Merge branch 'x86-ras-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 are:

   - RAS tracing/events infrastructure, by Gong Chen.

   - Various generalizations of the APEI code to make it available to
     non-x86 architectures, by Tomasz Nowicki"

* 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ras: Fix build warnings in <linux/aer.h>
  acpi, apei, ghes: Factor out ioremap virtual memory for IRQ and NMI context.
  acpi, apei, ghes: Make NMI error notification to be GHES architecture extension.
  apei, mce: Factor out APEI architecture specific MCE calls.
  RAS, extlog: Adjust init flow
  trace, eMCA: Add a knob to adjust where to save event log
  trace, RAS: Add eMCA trace event interface
  RAS, debugfs: Add debugfs interface for RAS subsystem
  CPER: Adjust code flow of some functions
  x86, MCE: Robustify mcheck_init_device
  trace, AER: Move trace into unified interface
  trace, RAS: Add basic RAS trace event
  x86, MCE: Kill CPU_POST_DEAD

3 files changed, 67 insertions, 5 deletions

diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index 163b225..3242e59 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -1,5 +1,6 @@
 obj-$(CONFIG_ACPI)		+= boot.o
 obj-$(CONFIG_ACPI_SLEEP)	+= sleep.o wakeup_$(BITS).o
+obj-$(CONFIG_ACPI_APEI)		+= apei.o
 
 ifneq ($(CONFIG_ACPI_PROCESSOR),)
 obj-y				+= cstate.o
diff --git a/arch/x86/kernel/acpi/apei.c b/arch/x86/kernel/acpi/apei.c
new file mode 100644
index 0000000..c280df6
--- /dev/null
+++ b/arch/x86/kernel/acpi/apei.c
@@ -0,0 +1,62 @@
+/*
+ * Arch-specific APEI-related functions.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <acpi/apei.h>
+
+#include <asm/mce.h>
+#include <asm/tlbflush.h>
+
+int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data)
+{
+#ifdef CONFIG_X86_MCE
+	int i;
+	struct acpi_hest_ia_corrected *cmc;
+	struct acpi_hest_ia_error_bank *mc_bank;
+
+	if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
+		return 0;
+
+	cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
+	if (!cmc->enabled)
+		return 0;
+
+	/*
+	 * We expect HEST to provide a list of MC banks that report errors
+	 * in firmware first mode. Otherwise, return non-zero value to
+	 * indicate that we are done parsing HEST.
+	 */
+	if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) ||
+	    !cmc->num_hardware_banks)
+		return 1;
+
+	pr_info("HEST: Enabling Firmware First mode for corrected errors.\n");
+
+	mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1);
+	for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++)
+		mce_disable_bank(mc_bank->bank_number);
+#endif
+	return 1;
+}
+
+void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
+{
+#ifdef CONFIG_X86_MCE
+	apei_mce_report_mem_error(sev, mem_err);
+#endif
+}
+
+void arch_apei_flush_tlb_one(unsigned long addr)
+{
+	__flush_tlb_one(addr);
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 9a79c8d..4fc5797 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2385,6 +2385,10 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 			threshold_cpu_callback(action, cpu);
 		mce_device_remove(cpu);
 		mce_intel_hcpu_update(cpu);
+
+		/* intentionally ignoring frozen here */
+		if (!(action & CPU_TASKS_FROZEN))
+			cmci_rediscover();
 		break;
 	case CPU_DOWN_PREPARE:
 		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
@@ -2396,11 +2400,6 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 	}
 
-	if (action == CPU_POST_DEAD) {
-		/* intentionally ignoring frozen here */
-		cmci_rediscover();
-	}
-
 	return NOTIFY_OK;
 }