// GOT slot is filled by the dynamic linker with the offset of the thread-local
	// symbol from the thread pointer (R13)).
	R_POWER_TLS_IE

	// R_POWER_TLS marks an X-form instruction such as "ADD R3,R13,R4" as completing
	// a sequence of GOT-relative relocations to compute a TLS address. This can be
	// used by the system linker to to rewrite the GOT-relative TLS relocation into a

	// faster than having the caller spill these.
	MOVQ	R12, 96(SP)
	MOVQ	R13, 104(SP)
retry:
	// TODO: Consider passing g.m.p in as an argument so they can be shared
	// across a sequence of write barriers.
	MOVQ	g_m(R14), R13
	MOVQ	m_p(R13), R13
	// Get current buffer write position.
	MOVQ	(p_wbBuf+wbBuf_next)(R13), R12	// original next position
	ADDQ	R11, R12			// new next position
	// Is the buffer full?

	rbx    uint64
	rcx    uint64
	rdx    uint64
	rdi    uint64
	rsi    uint64
	rbp    uint64
	rsp    uint64
	r8     uint64
	r9     uint64
	r10    uint64
	r11    uint64
	r12    uint64
	r13    uint64
	r14    uint64
	r15    uint64
	rip    uint64
	rflags uint64
	cs     uint64
	fs     uint64
	gs     uint64
}

type floatstate64 struct {
	fpu_reserved  [2]int32

	SizeofIovec           = 0x10
	SizeofMsghdr          = 0x38
	SizeofCmsghdr         = 0x10
)

const (
	SizeofSockFprog = 0x10
)

type PtraceRegs struct {
	R15      uint64
	R14      uint64
	R13      uint64
	R12      uint64
	Rbp      uint64
	Rbx      uint64
	R11      uint64
	R10      uint64
	R9       uint64
	R8       uint64
	Rax      uint64
	Rcx      uint64
	Rdx      uint64

#include "asm_ppc64x.h"

#ifdef GOOS_aix
#define cgoCalleeStackSize 48
#else
#define cgoCalleeStackSize 32
#endif

TEXT runtime·rt0_go(SB),NOSPLIT|TOPFRAME,$0
	// R1 = stack; R3 = argc; R4 = argv; R13 = C TLS base pointer

	// initialize essential registers
	BL	runtime·reginit(SB)

	SUB	$(FIXED_FRAME+16), R1
	MOVD	R2, 24(R1)		// stash the TOC pointer away again now we've created a new frame

// Round vars
#define rpState DI
#define rpStack SP

#define rDa BX
#define rDe CX
#define rDi DX
#define rDo R8
#define rDu R9

#define rBa R10
#define rBe R11
#define rBi R12
#define rBo R13
#define rBu R14

#define rCa SI
#define rCe BP
#define rCi rBi
#define rCo rBo
#define rCu R15

#define MOVQ_RBI_RCE MOVQ rBi, rCe
#define XORQ_RT1_RCA XORQ rT1, rCa
#define XORQ_RT1_RCE XORQ rT1, rCe

// A brief recap of the s390x C calling convention.
// Arguments are passed in R2...R6, the rest is on stack.
// Callee-saved registers are: R6...R13, R15.
// Temporary registers are: R0...R5, R14.

// When calling racecalladdr, R1 is the call target address.

// The race ctx, ThreadState *thr below, is passed in R2 and loaded in racecalladdr.

	"R0", // REGZERO, not used, but simplifies counting in regalloc
	"SP", // REGSP
	"SB", // REGSB
	"R3",
	"R4",
	"R5",
	"R6",
	"R7",
	"R8",
	"R9",
	"R10",
	"R11", // REGCTXT for closures
	"R12",
	"R13", // REGTLS
	"R14",
	"R15",
	"R16",
	"R17",
	"R18",
	"R19",
	"R20",
	"R21",
	"R22",
	"R23",
	"R24",
	"R25",
	"R26",
	"R27",
	"R28",
	"R29",

			ldr.Errorf(s, "R_POWER_TLS reloc only supports XO form ADD, not %08X", val)
		}
		// Verify RB is R13 in ADD RA,RB,RT.
		if (val>>11)&0x1F != 13 {
			// If external linking is made to support this, it may expect the linker to rewrite RB.
			ldr.Errorf(s, "R_POWER_TLS reloc requires R13 in RB (%08X).", uint32(val))
		}
		return val, nExtReloc, true

	case objabi.R_POWER_TLS_IE:

	MOVW	R3, 12(R29)
	MOVW	R4, 16(R29)
	MOVW	R5, 20(R29)
	MOVW	R6, 24(R29)
	MOVW	R7, 28(R29)
	MOVW	R8, 32(R29)
	MOVW	R9, 36(R29)
	MOVW	R10, 40(R29)
	MOVW	R11, 44(R29)
	MOVW	R12, 48(R29)
	MOVW	R13, 52(R29)
	MOVW	R14, 56(R29)
	MOVW	R15, 60(R29)
	MOVW	R16, 64(R29)
	MOVW	R17, 68(R29)
	MOVW	R18, 72(R29)
	MOVW	R19, 76(R29)
	MOVW	R20, 80(R29)
	// R21 already saved
	// R22 already saved.