linux-kernel - [PATCH v3 1/1] net/ipv4/inet_fragment: Batch fqdir destroy works

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Fri, 11 Dec 2020 09:20:32 +0100
From:   SeongJae Park <sjpark@...zon.com>
To:     <davem@...emloft.net>
CC:     SeongJae Park <sjpark@...zon.de>, <kuba@...nel.org>,
        <kuznet@....inr.ac.ru>, <edumazet@...gle.com>, <fw@...len.de>,
        <paulmck@...nel.org>, <netdev@...r.kernel.org>,
        <rcu@...r.kernel.org>, <linux-kernel@...r.kernel.org>
Subject: [PATCH v3 1/1] net/ipv4/inet_fragment: Batch fqdir destroy works

From: SeongJae Park <sjpark@...zon.de>

For each 'fqdir_exit()' call, a work for destroy of the 'fqdir' is
enqueued.  The work function, 'fqdir_work_fn()', internally calls
'rcu_barrier()'.  In case of intensive 'fqdir_exit()' (e.g., frequent
'unshare()' systemcalls), this increased contention could result in
unacceptably high latency of 'rcu_barrier()'.  This commit avoids such
contention by doing the 'rcu_barrier()' and subsequent lightweight works
in a batched manner using a dedicated singlethread worker, as similar to
that of 'cleanup_net()'.

Signed-off-by: SeongJae Park <sjpark@...zon.de>
---
 include/net/inet_frag.h  |  1 +
 net/ipv4/inet_fragment.c | 45 +++++++++++++++++++++++++++++++++-------
 2 files changed, 39 insertions(+), 7 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index bac79e817776..48cc5795ceda 100644
--- a/include/net/inet_frag.h
+++ b/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;
 };
 
 /**
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 10d31733297d..a6fc4afcc323 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -145,12 +145,17 @@ static void inet_frags_free_cb(void *ptr, void *arg)
 		inet_frag_destroy(fq);
 }
 
-static void fqdir_work_fn(struct work_struct *work)
+static struct workqueue_struct *fqdir_wq;
+static LLIST_HEAD(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(&free_list);
 
 	/* We need to make sure all ongoing call_rcu(..., inet_frag_destroy_rcu)
 	 * have completed, since they need to dereference fqdir.
@@ -158,12 +163,38 @@ 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, &free_list))
+		queue_work(fqdir_wq, &fqdir_free_work);
+}
+
+static int __init fqdir_wq_init(void)
+{
+	fqdir_wq = create_singlethread_workqueue("fqdir");
+	if (!fqdir_wq)
+		panic("Could not create fqdir workq");
+	return 0;
+}
+
+pure_initcall(fqdir_wq_init);
+
+
 int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net)
 {
 	struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL);
-- 
2.17.1