From 268551503d66dc0a266fe6034c84a31ab4f3edf7 Mon Sep 17 00:00:00 2001 From: gushengxian Date: Wed, 9 Jun 2021 18:11:59 -0700 Subject: vsock/vmci: remove the repeated word "be" Remove the repeated word "be". Signed-off-by: gushengxian Signed-off-by: David S. Miller --- net/vmw_vsock/vmci_transport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c99bc4ce78e2..e617ed93f06b 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1248,7 +1248,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, vsock_remove_pending(listener, pending); vsock_enqueue_accept(listener, pending); - /* Callers of accept() will be be waiting on the listening socket, not + /* Callers of accept() will be waiting on the listening socket, not * the pending socket. */ listener->sk_data_ready(listener); -- cgit From a9e29e5511b9e68b64e9031edb7b7f8920ad3de1 Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:09:47 +0300 Subject: af_vsock: update functions for connectible socket Prepare af_vsock.c for SEQPACKET support: rename some functions such as setsockopt(), getsockopt(), connect(), recvmsg(), sendmsg() in general manner, because they are shared with stream sockets. Signed-off-by: Arseny Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 64 +++++++++++++++++++++++++----------------------- 1 file changed, 34 insertions(+), 30 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 92a72f0e0d94..7dd8e70d78cd 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -604,8 +604,8 @@ out: /**** SOCKET OPERATIONS ****/ -static int __vsock_bind_stream(struct vsock_sock *vsk, - struct sockaddr_vm *addr) +static int __vsock_bind_connectible(struct vsock_sock *vsk, + struct sockaddr_vm *addr) { static u32 port; struct sockaddr_vm new_addr; @@ -685,7 +685,7 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) switch (sk->sk_socket->type) { case SOCK_STREAM: spin_lock_bh(&vsock_table_lock); - retval = __vsock_bind_stream(vsk, addr); + retval = __vsock_bind_connectible(vsk, addr); spin_unlock_bh(&vsock_table_lock); break; @@ -768,6 +768,11 @@ static struct sock *__vsock_create(struct net *net, return sk; } +static bool sock_type_connectible(u16 type) +{ + return type == SOCK_STREAM; +} + static void __vsock_release(struct sock *sk, int level) { if (sk) { @@ -786,7 +791,7 @@ static void __vsock_release(struct sock *sk, int level) if (vsk->transport) vsk->transport->release(vsk); - else if (sk->sk_type == SOCK_STREAM) + else if (sock_type_connectible(sk->sk_type)) vsock_remove_sock(vsk); sock_orphan(sk); @@ -948,7 +953,7 @@ static int vsock_shutdown(struct socket *sock, int mode) lock_sock(sk); if (sock->state == SS_UNCONNECTED) { err = -ENOTCONN; - if (sk->sk_type == SOCK_STREAM) + if (sock_type_connectible(sk->sk_type)) goto out; } else { sock->state = SS_DISCONNECTING; @@ -961,7 +966,7 @@ static int vsock_shutdown(struct socket *sock, int mode) sk->sk_shutdown |= mode; sk->sk_state_change(sk); - if (sk->sk_type == SOCK_STREAM) { + if (sock_type_connectible(sk->sk_type)) { sock_reset_flag(sk, SOCK_DONE); vsock_send_shutdown(sk, mode); } @@ -1016,7 +1021,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; - } else if (sock->type == SOCK_STREAM) { + } else if (sock_type_connectible(sk->sk_type)) { const struct vsock_transport *transport; lock_sock(sk); @@ -1263,8 +1268,8 @@ static void vsock_connect_timeout(struct work_struct *work) sock_put(sk); } -static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, - int addr_len, int flags) +static int vsock_connect(struct socket *sock, struct sockaddr *addr, + int addr_len, int flags) { int err; struct sock *sk; @@ -1414,7 +1419,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, lock_sock(listener); - if (sock->type != SOCK_STREAM) { + if (!sock_type_connectible(sock->type)) { err = -EOPNOTSUPP; goto out; } @@ -1491,7 +1496,7 @@ static int vsock_listen(struct socket *sock, int backlog) lock_sock(sk); - if (sock->type != SOCK_STREAM) { + if (!sock_type_connectible(sk->sk_type)) { err = -EOPNOTSUPP; goto out; } @@ -1535,11 +1540,11 @@ static void vsock_update_buffer_size(struct vsock_sock *vsk, vsk->buffer_size = val; } -static int vsock_stream_setsockopt(struct socket *sock, - int level, - int optname, - sockptr_t optval, - unsigned int optlen) +static int vsock_connectible_setsockopt(struct socket *sock, + int level, + int optname, + sockptr_t optval, + unsigned int optlen) { int err; struct sock *sk; @@ -1617,10 +1622,10 @@ exit: return err; } -static int vsock_stream_getsockopt(struct socket *sock, - int level, int optname, - char __user *optval, - int __user *optlen) +static int vsock_connectible_getsockopt(struct socket *sock, + int level, int optname, + char __user *optval, + int __user *optlen) { int err; int len; @@ -1688,8 +1693,8 @@ static int vsock_stream_getsockopt(struct socket *sock, return 0; } -static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, - size_t len) +static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk; struct vsock_sock *vsk; @@ -1828,10 +1833,9 @@ out: return err; } - static int -vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; @@ -2007,7 +2011,7 @@ static const struct proto_ops vsock_stream_ops = { .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, - .connect = vsock_stream_connect, + .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, @@ -2015,10 +2019,10 @@ static const struct proto_ops vsock_stream_ops = { .ioctl = sock_no_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, - .setsockopt = vsock_stream_setsockopt, - .getsockopt = vsock_stream_getsockopt, - .sendmsg = vsock_stream_sendmsg, - .recvmsg = vsock_stream_recvmsg, + .setsockopt = vsock_connectible_setsockopt, + .getsockopt = vsock_connectible_getsockopt, + .sendmsg = vsock_connectible_sendmsg, + .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; -- cgit From b3f7fd54881bcba5dc529935f38df649167803b1 Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:10:07 +0300 Subject: af_vsock: separate wait data loop Wait loop for data could be shared between SEQPACKET and STREAM sockets, so move it to dedicated function. While moving the code around, let's update an old comment. Signed-off-by: Arseny Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 156 +++++++++++++++++++++++++---------------------- 1 file changed, 84 insertions(+), 72 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 7dd8e70d78cd..4269e80b02cd 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1833,6 +1833,69 @@ out: return err; } +static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait, + long timeout, + struct vsock_transport_recv_notify_data *recv_data, + size_t target) +{ + const struct vsock_transport *transport; + struct vsock_sock *vsk; + s64 data; + int err; + + vsk = vsock_sk(sk); + err = 0; + transport = vsk->transport; + + while ((data = vsock_stream_has_data(vsk)) == 0) { + prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); + + if (sk->sk_err != 0 || + (sk->sk_shutdown & RCV_SHUTDOWN) || + (vsk->peer_shutdown & SEND_SHUTDOWN)) { + break; + } + + /* Don't wait for non-blocking sockets. */ + if (timeout == 0) { + err = -EAGAIN; + break; + } + + if (recv_data) { + err = transport->notify_recv_pre_block(vsk, target, recv_data); + if (err < 0) + break; + } + + release_sock(sk); + timeout = schedule_timeout(timeout); + lock_sock(sk); + + if (signal_pending(current)) { + err = sock_intr_errno(timeout); + break; + } else if (timeout == 0) { + err = -EAGAIN; + break; + } + } + + finish_wait(sk_sleep(sk), wait); + + if (err) + return err; + + /* Internal transport error when checking for available + * data. XXX This should be changed to a connection + * reset in a later change. + */ + if (data < 0) + return -ENOMEM; + + return data; +} + static int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) @@ -1912,85 +1975,34 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, while (1) { - s64 ready; + ssize_t read; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - ready = vsock_stream_has_data(vsk); + err = vsock_wait_data(sk, &wait, timeout, &recv_data, target); + if (err <= 0) + break; - if (ready == 0) { - if (sk->sk_err != 0 || - (sk->sk_shutdown & RCV_SHUTDOWN) || - (vsk->peer_shutdown & SEND_SHUTDOWN)) { - finish_wait(sk_sleep(sk), &wait); - break; - } - /* Don't wait for non-blocking sockets. */ - if (timeout == 0) { - err = -EAGAIN; - finish_wait(sk_sleep(sk), &wait); - break; - } - - err = transport->notify_recv_pre_block( - vsk, target, &recv_data); - if (err < 0) { - finish_wait(sk_sleep(sk), &wait); - break; - } - release_sock(sk); - timeout = schedule_timeout(timeout); - lock_sock(sk); - - if (signal_pending(current)) { - err = sock_intr_errno(timeout); - finish_wait(sk_sleep(sk), &wait); - break; - } else if (timeout == 0) { - err = -EAGAIN; - finish_wait(sk_sleep(sk), &wait); - break; - } - } else { - ssize_t read; - - finish_wait(sk_sleep(sk), &wait); - - if (ready < 0) { - /* Invalid queue pair content. XXX This should - * be changed to a connection reset in a later - * change. - */ - - err = -ENOMEM; - goto out; - } - - err = transport->notify_recv_pre_dequeue( - vsk, target, &recv_data); - if (err < 0) - break; + err = transport->notify_recv_pre_dequeue(vsk, target, + &recv_data); + if (err < 0) + break; - read = transport->stream_dequeue( - vsk, msg, - len - copied, flags); - if (read < 0) { - err = -ENOMEM; - break; - } + read = transport->stream_dequeue(vsk, msg, len - copied, flags); + if (read < 0) { + err = -ENOMEM; + break; + } - copied += read; + copied += read; - err = transport->notify_recv_post_dequeue( - vsk, target, read, - !(flags & MSG_PEEK), &recv_data); - if (err < 0) - goto out; + err = transport->notify_recv_post_dequeue(vsk, target, read, + !(flags & MSG_PEEK), &recv_data); + if (err < 0) + goto out; - if (read >= target || flags & MSG_PEEK) - break; + if (read >= target || flags & MSG_PEEK) + break; - target -= read; - } + target -= read; } if (sk->sk_err) -- cgit From 19c1b90e1979c3974cd6a3ec0cbb886a84278d84 Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:10:21 +0300 Subject: af_vsock: separate receive data loop Some code in receive data loop could be shared between SEQPACKET and STREAM sockets, while another part is type specific, so move STREAM specific data receive logic to '__vsock_stream_recvmsg()' dedicated function, while checks, that will be same for both STREAM and SEQPACKET sockets, stays in 'vsock_connectible_recvmsg()'. Signed-off-by: Arseny Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 116 +++++++++++++++++++++++++++-------------------- 1 file changed, 67 insertions(+), 49 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4269e80b02cd..c4f6bfa1e381 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1896,65 +1896,22 @@ static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait, return data; } -static int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int flags) { - struct sock *sk; - struct vsock_sock *vsk; + struct vsock_transport_recv_notify_data recv_data; const struct vsock_transport *transport; - int err; - size_t target; + struct vsock_sock *vsk; ssize_t copied; + size_t target; long timeout; - struct vsock_transport_recv_notify_data recv_data; + int err; DEFINE_WAIT(wait); - sk = sock->sk; vsk = vsock_sk(sk); - err = 0; - - lock_sock(sk); - transport = vsk->transport; - if (!transport || sk->sk_state != TCP_ESTABLISHED) { - /* Recvmsg is supposed to return 0 if a peer performs an - * orderly shutdown. Differentiate between that case and when a - * peer has not connected or a local shutdown occurred with the - * SOCK_DONE flag. - */ - if (sock_flag(sk, SOCK_DONE)) - err = 0; - else - err = -ENOTCONN; - - goto out; - } - - if (flags & MSG_OOB) { - err = -EOPNOTSUPP; - goto out; - } - - /* We don't check peer_shutdown flag here since peer may actually shut - * down, but there can be data in the queue that a local socket can - * receive. - */ - if (sk->sk_shutdown & RCV_SHUTDOWN) { - err = 0; - goto out; - } - - /* It is valid on Linux to pass in a zero-length receive buffer. This - * is not an error. We may as well bail out now. - */ - if (!len) { - err = 0; - goto out; - } - /* We must not copy less than target bytes into the user's buffer * before returning successfully, so we wait for the consume queue to * have that much data to consume before dequeueing. Note that this @@ -2013,6 +1970,67 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (copied > 0) err = copied; +out: + return err; +} + +static int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ + struct sock *sk; + struct vsock_sock *vsk; + const struct vsock_transport *transport; + int err; + + DEFINE_WAIT(wait); + + sk = sock->sk; + vsk = vsock_sk(sk); + err = 0; + + lock_sock(sk); + + transport = vsk->transport; + + if (!transport || sk->sk_state != TCP_ESTABLISHED) { + /* Recvmsg is supposed to return 0 if a peer performs an + * orderly shutdown. Differentiate between that case and when a + * peer has not connected or a local shutdown occurred with the + * SOCK_DONE flag. + */ + if (sock_flag(sk, SOCK_DONE)) + err = 0; + else + err = -ENOTCONN; + + goto out; + } + + if (flags & MSG_OOB) { + err = -EOPNOTSUPP; + goto out; + } + + /* We don't check peer_shutdown flag here since peer may actually shut + * down, but there can be data in the queue that a local socket can + * receive. + */ + if (sk->sk_shutdown & RCV_SHUTDOWN) { + err = 0; + goto out; + } + + /* It is valid on Linux to pass in a zero-length receive buffer. This + * is not an error. We may as well bail out now. + */ + if (!len) { + err = 0; + goto out; + } + + err = __vsock_stream_recvmsg(sk, msg, len, flags); + out: release_sock(sk); return err; -- cgit From 9942c192b256bc11cc903f89f4057bc97434dee9 Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:10:34 +0300 Subject: af_vsock: implement SEQPACKET receive loop Add receive loop for SEQPACKET. It looks like receive loop for STREAM, but there are differences: 1) It doesn't call notify callbacks. 2) It doesn't care about 'SO_SNDLOWAT' and 'SO_RCVLOWAT' values, because there is no sense for these values in SEQPACKET case. 3) It waits until whole record is received. 4) It processes and sets 'MSG_TRUNC' flag. So to avoid extra conditions for two types of socket inside one loop, two independent functions were created. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index c4f6bfa1e381..87ae26b2e3e1 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1974,6 +1974,56 @@ out: return err; } +static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int flags) +{ + const struct vsock_transport *transport; + struct vsock_sock *vsk; + ssize_t record_len; + long timeout; + int err = 0; + DEFINE_WAIT(wait); + + vsk = vsock_sk(sk); + transport = vsk->transport; + + timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + + err = vsock_wait_data(sk, &wait, timeout, NULL, 0); + if (err <= 0) + goto out; + + record_len = transport->seqpacket_dequeue(vsk, msg, flags); + + if (record_len < 0) { + err = -ENOMEM; + goto out; + } + + if (sk->sk_err) { + err = -sk->sk_err; + } else if (sk->sk_shutdown & RCV_SHUTDOWN) { + err = 0; + } else { + /* User sets MSG_TRUNC, so return real length of + * packet. + */ + if (flags & MSG_TRUNC) + err = record_len; + else + err = len - msg_data_left(msg); + + /* Always set MSG_TRUNC if real length of packet is + * bigger than user's buffer. + */ + if (record_len > len) + msg->msg_flags |= MSG_TRUNC; + } + +out: + return err; +} + static int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) @@ -2029,7 +2079,10 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } - err = __vsock_stream_recvmsg(sk, msg, len, flags); + if (sk->sk_type == SOCK_STREAM) + err = __vsock_stream_recvmsg(sk, msg, len, flags); + else + err = __vsock_seqpacket_recvmsg(sk, msg, len, flags); out: release_sock(sk); -- cgit From fbe70c480796d9052fcc786c76e6b029acb1c7bc Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:10:49 +0300 Subject: af_vsock: implement send logic for SEQPACKET Update current stream enqueue function for SEQPACKET support: 1) Call transport's seqpacket enqueue callback. 2) Return value from enqueue function is whole record length or error for SOCK_SEQPACKET. Signed-off-by: Arseny Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 87ae26b2e3e1..9e0cc07e3caf 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1808,9 +1808,13 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, * responsibility to check how many bytes we were able to send. */ - written = transport->stream_enqueue( - vsk, msg, - len - total_written); + if (sk->sk_type == SOCK_SEQPACKET) { + written = transport->seqpacket_enqueue(vsk, + msg, len - total_written); + } else { + written = transport->stream_enqueue(vsk, + msg, len - total_written); + } if (written < 0) { err = -ENOMEM; goto out_err; @@ -1826,8 +1830,14 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, } out_err: - if (total_written > 0) - err = total_written; + if (total_written > 0) { + /* Return number of written bytes only if: + * 1) SOCK_STREAM socket. + * 2) SOCK_SEQPACKET socket when whole buffer is sent. + */ + if (sk->sk_type == SOCK_STREAM || total_written == len) + err = total_written; + } out: release_sock(sk); return err; -- cgit From 0798e78b102b79ed9fe4b2beeb18cf0db117c79b Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:11:04 +0300 Subject: af_vsock: rest of SEQPACKET support Add socket ops for SEQPACKET type and .seqpacket_allow() callback to query transports if they support SEQPACKET. Also split path for data check for STREAM and SEQPACKET branches. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 46 insertions(+), 2 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9e0cc07e3caf..21a56f52d683 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -452,6 +452,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) new_transport = transport_dgram; break; case SOCK_STREAM: + case SOCK_SEQPACKET: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g || @@ -484,6 +485,14 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) if (!new_transport || !try_module_get(new_transport->module)) return -ENODEV; + if (sk->sk_type == SOCK_SEQPACKET) { + if (!new_transport->seqpacket_allow || + !new_transport->seqpacket_allow(remote_cid)) { + module_put(new_transport->module); + return -ESOCKTNOSUPPORT; + } + } + ret = new_transport->init(vsk, psk); if (ret) { module_put(new_transport->module); @@ -684,6 +693,7 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) switch (sk->sk_socket->type) { case SOCK_STREAM: + case SOCK_SEQPACKET: spin_lock_bh(&vsock_table_lock); retval = __vsock_bind_connectible(vsk, addr); spin_unlock_bh(&vsock_table_lock); @@ -770,7 +780,7 @@ static struct sock *__vsock_create(struct net *net, static bool sock_type_connectible(u16 type) { - return type == SOCK_STREAM; + return (type == SOCK_STREAM) || (type == SOCK_SEQPACKET); } static void __vsock_release(struct sock *sk, int level) @@ -849,6 +859,16 @@ s64 vsock_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(vsock_stream_has_data); +static s64 vsock_has_data(struct vsock_sock *vsk) +{ + struct sock *sk = sk_vsock(vsk); + + if (sk->sk_type == SOCK_SEQPACKET) + return vsk->transport->seqpacket_has_data(vsk); + else + return vsock_stream_has_data(vsk); +} + s64 vsock_stream_has_space(struct vsock_sock *vsk) { return vsk->transport->stream_has_space(vsk); @@ -1857,7 +1877,7 @@ static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait, err = 0; transport = vsk->transport; - while ((data = vsock_stream_has_data(vsk)) == 0) { + while ((data = vsock_has_data(vsk)) == 0) { prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); if (sk->sk_err != 0 || @@ -2120,6 +2140,27 @@ static const struct proto_ops vsock_stream_ops = { .sendpage = sock_no_sendpage, }; +static const struct proto_ops vsock_seqpacket_ops = { + .family = PF_VSOCK, + .owner = THIS_MODULE, + .release = vsock_release, + .bind = vsock_bind, + .connect = vsock_connect, + .socketpair = sock_no_socketpair, + .accept = vsock_accept, + .getname = vsock_getname, + .poll = vsock_poll, + .ioctl = sock_no_ioctl, + .listen = vsock_listen, + .shutdown = vsock_shutdown, + .setsockopt = vsock_connectible_setsockopt, + .getsockopt = vsock_connectible_getsockopt, + .sendmsg = vsock_connectible_sendmsg, + .recvmsg = vsock_connectible_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + static int vsock_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -2140,6 +2181,9 @@ static int vsock_create(struct net *net, struct socket *sock, case SOCK_STREAM: sock->ops = &vsock_stream_ops; break; + case SOCK_SEQPACKET: + sock->ops = &vsock_seqpacket_ops; + break; default: return -ESOCKTNOSUPPORT; } -- cgit From 8cb48554ad822fb8553380b4781ea65f1e3ca7bb Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:11:18 +0300 Subject: af_vsock: update comments for stream sockets Replace 'stream' to 'connection oriented' in comments as SEQPACKET is also connection oriented. Signed-off-by: Arseny Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 21a56f52d683..67954afef4e1 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -415,8 +415,8 @@ static void vsock_deassign_transport(struct vsock_sock *vsk) /* Assign a transport to a socket and call the .init transport callback. * - * Note: for stream socket this must be called when vsk->remote_addr is set - * (e.g. during the connect() or when a connection request on a listener + * Note: for connection oriented socket this must be called when vsk->remote_addr + * is set (e.g. during the connect() or when a connection request on a listener * socket is received). * The vsk->remote_addr is used to decide which transport to use: * - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if @@ -470,10 +470,10 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) return 0; /* transport->release() must be called with sock lock acquired. - * This path can only be taken during vsock_stream_connect(), - * where we have already held the sock lock. - * In the other cases, this function is called on a new socket - * which is not assigned to any transport. + * This path can only be taken during vsock_connect(), where we + * have already held the sock lock. In the other cases, this + * function is called on a new socket which is not assigned to + * any transport. */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); @@ -658,9 +658,10 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port); - /* Remove stream sockets from the unbound list and add them to the hash - * table for easy lookup by its address. The unbound list is simply an - * extra entry at the end of the hash table, a trick used by AF_UNIX. + /* Remove connection oriented sockets from the unbound list and add them + * to the hash table for easy lookup by its address. The unbound list + * is simply an extra entry at the end of the hash table, a trick used + * by AF_UNIX. */ __vsock_remove_bound(vsk); __vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk); @@ -962,10 +963,10 @@ static int vsock_shutdown(struct socket *sock, int mode) if ((mode & ~SHUTDOWN_MASK) || !mode) return -EINVAL; - /* If this is a STREAM socket and it is not connected then bail out - * immediately. If it is a DGRAM socket then we must first kick the - * socket so that it wakes up from any sleeping calls, for example - * recv(), and then afterwards return the error. + /* If this is a connection oriented socket and it is not connected then + * bail out immediately. If it is a DGRAM socket then we must first + * kick the socket so that it wakes up from any sleeping calls, for + * example recv(), and then afterwards return the error. */ sk = sock->sk; @@ -1737,7 +1738,9 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, transport = vsk->transport; - /* Callers should not provide a destination with stream sockets. */ + /* Callers should not provide a destination with connection oriented + * sockets. + */ if (msg->msg_namelen) { err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out; -- cgit From b93f8877c1f2e3d3dcdec7759c5de3d67777f45d Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:11:31 +0300 Subject: virtio/vsock: set packet's type in virtio_transport_send_pkt_info() There is no need to set type of packet which differs from type of socket, so move passing type of packet from 'info' structure to 'virtio_transport_send_pkt_info()' function. Since at current time only stream type is supported, set it directly in 'virtio_ transport_send_pkt_info()', so callers don't need to set it. Signed-off-by: Arseny Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport_common.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 902cb6dd710b..6503a8370130 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -179,6 +179,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; + info->type = VIRTIO_VSOCK_TYPE_STREAM; + t_ops = virtio_transport_get_ops(vsk); if (unlikely(!t_ops)) return -EFAULT; @@ -270,12 +272,10 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) EXPORT_SYMBOL_GPL(virtio_transport_put_credit); static int virtio_transport_send_credit_update(struct vsock_sock *vsk, - int type, struct virtio_vsock_hdr *hdr) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, - .type = type, .vsk = vsk, }; @@ -383,11 +383,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, * messages, we set the limit to a high value. TODO: experiment * with different values. */ - if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { - virtio_transport_send_credit_update(vsk, - VIRTIO_VSOCK_TYPE_STREAM, - NULL); - } + if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) + virtio_transport_send_credit_update(vsk, NULL); return total; @@ -496,8 +493,7 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val) vvs->buf_alloc = *val; - virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, - NULL); + virtio_transport_send_credit_update(vsk, NULL); } EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size); @@ -624,7 +620,6 @@ int virtio_transport_connect(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_REQUEST, - .type = VIRTIO_VSOCK_TYPE_STREAM, .vsk = vsk, }; @@ -636,7 +631,6 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_SHUTDOWN, - .type = VIRTIO_VSOCK_TYPE_STREAM, .flags = (mode & RCV_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | (mode & SEND_SHUTDOWN ? @@ -665,7 +659,6 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RW, - .type = VIRTIO_VSOCK_TYPE_STREAM, .msg = msg, .pkt_len = len, .vsk = vsk, @@ -688,7 +681,6 @@ static int virtio_transport_reset(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, - .type = VIRTIO_VSOCK_TYPE_STREAM, .reply = !!pkt, .vsk = vsk, }; @@ -1000,7 +992,6 @@ virtio_transport_send_response(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RESPONSE, - .type = VIRTIO_VSOCK_TYPE_STREAM, .remote_cid = le64_to_cpu(pkt->hdr.src_cid), .remote_port = le32_to_cpu(pkt->hdr.src_port), .reply = true, -- cgit From c10844c5979992fde734f566357059e4a7c815bc Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:12:08 +0300 Subject: virtio/vsock: simplify credit update function API This function is static and 'hdr' arg was always NULL. Signed-off-by: Arseny Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport_common.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 6503a8370130..ad0d34d41444 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -271,8 +271,7 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) } EXPORT_SYMBOL_GPL(virtio_transport_put_credit); -static int virtio_transport_send_credit_update(struct vsock_sock *vsk, - struct virtio_vsock_hdr *hdr) +static int virtio_transport_send_credit_update(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, @@ -384,7 +383,7 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, * with different values. */ if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) - virtio_transport_send_credit_update(vsk, NULL); + virtio_transport_send_credit_update(vsk); return total; @@ -493,7 +492,7 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val) vvs->buf_alloc = *val; - virtio_transport_send_credit_update(vsk, NULL); + virtio_transport_send_credit_update(vsk); } EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size); -- cgit From 44931195a5412a97c46d299227fbabad4e09010d Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:12:38 +0300 Subject: virtio/vsock: dequeue callback for SOCK_SEQPACKET Callback fetches RW packets from rx queue of socket until whole record is copied(if user's buffer is full, user is not woken up). This is done to not stall sender, because if we wake up user and it leaves syscall, nobody will send credit update for rest of record, and sender will wait for next enter of read syscall at receiver's side. So if user buffer is full, we just send credit update and drop data. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport_common.c | 84 +++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index ad0d34d41444..1e1df19ec164 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -393,6 +393,78 @@ out: return err; } +static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + struct virtio_vsock_pkt *pkt; + int dequeued_len = 0; + size_t user_buf_len = msg_data_left(msg); + bool copy_failed = false; + bool msg_ready = false; + + spin_lock_bh(&vvs->rx_lock); + + if (vvs->msg_count == 0) { + spin_unlock_bh(&vvs->rx_lock); + return 0; + } + + while (!msg_ready) { + pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list); + + if (!copy_failed) { + size_t pkt_len; + size_t bytes_to_copy; + + pkt_len = (size_t)le32_to_cpu(pkt->hdr.len); + bytes_to_copy = min(user_buf_len, pkt_len); + + if (bytes_to_copy) { + int err; + + /* sk_lock is held by caller so no one else can dequeue. + * Unlock rx_lock since memcpy_to_msg() may sleep. + */ + spin_unlock_bh(&vvs->rx_lock); + + err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy); + if (err) { + /* Copy of message failed, set flag to skip + * copy path for rest of fragments. Rest of + * fragments will be freed without copy. + */ + copy_failed = true; + dequeued_len = err; + } else { + user_buf_len -= bytes_to_copy; + } + + spin_lock_bh(&vvs->rx_lock); + } + + if (dequeued_len >= 0) + dequeued_len += pkt_len; + } + + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) { + msg_ready = true; + vvs->msg_count--; + } + + virtio_transport_dec_rx_pkt(vvs, pkt); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + + spin_unlock_bh(&vvs->rx_lock); + + virtio_transport_send_credit_update(vsk); + + return dequeued_len; +} + ssize_t virtio_transport_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -405,6 +477,18 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + if (flags & MSG_PEEK) + return -EOPNOTSUPP; + + return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); + int virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, -- cgit From e4b1ef152f53d5ea0cae89f12f241f7293657718 Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:12:53 +0300 Subject: virtio/vsock: add SEQPACKET receive logic Update current receive logic for SEQPACKET support: performs check for packet and socket types on receive(if mismatch, then reset connection). Increment EOR counter on receive. Also if buffer of new packet was appended to buffer of last packet in rx queue, update flags of last packet with flags of new packet. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport_common.c | 34 ++++++++++++++++++++++++++++++--- 1 file changed, 31 insertions(+), 3 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 1e1df19ec164..3a658ff8fccb 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -165,6 +165,14 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); +static u16 virtio_transport_get_type(struct sock *sk) +{ + if (sk->sk_type == SOCK_STREAM) + return VIRTIO_VSOCK_TYPE_STREAM; + else + return VIRTIO_VSOCK_TYPE_SEQPACKET; +} + /* This function can only be used on connecting/connected sockets, * since a socket assigned to a transport is required. * @@ -987,6 +995,9 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, goto out; } + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) + vvs->msg_count++; + /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small * payload. @@ -998,13 +1009,18 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, struct virtio_vsock_pkt, list); /* If there is space in the last packet queued, we copy the - * new packet in its buffer. + * new packet in its buffer. We avoid this if the last packet + * queued has VIRTIO_VSOCK_SEQ_EOR set, because this is + * delimiter of SEQPACKET record, so 'pkt' is the first packet + * of a new record. */ - if (pkt->len <= last_pkt->buf_len - last_pkt->len) { + if ((pkt->len <= last_pkt->buf_len - last_pkt->len) && + !(le32_to_cpu(last_pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)) { memcpy(last_pkt->buf + last_pkt->len, pkt->buf, pkt->len); last_pkt->len += pkt->len; free_pkt = true; + last_pkt->hdr.flags |= pkt->hdr.flags; goto out; } } @@ -1170,6 +1186,12 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, return 0; } +static bool virtio_transport_valid_type(u16 type) +{ + return (type == VIRTIO_VSOCK_TYPE_STREAM) || + (type == VIRTIO_VSOCK_TYPE_SEQPACKET); +} + /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex * lock. */ @@ -1195,7 +1217,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, le32_to_cpu(pkt->hdr.buf_alloc), le32_to_cpu(pkt->hdr.fwd_cnt)); - if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) { + if (!virtio_transport_valid_type(le16_to_cpu(pkt->hdr.type))) { (void)virtio_transport_reset_no_sock(t, pkt); goto free_pkt; } @@ -1212,6 +1234,12 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, } } + if (virtio_transport_get_type(sk) != le16_to_cpu(pkt->hdr.type)) { + (void)virtio_transport_reset_no_sock(t, pkt); + sock_put(sk); + goto free_pkt; + } + vsk = vsock_sk(sk); lock_sock(sk); -- cgit From 9ac841f5e9f261245d9d2841ad123566bd160a6e Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:13:06 +0300 Subject: virtio/vsock: rest of SOCK_SEQPACKET support Small updates to make SOCK_SEQPACKET work: 1) Send SHUTDOWN on socket close for SEQPACKET type. 2) Set SEQPACKET packet type during send. 3) Set 'VIRTIO_VSOCK_SEQ_EOR' bit in flags for last packet of message. 4) Implement data check function for SEQPACKET. 5) Check for max datagram size. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport_common.c | 41 +++++++++++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 3a658ff8fccb..23704a6bc437 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -74,6 +74,10 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; + + if (msg_data_left(info->msg) == 0 && + info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) + pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); } trace_virtio_transport_alloc_pkt(src_cid, src_port, @@ -187,7 +191,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; - info->type = VIRTIO_VSOCK_TYPE_STREAM; + info->type = virtio_transport_get_type(sk_vsock(vsk)); t_ops = virtio_transport_get_ops(vsk); if (unlikely(!t_ops)) @@ -497,6 +501,26 @@ virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + spin_lock_bh(&vvs->tx_lock); + + if (len > vvs->peer_buf_alloc) { + spin_unlock_bh(&vvs->tx_lock); + return -EMSGSIZE; + } + + spin_unlock_bh(&vvs->tx_lock); + + return virtio_transport_stream_enqueue(vsk, msg, len); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue); + int virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -519,6 +543,19 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + u32 msg_count; + + spin_lock_bh(&vvs->rx_lock); + msg_count = vvs->msg_count; + spin_unlock_bh(&vvs->rx_lock); + + return msg_count; +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data); + static s64 virtio_transport_has_space(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; @@ -931,7 +968,7 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - if (sk->sk_type == SOCK_STREAM) + if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) remove_sock = virtio_transport_close(vsk); if (remove_sock) { -- cgit From 53efbba12cc7ea2aa47d888532fdc1b3b43afef0 Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:13:22 +0300 Subject: virtio/vsock: enable SEQPACKET for transport To make transport work with SOCK_SEQPACKET add two things: 1) SOCK_SEQPACKET ops for virtio transport and 'seqpacket_allow()' callback. 2) Handling of SEQPACKET bit: guest tries to negotiate it with vhost, so feature will be enabled only if bit is negotiated with device. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 2700a63ab095..e73ce652bf3c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -62,6 +62,7 @@ struct virtio_vsock { struct virtio_vsock_event event_list[8]; u32 guest_cid; + bool seqpacket_allow; }; static u32 virtio_transport_get_local_cid(void) @@ -443,6 +444,8 @@ static void virtio_vsock_rx_done(struct virtqueue *vq) queue_work(virtio_vsock_workqueue, &vsock->rx_work); } +static bool virtio_transport_seqpacket_allow(u32 remote_cid); + static struct virtio_transport virtio_transport = { .transport = { .module = THIS_MODULE, @@ -469,6 +472,11 @@ static struct virtio_transport virtio_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = virtio_transport_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -485,6 +493,19 @@ static struct virtio_transport virtio_transport = { .send_pkt = virtio_transport_send_pkt, }; +static bool virtio_transport_seqpacket_allow(u32 remote_cid) +{ + struct virtio_vsock *vsock; + bool seqpacket_allow; + + rcu_read_lock(); + vsock = rcu_dereference(the_virtio_vsock); + seqpacket_allow = vsock->seqpacket_allow; + rcu_read_unlock(); + + return seqpacket_allow; +} + static void virtio_transport_rx_work(struct work_struct *work) { struct virtio_vsock *vsock = @@ -608,10 +629,14 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->event_run = true; mutex_unlock(&vsock->event_lock); + if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET)) + vsock->seqpacket_allow = true; + vdev->priv = vsock; rcu_assign_pointer(the_virtio_vsock, vsock); mutex_unlock(&the_virtio_vsock_mutex); + return 0; out: @@ -695,6 +720,7 @@ static struct virtio_device_id id_table[] = { }; static unsigned int features[] = { + VIRTIO_VSOCK_F_SEQPACKET }; static struct virtio_driver virtio_vsock_driver = { -- cgit From 6e90a57795aa6ab2ab65fd6ac76ee0b245e5988a Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:13:50 +0300 Subject: vsock/loopback: enable SEQPACKET for transport Add SEQPACKET ops for loopback transport and 'seqpacket_allow()' callback. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- net/vmw_vsock/vsock_loopback.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index a45f7ffca8c5..169a8cf65b39 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -63,6 +63,8 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk) return 0; } +static bool vsock_loopback_seqpacket_allow(u32 remote_cid); + static struct virtio_transport loopback_transport = { .transport = { .module = THIS_MODULE, @@ -89,6 +91,11 @@ static struct virtio_transport loopback_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = vsock_loopback_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -105,6 +112,11 @@ static struct virtio_transport loopback_transport = { .send_pkt = vsock_loopback_send_pkt, }; +static bool vsock_loopback_seqpacket_allow(u32 remote_cid) +{ + return true; +} + static void vsock_loopback_work(struct work_struct *work) { struct vsock_loopback *vsock = -- cgit From cc97141afd768d36eaef1b3e1afea2a74da7df27 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 18 Jun 2021 15:35:24 +0200 Subject: vsock: rename vsock_has_data() vsock_has_data() is used only by STREAM and SEQPACKET sockets, so let's rename it to vsock_connectible_has_data(), using the same nomenclature (connectible) used in other functions after the introduction of SEQPACKET. Signed-off-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 67954afef4e1..de8249483081 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -860,7 +860,7 @@ s64 vsock_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(vsock_stream_has_data); -static s64 vsock_has_data(struct vsock_sock *vsk) +static s64 vsock_connectible_has_data(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); @@ -1880,7 +1880,7 @@ static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait, err = 0; transport = vsk->transport; - while ((data = vsock_has_data(vsk)) == 0) { + while ((data = vsock_connectible_has_data(vsk)) == 0) { prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); if (sk->sk_err != 0 || -- cgit From 0de5b2e67275695d6ad7369c594feb1578f891fd Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 18 Jun 2021 15:35:25 +0200 Subject: vsock: rename vsock_wait_data() vsock_wait_data() is used only by STREAM and SEQPACKET sockets, so let's rename it to vsock_connectible_wait_data(), using the same nomenclature (connectible) used in other functions after the introduction of SEQPACKET. Signed-off-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index de8249483081..21ccf450e249 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1866,10 +1866,11 @@ out: return err; } -static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait, - long timeout, - struct vsock_transport_recv_notify_data *recv_data, - size_t target) +static int vsock_connectible_wait_data(struct sock *sk, + struct wait_queue_entry *wait, + long timeout, + struct vsock_transport_recv_notify_data *recv_data, + size_t target) { const struct vsock_transport *transport; struct vsock_sock *vsk; @@ -1967,7 +1968,8 @@ static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg, while (1) { ssize_t read; - err = vsock_wait_data(sk, &wait, timeout, &recv_data, target); + err = vsock_connectible_wait_data(sk, &wait, timeout, + &recv_data, target); if (err <= 0) break; @@ -2022,7 +2024,7 @@ static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - err = vsock_wait_data(sk, &wait, timeout, NULL, 0); + err = vsock_connectible_wait_data(sk, &wait, timeout, NULL, 0); if (err <= 0) goto out; -- cgit From 91aa49a8fa0ffa66966be275b2575009cc12fd3b Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 18 Jun 2021 15:35:26 +0200 Subject: vsock/virtio: remove redundant `copy_failed` variable When memcpy_to_msg() fails in virtio_transport_seqpacket_do_dequeue(), we already set `dequeued_len` with the negative error value returned by memcpy_to_msg(). So we can directly check `dequeued_len` value instead of using a dedicated flag variable to skip the copy path for the rest of fragments. Signed-off-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport_common.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 23704a6bc437..f014ccfdd9c2 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -413,7 +413,6 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt; int dequeued_len = 0; size_t user_buf_len = msg_data_left(msg); - bool copy_failed = false; bool msg_ready = false; spin_lock_bh(&vvs->rx_lock); @@ -426,7 +425,7 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, while (!msg_ready) { pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list); - if (!copy_failed) { + if (dequeued_len >= 0) { size_t pkt_len; size_t bytes_to_copy; @@ -443,11 +442,9 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy); if (err) { - /* Copy of message failed, set flag to skip - * copy path for rest of fragments. Rest of + /* Copy of message failed. Rest of * fragments will be freed without copy. */ - copy_failed = true; dequeued_len = err; } else { user_buf_len -= bytes_to_copy; -- cgit From c7ff9cff70601ea19245d997bb977344663434c7 Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Mon, 21 Jun 2021 14:26:01 +0800 Subject: vsock: notify server to shutdown when client has pending signal The client's sk_state will be set to TCP_ESTABLISHED if the server replay the client's connect request. However, if the client has pending signal, its sk_state will be set to TCP_CLOSE without notify the server, so the server will hold the corrupt connection. client server 1. sk_state=TCP_SYN_SENT | 2. call ->connect() | 3. wait reply | | 4. sk_state=TCP_ESTABLISHED | 5. insert to connected list | 6. reply to the client 7. sk_state=TCP_ESTABLISHED | 8. insert to connected list | 9. *signal pending* <--------------------- the user kill client 10. sk_state=TCP_CLOSE | client is exiting... | 11. call ->release() | virtio_transport_close if (!(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_CLOSING)) return true; *return at here, the server cannot notice the connection is corrupt* So the client should notify the peer in this case. Cc: David S. Miller Cc: Jakub Kicinski Cc: Jorgen Hansen Cc: Norbert Slusarek Cc: Andra Paraschiv Cc: Colin Ian King Cc: David Brazdil Cc: Alexander Popov Suggested-by: Stefano Garzarella Link: https://lkml.org/lkml/2021/5/17/418 Signed-off-by: lixianming Signed-off-by: Longpeng(Mike) Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 92a72f0e0d94..ae11311807fd 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1369,7 +1369,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (signal_pending(current)) { err = sock_intr_errno(timeout); - sk->sk_state = TCP_CLOSE; + sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; -- cgit From 64295f0d01ae0661a2cea42c598070b1c87ca6e0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 21 Jun 2021 07:53:48 -0700 Subject: virtio/vsock: avoid NULL deref in virtio_transport_seqpacket_allow() Make sure the_virtio_vsock is not NULL before dereferencing it. general protection fault, probably for non-canonical address 0xdffffc0000000071: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000388-0x000000000000038f] CPU: 0 PID: 8452 Comm: syz-executor406 Not tainted 5.13.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:virtio_transport_seqpacket_allow+0xbf/0x210 net/vmw_vsock/virtio_transport.c:503 Code: e8 c6 d9 ab f8 84 db 0f 84 0f 01 00 00 e8 09 d3 ab f8 48 8d bd 88 03 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 06 0f 8e 2a 01 00 00 44 0f b6 a5 88 03 00 00 RSP: 0018:ffffc90003757c18 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: 0000000000000071 RSI: ffffffff88c908e7 RDI: 0000000000000388 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff88c90a06 R11: 0000000000000000 R12: 0000000000000000 R13: ffffffff88c90840 R14: 0000000000000000 R15: 0000000000000001 FS: 0000000001bee300(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000082 CR3: 000000002847e000 CR4: 00000000001506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: vsock_assign_transport+0x575/0x700 net/vmw_vsock/af_vsock.c:490 vsock_connect+0x200/0xc00 net/vmw_vsock/af_vsock.c:1337 __sys_connect_file+0x155/0x1a0 net/socket.c:1824 __sys_connect+0x161/0x190 net/socket.c:1841 __do_sys_connect net/socket.c:1851 [inline] __se_sys_connect net/socket.c:1848 [inline] __x64_sys_connect+0x6f/0xb0 net/socket.c:1848 do_syscall_64+0x3a/0xb0 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x43ee69 Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd49e7c788 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000400488 RCX: 000000000043ee69 RDX: 0000000000000010 RSI: 0000000020000080 RDI: 0000000000000003 RBP: 0000000000402e50 R08: 0000000000000000 R09: 0000000000400488 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000402ee0 R13: 0000000000000000 R14: 00000000004ac018 R15: 0000000000400488 Fixes: 53efbba12cc7 ("virtio/vsock: enable SEQPACKET for transport") Signed-off-by: Eric Dumazet Cc: Arseny Krasnov Reported-by: syzbot Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index e73ce652bf3c..ed1664e7bd88 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -498,9 +498,11 @@ static bool virtio_transport_seqpacket_allow(u32 remote_cid) struct virtio_vsock *vsock; bool seqpacket_allow; + seqpacket_allow = false; rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); - seqpacket_allow = vsock->seqpacket_allow; + if (vsock) + seqpacket_allow = vsock->seqpacket_allow; rcu_read_unlock(); return seqpacket_allow; -- cgit From e3ae2365efc14269170a6326477e669332271ab3 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Sun, 27 Jun 2021 18:48:21 -0400 Subject: net: sock: introduce sk_error_report This patch introduces a function wrapper to call the sk_error_report callback. That will prepare to add additional handling whenever sk_error_report is called, for example to trace socket errors. Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 2 +- net/vmw_vsock/virtio_transport.c | 2 +- net/vmw_vsock/virtio_transport_common.c | 2 +- net/vmw_vsock/vmci_transport.c | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 21ccf450e249..9f12da1ff406 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1281,7 +1281,7 @@ static void vsock_connect_timeout(struct work_struct *work) (sk->sk_shutdown != SHUTDOWN_MASK)) { sk->sk_state = TCP_CLOSE; sk->sk_err = ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); vsock_transport_cancel_pkt(vsk); } release_sock(sk); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index ed1664e7bd88..e0c2c992ad9c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -360,7 +360,7 @@ static void virtio_vsock_reset_sock(struct sock *sk) lock_sock(sk); sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); release_sock(sk); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index f014ccfdd9c2..169ba8b72a63 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1007,7 +1007,7 @@ destroy: virtio_transport_reset(vsk, pkt); sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; - sk->sk_error_report(sk); + sk_error_report(sk); return err; } diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index e617ed93f06b..7aef34e32bdf 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -831,7 +831,7 @@ static void vmci_transport_handle_detach(struct sock *sk) sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); return; } sk->sk_state = TCP_CLOSE; @@ -1365,7 +1365,7 @@ destroy: sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; - sk->sk_error_report(sk); + sk_error_report(sk); return err; } -- cgit