[Clang] Always verify LLVM IR inputs

clang/include/clang/Basic/DiagnosticFrontendKinds.td

@@ -379,6 +379,8 @@ def err_ast_action_on_llvm_ir : Error<
   "cannot apply AST actions to LLVM IR file '%0'">,
   DefaultFatal;
 
+def err_invalid_llvm_ir : Error<"invalid LLVM IR input: %0">;
+
 def err_os_unsupport_riscv_fmv : Error<
   "function multiversioning is currently only supported on Linux">;
 

clang/lib/CodeGen/CodeGenAction.cpp

@@ -39,6 +39,7 @@
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/LLVMRemarkStreamer.h"
 #include "llvm/IR/Module.h"
+#include "llvm/IR/Verifier.h"
 #include "llvm/IRReader/IRReader.h"
 #include "llvm/LTO/LTOBackend.h"
 #include "llvm/Linker/Linker.h"
@@ -1048,8 +1049,17 @@ CodeGenAction::loadModule(MemoryBufferRef MBRef) {
 
   // Handle textual IR and bitcode file with one single module.
   llvm::SMDiagnostic Err;
-  if (std::unique_ptr<llvm::Module> M = parseIR(MBRef, Err, *VMContext))
+  if (std::unique_ptr<llvm::Module> M = parseIR(MBRef, Err, *VMContext)) {
+    // For LLVM IR files, always verify the input and report the error in a way
+    // that does not ask people to report an issue for it.
+    std::string VerifierErr;
+    raw_string_ostream VerifierErrStream(VerifierErr);
+    if (llvm::verifyModule(*M, &VerifierErrStream)) {
+      CI.getDiagnostics().Report(diag::err_invalid_llvm_ir) << VerifierErr;
+      return {};
+    }
     return M;
+  }
 
   // If MBRef is a bitcode with multiple modules (e.g., -fsplit-lto-unit
   // output), place the extra modules (actually only one, a regular LTO module)

clang/test/CodeGen/invalid_llvm_ir.ll

@@ -0,0 +1,12 @@
+; RUN: not %clang %s 2>&1 | FileCheck %s
+; RUN: llvm-as -disable-verify < %s > %t.bc
+; RUN: not %clang %t.bc 2>&1 | FileCheck %s
+
+; CHECK: error: invalid LLVM IR input: PHINode should have one entry for each predecessor of its parent basic block!
+; CHECK-NEXT: %phi = phi i32 [ 0, %entry ]
+
+define void @test() {
+entry:
+  %phi = phi i32 [ 0, %entry ]
+  ret void
+}