[CodeGen] Move fentry-insert, xray-instrumentation and patchable-function before addPreEmitPass()

This intention is to move patchable-function before aarch64-branch-targets
(configured in AArch64PassConfig::addPreEmitPass) so that we emit BTI before NOPs
(see https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92424).

This also allows addPreEmitPass() passes to know the precise instruction sizes if they want.

Tried x86-64 Debug/Release builds of ccls with -fxray-instrument -fxray-instruction-threshold=1.
No output difference with this commit and the previous commit.

(cherry picked from commit 9a24488cb67a90f889529987275c5e411ce01dda)

7 files changed, 45 insertions, 21 deletions

diff --git a/llvm/lib/CodeGen/TargetPassConfig.cpp b/llvm/lib/CodeGen/TargetPassConfig.cpp
index 41cb511ad9b..d08d05d4b2e 100644
--- a/llvm/lib/CodeGen/TargetPassConfig.cpp
+++ b/llvm/lib/CodeGen/TargetPassConfig.cpp
@@ -956,6 +956,12 @@ void TargetPassConfig::addMachinePasses() {
   if (getOptLevel() != CodeGenOpt::None)
     addBlockPlacement();
 
+  // Insert before XRay Instrumentation.
+  addPass(&FEntryInserterID, false);
+
+  addPass(&XRayInstrumentationID, false);
+  addPass(&PatchableFunctionID, false);
+
   addPreEmitPass();
 
   if (TM->Options.EnableIPRA)
@@ -968,12 +974,6 @@ void TargetPassConfig::addMachinePasses() {
   addPass(&StackMapLivenessID, false);
   addPass(&LiveDebugValuesID, false);
 
-  // Insert before XRay Instrumentation.
-  addPass(&FEntryInserterID, false);
-
-  addPass(&XRayInstrumentationID, false);
-  addPass(&PatchableFunctionID, false);
-
   if (TM->Options.EnableMachineOutliner && getOptLevel() != CodeGenOpt::None &&
       EnableMachineOutliner != NeverOutline) {
     bool RunOnAllFunctions = (EnableMachineOutliner == AlwaysOutline);
diff --git a/llvm/test/CodeGen/AArch64/O0-pipeline.ll b/llvm/test/CodeGen/AArch64/O0-pipeline.ll
index 07170fa6863..9b7e2f6dd28 100644
--- a/llvm/test/CodeGen/AArch64/O0-pipeline.ll
+++ b/llvm/test/CodeGen/AArch64/O0-pipeline.ll
@@ -63,14 +63,14 @@
 ; CHECK-NEXT:       AArch64 pseudo instruction expansion pass
 ; CHECK-NEXT:       AArch64 speculation hardening pass
 ; CHECK-NEXT:       Analyze Machine Code For Garbage Collection
+; CHECK-NEXT:       Insert fentry calls
+; CHECK-NEXT:       Insert XRay ops
+; CHECK-NEXT:       Implement the 'patchable-function' attribute
 ; CHECK-NEXT:       AArch64 Branch Targets
 ; CHECK-NEXT:       Branch relaxation pass
 ; CHECK-NEXT:       Contiguously Lay Out Funclets
 ; CHECK-NEXT:       StackMap Liveness Analysis
 ; CHECK-NEXT:       Live DEBUG_VALUE analysis
-; CHECK-NEXT:       Insert fentry calls
-; CHECK-NEXT:       Insert XRay ops
-; CHECK-NEXT:       Implement the 'patchable-function' attribute
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Optimization Remark Emitter
 ; CHECK-NEXT:       AArch64 Assembly Printer
diff --git a/llvm/test/CodeGen/AArch64/O3-pipeline.ll b/llvm/test/CodeGen/AArch64/O3-pipeline.ll
index 96f39f0d3d1..bf489cbbae6 100644
--- a/llvm/test/CodeGen/AArch64/O3-pipeline.ll
+++ b/llvm/test/CodeGen/AArch64/O3-pipeline.ll
@@ -171,6 +171,9 @@
 ; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       MachinePostDominator Tree Construction
 ; CHECK-NEXT:       Branch Probability Basic Block Placement
+; CHECK-NEXT:       Insert fentry calls
+; CHECK-NEXT:       Insert XRay ops
+; CHECK-NEXT:       Implement the 'patchable-function' attribute
 ; CHECK-NEXT:       AArch64 load / store optimization pass
 ; CHECK-NEXT:       AArch64 Branch Targets
 ; CHECK-NEXT:       Branch relaxation pass
@@ -178,9 +181,6 @@
 ; CHECK-NEXT:       Contiguously Lay Out Funclets
 ; CHECK-NEXT:       StackMap Liveness Analysis
 ; CHECK-NEXT:       Live DEBUG_VALUE analysis
-; CHECK-NEXT:       Insert fentry calls
-; CHECK-NEXT:       Insert XRay ops
-; CHECK-NEXT:       Implement the 'patchable-function' attribute
 ; CHECK-NEXT:     Machine Outliner
 ; CHECK-NEXT:     FunctionPass Manager
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
diff --git a/llvm/test/CodeGen/AArch64/patchable-function-entry-bti.ll b/llvm/test/CodeGen/AArch64/patchable-function-entry-bti.ll
new file mode 100644
index 00000000000..9b406d45da6
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/patchable-function-entry-bti.ll
@@ -0,0 +1,24 @@
+; RUN: llc -mtriple=aarch64 %s -o - | FileCheck --check-prefixes=CHECK %s
+
+define i32 @f0() "patchable-function-entry"="0" "branch-target-enforcement" {
+; CHECK-LABEL: f0:
+; CHECK-NEXT: .Lfunc_begin0:
+; CHECK:       hint #34
+; CHECK-NEXT:  mov w0, wzr
+; CHECK:       .section __patchable_function_entries,"awo",@progbits,f0,unique,0
+; CHECK-NEXT:  .p2align 3
+; CHECK-NEXT:  .xword .Lfunc_begin0
+  ret i32 0
+}
+
+define i32 @f1() "patchable-function-entry"="1" "branch-target-enforcement" {
+; CHECK-LABEL: f1:
+; CHECK-NEXT: .Lfunc_begin1:
+; CHECK:       hint #34
+; CHECK-NEXT:  nop
+; CHECK-NEXT:  mov w0, wzr
+; CHECK:       .section __patchable_function_entries,"awo",@progbits,f0,unique,0
+; CHECK-NEXT:  .p2align 3
+; CHECK-NEXT:  .xword .Lfunc_begin1
+  ret i32 0
+}
diff --git a/llvm/test/CodeGen/ARM/O3-pipeline.ll b/llvm/test/CodeGen/ARM/O3-pipeline.ll
index 42bad7c7487..8a9f84d3fd5 100644
--- a/llvm/test/CodeGen/ARM/O3-pipeline.ll
+++ b/llvm/test/CodeGen/ARM/O3-pipeline.ll
@@ -156,6 +156,9 @@
 ; CHECK-NEXT:      Machine Block Frequency Analysis
 ; CHECK-NEXT:      MachinePostDominator Tree Construction
 ; CHECK-NEXT:      Branch Probability Basic Block Placement
+; CHECK-NEXT:      Insert fentry calls
+; CHECK-NEXT:      Insert XRay ops
+; CHECK-NEXT:      Implement the 'patchable-function' attribute
 ; CHECK-NEXT:      Thumb2 instruction size reduce pass
 ; CHECK-NEXT:      Unpack machine instruction bundles
 ; CHECK-NEXT:      optimise barriers pass
@@ -168,9 +171,6 @@
 ; CHECK-NEXT:      Contiguously Lay Out Funclets
 ; CHECK-NEXT:      StackMap Liveness Analysis
 ; CHECK-NEXT:      Live DEBUG_VALUE analysis
-; CHECK-NEXT:      Insert fentry calls
-; CHECK-NEXT:      Insert XRay ops
-; CHECK-NEXT:      Implement the 'patchable-function' attribute
 ; CHECK-NEXT:      Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:      Machine Optimization Remark Emitter
 ; CHECK-NEXT:      ARM Assembly Printer
diff --git a/llvm/test/CodeGen/X86/O0-pipeline.ll b/llvm/test/CodeGen/X86/O0-pipeline.ll
index 33ecad677a6..d6f2fef13fe 100644
--- a/llvm/test/CodeGen/X86/O0-pipeline.ll
+++ b/llvm/test/CodeGen/X86/O0-pipeline.ll
@@ -61,6 +61,9 @@
 ; CHECK-NEXT:       Post-RA pseudo instruction expansion pass
 ; CHECK-NEXT:       X86 pseudo instruction expansion pass
 ; CHECK-NEXT:       Analyze Machine Code For Garbage Collection
+; CHECK-NEXT:       Insert fentry calls
+; CHECK-NEXT:       Insert XRay ops
+; CHECK-NEXT:       Implement the 'patchable-function' attribute
 ; CHECK-NEXT:       X86 Indirect Branch Tracking
 ; CHECK-NEXT:       X86 vzeroupper inserter
 ; CHECK-NEXT:       X86 Discriminate Memory Operands
@@ -68,9 +71,6 @@
 ; CHECK-NEXT:       Contiguously Lay Out Funclets
 ; CHECK-NEXT:       StackMap Liveness Analysis
 ; CHECK-NEXT:       Live DEBUG_VALUE analysis
-; CHECK-NEXT:       Insert fentry calls
-; CHECK-NEXT:       Insert XRay ops
-; CHECK-NEXT:       Implement the 'patchable-function' attribute
 ; CHECK-NEXT:       X86 Retpoline Thunks
 ; CHECK-NEXT:       Check CFA info and insert CFI instructions if needed
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
diff --git a/llvm/test/CodeGen/X86/O3-pipeline.ll b/llvm/test/CodeGen/X86/O3-pipeline.ll
index 575b704b8b4..c645bb63639 100644
--- a/llvm/test/CodeGen/X86/O3-pipeline.ll
+++ b/llvm/test/CodeGen/X86/O3-pipeline.ll
@@ -159,6 +159,9 @@
 ; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       MachinePostDominator Tree Construction
 ; CHECK-NEXT:       Branch Probability Basic Block Placement
+; CHECK-NEXT:       Insert fentry calls
+; CHECK-NEXT:       Insert XRay ops
+; CHECK-NEXT:       Implement the 'patchable-function' attribute
 ; CHECK-NEXT:       ReachingDefAnalysis
 ; CHECK-NEXT:       X86 Execution Dependency Fix
 ; CHECK-NEXT:       BreakFalseDeps
@@ -177,9 +180,6 @@
 ; CHECK-NEXT:       Contiguously Lay Out Funclets
 ; CHECK-NEXT:       StackMap Liveness Analysis
 ; CHECK-NEXT:       Live DEBUG_VALUE analysis
-; CHECK-NEXT:       Insert fentry calls
-; CHECK-NEXT:       Insert XRay ops
-; CHECK-NEXT:       Implement the 'patchable-function' attribute
 ; CHECK-NEXT:       X86 Retpoline Thunks
 ; CHECK-NEXT:       Check CFA info and insert CFI instructions if needed
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis