kernel/cpu: Allow non-zero CPU to be primary for suspend / kexec freeze

This patch provides an arch option, ARCH_SUSPEND_NONZERO_CPU, to
opt-in to allowing suspend to occur on one of the housekeeping CPUs
rather than hardcoded CPU0.

This will allow CPU0 to be a nohz_full CPU with a later change.

It may be possible for platforms with hardware/firmware restrictions
on suspend/wake effectively support this by handing off the final
stage to CPU0 when kernel housekeeping is no longer required. Another
option is to make housekeeping / nohz_full mask dynamic at runtime,
but the complexity could not be justified at this time.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lkml.kernel.org/r/20190411033448.20842-4-npiggin@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 28 insertions, 2 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2d0be82c3061..bc98b0e37a10 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -318,6 +318,10 @@ config ARCH_SUSPEND_POSSIBLE
 		   (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \
 		   || 44x || 40x
 
+config ARCH_SUSPEND_NONZERO_CPU
+	def_bool y
+	depends on PPC_POWERNV || PPC_PSERIES
+
 config PPC_DCR_NATIVE
 	bool
 
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 7ab2f09c0a14..73baab8535c1 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -140,7 +140,12 @@ extern void enable_nonboot_cpus(void);
 
 static inline int suspend_disable_secondary_cpus(void)
 {
-	return freeze_secondary_cpus(0);
+	int cpu = 0;
+
+	if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU))
+		cpu = -1;
+
+	return freeze_secondary_cpus(cpu);
 }
 static inline void suspend_enable_secondary_cpus(void)
 {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6754f3ecfd94..d1bf6e2b4752 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -9,6 +9,7 @@
 #include <linux/notifier.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
 #include <linux/sched/task.h>
 #include <linux/sched/smt.h>
 #include <linux/unistd.h>
@@ -1199,8 +1200,15 @@ int freeze_secondary_cpus(int primary)
 	int cpu, error = 0;
 
 	cpu_maps_update_begin();
-	if (!cpu_online(primary))
+	if (primary == -1) {
 		primary = cpumask_first(cpu_online_mask);
+		if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
+			primary = housekeeping_any_cpu(HK_FLAG_TIMER);
+	} else {
+		if (!cpu_online(primary))
+			primary = cpumask_first(cpu_online_mask);
+	}
+
 	/*
 	 * We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index f8fe57d1022e..9bbaaab14b36 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -114,6 +114,15 @@ config PM_SLEEP_SMP
 	depends on PM_SLEEP
 	select HOTPLUG_CPU
 
+config PM_SLEEP_SMP_NONZERO_CPU
+	def_bool y
+	depends on PM_SLEEP_SMP
+	depends on ARCH_SUSPEND_NONZERO_CPU
+	---help---
+	If an arch can suspend (for suspend, hibernate, kexec, etc) on a
+	non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This
+	will allow nohz_full mask to include CPU0.
+
 config PM_AUTOSLEEP
 	bool "Opportunistic sleep"
 	depends on PM_SLEEP