| 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: <20240710212555.1617795-12-amery.hung@bytedance.com>
Date: Wed, 10 Jul 2024 21:25:52 +0000
From: Amery Hung <ameryhung@...il.com>
To: stefanha@...hat.com,
sgarzare@...hat.com,
mst@...hat.com,
jasowang@...hat.com,
xuanzhuo@...ux.alibaba.com,
davem@...emloft.net,
edumazet@...gle.com,
kuba@...nel.org,
pabeni@...hat.com,
kys@...rosoft.com,
haiyangz@...rosoft.com,
wei.liu@...nel.org,
decui@...rosoft.com,
bryantan@...are.com,
vdasa@...are.com,
pv-drivers@...are.com
Cc: dan.carpenter@...aro.org,
simon.horman@...igine.com,
oxffffaa@...il.com,
kvm@...r.kernel.org,
virtualization@...ts.linux-foundation.org,
netdev@...r.kernel.org,
linux-kernel@...r.kernel.org,
linux-hyperv@...r.kernel.org,
bpf@...r.kernel.org,
bobby.eshleman@...edance.com,
jiang.wang@...edance.com,
amery.hung@...edance.com,
ameryhung@...il.com,
xiyou.wangcong@...il.com
Subject: [RFC PATCH net-next v6 11/14] vhost/vsock: implement datagram support
From: Bobby Eshleman <bobby.eshleman@...edance.com>
This commit implements datagram support for vhost/vsock by teaching
vhost to use the common virtio transport datagram functions.
If the virtio RX buffer is too small, then the transmission is
abandoned, the packet dropped, and EHOSTUNREACH is added to the socket's
error queue.
Signed-off-by: Bobby Eshleman <bobby.eshleman@...edance.com>
Signed-off-by: Amery Hung <amery.hung@...edance.com>
---
drivers/vhost/vsock.c | 60 ++++++++++++++++++++++++++++++++++++++--
net/vmw_vsock/af_vsock.c | 2 +-
2 files changed, 58 insertions(+), 4 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index fa1aefb78016..13c3cbff21da 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -8,6 +8,7 @@
*/
#include <linux/miscdevice.h>
#include <linux/atomic.h>
+#include <linux/errqueue.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/vmalloc.h>
@@ -32,7 +33,8 @@
enum {
VHOST_VSOCK_FEATURES = VHOST_FEATURES |
(1ULL << VIRTIO_F_ACCESS_PLATFORM) |
- (1ULL << VIRTIO_VSOCK_F_SEQPACKET)
+ (1ULL << VIRTIO_VSOCK_F_SEQPACKET) |
+ (1ULL << VIRTIO_VSOCK_F_DGRAM)
};
enum {
@@ -56,6 +58,7 @@ struct vhost_vsock {
atomic_t queued_replies;
u32 guest_cid;
+ bool dgram_allow;
bool seqpacket_allow;
};
@@ -86,6 +89,32 @@ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
return NULL;
}
+/* Claims ownership of the skb, do not free the skb after calling! */
+static void
+vhost_transport_error(struct sk_buff *skb, int err)
+{
+ struct sock_exterr_skb *serr;
+ struct sock *sk = skb->sk;
+ struct sk_buff *clone;
+
+ serr = SKB_EXT_ERR(skb);
+ memset(serr, 0, sizeof(*serr));
+ serr->ee.ee_errno = err;
+ serr->ee.ee_origin = SO_EE_ORIGIN_NONE;
+
+ clone = skb_clone(skb, GFP_KERNEL);
+ if (!clone)
+ goto out;
+
+ if (sock_queue_err_skb(sk, clone))
+ kfree_skb(clone);
+
+ sk->sk_err = err;
+ sk_error_report(sk);
+out:
+ kfree_skb(skb);
+}
+
static void
vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
struct vhost_virtqueue *vq)
@@ -162,9 +191,15 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
hdr = virtio_vsock_hdr(skb);
/* If the packet is greater than the space available in the
- * buffer, we split it using multiple buffers.
+ * buffer, we split it using multiple buffers for connectible
+ * sockets and drop the packet for datagram sockets.
*/
if (payload_len > iov_len - sizeof(*hdr)) {
+ if (le16_to_cpu(hdr->type) == VIRTIO_VSOCK_TYPE_DGRAM) {
+ vhost_transport_error(skb, EHOSTUNREACH);
+ continue;
+ }
+
payload_len = iov_len - sizeof(*hdr);
/* As we are copying pieces of large packet's buffer to
@@ -403,6 +438,22 @@ static bool vhost_transport_msgzerocopy_allow(void)
return true;
}
+static bool vhost_transport_dgram_allow(u32 cid, u32 port)
+{
+ struct vhost_vsock *vsock;
+ bool dgram_allow = false;
+
+ rcu_read_lock();
+ vsock = vhost_vsock_get(cid);
+
+ if (vsock)
+ dgram_allow = vsock->dgram_allow;
+
+ rcu_read_unlock();
+
+ return dgram_allow;
+}
+
static bool vhost_transport_seqpacket_allow(u32 remote_cid);
static struct virtio_transport vhost_transport = {
@@ -419,7 +470,7 @@ static struct virtio_transport vhost_transport = {
.cancel_pkt = vhost_transport_cancel_pkt,
.dgram_enqueue = virtio_transport_dgram_enqueue,
- .dgram_allow = virtio_transport_dgram_allow,
+ .dgram_allow = vhost_transport_dgram_allow,
.stream_enqueue = virtio_transport_stream_enqueue,
.stream_dequeue = virtio_transport_stream_dequeue,
@@ -811,6 +862,9 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
if (features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET))
vsock->seqpacket_allow = true;
+ if (features & (1ULL << VIRTIO_VSOCK_F_DGRAM))
+ vsock->dgram_allow = true;
+
for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
vq = &vsock->vqs[i];
mutex_lock(&vq->mutex);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index f0e5db0eb43a..344db0f3a602 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1463,7 +1463,7 @@ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
return prot->recvmsg(sk, msg, len, flags, NULL);
#endif
- if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
+ if (unlikely(flags & MSG_OOB))
return -EOPNOTSUPP;
if (unlikely(flags & MSG_ERRQUEUE))
--
2.20.1
Powered by blists - more mailing lists