x86/microcode: Replace the all-in-one rendevous handler

with a new handler which just separates the control flow of primary and
secondary CPUs.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20231002115903.433704135@linutronix.de

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

@@ -268,7 +268,7 @@ struct microcode_ctrl {
 };
 
 static DEFINE_PER_CPU(struct microcode_ctrl, ucode_ctrl);
-static atomic_t late_cpus_in, late_cpus_out;
+static atomic_t late_cpus_in;
 
 static bool wait_for_cpus(atomic_t *cnt)
 {
@@ -304,7 +304,7 @@ static bool wait_for_ctrl(void)
 	return false;
 }
 
-static __maybe_unused void load_secondary(unsigned int cpu)
+static void load_secondary(unsigned int cpu)
 {
 	unsigned int ctrl_cpu = this_cpu_read(ucode_ctrl.ctrl_cpu);
 	enum ucode_state ret;
@@ -339,7 +339,7 @@ static __maybe_unused void load_secondary(unsigned int cpu)
 	this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE);
 }
 
-static __maybe_unused void load_primary(unsigned int cpu)
+static void load_primary(unsigned int cpu)
 {
 	struct cpumask *secondaries = topology_sibling_cpumask(cpu);
 	enum sibling_ctrl ctrl;
@@ -376,46 +376,14 @@ static __maybe_unused void load_primary(unsigned int cpu)
 
 static int load_cpus_stopped(void *unused)
 {
-	int cpu = smp_processor_id();
-	enum ucode_state ret;
-
-	/*
-	 * Wait for all CPUs to arrive. A load will not be attempted unless all
-	 * CPUs show up.
-	 * */
-	if (!wait_for_cpus(&late_cpus_in)) {
-		this_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT);
-		return 0;
-	}
-
-	/*
-	 * On an SMT system, it suffices to load the microcode on one sibling of
-	 * the core because the microcode engine is shared between the threads.
-	 * Synchronization still needs to take place so that no concurrent
-	 * loading attempts happen on multiple threads of an SMT core. See
-	 * below.
-	 */
-	if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu)
-		goto wait_for_siblings;
+	unsigned int cpu = smp_processor_id();
 
-	ret = microcode_ops->apply_microcode(cpu);
-	this_cpu_write(ucode_ctrl.result, ret);
-
-wait_for_siblings:
-	if (!wait_for_cpus(&late_cpus_out))
-		panic("Timeout during microcode update!\n");
-
-	/*
-	 * At least one thread has completed update on each core.
-	 * For others, simply call the update to make sure the
-	 * per-cpu cpuinfo can be updated with right microcode
-	 * revision.
-	 */
-	if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu)
-		return 0;
+	if (this_cpu_read(ucode_ctrl.ctrl_cpu) == cpu)
+		load_primary(cpu);
+	else
+		load_secondary(cpu);
 
-	ret = microcode_ops->apply_microcode(cpu);
-	this_cpu_write(ucode_ctrl.result, ret);
+	/* No point to wait here. The CPUs will all wait in stop_machine(). */
 	return 0;
 }
 
@@ -429,7 +397,6 @@ static int load_late_stop_cpus(void)
 	pr_err("You should switch to early loading, if possible.\n");
 
 	atomic_set(&late_cpus_in, num_online_cpus());
-	atomic_set(&late_cpus_out, num_online_cpus());
 
 	/*
 	 * Take a snapshot before the microcode update in order to compare and