git/tempfile.c
Jeff King 076aa2cbda tempfile: auto-allocate tempfiles on heap
The previous commit taught the tempfile code to give up
ownership over tempfiles that have been renamed or deleted.
That makes it possible to use a stack variable like this:

  struct tempfile t;

  create_tempfile(&t, ...);
  ...
  if (!err)
          rename_tempfile(&t, ...);
  else
          delete_tempfile(&t);

But doing it this way has a high potential for creating
memory errors. The tempfile we pass to create_tempfile()
ends up on a global linked list, and it's not safe for it to
go out of scope until we've called one of those two
deactivation functions.

Imagine that we add an early return from the function that
forgets to call delete_tempfile(). With a static or heap
tempfile variable, the worst case is that the tempfile hangs
around until the program exits (and some functions like
setup_shallow_temporary rely on this intentionally, creating
a tempfile and then leaving it for later cleanup).

But with a stack variable as above, this is a serious memory
error: the variable goes out of scope and may be filled with
garbage by the time the tempfile code looks at it.  Let's
see if we can make it harder to get this wrong.

Since many callers need to allocate arbitrary numbers of
tempfiles, we can't rely on static storage as a general
solution. So we need to turn to the heap. We could just ask
all callers to pass us a heap variable, but that puts the
burden on them to call free() at the right time.

Instead, let's have the tempfile code handle the heap
allocation _and_ the deallocation (when the tempfile is
deactivated and removed from the list).

This changes the return value of all of the creation
functions. For the cleanup functions (delete and rename),
we'll add one extra bit of safety: instead of taking a
tempfile pointer, we'll take a pointer-to-pointer and set it
to NULL after freeing the object. This makes it safe to
double-call functions like delete_tempfile(), as the second
call treats the NULL input as a noop. Several callsites
follow this pattern.

The resulting patch does have a fair bit of noise, as each
caller needs to be converted to handle:

  1. Storing a pointer instead of the struct itself.

  2. Passing the pointer instead of taking the struct
     address.

  3. Handling a "struct tempfile *" return instead of a file
     descriptor.

We could play games to make this less noisy. For example, by
defining the tempfile like this:

  struct tempfile {
	struct heap_allocated_part_of_tempfile {
                int fd;
                ...etc
        } *actual_data;
  }

Callers would continue to have a "struct tempfile", and it
would be "active" only when the inner pointer was non-NULL.
But that just makes things more awkward in the long run.
There aren't that many callers, so we can simply bite
the bullet and adjust all of them. And the compiler makes it
easy for us to find them all.

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

321 lines
8.3 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 removed from `tempfile_list` (but could be used again)
*
* 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);
}
static struct tempfile *new_tempfile(void)
{
struct tempfile *tempfile = xmalloc(sizeof(*tempfile));
tempfile->fd = -1;
tempfile->fp = NULL;
tempfile->active = 0;
tempfile->owner = 0;
INIT_LIST_HEAD(&tempfile->list);
strbuf_init(&tempfile->filename, 0);
return tempfile;
}
static void activate_tempfile(struct tempfile *tempfile)
{
static int initialized;
if (is_tempfile_active(tempfile))
BUG("activate_tempfile called for active object");
if (!initialized) {
sigchain_push_common(remove_tempfiles_on_signal);
atexit(remove_tempfiles_on_exit);
initialized = 1;
}
volatile_list_add(&tempfile->list, &tempfile_list);
tempfile->owner = getpid();
tempfile->active = 1;
}
static void deactivate_tempfile(struct tempfile *tempfile)
{
tempfile->active = 0;
strbuf_release(&tempfile->filename);
volatile_list_del(&tempfile->list);
free(tempfile);
}
/* Make sure errno contains a meaningful value on error */
struct tempfile *create_tempfile(const char *path)
{
struct tempfile *tempfile = new_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 NULL;
}
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 NULL;
}
return tempfile;
}
struct tempfile *register_tempfile(const char *path)
{
struct tempfile *tempfile = new_tempfile();
strbuf_add_absolute_path(&tempfile->filename, path);
activate_tempfile(tempfile);
return tempfile;
}
struct tempfile *mks_tempfile_sm(const char *template, int suffixlen, int mode)
{
struct tempfile *tempfile = new_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 NULL;
}
activate_tempfile(tempfile);
return tempfile;
}
struct tempfile *mks_tempfile_tsm(const char *template, int suffixlen, int mode)
{
struct tempfile *tempfile = new_tempfile();
const char *tmpdir;
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 NULL;
}
activate_tempfile(tempfile);
return tempfile;
}
struct tempfile *xmks_tempfile_m(const char *template, int mode)
{
struct tempfile *tempfile;
struct strbuf full_template = STRBUF_INIT;
strbuf_add_absolute_path(&full_template, template);
tempfile = mks_tempfile_m(full_template.buf, mode);
if (!tempfile)
die_errno("Unable to create temporary file '%s'",
full_template.buf);
strbuf_release(&full_template);
return tempfile;
}
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_p, const char *path)
{
struct tempfile *tempfile = *tempfile_p;
if (!is_tempfile_active(tempfile))
BUG("rename_tempfile called for inactive object");
if (close_tempfile_gently(tempfile)) {
delete_tempfile(tempfile_p);
return -1;
}
if (rename(tempfile->filename.buf, path)) {
int save_errno = errno;
delete_tempfile(tempfile_p);
errno = save_errno;
return -1;
}
deactivate_tempfile(tempfile);
*tempfile_p = NULL;
return 0;
}
void delete_tempfile(struct tempfile **tempfile_p)
{
struct tempfile *tempfile = *tempfile_p;
if (!is_tempfile_active(tempfile))
return;
close_tempfile_gently(tempfile);
unlink_or_warn(tempfile->filename.buf);
deactivate_tempfile(tempfile);
*tempfile_p = NULL;
}