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

Pull ras fixes from Thomas Gleixner:
 "A set of fixes for RAS/MCE:

   - Improve the error message when the kernel cannot recover from a MCE
     so the maximum amount of information gets provided.

   - Individually check MCE recovery features on SkyLake CPUs instead of
     assuming none when the CAPID0 register does not advertise the
     general ability for recovery.

   - Prevent MCE to output inconsistent messages which first show an
     error location and then claim that the source is unknown.

   - Prevent overwriting MCi_STATUS in the attempt to gather more
     information when a fatal MCE has alreay been detected. This leads
     to empty status values in the printout and failing to react
     promptly on the fatal event"

* 'ras-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Fix incorrect "Machine check from unknown source" message
  x86/mce: Do not overwrite MCi_STATUS in mce_no_way_out()
  x86/mce: Check for alternate indication of machine check recovery on Skylake
  x86/mce: Improve error message when kernel cannot recover

1 files changed, 28 insertions, 16 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e4cf6ff1c2e1..c102ad51025e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -772,23 +772,25 @@ EXPORT_SYMBOL_GPL(machine_check_poll);
 static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			  struct pt_regs *regs)
 {
-	int i, ret = 0;
 	char *tmp;
+	int i;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		m->status = mce_rdmsrl(msr_ops.status(i));
-		if (m->status & MCI_STATUS_VAL) {
-			__set_bit(i, validp);
-			if (quirk_no_way_out)
-				quirk_no_way_out(i, m, regs);
-		}
+		if (!(m->status & MCI_STATUS_VAL))
+			continue;
+
+		__set_bit(i, validp);
+		if (quirk_no_way_out)
+			quirk_no_way_out(i, m, regs);
 
 		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			mce_read_aux(m, i);
 			*msg = tmp;
-			ret = 1;
+			return 1;
 		}
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -1205,13 +1207,18 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		lmce = m.mcgstatus & MCG_STATUS_LMCES;
 
 	/*
+	 * Local machine check may already know that we have to panic.
+	 * Broadcast machine check begins rendezvous in mce_start()
 	 * Go through all banks in exclusion of the other CPUs. This way we
 	 * don't report duplicated events on shared banks because the first one
-	 * to see it will clear it. If this is a Local MCE, then no need to
-	 * perform rendezvous.
+	 * to see it will clear it.
 	 */
-	if (!lmce)
+	if (lmce) {
+		if (no_way_out)
+			mce_panic("Fatal local machine check", &m, msg);
+	} else {
 		order = mce_start(&no_way_out);
+	}
 
 	for (i = 0; i < cfg->banks; i++) {
 		__clear_bit(i, toclear);
@@ -1287,12 +1294,17 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 			no_way_out = worst >= MCE_PANIC_SEVERITY;
 	} else {
 		/*
-		 * Local MCE skipped calling mce_reign()
-		 * If we found a fatal error, we need to panic here.
+		 * If there was a fatal machine check we should have
+		 * already called mce_panic earlier in this function.
+		 * Since we re-read the banks, we might have found
+		 * something new. Check again to see if we found a
+		 * fatal error. We call "mce_severity()" again to
+		 * make sure we have the right "msg".
 		 */
-		 if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
-			mce_panic("Machine check from unknown source",
-				NULL, NULL);
+		if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) {
+			mce_severity(&m, cfg->tolerant, &msg, true);
+			mce_panic("Local fatal machine check!", &m, msg);
+		}
 	}
 
 	/*