From 3b299af92383cb7558224482ccfa714f0162f772 Mon Sep 17 00:00:00 2001
From: Fangrui Song <i@maskray.me>
Date: Mon, 29 Sep 2025 09:15:25 -0700
Subject: ELF: Store EhInputSection relocations to simplify code. NFC

Store relocations directly as `SmallVector<Relocation, 0>` within
EhInputSection to avoid processing different relocation formats
(REL/RELA/CREL) throughout the codebase.

Next: Refactor RelocationScanner to utilize EhInputSection::rels

Pull Request: https://github.com/llvm/llvm-project/pull/161041
---
 lld/ELF/InputSection.cpp | 48 +++++++++++++++++++++++++++++++++---------------
 1 file changed, 33 insertions(+), 15 deletions(-)

(limited to 'lld/ELF/InputSection.cpp')

diff --git a/lld/ELF/InputSection.cpp b/lld/ELF/InputSection.cpp
index 98267d1e081d..1270f27a8d96 100644
--- a/lld/ELF/InputSection.cpp
+++ b/lld/ELF/InputSection.cpp
@@ -1358,20 +1358,21 @@ SyntheticSection *EhInputSection::getParent() const {
 // .eh_frame is a sequence of CIE or FDE records.
 // This function splits an input section into records and returns them.
 template <class ELFT> void EhInputSection::split() {
-  const RelsOrRelas<ELFT> rels = relsOrRelas<ELFT>(/*supportsCrel=*/false);
-  // getReloc expects the relocations to be sorted by r_offset. See the comment
-  // in scanRelocs.
-  if (rels.areRelocsRel()) {
-    SmallVector<typename ELFT::Rel, 0> storage;
-    split<ELFT>(sortRels(rels.rels, storage));
-  } else {
-    SmallVector<typename ELFT::Rela, 0> storage;
-    split<ELFT>(sortRels(rels.relas, storage));
-  }
-}
+  const RelsOrRelas<ELFT> elfRels = relsOrRelas<ELFT>();
+  if (elfRels.areRelocsCrel())
+    preprocessRelocs<ELFT>(elfRels.crels);
+  else if (elfRels.areRelocsRel())
+    preprocessRelocs<ELFT>(elfRels.rels);
+  else
+    preprocessRelocs<ELFT>(elfRels.relas);
+
+  // The loop below expects the relocations to be sorted by offset.
+  auto cmp = [](const Relocation &a, const Relocation &b) {
+    return a.offset < b.offset;
+  };
+  if (!llvm::is_sorted(rels, cmp))
+    llvm::stable_sort(rels, cmp);
 
-template <class ELFT, class RelTy>
-void EhInputSection::split(ArrayRef<RelTy> rels) {
   ArrayRef<uint8_t> d = content();
   const char *msg = nullptr;
   unsigned relI = 0;
@@ -1397,10 +1398,10 @@ void EhInputSection::split(ArrayRef<RelTy> rels) {
     // Find the first relocation that points to [off,off+size). Relocations
     // have been sorted by r_offset.
     const uint64_t off = d.data() - content().data();
-    while (relI != rels.size() && rels[relI].r_offset < off)
+    while (relI != rels.size() && rels[relI].offset < off)
       ++relI;
     unsigned firstRel = -1;
-    if (relI != rels.size() && rels[relI].r_offset < off + size)
+    if (relI != rels.size() && rels[relI].offset < off + size)
       firstRel = relI;
     (id == 0 ? cies : fdes).emplace_back(off, this, size, firstRel);
     d = d.slice(size);
@@ -1410,6 +1411,23 @@ void EhInputSection::split(ArrayRef<RelTy> rels) {
                    << getObjMsg(d.data() - content().data());
 }
 
+template <class ELFT, class RelTy>
+void EhInputSection::preprocessRelocs(Relocs<RelTy> elfRels) {
+  Ctx &ctx = file->ctx;
+  rels.reserve(elfRels.size());
+  for (auto rel : elfRels) {
+    uint64_t offset = rel.r_offset;
+    Symbol &sym = file->getSymbol(rel.getSymbol(ctx.arg.isMips64EL));
+    RelType type = rel.getType(ctx.arg.isMips64EL);
+    RelExpr expr = ctx.target->getRelExpr(type, sym, content().data() + offset);
+    int64_t addend =
+        RelTy::HasAddend
+            ? getAddend<ELFT>(rel)
+            : ctx.target->getImplicitAddend(content().data() + offset, type);
+    rels.push_back({expr, type, offset, addend, &sym});
+  }
+}
+
 // Return the offset in an output section for a given input offset.
 uint64_t EhInputSection::getParentOffset(uint64_t offset) const {
   auto it = partition_point(
-- 
cgit v1.2.3


From 3554c78d973477835b0b062a8aa16ecbc62446dd Mon Sep 17 00:00:00 2001
From: Fangrui Song <i@maskray.me>
Date: Mon, 29 Sep 2025 20:39:49 -0700
Subject: ELF: Use preprocessed relocations for EhInputSection scanning

.eh_frame sections require special sub-section processing, specifically,
CIEs are de-duplicated and FDEs are garbage collected. Create a
specialized scanEhSection() function utilizing the just-added
EhInputSection::rels. OffsetGetter is moved to scanEhSection.

This improves separation of concerns between InputSection and
EhInputSection processing.

This removes another `relsOrRelas` call using `supportsCrel=false`.
DWARF.cpp now has the last call.

Pull Request: https://github.com/llvm/llvm-project/pull/161091
---
 lld/ELF/InputSection.cpp | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'lld/ELF/InputSection.cpp')

diff --git a/lld/ELF/InputSection.cpp b/lld/ELF/InputSection.cpp
index 1270f27a8d96..ff7ef2dce5c7 100644
--- a/lld/ELF/InputSection.cpp
+++ b/lld/ELF/InputSection.cpp
@@ -1357,6 +1357,8 @@ SyntheticSection *EhInputSection::getParent() const {
 
 // .eh_frame is a sequence of CIE or FDE records.
 // This function splits an input section into records and returns them.
+// In rare cases (.eh_frame pieces are reordered by a linker script), the
+// relocations may be unordered.
 template <class ELFT> void EhInputSection::split() {
   const RelsOrRelas<ELFT> elfRels = relsOrRelas<ELFT>();
   if (elfRels.areRelocsCrel())
-- 
cgit v1.2.3