x86/mce: Avoid potential deadlock due to printk() in MCE context

Printing in MCE context is a no-no, currently, as printk() is
not NMI-safe. If some of the notifiers on the MCE chain call do
so, we may deadlock. In order to avoid that, delay printk() to
process context where it is safe.

Reported-by: Xie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
[ Fold in subsequent patch from Boris for early boot logging. ]
Signed-off-by: Tony Luck <tony.luck@intel.com>
[ Kick irq_work in mce_log() directly. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1439396985-12812-6-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index a1aef9533154b8c7be7cbc5dd271cadf78761093..34c89a3e8260a7acbfd29cb380fbc09fd2dad623 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -57,7 +57,6 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 
        m.addr = mem_err->physical_addr;
        mce_log(&m);
-       mce_notify_irq();
 }
 EXPORT_SYMBOL_GPL(apei_mce_report_mem_error);
 

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 82603690b65ced5b10a7c85de49d86a8ee56bd76..9568bb55bfe2f896801bda014c6f408cbc768d97 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -159,7 +159,8 @@ void mce_log(struct mce *mce)
        /* Emit the trace record: */
        trace_mce_record(mce);
 
-       atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+       if (!mce_gen_pool_add(mce))
+               irq_work_queue(&mce_irq_work);
 
        mce->finished = 0;
        wmb();
@@ -1122,7 +1123,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
                /* assuming valid severity level != 0 */
                m.severity = severity;
                m.usable_addr = mce_usable_address(&m);
-               mce_gen_pool_add(&m);
 
                mce_log(&m);
 

diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 844f56c5616d242dc41631957bf94f687f039b0d..70f567f774ed0fec3c3b936498d0f75b10969d92 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -246,7 +246,6 @@ static void intel_threshold_interrupt(void)
                return;
 
        machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
-       mce_notify_irq();
 }
 
 /*