diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp
--- a/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp
@@ -297,9 +297,26 @@
                                                     SDValue &Addr) {
   assert(N.getNumOperands() == 2 && "Attempting to fold in a non-binary op");
 
-  // WebAssembly constant offsets are performed as unsigned with infinite
-  // precision, so we need to check for NoUnsignedWrap so that we don't fold an
-  // offset for an add that needs wrapping.
+  // Fold target global addresses in an add into the offset.
+  if (!TM.isPositionIndependent()) {
+    for (size_t i = 0; i < 2; ++i) {
+      SDValue Op = N.getOperand(i);
+      SDValue OtherOp = N.getOperand(i == 0 ? 1 : 0);
+
+      if (Op.getOpcode() == WebAssemblyISD::Wrapper)
+        Op = Op.getOperand(0);
+
+      if (Op.getOpcode() == ISD::TargetGlobalAddress) {
+        Offset = Op;
+        Addr = OtherOp;
+        return true;
+      }
+    }
+  }
+
+  // WebAssembly constant offsets are performed as unsigned with
+  // infinite precision, so we need to check for NoUnsignedWrap so
+  // that we don't fold an offset for an add that needs wrapping.
   if (N.getOpcode() == ISD::ADD && !N.getNode()->getFlags().hasNoUnsignedWrap())
     return false;
 
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyRegisterInfo.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyRegisterInfo.cpp
--- a/llvm/lib/Target/WebAssembly/WebAssemblyRegisterInfo.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyRegisterInfo.cpp
@@ -75,14 +75,19 @@
   if (AddrOperandNum == FIOperandNum) {
     unsigned OffsetOperandNum = WebAssembly::getNamedOperandIdx(
         MI.getOpcode(), WebAssembly::OpName::off);
-    assert(FrameOffset >= 0 && MI.getOperand(OffsetOperandNum).getImm() >= 0);
-    int64_t Offset = MI.getOperand(OffsetOperandNum).getImm() + FrameOffset;
-
-    if (static_cast<uint64_t>(Offset) <= std::numeric_limits<uint32_t>::max()) {
-      MI.getOperand(OffsetOperandNum).setImm(Offset);
-      MI.getOperand(FIOperandNum)
-          .ChangeToRegister(FrameRegister, /*isDef=*/false);
-      return false;
+    auto &OffsetOp = MI.getOperand(OffsetOperandNum);
+    // Don't fold offset in if offset is a global address to be resolved later
+    if (OffsetOp.isImm()) {
+      assert(FrameOffset >= 0 && OffsetOp.getImm() >= 0);
+      int64_t Offset = OffsetOp.getImm() + FrameOffset;
+
+      if (static_cast<uint64_t>(Offset) <=
+          std::numeric_limits<uint32_t>::max()) {
+        OffsetOp.setImm(Offset);
+        MI.getOperand(FIOperandNum)
+            .ChangeToRegister(FrameRegister, /*isDef=*/false);
+        return false;
+      }
     }
   }
 
diff --git a/llvm/test/CodeGen/WebAssembly/offset.ll b/llvm/test/CodeGen/WebAssembly/offset.ll
--- a/llvm/test/CodeGen/WebAssembly/offset.ll
+++ b/llvm/test/CodeGen/WebAssembly/offset.ll
@@ -666,3 +666,29 @@
 define {i64,i32,i16,i8} @aggregate_return_without_merge() {
   ret {i64,i32,i16,i8} zeroinitializer
 }
+
+;===----------------------------------------------------------------------------
+; Global address loads
+;===----------------------------------------------------------------------------
+
+@global_i32 = external global i32
+@global_i8 = external global i8
+
+; CHECK-LABEL: load_i32_global_address_with_folded_offset:
+; CHECK: i32.const $push0=, 2
+; CHECK: i32.shl $push1=, $0, $pop0
+; CHECK: i32.load $push2=, global_i32($pop1)
+define i32 @load_i32_global_address_with_folded_offset(i32 %n) {
+  %s = getelementptr inbounds i32, i32* @global_i32, i32 %n
+  %t = load i32, i32* %s
+  ret i32 %t
+}
+
+; CHECK-LABEL: load_i8_i32s_global_address_with_folded_offset:
+; CHECK: i32.load8_s $push0=, global_i8($0)
+define i32 @load_i8_i32s_global_address_with_folded_offset(i32 %n) {
+  %s = getelementptr inbounds i8, i8* @global_i8, i32 %n
+  %t = load i8, i8* %s
+  %u = sext i8 %t to i32
+  ret i32 %u
+}
diff --git a/llvm/test/CodeGen/WebAssembly/userstack.ll b/llvm/test/CodeGen/WebAssembly/userstack.ll
--- a/llvm/test/CodeGen/WebAssembly/userstack.ll
+++ b/llvm/test/CodeGen/WebAssembly/userstack.ll
@@ -329,9 +329,10 @@
 
 ; We optimize the format of "frame offset + operand" by folding it, but this is
 ; only possible when that operand is an immediate. In this example it is a
-; global address, so we should not fold it.
+; global address, so we should fold the global address into the offset, but not
+; the frame offset.
 ; CHECK-LABEL: frame_offset_with_global_address
-; CHECK: i[[PTR]].const ${{.*}}=, str
+; CHECK: i32.load8_u ${{.*}}=, str({{.*}})
 @str = local_unnamed_addr global [3 x i8] c"abc", align 16
 define i8 @frame_offset_with_global_address() {
   %1 = alloca i8, align 4