From 076aa2cbda5782426c45cd65017b81d77876297a Mon Sep 17 00:00:00 2001 From: Jeff King Date: Tue, 5 Sep 2017 08:15:08 -0400 Subject: 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 Signed-off-by: Junio C Hamano --- refs/files-backend.c | 4 ++-- refs/packed-backend.c | 11 ++++++----- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'refs') diff --git a/refs/files-backend.c b/refs/files-backend.c index bc1899cd4a..36fe8a986b 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -1747,12 +1747,12 @@ static int create_symref_locked(struct files_ref_store *refs, if (!fdopen_lock_file(lock->lk, "w")) return error("unable to fdopen %s: %s", - lock->lk->tempfile.filename.buf, strerror(errno)); + lock->lk->tempfile->filename.buf, strerror(errno)); update_symref_reflog(refs, lock, refname, target, logmsg); /* no error check; commit_ref will check ferror */ - fprintf(lock->lk->tempfile.fp, "ref: %s\n", target); + fprintf(lock->lk->tempfile->fp, "ref: %s\n", target); if (commit_ref(lock) < 0) return error("unable to write symref for %s: %s", refname, strerror(errno)); diff --git a/refs/packed-backend.c b/refs/packed-backend.c index dca887c0fe..321608a114 100644 --- a/refs/packed-backend.c +++ b/refs/packed-backend.c @@ -75,7 +75,7 @@ struct packed_ref_store { * "packed-refs" file. Note that this (and thus the enclosing * `packed_ref_store`) must not be freed. */ - struct tempfile tempfile; + struct tempfile *tempfile; }; struct ref_store *packed_ref_store_create(const char *path, @@ -628,7 +628,8 @@ int commit_packed_refs(struct ref_store *ref_store, struct strbuf *err) */ packed_refs_path = get_locked_file_path(&refs->lock); strbuf_addf(&sb, "%s.new", packed_refs_path); - if (create_tempfile(&refs->tempfile, sb.buf) < 0) { + refs->tempfile = create_tempfile(sb.buf); + if (!refs->tempfile) { strbuf_addf(err, "unable to create file %s: %s", sb.buf, strerror(errno)); strbuf_release(&sb); @@ -636,7 +637,7 @@ int commit_packed_refs(struct ref_store *ref_store, struct strbuf *err) } strbuf_release(&sb); - out = fdopen_tempfile(&refs->tempfile, "w"); + out = fdopen_tempfile(refs->tempfile, "w"); if (!out) { strbuf_addf(err, "unable to fdopen packed-refs tempfile: %s", strerror(errno)); @@ -645,7 +646,7 @@ int commit_packed_refs(struct ref_store *ref_store, struct strbuf *err) if (fprintf(out, "%s", PACKED_REFS_HEADER) < 0) { strbuf_addf(err, "error writing to %s: %s", - get_tempfile_path(&refs->tempfile), strerror(errno)); + get_tempfile_path(refs->tempfile), strerror(errno)); goto error; } @@ -657,7 +658,7 @@ int commit_packed_refs(struct ref_store *ref_store, struct strbuf *err) if (write_packed_entry(out, iter->refname, iter->oid->hash, peel_error ? NULL : peeled.hash)) { strbuf_addf(err, "error writing to %s: %s", - get_tempfile_path(&refs->tempfile), + get_tempfile_path(refs->tempfile), strerror(errno)); ref_iterator_abort(iter); goto error; -- cgit v1.2.3