[lld][ELF] Support relax R_LARCH_ALIGN

lld/ELF/Arch/LoongArch.cpp

@@ -36,6 +36,8 @@ class LoongArch final : public TargetInfo {
   bool usesOnlyLowPageBits(RelType type) const override;
   void relocate(uint8_t *loc, const Relocation &rel,
                 uint64_t val) const override;
+  bool relaxOnce(int pass) const override;
+  void finalizeRelax(int passes) const override;
 };
 } // end anonymous namespace
 
@@ -465,8 +467,9 @@ RelExpr LoongArch::getRelExpr(const RelType type, const Symbol &s,
   case R_LARCH_TLS_GD_HI20:
     return R_TLSGD_GOT;
   case R_LARCH_RELAX:
-    // LoongArch linker relaxation is not implemented yet.
-    return R_NONE;
+    return config->relax ? R_RELAX_HINT : R_NONE;
+  case R_LARCH_ALIGN:
+    return R_RELAX_HINT;
 
   // Other known relocs that are explicitly unimplemented:
   //
@@ -659,6 +662,155 @@ void LoongArch::relocate(uint8_t *loc, const Relocation &rel,
   }
 }
 
+static bool relax(InputSection &sec) {
+  const uint64_t secAddr = sec.getVA();
+  const MutableArrayRef<Relocation> relocs = sec.relocs();
+  auto &aux = *sec.relaxAux;
+  bool changed = false;
+  ArrayRef<SymbolAnchor> sa = ArrayRef(aux.anchors);
+  uint64_t delta = 0;
+
+  std::fill_n(aux.relocTypes.get(), relocs.size(), R_LARCH_NONE);
+  aux.writes.clear();
+  for (auto [i, r] : llvm::enumerate(relocs)) {
+    const uint64_t loc = secAddr + r.offset - delta;
+    uint32_t &cur = aux.relocDeltas[i], remove = 0;
+    switch (r.type) {
+    case R_LARCH_ALIGN: {
+      const uint64_t addend =
+          r.sym->isUndefined() ? Log2_64(r.addend) + 1 : r.addend;
+      const uint64_t allBytes = (1 << (addend & 0xff)) - 4;
+      const uint64_t align = 1 << (addend & 0xff);
+      const uint64_t maxBytes = addend >> 8;
+      const uint64_t off = loc & (align - 1);
+      const uint64_t curBytes = off == 0 ? 0 : align - off;
+      // All bytes beyond the alignment boundary should be removed.
+      // If emit bytes more than max bytes to emit, remove all.
+      if (maxBytes != 0 && curBytes > maxBytes)
+        remove = allBytes;
+      else
+        remove = allBytes - curBytes;
+      // If we can't satisfy this alignment, we've found a bad input.
+      if (LLVM_UNLIKELY(static_cast<int32_t>(remove) < 0)) {
+        errorOrWarn(getErrorLocation((const uint8_t *)loc) +
+                    "insufficient padding bytes for " + lld::toString(r.type) +
+                    ": " + Twine(allBytes) + " bytes available for " +
+                    "requested alignment of " + Twine(align) + " bytes");
+        remove = 0;
+      }
+      break;
+    }
+    }
+
+    // For all anchors whose offsets are <= r.offset, they are preceded by
+    // the previous relocation whose `relocDeltas` value equals `delta`.
+    // Decrease their st_value and update their st_size.
+    for (; sa.size() && sa[0].offset <= r.offset; sa = sa.slice(1)) {
+      if (sa[0].end)
+        sa[0].d->size = sa[0].offset - delta - sa[0].d->value;
+      else
+        sa[0].d->value = sa[0].offset - delta;
+    }
+    delta += remove;
+    if (delta != cur) {
+      cur = delta;
+      changed = true;
+    }
+  }
+
+  for (const SymbolAnchor &a : sa) {
+    if (a.end)
+      a.d->size = a.offset - delta - a.d->value;
+    else
+      a.d->value = a.offset - delta;
+  }
+  // Inform assignAddresses that the size has changed.
+  if (!isUInt<32>(delta))
+    fatal("section size decrease is too large: " + Twine(delta));
+  sec.bytesDropped = delta;
+  return changed;
+}
+
+// When relaxing just R_LARCH_ALIGN, relocDeltas is usually changed only once in
+// the absence of a linker script. For call and load/store R_LARCH_RELAX, code
+// shrinkage may reduce displacement and make more relocations eligible for
+// relaxation. Code shrinkage may increase displacement to a call/load/store
+// target at a higher fixed address, invalidating an earlier relaxation. Any
+// change in section sizes can have cascading effect and require another
+// relaxation pass.
+bool LoongArch::relaxOnce(int pass) const {
+  if (config->relocatable)
+    return false;
+
+  if (pass == 0)
+    initSymbolAnchors();
+
+  SmallVector<InputSection *, 0> storage;
+  bool changed = false;
+  for (OutputSection *osec : outputSections) {
+    if (!(osec->flags & SHF_EXECINSTR))
+      continue;
+    for (InputSection *sec : getInputSections(*osec, storage))
+      changed |= relax(*sec);
+  }
+  return changed;
+}
+
+void LoongArch::finalizeRelax(int passes) const {
+  log("relaxation passes: " + Twine(passes));
+  SmallVector<InputSection *, 0> storage;
+  for (OutputSection *osec : outputSections) {
+    if (!(osec->flags & SHF_EXECINSTR))
+      continue;
+    for (InputSection *sec : getInputSections(*osec, storage)) {
+      RelaxAux &aux = *sec->relaxAux;
+      if (!aux.relocDeltas)
+        continue;
+
+      MutableArrayRef<Relocation> rels = sec->relocs();
+      ArrayRef<uint8_t> old = sec->content();
+      size_t newSize = old.size() - aux.relocDeltas[rels.size() - 1];
+      uint8_t *p = context().bAlloc.Allocate<uint8_t>(newSize);
+      uint64_t offset = 0;
+      int64_t delta = 0;
+      sec->content_ = p;
+      sec->size = newSize;
+      sec->bytesDropped = 0;
+
+      // Update section content: remove NOPs for R_LARCH_ALIGN and rewrite
+      // instructions for relaxed relocations.
+      for (size_t i = 0, e = rels.size(); i != e; ++i) {
+        uint32_t remove = aux.relocDeltas[i] - delta;
+        delta = aux.relocDeltas[i];
+        if (remove == 0 && aux.relocTypes[i] == R_LARCH_NONE)
+          continue;
+
+        // Copy from last location to the current relocated location.
+        const Relocation &r = rels[i];
+        uint64_t size = r.offset - offset;
+        memcpy(p, old.data() + offset, size);
+        p += size;
+        offset = r.offset + remove;
+      }
+      memcpy(p, old.data() + offset, old.size() - offset);
+
+      // Subtract the previous relocDeltas value from the relocation offset.
+      // For a pair of R_LARCH_XXX/R_LARCH_RELAX with the same offset, decrease
+      // their r_offset by the same delta.
+      delta = 0;
+      for (size_t i = 0, e = rels.size(); i != e;) {
+        uint64_t cur = rels[i].offset;
+        do {
+          rels[i].offset -= delta;
+          if (aux.relocTypes[i] != R_LARCH_NONE)
+            rels[i].type = aux.relocTypes[i];
+        } while (++i != e && rels[i].offset == cur);
+        delta = aux.relocDeltas[i - 1];
+      }
+    }
+  }
+}
+
 TargetInfo *elf::getLoongArchTargetInfo() {
   static LoongArch target;
   return &target;

lld/ELF/Arch/RISCV.cpp

@@ -45,6 +45,7 @@ class RISCV final : public TargetInfo {
                 uint64_t val) const override;
   void relocateAlloc(InputSectionBase &sec, uint8_t *buf) const override;
   bool relaxOnce(int pass) const override;
+  void finalizeRelax(int passes) const override;
 };
 
 } // end anonymous namespace
@@ -104,26 +105,6 @@ static uint32_t setLO12_S(uint32_t insn, uint32_t imm) {
          (extractBits(imm, 4, 0) << 7);
 }
 
-namespace {
-struct SymbolAnchor {
-  uint64_t offset;
-  Defined *d;
-  bool end; // true for the anchor of st_value+st_size
-};
-} // namespace
-
-struct elf::RISCVRelaxAux {
-  // This records symbol start and end offsets which will be adjusted according
-  // to the nearest relocDeltas element.
-  SmallVector<SymbolAnchor, 0> anchors;
-  // For relocations[i], the actual offset is
-  //   r_offset - (i ? relocDeltas[i-1] : 0).
-  std::unique_ptr<uint32_t[]> relocDeltas;
-  // For relocations[i], the actual type is relocTypes[i].
-  std::unique_ptr<RelType[]> relocTypes;
-  SmallVector<uint32_t, 0> writes;
-};
-
 RISCV::RISCV() {
   copyRel = R_RISCV_COPY;
   pltRel = R_RISCV_JUMP_SLOT;
@@ -695,13 +676,13 @@ void RISCV::relocateAlloc(InputSectionBase &sec, uint8_t *buf) const {
   }
 }
 
-static void initSymbolAnchors() {
+void elf::initSymbolAnchors() {
   SmallVector<InputSection *, 0> storage;
   for (OutputSection *osec : outputSections) {
     if (!(osec->flags & SHF_EXECINSTR))
       continue;
     for (InputSection *sec : getInputSections(*osec, storage)) {
-      sec->relaxAux = make<RISCVRelaxAux>();
+      sec->relaxAux = make<RelaxAux>();
       if (sec->relocs().size()) {
         sec->relaxAux->relocDeltas =
             std::make_unique<uint32_t[]>(sec->relocs().size());
@@ -948,15 +929,15 @@ bool RISCV::relaxOnce(int pass) const {
   return changed;
 }
 
-void elf::riscvFinalizeRelax(int passes) {
+void RISCV::finalizeRelax(int passes) const {
   llvm::TimeTraceScope timeScope("Finalize RISC-V relaxation");
   log("relaxation passes: " + Twine(passes));
   SmallVector<InputSection *, 0> storage;
   for (OutputSection *osec : outputSections) {
     if (!(osec->flags & SHF_EXECINSTR))
       continue;
     for (InputSection *sec : getInputSections(*osec, storage)) {
-      RISCVRelaxAux &aux = *sec->relaxAux;
+      RelaxAux &aux = *sec->relaxAux;
       if (!aux.relocDeltas)
         continue;
 

lld/ELF/InputSection.cpp

@@ -354,9 +354,10 @@ InputSectionBase *InputSection::getRelocatedSection() const {
 
 template <class ELFT, class RelTy>
 void InputSection::copyRelocations(uint8_t *buf) {
-  if (config->relax && !config->relocatable && config->emachine == EM_RISCV) {
-    // On RISC-V, relaxation might change relocations: copy from internal ones
-    // that are updated by relaxation.
+  if (config->relax && !config->relocatable &&
+      (config->emachine == EM_RISCV || config->emachine == EM_LOONGARCH)) {
+    // On LoongArch and RISC-V, relaxation might change relocations: copy
+    // from internal ones that are updated by relaxation.
     InputSectionBase *sec = getRelocatedSection();
     copyRelocations<ELFT, RelTy>(buf, llvm::make_range(sec->relocations.begin(),
                                                        sec->relocations.end()));

lld/ELF/InputSection.h

@@ -102,7 +102,23 @@ class SectionBase {
         link(link), info(info) {}
 };
 
-struct RISCVRelaxAux;
+struct SymbolAnchor {
+  uint64_t offset;
+  Defined *d;
+  bool end; // true for the anchor of st_value+st_size
+};
+
+struct RelaxAux {
+  // This records symbol start and end offsets which will be adjusted according
+  // to the nearest relocDeltas element.
+  SmallVector<SymbolAnchor, 0> anchors;
+  // For relocations[i], the actual offset is
+  //   r_offset - (i ? relocDeltas[i-1] : 0).
+  std::unique_ptr<uint32_t[]> relocDeltas;
+  // For relocations[i], the actual type is relocTypes[i].
+  std::unique_ptr<RelType[]> relocTypes;
+  SmallVector<uint32_t, 0> writes;
+};
 
 // This corresponds to a section of an input file.
 class InputSectionBase : public SectionBase {
@@ -227,9 +243,9 @@ class InputSectionBase : public SectionBase {
     // basic blocks.
     JumpInstrMod *jumpInstrMod = nullptr;
 
-    // Auxiliary information for RISC-V linker relaxation. RISC-V does not use
-    // jumpInstrMod.
-    RISCVRelaxAux *relaxAux;
+    // Auxiliary information for RISC-V and LoongArch linker relaxation.
+    // They do not use jumpInstrMod.
+    RelaxAux *relaxAux;
 
     // The compressed content size when `compressed` is true.
     size_t compressedSize;

lld/ELF/Target.h

@@ -95,6 +95,8 @@ class TargetInfo {
 
   // Do a linker relaxation pass and return true if we changed something.
   virtual bool relaxOnce(int pass) const { return false; }
+  // Do finalize relaxation after collecting relaxation infos.
+  virtual void finalizeRelax(int passes) const {}
 
   virtual void applyJumpInstrMod(uint8_t *loc, JumpModType type,
                                  JumpModType val) const {}
@@ -236,6 +238,7 @@ void addArmSyntheticSectionMappingSymbol(Defined *);
 void sortArmMappingSymbols();
 void convertArmInstructionstoBE8(InputSection *sec, uint8_t *buf);
 void createTaggedSymbols(const SmallVector<ELFFileBase *, 0> &files);
+void initSymbolAnchors();
 
 LLVM_LIBRARY_VISIBILITY extern const TargetInfo *target;
 TargetInfo *getTarget();

lld/ELF/Writer.cpp

@@ -1752,8 +1752,8 @@ template <class ELFT> void Writer<ELFT>::finalizeAddressDependentContent() {
       }
     }
   }
-  if (!config->relocatable && config->emachine == EM_RISCV)
-    riscvFinalizeRelax(pass);
+  if (!config->relocatable)
+    target->finalizeRelax(pass);
 
   if (config->relocatable)
     for (OutputSection *sec : outputSections)