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>

diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index d6b72df89d697cb6b809cc1e3c68540d28cfe1f3..cef3ee30744b9964c9503f1ffd137c7d5c9aaf69 100644 (file)
--- 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);
 }
 
 /*