Index: ELF/Relocations.h
===================================================================
--- ELF/Relocations.h
+++ ELF/Relocations.h
@@ -129,7 +129,7 @@
 
   ThunkSection *getISDThunkSec(OutputSection *OS, InputSection *IS,
                                InputSectionDescription *ISD, uint32_t Type,
-                               uint64_t Src);
+                               uint64_t Src, unsigned &ThunkSecIdx);
 
   ThunkSection *getISThunkSec(InputSection *IS);
 
Index: ELF/Relocations.cpp
===================================================================
--- ELF/Relocations.cpp
+++ ELF/Relocations.cpp
@@ -1240,10 +1240,9 @@
   for (auto I = Rels.begin(), End = Rels.end(); I != End;)
     scanReloc<ELFT>(Sec, GetOffset, I, End);
 
-  // Sort relocations by offset for more efficient searching for
-  // R_RISCV_PCREL_HI20 and R_PPC64_ADDR64.
-  if (Config->EMachine == EM_RISCV ||
-      (Config->EMachine == EM_PPC64 && Sec.Name == ".toc"))
+  // Efficient searching for R_RISCV_PCREL_HI20 and R_PPC64_ADDR64, and targets
+  // need thunks require relocations sorted by offset.
+  if (Target->NeedsThunks || Config->EMachine == EM_RISCV)
     llvm::stable_sort(Sec.Relocations,
                       [](const Relocation &LHS, const Relocation &RHS) {
                         return LHS.Offset < RHS.Offset;
@@ -1441,13 +1440,20 @@
 // linker script section pattern such as { .text .text.* }.
 ThunkSection *ThunkCreator::getISDThunkSec(OutputSection *OS, InputSection *IS,
                                            InputSectionDescription *ISD,
-                                           uint32_t Type, uint64_t Src) {
-  for (std::pair<ThunkSection *, uint32_t> TP : ISD->ThunkSections) {
-    ThunkSection *TS = TP.first;
+                                           uint32_t Type, uint64_t Src,
+                                           unsigned &ThunkSecIdx) {
+  for (unsigned E = ISD->ThunkSections.size(); ThunkSecIdx != E;
+       ++ThunkSecIdx) {
+    ThunkSection *TS = ISD->ThunkSections[ThunkSecIdx].first;
     uint64_t TSBase = OS->Addr + TS->OutSecOff;
     uint64_t TSLimit = TSBase + TS->getSize();
     if (Target->inBranchRange(Type, Src, (Src > TSLimit) ? TSBase : TSLimit))
       return TS;
+    if (Src < TSLimit)
+      break;
+
+    // If we reach here, we know ThunkSecIdx cannot satisfy any subsequent
+    // relocation, which has a larger offset. Thus we skip it (++ThunkSecIdx).
   }
 
   // No suitable ThunkSection exists. This can happen when there is a branch
@@ -1634,6 +1640,7 @@
   // InputSectionDescription as the caller.
   forEachInputSectionDescription(
       OutputSections, [&](OutputSection *OS, InputSectionDescription *ISD) {
+        unsigned ThunkSecIdx = 0;
         for (InputSection *IS : ISD->Sections)
           for (Relocation &Rel : IS->Relocations) {
             uint64_t Src = IS->getVA(Rel.Offset);
@@ -1658,7 +1665,7 @@
               if (auto *TIS = T->getTargetInputSection())
                 TS = getISThunkSec(TIS);
               else
-                TS = getISDThunkSec(OS, IS, ISD, Rel.Type, Src);
+                TS = getISDThunkSec(OS, IS, ISD, Rel.Type, Src, ThunkSecIdx);
               TS->addThunk(T);
               Thunks[T->getThunkTargetSym()] = T;
             }