Merge branch 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS update from Ingo Molnar:
 "The changes in this tree are:

   - ACPI APEI (ACPI Platform Error Interface) improvements, by Chen
     Gong
   - misc MCE fixes/cleanups"

* 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Update MCE severity condition check
  mce: acpi/apei: Add comments to clarify usage of the various bitfields in the MCA subsystem
  ACPI/APEI: Update einj documentation for param1/param2
  ACPI/APEI: Add parameter check before error injection
  ACPI, APEI, EINJ: Fix error return code in einj_init()
  x86, mce: Fix "braodcast" typo

4 files changed, 23 insertions, 13 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index ddc72f839332..5ac2d1fb28bc 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -153,7 +153,7 @@ static void raise_mce(struct mce *m)
 		return;
 
 #ifdef CONFIG_X86_LOCAL_APIC
-	if (m->inject_flags & (MCJ_IRQ_BRAODCAST | MCJ_NMI_BROADCAST)) {
+	if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) {
 		unsigned long start;
 		int cpu;
 
@@ -167,7 +167,7 @@ static void raise_mce(struct mce *m)
 				cpumask_clear_cpu(cpu, mce_inject_cpumask);
 		}
 		if (!cpumask_empty(mce_inject_cpumask)) {
-			if (m->inject_flags & MCJ_IRQ_BRAODCAST) {
+			if (m->inject_flags & MCJ_IRQ_BROADCAST) {
 				/*
 				 * don't wait because mce_irq_ipi is necessary
 				 * to be sync with following raise_local
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index beb1f1689e52..e2703520d120 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -110,22 +110,17 @@ static struct severity {
 	/* known AR MCACODs: */
 #ifdef	CONFIG_MEMORY_FAILURE
 	MCESEV(
-		KEEP, "HT thread notices Action required: data load error",
-		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
-		MCGMASK(MCG_STATUS_EIPV, 0)
+		KEEP, "Action required but unaffected thread is continuable",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR),
+		MCGMASK(MCG_STATUS_RIPV, MCG_STATUS_RIPV)
 		),
 	MCESEV(
-		AR, "Action required: data load error",
+		AR, "Action required: data load error in a user process",
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
 		USER
 		),
 	MCESEV(
-		KEEP, "HT thread notices Action required: instruction fetch error",
-		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
-		MCGMASK(MCG_STATUS_EIPV, 0)
-		),
-	MCESEV(
-		AR, "Action required: instruction fetch error",
+		AR, "Action required: instruction fetch error in a user process",
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
 		USER
 		),
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 9239504b41cb..bf49cdbb010f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -89,7 +89,10 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int			cpu_missing;
 
-/* MCA banks polled by the period polling timer for corrected events */
+/*
+ * MCA banks polled by the period polling timer for corrected events.
+ * With Intel CMCI, this only has MCA banks which do not support CMCI (if any).
+ */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
 };
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index ae1697c2afe3..d56405309dc1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -24,6 +24,18 @@
  * Also supports reliable discovery of shared banks.
  */
 
+/*
+ * CMCI can be delivered to multiple cpus that share a machine check bank
+ * so we need to designate a single cpu to process errors logged in each bank
+ * in the interrupt handler (otherwise we would have many races and potential
+ * double reporting of the same error).
+ * Note that this can change when a cpu is offlined or brought online since
+ * some MCA banks are shared across cpus. When a cpu is offlined, cmci_clear()
+ * disables CMCI on all banks owned by the cpu and clears this bitfield. At
+ * this point, cmci_rediscover() kicks in and a different cpu may end up
+ * taking ownership of some of the shared MCA banks that were previously
+ * owned by the offlined cpu.
+ */
 static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
 
 /*