ARM: re-implement physical address space switching

Re-implement the physical address space switching to be architecturally
compliant.  This involves flushing the caches, disabling the MMU, and
only then updating the page tables.  Once that is complete, the system
can be brought back up again.

Since we disable the MMU, we need to do the update in assembly code.
Luckily, the entries which need updating are fairly trivial, and are
all setup by the early assembly code.  We can merely adjust each entry
by the delta required.

Not only does this fix the code to be architecturally compliant, but it
fixes a couple of bugs too:

1. The original code would only ever update the first L2 entry covering
   a fraction of the kernel; the remainder were left untouched.
2. The L2 entries covering the DTB blob were likewise untouched.

This solution fixes up all entries.

Tested-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/mm/pv-fixup-asm.S b/arch/arm/mm/pv-fixup-asm.S
new file mode 100644
index 0000000..1867f3e4
--- /dev/null
+++ b/arch/arm/mm/pv-fixup-asm.S
@@ -0,0 +1,88 @@
+/*
+ *  Copyright (C) 2015 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This assembly is required to safely remap the physical address space
+ * for Keystone 2
+ */
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/cp15.h>
+#include <asm/memory.h>
+#include <asm/pgtable.h>
+
+	.section ".idmap.text", "ax"
+
+#define L1_ORDER 3
+#define L2_ORDER 3
+
+ENTRY(lpae_pgtables_remap_asm)
+	stmfd	sp!, {r4-r8, lr}
+
+	mrc	p15, 0, r8, c1, c0, 0		@ read control reg
+	bic	ip, r8, #CR_M			@ disable caches and MMU
+	mcr	p15, 0, ip, c1, c0, 0
+	dsb
+	isb
+
+	/* Update level 2 entries covering the kernel */
+	ldr	r6, =(_end - 1)
+	add	r7, r2, #0x1000
+	add	r6, r7, r6, lsr #SECTION_SHIFT - L2_ORDER
+	add	r7, r7, #PAGE_OFFSET >> (SECTION_SHIFT - L2_ORDER)
+1:	ldrd	r4, [r7]
+	adds	r4, r4, r0
+	adc	r5, r5, r1
+	strd	r4, [r7], #1 << L2_ORDER
+	cmp	r7, r6
+	bls	1b
+
+	/* Update level 2 entries for the boot data */
+	add	r7, r2, #0x1000
+	add	r7, r7, r3, lsr #SECTION_SHIFT - L2_ORDER
+	bic	r7, r7, #(1 << L2_ORDER) - 1
+	ldrd	r4, [r7]
+	adds	r4, r4, r0
+	adc	r5, r5, r1
+	strd	r4, [r7], #1 << L2_ORDER
+	ldrd	r4, [r7]
+	adds	r4, r4, r0
+	adc	r5, r5, r1
+	strd	r4, [r7]
+
+	/* Update level 1 entries */
+	mov	r6, #4
+	mov	r7, r2
+2:	ldrd	r4, [r7]
+	adds	r4, r4, r0
+	adc	r5, r5, r1
+	strd	r4, [r7], #1 << L1_ORDER
+	subs	r6, r6, #1
+	bne	2b
+
+	mrrc	p15, 0, r4, r5, c2		@ read TTBR0
+	adds	r4, r4, r0			@ update physical address
+	adc	r5, r5, r1
+	mcrr	p15, 0, r4, r5, c2		@ write back TTBR0
+	mrrc	p15, 1, r4, r5, c2		@ read TTBR1
+	adds	r4, r4, r0			@ update physical address
+	adc	r5, r5, r1
+	mcrr	p15, 1, r4, r5, c2		@ write back TTBR1
+
+	dsb
+
+	mov	ip, #0
+	mcr	p15, 0, ip, c7, c5, 0		@ I+BTB cache invalidate
+	mcr	p15, 0, ip, c8, c7, 0		@ local_flush_tlb_all()
+	dsb
+	isb
+
+	mcr	p15, 0, r8, c1, c0, 0		@ re-enable MMU
+	dsb
+	isb
+
+	ldmfd	sp!, {r4-r8, pc}
+ENDPROC(lpae_pgtables_remap_asm)