/*
   * Copyright (C) Paul Mackerras 1997.
   *
   * Adapted for 64 bit LE PowerPC by Andrew Tauferner
   *
   * This program is free software; you can redistribute it and/or
   * modify it under the terms of the GNU General Public License
   * as published by the Free Software Foundation; either version
   * 2 of the License, or (at your option) any later version.
   *
   */
  
  #include "ppc_asm.h"
  
  RELA = 7
  RELACOUNT = 0x6ffffff9
  
  	.text
  	/* A procedure descriptor used when booting this as a COFF file.
  	 * When making COFF, this comes first in the link and we're
  	 * linked at 0x500000.
  	 */
  	.globl	_zimage_start_opd
  _zimage_start_opd:
  	.long	0x500000, 0, 0, 0
  
  #ifdef __powerpc64__
  .balign 8
  p_start:	.llong	_start
  p_etext:	.llong	_etext
  p_bss_start:	.llong	__bss_start
  p_end:		.llong	_end
  
  p_toc:		.llong	__toc_start + 0x8000 - p_base
  p_dyn:		.llong	__dynamic_start - p_base
  p_rela:		.llong	__rela_dyn_start - p_base
  p_prom:		.llong	0
  	.weak	_platform_stack_top
  p_pstack:	.llong	_platform_stack_top
  #else
  p_start:	.long	_start
  p_etext:	.long	_etext
  p_bss_start:	.long	__bss_start
  p_end:		.long	_end
  
  	.weak	_platform_stack_top
  p_pstack:	.long	_platform_stack_top
  #endif
  
  	.weak	_zimage_start
  	.globl	_zimage_start
  _zimage_start:
  	.globl	_zimage_start_lib
  _zimage_start_lib:
  	/* Work out the offset between the address we were linked at
  	   and the address where we're running. */
  	bl	.+4
  p_base:	mflr	r10		/* r10 now points to runtime addr of p_base */
  #ifndef __powerpc64__
  	/* grab the link address of the dynamic section in r11 */
  	addis	r11,r10,(_GLOBAL_OFFSET_TABLE_-p_base)@ha
  	lwz	r11,(_GLOBAL_OFFSET_TABLE_-p_base)@l(r11)
  	cmpwi	r11,0
  	beq	3f		/* if not linked -pie */
  	/* get the runtime address of the dynamic section in r12 */
  	.weak	__dynamic_start
  	addis	r12,r10,(__dynamic_start-p_base)@ha
  	addi	r12,r12,(__dynamic_start-p_base)@l
  	subf	r11,r11,r12	/* runtime - linktime offset */
  
  	/* The dynamic section contains a series of tagged entries.
  	 * We need the RELA and RELACOUNT entries. */
  	li	r9,0
  	li	r0,0
  9:	lwz	r8,0(r12)	/* get tag */
  	cmpwi	r8,0
  	beq	10f		/* end of list */
  	cmpwi	r8,RELA
  	bne	11f
  	lwz	r9,4(r12)	/* get RELA pointer in r9 */
  	b	12f
  11:	addis	r8,r8,(-RELACOUNT)@ha
  	cmpwi	r8,RELACOUNT@l
  	bne	12f
  	lwz	r0,4(r12)	/* get RELACOUNT value in r0 */
  12:	addi	r12,r12,8
  	b	9b
  
  	/* The relocation section contains a list of relocations.
  	 * We now do the R_PPC_RELATIVE ones, which point to words
  	 * which need to be initialized with addend + offset.
  	 * The R_PPC_RELATIVE ones come first and there are RELACOUNT
  	 * of them. */
  10:	/* skip relocation if we don't have both */
  	cmpwi	r0,0
  	beq	3f
  	cmpwi	r9,0
  	beq	3f
  
  	add	r9,r9,r11	/* Relocate RELA pointer */
  	mtctr	r0
  2:	lbz	r0,4+3(r9)	/* ELF32_R_INFO(reloc->r_info) */
  	cmpwi	r0,22		/* R_PPC_RELATIVE */
  	bne	3f
  	lwz	r12,0(r9)	/* reloc->r_offset */
  	lwz	r0,8(r9)	/* reloc->r_addend */
  	add	r0,r0,r11
  	stwx	r0,r11,r12
  	addi	r9,r9,12
  	bdnz	2b
  
  	/* Do a cache flush for our text, in case the loader didn't */
  3:	lwz	r9,p_start-p_base(r10)	/* note: these are relocated now */
  	lwz	r8,p_etext-p_base(r10)
  4:	dcbf	r0,r9
  	icbi	r0,r9
  	addi	r9,r9,0x20
  	cmplw	cr0,r9,r8
  	blt	4b
  	sync
  	isync
  
  	/* Clear the BSS */
  	lwz	r9,p_bss_start-p_base(r10)
  	lwz	r8,p_end-p_base(r10)
  	li	r0,0
  5:	stw	r0,0(r9)
  	addi	r9,r9,4
  	cmplw	cr0,r9,r8
  	blt	5b
  
  	/* Possibly set up a custom stack */
  	lwz	r8,p_pstack-p_base(r10)
  	cmpwi	r8,0
  	beq	6f
  	lwz	r1,0(r8)
  	li	r0,0
  	stwu	r0,-16(r1)	/* establish a stack frame */
  6:
  #else /* __powerpc64__ */
  	/* Save the prom pointer at p_prom. */
  	std	r5,(p_prom-p_base)(r10)
  
  	/* Set r2 to the TOC. */
  	ld	r2,(p_toc-p_base)(r10)
  	add	r2,r2,r10
  
  	/* Grab the link address of the dynamic section in r11. */
  	ld	r11,-32768(r2)
  	cmpwi	r11,0
  	beq	3f              /* if not linked -pie then no dynamic section */
  
  	ld	r11,(p_dyn-p_base)(r10)
  	add	r11,r11,r10
  	ld	r9,(p_rela-p_base)(r10)
  	add	r9,r9,r10
  
  	li	r13,0
  	li	r8,0
  9:	ld	r12,0(r11)       /* get tag */
  	cmpdi	r12,0
  	beq	12f              /* end of list */
  	cmpdi	r12,RELA
  	bne	10f
  	ld	r13,8(r11)       /* get RELA pointer in r13 */
  	b	11f
  10:	addis	r12,r12,(-RELACOUNT)@ha
  	cmpdi	r12,RELACOUNT@l
  	bne	11f
  	ld	r8,8(r11)       /* get RELACOUNT value in r8 */
  11:	addi	r11,r11,16
  	b	9b
  12:
  	cmpdi	r13,0            /* check we have both RELA and RELACOUNT */
  	cmpdi	cr1,r8,0
  	beq	3f
  	beq	cr1,3f
  
  	/* Calcuate the runtime offset. */
  	subf	r13,r13,r9
  
  	/* Run through the list of relocations and process the
  	 * R_PPC64_RELATIVE ones. */
  	mtctr	r8
  13:	ld	r0,8(r9)        /* ELF64_R_TYPE(reloc->r_info) */
  	cmpdi	r0,22           /* R_PPC64_RELATIVE */
  	bne	3f
  	ld	r12,0(r9)        /* reloc->r_offset */
  	ld	r0,16(r9)       /* reloc->r_addend */
  	add	r0,r0,r13
  	stdx	r0,r13,r12
  	addi	r9,r9,24
  	bdnz	13b
  
  	/* Do a cache flush for our text, in case the loader didn't */
  3:	ld	r9,p_start-p_base(r10)	/* note: these are relocated now */
  	ld	r8,p_etext-p_base(r10)
  4:	dcbf	r0,r9
  	icbi	r0,r9
  	addi	r9,r9,0x20
  	cmpld	cr0,r9,r8
  	blt	4b
  	sync
  	isync
  
  	/* Clear the BSS */
  	ld	r9,p_bss_start-p_base(r10)
  	ld	r8,p_end-p_base(r10)
  	li	r0,0
  5:	std	r0,0(r9)
  	addi	r9,r9,8
  	cmpld	cr0,r9,r8
  	blt	5b
  
  	/* Possibly set up a custom stack */
  	ld	r8,p_pstack-p_base(r10)
  	cmpdi	r8,0
  	beq	6f
  	ld	r1,0(r8)
  	li	r0,0
  	stdu	r0,-112(r1)	/* establish a stack frame */
  6:
  #endif  /* __powerpc64__ */
  	/* Call platform_init() */
  	bl	platform_init
  
  	/* Call start */
  	b	start
  
  #ifdef __powerpc64__
  
  #define PROM_FRAME_SIZE 512
  #define SAVE_GPR(n, base)       std     n,8*(n)(base)
  #define REST_GPR(n, base)       ld      n,8*(n)(base)
  #define SAVE_2GPRS(n, base)     SAVE_GPR(n, base); SAVE_GPR(n+1, base)
  #define SAVE_4GPRS(n, base)     SAVE_2GPRS(n, base); SAVE_2GPRS(n+2, base)
  #define SAVE_8GPRS(n, base)     SAVE_4GPRS(n, base); SAVE_4GPRS(n+4, base)
  #define SAVE_10GPRS(n, base)    SAVE_8GPRS(n, base); SAVE_2GPRS(n+8, base)
  #define REST_2GPRS(n, base)     REST_GPR(n, base); REST_GPR(n+1, base)
  #define REST_4GPRS(n, base)     REST_2GPRS(n, base); REST_2GPRS(n+2, base)
  #define REST_8GPRS(n, base)     REST_4GPRS(n, base); REST_4GPRS(n+4, base)
  #define REST_10GPRS(n, base)    REST_8GPRS(n, base); REST_2GPRS(n+8, base)
  
  /* prom handles the jump into and return from firmware.  The prom args pointer
     is loaded in r3. */
  .globl prom
  prom:
  	mflr	r0
  	std	r0,16(r1)
  	stdu	r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */
  
  	SAVE_GPR(2, r1)
  	SAVE_GPR(13, r1)
  	SAVE_8GPRS(14, r1)
  	SAVE_10GPRS(22, r1)
  	mfcr    r10
  	std     r10,8*32(r1)
  	mfmsr   r10
  	std     r10,8*33(r1)
  
  	/* remove MSR_LE from msr but keep MSR_SF */
  	mfmsr	r10
  	rldicr	r10,r10,0,62
  	mtsrr1	r10
  
  	/* Load FW address, set LR to label 1, and jump to FW */
  	bl	0f
  0:	mflr	r10
  	addi	r11,r10,(1f-0b)
  	mtlr	r11
  
  	ld	r10,(p_prom-0b)(r10)
  	mtsrr0	r10
  
  	rfid
  
  1:	/* Return from OF */
  	FIXUP_ENDIAN
  
  	/* Restore registers and return. */
  	rldicl  r1,r1,0,32
  
  	/* Restore the MSR (back to 64 bits) */
  	ld      r10,8*(33)(r1)
  	mtmsr	r10
  	isync
  
  	/* Restore other registers */
  	REST_GPR(2, r1)
  	REST_GPR(13, r1)
  	REST_8GPRS(14, r1)
  	REST_10GPRS(22, r1)
  	ld      r10,8*32(r1)
  	mtcr	r10
  
  	addi    r1,r1,PROM_FRAME_SIZE
  	ld      r0,16(r1)
  	mtlr    r0
  	blr
  #endif