[WebAssembly] Implement thread-local storage (local-exec model)

Summary:
Thread local variables are placed inside a `.tdata` segment. Their symbols are
offsets from the start of the segment. The address of a thread local variable
is computed as `__tls_base` + the offset from the start of the segment.

`.tdata` segment is a passive segment and `memory.init` is used once per thread
to initialize the thread local storage.

`__tls_base` is a wasm global. Since each thread has its own wasm instance,
it is effectively thread local. Currently, `__tls_base` must be initialized
at thread startup, and so cannot be used with dynamic libraries.

`__tls_base` is to be initialized with a new linker-synthesized function,
`__wasm_init_tls`, which takes as an argument a block of memory to use as the
storage for thread locals. It then initializes the block of memory and sets
`__tls_base`. As `__wasm_init_tls` will handle the memory initialization,
the memory does not have to be zeroed.

To help allocating memory for thread-local storage, a new compiler intrinsic
is introduced: `__builtin_wasm_tls_size()`. This instrinsic function returns
the size of the thread-local storage for the current function.

The expected usage is to run something like the following upon thread startup:

    __wasm_init_tls(malloc(__builtin_wasm_tls_size()));

Reviewers: tlively, aheejin, kripken, sbc100

Subscribers: dschuff, jgravelle-google, hiraditya, sunfish, jfb, cfe-commits, llvm-commits

Tags: #clang, #llvm

Differential Revision: https://reviews.llvm.org/D64537

llvm-svn: 366272

4 files changed, 74 insertions, 10 deletions

diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp
index 312b203859d..2552e915083 100644
--- 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
index bd699d92f76..1efbb3b067b 100644
--- 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
index 611f05f9496..288b991ae2c 100644
--- 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
index a75df34979b..7e65368e671 100644
--- a/llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp
@@ -186,13 +186,21 @@ public:
     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 @@ private:
         // "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]) {