cpu/hotplug: Provide knobs to control SMT

commit 05736e4ac13c08a4a9b1ef2de26dd31a32cbee57 upstream.

Provide a command line and a sysfs knob to control SMT.

The command line options are:

 'nosmt':	Enumerate secondary threads, but do not online them

 'nosmt=force': Ignore secondary threads completely during enumeration
 		via MP table and ACPI/MADT.

The sysfs control file has the following states (read/write):

 'on':		 SMT is enabled. Secondary threads can be freely onlined
 'off':		 SMT is disabled. Secondary threads, even if enumerated
 		 cannot be onlined
 'forceoff':	 SMT is permanentely disabled. Writes to the control
 		 file are rejected.
 'notsupported': SMT is not supported by the CPU

The command line option 'nosmt' sets the sysfs control to 'off'. This
can be changed to 'on' to reenable SMT during runtime.

The command line option 'nosmt=force' sets the sysfs control to
'forceoff'. This cannot be changed during runtime.

When SMT is 'on' and the control file is changed to 'off' then all online
secondary threads are offlined and attempts to online a secondary thread
later on are rejected.

When SMT is 'off' and the control file is changed to 'on' then secondary
threads can be onlined again. The 'off' -> 'on' transition does not
automatically online the secondary threads.

When the control file is set to 'forceoff', the behaviour is the same as
setting it to 'off', but the operation is irreversible and later writes to
the control file are rejected.

When the control status is 'notsupported' then writes to the control file
are rejected.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

6 files changed, 215 insertions, 0 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 9c5e7732d24999..65d9b844ecfd4e 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -487,3 +487,23 @@ Description:	Information about CPU vulnerabilities
 		"Not affected"	  CPU is not affected by the vulnerability
 		"Vulnerable"	  CPU is affected and no mitigation in effect
 		"Mitigation: $M"  CPU is affected and mitigation $M is in effect
+
+What:		/sys/devices/system/cpu/smt
+		/sys/devices/system/cpu/smt/active
+		/sys/devices/system/cpu/smt/control
+Date:		June 2018
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Control Symetric Multi Threading (SMT)
+
+		active:  Tells whether SMT is active (enabled and siblings online)
+
+		control: Read/write interface to control SMT. Possible
+			 values:
+
+			 "on"		SMT is enabled
+			 "off"		SMT is disabled
+			 "forceoff"	SMT is force disabled. Cannot be changed.
+			 "notsupported" SMT is not supported by the CPU
+
+			 If control status is "forceoff" or "notsupported" writes
+			 are rejected.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 533ff5c68970ae..706960034a3659 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2687,6 +2687,14 @@
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
+			[KNL,x86] Disable symmetric multithreading (SMT).
+			nosmt=force: Force disable SMT, similar to disabling
+				     it in the BIOS except that some of the
+				     resource partitioning effects which are
+				     caused by having SMT enabled in the BIOS
+				     cannot be undone. Depending on the CPU
+				     type this might have a performance impact.
+
 	nospectre_v2	[X86] Disable all mitigations for the Spectre variant 2
 			(indirect branch prediction) vulnerability. System may
 			allow data leaks with this option, which is equivalent
diff --git a/arch/Kconfig b/arch/Kconfig
index 1aa59063f1fd9b..d1f2ed462ac84d 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -13,6 +13,9 @@ config KEXEC_CORE
 config HAVE_IMA_KEXEC
 	bool
 
+config HOTPLUG_SMT
+	bool
+
 config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 887d3a7bb64633..6b8065d718bdec 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -187,6 +187,7 @@ config X86
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
+	select HOTPLUG_SMT			if SMP
 	select IRQ_FORCED_THREADING
 	select NEED_SG_DMA_LENGTH
 	select PCI_LOCKLESS_CONFIG
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 1041da33ea591c..b79b3970e46b04 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -168,4 +168,17 @@ void cpuhp_report_idle_dead(void);
 static inline void cpuhp_report_idle_dead(void) { }
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
+enum cpuhp_smt_control {
+	CPU_SMT_ENABLED,
+	CPU_SMT_DISABLED,
+	CPU_SMT_FORCE_DISABLED,
+	CPU_SMT_NOT_SUPPORTED,
+};
+
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
+extern enum cpuhp_smt_control cpu_smt_control;
+#else
+# define cpu_smt_control		(CPU_SMT_ENABLED)
+#endif
+
 #endif /* _LINUX_CPU_H_ */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 90ca45b45e3a4f..fa10b5288527cc 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -933,6 +933,29 @@ EXPORT_SYMBOL(cpu_down);
 #define takedown_cpu		NULL
 #endif /*CONFIG_HOTPLUG_CPU*/
 
+#ifdef CONFIG_HOTPLUG_SMT
+enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+
+static int __init smt_cmdline_disable(char *str)
+{
+	cpu_smt_control = CPU_SMT_DISABLED;
+	if (str && !strcmp(str, "force")) {
+		pr_info("SMT: Force disabled\n");
+		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
+	}
+	return 0;
+}
+early_param("nosmt", smt_cmdline_disable);
+
+static inline bool cpu_smt_allowed(unsigned int cpu)
+{
+	return cpu_smt_control == CPU_SMT_ENABLED ||
+		topology_is_primary_thread(cpu);
+}
+#else
+static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
+#endif
+
 /**
  * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
  * @cpu: cpu that just started
@@ -1056,6 +1079,10 @@ static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
 		err = -EBUSY;
 		goto out;
 	}
+	if (!cpu_smt_allowed(cpu)) {
+		err = -EPERM;
+		goto out;
+	}
 
 	err = _cpu_up(cpu, 0, target);
 out:
@@ -1904,10 +1931,153 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
 	NULL
 };
 
+#ifdef CONFIG_HOTPLUG_SMT
+
+static const char *smt_states[] = {
+	[CPU_SMT_ENABLED]		= "on",
+	[CPU_SMT_DISABLED]		= "off",
+	[CPU_SMT_FORCE_DISABLED]	= "forceoff",
+	[CPU_SMT_NOT_SUPPORTED]		= "notsupported",
+};
+
+static ssize_t
+show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
+}
+
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = true;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	for_each_online_cpu(cpu) {
+		if (topology_is_primary_thread(cpu))
+			continue;
+		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+		if (ret)
+			break;
+		/*
+		 * As this needs to hold the cpu maps lock it's impossible
+		 * to call device_offline() because that ends up calling
+		 * cpu_down() which takes cpu maps lock. cpu maps lock
+		 * needs to be held as this might race against in kernel
+		 * abusers of the hotplug machinery (thermal management).
+		 *
+		 * So nothing would update device:offline state. That would
+		 * leave the sysfs entry stale and prevent onlining after
+		 * smt control has been changed to 'off' again. This is
+		 * called under the sysfs hotplug lock, so it is properly
+		 * serialized against the regular offline usage.
+		 */
+		cpuhp_offline_cpu_device(cpu);
+	}
+	if (!ret)
+		cpu_smt_control = ctrlval;
+	cpu_maps_update_done();
+	return ret;
+}
+
+static void cpuhp_smt_enable(void)
+{
+	cpu_maps_update_begin();
+	cpu_smt_control = CPU_SMT_ENABLED;
+	cpu_maps_update_done();
+}
+
+static ssize_t
+store_smt_control(struct device *dev, struct device_attribute *attr,
+		  const char *buf, size_t count)
+{
+	int ctrlval, ret;
+
+	if (sysfs_streq(buf, "on"))
+		ctrlval = CPU_SMT_ENABLED;
+	else if (sysfs_streq(buf, "off"))
+		ctrlval = CPU_SMT_DISABLED;
+	else if (sysfs_streq(buf, "forceoff"))
+		ctrlval = CPU_SMT_FORCE_DISABLED;
+	else
+		return -EINVAL;
+
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
+		return -EPERM;
+
+	if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		return -ENODEV;
+
+	ret = lock_device_hotplug_sysfs();
+	if (ret)
+		return ret;
+
+	if (ctrlval != cpu_smt_control) {
+		switch (ctrlval) {
+		case CPU_SMT_ENABLED:
+			cpuhp_smt_enable();
+			break;
+		case CPU_SMT_DISABLED:
+		case CPU_SMT_FORCE_DISABLED:
+			ret = cpuhp_smt_disable(ctrlval);
+			break;
+		}
+	}
+
+	unlock_device_hotplug();
+	return ret ? ret : count;
+}
+static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
+
+static ssize_t
+show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	bool active = topology_max_smt_threads() > 1;
+
+	return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
+}
+static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
+
+static struct attribute *cpuhp_smt_attrs[] = {
+	&dev_attr_control.attr,
+	&dev_attr_active.attr,
+	NULL
+};
+
+static const struct attribute_group cpuhp_smt_attr_group = {
+	.attrs = cpuhp_smt_attrs,
+	.name = "smt",
+	NULL
+};
+
+static int __init cpu_smt_state_init(void)
+{
+	if (!topology_smt_supported())
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+
+	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
+				  &cpuhp_smt_attr_group);
+}
+
+#else
+static inline int cpu_smt_state_init(void) { return 0; }
+#endif
+
 static int __init cpuhp_sysfs_init(void)
 {
 	int cpu, ret;
 
+	ret = cpu_smt_state_init();
+	if (ret)
+		return ret;
+
 	ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
 				 &cpuhp_cpu_root_attr_group);
 	if (ret)