From 85c675d0d09a45a135bddd15d7b385f8758c32fb Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 18 May 2024 19:35:05 +0200 Subject: Adding upstream version 6.7.7. Signed-off-by: Daniel Baumann --- net/vmw_vsock/af_vsock.c | 60 ++++++- net/vmw_vsock/diag.c | 1 + net/vmw_vsock/virtio_transport.c | 99 ++++++++++- net/vmw_vsock/virtio_transport_common.c | 306 ++++++++++++++++++++++++-------- net/vmw_vsock/vsock_loopback.c | 6 + 5 files changed, 392 insertions(+), 80 deletions(-) (limited to 'net/vmw_vsock') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4afb6a541c..54ba7316f8 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1032,7 +1032,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, poll_wait(file, sk_sleep(sk), wait); mask = 0; - if (sk->sk_err) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) /* Signify that there has been an error on this socket. */ mask |= EPOLLERR; @@ -1406,6 +1406,17 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, goto out; } + if (vsock_msgzerocopy_allow(transport)) { + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + } else if (sock_flag(sk, SOCK_ZEROCOPY)) { + /* If this option was set before 'connect()', + * when transport was unknown, check that this + * feature is supported here. + */ + err = -EOPNOTSUPP; + goto out; + } + err = vsock_auto_bind(vsk); if (err) goto out; @@ -1560,6 +1571,9 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, } else { newsock->state = SS_CONNECTED; sock_graft(connected, newsock); + if (vsock_msgzerocopy_allow(vconnected->transport)) + set_bit(SOCK_SUPPORT_ZC, + &connected->sk_socket->flags); } release_sock(connected); @@ -1637,7 +1651,7 @@ static int vsock_connectible_setsockopt(struct socket *sock, const struct vsock_transport *transport; u64 val; - if (level != AF_VSOCK) + if (level != AF_VSOCK && level != SOL_SOCKET) return -ENOPROTOOPT; #define COPY_IN(_v) \ @@ -1660,6 +1674,33 @@ static int vsock_connectible_setsockopt(struct socket *sock, transport = vsk->transport; + if (level == SOL_SOCKET) { + int zerocopy; + + if (optname != SO_ZEROCOPY) { + release_sock(sk); + return sock_setsockopt(sock, level, optname, optval, optlen); + } + + /* Use 'int' type here, because variable to + * set this option usually has this type. + */ + COPY_IN(zerocopy); + + if (zerocopy < 0 || zerocopy > 1) { + err = -EINVAL; + goto exit; + } + + if (transport && !vsock_msgzerocopy_allow(transport)) { + err = -EOPNOTSUPP; + goto exit; + } + + sock_valbool_flag(sk, SOCK_ZEROCOPY, zerocopy); + goto exit; + } + switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: COPY_IN(val); @@ -1824,6 +1865,12 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, goto out; } + if (msg->msg_flags & MSG_ZEROCOPY && + !vsock_msgzerocopy_allow(transport)) { + err = -EOPNOTSUPP; + goto out; + } + /* Wait for room in the produce queue to enqueue our user's data. */ timeout = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); @@ -1923,6 +1970,9 @@ out_err: err = total_written; } out: + if (sk->sk_type == SOCK_STREAM) + err = sk_stream_error(sk, msg->msg_flags, err); + release_sock(sk); return err; } @@ -2312,6 +2362,12 @@ static int vsock_create(struct net *net, struct socket *sock, } } + /* SOCK_DGRAM doesn't have 'setsockopt' callback set in its + * proto_ops, so there is no handler for custom logic. + */ + if (sock_type_connectible(sock->type)) + set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); + vsock_insert_unbound(vsk); return 0; diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c index a2823b1c5e..2e29994f92 100644 --- a/net/vmw_vsock/diag.c +++ b/net/vmw_vsock/diag.c @@ -174,5 +174,6 @@ static void __exit vsock_diag_exit(void) module_init(vsock_diag_init); module_exit(vsock_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("VMware Virtual Sockets monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 40 /* AF_VSOCK */); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index a64bf601b4..f495b9e518 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -63,6 +63,17 @@ struct virtio_vsock { u32 guest_cid; bool seqpacket_allow; + + /* These fields are used only in tx path in function + * 'virtio_transport_send_pkt_work()', so to save + * stack space in it, place both of them here. Each + * pointer from 'out_sgs' points to the corresponding + * element in 'out_bufs' - this is initialized in + * 'virtio_vsock_probe()'. Both fields are protected + * by 'tx_lock'. +1 is needed for packet header. + */ + struct scatterlist *out_sgs[MAX_SKB_FRAGS + 1]; + struct scatterlist out_bufs[MAX_SKB_FRAGS + 1]; }; static u32 virtio_transport_get_local_cid(void) @@ -100,8 +111,8 @@ virtio_transport_send_pkt_work(struct work_struct *work) vq = vsock->vqs[VSOCK_VQ_TX]; for (;;) { - struct scatterlist hdr, buf, *sgs[2]; int ret, in_sg = 0, out_sg = 0; + struct scatterlist **sgs; struct sk_buff *skb; bool reply; @@ -111,12 +122,43 @@ virtio_transport_send_pkt_work(struct work_struct *work) virtio_transport_deliver_tap_pkt(skb); reply = virtio_vsock_skb_reply(skb); - - sg_init_one(&hdr, virtio_vsock_hdr(skb), sizeof(*virtio_vsock_hdr(skb))); - sgs[out_sg++] = &hdr; - if (skb->len > 0) { - sg_init_one(&buf, skb->data, skb->len); - sgs[out_sg++] = &buf; + sgs = vsock->out_sgs; + sg_init_one(sgs[out_sg], virtio_vsock_hdr(skb), + sizeof(*virtio_vsock_hdr(skb))); + out_sg++; + + if (!skb_is_nonlinear(skb)) { + if (skb->len > 0) { + sg_init_one(sgs[out_sg], skb->data, skb->len); + out_sg++; + } + } else { + struct skb_shared_info *si; + int i; + + /* If skb is nonlinear, then its buffer must contain + * only header and nothing more. Data is stored in + * the fragged part. + */ + WARN_ON_ONCE(skb_headroom(skb) != sizeof(*virtio_vsock_hdr(skb))); + + si = skb_shinfo(skb); + + for (i = 0; i < si->nr_frags; i++) { + skb_frag_t *skb_frag = &si->frags[i]; + void *va; + + /* We will use 'page_to_virt()' for the userspace page + * here, because virtio or dma-mapping layers will call + * 'virt_to_phys()' later to fill the buffer descriptor. + * We don't touch memory at "virtual" address of this page. + */ + va = page_to_virt(skb_frag->bv_page); + sg_init_one(sgs[out_sg], + va + skb_frag->bv_offset, + skb_frag->bv_len); + out_sg++; + } } ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, GFP_KERNEL); @@ -413,6 +455,42 @@ static void virtio_vsock_rx_done(struct virtqueue *vq) queue_work(virtio_vsock_workqueue, &vsock->rx_work); } +static bool virtio_transport_can_msgzerocopy(int bufs_num) +{ + struct virtio_vsock *vsock; + bool res = false; + + rcu_read_lock(); + + vsock = rcu_dereference(the_virtio_vsock); + if (vsock) { + struct virtqueue *vq = vsock->vqs[VSOCK_VQ_TX]; + + /* Check that tx queue is large enough to keep whole + * data to send. This is needed, because when there is + * not enough free space in the queue, current skb to + * send will be reinserted to the head of tx list of + * the socket to retry transmission later, so if skb + * is bigger than whole queue, it will be reinserted + * again and again, thus blocking other skbs to be sent. + * Each page of the user provided buffer will be added + * as a single buffer to the tx virtqueue, so compare + * number of pages against maximum capacity of the queue. + */ + if (bufs_num <= vq->num_max) + res = true; + } + + rcu_read_unlock(); + + return res; +} + +static bool virtio_transport_msgzerocopy_allow(void) +{ + return true; +} + static bool virtio_transport_seqpacket_allow(u32 remote_cid); static struct virtio_transport virtio_transport = { @@ -446,6 +524,8 @@ static struct virtio_transport virtio_transport = { .seqpacket_allow = virtio_transport_seqpacket_allow, .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .msgzerocopy_allow = virtio_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, @@ -463,6 +543,7 @@ static struct virtio_transport virtio_transport = { }, .send_pkt = virtio_transport_send_pkt, + .can_msgzerocopy = virtio_transport_can_msgzerocopy, }; static bool virtio_transport_seqpacket_allow(u32 remote_cid) @@ -636,6 +717,7 @@ static int virtio_vsock_probe(struct virtio_device *vdev) { struct virtio_vsock *vsock = NULL; int ret; + int i; ret = mutex_lock_interruptible(&the_virtio_vsock_mutex); if (ret) @@ -678,6 +760,9 @@ static int virtio_vsock_probe(struct virtio_device *vdev) if (ret < 0) goto out; + for (i = 0; i < ARRAY_SIZE(vsock->out_sgs); i++) + vsock->out_sgs[i] = &vsock->out_bufs[i]; + rcu_assign_pointer(the_virtio_vsock, vsock); virtio_vsock_vqs_start(vsock); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e87fd9480a..16ff976a86 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -37,27 +37,88 @@ virtio_transport_get_ops(struct vsock_sock *vsk) return container_of(t, struct virtio_transport, transport); } -/* Returns a new packet on success, otherwise returns NULL. - * - * If NULL is returned, errp is set to a negative errno. - */ -static struct sk_buff * -virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info, - size_t len, - u32 src_cid, - u32 src_port, - u32 dst_cid, - u32 dst_port) -{ - const size_t skb_len = VIRTIO_VSOCK_SKB_HEADROOM + len; - struct virtio_vsock_hdr *hdr; - struct sk_buff *skb; - void *payload; - int err; +static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops, + struct virtio_vsock_pkt_info *info, + size_t pkt_len) +{ + struct iov_iter *iov_iter; - skb = virtio_vsock_alloc_skb(skb_len, GFP_KERNEL); - if (!skb) - return NULL; + if (!info->msg) + return false; + + iov_iter = &info->msg->msg_iter; + + if (iov_iter->iov_offset) + return false; + + /* We can't send whole iov. */ + if (iov_iter->count > pkt_len) + return false; + + /* Check that transport can send data in zerocopy mode. */ + t_ops = virtio_transport_get_ops(info->vsk); + + if (t_ops->can_msgzerocopy) { + int pages_to_send = iov_iter_npages(iov_iter, MAX_SKB_FRAGS); + + /* +1 is for packet header. */ + return t_ops->can_msgzerocopy(pages_to_send + 1); + } + + return true; +} + +static int virtio_transport_init_zcopy_skb(struct vsock_sock *vsk, + struct sk_buff *skb, + struct msghdr *msg, + bool zerocopy) +{ + struct ubuf_info *uarg; + + if (msg->msg_ubuf) { + uarg = msg->msg_ubuf; + net_zcopy_get(uarg); + } else { + struct iov_iter *iter = &msg->msg_iter; + struct ubuf_info_msgzc *uarg_zc; + + uarg = msg_zerocopy_realloc(sk_vsock(vsk), + iter->count, + NULL); + if (!uarg) + return -1; + + uarg_zc = uarg_to_msgzc(uarg); + uarg_zc->zerocopy = zerocopy ? 1 : 0; + } + + skb_zcopy_init(skb, uarg); + + return 0; +} + +static int virtio_transport_fill_skb(struct sk_buff *skb, + struct virtio_vsock_pkt_info *info, + size_t len, + bool zcopy) +{ + if (zcopy) + return __zerocopy_sg_from_iter(info->msg, NULL, skb, + &info->msg->msg_iter, + len); + + return memcpy_from_msg(skb_put(skb, len), info->msg, len); +} + +static void virtio_transport_init_hdr(struct sk_buff *skb, + struct virtio_vsock_pkt_info *info, + size_t payload_len, + u32 src_cid, + u32 src_port, + u32 dst_cid, + u32 dst_port) +{ + struct virtio_vsock_hdr *hdr; hdr = virtio_vsock_hdr(skb); hdr->type = cpu_to_le16(info->type); @@ -67,45 +128,30 @@ virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info, hdr->src_port = cpu_to_le32(src_port); hdr->dst_port = cpu_to_le32(dst_port); hdr->flags = cpu_to_le32(info->flags); - hdr->len = cpu_to_le32(len); + hdr->len = cpu_to_le32(payload_len); hdr->buf_alloc = cpu_to_le32(0); hdr->fwd_cnt = cpu_to_le32(0); +} - if (info->msg && len > 0) { - payload = skb_put(skb, len); - err = memcpy_from_msg(payload, info->msg, len); - if (err) - goto out; - - if (msg_data_left(info->msg) == 0 && - info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) { - hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); - - if (info->msg->msg_flags & MSG_EOR) - hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); - } - } - - if (info->reply) - virtio_vsock_skb_set_reply(skb); +static void virtio_transport_copy_nonlinear_skb(const struct sk_buff *skb, + void *dst, + size_t len) +{ + struct iov_iter iov_iter = { 0 }; + struct kvec kvec; + size_t to_copy; - trace_virtio_transport_alloc_pkt(src_cid, src_port, - dst_cid, dst_port, - len, - info->type, - info->op, - info->flags); + kvec.iov_base = dst; + kvec.iov_len = len; - if (info->vsk && !skb_set_owner_sk_safe(skb, sk_vsock(info->vsk))) { - WARN_ONCE(1, "failed to allocate skb on vsock socket with sk_refcnt == 0\n"); - goto out; - } + iov_iter.iter_type = ITER_KVEC; + iov_iter.kvec = &kvec; + iov_iter.nr_segs = 1; - return skb; + to_copy = min_t(size_t, len, skb->len); -out: - kfree_skb(skb); - return NULL; + skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset, + &iov_iter, to_copy); } /* Packet capture */ @@ -116,7 +162,6 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) struct af_vsockmon_hdr *hdr; struct sk_buff *skb; size_t payload_len; - void *payload_buf; /* A packet could be split to fit the RX buffer, so we can retrieve * the payload length from the header and the buffer pointer taking @@ -124,7 +169,6 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) */ pkt_hdr = virtio_vsock_hdr(pkt); payload_len = pkt->len; - payload_buf = pkt->data; skb = alloc_skb(sizeof(*hdr) + sizeof(*pkt_hdr) + payload_len, GFP_ATOMIC); @@ -167,7 +211,13 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) skb_put_data(skb, pkt_hdr, sizeof(*pkt_hdr)); if (payload_len) { - skb_put_data(skb, payload_buf, payload_len); + if (skb_is_nonlinear(pkt)) { + void *data = skb_put(skb, payload_len); + + virtio_transport_copy_nonlinear_skb(pkt, data, payload_len); + } else { + skb_put_data(skb, pkt->data, payload_len); + } } return skb; @@ -191,6 +241,82 @@ static u16 virtio_transport_get_type(struct sock *sk) return VIRTIO_VSOCK_TYPE_SEQPACKET; } +/* Returns new sk_buff on success, otherwise returns NULL. */ +static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info, + size_t payload_len, + bool zcopy, + u32 src_cid, + u32 src_port, + u32 dst_cid, + u32 dst_port) +{ + struct vsock_sock *vsk; + struct sk_buff *skb; + size_t skb_len; + + skb_len = VIRTIO_VSOCK_SKB_HEADROOM; + + if (!zcopy) + skb_len += payload_len; + + skb = virtio_vsock_alloc_skb(skb_len, GFP_KERNEL); + if (!skb) + return NULL; + + virtio_transport_init_hdr(skb, info, payload_len, src_cid, src_port, + dst_cid, dst_port); + + vsk = info->vsk; + + /* If 'vsk' != NULL then payload is always present, so we + * will never call '__zerocopy_sg_from_iter()' below without + * setting skb owner in 'skb_set_owner_w()'. The only case + * when 'vsk' == NULL is VIRTIO_VSOCK_OP_RST control message + * without payload. + */ + WARN_ON_ONCE(!(vsk && (info->msg && payload_len)) && zcopy); + + /* Set owner here, because '__zerocopy_sg_from_iter()' uses + * owner of skb without check to update 'sk_wmem_alloc'. + */ + if (vsk) + skb_set_owner_w(skb, sk_vsock(vsk)); + + if (info->msg && payload_len > 0) { + int err; + + err = virtio_transport_fill_skb(skb, info, payload_len, zcopy); + if (err) + goto out; + + if (msg_data_left(info->msg) == 0 && + info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); + + hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); + + if (info->msg->msg_flags & MSG_EOR) + hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); + } + } + + if (info->reply) + virtio_vsock_skb_set_reply(skb); + + trace_virtio_transport_alloc_pkt(src_cid, src_port, + dst_cid, dst_port, + payload_len, + info->type, + info->op, + info->flags, + zcopy); + + return skb; +out: + kfree_skb(skb); + return NULL; +} + /* This function can only be used on connecting/connected sockets, * since a socket assigned to a transport is required. * @@ -199,10 +325,12 @@ static u16 virtio_transport_get_type(struct sock *sk) static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt_info *info) { + u32 max_skb_len = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE; u32 src_cid, src_port, dst_cid, dst_port; const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; u32 pkt_len = info->pkt_len; + bool can_zcopy = false; u32 rest_len; int ret; @@ -231,15 +359,30 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW) return pkt_len; + if (info->msg) { + /* If zerocopy is not enabled by 'setsockopt()', we behave as + * there is no MSG_ZEROCOPY flag set. + */ + if (!sock_flag(sk_vsock(vsk), SOCK_ZEROCOPY)) + info->msg->msg_flags &= ~MSG_ZEROCOPY; + + if (info->msg->msg_flags & MSG_ZEROCOPY) + can_zcopy = virtio_transport_can_zcopy(t_ops, info, pkt_len); + + if (can_zcopy) + max_skb_len = min_t(u32, VIRTIO_VSOCK_MAX_PKT_BUF_SIZE, + (MAX_SKB_FRAGS * PAGE_SIZE)); + } + rest_len = pkt_len; do { struct sk_buff *skb; size_t skb_len; - skb_len = min_t(u32, VIRTIO_VSOCK_MAX_PKT_BUF_SIZE, rest_len); + skb_len = min(max_skb_len, rest_len); - skb = virtio_transport_alloc_skb(info, skb_len, + skb = virtio_transport_alloc_skb(info, skb_len, can_zcopy, src_cid, src_port, dst_cid, dst_port); if (!skb) { @@ -247,6 +390,21 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, break; } + /* We process buffer part by part, allocating skb on + * each iteration. If this is last skb for this buffer + * and MSG_ZEROCOPY mode is in use - we must allocate + * completion for the current syscall. + */ + if (info->msg && info->msg->msg_flags & MSG_ZEROCOPY && + skb_len == rest_len && info->op == VIRTIO_VSOCK_OP_RW) { + if (virtio_transport_init_zcopy_skb(vsk, skb, + info->msg, + can_zcopy)) { + ret = -ENOMEM; + break; + } + } + virtio_transport_inc_tx_pkt(vvs, skb); ret = t_ops->send_pkt(skb); @@ -366,9 +524,10 @@ virtio_transport_stream_do_peek(struct vsock_sock *vsk, spin_unlock_bh(&vvs->rx_lock); /* sk_lock is held by caller so no one else can dequeue. - * Unlock rx_lock since memcpy_to_msg() may sleep. + * Unlock rx_lock since skb_copy_datagram_iter() may sleep. */ - err = memcpy_to_msg(msg, skb->data, bytes); + err = skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset, + &msg->msg_iter, bytes); if (err) goto out; @@ -414,25 +573,27 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, while (total < len && !skb_queue_empty(&vvs->rx_queue)) { skb = skb_peek(&vvs->rx_queue); - bytes = len - total; - if (bytes > skb->len) - bytes = skb->len; + bytes = min_t(size_t, len - total, + skb->len - VIRTIO_VSOCK_SKB_CB(skb)->offset); /* sk_lock is held by caller so no one else can dequeue. - * Unlock rx_lock since memcpy_to_msg() may sleep. + * Unlock rx_lock since skb_copy_datagram_iter() may sleep. */ spin_unlock_bh(&vvs->rx_lock); - err = memcpy_to_msg(msg, skb->data, bytes); + err = skb_copy_datagram_iter(skb, + VIRTIO_VSOCK_SKB_CB(skb)->offset, + &msg->msg_iter, bytes); if (err) goto out; spin_lock_bh(&vvs->rx_lock); total += bytes; - skb_pull(skb, bytes); - if (skb->len == 0) { + VIRTIO_VSOCK_SKB_CB(skb)->offset += bytes; + + if (skb->len == VIRTIO_VSOCK_SKB_CB(skb)->offset) { u32 pkt_len = le32_to_cpu(virtio_vsock_hdr(skb)->len); virtio_transport_dec_rx_pkt(vvs, pkt_len); @@ -501,9 +662,10 @@ virtio_transport_seqpacket_do_peek(struct vsock_sock *vsk, spin_unlock_bh(&vvs->rx_lock); /* sk_lock is held by caller so no one else can dequeue. - * Unlock rx_lock since memcpy_to_msg() may sleep. + * Unlock rx_lock since skb_copy_datagram_iter() may sleep. */ - err = memcpy_to_msg(msg, skb->data, bytes); + err = skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset, + &msg->msg_iter, bytes); if (err) return err; @@ -562,11 +724,13 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, int err; /* sk_lock is held by caller so no one else can dequeue. - * Unlock rx_lock since memcpy_to_msg() may sleep. + * Unlock rx_lock since skb_copy_datagram_iter() may sleep. */ spin_unlock_bh(&vvs->rx_lock); - err = memcpy_to_msg(msg, skb->data, bytes_to_copy); + err = skb_copy_datagram_iter(skb, 0, + &msg->msg_iter, + bytes_to_copy); if (err) { /* Copy of message failed. Rest of * fragments will be freed without copy. @@ -963,7 +1127,7 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t, if (!t) return -ENOTCONN; - reply = virtio_transport_alloc_skb(&info, 0, + reply = virtio_transport_alloc_skb(&info, 0, false, le64_to_cpu(hdr->dst_cid), le32_to_cpu(hdr->dst_port), le64_to_cpu(hdr->src_cid), diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 0ce65d0a4a..6dea6119f5 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -47,6 +47,10 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk) } static bool vsock_loopback_seqpacket_allow(u32 remote_cid); +static bool vsock_loopback_msgzerocopy_allow(void) +{ + return true; +} static struct virtio_transport loopback_transport = { .transport = { @@ -79,6 +83,8 @@ static struct virtio_transport loopback_transport = { .seqpacket_allow = vsock_loopback_seqpacket_allow, .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .msgzerocopy_allow = vsock_loopback_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, -- cgit v1.2.3