From: David Woodhouse <dwmw@xxxxxxxxxxxx>
There are four logical parts to what native_cpu_up() does on the BSP (or
on the controlling CPU for a later hotplug):
1) Wake the AP by sending the INIT/SIPI/SIPI sequence.
2) Wait for the AP to make it as far as wait_for_master_cpu() which
sets that CPU's bit in cpu_initialized_mask, then sets the bit in
cpu_callout_mask to let the AP proceed through cpu_init().
3) Wait for the AP to finish cpu_init() and get as far as the
smp_callin() call, which sets that CPU's bit in cpu_callin_mask.
4) Perform the TSC synchronization and wait for the AP to actually
mark itself online in cpu_online_mask.
In preparation to allow these phases to operate in parallel on multiple
APs, split them out into separate functions and document the interactions
a little more clearly in both the BSP and AP code paths.
No functional change intended.
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: Usama Arif <usama.arif@xxxxxxxxxxxxx>
Tested-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Tested-by: Kim Phillips <kim.phillips@xxxxxxx>
Tested-by: Oleksandr Natalenko <oleksandr@xxxxxxxxxxxxxx>
Tested-by: Guilherme G. Piccoli <gpiccoli@xxxxxxxxxx>
---
arch/x86/kernel/smpboot.c | 179 ++++++++++++++++++++++++++------------
1 file changed, 125 insertions(+), 54 deletions(-)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 851477f7d728..2a8a18e23cc6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -204,6 +204,10 @@ static void smp_callin(void)
wmb();
+ /*
+ * This runs the AP through all the cpuhp states to its target
+ * state (CPUHP_ONLINE in the case of serial bringup).
+ */
notify_cpu_starting(cpuid);
/*
@@ -231,17 +235,32 @@ static void notrace start_secondary(void *unused)
load_cr3(swapper_pg_dir);
__flush_tlb_all();
#endif
+ /*
+ * Sync point with do_wait_cpu_initialized(). Before proceeding through
+ * cpu_init(), the AP will call wait_for_master_cpu() which sets its
+ * own bit in cpu_initialized_mask and then waits for the BSP to set
+ * its bit in cpu_callout_mask to release it.
+ */
cpu_init_secondary();
rcu_cpu_starting(raw_smp_processor_id());
x86_cpuinit.early_percpu_clock_init();
+
+ /*
+ * Sync point with do_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();
enable_start_cpu0 = 0;
/* otherwise gcc will move up smp_processor_id before the cpu_init */
barrier();
+
/*
- * Check TSC synchronization with the boot CPU:
+ * Check TSC synchronization with the boot CPU (or whichever CPU
+ * is controlling the bringup). It will do its part of this from
+ * do_wait_cpu_online(), making it an implicit sync point.
*/
check_tsc_sync_target();
@@ -254,6 +273,7 @@ static void notrace start_secondary(void *unused)
* half valid vector space.
*/
lock_vector_lock();
+ /* Sync point with do_wait_cpu_online() */
set_cpu_online(smp_processor_id(), true);
lapic_online();
unlock_vector_lock();
@@ -1081,7 +1101,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
unsigned long start_ip = real_mode_header->trampoline_start;
unsigned long boot_error = 0;
- unsigned long timeout;
#ifdef CONFIG_X86_64
/* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */
@@ -1147,55 +1166,94 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
cpu0_nmi_registered);
- if (!boot_error) {
- /*
- * Wait 10s total for first sign of life from AP
- */
- boot_error = -1;
- timeout = jiffies + 10*HZ;
- while (time_before(jiffies, timeout)) {
- if (cpumask_test_cpu(cpu, cpu_initialized_mask)) {
- /*
- * Tell AP to proceed with initialization
- */
- cpumask_set_cpu(cpu, cpu_callout_mask);
- boot_error = 0;
- break;
- }
- schedule();
- }
- }
+ return boot_error;
+}
- if (!boot_error) {
- /*
- * Wait till AP completes initial initialization
- */
- while (!cpumask_test_cpu(cpu, cpu_callin_mask)) {
- /*
- * Allow other tasks to run while we wait for the
- * AP to come online. This also gives a chance
- * for the MTRR work(triggered by the AP coming online)
- * to be completed in the stop machine context.
- */
- schedule();
- }
+static int do_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;
+}
- if (x86_platform.legacy.warm_reset) {
- /*
- * Cleanup possible dangling ends...
- */
- smpboot_restore_warm_reset_vector();
+/*
+ * 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
+ * do_wait_cpu_online() to tend to it.
+ */
+static int do_wait_cpu_initialized(unsigned int cpu)
+{
+ /*
+ * Wait for first sign of life from AP.
+ */
+ if (do_wait_cpu_cpumask(cpu, cpu_initialized_mask))
+ return -1;
+
+ cpumask_set_cpu(cpu, cpu_callout_mask);
+ return 0;
+}
+
+/*
+ * 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 int do_wait_cpu_callin(unsigned int cpu)
+{
+ /*
+ * Wait till AP completes initial initialization.
+ */
+ return do_wait_cpu_cpumask(cpu, cpu_callin_mask);
+}
+
+/*
+ * Bringup step four: Synchronize the TSC and wait for the target AP
+ * to reach set_cpu_online() in start_secondary().
+ */
+static int do_wait_cpu_online(unsigned int cpu)
+{
+ unsigned long flags;
+
+ /*
+ * Check TSC synchronization with the AP (keep irqs disabled
+ * while doing so):
+ */
+ local_irq_save(flags);
+ check_tsc_sync_source(cpu);
+ local_irq_restore(flags);
+
+ /*
+ * Wait for the AP to mark itself online. Not entirely
+ * clear why we care, since the generic cpuhp code will
+ * wait for it to each CPUHP_AP_ONLINE_IDLE before going
+ * ahead with the rest of the bringup anyway.
+ */
+ while (!cpu_online(cpu)) {
+ cpu_relax();
+ touch_nmi_watchdog();
}
- return boot_error;
+ return 0;
}
-int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
+static int do_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
int apicid = apic->cpu_present_to_apicid(cpu);
int cpu0_nmi_registered = 0;
- unsigned long flags;
int err, ret = 0;
lockdep_assert_irqs_enabled();
@@ -1242,19 +1300,6 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
goto unreg_nmi;
}
- /*
- * Check TSC synchronization with the AP (keep irqs disabled
- * while doing so):
- */
- local_irq_save(flags);
- check_tsc_sync_source(cpu);
- local_irq_restore(flags);
-
- while (!cpu_online(cpu)) {
- cpu_relax();
- touch_nmi_watchdog();
- }
-
unreg_nmi:
/*
* Clean up the nmi handler. Do this after the callin and callout sync
@@ -1266,6 +1311,32 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
return ret;
}
+int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+ int ret;
+
+ ret = do_cpu_up(cpu, tidle);
+ if (ret)
+ goto out;
+
+ ret = do_wait_cpu_initialized(cpu);
+ if (ret)
+ goto out;
+
+ ret = do_wait_cpu_callin(cpu);
+ if (ret)
+ goto out;
+
+ ret = do_wait_cpu_online(cpu);
+
+ out:
+ /* Cleanup possible dangling ends... */
+ if (x86_platform.legacy.warm_reset)
+ smpboot_restore_warm_reset_vector();
+
+ return ret;
+}
+
/**
* arch_disable_smp_support() - disables SMP support for x86 at runtime
*/
--
2.25.1
