[GIT PULL] CPU hotplug fix

[GIT PULL] CPU hotplug fix

[Ingo Molnar]

Linus,

Please pull the latest smp/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-urgent-2023-10-15

   # HEAD: c4dd854f740c21ae8dd9903fc67969c5497cb14b cpu-hotplug: Provide prototypes for arch CPU registration

Fix a Longsoon build warning by harmonizing the arch_[un]register_cpu()
prototypes between architectures.

 Thanks,

	Ingo

------------------>
Russell King (Oracle) (1):
      cpu-hotplug: Provide prototypes for arch CPU registration


 arch/ia64/include/asm/cpu.h   | 5 -----
 arch/ia64/kernel/topology.c   | 2 +-
 arch/x86/include/asm/cpu.h    | 2 --
 arch/x86/kernel/topology.c    | 2 +-
 drivers/acpi/acpi_processor.c | 1 +
 include/acpi/processor.h      | 5 -----
 include/linux/cpu.h           | 2 ++
 7 files changed, 5 insertions(+), 14 deletions(-)

diff --git a/arch/ia64/include/asm/cpu.h b/arch/ia64/include/asm/cpu.h
index db125df9e088..642d71675ddb 100644
--- a/arch/ia64/include/asm/cpu.h
+++ b/arch/ia64/include/asm/cpu.h
@@ -15,9 +15,4 @@ DECLARE_PER_CPU(struct ia64_cpu, cpu_devices);
 
 DECLARE_PER_CPU(int, cpu_state);
 
-#ifdef CONFIG_HOTPLUG_CPU
-extern int arch_register_cpu(int num);
-extern void arch_unregister_cpu(int);
-#endif
-
 #endif /* _ASM_IA64_CPU_H_ */
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index 94a848b06f15..741863a187a6 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -59,7 +59,7 @@ void __ref arch_unregister_cpu(int num)
 }
 EXPORT_SYMBOL(arch_unregister_cpu);
 #else
-static int __init arch_register_cpu(int num)
+int __init arch_register_cpu(int num)
 {
 	return register_cpu(&sysfs_cpus[num].cpu, num);
 }
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 3a233ebff712..25050d953eee 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -28,8 +28,6 @@ struct x86_cpu {
 };
 
 #ifdef CONFIG_HOTPLUG_CPU
-extern int arch_register_cpu(int num);
-extern void arch_unregister_cpu(int);
 extern void soft_restart_cpu(void);
 #endif
 
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index ca004e2e4469..0bab03130033 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -54,7 +54,7 @@ void arch_unregister_cpu(int num)
 EXPORT_SYMBOL(arch_unregister_cpu);
 #else /* CONFIG_HOTPLUG_CPU */
 
-static int __init arch_register_cpu(int num)
+int __init arch_register_cpu(int num)
 {
 	return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
 }
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index c711db8a9c33..0f5218e361df 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -12,6 +12,7 @@
 #define pr_fmt(fmt) "ACPI: " fmt
 
 #include <linux/acpi.h>
+#include <linux/cpu.h>
 #include <linux/device.h>
 #include <linux/dmi.h>
 #include <linux/kernel.h>
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 94181fe9780a..3f34ebb27525 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -465,9 +465,4 @@ extern int acpi_processor_ffh_lpi_probe(unsigned int cpu);
 extern int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi);
 #endif
 
-#ifdef CONFIG_ACPI_HOTPLUG_CPU
-extern int arch_register_cpu(int cpu);
-extern void arch_unregister_cpu(int cpu);
-#endif
-
 #endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 0abd60a7987b..eb768a866fe3 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -80,6 +80,8 @@ extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
 				 const struct attribute_group **groups,
 				 const char *fmt, ...);
+extern int arch_register_cpu(int cpu);
+extern void arch_unregister_cpu(int cpu);
 #ifdef CONFIG_HOTPLUG_CPU
 extern void unregister_cpu(struct cpu *cpu);
 extern ssize_t arch_cpu_probe(const char *, size_t);

Re: [GIT PULL] CPU hotplug fix

[pr-tracker-bot]

The pull request you sent on Sun, 15 Oct 2023 10:40:58 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-urgent-2023-10-15

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/ddf2085598021bc84c01b1e1ac3ed992045f23ec

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

Re: [GIT PULL] CPU hotplug fix

[pr-tracker-bot]

The pull request you sent on Sat, 2 Sep 2023 12:13:42 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-urgent-2023-09-02

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/23dfeae882ff45649d2379dde9c63c9476546db5

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

[GIT PULL] CPU hotplug fix

[Ingo Molnar]

Linus,

Please pull the latest smp/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-urgent-2023-09-02

   # HEAD: 2b8272ff4a70b866106ae13c36be7ecbef5d5da2 cpu/hotplug: Prevent self deadlock on CPU hot-unplug

Fix a CPU hotplug related deadlock between the task which initiates
and controls a CPU hot-unplug operation vs. the CFS bandwidth timer.

 Thanks,

	Ingo

------------------>
Thomas Gleixner (1):
      cpu/hotplug: Prevent self deadlock on CPU hot-unplug


 kernel/cpu.c | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index f6811c857102..6de7c6bb74ee 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1487,8 +1487,22 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	return ret;
 }
 
+struct cpu_down_work {
+	unsigned int		cpu;
+	enum cpuhp_state	target;
+};
+
+static long __cpu_down_maps_locked(void *arg)
+{
+	struct cpu_down_work *work = arg;
+
+	return _cpu_down(work->cpu, 0, work->target);
+}
+
 static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
 {
+	struct cpu_down_work work = { .cpu = cpu, .target = target, };
+
 	/*
 	 * If the platform does not support hotplug, report it explicitly to
 	 * differentiate it from a transient offlining failure.
@@ -1497,7 +1511,15 @@ static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
 		return -EOPNOTSUPP;
 	if (cpu_hotplug_disabled)
 		return -EBUSY;
-	return _cpu_down(cpu, 0, target);
+
+	/*
+	 * Ensure that the control task does not run on the to be offlined
+	 * CPU to prevent a deadlock against cfs_b->period_timer.
+	 */
+	cpu = cpumask_any_but(cpu_online_mask, cpu);
+	if (cpu >= nr_cpu_ids)
+		return -EBUSY;
+	return work_on_cpu(cpu, __cpu_down_maps_locked, &work);
 }
 
 static int cpu_down(unsigned int cpu, enum cpuhp_state target)

[GIT PULL] CPU hotplug fix

[Ingo Molnar]

Linus,

Please pull the latest smp-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-urgent-for-linus

   # HEAD: 46febd37f9c758b05cd25feae8512f22584742fe smp/hotplug: Move step CPUHP_AP_SMPCFD_DYING to the correct place

A single fix moving the smp-call queue flush step to the intended point in the 
state machine.

 Thanks,

	Ingo

------------------>
Lai Jiangshan (1):
      smp/hotplug: Move step CPUHP_AP_SMPCFD_DYING to the correct place


 kernel/cpu.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 04892a82f6ac..7891aecc6aec 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1289,11 +1289,6 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 		.teardown.single	= NULL,
 		.cant_stop		= true,
 	},
-	[CPUHP_AP_SMPCFD_DYING] = {
-		.name			= "smpcfd:dying",
-		.startup.single		= NULL,
-		.teardown.single	= smpcfd_dying_cpu,
-	},
 	/*
 	 * Handled on controll processor until the plugged processor manages
 	 * this itself.
@@ -1335,6 +1330,11 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.startup.single		= NULL,
 		.teardown.single	= rcutree_dying_cpu,
 	},
+	[CPUHP_AP_SMPCFD_DYING] = {
+		.name			= "smpcfd:dying",
+		.startup.single		= NULL,
+		.teardown.single	= smpcfd_dying_cpu,
+	},
 	/* Entry state on starting. Interrupts enabled from here on. Transient
 	 * state for synchronsization */
 	[CPUHP_AP_ONLINE] = {

[GIT PULL] CPU hotplug fix

[Ingo Molnar]

Linus,

Please pull the latest smp-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-urgent-for-linus

   # HEAD: 40da1b11f01e43aad1aa6cea64681b6125e8a2a7 cpu/hotplug: Drop the device lock on error

An error handling corner case fix.

 Thanks,

	Ingo

------------------>
Sebastian Andrzej Siewior (1):
      cpu/hotplug: Drop the device lock on error


 kernel/cpu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9ae6fbe5b5cf..cb5103413bd8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1658,13 +1658,13 @@ static ssize_t write_cpuhp_target(struct device *dev,
 	ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
 	mutex_unlock(&cpuhp_state_mutex);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (st->state < target)
 		ret = do_cpu_up(dev->id, target);
 	else
 		ret = do_cpu_down(dev->id, target);
-
+out:
 	unlock_device_hotplug();
 	return ret ? ret : count;
 }

[GIT PULL] CPU hotplug fix

[Ingo Molnar]

Linus,

Please pull the latest smp-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-urgent-for-linus

   # HEAD: 3b9d6da67e11ca8f78fde887918983523a36b0fa cpu/hotplug: Fix rollback during error-out in __cpu_disable()

Fix a CPU hotplug corner case regression, introduced by the recent hotplug rework.

 Thanks,

	Ingo

------------------>
Sebastian Andrzej Siewior (1):
      cpu/hotplug: Fix rollback during error-out in __cpu_disable()


 kernel/cpu.c | 33 ++++++++++++++++++++++++++-------
 1 file changed, 26 insertions(+), 7 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6ea42e8da861..3e3f6e49eabb 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -36,6 +36,7 @@
  * @target:	The target state
  * @thread:	Pointer to the hotplug thread
  * @should_run:	Thread should execute
+ * @rollback:	Perform a rollback
  * @cb_stat:	The state for a single callback (install/uninstall)
  * @cb:		Single callback function (install/uninstall)
  * @result:	Result of the operation
@@ -47,6 +48,7 @@ struct cpuhp_cpu_state {
 #ifdef CONFIG_SMP
 	struct task_struct	*thread;
 	bool			should_run;
+	bool			rollback;
 	enum cpuhp_state	cb_state;
 	int			(*cb)(unsigned int cpu);
 	int			result;
@@ -301,6 +303,11 @@ static int cpu_notify(unsigned long val, unsigned int cpu)
 	return __cpu_notify(val, cpu, -1, NULL);
 }
 
+static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
+{
+	BUG_ON(cpu_notify(val, cpu));
+}
+
 /* Notifier wrappers for transitioning to state machine */
 static int notify_prepare(unsigned int cpu)
 {
@@ -477,6 +484,16 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		} else {
 			ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
 		}
+	} else if (st->rollback) {
+		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
+
+		undo_cpu_down(cpu, st, cpuhp_ap_states);
+		/*
+		 * This is a momentary workaround to keep the notifier users
+		 * happy. Will go away once we got rid of the notifiers.
+		 */
+		cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
+		st->rollback = false;
 	} else {
 		/* Cannot happen .... */
 		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
@@ -636,11 +653,6 @@ static inline void check_for_tasks(int dead_cpu)
 	read_unlock(&tasklist_lock);
 }
 
-static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
-{
-	BUG_ON(cpu_notify(val, cpu));
-}
-
 static int notify_down_prepare(unsigned int cpu)
 {
 	int err, nr_calls = 0;
@@ -721,9 +733,10 @@ static int takedown_cpu(unsigned int cpu)
 	 */
 	err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu));
 	if (err) {
-		/* CPU didn't die: tell everyone.  Can't complain. */
-		cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
+		/* CPU refused to die */
 		irq_unlock_sparse();
+		/* Unpark the hotplug thread so we can rollback there */
+		kthread_unpark(per_cpu_ptr(&cpuhp_state, cpu)->thread);
 		return err;
 	}
 	BUG_ON(cpu_online(cpu));
@@ -832,6 +845,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	 * to do the further cleanups.
 	 */
 	ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target);
+	if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {
+		st->target = prev_state;
+		st->rollback = true;
+		cpuhp_kick_ap_work(cpu);
+	}
 
 	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
 out:
@@ -1249,6 +1267,7 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.name			= "notify:online",
 		.startup		= notify_online,
 		.teardown		= notify_down_prepare,
+		.skip_onerr		= true,
 	},
 #endif
 	/*