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

Pull RCU updates from Ingo Molnad:
 "The main RCU related changes in this cycle were:

   - Removal of spin_unlock_wait()
   - SRCU updates
   - RCU torture-test updates
   - RCU Documentation updates
   - Extend the sys_membarrier() ABI with the MEMBARRIER_CMD_PRIVATE_EXPEDITED variant
   - Miscellaneous RCU fixes
   - CPU-hotplug fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (63 commits)
  arch: Remove spin_unlock_wait() arch-specific definitions
  locking: Remove spin_unlock_wait() generic definitions
  drivers/ata: Replace spin_unlock_wait() with lock/unlock pair
  ipc: Replace spin_unlock_wait() with lock/unlock pair
  exit: Replace spin_unlock_wait() with lock/unlock pair
  completion: Replace spin_unlock_wait() with lock/unlock pair
  doc: Set down RCU's scheduling-clock-interrupt needs
  doc: No longer allowed to use rcu_dereference on non-pointers
  doc: Add RCU files to docbook-generation files
  doc: Update memory-barriers.txt for read-to-write dependencies
  doc: Update RCU documentation
  membarrier: Provide expedited private command
  rcu: Remove exports from rcu_idle_exit() and rcu_idle_enter()
  rcu: Add warning to rcu_idle_enter() for irqs enabled
  rcu: Make rcu_idle_enter() rely on callers disabling irqs
  rcu: Add assertions verifying blocked-tasks list
  rcu/tracing: Set disable_rcu_irq_enter on rcu_eqs_exit()
  rcu: Add TPS() protection for _rcu_barrier_trace strings
  rcu: Use idle versions of swait to make idle-hack clear
  swait: Add idle variants which don't contribute to load average
  ...

1 files changed, 29 insertions, 23 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 9979f46c81dc..51390febd5e3 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -96,19 +96,26 @@ static struct conntrack_gc_work conntrack_gc_work;
 
 void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
 {
+	/* 1) Acquire the lock */
 	spin_lock(lock);
-	while (unlikely(nf_conntrack_locks_all)) {
-		spin_unlock(lock);
 
-		/*
-		 * Order the 'nf_conntrack_locks_all' load vs. the
-		 * spin_unlock_wait() loads below, to ensure
-		 * that 'nf_conntrack_locks_all_lock' is indeed held:
-		 */
-		smp_rmb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
-		spin_unlock_wait(&nf_conntrack_locks_all_lock);
-		spin_lock(lock);
-	}
+	/* 2) read nf_conntrack_locks_all, with ACQUIRE semantics
+	 * It pairs with the smp_store_release() in nf_conntrack_all_unlock()
+	 */
+	if (likely(smp_load_acquire(&nf_conntrack_locks_all) == false))
+		return;
+
+	/* fast path failed, unlock */
+	spin_unlock(lock);
+
+	/* Slow path 1) get global lock */
+	spin_lock(&nf_conntrack_locks_all_lock);
+
+	/* Slow path 2) get the lock we want */
+	spin_lock(lock);
+
+	/* Slow path 3) release the global lock */
+	spin_unlock(&nf_conntrack_locks_all_lock);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_lock);
 
@@ -149,28 +156,27 @@ static void nf_conntrack_all_lock(void)
 	int i;
 
 	spin_lock(&nf_conntrack_locks_all_lock);
-	nf_conntrack_locks_all = true;
 
-	/*
-	 * Order the above store of 'nf_conntrack_locks_all' against
-	 * the spin_unlock_wait() loads below, such that if
-	 * nf_conntrack_lock() observes 'nf_conntrack_locks_all'
-	 * we must observe nf_conntrack_locks[] held:
-	 */
-	smp_mb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
+	nf_conntrack_locks_all = true;
 
 	for (i = 0; i < CONNTRACK_LOCKS; i++) {
-		spin_unlock_wait(&nf_conntrack_locks[i]);
+		spin_lock(&nf_conntrack_locks[i]);
+
+		/* This spin_unlock provides the "release" to ensure that
+		 * nf_conntrack_locks_all==true is visible to everyone that
+		 * acquired spin_lock(&nf_conntrack_locks[]).
+		 */
+		spin_unlock(&nf_conntrack_locks[i]);
 	}
 }
 
 static void nf_conntrack_all_unlock(void)
 {
-	/*
-	 * All prior stores must be complete before we clear
+	/* All prior stores must be complete before we clear
 	 * 'nf_conntrack_locks_all'. Otherwise nf_conntrack_lock()
 	 * might observe the false value but not the entire
-	 * critical section:
+	 * critical section.
+	 * It pairs with the smp_load_acquire() in nf_conntrack_lock()
 	 */
 	smp_store_release(&nf_conntrack_locks_all, false);
 	spin_unlock(&nf_conntrack_locks_all_lock);