[PATCH v3 06/12] arm64: smp: Use generic HOTPLUG_SPLIT_STARTUP machinery for CPU onlining

[Jinjie Ruan]

From: Will Deacon <will at kernel.org>

In preparation for enabling parallel bringup of secondary CPUs
on arm64, take the baby step of moving from HOTPLUG_CORE_SYNC_DEAD
to HOTPLUG_SPLIT_STARTUP.

To fully enable HOTPLUG_SPLIT_STARTUP, this patch implements:

1) arch_cpuhp_kick_ap_alive(). Kick the secondary CPU via firmware
without blocking.

2) arch_cpuhp_cleanup_kick_cpu(). Extracts early boot telemetry upon
AP bringup timeouts.

3) Callbacks to cpuhp_ap_sync_alive() inside secondary_start_kernel().
Enforces the initial pre-online boot handshake from the secondary
CPU side.

Signed-off-by: Will Deacon <will at kernel.org>
Signed-off-by: Jinjie Ruan <ruanjinjie at huawei.com>
---
 arch/arm64/Kconfig      |  2 +-
 arch/arm64/kernel/smp.c | 39 +++++++++++++++++++--------------------
 2 files changed, 20 insertions(+), 21 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fe60738e5943..24496e9967a8 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -231,7 +231,7 @@ config ARM64
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select HAVE_GENERIC_VDSO
-	select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU
+	select HOTPLUG_SPLIT_STARTUP if SMP
 	select HOTPLUG_SMT if HOTPLUG_CPU
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 87f92cf9ffa8..9482e8d38b98 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -107,12 +107,9 @@ static int boot_secondary(unsigned int cpu, struct task_struct *idle)
 	return -EOPNOTSUPP;
 }
 
-static DECLARE_COMPLETION(cpu_running);
-
-int __cpu_up(unsigned int cpu, struct task_struct *idle)
+int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
-	long status;
 
 	/*
 	 * We need to tell the secondary core where to find its stack and the
@@ -123,22 +120,22 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 
 	/* Now bring the CPU into our world */
 	ret = boot_secondary(cpu, idle);
-	if (ret) {
-		if (ret != -EPERM)
-			pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
-		return ret;
-	}
+	if (ret && ret != -EPERM)
+		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
+	return ret;
+}
+
+void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu, bool is_alive)
+{
+	long status;
+
+	if (is_alive)
+		return;
 
 	/*
-	 * CPU was successfully started, wait for it to come online or
-	 * time out.
+	 * We failed to synchronise with the CPU, so check if it left us
+	 * any breadcrumbs.
 	 */
-	wait_for_completion_timeout(&cpu_running,
-				    msecs_to_jiffies(5000));
-	if (cpu_online(cpu))
-		return 0;
-
-	pr_crit("CPU%u: failed to come online\n", cpu);
 	secondary_data.task = NULL;
 	status = READ_ONCE(secondary_data.status);
 	if (status == CPU_MMU_OFF)
@@ -170,8 +167,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	case CPU_PANIC_KERNEL:
 		panic("CPU%u detected unsupported configuration\n", cpu);
 	}
-
-	return -EIO;
 }
 
 static void init_gic_priority_masking(void)
@@ -231,6 +226,11 @@ asmlinkage notrace void secondary_start_kernel(void)
 	 */
 	check_local_cpu_capabilities();
 	lockdep_on();
+	/*
+	 * Synchronise with the core bringing us online so that it knows
+	 * we made it into the kernel. We're still not 'online'.
+	 */
+	cpuhp_ap_sync_alive();
 	rcutree_report_cpu_starting(cpu);
 	trace_hardirqs_off_finish();
 
@@ -264,7 +264,6 @@ asmlinkage notrace void secondary_start_kernel(void)
 					 read_cpuid_id());
 	update_cpu_boot_status(CPU_BOOT_SUCCESS);
 	set_cpu_online(cpu, true);
-	complete(&cpu_running);
 
 	/*
 	 * Secondary CPUs enter the kernel with all DAIF exceptions masked.
-- 
2.34.1