[Implicit Modules] Add -cc1 option -fmodules-strict-context-hash whic…

…h includes search paths and diagnostics.

Differential Revision: https://reviews.llvm.org/D68528

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@375322 91177308-0d34-0410-b5e6-96231b3b80d8

docs/Modules.rst

@@ -225,6 +225,16 @@ Command-line parameters
 ``-fprebuilt-module-path=<directory>``
   Specify the path to the prebuilt modules. If specified, we will look for modules in this directory for a given top-level module name. We don't need a module map for loading prebuilt modules in this directory and the compiler will not try to rebuild these modules. This can be specified multiple times.
 
+-cc1 Options
+^^^^^^^^^^^^
+
+``-fmodules-strict-context-hash``
+  Enables hashing of all compiler options that could impact the semantics of a
+  module in an implicit build. This includes things such as header search paths
+  and diagnostics. Using this option may lead to an excessive number of modules
+  being built if the command line arguments are not homogeneous across your
+  build.
+
 Module Semantics
 ================
 

include/clang/Driver/CC1Options.td

@@ -815,6 +815,9 @@ def fdisable_module_hash : Flag<["-"], "fdisable-module-hash">,
   HelpText<"Disable the module hash">;
 def fmodules_hash_content : Flag<["-"], "fmodules-hash-content">,
   HelpText<"Enable hashing the content of a module file">;
+def fmodules_strict_context_hash : Flag<["-"], "fmodules-strict-context-hash">,
+  HelpText<"Enable hashing of all compiler options that could impact the "
+           "semantics of a module in an implicit build">;
 def c_isystem : JoinedOrSeparate<["-"], "c-isystem">, MetaVarName<"<directory>">,
   HelpText<"Add directory to the C SYSTEM include search path">;
 def objc_isystem : JoinedOrSeparate<["-"], "objc-isystem">,

include/clang/Lex/HeaderSearchOptions.h

@@ -11,6 +11,7 @@
 
 #include "clang/Basic/LLVM.h"
 #include "llvm/ADT/CachedHashString.h"
+#include "llvm/ADT/Hashing.h"
 #include "llvm/ADT/SetVector.h"
 #include "llvm/ADT/StringRef.h"
 #include <cstdint>
@@ -206,6 +207,13 @@ class HeaderSearchOptions {
 
   unsigned ModulesHashContent : 1;
 
+  /// Whether we should include all things that could impact the module in the
+  /// hash.
+  ///
+  /// This includes things like the full header search path, and enabled
+  /// diagnostics.
+  unsigned ModulesStrictContextHash : 1;
+
   HeaderSearchOptions(StringRef _Sysroot = "/")
       : Sysroot(_Sysroot), ModuleFormat("raw"), DisableModuleHash(false),
         ImplicitModuleMaps(false), ModuleMapFileHomeIsCwd(false),
@@ -214,7 +222,8 @@ class HeaderSearchOptions {
         ModulesValidateOncePerBuildSession(false),
         ModulesValidateSystemHeaders(false),
         ValidateASTInputFilesContent(false), UseDebugInfo(false),
-        ModulesValidateDiagnosticOptions(true), ModulesHashContent(false) {}
+        ModulesValidateDiagnosticOptions(true), ModulesHashContent(false),
+        ModulesStrictContextHash(false) {}
 
   /// AddPath - Add the \p Path path to the specified \p Group list.
   void AddPath(StringRef Path, frontend::IncludeDirGroup Group,
@@ -238,6 +247,15 @@ class HeaderSearchOptions {
   }
 };
 
+inline llvm::hash_code hash_value(const HeaderSearchOptions::Entry &E) {
+  return llvm::hash_combine(E.Path, E.Group, E.IsFramework, E.IgnoreSysRoot);
+}
+
+inline llvm::hash_code
+hash_value(const HeaderSearchOptions::SystemHeaderPrefix &SHP) {
+  return llvm::hash_combine(SHP.Prefix, SHP.IsSystemHeader);
+}
+
 } // namespace clang
 
 #endif // LLVM_CLANG_LEX_HEADERSEARCHOPTIONS_H

lib/Frontend/CompilerInvocation.cpp

@@ -2067,6 +2067,7 @@ static void ParseHeaderSearchArgs(HeaderSearchOptions &Opts, ArgList &Args,
     Opts.AddPrebuiltModulePath(A->getValue());
   Opts.DisableModuleHash = Args.hasArg(OPT_fdisable_module_hash);
   Opts.ModulesHashContent = Args.hasArg(OPT_fmodules_hash_content);
+  Opts.ModulesStrictContextHash = Args.hasArg(OPT_fmodules_strict_context_hash);
   Opts.ModulesValidateDiagnosticOptions =
       !Args.hasArg(OPT_fmodules_disable_diagnostic_validation);
   Opts.ImplicitModuleMaps = Args.hasArg(OPT_fimplicit_module_maps);
@@ -3546,6 +3547,7 @@ std::string CompilerInvocation::getModuleHash() const {
   using llvm::hash_code;
   using llvm::hash_value;
   using llvm::hash_combine;
+  using llvm::hash_combine_range;
 
   // Start the signature with the compiler version.
   // FIXME: We'd rather use something more cryptographically sound than
@@ -3600,6 +3602,24 @@ std::string CompilerInvocation::getModuleHash() const {
                       hsOpts.ModulesValidateDiagnosticOptions);
   code = hash_combine(code, hsOpts.ResourceDir);
 
+  if (hsOpts.ModulesStrictContextHash) {
+    hash_code SHPC = hash_combine_range(hsOpts.SystemHeaderPrefixes.begin(),
+                                        hsOpts.SystemHeaderPrefixes.end());
+    hash_code UEC = hash_combine_range(hsOpts.UserEntries.begin(),
+                                       hsOpts.UserEntries.end());
+    code = hash_combine(code, hsOpts.SystemHeaderPrefixes.size(), SHPC,
+                        hsOpts.UserEntries.size(), UEC);
+
+    const DiagnosticOptions &diagOpts = getDiagnosticOpts();
+    #define DIAGOPT(Name, Bits, Default) \
+      code = hash_combine(code, diagOpts.Name);
+    #define ENUM_DIAGOPT(Name, Type, Bits, Default) \
+      code = hash_combine(code, diagOpts.get##Name());
+    #include "clang/Basic/DiagnosticOptions.def"
+    #undef DIAGOPT
+    #undef ENUM_DIAGOPT
+  }
+
   // Extend the signature with the user build path.
   code = hash_combine(code, hsOpts.ModuleUserBuildPath);
 

test/Modules/context-hash.c

@@ -0,0 +1,33 @@
+// RUN: rm -rf %t
+// RUN: %clang_cc1 -fsyntax-only -internal-isystem \
+// RUN:   %S/Inputs/System/usr/include -fmodules -fimplicit-module-maps \
+// RUN:   -fmodules-cache-path=%t %s -Rmodule-build 2> %t1
+// RUN: rm -rf %t
+// RUN: %clang_cc1 -fsyntax-only -internal-isystem \
+// RUN:   %S/Inputs/System/usr/include -internal-isystem %S -fmodules \
+// RUN:   -fimplicit-module-maps -fmodules-cache-path=%t %s -Rmodule-build 2> \
+// RUN:   %t2
+// RUN: rm -rf %t
+// RUN: %clang_cc1 -fsyntax-only -internal-isystem \
+// RUN:   %S/Inputs/System/usr/include -internal-isystem %S -fmodules \
+// RUN:   -fimplicit-module-maps -fmodules-cache-path=%t %s \
+// RUN:   -fmodules-strict-context-hash -Rmodule-build 2> %t3
+// RUN: rm -rf %t
+// RUN: %clang_cc1 -fsyntax-only -Weverything -internal-isystem \
+// RUN:   %S/Inputs/System/usr/include -fmodules -fmodules-strict-context-hash \
+// RUN:   -fimplicit-module-maps -fmodules-cache-path=%t %s -Rmodule-build 2> \
+// RUN:   %t4
+// RUN: echo %t | cat - %t1 %t2 %t3 %t4 | FileCheck %s
+
+// This test verifies that only strict hashing includes search paths and
+// diagnostics in the module context hash.
+
+#include <stdio.h>
+
+// CHECK: [[PREFIX:(.*[/\\])+[a-zA-Z0-9.-]+]]
+// CHECK: building module 'cstd' as '[[PREFIX]]{{[/\\]}}[[CONTEXT_HASH:[A-Z0-9]+]]{{[/\\]}}cstd-[[AST_HASH:[A-Z0-9]+]].pcm'
+// CHECK: building module 'cstd' as '{{.*[/\\]}}[[CONTEXT_HASH]]{{[/\\]}}cstd-[[AST_HASH]].pcm'
+// CHECK-NOT: building module 'cstd' as '{{.*[/\\]}}[[CONTEXT_HASH]]{{[/\\]}}
+// CHECK: cstd-[[AST_HASH]].pcm'
+// CHECK-NOT: building module 'cstd' as '{{.*[/\\]}}[[CONTEXT_HASH]]{{[/\\]}}
+// CHECK: cstd-[[AST_HASH]].pcm'