add options to binary_to_term

term_to_binary and binary_to_term are powerful tools that can be used easily in
lieu of a custom binary network protocol.  Unfortunately, carefully crafted
data can be used to exhaust the memory in an Erlang node by merely attempting
to decode binaries.  This makes it unsafe to receive data from untrusted
sources.

This is possible because binary_to_term/1 will allocate new atoms and new
external function references.  These data structures are not garbage collected.

This patch implements the new form of binary_to_term that takes a list of
options, and a simple option called 'safe'.  If specified, this option will
cause decoding to fail with a badarg error if an atom or external function
reference would be allocated.

In the general case, it will happily decode any Erlang term other than those
containing new atoms or new external function references.  However, fun, pid,
and ref data types can embed atoms.  They might fail to decode if one of these
embedded atoms is new to the node.  This may be an issue if encoded binaries
are transferred between nodes or persisted between invocations of Erlang.

6 files changed, 162 insertions, 19 deletions

diff --git a/erts/doc/src/erlang.xml b/erts/doc/src/erlang.xml
index 871fc0fd63..2541aa700b 100644
--- a/erts/doc/src/erlang.xml
+++ b/erts/doc/src/erlang.xml
@@ -342,8 +342,50 @@ iolist() = [char() | binary() | iolist()]
       <desc>
         <p>Returns an Erlang term which is the result of decoding
           the binary object <c>Binary</c>, which must be encoded
-          according to the Erlang external term format. See also
-          <seealso marker="#term_to_binary/1">term_to_binary/1</seealso>.</p>
+          according to the Erlang external term format.</p>
+        <warning>
+	  <p>When decoding binaries from untrusted sources, consider using
+	     <c>binary_to_term/2</c> to prevent denial of service attacks.</p>
+        </warning>
+	<p>See also
+	   <seealso marker="#term_to_binary/1">term_to_binary/1</seealso>
+           and
+	   <seealso marker="#binary_to_term/2">binary_to_term/2</seealso>.</p>
+      </desc>
+    </func>
+    <func>
+      <name>erlang:binary_to_term(Binary, Opts) -> term()</name>
+      <fsummary>Decode an Erlang external term format binary</fsummary>
+      <type>
+        <v>Opts = [safe]</v>
+        <v>Binary = ext_binary()</v>
+      </type>
+      <desc>
+        <p>As <c>binary_to_term/1</c>, but takes options that affect decoding
+           of the binary.</p>
+        <taglist>
+          <tag><c>safe</c></tag>
+          <item>
+	    <p>Use this option when receiving binaries from an untrusted
+               source.</p>
+	    <p>When enabled, it prevents decoding data that may be used to
+	       attack the Erlang system.  In the event of receiving unsafe
+               data, decoding fails with a badarg error.</p>
+	    <p>Currently, this prevents creation of new atoms directly,
+	       creation of new atoms indirectly (as they are embedded in
+	       certain structures like pids, refs, funs, etc.), and creation of
+	       new external function references.  None of those resources are
+	       currently garbage collected, so unchecked creation of them can
+               exhaust available memory.</p>
+          </item>
+        </taglist>
+	<p>Failure: <c>badarg</c> if <c>safe</c> is specified and unsafe data
+           is decoded.</p>
+        <p>See also
+           <seealso marker="#term_to_binary/1">term_to_binary/1</seealso>,
+           <seealso marker="#binary_to_term/1">binary_to_term/1</seealso>,
+           and <seealso marker="#list_to_existing_atom/1">
+             list_to_existing_atom/1</seealso>.</p>
       </desc>
     </func>
     <func>
diff --git a/erts/emulator/beam/atom.names b/erts/emulator/beam/atom.names
index 04eac2d807..117c4767c1 100644
--- a/erts/emulator/beam/atom.names
+++ b/erts/emulator/beam/atom.names
@@ -446,6 +446,7 @@ atom running
 atom running_ports
 atom running_procs
 atom runtime
+atom safe
 atom save_calls
 atom scheduler 
 atom scheduler_id
diff --git a/erts/emulator/beam/bif.tab b/erts/emulator/beam/bif.tab
index 85a729208f..ecc6c4699f 100644
--- a/erts/emulator/beam/bif.tab
+++ b/erts/emulator/beam/bif.tab
@@ -755,6 +755,11 @@ bif erlang:call_on_load_function/1
 bif erlang:finish_after_on_load/2
 
 #
+# New Bifs in R13B4
+#
+bif erlang:binary_to_term/2
+
+#
 # Obsolete
 #
 
diff --git a/erts/emulator/beam/external.c b/erts/emulator/beam/external.c
index f856cce18f..088a551329 100644
--- a/erts/emulator/beam/external.c
+++ b/erts/emulator/beam/external.c
@@ -1059,10 +1059,10 @@ binary2term_abort(ErtsBinary2TermState *state)
 }
 
 static ERTS_INLINE Eterm
-binary2term_create(ErtsBinary2TermState *state, Eterm **hpp, ErlOffHeap *ohp)
+binary2term_create(ErtsDistExternal *edep, ErtsBinary2TermState *state, Eterm **hpp, ErlOffHeap *ohp)
 {
     Eterm res;
-    if (!dec_term(NULL, hpp, state->extp, ohp, &res))
+    if (!dec_term(edep, hpp, state->extp, ohp, &res))
 	res = THE_NON_VALUE;
     if (state->exttmp) {
 	state->exttmp = 0;
@@ -1086,7 +1086,7 @@ erts_binary2term_abort(ErtsBinary2TermState *state)
 Eterm
 erts_binary2term_create(ErtsBinary2TermState *state, Eterm **hpp, ErlOffHeap *ohp)
 {
-    return binary2term_create(state, hpp, ohp);
+    return binary2term_create(NULL,state, hpp, ohp);
 }
 
 BIF_RETTYPE binary_to_term_1(BIF_ALIST_1)
@@ -1114,7 +1114,67 @@ BIF_RETTYPE binary_to_term_1(BIF_ALIST_1)
     hp = HAlloc(BIF_P, heap_size);
     endp = hp + heap_size;
 
-    res = binary2term_create(&b2ts, &hp, &MSO(BIF_P));
+    res = binary2term_create(NULL, &b2ts, &hp, &MSO(BIF_P));
+
+    erts_free_aligned_binary_bytes(temp_alloc);
+
+    if (hp > endp) {
+	erl_exit(1, ":%s, line %d: heap overrun by %d words(s)\n",
+		 __FILE__, __LINE__, hp-endp);
+    }
+
+    HRelease(BIF_P, endp, hp);
+
+    if (res == THE_NON_VALUE)
+	goto error;
+
+    return res;
+}
+
+BIF_RETTYPE binary_to_term_2(BIF_ALIST_2)
+{
+    Sint heap_size;
+    Eterm res;
+    Eterm opts;
+    Eterm opt;
+    Eterm* hp;
+    Eterm* endp;
+    Sint size;
+    byte* bytes;
+    byte* temp_alloc = NULL;
+    ErtsBinary2TermState b2ts;
+    ErtsDistExternal fakedep;
+
+    fakedep.flags = 0;
+    opts = BIF_ARG_2;
+    while (is_list(opts)) {
+        opt = CAR(list_val(opts));
+        if (opt == am_safe) {
+	    fakedep.flags |= ERTS_DIST_EXT_BTT_SAFE;
+        } else {
+            goto error;
+        }
+        opts = CDR(list_val(opts));
+    }
+
+    if (is_not_nil(opts))
+        goto error;
+
+    if ((bytes = erts_get_aligned_binary_bytes(BIF_ARG_1, &temp_alloc)) == NULL) {
+    error:
+	erts_free_aligned_binary_bytes(temp_alloc);
+	BIF_ERROR(BIF_P, BADARG);
+    }
+    size = binary_size(BIF_ARG_1);
+
+    heap_size = binary2term_prepare(&b2ts, bytes, size);
+    if (heap_size < 0)
+	goto error;
+
+    hp = HAlloc(BIF_P, heap_size);
+    endp = hp + heap_size;
+
+    res = binary2term_create(&fakedep, &b2ts, &hp, &MSO(BIF_P));
 
     erts_free_aligned_binary_bytes(temp_alloc);
 
@@ -1300,7 +1360,7 @@ dec_atom(ErtsDistExternal *edep, byte* ep, Eterm* objp)
 
     switch (*ep++) {
     case ATOM_CACHE_REF:
-	if (!(edep->flags & ERTS_DIST_EXT_ATOM_TRANS_TAB))
+	if (!(edep && (edep->flags & ERTS_DIST_EXT_ATOM_TRANS_TAB)))
 	    goto error;
 	n = get_int8(ep);
 	ep++;
@@ -1312,13 +1372,18 @@ dec_atom(ErtsDistExternal *edep, byte* ep, Eterm* objp)
     case ATOM_EXT:
 	len = get_int16(ep),
 	ep += 2;
-	*objp = am_atom_put((char*)ep, len);
-	ep += len;
-	break;
+        goto dec_atom_common;
     case SMALL_ATOM_EXT:
 	len = get_int8(ep);
 	ep++;
-	*objp = am_atom_put((char*)ep, len);
+    dec_atom_common:
+        if (edep && (edep->flags & ERTS_DIST_EXT_BTT_SAFE)) {
+	    if (!erts_atom_get((char*)ep, len, objp)) {
+                goto error;
+	    }
+        } else {
+            *objp = am_atom_put((char*)ep, len);
+        }
 	ep += len;
 	break;
     default:
@@ -1864,13 +1929,18 @@ dec_term(ErtsDistExternal *edep, Eterm** hpp, byte* ep, ErlOffHeap* off_heap, Et
 	case ATOM_EXT:
 	    n = get_int16(ep);
 	    ep += 2;
-	    *objp = am_atom_put((char*)ep, n);
-	    ep += n;
-	    break;
+            goto dec_term_atom_common;
 	case SMALL_ATOM_EXT:
 	    n = get_int8(ep);
 	    ep++;
-	    *objp = am_atom_put((char*)ep, n);
+dec_term_atom_common:
+	    if (edep && (edep->flags & ERTS_DIST_EXT_BTT_SAFE)) {
+		if (!erts_atom_get((char*)ep, n, objp)) {
+		    goto error;
+		}
+	    } else {
+	        *objp = am_atom_put((char*)ep, n);
+	    }
 	    ep += n;
 	    break;
 	case LARGE_TUPLE_EXT:
@@ -2039,7 +2109,6 @@ dec_term(ErtsDistExternal *edep, Eterm** hpp, byte* ep, ErlOffHeap* off_heap, Et
 		goto ref_ext_common;
 
 	    case NEW_REFERENCE_EXT:
-
 		ref_words = get_int16(ep);
 		ep += 2;
 
@@ -2218,6 +2287,10 @@ dec_term(ErtsDistExternal *edep, Eterm** hpp, byte* ep, ErlOffHeap* off_heap, Et
 		if (arity < 0) {
 		    goto error;
 		}
+		if (edep && (edep->flags & ERTS_DIST_EXT_BTT_SAFE)) {
+		    if (!erts_find_export_entry(mod, name, arity))
+			goto error;
+                }
 		*objp = make_export(hp);
 		*hp++ = HEADER_EXPORT;
 		*hp++ = (Eterm) erts_export_get_or_make_stub(mod, name, arity);
diff --git a/erts/emulator/beam/external.h b/erts/emulator/beam/external.h
index f308680f89..aa124f5197 100644
--- a/erts/emulator/beam/external.h
+++ b/erts/emulator/beam/external.h
@@ -100,7 +100,8 @@ typedef struct {
 
 #define ERTS_DIST_EXT_DFLAG_HDR (((Uint32) 1) << 31)
 #define ERTS_DIST_EXT_ATOM_TRANS_TAB (((Uint32) 1) << 30)
-#define ERTS_DIST_EXT_CON_ID_MASK ((Uint32) 0x3fffffff)
+#define ERTS_DIST_EXT_BTT_SAFE (((Uint32) 1) << 29)
+#define ERTS_DIST_EXT_CON_ID_MASK ((Uint32) 0x1fffffff)
 
 #define ERTS_DIST_EXT_CON_ID(DIST_EXTP) \
   ((DIST_EXTP)->flags & ERTS_DIST_EXT_CON_ID_MASK)
diff --git a/erts/emulator/test/binary_SUITE.erl b/erts/emulator/test/binary_SUITE.erl
index e47dfa18f7..83b815b883 100644
--- a/erts/emulator/test/binary_SUITE.erl
+++ b/erts/emulator/test/binary_SUITE.erl
@@ -27,6 +27,7 @@
 %%	binary_to_list/1
 %%	binary_to_list/3
 %%	binary_to_term/1
+%%  	binary_to_term/2
 %%      bitstr_to_list/1
 %%	term_to_binary/1
 %%      erlang:external_size/1
@@ -49,7 +50,7 @@
 	 t_hash/1,
 	 bad_size/1,
 	 bad_term_to_binary/1,
-	 bad_binary_to_term_2/1,
+	 bad_binary_to_term_2/1,safe_binary_to_term2/1,
 	 bad_binary_to_term/1, bad_terms/1, more_bad_terms/1,
 	 otp_5484/1,otp_5933/1,
 	 ordering/1,unaligned_order/1,gc_test/1,
@@ -66,7 +67,7 @@ all(suite) ->
      t_split_binary, bad_split, t_concat_binary,
      bad_list_to_binary, bad_binary_to_list, terms, terms_float,
      external_size, t_iolist_size,
-     bad_binary_to_term_2,
+     bad_binary_to_term_2,safe_binary_to_term2,
      bad_binary_to_term, bad_terms, t_hash, bad_size, bad_term_to_binary,
      more_bad_terms, otp_5484, otp_5933, ordering, unaligned_order,
      gc_test, bit_sized_binary_sizes, bitlevel_roundtrip, otp_6817, otp_8117,
@@ -438,8 +439,11 @@ terms(Config) when is_list(Config) ->
 			      ok
 		      end,
 		      Term = binary_to_term(Bin),
+		      Term = erlang:binary_to_term(Bin, [safe]),
 		      Unaligned = make_unaligned_sub_binary(Bin),
 		      Term = binary_to_term(Unaligned),
+		      Term = erlang:binary_to_term(Unaligned, []),
+		      Term = erlang:binary_to_term(Bin, [safe]),
 		      BinC = erlang:term_to_binary(Term, [compressed]),
 		      Term = binary_to_term(BinC),
 		      true = size(BinC) =< size(Bin),
@@ -538,6 +542,23 @@ bad_binary_to_term(Config) when is_list(Config) ->
 bad_bin_to_term(BadBin) ->
     {'EXIT',{badarg,_}} = (catch binary_to_term(BadBin)).
 
+bad_bin_to_term(BadBin,Opts) ->
+    {'EXIT',{badarg,_}} = (catch erlang:binary_to_term(BadBin,Opts)).
+
+safe_binary_to_term2(doc) -> "Test safety options for binary_to_term/2";
+safe_binary_to_term2(Config) when is_list(Config) ->
+    ?line bad_bin_to_term(<<131,100,0,14,"undefined_atom">>, [safe]),
+    ?line bad_bin_to_term(<<131,100,0,14,"other_bad_atom">>, [safe]),
+    BadHostAtom = <<100,0,14,"badguy@badhost">>,
+    Empty = <<0,0,0,0>>,
+    BadRef = <<131,114,0,3,BadHostAtom/binary,0,<<0,0,0,255>>/binary,
+	      Empty/binary,Empty/binary>>,
+    ?line bad_bin_to_term(BadRef, [safe]), % good ref, with a bad atom
+    ?line fullsweep_after = erlang:binary_to_term(<<131,100,0,15,"fullsweep_after">>, [safe]), % should be a good atom
+    BadExtFun = <<131,113,100,0,4,98,108,117,101,100,0,4,109,111,111,110,97,3>>,
+    ?line bad_bin_to_term(BadExtFun, [safe]),
+    ok.
+
 %% Tests bad input to binary_to_term/1.
 
 bad_terms(suite) -> [];