#include "funcdata.h"
#include "textflag.h"

// If !iscgo, this is a no-op.
// NOTE: gogo assumes load_g only clobers g (R30) and REGTMP (R23)
TEXT runtime·save_g(SB),NOSPLIT|NOFRAME,$0-0
	MOVB	runtime·iscgo(SB), R23
	BEQ	R23, nocgo

	MOVW	R3, R23
	MOVW	g, runtime·tls_g(SB) // TLS relocation clobbers R3
	MOVW	R23, R3

nocgo:
	RET

TEXT runtime·load_g(SB),NOSPLIT|NOFRAME,$0-0
	MOVW	runtime·tls_g(SB), g // TLS relocation clobbers R3

				{1, 670826495}, // R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15 R16 R17 R19 R20 R21 R22 R23 R24 R25 R26 R30
			},
			outputs: []outputInfo{
				{1, 0},
				{0, 670826495}, // R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15 R16 R17 R19 R20 R21 R22 R23 R24 R25 R26 R30
			},
		},
	},
	{

	MOVV	mp+16(FP), R23
	MOVV	gp+24(FP), R24
	MOVV	fn+32(FP), R25

	MOVV	R23, -8(R5)
	MOVV	R24, -16(R5)
	MOVV	R25, -24(R5)
	MOVV	$1234, R23
	MOVV	R23, -32(R5)

	MOVV	$SYS_clone, R11
	SYSCALL

	// In parent, return.
	BEQ	R4, 3(PC)
	MOVW	R4, ret+40(FP)
	RET

	// In child, on new stack.
	MOVV	-32(R3), R23
	MOVV	$1234, R19
	BEQ	R23, R19, 2(PC)

	MOVD    24(R8), R22       // R22 = x[i+2]
	MOVDU   32(R8), R23       // R23 = x[i+3]
	MULLD   R9, R20, R24      // R24 = z0[i]
	MULHDU  R9, R20, R20      // R20 = z1[i]
	ADDC    R4, R24           // R24 = z0[i] + c
	MULLD   R9, R21, R25
	MULHDU  R9, R21, R21
	ADDE    R20, R25
	MULLD   R9, R22, R26
	MULHDU  R9, R22, R22
	MULLD   R9, R23, R27
	MULHDU  R9, R23, R23
	ADDE    R21, R26
	MOVD    R24, 8(R10)       // z[i]

 *
 * Calling into the gc tool chain, where all registers are caller save.
 * Called from standard lp64d ABI, where $r1, $r3, $r23-$r30, and $f24-$f31
 * are callee-save, so they must be saved explicitly, along with $r1 (LR).
 */
.globl crosscall1
crosscall1:
	addi.d	$r3, $r3, -160
	st.d	$r1, $r3, 0
	st.d	$r23, $r3, 8
	st.d	$r24, $r3, 16
	st.d	$r25, $r3, 24
	st.d	$r26, $r3, 32
	st.d	$r27, $r3, 40
	st.d	$r28, $r3, 48

	BIC R12@>13, R12, R19                      // 9335ec8a
	BICSW R25->20, R3, R20                     // 7450b96a
	BICS R19->12, R1, R23                      // 3730b3ea
	BICS R19, R1, R23                          // 370033ea
	BICS R19>>0, R1, R23                       // 370073ea
	CALL -1(PC)                                // ffffff97
	CALL (R15)                                 // e0013fd6

	// Find the offset to those bytes
	SUB R5, R22, R22
	SLD $3, R22

	// Shift to get only the bytes in msg
	SRD R22, R17, R17

	// Put 1 at high end
	MOVD $1, R23
	SLD  $3, R21
	SLD  R21, R23, R23
	OR   R23, R17, R17

	// Remainder is 8
	MOVD $8, R5

just1:
	CMP R5, $8
	BLT less8

	// Exactly 8
	MOVD (R4), R16

	CMP R17, $0

	MOVV	R2, 192(R29)
retry:
	MOVV	g_m(g), R1
	MOVV	m_p(R1), R1
	MOVV	(p_wbBuf+wbBuf_next)(R1), R2
	MOVV	(p_wbBuf+wbBuf_end)(R1), R23 // R23 is linker temp register
	// Increment wbBuf.next position.
	ADDV	R25, R2
	// Is the buffer full?
	SGTU	R2, R23, R23
	BNE	R23, flush
	// Commit to the larger buffer.
	MOVV	R2, (p_wbBuf+wbBuf_next)(R1)
	// Make return value (the original next position)
	SUBV	R25, R2, R25

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

	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