cmd/compile: request r12 for indirect calls on ppc64le

On ppc64le, functions compiled with -shared expect r12 to
hold the function's address for indirect calls. Previously
this was enforced by generating a move instruction if the
address wasn't already in r12. This change avoids that extra
move by requesting r12 in the CALL ops that do indirect calls.

As a result of adding support for plugins on ppc64le, it was
discovered that there would be more cases where this extra
move was needed, so this seemed like a better solution.

Updates #20756

Change-Id: I6770885a46990f78c6d2902a715dcdaa822192a1
Reviewed-on: https://go-review.googlesource.com/62890
Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: David Crawshaw <crawshaw@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>

src/cmd/compile/internal/ppc64/ssa.go

@@ -1088,17 +1088,8 @@ func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
 		p.To.Type = obj.TYPE_REG
 		p.To.Reg = ppc64.REG_CTR
 
-		if gc.Ctxt.Flag_shared && p.From.Reg != ppc64.REG_R12 {
-			// Make sure function pointer is in R12 as well when
-			// compiling Go into PIC.
-			// TODO(mwhudson): it would obviously be better to
-			// change the register allocation to put the value in
-			// R12 already, but I don't know how to do that.
-			// TODO: We have the technology now to implement TODO above.
-			q := s.Prog(ppc64.AMOVD)
-			q.From = p.From
-			q.To.Type = obj.TYPE_REG
-			q.To.Reg = ppc64.REG_R12
+		if v.Args[0].Reg() != ppc64.REG_R12 {
+			v.Fatalf("Function address for %v should be in R12 %d but is in %d", v.LongString(), ppc64.REG_R12, p.From.Reg)
 		}
 
 		pp := s.Call(v)

src/cmd/compile/internal/ssa/gen/PPC64Ops.go

@@ -130,6 +130,7 @@ func init() {
 		// lr  = buildReg("LR")
 		tmp     = buildReg("R31")
 		ctxt    = buildReg("R11")
+		callptr = buildReg("R12")
 		// tls = buildReg("R13")
 		gp01        = regInfo{inputs: nil, outputs: []regMask{gp}}
 		gp11        = regInfo{inputs: []regMask{gp | sp | sb}, outputs: []regMask{gp}}
@@ -320,8 +321,8 @@ func init() {
 		{name: "MOVDconvert", argLength: 2, reg: gp11, asm: "MOVD"},
 
 		{name: "CALLstatic", argLength: 1, reg: regInfo{clobbers: callerSave}, aux: "SymOff", clobberFlags: true, call: true, symEffect: "None"},                   // call static function aux.(*obj.LSym).  arg0=mem, auxint=argsize, returns mem
-		{name: "CALLclosure", argLength: 3, reg: regInfo{inputs: []regMask{gp | sp, ctxt, 0}, clobbers: callerSave}, aux: "Int64", clobberFlags: true, call: true}, // call function via closure.  arg0=codeptr, arg1=closure, arg2=mem, auxint=argsize, returns mem
-		{name: "CALLinter", argLength: 2, reg: regInfo{inputs: []regMask{gp}, clobbers: callerSave}, aux: "Int64", clobberFlags: true, call: true},                 // call fn by pointer.  arg0=codeptr, arg1=mem, auxint=argsize, returns mem
+		{name: "CALLclosure", argLength: 3, reg: regInfo{inputs: []regMask{callptr, ctxt, 0}, clobbers: callerSave}, aux: "Int64", clobberFlags: true, call: true}, // call function via closure.  arg0=codeptr, arg1=closure, arg2=mem, auxint=argsize, returns mem
+		{name: "CALLinter", argLength: 2, reg: regInfo{inputs: []regMask{callptr}, clobbers: callerSave}, aux: "Int64", clobberFlags: true, call: true},            // call fn by pointer.  arg0=codeptr, arg1=mem, auxint=argsize, returns mem
 
 		// large or unaligned zeroing
 		// arg0 = address of memory to zero (in R3, changed as side effect)

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

@@ -18004,8 +18004,8 @@ var opcodeTable = [...]opInfo{
 		call:         true,
 		reg: regInfo{
 			inputs: []inputInfo{
+				{0, 4096}, // R12
 				{1, 2048}, // R11
-				{0, 1073733626}, // SP R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R14 R15 R16 R17 R18 R19 R20 R21 R22 R23 R24 R25 R26 R27 R28 R29
 			},
 			clobbers: 576460745860964344, // R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R14 R15 R16 R17 R18 R19 R20 R21 R22 R23 R24 R25 R26 R27 R28 R29 g 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
 		},
@@ -18018,7 +18018,7 @@ var opcodeTable = [...]opInfo{
 		call:         true,
 		reg: regInfo{
 			inputs: []inputInfo{
-				{0, 1073733624}, // R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R14 R15 R16 R17 R18 R19 R20 R21 R22 R23 R24 R25 R26 R27 R28 R29
+				{0, 4096}, // R12
 			},
 			clobbers: 576460745860964344, // R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R14 R15 R16 R17 R18 R19 R20 R21 R22 R23 R24 R25 R26 R27 R28 R29 g 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
 		},

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

@@ -562,12 +562,6 @@ func (s *regAllocState) init(f *Func) {
 	if s.f.Config.ctxt.Framepointer_enabled && s.f.Config.FPReg >= 0 {
 		s.allocatable &^= 1 << uint(s.f.Config.FPReg)
 	}
-	if s.f.Config.ctxt.Flag_shared {
-		switch s.f.Config.arch {
-		case "ppc64le": // R2 already reserved.
-			s.allocatable &^= 1 << 12 // R12
-		}
-	}
 	if s.f.Config.LinkReg != -1 {
 		if isLeaf(f) {
 			// Leaf functions don't save/restore the link register.
@@ -587,7 +581,7 @@ func (s *regAllocState) init(f *Func) {
 		case "arm":
 			s.allocatable &^= 1 << 9 // R9
 		case "ppc64le": // R2 already reserved.
-			s.allocatable &^= 1 << 12 // R12
+			// nothing to do
 		case "arm64":
 			// nothing to do?
 		case "386":