start.s

来自「U-boot源码 ARM7启动代码」· S 代码 · 共 2,098 行 · 第 1/4 页

	/*
	 * Setup temporary stack pointer only for boards
	 * that do not use SDRAM SPD I2C stuff since it
	 * is already initialized to use DCACHE or OCM
	 * stacks.
	 */
#if !(defined(CFG_INIT_DCACHE_CS) || defined(CFG_TEMP_STACK_OCM))
	lis	r1, CFG_INIT_RAM_ADDR@h
	ori	r1,r1,CFG_INIT_SP_OFFSET /* set up the stack in SDRAM */

	li	r0, 0			/* Make room for stack frame header and */
	stwu	r0, -4(r1)		/* clear final stack frame so that	*/
	stwu	r0, -4(r1)		/* stack backtraces terminate cleanly	*/
	/*
	 * Set up a dummy frame to store reset vector as return address.
	 * this causes stack underflow to reset board.
	 */
	stwu	r1, -8(r1)		/* Save back chain and move SP */
	lis	r0, RESET_VECTOR@h	/* Address of reset vector */
	ori	r0, r0, RESET_VECTOR@l
	stwu	r1, -8(r1)		/* Save back chain and move SP */
	stw	r0, +12(r1)		/* Save return addr (underflow vect) */
#endif /* !(CFG_INIT_DCACHE_CS	|| !CFG_TEM_STACK_OCM) */

#ifdef CONFIG_NAND_SPL
	bl	nand_boot		/* will not return */
#else
	GET_GOT			/* initialize GOT access			*/

	bl	cpu_init_f	/* run low-level CPU init code	   (from Flash) */

	/* NEVER RETURNS! */
	bl	board_init_f	/* run first part of init code (from Flash)	*/
#endif /* CONFIG_NAND_SPL */

#endif	/* CONFIG_405GP || CONFIG_405CR || CONFIG_405 || CONFIG_405EP */
	/*----------------------------------------------------------------------- */


#ifndef CONFIG_NAND_SPL
/*
 * This code finishes saving the registers to the exception frame
 * and jumps to the appropriate handler for the exception.
 * Register r21 is pointer into trap frame, r1 has new stack pointer.
 */
	.globl	transfer_to_handler
transfer_to_handler:
	stw	r22,_NIP(r21)
	lis	r22,MSR_POW@h
	andc	r23,r23,r22
	stw	r23,_MSR(r21)
	SAVE_GPR(7, r21)
	SAVE_4GPRS(8, r21)
	SAVE_8GPRS(12, r21)
	SAVE_8GPRS(24, r21)
	mflr	r23
	andi.	r24,r23,0x3f00		/* get vector offset */
	stw	r24,TRAP(r21)
	li	r22,0
	stw	r22,RESULT(r21)
	mtspr	SPRG2,r22		/* r1 is now kernel sp */
	lwz	r24,0(r23)		/* virtual address of handler */
	lwz	r23,4(r23)		/* where to go when done */
	mtspr	SRR0,r24
	mtspr	SRR1,r20
	mtlr	r23
	SYNC
	rfi				/* jump to handler, enable MMU */

int_return:
	mfmsr	r28		/* Disable interrupts */
	li	r4,0
	ori	r4,r4,MSR_EE
	andc	r28,r28,r4
	SYNC			/* Some chip revs need this... */
	mtmsr	r28
	SYNC
	lwz	r2,_CTR(r1)
	lwz	r0,_LINK(r1)
	mtctr	r2
	mtlr	r0
	lwz	r2,_XER(r1)
	lwz	r0,_CCR(r1)
	mtspr	XER,r2
	mtcrf	0xFF,r0
	REST_10GPRS(3, r1)
	REST_10GPRS(13, r1)
	REST_8GPRS(23, r1)
	REST_GPR(31, r1)
	lwz	r2,_NIP(r1)	/* Restore environment */
	lwz	r0,_MSR(r1)
	mtspr	SRR0,r2
	mtspr	SRR1,r0
	lwz	r0,GPR0(r1)
	lwz	r2,GPR2(r1)
	lwz	r1,GPR1(r1)
	SYNC
	rfi

crit_return:
	mfmsr	r28		/* Disable interrupts */
	li	r4,0
	ori	r4,r4,MSR_EE
	andc	r28,r28,r4
	SYNC			/* Some chip revs need this... */
	mtmsr	r28
	SYNC
	lwz	r2,_CTR(r1)
	lwz	r0,_LINK(r1)
	mtctr	r2
	mtlr	r0
	lwz	r2,_XER(r1)
	lwz	r0,_CCR(r1)
	mtspr	XER,r2
	mtcrf	0xFF,r0
	REST_10GPRS(3, r1)
	REST_10GPRS(13, r1)
	REST_8GPRS(23, r1)
	REST_GPR(31, r1)
	lwz	r2,_NIP(r1)	/* Restore environment */
	lwz	r0,_MSR(r1)
	mtspr	csrr0,r2
	mtspr	csrr1,r0
	lwz	r0,GPR0(r1)
	lwz	r2,GPR2(r1)
	lwz	r1,GPR1(r1)
	SYNC
	rfci

#ifdef CONFIG_440
mck_return:
	mfmsr	r28		/* Disable interrupts */
	li	r4,0
	ori	r4,r4,MSR_EE
	andc	r28,r28,r4
	SYNC			/* Some chip revs need this... */
	mtmsr	r28
	SYNC
	lwz	r2,_CTR(r1)
	lwz	r0,_LINK(r1)
	mtctr	r2
	mtlr	r0
	lwz	r2,_XER(r1)
	lwz	r0,_CCR(r1)
	mtspr	XER,r2
	mtcrf	0xFF,r0
	REST_10GPRS(3, r1)
	REST_10GPRS(13, r1)
	REST_8GPRS(23, r1)
	REST_GPR(31, r1)
	lwz	r2,_NIP(r1)	/* Restore environment */
	lwz	r0,_MSR(r1)
	mtspr	mcsrr0,r2
	mtspr	mcsrr1,r0
	lwz	r0,GPR0(r1)
	lwz	r2,GPR2(r1)
	lwz	r1,GPR1(r1)
	SYNC
	rfmci
#endif /* CONFIG_440 */


/*
 * Cache functions.
 *
 * NOTE: currently the 440s run with dcache _disabled_ once relocated to DRAM,
 * although for some cache-ralated calls stubs have to be provided to satisfy
 * symbols resolution.
 * Icache-related functions are used in POST framework.
 *
 */
#ifdef CONFIG_440
       .globl  dcache_disable
       .globl  icache_disable
       .globl  icache_enable
dcache_disable:
icache_disable:
icache_enable:
	blr

	.globl	dcache_status
	.globl	icache_status
dcache_status:
icache_status:
	mr	r3,  0
	blr
#else
flush_dcache:
	addis	r9,r0,0x0002		/* set mask for EE and CE msr bits */
	ori	r9,r9,0x8000
	mfmsr	r12			/* save msr */
	andc	r9,r12,r9
	mtmsr	r9			/* disable EE and CE */
	addi	r10,r0,0x0001		/* enable data cache for unused memory */
	mfdccr	r9			/* region 0xF8000000-0xFFFFFFFF via */
	or	r10,r10,r9		/* bit 31 in dccr */
	mtdccr	r10

	/* do loop for # of congruence classes. */
	lis	r10,(CFG_DCACHE_SIZE / CFG_CACHELINE_SIZE / 2)@ha	/* TBS: for large cache sizes */
	ori	r10,r10,(CFG_DCACHE_SIZE / CFG_CACHELINE_SIZE / 2)@l
	lis	r11,(CFG_DCACHE_SIZE / 2)@ha /* D cache set size - 2 way sets */
	ori	r11,r11,(CFG_DCACHE_SIZE / 2)@l /* D cache set size - 2 way sets */
	mtctr	r10
	addi	r10,r0,(0xE000-0x10000) /* start at 0xFFFFE000 */
	add	r11,r10,r11		/* add to get to other side of cache line */
..flush_dcache_loop:
	lwz	r3,0(r10)		/* least recently used side */
	lwz	r3,0(r11)		/* the other side */
	dccci	r0,r11			/* invalidate both sides */
	addi	r10,r10,CFG_CACHELINE_SIZE /* bump to next line */
	addi	r11,r11,CFG_CACHELINE_SIZE /* bump to next line */
	bdnz	..flush_dcache_loop
	sync				/* allow memory access to complete */
	mtdccr	r9			/* restore dccr */
	mtmsr	r12			/* restore msr */
	blr

	.globl	icache_enable
icache_enable:
	mflr	r8
	bl	invalidate_icache
	mtlr	r8
	isync
	addis	r3,r0, 0x8000	      /* set bit 0 */
	mticcr	r3
	blr

	.globl	icache_disable
icache_disable:
	addis	r3,r0, 0x0000	      /* clear bit 0 */
	mticcr	r3
	isync
	blr

	.globl	icache_status
icache_status:
	mficcr	r3
	srwi	r3, r3, 31	/* >>31 => select bit 0 */
	blr

	.globl	dcache_enable
dcache_enable:
	mflr	r8
	bl	invalidate_dcache
	mtlr	r8
	isync
	addis	r3,r0, 0x8000	      /* set bit 0 */
	mtdccr	r3
	blr

	.globl	dcache_disable
dcache_disable:
	mflr	r8
	bl	flush_dcache
	mtlr	r8
	addis	r3,r0, 0x0000	      /* clear bit 0 */
	mtdccr	r3
	blr

	.globl	dcache_status
dcache_status:
	mfdccr	r3
	srwi	r3, r3, 31	/* >>31 => select bit 0 */
	blr
#endif

	.globl get_pvr
get_pvr:
	mfspr	r3, PVR
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 out16 */
/* Description:	 Output 16 bits */
/*------------------------------------------------------------------------------- */
	.globl	out16
out16:
	sth	r4,0x0000(r3)
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 out16r */
/* Description:	 Byte reverse and output 16 bits */
/*------------------------------------------------------------------------------- */
	.globl	out16r
out16r:
	sthbrx	r4,r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 out32r */
/* Description:	 Byte reverse and output 32 bits */
/*------------------------------------------------------------------------------- */
	.globl	out32r
out32r:
	stwbrx	r4,r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 in16 */
/* Description:	 Input 16 bits */
/*------------------------------------------------------------------------------- */
	.globl	in16
in16:
	lhz	r3,0x0000(r3)
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 in16r */
/* Description:	 Input 16 bits and byte reverse */
/*------------------------------------------------------------------------------- */
	.globl	in16r
in16r:
	lhbrx	r3,r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 in32r */
/* Description:	 Input 32 bits and byte reverse */
/*------------------------------------------------------------------------------- */
	.globl	in32r
in32r:
	lwbrx	r3,r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 ppcDcbf */
/* Description:	 Data Cache block flush */
/* Input:	 r3 = effective address */
/* Output:	 none. */
/*------------------------------------------------------------------------------- */
	.globl	ppcDcbf
ppcDcbf:
	dcbf	r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 ppcDcbi */
/* Description:	 Data Cache block Invalidate */
/* Input:	 r3 = effective address */
/* Output:	 none. */
/*------------------------------------------------------------------------------- */
	.globl	ppcDcbi
ppcDcbi:
	dcbi	r0,r3
	blr

/*------------------------------------------------------------------------------- */
/* Function:	 ppcSync */
/* Description:	 Processor Synchronize */
/* Input:	 none. */
/* Output:	 none. */
/*------------------------------------------------------------------------------- */
	.globl	ppcSync
ppcSync:
	sync
	blr

/*
 * void relocate_code (addr_sp, gd, addr_moni)
 *
 * This "function" does not return, instead it continues in RAM
 * after relocating the monitor code.
 *
 * r3 = dest
 * r4 = src
 * r5 = length in bytes
 * r6 = cachelinesize
 */
	.globl	relocate_code
relocate_code:
#if defined(CONFIG_440EP) || defined(CONFIG_440GR) || \
    defined(CONFIG_440EPX) || defined(CONFIG_440GRX) || \
    defined(CONFIG_440SP) || defined(CONFIG_440SPE)
	/*
	 * On some 440er platforms the cache is enabled in the first TLB (Boot-CS)
	 * to speed up the boot process. Now this cache needs to be disabled.
	 */
	iccci	0,0			/* Invalidate inst cache */
	dccci	0,0			/* Invalidate data cache, now no longer our stack */
	sync
	isync
	addi	r1,r0,0x0000		/* TLB entry #0 */
	tlbre	r0,r1,0x0002		/* Read contents */
	ori	r0,r0,0x0c00		/* Or in the inhibit, write through bit */
	tlbwe	r0,r1,0x0002		/* Save it out */
	sync
	isync
#endif
	mr	r1,  r3		/* Set new stack pointer		*/
	mr	r9,  r4		/* Save copy of Init Data pointer	*/
	mr	r10, r5		/* Save copy of Destination Address	*/

	mr	r3,  r5				/* Destination Address	*/
	lis	r4, CFG_MONITOR_BASE@h		/* Source      Address	*/
	ori	r4, r4, CFG_MONITOR_BASE@l
	lwz	r5, GOT(__init_end)
	sub	r5, r5, r4
	li	r6, CFG_CACHELINE_SIZE		/* Cache Line Size	*/

	/*
	 * Fix GOT pointer:
	 *
	 * New GOT-PTR = (old GOT-PTR - CFG_MONITOR_BASE) + Destination Address
	 *
	 * Offset:
	 */
	sub	r15, r10, r4

	/* First our own GOT */
	add	r14, r14, r15
	/* the the one used by the C code */
	add	r30, r30, r15

	/*
	 * Now relocate code
	 */

	cmplw	cr1,r3,r4
	addi	r0,r5,3
	srwi.	r0,r0,2
	beq	cr1,4f		/* In place copy is not necessary	*/
	beq	7f		/* Protect against 0 count		*/
	mtctr	r0
	bge	cr1,2f

	la	r8,-4(r4)
	la	r7,-4(r3)
1:	lwzu	r0,4(r8)
	stwu	r0,4(r7)
	bdnz	1b
	b	4f

2:	slwi	r0,r0,2
	add	r8,r4,r0
	add	r7,r3,r0
3:	lwzu	r0,-4(r8)
	stwu	r0,-4(r7)
	bdnz	3b

/*
 * Now flush the cache: note that we must start from a cache aligned
 * address. Otherwise we might miss one cache line.
 */
4:	cmpwi	r6,0
	add	r5,r3,r5
	beq	7f		/* Always flush prefetch queue in any case */
	subi	r0,r6,1
	andc	r3,r3,r0
	mr	r4,r3
5:	dcbst	0,r4
	add	r4,r4,r6
	cmplw	r4,r5
	blt	5b
	sync			/* Wait for all dcbst to complete on bus */
	mr	r4,r3
6:	icbi	0,r4
	add	r4,r4,r6
	cmplw	r4,r5
	blt	6b
7:	sync			/* Wait for all icbi to complete on bus */
	isync

/*
 * We are done. Do not return, instead branch to second part of board
 * initialization, now running from RAM.
 */

	addi	r0, r10, in_ram - _start + _START_OFFSET
	mtlr	r0
	blr				/* NEVER RETURNS! */

in_ram:

	/*
	 * Relocation Function, r14 point to got2+0x8000
	 *
	 * Adjust got2 pointers, no need to check for 0, this code
	 * already puts a few entries in the table.
	 */
	li	r0,__got2_entries@sectoff@l
	la	r3,GOT(_GOT2_TABLE_)
	lwz	r11,GOT(_GOT2_TABLE_)
	mtctr	r0
	sub	r11,r3,r11
	addi	r3,r3,-4
1:	lwzu	r0,4(r3)
	add	r0,r0,r11
	stw	r0,0(r3)
	bdnz	1b

	/*
	 * Now adjust the fixups and the pointers to the fixups
	 * in case we need to move ourselves again.
	 */
2:	li	r0,__fixup_entries@sectoff@l
	lwz	r3,GOT(_FIXUP_TABLE_)
	cmpwi	r0,0
	mtctr	r0
	addi	r3,r3,-4
	beq	4f
3:	lwzu	r4,4(r3)
	lwzux	r0,r4,r11
	add	r0,r0,r11
	stw	r10,0(r3)
	stw	r0,0(r4)
	bdnz	3b
4:
clear_bss:
	/*
	 * Now clear BSS segment
	 */
	lwz	r3,GOT(__bss_start)
	lwz	r4,GOT(_end)

	cmplw	0, r3, r4
	beq	6f

	li	r0, 0
5:
	stw	r0, 0(r3)
	addi	r3, r3, 4
	cmplw	0, r3, r4