/* Relocatable DOL copier for netboot_launch().
 *
 * WHY THIS EXISTS IN ASSEMBLY, IN ITS OWN FILE:
 * a DOL's sections load over the memory this program is running from (the
 * standard load address is 0x80003100, right where our own .text sits), so a
 * copier compiled as an ordinary C function would overwrite its own
 * instructions partway through the copy and hang the console.  This routine is
 * copied into a reserved region at the top of MEM1 and executed THERE, so the
 * image cannot touch it.
 *
 * It must therefore be strictly position independent: no globals, no literal
 * pool, no TOC references, no calls.  Only PC-relative branches and
 * register-relative loads.  Anything else silently reads from the address it
 * was LINKED at rather than the one it is RUNNING at.
 *
 * r3 = descriptor, in the same reserved region:
 *   0x00  entry point
 *   0x04  stack pointer to hand the new image
 *   0x08  section count
 *   0x0C  bss address
 *   0x10  bss length
 *   0x14  section count * (src, dst, len)
 */
	.text
	.globl nb_stub
	.globl nb_stub_end
	.align 2

nb_stub:
	/* ---- copy every section ---- */
	lwz	4, 8(3)			/* nsec */
	addi	5, 3, 0x14		/* -> first (src,dst,len) */
1:	cmpwi	4, 0
	beq	3f
	lwz	6, 0(5)			/* src */
	lwz	7, 4(5)			/* dst */
	lwz	8, 8(5)			/* len */
	cmpwi	8, 0
	beq	2f
	mtctr	8
4:	lbz	9, 0(6)
	stb	9, 0(7)
	addi	6, 6, 1
	addi	7, 7, 1
	bdnz	4b
2:	addi	5, 5, 12
	addi	4, 4, -1
	b	1b

3:	/* ---- zero BSS ---- */
	lwz	7, 0xC(3)
	lwz	8, 0x10(3)
	cmpwi	8, 0
	beq	6f
	li	9, 0
	mtctr	8
5:	stb	9, 0(7)
	addi	7, 7, 1
	bdnz	5b

6:	/* ---- make the copies visible to the instruction fetcher ----
	 * Flush each destination out of the data cache and invalidate the
	 * matching instruction-cache lines.  Without this the CPU happily
	 * executes stale instructions from icache at the entry point. */
	lwz	4, 8(3)
	addi	5, 3, 0x14
7:	cmpwi	4, 0
	beq	9f
	lwz	7, 4(5)
	lwz	8, 8(5)
	cmpwi	8, 0
	beq	8f
	addi	8, 8, 31		/* round up to whole 32-byte lines */
	srwi	8, 8, 5
	mtctr	8
10:	dcbf	0, 7
	icbi	0, 7
	addi	7, 7, 32
	bdnz	10b
8:	addi	5, 5, 12
	addi	4, 4, -1
	b	7b

9:	sync
	isync
	lwz	1, 4(3)			/* stack for the new image */
	lwz	9, 0(3)			/* entry */
	mtlr	9
	li	3, 0
	li	4, 0
	li	5, 0
	blr

nb_stub_end: