Linux-HyperV Archive on lore.kernel.org
 help / color / Atom feed
From: Stefano Garzarella <sgarzare@redhat.com>
To: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, linux-hyperv@vger.kernel.org,
	virtualization@lists.linux-foundation.org, kvm@vger.kernel.org,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Stefano Garzarella <sgarzare@redhat.com>,
	"David S. Miller" <davem@davemloft.net>,
	Dexuan Cui <decui@microsoft.com>,
	Jason Wang <jasowang@redhat.com>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Jorgen Hansen <jhansen@vmware.com>
Subject: [RFC PATCH 1/3] vsock: add network namespace support
Date: Thu, 28 Nov 2019 18:15:17 +0100
Message-ID: <20191128171519.203979-2-sgarzare@redhat.com> (raw)
In-Reply-To: <20191128171519.203979-1-sgarzare@redhat.com>

This patch adds a check of the "net" assigned to a socket during
the vsock_find_bound_socket() and vsock_find_connected_socket()
to support network namespace, allowing to share the same address
(cid, port) across different network namespaces.

G2H transports will use the default network namepsace (init_net).
H2G transports can use different network namespace for different
VMs.

This patch uses default network namepsace (init_net) in all
transports.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
 include/net/af_vsock.h                  |  6 +++--
 net/vmw_vsock/af_vsock.c                | 31 ++++++++++++++++++-------
 net/vmw_vsock/hyperv_transport.c        |  5 ++--
 net/vmw_vsock/virtio_transport_common.c |  5 ++--
 net/vmw_vsock/vmci_transport.c          |  5 ++--
 5 files changed, 35 insertions(+), 17 deletions(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index b1c717286993..fb7dcf73af5b 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -193,13 +193,15 @@ void vsock_enqueue_accept(struct sock *listener, struct sock *connected);
 void vsock_insert_connected(struct vsock_sock *vsk);
 void vsock_remove_bound(struct vsock_sock *vsk);
 void vsock_remove_connected(struct vsock_sock *vsk);
-struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr);
+struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr, struct net *net);
 struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
-					 struct sockaddr_vm *dst);
+					 struct sockaddr_vm *dst,
+					 struct net *net);
 void vsock_remove_sock(struct vsock_sock *vsk);
 void vsock_for_each_connected_socket(void (*fn)(struct sock *sk));
 int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk);
 bool vsock_find_cid(unsigned int cid);
+struct net *vsock_default_net(void);
 
 /**** TAP ****/
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9c5b2a91baad..b485b4a4e3e9 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -226,15 +226,18 @@ static void __vsock_remove_connected(struct vsock_sock *vsk)
 	sock_put(&vsk->sk);
 }
 
-static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
+static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr,
+					      struct net *net)
 {
 	struct vsock_sock *vsk;
 
 	list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) {
-		if (vsock_addr_equals_addr(addr, &vsk->local_addr))
+		if (vsock_addr_equals_addr(addr, &vsk->local_addr) &&
+		    net_eq(net, sock_net(sk_vsock(vsk))))
 			return sk_vsock(vsk);
 
 		if (addr->svm_port == vsk->local_addr.svm_port &&
+		    net_eq(net, sock_net(sk_vsock(vsk))) &&
 		    (vsk->local_addr.svm_cid == VMADDR_CID_ANY ||
 		     addr->svm_cid == VMADDR_CID_ANY))
 			return sk_vsock(vsk);
@@ -244,13 +247,15 @@ static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
 }
 
 static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
-						  struct sockaddr_vm *dst)
+						  struct sockaddr_vm *dst,
+						  struct net *net)
 {
 	struct vsock_sock *vsk;
 
 	list_for_each_entry(vsk, vsock_connected_sockets(src, dst),
 			    connected_table) {
 		if (vsock_addr_equals_addr(src, &vsk->remote_addr) &&
+		    net_eq(net, sock_net(sk_vsock(vsk))) &&
 		    dst->svm_port == vsk->local_addr.svm_port) {
 			return sk_vsock(vsk);
 		}
@@ -295,12 +300,12 @@ void vsock_remove_connected(struct vsock_sock *vsk)
 }
 EXPORT_SYMBOL_GPL(vsock_remove_connected);
 
-struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
+struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr, struct net *net)
 {
 	struct sock *sk;
 
 	spin_lock_bh(&vsock_table_lock);
-	sk = __vsock_find_bound_socket(addr);
+	sk = __vsock_find_bound_socket(addr, net);
 	if (sk)
 		sock_hold(sk);
 
@@ -311,12 +316,13 @@ struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
 EXPORT_SYMBOL_GPL(vsock_find_bound_socket);
 
 struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
-					 struct sockaddr_vm *dst)
+					 struct sockaddr_vm *dst,
+					 struct net *net)
 {
 	struct sock *sk;
 
 	spin_lock_bh(&vsock_table_lock);
-	sk = __vsock_find_connected_socket(src, dst);
+	sk = __vsock_find_connected_socket(src, dst, net);
 	if (sk)
 		sock_hold(sk);
 
@@ -488,6 +494,12 @@ bool vsock_find_cid(unsigned int cid)
 }
 EXPORT_SYMBOL_GPL(vsock_find_cid);
 
+struct net *vsock_default_net(void)
+{
+	return &init_net;
+}
+EXPORT_SYMBOL_GPL(vsock_default_net);
+
 static struct sock *vsock_dequeue_accept(struct sock *listener)
 {
 	struct vsock_sock *vlistener;
@@ -586,6 +598,7 @@ static int __vsock_bind_stream(struct vsock_sock *vsk,
 {
 	static u32 port;
 	struct sockaddr_vm new_addr;
+	struct net *net = sock_net(sk_vsock(vsk));
 
 	if (!port)
 		port = LAST_RESERVED_PORT + 1 +
@@ -603,7 +616,7 @@ static int __vsock_bind_stream(struct vsock_sock *vsk,
 
 			new_addr.svm_port = port++;
 
-			if (!__vsock_find_bound_socket(&new_addr)) {
+			if (!__vsock_find_bound_socket(&new_addr, net)) {
 				found = true;
 				break;
 			}
@@ -620,7 +633,7 @@ static int __vsock_bind_stream(struct vsock_sock *vsk,
 			return -EACCES;
 		}
 
-		if (__vsock_find_bound_socket(&new_addr))
+		if (__vsock_find_bound_socket(&new_addr, net))
 			return -EADDRINUSE;
 	}
 
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 3c7d07a99fc5..fc48a861a0bc 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -201,7 +201,8 @@ static void hvs_remote_addr_init(struct sockaddr_vm *remote,
 
 		remote->svm_port = host_ephemeral_port++;
 
-		sk = vsock_find_connected_socket(remote, local);
+		sk = vsock_find_connected_socket(remote, local,
+						 vsock_default_net());
 		if (!sk) {
 			/* Found an available ephemeral port */
 			return;
@@ -350,7 +351,7 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 		return;
 
 	hvs_addr_init(&addr, conn_from_host ? if_type : if_instance);
-	sk = vsock_find_bound_socket(&addr);
+	sk = vsock_find_bound_socket(&addr, vsock_default_net());
 	if (!sk)
 		return;
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 0e20b0f6eb65..10a8cbe39f61 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1075,6 +1075,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt,
 void virtio_transport_recv_pkt(struct virtio_transport *t,
 			       struct virtio_vsock_pkt *pkt)
 {
+	struct net *net = vsock_default_net();
 	struct sockaddr_vm src, dst;
 	struct vsock_sock *vsk;
 	struct sock *sk;
@@ -1102,9 +1103,9 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 	/* 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(&src, &dst, net);
 	if (!sk) {
-		sk = vsock_find_bound_socket(&dst);
+		sk = vsock_find_bound_socket(&dst, net);
 		if (!sk) {
 			(void)virtio_transport_reset_no_sock(t, pkt);
 			goto free_pkt;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 4b8b1150a738..3ad15d51b30b 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -669,6 +669,7 @@ static bool vmci_transport_stream_allow(u32 cid, u32 port)
 
 static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg)
 {
+	struct net *net = vsock_default_net();
 	struct sock *sk;
 	struct sockaddr_vm dst;
 	struct sockaddr_vm src;
@@ -702,9 +703,9 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg)
 	vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port);
 	vsock_addr_init(&dst, pkt->dg.dst.context, pkt->dst_port);
 
-	sk = vsock_find_connected_socket(&src, &dst);
+	sk = vsock_find_connected_socket(&src, &dst, net);
 	if (!sk) {
-		sk = vsock_find_bound_socket(&dst);
+		sk = vsock_find_bound_socket(&dst, net);
 		if (!sk) {
 			/* We could not find a socket for this specified
 			 * address.  If this packet is a RST, we just drop it.
-- 
2.23.0


  reply index

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-28 17:15 [RFC PATCH 0/3] vsock: support network namespace Stefano Garzarella
2019-11-28 17:15 ` Stefano Garzarella [this message]
2019-11-28 17:15 ` [RFC PATCH 2/3] vsock/virtio_transport_common: handle netns of received packets Stefano Garzarella
2019-11-28 17:15 ` [RFC PATCH 3/3] vhost/vsock: use netns of process that opens the vhost-vsock device Stefano Garzarella
2019-12-03  9:26 ` [RFC PATCH 0/3] vsock: support network namespace Stefan Hajnoczi
2019-12-03 11:17   ` Stefano Garzarella

Reply instructions:

You may reply publically 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=20191128171519.203979-2-sgarzare@redhat.com \
    --to=sgarzare@redhat.com \
    --cc=davem@davemloft.net \
    --cc=decui@microsoft.com \
    --cc=jasowang@redhat.com \
    --cc=jhansen@vmware.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-hyperv@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=stefanha@redhat.com \
    --cc=virtualization@lists.linux-foundation.org \
    /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

Linux-HyperV Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-hyperv/0 linux-hyperv/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-hyperv linux-hyperv/ https://lore.kernel.org/linux-hyperv \
		linux-hyperv@vger.kernel.org
	public-inbox-index linux-hyperv

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-hyperv


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git