gem5: fix arm multicore with system.auto_reset_addr = True

baremetal: fix aarch64/no_bootloader/semihost_exit.S which was wrong
because was using unset sp for register block. Tests needed urgently!!

baremetal/arch/aarch64/multicore.S

@@ -7,10 +7,12 @@ main:
     ldr x1, =spinlock
     str x0, [x1]
 
-    /* Read cpu id into x1. */
+    /* Read cpu id into x1.
+     * TODO: cores beyond 4th?
+     */
     mrs x1, mpidr_el1
-    and x1, x1, 3
-    cbz x1, cpu0_only
+    ands x1, x1, 3
+    beq cpu0_only
 cpu1_only:
     /* Only CPU 1 reaches this point and sets the spinlock. */
     mov x0, 1
@@ -35,8 +37,7 @@ cpu0_only:
 
 #if !defined(GEM5)
     /* Wake up CPU 1 from initial sleep!
-     * In gem5, CPU 1 starts woken up from the start,
-     * so this is not needed.
+     * See:https://github.com/cirosantilli/linux-kernel-module-cheat#psci
      */
     /* Function identifier: PCSI CPU_ON. */
     ldr w0, =0xc4000003

baremetal/arch/aarch64/no_bootloader/semihost_exit.S

@@ -2,11 +2,14 @@
 
 .global mystart
 mystart:
-    mov x1, #0x26
-    movk x1, #2, lsl #16
-    str x1, [sp,#0]
+    mov x1, 0x26
+    movk x1, 2, lsl 16
+    ldr x2, =semihost_args
+    str x1, [x2, 0]
     mov x0, #0
-    str x0, [sp,#8]
-    mov x1, sp
-    mov w0, #0x18
+    str x0, [x2, 8]
+    mov x1, x2
+    mov w0, 0x18
     hlt 0xf000
+semihost_args:
+    .skip 16

baremetal/arch/aarch64/semihost_exit.S

@@ -1,20 +1,21 @@
 .global main
 main:
     /* 0x20026 == ADP_Stopped_ApplicationExit */
-    mov x1, #0x26
-    movk x1, #2, lsl #16
-    str x1, [sp,#0]
+    mov x1, 0x26
+    movk x1, 2, lsl 16
+    str x1, [sp, 0]
 
     /* Exit status code. Host QEMU process exits with that status. */
-    mov x0, #0
-    str x0, [sp,#8]
+    mov x0, 0
+    str x0, [sp, 8]
 
     /* x1 contains the address of parameter block.
-     * Any memory address could be used. */
+     * Any memory address could be used.
+     */
     mov x1, sp
 
     /* SYS_EXIT */
-    mov w0, #0x18
+    mov w0, 0x18
 
     /* Do the semihosting call on A64. */
     hlt 0xf000

baremetal/arch/arm/multicore.S

@@ -0,0 +1,37 @@
+/* https://github.com/cirosantilli/linux-kernel-module-cheat#arm-multicore */
+
+.global main
+main:
+    mov r0, #0
+    ldr r1, =spinlock
+    str r0, [r1]
+    /* Get CPU ID. */
+    mrc p15, 0, r1, c0, c0, 5
+    ands r1, r1, #3
+    beq cpu0_only
+cpu1_only:
+    mov r0, #1
+    ldr r1, =spinlock
+    str r0, [r1]
+    dmb sy
+    sev
+cpu1_sleep_forever:
+    wfe
+    b cpu1_sleep_forever
+cpu0_only:
+#if !defined(GEM5)
+    /* PCSI CPU_ON. */
+    ldr r0, =0x84000003
+    mov r1, #1
+    ldr r2, =cpu1_only
+    mov r3, #0
+    hvc 0
+#endif
+spinlock_start:
+    ldr r0, spinlock
+    wfe
+    cmp r0, #0
+    beq spinlock_start
+    bx lr
+spinlock:
+    .skip 4