netdev - [PATCH v2 net-next 3/4] af_unix: Run GC on only one CPU.

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]

Message-ID: <20231123014747.66063-4-kuniyu@amazon.com>
Date: Wed, 22 Nov 2023 17:47:46 -0800
From: Kuniyuki Iwashima <kuniyu@...zon.com>
To: "David S. Miller" <davem@...emloft.net>, Eric Dumazet
	<edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>, Paolo Abeni
	<pabeni@...hat.com>
CC: Ivan Babrou <ivan@...udflare.com>, Kuniyuki Iwashima <kuniyu@...zon.com>,
	Kuniyuki Iwashima <kuni1840@...il.com>, <netdev@...r.kernel.org>
Subject: [PATCH v2 net-next 3/4] af_unix: Run GC on only one CPU.

If more than 16000 inflight AF_UNIX sockets exist and the garbage
collector is not running, unix_(dgram|stream)_sendmsg() call unix_gc().
Also, they wait for unix_gc() to complete.

In unix_gc(), all inflight AF_UNIX sockets are traversed at least once,
and more if they are the GC candidate.  Thus, sendmsg() significantly
slows down with too many inflight AF_UNIX sockets.

There is a small window to invoke multiple unix_gc() instances, which
will then be blocked by the same spinlock except for one.

Let's convert unix_gc() to use struct work so that it will not consume
CPUs unnecessarily.

Signed-off-by: Kuniyuki Iwashima <kuniyu@...zon.com>
---
 net/unix/garbage.c | 40 ++++++++++++++++------------------------
 1 file changed, 16 insertions(+), 24 deletions(-)

diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 4d634f5f6a55..8bc93a7e745f 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -86,7 +86,9 @@
 /* Internal data structures and random procedures: */
 
 static LIST_HEAD(gc_candidates);
-static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);
+
+static void __unix_gc(struct work_struct *work);
+static DECLARE_WORK(unix_gc_work, __unix_gc);
 
 static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
 			  struct sk_buff_head *hitlist)
@@ -181,24 +183,22 @@ static void inc_inflight_move_tail(struct unix_sock *u)
 		list_move_tail(&u->link, &gc_candidates);
 }
 
-static bool gc_in_progress;
 #define UNIX_INFLIGHT_TRIGGER_GC 16000
 
 void wait_for_unix_gc(void)
 {
-	/* If number of inflight sockets is insane,
-	 * force a garbage collect right now.
+	/* If number of inflight sockets is insane, kick a
+	 * garbage collect right now.
 	 * Paired with the WRITE_ONCE() in unix_inflight(),
-	 * unix_notinflight() and gc_in_progress().
+	 * unix_notinflight().
 	 */
-	if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC &&
-	    !READ_ONCE(gc_in_progress))
-		unix_gc();
-	wait_event(unix_gc_wait, gc_in_progress == false);
+	if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC)
+		queue_work(system_unbound_wq, &unix_gc_work);
+
+	flush_work(&unix_gc_work);
 }
 
-/* The external entry point: unix_gc() */
-void unix_gc(void)
+static void __unix_gc(struct work_struct *work)
 {
 	struct sk_buff *next_skb, *skb;
 	struct unix_sock *u;
@@ -209,13 +209,6 @@ void unix_gc(void)
 
 	spin_lock(&unix_gc_lock);
 
-	/* Avoid a recursive GC. */
-	if (gc_in_progress)
-		goto out;
-
-	/* Paired with READ_ONCE() in wait_for_unix_gc(). */
-	WRITE_ONCE(gc_in_progress, true);
-
 	/* First, select candidates for garbage collection.  Only
 	 * in-flight sockets are considered, and from those only ones
 	 * which don't have any external reference.
@@ -319,11 +312,10 @@ void unix_gc(void)
 	/* All candidates should have been detached by now. */
 	BUG_ON(!list_empty(&gc_candidates));
 
-	/* Paired with READ_ONCE() in wait_for_unix_gc(). */
-	WRITE_ONCE(gc_in_progress, false);
-
-	wake_up(&unix_gc_wait);
-
- out:
 	spin_unlock(&unix_gc_lock);
 }
+
+void unix_gc(void)
+{
+	queue_work(system_unbound_wq, &unix_gc_work);
+}
-- 
2.30.2