#include <linux/linkage.h>
#include <init.h>
#include <asm/system.h>
#include <asm/opcodes-virt.h>

.section ".text_bare_init_","ax"
ENTRY(arm_cpu_lowlevel_init)
	/* save lr, since it may be banked away with a processor mode change */
	mov	r2, lr

#ifdef CONFIG_CPU_32v7
	/* careful: the hyp install corrupts r0 and r1 */
	bl	__hyp_install
#endif

	/* set the cpu to SVC32 mode, mask irq and fiq */
	mrs	r12, cpsr
	eor	r12, r12, #HYP_MODE
	tst	r12, #MODE_MASK
	bic	r12, r12, #MODE_MASK
	orr	r12, r12, #(PSR_I_BIT | PSR_F_BIT | SVC_MODE)
THUMB(	orr	r12, r12, #PSR_T_BIT	)
	bne	1f
	orr	r12, r12, #PSR_A_BIT
	adr	lr, 2f
	msr	spsr_cxsf, r12
	__MSR_ELR_HYP(14)
	__ERET
1:	msr	cpsr_c, r12
2:

#if __LINUX_ARM_ARCH__ >= 6
	/*
	 * ICIALLU: Invalidate all instruction caches to PoU,
	 * includes flushing of branch predictors.
	 * Even if the i-cache is off it might contain stale entries
	 * that are better discarded before enabling the cache.
	 * Architectually this is even possible after a cold reset.
	 */
	mcr	p15, 0, r12, c7, c5, 0
	/* DSB, ensure completion of the invalidation */
	mcr	p15, 0, r12, c7, c10, 4
	/*
	 * ISB, ensure instruction fetch path is in sync.
	 * Note that the ARM Architecture Reference Manual, ARMv7-A and ARMv7-R
	 * edition (ARM DDI 0406C.c) doesn't define this instruction in the
	 * ARMv6 part (D12.7.10). It only has: "Support of additional
	 * operations is IMPLEMENTATION DEFINED".
	 * But an earlier version of the ARMARM (ARM DDI 0100I) does define it
	 * as "Flush prefetch buffer (PrefetchFlush)".
	 */
	mcr	p15, 0, r12, c7, c5, 4
#endif

	/* disable MMU stuff and data/unified caches */
	mrc	p15, 0, r12, c1, c0, 0		/* SCTLR */
	bic	r12, r12, #(CR_M | CR_C | CR_B)
	bic	r12, r12, #(CR_S | CR_R | CR_V)

	/* enable instruction cache */
	orr	r12, r12, #CR_I

#if __LINUX_ARM_ARCH__ >= 6
	orr	r12, r12, #CR_U
	bic	r12, r12, #CR_A
#else
	orr	r12, r12, #CR_A
#endif

#ifdef __ARMEB__
	orr	r12, r12, #CR_B
#endif

	mcr	p15, 0, r12, c1, c0, 0		/* SCTLR */

	mov	pc, r2
ENDPROC(arm_cpu_lowlevel_init)

ENTRY(cortex_a7_lowlevel_init)
	mrc	p15, 0, r12, c1, c0, 1
	orr	r12, r12, #(1 << 6)	/* Enable SMP for cortex-a7 to make caches work */
	mcr	p15, 0, r12, c1, c0, 1
	mov	pc, lr
ENDPROC(cortex_a7_lowlevel_init)