1 files changed, 45 insertions, 22 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index cdbedeb3f3db..fee118b3b69f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -711,19 +711,49 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 
 		barrier();
 		m.status = mce_rdmsrl(msr_ops.status(i));
+
+		/* If this entry is not valid, ignore it */
 		if (!(m.status & MCI_STATUS_VAL))
 			continue;
 
 		/*
-		 * Uncorrected or signalled events are handled by the exception
-		 * handler when it is enabled, so don't process those here.
-		 *
-		 * TBD do the same check for MCI_STATUS_EN here?
+		 * If we are logging everything (at CPU online) or this
+		 * is a corrected error, then we must log it.
 		 */
-		if (!(flags & MCP_UC) &&
-		    (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
-			continue;
+		if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC))
+			goto log_it;
+
+		/*
+		 * Newer Intel systems that support software error
+		 * recovery need to make additional checks. Other
+		 * CPUs should skip over uncorrected errors, but log
+		 * everything else.
+		 */
+		if (!mca_cfg.ser) {
+			if (m.status & MCI_STATUS_UC)
+				continue;
+			goto log_it;
+		}
+
+		/* Log "not enabled" (speculative) errors */
+		if (!(m.status & MCI_STATUS_EN))
+			goto log_it;
+
+		/*
+		 * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
+		 * UC == 1 && PCC == 0 && S == 0
+		 */
+		if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S))
+			goto log_it;
+
+		/*
+		 * Skip anything else. Presumption is that our read of this
+		 * bank is racing with a machine check. Leave the log alone
+		 * for do_machine_check() to deal with it.
+		 */
+		continue;
 
+log_it:
 		error_seen = true;
 
 		mce_read_aux(&m, i);
@@ -783,6 +813,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			quirk_no_way_out(i, m, regs);
 
 		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			m->bank = i;
 			mce_read_aux(m, i);
 			*msg = tmp;
 			return 1;
@@ -1449,13 +1480,12 @@ EXPORT_SYMBOL_GPL(mce_notify_irq);
 static int __mcheck_cpu_mce_banks_init(void)
 {
 	int i;
-	u8 num_banks = mca_cfg.banks;
 
-	mce_banks = kcalloc(num_banks, sizeof(struct mce_bank), GFP_KERNEL);
+	mce_banks = kcalloc(MAX_NR_BANKS, sizeof(struct mce_bank), GFP_KERNEL);
 	if (!mce_banks)
 		return -ENOMEM;
 
-	for (i = 0; i < num_banks; i++) {
+	for (i = 0; i < MAX_NR_BANKS; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		b->ctl = -1ULL;
@@ -1469,28 +1499,19 @@ static int __mcheck_cpu_mce_banks_init(void)
  */
 static int __mcheck_cpu_cap_init(void)
 {
-	unsigned b;
 	u64 cap;
+	u8 b;
 
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 
 	b = cap & MCG_BANKCNT_MASK;
-	if (!mca_cfg.banks)
-		pr_info("CPU supports %d MCE banks\n", b);
-
-	if (b > MAX_NR_BANKS) {
-		pr_warn("Using only %u machine check banks out of %u\n",
-			MAX_NR_BANKS, b);
+	if (WARN_ON_ONCE(b > MAX_NR_BANKS))
 		b = MAX_NR_BANKS;
-	}
 
-	/* Don't support asymmetric configurations today */
-	WARN_ON(mca_cfg.banks != 0 && b != mca_cfg.banks);
-	mca_cfg.banks = b;
+	mca_cfg.banks = max(mca_cfg.banks, b);
 
 	if (!mce_banks) {
 		int err = __mcheck_cpu_mce_banks_init();
-
 		if (err)
 			return err;
 	}
@@ -2472,6 +2493,8 @@ EXPORT_SYMBOL_GPL(mcsafe_key);
 
 static int __init mcheck_late_init(void)
 {
+	pr_info("Using %d MCE banks\n", mca_cfg.banks);
+
 	if (mca_cfg.recovery)
 		static_branch_inc(&mcsafe_key);