merge main into amd-stg-open

reverts: [X86][AVX10] Permit AVX512 options/features used together with AVX10 (llvm#71318)
 breaks pgmath build

Change-Id: I14334b22129122d0aa04076dc992d45cf344f6c7

Author: ronlieb

bolt/include/bolt/Rewrite/RewriteInstance.h

@@ -430,6 +430,7 @@ class RewriteInstance {
 
   /// Common section names.
   static StringRef getEHFrameSectionName() { return ".eh_frame"; }
+  static StringRef getRelaDynSectionName() { return ".rela.dyn"; }
 
   /// An instance of the input binary we are processing, externally owned.
   llvm::object::ELFObjectFileBase *InputFile;

bolt/lib/Passes/ADRRelaxationPass.cpp

@@ -56,9 +56,14 @@ void ADRRelaxationPass::runOnFunction(BinaryFunction &BF) {
           continue;
       }
 
-      BinaryFunction *TargetBF = BC.getFunctionForSymbol(Symbol);
-      if (TargetBF && TargetBF == &BF)
-        continue;
+      // Don't relax adr if it points to the same function and it is not split
+      // and BF initial size is < 1MB.
+      const unsigned OneMB = 0x100000;
+      if (!BF.isSplit() && BF.getSize() < OneMB) {
+        BinaryFunction *TargetBF = BC.getFunctionForSymbol(Symbol);
+        if (TargetBF && TargetBF == &BF)
+          continue;
+      }
 
       MCPhysReg Reg;
       BC.MIB->getADRReg(Inst, Reg);
@@ -72,14 +77,17 @@ void ADRRelaxationPass::runOnFunction(BinaryFunction &BF) {
 
       if (It != BB.begin() && BC.MIB->isNoop(*std::prev(It))) {
         It = BB.eraseInstruction(std::prev(It));
-      } else if (opts::StrictMode && !BF.isSimple()) {
+      } else if (std::next(It) != BB.end() && BC.MIB->isNoop(*std::next(It))) {
+        BB.eraseInstruction(std::next(It));
+      } else if (!opts::StrictMode && !BF.isSimple()) {
         // If the function is not simple, it may contain a jump table undetected
         // by us. This jump table may use an offset from the branch instruction
         // to land in the desired place. If we add new instructions, we
         // invalidate this offset, so we have to rely on linker-inserted NOP to
         // replace it with ADRP, and abort if it is not present.
+        auto L = BC.scopeLock();
         errs() << formatv("BOLT-ERROR: Cannot relax adr in non-simple function "
-                          "{0}. Can't proceed in current mode.\n",
+                          "{0}. Use --strict option to override\n",
                           BF.getOneName());
         PassFailed = true;
         return;

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -2217,6 +2217,19 @@ void RewriteInstance::processDynamicRelocations() {
   }
 
   // The rest of dynamic relocations - DT_RELA.
+  // The static executable might have .rela.dyn secion and not have PT_DYNAMIC
+  if (!DynamicRelocationsSize && BC->IsStaticExecutable) {
+    ErrorOr<BinarySection &> DynamicRelSectionOrErr =
+        BC->getUniqueSectionByName(getRelaDynSectionName());
+    if (DynamicRelSectionOrErr) {
+      DynamicRelocationsAddress = DynamicRelSectionOrErr->getAddress();
+      DynamicRelocationsSize = DynamicRelSectionOrErr->getSize();
+      const SectionRef &SectionRef = DynamicRelSectionOrErr->getSectionRef();
+      DynamicRelativeRelocationsCount = std::distance(
+          SectionRef.relocation_begin(), SectionRef.relocation_end());
+    }
+  }
+
   if (DynamicRelocationsSize > 0) {
     ErrorOr<BinarySection &> DynamicRelSectionOrErr =
         BC->getSectionForAddress(*DynamicRelocationsAddress);

bolt/test/AArch64/ifunc.c

@@ -7,6 +7,20 @@
 // RUN: llvm-bolt %t.O0.exe -o %t.O0.bolt.exe \
 // RUN:   --print-disasm --print-only=_start | \
 // RUN:   FileCheck --check-prefix=O0_CHECK %s
+// RUN: llvm-readelf -aW %t.O0.bolt.exe | \
+// RUN:   FileCheck --check-prefix=REL_CHECK %s
+
+// Non-pie static executable doesn't generate PT_DYNAMIC, check relocation
+// is readed successfully and IPLT trampoline has been identified by bolt.
+// RUN: %clang %cflags -nostdlib -O3 %s -fuse-ld=lld -no-pie \
+// RUN:   -o %t.O3_nopie.exe -Wl,-q
+// RUN: llvm-readelf -l %t.O3_nopie.exe | \
+// RUN:   FileCheck --check-prefix=NON_DYN_CHECK %s
+// RUN: llvm-bolt %t.O3_nopie.exe -o %t.O3_nopie.bolt.exe  \
+// RUN:   --print-disasm --print-only=_start | \
+// RUN:   FileCheck --check-prefix=O3_CHECK %s
+// RUN: llvm-readelf -aW %t.O3_nopie.bolt.exe | \
+// RUN:   FileCheck --check-prefix=REL_CHECK %s
 
 // With -O3 direct call is performed on IPLT trampoline. IPLT trampoline
 // doesn't have associated symbol. The ifunc symbol has the same address as
@@ -16,6 +30,8 @@
 // RUN: llvm-bolt %t.O3_pie.exe -o %t.O3_pie.bolt.exe  \
 // RUN:   --print-disasm --print-only=_start | \
 // RUN:   FileCheck --check-prefix=O3_CHECK %s
+// RUN: llvm-readelf -aW %t.O3_pie.bolt.exe | \
+// RUN:   FileCheck --check-prefix=REL_CHECK %s
 
 // Check that IPLT trampoline located in .plt section are normally handled by
 // BOLT. The gnu-ld linker doesn't use separate .iplt section.
@@ -24,10 +40,17 @@
 // RUN: llvm-bolt %t.iplt_O3_pie.exe -o %t.iplt_O3_pie.bolt.exe  \
 // RUN:   --print-disasm --print-only=_start  | \
 // RUN:   FileCheck --check-prefix=O3_CHECK %s
+// RUN: llvm-readelf -aW %t.iplt_O3_pie.bolt.exe | \
+// RUN:   FileCheck --check-prefix=REL_CHECK %s
+
+// NON_DYN_CHECK-NOT: DYNAMIC
 
 // O0_CHECK: adr x{{[0-9]+}}, ifoo
 // O3_CHECK: b "{{resolver_foo|ifoo}}{{.*}}@PLT"
 
+// REL_CHECK: R_AARCH64_IRELATIVE [[#%x,REL_SYMB_ADDR:]]
+// REL_CHECK: [[#REL_SYMB_ADDR]] {{.*}} FUNC {{.*}} resolver_foo
+
 static void foo() {}
 
 static void *resolver_foo(void) { return foo; }

bolt/test/AArch64/r_aarch64_prelxx.s

@@ -12,7 +12,7 @@
 // CHECKPREL-NEXT:  R_AARCH64_PREL32      {{.*}} _start + 4
 // CHECKPREL-NEXT:  R_AARCH64_PREL64      {{.*}} _start + 8
 
-// RUN: llvm-bolt %t.exe -o %t.bolt
+// RUN: llvm-bolt %t.exe -o %t.bolt --strict
 // RUN: llvm-objdump -D %t.bolt | FileCheck %s --check-prefix=CHECKPREL32
 
 // CHECKPREL32: [[#%x,DATATABLEADDR:]] <datatable>:

bolt/test/runtime/AArch64/adrrelaxationpass.s

@@ -1,33 +1,27 @@
 # The second and third ADR instructions are non-local to functions
 # and must be replaced with ADRP + ADD by BOLT
-# Also since main is non-simple, we can't change it's length so we have to
-# replace NOP with adrp, and if there is no nop before adr in non-simple
+# Also since main and test are non-simple, we can't change it's length so we
+# have to replace NOP with adrp, and if there is no nop before adr in non-simple
 # function, we can't guarantee we didn't break possible jump tables, so we
-# fail in strict mode
+# fail in non-strict mode
 
 # REQUIRES: system-linux
 
 # RUN: llvm-mc -filetype=obj -triple aarch64-unknown-unknown \
 # RUN:   %s -o %t.o
 # RUN: %clang %cflags %t.o -o %t.exe -Wl,-q
-# RUN: llvm-bolt %t.exe -o %t.bolt --adr-relaxation=true
+# RUN: llvm-bolt %t.exe -o %t.bolt --adr-relaxation=true --strict
 # RUN: llvm-objdump --no-print-imm-hex -d --disassemble-symbols=main %t.bolt | FileCheck %s
 # RUN: %t.bolt
-# RUN: not llvm-bolt %t.exe -o %t.bolt --adr-relaxation=true --strict \
+# RUN: not llvm-bolt %t.exe -o %t.bolt --adr-relaxation=true \
 # RUN: 2>&1 | FileCheck %s --check-prefix CHECK-ERROR
 
-  .data
-  .align 8
-  .global Gvar
-Gvar: .xword 0x0
-  .global Gvar2
-Gvar2: .xword 0x42
-
   .text
   .align 4
   .global test
   .type test, %function
 test:
+  adr x2, Gvar
   mov x0, xzr
   ret
   .size test, .-test
@@ -47,11 +41,22 @@ br:
 .CI:
   .word 0xff
 
+  .data
+  .align 8
+  .global Gvar
+Gvar: .xword 0x0
+  .global Gvar2
+Gvar2: .xword 0x42
+  .balign 4
+jmptable:
+  .word 0
+  .word test - jmptable
+
 # CHECK: <main>:
 # CHECK-NEXT: adr x0, 0x{{[1-8a-f][0-9a-f]*}}
 # CHECK-NEXT: adrp x1, 0x{{[1-8a-f][0-9a-f]*}}
 # CHECK-NEXT: add x1, x1, #{{[1-8a-f][0-9a-f]*}}
 # CHECK-NEXT: adrp x2, 0x{{[1-8a-f][0-9a-f]*}}
 # CHECK-NEXT: add x2, x2, #{{[1-8a-f][0-9a-f]*}}
 # CHECK-NEXT: adr x3, 0x{{[1-8a-f][0-9a-f]*}}
-# CHECK-ERROR: BOLT-ERROR: Cannot relax adr in non-simple function main
+# CHECK-ERROR: BOLT-ERROR: Cannot relax adr in non-simple function

bolt/test/runtime/AArch64/controlflow.s

@@ -48,6 +48,7 @@ test_cond_branch:
   .global test_branch_reg
   .type test_branch_reg, %function
 test_branch_reg:
+  nop
   adr x0, test_branch_zero
   br x0
   panic
@@ -97,6 +98,7 @@ test_call:
   .global test_call_reg
   .type test_call_reg, %function
 test_call_reg:
+  nop
   adr x0, test_call_foo
   blr x0
   panic

clang-tools-extra/clang-tidy/utils/IncludeSorter.cpp

@@ -134,12 +134,13 @@ void IncludeSorter::addInclude(StringRef FileName, bool IsAngled,
   int Offset = findNextLine(SourceMgr->getCharacterData(EndLocation));
 
   // Record the relevant location information for this inclusion directive.
-  IncludeLocations[FileName].push_back(
+  auto &IncludeLocation = IncludeLocations[FileName];
+  IncludeLocation.push_back(
       SourceRange(HashLocation, EndLocation.getLocWithOffset(Offset)));
-  SourceLocations.push_back(IncludeLocations[FileName].back());
+  SourceLocations.push_back(IncludeLocation.back());
 
   // Stop if this inclusion is a duplicate.
-  if (IncludeLocations[FileName].size() > 1)
+  if (IncludeLocation.size() > 1)
     return;
 
   // Add the included file's name to the appropriate bucket.

clang-tools-extra/clangd/refactor/tweaks/CMakeLists.txt

@@ -27,6 +27,7 @@ add_clang_library(clangDaemonTweaks OBJECT
   PopulateSwitch.cpp
   RawStringLiteral.cpp
   RemoveUsingNamespace.cpp
+  ScopifyEnum.cpp
   SpecialMembers.cpp
   SwapIfBranches.cpp