[lld] [LLD][COFF] Implement support for hybrid IAT on ARM64X (PR #124189)

[Martin Storsjö via llvm-commits]

================
@@ -717,52 +717,155 @@ class ExportOrdinalChunk : public NonSectionChunk {
 void IdataContents::create(COFFLinkerContext &ctx) {
   std::vector<std::vector<DefinedImportData *>> v = binImports(ctx, imports);
 
+  // Merge compatible EC and native import files in hybrid images.
+  if (ctx.hybridSymtab) {
+    for (std::vector<DefinedImportData *> &syms : v) {
+      // At this point, symbols are sorted by base name, ensuring that
+      // compatible import files, if present, are adjacent.
+      std::vector<DefinedImportData *> hybridSyms;
+      ImportFile *prev = nullptr;
+      for (DefinedImportData *sym : syms) {
+        ImportFile *file = sym->file;
+        if (!prev || file->isEC() == prev->isEC() ||
+            !file->isSameImport(prev)) {
+          hybridSyms.push_back(sym);
+          prev = file;
+          continue;
+        }
+
+        // The native variant exposes a subset of EC symbols and chunks. Use the
+        // EC variant to represent both.
+        if (file->isEC()) {
+          hybridSyms.pop_back();
+          hybridSyms.push_back(sym);
+        }
+
+        prev->hybridFile = file;
+        file->hybridFile = prev;
+        prev = nullptr;
+      }
+
+      // Sort symbols by type: native-only files first, followed by merged
+      // hybrid files, and then EC-only files.
+      llvm::stable_sort(hybridSyms,
+                        [](DefinedImportData *a, DefinedImportData *b) {
+                          if (a->file->hybridFile)
+                            return !b->file->hybridFile && b->file->isEC();
+                          return !a->file->isEC() && b->file->isEC();
+                        });
+      syms = std::move(hybridSyms);
+    }
+  }
+
   // Create .idata contents for each DLL.
   for (std::vector<DefinedImportData *> &syms : v) {
     // Create lookup and address tables. If they have external names,
     // we need to create hintName chunks to store the names.
     // If they don't (if they are import-by-ordinals), we store only
     // ordinal values to the table.
     size_t base = lookups.size();
+    Chunk *lookupsTerminator = nullptr, *addressesTerminator = nullptr;
     for (DefinedImportData *s : syms) {
       uint16_t ord = s->getOrdinal();
+      HintNameChunk *hintChunk = nullptr;
+      Chunk *lookupsChunk, *addressesChunk;
+
       if (s->getExternalName().empty()) {
-        lookups.push_back(make<OrdinalOnlyChunk>(ctx, ord));
-        addresses.push_back(make<OrdinalOnlyChunk>(ctx, ord));
+        lookupsChunk = make<OrdinalOnlyChunk>(ctx, ord);
+        addressesChunk = make<OrdinalOnlyChunk>(ctx, ord);
       } else {
-        auto *c = make<HintNameChunk>(s->getExternalName(), ord);
-        lookups.push_back(make<LookupChunk>(ctx, c));
-        addresses.push_back(make<LookupChunk>(ctx, c));
-        hints.push_back(c);
+        hintChunk = make<HintNameChunk>(s->getExternalName(), ord);
+        lookupsChunk = make<LookupChunk>(ctx, hintChunk);
+        addressesChunk = make<LookupChunk>(ctx, hintChunk);
+        hints.push_back(hintChunk);
       }
 
-      if (s->file->impECSym) {
+      // Detect the first EC-only import in the hybrid IAT. Emit null chunks
+      // and add an ARM64X relocation to replace it with the import for the EC
+      // view. Additionally, use the original chunks as import terminators
+      // and zero them with ARM64X relocations. Since these chunks appear
+      // after the null terminator in the native view, they are always ignored
+      // by the loader. However, MSVC emits them for some reason.
+      if (ctx.hybridSymtab && !lookupsTerminator && s->file->isEC() &&
+          !s->file->hybridFile) {
+        lookupsTerminator = lookupsChunk;
+        addressesTerminator = addressesChunk;
+        lookupsChunk = make<NullChunk>(ctx);
+        addressesChunk = make<NullChunk>(ctx);
+
+        Arm64XRelocVal relocVal = hintChunk;
+        if (!hintChunk)
+          relocVal = (1ULL << 63) | ord;
+        ctx.dynamicRelocs->add(IMAGE_DVRT_ARM64X_FIXUP_TYPE_VALUE,
+                               sizeof(uint64_t), lookupsChunk, relocVal);
+        ctx.dynamicRelocs->add(IMAGE_DVRT_ARM64X_FIXUP_TYPE_VALUE,
+                               sizeof(uint64_t), addressesChunk, relocVal);
+        ctx.dynamicRelocs->add(IMAGE_DVRT_ARM64X_FIXUP_TYPE_ZEROFILL,
----------------
mstorsjo wrote:

I'm trying to form an understanding of the expected end state of things after this loop.

At the end, we're going to have the regular IAT (`lookups` here) look like this:
```
[native]...[native][hybrid]...[hybrid][null chunk][second EC-only]...[more EC-only][lookupTerminator]
```
I presume the purpose of the null chunk in the middle of the regular IAT is to terminate it, so in native mode you only see the native-only and hybrid entries? After applying dynamic relocations, the null chunk is turned into the entry it was initially meant to be, so you see all of it - and we adjust the pointer to the start, so that it points at the first non-native entry.

What's the idea and purpose of the lookupTerminator? In the native view, it's not visible, and after relocations in EC mode, it's turned into a null terminator. Why not just do a plain null terminator to begin with?

Secondly, if I follow it correctly, the aux IAT is supposed to look like this:
```
[null chunks for native-only][aux entries for hybrid imports][aux entries for ec-only imports][null chunk]
```

I've forgotten the purpose/role of the AUX IAT. Doesn't it use null pointers as terminators - how does this work? Or does the delta for the start of the regular IAT also get applied to this one?



https://github.com/llvm/llvm-project/pull/124189