cmd/compile/internal/devirtualize: improve concrete type analysis

src/cmd/compile/internal/inline/interleaved/interleaved.go

@@ -45,6 +45,8 @@ func DevirtualizeAndInlinePackage(pkg *ir.Package, profile *pgoir.Profile) {
 	inlState := make(map[*ir.Func]*inlClosureState)
 	calleeUseCounts := make(map[*ir.Func]int)
 
+	var state devirtualize.State
+
 	// Pre-process all the functions, adding parentheses around call sites and starting their "inl state".
 	for _, fn := range typecheck.Target.Funcs {
 		bigCaller := base.Flag.LowerL != 0 && inline.IsBigFunc(fn)
@@ -58,7 +60,7 @@ func DevirtualizeAndInlinePackage(pkg *ir.Package, profile *pgoir.Profile) {
 
 		// Do a first pass at counting call sites.
 		for i := range s.parens {
-			s.resolve(i)
+			s.resolve(&state, i)
 		}
 	}
 
@@ -102,10 +104,11 @@ func DevirtualizeAndInlinePackage(pkg *ir.Package, profile *pgoir.Profile) {
 					for {
 						for i := l0; i < l1; i++ { // can't use "range parens" here
 							paren := s.parens[i]
-							if new := s.edit(i); new != nil {
+							if origCall, inlinedCall := s.edit(&state, i); inlinedCall != nil {
 								// Update AST and recursively mark nodes.
-								paren.X = new
-								ir.EditChildren(new, s.mark) // mark may append to parens
+								paren.X = inlinedCall
+								ir.EditChildren(inlinedCall, s.mark) // mark may append to parens
+								state.InlinedCall(s.fn, origCall, inlinedCall)
 								done = false
 							}
 						}
@@ -114,7 +117,7 @@ func DevirtualizeAndInlinePackage(pkg *ir.Package, profile *pgoir.Profile) {
 							break
 						}
 						for i := l0; i < l1; i++ {
-							s.resolve(i)
+							s.resolve(&state, i)
 						}
 
 					}
@@ -188,7 +191,7 @@ type inlClosureState struct {
 // resolve attempts to resolve a call to a potentially inlineable callee
 // and updates use counts on the callees.  Returns the call site count
 // for that callee.
-func (s *inlClosureState) resolve(i int) (*ir.Func, int) {
+func (s *inlClosureState) resolve(state *devirtualize.State, i int) (*ir.Func, int) {
 	p := s.parens[i]
 	if i < len(s.resolved) {
 		if callee := s.resolved[i]; callee != nil {
@@ -200,7 +203,7 @@ func (s *inlClosureState) resolve(i int) (*ir.Func, int) {
 	if !ok { // previously inlined
 		return nil, -1
 	}
-	devirtualize.StaticCall(call)
+	devirtualize.StaticCall(state, call)
 	if callee := inline.InlineCallTarget(s.fn, call, s.profile); callee != nil {
 		for len(s.resolved) <= i {
 			s.resolved = append(s.resolved, nil)
@@ -213,23 +216,23 @@ func (s *inlClosureState) resolve(i int) (*ir.Func, int) {
 	return nil, 0
 }
 
-func (s *inlClosureState) edit(i int) ir.Node {
+func (s *inlClosureState) edit(state *devirtualize.State, i int) (*ir.CallExpr, *ir.InlinedCallExpr) {
 	n := s.parens[i].X
 	call, ok := n.(*ir.CallExpr)
 	if !ok {
-		return nil
+		return nil, nil
 	}
 	// This is redundant with earlier calls to
 	// resolve, but because things can change it
 	// must be re-checked.
-	callee, count := s.resolve(i)
+	callee, count := s.resolve(state, i)
 	if count <= 0 {
-		return nil
+		return nil, nil
 	}
 	if inlCall := inline.TryInlineCall(s.fn, call, s.bigCaller, s.profile, count == 1 && callee.ClosureParent != nil); inlCall != nil {
-		return inlCall
+		return call, inlCall
 	}
-	return nil
+	return nil, nil
 }
 
 // Mark inserts parentheses, and is called repeatedly.
@@ -338,16 +341,18 @@ func (s *inlClosureState) unparenthesize() {
 // returns.
 func (s *inlClosureState) fixpoint() bool {
 	changed := false
+	var state devirtualize.State
 	ir.WithFunc(s.fn, func() {
 		done := false
 		for !done {
 			done = true
 			for i := 0; i < len(s.parens); i++ { // can't use "range parens" here
 				paren := s.parens[i]
-				if new := s.edit(i); new != nil {
+				if origCall, inlinedCall := s.edit(&state, i); inlinedCall != nil {
 					// Update AST and recursively mark nodes.
-					paren.X = new
-					ir.EditChildren(new, s.mark) // mark may append to parens
+					paren.X = inlinedCall
+					ir.EditChildren(inlinedCall, s.mark) // mark may append to parens
+					state.InlinedCall(s.fn, origCall, inlinedCall)
 					done = false
 					changed = true
 				}

src/cmd/compile/internal/ir/expr.go

@@ -677,6 +677,11 @@ type TypeAssertExpr struct {
 
 	// An internal/abi.TypeAssert descriptor to pass to the runtime.
 	Descriptor *obj.LSym
+
+	// When set to true, if this assert would panic, then use a nil pointer panic
+	// instead of an interface conversion panic.
+	// It must not be set for type asserts using the commaok form.
+	UseNilPanic bool
 }
 
 func NewTypeAssertExpr(pos src.XPos, x Node, typ *types.Type) *TypeAssertExpr {

src/cmd/compile/internal/noder/reader.go

@@ -2941,6 +2941,7 @@ func (r *reader) multiExpr() []ir.Node {
 		as.Def = true
 		for i := range results {
 			tmp := r.temp(pos, r.typ())
+			tmp.Defn = as
 			as.PtrInit().Append(ir.NewDecl(pos, ir.ODCL, tmp))
 			as.Lhs.Append(tmp)
 

src/cmd/compile/internal/ssagen/ssa.go

@@ -5625,6 +5625,25 @@ func (s *state) dottype(n *ir.TypeAssertExpr, commaok bool) (res, resok *ssa.Val
 	if n.ITab != nil {
 		targetItab = s.expr(n.ITab)
 	}
+
+	if n.UseNilPanic {
+		if commaok {
+			base.Fatalf("unexpected *ir.TypeAssertExpr with UseNilPanic == true && commaok == true")
+		}
+		if n.Type().IsInterface() {
+			// Currently we do not expect the compiler to emit type asserts with UseNilPanic, that assert to an interface type.
+			// If needed, this can be relaxed in the future, but for now we can assert that.
+			base.Fatalf("unexpected *ir.TypeAssertExpr with UseNilPanic == true && Type().IsInterface() == true")
+		}
+		typs := s.f.Config.Types
+		iface = s.newValue2(
+			ssa.OpIMake,
+			iface.Type,
+			s.nilCheck(s.newValue1(ssa.OpITab, typs.BytePtr, iface)),
+			s.newValue1(ssa.OpIData, typs.BytePtr, iface),
+		)
+	}
+
 	return s.dottype1(n.Pos(), n.X.Type(), n.Type(), iface, nil, target, targetItab, commaok, n.Descriptor)
 }
 

src/crypto/sha256/sha256_test.go

@@ -391,3 +391,17 @@ func BenchmarkHash1K(b *testing.B) {
 func BenchmarkHash8K(b *testing.B) {
 	benchmarkSize(b, 8192)
 }
+
+func TestAllocatonsWithTypeAsserts(t *testing.T) {
+	cryptotest.SkipTestAllocations(t)
+	allocs := testing.AllocsPerRun(100, func() {
+		h := New()
+		h.Write([]byte{1, 2, 3})
+		marshaled, _ := h.(encoding.BinaryMarshaler).MarshalBinary()
+		marshaled, _ = h.(encoding.BinaryAppender).AppendBinary(marshaled[:0])
+		h.(encoding.BinaryUnmarshaler).UnmarshalBinary(marshaled)
+	})
+	if allocs != 0 {
+		t.Fatalf("allocs = %v; want = 0", allocs)
+	}
+}

src/runtime/pprof/pprof_test.go

@@ -348,6 +348,11 @@ func (h inlineWrapper) dump(pcs []uintptr) {
 
 func inlinedWrapperCallerDump(pcs []uintptr) {
 	var h inlineWrapperInterface
+
+	// Take the address of h, such that h.dump() call (below)
+	// does not get devirtualized by the compiler.
+	_ = &h
+
 	h = &inlineWrapper{}
 	h.dump(pcs)
 }