diff options
author | Andi Kleen <andi@firstfloor.org> | 2009-02-12 15:49:36 +0300 |
---|---|---|
committer | H. Peter Anvin <hpa@zytor.com> | 2009-02-25 00:41:00 +0300 |
commit | 88ccbedd9ca85d1aca6a6f99df48dce87b7c02d4 (patch) | |
tree | 9951e6f3554789523006f187e69286f5ed541b50 /arch/x86/kernel/cpu/mcheck/mce_64.c | |
parent | 03195c6b40f2b4db92545921daa7c3a19b4e4c32 (diff) | |
download | linux-88ccbedd9ca85d1aca6a6f99df48dce87b7c02d4.tar.xz |
x86, mce, cmci: add CMCI support
Impact: Major new feature
Intel CMCI (Corrected Machine Check Interrupt) is a new
feature on Nehalem CPUs. It allows the CPU to trigger
interrupts on corrected events, which allows faster
reaction to them instead of with the traditional
polling timer.
Also use CMCI to discover shared banks. Machine check banks
can be shared by CPU threads or even cores. Using the CMCI enable
bit it is possible to detect the fact that another CPU already
saw a specific bank. Use this to assign shared banks only
to one CPU to avoid reporting duplicated events.
On CPU hot unplug bank sharing is re discovered. This is done
using a thread that cycles through all the CPUs.
To avoid races between the poller and CMCI we only poll
for banks that are not CMCI capable and only check CMCI
owned banks on a interrupt.
The shared banks ownership information is currently only used for
CMCI interrupts, not polled banks.
The sharing discovery code follows the algorithm recommended in the
IA32 SDM Vol3a 14.5.2.1
The CMCI interrupt handler just calls the machine check poller to
pick up the machine check event that caused the interrupt.
I decided not to implement a separate threshold event like
the AMD version has, because the threshold is always one currently
and adding another event didn't seem to add any value.
Some code inspired by Yunhong Jiang's Xen implementation,
which was in term inspired by a earlier CMCI implementation
by me.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck/mce_64.c')
-rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce_64.c | 16 |
1 files changed, 13 insertions, 3 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index a8ff38bfa6ed..bfbd5323a635 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -166,7 +166,7 @@ static void mce_panic(char *msg, struct mce *backup, unsigned long start) panic(msg); } -static int mce_available(struct cpuinfo_x86 *c) +int mce_available(struct cpuinfo_x86 *c) { if (mce_dont_init) return 0; @@ -1060,9 +1060,12 @@ static __cpuinit void mce_remove_device(unsigned int cpu) static void mce_disable_cpu(void *h) { int i; + unsigned long action = *(unsigned long *)h; if (!mce_available(¤t_cpu_data)) return; + if (!(action & CPU_TASKS_FROZEN)) + cmci_clear(); for (i = 0; i < banks; i++) wrmsrl(MSR_IA32_MC0_CTL + i*4, 0); } @@ -1070,9 +1073,12 @@ static void mce_disable_cpu(void *h) static void mce_reenable_cpu(void *h) { int i; + unsigned long action = *(unsigned long *)h; if (!mce_available(¤t_cpu_data)) return; + if (!(action & CPU_TASKS_FROZEN)) + cmci_reenable(); for (i = 0; i < banks; i++) wrmsrl(MSR_IA32_MC0_CTL + i*4, bank[i]); } @@ -1100,13 +1106,17 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb, case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: del_timer_sync(t); - smp_call_function_single(cpu, mce_disable_cpu, NULL, 1); + smp_call_function_single(cpu, mce_disable_cpu, &action, 1); break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: t->expires = round_jiffies_relative(jiffies + next_interval); add_timer_on(t, cpu); - smp_call_function_single(cpu, mce_reenable_cpu, NULL, 1); + smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); + break; + case CPU_POST_DEAD: + /* intentionally ignoring frozen here */ + cmci_rediscover(cpu); break; } return NOTIFY_OK; |