x86/mce: Make the MCE notifier a blocking one

commit 0dc9c639 upstream.

The NFIT MCE handler callback (for handling media errors on NVDIMMs)
takes a mutex to add the location of a memory error to a list. But since
the notifier call chain for machine checks (x86_mce_decoder_chain) is
atomic, we get a lockdep splat like:

  BUG: sleeping function called from invalid context at kernel/locking/mutex.c:620
  in_atomic(): 1, irqs_disabled(): 0, pid: 4, name: kworker/0:0
  [..]
  Call Trace:
   dump_stack
   ___might_sleep
   __might_sleep
   mutex_lock_nested
   ? __lock_acquire
   nfit_handle_mce
   notifier_call_chain
   atomic_notifier_call_chain
   ? atomic_notifier_call_chain
   mce_gen_pool_process

Convert the notifier to a blocking one which gets to run only in process
context.

Boris: remove the notifier call in atomic context in print_mce(). For
now, let's print the MCE on the atomic path so that we can make sure
they go out and get logged at least.

Fixes: 6839a6d9 ("nfit: do an ARS scrub on hitting a latent media error")
Reported-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: x86-ml <x86@kernel.org>
Link: http://lkml.kernel.org/r/20170411224457.24777-1-vishal.l.verma@intel.comSigned-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/kernel/cpu/mcheck/mce-genpool.c

@@ -85,7 +85,7 @@ void mce_gen_pool_process(void)
 	head = llist_reverse_order(head);
 	llist_for_each_entry_safe(node, tmp, head, llnode) {
 		mce = &node->mce;
-		atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+		blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
 		gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
 	}
 }

arch/x86/kernel/cpu/mcheck/mce-internal.h

@@ -13,7 +13,7 @@ enum severity_level {
 	MCE_PANIC_SEVERITY,
 };
 
-extern struct atomic_notifier_head x86_mce_decoder_chain;
+extern struct blocking_notifier_head x86_mce_decoder_chain;
 
 #define ATTR_LEN		16
 #define INITIAL_CHECK_INTERVAL	5 * 60 /* 5 minutes */

arch/x86/kernel/cpu/mcheck/mce.c

@@ -120,7 +120,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
  */
-ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain);
 
 /* Do initial initialization of a struct mce */
 void mce_setup(struct mce *m)
@@ -213,13 +213,13 @@ void mce_register_decode_chain(struct notifier_block *nb)
 	if (nb != &mce_srao_nb && nb->priority == INT_MAX)
 		nb->priority -= 1;
 
-	atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
+	blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
 }
 EXPORT_SYMBOL_GPL(mce_register_decode_chain);
 
 void mce_unregister_decode_chain(struct notifier_block *nb)
 {
-	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
+	blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
 }
 EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
 
@@ -272,8 +272,6 @@ struct mca_msr_regs msr_ops = {
 
 static void print_mce(struct mce *m)
 {
-	int ret = 0;
-
 	pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
 	       m->extcpu, m->mcgstatus, m->bank, m->status);
 
@@ -309,14 +307,6 @@ static void print_mce(struct mce *m)
 		m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
 		cpu_data(m->extcpu).microcode);
 
-	/*
-	 * Print out human-readable details about the MCE error,
-	 * (if the CPU has an implementation for that)
-	 */
-	ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
-	if (ret == NOTIFY_STOP)
-		return;
-
 	pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
 }