Merge branch 'l1tf-final' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Merge L1 Terminal Fault fixes from Thomas Gleixner:
 "L1TF, aka L1 Terminal Fault, is yet another speculative hardware
  engineering trainwreck. It's a hardware vulnerability which allows
  unprivileged speculative access to data which is available in the
  Level 1 Data Cache when the page table entry controlling the virtual
  address, which is used for the access, has the Present bit cleared or
  other reserved bits set.

  If an instruction accesses a virtual address for which the relevant
  page table entry (PTE) has the Present bit cleared or other reserved
  bits set, then speculative execution ignores the invalid PTE and loads
  the referenced data if it is present in the Level 1 Data Cache, as if
  the page referenced by the address bits in the PTE was still present
  and accessible.

  While this is a purely speculative mechanism and the instruction will
  raise a page fault when it is retired eventually, the pure act of
  loading the data and making it available to other speculative
  instructions opens up the opportunity for side channel attacks to
  unprivileged malicious code, similar to the Meltdown attack.

  While Meltdown breaks the user space to kernel space protection, L1TF
  allows to attack any physical memory address in the system and the
  attack works across all protection domains. It allows an attack of SGX
  and also works from inside virtual machines because the speculation
  bypasses the extended page table (EPT) protection mechanism.

  The assoicated CVEs are: CVE-2018-3615, CVE-2018-3620, CVE-2018-3646

  The mitigations provided by this pull request include:

   - Host side protection by inverting the upper address bits of a non
     present page table entry so the entry points to uncacheable memory.

   - Hypervisor protection by flushing L1 Data Cache on VMENTER.

   - SMT (HyperThreading) control knobs, which allow to 'turn off' SMT
     by offlining the sibling CPU threads. The knobs are available on
     the kernel command line and at runtime via sysfs

   - Control knobs for the hypervisor mitigation, related to L1D flush
     and SMT control. The knobs are available on the kernel command line
     and at runtime via sysfs

   - Extensive documentation about L1TF including various degrees of
     mitigations.

  Thanks to all people who have contributed to this in various ways -
  patches, review, testing, backporting - and the fruitful, sometimes
  heated, but at the end constructive discussions.

  There is work in progress to provide other forms of mitigations, which
  might be less horrible performance wise for a particular kind of
  workloads, but this is not yet ready for consumption due to their
  complexity and limitations"

* 'l1tf-final' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (75 commits)
  x86/microcode: Allow late microcode loading with SMT disabled
  tools headers: Synchronise x86 cpufeatures.h for L1TF additions
  x86/mm/kmmio: Make the tracer robust against L1TF
  x86/mm/pat: Make set_memory_np() L1TF safe
  x86/speculation/l1tf: Make pmd/pud_mknotpresent() invert
  x86/speculation/l1tf: Invert all not present mappings
  cpu/hotplug: Fix SMT supported evaluation
  KVM: VMX: Tell the nested hypervisor to skip L1D flush on vmentry
  x86/speculation: Use ARCH_CAPABILITIES to skip L1D flush on vmentry
  x86/speculation: Simplify sysfs report of VMX L1TF vulnerability
  Documentation/l1tf: Remove Yonah processors from not vulnerable list
  x86/KVM/VMX: Don't set l1tf_flush_l1d from vmx_handle_external_intr()
  x86/irq: Let interrupt handlers set kvm_cpu_l1tf_flush_l1d
  x86: Don't include linux/irq.h from asm/hardirq.h
  x86/KVM/VMX: Introduce per-host-cpu analogue of l1tf_flush_l1d
  x86/irq: Demote irq_cpustat_t::__softirq_pending to u16
  x86/KVM/VMX: Move the l1tf_flush_l1d test to vmx_l1d_flush()
  x86/KVM/VMX: Replace 'vmx_l1d_flush_always' with 'vmx_l1d_flush_cond'
  x86/KVM/VMX: Don't set l1tf_flush_l1d to true from vmx_l1d_flush()
  cpu/hotplug: detect SMT disabled by BIOS
  ...

4 files changed, 283 insertions, 30 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index dd8634dde1ae..099fb20cd7be 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -60,6 +60,7 @@ struct cpuhp_cpu_state {
 	bool			rollback;
 	bool			single;
 	bool			bringup;
+	bool			booted_once;
 	struct hlist_node	*node;
 	struct hlist_node	*last;
 	enum cpuhp_state	cb_state;
@@ -342,6 +343,85 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
+#ifdef CONFIG_HOTPLUG_SMT
+enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+EXPORT_SYMBOL_GPL(cpu_smt_control);
+
+static bool cpu_smt_available __read_mostly;
+
+void __init cpu_smt_disable(bool force)
+{
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
+		cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		return;
+
+	if (force) {
+		pr_info("SMT: Force disabled\n");
+		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
+	} else {
+		cpu_smt_control = CPU_SMT_DISABLED;
+	}
+}
+
+/*
+ * The decision whether SMT is supported can only be done after the full
+ * CPU identification. Called from architecture code before non boot CPUs
+ * are brought up.
+ */
+void __init cpu_smt_check_topology_early(void)
+{
+	if (!topology_smt_supported())
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
+/*
+ * If SMT was disabled by BIOS, detect it here, after the CPUs have been
+ * brought online. This ensures the smt/l1tf sysfs entries are consistent
+ * with reality. cpu_smt_available is set to true during the bringup of non
+ * boot CPUs when a SMT sibling is detected. Note, this may overwrite
+ * cpu_smt_control's previous setting.
+ */
+void __init cpu_smt_check_topology(void)
+{
+	if (!cpu_smt_available)
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
+static int __init smt_cmdline_disable(char *str)
+{
+	cpu_smt_disable(str && !strcmp(str, "force"));
+	return 0;
+}
+early_param("nosmt", smt_cmdline_disable);
+
+static inline bool cpu_smt_allowed(unsigned int cpu)
+{
+	if (topology_is_primary_thread(cpu))
+		return true;
+
+	/*
+	 * If the CPU is not a 'primary' thread and the booted_once bit is
+	 * set then the processor has SMT support. Store this information
+	 * for the late check of SMT support in cpu_smt_check_topology().
+	 */
+	if (per_cpu(cpuhp_state, cpu).booted_once)
+		cpu_smt_available = true;
+
+	if (cpu_smt_control == CPU_SMT_ENABLED)
+		return true;
+
+	/*
+	 * On x86 it's required to boot all logical CPUs at least once so
+	 * that the init code can get a chance to set CR4.MCE on each
+	 * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
+	 * core will shutdown the machine.
+	 */
+	return !per_cpu(cpuhp_state, cpu).booted_once;
+}
+#else
+static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
+#endif
+
 static inline enum cpuhp_state
 cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
 {
@@ -422,6 +502,16 @@ static int bringup_wait_for_ap(unsigned int cpu)
 	stop_machine_unpark(cpu);
 	kthread_unpark(st->thread);
 
+	/*
+	 * SMT soft disabling on X86 requires to bring the CPU out of the
+	 * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit.  The
+	 * CPU marked itself as booted_once in cpu_notify_starting() so the
+	 * cpu_smt_allowed() check will now return false if this is not the
+	 * primary sibling.
+	 */
+	if (!cpu_smt_allowed(cpu))
+		return -ECANCELED;
+
 	if (st->target <= CPUHP_AP_ONLINE_IDLE)
 		return 0;
 
@@ -754,7 +844,6 @@ static int takedown_cpu(unsigned int cpu)
 
 	/* Park the smpboot threads */
 	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
-	smpboot_park_threads(cpu);
 
 	/*
 	 * Prevent irq alloc/free while the dying cpu reorganizes the
@@ -907,20 +996,19 @@ out:
 	return ret;
 }
 
+static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
+{
+	if (cpu_hotplug_disabled)
+		return -EBUSY;
+	return _cpu_down(cpu, 0, target);
+}
+
 static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
 {
 	int err;
 
 	cpu_maps_update_begin();
-
-	if (cpu_hotplug_disabled) {
-		err = -EBUSY;
-		goto out;
-	}
-
-	err = _cpu_down(cpu, 0, target);
-
-out:
+	err = cpu_down_maps_locked(cpu, target);
 	cpu_maps_update_done();
 	return err;
 }
@@ -949,6 +1037,7 @@ void notify_cpu_starting(unsigned int cpu)
 	int ret;
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
+	st->booted_once = true;
 	while (st->state < target) {
 		st->state++;
 		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
@@ -1058,6 +1147,10 @@ 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:
@@ -1332,7 +1425,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_AP_SMPBOOT_THREADS] = {
 		.name			= "smpboot/threads:online",
 		.startup.single		= smpboot_unpark_threads,
-		.teardown.single	= NULL,
+		.teardown.single	= smpboot_park_threads,
 	},
 	[CPUHP_AP_IRQ_AFFINITY_ONLINE] = {
 		.name			= "irq/affinity:online",
@@ -1911,10 +2004,172 @@ 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 void cpuhp_online_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = false;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+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 int cpuhp_smt_enable(void)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	cpu_smt_control = CPU_SMT_ENABLED;
+	for_each_present_cpu(cpu) {
+		/* Skip online CPUs and CPUs on offline nodes */
+		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+			continue;
+		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+		if (ret)
+			break;
+		/* See comment in cpuhp_smt_disable() */
+		cpuhp_online_cpu_device(cpu);
+	}
+	cpu_maps_update_done();
+	return ret;
+}
+
+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:
+			ret = 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)
+{
+	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)
@@ -2017,5 +2272,6 @@ void __init boot_cpu_init(void)
  */
 void __init boot_cpu_hotplug_init(void)
 {
-	per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
+	this_cpu_write(cpuhp_state.booted_once, true);
+	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c45de46fdf10..454adf9f8180 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5737,6 +5737,18 @@ int sched_cpu_activate(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
+#ifdef CONFIG_SCHED_SMT
+	/*
+	 * The sched_smt_present static key needs to be evaluated on every
+	 * hotplug event because at boot time SMT might be disabled when
+	 * the number of booted CPUs is limited.
+	 *
+	 * If then later a sibling gets hotplugged, then the key would stay
+	 * off and SMT scheduling would never be functional.
+	 */
+	if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
+		static_branch_enable_cpuslocked(&sched_smt_present);
+#endif
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {
@@ -5833,22 +5845,6 @@ int sched_cpu_dying(unsigned int cpu)
 }
 #endif
 
-#ifdef CONFIG_SCHED_SMT
-DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-
-static void sched_init_smt(void)
-{
-	/*
-	 * We've enumerated all CPUs and will assume that if any CPU
-	 * has SMT siblings, CPU0 will too.
-	 */
-	if (cpumask_weight(cpu_smt_mask(0)) > 1)
-		static_branch_enable(&sched_smt_present);
-}
-#else
-static inline void sched_init_smt(void) { }
-#endif
-
 void __init sched_init_smp(void)
 {
 	sched_init_numa();
@@ -5870,8 +5866,6 @@ void __init sched_init_smp(void)
 	init_sched_rt_class();
 	init_sched_dl_class();
 
-	sched_init_smt();
-
 	sched_smp_initialized = true;
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 309c93fcc604..b39fb596f6c1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5839,6 +5839,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 }
 
 #ifdef CONFIG_SCHED_SMT
+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 
 static inline void set_idle_cores(int cpu, int val)
 {
diff --git a/kernel/smp.c b/kernel/smp.c
index 084c8b3a2681..d86eec5f51c1 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -584,6 +584,8 @@ void __init smp_init(void)
 		num_nodes, (num_nodes > 1 ? "s" : ""),
 		num_cpus,  (num_cpus  > 1 ? "s" : ""));
 
+	/* Final decision about SMT support */
+	cpu_smt_check_topology();
 	/* Any cleanup work */
 	smp_cpus_done(setup_max_cpus);
 }