Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "This cycle's RCU changes were:

   - A few more RCU flavor consolidation cleanups.

   - Updates to RCU's list-traversal macros improving lockdep usability.

   - Forward-progress improvements for no-CBs CPUs: Avoid ignoring
     incoming callbacks during grace-period waits.

   - Forward-progress improvements for no-CBs CPUs: Use ->cblist
     structure to take advantage of others' grace periods.

   - Also added a small commit that avoids needlessly inflicting
     scheduler-clock ticks on callback-offloaded CPUs.

   - Forward-progress improvements for no-CBs CPUs: Reduce contention on
     ->nocb_lock guarding ->cblist.

   - Forward-progress improvements for no-CBs CPUs: Add ->nocb_bypass
     list to further reduce contention on ->nocb_lock guarding ->cblist.

   - Miscellaneous fixes.

   - Torture-test updates.

   - minor LKMM updates"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (86 commits)
  MAINTAINERS: Update from paulmck@linux.ibm.com to paulmck@kernel.org
  rcu: Don't include <linux/ktime.h> in rcutiny.h
  rcu: Allow rcu_do_batch() to dynamically adjust batch sizes
  rcu/nocb: Don't wake no-CBs GP kthread if timer posted under overload
  rcu/nocb: Reduce __call_rcu_nocb_wake() leaf rcu_node ->lock contention
  rcu/nocb: Reduce nocb_cb_wait() leaf rcu_node ->lock contention
  rcu/nocb: Advance CBs after merge in rcutree_migrate_callbacks()
  rcu/nocb: Avoid synchronous wakeup in __call_rcu_nocb_wake()
  rcu/nocb: Print no-CBs diagnostics when rcutorture writer unduly delayed
  rcu/nocb: EXP Check use and usefulness of ->nocb_lock_contended
  rcu/nocb: Add bypass callback queueing
  rcu/nocb: Atomic ->len field in rcu_segcblist structure
  rcu/nocb: Unconditionally advance and wake for excessive CBs
  rcu/nocb: Reduce ->nocb_lock contention with separate ->nocb_gp_lock
  rcu/nocb: Reduce contention at no-CBs invocation-done time
  rcu/nocb: Reduce contention at no-CBs registry-time CB advancement
  rcu/nocb: Round down for number of no-CBs grace-period kthreads
  rcu/nocb: Avoid ->nocb_lock capture by corresponding CPU
  rcu/nocb: Avoid needless wakeups of no-CBs grace-period kthread
  rcu/nocb: Make __call_rcu_nocb_wake() safe for many callbacks
  ...

3 files changed, 6 insertions, 7 deletions

diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index aab8ba40ce38..4b0bab2607e4 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -264,15 +264,13 @@ int __cpu_disable(void)
 	return 0;
 }
 
-static DECLARE_COMPLETION(cpu_died);
-
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
-	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+	if (!cpu_wait_death(cpu, 5)) {
 		pr_err("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
@@ -319,7 +317,7 @@ void arch_cpu_idle_dead(void)
 	 * this returns, power and/or clocks can be removed at any point
 	 * from this CPU and its cache by platform_cpu_kill().
 	 */
-	complete(&cpu_died);
+	(void)cpu_report_death();
 
 	/*
 	 * Ensure that the cache lines associated with that completion are
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index bb7c8cc77f1a..04b2b927bb5a 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -535,7 +535,7 @@ static inline void note_hpte_modification(struct kvm *kvm,
  */
 static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
 {
-	return rcu_dereference_raw_notrace(kvm->memslots[0]);
+	return rcu_dereference_raw_check(kvm->memslots[0]);
 }
 
 extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 7389db538c30..6fa42e9c4e6f 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -29,6 +29,7 @@
 static bool pci_mmcfg_running_state;
 static bool pci_mmcfg_arch_init_failed;
 static DEFINE_MUTEX(pci_mmcfg_lock);
+#define pci_mmcfg_lock_held() lock_is_held(&(pci_mmcfg_lock).dep_map)
 
 LIST_HEAD(pci_mmcfg_list);
 
@@ -54,7 +55,7 @@ static void list_add_sorted(struct pci_mmcfg_region *new)
 	struct pci_mmcfg_region *cfg;
 
 	/* keep list sorted by segment and starting bus number */
-	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) {
+	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held()) {
 		if (cfg->segment > new->segment ||
 		    (cfg->segment == new->segment &&
 		     cfg->start_bus >= new->start_bus)) {
@@ -118,7 +119,7 @@ struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus)
 {
 	struct pci_mmcfg_region *cfg;
 
-	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list)
+	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held())
 		if (cfg->segment == segment &&
 		    cfg->start_bus <= bus && bus <= cfg->end_bus)
 			return cfg;