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

[Fangrui Song via cfe-commits]

================
@@ -145,9 +160,78 @@ 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 (IsTLSLDAIXMI) {
+            // The relative order between the LoadOffset at toc node, and the
+            // ._tls_get_mod node is being tuned here. It is better to put the
+            // LoadOffset at toc node after the call, since the LoadOffset at toc node
+            // can use clobbers r4/r5. Search for the pattern of two Load at toc
+            // nodes, and then move the LoadOffset at toc node right before the
+            // node that uses the OutReg of the ._tls_get_mod node.
+            unsigned LDTocOp =
+                Is64Bit ? (IsLargeModel ? PPC::LDtocL : PPC::LDtoc)
+                        : (IsLargeModel ? PPC::LWZtocL : PPC::LWZtoc);
+            if (!RegInfo.use_empty(OutReg)) {
+              std::set<MachineInstr *> Uses;
+              // Collect all instructions that use the OutReg.
+              for (MachineOperand &MO : RegInfo.use_operands(OutReg))
+                Uses.insert(MO.getParent());
+              // Find the first user (e.g.: lwax/stfdx) within the current BB.
+              MachineBasicBlock::iterator UseIter = MBB.begin();
+              for (MachineBasicBlock::iterator IE = MBB.end(); UseIter != IE;
+                   ++UseIter)
+                if (Uses.count(&*UseIter))
+                  break;
+
+              if (UseIter != MBB.end()) {
+                // Collect associated Load at toc nodes.
+                std::set<MachineInstr *> LoadFromTocs;
+                for (MachineOperand &MO : UseIter->operands())
+                  if (MO.isReg() && MO.isUse()) {
+                    if (RegInfo.hasOneDef(MO.getReg())) {
+                      MachineInstr *Temp =
+                          RegInfo.getOneDef(MO.getReg())->getParent();
+                      if (Temp == &MI && RegInfo.hasOneDef(InReg))
+                        Temp = RegInfo.getOneDef(InReg)->getParent();
+                      if (Temp->getOpcode() == LDTocOp)
+                        LoadFromTocs.insert(Temp);
+                    } else {
+                      // FIXME: analyze this scenario if there is one.
+                      LoadFromTocs.clear();
+                      break;
+                    }
+                  }
+
+                // Check the two Load at toc: one should be _$TLSML, and the other
+                // will be moved before the node that uses the OutReg of the
+                // ._tls_get_mod node.
+                if (LoadFromTocs.size() == 2) {
+                  MachineBasicBlock::iterator TLSMLIter = MBB.end();
+                  MachineBasicBlock::iterator OffsetIter = MBB.end();
+                  for (MachineBasicBlock::iterator I = MBB.begin(),
+                                                   IE = MBB.end();
+                       I != IE; ++I)
+                    if (LoadFromTocs.count(&*I)) {
+                      if (I->getOperand(1).isGlobal() &&
+                          I->getOperand(1).getGlobal()->getName().equals(
----------------
MaskRay wrote:

`== ...`

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