diff --git a/lld/wasm/Writer.cpp b/lld/wasm/Writer.cpp
@@ -57,6 +57,7 @@ class Writer {
   void createInitMemoryFunction();
   void createApplyRelocationsFunction();
   void createCallCtorsFunction();
+  void createInitTLSFunction();
 
   void assignIndexes();
   void populateSymtab();
@@ -242,6 +243,11 @@ void Writer::layoutMemory() {
     log(formatv("mem: {0,-15} offset={1,-8} size={2,-8} align={3}", seg->name,
                 memoryPtr, seg->size, seg->alignment));
     memoryPtr += seg->size;
+
+    if (WasmSym::tlsSize && seg->name == ".tdata") {
+      auto *tlsSize = cast<DefinedGlobal>(WasmSym::tlsSize);
+      tlsSize->global->global.InitExpr.Value.Int32 = seg->size;
+    }
   }
 
   // TODO: Add .bss space here.
@@ -353,6 +359,7 @@ void Writer::populateTargetFeatures() {
   StringMap<std::string> used;
   StringMap<std::string> required;
   StringMap<std::string> disallowed;
+  bool tlsUsed = false;
 
   // Only infer used features if user did not specify features
   bool inferFeatures = !config->features.hasValue();
@@ -385,6 +392,14 @@ void Writer::populateTargetFeatures() {
               std::to_string(feature.Prefix));
       }
     }
+
+    for (InputSegment *segment : file->segments) {
+      if (!segment->live)
+        continue;
+      StringRef name = segment->getName();
+      if (name.startswith(".tdata") || name.startswith(".tbss"))
+        tlsUsed = true;
+    }
   }
 
   if (inferFeatures)
@@ -411,6 +426,10 @@ void Writer::populateTargetFeatures() {
     error("'bulk-memory' feature must be used in order to emit passive "
           "segments");
 
+  if (!used.count("bulk-memory") && tlsUsed)
+    error("'bulk-memory' feature must be used in order to use thread-local "
+          "storage");
+
   // Validate that used features are allowed in output
   if (!inferFeatures) {
     for (auto &feature : used.keys()) {
@@ -492,8 +511,8 @@ void Writer::calculateExports() {
       // implement in all major browsers.
       // See: https://github.com/WebAssembly/mutable-global
       if (g->getGlobalType()->Mutable) {
-        // Only the __stack_pointer should ever be create as mutable.
-        assert(g == WasmSym::stackPointer);
+        // Only __stack_pointer and __tls_base should ever be create as mutable.
+        assert(g == WasmSym::stackPointer || g == WasmSym::tlsBase);
         continue;
       }
       export_ = {name, WASM_EXTERNAL_GLOBAL, g->getGlobalIndex()};
@@ -602,6 +621,11 @@ static StringRef getOutputDataSegmentName(StringRef name) {
   // we only have a single __memory_base to use as our base address.
   if (config->isPic)
     return ".data";
+  // We only support one thread-local segment, so we must merge the segments
+  // despite --no-merge-data-segments.
+  // We also need to merge .tbss into .tdata so they share the same offsets.
+  if (name.startswith(".tdata") || name.startswith(".tbss"))
+    return ".tdata";
   if (!config->mergeDataSegments)
     return name;
   if (name.startswith(".text."))
@@ -625,7 +649,7 @@ void Writer::createOutputSegments() {
       if (s == nullptr) {
         LLVM_DEBUG(dbgs() << "new segment: " << name << "\n");
         s = make<OutputSegment>(name, segments.size());
-        if (config->passiveSegments)
+        if (config->passiveSegments || name == ".tdata")
           s->initFlags = WASM_SEGMENT_IS_PASSIVE;
         segments.push_back(s);
       }
@@ -655,7 +679,7 @@ void Writer::createInitMemoryFunction() {
 
     // initialize passive data segments
     for (const OutputSegment *s : segments) {
-      if (s->initFlags & WASM_SEGMENT_IS_PASSIVE) {
+      if (s->initFlags & WASM_SEGMENT_IS_PASSIVE && s->name != ".tdata") {
         // destination address
         writeU8(os, WASM_OPCODE_I32_CONST, "i32.const");
         writeSleb128(os, s->startVA, "destination address");
@@ -737,6 +761,49 @@ void Writer::createCallCtorsFunction() {
   createFunction(WasmSym::callCtors, bodyContent);
 }
 
+void Writer::createInitTLSFunction() {
+  if (!WasmSym::initTLS->isLive())
+    return;
+
+  std::string bodyContent;
+  {
+    raw_string_ostream os(bodyContent);
+
+    OutputSegment *tlsSeg = nullptr;
+    for (auto *seg : segments) {
+      if (seg->name == ".tdata")
+        tlsSeg = seg;
+      break;
+    }
+
+    writeUleb128(os, 0, "num locals");
+    if (tlsSeg) {
+      writeU8(os, WASM_OPCODE_LOCAL_GET, "local.get");
+      writeUleb128(os, 0, "local index");
+
+      writeU8(os, WASM_OPCODE_GLOBAL_SET, "global.set");
+      writeUleb128(os, WasmSym::tlsBase->getGlobalIndex(), "global index");
+
+      writeU8(os, WASM_OPCODE_LOCAL_GET, "local.get");
+      writeUleb128(os, 0, "local index");
+
+      writeU8(os, WASM_OPCODE_I32_CONST, "i32.const");
+      writeSleb128(os, 0, "segment offset");
+
+      writeU8(os, WASM_OPCODE_I32_CONST, "i32.const");
+      writeSleb128(os, tlsSeg->size, "memory region size");
+
+      writeU8(os, WASM_OPCODE_MISC_PREFIX, "bulk-memory prefix");
+      writeUleb128(os, WASM_OPCODE_MEMORY_INIT, "MEMORY.INIT");
+      writeUleb128(os, tlsSeg->index, "segment index immediate");
+      writeU8(os, 0, "memory index immediate");
+    }
+    writeU8(os, WASM_OPCODE_END, "end function");
+  }
+
+  createFunction(WasmSym::initTLS, bodyContent);
+}
+
 // Populate InitFunctions vector with init functions from all input objects.
 // This is then used either when creating the output linking section or to
 // synthesize the "__wasm_call_ctors" function.
@@ -829,6 +896,12 @@ void Writer::run() {
     createCallCtorsFunction();
   }
 
+  if (config->sharedMemory && !config->shared)
+    createInitTLSFunction();
+
+  if (errorCount())
+    return;
+
   log("-- calculateTypes");
   calculateTypes();
   log("-- calculateExports");

diff --git a/llvm/include/llvm/BinaryFormat/Wasm.h b/llvm/include/llvm/BinaryFormat/Wasm.h
@@ -242,7 +242,9 @@ enum : unsigned {
 enum : unsigned {
   WASM_OPCODE_END = 0x0b,
   WASM_OPCODE_CALL = 0x10,
+  WASM_OPCODE_LOCAL_GET = 0x20,
   WASM_OPCODE_GLOBAL_GET = 0x23,
+  WASM_OPCODE_GLOBAL_SET = 0x24,
   WASM_OPCODE_I32_STORE = 0x36,
   WASM_OPCODE_I32_CONST = 0x41,
   WASM_OPCODE_I64_CONST = 0x42,

diff --git a/llvm/include/llvm/IR/IntrinsicsWebAssembly.td b/llvm/include/llvm/IR/IntrinsicsWebAssembly.td
@@ -124,4 +124,13 @@ def int_wasm_data_drop :
             [llvm_i32_ty],
             [IntrNoDuplicate, IntrHasSideEffects, ImmArg<0>]>;
 
+//===----------------------------------------------------------------------===//
+// Thread-local storage intrinsics
+//===----------------------------------------------------------------------===//
+
+def int_wasm_tls_size :
+  Intrinsic<[llvm_anyint_ty],
+            [],
+            [IntrNoMem, IntrSpeculatable]>;
+
 } // TargetPrefix = "wasm"
diff --git a/llvm/include/llvm/MC/MCSectionWasm.h b/llvm/include/llvm/MC/MCSectionWasm.h
@@ -66,7 +66,8 @@ class MCSectionWasm final : public MCSection {
   bool isVirtualSection() const override;
 
   bool isWasmData() const {
-    return Kind.isGlobalWriteableData() || Kind.isReadOnly();
+    return Kind.isGlobalWriteableData() || Kind.isReadOnly() ||
+           Kind.isThreadLocal();
   }
 
   bool isUnique() const { return UniqueID != ~0U; }

diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp
@@ -233,6 +233,8 @@ bool WebAssemblyFastISel::computeAddress(const Value *Obj, Address &Addr) {
       return false;
     if (Addr.getGlobalValue())
       return false;
+    if (GV->isThreadLocal())
+      return false;
     Addr.setGlobalValue(GV);
     return true;
   }
@@ -614,6 +616,8 @@ unsigned WebAssemblyFastISel::fastMaterializeConstant(const Constant *C) {
   if (const GlobalValue *GV = dyn_cast<GlobalValue>(C)) {
     if (TLI.isPositionIndependent())
       return 0;
+    if (GV->isThreadLocal())
+      return 0;
     unsigned ResultReg =
         createResultReg(Subtarget->hasAddr64() ? &WebAssembly::I64RegClass
                                                : &WebAssembly::I32RegClass);

diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelDAGToDAG.cpp
@@ -15,6 +15,7 @@
 #include "WebAssembly.h"
 #include "WebAssemblyTargetMachine.h"
 #include "llvm/CodeGen/SelectionDAGISel.h"
+#include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/Function.h" // To access function attributes.
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/KnownBits.h"
@@ -171,6 +172,54 @@ void WebAssemblyDAGToDAGISel::Select(SDNode *Node) {
     }
   }
 
+  case ISD::GlobalTLSAddress: {
+    const auto *GA = cast<GlobalAddressSDNode>(Node);
+
+    if (!MF.getSubtarget<WebAssemblySubtarget>().hasBulkMemory())
+      report_fatal_error("cannot use thread-local storage without bulk memory",
+                         false);
+
+    if (GA->getGlobal()->getThreadLocalMode() !=
+        GlobalValue::LocalExecTLSModel) {
+      report_fatal_error("only -ftls-model=local-exec is supported for now",
+                         false);
+    }
+
+    MVT PtrVT = TLI->getPointerTy(CurDAG->getDataLayout());
+    assert(PtrVT == MVT::i32 && "only wasm32 is supported for now");
+
+    SDValue TLSBaseSym = CurDAG->getTargetExternalSymbol("__tls_base", PtrVT);
+    SDValue TLSOffsetSym = CurDAG->getTargetGlobalAddress(
+        GA->getGlobal(), DL, PtrVT, GA->getOffset(), 0);
+
+    MachineSDNode *TLSBase = CurDAG->getMachineNode(WebAssembly::GLOBAL_GET_I32,
+                                                    DL, MVT::i32, TLSBaseSym);
+    MachineSDNode *TLSOffset = CurDAG->getMachineNode(
+        WebAssembly::CONST_I32, DL, MVT::i32, TLSOffsetSym);
+    MachineSDNode *TLSAddress =
+        CurDAG->getMachineNode(WebAssembly::ADD_I32, DL, MVT::i32,
+                               SDValue(TLSBase, 0), SDValue(TLSOffset, 0));
+    ReplaceNode(Node, TLSAddress);
+    return;
+  }
+
+  case ISD::INTRINSIC_WO_CHAIN: {
+    unsigned IntNo = cast<ConstantSDNode>(Node->getOperand(0))->getZExtValue();
+    switch (IntNo) {
+    case Intrinsic::wasm_tls_size: {
+      MVT PtrVT = TLI->getPointerTy(CurDAG->getDataLayout());
+      assert(PtrVT == MVT::i32 && "only wasm32 is supported for now");
+
+      MachineSDNode *TLSSize = CurDAG->getMachineNode(
+          WebAssembly::GLOBAL_GET_I32, DL, PtrVT,
+          CurDAG->getTargetExternalSymbol("__tls_size", MVT::i32));
+      ReplaceNode(Node, TLSSize);
+      return;
+    }
+    }
+    break;
+  }
+
   default:
     break;
   }

diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyMCInstLower.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyMCInstLower.cpp
@@ -77,9 +77,11 @@ MCSymbol *WebAssemblyMCInstLower::GetExternalSymbolSymbol(
   // functions. It's OK to hardcode knowledge of specific symbols here; this
   // method is precisely there for fetching the signatures of known
   // Clang-provided symbols.
-  if (strcmp(Name, "__stack_pointer") == 0 ||
-      strcmp(Name, "__memory_base") == 0 || strcmp(Name, "__table_base") == 0) {
-    bool Mutable = strcmp(Name, "__stack_pointer") == 0;
+  if (strcmp(Name, "__stack_pointer") == 0 || strcmp(Name, "__tls_base") == 0 ||
+      strcmp(Name, "__memory_base") == 0 || strcmp(Name, "__table_base") == 0 ||
+      strcmp(Name, "__tls_size") == 0) {
+    bool Mutable =
+        strcmp(Name, "__stack_pointer") == 0 || strcmp(Name, "__tls_base") == 0;
     WasmSym->setType(wasm::WASM_SYMBOL_TYPE_GLOBAL);
     WasmSym->setGlobalType(wasm::WasmGlobalType{
         uint8_t(Subtarget.hasAddr64() ? wasm::WASM_TYPE_I64

diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp
@@ -186,13 +186,21 @@ class CoalesceFeaturesAndStripAtomics final : public ModulePass {
     for (auto &F : M)
       replaceFeatures(F, FeatureStr);
 
-    bool Stripped = false;
-    if (!Features[WebAssembly::FeatureAtomics]) {
-      Stripped |= stripAtomics(M);
-      Stripped |= stripThreadLocals(M);
-    }
+    bool StrippedAtomics = false;
+    bool StrippedTLS = false;
+
+    if (!Features[WebAssembly::FeatureAtomics])
+      StrippedAtomics = stripAtomics(M);
+
+    if (!Features[WebAssembly::FeatureBulkMemory])
+      StrippedTLS = stripThreadLocals(M);
+
+    if (StrippedAtomics && !StrippedTLS)
+      stripThreadLocals(M);
+    else if (StrippedTLS && !StrippedAtomics)
+      stripAtomics(M);
 
-    recordFeatures(M, Features, Stripped);
+    recordFeatures(M, Features, StrippedAtomics || StrippedTLS);
 
     // Conservatively assume we have made some change
     return true;
@@ -271,7 +279,8 @@ class CoalesceFeaturesAndStripAtomics final : public ModulePass {
         // "atomics" is special: code compiled without atomics may have had its
         // atomics lowered to nonatomic operations. In that case, atomics is
         // disallowed to prevent unsafe linking with atomics-enabled objects.
-        assert(!Features[WebAssembly::FeatureAtomics]);
+        assert(!Features[WebAssembly::FeatureAtomics] ||
+               !Features[WebAssembly::FeatureBulkMemory]);
         M.addModuleFlag(Module::ModFlagBehavior::Error, MDKey,
                         wasm::WASM_FEATURE_PREFIX_DISALLOWED);
       } else if (Features[KV.Value]) {

diff --git a/llvm/test/CodeGen/WebAssembly/target-features-tls.ll b/llvm/test/CodeGen/WebAssembly/target-features-tls.ll
@@ -1,5 +1,5 @@
-; RUN: llc < %s -mattr=-atomics | FileCheck %s --check-prefixes CHECK,NO-ATOMICS
-; RUN: llc < %s -mattr=+atomics | FileCheck %s --check-prefixes CHECK,ATOMICS
+; RUN: llc < %s -mattr=-bulk-memory | FileCheck %s --check-prefixes NO-BULK-MEM
+; RUN: llc < %s -mattr=+bulk-memory | FileCheck %s --check-prefixes BULK-MEM
 
 ; Test that the target features section contains -atomics or +atomics
 ; for modules that have thread local storage in their source.
@@ -9,18 +9,18 @@ target triple = "wasm32-unknown-unknown"
 
 @foo = internal thread_local global i32 0
 
-; CHECK-LABEL: .custom_section.target_features,"",@
+; -bulk-memory
+; NO-BULK-MEM-LABEL: .custom_section.target_features,"",@
+; NO-BULK-MEM-NEXT: .int8 1
+; NO-BULK-MEM-NEXT: .int8 45
+; NO-BULK-MEM-NEXT: .int8 7
+; NO-BULK-MEM-NEXT: .ascii "atomics"
+; NO-BULK-MEM-NEXT: .bss.foo,"",@
 
-; -atomics
-; NO-ATOMICS-NEXT: .int8 1
-; NO-ATOMICS-NEXT: .int8 45
-; NO-ATOMICS-NEXT: .int8 7
-; NO-ATOMICS-NEXT: .ascii "atomics"
-; NO-ATOMICS-NEXT: .bss.foo,"",@
-
-; +atomics
-; ATOMICS-NEXT: .int8 1
-; ATOMICS-NEXT: .int8 43
-; ATOMICS-NEXT: .int8 7
-; ATOMICS-NEXT: .ascii "atomics"
-; ATOMICS-NEXT: .tbss.foo,"",@
+; +bulk-memory
+; BULK-MEM-LABEL: .custom_section.target_features,"",@
+; BULK-MEM-NEXT: .int8 1
+; BULK-MEM-NEXT: .int8 43
+; BULK-MEM-NEXT: .int8 11
+; BULK-MEM-NEXT: .ascii "bulk-memory"
+; BULK-MEM-NEXT: .tbss.foo,"",@
diff --git a/llvm/test/CodeGen/WebAssembly/tls.ll b/llvm/test/CodeGen/WebAssembly/tls.ll
@@ -1,17 +1,82 @@
-; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers | FileCheck --check-prefix=SINGLE %s
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -mattr=+bulk-memory | FileCheck %s --check-prefixes=CHECK,TLS
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -mattr=+bulk-memory -fast-isel | FileCheck %s --check-prefixes=CHECK,TLS
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -mattr=-bulk-memory | FileCheck %s --check-prefixes=CHECK,NO-TLS
 target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
 target triple = "wasm32-unknown-unknown"
 
-; SINGLE-LABEL: address_of_tls:
+; CHECK-LABEL: address_of_tls:
+; CHECK-NEXT: .functype  address_of_tls () -> (i32)
 define i32 @address_of_tls() {
-  ; SINGLE: i32.const $push0=, tls
-  ; SINGLE-NEXT: return $pop0
+  ; TLS-DAG: global.get __tls_base
+  ; TLS-DAG: i32.const tls
+  ; TLS-NEXT: i32.add
+  ; TLS-NEXT: return
+
+  ; NO-TLS-NEXT: i32.const tls
+  ; NO-TLS-NEXT: return
   ret i32 ptrtoint(i32* @tls to i32)
 }
 
-; SINGLE: .type	tls,@object
-; SINGLE-NEXT: .section	.bss.tls,"",@
-; SINGLE-NEXT: .p2align 2
-; SINGLE-NEXT: tls:
-; SINGLE-NEXT: .int32 0
-@tls = internal thread_local global i32 0
+; CHECK-LABEL: ptr_to_tls:
+; CHECK-NEXT: .functype ptr_to_tls () -> (i32)
+define i32* @ptr_to_tls() {
+  ; TLS-DAG: global.get __tls_base
+  ; TLS-DAG: i32.const tls
+  ; TLS-NEXT: i32.add
+  ; TLS-NEXT: return
+
+  ; NO-TLS-NEXT: i32.const tls
+  ; NO-TLS-NEXT: return
+  ret i32* @tls
+}
+
+; CHECK-LABEL: tls_load:
+; CHECK-NEXT: .functype tls_load () -> (i32)
+define i32 @tls_load() {
+  ; TLS-DAG: global.get __tls_base
+  ; TLS-DAG: i32.const tls
+  ; TLS-NEXT: i32.add
+  ; TLS-NEXT: i32.load 0
+  ; TLS-NEXT: return
+
+  ; NO-TLS-NEXT: i32.const 0
+  ; NO-TLS-NEXT: i32.load tls
+  ; NO-TLS-NEXT: return
+  %tmp = load i32, i32* @tls, align 4
+  ret i32 %tmp
+}
+
+; CHECK-LABEL: tls_store:
+; CHECK-NEXT: .functype tls_store (i32) -> ()
+define void @tls_store(i32 %x) {
+  ; TLS-DAG: global.get __tls_base
+  ; TLS-DAG: i32.const tls
+  ; TLS-NEXT: i32.add
+  ; TLS-NEXT: i32.store 0
+  ; TLS-NEXT: return
+
+  ; NO-TLS-NEXT: i32.const 0
+  ; NO-TLS-NEXT: i32.store tls
+  ; NO-TLS-NEXT: return
+  store i32 %x, i32* @tls, align 4
+  ret void
+}
+
+; CHECK-LABEL: tls_size:
+; CHECK-NEXT: .functype tls_size () -> (i32)
+define i32 @tls_size() {
+; CHECK-NEXT: global.get __tls_size
+; CHECK-NEXT: return
+  %1 = call i32 @llvm.wasm.tls.size.i32()
+  ret i32 %1
+}
+
+; CHECK: .type tls,@object
+; TLS-NEXT: .section .tbss.tls,"",@
+; NO-TLS-NEXT: .section .bss.tls,"",@
+; CHECK-NEXT: .p2align 2
+; CHECK-NEXT: tls:
+; CHECK-NEXT: .int32 0
+@tls = internal thread_local(localexec) global i32 0
+
+declare i32 @llvm.wasm.tls.size.i32()