netdev - [PATCH 10/11] netlink: add flow control for memory mapped I/O

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: <1345443532-3707-11-git-send-email-kaber@trash.net>
Date:	Mon, 20 Aug 2012 08:18:51 +0200
From:	Patrick McHardy <kaber@...sh.net>
To:	Florian.Westphal@...hos.com
Cc:	netdev@...r.kernel.org, netfilter-devel@...r.kernel.org
Subject: [PATCH 10/11] netlink: add flow control for memory mapped I/O

Add flow control for memory mapped RX. Since user-space usually doesn't
invoke recvmsg() when using memory mapped I/O, flow control is performed
in netlink_poll(). Dumps are allowed to continue if at least half of the
ring frames are unused.

Signed-off-by: Patrick McHardy <kaber@...sh.net>
---
 net/netlink/af_netlink.c |   87 +++++++++++++++++++++++++++++++--------------
 1 files changed, 60 insertions(+), 27 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index c42a601..cc90aa8 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -177,6 +177,29 @@ static inline struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid
 	return &hash->table[jhash_1word(pid, hash->rnd) & hash->mask];
 }
 
+static void netlink_overrun(struct sock *sk)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) {
+		if (!test_and_set_bit(NETLINK_CONGESTED, &nlk_sk(sk)->state)) {
+			sk->sk_err = ENOBUFS;
+			sk->sk_error_report(sk);
+		}
+	}
+	atomic_inc(&sk->sk_drops);
+}
+
+static void netlink_rcv_wake(struct sock *sk)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (skb_queue_empty(&sk->sk_receive_queue))
+		clear_bit(NETLINK_CONGESTED, &nlk->state);
+	if (!test_bit(NETLINK_CONGESTED, &nlk->state))
+		wake_up_interruptible(&nlk->wait);
+}
+
 #ifdef CONFIG_NETLINK_MMAP
 static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
 {
@@ -508,15 +531,48 @@ static void netlink_forward_ring(struct netlink_ring *ring)
 	} while (ring->head != head);
 }
 
+static bool netlink_dump_space(struct netlink_sock *nlk)
+{
+	struct netlink_ring *ring = &nlk->rx_ring;
+	struct nl_mmap_hdr *hdr;
+	unsigned int n;
+
+	hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
+	if (hdr == NULL)
+		return false;
+
+	n = ring->head + ring->frame_max / 2;
+	if (n > ring->frame_max)
+		n -= ring->frame_max;
+
+	hdr = __netlink_lookup_frame(ring, n);
+
+	return hdr->nm_status == NL_MMAP_STATUS_UNUSED;
+}
+
 static unsigned int netlink_poll(struct file *file, struct socket *sock,
 				 poll_table *wait)
 {
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
 	unsigned int mask;
+	int err;
 
-	if (nlk->cb != NULL && nlk->rx_ring.pg_vec != NULL)
-		netlink_dump(sk);
+	if (nlk->rx_ring.pg_vec != NULL) {
+		/* Memory mapped sockets don't call recvmsg(), so flow control
+		 * for dumps is performed here. A dump is allowed to continue
+		 * if at least half the ring is unused.
+		 */
+		while (nlk->cb != NULL && netlink_dump_space(nlk)) {
+			err = netlink_dump(sk);
+			if (err < 0) {
+				sk->sk_err = err;
+				sk->sk_error_report(sk);
+				break;
+			}
+		}
+		netlink_rcv_wake(sk);
+	}
 
 	mask = datagram_poll(file, sock, wait);
 
@@ -688,8 +744,7 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 	if (hdr == NULL) {
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		kfree_skb(skb);
-		sk->sk_err = ENOBUFS;
-		sk->sk_error_report(sk);
+		netlink_overrun(sk);
 		return;
 	}
 	netlink_increment_head(ring);
@@ -1382,19 +1437,6 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr,
 	return 0;
 }
 
-static void netlink_overrun(struct sock *sk)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) {
-		if (!test_and_set_bit(NETLINK_CONGESTED, &nlk_sk(sk)->state)) {
-			sk->sk_err = ENOBUFS;
-			sk->sk_error_report(sk);
-		}
-	}
-	atomic_inc(&sk->sk_drops);
-}
-
 static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
 {
 	struct sock *sock;
@@ -1537,16 +1579,6 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
 	return skb;
 }
 
-static void netlink_rcv_wake(struct sock *sk)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (skb_queue_empty(&sk->sk_receive_queue))
-		clear_bit(NETLINK_CONGESTED, &nlk->state);
-	if (!test_bit(NETLINK_CONGESTED, &nlk->state))
-		wake_up_interruptible(&nlk->wait);
-}
-
 static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb)
 {
 	int ret;
@@ -1648,6 +1680,7 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
 err2:
 	kfree_skb(skb);
 	spin_unlock_bh(&sk->sk_receive_queue.lock);
+	netlink_overrun(sk);
 err1:
 	sock_put(sk);
 	return NULL;
-- 
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html