diff mbox series

[v2,1/3] vsock: add network namespace support

Message ID 20250312-vsock-netns-v2-1-84bffa1aa97a@gmail.com (mailing list archive)
State New
Delegated to: Netdev Maintainers
Headers show
Series vsock: add namespace support to vhost-vsock | expand

Checks

Context Check Description
netdev/series_format warning Target tree name not specified in the subject
netdev/tree_selection success Guessed tree name to be net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success Errors and warnings before: 26 (+0) this patch: 26 (+0)
netdev/cc_maintainers warning 3 maintainers not CCed: edumazet@google.com pabeni@redhat.com horms@kernel.org
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 176 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2025-03-13--00-00 (tests: 894)

Commit Message

Bobby Eshleman March 12, 2025, 8:59 p.m. UTC 
From: Stefano Garzarella <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.

This patch preserves old behavior, and does not yet bring up namespace
support fully.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@gmail.com>
---
v1 -> v2:
* remove 'netns' module param
* remove vsock_net_eq()
* use vsock_global_net() for "global" namespace
* use fallback logic in socket lookup functions, giving precedence to
  non-global vsock namespaces

RFC -> v1
* added 'netns' module param
* added 'vsock_net_eq()' to check the "net" assigned to a socket
  only when 'netns' support is enabled
---
 include/net/af_vsock.h                  |  7 +++--
 net/vmw_vsock/af_vsock.c                | 55 ++++++++++++++++++++++++---------
 net/vmw_vsock/hyperv_transport.c        |  2 +-
 net/vmw_vsock/virtio_transport_common.c |  5 +--
 net/vmw_vsock/vmci_transport.c          |  4 +--
 5 files changed, 51 insertions(+), 22 deletions(-)
diff mbox series

Patch

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 9e85424c834353d016a527070dd62e15ff3bfce1..41afbc18648c953da27a93571d408de968aa7668 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -213,9 +213,10 @@  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(struct vsock_transport *transport,
 				     void (*fn)(struct sock *sk));
@@ -255,4 +256,6 @@  static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t)
 {
 	return t->msgzerocopy_allow && t->msgzerocopy_allow();
 }
+
+struct net *vsock_global_net(void);
 #endif /* __AF_VSOCK_H__ */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 7e3db87ae4333cf63327ec105ca99253569bb9fe..d206489bf0a81cf989387c7c8063be91a7c21a7d 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -235,37 +235,60 @@  static void __vsock_remove_connected(struct vsock_sock *vsk)
 	sock_put(&vsk->sk);
 }
 
-static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
+struct net *vsock_global_net(void)
 {
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(vsock_global_net);
+
+static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr,
+					      struct net *net)
+{
+	struct sock *fallback = NULL;
 	struct vsock_sock *vsk;
 
 	list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) {
-		if (vsock_addr_equals_addr(addr, &vsk->local_addr))
-			return sk_vsock(vsk);
+		if (vsock_addr_equals_addr(addr, &vsk->local_addr)) {
+			if (net_eq(net, sock_net(sk_vsock(vsk))))
+				return sk_vsock(vsk);
 
+			if (net_eq(net, vsock_global_net()))
+				fallback = sk_vsock(vsk);
+		}
 		if (addr->svm_port == vsk->local_addr.svm_port &&
 		    (vsk->local_addr.svm_cid == VMADDR_CID_ANY ||
-		     addr->svm_cid == VMADDR_CID_ANY))
-			return sk_vsock(vsk);
+		     addr->svm_cid == VMADDR_CID_ANY)) {
+			if (net_eq(net, sock_net(sk_vsock(vsk))))
+				return sk_vsock(vsk);
+
+			if (net_eq(net, vsock_global_net()))
+				fallback = sk_vsock(vsk);
+		}
 	}
 
-	return NULL;
+	return fallback;
 }
 
 static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
-						  struct sockaddr_vm *dst)
+						  struct sockaddr_vm *dst,
+						  struct net *net)
 {
+	struct sock *fallback = NULL;
 	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) &&
 		    dst->svm_port == vsk->local_addr.svm_port) {
-			return sk_vsock(vsk);
+			if (net_eq(net, sock_net(sk_vsock(vsk))))
+				return sk_vsock(vsk);
+
+			if (net_eq(net, vsock_global_net()))
+				fallback = sk_vsock(vsk);
 		}
 	}
 
-	return NULL;
+	return fallback;
 }
 
 static void vsock_insert_unbound(struct vsock_sock *vsk)
@@ -304,12 +327,12 @@  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);
 
@@ -320,12 +343,13 @@  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);
 
@@ -644,6 +668,7 @@  static int __vsock_bind_connectible(struct vsock_sock *vsk,
 {
 	static u32 port;
 	struct sockaddr_vm new_addr;
+	struct net *net = sock_net(sk_vsock(vsk));
 
 	if (!port)
 		port = get_random_u32_above(LAST_RESERVED_PORT);
@@ -660,7 +685,7 @@  static int __vsock_bind_connectible(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;
 			}
@@ -677,7 +702,7 @@  static int __vsock_bind_connectible(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 31342ab502b4fc35feb812d2c94e0e35ded73771..253609898d24f8a484fcfc3296011c6f501a72a8 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -313,7 +313,7 @@  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, NULL);
 	if (!sk)
 		return;
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 7f7de6d8809655fe522749fbbc9025df71f071bd..256d2a4fe482b3cb938a681b6924be69b2065616 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1590,6 +1590,7 @@  void virtio_transport_recv_pkt(struct virtio_transport *t,
 			       struct sk_buff *skb)
 {
 	struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
+	struct net *net = vsock_global_net();
 	struct sockaddr_vm src, dst;
 	struct vsock_sock *vsk;
 	struct sock *sk;
@@ -1617,9 +1618,9 @@  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, skb);
 			goto free_pkt;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index b370070194fa4ac0df45a073d389ffccf69a0029..373b9fe30a26c18aaa181fbc16db840d8f839b13 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -703,9 +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, NULL);
 	if (!sk) {
-		sk = vsock_find_bound_socket(&dst);
+		sk = vsock_find_bound_socket(&dst, NULL);
 		if (!sk) {
 			/* We could not find a socket for this specified
 			 * address.  If this packet is a RST, we just drop it.