Add uncompressing code for the new CPU Id format

The current arch/arm/boot/compressed/head.S code only supports cores
to ARMv6 with the old CPU Id format. This patch adds support for the
new ARMv6 with the new CPU Id and ARMv7 cores that no longer have the
ARMv4 cache operations.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm/boot/compressed/head.S

@@ -435,6 +435,31 @@ __armv4_mmu_cache_on:
 		mcr	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
 		mov	pc, r12
 
+__armv7_mmu_cache_on:
+		mov	r12, lr
+		mrc	p15, 0, r11, c0, c1, 4	@ read ID_MMFR0
+		tst	r11, #0xf		@ VMSA
+		blne	__setup_mmu
+		mov	r0, #0
+		mcr	p15, 0, r0, c7, c10, 4	@ drain write buffer
+		tst	r11, #0xf		@ VMSA
+		mcrne	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
+		mrc	p15, 0, r0, c1, c0, 0	@ read control reg
+		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
+		orr	r0, r0, #0x003c		@ write buffer
+		tst	r11, #0xf		@ VMSA
+		orrne	r0, r0, #1		@ MMU enabled
+		movne	r1, #-1
+		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
+		mcrne	p15, 0, r1, c3, c0, 0	@ load domain access control
+		mcr	p15, 0, r0, c1, c0, 0	@ load control register
+		mrc	p15, 0, r0, c1, c0, 0	@ and read it back
+		mov	r0, r0
+		mov	r0, #0
+		mcrne	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
+		mcr	p15, 0, r0, c7, c5, 4	@ ISB
+		mov	pc, r12
+
 __arm6_mmu_cache_on:
 		mov	r12, lr
 		bl	__setup_mmu
@@ -619,11 +644,17 @@ proc_types:
 		b	__armv4_mmu_cache_flush
 
 		.word	0x0007b000		@ ARMv6
-		.word	0x0007f000
+		.word	0x000ff000
 		b	__armv4_mmu_cache_on
 		b	__armv4_mmu_cache_off
 		b	__armv6_mmu_cache_flush
 
+		.word	0x000f0000		@ new CPU Id
+		.word	0x000f0000
+		b	__armv7_mmu_cache_on
+		b	__armv7_mmu_cache_off
+		b	__armv7_mmu_cache_flush
+
 		.word	0			@ unrecognised type
 		.word	0
 		mov	pc, lr
@@ -671,6 +702,16 @@ __armv4_mmu_cache_off:
 		mcr	p15, 0, r0, c8, c7	@ invalidate whole TLB v4
 		mov	pc, lr
 
+__armv7_mmu_cache_off:
+		mrc	p15, 0, r0, c1, c0
+		bic	r0, r0, #0x000d
+		mcr	p15, 0, r0, c1, c0	@ turn MMU and cache off
+		mov	r12, lr
+		bl	__armv7_mmu_cache_flush
+		mov	r0, #0
+		mcr	p15, 0, r0, c8, c7, 0	@ invalidate whole TLB
+		mov	pc, r12
+
 __arm6_mmu_cache_off:
 		mov	r0, #0x00000030		@ ARM6 control reg.
 		b	__armv3_mmu_cache_off
@@ -727,6 +768,59 @@ __armv6_mmu_cache_flush:
 		mcr	p15, 0, r1, c7, c10, 4	@ drain WB
 		mov	pc, lr
 
+__armv7_mmu_cache_flush:
+		mrc	p15, 0, r10, c0, c1, 5	@ read ID_MMFR1
+		tst	r10, #0xf << 16		@ hierarchical cache (ARMv7)
+		beq	hierarchical
+		mov	r10, #0
+		mcr	p15, 0, r10, c7, c14, 0	@ clean+invalidate D
+		b	iflush
+hierarchical:
+		stmfd	sp!, {r0-r5, r7, r9-r11}
+		mrc	p15, 1, r0, c0, c0, 1	@ read clidr
+		ands	r3, r0, #0x7000000	@ extract loc from clidr
+		mov	r3, r3, lsr #23		@ left align loc bit field
+		beq	finished		@ if loc is 0, then no need to clean
+		mov	r10, #0			@ start clean at cache level 0
+loop1:
+		add	r2, r10, r10, lsr #1	@ work out 3x current cache level
+		mov	r1, r0, lsr r2		@ extract cache type bits from clidr
+		and	r1, r1, #7		@ mask of the bits for current cache only
+		cmp	r1, #2			@ see what cache we have at this level
+		blt	skip			@ skip if no cache, or just i-cache
+		mcr	p15, 2, r10, c0, c0, 0	@ select current cache level in cssr
+		mcr	p15, 0, r10, c7, c5, 4	@ isb to sych the new cssr&csidr
+		mrc	p15, 1, r1, c0, c0, 0	@ read the new csidr
+		and	r2, r1, #7		@ extract the length of the cache lines
+		add	r2, r2, #4		@ add 4 (line length offset)
+		ldr	r4, =0x3ff
+		ands	r4, r4, r1, lsr #3	@ find maximum number on the way size
+		.word	0xe16f5f14		@ clz r5, r4 - find bit position of way size increment
+		ldr	r7, =0x7fff
+		ands	r7, r7, r1, lsr #13	@ extract max number of the index size
+loop2:
+		mov	r9, r4			@ create working copy of max way size
+loop3:
+		orr	r11, r10, r9, lsl r5	@ factor way and cache number into r11
+		orr	r11, r11, r7, lsl r2	@ factor index number into r11
+		mcr	p15, 0, r11, c7, c14, 2	@ clean & invalidate by set/way
+		subs	r9, r9, #1		@ decrement the way
+		bge	loop3
+		subs	r7, r7, #1		@ decrement the index
+		bge	loop2
+skip:
+		add	r10, r10, #2		@ increment cache number
+		cmp	r3, r10
+		bgt	loop1
+finished:
+		mov	r10, #0			@ swith back to cache level 0
+		mcr	p15, 2, r10, c0, c0, 0	@ select current cache level in cssr
+		ldmfd	sp!, {r0-r5, r7, r9-r11}
+iflush:
+		mcr	p15, 0, r10, c7, c5, 0	@ invalidate I+BTB
+		mcr	p15, 0, r10, c7, c10, 4	@ drain WB
+		mov	pc, lr
+
 __armv4_mmu_cache_flush:
 		mov	r2, #64*1024		@ default: 32K dcache size (*2)
 		mov	r11, #32		@ default: 32 byte line size