[sledge][llvm] Fix a possible crash in llvm_struct_name

Summary:
The implementation of `llvm_struct_name` before this diff calls
`caml_copy_string`, which allocates, while the `result` local variable
points to a block allocated by `caml_alloc_small` that has not yet
been initialized. If the allocation in `caml_copy_string` triggers a
garbage collection, then the GC root `result` contains a pointer to
uninitialized data, which may crash the GC or lead to a memory
corruption.

This diff fixes this by allocating and initializing the string first
and then allocating and initializing the option, thereby leaving no
dangling pointers when allocations are made.

The conversion from a C string to an OCaml string option is refactored
into a function, `cstr_to_string_option`. This function is also used
to simplify the definitions of `llvm_get_mdstring` and
`llvm_string_of_const`.

Upstream Differential Revision: https://reviews.llvm.org/D99393

Reviewed By: ngorogiannis

Differential Revision: D27360848

fbshipit-source-id: f2daa7561

sledge/vendor/llvm-dune/llvm-project/llvm/bindings/ocaml/llvm/llvm_ocaml.c

@@ -45,6 +45,18 @@ CAMLprim value ptr_to_option(void *Ptr) {
   CAMLreturn(Option);
 }
 
+CAMLprim value cstr_to_string_option(const char *CStr, mlsize_t Len) {
+  CAMLparam0();
+  CAMLlocal2(Option, String);
+  if (!CStr)
+    CAMLreturn(Val_int(0));
+  String = caml_alloc_string(Len);
+  memcpy((char *)String_val(String), CStr, Len);
+  Option = caml_alloc_small(1, 0);
+  Store_field(Option, 0, (value)String);
+  CAMLreturn(Option);
+}
+
 void llvm_raise(value Prototype, char *Message) {
   CAMLparam1(Prototype);
   caml_raise_with_arg(Prototype, llvm_string_of_message(Message));
@@ -491,17 +503,13 @@ CAMLprim value llvm_struct_set_body(LLVMTypeRef Ty,
 }
 
 /* lltype -> string option */
-CAMLprim value llvm_struct_name(LLVMTypeRef Ty)
+CAMLprim value llvm_struct_name(LLVMTypeRef Ty) {
-{
+  const char *CStr = LLVMGetStructName(Ty);
-  CAMLparam0();
+  size_t Len;
-  CAMLlocal1(result);
+  if (!CStr)
-  const char *C = LLVMGetStructName(Ty);
+    return Val_int(0);
-  if (C) {
+  Len = strlen(CStr);
-    result = caml_alloc_small(1, 0);
+  return cstr_to_string_option(CStr, Len);
-    Store_field(result, 0, caml_copy_string(C));
-    CAMLreturn(result);
-  }
-  CAMLreturn(Val_int(0));
 }
 
 /* lltype -> lltype array */
@@ -832,19 +840,9 @@ CAMLprim LLVMValueRef llvm_mdnull(LLVMContextRef C) {
 
 /* llvalue -> string option */
 CAMLprim value llvm_get_mdstring(LLVMValueRef V) {
-  CAMLparam0();
-  CAMLlocal2(Option, Str);
-  const char *S;
   unsigned Len;
-
+  const char *CStr = LLVMGetMDString(V, &Len);
-  if ((S = LLVMGetMDString(V, &Len))) {
+  return cstr_to_string_option(CStr, Len);
-    Str = caml_alloc_string(Len);
-    memcpy((char *)String_val(Str), S, Len);
-    Option = alloc(1,0);
-    Store_field(Option, 0, Str);
-    CAMLreturn(Option);
-  }
-  CAMLreturn(Val_int(0));
 }
 
 CAMLprim value llvm_get_mdnode_operands(LLVMValueRef V) {
@@ -874,20 +872,6 @@ CAMLprim value llvm_append_namedmd(LLVMModuleRef M, value Name, LLVMValueRef Val
   return Val_unit;
 }
 
-/* Convert a C string with length to an OCaml string option */
-CAMLprim value cstr_to_string_option(const char *Chars, unsigned Length) {
-  CAMLparam0();
-  CAMLlocal2(Option, String);
-  if (Length > 0) {
-    String = caml_alloc_string(Length);
-    memcpy(String_val(String), Chars, Length);
-    Option = caml_alloc_small(1, 0);
-    Store_field(Option, 0, String);
-    CAMLreturn(Option);
-  }
-  CAMLreturn(Val_int(0));
-}
-
 /* Get the DIVariable associated with a GlobalVariable */
 LLVMMetadataRef global_variable_get_divariable(LLVMValueRef GV) {
   LLVMMetadataRef Var = NULL;
@@ -1109,22 +1093,12 @@ CAMLprim LLVMValueRef llvm_const_vector(value ElementVals) {
 
 /* llvalue -> string option */
 CAMLprim value llvm_string_of_const(LLVMValueRef Const) {
-  const char *S;
   size_t Len;
-  CAMLparam0();
+  const char *CStr;
-  CAMLlocal2(Option, Str);
+  if (!LLVMIsAConstantDataSequential(Const) || !LLVMIsConstantString(Const))
-
+    return Val_int(0);
-  if(LLVMIsAConstantDataSequential(Const) && LLVMIsConstantString(Const)) {
+  CStr = LLVMGetAsString(Const, &Len);
-    S = LLVMGetAsString(Const, &Len);
+  return cstr_to_string_option(CStr, Len);
-    Str = caml_alloc_string(Len);
-    memcpy((char *)String_val(Str), S, Len);
-
-    Option = alloc(1, 0);
-    Field(Option, 0) = Str;
-    CAMLreturn(Option);
-  } else {
-    CAMLreturn(Val_int(0));
-  }
 }
 
 /* llvalue -> int -> llvalue */