Merge branch 'vsock-virtio-vhost-zerocopy' (4b714fd1) · Commits · git / linux-net

Documentation/networking/msg_zerocopy.rst

+11 −2

Original line number	Diff line number	Diff line
		@@ -7,7 +7,8 @@ Intro
		=====

		The MSG_ZEROCOPY flag enables copy avoidance for socket send calls.
		The feature is currently implemented for TCP and UDP sockets.
		The feature is currently implemented for TCP, UDP and VSOCK (with
		virtio transport) sockets.


		Opportunity and Caveats
		@@ -174,7 +175,9 @@ read_notification() call in the previous snippet. A notification
		is encoded in the standard error format, sock_extended_err.

		The level and type fields in the control data are protocol family
		specific, IP_RECVERR or IPV6_RECVERR.
		specific, IP_RECVERR or IPV6_RECVERR (for TCP or UDP socket).
		For VSOCK socket, cmsg_level will be SOL_VSOCK and cmsg_type will be
		VSOCK_RECVERR.

		Error origin is the new type SO_EE_ORIGIN_ZEROCOPY. ee_errno is zero,
		as explained before, to avoid blocking read and write system calls on
		@@ -235,12 +238,15 @@ Implementation
		Loopback
		--------

		For TCP and UDP:
		Data sent to local sockets can be queued indefinitely if the receive
		process does not read its socket. Unbound notification latency is not
		acceptable. For this reason all packets generated with MSG_ZEROCOPY
		that are looped to a local socket will incur a deferred copy. This
		includes looping onto packet sockets (e.g., tcpdump) and tun devices.

		For VSOCK:
		Data path sent to local sockets is the same as for non-local sockets.

		Testing
		=======
		@@ -254,3 +260,6 @@ instance when run with msg_zerocopy.sh between a veth pair across
		namespaces, the test will not show any improvement. For testing, the
		loopback restriction can be temporarily relaxed by making
		skb_orphan_frags_rx identical to skb_orphan_frags.

		For VSOCK type of socket example can be found in
		tools/testing/vsock/vsock_test_zerocopy.c.

drivers/vhost/vsock.c

+7 −0

Original line number	Diff line number	Diff line
		@@ -398,6 +398,11 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock)
		return val < vq->num;
		}

		static bool vhost_transport_msgzerocopy_allow(void)
		{
		return true;
		}

		static bool vhost_transport_seqpacket_allow(u32 remote_cid);

		static struct virtio_transport vhost_transport = {
		@@ -431,6 +436,8 @@ static struct virtio_transport vhost_transport = {
		.seqpacket_allow = vhost_transport_seqpacket_allow,
		.seqpacket_has_data = virtio_transport_seqpacket_has_data,

		.msgzerocopy_allow = vhost_transport_msgzerocopy_allow,

		.notify_poll_in = virtio_transport_notify_poll_in,
		.notify_poll_out = virtio_transport_notify_poll_out,
		.notify_recv_init = virtio_transport_notify_recv_init,

include/linux/socket.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -383,6 +383,7 @@ struct ucred {
		#define SOL_MPTCP 284
		#define SOL_MCTP 285
		#define SOL_SMC 286
		#define SOL_VSOCK 287

		/* IPX options */
		#define IPX_TYPE 1

include/net/af_vsock.h

+7 −0

Original line number	Diff line number	Diff line
		@@ -177,6 +177,9 @@ struct vsock_transport {

		/* Read a single skb */
		int (read_skb)(struct vsock_sock , skb_read_actor_t);

		/* Zero-copy. */
		bool (*msgzerocopy_allow)(void);
		};

		/** CORE **/
		@@ -241,4 +244,8 @@ static inline void __init vsock_bpf_build_proto(void)
		{}
		#endif

		static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t)
		{
		return t->msgzerocopy_allow && t->msgzerocopy_allow();
		}
		#endif /* __AF_VSOCK_H__ */

include/uapi/linux/vm_sockets.h

+17 −0

Original line number	Diff line number	Diff line
		@@ -191,4 +191,21 @@ struct sockaddr_vm {

		#define IOCTL_VM_SOCKETS_GET_LOCAL_CID _IO(7, 0xb9)

		/* MSG_ZEROCOPY notifications are encoded in the standard error format,
		* sock_extended_err. See Documentation/networking/msg_zerocopy.rst in
		* kernel source tree for more details.
		*/

		/* 'cmsg_level' field value of 'struct cmsghdr' for notification parsing
		* when MSG_ZEROCOPY flag is used on transmissions.
		*/

		#define SOL_VSOCK 287

		/* 'cmsg_type' field value of 'struct cmsghdr' for notification parsing
		* when MSG_ZEROCOPY flag is used on transmissions.
		*/

		#define VSOCK_RECVERR 1

		#endif /* _UAPI_VM_SOCKETS_H */