| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <4DA5ACB2.1070505@redhat.com>
Date: Wed, 13 Apr 2011 10:01:22 -0400
From: Prarit Bhargava <prarit@...hat.com>
To: Borislav Petkov <bp@...64.org>
CC: linux-kernel@...r.kernel.org,
Borislav Petkov <borislav.petkov@....com>,
Russ Anderson <rja@....com>,
"Luck, Tony" <tony.luck@...el.com>,
"dzickus@...hat.com" <dzickus@...hat.com>,
"mstowe@...hat.com" <mstowe@...hat.com>,
"dnelson@...hat.com" <dnelson@...hat.com>,
"rja@...ricas.sgi.com" <rja@...ricas.sgi.com>
Subject: Re: [PATCH 2/3] x86, MCE: Drop default decoding notifier
On 04/13/2011 09:36 AM, Borislav Petkov wrote:
> From: Borislav Petkov <borislav.petkov@....com>
>
> The default notifier doesn't make a lot of sense to call in the
> correctable errors case. Drop it and emit the mcelog decoding hint only
> in the uncorrectable errors case and when no notifier is registered.
>
> Signed-off-by: Borislav Petkov <borislav.petkov@....com>
> ---
> arch/x86/include/asm/mce.h | 4 ++--
> arch/x86/kernel/cpu/mcheck/mce.c | 26 +++++++++-----------------
> 2 files changed, 11 insertions(+), 19 deletions(-)
>
> +extern atomic_t mce_decoders;
> +
Boris,
I don't think we need to do this. I think we can use the existing notifier chain tools to do this check for us ... *untested and uncompiled* patch below.
* Print out human-readable details about the MCE error,
> * (if the CPU has an implementation for that)
> */
> - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
> + if (!atomic_read(&mce_decoders)) {
> + pr_emerg(HW_ERR "No human readable MCE decoding support on this CPU type.\n");
> + pr_emerg(HW_ERR "Run the above through 'mcelog --ascii' to decode.\n");
I thought we didn't want these lines at all for CE errors?
> + } else
> + atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
> }
>
> #define PANIC_TIMEOUT 5 /* 5 seconds */
> @@ -589,7 +582,8 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
> */
> if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
> mce_log(&m);
> - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
> + if (atomic_read(&mce_decoders))
> + atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
> }
>
> /*
> @@ -1721,8 +1715,6 @@ __setup("mce", mcheck_enable);
>
> int __init mcheck_init(void)
> {
> - atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb);
> -
> mcheck_intel_therm_init();
>
> return 0;
Again, this patch has not been tested or compiled against latest upstream. I
have quickly tested it against RHEL6 (2.6.32,33,34,35,36,38,39 based) and
confirmed that I don't see the messages for CEs. I have NOT fully tested to see what happens when I add in a "dummy" notifier to see if the messages are not printed.
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3385ea2..b10a1f4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -100,25 +100,12 @@ static int cpu_missing;
/*
* CPU/chipset specific EDAC code can register a notifier call here to print
- * MCE errors in a human-readable form.
+ * MCE errors in a human-readable form. Notifiers must return NOTIFY_STOP
+ * upon completion.
*/
ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
-static int default_decode_mce(struct notifier_block *nb, unsigned long val,
- void *data)
-{
- pr_emerg(HW_ERR "No human readable MCE decoding support on this CPU type.\n");
- pr_emerg(HW_ERR "Run the message through 'mcelog --ascii' to decode.\n");
-
- return NOTIFY_STOP;
-}
-
-static struct notifier_block mce_dec_nb = {
- .notifier_call = default_decode_mce,
- .priority = -1,
-};
-
/* MCA banks polled by the period polling timer for corrected events */
DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
@@ -212,6 +199,8 @@ void mce_log(struct mce *mce)
static void print_mce(struct mce *m)
{
+ int ret;
+
pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
m->extcpu, m->mcgstatus, m->bank, m->status);
@@ -236,10 +225,13 @@ static void print_mce(struct mce *m)
m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid);
/*
- * Print out human-readable details about the MCE error,
- * (if the CPU has an implementation for that)
+ * Output a message if the CPU has human-readable information for
+ * unhandled UC errors
*/
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+ ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
+ if ((ret != NOTIFY_STOP) && (m->status & MCI_STATUS_UC))
+ pr_emerg(HW_ERR "Run the message through 'mcelog --ascii' "
+ "to decode.\n");
}
#define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -589,8 +581,8 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
*/
if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
mce_log(&m);
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
- add_taint(TAINT_MACHINE_CHECK);
+ atomic_notifier_call_chain(&x86_mce_decoder_chain, 0,
+ &m);
}
/*
@@ -1722,8 +1714,6 @@ __setup("mce", mcheck_enable);
int __init mcheck_init(void)
{
- atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb);
-
mcheck_intel_therm_init();
return 0;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists