cmd/compile: mark architecture-specific unsafe points

Introduce a mechanism for marking architecture-specific Ops
unsafe. And mark ones that use REGTMP on ARM64, as for async
preemption we will be using REGTMP as a temporary register in the
injected call.

Change-Id: I8ff22e87d8f9cb10d02a2f0af7c12ad6d7d58f54
Reviewed-on: https://go-review.googlesource.com/c/go/+/203459
Run-TryBot: Cherry Zhang <[email protected]>
Reviewed-by: Austin Clements <[email protected]>

src/cmd/compile/internal/gc/plive.go

@@ -639,6 +639,15 @@ func (lv *Liveness) markUnsafePoints() {
 
 	lv.unsafePoints = bvalloc(int32(lv.f.NumValues()))
 
+	// Mark architecture-specific unsafe pointes.
+	for _, b := range lv.f.Blocks {
+		for _, v := range b.Values {
+			if v.Op.UnsafePoint() {
+				lv.unsafePoints.Set(int32(v.ID))
+			}
+		}
+	}
+
 	// Mark write barrier unsafe points.
 	for _, wbBlock := range lv.f.WBLoads {
 		if wbBlock.Kind == ssa.BlockPlain && len(wbBlock.Values) == 0 {

src/cmd/compile/internal/ssa/gen/ARM64Ops.go

@@ -620,17 +620,17 @@ func init() {
 		// LDAXR	(Rarg0), Rout
 		// STLXR	Rarg1, (Rarg0), Rtmp
 		// CBNZ		Rtmp, -2(PC)
-		{name: "LoweredAtomicExchange64", argLength: 3, reg: gpxchg, resultNotInArgs: true, faultOnNilArg0: true, hasSideEffects: true},
-		{name: "LoweredAtomicExchange32", argLength: 3, reg: gpxchg, resultNotInArgs: true, faultOnNilArg0: true, hasSideEffects: true},
+		{name: "LoweredAtomicExchange64", argLength: 3, reg: gpxchg, resultNotInArgs: true, faultOnNilArg0: true, hasSideEffects: true, unsafePoint: true},
+		{name: "LoweredAtomicExchange32", argLength: 3, reg: gpxchg, resultNotInArgs: true, faultOnNilArg0: true, hasSideEffects: true, unsafePoint: true},
 
 		// atomic add.
 		// *arg0 += arg1. arg2=mem. returns <new content of *arg0, memory>. auxint must be zero.
 		// LDAXR	(Rarg0), Rout
 		// ADD		Rarg1, Rout
 		// STLXR	Rout, (Rarg0), Rtmp
 		// CBNZ		Rtmp, -3(PC)
-		{name: "LoweredAtomicAdd64", argLength: 3, reg: gpxchg, resultNotInArgs: true, faultOnNilArg0: true, hasSideEffects: true},
-		{name: "LoweredAtomicAdd32", argLength: 3, reg: gpxchg, resultNotInArgs: true, faultOnNilArg0: true, hasSideEffects: true},
+		{name: "LoweredAtomicAdd64", argLength: 3, reg: gpxchg, resultNotInArgs: true, faultOnNilArg0: true, hasSideEffects: true, unsafePoint: true},
+		{name: "LoweredAtomicAdd32", argLength: 3, reg: gpxchg, resultNotInArgs: true, faultOnNilArg0: true, hasSideEffects: true, unsafePoint: true},
 
 		// atomic add variant.
 		// *arg0 += arg1. arg2=mem. returns <new content of *arg0, memory>. auxint must be zero.
@@ -653,17 +653,17 @@ func init() {
 		// STLXR	Rarg2, (Rarg0), Rtmp
 		// CBNZ		Rtmp, -4(PC)
 		// CSET		EQ, Rout
-		{name: "LoweredAtomicCas64", argLength: 4, reg: gpcas, resultNotInArgs: true, clobberFlags: true, faultOnNilArg0: true, hasSideEffects: true},
-		{name: "LoweredAtomicCas32", argLength: 4, reg: gpcas, resultNotInArgs: true, clobberFlags: true, faultOnNilArg0: true, hasSideEffects: true},
+		{name: "LoweredAtomicCas64", argLength: 4, reg: gpcas, resultNotInArgs: true, clobberFlags: true, faultOnNilArg0: true, hasSideEffects: true, unsafePoint: true},
+		{name: "LoweredAtomicCas32", argLength: 4, reg: gpcas, resultNotInArgs: true, clobberFlags: true, faultOnNilArg0: true, hasSideEffects: true, unsafePoint: true},
 
 		// atomic and/or.
 		// *arg0 &= (|=) arg1. arg2=mem. returns <new content of *arg0, memory>. auxint must be zero.
 		// LDAXRB	(Rarg0), Rout
 		// AND/OR	Rarg1, Rout
 		// STLXRB	Rout, (Rarg0), Rtmp
 		// CBNZ		Rtmp, -3(PC)
-		{name: "LoweredAtomicAnd8", argLength: 3, reg: gpxchg, resultNotInArgs: true, asm: "AND", typ: "(UInt8,Mem)", faultOnNilArg0: true, hasSideEffects: true},
-		{name: "LoweredAtomicOr8", argLength: 3, reg: gpxchg, resultNotInArgs: true, asm: "ORR", typ: "(UInt8,Mem)", faultOnNilArg0: true, hasSideEffects: true},
+		{name: "LoweredAtomicAnd8", argLength: 3, reg: gpxchg, resultNotInArgs: true, asm: "AND", typ: "(UInt8,Mem)", faultOnNilArg0: true, hasSideEffects: true, unsafePoint: true},
+		{name: "LoweredAtomicOr8", argLength: 3, reg: gpxchg, resultNotInArgs: true, asm: "ORR", typ: "(UInt8,Mem)", faultOnNilArg0: true, hasSideEffects: true, unsafePoint: true},
 
 		// LoweredWB invokes runtime.gcWriteBarrier. arg0=destptr, arg1=srcptr, arg2=mem, aux=runtime.gcWriteBarrier
 		// It saves all GP registers if necessary,

src/cmd/compile/internal/ssa/gen/main.go

@@ -63,6 +63,7 @@ type opData struct {
 	usesScratch       bool   // this op requires scratch memory space
 	hasSideEffects    bool   // for "reasons", not to be eliminated.  E.g., atomic store, #19182.
 	zeroWidth         bool   // op never translates into any machine code. example: copy, which may sometimes translate to machine code, is not zero-width.
+	unsafePoint       bool   // this op is an unsafe point, i.e. not safe for async preemption
 	symEffect         string // effect this op has on symbol in aux
 	scale             uint8  // amd64/386 indexed load scale
 }
@@ -325,6 +326,9 @@ func genOp() {
 			if v.zeroWidth {
 				fmt.Fprintln(w, "zeroWidth: true,")
 			}
+			if v.unsafePoint {
+				fmt.Fprintln(w, "unsafePoint: true,")
+			}
 			needEffect := strings.HasPrefix(v.aux, "Sym")
 			if v.symEffect != "" {
 				if !needEffect {
@@ -401,6 +405,7 @@ func genOp() {
 
 	fmt.Fprintln(w, "func (o Op) SymEffect() SymEffect { return opcodeTable[o].symEffect }")
 	fmt.Fprintln(w, "func (o Op) IsCall() bool { return opcodeTable[o].call }")
+	fmt.Fprintln(w, "func (o Op) UnsafePoint() bool { return opcodeTable[o].unsafePoint }")
 
 	// generate registers
 	for _, a := range archs {

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

@@ -36,6 +36,7 @@ type opInfo struct {
 	usesScratch       bool      // this op requires scratch memory space
 	hasSideEffects    bool      // for "reasons", not to be eliminated.  E.g., atomic store, #19182.
 	zeroWidth         bool      // op never translates into any machine code. example: copy, which may sometimes translate to machine code, is not zero-width.
+	unsafePoint       bool      // this op is an unsafe point, i.e. not safe for async preemption
 	symEffect         SymEffect // effect this op has on symbol in aux
 	scale             uint8     // amd64/386 indexed load scale
 }