Merge pull request #50 from MaxKrummenacher/4.14-2.0.x-imx

4.14 2.0.x imx

1 files changed, 37 insertions, 7 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 54874e2b1d32..4f3be91f0b0b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -701,19 +701,49 @@ 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);