Merge branch 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Ingo Molnar:
 "The main changes in this cycle were:

   - add the 'Corrected Errors Collector' kernel feature which collect
     and monitor correctable errors statistics and will preemptively
     (soft-)offline physical pages that have a suspiciously high error
     count.

   - handle MCE errors during kexec() more gracefully

   - factor out and deprecate the /dev/mcelog driver

   - ... plus misc fixes and cleanpus"

* 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Check MCi_STATUS[MISCV] for usable addr on Intel only
  ACPI/APEI: Use setup_deferrable_timer()
  x86/mce: Update notifier priority check
  x86/mce: Enable PPIN for Knights Landing/Mill
  x86/mce: Do not register notifiers with invalid prio
  x86/mce: Factor out and deprecate the /dev/mcelog driver
  RAS: Add a Corrected Errors Collector
  x86/mce: Rename mce_log to mce_log_buffer
  x86/mce: Rename mce_log()'s argument
  x86/mce: Init some CPU features early
  x86/mce: Handle broadcasted MCE gracefully with kexec

Documentation/admin-guide/kernel-parameters.txt

@@ -3177,6 +3177,12 @@
 	ramdisk_size=	[RAM] Sizes of RAM disks in kilobytes
 			See Documentation/blockdev/ramdisk.txt.
 
+	ras=option[,option,...]	[KNL] RAS-specific options
+
+		cec_disable	[X86]
+				Disable the Correctable Errors Collector,
+				see CONFIG_RAS_CEC help text.
+
 	rcu_nocbs=	[KNL]
 			The argument is a cpu list, as described above.
 

arch/x86/Kconfig

@@ -1042,6 +1042,14 @@ 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"
@@ -1071,7 +1079,7 @@ 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.

arch/x86/include/asm/mce.h

@@ -128,7 +128,7 @@
  * debugging tools.  Each entry is only valid when its finished flag
  * is set.
  */
-struct mce_log {
+struct mce_log_buffer {
 	char signature[12]; /* "MACHINECHECK" */
 	unsigned len;	    /* = MCE_LOG_LEN */
 	unsigned next;
@@ -191,10 +191,12 @@ extern struct mca_config mca_cfg;
 extern struct mca_msr_regs msr_ops;
 
 enum mce_notifier_prios {
-	MCE_PRIO_SRAO		= INT_MAX,
-	MCE_PRIO_EXTLOG		= INT_MAX - 1,
-	MCE_PRIO_NFIT		= INT_MAX - 2,
-	MCE_PRIO_EDAC		= INT_MAX - 3,
+	MCE_PRIO_FIRST		= INT_MAX,
+	MCE_PRIO_SRAO		= INT_MAX - 1,
+	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,
 };
 

arch/x86/include/asm/reboot.h

@@ -15,6 +15,7 @@ struct machine_ops {
 };
 
 extern struct machine_ops machine_ops;
+extern int crashing_cpu;
 
 void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);

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

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);

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

arch/x86/kernel/cpu/mcheck/mce.c

@@ -35,6 +35,7 @@
 #include <linux/poll.h>
 #include <linux/nmi.h>
 #include <linux/cpu.h>
+#include <linux/ras.h>
 #include <linux/smp.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -49,20 +50,11 @@
 #include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
+#include <asm/reboot.h>
 
 #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>
@@ -87,15 +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.
@@ -145,80 +131,36 @@ 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 mcelog = {
-	.signature	= MCE_LOG_SIGNATURE,
-	.len		= MCE_LOG_LEN,
-	.recordlen	= sizeof(struct mce),
-};
-
-void mce_log(struct mce *mce)
+void mce_log(struct mce *m)
 {
-	unsigned next, entry;
-
-	/* Emit the trace record: */
-	trace_mce_record(mce);
-
-	if (!mce_gen_pool_add(mce))
+	if (!mce_gen_pool_add(m))
 		irq_work_queue(&mce_irq_work);
-
-	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;
-			}
-			/* 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();
-
-	set_bit(0, &mce_need_notify);
 }
 
 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);
 
 static struct notifier_block mce_srao_nb;
 
+/*
+ * We run the default notifier if we have only the SRAO, the first and the
+ * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS
+ * notifiers registered on the chain.
+ */
+#define NUM_DEFAULT_NOTIFIERS	3
 static atomic_t num_notifiers;
 
 void mce_register_decode_chain(struct notifier_block *nb)
 {
-	atomic_inc(&num_notifiers);
+	if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC))
+		return;
 
-	WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
+	atomic_inc(&num_notifiers);
 
 	blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
 }
@@ -510,7 +452,6 @@ static void mce_schedule_work(void)
 
 static void mce_irq_work_cb(struct irq_work *entry)
 {
-	mce_notify_irq();
 	mce_schedule_work();
 }
 
@@ -539,20 +480,97 @@ static void mce_report_event(struct pt_regs *regs)
  */
 static int mce_usable_address(struct mce *m)
 {
-	if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV))
+	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
 	/* Checks after this one are Intel-specific: */
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return 1;
 
+	if (!(m->status & MCI_STATUS_MISCV))
+		return 0;
+
 	if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
 		return 0;
+
 	if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
 		return 0;
+
 	return 1;
 }
 
+static bool memory_error(struct mce *m)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		/* ErrCodeExt[20:16] */
+		u8 xec = (m->status >> 16) & 0x1f;
+
+		return (xec == 0x0 || xec == 0x8);
+	} else if (c->x86_vendor == X86_VENDOR_INTEL) {
+		/*
+		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
+		 *
+		 * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
+		 * indicating a memory error. Bit 8 is used for indicating a
+		 * cache hierarchy error. The combination of bit 2 and bit 3
+		 * is used for indicating a `generic' cache hierarchy error
+		 * But we can't just blindly check the above bits, because if
+		 * bit 11 is set, then it is a bus/interconnect error - and
+		 * either way the above bits just gives more detail on what
+		 * bus/interconnect error happened. Note that bit 12 can be
+		 * ignored, as it's the "filter" bit.
+		 */
+		return (m->status & 0xef80) == BIT(7) ||
+		       (m->status & 0xef00) == BIT(8) ||
+		       (m->status & 0xeffc) == 0xc;
+	}
+
+	return false;
+}
+
+static bool cec_add_mce(struct mce *m)
+{
+	if (!m)
+		return false;
+
+	/* We eat only correctable DRAM errors with usable addresses. */
+	if (memory_error(m) &&
+	    !(m->status & MCI_STATUS_UC) &&
+	    mce_usable_address(m))
+		if (!cec_add_elem(m->addr >> PAGE_SHIFT))
+			return true;
+
+	return false;
+}
+
+static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
+			      void *data)
+{
+	struct mce *m = (struct mce *)data;
+
+	if (!m)
+		return NOTIFY_DONE;
+
+	if (cec_add_mce(m))
+		return NOTIFY_STOP;
+
+	/* Emit the trace record: */
+	trace_mce_record(m);
+
+	set_bit(0, &mce_need_notify);
+
+	mce_notify_irq();
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block first_nb = {
+	.notifier_call	= mce_first_notifier,
+	.priority	= MCE_PRIO_FIRST,
+};
+
 static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 				void *data)
 {
@@ -582,15 +600,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
 	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)
+	if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS)
 		return NOTIFY_DONE;
 
 	__print_mce(m);
@@ -643,37 +653,6 @@ static void mce_read_aux(struct mce *m, int i)
 	}
 }
 
-static bool memory_error(struct mce *m)
-{
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		/* ErrCodeExt[20:16] */
-		u8 xec = (m->status >> 16) & 0x1f;
-
-		return (xec == 0x0 || xec == 0x8);
-	} else if (c->x86_vendor == X86_VENDOR_INTEL) {
-		/*
-		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
-		 *
-		 * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
-		 * indicating a memory error. Bit 8 is used for indicating a
-		 * cache hierarchy error. The combination of bit 2 and bit 3
-		 * is used for indicating a `generic' cache hierarchy error
-		 * But we can't just blindly check the above bits, because if
-		 * bit 11 is set, then it is a bus/interconnect error - and
-		 * either way the above bits just gives more detail on what
-		 * bus/interconnect error happened. Note that bit 12 can be
-		 * ignored, as it's the "filter" bit.
-		 */
-		return (m->status & 0xef80) == BIT(7) ||
-		       (m->status & 0xef00) == BIT(8) ||
-		       (m->status & 0xeffc) == 0xc;
-	}
-
-	return false;
-}
-
 DEFINE_PER_CPU(unsigned, mce_poll_count);
 
 /*
@@ -1122,9 +1101,22 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	 * on Intel.
 	 */
 	int lmce = 1;
+	int cpu = smp_processor_id();
 
-	/* If this CPU is offline, just bail out. */
-	if (cpu_is_offline(smp_processor_id())) {
+	/*
+	 * Cases where we avoid rendezvous handler timeout:
+	 * 1) If this CPU is offline.
+	 *
+	 * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+	 *  skip those CPUs which remain looping in the 1st kernel - see
+	 *  crash_nmi_callback().
+	 *
+	 * Note: there still is a small window between kexec-ing and the new,
+	 * kdump kernel establishing a new #MC handler where a broadcasted MCE
+	 * might not get handled properly.
+	 */
+	if (cpu_is_offline(cpu) ||
+	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
 		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
@@ -1394,13 +1386,6 @@ 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
@@ -1412,11 +1397,7 @@ 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");
@@ -1683,30 +1664,35 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
 	return 0;
 }
 
-static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
+/*
+ * Init basic CPU features needed for early decoding of MCEs.
+ */
+static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
 {
-	switch (c->x86_vendor) {
-	case X86_VENDOR_INTEL:
-		mce_intel_feature_init(c);
-		mce_adjust_timer = cmci_intel_adjust_timer;
-		break;
-
-	case X86_VENDOR_AMD: {
+	if (c->x86_vendor == X86_VENDOR_AMD) {
 		mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
 		mce_flags.succor	 = !!cpu_has(c, X86_FEATURE_SUCCOR);
 		mce_flags.smca		 = !!cpu_has(c, X86_FEATURE_SMCA);
 
-		/*
-		 * Install proper ops for Scalable MCA enabled processors
-		 */
 		if (mce_flags.smca) {
 			msr_ops.ctl	= smca_ctl_reg;
 			msr_ops.status	= smca_status_reg;
 			msr_ops.addr	= smca_addr_reg;
 			msr_ops.misc	= smca_misc_reg;
 		}
-		mce_amd_feature_init(c);
+	}
+}
+
+static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
+{
+	switch (c->x86_vendor) {
+	case X86_VENDOR_INTEL:
+		mce_intel_feature_init(c);
+		mce_adjust_timer = cmci_intel_adjust_timer;
+		break;
 
+	case X86_VENDOR_AMD: {
+		mce_amd_feature_init(c);
 		break;
 		}
 
@@ -1793,6 +1779,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 
 	machine_check_vector = do_machine_check;
 
+	__mcheck_cpu_init_early(c);
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
@@ -1818,251 +1805,6 @@ 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.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 void __mce_disable_bank(void *arg)
 {
 	int bank = *((int *)arg);
@@ -2136,6 +1878,7 @@ __setup("mce", mcheck_enable);
 int __init mcheck_init(void)
 {
 	mcheck_intel_therm_init();
+	mce_register_decode_chain(&first_nb);
 	mce_register_decode_chain(&mce_srao_nb);
 	mce_register_decode_chain(&mce_default_nb);
 	mcheck_vendor_init_severity();
@@ -2280,29 +2023,6 @@ 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)
@@ -2359,7 +2079,6 @@ 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);
@@ -2382,7 +2101,9 @@ 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,
@@ -2556,7 +2277,6 @@ 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)) {
@@ -2584,21 +2304,11 @@ 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);
 
@@ -2606,7 +2316,7 @@ 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;
 }
@@ -2685,6 +2395,7 @@ static int __init mcheck_late_init(void)
 		static_branch_inc(&mcsafe_key);
 
 	mcheck_debugfs_init();
+	cec_init();
 
 	/*
 	 * Flush out everything that has been logged during early boot, now that

arch/x86/kernel/cpu/mcheck/mce_intel.c

@@ -481,6 +481,9 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
 	case INTEL_FAM6_BROADWELL_XEON_D:
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
+
 		if (rdmsrl_safe(MSR_PPIN_CTL, &val))
 			return;
 

arch/x86/kernel/reboot.c

@@ -765,10 +765,11 @@ void machine_crash_shutdown(struct pt_regs *regs)
 #endif
 
 
+/* This is the CPU performing the emergency shutdown work. */
+int crashing_cpu = -1;
+
 #if defined(CONFIG_SMP)
 
-/* This keeps a track of which one is crashing cpu. */
-static int crashing_cpu;
 static nmi_shootdown_cb shootdown_callback;
 
 static atomic_t waiting_for_crash_ipi;

arch/x86/ras/Kconfig

@@ -7,3 +7,17 @@ config MCE_AMD_INJ
 	  aspects of the MCE handling code.
 
 	  WARNING: Do not even assume this interface is staying stable!
+
+config RAS_CEC
+	bool "Correctable Errors Collector"
+	depends on X86_MCE && MEMORY_FAILURE && DEBUG_FS
+	---help---
+	  This is a small cache which collects correctable memory errors per 4K
+	  page PFN and counts their repeated occurrence. Once the counter for a
+	  PFN overflows, we try to soft-offline that page as we take it to mean
+	  that it has reached a relatively high error count and would probably
+	  be best if we don't use it anymore.
+
+	  Bear in mind that this is absolutely useless if your platform doesn't
+	  have ECC DIMMs and doesn't have DRAM ECC checking enabled in the BIOS.
+

drivers/acpi/apei/ghes.c

@@ -1005,9 +1005,8 @@ static int ghes_probe(struct platform_device *ghes_dev)
 
 	switch (generic->notify.type) {
 	case ACPI_HEST_NOTIFY_POLLED:
-		ghes->timer.function = ghes_poll_func;
-		ghes->timer.data = (unsigned long)ghes;
-		init_timer_deferrable(&ghes->timer);
+		setup_deferrable_timer(&ghes->timer, ghes_poll_func,
+				       (unsigned long)ghes);
 		ghes_add_timer(ghes);
 		break;
 	case ACPI_HEST_NOTIFY_EXTERNAL:

drivers/ras/Makefile

@@ -1 +1,2 @@
-obj-$(CONFIG_RAS) += ras.o debugfs.o
+obj-$(CONFIG_RAS)	+= ras.o debugfs.o
+obj-$(CONFIG_RAS_CEC)	+= cec.o

drivers/ras/cec.c

@@ -0,0 +1,532 @@
+#include <linux/mm.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+
+#include <asm/mce.h>
+
+#include "debugfs.h"
+
+/*
+ * RAS Correctable Errors Collector
+ *
+ * This is a simple gadget which collects correctable errors and counts their
+ * occurrence per physical page address.
+ *
+ * We've opted for possibly the simplest data structure to collect those - an
+ * array of the size of a memory page. It stores 512 u64's with the following
+ * structure:
+ *
+ * [63 ... PFN ... 12 | 11 ... generation ... 10 | 9 ... count ... 0]
+ *
+ * The generation in the two highest order bits is two bits which are set to 11b
+ * on every insertion. During the course of each entry's existence, the
+ * generation field gets decremented during spring cleaning to 10b, then 01b and
+ * then 00b.
+ *
+ * This way we're employing the natural numeric ordering to make sure that newly
+ * inserted/touched elements have higher 12-bit counts (which we've manufactured)
+ * and thus iterating over the array initially won't kick out those elements
+ * which were inserted last.
+ *
+ * Spring cleaning is what we do when we reach a certain number CLEAN_ELEMS of
+ * elements entered into the array, during which, we're decaying all elements.
+ * If, after decay, an element gets inserted again, its generation is set to 11b
+ * to make sure it has higher numerical count than other, older elements and
+ * thus emulate an an LRU-like behavior when deleting elements to free up space
+ * in the page.
+ *
+ * When an element reaches it's max count of count_threshold, we try to poison
+ * it by assuming that errors triggered count_threshold times in a single page
+ * are excessive and that page shouldn't be used anymore. count_threshold is
+ * initialized to COUNT_MASK which is the maximum.
+ *
+ * That error event entry causes cec_add_elem() to return !0 value and thus
+ * signal to its callers to log the error.
+ *
+ * To the question why we've chosen a page and moving elements around with
+ * memmove(), it is because it is a very simple structure to handle and max data
+ * movement is 4K which on highly optimized modern CPUs is almost unnoticeable.
+ * We wanted to avoid the pointer traversal of more complex structures like a
+ * linked list or some sort of a balancing search tree.
+ *
+ * Deleting an element takes O(n) but since it is only a single page, it should
+ * be fast enough and it shouldn't happen all too often depending on error
+ * patterns.
+ */
+
+#undef pr_fmt
+#define pr_fmt(fmt) "RAS: " fmt
+
+/*
+ * We use DECAY_BITS bits of PAGE_SHIFT bits for counting decay, i.e., how long
+ * elements have stayed in the array without having been accessed again.
+ */
+#define DECAY_BITS		2
+#define DECAY_MASK		((1ULL << DECAY_BITS) - 1)
+#define MAX_ELEMS		(PAGE_SIZE / sizeof(u64))
+
+/*
+ * Threshold amount of inserted elements after which we start spring
+ * cleaning.
+ */
+#define CLEAN_ELEMS		(MAX_ELEMS >> DECAY_BITS)
+
+/* Bits which count the number of errors happened in this 4K page. */
+#define COUNT_BITS		(PAGE_SHIFT - DECAY_BITS)
+#define COUNT_MASK		((1ULL << COUNT_BITS) - 1)
+#define FULL_COUNT_MASK		(PAGE_SIZE - 1)
+
+/*
+ * u64: [ 63 ... 12 | DECAY_BITS | COUNT_BITS ]
+ */
+
+#define PFN(e)			((e) >> PAGE_SHIFT)
+#define DECAY(e)		(((e) >> COUNT_BITS) & DECAY_MASK)
+#define COUNT(e)		((unsigned int)(e) & COUNT_MASK)
+#define FULL_COUNT(e)		((e) & (PAGE_SIZE - 1))
+
+static struct ce_array {
+	u64 *array;			/* container page */
+	unsigned int n;			/* number of elements in the array */
+
+	unsigned int decay_count;	/*
+					 * number of element insertions/increments
+					 * since the last spring cleaning.
+					 */
+
+	u64 pfns_poisoned;		/*
+					 * number of PFNs which got poisoned.
+					 */
+
+	u64 ces_entered;		/*
+					 * The number of correctable errors
+					 * entered into the collector.
+					 */
+
+	u64 decays_done;		/*
+					 * Times we did spring cleaning.
+					 */
+
+	union {
+		struct {
+			__u32	disabled : 1,	/* cmdline disabled */
+			__resv   : 31;
+		};
+		__u32 flags;
+	};
+} ce_arr;
+
+static DEFINE_MUTEX(ce_mutex);
+static u64 dfs_pfn;
+
+/* Amount of errors after which we offline */
+static unsigned int count_threshold = COUNT_MASK;
+
+/*
+ * The timer "decays" element count each timer_interval which is 24hrs by
+ * default.
+ */
+
+#define CEC_TIMER_DEFAULT_INTERVAL	24 * 60 * 60	/* 24 hrs */
+#define CEC_TIMER_MIN_INTERVAL		 1 * 60 * 60	/* 1h */
+#define CEC_TIMER_MAX_INTERVAL	   30 *	24 * 60 * 60	/* one month */
+static struct timer_list cec_timer;
+static u64 timer_interval = CEC_TIMER_DEFAULT_INTERVAL;
+
+/*
+ * Decrement decay value. We're using DECAY_BITS bits to denote decay of an
+ * element in the array. On insertion and any access, it gets reset to max.
+ */
+static void do_spring_cleaning(struct ce_array *ca)
+{
+	int i;
+
+	for (i = 0; i < ca->n; i++) {
+		u8 decay = DECAY(ca->array[i]);
+
+		if (!decay)
+			continue;
+
+		decay--;
+
+		ca->array[i] &= ~(DECAY_MASK << COUNT_BITS);
+		ca->array[i] |= (decay << COUNT_BITS);
+	}
+	ca->decay_count = 0;
+	ca->decays_done++;
+}
+
+/*
+ * @interval in seconds
+ */
+static void cec_mod_timer(struct timer_list *t, unsigned long interval)
+{
+	unsigned long iv;
+
+	iv = interval * HZ + jiffies;
+
+	mod_timer(t, round_jiffies(iv));
+}
+
+static void cec_timer_fn(unsigned long data)
+{
+	struct ce_array *ca = (struct ce_array *)data;
+
+	do_spring_cleaning(ca);
+
+	cec_mod_timer(&cec_timer, timer_interval);
+}
+
+/*
+ * @to: index of the smallest element which is >= then @pfn.
+ *
+ * Return the index of the pfn if found, otherwise negative value.
+ */
+static int __find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
+{
+	u64 this_pfn;
+	int min = 0, max = ca->n;
+
+	while (min < max) {
+		int tmp = (max + min) >> 1;
+
+		this_pfn = PFN(ca->array[tmp]);
+
+		if (this_pfn < pfn)
+			min = tmp + 1;
+		else if (this_pfn > pfn)
+			max = tmp;
+		else {
+			min = tmp;
+			break;
+		}
+	}
+
+	if (to)
+		*to = min;
+
+	this_pfn = PFN(ca->array[min]);
+
+	if (this_pfn == pfn)
+		return min;
+
+	return -ENOKEY;
+}
+
+static int find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
+{
+	WARN_ON(!to);
+
+	if (!ca->n) {
+		*to = 0;
+		return -ENOKEY;
+	}
+	return __find_elem(ca, pfn, to);
+}
+
+static void del_elem(struct ce_array *ca, int idx)
+{
+	/* Save us a function call when deleting the last element. */
+	if (ca->n - (idx + 1))
+		memmove((void *)&ca->array[idx],
+			(void *)&ca->array[idx + 1],
+			(ca->n - (idx + 1)) * sizeof(u64));
+
+	ca->n--;
+}
+
+static u64 del_lru_elem_unlocked(struct ce_array *ca)
+{
+	unsigned int min = FULL_COUNT_MASK;
+	int i, min_idx = 0;
+
+	for (i = 0; i < ca->n; i++) {
+		unsigned int this = FULL_COUNT(ca->array[i]);
+
+		if (min > this) {
+			min = this;
+			min_idx = i;
+		}
+	}
+
+	del_elem(ca, min_idx);
+
+	return PFN(ca->array[min_idx]);
+}
+
+/*
+ * We return the 0th pfn in the error case under the assumption that it cannot
+ * be poisoned and excessive CEs in there are a serious deal anyway.
+ */
+static u64 __maybe_unused del_lru_elem(void)
+{
+	struct ce_array *ca = &ce_arr;
+	u64 pfn;
+
+	if (!ca->n)
+		return 0;
+
+	mutex_lock(&ce_mutex);
+	pfn = del_lru_elem_unlocked(ca);
+	mutex_unlock(&ce_mutex);
+
+	return pfn;
+}
+
+
+int cec_add_elem(u64 pfn)
+{
+	struct ce_array *ca = &ce_arr;
+	unsigned int to;
+	int count, ret = 0;
+
+	/*
+	 * We can be called very early on the identify_cpu() path where we are
+	 * not initialized yet. We ignore the error for simplicity.
+	 */
+	if (!ce_arr.array || ce_arr.disabled)
+		return -ENODEV;
+
+	ca->ces_entered++;
+
+	mutex_lock(&ce_mutex);
+
+	if (ca->n == MAX_ELEMS)
+		WARN_ON(!del_lru_elem_unlocked(ca));
+
+	ret = find_elem(ca, pfn, &to);
+	if (ret < 0) {
+		/*
+		 * Shift range [to-end] to make room for one more element.
+		 */
+		memmove((void *)&ca->array[to + 1],
+			(void *)&ca->array[to],
+			(ca->n - to) * sizeof(u64));
+
+		ca->array[to] = (pfn << PAGE_SHIFT) |
+				(DECAY_MASK << COUNT_BITS) | 1;
+
+		ca->n++;
+
+		ret = 0;
+
+		goto decay;
+	}
+
+	count = COUNT(ca->array[to]);
+
+	if (count < count_threshold) {
+		ca->array[to] |= (DECAY_MASK << COUNT_BITS);
+		ca->array[to]++;
+
+		ret = 0;
+	} else {
+		u64 pfn = ca->array[to] >> PAGE_SHIFT;
+
+		if (!pfn_valid(pfn)) {
+			pr_warn("CEC: Invalid pfn: 0x%llx\n", pfn);
+		} else {
+			/* We have reached max count for this page, soft-offline it. */
+			pr_err("Soft-offlining pfn: 0x%llx\n", pfn);
+			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);
+			ca->pfns_poisoned++;
+		}
+
+		del_elem(ca, to);
+
+		/*
+		 * Return a >0 value to denote that we've reached the offlining
+		 * threshold.
+		 */
+		ret = 1;
+
+		goto unlock;
+	}
+
+decay:
+	ca->decay_count++;
+
+	if (ca->decay_count >= CLEAN_ELEMS)
+		do_spring_cleaning(ca);
+
+unlock:
+	mutex_unlock(&ce_mutex);
+
+	return ret;
+}
+
+static int u64_get(void *data, u64 *val)
+{
+	*val = *(u64 *)data;
+
+	return 0;
+}
+
+static int pfn_set(void *data, u64 val)
+{
+	*(u64 *)data = val;
+
+	return cec_add_elem(val);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(pfn_ops, u64_get, pfn_set, "0x%llx\n");
+
+static int decay_interval_set(void *data, u64 val)
+{
+	*(u64 *)data = val;
+
+	if (val < CEC_TIMER_MIN_INTERVAL)
+		return -EINVAL;
+
+	if (val > CEC_TIMER_MAX_INTERVAL)
+		return -EINVAL;
+
+	timer_interval = val;
+
+	cec_mod_timer(&cec_timer, timer_interval);
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(decay_interval_ops, u64_get, decay_interval_set, "%lld\n");
+
+static int count_threshold_set(void *data, u64 val)
+{
+	*(u64 *)data = val;
+
+	if (val > COUNT_MASK)
+		val = COUNT_MASK;
+
+	count_threshold = val;
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(count_threshold_ops, u64_get, count_threshold_set, "%lld\n");
+
+static int array_dump(struct seq_file *m, void *v)
+{
+	struct ce_array *ca = &ce_arr;
+	u64 prev = 0;
+	int i;
+
+	mutex_lock(&ce_mutex);
+
+	seq_printf(m, "{ n: %d\n", ca->n);
+	for (i = 0; i < ca->n; i++) {
+		u64 this = PFN(ca->array[i]);
+
+		seq_printf(m, " %03d: [%016llx|%03llx]\n", i, this, FULL_COUNT(ca->array[i]));
+
+		WARN_ON(prev > this);
+
+		prev = this;
+	}
+
+	seq_printf(m, "}\n");
+
+	seq_printf(m, "Stats:\nCEs: %llu\nofflined pages: %llu\n",
+		   ca->ces_entered, ca->pfns_poisoned);
+
+	seq_printf(m, "Flags: 0x%x\n", ca->flags);
+
+	seq_printf(m, "Timer interval: %lld seconds\n", timer_interval);
+	seq_printf(m, "Decays: %lld\n", ca->decays_done);
+
+	seq_printf(m, "Action threshold: %d\n", count_threshold);
+
+	mutex_unlock(&ce_mutex);
+
+	return 0;
+}
+
+static int array_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, array_dump, NULL);
+}
+
+static const struct file_operations array_ops = {
+	.owner	 = THIS_MODULE,
+	.open	 = array_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = single_release,
+};
+
+static int __init create_debugfs_nodes(void)
+{
+	struct dentry *d, *pfn, *decay, *count, *array;
+
+	d = debugfs_create_dir("cec", ras_debugfs_dir);
+	if (!d) {
+		pr_warn("Error creating cec debugfs node!\n");
+		return -1;
+	}
+
+	pfn = debugfs_create_file("pfn", S_IRUSR | S_IWUSR, d, &dfs_pfn, &pfn_ops);
+	if (!pfn) {
+		pr_warn("Error creating pfn debugfs node!\n");
+		goto err;
+	}
+
+	array = debugfs_create_file("array", S_IRUSR, d, NULL, &array_ops);
+	if (!array) {
+		pr_warn("Error creating array debugfs node!\n");
+		goto err;
+	}
+
+	decay = debugfs_create_file("decay_interval", S_IRUSR | S_IWUSR, d,
+				    &timer_interval, &decay_interval_ops);
+	if (!decay) {
+		pr_warn("Error creating decay_interval debugfs node!\n");
+		goto err;
+	}
+
+	count = debugfs_create_file("count_threshold", S_IRUSR | S_IWUSR, d,
+				    &count_threshold, &count_threshold_ops);
+	if (!decay) {
+		pr_warn("Error creating count_threshold debugfs node!\n");
+		goto err;
+	}
+
+
+	return 0;
+
+err:
+	debugfs_remove_recursive(d);
+
+	return 1;
+}
+
+void __init cec_init(void)
+{
+	if (ce_arr.disabled)
+		return;
+
+	ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!ce_arr.array) {
+		pr_err("Error allocating CE array page!\n");
+		return;
+	}
+
+	if (create_debugfs_nodes())
+		return;
+
+	setup_timer(&cec_timer, cec_timer_fn, (unsigned long)&ce_arr);
+	cec_mod_timer(&cec_timer, CEC_TIMER_DEFAULT_INTERVAL);
+
+	pr_info("Correctable Errors collector initialized.\n");
+}
+
+int __init parse_cec_param(char *str)
+{
+	if (!str)
+		return 0;
+
+	if (*str == '=')
+		str++;
+
+	if (!strncmp(str, "cec_disable", 7))
+		ce_arr.disabled = 1;
+	else
+		return 0;
+
+	return 1;
+}

drivers/ras/debugfs.c

@@ -1,6 +1,6 @@
 #include <linux/debugfs.h>
 
-static struct dentry *ras_debugfs_dir;
+struct dentry *ras_debugfs_dir;
 
 static atomic_t trace_count = ATOMIC_INIT(0);
 

drivers/ras/debugfs.h

@@ -0,0 +1,8 @@
+#ifndef __RAS_DEBUGFS_H__
+#define __RAS_DEBUGFS_H__
+
+#include <linux/debugfs.h>
+
+extern struct dentry *ras_debugfs_dir;
+
+#endif /* __RAS_DEBUGFS_H__ */

drivers/ras/ras.c

@@ -27,3 +27,14 @@ subsys_initcall(ras_init);
 EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
 #endif
 EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);
+
+
+int __init parse_ras_param(char *str)
+{
+#ifdef CONFIG_RAS_CEC
+	parse_cec_param(str);
+#endif
+
+	return 1;
+}
+__setup("ras", parse_ras_param);

include/linux/ras.h

@@ -1,14 +1,25 @@
 #ifndef __RAS_H__
 #define __RAS_H__
 
+#include <asm/errno.h>
+
 #ifdef CONFIG_DEBUG_FS
 int ras_userspace_consumers(void);
 void ras_debugfs_init(void);
 int ras_add_daemon_trace(void);
 #else
 static inline int ras_userspace_consumers(void) { return 0; }
-static inline void ras_debugfs_init(void) { return; }
+static inline void ras_debugfs_init(void) { }
 static inline int ras_add_daemon_trace(void) { return 0; }
 #endif
 
+#ifdef CONFIG_RAS_CEC
+void __init cec_init(void);
+int __init parse_cec_param(char *str);
+int cec_add_elem(u64 pfn);
+#else
+static inline void __init cec_init(void)	{ }
+static inline int cec_add_elem(u64 pfn)		{ return -ENODEV; }
 #endif
+
+#endif /* __RAS_H__ */