cpu hotplug: convert more drivers (batch #6 and last)

cpu hotplug: convert more drivers (batch #6 and last)

[Sebastian Andrzej Siewior]

Another small batch of drivers converted to the new hotplug state engine.
The whole series is also available at
  git://git.kernel.org/pub/scm/linux/kernel/git/bigeasy/hotplug-staging.git smp/hotplug

on top of tip/smp/hotplug (which includes last batch and is still on top of
v4.9-rc4).

Sebastian

[PATCH 01/22] cpufreq/acpi-cpufreq: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine.

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 drivers/cpufreq/acpi-cpufreq.c | 93 ++++++++++++++++++++----------------------
 1 file changed, 45 insertions(+), 48 deletions(-)

diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 297e9128fe9f..2c29cbaca7b5 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -536,46 +536,33 @@ static void free_acpi_perf_data(void)
 	free_percpu(acpi_perf_data);
 }
 
-static int boost_notify(struct notifier_block *nb, unsigned long action,
-		      void *hcpu)
+static int cpufreq_boost_online(unsigned int cpu)
+{
+	const struct cpumask *cpumask;
+
+	cpumask = get_cpu_mask(cpu);
+	/*
+	 * On the CPU_UP path we simply keep the boost-disable flag
+	 * in sync with the current global state.
+	 */
+	boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
+	return 0;
+}
+
+static int cpufreq_boost_down_prep(unsigned int cpu)
 {
-	unsigned cpu = (long)hcpu;
 	const struct cpumask *cpumask;
 
 	cpumask = get_cpu_mask(cpu);
 
 	/*
 	 * Clear the boost-disable bit on the CPU_DOWN path so that
-	 * this cpu cannot block the remaining ones from boosting. On
-	 * the CPU_UP path we simply keep the boost-disable flag in
-	 * sync with the current global state.
+	 * this cpu cannot block the remaining ones from boosting.
 	 */
-
-	switch (action) {
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
-		break;
-
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		boost_set_msrs(1, cpumask);
-		break;
-
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
+	boost_set_msrs(1, cpumask);
+	return 0;
 }
 
-
-static struct notifier_block boost_nb = {
-	.notifier_call          = boost_notify,
-};
-
 /*
  * acpi_cpufreq_early_init - initialize ACPI P-States library
  *
@@ -922,37 +909,47 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 	.attr		= acpi_cpufreq_attr,
 };
 
+static enum cpuhp_state acpi_cpufreq_online;
+
 static void __init acpi_cpufreq_boost_init(void)
 {
-	if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) {
-		msrs = msrs_alloc();
+	int ret;
 
-		if (!msrs)
-			return;
+	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
+		return;
 
-		acpi_cpufreq_driver.set_boost = set_boost;
-		acpi_cpufreq_driver.boost_enabled = boost_state(0);
+	msrs = msrs_alloc();
 
-		cpu_notifier_register_begin();
+	if (!msrs)
+		return;
 
-		/* Force all MSRs to the same value */
-		boost_set_msrs(acpi_cpufreq_driver.boost_enabled,
-			       cpu_online_mask);
+	acpi_cpufreq_driver.set_boost = set_boost;
+	acpi_cpufreq_driver.boost_enabled = boost_state(0);
 
-		__register_cpu_notifier(&boost_nb);
-
-		cpu_notifier_register_done();
+	/*
+	 * This calls the online callback on all online cpu and forces all
+	 * MSRs to the same value.
+	 */
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "cpufreq/acpi:online",
+				cpufreq_boost_online, cpufreq_boost_down_prep);
+	if (ret < 0) {
+		pr_err("acpi_cpufreq: failed to register hotplug callbacks\n");
+		msrs_free(msrs);
+		return;
 	}
+	acpi_cpufreq_online = ret;
 }
 
 static void acpi_cpufreq_boost_exit(void)
 {
-	if (msrs) {
-		unregister_cpu_notifier(&boost_nb);
+	if (!msrs)
+		return;
 
-		msrs_free(msrs);
-		msrs = NULL;
-	}
+	if (acpi_cpufreq_online >= 0)
+		cpuhp_remove_state_nocalls(acpi_cpufreq_online);
+
+	msrs_free(msrs);
+	msrs = NULL;
 }
 
 static int __init acpi_cpufreq_init(void)
-- 
2.10.2

Re: [PATCH 01/22] cpufreq/acpi-cpufreq: Convert to hotplug state machine

[Viresh Kumar]

On 27-11-16, 00:13, Sebastian Andrzej Siewior wrote:
> Install the callbacks via the state machine.
> 
> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
> Cc: Viresh Kumar <viresh.kumar@linaro.org>
> Cc: linux-pm@vger.kernel.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
>  drivers/cpufreq/acpi-cpufreq.c | 93 ++++++++++++++++++++----------------------
>  1 file changed, 45 insertions(+), 48 deletions(-)
> 
> diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
> index 297e9128fe9f..2c29cbaca7b5 100644
> --- a/drivers/cpufreq/acpi-cpufreq.c
> +++ b/drivers/cpufreq/acpi-cpufreq.c
> @@ -536,46 +536,33 @@ static void free_acpi_perf_data(void)
>  	free_percpu(acpi_perf_data);
>  }
>  
> -static int boost_notify(struct notifier_block *nb, unsigned long action,
> -		      void *hcpu)
> +static int cpufreq_boost_online(unsigned int cpu)
> +{
> +	const struct cpumask *cpumask;
> +
> +	cpumask = get_cpu_mask(cpu);
> +	/*
> +	 * On the CPU_UP path we simply keep the boost-disable flag
> +	 * in sync with the current global state.
> +	 */
> +	boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
> +	return 0;
> +}
> +
> +static int cpufreq_boost_down_prep(unsigned int cpu)
>  {
> -	unsigned cpu = (long)hcpu;
>  	const struct cpumask *cpumask;
>  
>  	cpumask = get_cpu_mask(cpu);
>  
>  	/*
>  	 * Clear the boost-disable bit on the CPU_DOWN path so that
> -	 * this cpu cannot block the remaining ones from boosting. On
> -	 * the CPU_UP path we simply keep the boost-disable flag in
> -	 * sync with the current global state.
> +	 * this cpu cannot block the remaining ones from boosting.
>  	 */
> -
> -	switch (action) {
> -	case CPU_DOWN_FAILED:
> -	case CPU_DOWN_FAILED_FROZEN:
> -	case CPU_ONLINE:
> -	case CPU_ONLINE_FROZEN:
> -		boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
> -		break;
> -
> -	case CPU_DOWN_PREPARE:
> -	case CPU_DOWN_PREPARE_FROZEN:
> -		boost_set_msrs(1, cpumask);
> -		break;
> -
> -	default:
> -		break;
> -	}
> -
> -	return NOTIFY_OK;
> +	boost_set_msrs(1, cpumask);
> +	return 0;
>  }
>  
> -
> -static struct notifier_block boost_nb = {
> -	.notifier_call          = boost_notify,
> -};
> -
>  /*
>   * acpi_cpufreq_early_init - initialize ACPI P-States library
>   *
> @@ -922,37 +909,47 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
>  	.attr		= acpi_cpufreq_attr,
>  };
>  
> +static enum cpuhp_state acpi_cpufreq_online;
> +
>  static void __init acpi_cpufreq_boost_init(void)
>  {
> -	if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) {
> -		msrs = msrs_alloc();
> +	int ret;
>  
> -		if (!msrs)
> -			return;
> +	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
> +		return;
>  
> -		acpi_cpufreq_driver.set_boost = set_boost;
> -		acpi_cpufreq_driver.boost_enabled = boost_state(0);
> +	msrs = msrs_alloc();
>  
> -		cpu_notifier_register_begin();
> +	if (!msrs)
> +		return;
>  
> -		/* Force all MSRs to the same value */
> -		boost_set_msrs(acpi_cpufreq_driver.boost_enabled,
> -			       cpu_online_mask);

Why isn't this required anymore ?

> +	acpi_cpufreq_driver.set_boost = set_boost;
> +	acpi_cpufreq_driver.boost_enabled = boost_state(0);
>  
> -		__register_cpu_notifier(&boost_nb);
> -
> -		cpu_notifier_register_done();
> +	/*
> +	 * This calls the online callback on all online cpu and forces all
> +	 * MSRs to the same value.
> +	 */
> +	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "cpufreq/acpi:online",
> +				cpufreq_boost_online, cpufreq_boost_down_prep);
> +	if (ret < 0) {
> +		pr_err("acpi_cpufreq: failed to register hotplug callbacks\n");
> +		msrs_free(msrs);

If 'msrs = NULL' is required to be done in the _exit() routine, then it should
be done here as well. Right?

> +		return;
>  	}
> +	acpi_cpufreq_online = ret;
>  }
>  
>  static void acpi_cpufreq_boost_exit(void)
>  {
> -	if (msrs) {
> -		unregister_cpu_notifier(&boost_nb);
> +	if (!msrs)
> +		return;
>  
> -		msrs_free(msrs);
> -		msrs = NULL;
> -	}
> +	if (acpi_cpufreq_online >= 0)
> +		cpuhp_remove_state_nocalls(acpi_cpufreq_online);
> +
> +	msrs_free(msrs);
> +	msrs = NULL;
>  }
>  
>  static int __init acpi_cpufreq_init(void)
> -- 
> 2.10.2

-- 
viresh

Re: [PATCH 01/22] cpufreq/acpi-cpufreq: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

On 2016-11-28 10:45:20 [+0530], Viresh Kumar wrote:
> > diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
> > index 297e9128fe9f..2c29cbaca7b5 100644
> > --- a/drivers/cpufreq/acpi-cpufreq.c
> > +++ b/drivers/cpufreq/acpi-cpufreq.c
> > @@ -922,37 +909,47 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
> >  	.attr		= acpi_cpufreq_attr,
> >  };
> >  
> > +static enum cpuhp_state acpi_cpufreq_online;
> > +
> >  static void __init acpi_cpufreq_boost_init(void)
> >  {
> > -	if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) {
> > -		msrs = msrs_alloc();
> > +	int ret;
> >  
> > -		if (!msrs)
> > -			return;
> > +	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
> > +		return;
> >  
> > -		acpi_cpufreq_driver.set_boost = set_boost;
> > -		acpi_cpufreq_driver.boost_enabled = boost_state(0);
> > +	msrs = msrs_alloc();
> >  
> > -		cpu_notifier_register_begin();
> > +	if (!msrs)
> > +		return;
> >  
> > -		/* Force all MSRs to the same value */
> > -		boost_set_msrs(acpi_cpufreq_driver.boost_enabled,
> > -			       cpu_online_mask);
> 
> Why isn't this required anymore ?

Later there is cpuhp_setup_state() which invokes the online callback
(cpufreq_boost_online) which is doing this.

> > +	acpi_cpufreq_driver.set_boost = set_boost;
> > +	acpi_cpufreq_driver.boost_enabled = boost_state(0);
> >  
> > -		__register_cpu_notifier(&boost_nb);
> > -
> > -		cpu_notifier_register_done();
> > +	/*
> > +	 * This calls the online callback on all online cpu and forces all
> > +	 * MSRs to the same value.
> > +	 */
> > +	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "cpufreq/acpi:online",
> > +				cpufreq_boost_online, cpufreq_boost_down_prep);
> > +	if (ret < 0) {
> > +		pr_err("acpi_cpufreq: failed to register hotplug callbacks\n");
> > +		msrs_free(msrs);
> 
> If 'msrs = NULL' is required to be done in the _exit() routine, then it should
> be done here as well. Right?

It is not required in the exit path, it is just needed here. It is gone
in the following patch anyway but I will post a fixed version.

> > +		return;
> >  	}
> > +	acpi_cpufreq_online = ret;
> >  }
> >  
> >  static void acpi_cpufreq_boost_exit(void)
> >  {
> > -	if (msrs) {
> > -		unregister_cpu_notifier(&boost_nb);
> > +	if (!msrs)
> > +		return;
> >  
> > -		msrs_free(msrs);
> > -		msrs = NULL;
> > -	}
> > +	if (acpi_cpufreq_online >= 0)
> > +		cpuhp_remove_state_nocalls(acpi_cpufreq_online);
> > +
> > +	msrs_free(msrs);
> > +	msrs = NULL;
> >  }
> >  
> >  static int __init acpi_cpufreq_init(void)
> > -- 
> > 2.10.2

Sebastian

[PATCH 01/22 v2] cpufreq/acpi-cpufreq: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine.

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1…v2: set msrs to NULL on error during init.

 drivers/cpufreq/acpi-cpufreq.c |   92 ++++++++++++++++++++---------------------
 1 file changed, 45 insertions(+), 47 deletions(-)

--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -536,46 +536,33 @@ static void free_acpi_perf_data(void)
 	free_percpu(acpi_perf_data);
 }
 
-static int boost_notify(struct notifier_block *nb, unsigned long action,
-		      void *hcpu)
+static int cpufreq_boost_online(unsigned int cpu)
 {
-	unsigned cpu = (long)hcpu;
 	const struct cpumask *cpumask;
 
 	cpumask = get_cpu_mask(cpu);
-
 	/*
-	 * Clear the boost-disable bit on the CPU_DOWN path so that
-	 * this cpu cannot block the remaining ones from boosting. On
-	 * the CPU_UP path we simply keep the boost-disable flag in
-	 * sync with the current global state.
+	 * On the CPU_UP path we simply keep the boost-disable flag
+	 * in sync with the current global state.
 	 */
+	boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
+	return 0;
+}
 
-	switch (action) {
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
-		break;
-
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		boost_set_msrs(1, cpumask);
-		break;
+static int cpufreq_boost_down_prep(unsigned int cpu)
+{
+	const struct cpumask *cpumask;
 
-	default:
-		break;
-	}
+	cpumask = get_cpu_mask(cpu);
 
-	return NOTIFY_OK;
+	/*
+	 * Clear the boost-disable bit on the CPU_DOWN path so that
+	 * this cpu cannot block the remaining ones from boosting.
+	 */
+	boost_set_msrs(1, cpumask);
+	return 0;
 }
 
-
-static struct notifier_block boost_nb = {
-	.notifier_call          = boost_notify,
-};
-
 /*
  * acpi_cpufreq_early_init - initialize ACPI P-States library
  *
@@ -922,37 +909,48 @@ static struct cpufreq_driver acpi_cpufre
 	.attr		= acpi_cpufreq_attr,
 };
 
+static enum cpuhp_state acpi_cpufreq_online;
+
 static void __init acpi_cpufreq_boost_init(void)
 {
-	if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) {
-		msrs = msrs_alloc();
+	int ret;
 
-		if (!msrs)
-			return;
+	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
+		return;
 
-		acpi_cpufreq_driver.set_boost = set_boost;
-		acpi_cpufreq_driver.boost_enabled = boost_state(0);
+	msrs = msrs_alloc();
 
-		cpu_notifier_register_begin();
+	if (!msrs)
+		return;
 
-		/* Force all MSRs to the same value */
-		boost_set_msrs(acpi_cpufreq_driver.boost_enabled,
-			       cpu_online_mask);
+	acpi_cpufreq_driver.set_boost = set_boost;
+	acpi_cpufreq_driver.boost_enabled = boost_state(0);
 
-		__register_cpu_notifier(&boost_nb);
-
-		cpu_notifier_register_done();
+	/*
+	 * This calls the online callback on all online cpu and forces all
+	 * MSRs to the same value.
+	 */
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "cpufreq/acpi:online",
+				cpufreq_boost_online, cpufreq_boost_down_prep);
+	if (ret < 0) {
+		pr_err("acpi_cpufreq: failed to register hotplug callbacks\n");
+		msrs_free(msrs);
+		msrs = NULL;
+		return;
 	}
+	acpi_cpufreq_online = ret;
 }
 
 static void acpi_cpufreq_boost_exit(void)
 {
-	if (msrs) {
-		unregister_cpu_notifier(&boost_nb);
+	if (!msrs)
+		return;
 
-		msrs_free(msrs);
-		msrs = NULL;
-	}
+	if (acpi_cpufreq_online >= 0)
+		cpuhp_remove_state_nocalls(acpi_cpufreq_online);
+
+	msrs_free(msrs);
+	msrs = NULL;
 }
 
 static int __init acpi_cpufreq_init(void)

Re: [PATCH 01/22 v2] cpufreq/acpi-cpufreq: Convert to hotplug state machine

[Viresh Kumar]

On 28-11-16, 10:51, Sebastian Andrzej Siewior wrote:
> Install the callbacks via the state machine.
> 
> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
> Cc: Viresh Kumar <viresh.kumar@linaro.org>
> Cc: linux-pm@vger.kernel.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
> v1…v2: set msrs to NULL on error during init.
> 
>  drivers/cpufreq/acpi-cpufreq.c |   92 ++++++++++++++++++++---------------------
>  1 file changed, 45 insertions(+), 47 deletions(-)

Acked-by: Viresh Kumar <viresh.kumar@linaro.org>

-- 
viresh

Re: [PATCH 01/22 v2] cpufreq/acpi-cpufreq: Convert to hotplug state machine

[Rafael J. Wysocki]

On Mon, Nov 28, 2016 at 10:51 AM, Sebastian Andrzej Siewior
<bigeasy@linutronix.de> wrote:
> Install the callbacks via the state machine.
>
> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
> Cc: Viresh Kumar <viresh.kumar@linaro.org>
> Cc: linux-pm@vger.kernel.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
> v1…v2: set msrs to NULL on error during init.

OK

Let me route this and the [2/22] through the PM tree (they are first
in the series anyway).

Thanks,
Rafael

[PATCH 02/22] cpufreq/acpi-cpufreq: drop rdmsr_on_cpus() usage

[Sebastian Andrzej Siewior]

The online / pre_down callback is invoked on the target CPU since commit
1cf4f629d9d2 ("cpu/hotplug: Move online calls to hotplugged cpu") which means
for the hotplug callback we can use rmdsrl() instead of rdmsr_on_cpus().

This leaves us with set_boost() as the only user which still needs to
read/write the MSR on different CPUs. There is no point in doing that
update on all cpus with the read modify write magic via per cpu data. We
simply can issue a function call on all online CPUs which also means that we
need half that many IPIs.

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 drivers/cpufreq/acpi-cpufreq.c | 58 +++++++++++++++---------------------------
 1 file changed, 20 insertions(+), 38 deletions(-)

diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 2c29cbaca7b5..3a98702b7445 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -84,7 +84,6 @@ static inline struct acpi_processor_performance *to_perf_data(struct acpi_cpufre
 static struct cpufreq_driver acpi_cpufreq_driver;
 
 static unsigned int acpi_pstate_strict;
-static struct msr __percpu *msrs;
 
 static bool boost_state(unsigned int cpu)
 {
@@ -104,11 +103,10 @@ static bool boost_state(unsigned int cpu)
 	return false;
 }
 
-static void boost_set_msrs(bool enable, const struct cpumask *cpumask)
+static int boost_set_msr(bool enable)
 {
-	u32 cpu;
 	u32 msr_addr;
-	u64 msr_mask;
+	u64 msr_mask, val;
 
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_INTEL:
@@ -120,26 +118,31 @@ static void boost_set_msrs(bool enable, const struct cpumask *cpumask)
 		msr_mask = MSR_K7_HWCR_CPB_DIS;
 		break;
 	default:
-		return;
+		return -EINVAL;
 	}
 
-	rdmsr_on_cpus(cpumask, msr_addr, msrs);
+	rdmsrl(msr_addr, val);
 
-	for_each_cpu(cpu, cpumask) {
-		struct msr *reg = per_cpu_ptr(msrs, cpu);
-		if (enable)
-			reg->q &= ~msr_mask;
-		else
-			reg->q |= msr_mask;
-	}
+	if (enable)
+		val &= ~msr_mask;
+	else
+		val |= msr_mask;
 
-	wrmsr_on_cpus(cpumask, msr_addr, msrs);
+	wrmsrl(msr_addr, val);
+	return 0;
+}
+
+static void boost_set_msr_each(void *p_en)
+{
+	bool enable = (bool) p_en;
+
+	boost_set_msr(enable);
 }
 
 static int set_boost(int val)
 {
 	get_online_cpus();
-	boost_set_msrs(val, cpu_online_mask);
+	on_each_cpu(boost_set_msr_each, (void *)(long)val, 1);
 	put_online_cpus();
 	pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis");
 
@@ -538,29 +541,20 @@ static void free_acpi_perf_data(void)
 
 static int cpufreq_boost_online(unsigned int cpu)
 {
-	const struct cpumask *cpumask;
-
-	cpumask = get_cpu_mask(cpu);
 	/*
 	 * On the CPU_UP path we simply keep the boost-disable flag
 	 * in sync with the current global state.
 	 */
-	boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
-	return 0;
+	return boost_set_msr(acpi_cpufreq_driver.boost_enabled);
 }
 
 static int cpufreq_boost_down_prep(unsigned int cpu)
 {
-	const struct cpumask *cpumask;
-
-	cpumask = get_cpu_mask(cpu);
-
 	/*
 	 * Clear the boost-disable bit on the CPU_DOWN path so that
 	 * this cpu cannot block the remaining ones from boosting.
 	 */
-	boost_set_msrs(1, cpumask);
-	return 0;
+	return boost_set_msr(1);
 }
 
 /*
@@ -918,11 +912,6 @@ static void __init acpi_cpufreq_boost_init(void)
 	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
 		return;
 
-	msrs = msrs_alloc();
-
-	if (!msrs)
-		return;
-
 	acpi_cpufreq_driver.set_boost = set_boost;
 	acpi_cpufreq_driver.boost_enabled = boost_state(0);
 
@@ -934,7 +923,6 @@ static void __init acpi_cpufreq_boost_init(void)
 				cpufreq_boost_online, cpufreq_boost_down_prep);
 	if (ret < 0) {
 		pr_err("acpi_cpufreq: failed to register hotplug callbacks\n");
-		msrs_free(msrs);
 		return;
 	}
 	acpi_cpufreq_online = ret;
@@ -942,14 +930,8 @@ static void __init acpi_cpufreq_boost_init(void)
 
 static void acpi_cpufreq_boost_exit(void)
 {
-	if (!msrs)
-		return;
-
 	if (acpi_cpufreq_online >= 0)
 		cpuhp_remove_state_nocalls(acpi_cpufreq_online);
-
-	msrs_free(msrs);
-	msrs = NULL;
 }
 
 static int __init acpi_cpufreq_init(void)
-- 
2.10.2

[PATCH 02/22 v2] cpufreq/acpi-cpufreq: drop rdmsr_on_cpus() usage

[Sebastian Andrzej Siewior]

The online / pre_down callback is invoked on the target CPU since commit
1cf4f629d9d2 ("cpu/hotplug: Move online calls to hotplugged cpu") which means
for the hotplug callback we can use rmdsrl() instead of rdmsr_on_cpus().

This leaves us with set_boost() as the only user which still needs to
read/write the MSR on different CPUs. There is no point in doing that
update on all cpus with the read modify write magic via per cpu data. We
simply can issue a function call on all online CPUs which also means that we
need half that many IPIs.

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1…v2: rebase ontop of the previous patch.

 drivers/cpufreq/acpi-cpufreq.c |   59 +++++++++++++----------------------------
 1 file changed, 20 insertions(+), 39 deletions(-)

--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -84,7 +84,6 @@ static inline struct acpi_processor_perf
 static struct cpufreq_driver acpi_cpufreq_driver;
 
 static unsigned int acpi_pstate_strict;
-static struct msr __percpu *msrs;
 
 static bool boost_state(unsigned int cpu)
 {
@@ -104,11 +103,10 @@ static bool boost_state(unsigned int cpu
 	return false;
 }
 
-static void boost_set_msrs(bool enable, const struct cpumask *cpumask)
+static int boost_set_msr(bool enable)
 {
-	u32 cpu;
 	u32 msr_addr;
-	u64 msr_mask;
+	u64 msr_mask, val;
 
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_INTEL:
@@ -120,26 +118,31 @@ static void boost_set_msrs(bool enable,
 		msr_mask = MSR_K7_HWCR_CPB_DIS;
 		break;
 	default:
-		return;
+		return -EINVAL;
 	}
 
-	rdmsr_on_cpus(cpumask, msr_addr, msrs);
+	rdmsrl(msr_addr, val);
 
-	for_each_cpu(cpu, cpumask) {
-		struct msr *reg = per_cpu_ptr(msrs, cpu);
-		if (enable)
-			reg->q &= ~msr_mask;
-		else
-			reg->q |= msr_mask;
-	}
+	if (enable)
+		val &= ~msr_mask;
+	else
+		val |= msr_mask;
 
-	wrmsr_on_cpus(cpumask, msr_addr, msrs);
+	wrmsrl(msr_addr, val);
+	return 0;
+}
+
+static void boost_set_msr_each(void *p_en)
+{
+	bool enable = (bool) p_en;
+
+	boost_set_msr(enable);
 }
 
 static int set_boost(int val)
 {
 	get_online_cpus();
-	boost_set_msrs(val, cpu_online_mask);
+	on_each_cpu(boost_set_msr_each, (void *)(long)val, 1);
 	put_online_cpus();
 	pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis");
 
@@ -538,29 +541,20 @@ static void free_acpi_perf_data(void)
 
 static int cpufreq_boost_online(unsigned int cpu)
 {
-	const struct cpumask *cpumask;
-
-	cpumask = get_cpu_mask(cpu);
 	/*
 	 * On the CPU_UP path we simply keep the boost-disable flag
 	 * in sync with the current global state.
 	 */
-	boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
-	return 0;
+	return boost_set_msr(acpi_cpufreq_driver.boost_enabled);
 }
 
 static int cpufreq_boost_down_prep(unsigned int cpu)
 {
-	const struct cpumask *cpumask;
-
-	cpumask = get_cpu_mask(cpu);
-
 	/*
 	 * Clear the boost-disable bit on the CPU_DOWN path so that
 	 * this cpu cannot block the remaining ones from boosting.
 	 */
-	boost_set_msrs(1, cpumask);
-	return 0;
+	return boost_set_msr(1);
 }
 
 /*
@@ -918,11 +912,6 @@ static void __init acpi_cpufreq_boost_in
 	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
 		return;
 
-	msrs = msrs_alloc();
-
-	if (!msrs)
-		return;
-
 	acpi_cpufreq_driver.set_boost = set_boost;
 	acpi_cpufreq_driver.boost_enabled = boost_state(0);
 
@@ -934,8 +923,6 @@ static void __init acpi_cpufreq_boost_in
 				cpufreq_boost_online, cpufreq_boost_down_prep);
 	if (ret < 0) {
 		pr_err("acpi_cpufreq: failed to register hotplug callbacks\n");
-		msrs_free(msrs);
-		msrs = NULL;
 		return;
 	}
 	acpi_cpufreq_online = ret;
@@ -943,14 +930,8 @@ static void __init acpi_cpufreq_boost_in
 
 static void acpi_cpufreq_boost_exit(void)
 {
-	if (!msrs)
-		return;
-
 	if (acpi_cpufreq_online >= 0)
 		cpuhp_remove_state_nocalls(acpi_cpufreq_online);
-
-	msrs_free(msrs);
-	msrs = NULL;
 }
 
 static int __init acpi_cpufreq_init(void)

Re: [PATCH 02/22 v2] cpufreq/acpi-cpufreq: drop rdmsr_on_cpus() usage

[Viresh Kumar]

On 28-11-16, 10:52, Sebastian Andrzej Siewior wrote:
> The online / pre_down callback is invoked on the target CPU since commit
> 1cf4f629d9d2 ("cpu/hotplug: Move online calls to hotplugged cpu") which means
> for the hotplug callback we can use rmdsrl() instead of rdmsr_on_cpus().
> 
> This leaves us with set_boost() as the only user which still needs to
> read/write the MSR on different CPUs. There is no point in doing that
> update on all cpus with the read modify write magic via per cpu data. We
> simply can issue a function call on all online CPUs which also means that we
> need half that many IPIs.
> 
> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
> Cc: Viresh Kumar <viresh.kumar@linaro.org>
> Cc: linux-pm@vger.kernel.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
> v1…v2: rebase ontop of the previous patch.

Acked-by: Viresh Kumar <viresh.kumar@linaro.org>

-- 
viresh

[PATCH 03/22] idle/intel: Remove superfluous SMP fuction call

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Since commit 1cf4f629d9d2 ("cpu/hotplug: Move online calls to
hotplugged cpu") the CPU_ONLINE and CPU_DOWN_PREPARE notifiers are
always run on the hot plugged CPU, and as of commit 3b9d6da67e11
("cpu/hotplug: Fix rollback during error-out in __cpu_disable()") the
CPU_DOWN_FAILED notifier also runs on the hot plugged CPU. This patch
converts the SMP functional calls into direct calls.

smp_function_call_single() executes the function with interrupts
disabled. This calling convention is not preserved, because
tick_broadcast_enable() and tick_braodcast_disable() handle
interrupts themselves.

Cc: Len Brown <lenb@kernel.org>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 drivers/idle/intel_idle.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 4466a2f969d7..f53b42a78186 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -927,8 +927,7 @@ static int cpu_hotplug_notify(struct notifier_block *n,
 	case CPU_ONLINE:
 
 		if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
-			smp_call_function_single(hotcpu, __setup_broadcast_timer,
-						 (void *)true, 1);
+			__setup_broadcast_timer((void *)true);
 
 		/*
 		 * Some systems can hotplug a cpu at runtime after
-- 
2.10.2

[PATCH 04/22] idle/intel: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine and let the core invoke the
callbacks on the already online CPUs.

The two smp_call_function_single() invocations in intel_idle_cpu_init() have
been removed because intel_idle_cpu_init() is now invoked via the hotplug
callback which runs on the target CPU. The IRQ-off calling convention for
auto_demotion_disable() and c1e_promotion_disable() has not been preserved
because only those two modify the MSR during CPU intialization.

Cc: Len Brown <lenb@kernel.org>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 drivers/idle/intel_idle.c | 106 ++++++++++++++++++----------------------------
 1 file changed, 42 insertions(+), 64 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index f53b42a78186..d9631db1b4f5 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -98,8 +98,6 @@ static int intel_idle(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv, int index);
 static void intel_idle_freeze(struct cpuidle_device *dev,
 			      struct cpuidle_driver *drv, int index);
-static int intel_idle_cpu_init(int cpu);
-
 static struct cpuidle_state *cpuidle_state_table;
 
 /*
@@ -907,50 +905,15 @@ static void intel_idle_freeze(struct cpuidle_device *dev,
 	mwait_idle_with_hints(eax, ecx);
 }
 
-static void __setup_broadcast_timer(void *arg)
+static void __setup_broadcast_timer(bool on)
 {
-	unsigned long on = (unsigned long)arg;
-
 	if (on)
 		tick_broadcast_enable();
 	else
 		tick_broadcast_disable();
 }
 
-static int cpu_hotplug_notify(struct notifier_block *n,
-			      unsigned long action, void *hcpu)
-{
-	int hotcpu = (unsigned long)hcpu;
-	struct cpuidle_device *dev;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-
-		if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
-			__setup_broadcast_timer((void *)true);
-
-		/*
-		 * Some systems can hotplug a cpu at runtime after
-		 * the kernel has booted, we have to initialize the
-		 * driver in this case
-		 */
-		dev = per_cpu_ptr(intel_idle_cpuidle_devices, hotcpu);
-		if (dev->registered)
-			break;
-
-		if (intel_idle_cpu_init(hotcpu))
-			return NOTIFY_BAD;
-
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block cpu_hotplug_notifier = {
-	.notifier_call = cpu_hotplug_notify,
-};
-
-static void auto_demotion_disable(void *dummy)
+static void auto_demotion_disable(void)
 {
 	unsigned long long msr_bits;
 
@@ -958,7 +921,7 @@ static void auto_demotion_disable(void *dummy)
 	msr_bits &= ~(icpu->auto_demotion_disable_flags);
 	wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
 }
-static void c1e_promotion_disable(void *dummy)
+static void c1e_promotion_disable(void)
 {
 	unsigned long long msr_bits;
 
@@ -1372,12 +1335,11 @@ static void __init intel_idle_cpuidle_driver_init(void)
  * allocate, initialize, register cpuidle_devices
  * @cpu: cpu/core to initialize
  */
-static int intel_idle_cpu_init(int cpu)
+static int intel_idle_cpu_init(unsigned int cpu)
 {
 	struct cpuidle_device *dev;
 
 	dev = per_cpu_ptr(intel_idle_cpuidle_devices, cpu);
-
 	dev->cpu = cpu;
 
 	if (cpuidle_register_device(dev)) {
@@ -1386,17 +1348,38 @@ static int intel_idle_cpu_init(int cpu)
 	}
 
 	if (icpu->auto_demotion_disable_flags)
-		smp_call_function_single(cpu, auto_demotion_disable, NULL, 1);
+		auto_demotion_disable();
 
 	if (icpu->disable_promotion_to_c1e)
-		smp_call_function_single(cpu, c1e_promotion_disable, NULL, 1);
+		c1e_promotion_disable();
 
 	return 0;
 }
 
+static int intel_idle_cpu_online(unsigned int cpu)
+{
+	struct cpuidle_device *dev;
+
+	if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
+		__setup_broadcast_timer(true);
+
+	/*
+	 * Some systems can hotplug a cpu at runtime after
+	 * the kernel has booted, we have to initialize the
+	 * driver in this case
+	 */
+	dev = per_cpu_ptr(intel_idle_cpuidle_devices, cpu);
+	if (!dev->registered)
+		return intel_idle_cpu_init(cpu);
+
+	return 0;
+}
+
+static enum cpuhp_state hp_online;
+
 static int __init intel_idle_init(void)
 {
-	int retval, i;
+	int retval;
 
 	/* Do not load intel_idle at all for now if idle= is passed */
 	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
@@ -1416,35 +1399,30 @@ static int __init intel_idle_init(void)
 		struct cpuidle_driver *drv = cpuidle_get_driver();
 		printk(KERN_DEBUG PREFIX "intel_idle yielding to %s",
 			drv ? drv->name : "none");
-		free_percpu(intel_idle_cpuidle_devices);
-		return retval;
+		goto init_driver_fail;
 	}
 
-	cpu_notifier_register_begin();
-
-	for_each_online_cpu(i) {
-		retval = intel_idle_cpu_init(i);
-		if (retval) {
-			intel_idle_cpuidle_devices_uninit();
-			cpu_notifier_register_done();
-			cpuidle_unregister_driver(&intel_idle_driver);
-			free_percpu(intel_idle_cpuidle_devices);
-			return retval;
-		}
-	}
-	__register_cpu_notifier(&cpu_hotplug_notifier);
-
 	if (boot_cpu_has(X86_FEATURE_ARAT))	/* Always Reliable APIC Timer */
 		lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE;
-	else
-		on_each_cpu(__setup_broadcast_timer, (void *)true, 1);
 
-	cpu_notifier_register_done();
+	retval = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "idle/intel:online",
+				   intel_idle_cpu_online, NULL);
+	if (retval < 0)
+		goto hp_setup_fail;
+	hp_online = retval;
 
 	pr_debug(PREFIX "lapic_timer_reliable_states 0x%x\n",
 		lapic_timer_reliable_states);
 
 	return 0;
+
+hp_setup_fail:
+	intel_idle_cpuidle_devices_uninit();
+	cpuidle_unregister_driver(&intel_idle_driver);
+init_driver_fail:
+	free_percpu(intel_idle_cpuidle_devices);
+	return retval;
+
 }
 device_initcall(intel_idle_init);
 
-- 
2.10.2

Re: [PATCH 04/22] idle/intel: Convert to hotplug state machine

[Thomas Gleixner]

On Sun, 27 Nov 2016, Sebastian Andrzej Siewior wrote:
> +static enum cpuhp_state hp_online;
> +
>  static int __init intel_idle_init(void)
>  {
...

> -	cpu_notifier_register_done();
> +	retval = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "idle/intel:online",
> +				   intel_idle_cpu_online, NULL);
> +	if (retval < 0)
> +		goto hp_setup_fail;
> +	hp_online = retval;

Why do you want to store that. There is no exit function AFAICT.

Thanks,

	tglx

Re: [PATCH 04/22] idle/intel: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

On 2016-11-28 18:29:41 [+0100], Thomas Gleixner wrote:
> Why do you want to store that. There is no exit function AFAICT.

There was one until 02c4fae9ea68 ("drivers/idle: make intel_idle.c
driver more explicitly non-modular"). I am going to remove it…

> Thanks,
> 
> 	tglx

Sebastian

[PATCH 04/22 v2] idle/intel: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine and let the core invoke the
callbacks on the already online CPUs.

The two smp_call_function_single() invocations in intel_idle_cpu_init() have
been removed because intel_idle_cpu_init() is now invoked via the hotplug
callback which runs on the target CPU. The IRQ-off calling convention for
auto_demotion_disable() and c1e_promotion_disable() has not been preserved
because only those two modify the MSR during CPU intialization.

Cc: Len Brown <lenb@kernel.org>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1…v2: drop the superfluous saving of the hotplug state (not a module
anymore).

 drivers/idle/intel_idle.c | 103 ++++++++++++++++++----------------------------
 1 file changed, 39 insertions(+), 64 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index f53b42a78186..df532c4398e5 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -98,8 +98,6 @@ static int intel_idle(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv, int index);
 static void intel_idle_freeze(struct cpuidle_device *dev,
 			      struct cpuidle_driver *drv, int index);
-static int intel_idle_cpu_init(int cpu);
-
 static struct cpuidle_state *cpuidle_state_table;
 
 /*
@@ -907,50 +905,15 @@ static void intel_idle_freeze(struct cpuidle_device *dev,
 	mwait_idle_with_hints(eax, ecx);
 }
 
-static void __setup_broadcast_timer(void *arg)
+static void __setup_broadcast_timer(bool on)
 {
-	unsigned long on = (unsigned long)arg;
-
 	if (on)
 		tick_broadcast_enable();
 	else
 		tick_broadcast_disable();
 }
 
-static int cpu_hotplug_notify(struct notifier_block *n,
-			      unsigned long action, void *hcpu)
-{
-	int hotcpu = (unsigned long)hcpu;
-	struct cpuidle_device *dev;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-
-		if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
-			__setup_broadcast_timer((void *)true);
-
-		/*
-		 * Some systems can hotplug a cpu at runtime after
-		 * the kernel has booted, we have to initialize the
-		 * driver in this case
-		 */
-		dev = per_cpu_ptr(intel_idle_cpuidle_devices, hotcpu);
-		if (dev->registered)
-			break;
-
-		if (intel_idle_cpu_init(hotcpu))
-			return NOTIFY_BAD;
-
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block cpu_hotplug_notifier = {
-	.notifier_call = cpu_hotplug_notify,
-};
-
-static void auto_demotion_disable(void *dummy)
+static void auto_demotion_disable(void)
 {
 	unsigned long long msr_bits;
 
@@ -958,7 +921,7 @@ static void auto_demotion_disable(void *dummy)
 	msr_bits &= ~(icpu->auto_demotion_disable_flags);
 	wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
 }
-static void c1e_promotion_disable(void *dummy)
+static void c1e_promotion_disable(void)
 {
 	unsigned long long msr_bits;
 
@@ -1372,12 +1335,11 @@ static void __init intel_idle_cpuidle_driver_init(void)
  * allocate, initialize, register cpuidle_devices
  * @cpu: cpu/core to initialize
  */
-static int intel_idle_cpu_init(int cpu)
+static int intel_idle_cpu_init(unsigned int cpu)
 {
 	struct cpuidle_device *dev;
 
 	dev = per_cpu_ptr(intel_idle_cpuidle_devices, cpu);
-
 	dev->cpu = cpu;
 
 	if (cpuidle_register_device(dev)) {
@@ -1386,17 +1348,36 @@ static int intel_idle_cpu_init(int cpu)
 	}
 
 	if (icpu->auto_demotion_disable_flags)
-		smp_call_function_single(cpu, auto_demotion_disable, NULL, 1);
+		auto_demotion_disable();
 
 	if (icpu->disable_promotion_to_c1e)
-		smp_call_function_single(cpu, c1e_promotion_disable, NULL, 1);
+		c1e_promotion_disable();
+
+	return 0;
+}
+
+static int intel_idle_cpu_online(unsigned int cpu)
+{
+	struct cpuidle_device *dev;
+
+	if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
+		__setup_broadcast_timer(true);
+
+	/*
+	 * Some systems can hotplug a cpu at runtime after
+	 * the kernel has booted, we have to initialize the
+	 * driver in this case
+	 */
+	dev = per_cpu_ptr(intel_idle_cpuidle_devices, cpu);
+	if (!dev->registered)
+		return intel_idle_cpu_init(cpu);
 
 	return 0;
 }
 
 static int __init intel_idle_init(void)
 {
-	int retval, i;
+	int retval;
 
 	/* Do not load intel_idle at all for now if idle= is passed */
 	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
@@ -1416,35 +1397,29 @@ static int __init intel_idle_init(void)
 		struct cpuidle_driver *drv = cpuidle_get_driver();
 		printk(KERN_DEBUG PREFIX "intel_idle yielding to %s",
 			drv ? drv->name : "none");
-		free_percpu(intel_idle_cpuidle_devices);
-		return retval;
+		goto init_driver_fail;
 	}
 
-	cpu_notifier_register_begin();
-
-	for_each_online_cpu(i) {
-		retval = intel_idle_cpu_init(i);
-		if (retval) {
-			intel_idle_cpuidle_devices_uninit();
-			cpu_notifier_register_done();
-			cpuidle_unregister_driver(&intel_idle_driver);
-			free_percpu(intel_idle_cpuidle_devices);
-			return retval;
-		}
-	}
-	__register_cpu_notifier(&cpu_hotplug_notifier);
-
 	if (boot_cpu_has(X86_FEATURE_ARAT))	/* Always Reliable APIC Timer */
 		lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE;
-	else
-		on_each_cpu(__setup_broadcast_timer, (void *)true, 1);
 
-	cpu_notifier_register_done();
+	retval = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "idle/intel:online",
+				   intel_idle_cpu_online, NULL);
+	if (retval < 0)
+		goto hp_setup_fail;
 
 	pr_debug(PREFIX "lapic_timer_reliable_states 0x%x\n",
 		lapic_timer_reliable_states);
 
 	return 0;
+
+hp_setup_fail:
+	intel_idle_cpuidle_devices_uninit();
+	cpuidle_unregister_driver(&intel_idle_driver);
+init_driver_fail:
+	free_percpu(intel_idle_cpuidle_devices);
+	return retval;
+
 }
 device_initcall(intel_idle_init);
 
-- 
2.10.2

[PATCH 05/22] oprofile/nmi timer: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Cc: Robert Richter <rric@kernel.org>
Cc: oprofile-list@lists.sf.net
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 drivers/oprofile/nmi_timer_int.c | 58 +++++++++++++---------------------------
 1 file changed, 19 insertions(+), 39 deletions(-)

diff --git a/drivers/oprofile/nmi_timer_int.c b/drivers/oprofile/nmi_timer_int.c
index 9559829fb234..e65a576e4032 100644
--- a/drivers/oprofile/nmi_timer_int.c
+++ b/drivers/oprofile/nmi_timer_int.c
@@ -59,25 +59,16 @@ static void nmi_timer_stop_cpu(int cpu)
 		perf_event_disable(event);
 }
 
-static int nmi_timer_cpu_notifier(struct notifier_block *b, unsigned long action,
-				  void *data)
+static int nmi_timer_cpu_online(unsigned int cpu)
 {
-	int cpu = (unsigned long)data;
-	switch (action) {
-	case CPU_DOWN_FAILED:
-	case CPU_ONLINE:
-		nmi_timer_start_cpu(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		nmi_timer_stop_cpu(cpu);
-		break;
-	}
-	return NOTIFY_DONE;
+	nmi_timer_start_cpu(cpu);
+	return 0;
+}
+static int nmi_timer_cpu_predown(unsigned int cpu)
+{
+	nmi_timer_stop_cpu(cpu);
+	return 0;
 }
-
-static struct notifier_block nmi_timer_cpu_nb = {
-	.notifier_call = nmi_timer_cpu_notifier
-};
 
 static int nmi_timer_start(void)
 {
@@ -103,13 +94,14 @@ static void nmi_timer_stop(void)
 	put_online_cpus();
 }
 
+static enum cpuhp_state hp_online;
+
 static void nmi_timer_shutdown(void)
 {
 	struct perf_event *event;
 	int cpu;
 
-	cpu_notifier_register_begin();
-	__unregister_cpu_notifier(&nmi_timer_cpu_nb);
+	cpuhp_remove_state(hp_online);
 	for_each_possible_cpu(cpu) {
 		event = per_cpu(nmi_timer_events, cpu);
 		if (!event)
@@ -118,13 +110,11 @@ static void nmi_timer_shutdown(void)
 		per_cpu(nmi_timer_events, cpu) = NULL;
 		perf_event_release_kernel(event);
 	}
-
-	cpu_notifier_register_done();
 }
 
 static int nmi_timer_setup(void)
 {
-	int cpu, err;
+	int err;
 	u64 period;
 
 	/* clock cycles per tick: */
@@ -132,24 +122,14 @@ static int nmi_timer_setup(void)
 	do_div(period, HZ);
 	nmi_timer_attr.sample_period = period;
 
-	cpu_notifier_register_begin();
-	err = __register_cpu_notifier(&nmi_timer_cpu_nb);
-	if (err)
-		goto out;
-
-	/* can't attach events to offline cpus: */
-	for_each_online_cpu(cpu) {
-		err = nmi_timer_start_cpu(cpu);
-		if (err) {
-			cpu_notifier_register_done();
-			nmi_timer_shutdown();
-			return err;
-		}
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "oprofile/nmi:online",
+				nmi_timer_cpu_online, nmi_timer_cpu_predown);
+	if (err < 0) {
+		nmi_timer_shutdown();
+		return err;
 	}
-
-out:
-	cpu_notifier_register_done();
-	return err;
+	hp_online = err;
+	return 0;
 }
 
 int __init op_nmi_timer_init(struct oprofile_operations *ops)
-- 
2.10.2

[tip:smp/hotplug] oprofile/nmi timer: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  14660b7ea3ca628410bb999d53926ca77973892b
Gitweb:     http://git.kernel.org/tip/14660b7ea3ca628410bb999d53926ca77973892b
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:33 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:34 +0100

oprofile/nmi timer: Convert to hotplug state machine

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: oprofile-list@lists.sf.net
Cc: Robert Richter <rric@kernel.org>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20161126231350.10321-6-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/oprofile/nmi_timer_int.c | 58 +++++++++++++---------------------------
 1 file changed, 19 insertions(+), 39 deletions(-)

diff --git a/drivers/oprofile/nmi_timer_int.c b/drivers/oprofile/nmi_timer_int.c
index 9559829..e65a576 100644
--- a/drivers/oprofile/nmi_timer_int.c
+++ b/drivers/oprofile/nmi_timer_int.c
@@ -59,25 +59,16 @@ static void nmi_timer_stop_cpu(int cpu)
 		perf_event_disable(event);
 }
 
-static int nmi_timer_cpu_notifier(struct notifier_block *b, unsigned long action,
-				  void *data)
+static int nmi_timer_cpu_online(unsigned int cpu)
 {
-	int cpu = (unsigned long)data;
-	switch (action) {
-	case CPU_DOWN_FAILED:
-	case CPU_ONLINE:
-		nmi_timer_start_cpu(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		nmi_timer_stop_cpu(cpu);
-		break;
-	}
-	return NOTIFY_DONE;
+	nmi_timer_start_cpu(cpu);
+	return 0;
+}
+static int nmi_timer_cpu_predown(unsigned int cpu)
+{
+	nmi_timer_stop_cpu(cpu);
+	return 0;
 }
-
-static struct notifier_block nmi_timer_cpu_nb = {
-	.notifier_call = nmi_timer_cpu_notifier
-};
 
 static int nmi_timer_start(void)
 {
@@ -103,13 +94,14 @@ static void nmi_timer_stop(void)
 	put_online_cpus();
 }
 
+static enum cpuhp_state hp_online;
+
 static void nmi_timer_shutdown(void)
 {
 	struct perf_event *event;
 	int cpu;
 
-	cpu_notifier_register_begin();
-	__unregister_cpu_notifier(&nmi_timer_cpu_nb);
+	cpuhp_remove_state(hp_online);
 	for_each_possible_cpu(cpu) {
 		event = per_cpu(nmi_timer_events, cpu);
 		if (!event)
@@ -118,13 +110,11 @@ static void nmi_timer_shutdown(void)
 		per_cpu(nmi_timer_events, cpu) = NULL;
 		perf_event_release_kernel(event);
 	}
-
-	cpu_notifier_register_done();
 }
 
 static int nmi_timer_setup(void)
 {
-	int cpu, err;
+	int err;
 	u64 period;
 
 	/* clock cycles per tick: */
@@ -132,24 +122,14 @@ static int nmi_timer_setup(void)
 	do_div(period, HZ);
 	nmi_timer_attr.sample_period = period;
 
-	cpu_notifier_register_begin();
-	err = __register_cpu_notifier(&nmi_timer_cpu_nb);
-	if (err)
-		goto out;
-
-	/* can't attach events to offline cpus: */
-	for_each_online_cpu(cpu) {
-		err = nmi_timer_start_cpu(cpu);
-		if (err) {
-			cpu_notifier_register_done();
-			nmi_timer_shutdown();
-			return err;
-		}
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "oprofile/nmi:online",
+				nmi_timer_cpu_online, nmi_timer_cpu_predown);
+	if (err < 0) {
+		nmi_timer_shutdown();
+		return err;
 	}
-
-out:
-	cpu_notifier_register_done();
-	return err;
+	hp_online = err;
+	return 0;
 }
 
 int __init op_nmi_timer_init(struct oprofile_operations *ops)

[PATCH 06/22] tracing/rb: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine. The notifier in struct
ring_buffer is replaced by the multi instance interface.  Upon
__ring_buffer_alloc() invocation, cpuhp_state_add_instance() will invoke
the trace_rb_cpu_prepare() on each CPU.

This callback may now fail. This means __ring_buffer_alloc() will fail and
cleanup (like previously) and during a CPU up event this failure will not
allow the CPU to come up.

Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h  |   1 +
 include/linux/ring_buffer.h |   6 ++
 kernel/trace/ring_buffer.c  | 133 +++++++++++++++-----------------------------
 kernel/trace/trace.c        |  15 ++++-
 4 files changed, 65 insertions(+), 90 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index e3771fb959c0..18bcfeb2463e 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -62,6 +62,7 @@ enum cpuhp_state {
 	CPUHP_TOPOLOGY_PREPARE,
 	CPUHP_NET_IUCV_PREPARE,
 	CPUHP_ARM_BL_PREPARE,
+	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 4acc552e9279..b6d4568795a7 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -198,4 +198,10 @@ enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
 };
 
+#ifdef CONFIG_RING_BUFFER
+int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node);
+#else
+#define trace_rb_cpu_prepare	NULL
+#endif
+
 #endif /* _LINUX_RING_BUFFER_H */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9c143739b8d7..a7a055f167c7 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -479,9 +479,7 @@ struct ring_buffer {
 
 	struct ring_buffer_per_cpu	**buffers;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	struct notifier_block		cpu_notify;
-#endif
+	struct hlist_node		node;
 	u64				(*clock)(void);
 
 	struct rb_irq_work		irq_work;
@@ -1274,11 +1272,6 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 	kfree(cpu_buffer);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-static int rb_cpu_notify(struct notifier_block *self,
-			 unsigned long action, void *hcpu);
-#endif
-
 /**
  * __ring_buffer_alloc - allocate a new ring_buffer
  * @size: the size in bytes per cpu that is needed.
@@ -1296,6 +1289,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	long nr_pages;
 	int bsize;
 	int cpu;
+	int ret;
 
 	/* keep it in its own cache line */
 	buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
@@ -1318,17 +1312,6 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (nr_pages < 2)
 		nr_pages = 2;
 
-	/*
-	 * In case of non-hotplug cpu, if the ring-buffer is allocated
-	 * in early initcall, it will not be notified of secondary cpus.
-	 * In that off case, we need to allocate for all possible cpus.
-	 */
-#ifdef CONFIG_HOTPLUG_CPU
-	cpu_notifier_register_begin();
-	cpumask_copy(buffer->cpumask, cpu_online_mask);
-#else
-	cpumask_copy(buffer->cpumask, cpu_possible_mask);
-#endif
 	buffer->cpus = nr_cpu_ids;
 
 	bsize = sizeof(void *) * nr_cpu_ids;
@@ -1337,19 +1320,15 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!buffer->buffers)
 		goto fail_free_cpumask;
 
-	for_each_buffer_cpu(buffer, cpu) {
-		buffer->buffers[cpu] =
-			rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
-		if (!buffer->buffers[cpu])
-			goto fail_free_buffers;
-	}
+	cpu = raw_smp_processor_id();
+	cpumask_set_cpu(cpu, buffer->cpumask);
+	buffer->buffers[cpu] = rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
+	if (!buffer->buffers[cpu])
+		goto fail_free_buffers;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	buffer->cpu_notify.notifier_call = rb_cpu_notify;
-	buffer->cpu_notify.priority = 0;
-	__register_cpu_notifier(&buffer->cpu_notify);
-	cpu_notifier_register_done();
-#endif
+	ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
+	if (ret < 0)
+		goto fail_free_buffers;
 
 	mutex_init(&buffer->mutex);
 
@@ -1364,9 +1343,6 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 
  fail_free_cpumask:
 	free_cpumask_var(buffer->cpumask);
-#ifdef CONFIG_HOTPLUG_CPU
-	cpu_notifier_register_done();
-#endif
 
  fail_free_buffer:
 	kfree(buffer);
@@ -1383,18 +1359,11 @@ ring_buffer_free(struct ring_buffer *buffer)
 {
 	int cpu;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	cpu_notifier_register_begin();
-	__unregister_cpu_notifier(&buffer->cpu_notify);
-#endif
+	cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
 
 	for_each_buffer_cpu(buffer, cpu)
 		rb_free_cpu_buffer(buffer->buffers[cpu]);
 
-#ifdef CONFIG_HOTPLUG_CPU
-	cpu_notifier_register_done();
-#endif
-
 	kfree(buffer->buffers);
 	free_cpumask_var(buffer->cpumask);
 
@@ -4633,62 +4602,48 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
-#ifdef CONFIG_HOTPLUG_CPU
-static int rb_cpu_notify(struct notifier_block *self,
-			 unsigned long action, void *hcpu)
+/*
+ * We only allocate new buffers, never free them if the CPU goes down.
+ * If we were to free the buffer, then the user would lose any trace that was in
+ * the buffer.
+ */
+int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node)
 {
-	struct ring_buffer *buffer =
-		container_of(self, struct ring_buffer, cpu_notify);
-	long cpu = (long)hcpu;
+	struct ring_buffer *buffer;
 	long nr_pages_same;
 	int cpu_i;
 	unsigned long nr_pages;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		if (cpumask_test_cpu(cpu, buffer->cpumask))
-			return NOTIFY_OK;
+	buffer = container_of(node, struct ring_buffer, node);
+	if (cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
 
-		nr_pages = 0;
-		nr_pages_same = 1;
-		/* check if all cpu sizes are same */
-		for_each_buffer_cpu(buffer, cpu_i) {
-			/* fill in the size from first enabled cpu */
-			if (nr_pages == 0)
-				nr_pages = buffer->buffers[cpu_i]->nr_pages;
-			if (nr_pages != buffer->buffers[cpu_i]->nr_pages) {
-				nr_pages_same = 0;
-				break;
-			}
+	nr_pages = 0;
+	nr_pages_same = 1;
+	/* check if all cpu sizes are same */
+	for_each_buffer_cpu(buffer, cpu_i) {
+		/* fill in the size from first enabled cpu */
+		if (nr_pages == 0)
+			nr_pages = buffer->buffers[cpu_i]->nr_pages;
+		if (nr_pages != buffer->buffers[cpu_i]->nr_pages) {
+			nr_pages_same = 0;
+			break;
 		}
-		/* allocate minimum pages, user can later expand it */
-		if (!nr_pages_same)
-			nr_pages = 2;
-		buffer->buffers[cpu] =
-			rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
-		if (!buffer->buffers[cpu]) {
-			WARN(1, "failed to allocate ring buffer on CPU %ld\n",
-			     cpu);
-			return NOTIFY_OK;
-		}
-		smp_wmb();
-		cpumask_set_cpu(cpu, buffer->cpumask);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		/*
-		 * Do nothing.
-		 *  If we were to free the buffer, then the user would
-		 *  lose any trace that was in the buffer.
-		 */
-		break;
-	default:
-		break;
 	}
-	return NOTIFY_OK;
+	/* allocate minimum pages, user can later expand it */
+	if (!nr_pages_same)
+		nr_pages = 2;
+	buffer->buffers[cpu] =
+		rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
+	if (!buffer->buffers[cpu]) {
+		WARN(1, "failed to allocate ring buffer on CPU %u\n",
+		     cpu);
+		return -ENOMEM;
+	}
+	smp_wmb();
+	cpumask_set_cpu(cpu, buffer->cpumask);
+	return 0;
 }
-#endif
 
 #ifdef CONFIG_RING_BUFFER_STARTUP_TEST
 /*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8696ce6bf2f6..465d56febc5b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7659,10 +7659,21 @@ __init static int tracer_alloc_buffers(void)
 
 	raw_spin_lock_init(&global_trace.start_lock);
 
+	/*
+	 * The prepare callbacks allocates some memory for the ring buffer. We
+	 * don't free the buffer if the if the CPU goes down. If we were to free
+	 * the buffer, then the user would lose any trace that was in the
+	 * buffer. The memory will be removed once the "instance" is removed.
+	 */
+	ret = cpuhp_setup_state_multi(CPUHP_TRACE_RB_PREPARE,
+				      "trace/RB:preapre", trace_rb_cpu_prepare,
+				      NULL);
+	if (ret < 0)
+		goto out_free_cpumask;
 	/* Used for event triggers */
 	temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
 	if (!temp_buffer)
-		goto out_free_cpumask;
+		goto out_rm_hp_state;
 
 	if (trace_create_savedcmd() < 0)
 		goto out_free_temp_buffer;
@@ -7723,6 +7734,8 @@ __init static int tracer_alloc_buffers(void)
 	free_saved_cmdlines_buffer(savedcmd);
 out_free_temp_buffer:
 	ring_buffer_free(temp_buffer);
+out_rm_hp_state:
+	cpuhp_remove_multi_state(CPUHP_TRACE_RB_PREPARE);
 out_free_cpumask:
 	free_cpumask_var(global_trace.tracing_cpumask);
 out_free_buffer_mask:
-- 
2.10.2

[tip:smp/hotplug] tracing/rb: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  b32614c03413f8a6025d8677c2b7c0ee976e63d4
Gitweb:     http://git.kernel.org/tip/b32614c03413f8a6025d8677c2b7c0ee976e63d4
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:34 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:34 +0100

tracing/rb: Convert to hotplug state machine

Install the callbacks via the state machine. The notifier in struct
ring_buffer is replaced by the multi instance interface.  Upon
__ring_buffer_alloc() invocation, cpuhp_state_add_instance() will invoke
the trace_rb_cpu_prepare() on each CPU.

This callback may now fail. This means __ring_buffer_alloc() will fail and
cleanup (like previously) and during a CPU up event this failure will not
allow the CPU to come up.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20161126231350.10321-7-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/cpuhotplug.h  |   1 +
 include/linux/ring_buffer.h |   6 ++
 kernel/trace/ring_buffer.c  | 135 +++++++++++++++-----------------------------
 kernel/trace/trace.c        |  15 ++++-
 4 files changed, 66 insertions(+), 91 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index e3771fb..18bcfeb 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -62,6 +62,7 @@ enum cpuhp_state {
 	CPUHP_TOPOLOGY_PREPARE,
 	CPUHP_NET_IUCV_PREPARE,
 	CPUHP_ARM_BL_PREPARE,
+	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 4acc552..b6d4568 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -198,4 +198,10 @@ enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
 };
 
+#ifdef CONFIG_RING_BUFFER
+int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node);
+#else
+#define trace_rb_cpu_prepare	NULL
+#endif
+
 #endif /* _LINUX_RING_BUFFER_H */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9c14373..a7a055f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -479,9 +479,7 @@ struct ring_buffer {
 
 	struct ring_buffer_per_cpu	**buffers;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	struct notifier_block		cpu_notify;
-#endif
+	struct hlist_node		node;
 	u64				(*clock)(void);
 
 	struct rb_irq_work		irq_work;
@@ -1274,11 +1272,6 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 	kfree(cpu_buffer);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-static int rb_cpu_notify(struct notifier_block *self,
-			 unsigned long action, void *hcpu);
-#endif
-
 /**
  * __ring_buffer_alloc - allocate a new ring_buffer
  * @size: the size in bytes per cpu that is needed.
@@ -1296,6 +1289,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	long nr_pages;
 	int bsize;
 	int cpu;
+	int ret;
 
 	/* keep it in its own cache line */
 	buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
@@ -1318,17 +1312,6 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (nr_pages < 2)
 		nr_pages = 2;
 
-	/*
-	 * In case of non-hotplug cpu, if the ring-buffer is allocated
-	 * in early initcall, it will not be notified of secondary cpus.
-	 * In that off case, we need to allocate for all possible cpus.
-	 */
-#ifdef CONFIG_HOTPLUG_CPU
-	cpu_notifier_register_begin();
-	cpumask_copy(buffer->cpumask, cpu_online_mask);
-#else
-	cpumask_copy(buffer->cpumask, cpu_possible_mask);
-#endif
 	buffer->cpus = nr_cpu_ids;
 
 	bsize = sizeof(void *) * nr_cpu_ids;
@@ -1337,19 +1320,15 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!buffer->buffers)
 		goto fail_free_cpumask;
 
-	for_each_buffer_cpu(buffer, cpu) {
-		buffer->buffers[cpu] =
-			rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
-		if (!buffer->buffers[cpu])
-			goto fail_free_buffers;
-	}
+	cpu = raw_smp_processor_id();
+	cpumask_set_cpu(cpu, buffer->cpumask);
+	buffer->buffers[cpu] = rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
+	if (!buffer->buffers[cpu])
+		goto fail_free_buffers;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	buffer->cpu_notify.notifier_call = rb_cpu_notify;
-	buffer->cpu_notify.priority = 0;
-	__register_cpu_notifier(&buffer->cpu_notify);
-	cpu_notifier_register_done();
-#endif
+	ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
+	if (ret < 0)
+		goto fail_free_buffers;
 
 	mutex_init(&buffer->mutex);
 
@@ -1364,9 +1343,6 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 
  fail_free_cpumask:
 	free_cpumask_var(buffer->cpumask);
-#ifdef CONFIG_HOTPLUG_CPU
-	cpu_notifier_register_done();
-#endif
 
  fail_free_buffer:
 	kfree(buffer);
@@ -1383,18 +1359,11 @@ ring_buffer_free(struct ring_buffer *buffer)
 {
 	int cpu;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	cpu_notifier_register_begin();
-	__unregister_cpu_notifier(&buffer->cpu_notify);
-#endif
+	cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
 
 	for_each_buffer_cpu(buffer, cpu)
 		rb_free_cpu_buffer(buffer->buffers[cpu]);
 
-#ifdef CONFIG_HOTPLUG_CPU
-	cpu_notifier_register_done();
-#endif
-
 	kfree(buffer->buffers);
 	free_cpumask_var(buffer->cpumask);
 
@@ -4633,62 +4602,48 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
-#ifdef CONFIG_HOTPLUG_CPU
-static int rb_cpu_notify(struct notifier_block *self,
-			 unsigned long action, void *hcpu)
+/*
+ * We only allocate new buffers, never free them if the CPU goes down.
+ * If we were to free the buffer, then the user would lose any trace that was in
+ * the buffer.
+ */
+int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node)
 {
-	struct ring_buffer *buffer =
-		container_of(self, struct ring_buffer, cpu_notify);
-	long cpu = (long)hcpu;
+	struct ring_buffer *buffer;
 	long nr_pages_same;
 	int cpu_i;
 	unsigned long nr_pages;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		if (cpumask_test_cpu(cpu, buffer->cpumask))
-			return NOTIFY_OK;
-
-		nr_pages = 0;
-		nr_pages_same = 1;
-		/* check if all cpu sizes are same */
-		for_each_buffer_cpu(buffer, cpu_i) {
-			/* fill in the size from first enabled cpu */
-			if (nr_pages == 0)
-				nr_pages = buffer->buffers[cpu_i]->nr_pages;
-			if (nr_pages != buffer->buffers[cpu_i]->nr_pages) {
-				nr_pages_same = 0;
-				break;
-			}
-		}
-		/* allocate minimum pages, user can later expand it */
-		if (!nr_pages_same)
-			nr_pages = 2;
-		buffer->buffers[cpu] =
-			rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
-		if (!buffer->buffers[cpu]) {
-			WARN(1, "failed to allocate ring buffer on CPU %ld\n",
-			     cpu);
-			return NOTIFY_OK;
+	buffer = container_of(node, struct ring_buffer, node);
+	if (cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	nr_pages = 0;
+	nr_pages_same = 1;
+	/* check if all cpu sizes are same */
+	for_each_buffer_cpu(buffer, cpu_i) {
+		/* fill in the size from first enabled cpu */
+		if (nr_pages == 0)
+			nr_pages = buffer->buffers[cpu_i]->nr_pages;
+		if (nr_pages != buffer->buffers[cpu_i]->nr_pages) {
+			nr_pages_same = 0;
+			break;
 		}
-		smp_wmb();
-		cpumask_set_cpu(cpu, buffer->cpumask);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		/*
-		 * Do nothing.
-		 *  If we were to free the buffer, then the user would
-		 *  lose any trace that was in the buffer.
-		 */
-		break;
-	default:
-		break;
 	}
-	return NOTIFY_OK;
+	/* allocate minimum pages, user can later expand it */
+	if (!nr_pages_same)
+		nr_pages = 2;
+	buffer->buffers[cpu] =
+		rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
+	if (!buffer->buffers[cpu]) {
+		WARN(1, "failed to allocate ring buffer on CPU %u\n",
+		     cpu);
+		return -ENOMEM;
+	}
+	smp_wmb();
+	cpumask_set_cpu(cpu, buffer->cpumask);
+	return 0;
 }
-#endif
 
 #ifdef CONFIG_RING_BUFFER_STARTUP_TEST
 /*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8696ce6..465d56f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7659,10 +7659,21 @@ __init static int tracer_alloc_buffers(void)
 
 	raw_spin_lock_init(&global_trace.start_lock);
 
+	/*
+	 * The prepare callbacks allocates some memory for the ring buffer. We
+	 * don't free the buffer if the if the CPU goes down. If we were to free
+	 * the buffer, then the user would lose any trace that was in the
+	 * buffer. The memory will be removed once the "instance" is removed.
+	 */
+	ret = cpuhp_setup_state_multi(CPUHP_TRACE_RB_PREPARE,
+				      "trace/RB:preapre", trace_rb_cpu_prepare,
+				      NULL);
+	if (ret < 0)
+		goto out_free_cpumask;
 	/* Used for event triggers */
 	temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
 	if (!temp_buffer)
-		goto out_free_cpumask;
+		goto out_rm_hp_state;
 
 	if (trace_create_savedcmd() < 0)
 		goto out_free_temp_buffer;
@@ -7723,6 +7734,8 @@ out_free_savedcmd:
 	free_saved_cmdlines_buffer(savedcmd);
 out_free_temp_buffer:
 	ring_buffer_free(temp_buffer);
+out_rm_hp_state:
+	cpuhp_remove_multi_state(CPUHP_TRACE_RB_PREPARE);
 out_free_cpumask:
 	free_cpumask_var(global_trace.tracing_cpumask);
 out_free_buffer_mask:

[linux-next] tracing/rb: NULL pointer dereference at trace_rb_cpu_prepare()

[Tetsuo Handa]

Hello.

----------
[    1.909018] NMI watchdog: disabled (cpu0): hardware events not enabled
[    1.911813] smp: Bringing up secondary CPUs ...
[    1.913965] NMI watchdog: Shutting down hard lockup detector on all cpus
[    1.917208] x86: Booting SMP configuration:
[    1.919148] .... node  #0, CPUs:        #1[    1.921275] Disabled fast string operations
[    1.922792] mce: CPU supports 0 MCE banks
[    1.925033] BUG: unable to handle kernel NULL pointer dereference at 0000000000000068
[    1.928636] IP: trace_rb_cpu_prepare+0xc5/0x170
[    1.930601] PGD 0 [    1.931313]
[    1.932289] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC
[    1.934234] Modules linked in:
[    1.935721] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.9.0-rc8-next-20161207 #5
[    1.939107] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013
[    1.943443] task: ffff88022cff8040 task.stack: ffffc9000000c000
[    1.945860] RIP: 0010:trace_rb_cpu_prepare+0xc5/0x170
[    1.947991] RSP: 0000:ffffc9000000fd20 EFLAGS: 00010202
[    1.950246] RAX: 0000000000000001 RBX: 0000000000000002 RCX: ffff88022e019738
[    1.953094] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88022e077dd8
[    1.955911] RBP: ffffc9000000fd50 R08: 0000000000000040 R09: 0000000000000000
[    1.958711] R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000002
[    1.961586] R13: ffff88022e01ead0 R14: 0000000000000002 R15: 0000000000000001
[    1.964426] FS:  0000000000000000(0000) GS:ffff88022e600000(0000) knlGS:0000000000000000
[    1.967988] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    1.970350] CR2: 0000000000000068 CR3: 0000000001c0c000 CR4: 00000000001406f0
[    1.973206] Call Trace:
[    1.974461]  cpuhp_invoke_callback+0x45f/0x9e0
[    1.976422]  ? ring_buffer_record_is_on+0x20/0x20
[    1.978424]  cpuhp_up_callbacks+0x37/0xb0
[    1.980239]  _cpu_up+0x89/0xf0
[    1.981705]  do_cpu_up+0x85/0xb0
[    1.983230]  cpu_up+0x13/0x20
[    1.984645]  smp_init+0x6b/0xcc
[    1.986157]  kernel_init_freeable+0x17d/0x2b1
[    1.988065]  ? kernel_init+0xe/0x110
[    1.989687]  ? _raw_spin_unlock_irq+0x2c/0x40
[    1.991578]  ? rest_init+0x140/0x140
[    1.993215]  kernel_init+0xe/0x110
[    1.994815]  ret_from_fork+0x2a/0x40
[    1.996482] Code: b9 80 3d 20 7d b2 00 00 75 b0 48 89 7d d0 e8 ec 7e 04 00 44 8b 05 30 76 c1 00 48 8b 7d d0 eb 9a 49 8b 4d f8 48 63 f0 48 8b 34 f1 <4c> 39 76 68 74 bf be 02 00 00 00 4e 8d 3c e1 49 8d bd 38 ff ff
[    2.006837] RIP: trace_rb_cpu_prepare+0xc5/0x170 RSP: ffffc9000000fd20
[    2.009441] CR2: 0000000000000068
[    2.011025] ---[ end trace 7da8119e80594e4e ]---
[    2.013058] Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000009
[    2.013058]
[    2.027641] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000009
[    2.027641]
----------

----------
    4db8:       eb 9a                   jmp    4d54 <trace_rb_cpu_prepare+0x54>
                /* fill in the size from first enabled cpu */
                if (nr_pages == 0)
                        nr_pages = buffer->buffers[cpu_i]->nr_pages;
                if (nr_pages != buffer->buffers[cpu_i]->nr_pages) {
    4dba:       49 8b 4d f8             mov    -0x8(%r13),%rcx
    4dbe:       48 63 f0                movslq %eax,%rsi
    4dc1:       48 8b 34 f1             mov    (%rcx,%rsi,8),%rsi
    4dc5:       4c 39 76 68             cmp    %r14,0x68(%rsi)                    // trace_rb_cpu_prepare+0xc5 is here.
    4dc9:       74 bf                   je     4d8a <trace_rb_cpu_prepare+0x8a>
    4dcb:       be 02 00 00 00          mov    $0x2,%esi
                }
        }
        /* allocate minimum pages, user can later expand it */
----------

Kernel config is at http://I-love.SAKURA.ne.jp/tmp/config-4.9-rc8-next-20161207
and console log is at http://I-love.SAKURA.ne.jp/tmp/serial-20161207.txt.xz .

Regards.

[PATCH] tracing/rb: init the CPU mask on allocation

[Sebastian Andrzej Siewior]

Before commit b32614c03413 ("tracing/rb: Convert to hotplug state
machine") the allocated cpumask was initialized to the mask of ONLINE or
POSSIBLE CPUs. After the CPU hotplug changes the buffer initialisation
moved to trace_rb_cpu_prepare() but I forgot to initially set the
cpumask to zero. This is done now.

Fixes: b32614c03413 ("tracing/rb: Convert to hotplug state machine")
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 kernel/trace/ring_buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 67da107e5712..a85739efcc30 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1297,7 +1297,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!buffer)
 		return NULL;
 
-	if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
 		goto fail_free_buffer;
 
 	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
-- 
2.11.0

[tip:smp/hotplug] tracing/rb: Init the CPU mask on allocation

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  b18cc3de00ec3442cf40ac60787dbe0703b99e24
Gitweb:     http://git.kernel.org/tip/b18cc3de00ec3442cf40ac60787dbe0703b99e24
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Wed, 7 Dec 2016 14:31:33 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Wed, 7 Dec 2016 14:36:21 +0100

tracing/rb: Init the CPU mask on allocation

Before commit b32614c03413 ("tracing/rb: Convert to hotplug state machine")
the allocated cpumask was initialized to the mask of online or possible
CPUs. After the CPU hotplug changes the buffer initialization moved to
trace_rb_cpu_prepare() but the cpumask is allocated with alloc_cpumask()
and therefor has random content. As a consequence the cpu buffers are not
initialized and a later access dereferences a NULL pointer.

Use zalloc_cpumask() instead so trace_rb_cpu_prepare() initializes the
buffers properly.

Fixes: b32614c03413 ("tracing/rb: Convert to hotplug state machine")
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: rostedt@goodmis.org
Link: http://lkml.kernel.org/r/20161207133133.hzkcqfllxcdi3joz@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 kernel/trace/ring_buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a7a055f..89a2611a16 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1297,7 +1297,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!buffer)
 		return NULL;
 
-	if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
 		goto fail_free_buffer;
 
 	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);

Re: [PATCH] tracing/rb: init the CPU mask on allocation

[Tetsuo Handa]

Sebastian Andrzej Siewior wrote:
> Before commit b32614c03413 ("tracing/rb: Convert to hotplug state
> machine") the allocated cpumask was initialized to the mask of ONLINE or
> POSSIBLE CPUs. After the CPU hotplug changes the buffer initialisation
> moved to trace_rb_cpu_prepare() but I forgot to initially set the
> cpumask to zero. This is done now.
> 
> Fixes: b32614c03413 ("tracing/rb: Convert to hotplug state machine")
> Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

The system can boot now. Thank you.

Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>

> ---
>  kernel/trace/ring_buffer.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
> index 67da107e5712..a85739efcc30 100644
> --- a/kernel/trace/ring_buffer.c
> +++ b/kernel/trace/ring_buffer.c
> @@ -1297,7 +1297,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
>  	if (!buffer)
>  		return NULL;
>  
> -	if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
> +	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
>  		goto fail_free_buffer;
>  
>  	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
> -- 
> 2.11.0

[PATCH 07/22] mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()

[Sebastian Andrzej Siewior]

Both functions are called with protection against cpu hotplug already so
*_online_cpus() could be dropped.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 mm/vmstat.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 604f26a4f696..0b63ffb5c407 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1722,24 +1722,19 @@ static void __init init_cpu_node_state(void)
 {
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu)
 		node_set_state(cpu_to_node(cpu), N_CPU);
-	put_online_cpus();
 }
 
 static void vmstat_cpu_dead(int node)
 {
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu)
 		if (cpu_to_node(cpu) == node)
-			goto end;
+			return;
 
 	node_clear_state(node, N_CPU);
-end:
-	put_online_cpus();
 }
 
 /*
-- 
2.10.2

[PATCH 07/22] mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()

[Sebastian Andrzej Siewior]

Both functions are called with protection against cpu hotplug already so
*_online_cpus() could be dropped.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 mm/vmstat.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 604f26a4f696..0b63ffb5c407 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1722,24 +1722,19 @@ static void __init init_cpu_node_state(void)
 {
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu)
 		node_set_state(cpu_to_node(cpu), N_CPU);
-	put_online_cpus();
 }
 
 static void vmstat_cpu_dead(int node)
 {
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu)
 		if (cpu_to_node(cpu) == node)
-			goto end;
+			return;
 
 	node_clear_state(node, N_CPU);
-end:
-	put_online_cpus();
 }
 
 /*
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 07/22] mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()

[Michal Hocko]

On Sun 27-11-16 00:13:35, Sebastian Andrzej Siewior wrote:
> Both functions are called with protection against cpu hotplug already so
> *_online_cpus() could be dropped.
> 
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: linux-mm@kvack.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
>  mm/vmstat.c | 7 +------
>  1 file changed, 1 insertion(+), 6 deletions(-)
> 
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 604f26a4f696..0b63ffb5c407 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1722,24 +1722,19 @@ static void __init init_cpu_node_state(void)
>  {
>  	int cpu;
>  
> -	get_online_cpus();
>  	for_each_online_cpu(cpu)
>  		node_set_state(cpu_to_node(cpu), N_CPU);
> -	put_online_cpus();
>  }
>  
>  static void vmstat_cpu_dead(int node)
>  {
>  	int cpu;
>  
> -	get_online_cpus();
>  	for_each_online_cpu(cpu)
>  		if (cpu_to_node(cpu) == node)
> -			goto end;
> +			return;
>  
>  	node_clear_state(node, N_CPU);
> -end:
> -	put_online_cpus();
>  }
>  
>  /*
> -- 
> 2.10.2
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

-- 
Michal Hocko
SUSE Labs

Re: [PATCH 07/22] mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()

[Michal Hocko]

On Sun 27-11-16 00:13:35, Sebastian Andrzej Siewior wrote:
> Both functions are called with protection against cpu hotplug already so
> *_online_cpus() could be dropped.
> 
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: linux-mm@kvack.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
>  mm/vmstat.c | 7 +------
>  1 file changed, 1 insertion(+), 6 deletions(-)
> 
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 604f26a4f696..0b63ffb5c407 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1722,24 +1722,19 @@ static void __init init_cpu_node_state(void)
>  {
>  	int cpu;
>  
> -	get_online_cpus();
>  	for_each_online_cpu(cpu)
>  		node_set_state(cpu_to_node(cpu), N_CPU);
> -	put_online_cpus();
>  }
>  
>  static void vmstat_cpu_dead(int node)
>  {
>  	int cpu;
>  
> -	get_online_cpus();
>  	for_each_online_cpu(cpu)
>  		if (cpu_to_node(cpu) == node)
> -			goto end;
> +			return;
>  
>  	node_clear_state(node, N_CPU);
> -end:
> -	put_online_cpus();
>  }
>  
>  /*
> -- 
> 2.10.2
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[tip:smp/hotplug] mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  76f290935b1a395ee6c9a14697f16593591d1fe8
Gitweb:     http://git.kernel.org/tip/76f290935b1a395ee6c9a14697f16593591d1fe8
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:35 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:35 +0100

mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()

Both functions are called with protection against cpu hotplug already so
*_online_cpus() could be dropped.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: linux-mm@kvack.org
Cc: rt@linutronix.de
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/20161126231350.10321-8-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 mm/vmstat.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 604f26a..0b63ffb 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1722,24 +1722,19 @@ static void __init init_cpu_node_state(void)
 {
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu)
 		node_set_state(cpu_to_node(cpu), N_CPU);
-	put_online_cpus();
 }
 
 static void vmstat_cpu_dead(int node)
 {
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu)
 		if (cpu_to_node(cpu) == node)
-			goto end;
+			return;
 
 	node_clear_state(node, N_CPU);
-end:
-	put_online_cpus();
 }
 
 /*

[PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Sebastian Andrzej Siewior]

Both iterations over online cpus can be replaced by the proper node
specific functions.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 mm/vmstat.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0b63ffb5c407..b96dcec7e7d7 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1720,19 +1720,19 @@ static void __init start_shepherd_timer(void)
 
 static void __init init_cpu_node_state(void)
 {
-	int cpu;
+	int node;
 
-	for_each_online_cpu(cpu)
-		node_set_state(cpu_to_node(cpu), N_CPU);
+	for_each_online_node(node)
+		node_set_state(node, N_CPU);
 }
 
 static void vmstat_cpu_dead(int node)
 {
-	int cpu;
+	const struct cpumask *node_cpus;
 
-	for_each_online_cpu(cpu)
-		if (cpu_to_node(cpu) == node)
-			return;
+	node_cpus = cpumask_of_node(node);
+	if (cpumask_weight(node_cpus) > 0)
+		return;
 
 	node_clear_state(node, N_CPU);
 }
-- 
2.10.2

[PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Sebastian Andrzej Siewior]

Both iterations over online cpus can be replaced by the proper node
specific functions.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 mm/vmstat.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0b63ffb5c407..b96dcec7e7d7 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1720,19 +1720,19 @@ static void __init start_shepherd_timer(void)
 
 static void __init init_cpu_node_state(void)
 {
-	int cpu;
+	int node;
 
-	for_each_online_cpu(cpu)
-		node_set_state(cpu_to_node(cpu), N_CPU);
+	for_each_online_node(node)
+		node_set_state(node, N_CPU);
 }
 
 static void vmstat_cpu_dead(int node)
 {
-	int cpu;
+	const struct cpumask *node_cpus;
 
-	for_each_online_cpu(cpu)
-		if (cpu_to_node(cpu) == node)
-			return;
+	node_cpus = cpumask_of_node(node);
+	if (cpumask_weight(node_cpus) > 0)
+		return;
 
 	node_clear_state(node, N_CPU);
 }
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Michal Hocko]

On Sun 27-11-16 00:13:36, Sebastian Andrzej Siewior wrote:
[...]
>  static void __init init_cpu_node_state(void)
>  {
> -	int cpu;
> +	int node;
>  
> -	for_each_online_cpu(cpu)
> -		node_set_state(cpu_to_node(cpu), N_CPU);
> +	for_each_online_node(node)
> +		node_set_state(node, N_CPU);

Is this really correct? The point of the original code was to mark only
those nodes which have at least one CPU. Or am I missing something?

>  }
>  
>  static void vmstat_cpu_dead(int node)
>  {
> -	int cpu;
> +	const struct cpumask *node_cpus;
>  
> -	for_each_online_cpu(cpu)
> -		if (cpu_to_node(cpu) == node)
> -			return;
> +	node_cpus = cpumask_of_node(node);
> +	if (cpumask_weight(node_cpus) > 0)
> +		return;

This looks OK

>  
>  	node_clear_state(node, N_CPU);
>  }
> -- 
> 2.10.2
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

-- 
Michal Hocko
SUSE Labs

Re: [PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Michal Hocko]

On Sun 27-11-16 00:13:36, Sebastian Andrzej Siewior wrote:
[...]
>  static void __init init_cpu_node_state(void)
>  {
> -	int cpu;
> +	int node;
>  
> -	for_each_online_cpu(cpu)
> -		node_set_state(cpu_to_node(cpu), N_CPU);
> +	for_each_online_node(node)
> +		node_set_state(node, N_CPU);

Is this really correct? The point of the original code was to mark only
those nodes which have at least one CPU. Or am I missing something?

>  }
>  
>  static void vmstat_cpu_dead(int node)
>  {
> -	int cpu;
> +	const struct cpumask *node_cpus;
>  
> -	for_each_online_cpu(cpu)
> -		if (cpu_to_node(cpu) == node)
> -			return;
> +	node_cpus = cpumask_of_node(node);
> +	if (cpumask_weight(node_cpus) > 0)
> +		return;

This looks OK

>  
>  	node_clear_state(node, N_CPU);
>  }
> -- 
> 2.10.2
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Thomas Gleixner]

On Mon, 28 Nov 2016, Michal Hocko wrote:
> On Sun 27-11-16 00:13:36, Sebastian Andrzej Siewior wrote:
> [...]
> >  static void __init init_cpu_node_state(void)
> >  {
> > -	int cpu;
> > +	int node;
> >  
> > -	for_each_online_cpu(cpu)
> > -		node_set_state(cpu_to_node(cpu), N_CPU);
> > +	for_each_online_node(node)
> > +		node_set_state(node, N_CPU);
> 
> Is this really correct? The point of the original code was to mark only
> those nodes which have at least one CPU. Or am I missing something?

You're right. An online node does not necessarily have an online CPU.

	for_each_online_node(node) {
		if (cpumask_weight(cpumask_of_node(node)) > 0)
			node_set_state(node, N_CPU);
	}

is probably more correct.

Thanks,

	tglx

Re: [PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Thomas Gleixner]

On Mon, 28 Nov 2016, Michal Hocko wrote:
> On Sun 27-11-16 00:13:36, Sebastian Andrzej Siewior wrote:
> [...]
> >  static void __init init_cpu_node_state(void)
> >  {
> > -	int cpu;
> > +	int node;
> >  
> > -	for_each_online_cpu(cpu)
> > -		node_set_state(cpu_to_node(cpu), N_CPU);
> > +	for_each_online_node(node)
> > +		node_set_state(node, N_CPU);
> 
> Is this really correct? The point of the original code was to mark only
> those nodes which have at least one CPU. Or am I missing something?

You're right. An online node does not necessarily have an online CPU.

	for_each_online_node(node) {
		if (cpumask_weight(cpumask_of_node(node)) > 0)
			node_set_state(node, N_CPU);
	}

is probably more correct.

Thanks,

	tglx

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Michal Hocko]

On Tue 29-11-16 15:08:10, Thomas Gleixner wrote:
> On Mon, 28 Nov 2016, Michal Hocko wrote:
> > On Sun 27-11-16 00:13:36, Sebastian Andrzej Siewior wrote:
> > [...]
> > >  static void __init init_cpu_node_state(void)
> > >  {
> > > -	int cpu;
> > > +	int node;
> > >  
> > > -	for_each_online_cpu(cpu)
> > > -		node_set_state(cpu_to_node(cpu), N_CPU);
> > > +	for_each_online_node(node)
> > > +		node_set_state(node, N_CPU);
> > 
> > Is this really correct? The point of the original code was to mark only
> > those nodes which have at least one CPU. Or am I missing something?
> 
> You're right. An online node does not necessarily have an online CPU.
> 
> 	for_each_online_node(node) {
> 		if (cpumask_weight(cpumask_of_node(node)) > 0)
> 			node_set_state(node, N_CPU);
> 	}
> 
> is probably more correct.

Yes, this looks correct. Considering that the same cpumask_weight is
used in another function I guess a small helper would be nice. E.g.
bool node_has_cpus(int node)
{
	return cpumask_weight(cpumask_of_node(node)) > 0;
}

-- 
Michal Hocko
SUSE Labs

Re: [PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Michal Hocko]

On Tue 29-11-16 15:08:10, Thomas Gleixner wrote:
> On Mon, 28 Nov 2016, Michal Hocko wrote:
> > On Sun 27-11-16 00:13:36, Sebastian Andrzej Siewior wrote:
> > [...]
> > >  static void __init init_cpu_node_state(void)
> > >  {
> > > -	int cpu;
> > > +	int node;
> > >  
> > > -	for_each_online_cpu(cpu)
> > > -		node_set_state(cpu_to_node(cpu), N_CPU);
> > > +	for_each_online_node(node)
> > > +		node_set_state(node, N_CPU);
> > 
> > Is this really correct? The point of the original code was to mark only
> > those nodes which have at least one CPU. Or am I missing something?
> 
> You're right. An online node does not necessarily have an online CPU.
> 
> 	for_each_online_node(node) {
> 		if (cpumask_weight(cpumask_of_node(node)) > 0)
> 			node_set_state(node, N_CPU);
> 	}
> 
> is probably more correct.

Yes, this looks correct. Considering that the same cpumask_weight is
used in another function I guess a small helper would be nice. E.g.
bool node_has_cpus(int node)
{
	return cpumask_weight(cpumask_of_node(node)) > 0;
}

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 08/22 v2] mm/vmstat: Avoid on each online CPU loops

[Sebastian Andrzej Siewior]

Both iterations over online cpus can be replaced by the proper node
specific functions.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1…v2: take into account that we may have online nodes with no CPUs.

 mm/vmstat.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0b63ffb5c407..5152cd1c490f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1720,19 +1720,21 @@ static void __init start_shepherd_timer(void)
 
 static void __init init_cpu_node_state(void)
 {
-	int cpu;
+	int node;
 
-	for_each_online_cpu(cpu)
-		node_set_state(cpu_to_node(cpu), N_CPU);
+	for_each_online_node(node) {
+		if (cpumask_weight(cpumask_of_node(node)) > 0)
+			node_set_state(node, N_CPU);
+	}
 }
 
 static void vmstat_cpu_dead(int node)
 {
-	int cpu;
+	const struct cpumask *node_cpus;
 
-	for_each_online_cpu(cpu)
-		if (cpu_to_node(cpu) == node)
-			return;
+	node_cpus = cpumask_of_node(node);
+	if (cpumask_weight(node_cpus) > 0)
+		return;
 
 	node_clear_state(node, N_CPU);
 }
-- 
2.10.2

[PATCH 08/22 v2] mm/vmstat: Avoid on each online CPU loops

[Sebastian Andrzej Siewior]

Both iterations over online cpus can be replaced by the proper node
specific functions.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1…v2: take into account that we may have online nodes with no CPUs.

 mm/vmstat.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0b63ffb5c407..5152cd1c490f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1720,19 +1720,21 @@ static void __init start_shepherd_timer(void)
 
 static void __init init_cpu_node_state(void)
 {
-	int cpu;
+	int node;
 
-	for_each_online_cpu(cpu)
-		node_set_state(cpu_to_node(cpu), N_CPU);
+	for_each_online_node(node) {
+		if (cpumask_weight(cpumask_of_node(node)) > 0)
+			node_set_state(node, N_CPU);
+	}
 }
 
 static void vmstat_cpu_dead(int node)
 {
-	int cpu;
+	const struct cpumask *node_cpus;
 
-	for_each_online_cpu(cpu)
-		if (cpu_to_node(cpu) == node)
-			return;
+	node_cpus = cpumask_of_node(node);
+	if (cpumask_weight(node_cpus) > 0)
+		return;
 
 	node_clear_state(node, N_CPU);
 }
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 08/22 v2] mm/vmstat: Avoid on each online CPU loops

[Michal Hocko]

On Tue 29-11-16 15:51:14, Sebastian Andrzej Siewior wrote:
> Both iterations over online cpus can be replaced by the proper node
> specific functions.
> 
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: linux-mm@kvack.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
> v1…v2: take into account that we may have online nodes with no CPUs.
> 
>  mm/vmstat.c | 16 +++++++++-------
>  1 file changed, 9 insertions(+), 7 deletions(-)
> 
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 0b63ffb5c407..5152cd1c490f 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1720,19 +1720,21 @@ static void __init start_shepherd_timer(void)
>  
>  static void __init init_cpu_node_state(void)
>  {
> -	int cpu;
> +	int node;
>  
> -	for_each_online_cpu(cpu)
> -		node_set_state(cpu_to_node(cpu), N_CPU);
> +	for_each_online_node(node) {
> +		if (cpumask_weight(cpumask_of_node(node)) > 0)
> +			node_set_state(node, N_CPU);
> +	}
>  }
>  
>  static void vmstat_cpu_dead(int node)
>  {
> -	int cpu;
> +	const struct cpumask *node_cpus;
>  
> -	for_each_online_cpu(cpu)
> -		if (cpu_to_node(cpu) == node)
> -			return;
> +	node_cpus = cpumask_of_node(node);
> +	if (cpumask_weight(node_cpus) > 0)
> +		return;
>  
>  	node_clear_state(node, N_CPU);
>  }
> -- 
> 2.10.2

-- 
Michal Hocko
SUSE Labs

Re: [PATCH 08/22 v2] mm/vmstat: Avoid on each online CPU loops

[Michal Hocko]

On Tue 29-11-16 15:51:14, Sebastian Andrzej Siewior wrote:
> Both iterations over online cpus can be replaced by the proper node
> specific functions.
> 
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: linux-mm@kvack.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
> v1a?|v2: take into account that we may have online nodes with no CPUs.
> 
>  mm/vmstat.c | 16 +++++++++-------
>  1 file changed, 9 insertions(+), 7 deletions(-)
> 
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 0b63ffb5c407..5152cd1c490f 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1720,19 +1720,21 @@ static void __init start_shepherd_timer(void)
>  
>  static void __init init_cpu_node_state(void)
>  {
> -	int cpu;
> +	int node;
>  
> -	for_each_online_cpu(cpu)
> -		node_set_state(cpu_to_node(cpu), N_CPU);
> +	for_each_online_node(node) {
> +		if (cpumask_weight(cpumask_of_node(node)) > 0)
> +			node_set_state(node, N_CPU);
> +	}
>  }
>  
>  static void vmstat_cpu_dead(int node)
>  {
> -	int cpu;
> +	const struct cpumask *node_cpus;
>  
> -	for_each_online_cpu(cpu)
> -		if (cpu_to_node(cpu) == node)
> -			return;
> +	node_cpus = cpumask_of_node(node);
> +	if (cpumask_weight(node_cpus) > 0)
> +		return;
>  
>  	node_clear_state(node, N_CPU);
>  }
> -- 
> 2.10.2

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[tip:smp/hotplug] mm/vmstat: Avoid on each online CPU loops

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  4c501327b4c67f2b874219f20c41d2619b49c78c
Gitweb:     http://git.kernel.org/tip/4c501327b4c67f2b874219f20c41d2619b49c78c
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Tue, 29 Nov 2016 15:51:14 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:35 +0100

mm/vmstat: Avoid on each online CPU loops

Both iterations over online cpus can be replaced by the proper node
specific functions.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: linux-mm@kvack.org
Cc: rt@linutronix.de
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/20161129145113.fn3lw5aazjjvdrr3@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 mm/vmstat.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0b63ffb..5152cd1 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1720,19 +1720,21 @@ static void __init start_shepherd_timer(void)
 
 static void __init init_cpu_node_state(void)
 {
-	int cpu;
+	int node;
 
-	for_each_online_cpu(cpu)
-		node_set_state(cpu_to_node(cpu), N_CPU);
+	for_each_online_node(node) {
+		if (cpumask_weight(cpumask_of_node(node)) > 0)
+			node_set_state(node, N_CPU);
+	}
 }
 
 static void vmstat_cpu_dead(int node)
 {
-	int cpu;
+	const struct cpumask *node_cpus;
 
-	for_each_online_cpu(cpu)
-		if (cpu_to_node(cpu) == node)
-			return;
+	node_cpus = cpumask_of_node(node);
+	if (cpumask_weight(node_cpus) > 0)
+		return;
 
 	node_clear_state(node, N_CPU);
 }

[PATCH 09/22] mm/vmstat: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine, but do not invoke them as we
can initialize the node state without calling the callbacks on all online
CPUs.

start_shepherd_timer() is now called outside the get_online_cpus() block
which is safe as it only operates on cpu possible mask.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/vmstat.c                | 76 +++++++++++++++++++++-------------------------
 2 files changed, 36 insertions(+), 41 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 18bcfeb2463e..4ebd1bc27f8d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -20,6 +20,7 @@ enum cpuhp_state {
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
+	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
 	CPUHP_CPUIDLE_DEAD,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b96dcec7e7d7..dfe3cb9f2c36 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1726,64 +1726,58 @@ static void __init init_cpu_node_state(void)
 		node_set_state(node, N_CPU);
 }
 
-static void vmstat_cpu_dead(int node)
+static int vmstat_cpu_online(unsigned int cpu)
+{
+	refresh_zone_stat_thresholds();
+	node_set_state(cpu_to_node(cpu), N_CPU);
+	return 0;
+}
+
+static int vmstat_cpu_down_prep(unsigned int cpu)
+{
+	cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+	return 0;
+}
+
+static int vmstat_cpu_dead(unsigned int cpu)
 {
 	const struct cpumask *node_cpus;
+	int node;
 
+	node = cpu_to_node(cpu);
+
+	refresh_zone_stat_thresholds();
 	node_cpus = cpumask_of_node(node);
 	if (cpumask_weight(node_cpus) > 0)
-		return;
+		return 0;
 
 	node_clear_state(node, N_CPU);
+	return 0;
 }
 
-/*
- * Use the cpu notifier to insure that the thresholds are recalculated
- * when necessary.
- */
-static int vmstat_cpuup_callback(struct notifier_block *nfb,
-		unsigned long action,
-		void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		refresh_zone_stat_thresholds();
-		node_set_state(cpu_to_node(cpu), N_CPU);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		break;
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		refresh_zone_stat_thresholds();
-		vmstat_cpu_dead(cpu_to_node(cpu));
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block vmstat_notifier =
-	{ &vmstat_cpuup_callback, NULL, 0 };
 #endif
 
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	cpu_notifier_register_begin();
-	__register_cpu_notifier(&vmstat_notifier);
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
+					NULL, vmstat_cpu_dead);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'dead' hotplug state\n");
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/vmstat:online",
+					vmstat_cpu_online,
+					vmstat_cpu_down_prep);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'online' hotplug state\n");
+
+	get_online_cpus();
 	init_cpu_node_state();
+	put_online_cpus();
 
 	start_shepherd_timer();
-	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
-- 
2.10.2

[PATCH 09/22] mm/vmstat: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine, but do not invoke them as we
can initialize the node state without calling the callbacks on all online
CPUs.

start_shepherd_timer() is now called outside the get_online_cpus() block
which is safe as it only operates on cpu possible mask.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/vmstat.c                | 76 +++++++++++++++++++++-------------------------
 2 files changed, 36 insertions(+), 41 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 18bcfeb2463e..4ebd1bc27f8d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -20,6 +20,7 @@ enum cpuhp_state {
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
+	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
 	CPUHP_CPUIDLE_DEAD,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b96dcec7e7d7..dfe3cb9f2c36 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1726,64 +1726,58 @@ static void __init init_cpu_node_state(void)
 		node_set_state(node, N_CPU);
 }
 
-static void vmstat_cpu_dead(int node)
+static int vmstat_cpu_online(unsigned int cpu)
+{
+	refresh_zone_stat_thresholds();
+	node_set_state(cpu_to_node(cpu), N_CPU);
+	return 0;
+}
+
+static int vmstat_cpu_down_prep(unsigned int cpu)
+{
+	cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+	return 0;
+}
+
+static int vmstat_cpu_dead(unsigned int cpu)
 {
 	const struct cpumask *node_cpus;
+	int node;
 
+	node = cpu_to_node(cpu);
+
+	refresh_zone_stat_thresholds();
 	node_cpus = cpumask_of_node(node);
 	if (cpumask_weight(node_cpus) > 0)
-		return;
+		return 0;
 
 	node_clear_state(node, N_CPU);
+	return 0;
 }
 
-/*
- * Use the cpu notifier to insure that the thresholds are recalculated
- * when necessary.
- */
-static int vmstat_cpuup_callback(struct notifier_block *nfb,
-		unsigned long action,
-		void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		refresh_zone_stat_thresholds();
-		node_set_state(cpu_to_node(cpu), N_CPU);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		break;
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		refresh_zone_stat_thresholds();
-		vmstat_cpu_dead(cpu_to_node(cpu));
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block vmstat_notifier =
-	{ &vmstat_cpuup_callback, NULL, 0 };
 #endif
 
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	cpu_notifier_register_begin();
-	__register_cpu_notifier(&vmstat_notifier);
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
+					NULL, vmstat_cpu_dead);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'dead' hotplug state\n");
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/vmstat:online",
+					vmstat_cpu_online,
+					vmstat_cpu_down_prep);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'online' hotplug state\n");
+
+	get_online_cpus();
 	init_cpu_node_state();
+	put_online_cpus();
 
 	start_shepherd_timer();
-	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 09/22 v2] mm/vmstat: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine, but do not invoke them as we
can initialize the node state without calling the callbacks on all online
CPUs.

start_shepherd_timer() is now called outside the get_online_cpus() block
which is safe as it only operates on cpu possible mask.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
v1…v2: rebase on top of PATCH 08/22 v2.

 include/linux/cpuhotplug.h |  1 +
 mm/vmstat.c                | 76 +++++++++++++++++++++-------------------------
 2 files changed, 36 insertions(+), 41 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 18bcfeb2463e..4ebd1bc27f8d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -20,6 +20,7 @@ enum cpuhp_state {
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
+	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
 	CPUHP_CPUIDLE_DEAD,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 5152cd1c490f..7c28df36f50f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1728,64 +1728,58 @@ static void __init init_cpu_node_state(void)
 	}
 }
 
-static void vmstat_cpu_dead(int node)
+static int vmstat_cpu_online(unsigned int cpu)
+{
+	refresh_zone_stat_thresholds();
+	node_set_state(cpu_to_node(cpu), N_CPU);
+	return 0;
+}
+
+static int vmstat_cpu_down_prep(unsigned int cpu)
+{
+	cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+	return 0;
+}
+
+static int vmstat_cpu_dead(unsigned int cpu)
 {
 	const struct cpumask *node_cpus;
+	int node;
 
+	node = cpu_to_node(cpu);
+
+	refresh_zone_stat_thresholds();
 	node_cpus = cpumask_of_node(node);
 	if (cpumask_weight(node_cpus) > 0)
-		return;
+		return 0;
 
 	node_clear_state(node, N_CPU);
+	return 0;
 }
 
-/*
- * Use the cpu notifier to insure that the thresholds are recalculated
- * when necessary.
- */
-static int vmstat_cpuup_callback(struct notifier_block *nfb,
-		unsigned long action,
-		void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		refresh_zone_stat_thresholds();
-		node_set_state(cpu_to_node(cpu), N_CPU);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		break;
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		refresh_zone_stat_thresholds();
-		vmstat_cpu_dead(cpu_to_node(cpu));
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block vmstat_notifier =
-	{ &vmstat_cpuup_callback, NULL, 0 };
 #endif
 
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	cpu_notifier_register_begin();
-	__register_cpu_notifier(&vmstat_notifier);
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
+					NULL, vmstat_cpu_dead);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'dead' hotplug state\n");
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/vmstat:online",
+					vmstat_cpu_online,
+					vmstat_cpu_down_prep);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'online' hotplug state\n");
+
+	get_online_cpus();
 	init_cpu_node_state();
+	put_online_cpus();
 
 	start_shepherd_timer();
-	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
-- 
2.10.2

[PATCH 09/22 v2] mm/vmstat: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine, but do not invoke them as we
can initialize the node state without calling the callbacks on all online
CPUs.

start_shepherd_timer() is now called outside the get_online_cpus() block
which is safe as it only operates on cpu possible mask.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
v1…v2: rebase on top of PATCH 08/22 v2.

 include/linux/cpuhotplug.h |  1 +
 mm/vmstat.c                | 76 +++++++++++++++++++++-------------------------
 2 files changed, 36 insertions(+), 41 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 18bcfeb2463e..4ebd1bc27f8d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -20,6 +20,7 @@ enum cpuhp_state {
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
+	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
 	CPUHP_CPUIDLE_DEAD,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 5152cd1c490f..7c28df36f50f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1728,64 +1728,58 @@ static void __init init_cpu_node_state(void)
 	}
 }
 
-static void vmstat_cpu_dead(int node)
+static int vmstat_cpu_online(unsigned int cpu)
+{
+	refresh_zone_stat_thresholds();
+	node_set_state(cpu_to_node(cpu), N_CPU);
+	return 0;
+}
+
+static int vmstat_cpu_down_prep(unsigned int cpu)
+{
+	cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+	return 0;
+}
+
+static int vmstat_cpu_dead(unsigned int cpu)
 {
 	const struct cpumask *node_cpus;
+	int node;
 
+	node = cpu_to_node(cpu);
+
+	refresh_zone_stat_thresholds();
 	node_cpus = cpumask_of_node(node);
 	if (cpumask_weight(node_cpus) > 0)
-		return;
+		return 0;
 
 	node_clear_state(node, N_CPU);
+	return 0;
 }
 
-/*
- * Use the cpu notifier to insure that the thresholds are recalculated
- * when necessary.
- */
-static int vmstat_cpuup_callback(struct notifier_block *nfb,
-		unsigned long action,
-		void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		refresh_zone_stat_thresholds();
-		node_set_state(cpu_to_node(cpu), N_CPU);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		break;
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		refresh_zone_stat_thresholds();
-		vmstat_cpu_dead(cpu_to_node(cpu));
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block vmstat_notifier =
-	{ &vmstat_cpuup_callback, NULL, 0 };
 #endif
 
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	cpu_notifier_register_begin();
-	__register_cpu_notifier(&vmstat_notifier);
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
+					NULL, vmstat_cpu_dead);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'dead' hotplug state\n");
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/vmstat:online",
+					vmstat_cpu_online,
+					vmstat_cpu_down_prep);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'online' hotplug state\n");
+
+	get_online_cpus();
 	init_cpu_node_state();
+	put_online_cpus();
 
 	start_shepherd_timer();
-	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[tip:smp/hotplug] mm/vmstat: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  5438da977f83c945d4e72ee4f9c4508c0eb64e15
Gitweb:     http://git.kernel.org/tip/5438da977f83c945d4e72ee4f9c4508c0eb64e15
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Tue, 29 Nov 2016 15:52:21 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:35 +0100

mm/vmstat: Convert to hotplug state machine

Install the callbacks via the state machine, but do not invoke them as we
can initialize the node state without calling the callbacks on all online
CPUs.

start_shepherd_timer() is now called outside the get_online_cpus() block
which is safe as it only operates on cpu possible mask.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
Cc: rt@linutronix.de
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/20161129145221.ffc3kg3hd7lxiwj6@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/cpuhotplug.h |  1 +
 mm/vmstat.c                | 76 +++++++++++++++++++++-------------------------
 2 files changed, 36 insertions(+), 41 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 18bcfeb..4ebd1bc 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -20,6 +20,7 @@ enum cpuhp_state {
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
+	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
 	CPUHP_CPUIDLE_DEAD,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 5152cd1..7c28df3 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1728,64 +1728,58 @@ static void __init init_cpu_node_state(void)
 	}
 }
 
-static void vmstat_cpu_dead(int node)
+static int vmstat_cpu_online(unsigned int cpu)
+{
+	refresh_zone_stat_thresholds();
+	node_set_state(cpu_to_node(cpu), N_CPU);
+	return 0;
+}
+
+static int vmstat_cpu_down_prep(unsigned int cpu)
+{
+	cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+	return 0;
+}
+
+static int vmstat_cpu_dead(unsigned int cpu)
 {
 	const struct cpumask *node_cpus;
+	int node;
 
+	node = cpu_to_node(cpu);
+
+	refresh_zone_stat_thresholds();
 	node_cpus = cpumask_of_node(node);
 	if (cpumask_weight(node_cpus) > 0)
-		return;
+		return 0;
 
 	node_clear_state(node, N_CPU);
+	return 0;
 }
 
-/*
- * Use the cpu notifier to insure that the thresholds are recalculated
- * when necessary.
- */
-static int vmstat_cpuup_callback(struct notifier_block *nfb,
-		unsigned long action,
-		void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		refresh_zone_stat_thresholds();
-		node_set_state(cpu_to_node(cpu), N_CPU);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		break;
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		refresh_zone_stat_thresholds();
-		vmstat_cpu_dead(cpu_to_node(cpu));
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block vmstat_notifier =
-	{ &vmstat_cpuup_callback, NULL, 0 };
 #endif
 
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	cpu_notifier_register_begin();
-	__register_cpu_notifier(&vmstat_notifier);
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
+					NULL, vmstat_cpu_dead);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'dead' hotplug state\n");
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/vmstat:online",
+					vmstat_cpu_online,
+					vmstat_cpu_down_prep);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'online' hotplug state\n");
+
+	get_online_cpus();
 	init_cpu_node_state();
+	put_online_cpus();
 
 	start_shepherd_timer();
-	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);

[PATCH 10/22] mm/zsmalloc: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
CC: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/zsmalloc.c              | 67 +++++++++-------------------------------------
 2 files changed, 14 insertions(+), 54 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 4ebd1bc27f8d..9f29dd996088 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -64,6 +64,7 @@ enum cpuhp_state {
 	CPUHP_NET_IUCV_PREPARE,
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
+	CPUHP_MM_ZS_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b0bc023d25c5..9cc3c0b2c2c1 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1284,61 +1284,21 @@ static void __zs_unmap_object(struct mapping_area *area,
 
 #endif /* CONFIG_PGTABLE_MAPPING */
 
-static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
-				void *pcpu)
+static int zs_cpu_prepare(unsigned int cpu)
 {
-	int ret, cpu = (long)pcpu;
 	struct mapping_area *area;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		area = &per_cpu(zs_map_area, cpu);
-		ret = __zs_cpu_up(area);
-		if (ret)
-			return notifier_from_errno(ret);
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		area = &per_cpu(zs_map_area, cpu);
-		__zs_cpu_down(area);
-		break;
-	}
-
-	return NOTIFY_OK;
+	area = &per_cpu(zs_map_area, cpu);
+	return __zs_cpu_up(area);
 }
 
-static struct notifier_block zs_cpu_nb = {
-	.notifier_call = zs_cpu_notifier
-};
-
-static int zs_register_cpu_notifier(void)
+static int zs_cpu_dead(unsigned int cpu)
 {
-	int cpu, uninitialized_var(ret);
+	struct mapping_area *area;
 
-	cpu_notifier_register_begin();
-
-	__register_cpu_notifier(&zs_cpu_nb);
-	for_each_online_cpu(cpu) {
-		ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
-		if (notifier_to_errno(ret))
-			break;
-	}
-
-	cpu_notifier_register_done();
-	return notifier_to_errno(ret);
-}
-
-static void zs_unregister_cpu_notifier(void)
-{
-	int cpu;
-
-	cpu_notifier_register_begin();
-
-	for_each_online_cpu(cpu)
-		zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
-	__unregister_cpu_notifier(&zs_cpu_nb);
-
-	cpu_notifier_register_done();
+	area = &per_cpu(zs_map_area, cpu);
+	__zs_cpu_down(area);
+	return 0;
 }
 
 static void __init init_zs_size_classes(void)
@@ -2534,10 +2494,10 @@ static int __init zs_init(void)
 	if (ret)
 		goto out;
 
-	ret = zs_register_cpu_notifier();
-
+	ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare",
+				zs_cpu_prepare, zs_cpu_dead);
 	if (ret)
-		goto notifier_fail;
+		goto hp_setup_fail;
 
 	init_zs_size_classes();
 
@@ -2549,8 +2509,7 @@ static int __init zs_init(void)
 
 	return 0;
 
-notifier_fail:
-	zs_unregister_cpu_notifier();
+hp_setup_fail:
 	zsmalloc_unmount();
 out:
 	return ret;
@@ -2562,7 +2521,7 @@ static void __exit zs_exit(void)
 	zpool_unregister_driver(&zs_zpool_driver);
 #endif
 	zsmalloc_unmount();
-	zs_unregister_cpu_notifier();
+	cpuhp_remove_state(CPUHP_MM_ZS_PREPARE);
 
 	zs_stat_exit();
 }
-- 
2.10.2

[PATCH 10/22] mm/zsmalloc: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
CC: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/zsmalloc.c              | 67 +++++++++-------------------------------------
 2 files changed, 14 insertions(+), 54 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 4ebd1bc27f8d..9f29dd996088 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -64,6 +64,7 @@ enum cpuhp_state {
 	CPUHP_NET_IUCV_PREPARE,
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
+	CPUHP_MM_ZS_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b0bc023d25c5..9cc3c0b2c2c1 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1284,61 +1284,21 @@ static void __zs_unmap_object(struct mapping_area *area,
 
 #endif /* CONFIG_PGTABLE_MAPPING */
 
-static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
-				void *pcpu)
+static int zs_cpu_prepare(unsigned int cpu)
 {
-	int ret, cpu = (long)pcpu;
 	struct mapping_area *area;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		area = &per_cpu(zs_map_area, cpu);
-		ret = __zs_cpu_up(area);
-		if (ret)
-			return notifier_from_errno(ret);
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		area = &per_cpu(zs_map_area, cpu);
-		__zs_cpu_down(area);
-		break;
-	}
-
-	return NOTIFY_OK;
+	area = &per_cpu(zs_map_area, cpu);
+	return __zs_cpu_up(area);
 }
 
-static struct notifier_block zs_cpu_nb = {
-	.notifier_call = zs_cpu_notifier
-};
-
-static int zs_register_cpu_notifier(void)
+static int zs_cpu_dead(unsigned int cpu)
 {
-	int cpu, uninitialized_var(ret);
+	struct mapping_area *area;
 
-	cpu_notifier_register_begin();
-
-	__register_cpu_notifier(&zs_cpu_nb);
-	for_each_online_cpu(cpu) {
-		ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
-		if (notifier_to_errno(ret))
-			break;
-	}
-
-	cpu_notifier_register_done();
-	return notifier_to_errno(ret);
-}
-
-static void zs_unregister_cpu_notifier(void)
-{
-	int cpu;
-
-	cpu_notifier_register_begin();
-
-	for_each_online_cpu(cpu)
-		zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
-	__unregister_cpu_notifier(&zs_cpu_nb);
-
-	cpu_notifier_register_done();
+	area = &per_cpu(zs_map_area, cpu);
+	__zs_cpu_down(area);
+	return 0;
 }
 
 static void __init init_zs_size_classes(void)
@@ -2534,10 +2494,10 @@ static int __init zs_init(void)
 	if (ret)
 		goto out;
 
-	ret = zs_register_cpu_notifier();
-
+	ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare",
+				zs_cpu_prepare, zs_cpu_dead);
 	if (ret)
-		goto notifier_fail;
+		goto hp_setup_fail;
 
 	init_zs_size_classes();
 
@@ -2549,8 +2509,7 @@ static int __init zs_init(void)
 
 	return 0;
 
-notifier_fail:
-	zs_unregister_cpu_notifier();
+hp_setup_fail:
 	zsmalloc_unmount();
 out:
 	return ret;
@@ -2562,7 +2521,7 @@ static void __exit zs_exit(void)
 	zpool_unregister_driver(&zs_zpool_driver);
 #endif
 	zsmalloc_unmount();
-	zs_unregister_cpu_notifier();
+	cpuhp_remove_state(CPUHP_MM_ZS_PREPARE);
 
 	zs_stat_exit();
 }
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[tip:smp/hotplug] mm/zsmalloc: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  215c89d055e085c42cea4fd571a1d0db0b6d5648
Gitweb:     http://git.kernel.org/tip/215c89d055e085c42cea4fd571a1d0db0b6d5648
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:38 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:36 +0100

mm/zsmalloc: Convert to hotplug state machine

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: linux-mm@kvack.org
Cc: Minchan Kim <minchan@kernel.org>
Cc: rt@linutronix.de
Cc: Nitin Gupta <ngupta@vflare.org>
Link: http://lkml.kernel.org/r/20161126231350.10321-11-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/cpuhotplug.h |  1 +
 mm/zsmalloc.c              | 67 +++++++++-------------------------------------
 2 files changed, 14 insertions(+), 54 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 4ebd1bc..9f29dd9 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -64,6 +64,7 @@ enum cpuhp_state {
 	CPUHP_NET_IUCV_PREPARE,
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
+	CPUHP_MM_ZS_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b0bc023..9cc3c0b 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1284,61 +1284,21 @@ out:
 
 #endif /* CONFIG_PGTABLE_MAPPING */
 
-static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
-				void *pcpu)
+static int zs_cpu_prepare(unsigned int cpu)
 {
-	int ret, cpu = (long)pcpu;
 	struct mapping_area *area;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		area = &per_cpu(zs_map_area, cpu);
-		ret = __zs_cpu_up(area);
-		if (ret)
-			return notifier_from_errno(ret);
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		area = &per_cpu(zs_map_area, cpu);
-		__zs_cpu_down(area);
-		break;
-	}
-
-	return NOTIFY_OK;
+	area = &per_cpu(zs_map_area, cpu);
+	return __zs_cpu_up(area);
 }
 
-static struct notifier_block zs_cpu_nb = {
-	.notifier_call = zs_cpu_notifier
-};
-
-static int zs_register_cpu_notifier(void)
+static int zs_cpu_dead(unsigned int cpu)
 {
-	int cpu, uninitialized_var(ret);
-
-	cpu_notifier_register_begin();
-
-	__register_cpu_notifier(&zs_cpu_nb);
-	for_each_online_cpu(cpu) {
-		ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
-		if (notifier_to_errno(ret))
-			break;
-	}
-
-	cpu_notifier_register_done();
-	return notifier_to_errno(ret);
-}
-
-static void zs_unregister_cpu_notifier(void)
-{
-	int cpu;
-
-	cpu_notifier_register_begin();
-
-	for_each_online_cpu(cpu)
-		zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
-	__unregister_cpu_notifier(&zs_cpu_nb);
+	struct mapping_area *area;
 
-	cpu_notifier_register_done();
+	area = &per_cpu(zs_map_area, cpu);
+	__zs_cpu_down(area);
+	return 0;
 }
 
 static void __init init_zs_size_classes(void)
@@ -2534,10 +2494,10 @@ static int __init zs_init(void)
 	if (ret)
 		goto out;
 
-	ret = zs_register_cpu_notifier();
-
+	ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare",
+				zs_cpu_prepare, zs_cpu_dead);
 	if (ret)
-		goto notifier_fail;
+		goto hp_setup_fail;
 
 	init_zs_size_classes();
 
@@ -2549,8 +2509,7 @@ static int __init zs_init(void)
 
 	return 0;
 
-notifier_fail:
-	zs_unregister_cpu_notifier();
+hp_setup_fail:
 	zsmalloc_unmount();
 out:
 	return ret;
@@ -2562,7 +2521,7 @@ static void __exit zs_exit(void)
 	zpool_unregister_driver(&zs_zpool_driver);
 #endif
 	zsmalloc_unmount();
-	zs_unregister_cpu_notifier();
+	cpuhp_remove_state(CPUHP_MM_ZS_PREPARE);
 
 	zs_stat_exit();
 }

[PATCH 11/22] mm/zswap: Convert dst-mem to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Cc: Seth Jennings <sjenning@redhat.com>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/zswap.c                 | 75 +++++++++++-----------------------------------
 2 files changed, 19 insertions(+), 57 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 9f29dd996088..62f51a4e8676 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -65,6 +65,7 @@ enum cpuhp_state {
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
+	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zswap.c b/mm/zswap.c
index 275b22cc8df4..b13aa5706348 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -352,70 +352,28 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
 **********************************/
 static DEFINE_PER_CPU(u8 *, zswap_dstmem);
 
-static int __zswap_cpu_dstmem_notifier(unsigned long action, unsigned long cpu)
+static int zswap_dstmem_prepare(unsigned int cpu)
 {
 	u8 *dst;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-		if (!dst) {
-			pr_err("can't allocate compressor buffer\n");
-			return NOTIFY_BAD;
-		}
-		per_cpu(zswap_dstmem, cpu) = dst;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		dst = per_cpu(zswap_dstmem, cpu);
-		kfree(dst);
-		per_cpu(zswap_dstmem, cpu) = NULL;
-		break;
-	default:
-		break;
+	dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!dst) {
+		pr_err("can't allocate compressor buffer\n");
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
-}
-
-static int zswap_cpu_dstmem_notifier(struct notifier_block *nb,
-				     unsigned long action, void *pcpu)
-{
-	return __zswap_cpu_dstmem_notifier(action, (unsigned long)pcpu);
-}
-
-static struct notifier_block zswap_dstmem_notifier = {
-	.notifier_call =	zswap_cpu_dstmem_notifier,
-};
-
-static int __init zswap_cpu_dstmem_init(void)
-{
-	unsigned long cpu;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		if (__zswap_cpu_dstmem_notifier(CPU_UP_PREPARE, cpu) ==
-		    NOTIFY_BAD)
-			goto cleanup;
-	__register_cpu_notifier(&zswap_dstmem_notifier);
-	cpu_notifier_register_done();
+	per_cpu(zswap_dstmem, cpu) = dst;
 	return 0;
-
-cleanup:
-	for_each_online_cpu(cpu)
-		__zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
 }
 
-static void zswap_cpu_dstmem_destroy(void)
+static int zswap_dstmem_dead(unsigned int cpu)
 {
-	unsigned long cpu;
+	u8 *dst;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&zswap_dstmem_notifier);
-	cpu_notifier_register_done();
+	dst = per_cpu(zswap_dstmem, cpu);
+	kfree(dst);
+	per_cpu(zswap_dstmem, cpu) = NULL;
+
+	return 0;
 }
 
 static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
@@ -1238,6 +1196,7 @@ static void __exit zswap_debugfs_exit(void) { }
 static int __init init_zswap(void)
 {
 	struct zswap_pool *pool;
+	int ret;
 
 	zswap_init_started = true;
 
@@ -1246,7 +1205,9 @@ static int __init init_zswap(void)
 		goto cache_fail;
 	}
 
-	if (zswap_cpu_dstmem_init()) {
+	ret = cpuhp_setup_state(CPUHP_MM_ZSWP_MEM_PREPARE, "mm/zswap:prepare",
+				zswap_dstmem_prepare, zswap_dstmem_dead);
+	if (ret) {
 		pr_err("dstmem alloc failed\n");
 		goto dstmem_fail;
 	}
@@ -1267,7 +1228,7 @@ static int __init init_zswap(void)
 	return 0;
 
 pool_fail:
-	zswap_cpu_dstmem_destroy();
+	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
 	zswap_entry_cache_destroy();
 cache_fail:
-- 
2.10.2

[PATCH 11/22] mm/zswap: Convert dst-mem to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Cc: Seth Jennings <sjenning@redhat.com>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/zswap.c                 | 75 +++++++++++-----------------------------------
 2 files changed, 19 insertions(+), 57 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 9f29dd996088..62f51a4e8676 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -65,6 +65,7 @@ enum cpuhp_state {
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
+	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zswap.c b/mm/zswap.c
index 275b22cc8df4..b13aa5706348 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -352,70 +352,28 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
 **********************************/
 static DEFINE_PER_CPU(u8 *, zswap_dstmem);
 
-static int __zswap_cpu_dstmem_notifier(unsigned long action, unsigned long cpu)
+static int zswap_dstmem_prepare(unsigned int cpu)
 {
 	u8 *dst;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-		if (!dst) {
-			pr_err("can't allocate compressor buffer\n");
-			return NOTIFY_BAD;
-		}
-		per_cpu(zswap_dstmem, cpu) = dst;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		dst = per_cpu(zswap_dstmem, cpu);
-		kfree(dst);
-		per_cpu(zswap_dstmem, cpu) = NULL;
-		break;
-	default:
-		break;
+	dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!dst) {
+		pr_err("can't allocate compressor buffer\n");
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
-}
-
-static int zswap_cpu_dstmem_notifier(struct notifier_block *nb,
-				     unsigned long action, void *pcpu)
-{
-	return __zswap_cpu_dstmem_notifier(action, (unsigned long)pcpu);
-}
-
-static struct notifier_block zswap_dstmem_notifier = {
-	.notifier_call =	zswap_cpu_dstmem_notifier,
-};
-
-static int __init zswap_cpu_dstmem_init(void)
-{
-	unsigned long cpu;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		if (__zswap_cpu_dstmem_notifier(CPU_UP_PREPARE, cpu) ==
-		    NOTIFY_BAD)
-			goto cleanup;
-	__register_cpu_notifier(&zswap_dstmem_notifier);
-	cpu_notifier_register_done();
+	per_cpu(zswap_dstmem, cpu) = dst;
 	return 0;
-
-cleanup:
-	for_each_online_cpu(cpu)
-		__zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
 }
 
-static void zswap_cpu_dstmem_destroy(void)
+static int zswap_dstmem_dead(unsigned int cpu)
 {
-	unsigned long cpu;
+	u8 *dst;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&zswap_dstmem_notifier);
-	cpu_notifier_register_done();
+	dst = per_cpu(zswap_dstmem, cpu);
+	kfree(dst);
+	per_cpu(zswap_dstmem, cpu) = NULL;
+
+	return 0;
 }
 
 static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
@@ -1238,6 +1196,7 @@ static void __exit zswap_debugfs_exit(void) { }
 static int __init init_zswap(void)
 {
 	struct zswap_pool *pool;
+	int ret;
 
 	zswap_init_started = true;
 
@@ -1246,7 +1205,9 @@ static int __init init_zswap(void)
 		goto cache_fail;
 	}
 
-	if (zswap_cpu_dstmem_init()) {
+	ret = cpuhp_setup_state(CPUHP_MM_ZSWP_MEM_PREPARE, "mm/zswap:prepare",
+				zswap_dstmem_prepare, zswap_dstmem_dead);
+	if (ret) {
 		pr_err("dstmem alloc failed\n");
 		goto dstmem_fail;
 	}
@@ -1267,7 +1228,7 @@ static int __init init_zswap(void)
 	return 0;
 
 pool_fail:
-	zswap_cpu_dstmem_destroy();
+	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
 	zswap_entry_cache_destroy();
 cache_fail:
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[tip:smp/hotplug] mm/zswap: Convert dst-mem to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  ad7ed7708db9ff388450935645816d44bf08a56d
Gitweb:     http://git.kernel.org/tip/ad7ed7708db9ff388450935645816d44bf08a56d
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:39 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:36 +0100

mm/zswap: Convert dst-mem to hotplug state machine

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: linux-mm@kvack.org
Cc: Seth Jennings <sjenning@redhat.com>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20161126231350.10321-12-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/cpuhotplug.h |  1 +
 mm/zswap.c                 | 73 +++++++++++-----------------------------------
 2 files changed, 18 insertions(+), 56 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 9f29dd9..62f51a4 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -65,6 +65,7 @@ enum cpuhp_state {
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
+	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zswap.c b/mm/zswap.c
index 275b22c..b13aa57 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -352,70 +352,28 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
 **********************************/
 static DEFINE_PER_CPU(u8 *, zswap_dstmem);
 
-static int __zswap_cpu_dstmem_notifier(unsigned long action, unsigned long cpu)
+static int zswap_dstmem_prepare(unsigned int cpu)
 {
 	u8 *dst;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-		if (!dst) {
-			pr_err("can't allocate compressor buffer\n");
-			return NOTIFY_BAD;
-		}
-		per_cpu(zswap_dstmem, cpu) = dst;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		dst = per_cpu(zswap_dstmem, cpu);
-		kfree(dst);
-		per_cpu(zswap_dstmem, cpu) = NULL;
-		break;
-	default:
-		break;
+	dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!dst) {
+		pr_err("can't allocate compressor buffer\n");
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
+	per_cpu(zswap_dstmem, cpu) = dst;
+	return 0;
 }
 
-static int zswap_cpu_dstmem_notifier(struct notifier_block *nb,
-				     unsigned long action, void *pcpu)
+static int zswap_dstmem_dead(unsigned int cpu)
 {
-	return __zswap_cpu_dstmem_notifier(action, (unsigned long)pcpu);
-}
-
-static struct notifier_block zswap_dstmem_notifier = {
-	.notifier_call =	zswap_cpu_dstmem_notifier,
-};
+	u8 *dst;
 
-static int __init zswap_cpu_dstmem_init(void)
-{
-	unsigned long cpu;
+	dst = per_cpu(zswap_dstmem, cpu);
+	kfree(dst);
+	per_cpu(zswap_dstmem, cpu) = NULL;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		if (__zswap_cpu_dstmem_notifier(CPU_UP_PREPARE, cpu) ==
-		    NOTIFY_BAD)
-			goto cleanup;
-	__register_cpu_notifier(&zswap_dstmem_notifier);
-	cpu_notifier_register_done();
 	return 0;
-
-cleanup:
-	for_each_online_cpu(cpu)
-		__zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
-}
-
-static void zswap_cpu_dstmem_destroy(void)
-{
-	unsigned long cpu;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&zswap_dstmem_notifier);
-	cpu_notifier_register_done();
 }
 
 static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
@@ -1238,6 +1196,7 @@ static void __exit zswap_debugfs_exit(void) { }
 static int __init init_zswap(void)
 {
 	struct zswap_pool *pool;
+	int ret;
 
 	zswap_init_started = true;
 
@@ -1246,7 +1205,9 @@ static int __init init_zswap(void)
 		goto cache_fail;
 	}
 
-	if (zswap_cpu_dstmem_init()) {
+	ret = cpuhp_setup_state(CPUHP_MM_ZSWP_MEM_PREPARE, "mm/zswap:prepare",
+				zswap_dstmem_prepare, zswap_dstmem_dead);
+	if (ret) {
 		pr_err("dstmem alloc failed\n");
 		goto dstmem_fail;
 	}
@@ -1267,7 +1228,7 @@ static int __init init_zswap(void)
 	return 0;
 
 pool_fail:
-	zswap_cpu_dstmem_destroy();
+	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
 	zswap_entry_cache_destroy();
 cache_fail:

[PATCH 12/22] mm/zswap: Convert pool to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine. Multi state is used to address the
per-pool notifier. Uppon adding of the intance the callback is invoked for all
online CPUs so the manual init can go.

Cc: Seth Jennings <sjenning@redhat.com>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/zswap.c                 | 99 ++++++++++++++++------------------------------
 2 files changed, 35 insertions(+), 65 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 62f51a4e8676..c7d0d76ef0ee 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -66,6 +66,7 @@ enum cpuhp_state {
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
 	CPUHP_MM_ZSWP_MEM_PREPARE,
+	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zswap.c b/mm/zswap.c
index b13aa5706348..067a0d62f318 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -118,7 +118,7 @@ struct zswap_pool {
 	struct kref kref;
 	struct list_head list;
 	struct work_struct work;
-	struct notifier_block notifier;
+	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
 };
 
@@ -376,77 +376,34 @@ static int zswap_dstmem_dead(unsigned int cpu)
 	return 0;
 }
 
-static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
-				     unsigned long action, unsigned long cpu)
+static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_comp *tfm;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
-			break;
-		tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
-		if (IS_ERR_OR_NULL(tfm)) {
-			pr_err("could not alloc crypto comp %s : %ld\n",
-			       pool->tfm_name, PTR_ERR(tfm));
-			return NOTIFY_BAD;
-		}
-		*per_cpu_ptr(pool->tfm, cpu) = tfm;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		tfm = *per_cpu_ptr(pool->tfm, cpu);
-		if (!IS_ERR_OR_NULL(tfm))
-			crypto_free_comp(tfm);
-		*per_cpu_ptr(pool->tfm, cpu) = NULL;
-		break;
-	default:
-		break;
+	if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
+		return 0;
+
+	tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
+	if (IS_ERR_OR_NULL(tfm)) {
+		pr_err("could not alloc crypto comp %s : %ld\n",
+		       pool->tfm_name, PTR_ERR(tfm));
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
-}
-
-static int zswap_cpu_comp_notifier(struct notifier_block *nb,
-				   unsigned long action, void *pcpu)
-{
-	unsigned long cpu = (unsigned long)pcpu;
-	struct zswap_pool *pool = container_of(nb, typeof(*pool), notifier);
-
-	return __zswap_cpu_comp_notifier(pool, action, cpu);
-}
-
-static int zswap_cpu_comp_init(struct zswap_pool *pool)
-{
-	unsigned long cpu;
-
-	memset(&pool->notifier, 0, sizeof(pool->notifier));
-	pool->notifier.notifier_call = zswap_cpu_comp_notifier;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		if (__zswap_cpu_comp_notifier(pool, CPU_UP_PREPARE, cpu) ==
-		    NOTIFY_BAD)
-			goto cleanup;
-	__register_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
+	*per_cpu_ptr(pool->tfm, cpu) = tfm;
 	return 0;
-
-cleanup:
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
 }
 
-static void zswap_cpu_comp_destroy(struct zswap_pool *pool)
+static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 {
-	unsigned long cpu;
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
+	struct crypto_comp *tfm;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
+	tfm = *per_cpu_ptr(pool->tfm, cpu);
+	if (!IS_ERR_OR_NULL(tfm))
+		crypto_free_comp(tfm);
+	*per_cpu_ptr(pool->tfm, cpu) = NULL;
+	return 0;
 }
 
 /*********************************
@@ -527,6 +484,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	struct zswap_pool *pool;
 	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
+	int ret;
 
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool) {
@@ -551,7 +509,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		goto error;
 	}
 
-	if (zswap_cpu_comp_init(pool))
+	ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
+				       &pool->node);
+	if (ret)
 		goto error;
 	pr_debug("using %s compressor\n", pool->tfm_name);
 
@@ -605,7 +565,7 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 {
 	zswap_pool_debug("destroying", pool);
 
-	zswap_cpu_comp_destroy(pool);
+	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->tfm);
 	zpool_destroy_pool(pool->zpool);
 	kfree(pool);
@@ -1212,6 +1172,13 @@ static int __init init_zswap(void)
 		goto dstmem_fail;
 	}
 
+	ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE,
+				      "mm/zswap_pool:prepare",
+				      zswap_cpu_comp_prepare,
+				      zswap_cpu_comp_dead);
+	if (ret)
+		goto hp_fail;
+
 	pool = __zswap_pool_create_fallback();
 	if (!pool) {
 		pr_err("pool creation failed\n");
@@ -1228,6 +1195,8 @@ static int __init init_zswap(void)
 	return 0;
 
 pool_fail:
+	cpuhp_remove_state_nocalls(CPUHP_MM_ZSWP_POOL_PREPARE);
+hp_fail:
 	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
 	zswap_entry_cache_destroy();
-- 
2.10.2

[PATCH 12/22] mm/zswap: Convert pool to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine. Multi state is used to address the
per-pool notifier. Uppon adding of the intance the callback is invoked for all
online CPUs so the manual init can go.

Cc: Seth Jennings <sjenning@redhat.com>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/zswap.c                 | 99 ++++++++++++++++------------------------------
 2 files changed, 35 insertions(+), 65 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 62f51a4e8676..c7d0d76ef0ee 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -66,6 +66,7 @@ enum cpuhp_state {
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
 	CPUHP_MM_ZSWP_MEM_PREPARE,
+	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zswap.c b/mm/zswap.c
index b13aa5706348..067a0d62f318 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -118,7 +118,7 @@ struct zswap_pool {
 	struct kref kref;
 	struct list_head list;
 	struct work_struct work;
-	struct notifier_block notifier;
+	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
 };
 
@@ -376,77 +376,34 @@ static int zswap_dstmem_dead(unsigned int cpu)
 	return 0;
 }
 
-static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
-				     unsigned long action, unsigned long cpu)
+static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_comp *tfm;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
-			break;
-		tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
-		if (IS_ERR_OR_NULL(tfm)) {
-			pr_err("could not alloc crypto comp %s : %ld\n",
-			       pool->tfm_name, PTR_ERR(tfm));
-			return NOTIFY_BAD;
-		}
-		*per_cpu_ptr(pool->tfm, cpu) = tfm;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		tfm = *per_cpu_ptr(pool->tfm, cpu);
-		if (!IS_ERR_OR_NULL(tfm))
-			crypto_free_comp(tfm);
-		*per_cpu_ptr(pool->tfm, cpu) = NULL;
-		break;
-	default:
-		break;
+	if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
+		return 0;
+
+	tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
+	if (IS_ERR_OR_NULL(tfm)) {
+		pr_err("could not alloc crypto comp %s : %ld\n",
+		       pool->tfm_name, PTR_ERR(tfm));
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
-}
-
-static int zswap_cpu_comp_notifier(struct notifier_block *nb,
-				   unsigned long action, void *pcpu)
-{
-	unsigned long cpu = (unsigned long)pcpu;
-	struct zswap_pool *pool = container_of(nb, typeof(*pool), notifier);
-
-	return __zswap_cpu_comp_notifier(pool, action, cpu);
-}
-
-static int zswap_cpu_comp_init(struct zswap_pool *pool)
-{
-	unsigned long cpu;
-
-	memset(&pool->notifier, 0, sizeof(pool->notifier));
-	pool->notifier.notifier_call = zswap_cpu_comp_notifier;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		if (__zswap_cpu_comp_notifier(pool, CPU_UP_PREPARE, cpu) ==
-		    NOTIFY_BAD)
-			goto cleanup;
-	__register_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
+	*per_cpu_ptr(pool->tfm, cpu) = tfm;
 	return 0;
-
-cleanup:
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
 }
 
-static void zswap_cpu_comp_destroy(struct zswap_pool *pool)
+static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 {
-	unsigned long cpu;
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
+	struct crypto_comp *tfm;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
+	tfm = *per_cpu_ptr(pool->tfm, cpu);
+	if (!IS_ERR_OR_NULL(tfm))
+		crypto_free_comp(tfm);
+	*per_cpu_ptr(pool->tfm, cpu) = NULL;
+	return 0;
 }
 
 /*********************************
@@ -527,6 +484,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	struct zswap_pool *pool;
 	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
+	int ret;
 
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool) {
@@ -551,7 +509,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		goto error;
 	}
 
-	if (zswap_cpu_comp_init(pool))
+	ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
+				       &pool->node);
+	if (ret)
 		goto error;
 	pr_debug("using %s compressor\n", pool->tfm_name);
 
@@ -605,7 +565,7 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 {
 	zswap_pool_debug("destroying", pool);
 
-	zswap_cpu_comp_destroy(pool);
+	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->tfm);
 	zpool_destroy_pool(pool->zpool);
 	kfree(pool);
@@ -1212,6 +1172,13 @@ static int __init init_zswap(void)
 		goto dstmem_fail;
 	}
 
+	ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE,
+				      "mm/zswap_pool:prepare",
+				      zswap_cpu_comp_prepare,
+				      zswap_cpu_comp_dead);
+	if (ret)
+		goto hp_fail;
+
 	pool = __zswap_pool_create_fallback();
 	if (!pool) {
 		pr_err("pool creation failed\n");
@@ -1228,6 +1195,8 @@ static int __init init_zswap(void)
 	return 0;
 
 pool_fail:
+	cpuhp_remove_state_nocalls(CPUHP_MM_ZSWP_POOL_PREPARE);
+hp_fail:
 	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
 	zswap_entry_cache_destroy();
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[tip:smp/hotplug] mm/zswap: Convert pool to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  cab7a7e5b6c5c2638b00c72559ff9fb715583c98
Gitweb:     http://git.kernel.org/tip/cab7a7e5b6c5c2638b00c72559ff9fb715583c98
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:40 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:36 +0100

mm/zswap: Convert pool to hotplug state machine

Install the callbacks via the state machine. Multi state is used to address the
per-pool notifier. Uppon adding of the intance the callback is invoked for all
online CPUs so the manual init can go.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: linux-mm@kvack.org
Cc: Seth Jennings <sjenning@redhat.com>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20161126231350.10321-13-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/cpuhotplug.h |  1 +
 mm/zswap.c                 | 99 ++++++++++++++++------------------------------
 2 files changed, 35 insertions(+), 65 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 62f51a4..c7d0d76 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -66,6 +66,7 @@ enum cpuhp_state {
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
 	CPUHP_MM_ZSWP_MEM_PREPARE,
+	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zswap.c b/mm/zswap.c
index b13aa57..067a0d6 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -118,7 +118,7 @@ struct zswap_pool {
 	struct kref kref;
 	struct list_head list;
 	struct work_struct work;
-	struct notifier_block notifier;
+	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
 };
 
@@ -376,77 +376,34 @@ static int zswap_dstmem_dead(unsigned int cpu)
 	return 0;
 }
 
-static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
-				     unsigned long action, unsigned long cpu)
+static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_comp *tfm;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
-			break;
-		tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
-		if (IS_ERR_OR_NULL(tfm)) {
-			pr_err("could not alloc crypto comp %s : %ld\n",
-			       pool->tfm_name, PTR_ERR(tfm));
-			return NOTIFY_BAD;
-		}
-		*per_cpu_ptr(pool->tfm, cpu) = tfm;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		tfm = *per_cpu_ptr(pool->tfm, cpu);
-		if (!IS_ERR_OR_NULL(tfm))
-			crypto_free_comp(tfm);
-		*per_cpu_ptr(pool->tfm, cpu) = NULL;
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static int zswap_cpu_comp_notifier(struct notifier_block *nb,
-				   unsigned long action, void *pcpu)
-{
-	unsigned long cpu = (unsigned long)pcpu;
-	struct zswap_pool *pool = container_of(nb, typeof(*pool), notifier);
-
-	return __zswap_cpu_comp_notifier(pool, action, cpu);
-}
+	if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
+		return 0;
 
-static int zswap_cpu_comp_init(struct zswap_pool *pool)
-{
-	unsigned long cpu;
-
-	memset(&pool->notifier, 0, sizeof(pool->notifier));
-	pool->notifier.notifier_call = zswap_cpu_comp_notifier;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		if (__zswap_cpu_comp_notifier(pool, CPU_UP_PREPARE, cpu) ==
-		    NOTIFY_BAD)
-			goto cleanup;
-	__register_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
+	tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
+	if (IS_ERR_OR_NULL(tfm)) {
+		pr_err("could not alloc crypto comp %s : %ld\n",
+		       pool->tfm_name, PTR_ERR(tfm));
+		return -ENOMEM;
+	}
+	*per_cpu_ptr(pool->tfm, cpu) = tfm;
 	return 0;
-
-cleanup:
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
 }
 
-static void zswap_cpu_comp_destroy(struct zswap_pool *pool)
+static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 {
-	unsigned long cpu;
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
+	struct crypto_comp *tfm;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
+	tfm = *per_cpu_ptr(pool->tfm, cpu);
+	if (!IS_ERR_OR_NULL(tfm))
+		crypto_free_comp(tfm);
+	*per_cpu_ptr(pool->tfm, cpu) = NULL;
+	return 0;
 }
 
 /*********************************
@@ -527,6 +484,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	struct zswap_pool *pool;
 	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
+	int ret;
 
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool) {
@@ -551,7 +509,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		goto error;
 	}
 
-	if (zswap_cpu_comp_init(pool))
+	ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
+				       &pool->node);
+	if (ret)
 		goto error;
 	pr_debug("using %s compressor\n", pool->tfm_name);
 
@@ -605,7 +565,7 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 {
 	zswap_pool_debug("destroying", pool);
 
-	zswap_cpu_comp_destroy(pool);
+	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->tfm);
 	zpool_destroy_pool(pool->zpool);
 	kfree(pool);
@@ -1212,6 +1172,13 @@ static int __init init_zswap(void)
 		goto dstmem_fail;
 	}
 
+	ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE,
+				      "mm/zswap_pool:prepare",
+				      zswap_cpu_comp_prepare,
+				      zswap_cpu_comp_dead);
+	if (ret)
+		goto hp_fail;
+
 	pool = __zswap_pool_create_fallback();
 	if (!pool) {
 		pr_err("pool creation failed\n");
@@ -1228,6 +1195,8 @@ static int __init init_zswap(void)
 	return 0;
 
 pool_fail:
+	cpuhp_remove_state_nocalls(CPUHP_MM_ZSWP_POOL_PREPARE);
+hp_fail:
 	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
 	zswap_entry_cache_destroy();

[PATCH 13/22] iommu/vt-d: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.

Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: iommu@lists.linux-foundation.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 drivers/iommu/intel-iommu.c | 24 ++++++------------------
 include/linux/cpuhotplug.h  |  1 +
 2 files changed, 7 insertions(+), 18 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a4407eabf0e6..fd7962560e56 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4665,25 +4665,13 @@ static void free_all_cpu_cached_iovas(unsigned int cpu)
 	}
 }
 
-static int intel_iommu_cpu_notifier(struct notifier_block *nfb,
-				    unsigned long action, void *v)
+static int intel_iommu_cpu_dead(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)v;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		free_all_cpu_cached_iovas(cpu);
-		flush_unmaps_timeout(cpu);
-		break;
-	}
-	return NOTIFY_OK;
+	free_all_cpu_cached_iovas(cpu);
+	flush_unmaps_timeout(cpu);
+	return 0;
 }
 
-static struct notifier_block intel_iommu_cpu_nb = {
-	.notifier_call = intel_iommu_cpu_notifier,
-};
-
 static ssize_t intel_iommu_show_version(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
@@ -4832,8 +4820,8 @@ int __init intel_iommu_init(void)
 	bus_register_notifier(&pci_bus_type, &device_nb);
 	if (si_domain && !hw_pass_through)
 		register_memory_notifier(&intel_iommu_memory_nb);
-	register_hotcpu_notifier(&intel_iommu_cpu_nb);
-
+	cpuhp_setup_state(CPUHP_IOMMU_INTEL_DEAD, "iommu/intel:dead", NULL,
+			  intel_iommu_cpu_dead);
 	intel_iommu_enabled = 1;
 
 	return 0;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index c7d0d76ef0ee..853f8176594d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -40,6 +40,7 @@ enum cpuhp_state {
 	CPUHP_PAGE_ALLOC_DEAD,
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
+	CPUHP_IOMMU_INTEL_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-- 
2.10.2

[PATCH 13/22] iommu/vt-d: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>

Install the callbacks via the state machine.

Cc: David Woodhouse <dwmw2-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
Cc: Joerg Roedel <joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
Cc: iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org
Signed-off-by: Anna-Maria Gleixner <anna-maria-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>
---
 drivers/iommu/intel-iommu.c | 24 ++++++------------------
 include/linux/cpuhotplug.h  |  1 +
 2 files changed, 7 insertions(+), 18 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a4407eabf0e6..fd7962560e56 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4665,25 +4665,13 @@ static void free_all_cpu_cached_iovas(unsigned int cpu)
 	}
 }
 
-static int intel_iommu_cpu_notifier(struct notifier_block *nfb,
-				    unsigned long action, void *v)
+static int intel_iommu_cpu_dead(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)v;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		free_all_cpu_cached_iovas(cpu);
-		flush_unmaps_timeout(cpu);
-		break;
-	}
-	return NOTIFY_OK;
+	free_all_cpu_cached_iovas(cpu);
+	flush_unmaps_timeout(cpu);
+	return 0;
 }
 
-static struct notifier_block intel_iommu_cpu_nb = {
-	.notifier_call = intel_iommu_cpu_notifier,
-};
-
 static ssize_t intel_iommu_show_version(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
@@ -4832,8 +4820,8 @@ int __init intel_iommu_init(void)
 	bus_register_notifier(&pci_bus_type, &device_nb);
 	if (si_domain && !hw_pass_through)
 		register_memory_notifier(&intel_iommu_memory_nb);
-	register_hotcpu_notifier(&intel_iommu_cpu_nb);
-
+	cpuhp_setup_state(CPUHP_IOMMU_INTEL_DEAD, "iommu/intel:dead", NULL,
+			  intel_iommu_cpu_dead);
 	intel_iommu_enabled = 1;
 
 	return 0;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index c7d0d76ef0ee..853f8176594d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -40,6 +40,7 @@ enum cpuhp_state {
 	CPUHP_PAGE_ALLOC_DEAD,
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
+	CPUHP_IOMMU_INTEL_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-- 
2.10.2

[tip:smp/hotplug] iommu/vt-d: Convert to hotplug state machine

[tip-bot for Anna-Maria Gleixner]

Commit-ID:  21647615db288d9dacad0de6a5df846b39d51bea
Gitweb:     http://git.kernel.org/tip/21647615db288d9dacad0de6a5df846b39d51bea
Author:     Anna-Maria Gleixner <anna-maria@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:41 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:37 +0100

iommu/vt-d: Convert to hotplug state machine

Install the callbacks via the state machine.

Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: iommu@lists.linux-foundation.org
Cc: rt@linutronix.de
Cc: David Woodhouse <dwmw2@infradead.org>
Link: http://lkml.kernel.org/r/20161126231350.10321-14-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/iommu/intel-iommu.c | 24 ++++++------------------
 include/linux/cpuhotplug.h  |  1 +
 2 files changed, 7 insertions(+), 18 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a4407ea..fd79625 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4665,25 +4665,13 @@ static void free_all_cpu_cached_iovas(unsigned int cpu)
 	}
 }
 
-static int intel_iommu_cpu_notifier(struct notifier_block *nfb,
-				    unsigned long action, void *v)
+static int intel_iommu_cpu_dead(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)v;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		free_all_cpu_cached_iovas(cpu);
-		flush_unmaps_timeout(cpu);
-		break;
-	}
-	return NOTIFY_OK;
+	free_all_cpu_cached_iovas(cpu);
+	flush_unmaps_timeout(cpu);
+	return 0;
 }
 
-static struct notifier_block intel_iommu_cpu_nb = {
-	.notifier_call = intel_iommu_cpu_notifier,
-};
-
 static ssize_t intel_iommu_show_version(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
@@ -4832,8 +4820,8 @@ int __init intel_iommu_init(void)
 	bus_register_notifier(&pci_bus_type, &device_nb);
 	if (si_domain && !hw_pass_through)
 		register_memory_notifier(&intel_iommu_memory_nb);
-	register_hotcpu_notifier(&intel_iommu_cpu_nb);
-
+	cpuhp_setup_state(CPUHP_IOMMU_INTEL_DEAD, "iommu/intel:dead", NULL,
+			  intel_iommu_cpu_dead);
 	intel_iommu_enabled = 1;
 
 	return 0;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index c7d0d76..853f817 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -40,6 +40,7 @@ enum cpuhp_state {
 	CPUHP_PAGE_ALLOC_DEAD,
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
+	CPUHP_IOMMU_INTEL_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,

[PATCH 14/22] mm/compaction: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine. Should the hotplug init fail then
no threads are spawned.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: linux-mm@kvack.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 mm/compaction.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 0409a4ad6ea1..0d37192d9423 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2043,33 +2043,38 @@ void kcompactd_stop(int nid)
  * away, we get changed to run anywhere: as the first one comes back,
  * restore their cpu bindings.
  */
-static int cpu_callback(struct notifier_block *nfb, unsigned long action,
-			void *hcpu)
+static int kcompactd_cpu_online(unsigned int cpu)
 {
 	int nid;
 
-	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
-		for_each_node_state(nid, N_MEMORY) {
-			pg_data_t *pgdat = NODE_DATA(nid);
-			const struct cpumask *mask;
+	for_each_node_state(nid, N_MEMORY) {
+		pg_data_t *pgdat = NODE_DATA(nid);
+		const struct cpumask *mask;
 
-			mask = cpumask_of_node(pgdat->node_id);
+		mask = cpumask_of_node(pgdat->node_id);
 
-			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
-				/* One of our CPUs online: restore mask */
-				set_cpus_allowed_ptr(pgdat->kcompactd, mask);
-		}
+		if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
+			/* One of our CPUs online: restore mask */
+			set_cpus_allowed_ptr(pgdat->kcompactd, mask);
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
 static int __init kcompactd_init(void)
 {
 	int nid;
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"mm/compaction:online",
+					kcompactd_cpu_online, NULL);
+	if (ret < 0) {
+		pr_err("kcompactd: failed to register hotplug callbacks.\n");
+		return ret;
+	}
 
 	for_each_node_state(nid, N_MEMORY)
 		kcompactd_run(nid);
-	hotcpu_notifier(cpu_callback, 0);
 	return 0;
 }
 subsys_initcall(kcompactd_init)
-- 
2.10.2

[PATCH 14/22] mm/compaction: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine. Should the hotplug init fail then
no threads are spawned.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: linux-mm@kvack.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 mm/compaction.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 0409a4ad6ea1..0d37192d9423 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2043,33 +2043,38 @@ void kcompactd_stop(int nid)
  * away, we get changed to run anywhere: as the first one comes back,
  * restore their cpu bindings.
  */
-static int cpu_callback(struct notifier_block *nfb, unsigned long action,
-			void *hcpu)
+static int kcompactd_cpu_online(unsigned int cpu)
 {
 	int nid;
 
-	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
-		for_each_node_state(nid, N_MEMORY) {
-			pg_data_t *pgdat = NODE_DATA(nid);
-			const struct cpumask *mask;
+	for_each_node_state(nid, N_MEMORY) {
+		pg_data_t *pgdat = NODE_DATA(nid);
+		const struct cpumask *mask;
 
-			mask = cpumask_of_node(pgdat->node_id);
+		mask = cpumask_of_node(pgdat->node_id);
 
-			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
-				/* One of our CPUs online: restore mask */
-				set_cpus_allowed_ptr(pgdat->kcompactd, mask);
-		}
+		if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
+			/* One of our CPUs online: restore mask */
+			set_cpus_allowed_ptr(pgdat->kcompactd, mask);
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
 static int __init kcompactd_init(void)
 {
 	int nid;
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"mm/compaction:online",
+					kcompactd_cpu_online, NULL);
+	if (ret < 0) {
+		pr_err("kcompactd: failed to register hotplug callbacks.\n");
+		return ret;
+	}
 
 	for_each_node_state(nid, N_MEMORY)
 		kcompactd_run(nid);
-	hotcpu_notifier(cpu_callback, 0);
 	return 0;
 }
 subsys_initcall(kcompactd_init)
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[tip:smp/hotplug] mm/compaction: Convert to hotplug state machine

[tip-bot for Anna-Maria Gleixner]

Commit-ID:  e46b1db249d83bb19b6bdbed2b2e2ff3858cd211
Gitweb:     http://git.kernel.org/tip/e46b1db249d83bb19b6bdbed2b2e2ff3858cd211
Author:     Anna-Maria Gleixner <anna-maria@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:42 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:37 +0100

mm/compaction: Convert to hotplug state machine

Install the callbacks via the state machine. Should the hotplug init fail then
no threads are spawned.

Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: linux-mm@kvack.org
Cc: rt@linutronix.de
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/20161126231350.10321-15-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 mm/compaction.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 0409a4a..0d37192 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2043,33 +2043,38 @@ void kcompactd_stop(int nid)
  * away, we get changed to run anywhere: as the first one comes back,
  * restore their cpu bindings.
  */
-static int cpu_callback(struct notifier_block *nfb, unsigned long action,
-			void *hcpu)
+static int kcompactd_cpu_online(unsigned int cpu)
 {
 	int nid;
 
-	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
-		for_each_node_state(nid, N_MEMORY) {
-			pg_data_t *pgdat = NODE_DATA(nid);
-			const struct cpumask *mask;
+	for_each_node_state(nid, N_MEMORY) {
+		pg_data_t *pgdat = NODE_DATA(nid);
+		const struct cpumask *mask;
 
-			mask = cpumask_of_node(pgdat->node_id);
+		mask = cpumask_of_node(pgdat->node_id);
 
-			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
-				/* One of our CPUs online: restore mask */
-				set_cpus_allowed_ptr(pgdat->kcompactd, mask);
-		}
+		if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
+			/* One of our CPUs online: restore mask */
+			set_cpus_allowed_ptr(pgdat->kcompactd, mask);
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
 static int __init kcompactd_init(void)
 {
 	int nid;
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"mm/compaction:online",
+					kcompactd_cpu_online, NULL);
+	if (ret < 0) {
+		pr_err("kcompactd: failed to register hotplug callbacks.\n");
+		return ret;
+	}
 
 	for_each_node_state(nid, N_MEMORY)
 		kcompactd_run(nid);
-	hotcpu_notifier(cpu_callback, 0);
 	return 0;
 }
 subsys_initcall(kcompactd_init)

[PATCH 15/22] arm64/cpuinfo: Make hotplug notifier symmetric

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

There is no requirement to keep the sysfs files around until the CPU is
completely dead. Remove them during the DOWN_PREPARE notification. This is
a preparatory patch for converting to the hotplug state machine.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 arch/arm64/kernel/cpuinfo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index b3d5b3e8fbcb..19aad7041e14 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -272,9 +272,10 @@ static int cpuid_callback(struct notifier_block *nb,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
 		rc = cpuid_add_regs(cpu);
 		break;
-	case CPU_DEAD:
+	case CPU_DOWN_PREPARE:
 		rc = cpuid_remove_regs(cpu);
 		break;
 	}
-- 
2.10.2

[PATCH 15/22] arm64/cpuinfo: Make hotplug notifier symmetric

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

There is no requirement to keep the sysfs files around until the CPU is
completely dead. Remove them during the DOWN_PREPARE notification. This is
a preparatory patch for converting to the hotplug state machine.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel at lists.infradead.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 arch/arm64/kernel/cpuinfo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index b3d5b3e8fbcb..19aad7041e14 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -272,9 +272,10 @@ static int cpuid_callback(struct notifier_block *nb,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
 		rc = cpuid_add_regs(cpu);
 		break;
-	case CPU_DEAD:
+	case CPU_DOWN_PREPARE:
 		rc = cpuid_remove_regs(cpu);
 		break;
 	}
-- 
2.10.2

Re: [PATCH 15/22] arm64/cpuinfo: Make hotplug notifier symmetric

[Suzuki K Poulose]

On 26/11/16 23:13, Sebastian Andrzej Siewior wrote:
> From: Anna-Maria Gleixner <anna-maria@linutronix.de>
>
> There is no requirement to keep the sysfs files around until the CPU is
> completely dead. Remove them during the DOWN_PREPARE notification. This is
> a preparatory patch for converting to the hotplug state machine.
>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Cc: linux-arm-kernel@lists.infradead.org
> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
>  arch/arm64/kernel/cpuinfo.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
> index b3d5b3e8fbcb..19aad7041e14 100644
> --- a/arch/arm64/kernel/cpuinfo.c
> +++ b/arch/arm64/kernel/cpuinfo.c
> @@ -272,9 +272,10 @@ static int cpuid_callback(struct notifier_block *nb,
>
>  	switch (action & ~CPU_TASKS_FROZEN) {
>  	case CPU_ONLINE:
> +	case CPU_DOWN_FAILED:
>  		rc = cpuid_add_regs(cpu);
>  		break;
> -	case CPU_DEAD:
> +	case CPU_DOWN_PREPARE:
>  		rc = cpuid_remove_regs(cpu);
>  		break;
>  	}

Looks reasonable to me:

Reviewed-by : Suzuki K Poulose <suzuki.poulose@arm.com>

[PATCH 15/22] arm64/cpuinfo: Make hotplug notifier symmetric

[Suzuki K Poulose]

On 26/11/16 23:13, Sebastian Andrzej Siewior wrote:
> From: Anna-Maria Gleixner <anna-maria@linutronix.de>
>
> There is no requirement to keep the sysfs files around until the CPU is
> completely dead. Remove them during the DOWN_PREPARE notification. This is
> a preparatory patch for converting to the hotplug state machine.
>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Cc: linux-arm-kernel at lists.infradead.org
> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
>  arch/arm64/kernel/cpuinfo.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
> index b3d5b3e8fbcb..19aad7041e14 100644
> --- a/arch/arm64/kernel/cpuinfo.c
> +++ b/arch/arm64/kernel/cpuinfo.c
> @@ -272,9 +272,10 @@ static int cpuid_callback(struct notifier_block *nb,
>
>  	switch (action & ~CPU_TASKS_FROZEN) {
>  	case CPU_ONLINE:
> +	case CPU_DOWN_FAILED:
>  		rc = cpuid_add_regs(cpu);
>  		break;
> -	case CPU_DEAD:
> +	case CPU_DOWN_PREPARE:
>  		rc = cpuid_remove_regs(cpu);
>  		break;
>  	}

Looks reasonable to me:

Reviewed-by : Suzuki K Poulose <suzuki.poulose@arm.com>

[tip:smp/hotplug] arm64/cpuinfo: Make hotplug notifier symmetric

[tip-bot for Anna-Maria Gleixner]

Commit-ID:  914fb85f01571233af199a78ed1f88d9268421fd
Gitweb:     http://git.kernel.org/tip/914fb85f01571233af199a78ed1f88d9268421fd
Author:     Anna-Maria Gleixner <anna-maria@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:43 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:37 +0100

arm64/cpuinfo: Make hotplug notifier symmetric

There is no requirement to keep the sysfs files around until the CPU is
completely dead. Remove them during the DOWN_PREPARE notification. This is
a preparatory patch for converting to the hotplug state machine.

Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: rt@linutronix.de
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/20161126231350.10321-16-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/arm64/kernel/cpuinfo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index b3d5b3e..19aad70 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -272,9 +272,10 @@ static int cpuid_callback(struct notifier_block *nb,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
 		rc = cpuid_add_regs(cpu);
 		break;
-	case CPU_DEAD:
+	case CPU_DOWN_PREPARE:
 		rc = cpuid_remove_regs(cpu);
 		break;
 	}

[PATCH 16/22] arm64/cpuinfo: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 arch/arm64/kernel/cpuinfo.c | 37 +++++++++----------------------------
 1 file changed, 9 insertions(+), 28 deletions(-)

diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 19aad7041e14..7b7be71e87bf 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -227,7 +227,7 @@ static struct attribute_group cpuregs_attr_group = {
 	.name = "identification"
 };
 
-static int cpuid_add_regs(int cpu)
+static int cpuid_cpu_online(unsigned int cpu)
 {
 	int rc;
 	struct device *dev;
@@ -248,7 +248,7 @@ static int cpuid_add_regs(int cpu)
 	return rc;
 }
 
-static int cpuid_remove_regs(int cpu)
+static int cpuid_cpu_offline(unsigned int cpu)
 {
 	struct device *dev;
 	struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
@@ -264,41 +264,22 @@ static int cpuid_remove_regs(int cpu)
 	return 0;
 }
 
-static int cpuid_callback(struct notifier_block *nb,
-			 unsigned long action, void *hcpu)
-{
-	int rc = 0;
-	unsigned long cpu = (unsigned long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-		rc = cpuid_add_regs(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		rc = cpuid_remove_regs(cpu);
-		break;
-	}
-
-	return notifier_from_errno(rc);
-}
-
 static int __init cpuinfo_regs_init(void)
 {
-	int cpu;
-
-	cpu_notifier_register_begin();
+	int cpu, ret;
 
 	for_each_possible_cpu(cpu) {
 		struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
 
 		kobject_init(&info->kobj, &cpuregs_kobj_type);
-		if (cpu_online(cpu))
-			cpuid_add_regs(cpu);
 	}
-	__hotcpu_notifier(cpuid_callback, 0);
 
-	cpu_notifier_register_done();
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/cpuinfo:online",
+				cpuid_cpu_online, cpuid_cpu_offline);
+	if (ret < 0) {
+		pr_err("cpuinfo: failed to register hotplug callbacks.\n");
+		return ret;
+	}
 	return 0;
 }
 static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
-- 
2.10.2

[PATCH 16/22] arm64/cpuinfo: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel at lists.infradead.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 arch/arm64/kernel/cpuinfo.c | 37 +++++++++----------------------------
 1 file changed, 9 insertions(+), 28 deletions(-)

diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 19aad7041e14..7b7be71e87bf 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -227,7 +227,7 @@ static struct attribute_group cpuregs_attr_group = {
 	.name = "identification"
 };
 
-static int cpuid_add_regs(int cpu)
+static int cpuid_cpu_online(unsigned int cpu)
 {
 	int rc;
 	struct device *dev;
@@ -248,7 +248,7 @@ static int cpuid_add_regs(int cpu)
 	return rc;
 }
 
-static int cpuid_remove_regs(int cpu)
+static int cpuid_cpu_offline(unsigned int cpu)
 {
 	struct device *dev;
 	struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
@@ -264,41 +264,22 @@ static int cpuid_remove_regs(int cpu)
 	return 0;
 }
 
-static int cpuid_callback(struct notifier_block *nb,
-			 unsigned long action, void *hcpu)
-{
-	int rc = 0;
-	unsigned long cpu = (unsigned long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-		rc = cpuid_add_regs(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		rc = cpuid_remove_regs(cpu);
-		break;
-	}
-
-	return notifier_from_errno(rc);
-}
-
 static int __init cpuinfo_regs_init(void)
 {
-	int cpu;
-
-	cpu_notifier_register_begin();
+	int cpu, ret;
 
 	for_each_possible_cpu(cpu) {
 		struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
 
 		kobject_init(&info->kobj, &cpuregs_kobj_type);
-		if (cpu_online(cpu))
-			cpuid_add_regs(cpu);
 	}
-	__hotcpu_notifier(cpuid_callback, 0);
 
-	cpu_notifier_register_done();
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/cpuinfo:online",
+				cpuid_cpu_online, cpuid_cpu_offline);
+	if (ret < 0) {
+		pr_err("cpuinfo: failed to register hotplug callbacks.\n");
+		return ret;
+	}
 	return 0;
 }
 static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
-- 
2.10.2

Re: [PATCH 16/22] arm64/cpuinfo: Convert to hotplug state machine

[Suzuki K Poulose]

On 26/11/16 23:13, Sebastian Andrzej Siewior wrote:
> From: Anna-Maria Gleixner <anna-maria@linutronix.de>
>
> Install the callbacks via the state machine and let the core invoke
> the callbacks on the already online CPUs.
>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Cc: linux-arm-kernel@lists.infradead.org
> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
>  arch/arm64/kernel/cpuinfo.c | 37 +++++++++----------------------------
>  1 file changed, 9 insertions(+), 28 deletions(-)
>
> diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
> index 19aad7041e14..7b7be71e87bf 100644
> --- a/arch/arm64/kernel/cpuinfo.c
> +++ b/arch/arm64/kernel/cpuinfo.c
> @@ -227,7 +227,7 @@ static struct attribute_group cpuregs_attr_group = {
...
> +	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/cpuinfo:online",
> +				cpuid_cpu_online, cpuid_cpu_offline);
> +	if (ret < 0) {
> +		pr_err("cpuinfo: failed to register hotplug callbacks.\n");
> +		return ret;
> +	}
>  	return 0;
>  }

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>

[PATCH 16/22] arm64/cpuinfo: Convert to hotplug state machine

[Suzuki K Poulose]

On 26/11/16 23:13, Sebastian Andrzej Siewior wrote:
> From: Anna-Maria Gleixner <anna-maria@linutronix.de>
>
> Install the callbacks via the state machine and let the core invoke
> the callbacks on the already online CPUs.
>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Cc: linux-arm-kernel at lists.infradead.org
> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
>  arch/arm64/kernel/cpuinfo.c | 37 +++++++++----------------------------
>  1 file changed, 9 insertions(+), 28 deletions(-)
>
> diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
> index 19aad7041e14..7b7be71e87bf 100644
> --- a/arch/arm64/kernel/cpuinfo.c
> +++ b/arch/arm64/kernel/cpuinfo.c
> @@ -227,7 +227,7 @@ static struct attribute_group cpuregs_attr_group = {
...
> +	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/cpuinfo:online",
> +				cpuid_cpu_online, cpuid_cpu_offline);
> +	if (ret < 0) {
> +		pr_err("cpuinfo: failed to register hotplug callbacks.\n");
> +		return ret;
> +	}
>  	return 0;
>  }

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>

[tip:smp/hotplug] arm64/cpuinfo: Convert to hotplug state machine

[tip-bot for Anna-Maria Gleixner]

Commit-ID:  a7ce95e1741f2d866481c8138a84ce5af61eb219
Gitweb:     http://git.kernel.org/tip/a7ce95e1741f2d866481c8138a84ce5af61eb219
Author:     Anna-Maria Gleixner <anna-maria@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:44 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:38 +0100

arm64/cpuinfo: Convert to hotplug state machine

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: rt@linutronix.de
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/20161126231350.10321-17-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/arm64/kernel/cpuinfo.c | 37 +++++++++----------------------------
 1 file changed, 9 insertions(+), 28 deletions(-)

diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 19aad70..7b7be71 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -227,7 +227,7 @@ static struct attribute_group cpuregs_attr_group = {
 	.name = "identification"
 };
 
-static int cpuid_add_regs(int cpu)
+static int cpuid_cpu_online(unsigned int cpu)
 {
 	int rc;
 	struct device *dev;
@@ -248,7 +248,7 @@ out:
 	return rc;
 }
 
-static int cpuid_remove_regs(int cpu)
+static int cpuid_cpu_offline(unsigned int cpu)
 {
 	struct device *dev;
 	struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
@@ -264,41 +264,22 @@ static int cpuid_remove_regs(int cpu)
 	return 0;
 }
 
-static int cpuid_callback(struct notifier_block *nb,
-			 unsigned long action, void *hcpu)
-{
-	int rc = 0;
-	unsigned long cpu = (unsigned long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-		rc = cpuid_add_regs(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		rc = cpuid_remove_regs(cpu);
-		break;
-	}
-
-	return notifier_from_errno(rc);
-}
-
 static int __init cpuinfo_regs_init(void)
 {
-	int cpu;
-
-	cpu_notifier_register_begin();
+	int cpu, ret;
 
 	for_each_possible_cpu(cpu) {
 		struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
 
 		kobject_init(&info->kobj, &cpuregs_kobj_type);
-		if (cpu_online(cpu))
-			cpuid_add_regs(cpu);
 	}
-	__hotcpu_notifier(cpuid_callback, 0);
 
-	cpu_notifier_register_done();
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/cpuinfo:online",
+				cpuid_cpu_online, cpuid_cpu_offline);
+	if (ret < 0) {
+		pr_err("cpuinfo: failed to register hotplug callbacks.\n");
+		return ret;
+	}
 	return 0;
 }
 static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)

[PATCH 17/22] KVM/PPC/Book3S HV: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.

Cc: Alexander Graf <agraf@suse.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: kvm-ppc@vger.kernel.org
Cc: kvm@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 arch/powerpc/kvm/book3s_hv.c | 48 ++++++++++----------------------------------
 include/linux/cpuhotplug.h   |  1 +
 2 files changed, 12 insertions(+), 37 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3686471be32b..39ef1f4a7b02 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2254,12 +2254,12 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master)
  * enter the guest. Only do this if it is the primary thread of the
  * core (not if a subcore) that is entering the guest.
  */
-static inline void kvmppc_clear_host_core(int cpu)
+static inline int kvmppc_clear_host_core(unsigned int cpu)
 {
 	int core;
 
 	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
-		return;
+		return 0;
 	/*
 	 * Memory barrier can be omitted here as we will do a smp_wmb()
 	 * later in kvmppc_start_thread and we need ensure that state is
@@ -2267,6 +2267,7 @@ static inline void kvmppc_clear_host_core(int cpu)
 	 */
 	core = cpu >> threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0;
+	return 0;
 }
 
 /*
@@ -2274,12 +2275,12 @@ static inline void kvmppc_clear_host_core(int cpu)
  * Only need to do this if it is the primary thread of the core that is
  * exiting.
  */
-static inline void kvmppc_set_host_core(int cpu)
+static inline int kvmppc_set_host_core(unsigned int cpu)
 {
 	int core;
 
 	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
-		return;
+		return 0;
 
 	/*
 	 * Memory barrier can be omitted here because we do a spin_unlock
@@ -2287,6 +2288,7 @@ static inline void kvmppc_set_host_core(int cpu)
 	 */
 	core = cpu >> threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1;
+	return 0;
 }
 
 /*
@@ -3094,36 +3096,6 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 }
 
 #ifdef CONFIG_KVM_XICS
-static int kvmppc_cpu_notify(struct notifier_block *self, unsigned long action,
-			void *hcpu)
-{
-	unsigned long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		kvmppc_set_host_core(cpu);
-		break;
-
-#ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		kvmppc_clear_host_core(cpu);
-		break;
-#endif
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block kvmppc_cpu_notifier = {
-	    .notifier_call = kvmppc_cpu_notify,
-};
-
 /*
  * Allocate a per-core structure for managing state about which cores are
  * running in the host versus the guest and for exchanging data between
@@ -3185,15 +3157,17 @@ void kvmppc_alloc_host_rm_ops(void)
 		return;
 	}
 
-	register_cpu_notifier(&kvmppc_cpu_notifier);
-
+	cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE,
+				  "ppc/kvm_book3s:prepare",
+				  kvmppc_set_host_core,
+				  kvmppc_clear_host_core);
 	put_online_cpus();
 }
 
 void kvmppc_free_host_rm_ops(void)
 {
 	if (kvmppc_host_rm_ops_hv) {
-		unregister_cpu_notifier(&kvmppc_cpu_notifier);
+		cpuhp_remove_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE);
 		kfree(kvmppc_host_rm_ops_hv->rm_core);
 		kfree(kvmppc_host_rm_ops_hv);
 		kvmppc_host_rm_ops_hv = NULL;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 853f8176594d..71c6822dd5be 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -68,6 +68,7 @@ enum cpuhp_state {
 	CPUHP_MM_ZS_PREPARE,
 	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_MM_ZSWP_POOL_PREPARE,
+	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
-- 
2.10.2

[PATCH 17/22] KVM/PPC/Book3S HV: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.

Cc: Alexander Graf <agraf@suse.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: kvm-ppc@vger.kernel.org
Cc: kvm@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 arch/powerpc/kvm/book3s_hv.c | 48 ++++++++++----------------------------------
 include/linux/cpuhotplug.h   |  1 +
 2 files changed, 12 insertions(+), 37 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3686471be32b..39ef1f4a7b02 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2254,12 +2254,12 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master)
  * enter the guest. Only do this if it is the primary thread of the
  * core (not if a subcore) that is entering the guest.
  */
-static inline void kvmppc_clear_host_core(int cpu)
+static inline int kvmppc_clear_host_core(unsigned int cpu)
 {
 	int core;
 
 	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
-		return;
+		return 0;
 	/*
 	 * Memory barrier can be omitted here as we will do a smp_wmb()
 	 * later in kvmppc_start_thread and we need ensure that state is
@@ -2267,6 +2267,7 @@ static inline void kvmppc_clear_host_core(int cpu)
 	 */
 	core = cpu >> threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0;
+	return 0;
 }
 
 /*
@@ -2274,12 +2275,12 @@ static inline void kvmppc_clear_host_core(int cpu)
  * Only need to do this if it is the primary thread of the core that is
  * exiting.
  */
-static inline void kvmppc_set_host_core(int cpu)
+static inline int kvmppc_set_host_core(unsigned int cpu)
 {
 	int core;
 
 	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
-		return;
+		return 0;
 
 	/*
 	 * Memory barrier can be omitted here because we do a spin_unlock
@@ -2287,6 +2288,7 @@ static inline void kvmppc_set_host_core(int cpu)
 	 */
 	core = cpu >> threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1;
+	return 0;
 }
 
 /*
@@ -3094,36 +3096,6 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 }
 
 #ifdef CONFIG_KVM_XICS
-static int kvmppc_cpu_notify(struct notifier_block *self, unsigned long action,
-			void *hcpu)
-{
-	unsigned long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		kvmppc_set_host_core(cpu);
-		break;
-
-#ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		kvmppc_clear_host_core(cpu);
-		break;
-#endif
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block kvmppc_cpu_notifier = {
-	    .notifier_call = kvmppc_cpu_notify,
-};
-
 /*
  * Allocate a per-core structure for managing state about which cores are
  * running in the host versus the guest and for exchanging data between
@@ -3185,15 +3157,17 @@ void kvmppc_alloc_host_rm_ops(void)
 		return;
 	}
 
-	register_cpu_notifier(&kvmppc_cpu_notifier);
-
+	cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE,
+				  "ppc/kvm_book3s:prepare",
+				  kvmppc_set_host_core,
+				  kvmppc_clear_host_core);
 	put_online_cpus();
 }
 
 void kvmppc_free_host_rm_ops(void)
 {
 	if (kvmppc_host_rm_ops_hv) {
-		unregister_cpu_notifier(&kvmppc_cpu_notifier);
+		cpuhp_remove_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE);
 		kfree(kvmppc_host_rm_ops_hv->rm_core);
 		kfree(kvmppc_host_rm_ops_hv);
 		kvmppc_host_rm_ops_hv = NULL;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 853f8176594d..71c6822dd5be 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -68,6 +68,7 @@ enum cpuhp_state {
 	CPUHP_MM_ZS_PREPARE,
 	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_MM_ZSWP_POOL_PREPARE,
+	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
-- 
2.10.2

[PATCH 17/22] KVM/PPC/Book3S HV: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.

Cc: Alexander Graf <agraf@suse.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Kr=C4=8Dm=C3=A1=C5=99" <rkrcmar@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: kvm-ppc@vger.kernel.org
Cc: kvm@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 arch/powerpc/kvm/book3s_hv.c | 48 ++++++++++------------------------------=
----
 include/linux/cpuhotplug.h   |  1 +
 2 files changed, 12 insertions(+), 37 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3686471be32b..39ef1f4a7b02 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2254,12 +2254,12 @@ static void post_guest_process(struct kvmppc_vcore =
*vc, bool is_master)
  * enter the guest. Only do this if it is the primary thread of the
  * core (not if a subcore) that is entering the guest.
  */
-static inline void kvmppc_clear_host_core(int cpu)
+static inline int kvmppc_clear_host_core(unsigned int cpu)
 {
 	int core;
=20
 	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
-		return;
+		return 0;
 	/*
 	 * Memory barrier can be omitted here as we will do a smp_wmb()
 	 * later in kvmppc_start_thread and we need ensure that state is
@@ -2267,6 +2267,7 @@ static inline void kvmppc_clear_host_core(int cpu)
 	 */
 	core =3D cpu >> threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host =3D 0;
+	return 0;
 }
=20
 /*
@@ -2274,12 +2275,12 @@ static inline void kvmppc_clear_host_core(int cpu)
  * Only need to do this if it is the primary thread of the core that is
  * exiting.
  */
-static inline void kvmppc_set_host_core(int cpu)
+static inline int kvmppc_set_host_core(unsigned int cpu)
 {
 	int core;
=20
 	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
-		return;
+		return 0;
=20
 	/*
 	 * Memory barrier can be omitted here because we do a spin_unlock
@@ -2287,6 +2288,7 @@ static inline void kvmppc_set_host_core(int cpu)
 	 */
 	core =3D cpu >> threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host =3D 1;
+	return 0;
 }
=20
 /*
@@ -3094,36 +3096,6 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu =
*vcpu)
 }
=20
 #ifdef CONFIG_KVM_XICS
-static int kvmppc_cpu_notify(struct notifier_block *self, unsigned long ac=
tion,
-			void *hcpu)
-{
-	unsigned long cpu =3D (long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		kvmppc_set_host_core(cpu);
-		break;
-
-#ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		kvmppc_clear_host_core(cpu);
-		break;
-#endif
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block kvmppc_cpu_notifier =3D {
-	    .notifier_call =3D kvmppc_cpu_notify,
-};
-
 /*
  * Allocate a per-core structure for managing state about which cores are
  * running in the host versus the guest and for exchanging data between
@@ -3185,15 +3157,17 @@ void kvmppc_alloc_host_rm_ops(void)
 		return;
 	}
=20
-	register_cpu_notifier(&kvmppc_cpu_notifier);
-
+	cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE,
+				  "ppc/kvm_book3s:prepare",
+				  kvmppc_set_host_core,
+				  kvmppc_clear_host_core);
 	put_online_cpus();
 }
=20
 void kvmppc_free_host_rm_ops(void)
 {
 	if (kvmppc_host_rm_ops_hv) {
-		unregister_cpu_notifier(&kvmppc_cpu_notifier);
+		cpuhp_remove_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE);
 		kfree(kvmppc_host_rm_ops_hv->rm_core);
 		kfree(kvmppc_host_rm_ops_hv);
 		kvmppc_host_rm_ops_hv =3D NULL;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 853f8176594d..71c6822dd5be 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -68,6 +68,7 @@ enum cpuhp_state {
 	CPUHP_MM_ZS_PREPARE,
 	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_MM_ZSWP_POOL_PREPARE,
+	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
--=20
2.10.2

[tip:smp/hotplug] KVM/PPC/Book3S HV: Convert to hotplug state machine

[tip-bot for Anna-Maria Gleixner]

Commit-ID:  3f7cd919f3df05918535de39273174710409eb40
Gitweb:     http://git.kernel.org/tip/3f7cd919f3df05918535de39273174710409eb40
Author:     Anna-Maria Gleixner <anna-maria@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:45 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:38 +0100

KVM/PPC/Book3S HV: Convert to hotplug state machine

Install the callbacks via the state machine.

Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: kvm@vger.kernel.org
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: kvm-ppc@vger.kernel.org
Cc: Paul Mackerras <paulus@samba.org>
Cc: rt@linutronix.de
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Alexander Graf <agraf@suse.com>
Link: http://lkml.kernel.org/r/20161126231350.10321-18-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/powerpc/kvm/book3s_hv.c | 48 ++++++++++----------------------------------
 include/linux/cpuhotplug.h   |  1 +
 2 files changed, 12 insertions(+), 37 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3686471..39ef1f4 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2254,12 +2254,12 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master)
  * enter the guest. Only do this if it is the primary thread of the
  * core (not if a subcore) that is entering the guest.
  */
-static inline void kvmppc_clear_host_core(int cpu)
+static inline int kvmppc_clear_host_core(unsigned int cpu)
 {
 	int core;
 
 	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
-		return;
+		return 0;
 	/*
 	 * Memory barrier can be omitted here as we will do a smp_wmb()
 	 * later in kvmppc_start_thread and we need ensure that state is
@@ -2267,6 +2267,7 @@ static inline void kvmppc_clear_host_core(int cpu)
 	 */
 	core = cpu >> threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0;
+	return 0;
 }
 
 /*
@@ -2274,12 +2275,12 @@ static inline void kvmppc_clear_host_core(int cpu)
  * Only need to do this if it is the primary thread of the core that is
  * exiting.
  */
-static inline void kvmppc_set_host_core(int cpu)
+static inline int kvmppc_set_host_core(unsigned int cpu)
 {
 	int core;
 
 	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
-		return;
+		return 0;
 
 	/*
 	 * Memory barrier can be omitted here because we do a spin_unlock
@@ -2287,6 +2288,7 @@ static inline void kvmppc_set_host_core(int cpu)
 	 */
 	core = cpu >> threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1;
+	return 0;
 }
 
 /*
@@ -3094,36 +3096,6 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 }
 
 #ifdef CONFIG_KVM_XICS
-static int kvmppc_cpu_notify(struct notifier_block *self, unsigned long action,
-			void *hcpu)
-{
-	unsigned long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		kvmppc_set_host_core(cpu);
-		break;
-
-#ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		kvmppc_clear_host_core(cpu);
-		break;
-#endif
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block kvmppc_cpu_notifier = {
-	    .notifier_call = kvmppc_cpu_notify,
-};
-
 /*
  * Allocate a per-core structure for managing state about which cores are
  * running in the host versus the guest and for exchanging data between
@@ -3185,15 +3157,17 @@ void kvmppc_alloc_host_rm_ops(void)
 		return;
 	}
 
-	register_cpu_notifier(&kvmppc_cpu_notifier);
-
+	cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE,
+				  "ppc/kvm_book3s:prepare",
+				  kvmppc_set_host_core,
+				  kvmppc_clear_host_core);
 	put_online_cpus();
 }
 
 void kvmppc_free_host_rm_ops(void)
 {
 	if (kvmppc_host_rm_ops_hv) {
-		unregister_cpu_notifier(&kvmppc_cpu_notifier);
+		cpuhp_remove_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE);
 		kfree(kvmppc_host_rm_ops_hv->rm_core);
 		kfree(kvmppc_host_rm_ops_hv);
 		kvmppc_host_rm_ops_hv = NULL;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 853f817..71c6822 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -68,6 +68,7 @@ enum cpuhp_state {
 	CPUHP_MM_ZS_PREPARE,
 	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_MM_ZSWP_POOL_PREPARE,
+	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,

[PATCH 18/22] zram: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine with multi instance support and let
the core invoke the callbacks on the already online CPUs.

Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
[bigeasy: wire up the multi instance stuff]
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/block/zram/zcomp.c    | 76 ++++++++++++++-----------------------------
 drivers/block/zram/zcomp.h    |  5 +--
 drivers/block/zram/zram_drv.c |  9 +++++
 include/linux/cpuhotplug.h    |  1 +
 4 files changed, 38 insertions(+), 53 deletions(-)

diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 4b5cd3a7b2b6..12046f4f00e4 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -160,82 +160,56 @@ int zcomp_decompress(struct zcomp_strm *zstrm,
 			dst, &dst_len);
 }
 
-static int __zcomp_cpu_notifier(struct zcomp *comp,
-		unsigned long action, unsigned long cpu)
+int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
 {
+	struct zcomp *comp = hlist_entry(node, struct zcomp, node);
 	struct zcomp_strm *zstrm;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
-			break;
-		zstrm = zcomp_strm_alloc(comp);
-		if (IS_ERR_OR_NULL(zstrm)) {
-			pr_err("Can't allocate a compression stream\n");
-			return NOTIFY_BAD;
-		}
-		*per_cpu_ptr(comp->stream, cpu) = zstrm;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		zstrm = *per_cpu_ptr(comp->stream, cpu);
-		if (!IS_ERR_OR_NULL(zstrm))
-			zcomp_strm_free(zstrm);
-		*per_cpu_ptr(comp->stream, cpu) = NULL;
-		break;
-	default:
-		break;
+	if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
+		return 0;
+
+	zstrm = zcomp_strm_alloc(comp);
+	if (IS_ERR_OR_NULL(zstrm)) {
+		pr_err("Can't allocate a compression stream\n");
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
+	*per_cpu_ptr(comp->stream, cpu) = zstrm;
+	return 0;
 }
 
-static int zcomp_cpu_notifier(struct notifier_block *nb,
-		unsigned long action, void *pcpu)
+int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node)
 {
-	unsigned long cpu = (unsigned long)pcpu;
-	struct zcomp *comp = container_of(nb, typeof(*comp), notifier);
+	struct zcomp *comp = hlist_entry(node, struct zcomp, node);
+	struct zcomp_strm *zstrm;
 
-	return __zcomp_cpu_notifier(comp, action, cpu);
+	zstrm = *per_cpu_ptr(comp->stream, cpu);
+	if (!IS_ERR_OR_NULL(zstrm))
+		zcomp_strm_free(zstrm);
+	*per_cpu_ptr(comp->stream, cpu) = NULL;
+	return 0;
 }
 
 static int zcomp_init(struct zcomp *comp)
 {
-	unsigned long cpu;
 	int ret;
 
-	comp->notifier.notifier_call = zcomp_cpu_notifier;
-
 	comp->stream = alloc_percpu(struct zcomp_strm *);
 	if (!comp->stream)
 		return -ENOMEM;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu) {
-		ret = __zcomp_cpu_notifier(comp, CPU_UP_PREPARE, cpu);
-		if (ret == NOTIFY_BAD)
-			goto cleanup;
-	}
-	__register_cpu_notifier(&comp->notifier);
-	cpu_notifier_register_done();
+	ret = cpuhp_state_add_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
+	if (ret < 0)
+		goto cleanup;
 	return 0;
 
 cleanup:
-	for_each_online_cpu(cpu)
-		__zcomp_cpu_notifier(comp, CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
+	free_percpu(comp->stream);
+	return ret;
 }
 
 void zcomp_destroy(struct zcomp *comp)
 {
-	unsigned long cpu;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zcomp_cpu_notifier(comp, CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&comp->notifier);
-	cpu_notifier_register_done();
-
+	cpuhp_state_remove_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
 	free_percpu(comp->stream);
 	kfree(comp);
 }
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 478cac2ed465..41c1002a7d7d 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -19,11 +19,12 @@ struct zcomp_strm {
 /* dynamic per-device compression frontend */
 struct zcomp {
 	struct zcomp_strm * __percpu *stream;
-	struct notifier_block notifier;
-
 	const char *name;
+	struct hlist_node node;
 };
 
+int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node);
+int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node);
 ssize_t zcomp_available_show(const char *comp, char *buf);
 bool zcomp_available_algorithm(const char *comp);
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 04365b17ee67..511c35fd5c6f 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -30,6 +30,7 @@
 #include <linux/err.h>
 #include <linux/idr.h>
 #include <linux/sysfs.h>
+#include <linux/cpuhotplug.h>
 
 #include "zram_drv.h"
 
@@ -1436,15 +1437,22 @@ static void destroy_devices(void)
 	idr_for_each(&zram_index_idr, &zram_remove_cb, NULL);
 	idr_destroy(&zram_index_idr);
 	unregister_blkdev(zram_major, "zram");
+	cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
 }
 
 static int __init zram_init(void)
 {
 	int ret;
 
+	ret = cpuhp_setup_state_multi(CPUHP_ZCOMP_PREPARE, "block/zram:prepare",
+				      zcomp_cpu_up_prepare, zcomp_cpu_dead);
+	if (ret < 0)
+		return ret;
+
 	ret = class_register(&zram_control_class);
 	if (ret) {
 		pr_err("Unable to register zram-control class\n");
+		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
 		return ret;
 	}
 
@@ -1452,6 +1460,7 @@ static int __init zram_init(void)
 	if (zram_major <= 0) {
 		pr_err("Unable to get major number\n");
 		class_unregister(&zram_control_class);
+		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
 		return -EBUSY;
 	}
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 71c6822dd5be..22acee76cf4c 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -69,6 +69,7 @@ enum cpuhp_state {
 	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
+	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
-- 
2.10.2

[tip:smp/hotplug] zram: Convert to hotplug state machine

[tip-bot for Anna-Maria Gleixner]

Commit-ID:  1dd6c834fa4a75a86fecefb6d1f1525f1cb755c7
Gitweb:     http://git.kernel.org/tip/1dd6c834fa4a75a86fecefb6d1f1525f1cb755c7
Author:     Anna-Maria Gleixner <anna-maria@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:46 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:39 +0100

zram: Convert to hotplug state machine

Install the callbacks via the state machine with multi instance support and let
the core invoke the callbacks on the already online CPUs.

[bigeasy: wire up the multi instance stuff]
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: rt@linutronix.de
Cc: Nitin Gupta <ngupta@vflare.org>
Link: http://lkml.kernel.org/r/20161126231350.10321-19-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/block/zram/zcomp.c    | 76 ++++++++++++++-----------------------------
 drivers/block/zram/zcomp.h    |  5 +--
 drivers/block/zram/zram_drv.c |  9 +++++
 include/linux/cpuhotplug.h    |  1 +
 4 files changed, 38 insertions(+), 53 deletions(-)

diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 4b5cd3a..12046f4 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -160,82 +160,56 @@ int zcomp_decompress(struct zcomp_strm *zstrm,
 			dst, &dst_len);
 }
 
-static int __zcomp_cpu_notifier(struct zcomp *comp,
-		unsigned long action, unsigned long cpu)
+int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
 {
+	struct zcomp *comp = hlist_entry(node, struct zcomp, node);
 	struct zcomp_strm *zstrm;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
-			break;
-		zstrm = zcomp_strm_alloc(comp);
-		if (IS_ERR_OR_NULL(zstrm)) {
-			pr_err("Can't allocate a compression stream\n");
-			return NOTIFY_BAD;
-		}
-		*per_cpu_ptr(comp->stream, cpu) = zstrm;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		zstrm = *per_cpu_ptr(comp->stream, cpu);
-		if (!IS_ERR_OR_NULL(zstrm))
-			zcomp_strm_free(zstrm);
-		*per_cpu_ptr(comp->stream, cpu) = NULL;
-		break;
-	default:
-		break;
+	if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
+		return 0;
+
+	zstrm = zcomp_strm_alloc(comp);
+	if (IS_ERR_OR_NULL(zstrm)) {
+		pr_err("Can't allocate a compression stream\n");
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
+	*per_cpu_ptr(comp->stream, cpu) = zstrm;
+	return 0;
 }
 
-static int zcomp_cpu_notifier(struct notifier_block *nb,
-		unsigned long action, void *pcpu)
+int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node)
 {
-	unsigned long cpu = (unsigned long)pcpu;
-	struct zcomp *comp = container_of(nb, typeof(*comp), notifier);
+	struct zcomp *comp = hlist_entry(node, struct zcomp, node);
+	struct zcomp_strm *zstrm;
 
-	return __zcomp_cpu_notifier(comp, action, cpu);
+	zstrm = *per_cpu_ptr(comp->stream, cpu);
+	if (!IS_ERR_OR_NULL(zstrm))
+		zcomp_strm_free(zstrm);
+	*per_cpu_ptr(comp->stream, cpu) = NULL;
+	return 0;
 }
 
 static int zcomp_init(struct zcomp *comp)
 {
-	unsigned long cpu;
 	int ret;
 
-	comp->notifier.notifier_call = zcomp_cpu_notifier;
-
 	comp->stream = alloc_percpu(struct zcomp_strm *);
 	if (!comp->stream)
 		return -ENOMEM;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu) {
-		ret = __zcomp_cpu_notifier(comp, CPU_UP_PREPARE, cpu);
-		if (ret == NOTIFY_BAD)
-			goto cleanup;
-	}
-	__register_cpu_notifier(&comp->notifier);
-	cpu_notifier_register_done();
+	ret = cpuhp_state_add_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
+	if (ret < 0)
+		goto cleanup;
 	return 0;
 
 cleanup:
-	for_each_online_cpu(cpu)
-		__zcomp_cpu_notifier(comp, CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
+	free_percpu(comp->stream);
+	return ret;
 }
 
 void zcomp_destroy(struct zcomp *comp)
 {
-	unsigned long cpu;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zcomp_cpu_notifier(comp, CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&comp->notifier);
-	cpu_notifier_register_done();
-
+	cpuhp_state_remove_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
 	free_percpu(comp->stream);
 	kfree(comp);
 }
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 478cac2..41c1002 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -19,11 +19,12 @@ struct zcomp_strm {
 /* dynamic per-device compression frontend */
 struct zcomp {
 	struct zcomp_strm * __percpu *stream;
-	struct notifier_block notifier;
-
 	const char *name;
+	struct hlist_node node;
 };
 
+int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node);
+int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node);
 ssize_t zcomp_available_show(const char *comp, char *buf);
 bool zcomp_available_algorithm(const char *comp);
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 04365b1..511c35f 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -30,6 +30,7 @@
 #include <linux/err.h>
 #include <linux/idr.h>
 #include <linux/sysfs.h>
+#include <linux/cpuhotplug.h>
 
 #include "zram_drv.h"
 
@@ -1436,15 +1437,22 @@ static void destroy_devices(void)
 	idr_for_each(&zram_index_idr, &zram_remove_cb, NULL);
 	idr_destroy(&zram_index_idr);
 	unregister_blkdev(zram_major, "zram");
+	cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
 }
 
 static int __init zram_init(void)
 {
 	int ret;
 
+	ret = cpuhp_setup_state_multi(CPUHP_ZCOMP_PREPARE, "block/zram:prepare",
+				      zcomp_cpu_up_prepare, zcomp_cpu_dead);
+	if (ret < 0)
+		return ret;
+
 	ret = class_register(&zram_control_class);
 	if (ret) {
 		pr_err("Unable to register zram-control class\n");
+		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
 		return ret;
 	}
 
@@ -1452,6 +1460,7 @@ static int __init zram_init(void)
 	if (zram_major <= 0) {
 		pr_err("Unable to get major number\n");
 		class_unregister(&zram_control_class);
+		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
 		return -EBUSY;
 	}
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 71c6822..22acee7 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -69,6 +69,7 @@ enum cpuhp_state {
 	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
+	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,

[PATCH 19/22] soc/fsl/qbman: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine.

Cc: Roy Pledge <roy.pledge@nxp.com>
Cc: Scott Wood <oss@buserror.net>
Cc: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 drivers/soc/fsl/qbman/bman_portal.c | 46 +++++++++++++------------------------
 1 file changed, 16 insertions(+), 30 deletions(-)

diff --git a/drivers/soc/fsl/qbman/bman_portal.c b/drivers/soc/fsl/qbman/bman_portal.c
index 6579cc18811a..986f64690e6e 100644
--- a/drivers/soc/fsl/qbman/bman_portal.c
+++ b/drivers/soc/fsl/qbman/bman_portal.c
@@ -53,58 +53,38 @@ static struct bman_portal *init_pcfg(struct bm_portal_config *pcfg)
 	return p;
 }
 
-static void bman_offline_cpu(unsigned int cpu)
+static int bman_offline_cpu(unsigned int cpu)
 {
 	struct bman_portal *p = affine_bportals[cpu];
 	const struct bm_portal_config *pcfg;
 
 	if (!p)
-		return;
+		return 0;
 
 	pcfg = bman_get_bm_portal_config(p);
 	if (!pcfg)
-		return;
+		return 0;
 
 	irq_set_affinity(pcfg->irq, cpumask_of(0));
+	return 0;
 }
 
-static void bman_online_cpu(unsigned int cpu)
+static int bman_online_cpu(unsigned int cpu)
 {
 	struct bman_portal *p = affine_bportals[cpu];
 	const struct bm_portal_config *pcfg;
 
 	if (!p)
-		return;
+		return 0;
 
 	pcfg = bman_get_bm_portal_config(p);
 	if (!pcfg)
-		return;
+		return 0;
 
 	irq_set_affinity(pcfg->irq, cpumask_of(cpu));
+	return 0;
 }
 
-static int bman_hotplug_cpu_callback(struct notifier_block *nfb,
-				     unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		bman_online_cpu(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		bman_offline_cpu(cpu);
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block bman_hotplug_cpu_notifier = {
-	.notifier_call = bman_hotplug_cpu_callback,
-};
-
 static int bman_portal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -210,8 +190,14 @@ static int __init bman_portal_driver_register(struct platform_driver *drv)
 	if (ret < 0)
 		return ret;
 
-	register_hotcpu_notifier(&bman_hotplug_cpu_notifier);
-
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"soc/qbman_portal:online",
+					bman_online_cpu, bman_offline_cpu);
+	if (ret < 0) {
+		pr_err("bman: failed to register hotplug callbacks.\n");
+		platform_driver_unregister(drv);
+		return ret;
+	}
 	return 0;
 }
 
-- 
2.10.2

[tip:smp/hotplug] soc/fsl/qbman: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  fce77c3562eccdd8002c9c7947f00af70e00a375
Gitweb:     http://git.kernel.org/tip/fce77c3562eccdd8002c9c7947f00af70e00a375
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:47 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:39 +0100

soc/fsl/qbman: Convert to hotplug state machine

Install the callbacks via the state machine.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Scott Wood <oss@buserror.net>
Cc: Claudiu Manoil <claudiu.manoil@nxp.com>
Cc: rt@linutronix.de
Cc: Roy Pledge <roy.pledge@nxp.com>
Link: http://lkml.kernel.org/r/20161126231350.10321-20-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/soc/fsl/qbman/bman_portal.c | 46 +++++++++++++------------------------
 1 file changed, 16 insertions(+), 30 deletions(-)

diff --git a/drivers/soc/fsl/qbman/bman_portal.c b/drivers/soc/fsl/qbman/bman_portal.c
index 6579cc1..986f646 100644
--- a/drivers/soc/fsl/qbman/bman_portal.c
+++ b/drivers/soc/fsl/qbman/bman_portal.c
@@ -53,58 +53,38 @@ static struct bman_portal *init_pcfg(struct bm_portal_config *pcfg)
 	return p;
 }
 
-static void bman_offline_cpu(unsigned int cpu)
+static int bman_offline_cpu(unsigned int cpu)
 {
 	struct bman_portal *p = affine_bportals[cpu];
 	const struct bm_portal_config *pcfg;
 
 	if (!p)
-		return;
+		return 0;
 
 	pcfg = bman_get_bm_portal_config(p);
 	if (!pcfg)
-		return;
+		return 0;
 
 	irq_set_affinity(pcfg->irq, cpumask_of(0));
+	return 0;
 }
 
-static void bman_online_cpu(unsigned int cpu)
+static int bman_online_cpu(unsigned int cpu)
 {
 	struct bman_portal *p = affine_bportals[cpu];
 	const struct bm_portal_config *pcfg;
 
 	if (!p)
-		return;
+		return 0;
 
 	pcfg = bman_get_bm_portal_config(p);
 	if (!pcfg)
-		return;
+		return 0;
 
 	irq_set_affinity(pcfg->irq, cpumask_of(cpu));
+	return 0;
 }
 
-static int bman_hotplug_cpu_callback(struct notifier_block *nfb,
-				     unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		bman_online_cpu(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		bman_offline_cpu(cpu);
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block bman_hotplug_cpu_notifier = {
-	.notifier_call = bman_hotplug_cpu_callback,
-};
-
 static int bman_portal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -210,8 +190,14 @@ static int __init bman_portal_driver_register(struct platform_driver *drv)
 	if (ret < 0)
 		return ret;
 
-	register_hotcpu_notifier(&bman_hotplug_cpu_notifier);
-
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"soc/qbman_portal:online",
+					bman_online_cpu, bman_offline_cpu);
+	if (ret < 0) {
+		pr_err("bman: failed to register hotplug callbacks.\n");
+		platform_driver_unregister(drv);
+		return ret;
+	}
 	return 0;
 }
 

[PATCH 20/22] soc/fsl/qbman: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine.

Cc: Claudiu Manoil <claudiu.manoil@nxp.com>
Cc: Scott Wood <oss@buserror.net>
Cc: Roy Pledge <roy.pledge@nxp.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 drivers/soc/fsl/qbman/qman_portal.c | 39 ++++++++++++-------------------------
 1 file changed, 12 insertions(+), 27 deletions(-)

diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c
index 148614388fca..d068e4820f49 100644
--- a/drivers/soc/fsl/qbman/qman_portal.c
+++ b/drivers/soc/fsl/qbman/qman_portal.c
@@ -179,7 +179,7 @@ static void qman_portal_update_sdest(const struct qm_portal_config *pcfg,
 	qman_set_sdest(pcfg->channel, cpu);
 }
 
-static void qman_offline_cpu(unsigned int cpu)
+static int qman_offline_cpu(unsigned int cpu)
 {
 	struct qman_portal *p;
 	const struct qm_portal_config *pcfg;
@@ -192,9 +192,10 @@ static void qman_offline_cpu(unsigned int cpu)
 			qman_portal_update_sdest(pcfg, 0);
 		}
 	}
+	return 0;
 }
 
-static void qman_online_cpu(unsigned int cpu)
+static int qman_online_cpu(unsigned int cpu)
 {
 	struct qman_portal *p;
 	const struct qm_portal_config *pcfg;
@@ -207,31 +208,9 @@ static void qman_online_cpu(unsigned int cpu)
 			qman_portal_update_sdest(pcfg, cpu);
 		}
 	}
+	return 0;
 }
 
-static int qman_hotplug_cpu_callback(struct notifier_block *nfb,
-				     unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		qman_online_cpu(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		qman_offline_cpu(cpu);
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block qman_hotplug_cpu_notifier = {
-	.notifier_call = qman_hotplug_cpu_callback,
-};
-
 static int qman_portal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -346,8 +325,14 @@ static int __init qman_portal_driver_register(struct platform_driver *drv)
 	if (ret < 0)
 		return ret;
 
-	register_hotcpu_notifier(&qman_hotplug_cpu_notifier);
-
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"soc/qman_portal:online",
+					qman_online_cpu, qman_offline_cpu);
+	if (ret < 0) {
+		pr_err("qman: failed to register hotplug callbacks.\n");
+		platform_driver_unregister(drv);
+		return ret;
+	}
 	return 0;
 }
 
-- 
2.10.2

[tip:smp/hotplug] soc/fsl/qbman: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  1f759d328f6d8c06b5db55374b028565187deaca
Gitweb:     http://git.kernel.org/tip/1f759d328f6d8c06b5db55374b028565187deaca
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Sun, 27 Nov 2016 00:13:48 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Fri, 2 Dec 2016 00:52:40 +0100

soc/fsl/qbman: Convert to hotplug state machine

Install the callbacks via the state machine.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Scott Wood <oss@buserror.net>
Cc: Claudiu Manoil <claudiu.manoil@nxp.com>
Cc: rt@linutronix.de
Cc: Roy Pledge <roy.pledge@nxp.com>
Link: http://lkml.kernel.org/r/20161126231350.10321-21-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/soc/fsl/qbman/qman_portal.c | 39 ++++++++++++-------------------------
 1 file changed, 12 insertions(+), 27 deletions(-)

diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c
index 1486143..d068e48 100644
--- a/drivers/soc/fsl/qbman/qman_portal.c
+++ b/drivers/soc/fsl/qbman/qman_portal.c
@@ -179,7 +179,7 @@ static void qman_portal_update_sdest(const struct qm_portal_config *pcfg,
 	qman_set_sdest(pcfg->channel, cpu);
 }
 
-static void qman_offline_cpu(unsigned int cpu)
+static int qman_offline_cpu(unsigned int cpu)
 {
 	struct qman_portal *p;
 	const struct qm_portal_config *pcfg;
@@ -192,9 +192,10 @@ static void qman_offline_cpu(unsigned int cpu)
 			qman_portal_update_sdest(pcfg, 0);
 		}
 	}
+	return 0;
 }
 
-static void qman_online_cpu(unsigned int cpu)
+static int qman_online_cpu(unsigned int cpu)
 {
 	struct qman_portal *p;
 	const struct qm_portal_config *pcfg;
@@ -207,31 +208,9 @@ static void qman_online_cpu(unsigned int cpu)
 			qman_portal_update_sdest(pcfg, cpu);
 		}
 	}
+	return 0;
 }
 
-static int qman_hotplug_cpu_callback(struct notifier_block *nfb,
-				     unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		qman_online_cpu(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		qman_offline_cpu(cpu);
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block qman_hotplug_cpu_notifier = {
-	.notifier_call = qman_hotplug_cpu_callback,
-};
-
 static int qman_portal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -346,8 +325,14 @@ static int __init qman_portal_driver_register(struct platform_driver *drv)
 	if (ret < 0)
 		return ret;
 
-	register_hotcpu_notifier(&qman_hotplug_cpu_notifier);
-
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"soc/qman_portal:online",
+					qman_online_cpu, qman_offline_cpu);
+	if (ret < 0) {
+		pr_err("qman: failed to register hotplug callbacks.\n");
+		platform_driver_unregister(drv);
+		return ret;
+	}
 	return 0;
 }
 

[PATCH 21/22] staging/lustre/libcfs: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.

Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: James Simmons <jsimmons@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: lustre-devel@lists.lustre.org
Cc: devel@driverdev.osuosl.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 .../staging/lustre/lnet/libcfs/linux/linux-cpu.c   | 89 ++++++++++++----------
 include/linux/cpuhotplug.h                         |  1 +
 2 files changed, 50 insertions(+), 40 deletions(-)

diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index e8b1a61420de..a75113ab2903 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -73,6 +73,9 @@ struct cfs_cpt_data {
 };
 
 static struct cfs_cpt_data	cpt_data;
+#ifdef CONFIG_HOTPLUG_CPU
+static enum cpuhp_state lustre_cpu_online;
+#endif
 
 static void
 cfs_node_to_cpumask(int node, cpumask_t *mask)
@@ -942,48 +945,38 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+
+static void cfs_cpu_incr_cpt_version(void)
 {
-	unsigned int  cpu = (unsigned long)hcpu;
-	bool	     warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
-
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
-
-	return NOTIFY_OK;
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
+}
 
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+	int next;
+
+	cfs_cpu_incr_cpt_version();
+
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask, topology_sibling_cpumask(cpu));
+	next = cpumask_any_and(cpt_data.cpt_cpumask, cpu_online_mask);
+	warn = next >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -993,7 +986,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1002,6 +997,10 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+#ifdef CONFIG_HOTPLUG_CPU
+	int ret;
+#endif
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1016,7 +1015,17 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
 
 	if (*cpu_pattern != 0) {
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 22acee76cf4c..141c3be242d1 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-- 
2.10.2

[lustre-devel] [PATCH 21/22] staging/lustre/libcfs: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.

Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: James Simmons <jsimmons@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: lustre-devel at lists.lustre.org
Cc: devel at driverdev.osuosl.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 .../staging/lustre/lnet/libcfs/linux/linux-cpu.c   | 89 ++++++++++++----------
 include/linux/cpuhotplug.h                         |  1 +
 2 files changed, 50 insertions(+), 40 deletions(-)

diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index e8b1a61420de..a75113ab2903 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -73,6 +73,9 @@ struct cfs_cpt_data {
 };
 
 static struct cfs_cpt_data	cpt_data;
+#ifdef CONFIG_HOTPLUG_CPU
+static enum cpuhp_state lustre_cpu_online;
+#endif
 
 static void
 cfs_node_to_cpumask(int node, cpumask_t *mask)
@@ -942,48 +945,38 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+
+static void cfs_cpu_incr_cpt_version(void)
 {
-	unsigned int  cpu = (unsigned long)hcpu;
-	bool	     warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
-
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
-
-	return NOTIFY_OK;
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
+}
 
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+	int next;
+
+	cfs_cpu_incr_cpt_version();
+
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask, topology_sibling_cpumask(cpu));
+	next = cpumask_any_and(cpt_data.cpt_cpumask, cpu_online_mask);
+	warn = next >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -993,7 +986,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1002,6 +997,10 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+#ifdef CONFIG_HOTPLUG_CPU
+	int ret;
+#endif
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1016,7 +1015,17 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
 
 	if (*cpu_pattern != 0) {
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 22acee76cf4c..141c3be242d1 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-- 
2.10.2

[PATCH 21/22 v2] staging/lustre/libcfs: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: James Simmons <jsimmons@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: lustre-devel@lists.lustre.org
Cc: devel@driverdev.osuosl.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
[bigeasy: rebase to linux-next]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1…v2: rebase to linux-next

Side note: Is there a reason the handle the down state very late at
CPU_DEAD time and use the counterpart of the online callback (the old
CPU_DOWN_PREPARE state).

 .../staging/lustre/lnet/libcfs/linux/linux-cpu.c   | 88 ++++++++++++----------
 include/linux/cpuhotplug.h                         |  1 +
 2 files changed, 49 insertions(+), 40 deletions(-)

diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index 6b9cf06e8df2..f70b7d16378c 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -75,6 +75,9 @@ struct cfs_cpt_data {
 };
 
 static struct cfs_cpt_data	cpt_data;
+#ifdef CONFIG_HOTPLUG_CPU
+static enum cpuhp_state lustre_cpu_online;
+#endif
 
 static void
 cfs_node_to_cpumask(int node, cpumask_t *mask)
@@ -967,48 +970,37 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+static void cfs_cpu_incr_cpt_version(void)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
-
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
-
-	return NOTIFY_OK;
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
+}
 
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
+
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask,
+		     topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1010,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1021,10 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+#ifdef CONFIG_HOTPLUG_CPU
+	int ret;
+#endif
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,7 +1039,17 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
 
 	if (*cpu_pattern) {
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 22acee76cf4c..141c3be242d1 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-- 
2.10.2

[lustre-devel] [PATCH 21/22 v2] staging/lustre/libcfs: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: James Simmons <jsimmons@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: lustre-devel at lists.lustre.org
Cc: devel at driverdev.osuosl.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
[bigeasy: rebase to linux-next]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1?v2: rebase to linux-next

Side note: Is there a reason the handle the down state very late at
CPU_DEAD time and use the counterpart of the online callback (the old
CPU_DOWN_PREPARE state).

 .../staging/lustre/lnet/libcfs/linux/linux-cpu.c   | 88 ++++++++++++----------
 include/linux/cpuhotplug.h                         |  1 +
 2 files changed, 49 insertions(+), 40 deletions(-)

diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index 6b9cf06e8df2..f70b7d16378c 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -75,6 +75,9 @@ struct cfs_cpt_data {
 };
 
 static struct cfs_cpt_data	cpt_data;
+#ifdef CONFIG_HOTPLUG_CPU
+static enum cpuhp_state lustre_cpu_online;
+#endif
 
 static void
 cfs_node_to_cpumask(int node, cpumask_t *mask)
@@ -967,48 +970,37 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+static void cfs_cpu_incr_cpt_version(void)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
-
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
-
-	return NOTIFY_OK;
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
+}
 
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
+
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask,
+		     topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1010,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1021,10 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+#ifdef CONFIG_HOTPLUG_CPU
+	int ret;
+#endif
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,7 +1039,17 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
 
 	if (*cpu_pattern) {
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 22acee76cf4c..141c3be242d1 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-- 
2.10.2

Re: [PATCH 21/22 v2] staging/lustre/libcfs: Convert to hotplug state machine

[Greg Kroah-Hartman]

On Fri, Dec 02, 2016 at 11:18:25AM +0100, Sebastian Andrzej Siewior wrote:
> From: Anna-Maria Gleixner <anna-maria@linutronix.de>
> 
> Install the callbacks via the state machine.
> Cc: Oleg Drokin <oleg.drokin@intel.com>
> Cc: Andreas Dilger <andreas.dilger@intel.com>
> Cc: James Simmons <jsimmons@infradead.org>
> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> Cc: lustre-devel@lists.lustre.org
> Cc: devel@driverdev.osuosl.org
> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
> [bigeasy: rebase to linux-next]
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
> v1…v2: rebase to linux-next
> 
> Side note: Is there a reason the handle the down state very late at
> CPU_DEAD time and use the counterpart of the online callback (the old
> CPU_DOWN_PREPARE state).

You need a blank line before the cc: lines in your changelog please...

thanks,

greg k-h

[lustre-devel] [PATCH 21/22 v2] staging/lustre/libcfs: Convert to hotplug state machine

[Greg Kroah-Hartman]

On Fri, Dec 02, 2016 at 11:18:25AM +0100, Sebastian Andrzej Siewior wrote:
> From: Anna-Maria Gleixner <anna-maria@linutronix.de>
> 
> Install the callbacks via the state machine.
> Cc: Oleg Drokin <oleg.drokin@intel.com>
> Cc: Andreas Dilger <andreas.dilger@intel.com>
> Cc: James Simmons <jsimmons@infradead.org>
> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> Cc: lustre-devel at lists.lustre.org
> Cc: devel at driverdev.osuosl.org
> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
> [bigeasy: rebase to linux-next]
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
> v1?v2: rebase to linux-next
> 
> Side note: Is there a reason the handle the down state very late at
> CPU_DEAD time and use the counterpart of the online callback (the old
> CPU_DOWN_PREPARE state).

You need a blank line before the cc: lines in your changelog please...

thanks,

greg k-h

[PATCH 21/22 v3] staging/lustre/libcfs: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.

Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: James Simmons <jsimmons@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: lustre-devel@lists.lustre.org
Cc: devel@driverdev.osuosl.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
[bigeasy: rebase to linux-next]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v2…v3: add the missing blank before the Cc: lines.
v1…v2: rebase to linux-next

Side note: Is there a reason the handle the down state very late at
CPU_DEAD time and use the counterpart of the online callback (the old
CPU_DOWN_PREPARE state).

 .../staging/lustre/lnet/libcfs/linux/linux-cpu.c   | 88 ++++++++++++----------
 include/linux/cpuhotplug.h                         |  1 +
 2 files changed, 49 insertions(+), 40 deletions(-)

diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index 6b9cf06e8df2..f70b7d16378c 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -75,6 +75,9 @@ struct cfs_cpt_data {
 };
 
 static struct cfs_cpt_data	cpt_data;
+#ifdef CONFIG_HOTPLUG_CPU
+static enum cpuhp_state lustre_cpu_online;
+#endif
 
 static void
 cfs_node_to_cpumask(int node, cpumask_t *mask)
@@ -967,48 +970,37 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+static void cfs_cpu_incr_cpt_version(void)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
-
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
-
-	return NOTIFY_OK;
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
+}
 
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
+
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask,
+		     topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1010,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1021,10 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+#ifdef CONFIG_HOTPLUG_CPU
+	int ret;
+#endif
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,7 +1039,17 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
 
 	if (*cpu_pattern) {
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 22acee76cf4c..141c3be242d1 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-- 
2.10.2

[lustre-devel] [PATCH 21/22 v3] staging/lustre/libcfs: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine.

Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: James Simmons <jsimmons@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: lustre-devel at lists.lustre.org
Cc: devel at driverdev.osuosl.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
[bigeasy: rebase to linux-next]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v2?v3: add the missing blank before the Cc: lines.
v1?v2: rebase to linux-next

Side note: Is there a reason the handle the down state very late at
CPU_DEAD time and use the counterpart of the online callback (the old
CPU_DOWN_PREPARE state).

 .../staging/lustre/lnet/libcfs/linux/linux-cpu.c   | 88 ++++++++++++----------
 include/linux/cpuhotplug.h                         |  1 +
 2 files changed, 49 insertions(+), 40 deletions(-)

diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index 6b9cf06e8df2..f70b7d16378c 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -75,6 +75,9 @@ struct cfs_cpt_data {
 };
 
 static struct cfs_cpt_data	cpt_data;
+#ifdef CONFIG_HOTPLUG_CPU
+static enum cpuhp_state lustre_cpu_online;
+#endif
 
 static void
 cfs_node_to_cpumask(int node, cpumask_t *mask)
@@ -967,48 +970,37 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+static void cfs_cpu_incr_cpt_version(void)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
-
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
-
-	return NOTIFY_OK;
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
+}
 
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
+
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask,
+		     topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1010,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1021,10 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+#ifdef CONFIG_HOTPLUG_CPU
+	int ret;
+#endif
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,7 +1039,17 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
 
 	if (*cpu_pattern) {
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 22acee76cf4c..141c3be242d1 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-- 
2.10.2

[PATCH 22/22] Remove obsolete cpu hotplug register / unregister functions

[Sebastian Andrzej Siewior]

Users of
	hotcpu_notifier()
	cpu_notifier()
	__hotcpu_notifier()
	__cpu_notifier()
	register_hotcpu_notifier()
	register_cpu_notifier()
	__register_hotcpu_notifier()
	__register_cpu_notifier()
	unregister_hotcpu_notifier()
	unregister_cpu_notifier()
	__unregister_hotcpu_notifier()
	__unregister_cpu_notifier()

are not longer in tree so remove them.
While at it, some unused CPU states are removed here, too. This includes the
compatibily wrappers. The remaining states (like CPU_ONLINE) are used SMP
bring up code to makr the current state.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/cpu.h        |  48 ----------------
 include/linux/cpuhotplug.h |   2 -
 kernel/cpu.c               | 139 +--------------------------------------------
 3 files changed, 1 insertion(+), 188 deletions(-)

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index b886dc17f2f3..d510e06b377f 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -57,9 +57,6 @@ struct notifier_block;
 
 #define CPU_ONLINE		0x0002 /* CPU (unsigned)v is up */
 #define CPU_UP_PREPARE		0x0003 /* CPU (unsigned)v coming up */
-#define CPU_UP_CANCELED		0x0004 /* CPU (unsigned)v NOT coming up */
-#define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
-#define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
 #define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
 					* lock is dropped */
@@ -134,33 +131,9 @@ void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 
-#define cpu_notifier_register_begin	cpu_maps_update_begin
-#define cpu_notifier_register_done	cpu_maps_update_done
-
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
 
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
 static inline void cpu_maps_update_begin(void)
 {
 }
@@ -169,14 +142,6 @@ static inline void cpu_maps_update_done(void)
 {
 }
 
-static inline void cpu_notifier_register_begin(void)
-{
-}
-
-static inline void cpu_notifier_register_done(void)
-{
-}
-
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -189,12 +154,6 @@ extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
-#define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
-#define __hotcpu_notifier(fn, pri)	__cpu_notifier(fn, pri)
-#define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
-#define __register_hotcpu_notifier(nb)	__register_cpu_notifier(nb)
-#define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
-#define __unregister_hotcpu_notifier(nb)	__unregister_cpu_notifier(nb)
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
@@ -206,13 +165,6 @@ static inline void cpu_hotplug_done(void) {}
 #define put_online_cpus()	do { } while (0)
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
-#define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-/* These aren't inline functions due to a GCC bug. */
-#define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define __register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define unregister_hotcpu_notifier(nb)	({ (void)(nb); })
-#define __unregister_hotcpu_notifier(nb)	({ (void)(nb); })
 #endif		/* CONFIG_HOTPLUG_CPU */
 
 #ifdef CONFIG_PM_SLEEP_SMP
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 141c3be242d1..42287b4a32f3 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -57,7 +57,6 @@ enum cpuhp_state {
 	CPUHP_POWERPC_MMU_CTX_PREPARE,
 	CPUHP_XEN_PREPARE,
 	CPUHP_XEN_EVTCHN_PREPARE,
-	CPUHP_NOTIFY_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
 	CPUHP_BLK_MQ_PREPARE,
@@ -142,7 +141,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_ARM_L2X0_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
-	CPUHP_AP_NOTIFY_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
 	CPUHP_AP_X86_HPET_ONLINE,
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 29de1a9352c0..e222600e53ec 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -183,23 +183,16 @@ EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
 /*
  * The following two APIs (cpu_maps_update_begin/done) must be used when
  * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
- * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
- * hotplug callback (un)registration performed using __register_cpu_notifier()
- * or __unregister_cpu_notifier().
  */
 void cpu_maps_update_begin(void)
 {
 	mutex_lock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_begin);
 
 void cpu_maps_update_done(void)
 {
 	mutex_unlock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_done);
-
-static RAW_NOTIFIER_HEAD(cpu_chain);
 
 /* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
  * Should always be manipulated under cpu_add_remove_lock
@@ -349,66 +342,7 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-/* Need to know about CPUs going up/down? */
-int register_cpu_notifier(struct notifier_block *nb)
-{
-	int ret;
-	cpu_maps_update_begin();
-	ret = raw_notifier_chain_register(&cpu_chain, nb);
-	cpu_maps_update_done();
-	return ret;
-}
-
-int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return raw_notifier_chain_register(&cpu_chain, nb);
-}
-
-static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
-			int *nr_calls)
-{
-	unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
-	void *hcpu = (void *)(long)cpu;
-
-	int ret;
-
-	ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
-					nr_calls);
-
-	return notifier_to_errno(ret);
-}
-
-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)
-{
-	int nr_calls = 0;
-	int ret;
-
-	ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
-	if (ret) {
-		nr_calls--;
-		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
-				__func__, cpu);
-		__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
-	}
-	return ret;
-}
-
-static int notify_online(unsigned int cpu)
-{
-	cpu_notify(CPU_ONLINE, cpu);
-	return 0;
-}
 
 static int bringup_wait_for_ap(unsigned int cpu)
 {
@@ -433,10 +367,8 @@ static int bringup_cpu(unsigned int cpu)
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
 	irq_unlock_sparse();
-	if (ret) {
-		cpu_notify(CPU_UP_CANCELED, cpu);
+	if (ret)
 		return ret;
-	}
 	ret = bringup_wait_for_ap(cpu);
 	BUG_ON(!cpu_online(cpu));
 	return ret;
@@ -565,11 +497,6 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
 
 		undo_cpu_down(cpu, st);
-		/*
-		 * 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 .... */
@@ -660,22 +587,6 @@ void __init cpuhp_threads_init(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-EXPORT_SYMBOL(register_cpu_notifier);
-EXPORT_SYMBOL(__register_cpu_notifier);
-void unregister_cpu_notifier(struct notifier_block *nb)
-{
-	cpu_maps_update_begin();
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-	cpu_maps_update_done();
-}
-EXPORT_SYMBOL(unregister_cpu_notifier);
-
-void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-}
-EXPORT_SYMBOL(__unregister_cpu_notifier);
-
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
  * @cpu: a CPU id
@@ -741,20 +652,6 @@ static inline void check_for_tasks(int dead_cpu)
 	read_unlock(&tasklist_lock);
 }
 
-static int notify_down_prepare(unsigned int cpu)
-{
-	int err, nr_calls = 0;
-
-	err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
-	if (err) {
-		nr_calls--;
-		__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
-		pr_warn("%s: attempt to take down CPU %u failed\n",
-				__func__, cpu);
-	}
-	return err;
-}
-
 /* Take this CPU down. */
 static int take_cpu_down(void *_param)
 {
@@ -833,13 +730,6 @@ static int takedown_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int notify_dead(unsigned int cpu)
-{
-	cpu_notify_nofail(CPU_DEAD, cpu);
-	check_for_tasks(cpu);
-	return 0;
-}
-
 static void cpuhp_complete_idle_dead(void *arg)
 {
 	struct cpuhp_cpu_state *st = arg;
@@ -863,9 +753,7 @@ void cpuhp_report_idle_dead(void)
 }
 
 #else
-#define notify_down_prepare	NULL
 #define takedown_cpu		NULL
-#define notify_dead		NULL
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -924,9 +812,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
 out:
 	cpu_hotplug_done();
-	/* This post dead nonsense must die */
-	if (!ret && hasdied)
-		cpu_notify_nofail(CPU_POST_DEAD, cpu);
 	return ret;
 }
 
@@ -1292,17 +1177,6 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 		.teardown.single	= rcutree_dead_cpu,
 	},
 	/*
-	 * Preparatory and dead notifiers. Will be replaced once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_NOTIFY_PREPARE] = {
-		.name			= "notify:prepare",
-		.startup.single		= notify_prepare,
-		.teardown.single	= notify_dead,
-		.skip_onerr		= true,
-		.cant_stop		= true,
-	},
-	/*
 	 * On the tear-down path, timers_dead_cpu() must be invoked
 	 * before blk_mq_queue_reinit_notify() from notify_dead(),
 	 * otherwise a RCU stall occurs.
@@ -1391,17 +1265,6 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.startup.single		= rcutree_online_cpu,
 		.teardown.single	= rcutree_offline_cpu,
 	},
-
-	/*
-	 * Online/down_prepare notifiers. Will be removed once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_AP_NOTIFY_ONLINE] = {
-		.name			= "notify:online",
-		.startup.single		= notify_online,
-		.teardown.single	= notify_down_prepare,
-		.skip_onerr		= true,
-	},
 #endif
 	/*
 	 * The dynamically registered state space is here
-- 
2.10.2

[patch 00/10] cpu/hotplug: Final cleanup

[Thomas Gleixner]

The following series completes the cpuhotplug rework stage ONE.

 - Fix a completely broken new user of the state machine

 - Prevent overwriting existing states

 - Convert the last left over drivers to the state machine

 - Remove the notifiers and related code

 - Cleanup the state names (tree wide)

 - Consolidate a few hotplug states

It's also available from:

  git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git WIP.hotplug

Thanks,

	tglx
---
 a/lib/cpu-notifier-error-inject.c                    |   84 ---------
 arch/arm/kernel/smp_twd.c                            |    2 
 arch/arm/mach-imx/mmdc.c                             |   34 ++-
 arch/arm/mach-mvebu/coherency.c                      |    2 
 arch/arm/mm/cache-l2x0-pmu.c                         |    2 
 arch/arm/mm/cache-l2x0.c                             |    2 
 arch/arm/vfp/vfpmodule.c                             |    2 
 arch/arm/xen/enlighten.c                             |    2 
 arch/arm64/kernel/armv8_deprecated.c                 |    2 
 arch/arm64/kernel/debug-monitors.c                   |    2 
 arch/arm64/kernel/hw_breakpoint.c                    |    2 
 arch/blackfin/kernel/perf_event.c                    |    2 
 arch/mips/kernel/pm-cps.c                            |    2 
 arch/mips/oprofile/op_model_loongson3.c              |    2 
 arch/powerpc/mm/numa.c                               |    2 
 arch/powerpc/perf/core-book3s.c                      |    2 
 arch/s390/kernel/perf_cpum_cf.c                      |    2 
 arch/s390/kernel/perf_cpum_sf.c                      |    2 
 arch/x86/entry/vdso/vma.c                            |    2 
 arch/x86/events/amd/ibs.c                            |    2 
 arch/x86/events/amd/power.c                          |    2 
 arch/x86/events/amd/uncore.c                         |    6 
 arch/x86/events/core.c                               |    6 
 arch/x86/events/intel/cqm.c                          |    4 
 arch/x86/events/intel/cstate.c                       |    5 
 arch/x86/events/intel/rapl.c                         |    4 
 arch/x86/events/intel/uncore.c                       |   10 -
 arch/x86/kernel/apb_timer.c                          |    2 
 arch/x86/kernel/apic/x2apic_cluster.c                |    2 
 arch/x86/kernel/hpet.c                               |    4 
 arch/x86/kernel/tboot.c                              |    2 
 arch/x86/kvm/x86.c                                   |    2 
 arch/x86/xen/enlighten.c                             |    4 
 arch/xtensa/kernel/perf_event.c                      |    2 
 b/arch/metag/kernel/perf/perf_event.c                |    2 
 drivers/bus/arm-cci.c                                |    2 
 drivers/bus/arm-ccn.c                                |    2 
 drivers/clocksource/arc_timer.c                      |    2 
 drivers/clocksource/arm_arch_timer.c                 |    2 
 drivers/clocksource/arm_global_timer.c               |    2 
 drivers/clocksource/dummy_timer.c                    |    2 
 drivers/clocksource/exynos_mct.c                     |    2 
 drivers/clocksource/jcore-pit.c                      |    2 
 drivers/clocksource/metag_generic.c                  |    2 
 drivers/clocksource/mips-gic-timer.c                 |    4 
 drivers/clocksource/qcom-timer.c                     |    2 
 drivers/clocksource/time-armada-370-xp.c             |    2 
 drivers/clocksource/timer-atlas7.c                   |    2 
 drivers/hwtracing/coresight/coresight-etm3x.c        |    4 
 drivers/hwtracing/coresight/coresight-etm4x.c        |    8 
 drivers/irqchip/irq-armada-370-xp.c                  |    6 
 drivers/irqchip/irq-bcm2836.c                        |    2 
 drivers/irqchip/irq-gic-v3.c                         |    6 
 drivers/irqchip/irq-gic.c                            |    2 
 drivers/irqchip/irq-hip04.c                          |    2 
 drivers/leds/trigger/ledtrig-cpu.c                   |    2 
 drivers/net/virtio_net.c                             |    4 
 drivers/perf/arm_pmu.c                               |    2 
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c                    |   81 +++-----
 drivers/scsi/bnx2i/bnx2i_init.c                      |   80 +++-----
 drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c |   85 ++++-----
 drivers/xen/events/events_fifo.c                     |    2 
 include/linux/cpu.h                                  |   90 ---------
 include/linux/cpuhotplug.h                           |    9 
 kernel/cpu.c                                         |  172 ++-----------------
 lib/Kconfig.debug                                    |   24 --
 lib/Makefile                                         |    1 
 virt/kvm/arm/arch_timer.c                            |    2 
 virt/kvm/arm/vgic/vgic-init.c                        |    2 
 virt/kvm/kvm_main.c                                  |    2 
 70 files changed, 240 insertions(+), 587 deletions(-)

[patch 01/10] ARM: imx: mmcd: Fix broken cpu hotplug handling

[Thomas Gleixner]

[-- Attachment #1: ARM--imx--Fix-broken-cpu-hotplug-handling.patch --]
[-- Type: text/plain, Size: 3649 bytes --]

The cpu hotplug support of this perf driver is broken in several ways:

1) It adds a instance before setting up the state.

2) The state for the instance is different from the state of the
   callback. It's just a randomly chosen state.

3) The instance registration is not error checked so nobody noticed that
   the call can never succeed.

4) The state for the multi install callbacks is chosen randomly and
   overwrites existing state. This is now prevented by the core code so the
   call is guaranteed to fail.

5) The error exit path in the init function leaves the instance registered
   and then frees the memory which contains the enqueued hlist node.

6) The remove function is removing the state and not the instance.

Fix it by:

- Setting up the state before adding instances. Use a dynamically allocated
  state for it.

- Install instances after the state has been set up

- Remove the instance in the error path before freeing memory

- Remove instance not the state in the driver remove callback

While at is use raw_cpu_processor_id(), because cpu_processor_id() cannot
be used in preemptible context, and set the driver data after successful
registration of the pmu.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Zhengyu Shen <zhengyu.shen@nxp.com>
Cc: Frank Li <frank.li@nxp.com>
Cc: Shawn Guo <shawnguo@kernel.org>

---
 arch/arm/mach-imx/mmdc.c |   34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -60,6 +60,7 @@
 
 #define to_mmdc_pmu(p) container_of(p, struct mmdc_pmu, pmu)
 
+static enum cpuhp_state cpuhp_mmdc_state;
 static int ddr_type;
 
 struct fsl_mmdc_devtype_data {
@@ -451,8 +452,8 @@ static int imx_mmdc_remove(struct platfo
 {
 	struct mmdc_pmu *pmu_mmdc = platform_get_drvdata(pdev);
 
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	perf_pmu_unregister(&pmu_mmdc->pmu);
-	cpuhp_remove_state_nocalls(CPUHP_ONLINE);
 	kfree(pmu_mmdc);
 	return 0;
 }
@@ -472,6 +473,18 @@ static int imx_mmdc_perf_init(struct pla
 		return -ENOMEM;
 	}
 
+	/* The first instance registers the hotplug state */
+	if (!cpuhp_mmdc_state) {
+		ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+					      "perf/arm/mmdc:online", NULL,
+					      mmdc_pmu_offline_cpu);
+		if (ret < 0) {
+			pr_err("cpuhp_setup_state_multi failed\n");
+			goto pmu_free;
+		}
+		cpuhp_mmdc_state = ret;
+	}
+
 	mmdc_num = mmdc_pmu_init(pmu_mmdc, mmdc_base, &pdev->dev);
 	if (mmdc_num == 0)
 		name = "mmdc";
@@ -485,26 +498,23 @@ static int imx_mmdc_perf_init(struct pla
 			HRTIMER_MODE_REL);
 	pmu_mmdc->hrtimer.function = mmdc_pmu_timer_handler;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_ONLINE,
-					 &pmu_mmdc->node);
-	cpumask_set_cpu(smp_processor_id(), &pmu_mmdc->cpu);
-	ret = cpuhp_setup_state_multi(CPUHP_AP_NOTIFY_ONLINE,
-				      "MMDC_ONLINE", NULL,
-				      mmdc_pmu_offline_cpu);
-	if (ret) {
-		pr_err("cpuhp_setup_state_multi failure\n");
-		goto pmu_register_err;
-	}
+	cpumask_set_cpu(raw_smp_processor_id(), &pmu_mmdc->cpu);
+
+	/* Register the pmu instance for cpu hotplug */
+	cpuhp_state_add_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 
 	ret = perf_pmu_register(&(pmu_mmdc->pmu), name, -1);
-	platform_set_drvdata(pdev, pmu_mmdc);
 	if (ret)
 		goto pmu_register_err;
+
+	platform_set_drvdata(pdev, pmu_mmdc);
 	return 0;
 
 pmu_register_err:
 	pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret);
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	hrtimer_cancel(&pmu_mmdc->hrtimer);
+pmu_free:
 	kfree(pmu_mmdc);
 	return ret;
 }

[tip:smp/urgent] ARM/imx/mmcd: Fix broken cpu hotplug handling

[tip-bot for Thomas Gleixner]

Commit-ID:  a5d3bb6a5ba9727a02b328a249652f3ea655a064
Gitweb:     http://git.kernel.org/tip/a5d3bb6a5ba9727a02b328a249652f3ea655a064
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:48 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:53 +0100

ARM/imx/mmcd: Fix broken cpu hotplug handling

The cpu hotplug support of this perf driver is broken in several ways:

1) It adds a instance before setting up the state.

2) The state for the instance is different from the state of the
   callback. It's just a randomly chosen state.

3) The instance registration is not error checked so nobody noticed that
   the call can never succeed.

4) The state for the multi install callbacks is chosen randomly and
   overwrites existing state. This is now prevented by the core code so the
   call is guaranteed to fail.

5) The error exit path in the init function leaves the instance registered
   and then frees the memory which contains the enqueued hlist node.

6) The remove function is removing the state and not the instance.

Fix it by:

- Setting up the state before adding instances. Use a dynamically allocated
  state for it.

- Installing instances after the state has been set up

- Removing the instance in the error path before freeing memory

- Removing the instance not the state in the driver remove callback

While at is use raw_cpu_processor_id(), because cpu_processor_id() cannot
be used in preemptible context, and set the driver data after successful
registration of the pmu.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Shawn Guo <shawnguo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Frank Li <frank.li@nxp.com>
Cc: Zhengyu Shen <zhengyu.shen@nxp.com>
Link: http://lkml.kernel.org/r/20161221192111.596204211@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/arm/mach-imx/mmdc.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index ba96bf9..6991577 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -60,6 +60,7 @@
 
 #define to_mmdc_pmu(p) container_of(p, struct mmdc_pmu, pmu)
 
+static enum cpuhp_state cpuhp_mmdc_state;
 static int ddr_type;
 
 struct fsl_mmdc_devtype_data {
@@ -451,8 +452,8 @@ static int imx_mmdc_remove(struct platform_device *pdev)
 {
 	struct mmdc_pmu *pmu_mmdc = platform_get_drvdata(pdev);
 
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	perf_pmu_unregister(&pmu_mmdc->pmu);
-	cpuhp_remove_state_nocalls(CPUHP_ONLINE);
 	kfree(pmu_mmdc);
 	return 0;
 }
@@ -472,6 +473,18 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 		return -ENOMEM;
 	}
 
+	/* The first instance registers the hotplug state */
+	if (!cpuhp_mmdc_state) {
+		ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+					      "perf/arm/mmdc:online", NULL,
+					      mmdc_pmu_offline_cpu);
+		if (ret < 0) {
+			pr_err("cpuhp_setup_state_multi failed\n");
+			goto pmu_free;
+		}
+		cpuhp_mmdc_state = ret;
+	}
+
 	mmdc_num = mmdc_pmu_init(pmu_mmdc, mmdc_base, &pdev->dev);
 	if (mmdc_num == 0)
 		name = "mmdc";
@@ -485,26 +498,23 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 			HRTIMER_MODE_REL);
 	pmu_mmdc->hrtimer.function = mmdc_pmu_timer_handler;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_ONLINE,
-					 &pmu_mmdc->node);
-	cpumask_set_cpu(smp_processor_id(), &pmu_mmdc->cpu);
-	ret = cpuhp_setup_state_multi(CPUHP_AP_NOTIFY_ONLINE,
-				      "MMDC_ONLINE", NULL,
-				      mmdc_pmu_offline_cpu);
-	if (ret) {
-		pr_err("cpuhp_setup_state_multi failure\n");
-		goto pmu_register_err;
-	}
+	cpumask_set_cpu(raw_smp_processor_id(), &pmu_mmdc->cpu);
+
+	/* Register the pmu instance for cpu hotplug */
+	cpuhp_state_add_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 
 	ret = perf_pmu_register(&(pmu_mmdc->pmu), name, -1);
-	platform_set_drvdata(pdev, pmu_mmdc);
 	if (ret)
 		goto pmu_register_err;
+
+	platform_set_drvdata(pdev, pmu_mmdc);
 	return 0;
 
 pmu_register_err:
 	pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret);
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	hrtimer_cancel(&pmu_mmdc->hrtimer);
+pmu_free:
 	kfree(pmu_mmdc);
 	return ret;
 }

[tip:smp/urgent] ARM/imx/mmcd: Fix broken cpu hotplug handling

[tip-bot for Thomas Gleixner]

Commit-ID:  a051f220d6b9bf9367695e2c319ccc3712b631ee
Gitweb:     http://git.kernel.org/tip/a051f220d6b9bf9367695e2c319ccc3712b631ee
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:48 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:40 +0100

ARM/imx/mmcd: Fix broken cpu hotplug handling

The cpu hotplug support of this perf driver is broken in several ways:

1) It adds a instance before setting up the state.

2) The state for the instance is different from the state of the
   callback. It's just a randomly chosen state.

3) The instance registration is not error checked so nobody noticed that
   the call can never succeed.

4) The state for the multi install callbacks is chosen randomly and
   overwrites existing state. This is now prevented by the core code so the
   call is guaranteed to fail.

5) The error exit path in the init function leaves the instance registered
   and then frees the memory which contains the enqueued hlist node.

6) The remove function is removing the state and not the instance.

Fix it by:

- Setting up the state before adding instances. Use a dynamically allocated
  state for it.

- Installing instances after the state has been set up

- Removing the instance in the error path before freeing memory

- Removing the instance not the state in the driver remove callback

While at is use raw_cpu_processor_id(), because cpu_processor_id() cannot
be used in preemptible context, and set the driver data after successful
registration of the pmu.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Shawn Guo <shawnguo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Frank Li <frank.li@nxp.com>
Cc: Zhengyu Shen <zhengyu.shen@nxp.com>
Link: http://lkml.kernel.org/r/20161221192111.596204211@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/arm/mach-imx/mmdc.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index ba96bf9..6991577 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -60,6 +60,7 @@
 
 #define to_mmdc_pmu(p) container_of(p, struct mmdc_pmu, pmu)
 
+static enum cpuhp_state cpuhp_mmdc_state;
 static int ddr_type;
 
 struct fsl_mmdc_devtype_data {
@@ -451,8 +452,8 @@ static int imx_mmdc_remove(struct platform_device *pdev)
 {
 	struct mmdc_pmu *pmu_mmdc = platform_get_drvdata(pdev);
 
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	perf_pmu_unregister(&pmu_mmdc->pmu);
-	cpuhp_remove_state_nocalls(CPUHP_ONLINE);
 	kfree(pmu_mmdc);
 	return 0;
 }
@@ -472,6 +473,18 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 		return -ENOMEM;
 	}
 
+	/* The first instance registers the hotplug state */
+	if (!cpuhp_mmdc_state) {
+		ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+					      "perf/arm/mmdc:online", NULL,
+					      mmdc_pmu_offline_cpu);
+		if (ret < 0) {
+			pr_err("cpuhp_setup_state_multi failed\n");
+			goto pmu_free;
+		}
+		cpuhp_mmdc_state = ret;
+	}
+
 	mmdc_num = mmdc_pmu_init(pmu_mmdc, mmdc_base, &pdev->dev);
 	if (mmdc_num == 0)
 		name = "mmdc";
@@ -485,26 +498,23 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 			HRTIMER_MODE_REL);
 	pmu_mmdc->hrtimer.function = mmdc_pmu_timer_handler;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_ONLINE,
-					 &pmu_mmdc->node);
-	cpumask_set_cpu(smp_processor_id(), &pmu_mmdc->cpu);
-	ret = cpuhp_setup_state_multi(CPUHP_AP_NOTIFY_ONLINE,
-				      "MMDC_ONLINE", NULL,
-				      mmdc_pmu_offline_cpu);
-	if (ret) {
-		pr_err("cpuhp_setup_state_multi failure\n");
-		goto pmu_register_err;
-	}
+	cpumask_set_cpu(raw_smp_processor_id(), &pmu_mmdc->cpu);
+
+	/* Register the pmu instance for cpu hotplug */
+	cpuhp_state_add_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 
 	ret = perf_pmu_register(&(pmu_mmdc->pmu), name, -1);
-	platform_set_drvdata(pdev, pmu_mmdc);
 	if (ret)
 		goto pmu_register_err;
+
+	platform_set_drvdata(pdev, pmu_mmdc);
 	return 0;
 
 pmu_register_err:
 	pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret);
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	hrtimer_cancel(&pmu_mmdc->hrtimer);
+pmu_free:
 	kfree(pmu_mmdc);
 	return ret;
 }

[patch 02/10] cpu/hotplug: Prevent overwriting of callbacks

[Thomas Gleixner]

[-- Attachment #1: cpu-hotplug--Prevent-overwriting-of-callbacks.patch --]
[-- Type: text/plain, Size: 2331 bytes --]

Developers manage to overwrite states blindly without thought. That's fatal
and hard to debug. Add sanity checks to make it fail.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 kernel/cpu.c |   33 +++++++++++++++++++++------------
 1 file changed, 21 insertions(+), 12 deletions(-)

--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1432,23 +1432,29 @@ static int cpuhp_cb_check(enum cpuhp_sta
 	return 0;
 }
 
-static void cpuhp_store_callbacks(enum cpuhp_state state,
-				  const char *name,
-				  int (*startup)(unsigned int cpu),
-				  int (*teardown)(unsigned int cpu),
-				  bool multi_instance)
+static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
+				 int (*startup)(unsigned int cpu),
+				 int (*teardown)(unsigned int cpu),
+				 bool multi_instance)
 {
 	/* (Un)Install the callbacks for further cpu hotplug operations */
 	struct cpuhp_step *sp;
+	int ret = 0;
 
 	mutex_lock(&cpuhp_state_mutex);
 	sp = cpuhp_get_step(state);
+	if (name && sp->name) {
+		ret = -EBUSY;
+		goto out;
+	}
 	sp->startup.single = startup;
 	sp->teardown.single = teardown;
 	sp->name = name;
 	sp->multi_instance = multi_instance;
 	INIT_HLIST_HEAD(&sp->list);
+out:
 	mutex_unlock(&cpuhp_state_mutex);
+	return ret;
 }
 
 static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
@@ -1580,11 +1586,13 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_inst
 
 /**
  * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
- * @state:	The state to setup
- * @invoke:	If true, the startup function is invoked for cpus where
- *		cpu state >= @state
- * @startup:	startup callback function
- * @teardown:	teardown callback function
+ * @state:		The state to setup
+ * @invoke:		If true, the startup function is invoked for cpus where
+ *			cpu state >= @state
+ * @startup:		startup callback function
+ * @teardown:		teardown callback function
+ * @multi_instance:	State is set up for multiple instances which get
+ *			added afterwards.
  *
  * Returns:
  *   On success:
@@ -1615,9 +1623,10 @@ int __cpuhp_setup_state(enum cpuhp_state
 		state = ret;
 	}
 
-	cpuhp_store_callbacks(state, name, startup, teardown, multi_instance);
+	ret = cpuhp_store_callbacks(state, name, startup, teardown,
+				    multi_instance);
 
-	if (!invoke || !startup)
+	if (ret || !invoke || !startup)
 		goto out;
 
 	/*

Re: [patch 02/10] cpu/hotplug: Prevent overwriting of callbacks

[Thomas Gleixner]

On Wed, 21 Dec 2016, Thomas Gleixner wrote:

> Developers manage to overwrite states blindly without thought. That's fatal
> and hard to debug. Add sanity checks to make it fail.

This breaks dynamic states :( Fixed version below.

Thanks,

	tglx

8<------------------

Subject: cpu/hotplug: Prevent overwriting of callbacks
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 21 Dec 2016 20:19:49 +0100

Developers manage to overwrite states blindly without thought. That's fatal
and hard to debug. Add sanity checks to make it fail.

This requries to restructure the code so that the dynamic state allocation
happens in the same lock protected section as the actual store. Otherwise
the previous assignment of 'Reserved' to the name field would trigger the
overwrite check.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>

---
 kernel/cpu.c |   96 ++++++++++++++++++++++++++++++-----------------------------
 1 file changed, 50 insertions(+), 46 deletions(-)

--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1432,23 +1432,53 @@ static int cpuhp_cb_check(enum cpuhp_sta
 	return 0;
 }
 
-static void cpuhp_store_callbacks(enum cpuhp_state state,
-				  const char *name,
-				  int (*startup)(unsigned int cpu),
-				  int (*teardown)(unsigned int cpu),
-				  bool multi_instance)
+/*
+ * Returns a free for dynamic slot assignment of the Online state. The states
+ * are protected by the cpuhp_slot_states mutex and an empty slot is identified
+ * by having no name assigned.
+ */
+static int cpuhp_reserve_state(enum cpuhp_state state)
+{
+	enum cpuhp_state i;
+
+	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
+		if (!cpuhp_ap_states[i].name)
+			return i;
+	}
+	WARN(1, "No more dynamic states available for CPU hotplug\n");
+	return -ENOSPC;
+}
+
+static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
+				 int (*startup)(unsigned int cpu),
+				 int (*teardown)(unsigned int cpu),
+				 bool multi_instance)
 {
 	/* (Un)Install the callbacks for further cpu hotplug operations */
 	struct cpuhp_step *sp;
+	int ret = 0;
 
 	mutex_lock(&cpuhp_state_mutex);
+
+	if (state == CPUHP_AP_ONLINE_DYN) {
+		ret = cpuhp_reserve_state(state);
+		if (ret < 0)
+			goto out;
+		state = ret;
+	}
 	sp = cpuhp_get_step(state);
+	if (name && sp->name) {
+		ret = -EBUSY;
+		goto out;
+	}
 	sp->startup.single = startup;
 	sp->teardown.single = teardown;
 	sp->name = name;
 	sp->multi_instance = multi_instance;
 	INIT_HLIST_HEAD(&sp->list);
+out:
 	mutex_unlock(&cpuhp_state_mutex);
+	return ret;
 }
 
 static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
@@ -1509,29 +1539,6 @@ static void cpuhp_rollback_install(int f
 	}
 }
 
-/*
- * Returns a free for dynamic slot assignment of the Online state. The states
- * are protected by the cpuhp_slot_states mutex and an empty slot is identified
- * by having no name assigned.
- */
-static int cpuhp_reserve_state(enum cpuhp_state state)
-{
-	enum cpuhp_state i;
-
-	mutex_lock(&cpuhp_state_mutex);
-	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
-		if (cpuhp_ap_states[i].name)
-			continue;
-
-		cpuhp_ap_states[i].name = "Reserved";
-		mutex_unlock(&cpuhp_state_mutex);
-		return i;
-	}
-	mutex_unlock(&cpuhp_state_mutex);
-	WARN(1, "No more dynamic states available for CPU hotplug\n");
-	return -ENOSPC;
-}
-
 int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 			       bool invoke)
 {
@@ -1580,11 +1587,13 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_inst
 
 /**
  * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
- * @state:	The state to setup
- * @invoke:	If true, the startup function is invoked for cpus where
- *		cpu state >= @state
- * @startup:	startup callback function
- * @teardown:	teardown callback function
+ * @state:		The state to setup
+ * @invoke:		If true, the startup function is invoked for cpus where
+ *			cpu state >= @state
+ * @startup:		startup callback function
+ * @teardown:		teardown callback function
+ * @multi_instance:	State is set up for multiple instances which get
+ *			added afterwards.
  *
  * Returns:
  *   On success:
@@ -1599,25 +1608,16 @@ int __cpuhp_setup_state(enum cpuhp_state
 			bool multi_instance)
 {
 	int cpu, ret = 0;
-	int dyn_state = 0;
 
 	if (cpuhp_cb_check(state) || !name)
 		return -EINVAL;
 
 	get_online_cpus();
 
-	/* currently assignments for the ONLINE state are possible */
-	if (state == CPUHP_AP_ONLINE_DYN) {
-		dyn_state = 1;
-		ret = cpuhp_reserve_state(state);
-		if (ret < 0)
-			goto out;
-		state = ret;
-	}
+	ret = cpuhp_store_callbacks(state, name, startup, teardown,
+				    multi_instance);
 
-	cpuhp_store_callbacks(state, name, startup, teardown, multi_instance);
-
-	if (!invoke || !startup)
+	if (ret || !invoke || !startup)
 		goto out;
 
 	/*
@@ -1641,7 +1641,11 @@ int __cpuhp_setup_state(enum cpuhp_state
 	}
 out:
 	put_online_cpus();
-	if (!ret && dyn_state)
+	/*
+	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
+	 * dynamically allocated state in case of success.
+	 */
+	if (!ret && state == CPUHP_AP_ONLINE_DYN)
 		return state;
 	return ret;
 }

Re: [patch 02/10] cpu/hotplug: Prevent overwriting of callbacks

[ojab]

Oh hai!

I have kernel panic on boot here after this patch, 4.10-rc1 with this 
commit (dc280d93623927570da279e99393879dbbab39e7) reverted boots fine.

Potato-quality photo of incomplete traceback of 4.10-rc1 panic can be 
found at https://ojab.ru/IMG_20161227_015233.jpg (unfortunately I can't 
figure out how to increase resolution to catch a full trace and I don't 
have a serial terminal).

CPU here is 'AMD Phenom(tm) II X4 905e Processor' (4 core, 4 threads).

//wbr ojab

Re: [patch 02/10] cpu/hotplug: Prevent overwriting of callbacks

[ojab]

On 2016/12/26 23:04, ojab wrote:
> Oh hai!
>
> I have kernel panic on boot here after this patch, 4.10-rc1 with this
> commit (dc280d93623927570da279e99393879dbbab39e7) reverted boots fine.
>
> Potato-quality photo of incomplete traceback of 4.10-rc1 panic can be
> found at https://ojab.ru/IMG_20161227_015233.jpg (unfortunately I can't
> figure out how to increase resolution to catch a full trace and I don't
> have a serial terminal).
>
> CPU here is 'AMD Phenom(tm) II X4 905e Processor' (4 core, 4 threads).
>
> //wbr ojab
>

…and looks like it's fixed by patches in `[patch 0/2] smp/hotplug: Fix 
last minute wreckage` thread

//wbr ojab

[tip:smp/urgent] cpu/hotplug: Prevent overwriting of callbacks

[tip-bot for Thomas Gleixner]

Commit-ID:  ab92ca2014a32ea5dc7f954f84661f6d96f0ba26
Gitweb:     http://git.kernel.org/tip/ab92ca2014a32ea5dc7f954f84661f6d96f0ba26
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:49 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:54 +0100

cpu/hotplug: Prevent overwriting of callbacks

Developers manage to overwrite states blindly without thought. That's fatal
and hard to debug. Add sanity checks to make it fail.

This requries to restructure the code so that the dynamic state allocation
happens in the same lock protected section as the actual store. Otherwise
the previous assignment of 'Reserved' to the name field would trigger the
overwrite check.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Link: http://lkml.kernel.org/r/20161221192111.675234535@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 kernel/cpu.c | 96 +++++++++++++++++++++++++++++++-----------------------------
 1 file changed, 50 insertions(+), 46 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5339aca..3ff0ea5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1432,23 +1432,53 @@ static int cpuhp_cb_check(enum cpuhp_state state)
 	return 0;
 }
 
-static void cpuhp_store_callbacks(enum cpuhp_state state,
-				  const char *name,
-				  int (*startup)(unsigned int cpu),
-				  int (*teardown)(unsigned int cpu),
-				  bool multi_instance)
+/*
+ * Returns a free for dynamic slot assignment of the Online state. The states
+ * are protected by the cpuhp_slot_states mutex and an empty slot is identified
+ * by having no name assigned.
+ */
+static int cpuhp_reserve_state(enum cpuhp_state state)
+{
+	enum cpuhp_state i;
+
+	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
+		if (!cpuhp_ap_states[i].name)
+			return i;
+	}
+	WARN(1, "No more dynamic states available for CPU hotplug\n");
+	return -ENOSPC;
+}
+
+static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
+				 int (*startup)(unsigned int cpu),
+				 int (*teardown)(unsigned int cpu),
+				 bool multi_instance)
 {
 	/* (Un)Install the callbacks for further cpu hotplug operations */
 	struct cpuhp_step *sp;
+	int ret = 0;
 
 	mutex_lock(&cpuhp_state_mutex);
+
+	if (state == CPUHP_AP_ONLINE_DYN) {
+		ret = cpuhp_reserve_state(state);
+		if (ret < 0)
+			goto out;
+		state = ret;
+	}
 	sp = cpuhp_get_step(state);
+	if (name && sp->name) {
+		ret = -EBUSY;
+		goto out;
+	}
 	sp->startup.single = startup;
 	sp->teardown.single = teardown;
 	sp->name = name;
 	sp->multi_instance = multi_instance;
 	INIT_HLIST_HEAD(&sp->list);
+out:
 	mutex_unlock(&cpuhp_state_mutex);
+	return ret;
 }
 
 static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
@@ -1509,29 +1539,6 @@ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
 	}
 }
 
-/*
- * Returns a free for dynamic slot assignment of the Online state. The states
- * are protected by the cpuhp_slot_states mutex and an empty slot is identified
- * by having no name assigned.
- */
-static int cpuhp_reserve_state(enum cpuhp_state state)
-{
-	enum cpuhp_state i;
-
-	mutex_lock(&cpuhp_state_mutex);
-	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
-		if (cpuhp_ap_states[i].name)
-			continue;
-
-		cpuhp_ap_states[i].name = "Reserved";
-		mutex_unlock(&cpuhp_state_mutex);
-		return i;
-	}
-	mutex_unlock(&cpuhp_state_mutex);
-	WARN(1, "No more dynamic states available for CPU hotplug\n");
-	return -ENOSPC;
-}
-
 int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 			       bool invoke)
 {
@@ -1580,11 +1587,13 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
 
 /**
  * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
- * @state:	The state to setup
- * @invoke:	If true, the startup function is invoked for cpus where
- *		cpu state >= @state
- * @startup:	startup callback function
- * @teardown:	teardown callback function
+ * @state:		The state to setup
+ * @invoke:		If true, the startup function is invoked for cpus where
+ *			cpu state >= @state
+ * @startup:		startup callback function
+ * @teardown:		teardown callback function
+ * @multi_instance:	State is set up for multiple instances which get
+ *			added afterwards.
  *
  * Returns:
  *   On success:
@@ -1599,25 +1608,16 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 			bool multi_instance)
 {
 	int cpu, ret = 0;
-	int dyn_state = 0;
 
 	if (cpuhp_cb_check(state) || !name)
 		return -EINVAL;
 
 	get_online_cpus();
 
-	/* currently assignments for the ONLINE state are possible */
-	if (state == CPUHP_AP_ONLINE_DYN) {
-		dyn_state = 1;
-		ret = cpuhp_reserve_state(state);
-		if (ret < 0)
-			goto out;
-		state = ret;
-	}
-
-	cpuhp_store_callbacks(state, name, startup, teardown, multi_instance);
+	ret = cpuhp_store_callbacks(state, name, startup, teardown,
+				    multi_instance);
 
-	if (!invoke || !startup)
+	if (ret || !invoke || !startup)
 		goto out;
 
 	/*
@@ -1641,7 +1641,11 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 	}
 out:
 	put_online_cpus();
-	if (!ret && dyn_state)
+	/*
+	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
+	 * dynamically allocated state in case of success.
+	 */
+	if (!ret && state == CPUHP_AP_ONLINE_DYN)
 		return state;
 	return ret;
 }

[tip:smp/urgent] cpu/hotplug: Prevent overwriting of callbacks

[tip-bot for Thomas Gleixner]

Commit-ID:  dc280d93623927570da279e99393879dbbab39e7
Gitweb:     http://git.kernel.org/tip/dc280d93623927570da279e99393879dbbab39e7
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:49 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:42 +0100

cpu/hotplug: Prevent overwriting of callbacks

Developers manage to overwrite states blindly without thought. That's fatal
and hard to debug. Add sanity checks to make it fail.

This requries to restructure the code so that the dynamic state allocation
happens in the same lock protected section as the actual store. Otherwise
the previous assignment of 'Reserved' to the name field would trigger the
overwrite check.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Link: http://lkml.kernel.org/r/20161221192111.675234535@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 kernel/cpu.c | 96 +++++++++++++++++++++++++++++++-----------------------------
 1 file changed, 50 insertions(+), 46 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5339aca..3ff0ea5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1432,23 +1432,53 @@ static int cpuhp_cb_check(enum cpuhp_state state)
 	return 0;
 }
 
-static void cpuhp_store_callbacks(enum cpuhp_state state,
-				  const char *name,
-				  int (*startup)(unsigned int cpu),
-				  int (*teardown)(unsigned int cpu),
-				  bool multi_instance)
+/*
+ * Returns a free for dynamic slot assignment of the Online state. The states
+ * are protected by the cpuhp_slot_states mutex and an empty slot is identified
+ * by having no name assigned.
+ */
+static int cpuhp_reserve_state(enum cpuhp_state state)
+{
+	enum cpuhp_state i;
+
+	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
+		if (!cpuhp_ap_states[i].name)
+			return i;
+	}
+	WARN(1, "No more dynamic states available for CPU hotplug\n");
+	return -ENOSPC;
+}
+
+static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
+				 int (*startup)(unsigned int cpu),
+				 int (*teardown)(unsigned int cpu),
+				 bool multi_instance)
 {
 	/* (Un)Install the callbacks for further cpu hotplug operations */
 	struct cpuhp_step *sp;
+	int ret = 0;
 
 	mutex_lock(&cpuhp_state_mutex);
+
+	if (state == CPUHP_AP_ONLINE_DYN) {
+		ret = cpuhp_reserve_state(state);
+		if (ret < 0)
+			goto out;
+		state = ret;
+	}
 	sp = cpuhp_get_step(state);
+	if (name && sp->name) {
+		ret = -EBUSY;
+		goto out;
+	}
 	sp->startup.single = startup;
 	sp->teardown.single = teardown;
 	sp->name = name;
 	sp->multi_instance = multi_instance;
 	INIT_HLIST_HEAD(&sp->list);
+out:
 	mutex_unlock(&cpuhp_state_mutex);
+	return ret;
 }
 
 static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
@@ -1509,29 +1539,6 @@ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
 	}
 }
 
-/*
- * Returns a free for dynamic slot assignment of the Online state. The states
- * are protected by the cpuhp_slot_states mutex and an empty slot is identified
- * by having no name assigned.
- */
-static int cpuhp_reserve_state(enum cpuhp_state state)
-{
-	enum cpuhp_state i;
-
-	mutex_lock(&cpuhp_state_mutex);
-	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
-		if (cpuhp_ap_states[i].name)
-			continue;
-
-		cpuhp_ap_states[i].name = "Reserved";
-		mutex_unlock(&cpuhp_state_mutex);
-		return i;
-	}
-	mutex_unlock(&cpuhp_state_mutex);
-	WARN(1, "No more dynamic states available for CPU hotplug\n");
-	return -ENOSPC;
-}
-
 int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 			       bool invoke)
 {
@@ -1580,11 +1587,13 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
 
 /**
  * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
- * @state:	The state to setup
- * @invoke:	If true, the startup function is invoked for cpus where
- *		cpu state >= @state
- * @startup:	startup callback function
- * @teardown:	teardown callback function
+ * @state:		The state to setup
+ * @invoke:		If true, the startup function is invoked for cpus where
+ *			cpu state >= @state
+ * @startup:		startup callback function
+ * @teardown:		teardown callback function
+ * @multi_instance:	State is set up for multiple instances which get
+ *			added afterwards.
  *
  * Returns:
  *   On success:
@@ -1599,25 +1608,16 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 			bool multi_instance)
 {
 	int cpu, ret = 0;
-	int dyn_state = 0;
 
 	if (cpuhp_cb_check(state) || !name)
 		return -EINVAL;
 
 	get_online_cpus();
 
-	/* currently assignments for the ONLINE state are possible */
-	if (state == CPUHP_AP_ONLINE_DYN) {
-		dyn_state = 1;
-		ret = cpuhp_reserve_state(state);
-		if (ret < 0)
-			goto out;
-		state = ret;
-	}
-
-	cpuhp_store_callbacks(state, name, startup, teardown, multi_instance);
+	ret = cpuhp_store_callbacks(state, name, startup, teardown,
+				    multi_instance);
 
-	if (!invoke || !startup)
+	if (ret || !invoke || !startup)
 		goto out;
 
 	/*
@@ -1641,7 +1641,11 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 	}
 out:
 	put_online_cpus();
-	if (!ret && dyn_state)
+	/*
+	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
+	 * dynamically allocated state in case of success.
+	 */
+	if (!ret && state == CPUHP_AP_ONLINE_DYN)
 		return state;
 	return ret;
 }

[patch 03/10] scsi/bnx2fc: Convert to hotplug state machine

[Thomas Gleixner]

[-- Attachment #1: scsibnx2fc_Convert_to_hotplug_state_machine.patch --]
[-- Type: text/plain, Size: 4794 bytes --]

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Install the callbacks via the state machine. No functional change.

This is the minimal fixup so we can remove the hotplug notifier mess
completely.

The real rework of this driver to use work queues is still stuck in
review/testing on the SCSI mailing list.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: James E.J. Bottomley <jejb@linux.vnet.ibm.com>
Cc: linux-scsi@vger.kernel.org
Cc: Chad Dupuis <chad.dupuis@qlogic.com>
Cc: QLogic-Storage-Upstream@qlogic.com
Cc: Johannes Thumshirn <jth@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c |   81 +++++++++++++++-----------------------
 include/linux/cpuhotplug.h        |    1 
 2 files changed, 35 insertions(+), 47 deletions(-)

--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -127,13 +127,6 @@ module_param_named(log_fka, bnx2fc_log_f
 MODULE_PARM_DESC(log_fka, " Print message to kernel log when fcoe is "
 	"initiating a FIP keep alive when debug logging is enabled.");
 
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2fc_cpu_notifier = {
-	.notifier_call = bnx2fc_cpu_callback,
-};
-
 static inline struct net_device *bnx2fc_netdev(const struct fc_lport *lport)
 {
 	return ((struct bnx2fc_interface *)
@@ -2622,37 +2615,19 @@ static void bnx2fc_percpu_thread_destroy
 		kthread_stop(thread);
 }
 
-/**
- * bnx2fc_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:    The callback data block
- * @action: The event triggering the callback
- * @hcpu:   The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for fcoe
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu)
+
+static int bnx2fc_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
+	printk(PFX "CPU %x online: Create Rx thread\n", cpu);
+	bnx2fc_percpu_thread_create(cpu);
+	return 0;
+}
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(PFX "CPU %x online: Create Rx thread\n", cpu);
-		bnx2fc_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2fc_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2fc_cpu_dead(unsigned int cpu)
+{
+	printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2fc_percpu_thread_destroy(cpu);
+	return 0;
 }
 
 static int bnx2fc_slave_configure(struct scsi_device *sdev)
@@ -2664,6 +2639,8 @@ static int bnx2fc_slave_configure(struct
 	return 0;
 }
 
+static enum cpuhp_state bnx2fc_online_state;
+
 /**
  * bnx2fc_mod_init - module init entry point
  *
@@ -2724,21 +2701,31 @@ static int __init bnx2fc_mod_init(void)
 		spin_lock_init(&p->fp_work_lock);
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
-	for_each_online_cpu(cpu) {
+	for_each_online_cpu(cpu)
 		bnx2fc_percpu_thread_create(cpu);
-	}
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2fc_cpu_notifier);
-
-	cpu_notifier_register_done();
+	rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2fc:online",
+				       bnx2fc_cpu_online, NULL);
+	if (rc < 0)
+		goto stop_threads;
+	bnx2fc_online_state = rc;
+
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD, "scsi/bnx2fc:dead",
+				  NULL, bnx2fc_cpu_dead);
+	put_online_cpus();
 
 	cnic_register_driver(CNIC_ULP_FCOE, &bnx2fc_cnic_cb);
 
 	return 0;
 
+stop_threads:
+	for_each_online_cpu(cpu)
+		bnx2fc_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	kthread_stop(l2_thread);
 free_wq:
 	destroy_workqueue(bnx2fc_wq);
 release_bt:
@@ -2797,16 +2784,16 @@ static void __exit bnx2fc_mod_exit(void)
 	if (l2_thread)
 		kthread_stop(l2_thread);
 
-	cpu_notifier_register_begin();
-
+	get_online_cpus();
 	/* Destroy per cpu threads */
 	for_each_online_cpu(cpu) {
 		bnx2fc_percpu_thread_destroy(cpu);
 	}
 
-	__unregister_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	cpuhp_remove_state_nocalls(bnx2fc_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD);
 
-	cpu_notifier_register_done();
+	put_online_cpus();
 
 	destroy_workqueue(bnx2fc_wq);
 	/*
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_SCSI_BNX2FC_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,

[tip:smp/urgent] scsi/bnx2fc: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  017426e49fec9fff11cba0dfcf9ea931425db904
Gitweb:     http://git.kernel.org/tip/017426e49fec9fff11cba0dfcf9ea931425db904
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:50 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:54 +0100

scsi/bnx2fc: Convert to hotplug state machine

Install the callbacks via the state machine. No functional change.

This is the minimal fixup so we can remove the hotplug notifier mess
completely.

The real rework of this driver to use work queues is still stuck in
review/testing on the SCSI mailing list.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
Cc: linux-scsi@vger.kernel.org
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Chad Dupuis <chad.dupuis@qlogic.com>
Cc: QLogic-Storage-Upstream@qlogic.com
Cc: Johannes Thumshirn <jth@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20161221192111.757309869@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c | 79 ++++++++++++++++-----------------------
 include/linux/cpuhotplug.h        |  1 +
 2 files changed, 34 insertions(+), 46 deletions(-)

diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 0990130..c639d5a 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -127,13 +127,6 @@ module_param_named(log_fka, bnx2fc_log_fka, uint, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(log_fka, " Print message to kernel log when fcoe is "
 	"initiating a FIP keep alive when debug logging is enabled.");
 
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2fc_cpu_notifier = {
-	.notifier_call = bnx2fc_cpu_callback,
-};
-
 static inline struct net_device *bnx2fc_netdev(const struct fc_lport *lport)
 {
 	return ((struct bnx2fc_interface *)
@@ -2622,37 +2615,19 @@ static void bnx2fc_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-/**
- * bnx2fc_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:    The callback data block
- * @action: The event triggering the callback
- * @hcpu:   The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for fcoe
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu)
+
+static int bnx2fc_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
+	printk(PFX "CPU %x online: Create Rx thread\n", cpu);
+	bnx2fc_percpu_thread_create(cpu);
+	return 0;
+}
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(PFX "CPU %x online: Create Rx thread\n", cpu);
-		bnx2fc_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2fc_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2fc_cpu_dead(unsigned int cpu)
+{
+	printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2fc_percpu_thread_destroy(cpu);
+	return 0;
 }
 
 static int bnx2fc_slave_configure(struct scsi_device *sdev)
@@ -2664,6 +2639,8 @@ static int bnx2fc_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
+static enum cpuhp_state bnx2fc_online_state;
+
 /**
  * bnx2fc_mod_init - module init entry point
  *
@@ -2724,21 +2701,31 @@ static int __init bnx2fc_mod_init(void)
 		spin_lock_init(&p->fp_work_lock);
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
-	for_each_online_cpu(cpu) {
+	for_each_online_cpu(cpu)
 		bnx2fc_percpu_thread_create(cpu);
-	}
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2fc:online",
+				       bnx2fc_cpu_online, NULL);
+	if (rc < 0)
+		goto stop_threads;
+	bnx2fc_online_state = rc;
 
-	cpu_notifier_register_done();
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD, "scsi/bnx2fc:dead",
+				  NULL, bnx2fc_cpu_dead);
+	put_online_cpus();
 
 	cnic_register_driver(CNIC_ULP_FCOE, &bnx2fc_cnic_cb);
 
 	return 0;
 
+stop_threads:
+	for_each_online_cpu(cpu)
+		bnx2fc_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	kthread_stop(l2_thread);
 free_wq:
 	destroy_workqueue(bnx2fc_wq);
 release_bt:
@@ -2797,16 +2784,16 @@ static void __exit bnx2fc_mod_exit(void)
 	if (l2_thread)
 		kthread_stop(l2_thread);
 
-	cpu_notifier_register_begin();
-
+	get_online_cpus();
 	/* Destroy per cpu threads */
 	for_each_online_cpu(cpu) {
 		bnx2fc_percpu_thread_destroy(cpu);
 	}
 
-	__unregister_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	cpuhp_remove_state_nocalls(bnx2fc_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD);
 
-	cpu_notifier_register_done();
+	put_online_cpus();
 
 	destroy_workqueue(bnx2fc_wq);
 	/*
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 2ab7bf5..ab0e54d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_SCSI_BNX2FC_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,

[tip:smp/urgent] scsi/bnx2fc: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  c53b005dd64bdcf5acac00bd55ecf94dda22dc4f
Gitweb:     http://git.kernel.org/tip/c53b005dd64bdcf5acac00bd55ecf94dda22dc4f
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:50 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:42 +0100

scsi/bnx2fc: Convert to hotplug state machine

Install the callbacks via the state machine. No functional change.

This is the minimal fixup so we can remove the hotplug notifier mess
completely.

The real rework of this driver to use work queues is still stuck in
review/testing on the SCSI mailing list.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
Cc: linux-scsi@vger.kernel.org
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Chad Dupuis <chad.dupuis@qlogic.com>
Cc: QLogic-Storage-Upstream@qlogic.com
Cc: Johannes Thumshirn <jth@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20161221192111.757309869@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c | 79 ++++++++++++++++-----------------------
 include/linux/cpuhotplug.h        |  1 +
 2 files changed, 34 insertions(+), 46 deletions(-)

diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 0990130..c639d5a 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -127,13 +127,6 @@ module_param_named(log_fka, bnx2fc_log_fka, uint, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(log_fka, " Print message to kernel log when fcoe is "
 	"initiating a FIP keep alive when debug logging is enabled.");
 
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2fc_cpu_notifier = {
-	.notifier_call = bnx2fc_cpu_callback,
-};
-
 static inline struct net_device *bnx2fc_netdev(const struct fc_lport *lport)
 {
 	return ((struct bnx2fc_interface *)
@@ -2622,37 +2615,19 @@ static void bnx2fc_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-/**
- * bnx2fc_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:    The callback data block
- * @action: The event triggering the callback
- * @hcpu:   The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for fcoe
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu)
+
+static int bnx2fc_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
+	printk(PFX "CPU %x online: Create Rx thread\n", cpu);
+	bnx2fc_percpu_thread_create(cpu);
+	return 0;
+}
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(PFX "CPU %x online: Create Rx thread\n", cpu);
-		bnx2fc_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2fc_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2fc_cpu_dead(unsigned int cpu)
+{
+	printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2fc_percpu_thread_destroy(cpu);
+	return 0;
 }
 
 static int bnx2fc_slave_configure(struct scsi_device *sdev)
@@ -2664,6 +2639,8 @@ static int bnx2fc_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
+static enum cpuhp_state bnx2fc_online_state;
+
 /**
  * bnx2fc_mod_init - module init entry point
  *
@@ -2724,21 +2701,31 @@ static int __init bnx2fc_mod_init(void)
 		spin_lock_init(&p->fp_work_lock);
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
-	for_each_online_cpu(cpu) {
+	for_each_online_cpu(cpu)
 		bnx2fc_percpu_thread_create(cpu);
-	}
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2fc:online",
+				       bnx2fc_cpu_online, NULL);
+	if (rc < 0)
+		goto stop_threads;
+	bnx2fc_online_state = rc;
 
-	cpu_notifier_register_done();
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD, "scsi/bnx2fc:dead",
+				  NULL, bnx2fc_cpu_dead);
+	put_online_cpus();
 
 	cnic_register_driver(CNIC_ULP_FCOE, &bnx2fc_cnic_cb);
 
 	return 0;
 
+stop_threads:
+	for_each_online_cpu(cpu)
+		bnx2fc_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	kthread_stop(l2_thread);
 free_wq:
 	destroy_workqueue(bnx2fc_wq);
 release_bt:
@@ -2797,16 +2784,16 @@ static void __exit bnx2fc_mod_exit(void)
 	if (l2_thread)
 		kthread_stop(l2_thread);
 
-	cpu_notifier_register_begin();
-
+	get_online_cpus();
 	/* Destroy per cpu threads */
 	for_each_online_cpu(cpu) {
 		bnx2fc_percpu_thread_destroy(cpu);
 	}
 
-	__unregister_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	cpuhp_remove_state_nocalls(bnx2fc_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD);
 
-	cpu_notifier_register_done();
+	put_online_cpus();
 
 	destroy_workqueue(bnx2fc_wq);
 	/*
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 2ab7bf5..ab0e54d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_SCSI_BNX2FC_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,

[patch 04/10] scsi/bnx2i: Convert to hotplug state machine

[Thomas Gleixner]

[-- Attachment #1: scsibnx2i_Convert_to_hotplug_state_machine.patch --]
[-- Type: text/plain, Size: 4478 bytes --]

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Install the callbacks via the state machine. No functional change.

This is the minimal fixup so we can remove the hotplug notifier mess
completely.

The real rework of this driver to use work queues is still stuck in
review/testing on the SCSI mailing list.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: James E.J. Bottomley <jejb@linux.vnet.ibm.com>
Cc: linux-scsi@vger.kernel.org
Cc: Chad Dupuis <chad.dupuis@qlogic.com>
Cc: QLogic-Storage-Upstream@qlogic.com
Cc: Johannes Thumshirn <jth@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/scsi/bnx2i/bnx2i_init.c |   80 +++++++++++++++-------------------------
 include/linux/cpuhotplug.h      |    1 
 2 files changed, 32 insertions(+), 49 deletions(-)

--- a/drivers/scsi/bnx2i/bnx2i_init.c
+++ b/drivers/scsi/bnx2i/bnx2i_init.c
@@ -70,14 +70,6 @@ u64 iscsi_error_mask = 0x00;
 
 DEFINE_PER_CPU(struct bnx2i_percpu_s, bnx2i_percpu);
 
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2i_cpu_notifier = {
-	.notifier_call = bnx2i_cpu_callback,
-};
-
-
 /**
  * bnx2i_identify_device - identifies NetXtreme II device type
  * @hba: 		Adapter structure pointer
@@ -461,41 +453,21 @@ static void bnx2i_percpu_thread_destroy(
 		kthread_stop(thread);
 }
 
-
-/**
- * bnx2i_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:	The callback data block
- * @action:	The event triggering the callback
- * @hcpu:	The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for iSCSI
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu)
+static int bnx2i_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
+	pr_info("bnx2i: CPU %x online: Create Rx thread\n", cpu);
+	bnx2i_percpu_thread_create(cpu);
+	return 0;
+}
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(KERN_INFO "bnx2i: CPU %x online: Create Rx thread\n",
-			cpu);
-		bnx2i_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(KERN_INFO "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2i_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2i_cpu_dead(unsigned int cpu)
+{
+	pr_info("CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2i_percpu_thread_destroy(cpu);
+	return 0;
 }
 
+static enum cpuhp_state bnx2i_online_state;
 
 /**
  * bnx2i_mod_init - module init entry point
@@ -539,18 +511,28 @@ static int __init bnx2i_mod_init(void)
 		p->iothread = NULL;
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_create(cpu);
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
-
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2i:online",
+				       bnx2i_cpu_online, NULL);
+	if (err < 0)
+		goto remove_threads;
+	bnx2i_online_state = err;
+
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2I_DEAD, "scsi/bnx2i:dead",
+				  NULL, bnx2i_cpu_dead);
+	put_online_cpus();
 	return 0;
 
+remove_threads:
+	for_each_online_cpu(cpu)
+		bnx2i_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	cnic_unregister_driver(CNIC_ULP_ISCSI);
 unreg_xport:
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 out:
@@ -587,14 +569,14 @@ static void __exit bnx2i_mod_exit(void)
 	}
 	mutex_unlock(&bnx2i_dev_lock);
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_destroy(cpu);
 
-	__unregister_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
+	cpuhp_remove_state_nocalls(bnx2i_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2I_DEAD);
+	put_online_cpus();
 
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 	cnic_unregister_driver(CNIC_ULP_ISCSI);
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -42,6 +42,7 @@ enum cpuhp_state {
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
 	CPUHP_SCSI_BNX2FC_DEAD,
+	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,

[tip:smp/urgent] scsi/bnx2i: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  ea1c68c71a84aafdcbd7f3a8a14a198a3879c0bf
Gitweb:     http://git.kernel.org/tip/ea1c68c71a84aafdcbd7f3a8a14a198a3879c0bf
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:51 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:54 +0100

scsi/bnx2i: Convert to hotplug state machine

Install the callbacks via the state machine. No functional change.

This is the minimal fixup so we can remove the hotplug notifier mess
completely.

The real rework of this driver to use work queues is still stuck in
review/testing on the SCSI mailing list.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
Cc: linux-scsi@vger.kernel.org
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Chad Dupuis <chad.dupuis@qlogic.com>
Cc: QLogic-Storage-Upstream@qlogic.com
Cc: Johannes Thumshirn <jth@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20161221192111.836895753@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/scsi/bnx2i/bnx2i_init.c | 78 ++++++++++++++++-------------------------
 include/linux/cpuhotplug.h      |  1 +
 2 files changed, 31 insertions(+), 48 deletions(-)

diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index c8b410c..86afc00 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
+++ b/drivers/scsi/bnx2i/bnx2i_init.c
@@ -70,14 +70,6 @@ u64 iscsi_error_mask = 0x00;
 
 DEFINE_PER_CPU(struct bnx2i_percpu_s, bnx2i_percpu);
 
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2i_cpu_notifier = {
-	.notifier_call = bnx2i_cpu_callback,
-};
-
-
 /**
  * bnx2i_identify_device - identifies NetXtreme II device type
  * @hba: 		Adapter structure pointer
@@ -461,41 +453,21 @@ static void bnx2i_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-
-/**
- * bnx2i_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:	The callback data block
- * @action:	The event triggering the callback
- * @hcpu:	The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for iSCSI
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu)
+static int bnx2i_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
+	pr_info("bnx2i: CPU %x online: Create Rx thread\n", cpu);
+	bnx2i_percpu_thread_create(cpu);
+	return 0;
+}
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(KERN_INFO "bnx2i: CPU %x online: Create Rx thread\n",
-			cpu);
-		bnx2i_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(KERN_INFO "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2i_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2i_cpu_dead(unsigned int cpu)
+{
+	pr_info("CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2i_percpu_thread_destroy(cpu);
+	return 0;
 }
 
+static enum cpuhp_state bnx2i_online_state;
 
 /**
  * bnx2i_mod_init - module init entry point
@@ -539,18 +511,28 @@ static int __init bnx2i_mod_init(void)
 		p->iothread = NULL;
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_create(cpu);
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2i:online",
+				       bnx2i_cpu_online, NULL);
+	if (err < 0)
+		goto remove_threads;
+	bnx2i_online_state = err;
 
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2I_DEAD, "scsi/bnx2i:dead",
+				  NULL, bnx2i_cpu_dead);
+	put_online_cpus();
 	return 0;
 
+remove_threads:
+	for_each_online_cpu(cpu)
+		bnx2i_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	cnic_unregister_driver(CNIC_ULP_ISCSI);
 unreg_xport:
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 out:
@@ -587,14 +569,14 @@ static void __exit bnx2i_mod_exit(void)
 	}
 	mutex_unlock(&bnx2i_dev_lock);
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_destroy(cpu);
 
-	__unregister_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
+	cpuhp_remove_state_nocalls(bnx2i_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2I_DEAD);
+	put_online_cpus();
 
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 	cnic_unregister_driver(CNIC_ULP_ISCSI);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index ab0e54d..fc4587c 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -42,6 +42,7 @@ enum cpuhp_state {
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
 	CPUHP_SCSI_BNX2FC_DEAD,
+	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,

[tip:smp/urgent] scsi/bnx2i: Convert to hotplug state machine

[tip-bot for Sebastian Andrzej Siewior]

Commit-ID:  e210faa2359f92eb2e417cd8462eb980a4dbb172
Gitweb:     http://git.kernel.org/tip/e210faa2359f92eb2e417cd8462eb980a4dbb172
Author:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:51 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:43 +0100

scsi/bnx2i: Convert to hotplug state machine

Install the callbacks via the state machine. No functional change.

This is the minimal fixup so we can remove the hotplug notifier mess
completely.

The real rework of this driver to use work queues is still stuck in
review/testing on the SCSI mailing list.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
Cc: linux-scsi@vger.kernel.org
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Chad Dupuis <chad.dupuis@qlogic.com>
Cc: QLogic-Storage-Upstream@qlogic.com
Cc: Johannes Thumshirn <jth@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20161221192111.836895753@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/scsi/bnx2i/bnx2i_init.c | 78 ++++++++++++++++-------------------------
 include/linux/cpuhotplug.h      |  1 +
 2 files changed, 31 insertions(+), 48 deletions(-)

diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index c8b410c..86afc00 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
+++ b/drivers/scsi/bnx2i/bnx2i_init.c
@@ -70,14 +70,6 @@ u64 iscsi_error_mask = 0x00;
 
 DEFINE_PER_CPU(struct bnx2i_percpu_s, bnx2i_percpu);
 
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2i_cpu_notifier = {
-	.notifier_call = bnx2i_cpu_callback,
-};
-
-
 /**
  * bnx2i_identify_device - identifies NetXtreme II device type
  * @hba: 		Adapter structure pointer
@@ -461,41 +453,21 @@ static void bnx2i_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-
-/**
- * bnx2i_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:	The callback data block
- * @action:	The event triggering the callback
- * @hcpu:	The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for iSCSI
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu)
+static int bnx2i_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
+	pr_info("bnx2i: CPU %x online: Create Rx thread\n", cpu);
+	bnx2i_percpu_thread_create(cpu);
+	return 0;
+}
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(KERN_INFO "bnx2i: CPU %x online: Create Rx thread\n",
-			cpu);
-		bnx2i_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(KERN_INFO "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2i_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2i_cpu_dead(unsigned int cpu)
+{
+	pr_info("CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2i_percpu_thread_destroy(cpu);
+	return 0;
 }
 
+static enum cpuhp_state bnx2i_online_state;
 
 /**
  * bnx2i_mod_init - module init entry point
@@ -539,18 +511,28 @@ static int __init bnx2i_mod_init(void)
 		p->iothread = NULL;
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_create(cpu);
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2i:online",
+				       bnx2i_cpu_online, NULL);
+	if (err < 0)
+		goto remove_threads;
+	bnx2i_online_state = err;
 
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2I_DEAD, "scsi/bnx2i:dead",
+				  NULL, bnx2i_cpu_dead);
+	put_online_cpus();
 	return 0;
 
+remove_threads:
+	for_each_online_cpu(cpu)
+		bnx2i_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	cnic_unregister_driver(CNIC_ULP_ISCSI);
 unreg_xport:
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 out:
@@ -587,14 +569,14 @@ static void __exit bnx2i_mod_exit(void)
 	}
 	mutex_unlock(&bnx2i_dev_lock);
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_destroy(cpu);
 
-	__unregister_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
+	cpuhp_remove_state_nocalls(bnx2i_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2I_DEAD);
+	put_online_cpus();
 
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 	cnic_unregister_driver(CNIC_ULP_ISCSI);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index ab0e54d..fc4587c 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -42,6 +42,7 @@ enum cpuhp_state {
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
 	CPUHP_SCSI_BNX2FC_DEAD,
+	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,

[patch 05/10] staging/lustre/libcfs: Convert to hotplug state machine

[Thomas Gleixner]

[-- Attachment #1: staginglustrelibcfs_Convert_to_hotplug_state_machine.patch --]
[-- Type: text/plain, Size: 4564 bytes --]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine. No functional change.

Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: devel@driverdev.osuosl.org
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: rt@linutronix.de
Cc: lustre-devel@lists.lustre.org
Link: http://lkml.kernel.org/r/20161202110027.htzzeervzkoc4muv@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---

 drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c |   85 ++++++++++---------
 include/linux/cpuhotplug.h                           |    1 
 2 files changed, 46 insertions(+), 40 deletions(-)

--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -967,48 +967,38 @@ cfs_cpt_table_create_pattern(char *patte
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
+static enum cpuhp_state lustre_cpu_online;
 
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
+static void cfs_cpu_incr_cpt_version(void)
+{
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
+}
 
-	return NOTIFY_OK;
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
 
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask, topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1008,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online > 0)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1019,8 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+	int ret = 0;
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,8 +1035,19 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
+	ret = -EINVAL;
 
 	if (*cpu_pattern) {
 		cfs_cpt_table = cfs_cpt_table_create_pattern(cpu_pattern);
@@ -1075,7 +1080,7 @@ cfs_cpu_init(void)
 
  failed:
 	cfs_cpu_fini();
-	return -1;
+	return ret;
 }
 
 #endif
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_SCSI_BNX2FC_DEAD,
 	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,

[lustre-devel] [patch 05/10] staging/lustre/libcfs: Convert to hotplug state machine

[Thomas Gleixner]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine. No functional change.

Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: devel at driverdev.osuosl.org
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: rt at linutronix.de
Cc: lustre-devel at lists.lustre.org
Link: http://lkml.kernel.org/r/20161202110027.htzzeervzkoc4muv at linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---

 drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c |   85 ++++++++++---------
 include/linux/cpuhotplug.h                           |    1 
 2 files changed, 46 insertions(+), 40 deletions(-)

--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -967,48 +967,38 @@ cfs_cpt_table_create_pattern(char *patte
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
+static enum cpuhp_state lustre_cpu_online;
 
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
+static void cfs_cpu_incr_cpt_version(void)
+{
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
+}
 
-	return NOTIFY_OK;
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
 
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask, topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1008,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online > 0)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1019,8 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+	int ret = 0;
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,8 +1035,19 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
+	ret = -EINVAL;
 
 	if (*cpu_pattern) {
 		cfs_cpt_table = cfs_cpt_table_create_pattern(cpu_pattern);
@@ -1075,7 +1080,7 @@ cfs_cpu_init(void)
 
  failed:
 	cfs_cpu_fini();
-	return -1;
+	return ret;
 }
 
 #endif
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_SCSI_BNX2FC_DEAD,
 	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,

[tip:smp/urgent] staging/lustre/libcfs: Convert to hotplug state machine

[tip-bot for Anna-Maria Gleixner]

Commit-ID:  b44c6c54a04a6d956c561a6ce4d64f4070405823
Gitweb:     http://git.kernel.org/tip/b44c6c54a04a6d956c561a6ce4d64f4070405823
Author:     Anna-Maria Gleixner <anna-maria@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:52 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:55 +0100

staging/lustre/libcfs: Convert to hotplug state machine

Install the callbacks via the state machine. No functional change.

Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: devel@driverdev.osuosl.org
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: rt@linutronix.de
Cc: lustre-devel@lists.lustre.org
Link: http://lkml.kernel.org/r/20161202110027.htzzeervzkoc4muv@linutronix.de
Link: http://lkml.kernel.org/r/20161221192111.922872524@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 .../staging/lustre/lnet/libcfs/linux/linux-cpu.c   | 85 ++++++++++++----------
 include/linux/cpuhotplug.h                         |  1 +
 2 files changed, 46 insertions(+), 40 deletions(-)

diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index 6b9cf06..427e219 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -967,48 +967,38 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
+static enum cpuhp_state lustre_cpu_online;
 
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
+static void cfs_cpu_incr_cpt_version(void)
+{
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
+}
 
-	return NOTIFY_OK;
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
 
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask, topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1008,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online > 0)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1019,8 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+	int ret = 0;
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,8 +1035,19 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
+	ret = -EINVAL;
 
 	if (*cpu_pattern) {
 		cfs_cpt_table = cfs_cpt_table_create_pattern(cpu_pattern);
@@ -1075,7 +1080,7 @@ cfs_cpu_init(void)
 
  failed:
 	cfs_cpu_fini();
-	return -1;
+	return ret;
 }
 
 #endif
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index fc4587c..175d276 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_SCSI_BNX2FC_DEAD,
 	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,

[tip:smp/urgent] staging/lustre/libcfs: Convert to hotplug state machine

[tip-bot for Anna-Maria Gleixner]

Commit-ID:  7b737965b33188bd3dbb44e938535c4006d97fbb
Gitweb:     http://git.kernel.org/tip/7b737965b33188bd3dbb44e938535c4006d97fbb
Author:     Anna-Maria Gleixner <anna-maria@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:52 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:43 +0100

staging/lustre/libcfs: Convert to hotplug state machine

Install the callbacks via the state machine. No functional change.

Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: devel@driverdev.osuosl.org
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: rt@linutronix.de
Cc: lustre-devel@lists.lustre.org
Link: http://lkml.kernel.org/r/20161202110027.htzzeervzkoc4muv@linutronix.de
Link: http://lkml.kernel.org/r/20161221192111.922872524@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 .../staging/lustre/lnet/libcfs/linux/linux-cpu.c   | 85 ++++++++++++----------
 include/linux/cpuhotplug.h                         |  1 +
 2 files changed, 46 insertions(+), 40 deletions(-)

diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index 6b9cf06..427e219 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -967,48 +967,38 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
+static enum cpuhp_state lustre_cpu_online;
 
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
+static void cfs_cpu_incr_cpt_version(void)
+{
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
+}
 
-	return NOTIFY_OK;
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
 
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask, topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1008,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online > 0)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1019,8 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+	int ret = 0;
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,8 +1035,19 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
+	ret = -EINVAL;
 
 	if (*cpu_pattern) {
 		cfs_cpt_table = cfs_cpt_table_create_pattern(cpu_pattern);
@@ -1075,7 +1080,7 @@ cfs_cpu_init(void)
 
  failed:
 	cfs_cpu_fini();
-	return -1;
+	return ret;
 }
 
 #endif
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index fc4587c..175d276 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,7 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_SCSI_BNX2FC_DEAD,
 	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,

[patch 06/10] cpu/hotplug: Remove obsolete cpu hotplug register/unregister functions

[Thomas Gleixner]

[-- Attachment #1: _Remove_obsolete_cpu_hotplug_register__unregister_functions.patch --]
[-- Type: text/plain, Size: 16443 bytes --]

hotcpu_notifier(), cpu_notifier(), __hotcpu_notifier(), __cpu_notifier(),
register_hotcpu_notifier(), register_cpu_notifier(),
__register_hotcpu_notifier(), __register_cpu_notifier(),
unregister_hotcpu_notifier(), unregister_cpu_notifier(),
__unregister_hotcpu_notifier(), __unregister_cpu_notifier()

are unused now. Remove them and all related code.

Remove also the now pointless cpu notifier error injection mechanism. The
states can be executed step by step and error rollback is the same as cpu
down, so any state transition can be tested w/o requiring the notifier
error injection.

Some CPU hotplug states are kept as they are (ab)used for hotplug state
tracking.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20161126231350.10321-23-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/cpu.h             |   90 -------------------------
 include/linux/cpuhotplug.h      |    3 
 kernel/cpu.c                    |  139 ----------------------------------------
 lib/Kconfig.debug               |   24 ------
 lib/Makefile                    |    1 
 lib/cpu-notifier-error-inject.c |   84 ------------------------
 6 files changed, 1 insertion(+), 340 deletions(-)

--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -57,9 +57,6 @@ struct notifier_block;
 
 #define CPU_ONLINE		0x0002 /* CPU (unsigned)v is up */
 #define CPU_UP_PREPARE		0x0003 /* CPU (unsigned)v coming up */
-#define CPU_UP_CANCELED		0x0004 /* CPU (unsigned)v NOT coming up */
-#define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
-#define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
 #define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
 					* lock is dropped */
@@ -80,80 +77,14 @@ struct notifier_block;
 
 #ifdef CONFIG_SMP
 extern bool cpuhp_tasks_frozen;
-/* Need to know about CPUs going up/down? */
-#if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
-#define cpu_notifier(fn, pri) {					\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	register_cpu_notifier(&fn##_nb);			\
-}
-
-#define __cpu_notifier(fn, pri) {				\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	__register_cpu_notifier(&fn##_nb);			\
-}
-
-extern int register_cpu_notifier(struct notifier_block *nb);
-extern int __register_cpu_notifier(struct notifier_block *nb);
-extern void unregister_cpu_notifier(struct notifier_block *nb);
-extern void __unregister_cpu_notifier(struct notifier_block *nb);
-
-#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-#endif
-
 int cpu_up(unsigned int cpu);
 void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 
-#define cpu_notifier_register_begin	cpu_maps_update_begin
-#define cpu_notifier_register_done	cpu_maps_update_done
-
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
 
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
 static inline void cpu_maps_update_begin(void)
 {
 }
@@ -162,14 +93,6 @@ static inline void cpu_maps_update_done(
 {
 }
 
-static inline void cpu_notifier_register_begin(void)
-{
-}
-
-static inline void cpu_notifier_register_done(void)
-{
-}
-
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -182,12 +105,6 @@ extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
-#define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
-#define __hotcpu_notifier(fn, pri)	__cpu_notifier(fn, pri)
-#define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
-#define __register_hotcpu_notifier(nb)	__register_cpu_notifier(nb)
-#define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
-#define __unregister_hotcpu_notifier(nb)	__unregister_cpu_notifier(nb)
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
@@ -199,13 +116,6 @@ static inline void cpu_hotplug_done(void
 #define put_online_cpus()	do { } while (0)
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
-#define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-/* These aren't inline functions due to a GCC bug. */
-#define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define __register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define unregister_hotcpu_notifier(nb)	({ (void)(nb); })
-#define __unregister_hotcpu_notifier(nb)	({ (void)(nb); })
 #endif		/* CONFIG_HOTPLUG_CPU */
 
 #ifdef CONFIG_PM_SLEEP_SMP
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -59,7 +59,6 @@ enum cpuhp_state {
 	CPUHP_POWERPC_MMU_CTX_PREPARE,
 	CPUHP_XEN_PREPARE,
 	CPUHP_XEN_EVTCHN_PREPARE,
-	CPUHP_NOTIFY_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
 	CPUHP_BLK_MQ_PREPARE,
@@ -74,7 +73,6 @@ enum cpuhp_state {
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_DEAD,
-	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BRINGUP_CPU,
 	CPUHP_AP_IDLE_DEAD,
@@ -145,7 +143,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_ARM_L2X0_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
-	CPUHP_AP_NOTIFY_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
 	CPUHP_AP_X86_HPET_ONLINE,
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -183,23 +183,16 @@ EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
 /*
  * The following two APIs (cpu_maps_update_begin/done) must be used when
  * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
- * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
- * hotplug callback (un)registration performed using __register_cpu_notifier()
- * or __unregister_cpu_notifier().
  */
 void cpu_maps_update_begin(void)
 {
 	mutex_lock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_begin);
 
 void cpu_maps_update_done(void)
 {
 	mutex_unlock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_done);
-
-static RAW_NOTIFIER_HEAD(cpu_chain);
 
 /* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
  * Should always be manipulated under cpu_add_remove_lock
@@ -349,66 +342,7 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-/* Need to know about CPUs going up/down? */
-int register_cpu_notifier(struct notifier_block *nb)
-{
-	int ret;
-	cpu_maps_update_begin();
-	ret = raw_notifier_chain_register(&cpu_chain, nb);
-	cpu_maps_update_done();
-	return ret;
-}
-
-int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return raw_notifier_chain_register(&cpu_chain, nb);
-}
-
-static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
-			int *nr_calls)
-{
-	unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
-	void *hcpu = (void *)(long)cpu;
-
-	int ret;
-
-	ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
-					nr_calls);
-
-	return notifier_to_errno(ret);
-}
-
-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)
-{
-	int nr_calls = 0;
-	int ret;
-
-	ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
-	if (ret) {
-		nr_calls--;
-		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
-				__func__, cpu);
-		__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
-	}
-	return ret;
-}
-
-static int notify_online(unsigned int cpu)
-{
-	cpu_notify(CPU_ONLINE, cpu);
-	return 0;
-}
 
 static int bringup_wait_for_ap(unsigned int cpu)
 {
@@ -433,10 +367,8 @@ static int bringup_cpu(unsigned int cpu)
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
 	irq_unlock_sparse();
-	if (ret) {
-		cpu_notify(CPU_UP_CANCELED, cpu);
+	if (ret)
 		return ret;
-	}
 	ret = bringup_wait_for_ap(cpu);
 	BUG_ON(!cpu_online(cpu));
 	return ret;
@@ -565,11 +497,6 @@ static void cpuhp_thread_fun(unsigned in
 		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
 
 		undo_cpu_down(cpu, st);
-		/*
-		 * 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 .... */
@@ -659,22 +586,6 @@ void __init cpuhp_threads_init(void)
 	kthread_unpark(this_cpu_read(cpuhp_state.thread));
 }
 
-EXPORT_SYMBOL(register_cpu_notifier);
-EXPORT_SYMBOL(__register_cpu_notifier);
-void unregister_cpu_notifier(struct notifier_block *nb)
-{
-	cpu_maps_update_begin();
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-	cpu_maps_update_done();
-}
-EXPORT_SYMBOL(unregister_cpu_notifier);
-
-void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-}
-EXPORT_SYMBOL(__unregister_cpu_notifier);
-
 #ifdef CONFIG_HOTPLUG_CPU
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
@@ -741,20 +652,6 @@ static inline void check_for_tasks(int d
 	read_unlock(&tasklist_lock);
 }
 
-static int notify_down_prepare(unsigned int cpu)
-{
-	int err, nr_calls = 0;
-
-	err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
-	if (err) {
-		nr_calls--;
-		__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
-		pr_warn("%s: attempt to take down CPU %u failed\n",
-				__func__, cpu);
-	}
-	return err;
-}
-
 /* Take this CPU down. */
 static int take_cpu_down(void *_param)
 {
@@ -833,13 +730,6 @@ static int takedown_cpu(unsigned int cpu
 	return 0;
 }
 
-static int notify_dead(unsigned int cpu)
-{
-	cpu_notify_nofail(CPU_DEAD, cpu);
-	check_for_tasks(cpu);
-	return 0;
-}
-
 static void cpuhp_complete_idle_dead(void *arg)
 {
 	struct cpuhp_cpu_state *st = arg;
@@ -863,9 +753,7 @@ void cpuhp_report_idle_dead(void)
 }
 
 #else
-#define notify_down_prepare	NULL
 #define takedown_cpu		NULL
-#define notify_dead		NULL
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -924,9 +812,6 @@ static int __ref _cpu_down(unsigned int
 	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
 out:
 	cpu_hotplug_done();
-	/* This post dead nonsense must die */
-	if (!ret && hasdied)
-		cpu_notify_nofail(CPU_POST_DEAD, cpu);
 	return ret;
 }
 
@@ -1292,17 +1177,6 @@ static struct cpuhp_step cpuhp_bp_states
 		.teardown.single	= rcutree_dead_cpu,
 	},
 	/*
-	 * Preparatory and dead notifiers. Will be replaced once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_NOTIFY_PREPARE] = {
-		.name			= "notify:prepare",
-		.startup.single		= notify_prepare,
-		.teardown.single	= notify_dead,
-		.skip_onerr		= true,
-		.cant_stop		= true,
-	},
-	/*
 	 * On the tear-down path, timers_dead_cpu() must be invoked
 	 * before blk_mq_queue_reinit_notify() from notify_dead(),
 	 * otherwise a RCU stall occurs.
@@ -1391,17 +1265,6 @@ static struct cpuhp_step cpuhp_ap_states
 		.startup.single		= rcutree_online_cpu,
 		.teardown.single	= rcutree_offline_cpu,
 	},
-
-	/*
-	 * Online/down_prepare notifiers. Will be removed once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_AP_NOTIFY_ONLINE] = {
-		.name			= "notify:online",
-		.startup.single		= notify_online,
-		.teardown.single	= notify_down_prepare,
-		.skip_onerr		= true,
-	},
 #endif
 	/*
 	 * The dynamically registered state space is here
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1538,30 +1538,6 @@ config NOTIFIER_ERROR_INJECTION
 
 	  Say N if unsure.
 
-config CPU_NOTIFIER_ERROR_INJECT
-	tristate "CPU notifier error injection module"
-	depends on HOTPLUG_CPU && NOTIFIER_ERROR_INJECTION
-	help
-	  This option provides a kernel module that can be used to test
-	  the error handling of the cpu notifiers by injecting artificial
-	  errors to CPU notifier chain callbacks.  It is controlled through
-	  debugfs interface under /sys/kernel/debug/notifier-error-inject/cpu
-
-	  If the notifier call chain should be failed with some events
-	  notified, write the error code to "actions/<notifier event>/error".
-
-	  Example: Inject CPU offline error (-1 == -EPERM)
-
-	  # cd /sys/kernel/debug/notifier-error-inject/cpu
-	  # echo -1 > actions/CPU_DOWN_PREPARE/error
-	  # echo 0 > /sys/devices/system/cpu/cpu1/online
-	  bash: echo: write error: Operation not permitted
-
-	  To compile this code as a module, choose M here: the module will
-	  be called cpu-notifier-error-inject.
-
-	  If unsure, say N.
-
 config PM_NOTIFIER_ERROR_INJECT
 	tristate "PM notifier error injection module"
 	depends on PM && NOTIFIER_ERROR_INJECTION
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -128,7 +128,6 @@ obj-$(CONFIG_SWIOTLB) += swiotlb.o
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
-obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o
 obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
 obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
 obj-$(CONFIG_MEMORY_NOTIFIER_ERROR_INJECT) += memory-notifier-error-inject.o
--- a/lib/cpu-notifier-error-inject.c
+++ /dev/null
@@ -1,84 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-
-#include "notifier-error-inject.h"
-
-static int priority;
-module_param(priority, int, 0);
-MODULE_PARM_DESC(priority, "specify cpu notifier priority");
-
-#define UP_PREPARE 0
-#define UP_PREPARE_FROZEN 0
-#define DOWN_PREPARE 0
-#define DOWN_PREPARE_FROZEN 0
-
-static struct notifier_err_inject cpu_notifier_err_inject = {
-	.actions = {
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE_FROZEN) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE_FROZEN) },
-		{}
-	}
-};
-
-static int notf_err_handle(struct notifier_err_inject_action *action)
-{
-	int ret;
-
-	ret = action->error;
-	if (ret)
-		pr_info("Injecting error (%d) to %s\n", ret, action->name);
-	return ret;
-}
-
-static int notf_err_inj_up_prepare(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[0]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[1]);
-}
-
-static int notf_err_inj_dead(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[2]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[3]);
-}
-
-static struct dentry *dir;
-
-static int err_inject_init(void)
-{
-	int err;
-
-	dir = notifier_err_inject_init("cpu", notifier_err_inject_dir,
-					&cpu_notifier_err_inject, priority);
-	if (IS_ERR(dir))
-		return PTR_ERR(dir);
-
-	err = cpuhp_setup_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE,
-					"cpu-err-notif:prepare",
-					notf_err_inj_up_prepare,
-					notf_err_inj_dead);
-	if (err)
-		debugfs_remove_recursive(dir);
-
-	return err;
-}
-
-static void err_inject_exit(void)
-{
-	cpuhp_remove_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE);
-	debugfs_remove_recursive(dir);
-}
-
-module_init(err_inject_init);
-module_exit(err_inject_exit);
-
-MODULE_DESCRIPTION("CPU notifier error injection module");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");

[tip:smp/urgent] cpu/hotplug: Remove obsolete cpu hotplug register/unregister functions

[tip-bot for Thomas Gleixner]

Commit-ID:  8e38db753d952410bb0928da921885900184391b
Gitweb:     http://git.kernel.org/tip/8e38db753d952410bb0928da921885900184391b
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:53 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:55 +0100

cpu/hotplug: Remove obsolete cpu hotplug register/unregister functions

hotcpu_notifier(), cpu_notifier(), __hotcpu_notifier(), __cpu_notifier(),
register_hotcpu_notifier(), register_cpu_notifier(),
__register_hotcpu_notifier(), __register_cpu_notifier(),
unregister_hotcpu_notifier(), unregister_cpu_notifier(),
__unregister_hotcpu_notifier(), __unregister_cpu_notifier()

are unused now. Remove them and all related code.

Remove also the now pointless cpu notifier error injection mechanism. The
states can be executed step by step and error rollback is the same as cpu
down, so any state transition can be tested w/o requiring the notifier
error injection.

Some CPU hotplug states are kept as they are (ab)used for hotplug state
tracking.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20161221192112.005642358@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/cpu.h             |  90 --------------------------
 include/linux/cpuhotplug.h      |   3 -
 kernel/cpu.c                    | 139 +---------------------------------------
 lib/Kconfig.debug               |  24 -------
 lib/Makefile                    |   1 -
 lib/cpu-notifier-error-inject.c |  84 ------------------------
 6 files changed, 1 insertion(+), 340 deletions(-)

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 09807c2..21f9c74 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -57,9 +57,6 @@ struct notifier_block;
 
 #define CPU_ONLINE		0x0002 /* CPU (unsigned)v is up */
 #define CPU_UP_PREPARE		0x0003 /* CPU (unsigned)v coming up */
-#define CPU_UP_CANCELED		0x0004 /* CPU (unsigned)v NOT coming up */
-#define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
-#define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
 #define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
 					* lock is dropped */
@@ -80,80 +77,14 @@ struct notifier_block;
 
 #ifdef CONFIG_SMP
 extern bool cpuhp_tasks_frozen;
-/* Need to know about CPUs going up/down? */
-#if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
-#define cpu_notifier(fn, pri) {					\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	register_cpu_notifier(&fn##_nb);			\
-}
-
-#define __cpu_notifier(fn, pri) {				\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	__register_cpu_notifier(&fn##_nb);			\
-}
-
-extern int register_cpu_notifier(struct notifier_block *nb);
-extern int __register_cpu_notifier(struct notifier_block *nb);
-extern void unregister_cpu_notifier(struct notifier_block *nb);
-extern void __unregister_cpu_notifier(struct notifier_block *nb);
-
-#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-#endif
-
 int cpu_up(unsigned int cpu);
 void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 
-#define cpu_notifier_register_begin	cpu_maps_update_begin
-#define cpu_notifier_register_done	cpu_maps_update_done
-
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
 
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
 static inline void cpu_maps_update_begin(void)
 {
 }
@@ -162,14 +93,6 @@ static inline void cpu_maps_update_done(void)
 {
 }
 
-static inline void cpu_notifier_register_begin(void)
-{
-}
-
-static inline void cpu_notifier_register_done(void)
-{
-}
-
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -182,12 +105,6 @@ extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
-#define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
-#define __hotcpu_notifier(fn, pri)	__cpu_notifier(fn, pri)
-#define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
-#define __register_hotcpu_notifier(nb)	__register_cpu_notifier(nb)
-#define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
-#define __unregister_hotcpu_notifier(nb)	__unregister_cpu_notifier(nb)
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
@@ -199,13 +116,6 @@ static inline void cpu_hotplug_done(void) {}
 #define put_online_cpus()	do { } while (0)
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
-#define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-/* These aren't inline functions due to a GCC bug. */
-#define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define __register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define unregister_hotcpu_notifier(nb)	({ (void)(nb); })
-#define __unregister_hotcpu_notifier(nb)	({ (void)(nb); })
 #endif		/* CONFIG_HOTPLUG_CPU */
 
 #ifdef CONFIG_PM_SLEEP_SMP
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 175d276..0d5ef85 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -59,7 +59,6 @@ enum cpuhp_state {
 	CPUHP_POWERPC_MMU_CTX_PREPARE,
 	CPUHP_XEN_PREPARE,
 	CPUHP_XEN_EVTCHN_PREPARE,
-	CPUHP_NOTIFY_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
 	CPUHP_BLK_MQ_PREPARE,
@@ -74,7 +73,6 @@ enum cpuhp_state {
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_DEAD,
-	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BRINGUP_CPU,
 	CPUHP_AP_IDLE_DEAD,
@@ -145,7 +143,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_ARM_L2X0_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
-	CPUHP_AP_NOTIFY_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
 	CPUHP_AP_X86_HPET_ONLINE,
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 3ff0ea5..042fd7e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -183,23 +183,16 @@ EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
 /*
  * The following two APIs (cpu_maps_update_begin/done) must be used when
  * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
- * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
- * hotplug callback (un)registration performed using __register_cpu_notifier()
- * or __unregister_cpu_notifier().
  */
 void cpu_maps_update_begin(void)
 {
 	mutex_lock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_begin);
 
 void cpu_maps_update_done(void)
 {
 	mutex_unlock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_done);
-
-static RAW_NOTIFIER_HEAD(cpu_chain);
 
 /* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
  * Should always be manipulated under cpu_add_remove_lock
@@ -349,66 +342,7 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-/* Need to know about CPUs going up/down? */
-int register_cpu_notifier(struct notifier_block *nb)
-{
-	int ret;
-	cpu_maps_update_begin();
-	ret = raw_notifier_chain_register(&cpu_chain, nb);
-	cpu_maps_update_done();
-	return ret;
-}
-
-int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return raw_notifier_chain_register(&cpu_chain, nb);
-}
-
-static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
-			int *nr_calls)
-{
-	unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
-	void *hcpu = (void *)(long)cpu;
-
-	int ret;
-
-	ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
-					nr_calls);
-
-	return notifier_to_errno(ret);
-}
-
-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)
-{
-	int nr_calls = 0;
-	int ret;
-
-	ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
-	if (ret) {
-		nr_calls--;
-		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
-				__func__, cpu);
-		__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
-	}
-	return ret;
-}
-
-static int notify_online(unsigned int cpu)
-{
-	cpu_notify(CPU_ONLINE, cpu);
-	return 0;
-}
 
 static int bringup_wait_for_ap(unsigned int cpu)
 {
@@ -433,10 +367,8 @@ static int bringup_cpu(unsigned int cpu)
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
 	irq_unlock_sparse();
-	if (ret) {
-		cpu_notify(CPU_UP_CANCELED, cpu);
+	if (ret)
 		return ret;
-	}
 	ret = bringup_wait_for_ap(cpu);
 	BUG_ON(!cpu_online(cpu));
 	return ret;
@@ -565,11 +497,6 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
 
 		undo_cpu_down(cpu, st);
-		/*
-		 * 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 .... */
@@ -659,22 +586,6 @@ void __init cpuhp_threads_init(void)
 	kthread_unpark(this_cpu_read(cpuhp_state.thread));
 }
 
-EXPORT_SYMBOL(register_cpu_notifier);
-EXPORT_SYMBOL(__register_cpu_notifier);
-void unregister_cpu_notifier(struct notifier_block *nb)
-{
-	cpu_maps_update_begin();
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-	cpu_maps_update_done();
-}
-EXPORT_SYMBOL(unregister_cpu_notifier);
-
-void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-}
-EXPORT_SYMBOL(__unregister_cpu_notifier);
-
 #ifdef CONFIG_HOTPLUG_CPU
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
@@ -741,20 +652,6 @@ static inline void check_for_tasks(int dead_cpu)
 	read_unlock(&tasklist_lock);
 }
 
-static int notify_down_prepare(unsigned int cpu)
-{
-	int err, nr_calls = 0;
-
-	err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
-	if (err) {
-		nr_calls--;
-		__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
-		pr_warn("%s: attempt to take down CPU %u failed\n",
-				__func__, cpu);
-	}
-	return err;
-}
-
 /* Take this CPU down. */
 static int take_cpu_down(void *_param)
 {
@@ -833,13 +730,6 @@ static int takedown_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int notify_dead(unsigned int cpu)
-{
-	cpu_notify_nofail(CPU_DEAD, cpu);
-	check_for_tasks(cpu);
-	return 0;
-}
-
 static void cpuhp_complete_idle_dead(void *arg)
 {
 	struct cpuhp_cpu_state *st = arg;
@@ -863,9 +753,7 @@ void cpuhp_report_idle_dead(void)
 }
 
 #else
-#define notify_down_prepare	NULL
 #define takedown_cpu		NULL
-#define notify_dead		NULL
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -924,9 +812,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
 out:
 	cpu_hotplug_done();
-	/* This post dead nonsense must die */
-	if (!ret && hasdied)
-		cpu_notify_nofail(CPU_POST_DEAD, cpu);
 	return ret;
 }
 
@@ -1292,17 +1177,6 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 		.teardown.single	= rcutree_dead_cpu,
 	},
 	/*
-	 * Preparatory and dead notifiers. Will be replaced once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_NOTIFY_PREPARE] = {
-		.name			= "notify:prepare",
-		.startup.single		= notify_prepare,
-		.teardown.single	= notify_dead,
-		.skip_onerr		= true,
-		.cant_stop		= true,
-	},
-	/*
 	 * On the tear-down path, timers_dead_cpu() must be invoked
 	 * before blk_mq_queue_reinit_notify() from notify_dead(),
 	 * otherwise a RCU stall occurs.
@@ -1391,17 +1265,6 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.startup.single		= rcutree_online_cpu,
 		.teardown.single	= rcutree_offline_cpu,
 	},
-
-	/*
-	 * Online/down_prepare notifiers. Will be removed once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_AP_NOTIFY_ONLINE] = {
-		.name			= "notify:online",
-		.startup.single		= notify_online,
-		.teardown.single	= notify_down_prepare,
-		.skip_onerr		= true,
-	},
 #endif
 	/*
 	 * The dynamically registered state space is here
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7446097..a403a5a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1538,30 +1538,6 @@ config NOTIFIER_ERROR_INJECTION
 
 	  Say N if unsure.
 
-config CPU_NOTIFIER_ERROR_INJECT
-	tristate "CPU notifier error injection module"
-	depends on HOTPLUG_CPU && NOTIFIER_ERROR_INJECTION
-	help
-	  This option provides a kernel module that can be used to test
-	  the error handling of the cpu notifiers by injecting artificial
-	  errors to CPU notifier chain callbacks.  It is controlled through
-	  debugfs interface under /sys/kernel/debug/notifier-error-inject/cpu
-
-	  If the notifier call chain should be failed with some events
-	  notified, write the error code to "actions/<notifier event>/error".
-
-	  Example: Inject CPU offline error (-1 == -EPERM)
-
-	  # cd /sys/kernel/debug/notifier-error-inject/cpu
-	  # echo -1 > actions/CPU_DOWN_PREPARE/error
-	  # echo 0 > /sys/devices/system/cpu/cpu1/online
-	  bash: echo: write error: Operation not permitted
-
-	  To compile this code as a module, choose M here: the module will
-	  be called cpu-notifier-error-inject.
-
-	  If unsure, say N.
-
 config PM_NOTIFIER_ERROR_INJECT
 	tristate "PM notifier error injection module"
 	depends on PM && NOTIFIER_ERROR_INJECTION
diff --git a/lib/Makefile b/lib/Makefile
index 50144a3..bc4073a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -128,7 +128,6 @@ obj-$(CONFIG_SWIOTLB) += swiotlb.o
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
-obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o
 obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
 obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
 obj-$(CONFIG_MEMORY_NOTIFIER_ERROR_INJECT) += memory-notifier-error-inject.o
diff --git a/lib/cpu-notifier-error-inject.c b/lib/cpu-notifier-error-inject.c
deleted file mode 100644
index 0e2c9a1..0000000
--- a/lib/cpu-notifier-error-inject.c
+++ /dev/null
@@ -1,84 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-
-#include "notifier-error-inject.h"
-
-static int priority;
-module_param(priority, int, 0);
-MODULE_PARM_DESC(priority, "specify cpu notifier priority");
-
-#define UP_PREPARE 0
-#define UP_PREPARE_FROZEN 0
-#define DOWN_PREPARE 0
-#define DOWN_PREPARE_FROZEN 0
-
-static struct notifier_err_inject cpu_notifier_err_inject = {
-	.actions = {
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE_FROZEN) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE_FROZEN) },
-		{}
-	}
-};
-
-static int notf_err_handle(struct notifier_err_inject_action *action)
-{
-	int ret;
-
-	ret = action->error;
-	if (ret)
-		pr_info("Injecting error (%d) to %s\n", ret, action->name);
-	return ret;
-}
-
-static int notf_err_inj_up_prepare(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[0]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[1]);
-}
-
-static int notf_err_inj_dead(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[2]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[3]);
-}
-
-static struct dentry *dir;
-
-static int err_inject_init(void)
-{
-	int err;
-
-	dir = notifier_err_inject_init("cpu", notifier_err_inject_dir,
-					&cpu_notifier_err_inject, priority);
-	if (IS_ERR(dir))
-		return PTR_ERR(dir);
-
-	err = cpuhp_setup_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE,
-					"cpu-err-notif:prepare",
-					notf_err_inj_up_prepare,
-					notf_err_inj_dead);
-	if (err)
-		debugfs_remove_recursive(dir);
-
-	return err;
-}
-
-static void err_inject_exit(void)
-{
-	cpuhp_remove_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE);
-	debugfs_remove_recursive(dir);
-}
-
-module_init(err_inject_init);
-module_exit(err_inject_exit);
-
-MODULE_DESCRIPTION("CPU notifier error injection module");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");

[tip:smp/urgent] cpu/hotplug: Remove obsolete cpu hotplug register/unregister functions

[tip-bot for Thomas Gleixner]

Commit-ID:  530e9b76ae8f863dfdef4a6ad0b38613d32e8c3f
Gitweb:     http://git.kernel.org/tip/530e9b76ae8f863dfdef4a6ad0b38613d32e8c3f
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:53 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:43 +0100

cpu/hotplug: Remove obsolete cpu hotplug register/unregister functions

hotcpu_notifier(), cpu_notifier(), __hotcpu_notifier(), __cpu_notifier(),
register_hotcpu_notifier(), register_cpu_notifier(),
__register_hotcpu_notifier(), __register_cpu_notifier(),
unregister_hotcpu_notifier(), unregister_cpu_notifier(),
__unregister_hotcpu_notifier(), __unregister_cpu_notifier()

are unused now. Remove them and all related code.

Remove also the now pointless cpu notifier error injection mechanism. The
states can be executed step by step and error rollback is the same as cpu
down, so any state transition can be tested w/o requiring the notifier
error injection.

Some CPU hotplug states are kept as they are (ab)used for hotplug state
tracking.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20161221192112.005642358@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 include/linux/cpu.h             |  90 --------------------------
 include/linux/cpuhotplug.h      |   3 -
 kernel/cpu.c                    | 139 +---------------------------------------
 lib/Kconfig.debug               |  24 -------
 lib/Makefile                    |   1 -
 lib/cpu-notifier-error-inject.c |  84 ------------------------
 6 files changed, 1 insertion(+), 340 deletions(-)

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 09807c2..21f9c74 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -57,9 +57,6 @@ struct notifier_block;
 
 #define CPU_ONLINE		0x0002 /* CPU (unsigned)v is up */
 #define CPU_UP_PREPARE		0x0003 /* CPU (unsigned)v coming up */
-#define CPU_UP_CANCELED		0x0004 /* CPU (unsigned)v NOT coming up */
-#define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
-#define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
 #define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
 					* lock is dropped */
@@ -80,80 +77,14 @@ struct notifier_block;
 
 #ifdef CONFIG_SMP
 extern bool cpuhp_tasks_frozen;
-/* Need to know about CPUs going up/down? */
-#if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
-#define cpu_notifier(fn, pri) {					\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	register_cpu_notifier(&fn##_nb);			\
-}
-
-#define __cpu_notifier(fn, pri) {				\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	__register_cpu_notifier(&fn##_nb);			\
-}
-
-extern int register_cpu_notifier(struct notifier_block *nb);
-extern int __register_cpu_notifier(struct notifier_block *nb);
-extern void unregister_cpu_notifier(struct notifier_block *nb);
-extern void __unregister_cpu_notifier(struct notifier_block *nb);
-
-#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-#endif
-
 int cpu_up(unsigned int cpu);
 void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 
-#define cpu_notifier_register_begin	cpu_maps_update_begin
-#define cpu_notifier_register_done	cpu_maps_update_done
-
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
 
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
 static inline void cpu_maps_update_begin(void)
 {
 }
@@ -162,14 +93,6 @@ static inline void cpu_maps_update_done(void)
 {
 }
 
-static inline void cpu_notifier_register_begin(void)
-{
-}
-
-static inline void cpu_notifier_register_done(void)
-{
-}
-
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -182,12 +105,6 @@ extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
-#define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
-#define __hotcpu_notifier(fn, pri)	__cpu_notifier(fn, pri)
-#define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
-#define __register_hotcpu_notifier(nb)	__register_cpu_notifier(nb)
-#define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
-#define __unregister_hotcpu_notifier(nb)	__unregister_cpu_notifier(nb)
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
@@ -199,13 +116,6 @@ static inline void cpu_hotplug_done(void) {}
 #define put_online_cpus()	do { } while (0)
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
-#define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-/* These aren't inline functions due to a GCC bug. */
-#define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define __register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define unregister_hotcpu_notifier(nb)	({ (void)(nb); })
-#define __unregister_hotcpu_notifier(nb)	({ (void)(nb); })
 #endif		/* CONFIG_HOTPLUG_CPU */
 
 #ifdef CONFIG_PM_SLEEP_SMP
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 175d276..0d5ef85 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -59,7 +59,6 @@ enum cpuhp_state {
 	CPUHP_POWERPC_MMU_CTX_PREPARE,
 	CPUHP_XEN_PREPARE,
 	CPUHP_XEN_EVTCHN_PREPARE,
-	CPUHP_NOTIFY_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
 	CPUHP_BLK_MQ_PREPARE,
@@ -74,7 +73,6 @@ enum cpuhp_state {
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_DEAD,
-	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BRINGUP_CPU,
 	CPUHP_AP_IDLE_DEAD,
@@ -145,7 +143,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_ARM_L2X0_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
-	CPUHP_AP_NOTIFY_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
 	CPUHP_AP_X86_HPET_ONLINE,
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 3ff0ea5..042fd7e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -183,23 +183,16 @@ EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
 /*
  * The following two APIs (cpu_maps_update_begin/done) must be used when
  * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
- * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
- * hotplug callback (un)registration performed using __register_cpu_notifier()
- * or __unregister_cpu_notifier().
  */
 void cpu_maps_update_begin(void)
 {
 	mutex_lock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_begin);
 
 void cpu_maps_update_done(void)
 {
 	mutex_unlock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_done);
-
-static RAW_NOTIFIER_HEAD(cpu_chain);
 
 /* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
  * Should always be manipulated under cpu_add_remove_lock
@@ -349,66 +342,7 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-/* Need to know about CPUs going up/down? */
-int register_cpu_notifier(struct notifier_block *nb)
-{
-	int ret;
-	cpu_maps_update_begin();
-	ret = raw_notifier_chain_register(&cpu_chain, nb);
-	cpu_maps_update_done();
-	return ret;
-}
-
-int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return raw_notifier_chain_register(&cpu_chain, nb);
-}
-
-static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
-			int *nr_calls)
-{
-	unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
-	void *hcpu = (void *)(long)cpu;
-
-	int ret;
-
-	ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
-					nr_calls);
-
-	return notifier_to_errno(ret);
-}
-
-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)
-{
-	int nr_calls = 0;
-	int ret;
-
-	ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
-	if (ret) {
-		nr_calls--;
-		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
-				__func__, cpu);
-		__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
-	}
-	return ret;
-}
-
-static int notify_online(unsigned int cpu)
-{
-	cpu_notify(CPU_ONLINE, cpu);
-	return 0;
-}
 
 static int bringup_wait_for_ap(unsigned int cpu)
 {
@@ -433,10 +367,8 @@ static int bringup_cpu(unsigned int cpu)
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
 	irq_unlock_sparse();
-	if (ret) {
-		cpu_notify(CPU_UP_CANCELED, cpu);
+	if (ret)
 		return ret;
-	}
 	ret = bringup_wait_for_ap(cpu);
 	BUG_ON(!cpu_online(cpu));
 	return ret;
@@ -565,11 +497,6 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
 
 		undo_cpu_down(cpu, st);
-		/*
-		 * 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 .... */
@@ -659,22 +586,6 @@ void __init cpuhp_threads_init(void)
 	kthread_unpark(this_cpu_read(cpuhp_state.thread));
 }
 
-EXPORT_SYMBOL(register_cpu_notifier);
-EXPORT_SYMBOL(__register_cpu_notifier);
-void unregister_cpu_notifier(struct notifier_block *nb)
-{
-	cpu_maps_update_begin();
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-	cpu_maps_update_done();
-}
-EXPORT_SYMBOL(unregister_cpu_notifier);
-
-void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-}
-EXPORT_SYMBOL(__unregister_cpu_notifier);
-
 #ifdef CONFIG_HOTPLUG_CPU
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
@@ -741,20 +652,6 @@ static inline void check_for_tasks(int dead_cpu)
 	read_unlock(&tasklist_lock);
 }
 
-static int notify_down_prepare(unsigned int cpu)
-{
-	int err, nr_calls = 0;
-
-	err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
-	if (err) {
-		nr_calls--;
-		__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
-		pr_warn("%s: attempt to take down CPU %u failed\n",
-				__func__, cpu);
-	}
-	return err;
-}
-
 /* Take this CPU down. */
 static int take_cpu_down(void *_param)
 {
@@ -833,13 +730,6 @@ static int takedown_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int notify_dead(unsigned int cpu)
-{
-	cpu_notify_nofail(CPU_DEAD, cpu);
-	check_for_tasks(cpu);
-	return 0;
-}
-
 static void cpuhp_complete_idle_dead(void *arg)
 {
 	struct cpuhp_cpu_state *st = arg;
@@ -863,9 +753,7 @@ void cpuhp_report_idle_dead(void)
 }
 
 #else
-#define notify_down_prepare	NULL
 #define takedown_cpu		NULL
-#define notify_dead		NULL
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -924,9 +812,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
 out:
 	cpu_hotplug_done();
-	/* This post dead nonsense must die */
-	if (!ret && hasdied)
-		cpu_notify_nofail(CPU_POST_DEAD, cpu);
 	return ret;
 }
 
@@ -1292,17 +1177,6 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 		.teardown.single	= rcutree_dead_cpu,
 	},
 	/*
-	 * Preparatory and dead notifiers. Will be replaced once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_NOTIFY_PREPARE] = {
-		.name			= "notify:prepare",
-		.startup.single		= notify_prepare,
-		.teardown.single	= notify_dead,
-		.skip_onerr		= true,
-		.cant_stop		= true,
-	},
-	/*
 	 * On the tear-down path, timers_dead_cpu() must be invoked
 	 * before blk_mq_queue_reinit_notify() from notify_dead(),
 	 * otherwise a RCU stall occurs.
@@ -1391,17 +1265,6 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.startup.single		= rcutree_online_cpu,
 		.teardown.single	= rcutree_offline_cpu,
 	},
-
-	/*
-	 * Online/down_prepare notifiers. Will be removed once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_AP_NOTIFY_ONLINE] = {
-		.name			= "notify:online",
-		.startup.single		= notify_online,
-		.teardown.single	= notify_down_prepare,
-		.skip_onerr		= true,
-	},
 #endif
 	/*
 	 * The dynamically registered state space is here
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index cb66a46..b06848a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1538,30 +1538,6 @@ config NOTIFIER_ERROR_INJECTION
 
 	  Say N if unsure.
 
-config CPU_NOTIFIER_ERROR_INJECT
-	tristate "CPU notifier error injection module"
-	depends on HOTPLUG_CPU && NOTIFIER_ERROR_INJECTION
-	help
-	  This option provides a kernel module that can be used to test
-	  the error handling of the cpu notifiers by injecting artificial
-	  errors to CPU notifier chain callbacks.  It is controlled through
-	  debugfs interface under /sys/kernel/debug/notifier-error-inject/cpu
-
-	  If the notifier call chain should be failed with some events
-	  notified, write the error code to "actions/<notifier event>/error".
-
-	  Example: Inject CPU offline error (-1 == -EPERM)
-
-	  # cd /sys/kernel/debug/notifier-error-inject/cpu
-	  # echo -1 > actions/CPU_DOWN_PREPARE/error
-	  # echo 0 > /sys/devices/system/cpu/cpu1/online
-	  bash: echo: write error: Operation not permitted
-
-	  To compile this code as a module, choose M here: the module will
-	  be called cpu-notifier-error-inject.
-
-	  If unsure, say N.
-
 config PM_NOTIFIER_ERROR_INJECT
 	tristate "PM notifier error injection module"
 	depends on PM && NOTIFIER_ERROR_INJECTION
diff --git a/lib/Makefile b/lib/Makefile
index 50144a3..bc4073a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -128,7 +128,6 @@ obj-$(CONFIG_SWIOTLB) += swiotlb.o
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
-obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o
 obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
 obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
 obj-$(CONFIG_MEMORY_NOTIFIER_ERROR_INJECT) += memory-notifier-error-inject.o
diff --git a/lib/cpu-notifier-error-inject.c b/lib/cpu-notifier-error-inject.c
deleted file mode 100644
index 0e2c9a1..0000000
--- a/lib/cpu-notifier-error-inject.c
+++ /dev/null
@@ -1,84 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-
-#include "notifier-error-inject.h"
-
-static int priority;
-module_param(priority, int, 0);
-MODULE_PARM_DESC(priority, "specify cpu notifier priority");
-
-#define UP_PREPARE 0
-#define UP_PREPARE_FROZEN 0
-#define DOWN_PREPARE 0
-#define DOWN_PREPARE_FROZEN 0
-
-static struct notifier_err_inject cpu_notifier_err_inject = {
-	.actions = {
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE_FROZEN) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE_FROZEN) },
-		{}
-	}
-};
-
-static int notf_err_handle(struct notifier_err_inject_action *action)
-{
-	int ret;
-
-	ret = action->error;
-	if (ret)
-		pr_info("Injecting error (%d) to %s\n", ret, action->name);
-	return ret;
-}
-
-static int notf_err_inj_up_prepare(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[0]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[1]);
-}
-
-static int notf_err_inj_dead(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[2]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[3]);
-}
-
-static struct dentry *dir;
-
-static int err_inject_init(void)
-{
-	int err;
-
-	dir = notifier_err_inject_init("cpu", notifier_err_inject_dir,
-					&cpu_notifier_err_inject, priority);
-	if (IS_ERR(dir))
-		return PTR_ERR(dir);
-
-	err = cpuhp_setup_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE,
-					"cpu-err-notif:prepare",
-					notf_err_inj_up_prepare,
-					notf_err_inj_dead);
-	if (err)
-		debugfs_remove_recursive(dir);
-
-	return err;
-}
-
-static void err_inject_exit(void)
-{
-	cpuhp_remove_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE);
-	debugfs_remove_recursive(dir);
-}
-
-module_init(err_inject_init);
-module_exit(err_inject_exit);
-
-MODULE_DESCRIPTION("CPU notifier error injection module");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");

[patch 07/10] cpu/hotplug: Cleanup state names

[Thomas Gleixner]

[-- Attachment #1: cpu-hotplug--Cleanup-state-names.patch --]
[-- Type: text/plain, Size: 30644 bytes --]

When the state names got added a script was used to add the extra argument
to the calls. The script basically converted the state constant to a
string, but the cleanup to convert these strings into meaningful ones did
not happen.

Replace all the useless strings with 'subsys/xxx/yyy:state' strings which
are used in all the other places already.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
---
 arch/arm/kernel/smp_twd.c                     |    2 +-
 arch/arm/mach-mvebu/coherency.c               |    2 +-
 arch/arm/mm/cache-l2x0-pmu.c                  |    2 +-
 arch/arm/mm/cache-l2x0.c                      |    2 +-
 arch/arm/vfp/vfpmodule.c                      |    2 +-
 arch/arm/xen/enlighten.c                      |    2 +-
 arch/arm64/kernel/armv8_deprecated.c          |    2 +-
 arch/arm64/kernel/debug-monitors.c            |    2 +-
 arch/arm64/kernel/hw_breakpoint.c             |    2 +-
 arch/blackfin/kernel/perf_event.c             |    2 +-
 arch/metag/kernel/perf/perf_event.c           |    2 +-
 arch/mips/kernel/pm-cps.c                     |    2 +-
 arch/mips/oprofile/op_model_loongson3.c       |    2 +-
 arch/powerpc/mm/numa.c                        |    2 +-
 arch/powerpc/perf/core-book3s.c               |    2 +-
 arch/s390/kernel/perf_cpum_cf.c               |    2 +-
 arch/s390/kernel/perf_cpum_sf.c               |    2 +-
 arch/x86/entry/vdso/vma.c                     |    2 +-
 arch/x86/events/amd/ibs.c                     |    2 +-
 arch/x86/events/amd/power.c                   |    2 +-
 arch/x86/events/amd/uncore.c                  |    6 +++---
 arch/x86/events/core.c                        |    6 +++---
 arch/x86/events/intel/cqm.c                   |    4 ++--
 arch/x86/events/intel/cstate.c                |    5 ++---
 arch/x86/events/intel/rapl.c                  |    4 ++--
 arch/x86/events/intel/uncore.c                |   10 +++++-----
 arch/x86/kernel/apb_timer.c                   |    2 +-
 arch/x86/kernel/apic/x2apic_cluster.c         |    2 +-
 arch/x86/kernel/hpet.c                        |    4 ++--
 arch/x86/kernel/tboot.c                       |    2 +-
 arch/x86/kvm/x86.c                            |    2 +-
 arch/x86/xen/enlighten.c                      |    4 ++--
 arch/xtensa/kernel/perf_event.c               |    2 +-
 drivers/bus/arm-cci.c                         |    2 +-
 drivers/bus/arm-ccn.c                         |    2 +-
 drivers/clocksource/arc_timer.c               |    2 +-
 drivers/clocksource/arm_arch_timer.c          |    2 +-
 drivers/clocksource/arm_global_timer.c        |    2 +-
 drivers/clocksource/dummy_timer.c             |    2 +-
 drivers/clocksource/exynos_mct.c              |    2 +-
 drivers/clocksource/jcore-pit.c               |    2 +-
 drivers/clocksource/metag_generic.c           |    2 +-
 drivers/clocksource/mips-gic-timer.c          |    4 ++--
 drivers/clocksource/qcom-timer.c              |    2 +-
 drivers/clocksource/time-armada-370-xp.c      |    2 +-
 drivers/clocksource/timer-atlas7.c            |    2 +-
 drivers/hwtracing/coresight/coresight-etm3x.c |    4 ++--
 drivers/hwtracing/coresight/coresight-etm4x.c |    4 ++--
 drivers/irqchip/irq-armada-370-xp.c           |    4 ++--
 drivers/irqchip/irq-bcm2836.c                 |    2 +-
 drivers/irqchip/irq-gic-v3.c                  |    4 ++--
 drivers/irqchip/irq-gic.c                     |    2 +-
 drivers/irqchip/irq-hip04.c                   |    2 +-
 drivers/leds/trigger/ledtrig-cpu.c            |    2 +-
 drivers/net/virtio_net.c                      |    4 ++--
 drivers/perf/arm_pmu.c                        |    2 +-
 drivers/xen/events/events_fifo.c              |    2 +-
 virt/kvm/arm/arch_timer.c                     |    2 +-
 virt/kvm/arm/vgic/vgic-init.c                 |    2 +-
 virt/kvm/kvm_main.c                           |    2 +-
 60 files changed, 79 insertions(+), 80 deletions(-)

--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -339,7 +339,7 @@ static int __init twd_local_timer_common
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_TWD_STARTING,
-				  "AP_ARM_TWD_STARTING",
+				  "arm/timer/twd:starting",
 				  twd_timer_starting_cpu, twd_timer_dying_cpu);
 
 	twd_get_clock(np);
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -148,7 +148,7 @@ static void __init armada_370_coherency_
 	of_node_put(cpu_config_np);
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_MVEBU_COHERENCY,
-				  "AP_ARM_MVEBU_COHERENCY",
+				  "arm/mvebu/coherency:starting",
 				  armada_xp_clear_l2_starting, NULL);
 exit:
 	set_cpu_coherent();
--- a/arch/arm/mm/cache-l2x0-pmu.c
+++ b/arch/arm/mm/cache-l2x0-pmu.c
@@ -563,7 +563,7 @@ static __init int l2x0_pmu_init(void)
 
 	cpumask_set_cpu(0, &pmu_cpu);
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE,
-					"AP_PERF_ARM_L2X0_ONLINE", NULL,
+					"perf/arm/l2x0:online", NULL,
 					l2x0_pmu_offline_cpu);
 	if (ret)
 		goto out_pmu;
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -683,7 +683,7 @@ static void __init l2c310_enable(void __
 
 	if (aux & L310_AUX_CTRL_FULL_LINE_ZERO)
 		cpuhp_setup_state(CPUHP_AP_ARM_L2X0_STARTING,
-				  "AP_ARM_L2X0_STARTING", l2c310_starting_cpu,
+				  "arm/l2x0:starting", l2c310_starting_cpu,
 				  l2c310_dying_cpu);
 }
 
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -799,7 +799,7 @@ static int __init vfp_init(void)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_VFP_STARTING,
-				  "AP_ARM_VFP_STARTING", vfp_starting_cpu,
+				  "arm/vfp:starting", vfp_starting_cpu,
 				  vfp_dying_cpu);
 
 	vfp_vector = vfp_support_entry;
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -412,7 +412,7 @@ static int __init xen_guest_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 
 	return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
-				 "AP_ARM_XEN_STARTING", xen_starting_cpu,
+				 "arm/xen:starting", xen_starting_cpu,
 				 xen_dying_cpu);
 }
 early_initcall(xen_guest_init);
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -640,7 +640,7 @@ static int __init armv8_deprecated_init(
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
-				  "AP_ARM64_ISNDEP_STARTING",
+				  "arm64/isndep:starting",
 				  run_all_insn_set_hw_mode, NULL);
 	register_insn_emulation_sysctl(ctl_abi);
 
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -140,7 +140,7 @@ static int clear_os_lock(unsigned int cp
 static int debug_monitors_init(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
-				 "CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING",
+				 "arm64/debug_monitors:starting",
 				 clear_os_lock, NULL);
 }
 postcore_initcall(debug_monitors_init);
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -1001,7 +1001,7 @@ static int __init arch_hw_breakpoint_ini
 	 * debugger will leave the world in a nice state for us.
 	 */
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
-			  "CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING",
+			  "perf/arm64/hw_breakpoint:starting",
 			  hw_breakpoint_reset, NULL);
 	if (ret)
 		pr_err("failed to register CPU hotplug notifier: %d\n", ret);
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -475,7 +475,7 @@ static int __init bfin_pmu_init(void)
 
 	ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	if (!ret)
-		cpuhp_setup_state(CPUHP_PERF_BFIN, "PERF_BFIN",
+		cpuhp_setup_state(CPUHP_PERF_BFIN,"perf/bfin:starting",
 				  bfin_pmu_prepare_cpu, NULL);
 	return ret;
 }
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -868,7 +868,7 @@ static int __init init_hw_perf_events(vo
 	metag_out32(0, PERF_COUNT(1));
 
 	cpuhp_setup_state(CPUHP_AP_PERF_METAG_STARTING,
-			  "AP_PERF_METAG_STARTING", metag_pmu_starting_cpu,
+			  "perf/metag:starting", metag_pmu_starting_cpu,
 			  NULL);
 
 	ret = perf_pmu_register(&pmu, metag_pmu->name, PERF_TYPE_RAW);
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -713,7 +713,7 @@ static int __init cps_pm_init(void)
 		pr_warn("pm-cps: no CPC, clock & power gating unavailable\n");
 	}
 
-	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PM_CPS_CPU_ONLINE",
+	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mips/cps_pm:online",
 				 cps_pm_online_cpu, NULL);
 }
 arch_initcall(cps_pm_init);
--- a/arch/mips/oprofile/op_model_loongson3.c
+++ b/arch/mips/oprofile/op_model_loongson3.c
@@ -186,7 +186,7 @@ static int __init loongson3_init(void)
 {
 	on_each_cpu(reset_counters, NULL, 1);
 	cpuhp_setup_state_nocalls(CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
-				  "AP_MIPS_OP_LOONGSON3_STARTING",
+				  "mips/oprofile/loongson3:starting",
 				  loongson3_starting_cpu, loongson3_dying_cpu);
 	save_perf_irq = perf_irq;
 	perf_irq = loongson3_perfcount_handler;
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -944,7 +944,7 @@ void __init initmem_init(void)
 	 * _nocalls() + manual invocation is used because cpuhp is not yet
 	 * initialized for the boot CPU.
 	 */
-	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "POWER_NUMA_PREPARE",
+	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "powerpc/numa:prepare",
 				  ppc_numa_cpu_prepare, ppc_numa_cpu_dead);
 	for_each_present_cpu(cpu)
 		numa_setup_cpu(cpu);
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2189,7 +2189,7 @@ int register_power_pmu(struct power_pmu
 #endif /* CONFIG_PPC64 */
 
 	perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW);
-	cpuhp_setup_state(CPUHP_PERF_POWER, "PERF_POWER",
+	cpuhp_setup_state(CPUHP_PERF_POWER, "perf/powerpc:prepare",
 			  power_pmu_prepare_cpu, NULL);
 	return 0;
 }
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -711,7 +711,7 @@ static int __init cpumf_pmu_init(void)
 		return rc;
 	}
 	return cpuhp_setup_state(CPUHP_AP_PERF_S390_CF_ONLINE,
-				 "AP_PERF_S390_CF_ONLINE",
+				 "perf/s390/cf:online",
 				 s390_pmu_online_cpu, s390_pmu_offline_cpu);
 }
 early_initcall(cpumf_pmu_init);
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1623,7 +1623,7 @@ static int __init init_cpum_sampling_pmu
 		goto out;
 	}
 
-	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "AP_PERF_S390_SF_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "perf/s390/sf:online",
 			  s390_pmu_sf_online_cpu, s390_pmu_sf_offline_cpu);
 out:
 	return err;
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -371,7 +371,7 @@ static int __init init_vdso(void)
 
 	/* notifier priority > KVM */
 	return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
-				 "AP_X86_VDSO_VMA_ONLINE", vgetcpu_online, NULL);
+				 "x86/vdso/vma:online", vgetcpu_online, NULL);
 }
 subsys_initcall(init_vdso);
 #endif /* CONFIG_X86_64 */
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1010,7 +1010,7 @@ static __init int amd_ibs_init(void)
 	 * all online cpus.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-			  "AP_PERF_X86_AMD_IBS_STARTING",
+			  "perf/x86/amd/ibs:STARTING",
 			  x86_pmu_amd_ibs_starting_cpu,
 			  x86_pmu_amd_ibs_dying_cpu);
 
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -291,7 +291,7 @@ static int __init amd_power_pmu_init(voi
 
 
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
-			  "AP_PERF_X86_AMD_POWER_ONLINE",
+			  "perf/x86/amd/power:online",
 			  power_cpu_init, power_cpu_exit);
 
 	ret = perf_pmu_register(&pmu_class, "power", -1);
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -527,16 +527,16 @@ static int __init amd_uncore_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 	if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
-			      "PERF_X86_AMD_UNCORE_PREP",
+			      "perf/x86/amd/uncore:prepare",
 			      amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
 		goto fail_l2;
 
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
-			      "AP_PERF_X86_AMD_UNCORE_STARTING",
+			      "perf/x86/amd/uncore:starting",
 			      amd_uncore_cpu_starting, NULL))
 		goto fail_prep;
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
-			      "AP_PERF_X86_AMD_UNCORE_ONLINE",
+			      "perf/x86/amd/uncore:online",
 			      amd_uncore_cpu_online,
 			      amd_uncore_cpu_down_prepare))
 		goto fail_start;
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1820,18 +1820,18 @@ static int __init init_hw_perf_events(vo
 	 * Install callbacks. Core will call them for each online
 	 * cpu.
 	 */
-	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "PERF_X86_PREPARE",
+	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "perf/x86:prepare",
 				x86_pmu_prepare_cpu, x86_pmu_dead_cpu);
 	if (err)
 		return err;
 
 	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING,
-				"AP_PERF_X86_STARTING", x86_pmu_starting_cpu,
+				"perf/x86:starting", x86_pmu_starting_cpu,
 				x86_pmu_dying_cpu);
 	if (err)
 		goto out;
 
-	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "AP_PERF_X86_ONLINE",
+	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "perf/x86:online",
 				x86_pmu_online_cpu, NULL);
 	if (err)
 		goto out1;
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -1766,9 +1766,9 @@ static int __init intel_cqm_init(void)
 	 * is enabled to avoid notifier leak.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
-			  "AP_PERF_X86_CQM_STARTING",
+			  "perf/x86/cqm:starting",
 			  intel_cqm_cpu_starting, NULL);
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "AP_PERF_X86_CQM_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online",
 			  NULL, intel_cqm_cpu_exit);
 
 out:
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -606,10 +606,9 @@ static int __init cstate_init(void)
 	int err;
 
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_STARTING,
-			  "AP_PERF_X86_CSTATE_STARTING", cstate_cpu_init,
-			  NULL);
+			  "perf/x86/cstate:starting", cstate_cpu_init, NULL);
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_ONLINE,
-			  "AP_PERF_X86_CSTATE_ONLINE", NULL, cstate_cpu_exit);
+			  "perf/x86/cstate:online", NULL, cstate_cpu_exit);
 
 	if (has_cstate_core) {
 		err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1);
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -803,13 +803,13 @@ static int __init rapl_pmu_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "PERF_X86_RAPL_PREP",
+	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
 				rapl_cpu_prepare, NULL);
 	if (ret)
 		goto out;
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
-				"AP_PERF_X86_RAPL_ONLINE",
+				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
 		goto out1;
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1398,22 +1398,22 @@ static int __init intel_uncore_init(void
 	 */
 	if (!cret) {
 	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
-					"PERF_X86_UNCORE_PREP",
-					uncore_cpu_prepare, NULL);
+				       "perf/x86/intel/uncore:prepare",
+				       uncore_cpu_prepare, NULL);
 		if (ret)
 			goto err;
 	} else {
 		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
-					  "PERF_X86_UNCORE_PREP",
+					  "perf/x86/intel/uncore:prepare",
 					  uncore_cpu_prepare, NULL);
 	}
 	first_init = 1;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
-			  "AP_PERF_X86_UNCORE_STARTING",
+			  "perf/x86/uncore:starting",
 			  uncore_cpu_starting, uncore_cpu_dying);
 	first_init = 0;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
-			  "AP_PERF_X86_UNCORE_ONLINE",
+			  "perf/x86/uncore:online",
 			  uncore_event_cpu_online, uncore_event_cpu_offline);
 	return 0;
 
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -234,7 +234,7 @@ static __init int apbt_late_init(void)
 	if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ||
 		!apb_timer_block_enabled)
 		return 0;
-	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "X86_APB_DEAD", NULL,
+	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "x86/apb:dead", NULL,
 				 apbt_cpu_dead);
 }
 fs_initcall(apbt_late_init);
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -191,7 +191,7 @@ static int x2apic_cluster_probe(void)
 	if (!x2apic_mode)
 		return 0;
 
-	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare",
 				x2apic_prepare_cpu, x2apic_dead_cpu);
 	if (ret < 0) {
 		pr_err("Failed to register X2APIC_PREPARE\n");
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1051,11 +1051,11 @@ static __init int hpet_late_init(void)
 		return 0;
 
 	/* This notifier should be called after workqueue is ready */
-	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "AP_X86_HPET_ONLINE",
+	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "x86/hpet:online",
 				hpet_cpuhp_online, NULL);
 	if (ret)
 		return ret;
-	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "X86_HPET_DEAD", NULL,
+	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "x86/hpet:dead", NULL,
 				hpet_cpuhp_dead);
 	if (ret)
 		goto err_cpuhp;
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -408,7 +408,7 @@ static __init int tboot_late_init(void)
 	tboot_create_trampoline();
 
 	atomic_set(&ap_wfs_count, 0);
-	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "AP_X86_TBOOT_DYING", NULL,
+	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "x86/tboot:dying", NULL,
 			  tboot_dying_cpu);
 #ifdef CONFIG_DEBUG_FS
 	debugfs_create_file("tboot_log", S_IRUSR,
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5838,7 +5838,7 @@ static void kvm_timer_init(void)
 	}
 	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
 
-	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
 }
 
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1529,11 +1529,11 @@ static int xen_cpuhp_setup(void)
 	int rc;
 
 	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
-				       "XEN_HVM_GUEST_PREPARE",
+				       "x86/xen/hvm_guest:prepare",
 				       xen_cpu_up_prepare, xen_cpu_dead);
 	if (rc >= 0) {
 		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					       "XEN_HVM_GUEST_ONLINE",
+					       "x86/xen/hvm_guest:online",
 					       xen_cpu_up_online, NULL);
 		if (rc < 0)
 			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -422,7 +422,7 @@ static int __init xtensa_pmu_init(void)
 	int irq = irq_create_mapping(NULL, XCHAL_PROFILING_INTERRUPT);
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_XTENSA_STARTING,
-				"AP_PERF_XTENSA_STARTING", xtensa_pmu_setup,
+				"perf/xtensa:starting", xtensa_pmu_setup,
 				NULL);
 	if (ret) {
 		pr_err("xtensa_pmu: failed to register CPU-hotplug.\n");
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -1796,7 +1796,7 @@ static int __init cci_platform_init(void
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCI_ONLINE,
-				      "AP_PERF_ARM_CCI_ONLINE", NULL,
+				      "perf/arm/cci:online", NULL,
 				      cci_pmu_offline_cpu);
 	if (ret)
 		return ret;
--- a/drivers/bus/arm-ccn.c
+++ b/drivers/bus/arm-ccn.c
@@ -1562,7 +1562,7 @@ static int __init arm_ccn_init(void)
 	int i, ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-				      "AP_PERF_ARM_CCN_ONLINE", NULL,
+				      "perf/arm/ccn:online", NULL,
 				      arm_ccn_pmu_offline_cpu);
 	if (ret)
 		return ret;
--- a/drivers/clocksource/arc_timer.c
+++ b/drivers/clocksource/arc_timer.c
@@ -309,7 +309,7 @@ static int __init arc_clockevent_setup(s
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_ARC_TIMER_STARTING,
-				"AP_ARC_TIMER_STARTING",
+				"clockevents/arc/timer:starting",
 				arc_timer_starting_cpu,
 				arc_timer_dying_cpu);
 	if (ret) {
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -738,7 +738,7 @@ static int __init arch_timer_register(vo
 
 	/* Register and immediately configure the timer on the boot CPU */
 	err = cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_STARTING,
-				"AP_ARM_ARCH_TIMER_STARTING",
+				"clockevents/arm/arch_timer:starting",
 				arch_timer_starting_cpu, arch_timer_dying_cpu);
 	if (err)
 		goto out_unreg_cpupm;
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -316,7 +316,7 @@ static int __init global_timer_of_regist
 		goto out_irq;
 	
 	err = cpuhp_setup_state(CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
-				"AP_ARM_GLOBAL_TIMER_STARTING",
+				"clockevents/arm/global_timer:starting",
 				gt_starting_cpu, gt_dying_cpu);
 	if (err)
 		goto out_irq;
--- a/drivers/clocksource/dummy_timer.c
+++ b/drivers/clocksource/dummy_timer.c
@@ -34,7 +34,7 @@ static int dummy_timer_starting_cpu(unsi
 static int __init dummy_timer_register(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_DUMMY_TIMER_STARTING,
-				 "AP_DUMMY_TIMER_STARTING",
+				 "clockevents/dummy_timer:starting",
 				 dummy_timer_starting_cpu, NULL);
 }
 early_initcall(dummy_timer_register);
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -552,7 +552,7 @@ static int __init exynos4_timer_resource
 
 	/* Install hotplug callbacks which configure the timer on this CPU */
 	err = cpuhp_setup_state(CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
-				"AP_EXYNOS4_MCT_TIMER_STARTING",
+				"clockevents/exynos4/mct_timer:starting",
 				exynos4_mct_starting_cpu,
 				exynos4_mct_dying_cpu);
 	if (err)
--- a/drivers/clocksource/jcore-pit.c
+++ b/drivers/clocksource/jcore-pit.c
@@ -240,7 +240,7 @@ static int __init jcore_pit_init(struct
 	}
 
 	cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
-			  "AP_JCORE_TIMER_STARTING",
+			  "clockevents/jcore:starting",
 			  jcore_pit_local_init, NULL);
 
 	return 0;
--- a/drivers/clocksource/metag_generic.c
+++ b/drivers/clocksource/metag_generic.c
@@ -154,6 +154,6 @@ int __init metag_generic_timer_init(void
 
 	/* Hook cpu boot to configure the CPU's timers */
 	return cpuhp_setup_state(CPUHP_AP_METAG_TIMER_STARTING,
-				 "AP_METAG_TIMER_STARTING",
+				 "clockevents/metag:starting",
 				 arch_timer_starting_cpu, NULL);
 }
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -120,8 +120,8 @@ static int gic_clockevent_init(void)
 	}
 
 	cpuhp_setup_state(CPUHP_AP_MIPS_GIC_TIMER_STARTING,
-			  "AP_MIPS_GIC_TIMER_STARTING", gic_starting_cpu,
-			  gic_dying_cpu);
+			  "clockevents/mips/gic/timer:starting",
+			  gic_starting_cpu, gic_dying_cpu);
 	return 0;
 }
 
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -182,7 +182,7 @@ static int __init msm_timer_init(u32 dgt
 	} else {
 		/* Install and invoke hotplug callbacks */
 		res = cpuhp_setup_state(CPUHP_AP_QCOM_TIMER_STARTING,
-					"AP_QCOM_TIMER_STARTING",
+					"clockevents/qcom/timer:starting",
 					msm_local_timer_starting_cpu,
 					msm_local_timer_dying_cpu);
 		if (res) {
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -320,7 +320,7 @@ static int __init armada_370_xp_timer_co
 	}
 
 	res = cpuhp_setup_state(CPUHP_AP_ARMADA_TIMER_STARTING,
-				"AP_ARMADA_TIMER_STARTING",
+				"clockevents/armada:starting",
 				armada_370_xp_timer_starting_cpu,
 				armada_370_xp_timer_dying_cpu);
 	if (res) {
--- a/drivers/clocksource/timer-atlas7.c
+++ b/drivers/clocksource/timer-atlas7.c
@@ -221,7 +221,7 @@ static int __init sirfsoc_clockevent_ini
 
 	/* Install and invoke hotplug callbacks */
 	return cpuhp_setup_state(CPUHP_AP_MARCO_TIMER_STARTING,
-				 "AP_MARCO_TIMER_STARTING",
+				 "clockevents/marco:starting",
 				 sirfsoc_local_timer_starting_cpu,
 				 sirfsoc_local_timer_dying_cpu);
 }
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -804,10 +804,10 @@ static int etm_probe(struct amba_device
 
 	if (!etm_count++) {
 		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
-					  "AP_ARM_CORESIGHT_STARTING",
+					  "arm/coresight:starting",
 					  etm_starting_cpu, etm_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT_ONLINE",
+						"arm/coresight:online",
 						etm_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -987,10 +987,10 @@ static int etm4_probe(struct amba_device
 
 	if (!etm4_count++) {
 		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING,
-					  "AP_ARM_CORESIGHT4_STARTING",
+					  "arm/coresight4:starting",
 					  etm4_starting_cpu, etm4_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT4_ONLINE",
+						"arm/coresight4:online",
 						etm4_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -578,13 +578,13 @@ static int __init armada_370_xp_mpic_of_
 #ifdef CONFIG_SMP
 		set_smp_cross_call(armada_mpic_send_doorbell);
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-					  "AP_IRQ_ARMADA_XP_STARTING",
+					  "irqchip/armada/ipi:starting",
 					  armada_xp_mpic_starting_cpu, NULL);
 #endif
 	} else {
 #ifdef CONFIG_SMP
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
-					  "AP_IRQ_ARMADA_CASC_STARTING",
+					  "irqchip/armada/cascade:starting",
 					  mpic_cascaded_starting_cpu, NULL);
 #endif
 		irq_set_chained_handler(parent_irq,
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -245,7 +245,7 @@ bcm2836_arm_irqchip_smp_init(void)
 #ifdef CONFIG_SMP
 	/* Unmask IPIs to the boot CPU. */
 	cpuhp_setup_state(CPUHP_AP_IRQ_BCM2836_STARTING,
-			  "AP_IRQ_BCM2836_STARTING", bcm2836_cpu_starting,
+			  "irqchip/bcm2836:starting", bcm2836_cpu_starting,
 			  bcm2836_cpu_dying);
 
 	set_smp_cross_call(bcm2836_arm_irqchip_send_ipi);
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -633,8 +633,8 @@ static void gic_smp_init(void)
 {
 	set_smp_cross_call(gic_raise_softirq);
 	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GICV3_STARTING,
-				  "AP_IRQ_GICV3_STARTING", gic_starting_cpu,
-				  NULL);
+				  "irqchip/arm/gicv3:starting",
+				  gic_starting_cpu, NULL);
 }
 
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1191,7 +1191,7 @@ static int __init __gic_init_bases(struc
 		set_smp_cross_call(gic_raise_softirq);
 #endif
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
-					  "AP_IRQ_GIC_STARTING",
+					  "irqchip/arm/gic:starting",
 					  gic_starting_cpu, NULL);
 		set_handle_irq(gic_handle_irq);
 		if (static_key_true(&supports_deactivate))
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -407,7 +407,7 @@ hip04_of_init(struct device_node *node,
 	set_handle_irq(hip04_handle_irq);
 
 	hip04_irq_dist_init(&hip04_data);
-	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "AP_IRQ_HIP04_STARTING",
+	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "irqchip/hip04:starting",
 			  hip04_irq_starting_cpu, NULL);
 	return 0;
 }
--- a/drivers/leds/trigger/ledtrig-cpu.c
+++ b/drivers/leds/trigger/ledtrig-cpu.c
@@ -127,7 +127,7 @@ static int __init ledtrig_cpu_init(void)
 
 	register_syscore_ops(&ledtrig_cpu_syscore_ops);
 
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_LEDTRIG_STARTING",
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "leds/trigger:starting",
 				ledtrig_online_cpu, ledtrig_prepare_down_cpu);
 	if (ret < 0)
 		pr_err("CPU hotplug notifier for ledtrig-cpu could not be registered: %d\n",
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2452,13 +2452,13 @@ static __init int virtio_net_driver_init
 {
 	int ret;
 
-	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "AP_VIRT_NET_ONLINE",
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "virtio/net:online",
 				      virtnet_cpu_online,
 				      virtnet_cpu_down_prep);
 	if (ret < 0)
 		goto out;
 	virtionet_online = ret;
-	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "VIRT_NET_DEAD",
+	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "virtio/net:dead",
 				      NULL, virtnet_cpu_dead);
 	if (ret)
 		goto err_dead;
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -1084,7 +1084,7 @@ static int arm_pmu_hp_init(void)
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_STARTING,
-				      "AP_PERF_ARM_STARTING",
+				      "perf/arm/pmu:starting",
 				      arm_perf_starting_cpu, NULL);
 	if (ret)
 		pr_err("CPU hotplug notifier for ARM PMU could not be registered: %d\n",
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -445,7 +445,7 @@ int __init xen_evtchn_fifo_init(void)
 	evtchn_ops = &evtchn_ops_fifo;
 
 	cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE,
-				  "CPUHP_XEN_EVTCHN_PREPARE",
+				  "xen/evtchn:prepare",
 				  xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead);
 out:
 	put_cpu();
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -456,7 +456,7 @@ int kvm_timer_hyp_init(void)
 	kvm_info("virtual timer IRQ%d\n", host_vtimer_irq);
 
 	cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING,
-			  "AP_KVM_ARM_TIMER_STARTING", kvm_timer_starting_cpu,
+			  "kvm/arm/timer:starting", kvm_timer_starting_cpu,
 			  kvm_timer_dying_cpu);
 	return err;
 }
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -428,7 +428,7 @@ int kvm_vgic_hyp_init(void)
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
-				"AP_KVM_ARM_VGIC_INIT_STARTING",
+				"kvm/arm/vgic:starting",
 				vgic_init_cpu_starting, vgic_init_cpu_dying);
 	if (ret) {
 		kvm_err("Cannot register vgic CPU notifier\n");
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3944,7 +3944,7 @@ int kvm_init(void *opaque, unsigned vcpu
 			goto out_free_1;
 	}
 
-	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "AP_KVM_STARTING",
+	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting",
 				      kvm_starting_cpu, kvm_dying_cpu);
 	if (r)
 		goto out_free_2;

[tip:smp/urgent] cpu/hotplug: Cleanup state names

[tip-bot for Thomas Gleixner]

Commit-ID:  8ea29129e7cd926901ee3396b963453c7f5c3c4b
Gitweb:     http://git.kernel.org/tip/8ea29129e7cd926901ee3396b963453c7f5c3c4b
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:54 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:55 +0100

cpu/hotplug: Cleanup state names

When the state names got added a script was used to add the extra argument
to the calls. The script basically converted the state constant to a
string, but the cleanup to convert these strings into meaningful ones did
not happen.

Replace all the useless strings with 'subsys/xxx/yyy:state' strings which
are used in all the other places already.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Link: http://lkml.kernel.org/r/20161221192112.085444152@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/arm/kernel/smp_twd.c                     |  2 +-
 arch/arm/mach-mvebu/coherency.c               |  2 +-
 arch/arm/mm/cache-l2x0-pmu.c                  |  2 +-
 arch/arm/mm/cache-l2x0.c                      |  2 +-
 arch/arm/vfp/vfpmodule.c                      |  2 +-
 arch/arm/xen/enlighten.c                      |  2 +-
 arch/arm64/kernel/armv8_deprecated.c          |  2 +-
 arch/arm64/kernel/debug-monitors.c            |  2 +-
 arch/arm64/kernel/hw_breakpoint.c             |  2 +-
 arch/blackfin/kernel/perf_event.c             |  2 +-
 arch/metag/kernel/perf/perf_event.c           |  2 +-
 arch/mips/kernel/pm-cps.c                     |  2 +-
 arch/mips/oprofile/op_model_loongson3.c       |  2 +-
 arch/powerpc/mm/numa.c                        |  2 +-
 arch/powerpc/perf/core-book3s.c               |  2 +-
 arch/s390/kernel/perf_cpum_cf.c               |  2 +-
 arch/s390/kernel/perf_cpum_sf.c               |  2 +-
 arch/x86/entry/vdso/vma.c                     |  2 +-
 arch/x86/events/amd/ibs.c                     |  2 +-
 arch/x86/events/amd/power.c                   |  2 +-
 arch/x86/events/amd/uncore.c                  |  6 +++---
 arch/x86/events/core.c                        |  6 +++---
 arch/x86/events/intel/cqm.c                   |  4 ++--
 arch/x86/events/intel/rapl.c                  |  4 ++--
 arch/x86/events/intel/uncore.c                | 10 +++++-----
 arch/x86/kernel/apb_timer.c                   |  2 +-
 arch/x86/kernel/apic/x2apic_cluster.c         |  2 +-
 arch/x86/kernel/hpet.c                        |  4 ++--
 arch/x86/kernel/tboot.c                       |  2 +-
 arch/x86/kvm/x86.c                            |  2 +-
 arch/x86/xen/enlighten.c                      |  4 ++--
 arch/xtensa/kernel/perf_event.c               |  2 +-
 drivers/bus/arm-cci.c                         |  2 +-
 drivers/bus/arm-ccn.c                         |  2 +-
 drivers/clocksource/arc_timer.c               |  2 +-
 drivers/clocksource/arm_arch_timer.c          |  2 +-
 drivers/clocksource/arm_global_timer.c        |  2 +-
 drivers/clocksource/dummy_timer.c             |  2 +-
 drivers/clocksource/exynos_mct.c              |  2 +-
 drivers/clocksource/jcore-pit.c               |  2 +-
 drivers/clocksource/metag_generic.c           |  2 +-
 drivers/clocksource/mips-gic-timer.c          |  4 ++--
 drivers/clocksource/qcom-timer.c              |  2 +-
 drivers/clocksource/time-armada-370-xp.c      |  2 +-
 drivers/clocksource/timer-atlas7.c            |  2 +-
 drivers/hwtracing/coresight/coresight-etm3x.c |  4 ++--
 drivers/hwtracing/coresight/coresight-etm4x.c |  4 ++--
 drivers/irqchip/irq-armada-370-xp.c           |  4 ++--
 drivers/irqchip/irq-bcm2836.c                 |  2 +-
 drivers/irqchip/irq-gic-v3.c                  |  4 ++--
 drivers/irqchip/irq-gic.c                     |  2 +-
 drivers/irqchip/irq-hip04.c                   |  2 +-
 drivers/leds/trigger/ledtrig-cpu.c            |  2 +-
 drivers/net/virtio_net.c                      |  4 ++--
 drivers/perf/arm_pmu.c                        |  2 +-
 drivers/xen/events/events_fifo.c              |  2 +-
 virt/kvm/arm/arch_timer.c                     |  2 +-
 virt/kvm/arm/vgic/vgic-init.c                 |  2 +-
 virt/kvm/kvm_main.c                           |  2 +-
 59 files changed, 77 insertions(+), 77 deletions(-)

diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 02d5e5e..895ae51 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -339,7 +339,7 @@ static int __init twd_local_timer_common_register(struct device_node *np)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_TWD_STARTING,
-				  "AP_ARM_TWD_STARTING",
+				  "arm/timer/twd:starting",
 				  twd_timer_starting_cpu, twd_timer_dying_cpu);
 
 	twd_get_clock(np);
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index ae2a018..8f8748a 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -148,7 +148,7 @@ static void __init armada_370_coherency_init(struct device_node *np)
 	of_node_put(cpu_config_np);
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_MVEBU_COHERENCY,
-				  "AP_ARM_MVEBU_COHERENCY",
+				  "arm/mvebu/coherency:starting",
 				  armada_xp_clear_l2_starting, NULL);
 exit:
 	set_cpu_coherent();
diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c
index 976d305..0a1e228 100644
--- a/arch/arm/mm/cache-l2x0-pmu.c
+++ b/arch/arm/mm/cache-l2x0-pmu.c
@@ -563,7 +563,7 @@ static __init int l2x0_pmu_init(void)
 
 	cpumask_set_cpu(0, &pmu_cpu);
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE,
-					"AP_PERF_ARM_L2X0_ONLINE", NULL,
+					"perf/arm/l2x0:online", NULL,
 					l2x0_pmu_offline_cpu);
 	if (ret)
 		goto out_pmu;
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index d1870c7..2290be3 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -683,7 +683,7 @@ static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
 
 	if (aux & L310_AUX_CTRL_FULL_LINE_ZERO)
 		cpuhp_setup_state(CPUHP_AP_ARM_L2X0_STARTING,
-				  "AP_ARM_L2X0_STARTING", l2c310_starting_cpu,
+				  "arm/l2x0:starting", l2c310_starting_cpu,
 				  l2c310_dying_cpu);
 }
 
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 0351f56..569d5a6 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -799,7 +799,7 @@ static int __init vfp_init(void)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_VFP_STARTING,
-				  "AP_ARM_VFP_STARTING", vfp_starting_cpu,
+				  "arm/vfp:starting", vfp_starting_cpu,
 				  vfp_dying_cpu);
 
 	vfp_vector = vfp_support_entry;
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 4986dc0..11d9f28 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -412,7 +412,7 @@ static int __init xen_guest_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 
 	return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
-				 "AP_ARM_XEN_STARTING", xen_starting_cpu,
+				 "arm/xen:starting", xen_starting_cpu,
 				 xen_dying_cpu);
 }
 early_initcall(xen_guest_init);
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 04de188..a211add 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -640,7 +640,7 @@ static int __init armv8_deprecated_init(void)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
-				  "AP_ARM64_ISNDEP_STARTING",
+				  "arm64/isndep:starting",
 				  run_all_insn_set_hw_mode, NULL);
 	register_insn_emulation_sysctl(ctl_abi);
 
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 605df76..2bd4264 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -140,7 +140,7 @@ static int clear_os_lock(unsigned int cpu)
 static int debug_monitors_init(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
-				 "CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING",
+				 "arm64/debug_monitors:starting",
 				 clear_os_lock, NULL);
 }
 postcore_initcall(debug_monitors_init);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 1b3c747..0296e79 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -1001,7 +1001,7 @@ static int __init arch_hw_breakpoint_init(void)
 	 * debugger will leave the world in a nice state for us.
 	 */
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
-			  "CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING",
+			  "perf/arm64/hw_breakpoint:starting",
 			  hw_breakpoint_reset, NULL);
 	if (ret)
 		pr_err("failed to register CPU hotplug notifier: %d\n", ret);
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 6355e97..6a9524a 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -475,7 +475,7 @@ static int __init bfin_pmu_init(void)
 
 	ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	if (!ret)
-		cpuhp_setup_state(CPUHP_PERF_BFIN, "PERF_BFIN",
+		cpuhp_setup_state(CPUHP_PERF_BFIN,"perf/bfin:starting",
 				  bfin_pmu_prepare_cpu, NULL);
 	return ret;
 }
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 052cba2..7e793eb 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -868,7 +868,7 @@ static int __init init_hw_perf_events(void)
 	metag_out32(0, PERF_COUNT(1));
 
 	cpuhp_setup_state(CPUHP_AP_PERF_METAG_STARTING,
-			  "AP_PERF_METAG_STARTING", metag_pmu_starting_cpu,
+			  "perf/metag:starting", metag_pmu_starting_cpu,
 			  NULL);
 
 	ret = perf_pmu_register(&pmu, metag_pmu->name, PERF_TYPE_RAW);
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index 7cf653e..5f928c3 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -713,7 +713,7 @@ static int __init cps_pm_init(void)
 		pr_warn("pm-cps: no CPC, clock & power gating unavailable\n");
 	}
 
-	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PM_CPS_CPU_ONLINE",
+	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mips/cps_pm:online",
 				 cps_pm_online_cpu, NULL);
 }
 arch_initcall(cps_pm_init);
diff --git a/arch/mips/oprofile/op_model_loongson3.c b/arch/mips/oprofile/op_model_loongson3.c
index 85f3ee4..d60d97b 100644
--- a/arch/mips/oprofile/op_model_loongson3.c
+++ b/arch/mips/oprofile/op_model_loongson3.c
@@ -186,7 +186,7 @@ static int __init loongson3_init(void)
 {
 	on_each_cpu(reset_counters, NULL, 1);
 	cpuhp_setup_state_nocalls(CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
-				  "AP_MIPS_OP_LOONGSON3_STARTING",
+				  "mips/oprofile/loongson3:starting",
 				  loongson3_starting_cpu, loongson3_dying_cpu);
 	save_perf_irq = perf_irq;
 	perf_irq = loongson3_perfcount_handler;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 0cb6bd8..b1099cb 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -944,7 +944,7 @@ void __init initmem_init(void)
 	 * _nocalls() + manual invocation is used because cpuhp is not yet
 	 * initialized for the boot CPU.
 	 */
-	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "POWER_NUMA_PREPARE",
+	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "powerpc/numa:prepare",
 				  ppc_numa_cpu_prepare, ppc_numa_cpu_dead);
 	for_each_present_cpu(cpu)
 		numa_setup_cpu(cpu);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 72c27b8..fd3e403 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2189,7 +2189,7 @@ int register_power_pmu(struct power_pmu *pmu)
 #endif /* CONFIG_PPC64 */
 
 	perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW);
-	cpuhp_setup_state(CPUHP_PERF_POWER, "PERF_POWER",
+	cpuhp_setup_state(CPUHP_PERF_POWER, "perf/powerpc:prepare",
 			  power_pmu_prepare_cpu, NULL);
 	return 0;
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 037c2a2..1aba10e 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -711,7 +711,7 @@ static int __init cpumf_pmu_init(void)
 		return rc;
 	}
 	return cpuhp_setup_state(CPUHP_AP_PERF_S390_CF_ONLINE,
-				 "AP_PERF_S390_CF_ONLINE",
+				 "perf/s390/cf:online",
 				 s390_pmu_online_cpu, s390_pmu_offline_cpu);
 }
 early_initcall(cpumf_pmu_init);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 763dec1..1c0b585 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1623,7 +1623,7 @@ static int __init init_cpum_sampling_pmu(void)
 		goto out;
 	}
 
-	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "AP_PERF_S390_SF_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "perf/s390/sf:online",
 			  s390_pmu_sf_online_cpu, s390_pmu_sf_offline_cpu);
 out:
 	return err;
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 40121d1..10820f6 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -371,7 +371,7 @@ static int __init init_vdso(void)
 
 	/* notifier priority > KVM */
 	return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
-				 "AP_X86_VDSO_VMA_ONLINE", vgetcpu_online, NULL);
+				 "x86/vdso/vma:online", vgetcpu_online, NULL);
 }
 subsys_initcall(init_vdso);
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index b26ee32..05612a2 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1010,7 +1010,7 @@ static __init int amd_ibs_init(void)
 	 * all online cpus.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-			  "AP_PERF_X86_AMD_IBS_STARTING",
+			  "perf/x86/amd/ibs:STARTING",
 			  x86_pmu_amd_ibs_starting_cpu,
 			  x86_pmu_amd_ibs_dying_cpu);
 
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 9842270..a6eee5a 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -291,7 +291,7 @@ static int __init amd_power_pmu_init(void)
 
 
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
-			  "AP_PERF_X86_AMD_POWER_ONLINE",
+			  "perf/x86/amd/power:online",
 			  power_cpu_init, power_cpu_exit);
 
 	ret = perf_pmu_register(&pmu_class, "power", -1);
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 65577f0..a0b1bdb 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -527,16 +527,16 @@ static int __init amd_uncore_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 	if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
-			      "PERF_X86_AMD_UNCORE_PREP",
+			      "perf/x86/amd/uncore:prepare",
 			      amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
 		goto fail_l2;
 
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
-			      "AP_PERF_X86_AMD_UNCORE_STARTING",
+			      "perf/x86/amd/uncore:starting",
 			      amd_uncore_cpu_starting, NULL))
 		goto fail_prep;
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
-			      "AP_PERF_X86_AMD_UNCORE_ONLINE",
+			      "perf/x86/amd/uncore:online",
 			      amd_uncore_cpu_online,
 			      amd_uncore_cpu_down_prepare))
 		goto fail_start;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index f1c2258..019c588 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1820,18 +1820,18 @@ static int __init init_hw_perf_events(void)
 	 * Install callbacks. Core will call them for each online
 	 * cpu.
 	 */
-	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "PERF_X86_PREPARE",
+	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "perf/x86:prepare",
 				x86_pmu_prepare_cpu, x86_pmu_dead_cpu);
 	if (err)
 		return err;
 
 	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING,
-				"AP_PERF_X86_STARTING", x86_pmu_starting_cpu,
+				"perf/x86:starting", x86_pmu_starting_cpu,
 				x86_pmu_dying_cpu);
 	if (err)
 		goto out;
 
-	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "AP_PERF_X86_ONLINE",
+	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "perf/x86:online",
 				x86_pmu_online_cpu, NULL);
 	if (err)
 		goto out1;
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 8f82b02..1ffdd1c 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -1766,9 +1766,9 @@ static int __init intel_cqm_init(void)
 	 * is enabled to avoid notifier leak.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
-			  "AP_PERF_X86_CQM_STARTING",
+			  "perf/x86/cqm:starting",
 			  intel_cqm_cpu_starting, NULL);
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "AP_PERF_X86_CQM_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online",
 			  NULL, intel_cqm_cpu_exit);
 
 out:
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 0a535ce..bd34124 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -803,13 +803,13 @@ static int __init rapl_pmu_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "PERF_X86_RAPL_PREP",
+	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
 				rapl_cpu_prepare, NULL);
 	if (ret)
 		goto out;
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
-				"AP_PERF_X86_RAPL_ONLINE",
+				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
 		goto out1;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index dbaaf7dc..97c246f 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1398,22 +1398,22 @@ static int __init intel_uncore_init(void)
 	 */
 	if (!cret) {
 	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
-					"PERF_X86_UNCORE_PREP",
-					uncore_cpu_prepare, NULL);
+				       "perf/x86/intel/uncore:prepare",
+				       uncore_cpu_prepare, NULL);
 		if (ret)
 			goto err;
 	} else {
 		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
-					  "PERF_X86_UNCORE_PREP",
+					  "perf/x86/intel/uncore:prepare",
 					  uncore_cpu_prepare, NULL);
 	}
 	first_init = 1;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
-			  "AP_PERF_X86_UNCORE_STARTING",
+			  "perf/x86/uncore:starting",
 			  uncore_cpu_starting, uncore_cpu_dying);
 	first_init = 0;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
-			  "AP_PERF_X86_UNCORE_ONLINE",
+			  "perf/x86/uncore:online",
 			  uncore_event_cpu_online, uncore_event_cpu_offline);
 	return 0;
 
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 456316f..202a781 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -234,7 +234,7 @@ static __init int apbt_late_init(void)
 	if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ||
 		!apb_timer_block_enabled)
 		return 0;
-	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "X86_APB_DEAD", NULL,
+	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "x86/apb:dead", NULL,
 				 apbt_cpu_dead);
 }
 fs_initcall(apbt_late_init);
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 200af5a..5a35f20 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -191,7 +191,7 @@ static int x2apic_cluster_probe(void)
 	if (!x2apic_mode)
 		return 0;
 
-	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare",
 				x2apic_prepare_cpu, x2apic_dead_cpu);
 	if (ret < 0) {
 		pr_err("Failed to register X2APIC_PREPARE\n");
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 274fab9..38c8fd6 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1051,11 +1051,11 @@ static __init int hpet_late_init(void)
 		return 0;
 
 	/* This notifier should be called after workqueue is ready */
-	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "AP_X86_HPET_ONLINE",
+	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "x86/hpet:online",
 				hpet_cpuhp_online, NULL);
 	if (ret)
 		return ret;
-	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "X86_HPET_DEAD", NULL,
+	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "x86/hpet:dead", NULL,
 				hpet_cpuhp_dead);
 	if (ret)
 		goto err_cpuhp;
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 8402907..b868fa1 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -408,7 +408,7 @@ static __init int tboot_late_init(void)
 	tboot_create_trampoline();
 
 	atomic_set(&ap_wfs_count, 0);
-	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "AP_X86_TBOOT_DYING", NULL,
+	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "x86/tboot:dying", NULL,
 			  tboot_dying_cpu);
 #ifdef CONFIG_DEBUG_FS
 	debugfs_create_file("tboot_log", S_IRUSR,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1f0d238..b062f3d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5838,7 +5838,7 @@ static void kvm_timer_init(void)
 	}
 	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
 
-	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
 }
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ced7027..51ef952 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1529,11 +1529,11 @@ static int xen_cpuhp_setup(void)
 	int rc;
 
 	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
-				       "XEN_HVM_GUEST_PREPARE",
+				       "x86/xen/hvm_guest:prepare",
 				       xen_cpu_up_prepare, xen_cpu_dead);
 	if (rc >= 0) {
 		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					       "XEN_HVM_GUEST_ONLINE",
+					       "x86/xen/hvm_guest:online",
 					       xen_cpu_up_online, NULL);
 		if (rc < 0)
 			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 0fecc8a..ff1d813 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -422,7 +422,7 @@ static int __init xtensa_pmu_init(void)
 	int irq = irq_create_mapping(NULL, XCHAL_PROFILING_INTERRUPT);
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_XTENSA_STARTING,
-				"AP_PERF_XTENSA_STARTING", xtensa_pmu_setup,
+				"perf/xtensa:starting", xtensa_pmu_setup,
 				NULL);
 	if (ret) {
 		pr_err("xtensa_pmu: failed to register CPU-hotplug.\n");
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 2316333..c49da15 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -1796,7 +1796,7 @@ static int __init cci_platform_init(void)
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCI_ONLINE,
-				      "AP_PERF_ARM_CCI_ONLINE", NULL,
+				      "perf/arm/cci:online", NULL,
 				      cci_pmu_offline_cpu);
 	if (ret)
 		return ret;
diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c
index aee8346..4d6a2b7 100644
--- a/drivers/bus/arm-ccn.c
+++ b/drivers/bus/arm-ccn.c
@@ -1562,7 +1562,7 @@ static int __init arm_ccn_init(void)
 	int i, ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-				      "AP_PERF_ARM_CCN_ONLINE", NULL,
+				      "perf/arm/ccn:online", NULL,
 				      arm_ccn_pmu_offline_cpu);
 	if (ret)
 		return ret;
diff --git a/drivers/clocksource/arc_timer.c b/drivers/clocksource/arc_timer.c
index a49748d..2b7e871 100644
--- a/drivers/clocksource/arc_timer.c
+++ b/drivers/clocksource/arc_timer.c
@@ -309,7 +309,7 @@ static int __init arc_clockevent_setup(struct device_node *node)
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_ARC_TIMER_STARTING,
-				"AP_ARC_TIMER_STARTING",
+				"clockevents/arc/timer:starting",
 				arc_timer_starting_cpu,
 				arc_timer_dying_cpu);
 	if (ret) {
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 02fef68..cdeca85 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -738,7 +738,7 @@ static int __init arch_timer_register(void)
 
 	/* Register and immediately configure the timer on the boot CPU */
 	err = cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_STARTING,
-				"AP_ARM_ARCH_TIMER_STARTING",
+				"clockevents/arm/arch_timer:starting",
 				arch_timer_starting_cpu, arch_timer_dying_cpu);
 	if (err)
 		goto out_unreg_cpupm;
diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index 8da0329..bbfeb28 100644
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -316,7 +316,7 @@ static int __init global_timer_of_register(struct device_node *np)
 		goto out_irq;
 	
 	err = cpuhp_setup_state(CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
-				"AP_ARM_GLOBAL_TIMER_STARTING",
+				"clockevents/arm/global_timer:starting",
 				gt_starting_cpu, gt_dying_cpu);
 	if (err)
 		goto out_irq;
diff --git a/drivers/clocksource/dummy_timer.c b/drivers/clocksource/dummy_timer.c
index 89f1c2e..01f3f5a 100644
--- a/drivers/clocksource/dummy_timer.c
+++ b/drivers/clocksource/dummy_timer.c
@@ -34,7 +34,7 @@ static int dummy_timer_starting_cpu(unsigned int cpu)
 static int __init dummy_timer_register(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_DUMMY_TIMER_STARTING,
-				 "AP_DUMMY_TIMER_STARTING",
+				 "clockevents/dummy_timer:starting",
 				 dummy_timer_starting_cpu, NULL);
 }
 early_initcall(dummy_timer_register);
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 8f3488b..b45b72b 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -552,7 +552,7 @@ static int __init exynos4_timer_resources(struct device_node *np, void __iomem *
 
 	/* Install hotplug callbacks which configure the timer on this CPU */
 	err = cpuhp_setup_state(CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
-				"AP_EXYNOS4_MCT_TIMER_STARTING",
+				"clockevents/exynos4/mct_timer:starting",
 				exynos4_mct_starting_cpu,
 				exynos4_mct_dying_cpu);
 	if (err)
diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c
index 54e1665..4e4146f 100644
--- a/drivers/clocksource/jcore-pit.c
+++ b/drivers/clocksource/jcore-pit.c
@@ -240,7 +240,7 @@ static int __init jcore_pit_init(struct device_node *node)
 	}
 
 	cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
-			  "AP_JCORE_TIMER_STARTING",
+			  "clockevents/jcore:starting",
 			  jcore_pit_local_init, NULL);
 
 	return 0;
diff --git a/drivers/clocksource/metag_generic.c b/drivers/clocksource/metag_generic.c
index a80ab3e..172f43d 100644
--- a/drivers/clocksource/metag_generic.c
+++ b/drivers/clocksource/metag_generic.c
@@ -154,6 +154,6 @@ int __init metag_generic_timer_init(void)
 
 	/* Hook cpu boot to configure the CPU's timers */
 	return cpuhp_setup_state(CPUHP_AP_METAG_TIMER_STARTING,
-				 "AP_METAG_TIMER_STARTING",
+				 "clockevents/metag:starting",
 				 arch_timer_starting_cpu, NULL);
 }
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index 7a960cd..d927884 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -120,8 +120,8 @@ static int gic_clockevent_init(void)
 	}
 
 	cpuhp_setup_state(CPUHP_AP_MIPS_GIC_TIMER_STARTING,
-			  "AP_MIPS_GIC_TIMER_STARTING", gic_starting_cpu,
-			  gic_dying_cpu);
+			  "clockevents/mips/gic/timer:starting",
+			  gic_starting_cpu, gic_dying_cpu);
 	return 0;
 }
 
diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c
index 3283cfa..3bf65ff 100644
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -182,7 +182,7 @@ static int __init msm_timer_init(u32 dgt_hz, int sched_bits, int irq,
 	} else {
 		/* Install and invoke hotplug callbacks */
 		res = cpuhp_setup_state(CPUHP_AP_QCOM_TIMER_STARTING,
-					"AP_QCOM_TIMER_STARTING",
+					"clockevents/qcom/timer:starting",
 					msm_local_timer_starting_cpu,
 					msm_local_timer_dying_cpu);
 		if (res) {
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 3c39e6f..4440aef 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -320,7 +320,7 @@ static int __init armada_370_xp_timer_common_init(struct device_node *np)
 	}
 
 	res = cpuhp_setup_state(CPUHP_AP_ARMADA_TIMER_STARTING,
-				"AP_ARMADA_TIMER_STARTING",
+				"clockevents/armada:starting",
 				armada_370_xp_timer_starting_cpu,
 				armada_370_xp_timer_dying_cpu);
 	if (res) {
diff --git a/drivers/clocksource/timer-atlas7.c b/drivers/clocksource/timer-atlas7.c
index 4334e03..3c23e17 100644
--- a/drivers/clocksource/timer-atlas7.c
+++ b/drivers/clocksource/timer-atlas7.c
@@ -221,7 +221,7 @@ static int __init sirfsoc_clockevent_init(void)
 
 	/* Install and invoke hotplug callbacks */
 	return cpuhp_setup_state(CPUHP_AP_MARCO_TIMER_STARTING,
-				 "AP_MARCO_TIMER_STARTING",
+				 "clockevents/marco:starting",
 				 sirfsoc_local_timer_starting_cpu,
 				 sirfsoc_local_timer_dying_cpu);
 }
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index 3fe368b..a51b6b6 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -804,10 +804,10 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	if (!etm_count++) {
 		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
-					  "AP_ARM_CORESIGHT_STARTING",
+					  "arm/coresight:starting",
 					  etm_starting_cpu, etm_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT_ONLINE",
+						"arm/coresight:online",
 						etm_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 4db8d6a..5edc63f 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -987,10 +987,10 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 	if (!etm4_count++) {
 		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING,
-					  "AP_ARM_CORESIGHT4_STARTING",
+					  "arm/coresight4:starting",
 					  etm4_starting_cpu, etm4_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT4_ONLINE",
+						"arm/coresight4:online",
 						etm4_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 8bcee65..9d9c2c4 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -578,13 +578,13 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 #ifdef CONFIG_SMP
 		set_smp_cross_call(armada_mpic_send_doorbell);
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-					  "AP_IRQ_ARMADA_XP_STARTING",
+					  "irqchip/armada/ipi:starting",
 					  armada_xp_mpic_starting_cpu, NULL);
 #endif
 	} else {
 #ifdef CONFIG_SMP
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
-					  "AP_IRQ_ARMADA_CASC_STARTING",
+					  "irqchip/armada/cascade:starting",
 					  mpic_cascaded_starting_cpu, NULL);
 #endif
 		irq_set_chained_handler(parent_irq,
diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c
index d96b2c9..e7463e3 100644
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -245,7 +245,7 @@ bcm2836_arm_irqchip_smp_init(void)
 #ifdef CONFIG_SMP
 	/* Unmask IPIs to the boot CPU. */
 	cpuhp_setup_state(CPUHP_AP_IRQ_BCM2836_STARTING,
-			  "AP_IRQ_BCM2836_STARTING", bcm2836_cpu_starting,
+			  "irqchip/bcm2836:starting", bcm2836_cpu_starting,
 			  bcm2836_cpu_dying);
 
 	set_smp_cross_call(bcm2836_arm_irqchip_send_ipi);
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 26e1d7f..d696de1 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -633,8 +633,8 @@ static void gic_smp_init(void)
 {
 	set_smp_cross_call(gic_raise_softirq);
 	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GICV3_STARTING,
-				  "AP_IRQ_GICV3_STARTING", gic_starting_cpu,
-				  NULL);
+				  "irqchip/arm/gicv3:starting",
+				  gic_starting_cpu, NULL);
 }
 
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index d6c404b..1b1df4f 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1191,7 +1191,7 @@ static int __init __gic_init_bases(struct gic_chip_data *gic,
 		set_smp_cross_call(gic_raise_softirq);
 #endif
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
-					  "AP_IRQ_GIC_STARTING",
+					  "irqchip/arm/gic:starting",
 					  gic_starting_cpu, NULL);
 		set_handle_irq(gic_handle_irq);
 		if (static_key_true(&supports_deactivate))
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
index 021b0e0..c1b4ee9 100644
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -407,7 +407,7 @@ hip04_of_init(struct device_node *node, struct device_node *parent)
 	set_handle_irq(hip04_handle_irq);
 
 	hip04_irq_dist_init(&hip04_data);
-	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "AP_IRQ_HIP04_STARTING",
+	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "irqchip/hip04:starting",
 			  hip04_irq_starting_cpu, NULL);
 	return 0;
 }
diff --git a/drivers/leds/trigger/ledtrig-cpu.c b/drivers/leds/trigger/ledtrig-cpu.c
index 9719caf..a418964 100644
--- a/drivers/leds/trigger/ledtrig-cpu.c
+++ b/drivers/leds/trigger/ledtrig-cpu.c
@@ -127,7 +127,7 @@ static int __init ledtrig_cpu_init(void)
 
 	register_syscore_ops(&ledtrig_cpu_syscore_ops);
 
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_LEDTRIG_STARTING",
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "leds/trigger:starting",
 				ledtrig_online_cpu, ledtrig_prepare_down_cpu);
 	if (ret < 0)
 		pr_err("CPU hotplug notifier for ledtrig-cpu could not be registered: %d\n",
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 08327e0..ba1aa24 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2452,13 +2452,13 @@ static __init int virtio_net_driver_init(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "AP_VIRT_NET_ONLINE",
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "virtio/net:online",
 				      virtnet_cpu_online,
 				      virtnet_cpu_down_prep);
 	if (ret < 0)
 		goto out;
 	virtionet_online = ret;
-	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "VIRT_NET_DEAD",
+	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "virtio/net:dead",
 				      NULL, virtnet_cpu_dead);
 	if (ret)
 		goto err_dead;
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index b37b572..6d93358 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -1084,7 +1084,7 @@ static int arm_pmu_hp_init(void)
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_STARTING,
-				      "AP_PERF_ARM_STARTING",
+				      "perf/arm/pmu:starting",
 				      arm_perf_starting_cpu, NULL);
 	if (ret)
 		pr_err("CPU hotplug notifier for ARM PMU could not be registered: %d\n",
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 7ef27c6..c03f9c8 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -445,7 +445,7 @@ int __init xen_evtchn_fifo_init(void)
 	evtchn_ops = &evtchn_ops_fifo;
 
 	cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE,
-				  "CPUHP_XEN_EVTCHN_PREPARE",
+				  "xen/evtchn:prepare",
 				  xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead);
 out:
 	put_cpu();
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index ae95fc0..5b4f60d 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -456,7 +456,7 @@ int kvm_timer_hyp_init(void)
 	kvm_info("virtual timer IRQ%d\n", host_vtimer_irq);
 
 	cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING,
-			  "AP_KVM_ARM_TIMER_STARTING", kvm_timer_starting_cpu,
+			  "kvm/arm/timer:starting", kvm_timer_starting_cpu,
 			  kvm_timer_dying_cpu);
 	return err;
 }
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 8cebfbc..5114391 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -428,7 +428,7 @@ int kvm_vgic_hyp_init(void)
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
-				"AP_KVM_ARM_VGIC_INIT_STARTING",
+				"kvm/arm/vgic:starting",
 				vgic_init_cpu_starting, vgic_init_cpu_dying);
 	if (ret) {
 		kvm_err("Cannot register vgic CPU notifier\n");
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index de102ca..ec298b7 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3944,7 +3944,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 			goto out_free_1;
 	}
 
-	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "AP_KVM_STARTING",
+	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting",
 				      kvm_starting_cpu, kvm_dying_cpu);
 	if (r)
 		goto out_free_2;

[tip:smp/urgent] cpu/hotplug: Cleanup state names

[tip-bot for Thomas Gleixner]

Commit-ID:  73c1b41e63f040e92669e61a02c7893933bfe743
Gitweb:     http://git.kernel.org/tip/73c1b41e63f040e92669e61a02c7893933bfe743
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:54 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:44 +0100

cpu/hotplug: Cleanup state names

When the state names got added a script was used to add the extra argument
to the calls. The script basically converted the state constant to a
string, but the cleanup to convert these strings into meaningful ones did
not happen.

Replace all the useless strings with 'subsys/xxx/yyy:state' strings which
are used in all the other places already.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Link: http://lkml.kernel.org/r/20161221192112.085444152@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/arm/kernel/smp_twd.c                     |  2 +-
 arch/arm/mach-mvebu/coherency.c               |  2 +-
 arch/arm/mm/cache-l2x0-pmu.c                  |  2 +-
 arch/arm/mm/cache-l2x0.c                      |  2 +-
 arch/arm/vfp/vfpmodule.c                      |  2 +-
 arch/arm/xen/enlighten.c                      |  2 +-
 arch/arm64/kernel/armv8_deprecated.c          |  2 +-
 arch/arm64/kernel/debug-monitors.c            |  2 +-
 arch/arm64/kernel/hw_breakpoint.c             |  2 +-
 arch/blackfin/kernel/perf_event.c             |  2 +-
 arch/metag/kernel/perf/perf_event.c           |  2 +-
 arch/mips/kernel/pm-cps.c                     |  2 +-
 arch/mips/oprofile/op_model_loongson3.c       |  2 +-
 arch/powerpc/mm/numa.c                        |  2 +-
 arch/powerpc/perf/core-book3s.c               |  2 +-
 arch/s390/kernel/perf_cpum_cf.c               |  2 +-
 arch/s390/kernel/perf_cpum_sf.c               |  2 +-
 arch/x86/entry/vdso/vma.c                     |  2 +-
 arch/x86/events/amd/ibs.c                     |  2 +-
 arch/x86/events/amd/power.c                   |  2 +-
 arch/x86/events/amd/uncore.c                  |  6 +++---
 arch/x86/events/core.c                        |  6 +++---
 arch/x86/events/intel/cqm.c                   |  4 ++--
 arch/x86/events/intel/rapl.c                  |  4 ++--
 arch/x86/events/intel/uncore.c                | 10 +++++-----
 arch/x86/kernel/apb_timer.c                   |  2 +-
 arch/x86/kernel/apic/x2apic_cluster.c         |  2 +-
 arch/x86/kernel/hpet.c                        |  4 ++--
 arch/x86/kernel/tboot.c                       |  2 +-
 arch/x86/kvm/x86.c                            |  2 +-
 arch/x86/xen/enlighten.c                      |  4 ++--
 arch/xtensa/kernel/perf_event.c               |  2 +-
 drivers/bus/arm-cci.c                         |  2 +-
 drivers/bus/arm-ccn.c                         |  2 +-
 drivers/clocksource/arc_timer.c               |  2 +-
 drivers/clocksource/arm_arch_timer.c          |  2 +-
 drivers/clocksource/arm_global_timer.c        |  2 +-
 drivers/clocksource/dummy_timer.c             |  2 +-
 drivers/clocksource/exynos_mct.c              |  2 +-
 drivers/clocksource/jcore-pit.c               |  2 +-
 drivers/clocksource/metag_generic.c           |  2 +-
 drivers/clocksource/mips-gic-timer.c          |  4 ++--
 drivers/clocksource/qcom-timer.c              |  2 +-
 drivers/clocksource/time-armada-370-xp.c      |  2 +-
 drivers/clocksource/timer-atlas7.c            |  2 +-
 drivers/hwtracing/coresight/coresight-etm3x.c |  4 ++--
 drivers/hwtracing/coresight/coresight-etm4x.c |  4 ++--
 drivers/irqchip/irq-armada-370-xp.c           |  4 ++--
 drivers/irqchip/irq-bcm2836.c                 |  2 +-
 drivers/irqchip/irq-gic-v3.c                  |  4 ++--
 drivers/irqchip/irq-gic.c                     |  2 +-
 drivers/irqchip/irq-hip04.c                   |  2 +-
 drivers/leds/trigger/ledtrig-cpu.c            |  2 +-
 drivers/net/virtio_net.c                      |  4 ++--
 drivers/perf/arm_pmu.c                        |  2 +-
 drivers/xen/events/events_fifo.c              |  2 +-
 virt/kvm/arm/arch_timer.c                     |  2 +-
 virt/kvm/arm/vgic/vgic-init.c                 |  2 +-
 virt/kvm/kvm_main.c                           |  2 +-
 59 files changed, 77 insertions(+), 77 deletions(-)

diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 02d5e5e..895ae51 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -339,7 +339,7 @@ static int __init twd_local_timer_common_register(struct device_node *np)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_TWD_STARTING,
-				  "AP_ARM_TWD_STARTING",
+				  "arm/timer/twd:starting",
 				  twd_timer_starting_cpu, twd_timer_dying_cpu);
 
 	twd_get_clock(np);
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index ae2a018..8f8748a 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -148,7 +148,7 @@ static void __init armada_370_coherency_init(struct device_node *np)
 	of_node_put(cpu_config_np);
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_MVEBU_COHERENCY,
-				  "AP_ARM_MVEBU_COHERENCY",
+				  "arm/mvebu/coherency:starting",
 				  armada_xp_clear_l2_starting, NULL);
 exit:
 	set_cpu_coherent();
diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c
index 976d305..0a1e228 100644
--- a/arch/arm/mm/cache-l2x0-pmu.c
+++ b/arch/arm/mm/cache-l2x0-pmu.c
@@ -563,7 +563,7 @@ static __init int l2x0_pmu_init(void)
 
 	cpumask_set_cpu(0, &pmu_cpu);
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE,
-					"AP_PERF_ARM_L2X0_ONLINE", NULL,
+					"perf/arm/l2x0:online", NULL,
 					l2x0_pmu_offline_cpu);
 	if (ret)
 		goto out_pmu;
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index d1870c7..2290be3 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -683,7 +683,7 @@ static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
 
 	if (aux & L310_AUX_CTRL_FULL_LINE_ZERO)
 		cpuhp_setup_state(CPUHP_AP_ARM_L2X0_STARTING,
-				  "AP_ARM_L2X0_STARTING", l2c310_starting_cpu,
+				  "arm/l2x0:starting", l2c310_starting_cpu,
 				  l2c310_dying_cpu);
 }
 
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 0351f56..569d5a6 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -799,7 +799,7 @@ static int __init vfp_init(void)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_VFP_STARTING,
-				  "AP_ARM_VFP_STARTING", vfp_starting_cpu,
+				  "arm/vfp:starting", vfp_starting_cpu,
 				  vfp_dying_cpu);
 
 	vfp_vector = vfp_support_entry;
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 4986dc0..11d9f28 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -412,7 +412,7 @@ static int __init xen_guest_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 
 	return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
-				 "AP_ARM_XEN_STARTING", xen_starting_cpu,
+				 "arm/xen:starting", xen_starting_cpu,
 				 xen_dying_cpu);
 }
 early_initcall(xen_guest_init);
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 04de188..a211add 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -640,7 +640,7 @@ static int __init armv8_deprecated_init(void)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
-				  "AP_ARM64_ISNDEP_STARTING",
+				  "arm64/isndep:starting",
 				  run_all_insn_set_hw_mode, NULL);
 	register_insn_emulation_sysctl(ctl_abi);
 
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 605df76..2bd4264 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -140,7 +140,7 @@ static int clear_os_lock(unsigned int cpu)
 static int debug_monitors_init(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
-				 "CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING",
+				 "arm64/debug_monitors:starting",
 				 clear_os_lock, NULL);
 }
 postcore_initcall(debug_monitors_init);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 1b3c747..0296e79 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -1001,7 +1001,7 @@ static int __init arch_hw_breakpoint_init(void)
 	 * debugger will leave the world in a nice state for us.
 	 */
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
-			  "CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING",
+			  "perf/arm64/hw_breakpoint:starting",
 			  hw_breakpoint_reset, NULL);
 	if (ret)
 		pr_err("failed to register CPU hotplug notifier: %d\n", ret);
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 6355e97..6a9524a 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -475,7 +475,7 @@ static int __init bfin_pmu_init(void)
 
 	ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	if (!ret)
-		cpuhp_setup_state(CPUHP_PERF_BFIN, "PERF_BFIN",
+		cpuhp_setup_state(CPUHP_PERF_BFIN,"perf/bfin:starting",
 				  bfin_pmu_prepare_cpu, NULL);
 	return ret;
 }
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 052cba2..7e793eb 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -868,7 +868,7 @@ static int __init init_hw_perf_events(void)
 	metag_out32(0, PERF_COUNT(1));
 
 	cpuhp_setup_state(CPUHP_AP_PERF_METAG_STARTING,
-			  "AP_PERF_METAG_STARTING", metag_pmu_starting_cpu,
+			  "perf/metag:starting", metag_pmu_starting_cpu,
 			  NULL);
 
 	ret = perf_pmu_register(&pmu, metag_pmu->name, PERF_TYPE_RAW);
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index 7cf653e..5f928c3 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -713,7 +713,7 @@ static int __init cps_pm_init(void)
 		pr_warn("pm-cps: no CPC, clock & power gating unavailable\n");
 	}
 
-	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PM_CPS_CPU_ONLINE",
+	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mips/cps_pm:online",
 				 cps_pm_online_cpu, NULL);
 }
 arch_initcall(cps_pm_init);
diff --git a/arch/mips/oprofile/op_model_loongson3.c b/arch/mips/oprofile/op_model_loongson3.c
index 85f3ee4..d60d97b 100644
--- a/arch/mips/oprofile/op_model_loongson3.c
+++ b/arch/mips/oprofile/op_model_loongson3.c
@@ -186,7 +186,7 @@ static int __init loongson3_init(void)
 {
 	on_each_cpu(reset_counters, NULL, 1);
 	cpuhp_setup_state_nocalls(CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
-				  "AP_MIPS_OP_LOONGSON3_STARTING",
+				  "mips/oprofile/loongson3:starting",
 				  loongson3_starting_cpu, loongson3_dying_cpu);
 	save_perf_irq = perf_irq;
 	perf_irq = loongson3_perfcount_handler;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 0cb6bd8..b1099cb 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -944,7 +944,7 @@ void __init initmem_init(void)
 	 * _nocalls() + manual invocation is used because cpuhp is not yet
 	 * initialized for the boot CPU.
 	 */
-	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "POWER_NUMA_PREPARE",
+	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "powerpc/numa:prepare",
 				  ppc_numa_cpu_prepare, ppc_numa_cpu_dead);
 	for_each_present_cpu(cpu)
 		numa_setup_cpu(cpu);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 72c27b8..fd3e403 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2189,7 +2189,7 @@ int register_power_pmu(struct power_pmu *pmu)
 #endif /* CONFIG_PPC64 */
 
 	perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW);
-	cpuhp_setup_state(CPUHP_PERF_POWER, "PERF_POWER",
+	cpuhp_setup_state(CPUHP_PERF_POWER, "perf/powerpc:prepare",
 			  power_pmu_prepare_cpu, NULL);
 	return 0;
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 037c2a2..1aba10e 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -711,7 +711,7 @@ static int __init cpumf_pmu_init(void)
 		return rc;
 	}
 	return cpuhp_setup_state(CPUHP_AP_PERF_S390_CF_ONLINE,
-				 "AP_PERF_S390_CF_ONLINE",
+				 "perf/s390/cf:online",
 				 s390_pmu_online_cpu, s390_pmu_offline_cpu);
 }
 early_initcall(cpumf_pmu_init);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 763dec1..1c0b585 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1623,7 +1623,7 @@ static int __init init_cpum_sampling_pmu(void)
 		goto out;
 	}
 
-	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "AP_PERF_S390_SF_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "perf/s390/sf:online",
 			  s390_pmu_sf_online_cpu, s390_pmu_sf_offline_cpu);
 out:
 	return err;
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 40121d1..10820f6 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -371,7 +371,7 @@ static int __init init_vdso(void)
 
 	/* notifier priority > KVM */
 	return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
-				 "AP_X86_VDSO_VMA_ONLINE", vgetcpu_online, NULL);
+				 "x86/vdso/vma:online", vgetcpu_online, NULL);
 }
 subsys_initcall(init_vdso);
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index b26ee32..05612a2 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1010,7 +1010,7 @@ static __init int amd_ibs_init(void)
 	 * all online cpus.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-			  "AP_PERF_X86_AMD_IBS_STARTING",
+			  "perf/x86/amd/ibs:STARTING",
 			  x86_pmu_amd_ibs_starting_cpu,
 			  x86_pmu_amd_ibs_dying_cpu);
 
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 9842270..a6eee5a 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -291,7 +291,7 @@ static int __init amd_power_pmu_init(void)
 
 
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
-			  "AP_PERF_X86_AMD_POWER_ONLINE",
+			  "perf/x86/amd/power:online",
 			  power_cpu_init, power_cpu_exit);
 
 	ret = perf_pmu_register(&pmu_class, "power", -1);
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 65577f0..a0b1bdb 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -527,16 +527,16 @@ static int __init amd_uncore_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 	if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
-			      "PERF_X86_AMD_UNCORE_PREP",
+			      "perf/x86/amd/uncore:prepare",
 			      amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
 		goto fail_l2;
 
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
-			      "AP_PERF_X86_AMD_UNCORE_STARTING",
+			      "perf/x86/amd/uncore:starting",
 			      amd_uncore_cpu_starting, NULL))
 		goto fail_prep;
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
-			      "AP_PERF_X86_AMD_UNCORE_ONLINE",
+			      "perf/x86/amd/uncore:online",
 			      amd_uncore_cpu_online,
 			      amd_uncore_cpu_down_prepare))
 		goto fail_start;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index f1c2258..019c588 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1820,18 +1820,18 @@ static int __init init_hw_perf_events(void)
 	 * Install callbacks. Core will call them for each online
 	 * cpu.
 	 */
-	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "PERF_X86_PREPARE",
+	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "perf/x86:prepare",
 				x86_pmu_prepare_cpu, x86_pmu_dead_cpu);
 	if (err)
 		return err;
 
 	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING,
-				"AP_PERF_X86_STARTING", x86_pmu_starting_cpu,
+				"perf/x86:starting", x86_pmu_starting_cpu,
 				x86_pmu_dying_cpu);
 	if (err)
 		goto out;
 
-	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "AP_PERF_X86_ONLINE",
+	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "perf/x86:online",
 				x86_pmu_online_cpu, NULL);
 	if (err)
 		goto out1;
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 0c45cc8..8c00dc0 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -1747,9 +1747,9 @@ static int __init intel_cqm_init(void)
 	 * is enabled to avoid notifier leak.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
-			  "AP_PERF_X86_CQM_STARTING",
+			  "perf/x86/cqm:starting",
 			  intel_cqm_cpu_starting, NULL);
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "AP_PERF_X86_CQM_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online",
 			  NULL, intel_cqm_cpu_exit);
 
 out:
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 0a535ce..bd34124 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -803,13 +803,13 @@ static int __init rapl_pmu_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "PERF_X86_RAPL_PREP",
+	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
 				rapl_cpu_prepare, NULL);
 	if (ret)
 		goto out;
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
-				"AP_PERF_X86_RAPL_ONLINE",
+				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
 		goto out1;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index dbaaf7dc..97c246f 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1398,22 +1398,22 @@ static int __init intel_uncore_init(void)
 	 */
 	if (!cret) {
 	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
-					"PERF_X86_UNCORE_PREP",
-					uncore_cpu_prepare, NULL);
+				       "perf/x86/intel/uncore:prepare",
+				       uncore_cpu_prepare, NULL);
 		if (ret)
 			goto err;
 	} else {
 		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
-					  "PERF_X86_UNCORE_PREP",
+					  "perf/x86/intel/uncore:prepare",
 					  uncore_cpu_prepare, NULL);
 	}
 	first_init = 1;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
-			  "AP_PERF_X86_UNCORE_STARTING",
+			  "perf/x86/uncore:starting",
 			  uncore_cpu_starting, uncore_cpu_dying);
 	first_init = 0;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
-			  "AP_PERF_X86_UNCORE_ONLINE",
+			  "perf/x86/uncore:online",
 			  uncore_event_cpu_online, uncore_event_cpu_offline);
 	return 0;
 
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 456316f..202a781 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -234,7 +234,7 @@ static __init int apbt_late_init(void)
 	if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ||
 		!apb_timer_block_enabled)
 		return 0;
-	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "X86_APB_DEAD", NULL,
+	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "x86/apb:dead", NULL,
 				 apbt_cpu_dead);
 }
 fs_initcall(apbt_late_init);
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 200af5a..5a35f20 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -191,7 +191,7 @@ static int x2apic_cluster_probe(void)
 	if (!x2apic_mode)
 		return 0;
 
-	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare",
 				x2apic_prepare_cpu, x2apic_dead_cpu);
 	if (ret < 0) {
 		pr_err("Failed to register X2APIC_PREPARE\n");
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 274fab9..38c8fd6 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1051,11 +1051,11 @@ static __init int hpet_late_init(void)
 		return 0;
 
 	/* This notifier should be called after workqueue is ready */
-	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "AP_X86_HPET_ONLINE",
+	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "x86/hpet:online",
 				hpet_cpuhp_online, NULL);
 	if (ret)
 		return ret;
-	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "X86_HPET_DEAD", NULL,
+	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "x86/hpet:dead", NULL,
 				hpet_cpuhp_dead);
 	if (ret)
 		goto err_cpuhp;
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 8402907..b868fa1 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -408,7 +408,7 @@ static __init int tboot_late_init(void)
 	tboot_create_trampoline();
 
 	atomic_set(&ap_wfs_count, 0);
-	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "AP_X86_TBOOT_DYING", NULL,
+	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "x86/tboot:dying", NULL,
 			  tboot_dying_cpu);
 #ifdef CONFIG_DEBUG_FS
 	debugfs_create_file("tboot_log", S_IRUSR,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 445c51b..6414fa6c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5855,7 +5855,7 @@ static void kvm_timer_init(void)
 	}
 	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
 
-	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
 }
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ced7027..51ef952 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1529,11 +1529,11 @@ static int xen_cpuhp_setup(void)
 	int rc;
 
 	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
-				       "XEN_HVM_GUEST_PREPARE",
+				       "x86/xen/hvm_guest:prepare",
 				       xen_cpu_up_prepare, xen_cpu_dead);
 	if (rc >= 0) {
 		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					       "XEN_HVM_GUEST_ONLINE",
+					       "x86/xen/hvm_guest:online",
 					       xen_cpu_up_online, NULL);
 		if (rc < 0)
 			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 0fecc8a..ff1d813 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -422,7 +422,7 @@ static int __init xtensa_pmu_init(void)
 	int irq = irq_create_mapping(NULL, XCHAL_PROFILING_INTERRUPT);
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_XTENSA_STARTING,
-				"AP_PERF_XTENSA_STARTING", xtensa_pmu_setup,
+				"perf/xtensa:starting", xtensa_pmu_setup,
 				NULL);
 	if (ret) {
 		pr_err("xtensa_pmu: failed to register CPU-hotplug.\n");
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 2316333..c49da15 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -1796,7 +1796,7 @@ static int __init cci_platform_init(void)
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCI_ONLINE,
-				      "AP_PERF_ARM_CCI_ONLINE", NULL,
+				      "perf/arm/cci:online", NULL,
 				      cci_pmu_offline_cpu);
 	if (ret)
 		return ret;
diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c
index aee8346..4d6a2b7 100644
--- a/drivers/bus/arm-ccn.c
+++ b/drivers/bus/arm-ccn.c
@@ -1562,7 +1562,7 @@ static int __init arm_ccn_init(void)
 	int i, ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-				      "AP_PERF_ARM_CCN_ONLINE", NULL,
+				      "perf/arm/ccn:online", NULL,
 				      arm_ccn_pmu_offline_cpu);
 	if (ret)
 		return ret;
diff --git a/drivers/clocksource/arc_timer.c b/drivers/clocksource/arc_timer.c
index a49748d..2b7e871 100644
--- a/drivers/clocksource/arc_timer.c
+++ b/drivers/clocksource/arc_timer.c
@@ -309,7 +309,7 @@ static int __init arc_clockevent_setup(struct device_node *node)
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_ARC_TIMER_STARTING,
-				"AP_ARC_TIMER_STARTING",
+				"clockevents/arc/timer:starting",
 				arc_timer_starting_cpu,
 				arc_timer_dying_cpu);
 	if (ret) {
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 02fef68..cdeca85 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -738,7 +738,7 @@ static int __init arch_timer_register(void)
 
 	/* Register and immediately configure the timer on the boot CPU */
 	err = cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_STARTING,
-				"AP_ARM_ARCH_TIMER_STARTING",
+				"clockevents/arm/arch_timer:starting",
 				arch_timer_starting_cpu, arch_timer_dying_cpu);
 	if (err)
 		goto out_unreg_cpupm;
diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index 8da0329..bbfeb28 100644
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -316,7 +316,7 @@ static int __init global_timer_of_register(struct device_node *np)
 		goto out_irq;
 	
 	err = cpuhp_setup_state(CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
-				"AP_ARM_GLOBAL_TIMER_STARTING",
+				"clockevents/arm/global_timer:starting",
 				gt_starting_cpu, gt_dying_cpu);
 	if (err)
 		goto out_irq;
diff --git a/drivers/clocksource/dummy_timer.c b/drivers/clocksource/dummy_timer.c
index 89f1c2e..01f3f5a 100644
--- a/drivers/clocksource/dummy_timer.c
+++ b/drivers/clocksource/dummy_timer.c
@@ -34,7 +34,7 @@ static int dummy_timer_starting_cpu(unsigned int cpu)
 static int __init dummy_timer_register(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_DUMMY_TIMER_STARTING,
-				 "AP_DUMMY_TIMER_STARTING",
+				 "clockevents/dummy_timer:starting",
 				 dummy_timer_starting_cpu, NULL);
 }
 early_initcall(dummy_timer_register);
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 8f3488b..b45b72b 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -552,7 +552,7 @@ static int __init exynos4_timer_resources(struct device_node *np, void __iomem *
 
 	/* Install hotplug callbacks which configure the timer on this CPU */
 	err = cpuhp_setup_state(CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
-				"AP_EXYNOS4_MCT_TIMER_STARTING",
+				"clockevents/exynos4/mct_timer:starting",
 				exynos4_mct_starting_cpu,
 				exynos4_mct_dying_cpu);
 	if (err)
diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c
index 54e1665..4e4146f 100644
--- a/drivers/clocksource/jcore-pit.c
+++ b/drivers/clocksource/jcore-pit.c
@@ -240,7 +240,7 @@ static int __init jcore_pit_init(struct device_node *node)
 	}
 
 	cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
-			  "AP_JCORE_TIMER_STARTING",
+			  "clockevents/jcore:starting",
 			  jcore_pit_local_init, NULL);
 
 	return 0;
diff --git a/drivers/clocksource/metag_generic.c b/drivers/clocksource/metag_generic.c
index a80ab3e..172f43d 100644
--- a/drivers/clocksource/metag_generic.c
+++ b/drivers/clocksource/metag_generic.c
@@ -154,6 +154,6 @@ int __init metag_generic_timer_init(void)
 
 	/* Hook cpu boot to configure the CPU's timers */
 	return cpuhp_setup_state(CPUHP_AP_METAG_TIMER_STARTING,
-				 "AP_METAG_TIMER_STARTING",
+				 "clockevents/metag:starting",
 				 arch_timer_starting_cpu, NULL);
 }
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index 7a960cd..d927884 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -120,8 +120,8 @@ static int gic_clockevent_init(void)
 	}
 
 	cpuhp_setup_state(CPUHP_AP_MIPS_GIC_TIMER_STARTING,
-			  "AP_MIPS_GIC_TIMER_STARTING", gic_starting_cpu,
-			  gic_dying_cpu);
+			  "clockevents/mips/gic/timer:starting",
+			  gic_starting_cpu, gic_dying_cpu);
 	return 0;
 }
 
diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c
index 3283cfa..3bf65ff 100644
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -182,7 +182,7 @@ static int __init msm_timer_init(u32 dgt_hz, int sched_bits, int irq,
 	} else {
 		/* Install and invoke hotplug callbacks */
 		res = cpuhp_setup_state(CPUHP_AP_QCOM_TIMER_STARTING,
-					"AP_QCOM_TIMER_STARTING",
+					"clockevents/qcom/timer:starting",
 					msm_local_timer_starting_cpu,
 					msm_local_timer_dying_cpu);
 		if (res) {
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 3c39e6f..4440aef 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -320,7 +320,7 @@ static int __init armada_370_xp_timer_common_init(struct device_node *np)
 	}
 
 	res = cpuhp_setup_state(CPUHP_AP_ARMADA_TIMER_STARTING,
-				"AP_ARMADA_TIMER_STARTING",
+				"clockevents/armada:starting",
 				armada_370_xp_timer_starting_cpu,
 				armada_370_xp_timer_dying_cpu);
 	if (res) {
diff --git a/drivers/clocksource/timer-atlas7.c b/drivers/clocksource/timer-atlas7.c
index 4334e03..3c23e17 100644
--- a/drivers/clocksource/timer-atlas7.c
+++ b/drivers/clocksource/timer-atlas7.c
@@ -221,7 +221,7 @@ static int __init sirfsoc_clockevent_init(void)
 
 	/* Install and invoke hotplug callbacks */
 	return cpuhp_setup_state(CPUHP_AP_MARCO_TIMER_STARTING,
-				 "AP_MARCO_TIMER_STARTING",
+				 "clockevents/marco:starting",
 				 sirfsoc_local_timer_starting_cpu,
 				 sirfsoc_local_timer_dying_cpu);
 }
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index 3fe368b..a51b6b6 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -804,10 +804,10 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	if (!etm_count++) {
 		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
-					  "AP_ARM_CORESIGHT_STARTING",
+					  "arm/coresight:starting",
 					  etm_starting_cpu, etm_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT_ONLINE",
+						"arm/coresight:online",
 						etm_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 4db8d6a..5edc63f 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -987,10 +987,10 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 	if (!etm4_count++) {
 		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING,
-					  "AP_ARM_CORESIGHT4_STARTING",
+					  "arm/coresight4:starting",
 					  etm4_starting_cpu, etm4_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT4_ONLINE",
+						"arm/coresight4:online",
 						etm4_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 8bcee65..9d9c2c4 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -578,13 +578,13 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 #ifdef CONFIG_SMP
 		set_smp_cross_call(armada_mpic_send_doorbell);
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-					  "AP_IRQ_ARMADA_XP_STARTING",
+					  "irqchip/armada/ipi:starting",
 					  armada_xp_mpic_starting_cpu, NULL);
 #endif
 	} else {
 #ifdef CONFIG_SMP
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
-					  "AP_IRQ_ARMADA_CASC_STARTING",
+					  "irqchip/armada/cascade:starting",
 					  mpic_cascaded_starting_cpu, NULL);
 #endif
 		irq_set_chained_handler(parent_irq,
diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c
index d96b2c9..e7463e3 100644
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -245,7 +245,7 @@ bcm2836_arm_irqchip_smp_init(void)
 #ifdef CONFIG_SMP
 	/* Unmask IPIs to the boot CPU. */
 	cpuhp_setup_state(CPUHP_AP_IRQ_BCM2836_STARTING,
-			  "AP_IRQ_BCM2836_STARTING", bcm2836_cpu_starting,
+			  "irqchip/bcm2836:starting", bcm2836_cpu_starting,
 			  bcm2836_cpu_dying);
 
 	set_smp_cross_call(bcm2836_arm_irqchip_send_ipi);
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 26e1d7f..d696de1 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -633,8 +633,8 @@ static void gic_smp_init(void)
 {
 	set_smp_cross_call(gic_raise_softirq);
 	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GICV3_STARTING,
-				  "AP_IRQ_GICV3_STARTING", gic_starting_cpu,
-				  NULL);
+				  "irqchip/arm/gicv3:starting",
+				  gic_starting_cpu, NULL);
 }
 
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index d6c404b..1b1df4f 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1191,7 +1191,7 @@ static int __init __gic_init_bases(struct gic_chip_data *gic,
 		set_smp_cross_call(gic_raise_softirq);
 #endif
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
-					  "AP_IRQ_GIC_STARTING",
+					  "irqchip/arm/gic:starting",
 					  gic_starting_cpu, NULL);
 		set_handle_irq(gic_handle_irq);
 		if (static_key_true(&supports_deactivate))
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
index 021b0e0..c1b4ee9 100644
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -407,7 +407,7 @@ hip04_of_init(struct device_node *node, struct device_node *parent)
 	set_handle_irq(hip04_handle_irq);
 
 	hip04_irq_dist_init(&hip04_data);
-	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "AP_IRQ_HIP04_STARTING",
+	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "irqchip/hip04:starting",
 			  hip04_irq_starting_cpu, NULL);
 	return 0;
 }
diff --git a/drivers/leds/trigger/ledtrig-cpu.c b/drivers/leds/trigger/ledtrig-cpu.c
index 9719caf..a418964 100644
--- a/drivers/leds/trigger/ledtrig-cpu.c
+++ b/drivers/leds/trigger/ledtrig-cpu.c
@@ -127,7 +127,7 @@ static int __init ledtrig_cpu_init(void)
 
 	register_syscore_ops(&ledtrig_cpu_syscore_ops);
 
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_LEDTRIG_STARTING",
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "leds/trigger:starting",
 				ledtrig_online_cpu, ledtrig_prepare_down_cpu);
 	if (ret < 0)
 		pr_err("CPU hotplug notifier for ledtrig-cpu could not be registered: %d\n",
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5deeda6..4a10500 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2484,13 +2484,13 @@ static __init int virtio_net_driver_init(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "AP_VIRT_NET_ONLINE",
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "virtio/net:online",
 				      virtnet_cpu_online,
 				      virtnet_cpu_down_prep);
 	if (ret < 0)
 		goto out;
 	virtionet_online = ret;
-	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "VIRT_NET_DEAD",
+	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "virtio/net:dead",
 				      NULL, virtnet_cpu_dead);
 	if (ret)
 		goto err_dead;
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index b37b572..6d93358 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -1084,7 +1084,7 @@ static int arm_pmu_hp_init(void)
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_STARTING,
-				      "AP_PERF_ARM_STARTING",
+				      "perf/arm/pmu:starting",
 				      arm_perf_starting_cpu, NULL);
 	if (ret)
 		pr_err("CPU hotplug notifier for ARM PMU could not be registered: %d\n",
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 7ef27c6..c03f9c8 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -445,7 +445,7 @@ int __init xen_evtchn_fifo_init(void)
 	evtchn_ops = &evtchn_ops_fifo;
 
 	cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE,
-				  "CPUHP_XEN_EVTCHN_PREPARE",
+				  "xen/evtchn:prepare",
 				  xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead);
 out:
 	put_cpu();
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index ae95fc0..5b4f60d 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -456,7 +456,7 @@ int kvm_timer_hyp_init(void)
 	kvm_info("virtual timer IRQ%d\n", host_vtimer_irq);
 
 	cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING,
-			  "AP_KVM_ARM_TIMER_STARTING", kvm_timer_starting_cpu,
+			  "kvm/arm/timer:starting", kvm_timer_starting_cpu,
 			  kvm_timer_dying_cpu);
 	return err;
 }
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 8cebfbc..5114391 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -428,7 +428,7 @@ int kvm_vgic_hyp_init(void)
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
-				"AP_KVM_ARM_VGIC_INIT_STARTING",
+				"kvm/arm/vgic:starting",
 				vgic_init_cpu_starting, vgic_init_cpu_dying);
 	if (ret) {
 		kvm_err("Cannot register vgic CPU notifier\n");
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index de102ca..ec298b7 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3944,7 +3944,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 			goto out_free_1;
 	}
 
-	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "AP_KVM_STARTING",
+	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting",
 				      kvm_starting_cpu, kvm_dying_cpu);
 	if (r)
 		goto out_free_2;

[patch 08/10] coresight: etm3/4x: Consolidate hotplug state space

[Thomas Gleixner]

[-- Attachment #1: coresight--etm3-4x--Consolidate-hotplug-state-space.patch --]
[-- Type: text/plain, Size: 1576 bytes --]

Even if both drivers are compiled in only one instance can run on a given
system depending on the available tracer cell.

So having seperate hotplug states for them is pointless.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/hwtracing/coresight/coresight-etm4x.c |    4 ++--
 include/linux/cpuhotplug.h                    |    1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -986,7 +986,7 @@ static int etm4_probe(struct amba_device
 		dev_err(dev, "ETM arch init failed\n");
 
 	if (!etm4_count++) {
-		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING,
+		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
 					  "arm/coresight4:starting",
 					  etm4_starting_cpu, etm4_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
@@ -1037,7 +1037,7 @@ static int etm4_probe(struct amba_device
 
 err_arch_supported:
 	if (--etm4_count == 0) {
-		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING);
+		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
 		if (hp_online)
 			cpuhp_remove_state_nocalls(hp_online);
 	}
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -119,7 +119,6 @@ enum cpuhp_state {
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
-	CPUHP_AP_ARM_CORESIGHT4_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,

Re: [patch 08/10] coresight: etm3/4x: Consolidate hotplug state space

[Mathieu Poirier]

On 21 December 2016 at 12:19, Thomas Gleixner <tglx@linutronix.de> wrote:
> Even if both drivers are compiled in only one instance can run on a given
> system depending on the available tracer cell.

>From a HW point of view both ETM 3x and 4x can be found on the same
system but that wouldn't be practical.  As such,

Acked-by: Mathieu Poirier <mathieu.poirier@linaro.org>

>
> So having seperate hotplug states for them is pointless.
>
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
> ---
>  drivers/hwtracing/coresight/coresight-etm4x.c |    4 ++--
>  include/linux/cpuhotplug.h                    |    1 -
>  2 files changed, 2 insertions(+), 3 deletions(-)
>
> --- a/drivers/hwtracing/coresight/coresight-etm4x.c
> +++ b/drivers/hwtracing/coresight/coresight-etm4x.c
> @@ -986,7 +986,7 @@ static int etm4_probe(struct amba_device
>                 dev_err(dev, "ETM arch init failed\n");
>
>         if (!etm4_count++) {
> -               cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING,
> +               cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
>                                           "arm/coresight4:starting",
>                                           etm4_starting_cpu, etm4_dying_cpu);
>                 ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
> @@ -1037,7 +1037,7 @@ static int etm4_probe(struct amba_device
>
>  err_arch_supported:
>         if (--etm4_count == 0) {
> -               cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING);
> +               cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
>                 if (hp_online)
>                         cpuhp_remove_state_nocalls(hp_online);
>         }
> --- a/include/linux/cpuhotplug.h
> +++ b/include/linux/cpuhotplug.h
> @@ -119,7 +119,6 @@ enum cpuhp_state {
>         CPUHP_AP_DUMMY_TIMER_STARTING,
>         CPUHP_AP_ARM_XEN_STARTING,
>         CPUHP_AP_ARM_CORESIGHT_STARTING,
> -       CPUHP_AP_ARM_CORESIGHT4_STARTING,
>         CPUHP_AP_ARM64_ISNDEP_STARTING,
>         CPUHP_AP_SMPCFD_DYING,
>         CPUHP_AP_X86_TBOOT_DYING,
>
>

[tip:smp/urgent] coresight/etm3/4x: Consolidate hotplug state space

[tip-bot for Thomas Gleixner]

Commit-ID:  3ee93ef2527389b5e83039239e2a754dabd3a5e5
Gitweb:     http://git.kernel.org/tip/3ee93ef2527389b5e83039239e2a754dabd3a5e5
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:55 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:56 +0100

coresight/etm3/4x: Consolidate hotplug state space

Even if both drivers are compiled in only one instance can run on a given
system depending on the available tracer cell.

So having seperate hotplug states for them is pointless.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: http://lkml.kernel.org/r/20161221192112.162765484@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/hwtracing/coresight/coresight-etm4x.c | 4 ++--
 include/linux/cpuhotplug.h                    | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 5edc63f..031480f 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -986,7 +986,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(dev, "ETM arch init failed\n");
 
 	if (!etm4_count++) {
-		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING,
+		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
 					  "arm/coresight4:starting",
 					  etm4_starting_cpu, etm4_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
@@ -1037,7 +1037,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 err_arch_supported:
 	if (--etm4_count == 0) {
-		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING);
+		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
 		if (hp_online)
 			cpuhp_remove_state_nocalls(hp_online);
 	}
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 0d5ef85..4a938be 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -119,7 +119,6 @@ enum cpuhp_state {
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
-	CPUHP_AP_ARM_CORESIGHT4_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,

[tip:smp/urgent] coresight/etm3/4x: Consolidate hotplug state space

[tip-bot for Thomas Gleixner]

Commit-ID:  36e5b0e39194b09a10f19697fb9ea4ccc44eb166
Gitweb:     http://git.kernel.org/tip/36e5b0e39194b09a10f19697fb9ea4ccc44eb166
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:55 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:44 +0100

coresight/etm3/4x: Consolidate hotplug state space

Even if both drivers are compiled in only one instance can run on a given
system depending on the available tracer cell.

So having seperate hotplug states for them is pointless.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: http://lkml.kernel.org/r/20161221192112.162765484@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/hwtracing/coresight/coresight-etm4x.c | 4 ++--
 include/linux/cpuhotplug.h                    | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 5edc63f..031480f 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -986,7 +986,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(dev, "ETM arch init failed\n");
 
 	if (!etm4_count++) {
-		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING,
+		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
 					  "arm/coresight4:starting",
 					  etm4_starting_cpu, etm4_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
@@ -1037,7 +1037,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 err_arch_supported:
 	if (--etm4_count == 0) {
-		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING);
+		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
 		if (hp_online)
 			cpuhp_remove_state_nocalls(hp_online);
 	}
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 0d5ef85..4a938be 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -119,7 +119,6 @@ enum cpuhp_state {
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
-	CPUHP_AP_ARM_CORESIGHT4_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,

[patch 09/10] irqchip/gic: Consolidate hotplug state space

[Thomas Gleixner]

[-- Attachment #1: irqchip-gic--Consolidate-hotplug-state-space.patch --]
[-- Type: text/plain, Size: 1116 bytes --]

Even if both drivers are compiled in only one instance can run on a given
system depending on the available GIC version.

So having seperate hotplug states for them is pointless.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Marc Zyngier <marc.zyngier@arm.com>

---
 drivers/irqchip/irq-gic-v3.c |    2 +-
 include/linux/cpuhotplug.h   |    1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -632,7 +632,7 @@ static void gic_raise_softirq(const stru
 static void gic_smp_init(void)
 {
 	set_smp_cross_call(gic_raise_softirq);
-	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GICV3_STARTING,
+	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
 				  "irqchip/arm/gicv3:starting",
 				  gic_starting_cpu, NULL);
 }
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -80,7 +80,6 @@ enum cpuhp_state {
 	CPUHP_AP_SCHED_STARTING,
 	CPUHP_AP_RCUTREE_DYING,
 	CPUHP_AP_IRQ_GIC_STARTING,
-	CPUHP_AP_IRQ_GICV3_STARTING,
 	CPUHP_AP_IRQ_HIP04_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_ARMADA_CASC_STARTING,

[tip:smp/urgent] irqchip/gic: Consolidate hotplug state space

[tip-bot for Thomas Gleixner]

Commit-ID:  8fe1c3c1b44a5afe44279178afec705fad55c8c4
Gitweb:     http://git.kernel.org/tip/8fe1c3c1b44a5afe44279178afec705fad55c8c4
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:56 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:56 +0100

irqchip/gic: Consolidate hotplug state space

Even if both drivers are compiled in only one instance can run on a given
system depending on the available GIC version.

So having seperate hotplug states for them is pointless.


Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Link: http://lkml.kernel.org/r/20161221192112.252416267@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/irqchip/irq-gic-v3.c | 2 +-
 include/linux/cpuhotplug.h   | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index d696de1..c132f29 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -632,7 +632,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 static void gic_smp_init(void)
 {
 	set_smp_cross_call(gic_raise_softirq);
-	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GICV3_STARTING,
+	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
 				  "irqchip/arm/gicv3:starting",
 				  gic_starting_cpu, NULL);
 }
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 4a938be..45c786c 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -80,7 +80,6 @@ enum cpuhp_state {
 	CPUHP_AP_SCHED_STARTING,
 	CPUHP_AP_RCUTREE_DYING,
 	CPUHP_AP_IRQ_GIC_STARTING,
-	CPUHP_AP_IRQ_GICV3_STARTING,
 	CPUHP_AP_IRQ_HIP04_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_ARMADA_CASC_STARTING,

[tip:smp/urgent] irqchip/gic: Consolidate hotplug state space

[tip-bot for Thomas Gleixner]

Commit-ID:  6896bcd198df04777820cab4acc70142e87d5ce0
Gitweb:     http://git.kernel.org/tip/6896bcd198df04777820cab4acc70142e87d5ce0
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:56 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:44 +0100

irqchip/gic: Consolidate hotplug state space

Even if both drivers are compiled in only one instance can run on a given
system depending on the available GIC version.

So having seperate hotplug states for them is pointless.


Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Link: http://lkml.kernel.org/r/20161221192112.252416267@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/irqchip/irq-gic-v3.c | 2 +-
 include/linux/cpuhotplug.h   | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index d696de1..c132f29 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -632,7 +632,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 static void gic_smp_init(void)
 {
 	set_smp_cross_call(gic_raise_softirq);
-	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GICV3_STARTING,
+	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
 				  "irqchip/arm/gicv3:starting",
 				  gic_starting_cpu, NULL);
 }
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 4a938be..45c786c 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -80,7 +80,6 @@ enum cpuhp_state {
 	CPUHP_AP_SCHED_STARTING,
 	CPUHP_AP_RCUTREE_DYING,
 	CPUHP_AP_IRQ_GIC_STARTING,
-	CPUHP_AP_IRQ_GICV3_STARTING,
 	CPUHP_AP_IRQ_HIP04_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_ARMADA_CASC_STARTING,

[patch 10/10] irqchip/armada-xp: Consolidate hotplug state space

[Thomas Gleixner]

[-- Attachment #1: irqchip-armada-xp--Consolidate-hotplug-state-space.patch --]
[-- Type: text/plain, Size: 1213 bytes --]

The mpic is either the main interrupt controller or sits behind a GIC. But
there is no way that both variants are available on the same system.

Share the cpu hotplug state.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-armada-370-xp.c |    2 +-
 include/linux/cpuhotplug.h          |    1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -583,7 +583,7 @@ static int __init armada_370_xp_mpic_of_
 #endif
 	} else {
 #ifdef CONFIG_SMP
-		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
+		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 					  "irqchip/armada/cascade:starting",
 					  mpic_cascaded_starting_cpu, NULL);
 #endif
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -82,7 +82,6 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_GIC_STARTING,
 	CPUHP_AP_IRQ_HIP04_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-	CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_PERF_X86_UNCORE_STARTING,

Re: [patch 10/10] irqchip/armada-xp: Consolidate hotplug state space

[Thomas Petazzoni]

Hello,

On Wed, 21 Dec 2016 20:19:57 +0100, Thomas Gleixner wrote:
> The mpic is either the main interrupt controller or sits behind a GIC. But
> there is no way that both variants are available on the same system.

By "both variants", you mean the MPIC acting as the main interrupt
controller on one side, and the MPIC acting as a "cascaded" controller,
child of the GIC on the other side ?

If that's what you meant, then indeed it's correct.

Best regards,

Thomas
-- 
Thomas Petazzoni, CTO, Free Electrons
Embedded Linux and Kernel engineering
http://free-electrons.com

Re: [patch 10/10] irqchip/armada-xp: Consolidate hotplug state space

[Thomas Gleixner]

On Wed, 21 Dec 2016, Thomas Petazzoni wrote:
> On Wed, 21 Dec 2016 20:19:57 +0100, Thomas Gleixner wrote:
> > The mpic is either the main interrupt controller or sits behind a GIC. But
> > there is no way that both variants are available on the same system.
> 
> By "both variants", you mean the MPIC acting as the main interrupt
> controller on one side, and the MPIC acting as a "cascaded" controller,
> child of the GIC on the other side ?
> 
> If that's what you meant, then indeed it's correct.

Yes. I'll rephrase that.

Thanks,

	tglx

[tip:smp/urgent] irqchip/armada-xp: Consolidate hotplug state space

[tip-bot for Thomas Gleixner]

Commit-ID:  504dcba246a5bc451bd7f37d8da3de11310cad71
Gitweb:     http://git.kernel.org/tip/504dcba246a5bc451bd7f37d8da3de11310cad71
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:57 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Thu, 22 Dec 2016 11:37:56 +0100

irqchip/armada-xp: Consolidate hotplug state space

The mpic is either the main interrupt controller or is cascaded behind a
GIC. The mpic is single instance and the modes are mutually exclusive, so
there is no reason to have seperate cpu hotplug states.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Link: http://lkml.kernel.org/r/20161221192112.333161745@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/irqchip/irq-armada-370-xp.c | 2 +-
 include/linux/cpuhotplug.h          | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 9d9c2c4..eb0d4d4 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -583,7 +583,7 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 #endif
 	} else {
 #ifdef CONFIG_SMP
-		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
+		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 					  "irqchip/armada/cascade:starting",
 					  mpic_cascaded_starting_cpu, NULL);
 #endif
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 45c786c..20bfefb 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -82,7 +82,6 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_GIC_STARTING,
 	CPUHP_AP_IRQ_HIP04_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-	CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_PERF_X86_UNCORE_STARTING,

[tip:smp/urgent] irqchip/armada-xp: Consolidate hotplug state space

[tip-bot for Thomas Gleixner]

Commit-ID:  008b69e4d52f2cbee3ed0d0502edd78155000b1a
Gitweb:     http://git.kernel.org/tip/008b69e4d52f2cbee3ed0d0502edd78155000b1a
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Wed, 21 Dec 2016 20:19:57 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Sun, 25 Dec 2016 10:47:44 +0100

irqchip/armada-xp: Consolidate hotplug state space

The mpic is either the main interrupt controller or is cascaded behind a
GIC. The mpic is single instance and the modes are mutually exclusive, so
there is no reason to have seperate cpu hotplug states.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Link: http://lkml.kernel.org/r/20161221192112.333161745@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 drivers/irqchip/irq-armada-370-xp.c | 2 +-
 include/linux/cpuhotplug.h          | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 9d9c2c4..eb0d4d4 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -583,7 +583,7 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 #endif
 	} else {
 #ifdef CONFIG_SMP
-		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
+		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 					  "irqchip/armada/cascade:starting",
 					  mpic_cascaded_starting_cpu, NULL);
 #endif
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 45c786c..20bfefb 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -82,7 +82,6 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_GIC_STARTING,
 	CPUHP_AP_IRQ_HIP04_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-	CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_PERF_X86_UNCORE_STARTING,

Re: [patch 00/10] cpu/hotplug: Final cleanup

[Sam Ravnborg]

Hi Thomas.

On Wed, Dec 21, 2016 at 08:19:47PM +0100, Thomas Gleixner wrote:
> The following series completes the cpuhotplug rework stage ONE.

Just curious - what is the stage TWO (and onwards) plan?
lwn had some coverage of this work but I assume the
article is somewhat outdated.

	Sam

Re: [patch 00/10] cpu/hotplug: Final cleanup

[Thomas Gleixner]

On Thu, 22 Dec 2016, Sam Ravnborg wrote:
> Hi Thomas.
> 
> On Wed, Dec 21, 2016 at 08:19:47PM +0100, Thomas Gleixner wrote:
> > The following series completes the cpuhotplug rework stage ONE.
> 
> Just curious - what is the stage TWO (and onwards) plan?
> lwn had some coverage of this work but I assume the
> article is somewhat outdated.

Stage 2 is to consolidate all the archictecture code, i.e. reduce it to
really arch specific callbacks and keep all the other things
(synchronization, state settings etc.) in the core code.

After that we can do smart things like speed up the boot hotplug process:

prepare CPU1
kick CPU1

prepare CPU2
kick CPU2

....

prepare CPUN
kick CPUN

check CPU1 alive
bringup CPU1

...

check CPUN alive
bringup CPUN

That saves ~200ms per CPU on x86, which we now spend busy waiting for the
CPU to come alive.

There is more stuff which we can do in the long run like synchrounosly
letting CPUs bring up themself after the basic init/sync checks, but that
needs lot of surgery all over the place.

Thanks,

	tglx

Re: [patch 00/10] cpu/hotplug: Final cleanup

[Sam Ravnborg]

> > Just curious - what is the stage TWO (and onwards) plan?
> > lwn had some coverage of this work but I assume the
> > article is somewhat outdated.
> 
> Stage 2 is to consolidate all the archictecture code, i.e. reduce it to
> really arch specific callbacks and keep all the other things
> (synchronization, state settings etc.) in the core code.
> 
> After that we can do smart things like speed up the boot hotplug process:
> 
> prepare CPU1
> kick CPU1
> 
> prepare CPU2
> kick CPU2
> 
> ....
> 
> prepare CPUN
> kick CPUN
> 
> check CPU1 alive
> bringup CPU1
> 
> ...
> 
> check CPUN alive
> bringup CPUN
> 
> That saves ~200ms per CPU on x86, which we now spend busy waiting for the
> CPU to come alive.
> 
> There is more stuff which we can do in the long run like synchrounosly
> letting CPUs bring up themself after the basic init/sync checks, but that
> needs lot of surgery all over the place.

Thanks for the update - looking forward to follow this great clean-up!

	Sam