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

Pull RAS updates from Ingo Molnar:
 "MCE handling updates, but also some generic drivers/edac/ changes to
  better organize the Kconfig space"

* 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ras: Move AMD MCE injector to arch/x86/ras/
  x86/mce: Add a wrapper around mce_log() for injection
  x86/mce: Rename rcu_dereference_check_mce() to mce_log_get_idx_check()
  RAS: Add a menuconfig option with descriptive text
  x86/mce: Reenable CMCI banks when swiching back to interrupt mode
  x86/mce: Clear Local MCE opt-in before kexec
  x86/mce: Remove unused function declarations
  x86/mce: Kill drain_mcelog_buffer()
  x86/mce: Avoid potential deadlock due to printk() in MCE context
  x86/mce: Remove the MCE ring for Action Optional errors
  x86/mce: Don't use percpu workqueues
  x86/mce: Provide a lockless memory pool to save error records
  x86/mce: Reuse one of the u16 padding fields in 'struct mce'

6 files changed, 265 insertions, 143 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index bb34b03af252..a3311c886194 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -1,4 +1,4 @@
-obj-y				=  mce.o mce-severity.o
+obj-y				=  mce.o mce-severity.o mce-genpool.o
 
 obj-$(CONFIG_X86_ANCIENT_MCE)	+= winchip.o p5.o
 obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel.o
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index a1aef9533154..34c89a3e8260 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -57,7 +57,6 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 
 	m.addr = mem_err->physical_addr;
 	mce_log(&m);
-	mce_notify_irq();
 }
 EXPORT_SYMBOL_GPL(apei_mce_report_mem_error);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
new file mode 100644
index 000000000000..0a850100c594
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -0,0 +1,99 @@
+/*
+ * MCE event pool management in MCE context
+ *
+ * Copyright (C) 2015 Intel Corp.
+ * Author: Chen, Gong <gong.chen@linux.intel.com>
+ *
+ * This file is licensed under GPLv2.
+ */
+#include <linux/smp.h>
+#include <linux/mm.h>
+#include <linux/genalloc.h>
+#include <linux/llist.h>
+#include "mce-internal.h"
+
+/*
+ * printk() is not safe in MCE context. This is a lock-less memory allocator
+ * used to save error information organized in a lock-less list.
+ *
+ * This memory pool is only to be used to save MCE records in MCE context.
+ * MCE events are rare, so a fixed size memory pool should be enough. Use
+ * 2 pages to save MCE events for now (~80 MCE records at most).
+ */
+#define MCE_POOLSZ	(2 * PAGE_SIZE)
+
+static struct gen_pool *mce_evt_pool;
+static LLIST_HEAD(mce_event_llist);
+static char gen_pool_buf[MCE_POOLSZ];
+
+void mce_gen_pool_process(void)
+{
+	struct llist_node *head;
+	struct mce_evt_llist *node;
+	struct mce *mce;
+
+	head = llist_del_all(&mce_event_llist);
+	if (!head)
+		return;
+
+	head = llist_reverse_order(head);
+	llist_for_each_entry(node, head, llnode) {
+		mce = &node->mce;
+		atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+		gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
+	}
+}
+
+bool mce_gen_pool_empty(void)
+{
+	return llist_empty(&mce_event_llist);
+}
+
+int mce_gen_pool_add(struct mce *mce)
+{
+	struct mce_evt_llist *node;
+
+	if (!mce_evt_pool)
+		return -EINVAL;
+
+	node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node));
+	if (!node) {
+		pr_warn_ratelimited("MCE records pool full!\n");
+		return -ENOMEM;
+	}
+
+	memcpy(&node->mce, mce, sizeof(*mce));
+	llist_add(&node->llnode, &mce_event_llist);
+
+	return 0;
+}
+
+static int mce_gen_pool_create(void)
+{
+	struct gen_pool *tmpp;
+	int ret = -ENOMEM;
+
+	tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1);
+	if (!tmpp)
+		goto out;
+
+	ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1);
+	if (ret) {
+		gen_pool_destroy(tmpp);
+		goto out;
+	}
+
+	mce_evt_pool = tmpp;
+
+out:
+	return ret;
+}
+
+int mce_gen_pool_init(void)
+{
+	/* Just init mce_gen_pool once. */
+	if (mce_evt_pool)
+		return 0;
+
+	return mce_gen_pool_create();
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index fe32074b865b..547720efd923 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -13,6 +13,8 @@ enum severity_level {
 	MCE_PANIC_SEVERITY,
 };
 
+extern struct atomic_notifier_head x86_mce_decoder_chain;
+
 #define ATTR_LEN		16
 #define INITIAL_CHECK_INTERVAL	5 * 60 /* 5 minutes */
 
@@ -24,6 +26,16 @@ struct mce_bank {
 	char			attrname[ATTR_LEN];	/* attribute name */
 };
 
+struct mce_evt_llist {
+	struct llist_node llnode;
+	struct mce mce;
+};
+
+void mce_gen_pool_process(void);
+bool mce_gen_pool_empty(void);
+int mce_gen_pool_add(struct mce *mce);
+int mce_gen_pool_init(void);
+
 extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp);
 struct dentry *mce_get_debugfs_dir(void);
 
@@ -67,3 +79,5 @@ static inline int apei_clear_mce(u64 record_id)
 	return -EINVAL;
 }
 #endif
+
+void mce_inject_log(struct mce *m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3d6b5269fb2e..0f8f21c8284a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -52,11 +52,11 @@
 
 static DEFINE_MUTEX(mce_chrdev_read_mutex);
 
-#define rcu_dereference_check_mce(p) \
+#define mce_log_get_idx_check(p) \
 ({ \
 	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
 			 !lockdep_is_held(&mce_chrdev_read_mutex), \
-			 "suspicious rcu_dereference_check_mce() usage"); \
+			 "suspicious mce_log_get_idx_check() usage"); \
 	smp_load_acquire(&(p)); \
 })
 
@@ -110,15 +110,17 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
  */
 mce_banks_t mce_banks_ce_disabled;
 
-static DEFINE_PER_CPU(struct work_struct, mce_work);
+static struct work_struct mce_work;
+static struct irq_work mce_irq_work;
 
 static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
+static int mce_usable_address(struct mce *m);
 
 /*
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
  */
-static ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
 
 /* Do initial initialization of a struct mce */
 void mce_setup(struct mce *m)
@@ -157,12 +159,13 @@ void mce_log(struct mce *mce)
 	/* Emit the trace record: */
 	trace_mce_record(mce);
 
-	atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+	if (!mce_gen_pool_add(mce))
+		irq_work_queue(&mce_irq_work);
 
 	mce->finished = 0;
 	wmb();
 	for (;;) {
-		entry = rcu_dereference_check_mce(mcelog.next);
+		entry = mce_log_get_idx_check(mcelog.next);
 		for (;;) {
 
 			/*
@@ -196,48 +199,23 @@ void mce_log(struct mce *mce)
 	set_bit(0, &mce_need_notify);
 }
 
-static void drain_mcelog_buffer(void)
+void mce_inject_log(struct mce *m)
 {
-	unsigned int next, i, prev = 0;
-
-	next = ACCESS_ONCE(mcelog.next);
-
-	do {
-		struct mce *m;
-
-		/* drain what was logged during boot */
-		for (i = prev; i < next; i++) {
-			unsigned long start = jiffies;
-			unsigned retries = 1;
-
-			m = &mcelog.entry[i];
-
-			while (!m->finished) {
-				if (time_after_eq(jiffies, start + 2*retries))
-					retries++;
-
-				cpu_relax();
-
-				if (!m->finished && retries >= 4) {
-					pr_err("skipping error being logged currently!\n");
-					break;
-				}
-			}
-			smp_rmb();
-			atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
-		}
-
-		memset(mcelog.entry + prev, 0, (next - prev) * sizeof(*m));
-		prev = next;
-		next = cmpxchg(&mcelog.next, prev, 0);
-	} while (next != prev);
+	mutex_lock(&mce_chrdev_read_mutex);
+	mce_log(m);
+	mutex_unlock(&mce_chrdev_read_mutex);
 }
+EXPORT_SYMBOL_GPL(mce_inject_log);
 
+static struct notifier_block mce_srao_nb;
 
 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_notifier_chain_register(&x86_mce_decoder_chain, nb);
-	drain_mcelog_buffer();
 }
 EXPORT_SYMBOL_GPL(mce_register_decode_chain);
 
@@ -461,61 +439,6 @@ static inline void mce_gather_info(struct mce *m, struct pt_regs *regs)
 	}
 }
 
-/*
- * Simple lockless ring to communicate PFNs from the exception handler with the
- * process context work function. This is vastly simplified because there's
- * only a single reader and a single writer.
- */
-#define MCE_RING_SIZE 16	/* we use one entry less */
-
-struct mce_ring {
-	unsigned short start;
-	unsigned short end;
-	unsigned long ring[MCE_RING_SIZE];
-};
-static DEFINE_PER_CPU(struct mce_ring, mce_ring);
-
-/* Runs with CPU affinity in workqueue */
-static int mce_ring_empty(void)
-{
-	struct mce_ring *r = this_cpu_ptr(&mce_ring);
-
-	return r->start == r->end;
-}
-
-static int mce_ring_get(unsigned long *pfn)
-{
-	struct mce_ring *r;
-	int ret = 0;
-
-	*pfn = 0;
-	get_cpu();
-	r = this_cpu_ptr(&mce_ring);
-	if (r->start == r->end)
-		goto out;
-	*pfn = r->ring[r->start];
-	r->start = (r->start + 1) % MCE_RING_SIZE;
-	ret = 1;
-out:
-	put_cpu();
-	return ret;
-}
-
-/* Always runs in MCE context with preempt off */
-static int mce_ring_add(unsigned long pfn)
-{
-	struct mce_ring *r = this_cpu_ptr(&mce_ring);
-	unsigned next;
-
-	next = (r->end + 1) % MCE_RING_SIZE;
-	if (next == r->start)
-		return -1;
-	r->ring[r->end] = pfn;
-	wmb();
-	r->end = next;
-	return 0;
-}
-
 int mce_available(struct cpuinfo_x86 *c)
 {
 	if (mca_cfg.disabled)
@@ -525,12 +448,10 @@ int mce_available(struct cpuinfo_x86 *c)
 
 static void mce_schedule_work(void)
 {
-	if (!mce_ring_empty())
-		schedule_work(this_cpu_ptr(&mce_work));
+	if (!mce_gen_pool_empty() && keventd_up())
+		schedule_work(&mce_work);
 }
 
-static DEFINE_PER_CPU(struct irq_work, mce_irq_work);
-
 static void mce_irq_work_cb(struct irq_work *entry)
 {
 	mce_notify_irq();
@@ -551,8 +472,29 @@ static void mce_report_event(struct pt_regs *regs)
 		return;
 	}
 
-	irq_work_queue(this_cpu_ptr(&mce_irq_work));
+	irq_work_queue(&mce_irq_work);
+}
+
+static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
+				void *data)
+{
+	struct mce *mce = (struct mce *)data;
+	unsigned long pfn;
+
+	if (!mce)
+		return NOTIFY_DONE;
+
+	if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) {
+		pfn = mce->addr >> PAGE_SHIFT;
+		memory_failure(pfn, MCE_VECTOR, 0);
+	}
+
+	return NOTIFY_OK;
 }
+static struct notifier_block mce_srao_nb = {
+	.notifier_call	= srao_decode_notifier,
+	.priority = INT_MAX,
+};
 
 /*
  * Read ADDR and MISC registers.
@@ -672,8 +614,11 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		 */
 		if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) {
 			if (m.status & MCI_STATUS_ADDRV) {
-				mce_ring_add(m.addr >> PAGE_SHIFT);
-				mce_schedule_work();
+				m.severity = severity;
+				m.usable_addr = mce_usable_address(&m);
+
+				if (!mce_gen_pool_add(&m))
+					mce_schedule_work();
 			}
 		}
 
@@ -1143,15 +1088,9 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 		mce_read_aux(&m, i);
 
-		/*
-		 * Action optional error. Queue address for later processing.
-		 * When the ring overflows we just ignore the AO error.
-		 * RED-PEN add some logging mechanism when
-		 * usable_address or mce_add_ring fails.
-		 * RED-PEN don't ignore overflow for mca_cfg.tolerant == 0
-		 */
-		if (severity == MCE_AO_SEVERITY && mce_usable_address(&m))
-			mce_ring_add(m.addr >> PAGE_SHIFT);
+		/* assuming valid severity level != 0 */
+		m.severity = severity;
+		m.usable_addr = mce_usable_address(&m);
 
 		mce_log(&m);
 
@@ -1247,14 +1186,11 @@ int memory_failure(unsigned long pfn, int vector, int flags)
 /*
  * Action optional processing happens here (picking up
  * from the list of faulting pages that do_machine_check()
- * placed into the "ring").
+ * placed into the genpool).
  */
 static void mce_process_work(struct work_struct *dummy)
 {
-	unsigned long pfn;
-
-	while (mce_ring_get(&pfn))
-		memory_failure(pfn, MCE_VECTOR, 0);
+	mce_gen_pool_process();
 }
 
 #ifdef CONFIG_X86_MCE_INTEL
@@ -1678,6 +1614,17 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 	}
 }
 
+static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
+{
+	switch (c->x86_vendor) {
+	case X86_VENDOR_INTEL:
+		mce_intel_feature_clear(c);
+		break;
+	default:
+		break;
+	}
+}
+
 static void mce_start_timer(unsigned int cpu, struct timer_list *t)
 {
 	unsigned long iv = check_interval * HZ;
@@ -1731,13 +1678,36 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 		return;
 	}
 
+	if (mce_gen_pool_init()) {
+		mca_cfg.disabled = true;
+		pr_emerg("Couldn't allocate MCE records pool!\n");
+		return;
+	}
+
 	machine_check_vector = do_machine_check;
 
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_timer();
-	INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work);
-	init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb);
+}
+
+/*
+ * Called for each booted CPU to clear some machine checks opt-ins
+ */
+void mcheck_cpu_clear(struct cpuinfo_x86 *c)
+{
+	if (mca_cfg.disabled)
+		return;
+
+	if (!mce_available(c))
+		return;
+
+	/*
+	 * Possibly to clear general settings generic to x86
+	 * __mcheck_cpu_clear_generic(c);
+	 */
+	__mcheck_cpu_clear_vendor(c);
+
 }
 
 /*
@@ -1850,7 +1820,7 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
 			goto out;
 	}
 
-	next = rcu_dereference_check_mce(mcelog.next);
+	next = mce_log_get_idx_check(mcelog.next);
 
 	/* Only supports full reads right now */
 	err = -EINVAL;
@@ -2056,8 +2026,12 @@ __setup("mce", mcheck_enable);
 int __init mcheck_init(void)
 {
 	mcheck_intel_therm_init();
+	mce_register_decode_chain(&mce_srao_nb);
 	mcheck_vendor_init_severity();
 
+	INIT_WORK(&mce_work, mce_process_work);
+	init_irq_work(&mce_irq_work, mce_irq_work_cb);
+
 	return 0;
 }
 
@@ -2591,5 +2565,20 @@ static int __init mcheck_debugfs_init(void)
 
 	return 0;
 }
-late_initcall(mcheck_debugfs_init);
+#else
+static int __init mcheck_debugfs_init(void) { return -EINVAL; }
 #endif
+
+static int __init mcheck_late_init(void)
+{
+	mcheck_debugfs_init();
+
+	/*
+	 * Flush out everything that has been logged during early boot, now that
+	 * everything has been initialized (workqueues, decoders, ...).
+	 */
+	mce_schedule_work();
+
+	return 0;
+}
+late_initcall(mcheck_late_init);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 844f56c5616d..1e8bb6c94f14 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -146,6 +146,27 @@ void mce_intel_hcpu_update(unsigned long cpu)
 	per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
 }
 
+static void cmci_toggle_interrupt_mode(bool on)
+{
+	unsigned long flags, *owned;
+	int bank;
+	u64 val;
+
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	owned = this_cpu_ptr(mce_banks_owned);
+	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
+		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+
+		if (on)
+			val |= MCI_CTL2_CMCI_EN;
+		else
+			val &= ~MCI_CTL2_CMCI_EN;
+
+		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	}
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
 unsigned long cmci_intel_adjust_timer(unsigned long interval)
 {
 	if ((this_cpu_read(cmci_backoff_cnt) > 0) &&
@@ -175,7 +196,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval)
 		 */
 		if (!atomic_read(&cmci_storm_on_cpus)) {
 			__this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
-			cmci_reenable();
+			cmci_toggle_interrupt_mode(true);
 			cmci_recheck();
 		}
 		return CMCI_POLL_INTERVAL;
@@ -186,22 +207,6 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval)
 	}
 }
 
-static void cmci_storm_disable_banks(void)
-{
-	unsigned long flags, *owned;
-	int bank;
-	u64 val;
-
-	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	owned = this_cpu_ptr(mce_banks_owned);
-	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
-		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
-		val &= ~MCI_CTL2_CMCI_EN;
-		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
-	}
-	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
-}
-
 static bool cmci_storm_detect(void)
 {
 	unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
@@ -223,7 +228,7 @@ static bool cmci_storm_detect(void)
 	if (cnt <= CMCI_STORM_THRESHOLD)
 		return false;
 
-	cmci_storm_disable_banks();
+	cmci_toggle_interrupt_mode(false);
 	__this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
 	r = atomic_add_return(1, &cmci_storm_on_cpus);
 	mce_timer_kick(CMCI_STORM_INTERVAL);
@@ -246,7 +251,6 @@ static void intel_threshold_interrupt(void)
 		return;
 
 	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
-	mce_notify_irq();
 }
 
 /*
@@ -435,7 +439,7 @@ static void intel_init_cmci(void)
 	cmci_recheck();
 }
 
-void intel_init_lmce(void)
+static void intel_init_lmce(void)
 {
 	u64 val;
 
@@ -448,9 +452,26 @@ void intel_init_lmce(void)
 		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
 }
 
+static void intel_clear_lmce(void)
+{
+	u64 val;
+
+	if (!lmce_supported())
+		return;
+
+	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+	val &= ~MCG_EXT_CTL_LMCE_EN;
+	wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
+}
+
 void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
 	intel_init_thermal(c);
 	intel_init_cmci();
 	intel_init_lmce();
 }
+
+void mce_intel_feature_clear(struct cpuinfo_x86 *c)
+{
+	intel_clear_lmce();
+}