x86/smpboot: Remove cpu_callin_mask

Now that TSC synchronization is SMP function call based there is no reason
to wait for the AP to be set in smp_callin_mask. The control CPU waits for
the AP to set itself in the online mask anyway.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Michael Kelley <mikelley@microsoft.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Helge Deller <deller@gmx.de> # parisc
Tested-by: Guilherme G. Piccoli <gpiccoli@igalia.com> # Steam Deck
Link: https://lore.kernel.org/r/20230512205256.206394064@linutronix.de

arch/x86/kernel/smpboot.c

@@ -104,7 +104,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 /* All of these masks are initialized in setup_cpu_local_masks() */
 static cpumask_var_t cpu_initialized_mask;
 static cpumask_var_t cpu_callout_mask;
-static cpumask_var_t cpu_callin_mask;
 /* Representing CPUs for which sibling maps can be computed */
 static cpumask_var_t cpu_sibling_setup_mask;
 
@@ -161,38 +160,30 @@ static inline void smpboot_restore_warm_reset_vector(void)
 
 }
 
-/*
- * Report back to the Boot Processor during boot time or to the caller processor
- * during CPU online.
- */
-static void smp_callin(void)
+/* Run the next set of setup steps for the upcoming CPU */
+static void ap_starting(void)
 {
-	int cpuid;
-
-	/*
-	 * If waken up by an INIT in an 82489DX configuration
-	 * cpu_callout_mask guarantees we don't get here before
-	 * an INIT_deassert IPI reaches our local APIC, so it is
-	 * now safe to touch our local APIC.
-	 */
-	cpuid = smp_processor_id();
+	int cpuid = smp_processor_id();
 
 	/*
-	 * the boot CPU has finished the init stage and is spinning
-	 * on callin_map until we finish. We are free to set up this
-	 * CPU, first the APIC. (this is probably redundant on most
-	 * boards)
+	 * If woken up by an INIT in an 82489DX configuration
+	 * cpu_callout_mask guarantees the CPU does not reach this point
+	 * before an INIT_deassert IPI reaches the local APIC, so it is now
+	 * safe to touch the local APIC.
+	 *
+	 * Set up this CPU, first the APIC, which is probably redundant on
+	 * most boards.
 	 */
 	apic_ap_setup();
 
-	/* Save our processor parameters. */
+	/* Save the processor parameters. */
 	smp_store_cpu_info(cpuid);
 
 	/*
 	 * The topology information must be up to date before
 	 * notify_cpu_starting().
 	 */
-	set_cpu_sibling_map(raw_smp_processor_id());
+	set_cpu_sibling_map(cpuid);
 
 	ap_init_aperfmperf();
 
@@ -205,11 +196,6 @@ static void smp_callin(void)
 	 * state CPUHP_ONLINE.
 	 */
 	notify_cpu_starting(cpuid);
-
-	/*
-	 * Allow the master to continue.
-	 */
-	cpumask_set_cpu(cpuid, cpu_callin_mask);
 }
 
 static void ap_calibrate_delay(void)
@@ -268,12 +254,7 @@ static void notrace start_secondary(void *unused)
 	rcu_cpu_starting(raw_smp_processor_id());
 	x86_cpuinit.early_percpu_clock_init();
 
-	/*
-	 * Sync point with wait_cpu_callin(). The AP doesn't wait here
-	 * but just sets the bit to let the controlling CPU (BSP) know that
-	 * it's got this far.
-	 */
-	smp_callin();
+	ap_starting();
 
 	/* Check TSC synchronization with the control CPU. */
 	check_tsc_sync_target();
@@ -1109,7 +1090,7 @@ static int wait_cpu_cpumask(unsigned int cpu, const struct cpumask *mask)
  * and thus wait_for_master_cpu(), then set cpu_callout_mask to allow it
  * to proceed.  The AP will then proceed past setting its 'callin' bit
  * and end up waiting in check_tsc_sync_target() until we reach
- * do_wait_cpu_online() to tend to it.
+ * wait_cpu_online() to tend to it.
  */
 static int wait_cpu_initialized(unsigned int cpu)
 {
@@ -1124,20 +1105,7 @@ static int wait_cpu_initialized(unsigned int cpu)
 }
 
 /*
- * Bringup step three: Wait for the target AP to reach smp_callin().
- * The AP is not waiting for us here so we don't need to parallelise
- * this step. Not entirely clear why we care about this, since we just
- * proceed directly to TSC synchronization which is the next sync
- * point with the AP anyway.
- */
-static void wait_cpu_callin(unsigned int cpu)
-{
-	while (!cpumask_test_cpu(cpu, cpu_callin_mask))
-		schedule();
-}
-
-/*
- * Bringup step four: Wait for the target AP to reach set_cpu_online() in
+ * Bringup step three: Wait for the target AP to reach set_cpu_online() in
  * start_secondary().
  */
 static void wait_cpu_online(unsigned int cpu)
@@ -1166,14 +1134,6 @@ static int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
 		return -EINVAL;
 	}
 
-	/*
-	 * Already booted CPU?
-	 */
-	if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
-		pr_debug("do_boot_cpu %d Already started\n", cpu);
-		return -ENOSYS;
-	}
-
 	/*
 	 * Save current MTRR state in case it was changed since early boot
 	 * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync:
@@ -1211,7 +1171,6 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	if (ret)
 		goto out;
 
-	wait_cpu_callin(cpu);
 	wait_cpu_online(cpu);
 
 out:
@@ -1327,7 +1286,6 @@ void __init smp_prepare_cpus_common(void)
 	 * Setup boot CPU information
 	 */
 	smp_store_boot_cpu_info(); /* Final full version of the data */
-	cpumask_copy(cpu_callin_mask, cpumask_of(0));
 	mb();
 
 	for_each_possible_cpu(i) {
@@ -1542,7 +1500,6 @@ __init void prefill_possible_map(void)
 void __init setup_cpu_local_masks(void)
 {
 	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
-	alloc_bootmem_cpumask_var(&cpu_callin_mask);
 	alloc_bootmem_cpumask_var(&cpu_callout_mask);
 	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
 }
@@ -1606,7 +1563,6 @@ static void remove_cpu_from_maps(int cpu)
 {
 	set_cpu_online(cpu, false);
 	cpumask_clear_cpu(cpu, cpu_callout_mask);
-	cpumask_clear_cpu(cpu, cpu_callin_mask);
 	/* was set by cpu_init() */
 	cpumask_clear_cpu(cpu, cpu_initialized_mask);
 	numa_remove_cpu(cpu);