From: Bobby Eshleman bobbyeshleman@meta.com
Add netns support to loopback and vhost. Keep netns disabled for virtio-vsock, but add necessary changes to comply with common API updates.
Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- Changes in v10: - Splitting patches complicates the series with meaningless placeholder values that eventually get replaced anyway, so to avoid that this patch combines into one. Links to previous patches here: - Link: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-3-852787a37bed@meta.com... - Link: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-6-852787a37bed@meta.com... - Link: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-7-852787a37bed@meta.com... - remove placeholder values (Stefano) - update comment describe net/net_mode for virtio_transport_reset_no_sock() --- drivers/vhost/vsock.c | 45 +++++++++++++++++------ include/linux/virtio_vsock.h | 8 +++-- net/vmw_vsock/virtio_transport.c | 10 ++++-- net/vmw_vsock/virtio_transport_common.c | 63 ++++++++++++++++++++++++--------- net/vmw_vsock/vsock_loopback.c | 8 +++-- 5 files changed, 102 insertions(+), 32 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index c8319cd1c232..2846076d484f 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -46,6 +46,11 @@ static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8); struct vhost_vsock { struct vhost_dev dev; struct vhost_virtqueue vqs[2]; + struct net *net; + netns_tracker ns_tracker; + + /* The ns mode at the time vhost_vsock was created */ + enum vsock_net_mode net_mode;
/* Link to global vhost_vsock_hash, writes use vhost_vsock_mutex */ struct hlist_node hash; @@ -72,7 +77,8 @@ static bool vhost_transport_supports_local_mode(void) /* Callers that dereference the return value must hold vhost_vsock_mutex or the * RCU read lock. */ -static struct vhost_vsock *vhost_vsock_get(u32 guest_cid) +static struct vhost_vsock *vhost_vsock_get(u32 guest_cid, struct net *net, + enum vsock_net_mode mode) { struct vhost_vsock *vsock;
@@ -83,9 +89,10 @@ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid) if (other_cid == 0) continue;
- if (other_cid == guest_cid) + if (other_cid == guest_cid && + vsock_net_check_mode(net, mode, vsock->net, + vsock->net_mode)) return vsock; - }
return NULL; @@ -274,7 +281,8 @@ static void vhost_transport_send_pkt_work(struct vhost_work *work) }
static int -vhost_transport_send_pkt(struct sk_buff *skb) +vhost_transport_send_pkt(struct sk_buff *skb, struct net *net, + enum vsock_net_mode net_mode) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vhost_vsock *vsock; @@ -283,7 +291,7 @@ vhost_transport_send_pkt(struct sk_buff *skb) rcu_read_lock();
/* Find the vhost_vsock according to guest context id */ - vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid)); + vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid), net, net_mode); if (!vsock) { rcu_read_unlock(); kfree_skb(skb); @@ -310,7 +318,8 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk) rcu_read_lock();
/* Find the vhost_vsock according to guest context id */ - vsock = vhost_vsock_get(vsk->remote_addr.svm_cid); + vsock = vhost_vsock_get(vsk->remote_addr.svm_cid, + sock_net(sk_vsock(vsk)), vsk->net_mode); if (!vsock) goto out;
@@ -470,11 +479,12 @@ static struct virtio_transport vhost_transport = { static bool vhost_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid) { + struct net *net = sock_net(sk_vsock(vsk)); struct vhost_vsock *vsock; bool seqpacket_allow = false;
rcu_read_lock(); - vsock = vhost_vsock_get(remote_cid); + vsock = vhost_vsock_get(remote_cid, net, vsk->net_mode);
if (vsock) seqpacket_allow = vsock->seqpacket_allow; @@ -545,7 +555,8 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) if (le64_to_cpu(hdr->src_cid) == vsock->guest_cid && le64_to_cpu(hdr->dst_cid) == vhost_transport_get_local_cid()) - virtio_transport_recv_pkt(&vhost_transport, skb); + virtio_transport_recv_pkt(&vhost_transport, skb, + vsock->net, vsock->net_mode); else kfree_skb(skb);
@@ -662,6 +673,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) { struct vhost_virtqueue **vqs; struct vhost_vsock *vsock; + struct net *net; int ret;
/* This struct is large and allocation could fail, fall back to vmalloc @@ -677,6 +689,17 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) goto out; }
+ net = current->nsproxy->net_ns; + vsock->net = get_net_track(net, &vsock->ns_tracker, GFP_KERNEL); + + /* Store the mode of the namespace at the time of creation. If this + * namespace later changes from "global" to "local", we want this vsock + * to continue operating normally and not suddenly break. For that + * reason, we save the mode here and later use it when performing + * socket lookups with vsock_net_check_mode() (see vhost_vsock_get()). + */ + vsock->net_mode = vsock_net_mode(net); + vsock->guest_cid = 0; /* no CID assigned yet */ vsock->seqpacket_allow = false;
@@ -716,7 +739,8 @@ static void vhost_vsock_reset_orphans(struct sock *sk) */
/* If the peer is still valid, no need to reset connection */ - if (vhost_vsock_get(vsk->remote_addr.svm_cid)) + if (vhost_vsock_get(vsk->remote_addr.svm_cid, sock_net(sk), + vsk->net_mode)) return;
/* If the close timeout is pending, let it expire. This avoids races @@ -761,6 +785,7 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file) virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue);
vhost_dev_cleanup(&vsock->dev); + put_net_track(vsock->net, &vsock->ns_tracker); kfree(vsock->dev.vqs); vhost_vsock_free(vsock); return 0; @@ -787,7 +812,7 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid)
/* Refuse if CID is already in use */ mutex_lock(&vhost_vsock_mutex); - other = vhost_vsock_get(guest_cid); + other = vhost_vsock_get(guest_cid, vsock->net, vsock->net_mode); if (other && other != vsock) { mutex_unlock(&vhost_vsock_mutex); return -EADDRINUSE; diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 0c67543a45c8..5ed6136a4ed4 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -173,6 +173,8 @@ struct virtio_vsock_pkt_info { u32 remote_cid, remote_port; struct vsock_sock *vsk; struct msghdr *msg; + struct net *net; + enum vsock_net_mode net_mode; u32 pkt_len; u16 type; u16 op; @@ -185,7 +187,8 @@ struct virtio_transport { struct vsock_transport transport;
/* Takes ownership of the packet */ - int (*send_pkt)(struct sk_buff *skb); + int (*send_pkt)(struct sk_buff *skb, struct net *net, + enum vsock_net_mode net_mode);
/* Used in MSG_ZEROCOPY mode. Checks, that provided data * (number of buffers) could be transmitted with zerocopy @@ -280,7 +283,8 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk, void virtio_transport_destruct(struct vsock_sock *vsk);
void virtio_transport_recv_pkt(struct virtio_transport *t, - struct sk_buff *skb); + struct sk_buff *skb, struct net *net, + enum vsock_net_mode net_mode); void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff *skb); u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index e585cb66c6f5..bc266bdb7faa 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -243,7 +243,8 @@ static int virtio_transport_send_skb_fast_path(struct virtio_vsock *vsock, struc }
static int -virtio_transport_send_pkt(struct sk_buff *skb) +virtio_transport_send_pkt(struct sk_buff *skb, struct net *net, + enum vsock_net_mode net_mode) { struct virtio_vsock_hdr *hdr; struct virtio_vsock *vsock; @@ -675,7 +676,12 @@ static void virtio_transport_rx_work(struct work_struct *work) virtio_vsock_skb_put(skb, payload_len);
virtio_transport_deliver_tap_pkt(skb); - virtio_transport_recv_pkt(&virtio_transport, skb); + + /* Force virtio-transport into global mode since it + * does not yet support local-mode namespacing. + */ + virtio_transport_recv_pkt(&virtio_transport, skb, + NULL, VSOCK_NET_MODE_GLOBAL); } } while (!virtqueue_enable_cb(vq));
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index dcc8a1d5851e..168e7517a3f0 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -413,7 +413,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
virtio_transport_inc_tx_pkt(vvs, skb);
- ret = t_ops->send_pkt(skb); + ret = t_ops->send_pkt(skb, info->net, info->net_mode); if (ret < 0) break;
@@ -527,6 +527,8 @@ static int virtio_transport_send_credit_update(struct vsock_sock *vsk) struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), + .net_mode = vsk->net_mode, };
return virtio_transport_send_pkt_info(vsk, &info); @@ -1067,6 +1069,8 @@ int virtio_transport_connect(struct vsock_sock *vsk) struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_REQUEST, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), + .net_mode = vsk->net_mode, };
return virtio_transport_send_pkt_info(vsk, &info); @@ -1082,6 +1086,8 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) (mode & SEND_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_SEND : 0), .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), + .net_mode = vsk->net_mode, };
return virtio_transport_send_pkt_info(vsk, &info); @@ -1108,6 +1114,8 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk, .msg = msg, .pkt_len = len, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), + .net_mode = vsk->net_mode, };
return virtio_transport_send_pkt_info(vsk, &info); @@ -1145,6 +1153,8 @@ static int virtio_transport_reset(struct vsock_sock *vsk, .op = VIRTIO_VSOCK_OP_RST, .reply = !!skb, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), + .net_mode = vsk->net_mode, };
/* Send RST only if the original pkt is not a RST pkt */ @@ -1156,15 +1166,27 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
/* Normally packets are associated with a socket. There may be no socket if an * attempt was made to connect to a socket that does not exist. + * + * net and net_mode refer to the namespace of whoever sent the invalid message. + * For loopback, this is the namespace of the socket. For vhost, this is the + * namespace of the VM (i.e., vhost_vsock). */ static int virtio_transport_reset_no_sock(const struct virtio_transport *t, - struct sk_buff *skb) + struct sk_buff *skb, struct net *net, + enum vsock_net_mode net_mode) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, .type = le16_to_cpu(hdr->type), .reply = true, + + /* net or net_mode are not defined here because we pass + * net and net_mode directly to t->send_pkt(), instead of + * relying on virtio_transport_send_pkt_info() to pass them to + * t->send_pkt(). They are not needed by + * virtio_transport_alloc_skb(). + */ }; struct sk_buff *reply;
@@ -1183,7 +1205,7 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t, if (!reply) return -ENOMEM;
- return t->send_pkt(reply); + return t->send_pkt(reply, net, net_mode); }
/* This function should be called with sk_lock held and SOCK_DONE set */ @@ -1465,6 +1487,8 @@ virtio_transport_send_response(struct vsock_sock *vsk, .remote_port = le32_to_cpu(hdr->src_port), .reply = true, .vsk = vsk, + .net = sock_net(sk_vsock(vsk)), + .net_mode = vsk->net_mode, };
return virtio_transport_send_pkt_info(vsk, &info); @@ -1507,12 +1531,14 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb, int ret;
if (le16_to_cpu(hdr->op) != VIRTIO_VSOCK_OP_REQUEST) { - virtio_transport_reset_no_sock(t, skb); + virtio_transport_reset_no_sock(t, skb, sock_net(sk), + vsk->net_mode); return -EINVAL; }
if (sk_acceptq_is_full(sk)) { - virtio_transport_reset_no_sock(t, skb); + virtio_transport_reset_no_sock(t, skb, sock_net(sk), + vsk->net_mode); return -ENOMEM; }
@@ -1520,13 +1546,15 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb, * Subsequent enqueues would lead to a memory leak. */ if (sk->sk_shutdown == SHUTDOWN_MASK) { - virtio_transport_reset_no_sock(t, skb); + virtio_transport_reset_no_sock(t, skb, sock_net(sk), + vsk->net_mode); return -ESHUTDOWN; }
child = vsock_create_connected(sk); if (!child) { - virtio_transport_reset_no_sock(t, skb); + virtio_transport_reset_no_sock(t, skb, sock_net(sk), + vsk->net_mode); return -ENOMEM; }
@@ -1548,7 +1576,8 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb, */ if (ret || vchild->transport != &t->transport) { release_sock(child); - virtio_transport_reset_no_sock(t, skb); + virtio_transport_reset_no_sock(t, skb, sock_net(sk), + vsk->net_mode); sock_put(child); return ret; } @@ -1576,7 +1605,8 @@ static bool virtio_transport_valid_type(u16 type) * lock. */ void virtio_transport_recv_pkt(struct virtio_transport *t, - struct sk_buff *skb) + struct sk_buff *skb, struct net *net, + enum vsock_net_mode net_mode) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct sockaddr_vm src, dst; @@ -1599,24 +1629,25 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, le32_to_cpu(hdr->fwd_cnt));
if (!virtio_transport_valid_type(le16_to_cpu(hdr->type))) { - (void)virtio_transport_reset_no_sock(t, skb); + (void)virtio_transport_reset_no_sock(t, skb, net, net_mode); goto free_pkt; }
/* The socket must be in connected or bound table * otherwise send reset back */ - sk = vsock_find_connected_socket(&src, &dst); + sk = vsock_find_connected_socket_net(&src, &dst, net, net_mode); if (!sk) { - sk = vsock_find_bound_socket(&dst); + sk = vsock_find_bound_socket_net(&dst, net, net_mode); if (!sk) { - (void)virtio_transport_reset_no_sock(t, skb); + (void)virtio_transport_reset_no_sock(t, skb, net, + net_mode); goto free_pkt; } }
if (virtio_transport_get_type(sk) != le16_to_cpu(hdr->type)) { - (void)virtio_transport_reset_no_sock(t, skb); + (void)virtio_transport_reset_no_sock(t, skb, net, net_mode); sock_put(sk); goto free_pkt; } @@ -1635,7 +1666,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, */ if (sock_flag(sk, SOCK_DONE) || (sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) { - (void)virtio_transport_reset_no_sock(t, skb); + (void)virtio_transport_reset_no_sock(t, skb, net, net_mode); release_sock(sk); sock_put(sk); goto free_pkt; @@ -1667,7 +1698,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, kfree_skb(skb); break; default: - (void)virtio_transport_reset_no_sock(t, skb); + (void)virtio_transport_reset_no_sock(t, skb, net, net_mode); kfree_skb(skb); break; } diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 1e25c1a6b43f..a730fa74d2d9 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -31,7 +31,8 @@ static bool vsock_loopback_supports_local_mode(void) return true; }
-static int vsock_loopback_send_pkt(struct sk_buff *skb) +static int vsock_loopback_send_pkt(struct sk_buff *skb, struct net *net, + enum vsock_net_mode net_mode) { struct vsock_loopback *vsock = &the_vsock_loopback; int len = skb->len; @@ -138,7 +139,10 @@ static void vsock_loopback_work(struct work_struct *work) */ virtio_transport_consume_skb_sent(skb, false); virtio_transport_deliver_tap_pkt(skb); - virtio_transport_recv_pkt(&loopback_transport, skb); + + virtio_transport_recv_pkt(&loopback_transport, skb, + sock_net(skb->sk), + vsock_sk(skb->sk)->net_mode); } }