diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
index 91c3e60bb0acb..dcf6ca4cb58a7 100644
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -12658,10 +12658,67 @@ This instruction requires several arguments:
       the return value of the callee is returned to the caller's caller, even
       if a void return type is in use.
 
-   Both markers imply that the callee does not access allocas from the caller.
-   The ``tail`` marker additionally implies that the callee does not access
-   varargs from the caller. Calls marked ``musttail`` must obey the following
-   additional  rules:
+   Both markers imply that the callee does not access allocas, va_args, or
+   byval arguments from the caller. As an exception to that, an alloca or byval
+   argument may be passed to the callee as a byval argument, which can be
+   dereferenced inside the callee. For example:
+
+.. code-block:: llvm
+
+      declare void @take_byval(ptr byval(i64))
+      declare void @take_ptr(ptr)
+
+      ; Invalid (assuming @take_ptr dereferences the pointer), because %local
+      ; may be de-allocated before the call to @take_ptr.
+      define void @invalid_alloca() {
+      entry:
+        %local = alloca i64
+        tail call void @take_ptr(ptr %local)
+        ret void
+      }
+
+      ; Valid, the byval attribute causes the memory allocated by %local to be
+      ; copied into @take_byval's stack frame.
+      define void @byval_alloca() {
+      entry:
+        %local = alloca i64
+        tail call void @take_byval(ptr byval(i64) %local)
+        ret void
+      }
+
+      ; Invalid, because @use_global_va_list uses the variadic arguments from
+      ; @invalid_va_list.
+      %struct.va_list = type { ptr }
+      @va_list = external global %struct.va_list
+      define void @use_global_va_list() {
+      entry:
+        %arg = va_arg ptr @va_list, i64
+        ret void
+      }
+      define void @invalid_va_list(i32 %a, ...) {
+      entry:
+        call void @llvm.va_start.p0(ptr @va_list)
+        tail call void @use_global_va_list()
+        ret void
+      }
+
+      ; Valid, byval argument forwarded to tail call as another byval argument.
+      define void @forward_byval(ptr byval(i64) %x) {
+      entry:
+        tail call void @take_byval(ptr byval(i64) %x)
+        ret void
+      }
+
+      ; Invalid (assuming @take_ptr dereferences the pointer), byval argument
+      ; passed to tail callee as non-byval ptr.
+      define void @invalid_byval(ptr byval(i64) %x) {
+      entry:
+        tail call void @take_ptr(ptr %x)
+        ret void
+      }
+
+
+   Calls marked ``musttail`` must obey the following additional rules:
 
    - The call must immediately precede a :ref:`ret <i_ret>` instruction,
      or a pointer bitcast followed by a ret instruction.
diff --git a/llvm/test/CodeGen/ARM/struct_byval.ll b/llvm/test/CodeGen/ARM/struct_byval.ll
index 73a1b5ee33bca..2bc4f9c816d53 100644
--- a/llvm/test/CodeGen/ARM/struct_byval.ll
+++ b/llvm/test/CodeGen/ARM/struct_byval.ll
@@ -63,25 +63,6 @@ declare i32 @e1(ptr nocapture byval(%struct.SmallStruct) %in) nounwind
 declare i32 @e2(ptr nocapture byval(%struct.LargeStruct) %in) nounwind
 declare i32 @e3(ptr nocapture byval(%struct.LargeStruct) align 16 %in) nounwind
 
-; rdar://12442472
-; We can't do tail call since address of s is passed to the callee and part of
-; s is in caller's local frame.
-define void @f3(ptr nocapture byval(%struct.SmallStruct) %s) nounwind optsize {
-; CHECK-LABEL: f3
-; CHECK: bl _consumestruct
-entry:
-  tail call void @consumestruct(ptr %s, i32 80) optsize
-  ret void
-}
-
-define void @f4(ptr nocapture byval(%struct.SmallStruct) %s) nounwind optsize {
-; CHECK-LABEL: f4
-; CHECK: bl _consumestruct
-entry:
-  tail call void @consumestruct(ptr %s, i32 80) optsize
-  ret void
-}
-
 ; We can do tail call here since s is in the incoming argument area.
 define void @f5(i32 %a, i32 %b, i32 %c, i32 %d, ptr nocapture byval(%struct.SmallStruct) %s) nounwind optsize {
 ; CHECK-LABEL: f5