armv8: Fix and simplify branch_if_master/branch_if_slave

The branch_if_master macro jumps to a label if the CPU is the "master"
core, which we define as having all affinity levels set to 0. To check
for this condition, we need to mask off some bits from the MPIDR
register, then compare the remaining register value against zero.

The implementation of this was slighly broken (it preserved the upper
RES0 bits), overly complicated and hard to understand, especially since
it lacked comments. The same was true for the very similar
branch_if_slave macro.

Use a much shorter assembly sequence for those checks, use the same
masking for both macros (just negate the final branch), and put some
comments on them, to make it clear what the code does.
This allows to drop the second temporary register for branch_if_master,
so we adjust all call sites as well.

Also use the opportunity to remove a misleading comment: the macro
works fine on SoCs with multiple clusters. Judging by the commit
message, the original problem with the Juno SoC stems from the fact that
the master CPU *can* be configured to be from cluster 1, so the
assumption that the master CPU has all affinity values set to 0 does not
hold there. But this is already mentioned above in a comment, so remove
the extra comment.

Signed-off-by: Andre Przywara <andre.przywara@arm.com>

arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S

@@ -200,7 +200,7 @@ ENTRY(lowlevel_init)
 #endif
 
 100:
-	branch_if_master x0, x1, 2f
+	branch_if_master x0, 2f
 
 #if defined(CONFIG_MP) && defined(CONFIG_ARMV8_MULTIENTRY)
 	/*

arch/arm/cpu/armv8/start.S

@@ -175,11 +175,11 @@ pie_fixup_done:
 	bl	lowlevel_init
 
 #if defined(CONFIG_ARMV8_SPIN_TABLE) && !defined(CONFIG_SPL_BUILD)
-	branch_if_master x0, x1, master_cpu
+	branch_if_master x0, master_cpu
 	b	spin_table_secondary_jump
 	/* never return */
 #elif defined(CONFIG_ARMV8_MULTIENTRY)
-	branch_if_master x0, x1, master_cpu
+	branch_if_master x0, master_cpu
 
 	/*
 	 * Slave CPUs
@@ -305,7 +305,7 @@ WEAK(lowlevel_init)
 #endif
 
 #ifdef CONFIG_ARMV8_MULTIENTRY
-	branch_if_master x0, x1, 2f
+	branch_if_master x0, 2f
 
 	/*
 	 * Slave should wait for master clearing spin table.

arch/arm/include/asm/macro.h

@@ -121,19 +121,10 @@ lr	.req	x30
  */
 .macro	branch_if_slave, xreg, slave_label
 #ifdef CONFIG_ARMV8_MULTIENTRY
-	/* NOTE: MPIDR handling will be erroneous on multi-cluster machines */
 	mrs	\xreg, mpidr_el1
-	tst	\xreg, #0xff		/* Test Affinity 0 */
-	b.ne	\slave_label
-	lsr	\xreg, \xreg, #8
-	tst	\xreg, #0xff		/* Test Affinity 1 */
-	b.ne	\slave_label
-	lsr	\xreg, \xreg, #8
-	tst	\xreg, #0xff		/* Test Affinity 2 */
-	b.ne	\slave_label
-	lsr	\xreg, \xreg, #16
-	tst	\xreg, #0xff		/* Test Affinity 3 */
-	b.ne	\slave_label
+	and	\xreg, \xreg,  0xffffffffff	/* clear bits [63:40] */
+	and	\xreg, \xreg, ~0x00ff000000	/* also clear bits [31:24] */
+	cbnz	\xreg, \slave_label
 #endif
 .endm
 
@@ -141,16 +132,12 @@ lr	.req	x30
  * Branch if current processor is a master,
  * choose processor with all zero affinity value as the master.
  */
-.macro	branch_if_master, xreg1, xreg2, master_label
+.macro	branch_if_master, xreg, master_label
 #ifdef CONFIG_ARMV8_MULTIENTRY
-	/* NOTE: MPIDR handling will be erroneous on multi-cluster machines */
-	mrs	\xreg1, mpidr_el1
-	lsr	\xreg2, \xreg1, #32
-	lsl	\xreg2, \xreg2, #32
-	lsl	\xreg1, \xreg1, #40
-	lsr	\xreg1, \xreg1, #40
-	orr	\xreg1, \xreg1, \xreg2
-	cbz	\xreg1, \master_label
+	mrs	\xreg, mpidr_el1
+	and	\xreg, \xreg,  0xffffffffff	/* clear bits [63:40] */
+	and	\xreg, \xreg, ~0x00ff000000	/* also clear bits [31:24] */
+	cbz	\xreg, \master_label
 #else
 	b	\master_label
 #endif

arch/arm/mach-rmobile/lowlevel_init_gen3.S

@@ -64,7 +64,7 @@ ENTRY(lowlevel_init)
 #endif
 #endif
 
-	branch_if_master x0, x1, 2f
+	branch_if_master x0, 2f
 
 	/*
 	 * Slave should wait for master clearing spin table.

arch/arm/mach-socfpga/lowlevel_init_soc64.S

@@ -38,7 +38,7 @@ slave_wait_atf:
 #endif
 
 #ifdef CONFIG_ARMV8_MULTIENTRY
-	branch_if_master x0, x1, 2f
+	branch_if_master x0, 2f
 
 	/*
 	 * Slave should wait for master clearing spin table.

board/cortina/presidio-asic/lowlevel_init.S

@@ -50,7 +50,7 @@ skip_smp_setup:
 #endif
 
 #ifdef CONFIG_ARMV8_MULTIENTRY
-	branch_if_master x0, x1, 2f
+	branch_if_master x0, 2f
 
 	/*
 	 * Slave should wait for master clearing spin table.