[tip:ras/core] x86/mce: Reenable CMCI banks when swiching back to interrupt mode

From: tip-bot for Xie XiuQi
Date: Thu Aug 13 2015 - 06:49:52 EST


Commit-ID: 1b48465500611a2dc5e75800c61ac352e22d41c3
Gitweb: http://git.kernel.org/tip/1b48465500611a2dc5e75800c61ac352e22d41c3
Author: Xie XiuQi <xiexiuqi@xxxxxxxxxx>
AuthorDate: Wed, 12 Aug 2015 18:29:41 +0200
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Thu, 13 Aug 2015 10:12:52 +0200

x86/mce: Reenable CMCI banks when swiching back to interrupt mode

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: <stable@xxxxxxxxxxxxxxx> # v3.15+
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>
---
arch/x86/kernel/cpu/mcheck/mce_intel.c | 41 +++++++++++++++++++---------------
1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index c5c0032..1e8bb6c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -146,6 +146,27 @@ void mce_intel_hcpu_update(unsigned long cpu)
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) &&
@@ -175,7 +196,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval)
*/
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;
@@ -186,22 +207,6 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval)
}
}

-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);
@@ -223,7 +228,7 @@ 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);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/