From: "Björn Töpel" <bjorn.topel@gmail.com>
To: ast@kernel.org, daniel@iogearbox.net, netdev@vger.kernel.org
Cc: "Björn Töpel" <bjorn.topel@intel.com>,
magnus.karlsson@intel.com, magnus.karlsson@gmail.com,
bpf@vger.kernel.org, jonathan.lemon@gmail.com,
syzbot+c82697e3043781e08802@syzkaller.appspotmail.com,
hdanton@sina.com, i.maximets@samsung.com
Subject: [PATCH bpf-next v2 2/4] xsk: add proper barriers and {READ, WRITE}_ONCE-correctness for state
Date: Mon, 26 Aug 2019 08:10:51 +0200 [thread overview]
Message-ID: <20190826061053.15996-3-bjorn.topel@gmail.com> (raw)
In-Reply-To: <20190826061053.15996-1-bjorn.topel@gmail.com>
From: Björn Töpel <bjorn.topel@intel.com>
The state variable was read, and written outside the control mutex
(struct xdp_sock, mutex), without proper barriers and {READ,
WRITE}_ONCE correctness.
In this commit this issue is addressed, and the state member is now
used a point of synchronization whether the socket is setup correctly
or not.
This also fixes a race, found by syzcaller, in xsk_poll() where umem
could be accessed when stale.
Suggested-by: Hillf Danton <hdanton@sina.com>
Reported-by: syzbot+c82697e3043781e08802@syzkaller.appspotmail.com
Fixes: 77cd0d7b3f25 ("xsk: add support for need_wakeup flag in AF_XDP rings")
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
---
net/xdp/xsk.c | 57 ++++++++++++++++++++++++++++++++++++---------------
1 file changed, 40 insertions(+), 17 deletions(-)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index f3351013c2a5..8fafa3ce3ae6 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -162,10 +162,23 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
return err;
}
+static bool xsk_is_bound(struct xdp_sock *xs)
+{
+ if (READ_ONCE(xs->state) == XSK_BOUND) {
+ /* Matches smp_wmb() in bind(). */
+ smp_rmb();
+ return true;
+ }
+ return false;
+}
+
int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
u32 len;
+ if (!xsk_is_bound(xs))
+ return -EINVAL;
+
if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
return -EINVAL;
@@ -362,7 +375,7 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
struct sock *sk = sock->sk;
struct xdp_sock *xs = xdp_sk(sk);
- if (unlikely(!xs->dev))
+ if (unlikely(!xsk_is_bound(xs)))
return -ENXIO;
if (unlikely(!(xs->dev->flags & IFF_UP)))
return -ENETDOWN;
@@ -378,10 +391,15 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait)
{
unsigned int mask = datagram_poll(file, sock, wait);
- struct sock *sk = sock->sk;
- struct xdp_sock *xs = xdp_sk(sk);
- struct net_device *dev = xs->dev;
- struct xdp_umem *umem = xs->umem;
+ struct xdp_sock *xs = xdp_sk(sock->sk);
+ struct net_device *dev;
+ struct xdp_umem *umem;
+
+ if (unlikely(!xsk_is_bound(xs)))
+ return mask;
+
+ dev = xs->dev;
+ umem = xs->umem;
if (umem->need_wakeup)
dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
@@ -417,10 +435,9 @@ static void xsk_unbind_dev(struct xdp_sock *xs)
{
struct net_device *dev = xs->dev;
- if (!dev || xs->state != XSK_BOUND)
+ if (xs->state != XSK_BOUND)
return;
-
- xs->state = XSK_UNBOUND;
+ WRITE_ONCE(xs->state, XSK_UNBOUND);
/* Wait for driver to stop using the xdp socket. */
xdp_del_sk_umem(xs->umem, xs);
@@ -495,7 +512,9 @@ static int xsk_release(struct socket *sock)
local_bh_enable();
xsk_delete_from_maps(xs);
+ mutex_lock(&xs->mutex);
xsk_unbind_dev(xs);
+ mutex_unlock(&xs->mutex);
xskq_destroy(xs->rx);
xskq_destroy(xs->tx);
@@ -589,19 +608,18 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
}
umem_xs = xdp_sk(sock->sk);
- if (!umem_xs->umem) {
- /* No umem to inherit. */
+ if (!xsk_is_bound(umem_xs)) {
err = -EBADF;
sockfd_put(sock);
goto out_unlock;
- } else if (umem_xs->dev != dev || umem_xs->queue_id != qid) {
+ }
+ if (umem_xs->dev != dev || umem_xs->queue_id != qid) {
err = -EINVAL;
sockfd_put(sock);
goto out_unlock;
}
-
xdp_get_umem(umem_xs->umem);
- xs->umem = umem_xs->umem;
+ WRITE_ONCE(xs->umem, umem_xs->umem);
sockfd_put(sock);
} else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) {
err = -EINVAL;
@@ -626,10 +644,15 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
xdp_add_sk_umem(xs->umem, xs);
out_unlock:
- if (err)
+ if (err) {
dev_put(dev);
- else
- xs->state = XSK_BOUND;
+ } else {
+ /* Matches smp_rmb() in bind() for shared umem
+ * sockets, and xsk_is_bound().
+ */
+ smp_wmb();
+ WRITE_ONCE(xs->state, XSK_BOUND);
+ }
out_release:
mutex_unlock(&xs->mutex);
rtnl_unlock();
@@ -869,7 +892,7 @@ static int xsk_mmap(struct file *file, struct socket *sock,
unsigned long pfn;
struct page *qpg;
- if (xs->state != XSK_READY)
+ if (READ_ONCE(xs->state) != XSK_READY)
return -EBUSY;
if (offset == XDP_PGOFF_RX_RING) {
--
2.20.1
next prev parent reply other threads:[~2019-08-26 6:11 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-26 6:10 [PATCH bpf-next v2 0/4] xsk: various CPU barrier and {READ, WRITE}_ONCE fixes Björn Töpel
2019-08-26 6:10 ` [PATCH bpf-next v2 1/4] xsk: avoid store-tearing when assigning queues Björn Töpel
2019-08-26 6:10 ` Björn Töpel [this message]
2019-08-26 15:24 ` [PATCH bpf-next v2 2/4] xsk: add proper barriers and {READ, WRITE}_ONCE-correctness for state Ilya Maximets
2019-08-26 16:34 ` Björn Töpel
2019-08-26 17:57 ` Jonathan Lemon
2019-08-26 17:54 ` Jonathan Lemon
2019-09-03 15:22 ` Daniel Borkmann
2019-09-03 15:26 ` Björn Töpel
2019-08-26 6:10 ` [PATCH bpf-next v2 3/4] xsk: avoid store-tearing when assigning umem Björn Töpel
2019-08-26 6:10 ` [PATCH bpf-next v2 4/4] xsk: lock the control mutex in sock_diag interface Björn Töpel
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190826061053.15996-3-bjorn.topel@gmail.com \
--to=bjorn.topel@gmail.com \
--cc=ast@kernel.org \
--cc=bjorn.topel@intel.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=hdanton@sina.com \
--cc=i.maximets@samsung.com \
--cc=jonathan.lemon@gmail.com \
--cc=magnus.karlsson@gmail.com \
--cc=magnus.karlsson@intel.com \
--cc=netdev@vger.kernel.org \
--cc=syzbot+c82697e3043781e08802@syzkaller.appspotmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).