x86/mce: Factor out and deprecate the /dev/mcelog driver

Move all code relating to /dev/mcelog to a separate source file.
/dev/mcelog driver can now operate from the machine check notifier with
lowest prio.

Signed-off-by: Tony Luck <tony.luck@intel.com>
[ Move the mce_helper and trigger functionality behind CONFIG_X86_MCELOG_LEGACY. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/20170327093304.10683-6-bp@alien8.de
[ Renamed CONFIG_X86_MCELOG to CONFIG_X86_MCELOG_LEGACY. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 426 insertions, 364 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cc98d5a294ee..43e6bac6b950 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1043,6 +1043,14 @@ config X86_MCE
 	  The action the kernel takes depends on the severity of the problem,
 	  ranging from warning messages to halting the machine.
 
+config X86_MCELOG_LEGACY
+	bool "Support for deprecated /dev/mcelog character device"
+	depends on X86_MCE
+	---help---
+	  Enable support for /dev/mcelog which is needed by the old mcelog
+	  userspace logging daemon. Consider switching to the new generation
+	  rasdaemon solution.
+
 config X86_MCE_INTEL
 	def_bool y
 	prompt "Intel MCE features"
@@ -1072,7 +1080,7 @@ config X86_MCE_THRESHOLD
 	def_bool y
 
 config X86_MCE_INJECT
-	depends on X86_MCE && X86_LOCAL_APIC
+	depends on X86_MCE && X86_LOCAL_APIC && X86_MCELOG_LEGACY
 	tristate "Machine check injector support"
 	---help---
 	  Provide support for injecting machine checks for testing purposes.
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c5ae545d27d8..4fd5195deed0 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -196,6 +196,7 @@ enum mce_notifier_prios {
 	MCE_PRIO_EXTLOG		= INT_MAX - 2,
 	MCE_PRIO_NFIT		= INT_MAX - 3,
 	MCE_PRIO_EDAC		= INT_MAX - 4,
+	MCE_PRIO_MCELOG		= 1,
 	MCE_PRIO_LOWEST		= 0,
 };
 
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index a3311c886194..43051f0777d4 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -9,3 +9,5 @@ obj-$(CONFIG_X86_MCE_INJECT)	+= mce-inject.o
 obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
 
 obj-$(CONFIG_ACPI_APEI)		+= mce-apei.o
+
+obj-$(CONFIG_X86_MCELOG_LEGACY)	+= dev-mcelog.o
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
new file mode 100644
index 000000000000..9c632cb88546
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -0,0 +1,397 @@
+/*
+ * /dev/mcelog driver
+ *
+ * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs.
+ * Rest from unknown author(s).
+ * 2004 Andi Kleen. Rewrote most of it.
+ * Copyright 2008 Intel Corporation
+ * Author: Andi Kleen
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/miscdevice.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/poll.h>
+
+#include "mce-internal.h"
+
+static DEFINE_MUTEX(mce_chrdev_read_mutex);
+
+static char mce_helper[128];
+static char *mce_helper_argv[2] = { mce_helper, NULL };
+
+#define mce_log_get_idx_check(p) \
+({ \
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
+			 !lockdep_is_held(&mce_chrdev_read_mutex), \
+			 "suspicious mce_log_get_idx_check() usage"); \
+	smp_load_acquire(&(p)); \
+})
+
+/*
+ * Lockless MCE logging infrastructure.
+ * This avoids deadlocks on printk locks without having to break locks. Also
+ * separate MCEs from kernel messages to avoid bogus bug reports.
+ */
+
+static struct mce_log_buffer mcelog = {
+	.signature	= MCE_LOG_SIGNATURE,
+	.len		= MCE_LOG_LEN,
+	.recordlen	= sizeof(struct mce),
+};
+
+static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
+
+/* User mode helper program triggered by machine check event */
+extern char			mce_helper[128];
+
+static int dev_mce_log(struct notifier_block *nb, unsigned long val,
+				void *data)
+{
+	struct mce *mce = (struct mce *)data;
+	unsigned int next, entry;
+
+	wmb();
+	for (;;) {
+		entry = mce_log_get_idx_check(mcelog.next);
+		for (;;) {
+
+			/*
+			 * When the buffer fills up discard new entries.
+			 * Assume that the earlier errors are the more
+			 * interesting ones:
+			 */
+			if (entry >= MCE_LOG_LEN) {
+				set_bit(MCE_OVERFLOW,
+					(unsigned long *)&mcelog.flags);
+				return NOTIFY_OK;
+			}
+			/* Old left over entry. Skip: */
+			if (mcelog.entry[entry].finished) {
+				entry++;
+				continue;
+			}
+			break;
+		}
+		smp_rmb();
+		next = entry + 1;
+		if (cmpxchg(&mcelog.next, entry, next) == entry)
+			break;
+	}
+	memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
+	wmb();
+	mcelog.entry[entry].finished = 1;
+	wmb();
+
+	/* wake processes polling /dev/mcelog */
+	wake_up_interruptible(&mce_chrdev_wait);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dev_mcelog_nb = {
+	.notifier_call	= dev_mce_log,
+	.priority	= MCE_PRIO_MCELOG,
+};
+
+static void mce_do_trigger(struct work_struct *work)
+{
+	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
+}
+
+static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
+
+
+void mce_work_trigger(void)
+{
+	if (mce_helper[0])
+		schedule_work(&mce_trigger_work);
+}
+
+static ssize_t
+show_trigger(struct device *s, struct device_attribute *attr, char *buf)
+{
+	strcpy(buf, mce_helper);
+	strcat(buf, "\n");
+	return strlen(mce_helper) + 1;
+}
+
+static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
+				const char *buf, size_t siz)
+{
+	char *p;
+
+	strncpy(mce_helper, buf, sizeof(mce_helper));
+	mce_helper[sizeof(mce_helper)-1] = 0;
+	p = strchr(mce_helper, '\n');
+
+	if (p)
+		*p = 0;
+
+	return strlen(mce_helper) + !!p;
+}
+
+DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
+
+/*
+ * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log.
+ */
+
+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)
+{
+	spin_lock(&mce_chrdev_state_lock);
+
+	if (mce_chrdev_open_exclu ||
+	    (mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
+		spin_unlock(&mce_chrdev_state_lock);
+
+		return -EBUSY;
+	}
+
+	if (file->f_flags & O_EXCL)
+		mce_chrdev_open_exclu = 1;
+	mce_chrdev_open_count++;
+
+	spin_unlock(&mce_chrdev_state_lock);
+
+	return nonseekable_open(inode, file);
+}
+
+static int mce_chrdev_release(struct inode *inode, struct file *file)
+{
+	spin_lock(&mce_chrdev_state_lock);
+
+	mce_chrdev_open_count--;
+	mce_chrdev_open_exclu = 0;
+
+	spin_unlock(&mce_chrdev_state_lock);
+
+	return 0;
+}
+
+static void collect_tscs(void *data)
+{
+	unsigned long *cpu_tsc = (unsigned long *)data;
+
+	cpu_tsc[smp_processor_id()] = rdtsc();
+}
+
+static int mce_apei_read_done;
+
+/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
+static int __mce_read_apei(char __user **ubuf, size_t usize)
+{
+	int rc;
+	u64 record_id;
+	struct mce m;
+
+	if (usize < sizeof(struct mce))
+		return -EINVAL;
+
+	rc = apei_read_mce(&m, &record_id);
+	/* Error or no more MCE record */
+	if (rc <= 0) {
+		mce_apei_read_done = 1;
+		/*
+		 * When ERST is disabled, mce_chrdev_read() should return
+		 * "no record" instead of "no device."
+		 */
+		if (rc == -ENODEV)
+			return 0;
+		return rc;
+	}
+	rc = -EFAULT;
+	if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
+		return rc;
+	/*
+	 * In fact, we should have cleared the record after that has
+	 * been flushed to the disk or sent to network in
+	 * /sbin/mcelog, but we have no interface to support that now,
+	 * so just clear it to avoid duplication.
+	 */
+	rc = apei_clear_mce(record_id);
+	if (rc) {
+		mce_apei_read_done = 1;
+		return rc;
+	}
+	*ubuf += sizeof(struct mce);
+
+	return 0;
+}
+
+static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
+				size_t usize, loff_t *off)
+{
+	char __user *buf = ubuf;
+	unsigned long *cpu_tsc;
+	unsigned prev, next;
+	int i, err;
+
+	cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
+	if (!cpu_tsc)
+		return -ENOMEM;
+
+	mutex_lock(&mce_chrdev_read_mutex);
+
+	if (!mce_apei_read_done) {
+		err = __mce_read_apei(&buf, usize);
+		if (err || buf != ubuf)
+			goto out;
+	}
+
+	next = mce_log_get_idx_check(mcelog.next);
+
+	/* Only supports full reads right now */
+	err = -EINVAL;
+	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
+		goto out;
+
+	err = 0;
+	prev = 0;
+	do {
+		for (i = prev; i < next; i++) {
+			unsigned long start = jiffies;
+			struct mce *m = &mcelog.entry[i];
+
+			while (!m->finished) {
+				if (time_after_eq(jiffies, start + 2)) {
+					memset(m, 0, sizeof(*m));
+					goto timeout;
+				}
+				cpu_relax();
+			}
+			smp_rmb();
+			err |= copy_to_user(buf, m, sizeof(*m));
+			buf += sizeof(*m);
+timeout:
+			;
+		}
+
+		memset(mcelog.entry + prev, 0,
+		       (next - prev) * sizeof(struct mce));
+		prev = next;
+		next = cmpxchg(&mcelog.next, prev, 0);
+	} while (next != prev);
+
+	synchronize_sched();
+
+	/*
+	 * Collect entries that were still getting written before the
+	 * synchronize.
+	 */
+	on_each_cpu(collect_tscs, cpu_tsc, 1);
+
+	for (i = next; i < MCE_LOG_LEN; i++) {
+		struct mce *m = &mcelog.entry[i];
+
+		if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
+			err |= copy_to_user(buf, m, sizeof(*m));
+			smp_rmb();
+			buf += sizeof(*m);
+			memset(m, 0, sizeof(*m));
+		}
+	}
+
+	if (err)
+		err = -EFAULT;
+
+out:
+	mutex_unlock(&mce_chrdev_read_mutex);
+	kfree(cpu_tsc);
+
+	return err ? err : buf - ubuf;
+}
+
+static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
+{
+	poll_wait(file, &mce_chrdev_wait, wait);
+	if (READ_ONCE(mcelog.next))
+		return POLLIN | POLLRDNORM;
+	if (!mce_apei_read_done && apei_check_mce())
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+
+static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
+				unsigned long arg)
+{
+	int __user *p = (int __user *)arg;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (cmd) {
+	case MCE_GET_RECORD_LEN:
+		return put_user(sizeof(struct mce), p);
+	case MCE_GET_LOG_LEN:
+		return put_user(MCE_LOG_LEN, p);
+	case MCE_GETCLEAR_FLAGS: {
+		unsigned flags;
+
+		do {
+			flags = mcelog.flags;
+		} while (cmpxchg(&mcelog.flags, flags, 0) != flags);
+
+		return put_user(flags, p);
+	}
+	default:
+		return -ENOTTY;
+	}
+}
+
+static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
+			    size_t usize, loff_t *off);
+
+void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
+			     const char __user *ubuf,
+			     size_t usize, loff_t *off))
+{
+	mce_write = fn;
+}
+EXPORT_SYMBOL_GPL(register_mce_write_callback);
+
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+				size_t usize, loff_t *off)
+{
+	if (mce_write)
+		return mce_write(filp, ubuf, usize, off);
+	else
+		return -EINVAL;
+}
+
+static const struct file_operations mce_chrdev_ops = {
+	.open			= mce_chrdev_open,
+	.release		= mce_chrdev_release,
+	.read			= mce_chrdev_read,
+	.write			= mce_chrdev_write,
+	.poll			= mce_chrdev_poll,
+	.unlocked_ioctl		= mce_chrdev_ioctl,
+	.llseek			= no_llseek,
+};
+
+static struct miscdevice mce_chrdev_device = {
+	MISC_MCELOG_MINOR,
+	"mcelog",
+	&mce_chrdev_ops,
+};
+
+static __init int dev_mcelog_init_device(void)
+{
+	int err;
+
+	/* register character device /dev/mcelog */
+	err = misc_register(&mce_chrdev_device);
+	if (err) {
+		pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);
+		return err;
+	}
+	mce_register_decode_chain(&dev_mcelog_nb);
+	return 0;
+}
+device_initcall_sync(dev_mcelog_init_device);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 903043e6a62b..7f2a7c54391f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -96,3 +96,11 @@ static inline bool mce_cmp(struct mce *m1, struct mce *m2)
 		m1->addr != m2->addr ||
 		m1->misc != m2->misc;
 }
+
+extern struct device_attribute dev_attr_trigger;
+
+#ifdef CONFIG_X86_MCELOG_LEGACY
+extern void mce_work_trigger(void);
+#else
+static inline void mce_work_trigger(void)	{ }
+#endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 4a907758a516..36082c7fe4a0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -54,17 +54,7 @@
 
 #include "mce-internal.h"
 
-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() && \
-			 !lockdep_is_held(&mce_chrdev_read_mutex), \
-			 "suspicious mce_log_get_idx_check() usage"); \
-	smp_load_acquire(&(p)); \
-})
+static DEFINE_MUTEX(mce_log_mutex);
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
@@ -89,15 +79,9 @@ struct mca_config mca_cfg __read_mostly = {
 	.monarch_timeout = -1
 };
 
-/* User mode helper program triggered by machine check event */
-static unsigned long		mce_need_notify;
-static char			mce_helper[128];
-static char			*mce_helper_argv[2] = { mce_helper, NULL };
-
-static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
-
 static DEFINE_PER_CPU(struct mce, mces_seen);
-static int			cpu_missing;
+static unsigned long mce_need_notify;
+static int cpu_missing;
 
 /*
  * MCA banks polled by the period polling timer for corrected events.
@@ -147,18 +131,6 @@ void mce_setup(struct mce *m)
 DEFINE_PER_CPU(struct mce, injectm);
 EXPORT_PER_CPU_SYMBOL_GPL(injectm);
 
-/*
- * Lockless MCE logging infrastructure.
- * This avoids deadlocks on printk locks without having to break locks. Also
- * separate MCEs from kernel messages to avoid bogus bug reports.
- */
-
-static struct mce_log_buffer mcelog_buf = {
-	.signature	= MCE_LOG_SIGNATURE,
-	.len		= MCE_LOG_LEN,
-	.recordlen	= sizeof(struct mce),
-};
-
 void mce_log(struct mce *m)
 {
 	if (!mce_gen_pool_add(m))
@@ -167,9 +139,9 @@ void mce_log(struct mce *m)
 
 void mce_inject_log(struct mce *m)
 {
-	mutex_lock(&mce_chrdev_read_mutex);
+	mutex_lock(&mce_log_mutex);
 	mce_log(m);
-	mutex_unlock(&mce_chrdev_read_mutex);
+	mutex_unlock(&mce_log_mutex);
 }
 EXPORT_SYMBOL_GPL(mce_inject_log);
 
@@ -582,7 +554,6 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
 			      void *data)
 {
 	struct mce *m = (struct mce *)data;
-	unsigned int next, entry;
 
 	if (!m)
 		return NOTIFY_DONE;
@@ -593,38 +564,6 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
 	/* Emit the trace record: */
 	trace_mce_record(m);
 
-	wmb();
-	for (;;) {
-		entry = mce_log_get_idx_check(mcelog_buf.next);
-		for (;;) {
-
-			/*
-			 * When the buffer fills up discard new entries.
-			 * Assume that the earlier errors are the more
-			 * interesting ones:
-			 */
-			if (entry >= MCE_LOG_LEN) {
-				set_bit(MCE_OVERFLOW,
-					(unsigned long *)&mcelog_buf.flags);
-				return NOTIFY_DONE;
-			}
-			/* Old left over entry. Skip: */
-			if (mcelog_buf.entry[entry].finished) {
-				entry++;
-				continue;
-			}
-			break;
-		}
-		smp_rmb();
-		next = entry + 1;
-		if (cmpxchg(&mcelog_buf.next, entry, next) == entry)
-			break;
-	}
-	memcpy(mcelog_buf.entry + entry, m, sizeof(struct mce));
-	wmb();
-	mcelog_buf.entry[entry].finished = 1;
-	wmb();
-
 	set_bit(0, &mce_need_notify);
 
 	mce_notify_irq();
@@ -669,10 +608,6 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
 	if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS)
 		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;
@@ -1456,13 +1391,6 @@ static void mce_timer_delete_all(void)
 		del_timer_sync(&per_cpu(mce_timer, cpu));
 }
 
-static void mce_do_trigger(struct work_struct *work)
-{
-	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
-}
-
-static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
-
 /*
  * Notify the user(s) about new machine check events.
  * Can be called from interrupt context, but not from machine check/NMI
@@ -1474,11 +1402,7 @@ int mce_notify_irq(void)
 	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
 
 	if (test_and_clear_bit(0, &mce_need_notify)) {
-		/* wake processes polling /dev/mcelog */
-		wake_up_interruptible(&mce_chrdev_wait);
-
-		if (mce_helper[0])
-			schedule_work(&mce_trigger_work);
+		mce_work_trigger();
 
 		if (__ratelimit(&ratelimit))
 			pr_info(HW_ERR "Machine check events logged\n");
@@ -1886,251 +1810,6 @@ void mcheck_cpu_clear(struct cpuinfo_x86 *c)
 
 }
 
-/*
- * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log.
- */
-
-static DEFINE_SPINLOCK(mce_chrdev_state_lock);
-static int mce_chrdev_open_exclu;	/* already open exclusive? */
-
-static int mce_chrdev_open(struct inode *inode, struct file *file)
-{
-	spin_lock(&mce_chrdev_state_lock);
-
-	if (mce_chrdev_open_exclu ||
-	    (mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
-		spin_unlock(&mce_chrdev_state_lock);
-
-		return -EBUSY;
-	}
-
-	if (file->f_flags & O_EXCL)
-		mce_chrdev_open_exclu = 1;
-	mce_chrdev_open_count++;
-
-	spin_unlock(&mce_chrdev_state_lock);
-
-	return nonseekable_open(inode, file);
-}
-
-static int mce_chrdev_release(struct inode *inode, struct file *file)
-{
-	spin_lock(&mce_chrdev_state_lock);
-
-	mce_chrdev_open_count--;
-	mce_chrdev_open_exclu = 0;
-
-	spin_unlock(&mce_chrdev_state_lock);
-
-	return 0;
-}
-
-static void collect_tscs(void *data)
-{
-	unsigned long *cpu_tsc = (unsigned long *)data;
-
-	cpu_tsc[smp_processor_id()] = rdtsc();
-}
-
-static int mce_apei_read_done;
-
-/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
-static int __mce_read_apei(char __user **ubuf, size_t usize)
-{
-	int rc;
-	u64 record_id;
-	struct mce m;
-
-	if (usize < sizeof(struct mce))
-		return -EINVAL;
-
-	rc = apei_read_mce(&m, &record_id);
-	/* Error or no more MCE record */
-	if (rc <= 0) {
-		mce_apei_read_done = 1;
-		/*
-		 * When ERST is disabled, mce_chrdev_read() should return
-		 * "no record" instead of "no device."
-		 */
-		if (rc == -ENODEV)
-			return 0;
-		return rc;
-	}
-	rc = -EFAULT;
-	if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
-		return rc;
-	/*
-	 * In fact, we should have cleared the record after that has
-	 * been flushed to the disk or sent to network in
-	 * /sbin/mcelog, but we have no interface to support that now,
-	 * so just clear it to avoid duplication.
-	 */
-	rc = apei_clear_mce(record_id);
-	if (rc) {
-		mce_apei_read_done = 1;
-		return rc;
-	}
-	*ubuf += sizeof(struct mce);
-
-	return 0;
-}
-
-static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
-				size_t usize, loff_t *off)
-{
-	char __user *buf = ubuf;
-	unsigned long *cpu_tsc;
-	unsigned prev, next;
-	int i, err;
-
-	cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
-	if (!cpu_tsc)
-		return -ENOMEM;
-
-	mutex_lock(&mce_chrdev_read_mutex);
-
-	if (!mce_apei_read_done) {
-		err = __mce_read_apei(&buf, usize);
-		if (err || buf != ubuf)
-			goto out;
-	}
-
-	next = mce_log_get_idx_check(mcelog_buf.next);
-
-	/* Only supports full reads right now */
-	err = -EINVAL;
-	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
-		goto out;
-
-	err = 0;
-	prev = 0;
-	do {
-		for (i = prev; i < next; i++) {
-			unsigned long start = jiffies;
-			struct mce *m = &mcelog_buf.entry[i];
-
-			while (!m->finished) {
-				if (time_after_eq(jiffies, start + 2)) {
-					memset(m, 0, sizeof(*m));
-					goto timeout;
-				}
-				cpu_relax();
-			}
-			smp_rmb();
-			err |= copy_to_user(buf, m, sizeof(*m));
-			buf += sizeof(*m);
-timeout:
-			;
-		}
-
-		memset(mcelog_buf.entry + prev, 0,
-		       (next - prev) * sizeof(struct mce));
-		prev = next;
-		next = cmpxchg(&mcelog_buf.next, prev, 0);
-	} while (next != prev);
-
-	synchronize_sched();
-
-	/*
-	 * Collect entries that were still getting written before the
-	 * synchronize.
-	 */
-	on_each_cpu(collect_tscs, cpu_tsc, 1);
-
-	for (i = next; i < MCE_LOG_LEN; i++) {
-		struct mce *m = &mcelog_buf.entry[i];
-
-		if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
-			err |= copy_to_user(buf, m, sizeof(*m));
-			smp_rmb();
-			buf += sizeof(*m);
-			memset(m, 0, sizeof(*m));
-		}
-	}
-
-	if (err)
-		err = -EFAULT;
-
-out:
-	mutex_unlock(&mce_chrdev_read_mutex);
-	kfree(cpu_tsc);
-
-	return err ? err : buf - ubuf;
-}
-
-static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
-{
-	poll_wait(file, &mce_chrdev_wait, wait);
-	if (READ_ONCE(mcelog_buf.next))
-		return POLLIN | POLLRDNORM;
-	if (!mce_apei_read_done && apei_check_mce())
-		return POLLIN | POLLRDNORM;
-	return 0;
-}
-
-static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
-				unsigned long arg)
-{
-	int __user *p = (int __user *)arg;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	switch (cmd) {
-	case MCE_GET_RECORD_LEN:
-		return put_user(sizeof(struct mce), p);
-	case MCE_GET_LOG_LEN:
-		return put_user(MCE_LOG_LEN, p);
-	case MCE_GETCLEAR_FLAGS: {
-		unsigned flags;
-
-		do {
-			flags = mcelog_buf.flags;
-		} while (cmpxchg(&mcelog_buf.flags, flags, 0) != flags);
-
-		return put_user(flags, p);
-	}
-	default:
-		return -ENOTTY;
-	}
-}
-
-static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
-			    size_t usize, loff_t *off);
-
-void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
-			     const char __user *ubuf,
-			     size_t usize, loff_t *off))
-{
-	mce_write = fn;
-}
-EXPORT_SYMBOL_GPL(register_mce_write_callback);
-
-static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
-				size_t usize, loff_t *off)
-{
-	if (mce_write)
-		return mce_write(filp, ubuf, usize, off);
-	else
-		return -EINVAL;
-}
-
-static const struct file_operations mce_chrdev_ops = {
-	.open			= mce_chrdev_open,
-	.release		= mce_chrdev_release,
-	.read			= mce_chrdev_read,
-	.write			= mce_chrdev_write,
-	.poll			= mce_chrdev_poll,
-	.unlocked_ioctl		= mce_chrdev_ioctl,
-	.llseek			= no_llseek,
-};
-
-static struct miscdevice mce_chrdev_device = {
-	MISC_MCELOG_MINOR,
-	"mcelog",
-	&mce_chrdev_ops,
-};
-
 static void __mce_disable_bank(void *arg)
 {
 	int bank = *((int *)arg);
@@ -2349,29 +2028,6 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 	return size;
 }
 
-static ssize_t
-show_trigger(struct device *s, struct device_attribute *attr, char *buf)
-{
-	strcpy(buf, mce_helper);
-	strcat(buf, "\n");
-	return strlen(mce_helper) + 1;
-}
-
-static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
-				const char *buf, size_t siz)
-{
-	char *p;
-
-	strncpy(mce_helper, buf, sizeof(mce_helper));
-	mce_helper[sizeof(mce_helper)-1] = 0;
-	p = strchr(mce_helper, '\n');
-
-	if (p)
-		*p = 0;
-
-	return strlen(mce_helper) + !!p;
-}
-
 static ssize_t set_ignore_ce(struct device *s,
 			     struct device_attribute *attr,
 			     const char *buf, size_t size)
@@ -2428,7 +2084,6 @@ static ssize_t store_int_with_restart(struct device *s,
 	return ret;
 }
 
-static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
 static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant);
 static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout);
 static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce);
@@ -2451,7 +2106,9 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = {
 static struct device_attribute *mce_device_attrs[] = {
 	&dev_attr_tolerant.attr,
 	&dev_attr_check_interval.attr,
+#ifdef CONFIG_X86_MCELOG_LEGACY
 	&dev_attr_trigger,
+#endif
 	&dev_attr_monarch_timeout.attr,
 	&dev_attr_dont_log_ce.attr,
 	&dev_attr_ignore_ce.attr,
@@ -2625,7 +2282,6 @@ static __init void mce_init_banks(void)
 
 static __init int mcheck_init_device(void)
 {
-	enum cpuhp_state hp_online;
 	int err;
 
 	if (!mce_available(&boot_cpu_data)) {
@@ -2653,21 +2309,11 @@ static __init int mcheck_init_device(void)
 				mce_cpu_online, mce_cpu_pre_down);
 	if (err < 0)
 		goto err_out_online;
-	hp_online = err;
 
 	register_syscore_ops(&mce_syscore_ops);
 
-	/* register character device /dev/mcelog */
-	err = misc_register(&mce_chrdev_device);
-	if (err)
-		goto err_register;
-
 	return 0;
 
-err_register:
-	unregister_syscore_ops(&mce_syscore_ops);
-	cpuhp_remove_state(hp_online);
-
 err_out_online:
 	cpuhp_remove_state(CPUHP_X86_MCE_DEAD);
 
@@ -2675,7 +2321,7 @@ err_out_mem:
 	free_cpumask_var(mce_device_initialized);
 
 err_out:
-	pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);
+	pr_err("Unable to init MCE device (rc: %d)\n", err);
 
 	return err;
 }