This is a note to let you know that I've just added the patch titled
x86/mce: Reenable CMCI banks when swiching back to interrupt mode
to the 4.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
x86-mce-reenable-cmci-banks-when-swiching-back-to-interrupt-mode.patch
and it can be found in the queue-4.1 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 1b48465500611a2dc5e75800c61ac352e22d41c3 Mon Sep 17 00:00:00 2001
From: Xie XiuQi <xiexiuqi@xxxxxxxxxx>
Date: Wed, 12 Aug 2015 18:29:41 +0200
Subject: x86/mce: Reenable CMCI banks when swiching back to interrupt mode
From: Xie XiuQi <xiexiuqi@xxxxxxxxxx>
commit 1b48465500611a2dc5e75800c61ac352e22d41c3 upstream.
Zhang Liguang reported the following issue:
1) System detects a CMCI storm on the current CPU.
2) Kernel disables the CMCI interrupt on banks owned by the
current CPU and switches to poll mode
3) After the CMCI storm subsides, kernel switches back to
interrupt mode
4) We expect the system to reenable the CMCI interrupt on banks
owned by the current CPU
mce_intel_adjust_timer
|-> cmci_reenable
|-> cmci_discover # owned banks are ignored here
static void cmci_discover(int banks)
...
for (i = 0; i < banks; i++) {
...
if (test_bit(i, owned)) # ownd banks is ignore here
continue;
So convert cmci_storm_disable_banks() to
cmci_toggle_interrupt_mode() which controls whether to enable or
disable CMCI interrupts with its argument.
NB: We cannot clear the owned bit because the banks won't be
polled, otherwise. See:
27f6c573e0f7 ("x86, CMCI: Add proper detection of end of CMCI storms")
for more info.
Reported-by: Zhang Liguang <zhangliguang@xxxxxxxxxx>
Signed-off-by: Xie XiuQi <xiexiuqi@xxxxxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: huawei.libin@xxxxxxxxxx
Cc: linux-edac <linux-edac@xxxxxxxxxxxxxxx>
Cc: rui.xiang@xxxxxxxxxx
Link: http://lkml.kernel.org/r/1439396985-12812-10-git-send-email-bp@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/kernel/cpu/mcheck/mce_intel.c | 41 ++++++++++++++++++---------------
1 file changed, 23 insertions(+), 18 deletions(-)
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -116,6 +116,27 @@ void mce_intel_hcpu_update(unsigned long
per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
}
+static void cmci_toggle_interrupt_mode(bool on)
+{
+ unsigned long flags, *owned;
+ int bank;
+ u64 val;
+
+ raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ owned = this_cpu_ptr(mce_banks_owned);
+ for_each_set_bit(bank, owned, MAX_NR_BANKS) {
+ rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+
+ if (on)
+ val |= MCI_CTL2_CMCI_EN;
+ else
+ val &= ~MCI_CTL2_CMCI_EN;
+
+ wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ }
+ raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
unsigned long cmci_intel_adjust_timer(unsigned long interval)
{
if ((this_cpu_read(cmci_backoff_cnt) > 0) &&
@@ -145,7 +166,7 @@ unsigned long cmci_intel_adjust_timer(un
*/
if (!atomic_read(&cmci_storm_on_cpus)) {
__this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
- cmci_reenable();
+ cmci_toggle_interrupt_mode(true);
cmci_recheck();
}
return CMCI_POLL_INTERVAL;
@@ -156,22 +177,6 @@ unsigned long cmci_intel_adjust_timer(un
}
}
-static void cmci_storm_disable_banks(void)
-{
- unsigned long flags, *owned;
- int bank;
- u64 val;
-
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
- owned = this_cpu_ptr(mce_banks_owned);
- for_each_set_bit(bank, owned, MAX_NR_BANKS) {
- rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
- val &= ~MCI_CTL2_CMCI_EN;
- wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
- }
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
-}
-
static bool cmci_storm_detect(void)
{
unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
@@ -193,7 +198,7 @@ static bool cmci_storm_detect(void)
if (cnt <= CMCI_STORM_THRESHOLD)
return false;
- cmci_storm_disable_banks();
+ cmci_toggle_interrupt_mode(false);
__this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
r = atomic_add_return(1, &cmci_storm_on_cpus);
mce_timer_kick(CMCI_STORM_INTERVAL);
Patches currently in stable-queue which might be from xiexiuqi@xxxxxxxxxx are
queue-4.1/x86-mce-reenable-cmci-banks-when-swiching-back-to-interrupt-mode.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html