's PID. This
* field is used to prevent a forked process from deleting a temporary
* file created by its parent.
*/
#include "cache.h"
#include "tempfile.h"
#include "sigchain.h"
static VOLATILE_LIST_HEAD(tempfile_list);
static void remove_tempfiles(int in_signal_handler)
{
pid_t me = getpid();
volatile struct volatile_list_head *pos;
list_for_each(pos, &tempfile_list) {
struct tempfile *p = list_entry(pos, struct tempfile, list);
if (!is_tempfile_active(p) || p->owner != me)
continue;
if (p->fd >= 0)
close(p->fd);
if (in_signal_handler)
unlink(p->filename.buf);
else
unlink_or_warn(p->filename.buf);
p->active = 0;
}
}
static void remove_tempfiles_on_exit(void)
{
remove_tempfiles(0);
}
static void remove_tempfiles_on_signal(int signo)
{
remove_tempfiles(1);
sigchain_pop(signo);
raise(signo);
}
/*
* Initialize *tempfile if necessary and add it to tempfile_list.
*/
static void prepare_tempfile_object(struct tempfile *tempfile)
{
if (volatile_list_empty(&tempfile_list)) {
/* One-time initialization */
sigchain_push_common(remove_tempfiles_on_signal);
atexit(remove_tempfiles_on_exit);
}
if (is_tempfile_active(tempfile))
BUG("prepare_tempfile_object called for active object");
if (!tempfile->on_list) {
/* Initialize *tempfile and add it to tempfile_list: */
tempfile->fd = -1;
tempfile->fp = NULL;
tempfile->active = 0;
tempfile->owner = 0;
strbuf_init(&tempfile->filename, 0);
volatile_list_add(&tempfile->list, &tempfile_list);
tempfile->on_list = 1;
} else if (tempfile->filename.len) {
/* This shouldn't happen, but better safe than sorry. */
BUG("prepare_tempfile_object called for improperly-reset object");
}
}
static void activate_tempfile(struct tempfile *tempfile)
{
tempfile->owner = getpid();
tempfile->active = 1;
}
static void deactivate_tempfile(struct tempfile *tempfile)
{
tempfile->active = 0;
strbuf_release(&tempfile->filename);
}
/* Make sure errno contains a meaningful value on error */
int create_tempfile(struct tempfile *tempfile, const char *path)
{
prepare_tempfile_object(tempfile);
strbuf_add_absolute_path(&tempfile->filename, path);
tempfile->fd = open(tempfile->filename.buf,
O_RDWR | O_CREAT | O_EXCL | O_CLOEXEC, 0666);
if (O_CLOEXEC && tempfile->fd < 0 && errno == EINVAL)
/* Try again w/o O_CLOEXEC: the kernel might not support it */
tempfile->fd = open(tempfile->filename.buf,
O_RDWR | O_CREAT | O_EXCL, 0666);
if (tempfile->fd < 0) {
deactivate_tempfile(tempfile);
return -1;
}
activate_tempfile(tempfile);
if (adjust_shared_perm(tempfile->filename.buf)) {
int save_errno = errno;
error("cannot fix permission bits on %s", tempfile->filename.buf);
delete_tempfile(tempfile);
errno = save_errno;
return -1;
}
return tempfile->fd;
}
void register_tempfile(struct tempfile *tempfile, const char *path)
{
prepare_tempfile_object(tempfile);
strbuf_add_absolute_path(&tempfile->filename, path);
activate_tempfile(tempfile);
}
int mks_tempfile_sm(struct tempfile *tempfile,
const char *template, int suffixlen, int mode)
{
prepare_tempfile_object(tempfile);
strbuf_add_absolute_path(&tempfile->filename, template);
tempfile->fd = git_mkstemps_mode(tempfile->filename.buf, suffixlen, mode);
if (tempfile->fd < 0) {
deactivate_tempfile(tempfile);
return -1;
}
activate_tempfile(tempfile);
return tempfile->fd;
}
int mks_tempfile_tsm(struct tempfile *tempfile,
const char *template, int suffixlen, int mode)
{
const char *tmpdir;
prepare_tempfile_object(tempfile);
tmpdir = getenv("TMPDIR");
if (!tmpdir)
tmpdir = "/tmp";
strbuf_addf(&tempfile->filename, "%s/%s", tmpdir, template);
tempfile->fd = git_mkstemps_mode(tempfile->filename.buf, suffixlen, mode);
if (tempfile->fd < 0) {
deactivate_tempfile(tempfile);
return -1;
}
activate_tempfile(tempfile);
return tempfile->fd;
}
int xmks_tempfile_m(struct tempfile *tempfile, const char *template, int mode)
{
int fd;
struct strbuf full_template = STRBUF_INIT;
strbuf_add_absolute_path(&full_template, template);
fd = mks_tempfile_m(tempfile, full_template.buf, mode);
if (fd < 0)
die_errno("Unable to create temporary file '%s'",
full_template.buf);
strbuf_release(&full_template);
return fd;
}
FILE *fdopen_tempfile(struct tempfile *tempfile, const char *mode)
{
if (!is_tempfile_active(tempfile))
BUG("fdopen_tempfile() called for inactive object");
if (tempfile->fp)
BUG("fdopen_tempfile() called for open object");
tempfile->fp = fdopen(tempfile->fd, mode);
return tempfile->fp;
}
const char *get_tempfile_path(struct tempfile *tempfile)
{
if (!is_tempfile_active(tempfile))
BUG("get_tempfile_path() called for inactive object");
return tempfile->filename.buf;
}
int get_tempfile_fd(struct tempfile *tempfile)
{
if (!is_tempfile_active(tempfile))
BUG("get_tempfile_fd() called for inactive object");
return tempfile->fd;
}
FILE *get_tempfile_fp(struct tempfile *tempfile)
{
if (!is_tempfile_active(tempfile))
BUG("get_tempfile_fp() called for inactive object");
return tempfile->fp;
}
int close_tempfile_gently(struct tempfile *tempfile)
{
int fd;
FILE *fp;
int err;
if (!is_tempfile_active(tempfile) || tempfile->fd < 0)
return 0;
fd = tempfile->fd;
fp = tempfile->fp;
tempfile->fd = -1;
if (fp) {
tempfile->fp = NULL;
if (ferror(fp)) {
err = -1;
if (!fclose(fp))
errno = EIO;
} else {
err = fclose(fp);
}
} else {
err = close(fd);
}
return err ? -1 : 0;
}
int reopen_tempfile(struct tempfile *tempfile)
{
if (!is_tempfile_active(tempfile))
BUG("reopen_tempfile called for an inactive object");
if (0 <= tempfile->fd)
BUG("reopen_tempfile called for an open object");
tempfile->fd = open(tempfile->filename.buf, O_WRONLY);
return tempfile->fd;
}
int rename_tempfile(struct tempfile *tempfile, const char *path)
{
if (!is_tempfile_active(tempfile))
BUG("rename_tempfile called for inactive object");
if (close_tempfile_gently(tempfile)) {
delete_tempfile(tempfile);
return -1;
}
if (rename(tempfile->filename.buf, path)) {
int save_errno = errno;
delete_tempfile(tempfile);
errno = save_errno;
return -1;
}
deactivate_tempfile(tempfile);
return 0;
}
void delete_tempfile(struct tempfile *tempfile)
{
if (!is_tempfile_active(tempfile))
return;
close_tempfile_gently(tempfile);
unlink_or_warn(tempfile->filename.buf);
deactivate_tempfile(tempfile);
}