[clang] [clang] Catch missing format attributes (PR #70024)

[Budimir Aranđelović via cfe-commits]

https://github.com/budimirarandjelovicsyrmia updated https://github.com/llvm/llvm-project/pull/70024

>From 36477198e67e225e6fc686cf08c194438e65d39c Mon Sep 17 00:00:00 2001
From: budimirarandjelovicsyrmia <budimir.arandjelovic at syrmia.com>
Date: Fri, 13 Oct 2023 14:45:15 +0200
Subject: [PATCH] [clang] Catch missing format attributes

---
 clang/include/clang/Basic/DiagnosticGroups.td |  2 +-
 .../clang/Basic/DiagnosticSemaKinds.td        |  3 +
 clang/include/clang/Sema/Sema.h               |  3 +
 clang/lib/Sema/SemaAttr.cpp                   | 58 +++++++++++++++++++
 clang/lib/Sema/SemaChecking.cpp               |  4 +-
 clang/test/Sema/attr-format-missing.c         | 13 +++++
 6 files changed, 81 insertions(+), 2 deletions(-)
 create mode 100644 clang/test/Sema/attr-format-missing.c

diff --git a/clang/include/clang/Basic/DiagnosticGroups.td b/clang/include/clang/Basic/DiagnosticGroups.td
index 17fdcffa2d42740..b8b77df84beb2be 100644
--- a/clang/include/clang/Basic/DiagnosticGroups.td
+++ b/clang/include/clang/Basic/DiagnosticGroups.td
@@ -482,7 +482,7 @@ def MainReturnType : DiagGroup<"main-return-type">;
 def MaxUnsignedZero : DiagGroup<"max-unsigned-zero">;
 def MissingBraces : DiagGroup<"missing-braces">;
 def MissingDeclarations: DiagGroup<"missing-declarations">;
-def : DiagGroup<"missing-format-attribute">;
+def MissingFormatAttribute: DiagGroup<"missing-format-attribute">;
 def : DiagGroup<"missing-include-dirs">;
 def MissingNoreturn : DiagGroup<"missing-noreturn">;
 def MultiChar : DiagGroup<"multichar">;
diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td
index 6d6f474f6dcdab9..7125de143c1710e 100644
--- a/clang/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -936,6 +936,9 @@ def err_opencl_invalid_param : Error<
 def err_opencl_invalid_return : Error<
   "declaring function return value of type %0 is not allowed %select{; did you forget * ?|}1">;
 def warn_enum_value_overflow : Warning<"overflow in enumeration value">;
+def warn_missing_format_attribute : Warning<
+  "Function %0 might be candidate for %1 format attribute.">,
+  InGroup<MissingFormatAttribute>, DefaultIgnore;
 def warn_pragma_options_align_reset_failed : Warning<
   "#pragma options align=reset failed: %0">,
   InGroup<IgnoredPragmas>;
diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h
index 741c2503127af7a..ee5ccfab7b82feb 100644
--- a/clang/include/clang/Sema/Sema.h
+++ b/clang/include/clang/Sema/Sema.h
@@ -10615,6 +10615,9 @@ class Sema final {
     ChangedStateAtExit
   };
 
+  void DiagnoseMissingFormatAttributes(const FunctionDecl *FDecl,
+                                       SourceLocation Loc);
+
   void DiagnoseNonDefaultPragmaAlignPack(PragmaAlignPackDiagnoseKind Kind,
                                          SourceLocation IncludeLoc);
   void DiagnoseUnterminatedPragmaAlignPack();
diff --git a/clang/lib/Sema/SemaAttr.cpp b/clang/lib/Sema/SemaAttr.cpp
index 42f582724564d06..ebd3e29a9efd507 100644
--- a/clang/lib/Sema/SemaAttr.cpp
+++ b/clang/lib/Sema/SemaAttr.cpp
@@ -435,6 +435,64 @@ bool Sema::ConstantFoldAttrArgs(const AttributeCommonInfo &CI,
   return true;
 }
 
+// Warn if parent function does not have builtin function format attribute.
+void Sema::DiagnoseMissingFormatAttributes(const FunctionDecl *FDecl,
+                                           SourceLocation Loc) {
+  assert(FDecl);
+
+  unsigned BuiltinID = FDecl->getBuiltinID(/*ConsiderWrappers=*/true);
+
+  // Function is not builtin if it's builtin ID is 0.
+  if (!BuiltinID)
+    return;
+
+  // Check if function is one with format attribute.
+  switch (BuiltinID) {
+  case Builtin::BIprintf:
+  case Builtin::BIfprintf:
+  case Builtin::BIsprintf:
+  case Builtin::BIscanf:
+  case Builtin::BIfscanf:
+  case Builtin::BIsscanf:
+  case Builtin::BIvprintf:
+  case Builtin::BIvfprintf:
+  case Builtin::BIvsprintf:
+    break;
+  // C99 mode
+  case Builtin::BIsnprintf:
+  case Builtin::BIvsnprintf:
+  case Builtin::BIvscanf:
+  case Builtin::BIvfscanf:
+  case Builtin::BIvsscanf:
+    if (!getLangOpts().C99)
+      return;
+    break;
+  default:
+    return;
+  }
+
+  const FunctionDecl *ParentFuncDecl = getCurFunctionDecl();
+  if (!ParentFuncDecl)
+    return;
+
+  // Iterate through builtin function format attributes. Then check
+  // if parent function has these attributes. If parent function does
+  // not have builtin function format attribut, emit warning.
+  for (const FormatAttr *Attr : FDecl->specific_attrs<FormatAttr>()) {
+    bool hasFormatAttr =
+        llvm::any_of(ParentFuncDecl->specific_attrs<FormatAttr>(),
+                     [&](const FormatAttr *ParentAttr) {
+                       // What about checking other arguments?
+                       return ParentAttr->getType() == Attr->getType();
+                     });
+    if (!hasFormatAttr) {
+      Diag(Loc, diag::warn_missing_format_attribute)
+          << ParentFuncDecl << Attr->getType();
+      // Diag(Loc, diag::warn_unannotated_fallthrough);
+    }
+  }
+}
+
 void Sema::DiagnoseNonDefaultPragmaAlignPack(PragmaAlignPackDiagnoseKind Kind,
                                              SourceLocation IncludeLoc) {
   if (Kind == PragmaAlignPackDiagnoseKind::NonDefaultStateAtInclude) {
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
index 4602284309491c1..629354302dfd3a7 100644
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -6014,8 +6014,10 @@ void Sema::checkCall(NamedDecl *FDecl, const FunctionProtoType *Proto,
     }
   }
 
-  if (FD)
+  if (FD) {
     diagnoseArgDependentDiagnoseIfAttrs(FD, ThisArg, Args, Loc);
+    DiagnoseMissingFormatAttributes(FD, Range.getBegin());
+  }
 }
 
 /// CheckConstructorCall - Check a constructor call for correctness and safety
diff --git a/clang/test/Sema/attr-format-missing.c b/clang/test/Sema/attr-format-missing.c
new file mode 100644
index 000000000000000..1926d3d3163124b
--- /dev/null
+++ b/clang/test/Sema/attr-format-missing.c
@@ -0,0 +1,13 @@
+// RUN: %clang_cc1 -fsyntax-only -verify -Wmissing-format-attribute %s
+// RUN: %clang_cc1 -fsyntax-only -verify -std=c99 -Wmissing-format-attribute %s
+
+#include <stdarg.h>
+#include <stdio.h>
+
+__attribute__((__format__ (__scanf__, 1, 4)))
+void foo(char *out, const size_t len, const char *format, ... /* args */)
+{
+    va_list args;
+
+    vsnprintf(out, len, format, args); // expected-warning {{Function 'foo' might be candidate for 'printf' format attribute}}
+}