cmd/compile: move arm64 over to new bounds check strategy

For all the static bounds checks in cmd/go, we have:

    6877    just a single instruction (the call itself)
    139     needs an additional reg-reg move
    602     needs an additional constant load
    25      needs some other instruction

that's ~90% implemented using just a single instruction.

Reduces the text size of cmd/go by ~0.8%.
Total binary size is just barely smaller, ~0.2%. (The difference
is the new pcdata table.)

Change-Id: I416e9c196f5d8d0e8f08e191e6df3045e11dccbe
Reviewed-on: https://go-review.googlesource.com/c/go/+/682496
LUCI-TryBot-Result: Go LUCI <[email protected]>
Reviewed-by: David Chase <[email protected]>
Reviewed-by: Michael Knyszek <[email protected]>

Author: randall77

src/cmd/compile/internal/arm64/ssa.go

@@ -16,6 +16,7 @@ import (
 	"cmd/compile/internal/types"
 	"cmd/internal/obj"
 	"cmd/internal/obj/arm64"
+	"internal/abi"
 )
 
 // loadByType returns the load instruction of the given type.
@@ -1122,12 +1123,91 @@ func ssaGenValue(s *ssagen.State, v *ssa.Value) {
 		// AuxInt encodes how many buffer entries we need.
 		p.To.Sym = ir.Syms.GCWriteBarrier[v.AuxInt-1]
 
-	case ssa.OpARM64LoweredPanicBoundsA, ssa.OpARM64LoweredPanicBoundsB, ssa.OpARM64LoweredPanicBoundsC:
-		p := s.Prog(obj.ACALL)
+	case ssa.OpARM64LoweredPanicBoundsRR, ssa.OpARM64LoweredPanicBoundsRC, ssa.OpARM64LoweredPanicBoundsCR, ssa.OpARM64LoweredPanicBoundsCC:
+		// Compute the constant we put in the PCData entry for this call.
+		code, signed := ssa.BoundsKind(v.AuxInt).Code()
+		xIsReg := false
+		yIsReg := false
+		xVal := 0
+		yVal := 0
+		switch v.Op {
+		case ssa.OpARM64LoweredPanicBoundsRR:
+			xIsReg = true
+			xVal = int(v.Args[0].Reg() - arm64.REG_R0)
+			yIsReg = true
+			yVal = int(v.Args[1].Reg() - arm64.REG_R0)
+		case ssa.OpARM64LoweredPanicBoundsRC:
+			xIsReg = true
+			xVal = int(v.Args[0].Reg() - arm64.REG_R0)
+			c := v.Aux.(ssa.PanicBoundsC).C
+			if c >= 0 && c <= abi.BoundsMaxConst {
+				yVal = int(c)
+			} else {
+				// Move constant to a register
+				yIsReg = true
+				if yVal == xVal {
+					yVal = 1
+				}
+				p := s.Prog(arm64.AMOVD)
+				p.From.Type = obj.TYPE_CONST
+				p.From.Offset = c
+				p.To.Type = obj.TYPE_REG
+				p.To.Reg = arm64.REG_R0 + int16(yVal)
+			}
+		case ssa.OpARM64LoweredPanicBoundsCR:
+			yIsReg = true
+			yVal := int(v.Args[0].Reg() - arm64.REG_R0)
+			c := v.Aux.(ssa.PanicBoundsC).C
+			if c >= 0 && c <= abi.BoundsMaxConst {
+				xVal = int(c)
+			} else {
+				// Move constant to a register
+				if xVal == yVal {
+					xVal = 1
+				}
+				p := s.Prog(arm64.AMOVD)
+				p.From.Type = obj.TYPE_CONST
+				p.From.Offset = c
+				p.To.Type = obj.TYPE_REG
+				p.To.Reg = arm64.REG_R0 + int16(xVal)
+			}
+		case ssa.OpARM64LoweredPanicBoundsCC:
+			c := v.Aux.(ssa.PanicBoundsCC).Cx
+			if c >= 0 && c <= abi.BoundsMaxConst {
+				xVal = int(c)
+			} else {
+				// Move constant to a register
+				xIsReg = true
+				p := s.Prog(arm64.AMOVD)
+				p.From.Type = obj.TYPE_CONST
+				p.From.Offset = c
+				p.To.Type = obj.TYPE_REG
+				p.To.Reg = arm64.REG_R0 + int16(xVal)
+			}
+			c = v.Aux.(ssa.PanicBoundsCC).Cy
+			if c >= 0 && c <= abi.BoundsMaxConst {
+				yVal = int(c)
+			} else {
+				// Move constant to a register
+				yIsReg = true
+				yVal = 1
+				p := s.Prog(arm64.AMOVD)
+				p.From.Type = obj.TYPE_CONST
+				p.From.Offset = c
+				p.To.Type = obj.TYPE_REG
+				p.To.Reg = arm64.REG_R0 + int16(yVal)
+			}
+		}
+		c := abi.BoundsEncode(code, signed, xIsReg, yIsReg, xVal, yVal)
+
+		p := s.Prog(obj.APCDATA)
+		p.From.SetConst(abi.PCDATA_PanicBounds)
+		p.To.SetConst(int64(c))
+		p = s.Prog(obj.ACALL)
 		p.To.Type = obj.TYPE_MEM
 		p.To.Name = obj.NAME_EXTERN
-		p.To.Sym = ssagen.BoundsCheckFunc[v.AuxInt]
-		s.UseArgs(16) // space used in callee args area by assembly stubs
+		p.To.Sym = ir.Syms.PanicBounds
+
 	case ssa.OpARM64LoweredNilCheck:
 		// Issue a load which will fault if arg is nil.
 		p := s.Prog(arm64.AMOVB)

src/cmd/compile/internal/ssa/_gen/ARM64.rules

@@ -601,9 +601,11 @@
 // Publication barrier (0xe is ST option)
 (PubBarrier mem) => (DMB [0xe] mem)
 
-(PanicBounds [kind] x y mem) && boundsABI(kind) == 0 => (LoweredPanicBoundsA [kind] x y mem)
-(PanicBounds [kind] x y mem) && boundsABI(kind) == 1 => (LoweredPanicBoundsB [kind] x y mem)
-(PanicBounds [kind] x y mem) && boundsABI(kind) == 2 => (LoweredPanicBoundsC [kind] x y mem)
+(PanicBounds ...) => (LoweredPanicBoundsRR ...)
+(LoweredPanicBoundsRR [kind] x (MOVDconst [c]) mem) => (LoweredPanicBoundsRC [kind] x {PanicBoundsC{C:c}} mem)
+(LoweredPanicBoundsRR [kind] (MOVDconst [c]) y mem) => (LoweredPanicBoundsCR [kind] {PanicBoundsC{C:c}} y mem)
+(LoweredPanicBoundsRC [kind] {p} (MOVDconst [c]) mem) => (LoweredPanicBoundsCC [kind] {PanicBoundsCC{Cx:c, Cy:p.C}} mem)
+(LoweredPanicBoundsCR [kind] {p} (MOVDconst [c]) mem) => (LoweredPanicBoundsCC [kind] {PanicBoundsCC{Cx:p.C, Cy:c}} mem)
 
 // Optimizations
 

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

@@ -144,11 +144,8 @@ func init() {
 		gpspsbg    = gpspg | buildReg("SB")
 		fp         = buildReg("F0 F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13 F14 F15 F16 F17 F18 F19 F20 F21 F22 F23 F24 F25 F26 F27 F28 F29 F30 F31")
 		callerSave = gp | fp | buildReg("g") // runtime.setg (and anything calling it) may clobber g
-		r0         = buildReg("R0")
-		r1         = buildReg("R1")
-		r2         = buildReg("R2")
-		r3         = buildReg("R3")
 		rz         = buildReg("ZERO")
+		first16    = buildReg("R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15")
 	)
 	// Common regInfo
 	var (
@@ -760,12 +757,15 @@ func init() {
 		// Returns a pointer to a write barrier buffer in R25.
 		{name: "LoweredWB", argLength: 1, reg: regInfo{clobbers: (callerSave &^ gpg) | buildReg("R16 R17 R30"), outputs: []regMask{buildReg("R25")}}, clobberFlags: true, aux: "Int64"},
 
-		// There are three of these functions so that they can have three different register inputs.
-		// When we check 0 <= c <= cap (A), then 0 <= b <= c (B), then 0 <= a <= b (C), we want the
-		// default registers to match so we don't need to copy registers around unnecessarily.
-		{name: "LoweredPanicBoundsA", argLength: 3, aux: "Int64", reg: regInfo{inputs: []regMask{r2, r3}}, typ: "Mem", call: true}, // arg0=idx, arg1=len, arg2=mem, returns memory. AuxInt contains report code (see PanicBounds in generic.go).
-		{name: "LoweredPanicBoundsB", argLength: 3, aux: "Int64", reg: regInfo{inputs: []regMask{r1, r2}}, typ: "Mem", call: true}, // arg0=idx, arg1=len, arg2=mem, returns memory. AuxInt contains report code (see PanicBounds in generic.go).
-		{name: "LoweredPanicBoundsC", argLength: 3, aux: "Int64", reg: regInfo{inputs: []regMask{r0, r1}}, typ: "Mem", call: true}, // arg0=idx, arg1=len, arg2=mem, returns memory. AuxInt contains report code (see PanicBounds in generic.go).
+		// LoweredPanicBoundsRR takes x and y, two values that caused a bounds check to fail.
+		// the RC and CR versions are used when one of the arguments is a constant. CC is used
+		// when both are constant (normally both 0, as prove derives the fact that a [0] bounds
+		// failure means the length must have also been 0).
+		// AuxInt contains a report code (see PanicBounds in genericOps.go).
+		{name: "LoweredPanicBoundsRR", argLength: 3, aux: "Int64", reg: regInfo{inputs: []regMask{first16, first16}}, typ: "Mem", call: true}, // arg0=x, arg1=y, arg2=mem, returns memory.
+		{name: "LoweredPanicBoundsRC", argLength: 2, aux: "PanicBoundsC", reg: regInfo{inputs: []regMask{first16}}, typ: "Mem", call: true},   // arg0=x, arg1=mem, returns memory.
+		{name: "LoweredPanicBoundsCR", argLength: 2, aux: "PanicBoundsC", reg: regInfo{inputs: []regMask{first16}}, typ: "Mem", call: true},   // arg0=y, arg1=mem, returns memory.
+		{name: "LoweredPanicBoundsCC", argLength: 1, aux: "PanicBoundsCC", reg: regInfo{}, typ: "Mem", call: true},                            // arg0=mem, returns memory.
 
 		// Prefetch instruction
 		// Do prefetch arg0 address with option aux. arg0=addr, arg1=memory, aux=option.