From: Borislav Petkov <bp@alien8.de>
To: Tony Luck <tony.luck@intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>, X86 ML <x86@kernel.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: [RFC PATCH 3/3] x86/MCE: Dump MCE to dmesg if no consumers
Date: Tue, 1 Nov 2016 13:09:11 +0100 [thread overview]
Message-ID: <20161101120911.13163-4-bp@alien8.de> (raw)
In-Reply-To: <20161101120911.13163-1-bp@alien8.de>
From: Borislav Petkov <bp@suse.de>
When there are no error record consumers registered with the kernel, the
only thing that appears in dmesg is something like:
[ 300.000326] mce: [Hardware Error]: Machine check events logged
and the error records are gone. Which is seriously counterproductive.
So let's dump them to dmesg instead, in such a case.
Signed-off-by: Borislav Petkov <bp@suse.de>
---
arch/x86/kernel/cpu/mcheck/mce.c | 52 +++++++++++++++++++++++++++++++++++-----
1 file changed, 46 insertions(+), 6 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a7fdf453d895..4ca00474804b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -207,8 +207,12 @@ EXPORT_SYMBOL_GPL(mce_inject_log);
static struct notifier_block mce_srao_nb;
+static atomic_t num_notifiers;
+
void mce_register_decode_chain(struct notifier_block *nb)
{
+ atomic_inc(&num_notifiers);
+
/* Ensure SRAO notifier has the highest priority in the decode chain. */
if (nb != &mce_srao_nb && nb->priority == INT_MAX)
nb->priority -= 1;
@@ -219,6 +223,8 @@ EXPORT_SYMBOL_GPL(mce_register_decode_chain);
void mce_unregister_decode_chain(struct notifier_block *nb)
{
+ atomic_dec(&num_notifiers);
+
atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
@@ -270,17 +276,17 @@ struct mca_msr_regs msr_ops = {
.misc = misc_reg
};
-static void print_mce(struct mce *m)
+static void __print_mce(struct mce *m)
{
- int ret = 0;
-
- pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
- m->extcpu, m->mcgstatus, m->bank, m->status);
+ pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n",
+ m->extcpu,
+ (m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""),
+ m->mcgstatus, m->bank, m->status);
if (m->ip) {
pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ",
!(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
- m->cs, m->ip);
+ m->cs, m->ip);
if (m->cs == __KERNEL_CS)
print_symbol("{%s}", m->ip);
@@ -308,6 +314,13 @@ static void print_mce(struct mce *m)
pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
cpu_data(m->extcpu).microcode);
+}
+
+static void print_mce(struct mce *m)
+{
+ int ret = 0;
+
+ __print_mce(m);
/*
* Print out human-readable details about the MCE error,
@@ -569,6 +582,32 @@ static struct notifier_block mce_srao_nb = {
.priority = INT_MAX,
};
+static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct mce *m = (struct mce *)data;
+
+ if (!m)
+ return NOTIFY_DONE;
+
+ /*
+ * Run the default notifier if we have only the SRAO
+ * notifier and us registered.
+ */
+ if (atomic_read(&num_notifiers) > 2)
+ return NOTIFY_DONE;
+
+ __print_mce(m);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block mce_default_nb = {
+ .notifier_call = mce_default_notifier,
+ /* lowest prio, we want it to run last. */
+ .priority = 0,
+};
+
/*
* Read ADDR and MISC registers.
*/
@@ -2138,6 +2177,7 @@ int __init mcheck_init(void)
{
mcheck_intel_therm_init();
mce_register_decode_chain(&mce_srao_nb);
+ mce_register_decode_chain(&mce_default_nb);
mcheck_vendor_init_severity();
INIT_WORK(&mce_work, mce_process_work);
--
2.10.0
next prev parent reply other threads:[~2016-11-01 12:09 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-01 12:09 [RFC PATCH 0/3] x86/RAS: Dump error record to dmesg if no consumers Borislav Petkov
2016-11-01 12:09 ` [RFC PATCH 1/3] notifiers: Document notifier priority Borislav Petkov
2016-11-01 12:09 ` [RFC PATCH 2/3] x86/RAS: Add TSC to the injected MCE Borislav Petkov
2016-11-08 16:19 ` [tip:ras/core] x86/RAS: Add TSC timestamp " tip-bot for Borislav Petkov
2016-11-01 12:09 ` Borislav Petkov [this message]
2016-11-08 16:19 ` [tip:ras/core] x86/MCE: Dump MCE to dmesg if no consumers tip-bot for Borislav Petkov
2016-11-05 13:11 ` [PATCH] x86/MCE: Remove MCP_TIMESTAMP Borislav Petkov
2016-11-07 17:48 ` Luck, Tony
2016-11-07 18:08 ` Borislav Petkov
2016-11-07 18:37 ` Luck, Tony
2016-11-08 18:09 ` Borislav Petkov
2016-11-08 18:22 ` Luck, Tony
2016-11-08 20:39 ` Thomas Gleixner
2016-11-08 21:08 ` Borislav Petkov
2016-11-08 21:14 ` Thomas Gleixner
2016-11-08 21:24 ` Borislav Petkov
2016-11-08 21:54 ` Thomas Gleixner
2016-11-09 18:06 ` Borislav Petkov
2017-01-18 20:34 ` Borislav Petkov
2017-01-19 13:34 ` Borislav Petkov
2016-11-07 7:37 ` [RFC PATCH 0/3] x86/RAS: Dump error record to dmesg if no consumers Ingo Molnar
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=20161101120911.13163-4-bp@alien8.de \
--to=bp@alien8.de \
--cc=linux-edac@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tony.luck@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.