From: Andi Kleen <ak@suse.de>
Date: Mon, 12 Sep 2005 16:49:24 +0000 (+0200)
Subject: [PATCH] x86-64: Make lockless machine check record passing a bit more robust.
X-Git-Tag: v2.6.14-rc1~68
X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=673242c10d535bfe238d9d8e82ac93432d35b88e;p=linux-2.6

[PATCH] x86-64: Make lockless machine check record passing a bit more robust.

One machine is constantly throwing NMI watchdog timeouts in mce_log

This was one attempt to fix it.

(AK: this doesn't actually fix the bug I'm seeing unfortunately, probably
drop.  I don't like it that the reader can spin forever now waiting
for a writer)

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
---

diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index 8aa56736cd..87ea8fdd43 100644
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -56,15 +56,19 @@ void mce_log(struct mce *mce)
 	smp_wmb();
 	for (;;) {
 		entry = rcu_dereference(mcelog.next);
-		/* When the buffer fills up discard new entries. Assume 
-		   that the earlier errors are the more interesting. */
-		if (entry >= MCE_LOG_LEN) {
-			set_bit(MCE_OVERFLOW, &mcelog.flags);
-			return;
+		for (;;) {
+			/* When the buffer fills up discard new entries. Assume
+			   that the earlier errors are the more interesting. */
+			if (entry >= MCE_LOG_LEN) {
+				set_bit(MCE_OVERFLOW, &mcelog.flags);
+				return;
+			}
+			/* Old left over entry. Skip. */
+			if (mcelog.entry[entry].finished) {
+				entry++;
+				continue;
+			}
 		}
-		/* Old left over entry. Skip. */
-		if (mcelog.entry[entry].finished)
-			continue;
 		smp_rmb();
 		next = entry + 1;
 		if (cmpxchg(&mcelog.next, entry, next) == entry)
@@ -404,9 +408,15 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff
 	}
 
 	err = 0;
-	for (i = 0; i < next; i++) {
-		if (!mcelog.entry[i].finished)
-			continue;
+	for (i = 0; i < next; i++) {		
+		unsigned long start = jiffies;
+		while (!mcelog.entry[i].finished) {
+			if (!time_before(jiffies, start + 2)) {
+				memset(mcelog.entry + i,0, sizeof(struct mce));
+				continue;
+			}
+			cpu_relax();
+		}
 		smp_rmb();
 		err |= copy_to_user(buf, mcelog.entry + i, sizeof(struct mce));
 		buf += sizeof(struct mce);