diff --git a/compiler-rt/lib/scudo/standalone/combined.h b/compiler-rt/lib/scudo/standalone/combined.h
--- a/compiler-rt/lib/scudo/standalone/combined.h
+++ b/compiler-rt/lib/scudo/standalone/combined.h
@@ -1103,6 +1103,50 @@
     return Offset + Chunk::getHeaderSize();
   }
 
+  void *prepareTaggedChunk(void *Ptr, uptr Size, uptr ExcludeMask,
+                           uptr BlockEnd) {
+    // Prepare the granule before the chunk to store the chunk header by setting
+    // its tag to 0. Normally its tag will already be 0, but in the case where a
+    // chunk holding a low alignment allocation is reused for a higher alignment
+    // allocation, the chunk may already have a non-zero tag from the previous
+    // allocation.
+    storeTag(reinterpret_cast<uptr>(Ptr) - archMemoryTagGranuleSize());
+
+    uptr TaggedBegin, TaggedEnd;
+    setRandomTag(Ptr, Size, ExcludeMask, &TaggedBegin, &TaggedEnd);
+
+    // Finally, set the tag of the granule past the end of the allocation to 0,
+    // to catch linear overflows even if a previous larger allocation used the
+    // same block and tag. Only do this if the granule past the end is in our
+    // block, because this would otherwise lead to a SEGV if the allocation
+    // covers the entire block and our block is at the end of a mapping. The tag
+    // of the next block's header granule will be set to 0, so it will serve the
+    // purpose of catching linear overflows in this case.
+    uptr UntaggedEnd = untagPointer(TaggedEnd);
+    if (UntaggedEnd != BlockEnd)
+      storeTag(UntaggedEnd);
+    return reinterpret_cast<void *>(TaggedBegin);
+  }
+
+  void resizeTaggedChunk(uptr OldPtr, uptr NewPtr, uptr BlockEnd) {
+    uptr RoundOldPtr = roundUpTo(OldPtr, archMemoryTagGranuleSize());
+    uptr RoundNewPtr;
+    if (RoundOldPtr >= NewPtr) {
+      // If the allocation is shrinking we just need to set the tag past the end
+      // of the allocation to 0. See explanation in prepareTaggedChunk above.
+      RoundNewPtr = roundUpTo(NewPtr, archMemoryTagGranuleSize());
+    } else {
+      // Set the memory tag of the region
+      // [RoundOldPtr, roundUpTo(NewPtr, archMemoryTagGranuleSize()))
+      // to the pointer tag stored in OldPtr.
+      RoundNewPtr = storeTags(RoundOldPtr, NewPtr);
+    }
+
+    uptr UntaggedNewPtr = untagPointer(RoundNewPtr);
+    if (UntaggedNewPtr != BlockEnd)
+      storeTag(UntaggedNewPtr);
+  }
+
   void storePrimaryAllocationStackMaybe(Options Options, void *Ptr) {
     if (!UNLIKELY(Options.get(OptionBit::TrackAllocationStacks)))
       return;
diff --git a/compiler-rt/lib/scudo/standalone/memtag.h b/compiler-rt/lib/scudo/standalone/memtag.h
--- a/compiler-rt/lib/scudo/standalone/memtag.h
+++ b/compiler-rt/lib/scudo/standalone/memtag.h
@@ -18,9 +18,6 @@
 
 namespace scudo {
 
-void setRandomTag(void *Ptr, uptr Size, uptr ExcludeMask, uptr *TaggedBegin,
-                  uptr *TaggedEnd);
-
 #if defined(__aarch64__) || defined(SCUDO_FUZZ)
 
 // We assume that Top-Byte Ignore is enabled if the architecture supports memory
@@ -214,84 +211,13 @@
   return Begin;
 }
 
-inline void *prepareTaggedChunk(void *Ptr, uptr Size, uptr ExcludeMask,
-                                uptr BlockEnd) {
-  // Prepare the granule before the chunk to store the chunk header by setting
-  // its tag to 0. Normally its tag will already be 0, but in the case where a
-  // chunk holding a low alignment allocation is reused for a higher alignment
-  // allocation, the chunk may already have a non-zero tag from the previous
-  // allocation.
-  __asm__ __volatile__(
-      R"(
-      .arch_extension memtag
-      stg %0, [%0, #-16]
-      )"
-      :
-      : "r"(Ptr)
-      : "memory");
-
-  uptr TaggedBegin, TaggedEnd;
-  setRandomTag(Ptr, Size, ExcludeMask, &TaggedBegin, &TaggedEnd);
-
-  // Finally, set the tag of the granule past the end of the allocation to 0,
-  // to catch linear overflows even if a previous larger allocation used the
-  // same block and tag. Only do this if the granule past the end is in our
-  // block, because this would otherwise lead to a SEGV if the allocation
-  // covers the entire block and our block is at the end of a mapping. The tag
-  // of the next block's header granule will be set to 0, so it will serve the
-  // purpose of catching linear overflows in this case.
-  uptr UntaggedEnd = untagPointer(TaggedEnd);
-  if (UntaggedEnd != BlockEnd)
-    __asm__ __volatile__(
-        R"(
-        .arch_extension memtag
-        stg %0, [%0]
-        )"
-        :
-        : "r"(UntaggedEnd)
-        : "memory");
-  return reinterpret_cast<void *>(TaggedBegin);
-}
-
-inline void resizeTaggedChunk(uptr OldPtr, uptr NewPtr, uptr BlockEnd) {
-  uptr RoundOldPtr = roundUpTo(OldPtr, 16);
-  if (RoundOldPtr >= NewPtr) {
-    // If the allocation is shrinking we just need to set the tag past the end
-    // of the allocation to 0. See explanation in prepareTaggedChunk above.
-    uptr RoundNewPtr = untagPointer(roundUpTo(NewPtr, 16));
-    if (RoundNewPtr != BlockEnd)
-      __asm__ __volatile__(
-          R"(
-          .arch_extension memtag
-          stg %0, [%0]
-          )"
-          :
-          : "r"(RoundNewPtr)
-          : "memory");
-    return;
-  }
-
+inline void storeTag(uptr Ptr) {
   __asm__ __volatile__(R"(
     .arch_extension memtag
-
-    // Set the memory tag of the region
-    // [roundUpTo(OldPtr, 16), roundUpTo(NewPtr, 16))
-    // to the pointer tag stored in OldPtr.
-  1:
-    stzg %[Cur], [%[Cur]], #16
-    cmp %[Cur], %[End]
-    b.lt 1b
-
-    // Finally, set the tag of the granule past the end of the allocation to 0.
-    and %[Cur], %[Cur], #(1 << 56) - 1
-    cmp %[Cur], %[BlockEnd]
-    b.eq 2f
-    stg %[Cur], [%[Cur]]
-
-  2:
+    stg %0, [%0]
   )"
-                       : [Cur] "+&r"(RoundOldPtr), [End] "+&r"(NewPtr)
-                       : [BlockEnd] "r"(BlockEnd)
+                       :
+                       : "r"(Ptr)
                        : "memory");
 }
 
@@ -348,19 +274,8 @@
   UNREACHABLE("memory tagging not supported");
 }
 
-inline void *prepareTaggedChunk(void *Ptr, uptr Size, uptr ExcludeMask,
-                                uptr BlockEnd) {
+inline void storeTag(uptr Ptr) {
   (void)Ptr;
-  (void)Size;
-  (void)ExcludeMask;
-  (void)BlockEnd;
-  UNREACHABLE("memory tagging not supported");
-}
-
-inline void resizeTaggedChunk(uptr OldPtr, uptr NewPtr, uptr BlockEnd) {
-  (void)OldPtr;
-  (void)NewPtr;
-  (void)BlockEnd;
   UNREACHABLE("memory tagging not supported");
 }