1 files changed, 140 insertions, 138 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index df919ff103c3..c5b0d562dbf5 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_assert(rcu_read_lock_sched_held() || \
-			   lockdep_is_held(&mce_chrdev_read_mutex), \
-			   "suspicious rcu_dereference_check_mce() usage"); \
+	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)); \
 })
 
@@ -110,22 +110,24 @@ 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)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
-	rdtscll(m->tsc);
+	m->tsc = rdtsc();
 	/* We hope get_seconds stays lockless */
 	m->time = get_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
@@ -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();
@@ -551,9 +472,30 @@ 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();
 			}
 		}
 
@@ -1029,7 +974,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 {
 	struct mca_config *cfg = &mca_cfg;
 	struct mce m, *final;
-	enum ctx_state prev_state;
 	int i;
 	int worst = 0;
 	int severity;
@@ -1055,7 +999,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	int flags = MF_ACTION_REQUIRED;
 	int lmce = 0;
 
-	prev_state = ist_enter(regs);
+	ist_enter(regs);
 
 	this_cpu_inc(mce_exception_count);
 
@@ -1143,15 +1087,9 @@ 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);
 
@@ -1227,7 +1165,7 @@ out:
 	local_irq_disable();
 	ist_end_non_atomic();
 done:
-	ist_exit(regs, prev_state);
+	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 
@@ -1247,14 +1185,11 @@ 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
@@ -1651,6 +1586,8 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
 		winchip_mcheck_init(c);
 		return 1;
 		break;
+	default:
+		return 0;
 	}
 
 	return 0;
@@ -1670,6 +1607,8 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_amd_feature_init(c);
 		mce_flags.overflow_recov = !!(ebx & BIT(0));
 		mce_flags.succor	 = !!(ebx & BIT(1));
+		mce_flags.smca		 = !!(ebx & BIT(3));
+
 		break;
 		}
 
@@ -1678,6 +1617,17 @@ 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 +1681,36 @@ 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);
+
 }
 
 /*
@@ -1784,7 +1757,7 @@ static void collect_tscs(void *data)
 {
 	unsigned long *cpu_tsc = (unsigned long *)data;
 
-	rdtscll(cpu_tsc[smp_processor_id()]);
+	cpu_tsc[smp_processor_id()] = rdtsc();
 }
 
 static int mce_apei_read_done;
@@ -1850,7 +1823,7 @@ 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 +2029,12 @@ __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;
 }
 
@@ -2069,7 +2046,7 @@ int __init mcheck_init(void)
  * Disable machine checks on suspend and shutdown. We can't really handle
  * them later.
  */
-static int mce_disable_error_reporting(void)
+static void mce_disable_error_reporting(void)
 {
 	int i;
 
@@ -2079,17 +2056,32 @@ static int mce_disable_error_reporting(void)
 		if (b->init)
 			wrmsrl(MSR_IA32_MCx_CTL(i), 0);
 	}
-	return 0;
+	return;
+}
+
+static void vendor_disable_error_reporting(void)
+{
+	/*
+	 * Don't clear on Intel CPUs. Some of these MSRs are socket-wide.
+	 * Disabling them for just a single offlined CPU is bad, since it will
+	 * inhibit reporting for all shared resources on the socket like the
+	 * last level cache (LLC), the integrated memory controller (iMC), etc.
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		return;
+
+	mce_disable_error_reporting();
 }
 
 static int mce_syscore_suspend(void)
 {
-	return mce_disable_error_reporting();
+	vendor_disable_error_reporting();
+	return 0;
 }
 
 static void mce_syscore_shutdown(void)
 {
-	mce_disable_error_reporting();
+	vendor_disable_error_reporting();
 }
 
 /*
@@ -2369,19 +2361,14 @@ static void mce_device_remove(unsigned int cpu)
 static void mce_disable_cpu(void *h)
 {
 	unsigned long action = *(unsigned long *)h;
-	int i;
 
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
 	if (!(action & CPU_TASKS_FROZEN))
 		cmci_clear();
-	for (i = 0; i < mca_cfg.banks; i++) {
-		struct mce_bank *b = &mce_banks[i];
 
-		if (b->init)
-			wrmsrl(MSR_IA32_MCx_CTL(i), 0);
-	}
+	vendor_disable_error_reporting();
 }
 
 static void mce_reenable_cpu(void *h)
@@ -2591,5 +2578,20 @@ 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);