--- zzzz-none-000/linux-3.10.107/arch/arm/mach-mvebu/coherency_ll.S	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/arch/arm/mach-mvebu/coherency_ll.S	2021-02-04 17:41:59.000000000 +0000
@@ -20,36 +20,147 @@
 #define ARMADA_XP_CFB_CTL_REG_OFFSET 0x0
 #define ARMADA_XP_CFB_CFG_REG_OFFSET 0x4
 
+#include <asm/assembler.h>
+#include <asm/cp15.h>
+
 	.text
 /*
- * r0: Coherency fabric base register address
- * r1: HW CPU id
+ * Returns the coherency base address in r1 (r0 is untouched), or 0 if
+ * the coherency fabric is not enabled.
  */
-ENTRY(ll_set_cpu_coherent)
-	/* Create bit by cpu index */
-	mov	r3, #(1 << 24)
-	lsl	r1, r3, r1
+ENTRY(ll_get_coherency_base)
+	mrc	p15, 0, r1, c1, c0, 0
+	tst	r1, #CR_M @ Check MMU bit enabled
+	bne	1f
 
-	/* Add CPU to SMP group - Atomic */
-	add	r3, r0, #ARMADA_XP_CFB_CTL_REG_OFFSET
+	/*
+	 * MMU is disabled, use the physical address of the coherency
+	 * base address. However, if the coherency fabric isn't mapped
+	 * (i.e its virtual address is zero), it means coherency is
+	 * not enabled, so we return 0.
+	 */
+	ldr	r1, =coherency_base
+	cmp	r1, #0
+	beq	2f
+	adr	r1, 3f
+	ldr	r3, [r1]
+	ldr	r1, [r1, r3]
+	b	2f
 1:
-	ldrex	r2, [r3]
-	orr	r2, r2, r1
-	strex 	r0, r2, [r3]
-	cmp	r0, #0
-	bne 1b
+	/*
+	 * MMU is enabled, use the virtual address of the coherency
+	 * base address.
+	 */
+	ldr	r1, =coherency_base
+	ldr	r1, [r1]
+2:
+	ret	lr
+ENDPROC(ll_get_coherency_base)
+
+/*
+ * Returns the coherency CPU mask in r3 (r0 is untouched). This
+ * coherency CPU mask can be used with the coherency fabric
+ * configuration and control registers. Note that the mask is already
+ * endian-swapped as appropriate so that the calling functions do not
+ * have to care about endianness issues while accessing the coherency
+ * fabric registers
+ */
+ENTRY(ll_get_coherency_cpumask)
+	mrc	15, 0, r3, cr0, cr0, 5
+	and	r3, r3, #15
+	mov	r2, #(1 << 24)
+	lsl	r3, r2, r3
+ARM_BE8(rev	r3, r3)
+	ret	lr
+ENDPROC(ll_get_coherency_cpumask)
+
+/*
+ * ll_add_cpu_to_smp_group(), ll_enable_coherency() and
+ * ll_disable_coherency() use the strex/ldrex instructions while the
+ * MMU can be disabled. The Armada XP SoC has an exclusive monitor
+ * that tracks transactions to Device and/or SO memory and thanks to
+ * that, exclusive transactions are functional even when the MMU is
+ * disabled.
+ */
 
-	/* Enable coherency on CPU - Atomic */
-	add	r3, r3, #ARMADA_XP_CFB_CFG_REG_OFFSET
+ENTRY(ll_add_cpu_to_smp_group)
+	/*
+	 * As r0 is not modified by ll_get_coherency_base() and
+	 * ll_get_coherency_cpumask(), we use it to temporarly save lr
+	 * and avoid it being modified by the branch and link
+	 * calls. This function is used very early in the secondary
+	 * CPU boot, and no stack is available at this point.
+	 */
+	mov 	r0, lr
+	bl	ll_get_coherency_base
+	/* Bail out if the coherency is not enabled */
+	cmp	r1, #0
+	reteq	r0
+	bl	ll_get_coherency_cpumask
+	mov 	lr, r0
+	add	r0, r1, #ARMADA_XP_CFB_CFG_REG_OFFSET
 1:
-	ldrex	r2, [r3]
-	orr	r2, r2, r1
-	strex	r0, r2, [r3]
-	cmp	r0, #0
-	bne 1b
+	ldrex	r2, [r0]
+	orr	r2, r2, r3
+	strex	r1, r2, [r0]
+	cmp	r1, #0
+	bne	1b
+	ret	lr
+ENDPROC(ll_add_cpu_to_smp_group)
 
+ENTRY(ll_enable_coherency)
+	/*
+	 * As r0 is not modified by ll_get_coherency_base() and
+	 * ll_get_coherency_cpumask(), we use it to temporarly save lr
+	 * and avoid it being modified by the branch and link
+	 * calls. This function is used very early in the secondary
+	 * CPU boot, and no stack is available at this point.
+	 */
+	mov r0, lr
+	bl	ll_get_coherency_base
+	/* Bail out if the coherency is not enabled */
+	cmp	r1, #0
+	reteq	r0
+	bl	ll_get_coherency_cpumask
+	mov lr, r0
+	add	r0, r1, #ARMADA_XP_CFB_CTL_REG_OFFSET
+1:
+	ldrex	r2, [r0]
+	orr	r2, r2, r3
+	strex	r1, r2, [r0]
+	cmp	r1, #0
+	bne	1b
 	dsb
-
 	mov	r0, #0
-	mov	pc, lr
-ENDPROC(ll_set_cpu_coherent)
+	ret	lr
+ENDPROC(ll_enable_coherency)
+
+ENTRY(ll_disable_coherency)
+	/*
+	 * As r0 is not modified by ll_get_coherency_base() and
+	 * ll_get_coherency_cpumask(), we use it to temporarly save lr
+	 * and avoid it being modified by the branch and link
+	 * calls. This function is used very early in the secondary
+	 * CPU boot, and no stack is available at this point.
+	 */
+	mov 	r0, lr
+	bl	ll_get_coherency_base
+	/* Bail out if the coherency is not enabled */
+	cmp	r1, #0
+	reteq	r0
+	bl	ll_get_coherency_cpumask
+	mov 	lr, r0
+	add	r0, r1, #ARMADA_XP_CFB_CTL_REG_OFFSET
+1:
+	ldrex	r2, [r0]
+	bic	r2, r2, r3
+	strex	r1, r2, [r0]
+	cmp	r1, #0
+	bne	1b
+	dsb
+	ret	lr
+ENDPROC(ll_disable_coherency)
+
+	.align 2
+3:
+	.long	coherency_phys_base - .