fetch: fix deadlock when cleaning up lockfiles in async signals

When fetching packfiles, we write a bunch of lockfiles for the packfiles
we're writing into the repository. In order to not leave behind any
cruft in case we exit or receive a signal, we register both an exit
handler as well as signal handlers for common signals like SIGINT. These
handlers will then unlink the locks and free the data structure tracking
them. We have observed a deadlock in this logic though:

    (gdb) bt
    #0  __lll_lock_wait_private () at ../sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:95
    #1  0x00007f4932bea2cd in _int_free (av=0x7f4932f2eb20 <main_arena>, p=0x3e3e4200, have_lock=0) at malloc.c:3969
    #2  0x00007f4932bee58c in __GI___libc_free (mem=<optimized out>) at malloc.c:2975
    #3  0x0000000000662ab1 in string_list_clear ()
    #4  0x000000000044f5bc in unlock_pack_on_signal ()
    #5  <signal handler called>
    #6  _int_free (av=0x7f4932f2eb20 <main_arena>, p=<optimized out>, have_lock=0) at malloc.c:4024
    #7  0x00007f4932bee58c in __GI___libc_free (mem=<optimized out>) at malloc.c:2975
    #8  0x000000000065afd5 in strbuf_release ()
    #9  0x000000000066ddb9 in delete_tempfile ()
    #10 0x0000000000610d0b in files_transaction_cleanup.isra ()
    #11 0x0000000000611718 in files_transaction_abort ()
    #12 0x000000000060d2ef in ref_transaction_abort ()
    #13 0x000000000060d441 in ref_transaction_prepare ()
    #14 0x000000000060e0b5 in ref_transaction_commit ()
    #15 0x00000000004511c2 in fetch_and_consume_refs ()
    #16 0x000000000045279a in cmd_fetch ()
    #17 0x0000000000407c48 in handle_builtin ()
    #18 0x0000000000408df2 in cmd_main ()
    #19 0x00000000004078b5 in main ()

The process was killed with a signal, which caused the signal handler to
kick in and try free the data structures after we have unlinked the
locks. It then deadlocks while calling free(3P).

The root cause of this is that it is not allowed to call certain
functions in async-signal handlers, as specified by signal-safety(7).
Next to most I/O functions, this list of disallowed functions also
includes memory-handling functions like malloc(3P) and free(3P) because
they may not be reentrant. As a result, if we execute such functions in
the signal handler, then they may operate on inconistent state and fail
in unexpected ways.

Fix this bug by not calling non-async-signal-safe functions when running
in the signal handler. We're about to re-raise the signal anyway and
will thus exit, so it's not much of a problem to keep the string list of
lockfiles untouched. Note that it's fine though to call unlink(2), so
we'll still clean up the lockfiles correctly.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Reviewed-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 12 insertions, 7 deletions

diff --git a/builtin/clone.c b/builtin/clone.c
index fb377b2765..dd42c89b68 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -1290,7 +1290,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	 */
 	submodule_progress = transport->progress;
 
-	transport_unlock_pack(transport);
+	transport_unlock_pack(transport, 0);
 	transport_disconnect(transport);
 
 	if (option_dissociate) {
diff --git a/builtin/fetch.c b/builtin/fetch.c
index f7abbc31ff..7edf98e33b 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -222,17 +222,22 @@ static struct option builtin_fetch_options[] = {
 	OPT_END()
 };
 
-static void unlock_pack(void)
+static void unlock_pack(unsigned int flags)
 {
 	if (gtransport)
-		transport_unlock_pack(gtransport);
+		transport_unlock_pack(gtransport, flags);
 	if (gsecondary)
-		transport_unlock_pack(gsecondary);
+		transport_unlock_pack(gsecondary, flags);
+}
+
+static void unlock_pack_atexit(void)
+{
+	unlock_pack(0);
 }
 
 static void unlock_pack_on_signal(int signo)
 {
-	unlock_pack();
+	unlock_pack(TRANSPORT_UNLOCK_PACK_IN_SIGNAL_HANDLER);
 	sigchain_pop(signo);
 	raise(signo);
 }
@@ -1326,7 +1331,7 @@ static int fetch_and_consume_refs(struct transport *transport, struct ref *ref_m
 	trace2_region_leave("fetch", "consume_refs", the_repository);
 
 out:
-	transport_unlock_pack(transport);
+	transport_unlock_pack(transport, 0);
 	return ret;
 }
 
@@ -1962,7 +1967,7 @@ static int fetch_one(struct remote *remote, int argc, const char **argv,
 		gtransport->server_options = &server_options;
 
 	sigchain_push_common(unlock_pack_on_signal);
-	atexit(unlock_pack);
+	atexit(unlock_pack_atexit);
 	sigchain_push(SIGPIPE, SIG_IGN);
 	exit_code = do_fetch(gtransport, &rs);
 	sigchain_pop(SIGPIPE);