OpenZFS 9424 - ztest failure: "unprotected error in call to Lua API (Invalid value type 'function' for key 'error')"

Ztest failed with the following crash.

    ::status

    debugging core file of ztest (64-bit) from clone-dc-slave-280-bc7947b1.dcenter
    file: /usr/bin/amd64/ztest
    initial argv: /usr/bin/amd64/ztest
    threading model: raw lwps
    status: process terminated by SIGABRT (Abort), pid=2150 uid=1025 code=-1
    panic message: failure for thread 0xfffffd7fff112a40, thread-id 1: unprotected error in call to Lua API (Invalid
    value type 'function' for key 'error')

    ::stack

    libc.so.1`_lwp_kill+0xa()
    libc.so.1`_assfail+0x182(fffffd7fffdfe8d0, 0, 0)
    libc.so.1`assfail+0x19(fffffd7fffdfe8d0, 0, 0)
    libzpool.so.1`vpanic+0x3d(fffffd7ffaa58c20, fffffd7fffdfeb00)
    0xfffffd7ffaa28146()
    0xfffffd7ffaa0a109()
    libzpool.so.1`luaD_throw+0x86(3011a48, 2)
    0xfffffd7ffa9350d3()
    0xfffffd7ffa93e3f1()
    libzpool.so.1`zcp_lua_to_nvlist+0x33(3011a48, 1, 2686470, fffffd7ffaa2e2c3)
    libzpool.so.1`zcp_convert_return_values+0xa4(3011a48, 2686470, fffffd7ffaa2e2c3, fffffd7fffdfedd0)
    libzpool.so.1`zcp_pool_error+0x59(fffffd7fffdfedd0, 1e0f450)
    libzpool.so.1`zcp_eval+0x6f8(1e0f450, fffffd7ffaa483f8, 1, 0, 6400000, 1d33b30)
    libzpool.so.1`dsl_destroy_snapshots_nvl+0x12c(2786b60, 0, 484750)
    libzpool.so.1`dsl_destroy_snapshot+0x4f(fffffd7fffdfef70, 0)
    ztest_dsl_dataset_cleanup+0xea(fffffd7fffdff4c0, 1)
    ztest_dataset_destroy+0x53(1)
    ztest_run+0x59f(fffffd7fff0e0498)
    main+0x7ff(1, fffffd7fffdffa88)
    _start+0x6c()

The problem is that zcp_convert_return_values() assumes that there's
exactly one value on the stack, but that isn't always true. It ends up
putting the wrong thing on the stack which is then consumed by
zcp_convert_return values, which either adds the wrong message to the
nvlist, or blows up.

The fix is to make sure that callers of zcp_convert_return_values()
clear the stack before pushing their error message, and
zcp_convert_return_values() should VERIFY that the stack is the expected
size.

Authored by: Matthew Ahrens <[email protected]>
Reviewed by: Sebastien Roy <[email protected]>
Reviewed by: Paul Dagnelie <[email protected]>
Reviewed by: Don Brady <[email protected]>
Ported-by: Brian Behlendorf <[email protected]>
Approved by: Robert Mustacchi <[email protected]>

OpenZFS-issue: https://www.illumos.org/issues/9424
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/eb7e57429
Closes #7696

1 files changed, 6 insertions, 3 deletions

diff --git a/module/zfs/zcp.c b/module/zfs/zcp.c
index 475138621..4894df11d 100644
--- a/module/zfs/zcp.c
+++ b/module/zfs/zcp.c
@@ -429,7 +429,7 @@ zcp_lua_to_nvlist_impl(lua_State *state, int index, nvlist_t *nvl,
 /*
  * Convert a lua value to an nvpair, adding it to an nvlist with the given key.
  */
-void
+static void
 zcp_lua_to_nvlist(lua_State *state, int index, nvlist_t *nvl, const char *key)
 {
 	/*
@@ -441,7 +441,7 @@ zcp_lua_to_nvlist(lua_State *state, int index, nvlist_t *nvl, const char *key)
 		(void) lua_error(state);
 }
 
-int
+static int
 zcp_lua_to_nvlist_helper(lua_State *state)
 {
 	nvlist_t *nv = (nvlist_t *)lua_touserdata(state, 2);
@@ -450,11 +450,12 @@ zcp_lua_to_nvlist_helper(lua_State *state)
 	return (0);
 }
 
-void
+static void
 zcp_convert_return_values(lua_State *state, nvlist_t *nvl,
     const char *key, zcp_eval_arg_t *evalargs)
 {
 	int err;
+	VERIFY3U(1, ==, lua_gettop(state));
 	lua_pushcfunction(state, zcp_lua_to_nvlist_helper);
 	lua_pushlightuserdata(state, (char *)key);
 	lua_pushlightuserdata(state, nvl);
@@ -900,6 +901,7 @@ zcp_eval_impl(dmu_tx_t *tx, boolean_t sync, zcp_eval_arg_t *evalargs)
 			    ZCP_RET_RETURN, evalargs);
 		} else if (return_count > 1) {
 			evalargs->ea_result = SET_ERROR(ECHRNG);
+			lua_settop(state, 0);
 			(void) lua_pushfstring(state, "Multiple return "
 			    "values not supported");
 			zcp_convert_return_values(state, evalargs->ea_outnvl,
@@ -967,6 +969,7 @@ static void
 zcp_pool_error(zcp_eval_arg_t *evalargs, const char *poolname)
 {
 	evalargs->ea_result = SET_ERROR(ECHRNG);
+	lua_settop(evalargs->ea_state, 0);
 	(void) lua_pushfstring(evalargs->ea_state, "Could not open pool: %s",
 	    poolname);
 	zcp_convert_return_values(evalargs->ea_state, evalargs->ea_outnvl,