dev-embedded/ti50-sdk/files/D100835.patch

diff --git lld/ELF/Arch/RISCV.cpp lld/ELF/Arch/RISCV.cpp
--- lld/ELF/Arch/RISCV.cpp
+++ lld/ELF/Arch/RISCV.cpp
@@ -7,6 +7,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "InputFiles.h"
+#include "OutputSections.h"
 #include "Symbols.h"
 #include "SyntheticSections.h"
 #include "Target.h"
@@ -36,6 +37,7 @@
                      const uint8_t *loc) const override;
   void relocate(uint8_t *loc, const Relocation &rel,
                 uint64_t val) const override;
+  void finalizeSections() const override;
 };
 
 } // end anonymous namespace
@@ -54,6 +56,7 @@
 
 enum Reg {
   X_RA = 1,
+  X_GP = 3,
   X_T0 = 5,
   X_T1 = 6,
   X_T2 = 7,
@@ -267,16 +270,11 @@
   case R_RISCV_TPREL_LO12_I:
   case R_RISCV_TPREL_LO12_S:
     return R_TPREL;
-  case R_RISCV_RELAX:
   case R_RISCV_TPREL_ADD:
     return R_NONE;
+  case R_RISCV_RELAX:
   case R_RISCV_ALIGN:
-    // Not just a hint; always padded to the worst-case number of NOPs, so may
-    // not currently be aligned, and without linker relaxation support we can't
-    // delete NOPs to realign.
-    errorOrWarn(getErrorLocation(loc) + "relocation R_RISCV_ALIGN requires "
-                "unimplemented linker relaxation; recompile with -mno-relax");
-    return R_NONE;
+    return R_RELAX_HINT;
   default:
     error(getErrorLocation(loc) + "unknown relocation (" + Twine(type) +
           ") against symbol " + toString(s));
@@ -469,6 +467,7 @@
     break;
 
   case R_RISCV_RELAX:
+  case R_RISCV_TPREL_ADD:
     return; // Ignored (for now)
 
   default:
@@ -476,6 +475,306 @@
   }
 }
 
+static uint64_t maxOutputSectionAlignment() {
+  uint64_t maxAlign = 1;
+  for (auto *os : outputSections) {
+    maxAlign = std::max<uint64_t>(maxAlign, os->alignment);
+  }
+
+  return maxAlign;
+}
+
+static void setRs1(uint8_t *buf, int rs1) {
+  write32le(buf, (read32le(buf) & 0xfff07fff) | rs1 << 15);
+}
+
+static int64_t addWorstCaseAlignment(int64_t offset, uint64_t alignment) {
+  return offset >= 0 ? offset + alignment : offset - alignment;
+}
+
+using DeleteRanges = std::vector<InputSectionBase::DeleteRange>;
+
+static void addDeleteRange(DeleteRanges &ranges, uint64_t offset,
+                           uint64_t size) {
+  ranges.push_back({offset, size});
+}
+
+// Relax R_RISCV_CALL to jal or c.jal.
+//
+// We always assume during relaxation the symbols can only come closer modulo
+// the effects of alignment.
+static bool relaxCall(InputSection *is, Relocation &rel,
+                      DeleteRanges &deleteRanges) {
+  auto *sym = dyn_cast_or_null<Defined>(rel.sym);
+  if (!sym || !sym->section)
+    return false;
+
+  uint64_t pc = is->getVA(rel.offset);
+  uint64_t target = sym->getVA(rel.addend);
+  int64_t offset = target - pc;
+
+  // As the call site and callee may reside in different sections, we need to
+  // consider the worst case possible offset caused by alignment.
+  if (is->getOutputSection() != sym->getOutputSection()) {
+    offset = addWorstCaseAlignment(offset, maxOutputSectionAlignment());
+  } else if (is != sym->section) {
+    offset = addWorstCaseAlignment(offset, is->getOutputSection()->alignment);
+  }
+
+  bool rvc = config->eflags & EF_RISCV_RVC;
+  unsigned rd =
+      (read32le(is->data().data() + rel.offset + 4) & 0x00000fe0) >> 7;
+
+  // Convert to c.j or c.jal (RV32-only) if offset fits in 12 bits.
+  if (rvc && isInt<12>(offset) && rd == 0) {
+    write16le(is->mutableData().data() + rel.offset, 0xa001); // c.j 0
+    addDeleteRange(deleteRanges, rel.offset + 2, 6);
+    rel.type = R_RISCV_RVC_JUMP;
+    return true;
+  }
+
+  if (!config->is64 && rvc && isInt<12>(offset) && rd == 1) {
+    write16le(is->mutableData().data() + rel.offset, 0x2001); // c.jal 0
+    addDeleteRange(deleteRanges, rel.offset + 2, 6);
+    rel.type = R_RISCV_RVC_JUMP;
+    return true;
+  }
+
+  // Convert to jal if offset fits in 21 bits.
+  if (isInt<21>(offset)) {
+    write32le(is->mutableData().data() + rel.offset,
+              0x0000006f | rd << 7); // jal rd, 0
+    addDeleteRange(deleteRanges, rel.offset + 4, 4);
+    rel.type = R_RISCV_JAL;
+    return true;
+  }
+
+  return false;
+}
+
+// For R_RISCV_HI20 and R_RISCV_LO12_[IS], only relax to GP-relative form if
+// __global_pointer$ symbol is defined and the target symbol is within the
+// same section as gp. This assumes the offset between gp and the target
+// symbol is static during relaxation.
+static bool relaxHi20Lo12(InputSection *is, Relocation &rel,
+                          DeleteRanges &deleteRanges) {
+  bool rvc = config->eflags & EF_RISCV_RVC;
+  uint64_t target = rel.sym->getVA(rel.addend);
+
+  Defined *gp = ElfSym::riscvGlobalPointer;
+
+  auto relaxToCLui = [&]() -> bool {
+    unsigned rd = (read32le(is->data().data() + rel.offset) & 0x00000fe0) >> 7;
+    if (rvc &&
+        isInt<6>(SignExtend64(target + 0x800, config->wordsize * 8) >> 12) &&
+        rd != 0 && rd != 2 && target != 0) {
+      write16le(is->mutableData().data() + rel.offset,
+                0x6001 | rd << 7); // c.lui rd, 0
+      addDeleteRange(deleteRanges, rel.offset + 2, 2);
+      rel.type = R_RISCV_RVC_LUI;
+      return true;
+    }
+    return false;
+  };
+
+  if (!gp || rel.sym->getOutputSection() != gp->section->getOutputSection())
+    return rel.type == R_RISCV_HI20 ? relaxToCLui() : false;
+
+  uint64_t offset = target - gp->getVA();
+
+  if (isInt<12>(offset)) {
+    if (rel.type == R_RISCV_HI20) {
+      addDeleteRange(deleteRanges, rel.offset, 4);
+      rel.type = R_RISCV_NONE;
+      rel.expr = R_NONE;
+    } else { // R_RISCV_LO12_[IS]
+      setRs1(is->mutableData().data() + rel.offset, X_GP);
+      rel.expr = R_RISCV_GPREL;
+    }
+    return true;
+  }
+
+  return false;
+}
+
+// Relaxing PCREL relocations requires two passes due to the linkage from
+// LO12 to HI20. The first pass only relaxes PCREL_LO12 and the second one
+// relaxes PCREL_HI20.
+static bool relaxPcrel(InputSection *is, Relocation &rel,
+                       DeleteRanges &deleteRanges) {
+  Defined *gp = ElfSym::riscvGlobalPointer;
+  if (!gp)
+    return false;
+
+  const Relocation *hi20 = &rel;
+  if (rel.type == R_RISCV_PCREL_LO12_I || rel.type == R_RISCV_PCREL_LO12_S) {
+    hi20 = getRISCVPCRelHi20(rel.sym, rel.addend);
+    if (!hi20)
+      return false;
+  }
+
+  if (hi20->sym->getOutputSection() != gp->section->getOutputSection())
+    return false;
+
+  uint64_t target = hi20->sym->getVA(hi20->addend);
+  uint64_t offset = target - gp->getVA();
+
+  if (isInt<12>(offset)) {
+    if (rel.type == R_RISCV_PCREL_HI20) {
+      addDeleteRange(deleteRanges, rel.offset, 4);
+      rel.type = R_RISCV_NONE;
+      rel.expr = R_NONE;
+    } else {
+      setRs1(is->mutableData().data() + rel.offset, X_GP);
+      rel.sym = hi20->sym;
+      rel.addend = hi20->addend + rel.addend;
+      rel.type =
+          rel.type == R_RISCV_PCREL_LO12_I ? R_RISCV_LO12_I : R_RISCV_LO12_S;
+      rel.expr = R_RISCV_GPREL;
+    }
+    return true;
+  }
+
+  return false;
+}
+
+template <typename F>
+void processRelaxations(MutableArrayRef<Relocation> rels, F f) {
+  if (rels.empty())
+    return;
+
+  for (auto *r = rels.begin() + 1, *e = rels.end(); r != e; ++r) {
+    if (r->type != R_RISCV_RELAX)
+      continue;
+
+    Relocation *rel = std::prev(r);
+    if (r->offset != rel->offset)
+      continue;
+
+    if (f(*rel)) {
+      r->type = R_RISCV_NONE;
+      r->expr = R_NONE;
+    }
+  }
+}
+
+static bool relax() {
+  bool changed = false;
+
+  for (OutputSection *os : outputSections) {
+    for (InputSection *is : getInputSections(*os)) {
+      if (!(is->flags & SHF_EXECINSTR))
+        continue;
+
+      DeleteRanges deleteRanges;
+      processRelaxations(is->relocations, [&](Relocation &rel) {
+        switch (rel.type) {
+        case R_RISCV_CALL:
+        case R_RISCV_CALL_PLT:
+          return relaxCall(is, rel, deleteRanges);
+        case R_RISCV_HI20:
+        case R_RISCV_LO12_I:
+        case R_RISCV_LO12_S:
+          return relaxHi20Lo12(is, rel, deleteRanges);
+        case R_RISCV_PCREL_LO12_I:
+        case R_RISCV_PCREL_LO12_S:
+          return relaxPcrel(is, rel, deleteRanges);
+        }
+
+        return false;
+      });
+
+      // The second-pass for PCREL_HI20 relaxation.
+      processRelaxations(is->relocations, [&](Relocation &rel) {
+        if (rel.type != R_RISCV_PCREL_HI20)
+          return false;
+
+        return relaxPcrel(is, rel, deleteRanges);
+      });
+
+      using DeleteRange = InputSectionBase::DeleteRange;
+      llvm::sort(deleteRanges,
+                 [](const DeleteRange &lhs, const DeleteRange &rhs) {
+                   return lhs.offset < rhs.offset;
+                 });
+
+      is->deleteRanges(deleteRanges);
+      script->assignAddresses();
+      changed |= !deleteRanges.empty();
+    }
+  }
+
+  return changed;
+}
+
+static void relaxAlign() {
+  bool rvc = config->eflags & EF_RISCV_RVC;
+
+  for (OutputSection *os : outputSections) {
+    for (InputSection *is : getInputSections(*os)) {
+      if (!(is->flags & SHF_EXECINSTR))
+        continue;
+
+      uint64_t bytesDeleted = 0;
+      DeleteRanges deleteRanges;
+      for (auto &rel : is->relocations) {
+        if (rel.type == R_RISCV_ALIGN && rel.addend > 0) {
+          uint64_t pc = is->getVA(rel.offset) - bytesDeleted;
+          uint64_t alignment = PowerOf2Ceil(rel.addend + 2);
+          uint64_t nopBytes = alignTo(pc, alignment) - pc;
+
+          if (nopBytes % 2 != 0 || (!rvc && nopBytes % 4 != 0)) {
+            errorOrWarn(is->getObjMsg(rel.offset) + ": alignment requires " +
+                        Twine(nopBytes) + " of nop");
+            break;
+          }
+
+          if (nopBytes > (uint64_t)rel.addend) {
+            errorOrWarn(is->getObjMsg(rel.offset) + ": alignment requires " +
+                        Twine(nopBytes) + " of nop, but only " +
+                        Twine(rel.addend) + " bytes are available");
+            break;
+          }
+          uint64_t bytesToDelete = rel.addend - nopBytes;
+
+          if (bytesToDelete > 0) {
+            addDeleteRange(deleteRanges, rel.offset + nopBytes, bytesToDelete);
+            bytesDeleted += bytesToDelete;
+          }
+
+          uint8_t *buf = is->mutableData().data() + rel.offset;
+          while (nopBytes != 0) {
+            if (nopBytes >= 4) {
+              write32le(buf, 0x00000013); // nop
+              nopBytes -= 4;
+              buf += 4;
+            } else if (rvc && nopBytes == 2) {
+              write16le(buf, 0x0001); // c.nop
+              nopBytes -= 2;
+              buf += 2;
+            }
+          }
+        }
+      }
+
+      is->deleteRanges(deleteRanges);
+      script->assignAddresses();
+    }
+  }
+}
+
+void RISCV::finalizeSections() const {
+  // Can't perform relaxation if it is not a final link.
+  if (config->relocatable)
+    return;
+
+  if (config->relax)
+    while (relax())
+      ;
+
+  relaxAlign();
+}
+
 TargetInfo *elf::getRISCVTargetInfo() {
   static RISCV target;
   return &target;
diff --git lld/ELF/InputSection.h lld/ELF/InputSection.h
--- lld/ELF/InputSection.h
+++ lld/ELF/InputSection.h
@@ -12,7 +12,9 @@
 #include "Config.h"
 #include "Relocations.h"
 #include "Thunks.h"
+#include "lld/Common/CommonLinkerContext.h"
 #include "lld/Common/LLVM.h"
+#include "lld/Common/Memory.h"
 #include "llvm/ADT/CachedHashString.h"
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/TinyPtrVector.h"
@@ -162,6 +164,29 @@
     return rawData;
   }
 
+  MutableArrayRef<uint8_t> mutableData() const {
+    if (!copiedData) {
+      size_t size = data().size();
+      uint8_t *mutData = context().bAlloc.Allocate<uint8_t>(size);
+      memcpy(mutData, data().data(), size);
+      rawData = llvm::makeArrayRef(mutData, size);
+      copiedData = true;
+    }
+
+    return llvm::makeMutableArrayRef(const_cast<uint8_t *>(rawData.data()),
+                                     rawData.size());
+  }
+
+  // A pair of range to delete in (offset, size)
+  struct DeleteRange {
+    uint64_t offset;
+    uint64_t size;
+  };
+
+  // Delete ranges and adjust section content, symbols and relocations.
+  // The deleteRanges must be sorted by offset and must not overlap.
+  void deleteRanges(ArrayRef<DeleteRange> deleteRanges);
+
   // The next member in the section group if this section is in a group. This is
   // used by --gc-sections.
   InputSectionBase *nextInSectionGroup = nullptr;
@@ -229,6 +254,7 @@
   void uncompress() const;
 
   mutable ArrayRef<uint8_t> rawData;
+  mutable bool copiedData;
 
   // This field stores the uncompressed size of the compressed data in rawData,
   // or -1 if rawData is not compressed (either because the section wasn't
@@ -383,7 +409,7 @@
   template <class ELFT> void copyShtGroup(uint8_t *buf);
 };
 
-static_assert(sizeof(InputSection) <= 160, "InputSection is too big");
+static_assert(sizeof(InputSection) <= 168, "InputSection is too big");
 
 inline bool isDebugSection(const InputSectionBase &sec) {
   return (sec.flags & llvm::ELF::SHF_ALLOC) == 0 &&
@@ -398,6 +424,7 @@
 // STT_SECTION symbol associated to the .toc input section.
 extern llvm::DenseSet<std::pair<const Symbol *, uint64_t>> ppc64noTocRelax;
 
+Relocation *getRISCVPCRelHi20(const Symbol *sym, uint64_t addend);
 } // namespace elf
 
 std::string toString(const elf::InputSectionBase *);
diff --git lld/ELF/InputSection.cpp lld/ELF/InputSection.cpp
--- lld/ELF/InputSection.cpp
+++ lld/ELF/InputSection.cpp
@@ -56,7 +56,7 @@
                                    StringRef name, Kind sectionKind)
     : SectionBase(sectionKind, name, flags, entsize, alignment, type, info,
                   link),
-      file(file), rawData(data) {
+      file(file), rawData(data), copiedData(false) {
   // In order to reduce memory allocation, we assume that mergeable
   // sections are smaller than 4 GiB, which is not an unreasonable
   // assumption as of 2017.
@@ -150,6 +150,86 @@
   return ret;
 }
 
+void InputSectionBase::deleteRanges(ArrayRef<DeleteRange> ranges) {
+  if (ranges.empty())
+    return;
+
+  // Adjust all symbol offsets and sizes within the InputSection, using the
+  // following algorithm to avoid quadratic behavior.
+
+  // Gather all symbols within the section.
+  SmallVector<Defined *> symbols;
+  for (auto &sym : file->getSymbols()) {
+    auto *dr = dyn_cast<Defined>(sym);
+    if (!dr || dr->section != this)
+      continue;
+
+    symbols.push_back(dr);
+  }
+
+  // Sort symbols by their starting address.
+  llvm::sort(symbols, [](const Defined *a, const Defined *b) {
+    return a->value < b->value;
+  });
+
+  // Adjust each symbol's address by bytes deleted and also enlarge the symbol's
+  // size to keep its "end" fixed.
+  {
+    uint64_t removedBytes = 0;
+    const auto *r = ranges.begin(), *rend = ranges.end();
+    for (auto *dr : symbols) {
+      for (; r != rend && r->offset < dr->value; ++r)
+        removedBytes += r->size;
+
+      dr->value -= removedBytes;
+      dr->size += removedBytes;
+    }
+  }
+
+  const auto endOff = [](const Defined *dr) { return dr->value + dr->size; };
+
+  // Sort symbols by their "end" address before relaxation.
+  llvm::sort(symbols, [&](const Defined *a, const Defined *b) {
+    return endOff(a) < endOff(b);
+  });
+
+  // Adjust each symbol's end address to their actual end by reducing size.
+  {
+    uint64_t removedBytes = 0;
+    const auto *r = ranges.begin(), *rend = ranges.end();
+    for (auto *dr : symbols) {
+      for (; r != rend && r->offset < endOff(dr); ++r)
+        removedBytes += r->size;
+
+      dr->size -= removedBytes;
+    }
+  }
+
+  // Adjust relocation offsets within the section.
+  uint64_t removedBytes = 0;
+  const auto *r = ranges.begin(), *rend = ranges.end();
+  for (auto &rel : relocations) {
+    for (; r != rend && r->offset < rel.offset; ++r)
+      removedBytes += r->size;
+
+    rel.offset -= removedBytes;
+  }
+
+  // Adjust section content piece-wise and resize the section.
+  MutableArrayRef<uint8_t> buf = this->mutableData();
+  auto *dst = buf.begin() + ranges.begin()->offset;
+  for (auto it = ranges.begin(), e = ranges.end(); it != e; ++it) {
+    auto *from = buf.begin() + it->offset + it->size;
+    auto *to = std::next(it) != ranges.end()
+                   ? (buf.begin() + std::next(it)->offset)
+                   : buf.end();
+    dst = std::copy(from, to, dst);
+  }
+
+  // Resize the section
+  rawData = makeArrayRef(data().data(), dst);
+}
+
 uint64_t SectionBase::getOffset(uint64_t offset) const {
   switch (kind()) {
   case Output: {
@@ -554,7 +634,7 @@
 //
 // This function returns the R_RISCV_PCREL_HI20 relocation from
 // R_RISCV_PCREL_LO12's symbol and addend.
-static Relocation *getRISCVPCRelHi20(const Symbol *sym, uint64_t addend) {
+Relocation *lld::elf::getRISCVPCRelHi20(const Symbol *sym, uint64_t addend) {
   const Defined *d = cast<Defined>(sym);
   if (!d->section) {
     error("R_RISCV_PCREL_LO12 relocation points to an absolute symbol: " +
@@ -717,6 +797,13 @@
     uint64_t val = sym.isUndefWeak() ? p + a : sym.getVA(a);
     return getAArch64Page(val) - getAArch64Page(p);
   }
+  case R_RISCV_GPREL: {
+    if (!ElfSym::riscvGlobalPointer)
+      llvm_unreachable(
+          "Cannot compute R_RISCV_GPREL if __global_pointer$ is not set");
+
+    return sym.getVA(a) - ElfSym::riscvGlobalPointer->getVA();
+  }
   case R_RISCV_PC_INDIRECT: {
     if (const Relocation *hiRel = getRISCVPCRelHi20(&sym, a))
       return getRelocTargetVA(file, hiRel->type, hiRel->addend, sym.getVA(),
@@ -997,7 +1084,7 @@
   AArch64Relaxer aarch64relaxer(relocations);
   for (size_t i = 0, size = relocations.size(); i != size; ++i) {
     const Relocation &rel = relocations[i];
-    if (rel.expr == R_NONE)
+    if (rel.expr == R_NONE || rel.expr == R_RELAX_HINT)
       continue;
     uint64_t offset = rel.offset;
     uint8_t *bufLoc = buf + offset;
diff --git lld/ELF/Relocations.h lld/ELF/Relocations.h
--- lld/ELF/Relocations.h
+++ lld/ELF/Relocations.h
@@ -46,6 +46,7 @@
   R_PLT,
   R_PLT_PC,
   R_PLT_GOTPLT,
+  R_RELAX_HINT,
   R_RELAX_GOT_PC,
   R_RELAX_GOT_PC_NOPIC,
   R_RELAX_TLS_GD_TO_IE,
@@ -101,6 +102,7 @@
   R_PPC64_TOCBASE,
   R_PPC64_RELAX_GOT_PC,
   R_RISCV_ADD,
+  R_RISCV_GPREL,
   R_RISCV_PC_INDIRECT,
 };
 
diff --git lld/ELF/Relocations.cpp lld/ELF/Relocations.cpp
--- lld/ELF/Relocations.cpp
+++ lld/ELF/Relocations.cpp
@@ -960,7 +960,8 @@
             R_MIPS_GOT_OFF, R_MIPS_GOT_OFF32, R_MIPS_GOT_GP_PC,
             R_AARCH64_GOT_PAGE_PC, R_GOT_PC, R_GOTONLY_PC, R_GOTPLTONLY_PC,
             R_PLT_PC, R_PLT_GOTPLT, R_PPC32_PLTREL, R_PPC64_CALL_PLT,
-            R_PPC64_RELAX_TOC, R_RISCV_ADD, R_AARCH64_GOT_PAGE>(e))
+            R_PPC64_RELAX_TOC, R_RISCV_ADD, R_RELAX_HINT, R_AARCH64_GOT_PAGE>(
+          e))
     return true;
 
   // These never do, except if the entire file is position dependent or if
diff --git lld/ELF/Target.h lld/ELF/Target.h
--- lld/ELF/Target.h
+++ lld/ELF/Target.h
@@ -92,6 +92,8 @@
   virtual void applyJumpInstrMod(uint8_t *loc, JumpModType type,
                                  JumpModType val) const {}
 
+  virtual void finalizeSections() const {}
+
   virtual ~TargetInfo();
 
   // This deletes a jump insn at the end of the section if it is a fall thru to
diff --git lld/ELF/Writer.cpp lld/ELF/Writer.cpp
--- lld/ELF/Writer.cpp
+++ lld/ELF/Writer.cpp
@@ -1628,6 +1628,8 @@
   if (config->emachine == EM_HEXAGON)
     hexagonTLSSymbolUpdate(outputSections);
 
+  target->finalizeSections();
+
   int assignPasses = 0;
   for (;;) {
     bool changed = target->needsThunks && tc.createThunks(outputSections);
diff --git lld/test/ELF/riscv-gp.s lld/test/ELF/riscv-gp.s
--- lld/test/ELF/riscv-gp.s
+++ lld/test/ELF/riscv-gp.s
@@ -1,14 +1,16 @@
 # REQUIRES: riscv
-# RUN: llvm-mc -filetype=obj -triple=riscv32 %s -o %t.32.o
+# RUN: llvm-mc -filetype=obj -triple=riscv32 -mattr=+relax %s -o %t.32.o
 # RUN: ld.lld -pie %t.32.o -o %t.32
 # RUN: llvm-readelf -s %t.32 | FileCheck --check-prefix=SYM32 %s
 # RUN: llvm-readelf -S %t.32 | FileCheck --check-prefix=SEC32 %s
+# RUN: llvm-objdump -d --print-imm-hex %t.32 | FileCheck --check-prefix=DIS32 %s
 # RUN: not ld.lld -shared %t.32.o -o /dev/null 2>&1 | FileCheck --check-prefix=ERR %s
 
-# RUN: llvm-mc -filetype=obj -triple=riscv64 %s -o %t.64.o
+# RUN: llvm-mc -filetype=obj -triple=riscv64 -mattr=+relax %s -o %t.64.o
 # RUN: ld.lld -pie %t.64.o -o %t.64
 # RUN: llvm-readelf -s %t.64 | FileCheck --check-prefix=SYM64 %s
 # RUN: llvm-readelf -S %t.64 | FileCheck --check-prefix=SEC64 %s
+# RUN: llvm-objdump -d %t.64 | FileCheck --check-prefix=DIS64 %s
 # RUN: not ld.lld -shared %t.64.o -o /dev/null 2>&1 | FileCheck --check-prefix=ERR %s
 
 ## __global_pointer$ = .sdata+0x800 = 0x39c0
@@ -18,12 +20,15 @@
 # SEC64: [ 7] .sdata PROGBITS {{0*}}000032e0
 # SYM64: {{0*}}00003ae0 0 NOTYPE GLOBAL DEFAULT 7 __global_pointer$
 
-## __global_pointer$ - 0x1000 = 4096*3-2048
-# DIS:      1000: auipc gp, 3
-# DIS-NEXT:       addi gp, gp, -2048
+# DIS32:      auipc gp, 3
+# DIS32-NEXT: addi gp, gp, -1968
+
+# DIS64:      auipc gp, 3
+# DIS64-NEXT: addi gp, gp, -1896
 
 # ERR: error: relocation R_RISCV_PCREL_HI20 cannot be used against symbol '__global_pointer$'; recompile with -fPIC
 
+.option norelax
 lla gp, __global_pointer$
 
 .section .sdata,"aw"
diff --git lld/test/ELF/riscv-relax-align-rvc.s lld/test/ELF/riscv-relax-align-rvc.s
new file mode 100644
--- /dev/null
+++ lld/test/ELF/riscv-relax-align-rvc.s
@@ -0,0 +1,31 @@
+# REQUIRES: riscv
+
+# RUN: llvm-mc -filetype=obj -triple=riscv32-unknown-elf -mattr=+c,+relax %s -o %t.rv32.o
+# RUN: llvm-mc -filetype=obj -triple=riscv64-unknown-elf -mattr=+c,+relax %s -o %t.rv64.o
+
+# RUN: ld.lld %t.rv32.o -o %t.rv32
+# RUN: ld.lld %t.rv64.o -o %t.rv64
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv32 | FileCheck %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv64 | FileCheck %s
+
+# CHECK:      c.add   a0, a1
+# CHECK-NEXT: addi    zero, zero, 0
+# CHECK-NEXT: addi    zero, zero, 0
+# CHECK-NEXT: addi    zero, zero, 0
+# CHECK-NEXT: c.nop
+# CHECK-NEXT: c.add   s0, s1
+# CHECK-NEXT: c.add   s2, s3
+# CHECK-NEXT: c.add   s4, s5
+# CHECK-NEXT: c.nop
+# CHECK-NEXT: c.add   t0, t1
+
+.global _start
+_start:
+.balign 4
+  c.add a0, a1
+.balign 16
+  c.add s0, s1
+  c.add s2, s3
+  c.add s4, s5
+.balign 8
+  c.add t0, t1
diff --git lld/test/ELF/riscv-relax-align.s lld/test/ELF/riscv-relax-align.s
new file mode 100644
--- /dev/null
+++ lld/test/ELF/riscv-relax-align.s
@@ -0,0 +1,33 @@
+# REQUIRES: riscv
+
+# RUN: llvm-mc -filetype=obj -triple=riscv32-unknown-elf -mattr=+relax %s -o %t.rv32.o
+# RUN: llvm-mc -filetype=obj -triple=riscv64-unknown-elf -mattr=+relax %s -o %t.rv64.o
+
+# RUN: ld.lld %t.rv32.o -o %t.rv32
+# RUN: ld.lld %t.rv64.o -o %t.rv64
+# RUN: llvm-objdump -d --no-show-raw-insn %t.rv32 | FileCheck %s
+# RUN: llvm-objdump -d --no-show-raw-insn %t.rv64 | FileCheck %s
+
+# Check that alignment is always handled regardless of --relax option
+# RUN: ld.lld --no-relax %t.rv32.o -o %t-no-relax.rv32
+# RUN: ld.lld --no-relax %t.rv64.o -o %t-no-relax.rv64
+# RUN: llvm-objdump -d --no-show-raw-insn %t-no-relax.rv32 | FileCheck %s
+# RUN: llvm-objdump -d --no-show-raw-insn %t-no-relax.rv64 | FileCheck %s
+
+# CHECK:      add     a0, a1, a2
+# CHECK-NEXT: add     a3, a4, a5
+# CHECK-NEXT: nop
+# CHECK-NEXT: nop
+# CHECK-NEXT: add     s0, s1, s2
+# CHECK-NEXT: add     t0, t1, t2
+
+.global _start
+_start:
+.balign 4
+  add a0, a1, a2
+  add a3, a4, a5
+.balign 16
+  add s0, s1, s2
+.balign 4
+.balign 4
+  add t0, t1, t2
diff --git lld/test/ELF/riscv-relax-call.s lld/test/ELF/riscv-relax-call.s
new file mode 100644
--- /dev/null
+++ lld/test/ELF/riscv-relax-call.s
@@ -0,0 +1,72 @@
+# REQUIRES: riscv
+
+# RUN: llvm-mc -filetype=obj -triple=riscv32-unknown-elf -mattr=+relax %s -o %t.rv32.o
+# RUN: llvm-mc -filetype=obj -triple=riscv64-unknown-elf -mattr=+relax %s -o %t.rv64.o
+# RUN: llvm-mc -filetype=obj -triple=riscv32-unknown-elf -mattr=+c,+relax %s -o %t.rv32c.o
+# RUN: llvm-mc -filetype=obj -triple=riscv64-unknown-elf -mattr=+c,+relax %s -o %t.rv64c.o
+
+# jal relaxation
+# RUN: ld.lld %t.rv32.o --defsym foo=_start+20 -o %t.rv32
+# RUN: ld.lld %t.rv64.o --defsym foo=_start+20 -o %t.rv64
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv32 | FileCheck --check-prefix=JAL %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv64 | FileCheck --check-prefix=JAL %s
+# JAL:      jal     ra, {{.*}} <foo>
+# JAL-NEXT: jal     zero, {{.*}} <foo>
+
+# c.j and c.jal (RV32C-only) relaxation
+# RUN: ld.lld %t.rv32c.o --defsym foo=_start+20 -o %t.rv32c
+# RUN: ld.lld %t.rv64c.o --defsym foo=_start+20 -o %t.rv64c
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv32c | FileCheck --check-prefix=RV32C %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv64c | FileCheck --check-prefix=RV64C %s
+# RV32C:      c.jal     {{.*}} <foo>
+# RV32C-NEXT: c.j       {{.*}} <foo>
+# RV64C:      jal       ra, {{.*}} <foo>
+# RV64C-NEXT: c.j       {{.*}} <foo>
+
+# Don't relax to c.j/c.jal if out of range
+# RUN: ld.lld %t.rv32c.o --defsym foo=_start+0x1004 -o %t.rv32c
+# RUN: ld.lld %t.rv64c.o --defsym foo=_start+0x1004 -o %t.rv64c
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv32c | FileCheck --check-prefix=JAL %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv64c | FileCheck --check-prefix=JAL %s
+
+# Don't relax if out of range (for the first call)
+# RUN: ld.lld %t.rv32c.o --defsym foo=_start+0x100000 -o %t-boundary.rv32
+# RUN: ld.lld %t.rv64c.o --defsym foo=_start+0x100000 -o %t-boundary.rv64
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-boundary.rv32 | FileCheck --check-prefix=BOUNDARY %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-boundary.rv64 | FileCheck --check-prefix=BOUNDARY %s
+# BOUNDARY:      auipc  ra, 256
+# BOUNDARY-NEXT: jalr   ra, 0(ra)
+# BOUNDARY-NEXT: jal    zero, {{.*}} <foo>
+
+# Check relaxation works across output sections
+# RUN: echo 'SECTIONS { .text 0x100000 : { *(.text) } .foo : ALIGN(8) { foo = .; } }' > %t-cross-section.lds
+# RUN: ld.lld %t.rv32c.o %t-cross-section.lds -o %t-cross-section.rv32
+# RUN: ld.lld %t.rv64c.o %t-cross-section.lds -o %t-cross-section.rv64
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-cross-section.rv32 | FileCheck --check-prefix=RV32C %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-cross-section.rv64 | FileCheck --check-prefix=RV64C %s
+
+# Test for output section alignment checking during relaxation. The .foo section
+# cannot be moved closer due to alignment so lld must not relax the call, even
+# though it seems it may be in range before relaxation.
+
+# RUN: echo 'SECTIONS { .text 0x100000 : { *(.text); } .foo : ALIGN(0x100000) { foo = .; } }' > %t-cross-section-out-of-range.lds
+# RUN: ld.lld %t.rv32c.o %t-cross-section-out-of-range.lds -o %t-cross-section-out-of-range.rv32
+# RUN: ld.lld %t.rv64c.o %t-cross-section-out-of-range.lds -o %t-cross-section-out-of-range.rv64
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-cross-section-out-of-range.rv32 | FileCheck --check-prefix=NORELAX %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-cross-section-out-of-range.rv64 | FileCheck --check-prefix=NORELAX %s
+# NORELAX:      auipc  ra, {{.*}}
+# NORELAX-NEXT: jalr   ra, {{.*}}(ra)
+# NORELAX:      auipc  t1, {{.*}}
+# NORELAX-NEXT: jalr   zero, {{.*}}(t1)
+
+# Don't relax to absolute symbols
+# RUN: ld.lld %t.rv32c.o -Ttext=0x100000 --defsym foo=0x100000 -o %t-abs.rv32
+# RUN: ld.lld %t.rv64c.o -Ttext=0x100000 --defsym foo=0x100000 -o %t-abs.rv64
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-abs.rv32 | FileCheck --check-prefix=NORELAX %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-abs.rv64 | FileCheck --check-prefix=NORELAX %s
+
+.global _start
+.p2align 3
+_start:
+  call foo
+  tail foo
diff --git lld/test/ELF/riscv-relax-hi20-lo12.s lld/test/ELF/riscv-relax-hi20-lo12.s
new file mode 100644
--- /dev/null
+++ lld/test/ELF/riscv-relax-hi20-lo12.s
@@ -0,0 +1,51 @@
+# REQUIRES: riscv
+
+# RUN: llvm-mc -filetype=obj -triple=riscv32-unknown-elf -mattr=+relax %s -o %t.rv32.o
+# RUN: llvm-mc -filetype=obj -triple=riscv64-unknown-elf -mattr=+relax %s -o %t.rv64.o
+# RUN: llvm-mc -filetype=obj -triple=riscv32-unknown-elf -mattr=+c,+relax %s -o %t.rv32c.o
+# RUN: llvm-mc -filetype=obj -triple=riscv64-unknown-elf -mattr=+c,+relax %s -o %t.rv64c.o
+
+# RUN: echo 'SECTIONS { .text : { *(.text) } .sdata 0x200000 : { foo = .; } }' > %t.lds
+# RUN: ld.lld --undefined=__global_pointer$ %t.rv32.o %t.lds -o %t.rv32
+# RUN: ld.lld --undefined=__global_pointer$ %t.rv64.o %t.lds -o %t.rv64
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv32 | FileCheck --check-prefix=GP %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv64 | FileCheck --check-prefix=GP %s
+# GP-NOT:  lui
+# GP:      addi    a0, gp, -2048
+# GP-NEXT: lw      a0, -2048(gp)
+# GP-NEXT: sw      a0, -2048(gp)
+
+# RUN: echo 'SECTIONS { .text : { *(.text) } .sdata 0x200000 : { foo = . + 4096; } }' > %t-out-of-range.lds
+# RUN: ld.lld --undefined=__global_pointer$ %t.rv32.o %t-out-of-range.lds -o %t.rv32-out-of-range
+# RUN: ld.lld --undefined=__global_pointer$ %t.rv64.o %t-out-of-range.lds -o %t.rv64-out-of-range
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv32-out-of-range | FileCheck --check-prefix=NORELAX %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv64-out-of-range | FileCheck --check-prefix=NORELAX %s
+# NORELAX:      lui     a0, 513
+# NORELAX-NEXT: addi    a0, a0, 0
+# NORELAX-NEXT: lw      a0, 0(a0)
+# NORELAX-NEXT: sw      a0, 0(a0)
+
+# RUN: ld.lld --defsym=foo=0x1000 %t.rv32c.o -o %t.rv32-clui
+# RUN: ld.lld --defsym=foo=0x1000 %t.rv64c.o -o %t.rv64-clui
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv32-clui | FileCheck --check-prefix=CLUI %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv64-clui | FileCheck --check-prefix=CLUI %s
+# CLUI:      c.lui   a0, 1
+# CLUI-NEXT: addi    a0, a0, 0
+# CLUI-NEXT: lw      a0, 0(a0)
+# CLUI-NEXT: sw      a0, 0(a0)
+
+# RUN: ld.lld --defsym=foo=0x10 %t.rv32c.o -o %t.rv32-cli
+# RUN: ld.lld --defsym=foo=0x10 %t.rv64c.o -o %t.rv64-cli
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv32-cli | FileCheck --check-prefix=CLI %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv64-cli | FileCheck --check-prefix=CLI %s
+# CLI:      c.li    a0, 0
+# CLI-NEXT: addi    a0, a0, 16
+# CLI-NEXT: lw      a0, 16(a0)
+# CLI-NEXT: sw      a0, 16(a0)
+
+.global _start
+_start:
+  lui a0, %hi(foo)
+  addi a0, a0, %lo(foo)
+  lw a0, %lo(foo)(a0)
+  sw a0, %lo(foo)(a0)
diff --git lld/test/ELF/riscv-relax-pcrel.s lld/test/ELF/riscv-relax-pcrel.s
new file mode 100644
--- /dev/null
+++ lld/test/ELF/riscv-relax-pcrel.s
@@ -0,0 +1,28 @@
+# REQUIRES: riscv
+
+# RUN: llvm-mc -filetype=obj -triple=riscv32-unknown-elf -mattr=+relax %s -o %t.rv32.o
+# RUN: llvm-mc -filetype=obj -triple=riscv64-unknown-elf -mattr=+relax %s -o %t.rv64.o
+
+# RUN: echo 'SECTIONS { .text 0x100000 : { *(.text) } .sdata 0x200000 : { foo = .; } }' > %t.lds
+# RUN: ld.lld --undefined=__global_pointer$ %t.rv32.o %t.lds -o %t.rv32
+# RUN: ld.lld --undefined=__global_pointer$ %t.rv64.o %t.lds -o %t.rv64
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv32 | FileCheck --check-prefix=GP %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t.rv64 | FileCheck --check-prefix=GP %s
+# GP-NOT:  auipc
+# GP:      addi    a0, gp, -2048
+# GP-NEXT: sw      a0, -2048(gp)
+
+# RUN: echo 'SECTIONS { .text 0x100000 : { *(.text) } .sdata 0x200000 : { foo = . + 4096; } }' > %t-norelax.lds
+# RUN: ld.lld --undefined=__global_pointer$ %t.rv32.o %t-norelax.lds -o %t-norelax.rv32
+# RUN: ld.lld --undefined=__global_pointer$ %t.rv64.o %t-norelax.lds -o %t-norelax.rv64
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-norelax.rv32 | FileCheck --check-prefix=NORELAX %s
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn %t-norelax.rv64 | FileCheck --check-prefix=NORELAX %s
+# NORELAX:      auipc   a0, 257
+# NORELAX-NEXT: addi    a0, a0, 0
+# NORELAX-NEXT: sw      a0, 0(a0)
+
+.global _start
+_start:
+  auipc a0, %pcrel_hi(foo)
+  addi a0, a0, %pcrel_lo(_start)
+  sw a0, %pcrel_lo(_start)(a0)
diff --git lld/test/ELF/riscv-relax-syms.s lld/test/ELF/riscv-relax-syms.s
new file mode 100644
--- /dev/null
+++ lld/test/ELF/riscv-relax-syms.s
@@ -0,0 +1,32 @@
+# REQUIRES: riscv
+
+// Check that relaxation correctly adjusts symbol addresses and sizes.
+
+# RUN: llvm-mc -filetype=obj -triple=riscv32-unknown-elf -mattr=+relax %s -o %t.rv32.o
+# RUN: llvm-mc -filetype=obj -triple=riscv64-unknown-elf -mattr=+relax %s -o %t.rv64.o
+# RUN: ld.lld -Ttext=0x100000 %t.rv32.o -o %t.rv32
+# RUN: ld.lld -Ttext=0x100000 %t.rv64.o -o %t.rv64
+
+# RUN: llvm-readelf -s %t.rv32 | FileCheck %s
+# RUN: llvm-readelf -s %t.rv64 | FileCheck %s
+
+# CHECK: 100000     4 NOTYPE  LOCAL  DEFAULT     1 a
+# CHECK: 100000     8 NOTYPE  LOCAL  DEFAULT     1 b
+# CHECK: 100004     4 NOTYPE  LOCAL  DEFAULT     1 c
+# CHECK: 100004     8 NOTYPE  LOCAL  DEFAULT     1 d
+# CHECK: 100000    12 NOTYPE  GLOBAL DEFAULT     1 _start
+
+.global _start
+_start:
+a:
+b:
+  add  a0, a1, a2
+.size a, . - a
+c:
+d:
+  call _start
+.size b, . - b
+.size c, . - c
+  add a0, a1, a2
+.size d, . - d
+.size _start, . - _start
diff --git lld/test/ELF/riscv-reloc-align.s lld/test/ELF/riscv-reloc-align.s
deleted file mode 100644
--- lld/test/ELF/riscv-reloc-align.s
+++ /dev/null
@@ -1,12 +0,0 @@
-# REQUIRES: riscv
-
-# RUN: llvm-mc -filetype=obj -triple=riscv32 -mattr=+relax %s -o %t.o
-# RUN: not ld.lld %t.o -o /dev/null 2>&1 | FileCheck %s
-
-# CHECK: relocation R_RISCV_ALIGN requires unimplemented linker relaxation
-
-.global _start
-_start:
-    nop
-    .balign 8
-    nop