net: Add a second bind table hashed by port and address

We currently have one tcp bind table (bhash) which hashes by port
number only. In the socket bind path, we check for bind conflicts by
traversing the specified port's inet_bind2_bucket while holding the
bucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()).

In instances where there are tons of sockets hashed to the same port
at different addresses, checking for a bind conflict is time-intensive
and can cause softirq cpu lockups, as well as stops new tcp connections
since __inet_inherit_port() also contests for the spinlock.

This patch proposes adding a second bind table, bhash2, that hashes by
port and ip address. Searching the bhash2 table leads to significantly
faster conflict resolution and less time holding the spinlock.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 28 insertions, 5 deletions

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index eb8e128e43e8..2e78458900f2 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1120,6 +1120,12 @@ static int __init dccp_init(void)
 				  SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL);
 	if (!dccp_hashinfo.bind_bucket_cachep)
 		goto out_free_hashinfo2;
+	dccp_hashinfo.bind2_bucket_cachep =
+		kmem_cache_create("dccp_bind2_bucket",
+				  sizeof(struct inet_bind2_bucket), 0,
+				  SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL);
+	if (!dccp_hashinfo.bind2_bucket_cachep)
+		goto out_free_bind_bucket_cachep;
 
 	/*
 	 * Size and allocate the main established and bind bucket
@@ -1150,7 +1156,7 @@ static int __init dccp_init(void)
 
 	if (!dccp_hashinfo.ehash) {
 		DCCP_CRIT("Failed to allocate DCCP established hash table");
-		goto out_free_bind_bucket_cachep;
+		goto out_free_bind2_bucket_cachep;
 	}
 
 	for (i = 0; i <= dccp_hashinfo.ehash_mask; i++)
@@ -1176,14 +1182,23 @@ static int __init dccp_init(void)
 		goto out_free_dccp_locks;
 	}
 
+	dccp_hashinfo.bhash2 = (struct inet_bind2_hashbucket *)
+		__get_free_pages(GFP_ATOMIC | __GFP_NOWARN, bhash_order);
+
+	if (!dccp_hashinfo.bhash2) {
+		DCCP_CRIT("Failed to allocate DCCP bind2 hash table");
+		goto out_free_dccp_bhash;
+	}
+
 	for (i = 0; i < dccp_hashinfo.bhash_size; i++) {
 		spin_lock_init(&dccp_hashinfo.bhash[i].lock);
 		INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain);
+		INIT_HLIST_HEAD(&dccp_hashinfo.bhash2[i].chain);
 	}
 
 	rc = dccp_mib_init();
 	if (rc)
-		goto out_free_dccp_bhash;
+		goto out_free_dccp_bhash2;
 
 	rc = dccp_ackvec_init();
 	if (rc)
@@ -1207,30 +1222,38 @@ out_ackvec_exit:
 	dccp_ackvec_exit();
 out_free_dccp_mib:
 	dccp_mib_exit();
+out_free_dccp_bhash2:
+	free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order);
 out_free_dccp_bhash:
 	free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
 out_free_dccp_locks:
 	inet_ehash_locks_free(&dccp_hashinfo);
 out_free_dccp_ehash:
 	free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
+out_free_bind2_bucket_cachep:
+	kmem_cache_destroy(dccp_hashinfo.bind2_bucket_cachep);
 out_free_bind_bucket_cachep:
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
 out_free_hashinfo2:
 	inet_hashinfo2_free_mod(&dccp_hashinfo);
 out_fail:
 	dccp_hashinfo.bhash = NULL;
+	dccp_hashinfo.bhash2 = NULL;
 	dccp_hashinfo.ehash = NULL;
 	dccp_hashinfo.bind_bucket_cachep = NULL;
+	dccp_hashinfo.bind2_bucket_cachep = NULL;
 	return rc;
 }
 
 static void __exit dccp_fini(void)
 {
+	int bhash_order = get_order(dccp_hashinfo.bhash_size *
+				    sizeof(struct inet_bind_hashbucket));
+
 	ccid_cleanup_builtins();
 	dccp_mib_exit();
-	free_pages((unsigned long)dccp_hashinfo.bhash,
-		   get_order(dccp_hashinfo.bhash_size *
-			     sizeof(struct inet_bind_hashbucket)));
+	free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
+	free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order);
 	free_pages((unsigned long)dccp_hashinfo.ehash,
 		   get_order((dccp_hashinfo.ehash_mask + 1) *
 			     sizeof(struct inet_ehash_bucket)));