Merge pull request 'Replace SIMD assembly with initialized Node16::index + valgrind client request' (#77) from client-request-instead-of-asm into main

Reviewed-on: #77

ConflictSet.cpp

@@ -549,6 +549,7 @@ inline void Node48::copyChildrenAndKeyFrom(const Node16 &other) {
   assert(numChildren == Node16::kMaxNodes);
   memset(index, -1, sizeof(index));
   memset(children, 0, sizeof(children));
+  memset(reverseIndex, 0, sizeof(reverseIndex));
   const auto z = InternalVersionT::zero;
   for (auto &v : childMaxVersion) {
     v = z;
@@ -568,6 +569,13 @@ inline void Node48::copyChildrenAndKeyFrom(const Node16 &other) {
         std::max(maxOfMax[i >> Node48::kMaxOfMaxShift], childMaxVersion[i]);
     ++i;
   }
+  // The reverseIndex bytes beyond numChildren are initialized so that the
+  // SIMD loads of a full 16-byte page in scan16 are well-defined (reading
+  // indeterminate bytes is UB in C++). valgrind then treats them as undefined
+  // so that it can still flag any read that relies on them.
+  VALGRIND_MAKE_MEM_UNDEFINED(reverseIndex + numChildren,
+                              sizeof(reverseIndex) -
+                                  numChildren * sizeof(reverseIndex[0]));
 }
 
 inline void Node48::copyChildrenAndKeyFrom(const Node48 &other) {
@@ -594,6 +602,7 @@ inline void Node48::copyChildrenAndKeyFrom(const Node256 &other) {
   copyCommon(*this, other);
   memset(index, -1, sizeof(index));
   memset(children, 0, sizeof(children));
+  memset(reverseIndex, 0, sizeof(reverseIndex));
   const auto z = InternalVersionT::zero;
   for (auto &v : childMaxVersion) {
     v = z;
@@ -615,6 +624,13 @@ inline void Node48::copyChildrenAndKeyFrom(const Node256 &other) {
     ++i;
   });
   memcpy(partialKey(), &other + 1, partialKeyLen);
+  // The reverseIndex bytes beyond numChildren are initialized so that the
+  // SIMD loads of a full 16-byte page in scan16 are well-defined (reading
+  // indeterminate bytes is UB in C++). valgrind then treats them as undefined
+  // so that it can still flag any read that relies on them.
+  VALGRIND_MAKE_MEM_UNDEFINED(reverseIndex + numChildren,
+                              sizeof(reverseIndex) -
+                                  numChildren * sizeof(reverseIndex[0]));
 }
 
 inline void Node256::copyChildrenAndKeyFrom(const Node48 &other) {
@@ -2009,6 +2025,8 @@ Node *erase(Node *self, WriteContext *writeContext, bool logical) {
     parent48->childMaxVersion[lastChildrenIndex] = writeContext->zero;
     VALGRIND_MAKE_MEM_UNDEFINED(parent48->children + lastChildrenIndex,
                                 sizeof(parent48->children[0]));
+    VALGRIND_MAKE_MEM_UNDEFINED(parent48->reverseIndex + lastChildrenIndex,
+                                sizeof(parent48->reverseIndex[0]));
 
     if (needsDownsize(parent48)) {
       downsize(parent48, writeContext);