Recognize setjmp and friends as builtins even if jmp_buf is not declared yet.

This happens in glibc's headers. It's important that we recognize these
functions so that we can mark them as returns_twice.

Differential Revision: https://reviews.llvm.org/D88518

6 files changed, 116 insertions, 32 deletions

diff --git a/clang/include/clang/Basic/Builtins.def b/clang/include/clang/Basic/Builtins.def
index 01c28eb..dbb5dde 100644
--- a/clang/include/clang/Basic/Builtins.def
+++ b/clang/include/clang/Basic/Builtins.def
@@ -75,6 +75,9 @@
 //  U -> pure
 //  c -> const
 //  t -> signature is meaningless, use custom typechecking
+//  T -> type is not important to semantic analysis and codegen; recognize as
+//       builtin even if type doesn't match signature, and don't warn if we
+//       can't be sure the type is right
 //  F -> this is a libc/libm function with a '__builtin_' prefix added.
 //  f -> this is a libc/libm function without the '__builtin_' prefix. It can
 //       be followed by ':headername:' to state which header this function
@@ -893,7 +896,7 @@ LANGBUILTIN(__va_start,       "vc**.", "nt", ALL_MS_LANGUAGES)
 LANGBUILTIN(__fastfail, "vUi",    "nr", ALL_MS_LANGUAGES)
 
 // Microsoft library builtins.
-LIBBUILTIN(_setjmpex, "iJ", "fj",   "setjmpex.h", ALL_MS_LANGUAGES)
+LIBBUILTIN(_setjmpex, "iJ", "fjT", "setjmpex.h", ALL_MS_LANGUAGES)
 
 // C99 library functions
 // C99 stdarg.h
@@ -987,8 +990,8 @@ LIBBUILTIN(wmemmove,"w*w*wC*z", "f", "wchar.h", ALL_LANGUAGES)
 // In some systems setjmp is a macro that expands to _setjmp. We undefine
 // it here to avoid having two identical LIBBUILTIN entries.
 #undef setjmp
-LIBBUILTIN(setjmp, "iJ",          "fj",    "setjmp.h", ALL_LANGUAGES)
-LIBBUILTIN(longjmp, "vJi",        "fr",    "setjmp.h", ALL_LANGUAGES)
+LIBBUILTIN(setjmp, "iJ",          "fjT",   "setjmp.h", ALL_LANGUAGES)
+LIBBUILTIN(longjmp, "vJi",        "frT",   "setjmp.h", ALL_LANGUAGES)
 
 // Non-C library functions, active in GNU mode only.
 // Functions with (returns_twice) attribute (marked as "j") are still active in
@@ -1015,21 +1018,21 @@ LIBBUILTIN(strcasecmp, "icC*cC*", "f",     "strings.h", ALL_GNU_LANGUAGES)
 LIBBUILTIN(strncasecmp, "icC*cC*z", "f",   "strings.h", ALL_GNU_LANGUAGES)
 // POSIX unistd.h
 LIBBUILTIN(_exit, "vi",           "fr",    "unistd.h", ALL_GNU_LANGUAGES)
-LIBBUILTIN(vfork, "p",            "fj",    "unistd.h", ALL_LANGUAGES)
+LIBBUILTIN(vfork, "p",            "fjT",   "unistd.h", ALL_LANGUAGES)
 // POSIX pthread.h
 // FIXME: Should specify argument types.
 LIBBUILTIN(pthread_create, "",  "fC<2,3>", "pthread.h", ALL_GNU_LANGUAGES)
 
 // POSIX setjmp.h
 
-LIBBUILTIN(_setjmp, "iJ",         "fj",   "setjmp.h", ALL_LANGUAGES)
-LIBBUILTIN(__sigsetjmp, "iSJi",   "fj",   "setjmp.h", ALL_LANGUAGES)
-LIBBUILTIN(sigsetjmp, "iSJi",     "fj",   "setjmp.h", ALL_LANGUAGES)
-LIBBUILTIN(savectx, "iJ",         "fj",   "setjmp.h", ALL_LANGUAGES)
-LIBBUILTIN(getcontext, "iK*",     "fj",   "setjmp.h", ALL_LANGUAGES)
+LIBBUILTIN(_setjmp, "iJ",         "fjT",   "setjmp.h", ALL_LANGUAGES)
+LIBBUILTIN(__sigsetjmp, "iSJi",   "fjT",   "setjmp.h", ALL_LANGUAGES)
+LIBBUILTIN(sigsetjmp, "iSJi",     "fjT",   "setjmp.h", ALL_LANGUAGES)
+LIBBUILTIN(savectx, "iJ",         "fjT",   "setjmp.h", ALL_LANGUAGES)
+LIBBUILTIN(getcontext, "iK*",     "fjT",   "setjmp.h", ALL_LANGUAGES)
 
-LIBBUILTIN(_longjmp, "vJi",       "fr",    "setjmp.h", ALL_GNU_LANGUAGES)
-LIBBUILTIN(siglongjmp, "vSJi",    "fr",    "setjmp.h", ALL_GNU_LANGUAGES)
+LIBBUILTIN(_longjmp, "vJi",       "frT",   "setjmp.h", ALL_GNU_LANGUAGES)
+LIBBUILTIN(siglongjmp, "vSJi",    "frT",   "setjmp.h", ALL_GNU_LANGUAGES)
 // non-standard but very common
 LIBBUILTIN(strlcpy, "zc*cC*z",    "f",     "string.h", ALL_GNU_LANGUAGES)
 LIBBUILTIN(strlcat, "zc*cC*z",    "f",     "string.h", ALL_GNU_LANGUAGES)
diff --git a/clang/include/clang/Basic/Builtins.h b/clang/include/clang/Basic/Builtins.h
index e4ed482..15bfcf7 100644
--- a/clang/include/clang/Basic/Builtins.h
+++ b/clang/include/clang/Basic/Builtins.h
@@ -158,6 +158,13 @@ public:
     return strchr(getRecord(ID).Attributes, 't') != nullptr;
   }
 
+  /// Determines whether a declaration of this builtin should be recognized
+  /// even if the type doesn't match the specified signature.
+  bool allowTypeMismatch(unsigned ID) const {
+    return strchr(getRecord(ID).Attributes, 'T') != nullptr ||
+           hasCustomTypechecking(ID);
+  }
+
   /// Determines whether this builtin has a result or any arguments which
   /// are pointer types.
   bool hasPtrArgsOrResult(unsigned ID) const {
diff --git a/clang/lib/Sema/SemaDecl.cpp b/clang/lib/Sema/SemaDecl.cpp
index 82c78e3..5b0417f 100644
--- a/clang/lib/Sema/SemaDecl.cpp
+++ b/clang/lib/Sema/SemaDecl.cpp
@@ -2107,7 +2107,8 @@ NamedDecl *Sema::LazilyCreateBuiltin(IdentifierInfo *II, unsigned ID,
 
     // If we have a builtin without an associated type we should not emit a
     // warning when we were not able to find a type for it.
-    if (Error == ASTContext::GE_Missing_type)
+    if (Error == ASTContext::GE_Missing_type ||
+        Context.BuiltinInfo.allowTypeMismatch(ID))
       return nullptr;
 
     // If we could not find a type for setjmp it is because the jmp_buf type was
@@ -2131,11 +2132,9 @@ NamedDecl *Sema::LazilyCreateBuiltin(IdentifierInfo *II, unsigned ID,
        Context.BuiltinInfo.isHeaderDependentFunction(ID))) {
     Diag(Loc, diag::ext_implicit_lib_function_decl)
         << Context.BuiltinInfo.getName(ID) << R;
-    if (Context.BuiltinInfo.getHeaderName(ID) &&
-        !Diags.isIgnored(diag::ext_implicit_lib_function_decl, Loc))
+    if (const char *Header = Context.BuiltinInfo.getHeaderName(ID))
       Diag(Loc, diag::note_include_header_or_declare)
-          << Context.BuiltinInfo.getHeaderName(ID)
-          << Context.BuiltinInfo.getName(ID);
+          << Header << Context.BuiltinInfo.getName(ID);
   }
 
   if (R.isNull())
@@ -9630,16 +9629,16 @@ Sema::ActOnFunctionDeclarator(Scope *S, Declarator &D, DeclContext *DC,
     }
   }
 
-  // In C builtins get merged with implicitly lazily created declarations.
-  // In C++ we need to check if it's a builtin and add the BuiltinAttr here.
-  if (getLangOpts().CPlusPlus) {
+  // If this is the first declaration of a library builtin function, add
+  // attributes as appropriate.
+  if (!D.isRedeclaration() &&
+      NewFD->getDeclContext()->getRedeclContext()->isFileContext()) {
     if (IdentifierInfo *II = Previous.getLookupName().getAsIdentifierInfo()) {
       if (unsigned BuiltinID = II->getBuiltinID()) {
         if (NewFD->getLanguageLinkage() == CLanguageLinkage) {
-          // Declarations for builtins with custom typechecking by definition
-          // don't make sense. Don't attempt typechecking and simply add the
-          // attribute.
-          if (Context.BuiltinInfo.hasCustomTypechecking(BuiltinID)) {
+          // Validate the type matches unless this builtin is specified as
+          // matching regardless of its declared type.
+          if (Context.BuiltinInfo.allowTypeMismatch(BuiltinID)) {
             NewFD->addAttr(BuiltinAttr::CreateImplicit(Context, BuiltinID));
           } else {
             ASTContext::GetBuiltinTypeError Error;
diff --git a/clang/test/CodeGen/setjmp.c b/clang/test/CodeGen/setjmp.c
new file mode 100644
index 0000000..4ca360d
--- /dev/null
+++ b/clang/test/CodeGen/setjmp.c
@@ -0,0 +1,44 @@
+// RUN: %clang_cc1 -x c %s -triple x86_64-linux-gnu -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ %s -triple x86_64-linux-gnu -emit-llvm -o - | FileCheck %s
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+struct __jmp_buf_tag { int n; };
+int setjmp(struct __jmp_buf_tag*);
+int sigsetjmp(struct __jmp_buf_tag*, int);
+int _setjmp(struct __jmp_buf_tag*);
+int __sigsetjmp(struct __jmp_buf_tag*, int);
+
+typedef struct __jmp_buf_tag jmp_buf[1];
+typedef struct __jmp_buf_tag sigjmp_buf[1];
+
+#ifdef __cplusplus
+}
+#endif
+
+void f() {
+  jmp_buf jb;
+  // CHECK: call {{.*}}@setjmp(
+  setjmp(jb);
+  // CHECK: call {{.*}}@sigsetjmp(
+  sigsetjmp(jb, 0);
+  // CHECK: call {{.*}}@_setjmp(
+  _setjmp(jb);
+  // CHECK: call {{.*}}@__sigsetjmp(
+  __sigsetjmp(jb, 0);
+}
+
+// CHECK: ; Function Attrs: returns_twice
+// CHECK-NEXT: declare {{.*}} @setjmp(
+
+// CHECK: ; Function Attrs: returns_twice
+// CHECK-NEXT: declare {{.*}} @sigsetjmp(
+
+// CHECK: ; Function Attrs: returns_twice
+// CHECK-NEXT: declare {{.*}} @_setjmp(
+
+// CHECK: ; Function Attrs: returns_twice
+// CHECK-NEXT: declare {{.*}} @__sigsetjmp(
+
diff --git a/clang/test/Sema/builtin-setjmp.c b/clang/test/Sema/builtin-setjmp.c
index f8770d8..6a114fa 100644
--- a/clang/test/Sema/builtin-setjmp.c
+++ b/clang/test/Sema/builtin-setjmp.c
@@ -1,10 +1,42 @@
-// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fsyntax-only -verify -DNO_JMP_BUF %s
-// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fsyntax-only -verify %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fsyntax-only -verify -DNO_JMP_BUF %s -ast-dump | FileCheck %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fsyntax-only -verify -DWRONG_JMP_BUF %s -ast-dump | FileCheck %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fsyntax-only -verify -DRIGHT_JMP_BUF %s -ast-dump | FileCheck %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fsyntax-only -verify -DONLY_JMP_BUF %s -ast-dump | FileCheck %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fsyntax-only -verify -DNO_SETJMP %s -ast-dump 2>&1 | FileCheck %s
 
 #ifdef NO_JMP_BUF
-extern long setjmp(long *);   // expected-warning {{declaration of built-in function 'setjmp' requires the declaration of the 'jmp_buf' type, commonly provided in the header <setjmp.h>.}}
-#else
+// This happens in some versions of glibc: the declaration of __sigsetjmp
+// precedes the declaration of sigjmp_buf.
+extern long setjmp(long *); // Can't check, so we trust that this is the right type
+// FIXME: We could still diagnose the missing `jmp_buf` at the point of the call.
+// expected-no-diagnostics
+#elif WRONG_JMP_BUF
 typedef long jmp_buf;
-extern int setjmp(char);      // expected-warning@8 {{incompatible redeclaration of library function 'setjmp'}}
-                              // expected-note@8    {{'setjmp' is a builtin with type 'int (jmp_buf)' (aka 'int (long)')}}
+extern int setjmp(char); // expected-warning {{incompatible redeclaration of library function 'setjmp'}}
+                         // expected-note@-1 {{'setjmp' is a builtin with type 'int (jmp_buf)' (aka 'int (long)')}}
+#elif RIGHT_JMP_BUF
+typedef long jmp_buf;
+extern int setjmp(long); // OK, right type.
+// expected-no-diagnostics
+#elif ONLY_JMP_BUF
+typedef int *jmp_buf;
 #endif
+
+void use() {
+  setjmp(0);
+  #ifdef NO_SETJMP
+  // expected-warning@-2 {{implicit declaration of function 'setjmp' is invalid in C99}}
+  #elif ONLY_JMP_BUF
+  // expected-warning@-4 {{implicitly declaring library function 'setjmp' with type 'int (jmp_buf)' (aka 'int (int *)')}}
+  // expected-note@-5 {{include the header <setjmp.h> or explicitly provide a declaration for 'setjmp'}}
+  #endif
+
+  #ifdef NO_SETJMP
+  // In this case, the regular AST dump doesn't dump the implicit declaration of 'setjmp'.
+  #pragma clang __debug dump setjmp
+  #endif
+}
+
+// CHECK: FunctionDecl {{.*}} used setjmp
+// CHECK: BuiltinAttr {{.*}} Implicit
+// CHECK: ReturnsTwiceAttr {{.*}} Implicit
diff --git a/clang/test/Sema/implicit-builtin-decl.c b/clang/test/Sema/implicit-builtin-decl.c
index b25e86b..9434b50 100644
--- a/clang/test/Sema/implicit-builtin-decl.c
+++ b/clang/test/Sema/implicit-builtin-decl.c
@@ -54,13 +54,12 @@ main(int argc, char *argv[])
 
 void snprintf() { }
 
-// PR8316 & PR40692
-void longjmp(); // expected-warning{{declaration of built-in function 'longjmp' requires the declaration of the 'jmp_buf' type, commonly provided in the header <setjmp.h>.}}
+void longjmp();
 
 extern float fmaxf(float, float);
 
 struct __jmp_buf_tag {};
-void sigsetjmp(struct __jmp_buf_tag[1], int); // expected-warning{{declaration of built-in function 'sigsetjmp' requires the declaration of the 'jmp_buf' type, commonly provided in the header <setjmp.h>.}}
+void sigsetjmp(struct __jmp_buf_tag[1], int);
 
 // PR40692
 void pthread_create(); // no warning expected