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

Pull locking updates from Ingo Molnar:

 - Add 'cross-release' support to lockdep, which allows APIs like
   completions, where it's not the 'owner' who releases the lock, to be
   tracked. It's all activated automatically under
   CONFIG_PROVE_LOCKING=y.

 - Clean up (restructure) the x86 atomics op implementation to be more
   readable, in preparation of KASAN annotations. (Dmitry Vyukov)

 - Fix static keys (Paolo Bonzini)

 - Add killable versions of down_read() et al (Kirill Tkhai)

 - Rework and fix jump_label locking (Marc Zyngier, Paolo Bonzini)

 - Rework (and fix) tlb_flush_pending() barriers (Peter Zijlstra)

 - Remove smp_mb__before_spinlock() and convert its usages, introduce
   smp_mb__after_spinlock() (Peter Zijlstra)

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (56 commits)
  locking/lockdep/selftests: Fix mixed read-write ABBA tests
  sched/completion: Avoid unnecessary stack allocation for COMPLETION_INITIALIZER_ONSTACK()
  acpi/nfit: Fix COMPLETION_INITIALIZER_ONSTACK() abuse
  locking/pvqspinlock: Relax cmpxchg's to improve performance on some architectures
  smp: Avoid using two cache lines for struct call_single_data
  locking/lockdep: Untangle xhlock history save/restore from task independence
  locking/refcounts, x86/asm: Disable CONFIG_ARCH_HAS_REFCOUNT for the time being
  futex: Remove duplicated code and fix undefined behaviour
  Documentation/locking/atomic: Finish the document...
  locking/lockdep: Fix workqueue crossrelease annotation
  workqueue/lockdep: 'Fix' flush_work() annotation
  locking/lockdep/selftests: Add mixed read-write ABBA tests
  mm, locking/barriers: Clarify tlb_flush_pending() barriers
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE and CONFIG_LOCKDEP_COMPLETIONS truly non-interactive
  locking/lockdep: Explicitly initialize wq_barrier::done::map
  locking/lockdep: Rename CONFIG_LOCKDEP_COMPLETE to CONFIG_LOCKDEP_COMPLETIONS
  locking/lockdep: Reword title of LOCKDEP_CROSSRELEASE config
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE part of CONFIG_PROVE_LOCKING
  locking/refcounts, x86/asm: Implement fast refcount overflow protection
  locking/lockdep: Fix the rollback and overwrite detection logic in crossrelease
  ...

7 files changed, 17 insertions, 12 deletions

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 19182d091587..1893e416e7c0 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -2884,7 +2884,7 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
 	 * need to be interruptible while waiting.
 	 */
 	INIT_WORK_ONSTACK(&flush.work, flush_probe);
-	COMPLETION_INITIALIZER_ONSTACK(flush.cmp);
+	init_completion(&flush.cmp);
 	queue_work(nfit_wq, &flush.work);
 	mutex_unlock(&acpi_desc->init_mutex);
 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 85c24cace973..81142ce781da 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -13,7 +13,7 @@
 struct nullb_cmd {
 	struct list_head list;
 	struct llist_node ll_list;
-	struct call_single_data csd;
+	call_single_data_t csd;
 	struct request *rq;
 	struct bio *bio;
 	unsigned int tag;
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 72bbfccef113..fd4b7f684bd0 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -455,7 +455,11 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
 			per_cpu(timer_unstable_counter_workaround, i) = wa;
 	}
 
-	static_branch_enable(&arch_timer_read_ool_enabled);
+	/*
+	 * Use the locked version, as we're called from the CPU
+	 * hotplug framework. Otherwise, we end-up in deadlock-land.
+	 */
+	static_branch_enable_cpuslocked(&arch_timer_read_ool_enabled);
 
 	/*
 	 * Don't use the vdso fastpath if errata require using the
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 71e586d7df71..147f38ea0fcd 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -119,13 +119,13 @@ struct cpuidle_coupled {
 
 #define CPUIDLE_COUPLED_NOT_IDLE	(-1)
 
-static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb);
+static DEFINE_PER_CPU(call_single_data_t, cpuidle_coupled_poke_cb);
 
 /*
  * The cpuidle_coupled_poke_pending mask is used to avoid calling
- * __smp_call_function_single with the per cpu call_single_data struct already
+ * __smp_call_function_single with the per cpu call_single_data_t struct already
  * in use.  This prevents a deadlock where two cpus are waiting for each others
- * call_single_data struct to be available
+ * call_single_data_t struct to be available
  */
 static cpumask_t cpuidle_coupled_poke_pending;
 
@@ -339,7 +339,7 @@ static void cpuidle_coupled_handle_poke(void *info)
  */
 static void cpuidle_coupled_poke(int cpu)
 {
-	struct call_single_data *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu);
+	call_single_data_t *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu);
 
 	if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poke_pending))
 		smp_call_function_single_async(cpu, csd);
@@ -651,7 +651,7 @@ int cpuidle_coupled_register_device(struct cpuidle_device *dev)
 {
 	int cpu;
 	struct cpuidle_device *other_dev;
-	struct call_single_data *csd;
+	call_single_data_t *csd;
 	struct cpuidle_coupled *coupled;
 
 	if (cpumask_empty(&dev->coupled_cpus))
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 48572b157222..a36216bd2a84 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -28,6 +28,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/sort.h>
+#include <linux/sched/mm.h>
 #include "intel_drv.h"
 
 static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node)
@@ -4305,7 +4306,7 @@ i915_drop_caches_set(void *data, u64 val)
 		mutex_unlock(&dev->struct_mutex);
 	}
 
-	lockdep_set_current_reclaim_state(GFP_KERNEL);
+	fs_reclaim_acquire(GFP_KERNEL);
 	if (val & DROP_BOUND)
 		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND);
 
@@ -4314,7 +4315,7 @@ i915_drop_caches_set(void *data, u64 val)
 
 	if (val & DROP_SHRINK_ALL)
 		i915_gem_shrink_all(dev_priv);
-	lockdep_clear_current_reclaim_state();
+	fs_reclaim_release(GFP_KERNEL);
 
 	if (val & DROP_FREED) {
 		synchronize_rcu();
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 51583ae4b1eb..120b6e537b28 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2468,7 +2468,7 @@ static void liquidio_napi_drv_callback(void *arg)
 	if (OCTEON_CN23XX_PF(oct) || droq->cpu_id == this_cpu) {
 		napi_schedule_irqoff(&droq->napi);
 	} else {
-		struct call_single_data *csd = &droq->csd;
+		call_single_data_t *csd = &droq->csd;
 
 		csd->func = napi_schedule_wrapper;
 		csd->info = &droq->napi;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index 6efd139b894d..f91bc84d1719 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -328,7 +328,7 @@ struct octeon_droq {
 
 	u32 cpu_id;
 
-	struct call_single_data csd;
+	call_single_data_t csd;
 };
 
 #define OCT_DROQ_SIZE   (sizeof(struct octeon_droq))