scudo: Obtain tag from pointer instead of loading it from memory. NFCI.

[pcc]

Summary

Since we already have a tagged pointer available to us, we can just
extract the tag from it and avoid an LDG instruction.

compiler-rt/lib/scudo/standalone/combined.h

#endif // GWP_ASAN_HOOKS
     if (UNLIKELY(&__scudo_deallocate_hook))
       __scudo_deallocate_hook(Ptr);
 
     if (UNLIKELY(!Ptr))
       return;
     if (UNLIKELY(!isAligned(reinterpret_cast<uptr>(Ptr), MinAlignment)))
       reportMisalignedPointer(AllocatorAction::Deallocating, Ptr);
 
+    void *TaggedPtr = Ptr;
     Ptr = getHeaderTaggedPointer(Ptr);
 
     Chunk::UnpackedHeader Header;
     Chunk::loadHeader(Cookie, Ptr, &Header);
 
     if (UNLIKELY(Header.State != Chunk::State::Allocated))
       reportInvalidChunkState(AllocatorAction::Deallocating, Ptr);
 
#endif // GWP_ASAN_HOOKS
     }
 
     const uptr Size = getSize(Ptr, &Header);
     if (DeleteSize && Options.get(OptionBit::DeleteSizeMismatch)) {
       if (UNLIKELY(DeleteSize != Size))
         reportDeleteSizeMismatch(Ptr, DeleteSize, Size);
     }
 
-    quarantineOrDeallocateChunk(Options, Ptr, &Header, Size);
+    quarantineOrDeallocateChunk(Options, TaggedPtr, &Header, Size);
   }
 
   void *reallocate(void *OldPtr, uptr NewSize, uptr Alignment = MinAlignment) {
     initThreadMaybe();
 
     const Options Options = Primary.Options.load();
     if (UNLIKELY(NewSize >= MaxAllowedMallocSize)) {
       if (Options.get(OptionBit::MayReturnNull))
#endif // GWP_ASAN_HOOKS
 
     // Otherwise we allocate a new one, and deallocate the old one. Some
     // allocators will allocate an even larger chunk (by a fixed factor) to
     // allow for potential further in-place realloc. The gains of such a trick
     // are currently unclear.
     void *NewPtr = allocate(NewSize, Chunk::Origin::Malloc, Alignment);
     if (LIKELY(NewPtr)) {
       memcpy(NewPtr, OldTaggedPtr, Min(NewSize, OldSize));
-      quarantineOrDeallocateChunk(Options, OldPtr, &OldHeader, OldSize);
+      quarantineOrDeallocateChunk(Options, OldTaggedPtr, &OldHeader, OldSize);
     }
     return NewPtr;
   }
 
   // TODO(kostyak): disable() is currently best-effort. There are some small
   //                windows of time when an allocation could still succeed after
   //                this function finishes. We will revisit that later.
   void disable() {
inline uptr getSize(const void *Ptr, Chunk::UnpackedHeader *Header) {
     if (LIKELY(Header->ClassId))
       return SizeOrUnusedBytes;
     if (allocatorSupportsMemoryTagging<Params>())
       Ptr = untagPointer(const_cast<void *>(Ptr));
     return SecondaryT::getBlockEnd(getBlockBegin(Ptr, Header)) -
            reinterpret_cast<uptr>(Ptr) - SizeOrUnusedBytes;
   }
 
-  void quarantineOrDeallocateChunk(Options Options, void *Ptr,
+  void quarantineOrDeallocateChunk(Options Options, void *TaggedPtr,
                                    Chunk::UnpackedHeader *Header, uptr Size) {
+    void *Ptr = getHeaderTaggedPointer(TaggedPtr);
     Chunk::UnpackedHeader NewHeader = *Header;
     if (UNLIKELY(useMemoryTagging<Params>(Options))) {
-      u8 PrevTag = 0;
+      u8 PrevTag = extractTag(reinterpret_cast<uptr>(TaggedPtr));
       if (NewHeader.ClassId) {
-        PrevTag = extractTag(loadTag(reinterpret_cast<uptr>(Ptr)));
         if (!TSDRegistry.getDisableMemInit()) {
           uptr TaggedBegin, TaggedEnd;
           const uptr OddEvenMask = computeOddEvenMaskForPointerMaybe(
               Options, reinterpret_cast<uptr>(getBlockBegin(Ptr, &NewHeader)),
               SizeClassMap::getSizeByClassId(NewHeader.ClassId));
           // Exclude the previous tag so that immediate use after free is
           // detected 100% of the time.
           setRandomTag(Ptr, Size, OddEvenMask | (1UL << PrevTag), &TaggedBegin,