x86/smpboot: Switch to hotplug core state synchronization

The new AP state tracking and synchronization mechanism in the CPU hotplug
core code allows to remove quite some x86 specific code:

  1) The AP alive synchronization based on cpumasks

  2) The decision whether an AP can be brought up again

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/20230512205256.529657366@linutronix.de

1 files changed, 41 insertions, 124 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4349e8ab2566..59386419b4b1 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -57,6 +57,7 @@
 #include <linux/pgtable.h>
 #include <linux/overflow.h>
 #include <linux/stackprotector.h>
+#include <linux/cpuhotplug.h>
 
 #include <asm/acpi.h>
 #include <asm/cacheinfo.h>
@@ -101,9 +102,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_die_map);
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 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;
 /* Representing CPUs for which sibling maps can be computed */
 static cpumask_var_t cpu_sibling_setup_mask;
 
@@ -166,10 +164,10 @@ static void ap_starting(void)
 	int cpuid = smp_processor_id();
 
 	/*
-	 * 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.
+	 * If woken up by an INIT in an 82489DX configuration the alive
+	 * synchronization guarantees that 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.
@@ -213,17 +211,6 @@ static void ap_calibrate_delay(void)
 	cpu_data(smp_processor_id()).loops_per_jiffy = loops_per_jiffy;
 }
 
-static void wait_for_master_cpu(int cpu)
-{
-	/*
-	 * Wait for release by control CPU before continuing with AP
-	 * initialization.
-	 */
-	WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask));
-	while (!cpumask_test_cpu(cpu, cpu_callout_mask))
-		cpu_relax();
-}
-
 /*
  * Activate a secondary processor.
  */
@@ -244,11 +231,11 @@ static void notrace start_secondary(void *unused)
 	cpu_init_exception_handling();
 
 	/*
-	 * Sync point with wait_cpu_initialized(). Sets AP in
-	 * cpu_initialized_mask and then waits for the control CPU
-	 * to release it.
+	 * Synchronization point with the hotplug core. Sets the
+	 * synchronization state to ALIVE and waits for the control CPU to
+	 * release this CPU for further bringup.
 	 */
-	wait_for_master_cpu(raw_smp_processor_id());
+	cpuhp_ap_sync_alive();
 
 	cpu_init();
 	rcu_cpu_starting(raw_smp_processor_id());
@@ -278,7 +265,6 @@ static void notrace start_secondary(void *unused)
 	set_cpu_online(smp_processor_id(), true);
 	lapic_online();
 	unlock_vector_lock();
-	cpu_set_state_online(smp_processor_id());
 	x86_platform.nmi_init();
 
 	/* enable local interrupts */
@@ -729,9 +715,9 @@ static void impress_friends(void)
 	 * Allow the user to impress friends.
 	 */
 	pr_debug("Before bogomips\n");
-	for_each_possible_cpu(cpu)
-		if (cpumask_test_cpu(cpu, cpu_callout_mask))
-			bogosum += cpu_data(cpu).loops_per_jiffy;
+	for_each_online_cpu(cpu)
+		bogosum += cpu_data(cpu).loops_per_jiffy;
+
 	pr_info("Total of %d processors activated (%lu.%02lu BogoMIPS)\n",
 		num_online_cpus(),
 		bogosum/(500000/HZ),
@@ -1003,6 +989,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 {
 	unsigned long start_ip = real_mode_header->trampoline_start;
+	int ret;
 
 #ifdef CONFIG_X86_64
 	/* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */
@@ -1043,13 +1030,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 		}
 	}
 
-	/*
-	 * AP might wait on cpu_callout_mask in cpu_init() with
-	 * cpu_initialized_mask set if previous attempt to online
-	 * it timed-out. Clear cpu_initialized_mask so that after
-	 * INIT/SIPI it could start with a clean state.
-	 */
-	cpumask_clear_cpu(cpu, cpu_initialized_mask);
 	smp_mb();
 
 	/*
@@ -1060,47 +1040,16 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	 * - Use an INIT boot APIC message
 	 */
 	if (apic->wakeup_secondary_cpu_64)
-		return apic->wakeup_secondary_cpu_64(apicid, start_ip);
+		ret = apic->wakeup_secondary_cpu_64(apicid, start_ip);
 	else if (apic->wakeup_secondary_cpu)
-		return apic->wakeup_secondary_cpu(apicid, start_ip);
-
-	return wakeup_secondary_cpu_via_init(apicid, start_ip);
-}
-
-static int wait_cpu_cpumask(unsigned int cpu, const struct cpumask *mask)
-{
-	unsigned long timeout;
-
-	/*
-	 * Wait up to 10s for the CPU to report in.
-	 */
-	timeout = jiffies + 10*HZ;
-	while (time_before(jiffies, timeout)) {
-		if (cpumask_test_cpu(cpu, mask))
-			return 0;
-
-		schedule();
-	}
-	return -1;
-}
-
-/*
- * Bringup step two: Wait for the target AP to reach cpu_init_secondary()
- * 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
- * wait_cpu_online() to tend to it.
- */
-static int wait_cpu_initialized(unsigned int cpu)
-{
-	/*
-	 * Wait for first sign of life from AP.
-	 */
-	if (wait_cpu_cpumask(cpu, cpu_initialized_mask))
-		return -1;
+		ret = apic->wakeup_secondary_cpu(apicid, start_ip);
+	else
+		ret = wakeup_secondary_cpu_via_init(apicid, start_ip);
 
-	cpumask_set_cpu(cpu, cpu_callout_mask);
-	return 0;
+	/* If the wakeup mechanism failed, cleanup the warm reset vector */
+	if (ret)
+		arch_cpuhp_cleanup_kick_cpu(cpu);
+	return ret;
 }
 
 static int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
@@ -1125,11 +1074,6 @@ static int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
 	 */
 	mtrr_save_state();
 
-	/* x86 CPUs take themselves offline, so delayed offline is OK. */
-	err = cpu_check_up_prepare(cpu);
-	if (err && err != -EBUSY)
-		return err;
-
 	/* the FPU context is blank, nobody can own it */
 	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
 
@@ -1146,17 +1090,29 @@ static int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
 
 int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
-	int ret;
-
-	ret = native_kick_ap(cpu, tidle);
-	if (!ret)
-		ret = wait_cpu_initialized(cpu);
+	return native_kick_ap(cpu, tidle);
+}
 
+void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu)
+{
 	/* Cleanup possible dangling ends... */
-	if (x86_platform.legacy.warm_reset)
+	if (smp_ops.cpu_up == native_cpu_up && x86_platform.legacy.warm_reset)
 		smpboot_restore_warm_reset_vector();
+}
 
-	return ret;
+void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
+{
+	if (smp_ops.cleanup_dead_cpu)
+		smp_ops.cleanup_dead_cpu(cpu);
+
+	if (system_state == SYSTEM_RUNNING)
+		pr_info("CPU %u is now offline\n", cpu);
+}
+
+void arch_cpuhp_sync_state_poll(void)
+{
+	if (smp_ops.poll_sync_state)
+		smp_ops.poll_sync_state();
 }
 
 /**
@@ -1348,9 +1304,6 @@ void __init native_smp_prepare_boot_cpu(void)
 	if (!IS_ENABLED(CONFIG_SMP))
 		switch_gdt_and_percpu_base(me);
 
-	/* already set me in cpu_online_mask in boot_cpu_init() */
-	cpumask_set_cpu(me, cpu_callout_mask);
-	cpu_set_state_online(me);
 	native_pv_lock_init();
 }
 
@@ -1477,8 +1430,6 @@ __init void prefill_possible_map(void)
 /* correctly size the local cpu masks */
 void __init setup_cpu_local_masks(void)
 {
-	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
-	alloc_bootmem_cpumask_var(&cpu_callout_mask);
 	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
 }
 
@@ -1540,9 +1491,6 @@ static void remove_siblinginfo(int cpu)
 static void remove_cpu_from_maps(int cpu)
 {
 	set_cpu_online(cpu, false);
-	cpumask_clear_cpu(cpu, cpu_callout_mask);
-	/* was set by cpu_init() */
-	cpumask_clear_cpu(cpu, cpu_initialized_mask);
 	numa_remove_cpu(cpu);
 }
 
@@ -1593,36 +1541,11 @@ int native_cpu_disable(void)
 	return 0;
 }
 
-int common_cpu_die(unsigned int cpu)
-{
-	int ret = 0;
-
-	/* We don't do anything here: idle task is faking death itself. */
-
-	/* They ack this in play_dead() by setting CPU_DEAD */
-	if (cpu_wait_death(cpu, 5)) {
-		if (system_state == SYSTEM_RUNNING)
-			pr_info("CPU %u is now offline\n", cpu);
-	} else {
-		pr_err("CPU %u didn't die...\n", cpu);
-		ret = -1;
-	}
-
-	return ret;
-}
-
-void native_cpu_die(unsigned int cpu)
-{
-	common_cpu_die(cpu);
-}
-
 void play_dead_common(void)
 {
 	idle_task_exit();
 
-	/* Ack it */
-	(void)cpu_report_death();
-
+	cpuhp_ap_report_dead();
 	/*
 	 * With physical CPU hotplug, we should halt the cpu
 	 */
@@ -1724,12 +1647,6 @@ int native_cpu_disable(void)
 	return -ENOSYS;
 }
 
-void native_cpu_die(unsigned int cpu)
-{
-	/* We said "no" in __cpu_disable */
-	BUG();
-}
-
 void native_play_dead(void)
 {
 	BUG();