| 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
| ||
|
Message-Id: <1366217229-22705-11-git-send-email-kaber@trash.net>
Date: Wed, 17 Apr 2013 18:47:05 +0200
From: Patrick McHardy <kaber@...sh.net>
To: davem@...emloft.net
Cc: netfilter-devel@...r.kernel.org, netdev@...r.kernel.org
Subject: [PATCH 10/14] netlink: add flow control for memory mapped I/O
From: Patrick McHardy <kaber@...sh.net>
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 | 88 +++++++++++++++++++++++++++++++++---------------
1 file changed, 61 insertions(+), 27 deletions(-)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index d120b5d..2a3e9ba 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -3,6 +3,7 @@
*
* Authors: Alan Cox <alan@...rguk.ukuu.org.uk>
* Alexey Kuznetsov <kuznet@....inr.ac.ru>
+ * Patrick McHardy <kaber@...sh.net>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -110,6 +111,29 @@ static inline struct hlist_head *nl_portid_hashfn(struct nl_portid_hash *hash, u
return &hash->table[jhash_1word(portid, 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)
{
@@ -441,15 +465,48 @@ 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);
@@ -623,8 +680,7 @@ 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);
@@ -1329,19 +1385,6 @@ 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_getsockbyportid(struct sock *ssk, u32 portid)
{
struct sock *sock;
@@ -1484,16 +1527,6 @@ 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,
struct sock *ssk)
{
@@ -1597,6 +1630,7 @@ 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;
--
1.8.1.4
--
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
Powered by blists - more mailing lists