net/netfilter/nf_conntrack_core: Fix net_conntrack_lock()

As we want to remove spin_unlock_wait() and replace it with explicit
spin_lock()/spin_unlock() calls, we can use this to simplify the
locking.

In addition:
- Reading nf_conntrack_locks_all needs ACQUIRE memory ordering.
- The new code avoids the backwards loop.

Only slightly tested, I did not manage to trigger calls to
nf_conntrack_all_lock().

V2: With improved comments, to clearly show how the barriers
    pair.

Fixes: b16c29191dc8 ("netfilter: nf_conntrack: use safer way to lock all buckets")
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Cc: <stable@vger.kernel.org>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

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);