[llvm] 6145b9d - [RISCV] Support outlining of CFI instructions in the machine outliner (#166149)

via llvm-commits llvm-commits at lists.llvm.org
Thu Nov 6 23:05:43 PST 2025


Author: Sudharsan Veeravalli
Date: 2025-11-07T12:35:39+05:30
New Revision: 6145b9d1925ada30b49ddf0a190d01407edc4e10

URL: https://github.com/llvm/llvm-project/commit/6145b9d1925ada30b49ddf0a190d01407edc4e10
DIFF: https://github.com/llvm/llvm-project/commit/6145b9d1925ada30b49ddf0a190d01407edc4e10.diff

LOG: [RISCV] Support outlining of CFI instructions in the machine outliner (#166149)

Add support for outlining CFI instructions if

  a) the outlined function is being tail called
  b) all of the CFI instructions in the function are being outlined

This is similar to what is being done on AArch64 and X86.

---------

Co-authored-by: Craig Topper <craig.topper at sifive.com>

Added: 
    

Modified: 
    llvm/lib/Target/RISCV/RISCVInstrInfo.cpp
    llvm/test/CodeGen/RISCV/machine-outliner-cfi.mir

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp b/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp
index b8ab70bd9e386..b05956b674d18 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfo.cpp
@@ -31,6 +31,7 @@
 #include "llvm/CodeGen/StackMaps.h"
 #include "llvm/IR/DebugInfoMetadata.h"
 #include "llvm/IR/Module.h"
+#include "llvm/MC/MCDwarf.h"
 #include "llvm/MC/MCInstBuilder.h"
 #include "llvm/MC/TargetRegistry.h"
 #include "llvm/Support/ErrorHandling.h"
@@ -3526,6 +3527,27 @@ RISCVInstrInfo::getOutliningCandidateInfo(
       Candidate.getMF()->getSubtarget<RISCVSubtarget>().hasStdExtZca() ? 2 : 4;
   unsigned CallOverhead = 0, FrameOverhead = 0;
 
+  // Count the number of CFI instructions in the candidate, if present.
+  unsigned CFICount = 0;
+  for (auto &I : Candidate) {
+    if (I.isCFIInstruction())
+      CFICount++;
+  }
+
+  // Ensure CFI coverage matches: comparing the number of CFIs in the candidate
+  // with the total number of CFIs in the parent function for each candidate.
+  // Outlining only a subset of a function’s CFIs would split the unwind state
+  // across two code regions and lead to incorrect address offsets between the
+  // outlined body and the remaining code. To preserve correct unwind info, we
+  // only outline when all CFIs in the function can be outlined together.
+  for (outliner::Candidate &C : RepeatedSequenceLocs) {
+    std::vector<MCCFIInstruction> CFIInstructions =
+        C.getMF()->getFrameInstructions();
+
+    if (CFICount > 0 && CFICount != CFIInstructions.size())
+      return std::nullopt;
+  }
+
   MachineOutlinerConstructionID MOCI = MachineOutlinerDefault;
   if (Candidate.back().isReturn()) {
     MOCI = MachineOutlinerTailCall;
@@ -3541,6 +3563,11 @@ RISCVInstrInfo::getOutliningCandidateInfo(
     FrameOverhead = InstrSizeCExt;
   }
 
+  // If we have CFI instructions, we can only outline if the outlined section
+  // can be a tail call.
+  if (MOCI != MachineOutlinerTailCall && CFICount > 0)
+    return std::nullopt;
+
   for (auto &C : RepeatedSequenceLocs)
     C.setCallInfo(MOCI, CallOverhead);
 
@@ -3562,13 +3589,11 @@ RISCVInstrInfo::getOutliningTypeImpl(const MachineModuleInfo &MMI,
       MBB->getParent()->getSubtarget().getRegisterInfo();
   const auto &F = MI.getMF()->getFunction();
 
-  // We can manually strip out CFI instructions later.
+  // We can only outline CFI instructions if we will tail call the outlined
+  // function, or fix up the CFI offsets. Currently, CFI instructions are
+  // outlined only if in a tail call.
   if (MI.isCFIInstruction())
-    // If current function has exception handling code, we can't outline &
-    // strip these CFI instructions since it may break .eh_frame section
-    // needed in unwinding.
-    return F.needsUnwindTableEntry() ? outliner::InstrType::Illegal
-                                     : outliner::InstrType::Invisible;
+    return outliner::InstrType::Legal;
 
   if (cannotInsertTailCall(*MBB) &&
       (MI.isReturn() || isMIModifiesReg(MI, TRI, RISCV::X5)))
@@ -3595,21 +3620,6 @@ void RISCVInstrInfo::buildOutlinedFrame(
     MachineBasicBlock &MBB, MachineFunction &MF,
     const outliner::OutlinedFunction &OF) const {
 
-  // Strip out any CFI instructions
-  bool Changed = true;
-  while (Changed) {
-    Changed = false;
-    auto I = MBB.begin();
-    auto E = MBB.end();
-    for (; I != E; ++I) {
-      if (I->isCFIInstruction()) {
-        I->removeFromParent();
-        Changed = true;
-        break;
-      }
-    }
-  }
-
   if (OF.FrameConstructionID == MachineOutlinerTailCall)
     return;
 

diff  --git a/llvm/test/CodeGen/RISCV/machine-outliner-cfi.mir b/llvm/test/CodeGen/RISCV/machine-outliner-cfi.mir
index 2acb1d43e01ea..78d242b5a28b9 100644
--- a/llvm/test/CodeGen/RISCV/machine-outliner-cfi.mir
+++ b/llvm/test/CodeGen/RISCV/machine-outliner-cfi.mir
@@ -3,27 +3,33 @@
 # RUN: llc -mtriple=riscv64 -x mir -run-pass=machine-outliner -simplify-mir -verify-machineinstrs < %s \
 # RUN: | FileCheck -check-prefixes=OUTLINED,RV64I-MO %s
 
-# CFIs are invisible (they can be outlined, but won't actually impact the outlining result) if there
-# is no need to unwind. CFIs will be stripped when we build outlined functions.
+# Combined tests for outlining with CFI instructions on RISC-V:
+# 1) All CFIs present in candidate: outline as tail-call and keep CFIs.
+# 2) Partial CFIs in function (extra outside candidate): do not outline.
+# 3) CFIs present but candidate is not a tail-call: do not outline.
 
 --- |
-  define void @func1(i32 %a, i32 %b) nounwind { ret void }
-
-  define void @func2(i32 %a, i32 %b) nounwind { ret void }
-
-  define void @func3(i32 %a, i32 %b) nounwind { ret void }
+  define void @funcA(i32 %a, i32 %b) nounwind { ret void }
+  define void @funcB(i32 %a, i32 %b) nounwind { ret void }
+  define void @funcC(i32 %a, i32 %b) nounwind { ret void }
+  define void @funcD(i32 %a, i32 %b) nounwind { ret void }
+  define void @funcE(i32 %a, i32 %b) nounwind { ret void }
+  define void @funcF(i32 %a, i32 %b) nounwind { ret void }
 ...
+
+# Case 1: All CFIs present; expect outlining and CFIs retained in outlined body.
 ---
-name:            func1
+name:            funcA
 tracksRegLiveness: true
 body:             |
   bb.0:
     liveins: $x10, $x11
-    ; RV32I-MO-LABEL: name: func1
+    ; RV32I-MO-LABEL: name: funcA
     ; RV32I-MO: liveins: $x10, $x11
     ; RV32I-MO-NEXT: {{  $}}
     ; RV32I-MO-NEXT: PseudoTAIL target-flags(riscv-call) @OUTLINED_FUNCTION_0, implicit $x2, implicit-def $x10, implicit-def $x11, implicit-def $x12, implicit $x2, implicit $x10, implicit $x11
-    ; RV64I-MO-LABEL: name: func1
+    ;
+    ; RV64I-MO-LABEL: name: funcA
     ; RV64I-MO: liveins: $x10, $x11
     ; RV64I-MO-NEXT: {{  $}}
     ; RV64I-MO-NEXT: PseudoTAIL target-flags(riscv-call) @OUTLINED_FUNCTION_0, implicit $x2, implicit-def $x10, implicit-def $x11, implicit-def $x12, implicit $x2, implicit $x10, implicit $x11
@@ -39,62 +45,213 @@ body:             |
     PseudoRET
 ...
 ---
-name:            func2
+name:            funcB
 tracksRegLiveness: true
 body:             |
   bb.0:
     liveins: $x10, $x11
-    ; RV32I-MO-LABEL: name: func2
+    ; RV32I-MO-LABEL: name: funcB
     ; RV32I-MO: liveins: $x10, $x11
     ; RV32I-MO-NEXT: {{  $}}
     ; RV32I-MO-NEXT: PseudoTAIL target-flags(riscv-call) @OUTLINED_FUNCTION_0, implicit $x2, implicit-def $x10, implicit-def $x11, implicit-def $x12, implicit $x2, implicit $x10, implicit $x11
-    ; RV64I-MO-LABEL: name: func2
+    ;
+    ; RV64I-MO-LABEL: name: funcB
     ; RV64I-MO: liveins: $x10, $x11
     ; RV64I-MO-NEXT: {{  $}}
     ; RV64I-MO-NEXT: PseudoTAIL target-flags(riscv-call) @OUTLINED_FUNCTION_0, implicit $x2, implicit-def $x10, implicit-def $x11, implicit-def $x12, implicit $x2, implicit $x10, implicit $x11
     $x10 = ORI $x10, 1023
     CFI_INSTRUCTION offset $x1, 0
     $x11 = ORI $x11, 1023
-    CFI_INSTRUCTION offset $x1, -8
-    $x12 = ADDI $x10, 17
     CFI_INSTRUCTION offset $x1, -4
+    $x12 = ADDI $x10, 17
+    CFI_INSTRUCTION offset $x1, -8
     $x11 = AND $x12, $x11
     CFI_INSTRUCTION offset $x1, -12
     $x10 = SUB $x10, $x11
     PseudoRET
 ...
+
+# Case 2: Partial CFIs (extra CFI outside candidate in funcD); expect no outlining.
 ---
-name:            func3
+name:            funcC
 tracksRegLiveness: true
 body:             |
   bb.0:
     liveins: $x10, $x11
-    ; RV32I-MO-LABEL: name: func3
+    ; RV32I-MO-LABEL: name: funcC
     ; RV32I-MO: liveins: $x10, $x11
     ; RV32I-MO-NEXT: {{  $}}
     ; RV32I-MO-NEXT: PseudoTAIL target-flags(riscv-call) @OUTLINED_FUNCTION_0, implicit $x2, implicit-def $x10, implicit-def $x11, implicit-def $x12, implicit $x2, implicit $x10, implicit $x11
-    ; RV64I-MO-LABEL: name: func3
+    ;
+    ; RV64I-MO-LABEL: name: funcC
     ; RV64I-MO: liveins: $x10, $x11
     ; RV64I-MO-NEXT: {{  $}}
     ; RV64I-MO-NEXT: PseudoTAIL target-flags(riscv-call) @OUTLINED_FUNCTION_0, implicit $x2, implicit-def $x10, implicit-def $x11, implicit-def $x12, implicit $x2, implicit $x10, implicit $x11
     $x10 = ORI $x10, 1023
-    CFI_INSTRUCTION offset $x1, -12
+    CFI_INSTRUCTION offset $x1, 0
     $x11 = ORI $x11, 1023
+    CFI_INSTRUCTION offset $x1, -4
+    $x12 = ADDI $x10, 17
     CFI_INSTRUCTION offset $x1, -8
+    $x11 = AND $x12, $x11
+    CFI_INSTRUCTION offset $x1, -12
+    $x10 = SUB $x10, $x11
+    PseudoRET
+...
+---
+name:            funcD
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x10, $x11
+    ; RV32I-MO-LABEL: name: funcD
+    ; RV32I-MO: liveins: $x10, $x11
+    ; RV32I-MO-NEXT: {{  $}}
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -16
+    ; RV32I-MO-NEXT: $x10 = ORI $x10, 1023
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, 0
+    ; RV32I-MO-NEXT: $x11 = ORI $x11, 1023
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -4
+    ; RV32I-MO-NEXT: $x12 = ADDI $x10, 17
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -8
+    ; RV32I-MO-NEXT: $x11 = AND $x12, $x11
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -12
+    ; RV32I-MO-NEXT: $x10 = SUB $x10, $x11
+    ; RV32I-MO-NEXT: PseudoRET
+    ;
+    ; RV64I-MO-LABEL: name: funcD
+    ; RV64I-MO: liveins: $x10, $x11
+    ; RV64I-MO-NEXT: {{  $}}
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -16
+    ; RV64I-MO-NEXT: $x10 = ORI $x10, 1023
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, 0
+    ; RV64I-MO-NEXT: $x11 = ORI $x11, 1023
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -4
+    ; RV64I-MO-NEXT: $x12 = ADDI $x10, 17
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -8
+    ; RV64I-MO-NEXT: $x11 = AND $x12, $x11
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -12
+    ; RV64I-MO-NEXT: $x10 = SUB $x10, $x11
+    ; RV64I-MO-NEXT: PseudoRET
+    CFI_INSTRUCTION offset $x1, -16
+    $x10 = ORI $x10, 1023
+    CFI_INSTRUCTION offset $x1, 0
+    $x11 = ORI $x11, 1023
+    CFI_INSTRUCTION offset $x1, -4
     $x12 = ADDI $x10, 17
+    CFI_INSTRUCTION offset $x1, -8
+    $x11 = AND $x12, $x11
+    CFI_INSTRUCTION offset $x1, -12
+    $x10 = SUB $x10, $x11
+    PseudoRET
+...
+
+# Case 3: CFIs present but candidate is not a tail-call; expect no outlining.
+---
+name:            funcE
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x10, $x11
+    ; RV32I-MO-LABEL: name: funcE
+    ; RV32I-MO: liveins: $x10, $x11
+    ; RV32I-MO-NEXT: {{  $}}
+    ; RV32I-MO-NEXT: $x10 = ORI $x10, 1023
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, 0
+    ; RV32I-MO-NEXT: $x11 = ORI $x11, 1023
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -4
+    ; RV32I-MO-NEXT: $x12 = ADDI $x10, 17
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -8
+    ; RV32I-MO-NEXT: $x11 = AND $x12, $x11
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -12
+    ; RV32I-MO-NEXT: $x10 = SUB $x10, $x11
+    ; RV32I-MO-NEXT: $x10 = ADDI $x10, 1
+    ; RV32I-MO-NEXT: PseudoRET
+    ;
+    ; RV64I-MO-LABEL: name: funcE
+    ; RV64I-MO: liveins: $x10, $x11
+    ; RV64I-MO-NEXT: {{  $}}
+    ; RV64I-MO-NEXT: $x10 = ORI $x10, 1023
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, 0
+    ; RV64I-MO-NEXT: $x11 = ORI $x11, 1023
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -4
+    ; RV64I-MO-NEXT: $x12 = ADDI $x10, 17
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -8
+    ; RV64I-MO-NEXT: $x11 = AND $x12, $x11
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -12
+    ; RV64I-MO-NEXT: $x10 = SUB $x10, $x11
+    ; RV64I-MO-NEXT: $x10 = ADDI $x10, 1
+    ; RV64I-MO-NEXT: PseudoRET
+    $x10 = ORI $x10, 1023
+    CFI_INSTRUCTION offset $x1, 0
+    $x11 = ORI $x11, 1023
     CFI_INSTRUCTION offset $x1, -4
+    $x12 = ADDI $x10, 17
+    CFI_INSTRUCTION offset $x1, -8
     $x11 = AND $x12, $x11
+    CFI_INSTRUCTION offset $x1, -12
+    $x10 = SUB $x10, $x11
+    $x10 = ADDI $x10, 1
+    PseudoRET
+...
+---
+name:            funcF
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $x10, $x11
+    ; RV32I-MO-LABEL: name: funcF
+    ; RV32I-MO: liveins: $x10, $x11
+    ; RV32I-MO-NEXT: {{  $}}
+    ; RV32I-MO-NEXT: $x10 = ORI $x10, 1023
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, 0
+    ; RV32I-MO-NEXT: $x11 = ORI $x11, 1023
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -4
+    ; RV32I-MO-NEXT: $x12 = ADDI $x10, 17
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -8
+    ; RV32I-MO-NEXT: $x11 = AND $x12, $x11
+    ; RV32I-MO-NEXT: CFI_INSTRUCTION offset $x1, -12
+    ; RV32I-MO-NEXT: $x10 = SUB $x10, $x11
+    ; RV32I-MO-NEXT: $x10 = ADDI $x10, 2
+    ; RV32I-MO-NEXT: PseudoRET
+    ;
+    ; RV64I-MO-LABEL: name: funcF
+    ; RV64I-MO: liveins: $x10, $x11
+    ; RV64I-MO-NEXT: {{  $}}
+    ; RV64I-MO-NEXT: $x10 = ORI $x10, 1023
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, 0
+    ; RV64I-MO-NEXT: $x11 = ORI $x11, 1023
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -4
+    ; RV64I-MO-NEXT: $x12 = ADDI $x10, 17
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -8
+    ; RV64I-MO-NEXT: $x11 = AND $x12, $x11
+    ; RV64I-MO-NEXT: CFI_INSTRUCTION offset $x1, -12
+    ; RV64I-MO-NEXT: $x10 = SUB $x10, $x11
+    ; RV64I-MO-NEXT: $x10 = ADDI $x10, 2
+    ; RV64I-MO-NEXT: PseudoRET
+    $x10 = ORI $x10, 1023
     CFI_INSTRUCTION offset $x1, 0
+    $x11 = ORI $x11, 1023
+    CFI_INSTRUCTION offset $x1, -4
+    $x12 = ADDI $x10, 17
+    CFI_INSTRUCTION offset $x1, -8
+    $x11 = AND $x12, $x11
+    CFI_INSTRUCTION offset $x1, -12
     $x10 = SUB $x10, $x11
+    $x10 = ADDI $x10, 2
     PseudoRET
-
+...
 
 # OUTLINED-LABEL: name: OUTLINED_FUNCTION_0
 # OUTLINED: liveins: $x11, $x10
 # OUTLINED-NEXT: {{  $}}
 # OUTLINED-NEXT: $x10 = ORI $x10, 1023
+# OUTLINED-NEXT: CFI_INSTRUCTION offset $x1, 0
 # OUTLINED-NEXT: $x11 = ORI $x11, 1023
+# OUTLINED-NEXT: CFI_INSTRUCTION offset $x1, -4
 # OUTLINED-NEXT: $x12 = ADDI $x10, 17
+# OUTLINED-NEXT: CFI_INSTRUCTION offset $x1, -8
 # OUTLINED-NEXT: $x11 = AND $x12, $x11
+# OUTLINED-NEXT: CFI_INSTRUCTION offset $x1, -12
 # OUTLINED-NEXT: $x10 = SUB $x10, $x11
 # OUTLINED-NEXT: PseudoRET


        


More information about the llvm-commits mailing list