[CodeGen] Merge identical block descriptor global variables.

Currently, clang generates a new block descriptor global variable for
each new block literal. This commit merges block descriptors that are
identical inside and across translation units using the same approach
taken in r339438.

To enable merging identical block descriptors, the size and signature of
the block and information about the captures are encoded into the name
of the block descriptor variable. Also, the block descriptor variable is
marked as linkonce_odr and unnamed_addr.

rdar://problem/42640703

Differential Revision: https://reviews.llvm.org/D50783

llvm-svn: 340041

clang/lib/CodeGen/CGBlocks.h

@@ -132,6 +132,9 @@ class BlockFieldFlags {
   friend bool operator&(BlockFieldFlags l, BlockFieldFlags r) {
     return (l.flags & r.flags);
   }
+  bool operator==(BlockFieldFlags Other) const {
+    return flags == Other.flags;
+  }
 };
 inline BlockFieldFlags operator|(BlockFieldFlag_t l, BlockFieldFlag_t r) {
   return BlockFieldFlags(l) | BlockFieldFlags(r);

clang/lib/CodeGen/CGObjCMac.cpp

@@ -37,6 +37,7 @@
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
+#include "llvm/Support/ScopedPrinter.h"
 #include "llvm/Support/raw_ostream.h"
 #include <cstdio>
 
@@ -1085,9 +1086,14 @@ class CGObjCCommonMac : public CodeGen::CGObjCRuntime {
                                      const CGBlockInfo &blockInfo) override;
   llvm::Constant *BuildRCBlockLayout(CodeGen::CodeGenModule &CGM,
                                      const CGBlockInfo &blockInfo) override;
+  std::string getRCBlockLayoutStr(CodeGen::CodeGenModule &CGM,
+                                  const CGBlockInfo &blockInfo) override;
 
   llvm::Constant *BuildByrefLayout(CodeGen::CodeGenModule &CGM,
                                    QualType T) override;
+
+private:
+  void fillRunSkipBlockVars(CodeGenModule &CGM, const CGBlockInfo &blockInfo);
 };
 
 namespace {
@@ -2795,8 +2801,44 @@ llvm::Constant *CGObjCCommonMac::getBitmapBlockLayout(bool ComputeByrefLayout) {
   return getConstantGEP(VMContext, Entry, 0, 0);
 }
 
-llvm::Constant *CGObjCCommonMac::BuildRCBlockLayout(CodeGenModule &CGM,
-                                                    const CGBlockInfo &blockInfo) {
+static std::string getBlockLayoutInfoString(
+    const SmallVectorImpl<CGObjCCommonMac::RUN_SKIP> &RunSkipBlockVars,
+    bool HasCopyDisposeHelpers) {
+  std::string Str;
+  for (const CGObjCCommonMac::RUN_SKIP &R : RunSkipBlockVars) {
+    if (R.opcode == CGObjCCommonMac::BLOCK_LAYOUT_UNRETAINED) {
+      // Copy/dispose helpers don't have any information about
+      // __unsafe_unretained captures, so unconditionally concatenate a string.
+      Str += "u";
+    } else if (HasCopyDisposeHelpers) {
+      // Information about __strong, __weak, or byref captures has already been
+      // encoded into the names of the copy/dispose helpers. We have to add a
+      // string here only when the copy/dispose helpers aren't generated (which
+      // happens when the block is non-escaping).
+      continue;
+    } else {
+      switch (R.opcode) {
+      case CGObjCCommonMac::BLOCK_LAYOUT_STRONG:
+        Str += "s";
+        break;
+      case CGObjCCommonMac::BLOCK_LAYOUT_BYREF:
+        Str += "r";
+        break;
+      case CGObjCCommonMac::BLOCK_LAYOUT_WEAK:
+        Str += "w";
+        break;
+      default:
+        continue;
+      }
+    }
+    Str += llvm::to_string(R.block_var_bytepos.getQuantity());
+    Str += "l" + llvm::to_string(R.block_var_size.getQuantity());
+  }
+  return Str;
+}
+
+void CGObjCCommonMac::fillRunSkipBlockVars(CodeGenModule &CGM,
+                                           const CGBlockInfo &blockInfo) {
   assert(CGM.getLangOpts().getGC() == LangOptions::NonGC);
 
   RunSkipBlockVars.clear();
@@ -2845,9 +2887,22 @@ llvm::Constant *CGObjCCommonMac::BuildRCBlockLayout(CodeGenModule &CGM,
     UpdateRunSkipBlockVars(CI.isByRef(), getBlockCaptureLifetime(type, false),
                            fieldOffset, fieldSize);
   }
+}
+
+llvm::Constant *
+CGObjCCommonMac::BuildRCBlockLayout(CodeGenModule &CGM,
+                                    const CGBlockInfo &blockInfo) {
+  fillRunSkipBlockVars(CGM, blockInfo);
   return getBitmapBlockLayout(false);
 }
 
+std::string CGObjCCommonMac::getRCBlockLayoutStr(CodeGenModule &CGM,
+                                                 const CGBlockInfo &blockInfo) {
+  fillRunSkipBlockVars(CGM, blockInfo);
+  return getBlockLayoutInfoString(RunSkipBlockVars,
+                                  blockInfo.needsCopyDisposeHelpers());
+}
+
 llvm::Constant *CGObjCCommonMac::BuildByrefLayout(CodeGen::CodeGenModule &CGM,
                                                   QualType T) {
   assert(CGM.getLangOpts().getGC() == LangOptions::NonGC);

clang/lib/CodeGen/CGObjCRuntime.h

@@ -278,6 +278,10 @@ class CGObjCRuntime {
                                   const CodeGen::CGBlockInfo &blockInfo) = 0;
   virtual llvm::Constant *BuildRCBlockLayout(CodeGen::CodeGenModule &CGM,
                                   const CodeGen::CGBlockInfo &blockInfo) = 0;
+  virtual std::string getRCBlockLayoutStr(CodeGen::CodeGenModule &CGM,
+                                          const CGBlockInfo &blockInfo) {
+    return {};
+  }
 
   /// Returns an i8* which points to the byref layout information.
   virtual llvm::Constant *BuildByrefLayout(CodeGen::CodeGenModule &CGM,

clang/test/CodeGenCXX/blocks.cpp

@@ -1,5 +1,8 @@
 // RUN: %clang_cc1 %s -fblocks -triple x86_64-apple-darwin -emit-llvm -o - | FileCheck %s
 
+// CHECK: %[[STRUCT_BLOCK_DESCRIPTOR:.*]] = type { i64, i64 }
+// CHECK: @[[BLOCK_DESCRIPTOR22:.*]] = internal constant { i64, i64, i8*, i8*, i8*, i8* } { i64 0, i64 36, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32c22_ZTSN12_GLOBAL__N_11BE to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32c22_ZTSN12_GLOBAL__N_11BE to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i8* null }, align 8
+
 namespace test0 {
   // CHECK-LABEL: define void @_ZN5test04testEi(
   // CHECK: define internal void @___ZN5test04testEi_block_invoke{{.*}}(
@@ -122,7 +125,7 @@ namespace test4 {
   // CHECK-LABEL: define internal void @___ZN5test44testEv_block_invoke
   // CHECK: [[TMP:%.*]] = alloca [[A:%.*]], align 1
   // CHECK-NEXT: store i8* [[BLOCKDESC:%.*]], i8** {{.*}}, align 8
-  // CHECK-NEXT: bitcast i8* [[BLOCKDESC]] to <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>*
+  // CHECK-NEXT: bitcast i8* [[BLOCKDESC]] to <{ i8*, i32, i32, i8*, %[[STRUCT_BLOCK_DESCRIPTOR]]* }>*
   // CHECK:      call void @_ZN5test41AC1Ev([[A]]* [[TMP]])
   // CHECK-NEXT: call void @_ZN5test43fooENS_1AE([[A]]* [[TMP]])
   // CHECK-NEXT: call void @_ZN5test41AD1Ev([[A]]* [[TMP]])
@@ -277,8 +280,11 @@ namespace test10 {
   }
 }
 
-// Copy/dispose helper functions that capture objects of non-external types
-// should have internal linkage.
+// Copy/dispose helper functions and block descriptors of blocks that capture
+// objects that are non-external and non-trivial have internal linkage.
+
+// CHECK-LABEL: define internal void @_ZN12_GLOBAL__N_14testEv(
+// CHECK: store %[[STRUCT_BLOCK_DESCRIPTOR]]* bitcast ({ i64, i64, i8*, i8*, i8*, i8* }* @[[BLOCK_DESCRIPTOR22]] to %[[STRUCT_BLOCK_DESCRIPTOR]]*), %[[STRUCT_BLOCK_DESCRIPTOR]]** %{{.*}}, align 8
 
 // CHECK-LABEL: define internal void @__copy_helper_block_8_32c22_ZTSN12_GLOBAL__N_11BE(
 // CHECK-LABEL: define internal void @__destroy_helper_block_8_32c22_ZTSN12_GLOBAL__N_11BE(

clang/test/CodeGenObjC/arc-blocks.m

@@ -2,15 +2,10 @@
 // RUN: %clang_cc1 -triple x86_64-apple-darwin10 -emit-llvm -fblocks -fobjc-arc -fobjc-runtime-has-weak -o - %s | FileCheck -check-prefix=CHECK-UNOPT -check-prefix=CHECK-COMMON %s
 
 // CHECK-COMMON: %[[STRUCT_BLOCK_DESCRIPTOR:.*]] = type { i64, i64 }
-// CHECK-COMMON: @{{.*}} = internal constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32r to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32r to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 16 }, align 8
-// CHECK-COMMON: @[[BLOCK_DESCRIPTOR_TMP9:.*]] = internal constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32r to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32r to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 16 }, align 8
-// CHECK-COMMON: @{{.*}} = internal constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32s to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 256 }, align 8
-// CHECK-COMMON: @{{.*}} = internal constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32s to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 256 }, align 8
-// CHECK-COMMON: @{{.*}} = internal constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32s to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 256 }, align 8
-// CHECK-COMMON: @{{.*}} = internal constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32s to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 256 }, align 8
-// CHECK-COMMON: @[[BLOCK_DESCRIPTOR_TMP44:.*]] = internal constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32s to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 256 }, align 8
-// CHECK-COMMON: @[[BLOCK_DESCRIPTOR_TMP46:.*]] = internal constant { i64, i64, i8*, i8*, i8*, i8* } { i64 0, i64 48, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32s to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i8* getelementptr inbounds ([3 x i8], [3 x i8]* @{{.*}}, i32 0, i32 0) }, align 8
-// CHECK-COMMON: @[[BLOCK_DESCRIPTOR_TMP48:.*]] = internal constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32b to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.47, i32 0, i32 0), i64 256 }, align 8
+// CHECK-COMMON: @[[BLOCK_DESCRIPTOR_TMP44:.*]] = linkonce_odr hidden unnamed_addr constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32s to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 256 }, align 8
+// CHECK-COMMON: @[[BLOCK_DESCRIPTOR_TMP9:.*]] = linkonce_odr hidden unnamed_addr constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32r to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32r to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 16 }, align 8
+// CHECK-COMMON: @[[BLOCK_DESCRIPTOR_TMP46:.*]] = linkonce_odr hidden unnamed_addr constant { i64, i64, i8*, i8*, i8*, i8* } { i64 0, i64 48, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32s to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i8* getelementptr inbounds ([3 x i8], [3 x i8]* @{{.*}}, i32 0, i32 0) }, align 8
+// CHECK-COMMON: @[[BLOCK_DESCRIPTOR_TMP48:.*]] = linkonce_odr hidden unnamed_addr constant { i64, i64, i8*, i8*, i8*, i64 } { i64 0, i64 40, i8* bitcast (void (i8*, i8*)* @__copy_helper_block_8_32b to i8*), i8* bitcast (void (i8*)* @__destroy_helper_block_8_32s to i8*), i8* getelementptr inbounds ([9 x i8], [9 x i8]* @{{.*}}, i32 0, i32 0), i64 256 }, align 8
 
 // This shouldn't crash.
 void test0(id (^maker)(void)) {

clang/test/CodeGenObjC/arc-captured-32bit-block-var-layout-2.m

@@ -30,7 +30,8 @@ int main() {
   void (^block4)() = ^{ printf("%c %#lx", ch, fourByte); NSLog(@"%@", strong); };
 
   // Test5
-  // CHECK: Inline block variable layout: 0x0100, BL_STRONG:1, BL_OPERATOR:0
+  // Nothing gets printed here since the descriptor of this block is merged with
+  // the descriptor of Test3's block.
   void (^block5)() = ^{ NSLog(@"%@", strong); printf("%c %#llx", ch, eightByte); };
 
   // Test6

clang/test/CodeGenObjC/fragile-arc.m

@@ -126,13 +126,13 @@ @implementation C @end
 extern void useBlock(void (^block)(void));
 
 //  256 == 0x100 == starts with 1 strong
-// GLOBALS: @__block_descriptor_tmp{{.*}} = internal constant {{.*}}, i32 256 }
+// GLOBALS: @"__block_descriptor{{.*}} = linkonce_odr hidden {{.*}}, i32 256 }
 void testBlockLayoutStrong(id x) {
   useBlock(^{ (void) x; });
 }
 
 //  1   == 0x001 == starts with 1 weak
-// GLOBALS: @__block_descriptor_tmp{{.*}} = internal constant {{.*}}, i32 1 }
+// GLOBALS: @"__block_descriptor{{.*}} = linkonce_odr hidden {{.*}}, i32 1 }
 void testBlockLayoutWeak(__weak id x) {
   useBlock(^{ (void) x; });
 }

clang/test/CodeGenObjC/noescape.m

@@ -17,7 +17,11 @@
 // helper functions.
 
 // CHECK: %[[STRUCT_BLOCK_DESCRIPTOR:.*]] = type { i64, i64 }
-// CHECK: @[[BLOCK_DESCIPTOR_TMP_2:.*]] = internal constant { i64, i64, i8*, i64 } { i64 0, i64 40, i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 256 }, align 8
+
+// When the block is non-escaping, copy/dispose helpers aren't generated, so the
+// block layout string must include information about __strong captures.
+
+// CHECK: @[[BLOCK_DESCIPTOR_TMP_2:.*ls32l8"]] = linkonce_odr hidden unnamed_addr constant { i64, i64, i8*, i64 } { i64 0, i64 40, i8* getelementptr inbounds ([6 x i8], [6 x i8]* @{{.*}}, i32 0, i32 0), i64 256 }, align 8
 
 // CHECK-LABEL: define void @test0(
 // CHECK: call void @noescapeFunc0({{.*}}, {{.*}} nocapture {{.*}})