1 files changed, 134 insertions, 150 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a7fdf453d895..af44ebeb593f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -43,6 +43,7 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 
+#include <asm/intel-family.h>
 #include <asm/processor.h>
 #include <asm/traps.h>
 #include <asm/tlbflush.h>
@@ -53,6 +54,8 @@
 
 static DEFINE_MUTEX(mce_chrdev_read_mutex);
 
+static int mce_chrdev_open_count;	/* #times opened */
+
 #define mce_log_get_idx_check(p) \
 ({ \
 	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
@@ -120,14 +123,13 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
  */
-ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain);
 
 /* Do initial initialization of a struct mce */
 void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
-	m->tsc = rdtsc();
 	/* We hope get_seconds stays lockless */
 	m->time = get_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
@@ -135,6 +137,9 @@ void mce_setup(struct mce *m)
 	m->socketid = cpu_data(m->extcpu).phys_proc_id;
 	m->apicid = cpu_data(m->extcpu).initial_apicid;
 	rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);
+
+	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
+		rdmsrl(MSR_PPIN, m->ppin);
 }
 
 DEFINE_PER_CPU(struct mce, injectm);
@@ -207,19 +212,23 @@ EXPORT_SYMBOL_GPL(mce_inject_log);
 
 static struct notifier_block mce_srao_nb;
 
+static atomic_t num_notifiers;
+
 void mce_register_decode_chain(struct notifier_block *nb)
 {
-	/* Ensure SRAO notifier has the highest priority in the decode chain. */
-	if (nb != &mce_srao_nb && nb->priority == INT_MAX)
-		nb->priority -= 1;
+	atomic_inc(&num_notifiers);
+
+	WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
 
-	atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
+	blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
 }
 EXPORT_SYMBOL_GPL(mce_register_decode_chain);
 
 void mce_unregister_decode_chain(struct notifier_block *nb)
 {
-	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
+	atomic_dec(&num_notifiers);
+
+	blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
 }
 EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
 
@@ -270,17 +279,17 @@ struct mca_msr_regs msr_ops = {
 	.misc	= misc_reg
 };
 
-static void print_mce(struct mce *m)
+static void __print_mce(struct mce *m)
 {
-	int ret = 0;
-
-	pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
-	       m->extcpu, m->mcgstatus, m->bank, m->status);
+	pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n",
+		 m->extcpu,
+		 (m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""),
+		 m->mcgstatus, m->bank, m->status);
 
 	if (m->ip) {
 		pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ",
 			!(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
-				m->cs, m->ip);
+			m->cs, m->ip);
 
 		if (m->cs == __KERNEL_CS)
 			print_symbol("{%s}", m->ip);
@@ -308,15 +317,11 @@ static void print_mce(struct mce *m)
 	pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
 		m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
 		cpu_data(m->extcpu).microcode);
+}
 
-	/*
-	 * Print out human-readable details about the MCE error,
-	 * (if the CPU has an implementation for that)
-	 */
-	ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
-	if (ret == NOTIFY_STOP)
-		return;
-
+static void print_mce(struct mce *m)
+{
+	__print_mce(m);
 	pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
 }
 
@@ -499,7 +504,7 @@ int mce_available(struct cpuinfo_x86 *c)
 
 static void mce_schedule_work(void)
 {
-	if (!mce_gen_pool_empty() && keventd_up())
+	if (!mce_gen_pool_empty())
 		schedule_work(&mce_work);
 }
 
@@ -566,7 +571,37 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 }
 static struct notifier_block mce_srao_nb = {
 	.notifier_call	= srao_decode_notifier,
-	.priority = INT_MAX,
+	.priority	= MCE_PRIO_SRAO,
+};
+
+static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
+				void *data)
+{
+	struct mce *m = (struct mce *)data;
+
+	if (!m)
+		return NOTIFY_DONE;
+
+	/*
+	 * Run the default notifier if we have only the SRAO
+	 * notifier and us registered.
+	 */
+	if (atomic_read(&num_notifiers) > 2)
+		return NOTIFY_DONE;
+
+	/* Don't print when mcelog is running */
+	if (mce_chrdev_open_count > 0)
+		return NOTIFY_DONE;
+
+	__print_mce(m);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block mce_default_nb = {
+	.notifier_call	= mce_default_notifier,
+	/* lowest prio, we want it to run last. */
+	.priority	= MCE_PRIO_LOWEST,
 };
 
 /*
@@ -667,6 +702,9 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 
 	mce_gather_info(&m, NULL);
 
+	if (flags & MCP_TIMESTAMP)
+		m.tsc = rdtsc();
+
 	for (i = 0; i < mca_cfg.banks; i++) {
 		if (!mce_banks[i].ctl || !test_bit(i, *b))
 			continue;
@@ -674,14 +712,12 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		m.misc = 0;
 		m.addr = 0;
 		m.bank = i;
-		m.tsc = 0;
 
 		barrier();
 		m.status = mce_rdmsrl(msr_ops.status(i));
 		if (!(m.status & MCI_STATUS_VAL))
 			continue;
 
-
 		/*
 		 * Uncorrected or signalled events are handled by the exception
 		 * handler when it is enabled, so don't process those here.
@@ -696,9 +732,6 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 
 		mce_read_aux(&m, i);
 
-		if (!(flags & MCP_TIMESTAMP))
-			m.tsc = 0;
-
 		severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
 
 		if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m))
@@ -1109,6 +1142,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		goto out;
 
 	mce_gather_info(&m, regs);
+	m.tsc = rdtsc();
 
 	final = this_cpu_ptr(&mces_seen);
 	*final = m;
@@ -1275,41 +1309,6 @@ int memory_failure(unsigned long pfn, int vector, int flags)
 #endif
 
 /*
- * Action optional processing happens here (picking up
- * from the list of faulting pages that do_machine_check()
- * placed into the genpool).
- */
-static void mce_process_work(struct work_struct *dummy)
-{
-	mce_gen_pool_process();
-}
-
-#ifdef CONFIG_X86_MCE_INTEL
-/***
- * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog
- * @cpu: The CPU on which the event occurred.
- * @status: Event status information
- *
- * This function should be called by the thermal interrupt after the
- * event has been processed and the decision was made to log the event
- * further.
- *
- * The status parameter will be saved to the 'status' field of 'struct mce'
- * and historically has been the register value of the
- * MSR_IA32_THERMAL_STATUS (Intel) msr.
- */
-void mce_log_therm_throt_event(__u64 status)
-{
-	struct mce m;
-
-	mce_setup(&m);
-	m.bank = MCE_THERMAL_BANK;
-	m.status = status;
-	mce_log(&m);
-}
-#endif /* CONFIG_X86_MCE_INTEL */
-
-/*
  * Periodic polling timer for "silent" machine check errors.  If the
  * poller finds an MCE, poll 2x faster.  When the poller finds no more
  * errors, poll 2x slower (up to check_interval seconds).
@@ -1326,20 +1325,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval)
 
 static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
 
-static void __restart_timer(struct timer_list *t, unsigned long interval)
+static void __start_timer(struct timer_list *t, unsigned long interval)
 {
 	unsigned long when = jiffies + interval;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
-	if (timer_pending(t)) {
-		if (time_before(when, t->expires))
-			mod_timer(t, when);
-	} else {
-		t->expires = round_jiffies(when);
-		add_timer_on(t, smp_processor_id());
-	}
+	if (!timer_pending(t) || time_before(when, t->expires))
+		mod_timer(t, round_jiffies(when));
 
 	local_irq_restore(flags);
 }
@@ -1355,7 +1349,7 @@ static void mce_timer_fn(unsigned long data)
 	iv = __this_cpu_read(mce_next_interval);
 
 	if (mce_available(this_cpu_ptr(&cpu_info))) {
-		machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_poll_banks));
+		machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));
 
 		if (mce_intel_cmci_poll()) {
 			iv = mce_adjust_timer(iv);
@@ -1374,7 +1368,7 @@ static void mce_timer_fn(unsigned long data)
 
 done:
 	__this_cpu_write(mce_next_interval, iv);
-	__restart_timer(t, iv);
+	__start_timer(t, iv);
 }
 
 /*
@@ -1385,7 +1379,7 @@ void mce_timer_kick(unsigned long interval)
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned long iv = __this_cpu_read(mce_next_interval);
 
-	__restart_timer(t, interval);
+	__start_timer(t, interval);
 
 	if (interval < iv)
 		__this_cpu_write(mce_next_interval, interval);
@@ -1732,17 +1726,23 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
 	}
 }
 
-static void mce_start_timer(unsigned int cpu, struct timer_list *t)
+static void mce_start_timer(struct timer_list *t)
 {
 	unsigned long iv = check_interval * HZ;
 
 	if (mca_cfg.ignore_ce || !iv)
 		return;
 
-	per_cpu(mce_next_interval, cpu) = iv;
+	this_cpu_write(mce_next_interval, iv);
+	__start_timer(t, iv);
+}
+
+static void __mcheck_cpu_setup_timer(void)
+{
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
+	unsigned int cpu = smp_processor_id();
 
-	t->expires = round_jiffies(jiffies + iv);
-	add_timer_on(t, cpu);
+	setup_pinned_timer(t, mce_timer_fn, cpu);
 }
 
 static void __mcheck_cpu_init_timer(void)
@@ -1751,7 +1751,7 @@ static void __mcheck_cpu_init_timer(void)
 	unsigned int cpu = smp_processor_id();
 
 	setup_pinned_timer(t, mce_timer_fn, cpu);
-	mce_start_timer(cpu, t);
+	mce_start_timer(t);
 }
 
 /* Handle unconfigured int18 (should never happen) */
@@ -1796,7 +1796,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
-	__mcheck_cpu_init_timer();
+	__mcheck_cpu_setup_timer();
 }
 
 /*
@@ -1823,7 +1823,6 @@ void mcheck_cpu_clear(struct cpuinfo_x86 *c)
  */
 
 static DEFINE_SPINLOCK(mce_chrdev_state_lock);
-static int mce_chrdev_open_count;	/* #times opened */
 static int mce_chrdev_open_exclu;	/* already open exclusive? */
 
 static int mce_chrdev_open(struct inode *inode, struct file *file)
@@ -2138,9 +2137,10 @@ int __init mcheck_init(void)
 {
 	mcheck_intel_therm_init();
 	mce_register_decode_chain(&mce_srao_nb);
+	mce_register_decode_chain(&mce_default_nb);
 	mcheck_vendor_init_severity();
 
-	INIT_WORK(&mce_work, mce_process_work);
+	INIT_WORK(&mce_work, mce_gen_pool_process);
 	init_irq_work(&mce_irq_work, mce_irq_work_cb);
 
 	return 0;
@@ -2255,8 +2255,6 @@ static struct bus_type mce_subsys = {
 
 DEFINE_PER_CPU(struct device *, mce_device);
 
-void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
-
 static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
 {
 	return container_of(attr, struct mce_bank, attr);
@@ -2409,6 +2407,10 @@ static int mce_device_create(unsigned int cpu)
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
 
+	dev = per_cpu(mce_device, cpu);
+	if (dev)
+		return 0;
+
 	dev = kzalloc(sizeof *dev, GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
@@ -2468,28 +2470,25 @@ static void mce_device_remove(unsigned int cpu)
 }
 
 /* Make sure there are no machine checks on offlined CPUs. */
-static void mce_disable_cpu(void *h)
+static void mce_disable_cpu(void)
 {
-	unsigned long action = *(unsigned long *)h;
-
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
-	if (!(action & CPU_TASKS_FROZEN))
+	if (!cpuhp_tasks_frozen)
 		cmci_clear();
 
 	vendor_disable_error_reporting();
 }
 
-static void mce_reenable_cpu(void *h)
+static void mce_reenable_cpu(void)
 {
-	unsigned long action = *(unsigned long *)h;
 	int i;
 
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
-	if (!(action & CPU_TASKS_FROZEN))
+	if (!cpuhp_tasks_frozen)
 		cmci_reenable();
 	for (i = 0; i < mca_cfg.banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
@@ -2499,45 +2498,43 @@ static void mce_reenable_cpu(void *h)
 	}
 }
 
-/* Get notified when a cpu comes on/off. Be hotplug friendly. */
-static int
-mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+static int mce_cpu_dead(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	struct timer_list *t = &per_cpu(mce_timer, cpu);
+	mce_intel_hcpu_update(cpu);
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-		mce_device_create(cpu);
-		if (threshold_cpu_callback)
-			threshold_cpu_callback(action, cpu);
-		break;
-	case CPU_DEAD:
-		if (threshold_cpu_callback)
-			threshold_cpu_callback(action, cpu);
-		mce_device_remove(cpu);
-		mce_intel_hcpu_update(cpu);
+	/* intentionally ignoring frozen here */
+	if (!cpuhp_tasks_frozen)
+		cmci_rediscover();
+	return 0;
+}
 
-		/* intentionally ignoring frozen here */
-		if (!(action & CPU_TASKS_FROZEN))
-			cmci_rediscover();
-		break;
-	case CPU_DOWN_PREPARE:
-		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
-		del_timer_sync(t);
-		break;
-	case CPU_DOWN_FAILED:
-		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
-		mce_start_timer(cpu, t);
-		break;
-	}
+static int mce_cpu_online(unsigned int cpu)
+{
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
+	int ret;
 
-	return NOTIFY_OK;
+	mce_device_create(cpu);
+
+	ret = mce_threshold_create_device(cpu);
+	if (ret) {
+		mce_device_remove(cpu);
+		return ret;
+	}
+	mce_reenable_cpu();
+	mce_start_timer(t);
+	return 0;
 }
 
-static struct notifier_block mce_cpu_notifier = {
-	.notifier_call = mce_cpu_callback,
-};
+static int mce_cpu_pre_down(unsigned int cpu)
+{
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
+
+	mce_disable_cpu();
+	del_timer_sync(t);
+	mce_threshold_remove_device(cpu);
+	mce_device_remove(cpu);
+	return 0;
+}
 
 static __init void mce_init_banks(void)
 {
@@ -2559,8 +2556,8 @@ static __init void mce_init_banks(void)
 
 static __init int mcheck_init_device(void)
 {
+	enum cpuhp_state hp_online;
 	int err;
-	int i = 0;
 
 	if (!mce_available(&boot_cpu_data)) {
 		err = -EIO;
@@ -2578,23 +2575,16 @@ static __init int mcheck_init_device(void)
 	if (err)
 		goto err_out_mem;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(i) {
-		err = mce_device_create(i);
-		if (err) {
-			/*
-			 * Register notifier anyway (and do not unreg it) so
-			 * that we don't leave undeleted timers, see notifier
-			 * callback above.
-			 */
-			__register_hotcpu_notifier(&mce_cpu_notifier);
-			cpu_notifier_register_done();
-			goto err_device_create;
-		}
-	}
+	err = cpuhp_setup_state(CPUHP_X86_MCE_DEAD, "x86/mce:dead", NULL,
+				mce_cpu_dead);
+	if (err)
+		goto err_out_mem;
 
-	__register_hotcpu_notifier(&mce_cpu_notifier);
-	cpu_notifier_register_done();
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online",
+				mce_cpu_online, mce_cpu_pre_down);
+	if (err < 0)
+		goto err_out_online;
+	hp_online = err;
 
 	register_syscore_ops(&mce_syscore_ops);
 
@@ -2607,16 +2597,10 @@ static __init int mcheck_init_device(void)
 
 err_register:
 	unregister_syscore_ops(&mce_syscore_ops);
+	cpuhp_remove_state(hp_online);
 
-err_device_create:
-	/*
-	 * We didn't keep track of which devices were created above, but
-	 * even if we had, the set of online cpus might have changed.
-	 * Play safe and remove for every possible cpu, since
-	 * mce_device_remove() will do the right thing.
-	 */
-	for_each_possible_cpu(i)
-		mce_device_remove(i);
+err_out_online:
+	cpuhp_remove_state(CPUHP_X86_MCE_DEAD);
 
 err_out_mem:
 	free_cpumask_var(mce_device_initialized);