inet: frags: batch fqdir destroy works

On a few of our systems, I found frequent 'unshare(CLONE_NEWNET)' calls
make the number of active slab objects including 'sock_inode_cache' type
rapidly and continuously increase.  As a result, memory pressure occurs.

In more detail, I made an artificial reproducer that resembles the
workload that we found the problem and reproduce the problem faster.  It
merely repeats 'unshare(CLONE_NEWNET)' 50,000 times in a loop.  It takes
about 2 minutes.  On 40 CPU cores / 70GB DRAM machine, the available
memory continuously reduced in a fast speed (about 120MB per second,
15GB in total within the 2 minutes).  Note that the issue don't
reproduce on every machine.  On my 6 CPU cores machine, the problem
didn't reproduce.

'cleanup_net()' and 'fqdir_work_fn()' are functions that deallocate the
relevant memory objects.  They are asynchronously invoked by the work
queues and internally use 'rcu_barrier()' to ensure safe destructions.
'cleanup_net()' works in a batched maneer in a single thread worker,
while 'fqdir_work_fn()' works for each 'fqdir_exit()' call in the
'system_wq'.  Therefore, 'fqdir_work_fn()' called frequently under the
workload and made the contention for 'rcu_barrier()' high.  In more
detail, the global mutex, 'rcu_state.barrier_mutex' became the
bottleneck.

This commit avoids such contention by doing the 'rcu_barrier()' and
subsequent lightweight works in a batched manner, as similar to that of
'cleanup_net()'.  The fqdir hashtable destruction, which is done before
the 'rcu_barrier()', is still allowed to run in parallel for fast
processing, but this commit makes it to use a dedicated work queue
instead of the 'system_wq', to make sure that the number of threads is
bounded.
Signed-off-by: SeongJae Park <sjpark@amazon.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20201211112405.31158-1-sjpark@amazon.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/inet_frag.h

@@ -21,6 +21,7 @@ struct fqdir {
 	/* Keep atomic mem on separate cachelines in structs that include it */
 	atomic_long_t		mem ____cacheline_aligned_in_smp;
 	struct work_struct	destroy_work;
+	struct llist_node	free_list;
 };
 
 /**

net/ipv4/inet_fragment.c

@@ -145,12 +145,16 @@ static void inet_frags_free_cb(void *ptr, void *arg)
 		inet_frag_destroy(fq);
 }
 
-static void fqdir_work_fn(struct work_struct *work)
+static LLIST_HEAD(fqdir_free_list);
+
+static void fqdir_free_fn(struct work_struct *work)
 {
-	struct fqdir *fqdir = container_of(work, struct fqdir, destroy_work);
-	struct inet_frags *f = fqdir->f;
+	struct llist_node *kill_list;
+	struct fqdir *fqdir, *tmp;
+	struct inet_frags *f;
 
-	rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL);
+	/* Atomically snapshot the list of fqdirs to free */
+	kill_list = llist_del_all(&fqdir_free_list);
 
 	/* We need to make sure all ongoing call_rcu(..., inet_frag_destroy_rcu)
 	 * have completed, since they need to dereference fqdir.
@@ -158,10 +162,25 @@ static void fqdir_work_fn(struct work_struct *work)
 	 */
 	rcu_barrier();
 
-	if (refcount_dec_and_test(&f->refcnt))
-		complete(&f->completion);
+	llist_for_each_entry_safe(fqdir, tmp, kill_list, free_list) {
+		f = fqdir->f;
+		if (refcount_dec_and_test(&f->refcnt))
+			complete(&f->completion);
 
-	kfree(fqdir);
+		kfree(fqdir);
+	}
+}
+
+static DECLARE_WORK(fqdir_free_work, fqdir_free_fn);
+
+static void fqdir_work_fn(struct work_struct *work)
+{
+	struct fqdir *fqdir = container_of(work, struct fqdir, destroy_work);
+
+	rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL);
+
+	if (llist_add(&fqdir->free_list, &fqdir_free_list))
+		queue_work(system_wq, &fqdir_free_work);
 }
 
 int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net)
@@ -184,10 +203,22 @@ int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net)
 }
 EXPORT_SYMBOL(fqdir_init);
 
+static struct workqueue_struct *inet_frag_wq;
+
+static int __init inet_frag_wq_init(void)
+{
+	inet_frag_wq = create_workqueue("inet_frag_wq");
+	if (!inet_frag_wq)
+		panic("Could not create inet frag workq");
+	return 0;
+}
+
+pure_initcall(inet_frag_wq_init);
+
 void fqdir_exit(struct fqdir *fqdir)
 {
 	INIT_WORK(&fqdir->destroy_work, fqdir_work_fn);
-	queue_work(system_wq, &fqdir->destroy_work);
+	queue_work(inet_frag_wq, &fqdir->destroy_work);
 }
 EXPORT_SYMBOL(fqdir_exit);