Improve support of GNU mempcpy

- Lower to the memcpy intrinsic
- Raise warnings when size/bounds are known

Author: serge-sans-paille

clang/include/clang/Basic/Builtins.def

@@ -984,6 +984,7 @@ LIBBUILTIN(longjmp, "vJi",        "fr",    "setjmp.h", ALL_LANGUAGES)
 LIBBUILTIN(alloca, "v*z",         "f",     "stdlib.h", ALL_GNU_LANGUAGES)
 // POSIX string.h
 LIBBUILTIN(memccpy, "v*v*vC*iz",  "f",     "string.h", ALL_GNU_LANGUAGES)
+LIBBUILTIN(mempcpy, "v*v*vC*z",   "f",     "string.h", ALL_GNU_LANGUAGES)
 LIBBUILTIN(stpcpy, "c*c*cC*",     "f",     "string.h", ALL_GNU_LANGUAGES)
 LIBBUILTIN(stpncpy, "c*c*cC*z",   "f",     "string.h", ALL_GNU_LANGUAGES)
 LIBBUILTIN(strdup, "c*cC*",       "f",     "string.h", ALL_GNU_LANGUAGES)

clang/lib/AST/Decl.cpp

@@ -3866,6 +3866,11 @@ unsigned FunctionDecl::getMemoryFunctionKind() const {
   case Builtin::BImemcpy:
     return Builtin::BImemcpy;
 
+  case Builtin::BI__builtin_mempcpy:
+  case Builtin::BI__builtin___mempcpy_chk:
+  case Builtin::BImempcpy:
+    return Builtin::BImempcpy;
+
   case Builtin::BI__builtin_memmove:
   case Builtin::BI__builtin___memmove_chk:
   case Builtin::BImemmove:
@@ -3923,6 +3928,8 @@ unsigned FunctionDecl::getMemoryFunctionKind() const {
         return Builtin::BImemset;
       else if (FnInfo->isStr("memcpy"))
         return Builtin::BImemcpy;
+      else if (FnInfo->isStr("mempcpy"))
+        return Builtin::BImempcpy;
       else if (FnInfo->isStr("memmove"))
         return Builtin::BImemmove;
       else if (FnInfo->isStr("memcmp"))

clang/lib/CodeGen/CGBuiltin.cpp

@@ -2506,7 +2506,9 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
     return RValue::get(nullptr);
   }
   case Builtin::BImemcpy:
-  case Builtin::BI__builtin_memcpy: {
+  case Builtin::BI__builtin_memcpy:
+  case Builtin::BImempcpy:
+  case Builtin::BI__builtin_mempcpy: {
     Address Dest = EmitPointerWithAlignment(E->getArg(0));
     Address Src = EmitPointerWithAlignment(E->getArg(1));
     Value *SizeVal = EmitScalarExpr(E->getArg(2));
@@ -2515,7 +2517,11 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
     EmitNonNullArgCheck(RValue::get(Src.getPointer()), E->getArg(1)->getType(),
                         E->getArg(1)->getExprLoc(), FD, 1);
     Builder.CreateMemCpy(Dest, Src, SizeVal, false);
-    return RValue::get(Dest.getPointer());
+    if (BuiltinID == Builtin::BImempcpy ||
+        BuiltinID == Builtin::BI__builtin_mempcpy)
+      return RValue::get(Builder.CreateInBoundsGEP(Dest.getPointer(), SizeVal));
+    else
+      return RValue::get(Dest.getPointer());
   }
 
   case Builtin::BI__builtin_char_memchr:

clang/lib/Sema/SemaChecking.cpp

@@ -340,7 +340,8 @@ void Sema::checkFortifiedBuiltinMemoryFunction(FunctionDecl *FD,
   case Builtin::BI__builtin___strncat_chk:
   case Builtin::BI__builtin___strncpy_chk:
   case Builtin::BI__builtin___stpncpy_chk:
-  case Builtin::BI__builtin___memccpy_chk: {
+  case Builtin::BI__builtin___memccpy_chk:
+  case Builtin::BI__builtin___mempcpy_chk: {
     DiagID = diag::warn_builtin_chk_overflow;
     IsChkVariant = true;
     SizeIndex = TheCall->getNumArgs() - 2;
@@ -379,7 +380,9 @@ void Sema::checkFortifiedBuiltinMemoryFunction(FunctionDecl *FD,
   case Builtin::BImemmove:
   case Builtin::BI__builtin_memmove:
   case Builtin::BImemset:
-  case Builtin::BI__builtin_memset: {
+  case Builtin::BI__builtin_memset:
+  case Builtin::BImempcpy:
+  case Builtin::BI__builtin_mempcpy: {
     DiagID = diag::warn_fortify_source_overflow;
     SizeIndex = TheCall->getNumArgs() - 1;
     ObjectIndex = 0;

clang/test/Analysis/bstring.c

@@ -222,6 +222,9 @@ void mempcpy2 () {
   char dst[1];
 
   mempcpy(dst, src, 4); // expected-warning{{Memory copy function overflows destination buffer}}
+#ifndef VARIANT
+// expected-warning@-2{{'mempcpy' will always overflow; destination buffer has size 1, but size argument is 4}}
+#endif
 }
 
 void mempcpy3 () {
@@ -243,6 +246,9 @@ void mempcpy5() {
   char dst[3];
 
   mempcpy(dst+2, src+2, 2); // expected-warning{{Memory copy function overflows destination buffer}}
+#ifndef VARIANT
+// expected-warning@-2{{'mempcpy' will always overflow; destination buffer has size 1, but size argument is 2}}
+#endif
 }
 
 void mempcpy6() {

clang/test/CodeGen/mempcpy-libcall.c

@@ -0,0 +1,12 @@
+// RUN: %clang_cc1 -emit-llvm < %s| FileCheck %s
+
+typedef __SIZE_TYPE__ size_t;
+
+void *mempcpy(void *, void const *, size_t);
+
+char *test(char *d, char *s, size_t n) {
+  // CHECK:      call void @llvm.memcpy.p0i8.p0i8.i64(i8* {{.*}} %[[REG1:[^ ]+]], i8* {{.*}} %1, i64 %[[REG2:[^ ]+]], i1 false)
+  // CHECK-NEXT: %[[REGr:[^ ]+]] = getelementptr inbounds i8, i8* %[[REG1]], i64 %[[REG2]]
+  // CHECK-NEXT: ret i8* %[[REGr]]
+  return mempcpy(d, s, n);
+}