plat/arm/sgi: include AFF3 affinity in core position calculation

AFF3 bits of MPIDR corresponds to Chip-Id in Arm multi-chip platforms.
For calculating linear core position of CPU cores from slave chips, AFF3
bits has to be used. Update `plat_arm_calc_core_pos` assembly function
to include AFF3 bits in calculation.

Change-Id: I4af2bd82ab8e31e18bc61de22705a73893954260
Signed-off-by: Vijayenthiran Subramaniam <vijayenthiran.subramaniam@arm.com>

plat/arm/css/sgi/aarch64/sgi_helper.S

 /*
- * Copyright (c) 2018-2019, ARM Limited and Contributors. All rights reserved.
+ * Copyright (c) 2018-2020, ARM Limited and Contributors. All rights reserved.
  *
  * SPDX-License-Identifier: BSD-3-Clause
  */
@@ -18,19 +18,22 @@
 	 * unsigned int plat_arm_calc_core_pos(u_register_t mpidr)
 	 *
 	 * Helper function to calculate the core position.
+	 * (ChipId * PLAT_ARM_CLUSTER_COUNT *
+	 *  CSS_SGI_MAX_CPUS_PER_CLUSTER * CSS_SGI_MAX_PE_PER_CPU) +
 	 * (ClusterId * CSS_SGI_MAX_CPUS_PER_CLUSTER * CSS_SGI_MAX_PE_PER_CPU) +
 	 * (CPUId * CSS_SGI_MAX_PE_PER_CPU) +
 	 * ThreadId
 	 *
 	 * which can be simplified as:
 	 *
-	 * ((ClusterId * CSS_SGI_MAX_CPUS_PER_CLUSTER + CPUId) *
-	 * CSS_SGI_MAX_PE_PER_CPU) + ThreadId
+	 * ((((ChipId * PLAT_ARM_CLUSTER_COUNT) + ClusterId) *
+	 *   CSS_SGI_MAX_CPUS_PER_CLUSTER) + CPUId) * CSS_SGI_MAX_PE_PER_CPU +
+	 * ThreadId
 	 * ------------------------------------------------------
 	 */
 
 func plat_arm_calc_core_pos
-	mov	x3, x0
+	mov	x4, x0
 
 	/*
 	 * The MT bit in MPIDR is always set for SGI platforms
@@ -38,15 +41,18 @@ func plat_arm_calc_core_pos
 	 */
 
 	/* Extract individual affinity fields from MPIDR */
-	ubfx    x0, x3, #MPIDR_AFF0_SHIFT, #MPIDR_AFFINITY_BITS
-	ubfx    x1, x3, #MPIDR_AFF1_SHIFT, #MPIDR_AFFINITY_BITS
-	ubfx    x2, x3, #MPIDR_AFF2_SHIFT, #MPIDR_AFFINITY_BITS
+	ubfx    x0, x4, #MPIDR_AFF0_SHIFT, #MPIDR_AFFINITY_BITS
+	ubfx    x1, x4, #MPIDR_AFF1_SHIFT, #MPIDR_AFFINITY_BITS
+	ubfx    x2, x4, #MPIDR_AFF2_SHIFT, #MPIDR_AFFINITY_BITS
+	ubfx    x3, x4, #MPIDR_AFF3_SHIFT, #MPIDR_AFFINITY_BITS
 
 	/* Compute linear position */
+	mov     x4, #PLAT_ARM_CLUSTER_COUNT
+	madd    x2, x3, x4, x2
 	mov     x4, #CSS_SGI_MAX_CPUS_PER_CLUSTER
 	madd    x1, x2, x4, x1
-	mov     x5, #CSS_SGI_MAX_PE_PER_CPU
-	madd    x0, x1, x5, x0
+	mov     x4, #CSS_SGI_MAX_PE_PER_CPU
+	madd    x0, x1, x4, x0
 	ret
 endfunc plat_arm_calc_core_pos