x86/microcode: Provide new control functions

The current all in one code is unreadable and really not suited for
adding future features like uniform loading with package or system
scope.

Provide a set of new control functions which split the handling of the
primary and secondary CPUs. These will replace the current rendezvous
all in one function in the next step. This is intentionally a separate
change because diff makes an complete unreadable mess otherwise.

So the flow separates the primary and the secondary CPUs into their own
functions which use the control field in the per CPU ucode_ctrl struct.

   primary()			secondary()
    wait_for_all()		 wait_for_all()
    apply_ucode()		 wait_for_release()
    release()			 apply_ucode()

Signed-off-by: Thomas Gleixner <[email protected]>
Signed-off-by: Borislav Petkov (AMD) <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: KAGA-KOKO

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

@@ -290,6 +290,90 @@ static bool wait_for_cpus(atomic_t *cnt)
 	return false;
 }
 
+static bool wait_for_ctrl(void)
+{
+	unsigned int timeout;
+
+	for (timeout = 0; timeout < USEC_PER_SEC; timeout++) {
+		if (this_cpu_read(ucode_ctrl.ctrl) != SCTRL_WAIT)
+			return true;
+		udelay(1);
+		if (!(timeout % 1000))
+			touch_nmi_watchdog();
+	}
+	return false;
+}
+
+static __maybe_unused void load_secondary(unsigned int cpu)
+{
+	unsigned int ctrl_cpu = this_cpu_read(ucode_ctrl.ctrl_cpu);
+	enum ucode_state ret;
+
+	/* Initial rendezvous to ensure that all CPUs have arrived */
+	if (!wait_for_cpus(&late_cpus_in)) {
+		pr_err_once("load: %d CPUs timed out\n", atomic_read(&late_cpus_in) - 1);
+		this_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT);
+		return;
+	}
+
+	/*
+	 * Wait for primary threads to complete. If one of them hangs due
+	 * to the update, there is no way out. This is non-recoverable
+	 * because the CPU might hold locks or resources and confuse the
+	 * scheduler, watchdogs etc. There is no way to safely evacuate the
+	 * machine.
+	 */
+	if (!wait_for_ctrl())
+		panic("Microcode load: Primary CPU %d timed out\n", ctrl_cpu);
+
+	/*
+	 * If the primary succeeded then invoke the apply() callback,
+	 * otherwise copy the state from the primary thread.
+	 */
+	if (this_cpu_read(ucode_ctrl.ctrl) == SCTRL_APPLY)
+		ret = microcode_ops->apply_microcode(cpu);
+	else
+		ret = per_cpu(ucode_ctrl.result, ctrl_cpu);
+
+	this_cpu_write(ucode_ctrl.result, ret);
+	this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE);
+}
+
+static __maybe_unused void load_primary(unsigned int cpu)
+{
+	struct cpumask *secondaries = topology_sibling_cpumask(cpu);
+	enum sibling_ctrl ctrl;
+	enum ucode_state ret;
+	unsigned int sibling;
+
+	/* Initial rendezvous to ensure that all CPUs have arrived */
+	if (!wait_for_cpus(&late_cpus_in)) {
+		this_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT);
+		pr_err_once("load: %d CPUs timed out\n", atomic_read(&late_cpus_in) - 1);
+		return;
+	}
+
+	ret = microcode_ops->apply_microcode(cpu);
+	this_cpu_write(ucode_ctrl.result, ret);
+	this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE);
+
+	/*
+	 * If the update was successful, let the siblings run the apply()
+	 * callback. If not, tell them it's done. This also covers the
+	 * case where the CPU has uniform loading at package or system
+	 * scope implemented but does not advertise it.
+	 */
+	if (ret == UCODE_UPDATED || ret == UCODE_OK)
+		ctrl = SCTRL_APPLY;
+	else
+		ctrl = SCTRL_DONE;
+
+	for_each_cpu(sibling, secondaries) {
+		if (sibling != cpu)
+			per_cpu(ucode_ctrl.ctrl, sibling) = ctrl;
+	}
+}
+
 static int load_cpus_stopped(void *unused)
 {
 	int cpu = smp_processor_id();