[llvm] [PowerPC][AIX] Refactor existing logic to handle non-zero offsets for aix-small-local-dynamic-tls (PR #89182)

[Felix via llvm-commits]

================
@@ -7600,52 +7594,54 @@ static bool isEligibleToFoldADDIForLocalExecAccesses(SelectionDAG *DAG,
   if (!GA)
     return false;
 
-  // The local-exec TLS variable should only have the MO_TPREL_FLAG target flag,
-  // so this optimization is not performed otherwise if the flag is not set.
+  if (DAG->getTarget().getTLSModel(GA->getGlobal()) == TLSModel::LocalExec) {
+    // The first operand of the ADDIToFold should be the thread pointer.
+    // This transformation is only performed if the first operand of the
+    // addi is the thread pointer.
+    SDValue TPRegNode = ADDIToFold.getOperand(0);
+    RegisterSDNode *TPReg = dyn_cast<RegisterSDNode>(TPRegNode.getNode());
+    if (!TPReg || (TPReg->getReg() != Subtarget.getThreadPointerRegister()))
+      return false;
+  }
+
+  // The local-[exec|dynamic] TLS variable should only have the
+  // [MO_TPREL_FLAG|MO_TLSLD_FLAG] target flags, so this optimization is not
+  // performed otherwise if the flag is not set.
   unsigned TargetFlags = GA->getTargetFlags();
-  if (TargetFlags != PPCII::MO_TPREL_FLAG)
+  if (!(TargetFlags == PPCII::MO_TPREL_FLAG ||
+        TargetFlags == PPCII::MO_TLSLD_FLAG))
     return false;
 
   // If all conditions are satisfied, the ADDI is valid for folding.
   return true;
 }
 
-// For non-TOC-based local-exec access where an addi is feeding into another
-// addi, fold this sequence into a single addi if possible.
-// Before this optimization, the sequence appears as:
-//    addi rN, r13, sym at le
+// For non-TOC-based local-[exec|dynamic] access where an addi is feeding into
+// another addi, fold this sequence into a single addi if possible. Before this
+// optimization, the sequence appears as:
+//    addi rN, r13, sym@[le|ld]
 //    addi rM, rN, imm
 // After this optimization, we can fold the two addi into a single one:
-//    addi rM, r13, sym at le + imm
-static void foldADDIForLocalExecAccesses(SDNode *N, SelectionDAG *DAG) {
+//    addi rM, r13, sym@[le|ld] + imm
+static void foldADDIForFasterLocalAccesses(SDNode *N, SelectionDAG *DAG) {
   if (N->getMachineOpcode() != PPC::ADDI8)
     return;
 
   // InitialADDI is the addi feeding into N (also an addi), and the addi that
   // we want optimized out.
   SDValue InitialADDI = N->getOperand(0);
 
-  if (!isEligibleToFoldADDIForLocalExecAccesses(DAG, InitialADDI))
+  if (!isEligibleToFoldADDIForFasterLocalAccesses(DAG, InitialADDI))
     return;
 
-  // At this point, InitialADDI can be folded into a non-TOC-based local-exec
----------------
orcguru wrote:

Similar check already exists in isEligible..., so I removed this one.

https://github.com/llvm/llvm-project/pull/89182