x86/ucode: Fix error paths control_thread_fn()

These two early exits skipped re-enabling the watchdog, restoring the NMI
callback, and clearing the nmi_patch global pointer.  Always execute the tail
of the function on the way out.

Fixes: 8dd4dfa92d ("x86/microcode: Synchronize late microcode loading")
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Sergey Dyasli <sergey.dyasli@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/cpu/microcode/core.c

@@ -492,10 +492,7 @@ static int control_thread_fn(const struct microcode_patch *patch)
     ret = wait_for_condition(wait_cpu_callin, num_online_cpus(),
                              MICROCODE_CALLIN_TIMEOUT_US);
     if ( ret )
-    {
-        set_state(LOADING_EXIT);
-        return ret;
-    }
+        goto out;
 
     /* Control thread loads ucode first while others are in NMI handler. */
     ret = alternative_call(ucode_ops.apply_microcode, patch);
@@ -507,8 +504,7 @@ static int control_thread_fn(const struct microcode_patch *patch)
     {
         printk(XENLOG_ERR
                "Late loading aborted: CPU%u failed to update ucode\n", cpu);
-        set_state(LOADING_EXIT);
-        return ret;
+        goto out;
     }
 
     /* Let primary threads load the given ucode update */
@@ -539,6 +535,7 @@ static int control_thread_fn(const struct microcode_patch *patch)
         }
     }
 
+ out:
     /* Mark loading is done to unblock other threads */
     set_state(LOADING_EXIT);