GlobalStructInference: Handle nested optimizable global.gets (#8019)

When we un-nest, temporarily there is a global.get of a global we have
not yet created. Mark those so we don't read them and get confused.

Author: kripken

src/passes/GlobalStructInference.cpp

@@ -309,6 +309,12 @@ struct GlobalStructInference : public Pass {
 
       bool refinalize = false;
 
+      // As we prepare to un-nest globals, we create global.gets of the global
+      // that we will un-nest the content to. That global does not yet exist,
+      // and we note such globals as we go so we ignore them (they are invalid
+      // IR until the global is created, later in this pass).
+      std::unordered_set<GlobalGet*> unnestingGlobalGets;
+
       void visitStructGet(StructGet* curr) {
         optimize(curr, curr->ref, curr->index);
       }
@@ -347,14 +353,18 @@ struct GlobalStructInference : public Pass {
         // This is a read of an immutable field. See if it is a trivial case, of
         // a read from an immutable global.
         if (auto* get = ref->dynCast<GlobalGet>()) {
-          auto* global = wasm.getGlobal(get->name);
-          if (!global->mutable_ && !global->imported()) {
-            if (auto* structNew = global->init->dynCast<StructNew>()) {
-              auto value = readFromStructNew(structNew, fieldIndex, field);
-              // We know the exact global being read here.
-              value.globals.push_back(global->name);
-              replaceCurrent(getReadValue(value, fieldIndex, field, curr));
-              return;
+          // The global.get must be valid, and not in the process of being
+          // rewritten to point to a new un-nested global.
+          if (!unnestingGlobalGets.count(get)) {
+            auto* global = wasm.getGlobal(get->name);
+            if (!global->mutable_ && !global->imported()) {
+              if (auto* structNew = global->init->dynCast<StructNew>()) {
+                auto value = readFromStructNew(structNew, fieldIndex, field);
+                // We know the exact global being read here.
+                value.globals.push_back(global->name);
+                replaceCurrent(getReadValue(value, fieldIndex, field, curr));
+                return;
+              }
             }
           }
         }
@@ -541,6 +551,7 @@ struct GlobalStructInference : public Pass {
 
           globalsToUnnest.emplace_back(
             GlobalToUnnest{value.globals[0], fieldIndex, get});
+          unnestingGlobalGets.insert(get);
 
           ret = get;
         }

test/lit/passes/gsi-nontype.wast

@@ -267,3 +267,61 @@
   )
 )
 
+;; Nested struct.gets that seem optimizable.
+(module
+  (rec
+    ;; CHECK:      (rec
+    ;; CHECK-NEXT:  (type $func (func (result anyref)))
+    (type $func (func (result anyref)))
+    ;; CHECK:       (type $outer (sub (struct (field (ref $inner)))))
+    (type $outer (sub (struct (field (ref $inner)))))
+    ;; CHECK:       (type $inner (sub (struct (field (ref $func)))))
+    (type $inner (sub (struct (field (ref $func)))))
+  )
+
+  ;; CHECK:      (type $3 (func (result anyref)))
+
+  ;; CHECK:      (global $global.unnested.0 (ref (exact $inner)) (struct.new $inner
+  ;; CHECK-NEXT:  (ref.func $func)
+  ;; CHECK-NEXT: ))
+
+  ;; CHECK:      (global $global (ref $outer) (struct.new $outer
+  ;; CHECK-NEXT:  (global.get $global.unnested.0)
+  ;; CHECK-NEXT: ))
+  (global $global (ref $outer) (struct.new $outer
+    (struct.new $inner
+      (ref.func $func)
+    )
+  ))
+
+  ;; CHECK:      (func $func (type $func) (result anyref)
+  ;; CHECK-NEXT:  (unreachable)
+  ;; CHECK-NEXT: )
+  (func $func (type $func) (result anyref)
+    (unreachable)
+  )
+
+  ;; CHECK:      (func $caller (type $3) (result anyref)
+  ;; CHECK-NEXT:  (call_ref $func
+  ;; CHECK-NEXT:   (struct.get $inner 0
+  ;; CHECK-NEXT:    (global.get $global.unnested.0)
+  ;; CHECK-NEXT:   )
+  ;; CHECK-NEXT:  )
+  ;; CHECK-NEXT: )
+  (func $caller (result anyref)
+    (call_ref $func
+      ;; TODO: If we did two passes, we could optimize this one too.
+      (struct.get $inner 0
+        ;; These two can be optimized, if we un-nest the global. When doing so we
+        ;; turn these into a global.get, with a global name that does not exist yet
+        ;; (we only create that global later in the pass). We must not think it is
+        ;; a complete global.get and try to optimize with it when we reach the
+        ;; parent struct.get.
+        (struct.get $outer 0
+          (global.get $global)
+        )
+      )
+    )
+  )
+)
+