TEXT	asancall<>(SB), NOSPLIT, $0-0
	MOVV	R3, R23         // callee-saved
	BEQ	g, g0stack      // no g, still on a system stack
	MOVV	g_m(g), R14
	MOVV	m_g0(R14), R15
	BEQ	R15, g, g0stack

	MOVV	(g_sched+gobuf_sp)(R15), R9
	MOVV	R9, R3

g0stack:
	JAL	(FARG)
	MOVV	R23, R3

	STP (R6, R7), 56(RSP)
	STP (R8, R9), 72(RSP)
	STP (R10, R11), 88(RSP)
	STP (R12, R13), 104(RSP)
	STP (R14, R15), 120(RSP)
	STP (R16, R17), 136(RSP)
	STP (R19, R20), 152(RSP)
	STP (R21, R22), 168(RSP)
	STP (R23, R24), 184(RSP)
	STP (R25, R26), 200(RSP)
	MOVD NZCV, R0
	MOVD R0, 216(RSP)
	MOVD FPSR, R0
	MOVD R0, 224(RSP)
	FSTPD (F0, F1), 232(RSP)
	FSTPD (F2, F3), 248(RSP)
	FSTPD (F4, F5), 264(RSP)

	STP	(R19, R20), ((offset)+0*8)(RSP) \
	STP	(R21, R22), ((offset)+2*8)(RSP) \
	STP	(R23, R24), ((offset)+4*8)(RSP) \
	STP	(R25, R26), ((offset)+6*8)(RSP) \
	STP	(R27, g), ((offset)+8*8)(RSP)

#define RESTORE_R19_TO_R28(offset) \
	LDP	((offset)+0*8)(RSP), (R19, R20) \
	LDP	((offset)+2*8)(RSP), (R21, R22) \
	LDP	((offset)+4*8)(RSP), (R23, R24) \
	LDP	((offset)+6*8)(RSP), (R25, R26) \
	LDP	((offset)+8*8)(RSP), (R27, g) /* R28 */

	MOVW	R2, 104(R29)
retry:
	MOVW	g_m(g), R1
	MOVW	m_p(R1), R1
	MOVW	(p_wbBuf+wbBuf_next)(R1), R2
	MOVW	(p_wbBuf+wbBuf_end)(R1), R23 // R23 is linker temp register
	// Increment wbBuf.next position.
	ADD	R25, R2
	// Is the buffer full?
	SGTU	R2, R23, R23
	BNE	R23, flush
	// Commit to the larger buffer.
	MOVW	R2, (p_wbBuf+wbBuf_next)(R1)
	// Make return value (the original next position)
	SUB	R25, R2, R25

	print("r18  ", hex(c.r18()), "\t")
	print("r19  ", hex(c.r19()), "\n")
	print("r20  ", hex(c.r20()), "\t")
	print("r21  ", hex(c.r21()), "\n")
	print("r22  ", hex(c.r22()), "\t")
	print("r23  ", hex(c.r23()), "\n")
	print("r24  ", hex(c.r24()), "\t")
	print("r25  ", hex(c.r25()), "\n")
	print("r26  ", hex(c.r26()), "\t")
	print("r27  ", hex(c.r27()), "\n")
	print("r28  ", hex(c.r28()), "\t")

TEXT	msancall<>(SB), NOSPLIT, $0-0
	MOVV	R3, R23         // callee-saved
	BEQ	g, g0stack      // no g, still on a system stack
	MOVV	g_m(g), R14
	MOVV	m_g0(R14), R15
	BEQ	R15, g, g0stack

	MOVV	(g_sched+gobuf_sp)(R15), R9
	MOVV	R9, R3

g0stack:
	JAL	(FARG)
	MOVV	R23, R3

//
// SAVE_F24_TO_F31(offset) saves F24 ~ F31 to the stack space
// of ((offset)+0*8)(R3) ~ ((offset)+7*8)(R3).
//
// Note: g is R22

#define SAVE_R22_TO_R31(offset)	\
	MOVV	g,   ((offset)+(0*8))(R3)	\
	MOVV	R23, ((offset)+(1*8))(R3)	\
	MOVV	R24, ((offset)+(2*8))(R3)	\
	MOVV	R25, ((offset)+(3*8))(R3)	\
	MOVV	R26, ((offset)+(4*8))(R3)	\
	MOVV	R27, ((offset)+(5*8))(R3)	\
	MOVV	R28, ((offset)+(6*8))(R3)	\

	MOVW	R7, (4*3)(R29)	// ctxt uintptr
	MOVW	R16, (4*4)(R29)
	MOVW	R17, (4*5)(R29)
	MOVW	R18, (4*6)(R29)
	MOVW	R19, (4*7)(R29)
	MOVW	R20, (4*8)(R29)
	MOVW	R21, (4*9)(R29)
	MOVW	R22, (4*10)(R29)
	MOVW	R23, (4*11)(R29)
	MOVW	g, (4*12)(R29)
	MOVW	R31, (4*13)(R29)
#ifndef GOMIPS_softfloat
	MOVD	F20, (4*14)(R29)
	MOVD	F22, (4*14+8*1)(R29)
	MOVD	F24, (4*14+8*2)(R29)
	MOVD	F26, (4*14+8*3)(R29)
	MOVD	F28, (4*14+8*4)(R29)

	MOVV 64(R29), R8
	MOVV 56(R29), R7
	MOVV 48(R29), R6
	MOVV 40(R29), R5
	MOVV 32(R29), R4
	MOVV 24(R29), R3
	MOVV 16(R29), R2
	MOVV 8(R29), R1
	MOVV 488(R29), R31
	MOVV (R29), R23
	ADDV $496, R29

	MSR	R14, PMEVCNTR29_EL0                // aeeb1bd5
	MSR	R23, PMEVCNTR30_EL0                // d7eb1bd5
	MRS	PMEVTYPER0_EL0, R23                // 17ec3bd5
	MRS	PMEVTYPER1_EL0, R30                // 3eec3bd5
	MRS	PMEVTYPER2_EL0, R12                // 4cec3bd5
	MRS	PMEVTYPER3_EL0, R13                // 6dec3bd5
	MRS	PMEVTYPER4_EL0, R25                // 99ec3bd5
	MRS	PMEVTYPER5_EL0, R23                // b7ec3bd5