diff mbox series

[RFC,net-next,v6,11/14] vhost/vsock: implement datagram support

Message ID 20240710212555.1617795-12-amery.hung@bytedance.com (mailing list archive)
State RFC
Delegated to: Netdev Maintainers
Headers show
Series virtio/vsock: support datagrams | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for 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 fail Errors and warnings before: 821 this patch: 821
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 2 maintainers not CCed: virtualization@lists.linux.dev eperezma@redhat.com
netdev/build_clang fail Errors and warnings before: 826 this patch: 826
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 fail Errors and warnings before: 826 this patch: 826
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 118 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

Commit Message

Amery Hung July 10, 2024, 9:25 p.m. UTC 
From: Bobby Eshleman <bobby.eshleman@bytedance.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@bytedance.com>
Signed-off-by: Amery Hung <amery.hung@bytedance.com>
---
 drivers/vhost/vsock.c    | 60 ++++++++++++++++++++++++++++++++++++++--
 net/vmw_vsock/af_vsock.c |  2 +-
 2 files changed, 58 insertions(+), 4 deletions(-)
diff mbox series

Patch

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))