[llvm] [PowerPC] Support local-dynamic TLS relocation on AIX (PR #66316)

[Amy Kwan via llvm-commits]

================
@@ -145,9 +160,92 @@ namespace {
                                                               .addImm(0);
 
         if (IsAIX) {
-          // The variable offset and region handle are copied in r4 and r3. The
-          // copies are followed by GETtlsADDR32AIX/GETtlsADDR64AIX.
-          if (!IsTLSTPRelMI) {
+          if (MI.getOpcode() == PPC::TLSLDAIX8 ||
+              MI.getOpcode() == PPC::TLSLDAIX) {
+            // It is better to put TLSLDAIX node before LoadOffsetToc node,
+            // because LoadOffsetToc node can use clobbers r4/r5. Search for the
+            // first paired LoadOffsetToc node within the same BB.
+            const PPCSubtarget &Subtarget =
+                MBB.getParent()->getSubtarget<PPCSubtarget>();
+            bool IsLargeModel =
+                Subtarget.getTargetMachine().getCodeModel() == CodeModel::Large;
+            unsigned LDTocOp =
+                Is64Bit ? (IsLargeModel ? PPC::LDtocL : PPC::LDtoc)
+                        : (IsLargeModel ? PPC::LWZtocL : PPC::LWZtoc);
+            MachineBasicBlock::iterator Anchor = I;
+            if (!RegInfo.use_empty(OutReg)) {
+              std::set<MachineInstr *> Uses;
+              // Collect all instructions that use OutReg
+              for (MachineOperand &MO : RegInfo.use_operands(OutReg)) {
+                if (Uses.count(MO.getParent()))
+                  continue;
+                Uses.insert(MO.getParent());
+              }
+              // Find the first Add within current BB.
+              MachineBasicBlock::iterator UseIter = MBB.begin();
+              for (MachineBasicBlock::iterator AE = MBB.end(); UseIter != AE;
+                   ++UseIter)
+                if (Uses.count(&*UseIter))
+                  break;
+
+              if (UseIter != MBB.end()) {
+                // Get the instruction that defines the other used register
+                // operand of UseIter. The match pattern is that: UseIter has
+                // exactly one used-operand defined by LDTocOp
+                // (LDtocL/LDtoc/LWZtocL/LWZtoc).
+                MachineInstr *LoadOffsetToc = nullptr;
+                int MatchCount = 0;
+                for (MachineOperand &MO : UseIter->operands()) {
+                  if (MO.isReg() && MO.isUse()) {
+                    if (RegInfo.hasOneDef(MO.getReg())) {
----------------
amy-kwan wrote:

Pull out `MO.getReg()` calls into a separate variable after the `isReg()` check.

https://github.com/llvm/llvm-project/pull/66316