Messages in this thread Patch in this message | | | Date | Fri, 8 May 2009 11:04:24 +0200 | From | Ingo Molnar <> | Subject | Re: [PATCH] x86 MCE: shut up lockdep warning |
| |
* Shaohua Li <shaohua.li@intel.com> wrote:
> lockdep report below warning when I try to offline one cpu: > [ 110.835487] ================================= > [ 110.835616] [ INFO: inconsistent lock state ] > [ 110.835688] 2.6.30-rc4-00336-g8c9ed89 #52 > [ 110.835757] --------------------------------- > [ 110.835828] inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. > [ 110.835908] swapper/0 [HC1[1]:SC0[0]:HE0:SE1] takes: > [ 110.835982] (cmci_discover_lock){?.+...}, at: [<ffffffff80236dc0>] cmci_clear+0x30/0x9b > > smp_call_function_single() will disable interrupt. moving mce reenable/disable > to workqueue, so no irq is disabled. > > Signed-off-by: Shaohua Li<shaohua.li@intel.com> > diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c > index 6fb0b35..739c824 100644 > --- a/arch/x86/kernel/cpu/mcheck/mce_64.c > +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c > @@ -1057,30 +1057,32 @@ static __cpuinit void mce_remove_device(unsigned int cpu) > } > > /* Make sure there are no machine checks on offlined CPUs. */ > -static void mce_disable_cpu(void *h) > +static long mce_disable_cpu(void *h) > { > int i; > unsigned long action = *(unsigned long *)h; > > if (!mce_available(¤t_cpu_data)) > - return; > + return 0; > if (!(action & CPU_TASKS_FROZEN)) > cmci_clear(); > for (i = 0; i < banks; i++) > wrmsrl(MSR_IA32_MC0_CTL + i*4, 0); > + return 0; > } > > -static void mce_reenable_cpu(void *h) > +static long mce_reenable_cpu(void *h) > { > int i; > unsigned long action = *(unsigned long *)h; > > if (!mce_available(¤t_cpu_data)) > - return; > + return 0; > if (!(action & CPU_TASKS_FROZEN)) > cmci_reenable(); > for (i = 0; i < banks; i++) > wrmsrl(MSR_IA32_MC0_CTL + i*4, bank[i]); > + return 0; > } > > /* Get notified when a cpu comes on/off. Be hotplug friendly. */ > @@ -1106,14 +1108,14 @@ 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, &action, 1); > + work_on_cpu(cpu, mce_disable_cpu, &action); > break; > case CPU_DOWN_FAILED: > case CPU_DOWN_FAILED_FROZEN: > t->expires = round_jiffies(jiffies + > __get_cpu_var(next_interval)); > add_timer_on(t, cpu); > - smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); > + work_on_cpu(cpu, mce_reenable_cpu, &action); > break;
No, this needs a real fix - not a 'shut up lockdep' workaround.
One problem is that cmci_discover_lock is taken irq-unsafe, which is obviously a bad idea ...
Could you please try the fix for that from Hidetoshi-san, attached below (also available in latest -tip).
Thanks,
Ingo
------------------> From e5299926d7459d9fa7c7f856983147817aedb10e Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Date: Fri, 8 May 2009 17:28:40 +0900 Subject: [PATCH] x86: MCE: make cmci_discover_lock irq-safe
Lockdep reports the warning below when Li tries to offline one cpu:
[ 110.835487] ================================= [ 110.835616] [ INFO: inconsistent lock state ] [ 110.835688] 2.6.30-rc4-00336-g8c9ed89 #52 [ 110.835757] --------------------------------- [ 110.835828] inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. [ 110.835908] swapper/0 [HC1[1]:SC0[0]:HE0:SE1] takes: [ 110.835982] (cmci_discover_lock){?.+...}, at: [<ffffffff80236dc0>] cmci_clear+0x30/0x9b
cmci_clear() can be called via smp_call_function_single().
It is better to disable interrupt while holding cmci_discover_lock, to turn it into an irq-safe lock - we can deadlock otherwise.
[ Impact: fix possible deadlock in the MCE code ]
Reported-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <4A03ED38.8000700@jp.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Reported-by: Shaohua Li<shaohua.li@intel.com> --- arch/x86/kernel/cpu/mcheck/mce_intel_64.c | 10 ++++++---- 1 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index d6b72df..cef3ee3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -151,10 +151,11 @@ static void print_update(char *type, int *hdr, int num) static void cmci_discover(int banks, int boot) { unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); + unsigned long flags; int hdr = 0; int i; - spin_lock(&cmci_discover_lock); + spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; @@ -184,7 +185,7 @@ static void cmci_discover(int banks, int boot) WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } - spin_unlock(&cmci_discover_lock); + spin_unlock_irqrestore(&cmci_discover_lock, flags); if (hdr) printk(KERN_CONT "\n"); } @@ -211,13 +212,14 @@ void cmci_recheck(void) */ void cmci_clear(void) { + unsigned long flags; int i; int banks; u64 val; if (!cmci_supported(&banks)) return; - spin_lock(&cmci_discover_lock); + spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { if (!test_bit(i, __get_cpu_var(mce_banks_owned))) continue; @@ -227,7 +229,7 @@ void cmci_clear(void) wrmsrl(MSR_IA32_MC0_CTL2 + i, val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } - spin_unlock(&cmci_discover_lock); + spin_unlock_irqrestore(&cmci_discover_lock, flags); } /*
| |