x86/smpboot: Enable split CPU startup

The x86 CPU bringup state currently does AP wake-up, wait for AP to
respond and then release it for full bringup.

It is safe to be split into a wake-up and and a separate wait+release
state.

Provide the required functions and enable the split CPU bringup, which
prepares for parallel bringup, where the bringup of the non-boot CPUs takes
two iterations: One to prepare and wake all APs and the second to wait and
release them. Depending on timing this can eliminate the wait time
completely.

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/20230512205257.133453992@linutronix.de

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index adb1ec8503d0a4448fbe1dd39036885ea9b8cfb8..c140a73b429539bbf9d3a538be8965868827fee0 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -274,8 +274,8 @@ config X86
        select HAVE_UNSTABLE_SCHED_CLOCK
        select HAVE_USER_RETURN_NOTIFIER
        select HAVE_GENERIC_VDSO
-       select HOTPLUG_CORE_SYNC_FULL           if SMP
        select HOTPLUG_SMT                      if SMP
+       select HOTPLUG_SPLIT_STARTUP            if SMP
        select IRQ_FORCED_THREADING
        select NEED_PER_CPU_EMBED_FIRST_CHUNK
        select NEED_PER_CPU_PAGE_FIRST_CHUNK

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 693c9997c069f37d7646d41dcaf4bbc8e5b03ff4..726c2a243eb077b40a9b655b3ab5c8611a8ec535 100644 (file)
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -40,7 +40,7 @@ struct smp_ops {
 
        void (*cleanup_dead_cpu)(unsigned cpu);
        void (*poll_sync_state)(void);
-       int (*cpu_up)(unsigned cpu, struct task_struct *tidle);
+       int (*kick_ap_alive)(unsigned cpu, struct task_struct *tidle);
        int (*cpu_disable)(void);
        void (*cpu_die)(unsigned int cpu);
        void (*play_dead)(void);
@@ -80,11 +80,6 @@ static inline void smp_cpus_done(unsigned int max_cpus)
        smp_ops.smp_cpus_done(max_cpus);
 }
 
-static inline int __cpu_up(unsigned int cpu, struct task_struct *tidle)
-{
-       return smp_ops.cpu_up(cpu, tidle);
-}
-
 static inline int __cpu_disable(void)
 {
        return smp_ops.cpu_disable();
@@ -124,7 +119,7 @@ void native_smp_prepare_cpus(unsigned int max_cpus);
 void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
 int common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
-int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
+int native_kick_ap(unsigned int cpu, struct task_struct *tidle);
 int native_cpu_disable(void);
 void __noreturn hlt_play_dead(void);
 void native_play_dead(void);

diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 4f6375b4ba9a181da8134b2bb16e6d7058a6b834..0d54115c3859f604285f0751d0cd1b4d43f28a91 100644 (file)
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -268,7 +268,7 @@ struct smp_ops smp_ops = {
 #endif
        .smp_send_reschedule    = native_smp_send_reschedule,
 
-       .cpu_up                 = native_cpu_up,
+       .kick_ap_alive          = native_kick_ap,
        .cpu_disable            = native_cpu_disable,
        .play_dead              = native_play_dead,
 

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 59386419b4b1d6db7778bd7647427581483978e8..a27941ac528c76390a1c63e08a710816a0a3ba1d 100644 (file)
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1052,7 +1052,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
        return ret;
 }
 
-static int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
+int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
 {
        int apicid = apic->cpu_present_to_apicid(cpu);
        int err;
@@ -1088,15 +1088,15 @@ static int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
        return err;
 }
 
-int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
+int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle)
 {
-       return native_kick_ap(cpu, tidle);
+       return smp_ops.kick_ap_alive(cpu, tidle);
 }
 
 void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu)
 {
        /* Cleanup possible dangling ends... */
-       if (smp_ops.cpu_up == native_cpu_up && x86_platform.legacy.warm_reset)
+       if (smp_ops.kick_ap_alive == native_kick_ap && x86_platform.legacy.warm_reset)
                smpboot_restore_warm_reset_vector();
 }
 

diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index b089fb1cefc6ebd9d0add1671f32784f81bf9610..a92e8002b5cf610de05975af234c6287b6266939 100644 (file)
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -314,7 +314,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
        return 0;
 }
 
-static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
+static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle)
 {
        int rc;
 
@@ -438,7 +438,7 @@ static const struct smp_ops xen_smp_ops __initconst = {
        .smp_prepare_cpus = xen_pv_smp_prepare_cpus,
        .smp_cpus_done = xen_smp_cpus_done,
 
-       .cpu_up = xen_pv_cpu_up,
+       .kick_ap_alive = xen_pv_kick_ap,
        .cpu_die = xen_pv_cpu_die,
        .cleanup_dead_cpu = xen_pv_cleanup_dead_cpu,
        .poll_sync_state = xen_pv_poll_sync_state,