ARM: mm: Correct virt_to_phys patching for 64 bit physical addresses

The current phys_to_virt patching mechanism works only for 32 bit
physical addresses and this patch extends the idea for 64bit physical
addresses.

The 64bit v2p patching mechanism patches the higher 8 bits of physical
address with a constant using 'mov' instruction and lower 32bits are patched
using 'add'. While this is correct, in those platforms where the lowmem addressable
physical memory spawns across 4GB boundary, a carry bit can be produced as a
result of addition of lower 32bits. This has to be taken in to account and added
in to the upper. The patched __pv_offset and va are added in lower 32bits, where
__pv_offset can be in two's complement form when PA_START < VA_START and that can
result in a false carry bit.

e.g
    1) PA = 0x80000000; VA = 0xC0000000
       __pv_offset = PA - VA = 0xC0000000 (2's complement)

    2) PA = 0x2 80000000; VA = 0xC000000
       __pv_offset = PA - VA = 0x1 C0000000

So adding __pv_offset + VA should never result in a true overflow for (1).
So in order to differentiate between a true carry, a __pv_offset is extended
to 64bit and the upper 32bits will have 0xffffffff if __pv_offset is
2's complement. So 'mvn #0' is inserted instead of 'mov' while patching
for the same reason. Since mov, add, sub instruction are to patched
with different constants inside the same stub, the rotation field
of the opcode is using to differentiate between them.

So the above examples for v2p translation becomes for VA=0xC0000000,
    1) PA[63:32] = 0xffffffff
       PA[31:0] = VA + 0xC0000000 --> results in a carry
       PA[63:32] = PA[63:32] + carry

       PA[63:0] = 0x0 80000000

    2) PA[63:32] = 0x1
       PA[31:0] = VA + 0xC0000000 --> results in a carry
       PA[63:32] = PA[63:32] + carry

       PA[63:0] = 0x2 80000000

The above ideas were suggested by Nicolas Pitre <nico@linaro.org> as
part of the review of first and second versions of the subject patch.

There is no corresponding change on the phys_to_virt() side, because
computations on the upper 32-bits would be discarded anyway.

Cc: Russell King <linux@arm.linux.org.uk>

Reviewed-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Sricharan R <r.sricharan@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com>

1 files changed, 47 insertions, 16 deletions

diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 2c7cc1e03473..54547947a4e9 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -536,6 +536,14 @@ ENTRY(fixup_smp)
 	ldmfd	sp!, {r4 - r6, pc}
 ENDPROC(fixup_smp)
 
+#ifdef __ARMEB_
+#define LOW_OFFSET	0x4
+#define HIGH_OFFSET	0x0
+#else
+#define LOW_OFFSET	0x0
+#define HIGH_OFFSET	0x4
+#endif
+
 #ifdef CONFIG_ARM_PATCH_PHYS_VIRT
 
 /* __fixup_pv_table - patch the stub instructions with the delta between
@@ -546,17 +554,20 @@ ENDPROC(fixup_smp)
 	__HEAD
 __fixup_pv_table:
 	adr	r0, 1f
-	ldmia	r0, {r3-r5, r7}
-	sub	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
+	ldmia	r0, {r3-r7}
+	mvn	ip, #0
+	subs	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
 	add	r4, r4, r3	@ adjust table start address
 	add	r5, r5, r3	@ adjust table end address
-	add	r7, r7, r3	@ adjust __pv_phys_offset address
-	str	r8, [r7]	@ save computed PHYS_OFFSET to __pv_phys_offset
+	add	r6, r6, r3	@ adjust __pv_phys_offset address
+	add	r7, r7, r3	@ adjust __pv_offset address
+	str	r8, [r6, #LOW_OFFSET]	@ save computed PHYS_OFFSET to __pv_phys_offset
+	strcc	ip, [r7, #HIGH_OFFSET]	@ save to __pv_offset high bits
 	mov	r6, r3, lsr #24	@ constant for add/sub instructions
 	teq	r3, r6, lsl #24 @ must be 16MiB aligned
 THUMB(	it	ne		@ cross section branch )
 	bne	__error
-	str	r6, [r7, #4]	@ save to __pv_offset
+	str	r3, [r7, #LOW_OFFSET]	@ save to __pv_offset low bits
 	b	__fixup_a_pv_table
 ENDPROC(__fixup_pv_table)
 
@@ -565,10 +576,19 @@ ENDPROC(__fixup_pv_table)
 	.long	__pv_table_begin
 	.long	__pv_table_end
 2:	.long	__pv_phys_offset
+	.long	__pv_offset
 
 	.text
 __fixup_a_pv_table:
+	adr	r0, 3f
+	ldr	r6, [r0]
+	add	r6, r6, r3
+	ldr	r0, [r6, #HIGH_OFFSET]	@ pv_offset high word
+	ldr	r6, [r6, #LOW_OFFSET]	@ pv_offset low word
+	mov	r6, r6, lsr #24
+	cmn	r0, #1
 #ifdef CONFIG_THUMB2_KERNEL
+	moveq	r0, #0x200000	@ set bit 21, mov to mvn instruction
 	lsls	r6, #24
 	beq	2f
 	clz	r7, r6
@@ -582,18 +602,28 @@ __fixup_a_pv_table:
 	b	2f
 1:	add     r7, r3
 	ldrh	ip, [r7, #2]
-	and	ip, 0x8f00
-	orr	ip, r6	@ mask in offset bits 31-24
+	tst	ip, #0x4000
+	and	ip, #0x8f00
+	orrne	ip, r6	@ mask in offset bits 31-24
+	orreq	ip, r0	@ mask in offset bits 7-0
 	strh	ip, [r7, #2]
+	ldrheq	ip, [r7]
+	biceq	ip, #0x20
+	orreq	ip, ip, r0, lsr #16
+	strheq	ip, [r7]
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
 	bcc	1b
 	bx	lr
 #else
+	moveq	r0, #0x400000	@ set bit 22, mov to mvn instruction
 	b	2f
 1:	ldr	ip, [r7, r3]
 	bic	ip, ip, #0x000000ff
-	orr	ip, ip, r6	@ mask in offset bits 31-24
+	tst	ip, #0xf00	@ check the rotation field
+	orrne	ip, ip, r6	@ mask in offset bits 31-24
+	biceq	ip, ip, #0x400000	@ clear bit 22
+	orreq	ip, ip, r0	@ mask in offset bits 7-0
 	str	ip, [r7, r3]
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
@@ -602,28 +632,29 @@ __fixup_a_pv_table:
 #endif
 ENDPROC(__fixup_a_pv_table)
 
+3:	.long __pv_offset
+
 ENTRY(fixup_pv_table)
 	stmfd	sp!, {r4 - r7, lr}
-	ldr	r2, 2f			@ get address of __pv_phys_offset
 	mov	r3, #0			@ no offset
 	mov	r4, r0			@ r0 = table start
 	add	r5, r0, r1		@ r1 = table size
-	ldr	r6, [r2, #4]		@ get __pv_offset
 	bl	__fixup_a_pv_table
 	ldmfd	sp!, {r4 - r7, pc}
 ENDPROC(fixup_pv_table)
 
-	.align
-2:	.long	__pv_phys_offset
-
 	.data
 	.globl	__pv_phys_offset
 	.type	__pv_phys_offset, %object
 __pv_phys_offset:
-	.long	0
-	.size	__pv_phys_offset, . - __pv_phys_offset
+	.quad	0
+	.size	__pv_phys_offset, . -__pv_phys_offset
+
+	.globl	__pv_offset
+	.type	__pv_offset, %object
 __pv_offset:
-	.long	0
+	.quad	0
+	.size	__pv_offset, . -__pv_offset
 #endif
 
 #include "head-common.S"