From: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
To: linux-kernel@vger.kernel.org, x86@kernel.org
Cc: Andi Kleen <ak@linux.intel.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
Mike Travis <travis@sgi.com>, Roland Dreier <rdreier@cisco.com>
Subject: [PATCH] x86, mce: short output of MCE banks ownership information
Date: Thu, 29 Oct 2009 12:38:43 +0900 [thread overview]
Message-ID: <4AE90E43.2030709@jp.fujitsu.com> (raw)
The output of MCE banks ownership information on boot tend to be long on
new processor which has many banks:
CPU 1 MCA banks SHD:0 SHD:1 CMCI:2 CMCI:3 CMCI:5 SHD:6 SHD:7 SHD:8 SHD:9 SHD:12 SHD:13 SHD:14 SHD:15 SHD:16 SHD:17 SHD:18 SHD:19 SHD:20 SHD:21
This patch changes this message to shorter format, in lower message level
(KERN_INFO -> KERN_DEBUG), and replace "MCA" by "MCE":
CPU 1 MCE banks map: ssCC PCss ssPP ssss ssss ss
where: s: shared, C: checked by CMCI, P: checked by poll.
(NOTE: This patch still use old format on the output when ownership is
updated, e.g. a cpu take over the ownership from hot-removed cpu.
CPU 1 MCE banks map updated: CMCI:6 CMCI:7 CMCI:10 CMCI:11
CPU 1 MCE banks map: ssCC PCCC ssPP ssCC ssss ss
)
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
---
arch/x86/kernel/cpu/mcheck/mce_intel.c | 29 +++++++++++++++++++++++------
1 files changed, 23 insertions(+), 6 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 7c78563..2b4c78b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -64,12 +64,25 @@ static void intel_threshold_interrupt(void)
mce_notify_irq();
}
+static void print_banks_map(int banks)
+{
+ int i;
+
+ pr_debug("CPU %d MCE banks map:", smp_processor_id());
+ for (i = 0; i < banks; i++) {
+ pr_cont("%s%s", (i % 4) ? "" : " ",
+ test_bit(i, __get_cpu_var(mce_banks_owned)) ? "C" :
+ test_bit(i, __get_cpu_var(mce_poll_banks)) ? "P" : "s");
+ }
+ pr_cont("\n");
+}
+
static void print_update(char *type, int *hdr, int num)
{
if (*hdr == 0)
- printk(KERN_INFO "CPU %d MCA banks", smp_processor_id());
+ pr_debug("CPU %d MCE banks map updated:", smp_processor_id());
*hdr = 1;
- printk(KERN_CONT " %s:%d", type, num);
+ pr_cont(" %s:%d", type, num);
}
/*
@@ -85,6 +98,7 @@ static void cmci_discover(int banks, int boot)
int i;
spin_lock_irqsave(&cmci_discover_lock, flags);
+
for (i = 0; i < banks; i++) {
u64 val;
@@ -95,7 +109,7 @@ static void cmci_discover(int banks, int boot)
/* Already owned by someone else? */
if (val & CMCI_EN) {
- if (test_and_clear_bit(i, owned) || boot)
+ if (test_and_clear_bit(i, owned) && !boot)
print_update("SHD", &hdr, i);
__clear_bit(i, __get_cpu_var(mce_poll_banks));
continue;
@@ -107,16 +121,19 @@ static void cmci_discover(int banks, int boot)
/* Did the enable bit stick? -- the bank supports CMCI */
if (val & CMCI_EN) {
- if (!test_and_set_bit(i, owned) || boot)
+ if (!test_and_set_bit(i, owned) && !boot)
print_update("CMCI", &hdr, i);
__clear_bit(i, __get_cpu_var(mce_poll_banks));
} else {
WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
}
}
- spin_unlock_irqrestore(&cmci_discover_lock, flags);
if (hdr)
- printk(KERN_CONT "\n");
+ pr_cont("\n");
+ if (boot || hdr)
+ print_banks_map(banks);
+
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
/*
--
1.6.5.2
next reply other threads:[~2009-10-29 3:39 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-10-29 3:38 Hidetoshi Seto [this message]
2009-10-29 3:45 ` [PATCH] x86, mce: short output of MCE banks ownership information Roland Dreier
2009-10-29 6:50 ` Hidetoshi Seto
2009-10-29 7:34 ` Ingo Molnar
2009-10-29 8:27 ` Hidetoshi Seto
2009-10-29 9:09 ` Ingo Molnar
2009-10-29 16:07 ` Mike Travis
2009-10-29 16:00 ` Mike Travis
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4AE90E43.2030709@jp.fujitsu.com \
--to=seto.hidetoshi@jp.fujitsu.com \
--cc=ak@linux.intel.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=rdreier@cisco.com \
--cc=tglx@linutronix.de \
--cc=travis@sgi.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox