diff options
Diffstat (limited to 'drivers/vhost/net.c')
| -rw-r--r-- | drivers/vhost/net.c | 596 |
1 files changed, 325 insertions, 271 deletions
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index bca86bf7189f..7f886d3dba7d 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1,8 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2009 Red Hat, Inc. * Author: Michael S. Tsirkin <mst@redhat.com> * - * This work is licensed under the terms of the GNU GPL, version 2. - * * virtio-net server in host kernel. */ @@ -36,7 +35,7 @@ #include "vhost.h" -static int experimental_zcopytx = 1; +static int experimental_zcopytx = 0; module_param(experimental_zcopytx, int, 0444); MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" " 1 -Enable; 0 - Disable"); @@ -70,11 +69,15 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" #define VHOST_DMA_IS_DONE(len) ((__force u32)(len) >= (__force u32)VHOST_DMA_DONE_LEN) -enum { - VHOST_NET_FEATURES = VHOST_FEATURES | - (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) | - (1ULL << VIRTIO_NET_F_MRG_RXBUF) | - (1ULL << VIRTIO_F_IOMMU_PLATFORM) +static const int vhost_net_bits[] = { + VHOST_FEATURES, + VHOST_NET_F_VIRTIO_NET_HDR, + VIRTIO_NET_F_MRG_RXBUF, + VIRTIO_F_ACCESS_PLATFORM, + VIRTIO_F_RING_RESET, + VIRTIO_F_IN_ORDER, + VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO, + VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO }; enum { @@ -96,6 +99,7 @@ struct vhost_net_ubuf_ref { atomic_t refcount; wait_queue_head_t wait; struct vhost_virtqueue *vq; + struct rcu_head rcu; }; #define VHOST_NET_BATCH 64 @@ -119,7 +123,7 @@ struct vhost_net_virtqueue { /* Number of XDP frames batched */ int batched_xdp; /* an array of userspace buffers info */ - struct ubuf_info *ubuf_info; + struct ubuf_info_msgzc *ubuf_info; /* Reference counting for outstanding ubufs. * Protected by vq mutex. Writers must also take device mutex. */ struct vhost_net_ubuf_ref *ubufs; @@ -141,10 +145,8 @@ struct vhost_net { unsigned tx_zcopy_err; /* Flush in progress. Protected by tx vq lock. */ bool tx_flush; - /* Private page frag */ - struct page_frag page_frag; - /* Refcount bias of page frag */ - int refcnt_bias; + /* Private page frag cache */ + struct page_frag_cache pf_cache; }; static unsigned vhost_net_zcopy_mask __read_mostly; @@ -249,9 +251,13 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy) static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs) { - int r = atomic_sub_return(1, &ubufs->refcount); + int r; + + rcu_read_lock(); + r = atomic_sub_return(1, &ubufs->refcount); if (unlikely(!r)) wake_up(&ubufs->wait); + rcu_read_unlock(); return r; } @@ -264,7 +270,7 @@ static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs) static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs) { vhost_net_ubuf_put_and_wait(ubufs); - kfree(ubufs); + kfree_rcu(ubufs, rcu); } static void vhost_net_clear_ubuf_info(struct vhost_net *n) @@ -376,14 +382,17 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net, while (j) { add = min(UIO_MAXIOV - nvq->done_idx, j); vhost_add_used_and_signal_n(vq->dev, vq, - &vq->heads[nvq->done_idx], add); + &vq->heads[nvq->done_idx], + NULL, add); nvq->done_idx = (nvq->done_idx + add) % UIO_MAXIOV; j -= add; } } -static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) +static void vhost_zerocopy_complete(struct sk_buff *skb, + struct ubuf_info *ubuf_base, bool success) { + struct ubuf_info_msgzc *ubuf = uarg_to_msgzc(ubuf_base); struct vhost_net_ubuf_ref *ubufs = ubuf->ctx; struct vhost_virtqueue *vq = ubufs->vq; int cnt; @@ -408,6 +417,10 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) rcu_read_unlock_bh(); } +static const struct ubuf_info_ops vhost_ubuf_ops = { + .complete = vhost_zerocopy_complete, +}; + static inline unsigned long busy_clock(void) { return local_clock() >> 10; @@ -425,7 +438,7 @@ static void vhost_net_disable_vq(struct vhost_net *n, struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); struct vhost_poll *poll = n->poll + (nvq - n->vqs); - if (!vq->private_data) + if (!vhost_vq_get_backend(vq)) return; vhost_poll_stop(poll); } @@ -438,14 +451,15 @@ static int vhost_net_enable_vq(struct vhost_net *n, struct vhost_poll *poll = n->poll + (nvq - n->vqs); struct socket *sock; - sock = vq->private_data; + sock = vhost_vq_get_backend(vq); if (!sock) return 0; return vhost_poll_start(poll, sock->file); } -static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) +static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq, + unsigned int count) { struct vhost_virtqueue *vq = &nvq->vq; struct vhost_dev *dev = vq->dev; @@ -453,7 +467,8 @@ static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) if (!nvq->done_idx) return; - vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx); + vhost_add_used_and_signal_n(dev, vq, vq->heads, + vq->nheads, count); nvq->done_idx = 0; } @@ -462,25 +477,42 @@ static void vhost_tx_batch(struct vhost_net *net, struct socket *sock, struct msghdr *msghdr) { + struct vhost_virtqueue *vq = &nvq->vq; + bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER); struct tun_msg_ctl ctl = { .type = TUN_MSG_PTR, .num = nvq->batched_xdp, .ptr = nvq->xdp, }; - int err; + int i, err; + + if (in_order) { + vq->heads[0].len = 0; + vq->nheads[0] = nvq->done_idx; + } if (nvq->batched_xdp == 0) goto signal_used; msghdr->msg_control = &ctl; + msghdr->msg_controllen = sizeof(ctl); err = sock->ops->sendmsg(sock, msghdr, 0); if (unlikely(err < 0)) { vq_err(&nvq->vq, "Fail to batch sending packets\n"); + + /* free pages owned by XDP; since this is an unlikely error path, + * keep it simple and avoid more complex bulk update for the + * used pages + */ + for (i = 0; i < nvq->batched_xdp; ++i) + put_page(virt_to_head_page(nvq->xdp[i].data)); + nvq->batched_xdp = 0; + nvq->done_idx = 0; return; } signal_used: - vhost_net_signal_used(nvq); + vhost_net_signal_used(nvq, in_order ? 1 : nvq->done_idx); nvq->batched_xdp = 0; } @@ -525,7 +557,7 @@ static void vhost_net_busy_poll(struct vhost_net *net, return; vhost_disable_notify(&net->dev, vq); - sock = rvq->private_data; + sock = vhost_vq_get_backend(rvq); busyloop_timeout = poll_rx ? rvq->busyloop_timeout: tvq->busyloop_timeout; @@ -534,7 +566,7 @@ static void vhost_net_busy_poll(struct vhost_net *net, endtime = busy_clock() + busyloop_timeout; while (vhost_can_busy_poll(endtime)) { - if (vhost_has_work(&net->dev)) { + if (vhost_vq_has_work(vq)) { *busyloop_intr = true; break; } @@ -560,24 +592,27 @@ static void vhost_net_busy_poll(struct vhost_net *net, static int vhost_net_tx_get_vq_desc(struct vhost_net *net, struct vhost_net_virtqueue *tnvq, unsigned int *out_num, unsigned int *in_num, - struct msghdr *msghdr, bool *busyloop_intr) + struct msghdr *msghdr, bool *busyloop_intr, + unsigned int *ndesc) { struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_virtqueue *rvq = &rnvq->vq; struct vhost_virtqueue *tvq = &tnvq->vq; - int r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), - out_num, in_num, NULL, NULL); + int r = vhost_get_vq_desc_n(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), + out_num, in_num, NULL, NULL, ndesc); if (r == tvq->num && tvq->busyloop_timeout) { /* Flush batched packets first */ - if (!vhost_sock_zcopy(tvq->private_data)) - vhost_tx_batch(net, tnvq, tvq->private_data, msghdr); + if (!vhost_sock_zcopy(vhost_vq_get_backend(tvq))) + vhost_tx_batch(net, tnvq, + vhost_vq_get_backend(tvq), + msghdr); vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, false); - r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), - out_num, in_num, NULL, NULL); + r = vhost_get_vq_desc_n(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), + out_num, in_num, NULL, NULL, ndesc); } return r; @@ -598,28 +633,24 @@ static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter, /* Skip header. TODO: support TSO. */ size_t len = iov_length(vq->iov, out); - iov_iter_init(iter, WRITE, vq->iov, out, len); + iov_iter_init(iter, ITER_SOURCE, vq->iov, out, len); iov_iter_advance(iter, hdr_size); return iov_iter_count(iter); } -static bool vhost_exceeds_weight(int pkts, int total_len) -{ - return total_len >= VHOST_NET_WEIGHT || - pkts >= VHOST_NET_PKT_WEIGHT; -} - static int get_tx_bufs(struct vhost_net *net, struct vhost_net_virtqueue *nvq, struct msghdr *msg, unsigned int *out, unsigned int *in, - size_t *len, bool *busyloop_intr) + size_t *len, bool *busyloop_intr, + unsigned int *ndesc) { struct vhost_virtqueue *vq = &nvq->vq; int ret; - ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); + ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, + busyloop_intr, ndesc); if (ret < 0 || ret == vq->num) return ret; @@ -647,43 +678,6 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len) !vhost_vq_avail_empty(vq->dev, vq); } -#define SKB_FRAG_PAGE_ORDER get_order(32768) - -static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz, - struct page_frag *pfrag, gfp_t gfp) -{ - if (pfrag->page) { - if (pfrag->offset + sz <= pfrag->size) - return true; - __page_frag_cache_drain(pfrag->page, net->refcnt_bias); - } - - pfrag->offset = 0; - net->refcnt_bias = 0; - if (SKB_FRAG_PAGE_ORDER) { - /* Avoid direct reclaim but allow kswapd to wake */ - pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | - __GFP_COMP | __GFP_NOWARN | - __GFP_NORETRY, - SKB_FRAG_PAGE_ORDER); - if (likely(pfrag->page)) { - pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; - goto done; - } - } - pfrag->page = alloc_page(gfp); - if (likely(pfrag->page)) { - pfrag->size = PAGE_SIZE; - goto done; - } - return false; - -done: - net->refcnt_bias = USHRT_MAX; - page_ref_add(pfrag->page, USHRT_MAX - 1); - return true; -} - #define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, @@ -692,11 +686,9 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, struct vhost_virtqueue *vq = &nvq->vq; struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); - struct socket *sock = vq->private_data; - struct page_frag *alloc_frag = &net->page_frag; + struct socket *sock = vhost_vq_get_backend(vq); struct virtio_net_hdr *gso; struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; - struct tun_xdp_hdr *hdr; size_t len = iov_iter_count(from); int headroom = vhost_sock_xdp(sock) ? XDP_PACKET_HEADROOM : 0; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -704,6 +696,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, int sock_hlen = nvq->sock_hlen; void *buf; int copied; + int ret; if (unlikely(len < nvq->sock_hlen)) return -EFAULT; @@ -713,21 +706,21 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, return -ENOSPC; buflen += SKB_DATA_ALIGN(len + pad); - alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); - if (unlikely(!vhost_net_page_frag_refill(net, buflen, - alloc_frag, GFP_KERNEL))) + buf = page_frag_alloc_align(&net->pf_cache, buflen, GFP_KERNEL, + SMP_CACHE_BYTES); + if (unlikely(!buf)) return -ENOMEM; - buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; - copied = copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + - offsetof(struct tun_xdp_hdr, gso), - sock_hlen, from); - if (copied != sock_hlen) - return -EFAULT; + copied = copy_from_iter(buf + pad - sock_hlen, len, from); + if (copied != len) { + ret = -EFAULT; + goto err; + } + + gso = buf + pad - sock_hlen; - hdr = buf; - gso = &hdr->gso; + if (!sock_hlen) + memset(buf, 0, pad); if ((gso->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && vhost16_to_cpu(vq, gso->csum_start) + @@ -737,28 +730,25 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2); - if (vhost16_to_cpu(vq, gso->hdr_len) > len) - return -EINVAL; + if (vhost16_to_cpu(vq, gso->hdr_len) > len) { + ret = -EINVAL; + goto err; + } } - len -= sock_hlen; - copied = copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + pad, - len, from); - if (copied != len) - return -EFAULT; - - xdp->data_hard_start = buf; - xdp->data = buf + pad; - xdp->data_end = xdp->data + len; - hdr->buflen = buflen; + /* pad contains sock_hlen */ + memcpy(buf, buf + pad - sock_hlen, sock_hlen); - --net->refcnt_bias; - alloc_frag->offset += buflen; + xdp_init_buff(xdp, buflen, NULL); + xdp_prepare_buff(xdp, buf, pad, len - sock_hlen, true); ++nvq->batched_xdp; return 0; + +err: + page_frag_free(buf); + return ret; } static void handle_tx_copy(struct vhost_net *net, struct socket *sock) @@ -778,20 +768,27 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) int err; int sent_pkts = 0; bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX); + bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER); + unsigned int ndesc = 0; - for (;;) { + do { bool busyloop_intr = false; if (nvq->done_idx == VHOST_NET_BATCH) vhost_tx_batch(net, nvq, sock, &msg); head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, - &busyloop_intr); + &busyloop_intr, &ndesc); /* On error, stop handling until the next kick. */ if (unlikely(head < 0)) break; /* Nothing new? Wait for eventfd to tell us they refilled. */ if (head == vq->num) { + /* Flush batched packets to handle pending RX + * work (if busyloop_intr is set) and to avoid + * unnecessary virtqueue kicks. + */ + vhost_tx_batch(net, nvq, sock, &msg); if (unlikely(busyloop_intr)) { vhost_poll_queue(&vq->poll); } else if (unlikely(vhost_enable_notify(&net->dev, @@ -813,16 +810,18 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) goto done; } else if (unlikely(err != -ENOSPC)) { vhost_tx_batch(net, nvq, sock, &msg); - vhost_discard_vq_desc(vq, 1); + vhost_discard_vq_desc(vq, 1, ndesc); vhost_net_enable_vq(net, vq); break; } - /* We can't build XDP buff, go for single - * packet path but let's flush batched - * packets. - */ - vhost_tx_batch(net, nvq, sock, &msg); + if (nvq->batched_xdp) { + /* We can't build XDP buff, go for single + * packet path but let's flush batched + * packets. + */ + vhost_tx_batch(net, nvq, sock, &msg); + } msg.msg_control = NULL; } else { if (tx_can_batch(vq, total_len)) @@ -831,25 +830,26 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) msg.msg_flags &= ~MSG_MORE; } - /* TODO: Check specific error and bomb out unless ENOBUFS? */ err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { - vhost_discard_vq_desc(vq, 1); - vhost_net_enable_vq(net, vq); - break; - } - if (err != len) + if (err == -EAGAIN || err == -ENOMEM || err == -ENOBUFS) { + vhost_discard_vq_desc(vq, 1, ndesc); + vhost_net_enable_vq(net, vq); + break; + } + pr_debug("Fail to send packet: err %d", err); + } else if (unlikely(err != len)) pr_debug("Truncated TX packet: len %d != %zd\n", err, len); done: - vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); - vq->heads[nvq->done_idx].len = 0; - ++nvq->done_idx; - if (vhost_exceeds_weight(++sent_pkts, total_len)) { - vhost_poll_queue(&vq->poll); - break; + if (in_order) { + vq->heads[0].id = cpu_to_vhost32(vq, head); + } else { + vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); + vq->heads[nvq->done_idx].len = 0; } - } + ++nvq->done_idx; + } while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len))); vhost_tx_batch(net, nvq, sock, &msg); } @@ -870,11 +870,13 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) struct tun_msg_ctl ctl; size_t len, total_len = 0; int err; - struct vhost_net_ubuf_ref *uninitialized_var(ubufs); + struct vhost_net_ubuf_ref *ubufs; + struct ubuf_info_msgzc *ubuf; + unsigned int ndesc = 0; bool zcopy_used; int sent_pkts = 0; - for (;;) { + do { bool busyloop_intr; /* Release DMAs done buffers first */ @@ -882,7 +884,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) busyloop_intr = false; head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, - &busyloop_intr); + &busyloop_intr, &ndesc); /* On error, stop handling until the next kick. */ if (unlikely(head < 0)) break; @@ -903,18 +905,17 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) /* use msg_control to pass vhost zerocopy ubuf info to skb */ if (zcopy_used) { - struct ubuf_info *ubuf; ubuf = nvq->ubuf_info + nvq->upend_idx; - vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head); vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS; - ubuf->callback = vhost_zerocopy_callback; ubuf->ctx = nvq->ubufs; ubuf->desc = nvq->upend_idx; - refcount_set(&ubuf->refcnt, 1); + ubuf->ubuf.ops = &vhost_ubuf_ops; + ubuf->ubuf.flags = SKBFL_ZEROCOPY_FRAG; + refcount_set(&ubuf->ubuf.refcnt, 1); msg.msg_control = &ctl; ctl.type = TUN_MSG_UBUF; - ctl.ptr = ubuf; + ctl.ptr = &ubuf->ubuf; msg.msg_controllen = sizeof(ctl); ubufs = nvq->ubufs; atomic_inc(&ubufs->refcount); @@ -931,19 +932,26 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) msg.msg_flags &= ~MSG_MORE; } - /* TODO: Check specific error and bomb out unless ENOBUFS? */ err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { + bool retry = err == -EAGAIN || err == -ENOMEM || err == -ENOBUFS; + if (zcopy_used) { - vhost_net_ubuf_put(ubufs); - nvq->upend_idx = ((unsigned)nvq->upend_idx - 1) - % UIO_MAXIOV; + if (vq->heads[ubuf->desc].len == VHOST_DMA_IN_PROGRESS) + vhost_net_ubuf_put(ubufs); + if (retry) + nvq->upend_idx = ((unsigned)nvq->upend_idx - 1) + % UIO_MAXIOV; + else + vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN; } - vhost_discard_vq_desc(vq, 1); - vhost_net_enable_vq(net, vq); - break; - } - if (err != len) + if (retry) { + vhost_discard_vq_desc(vq, 1, ndesc); + vhost_net_enable_vq(net, vq); + break; + } + pr_debug("Fail to send packet: err %d", err); + } else if (unlikely(err != len)) pr_debug("Truncated TX packet: " " len %d != %zd\n", err, len); if (!zcopy_used) @@ -951,11 +959,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) else vhost_zerocopy_signal_used(net, vq); vhost_net_tx_packet(net); - if (unlikely(vhost_exceeds_weight(++sent_pkts, total_len))) { - vhost_poll_queue(&vq->poll); - break; - } - } + } while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len))); } /* Expects to be always run from workqueue - which acts as @@ -967,11 +971,11 @@ static void handle_tx(struct vhost_net *net) struct socket *sock; mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_TX); - sock = vq->private_data; + sock = vhost_vq_get_backend(vq); if (!sock) goto out; - if (!vq_iotlb_prefetch(vq)) + if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(&net->dev, vq); @@ -1008,7 +1012,7 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk) } static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk, - bool *busyloop_intr) + bool *busyloop_intr, unsigned int *count) { struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX]; @@ -1018,7 +1022,8 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk, if (!len && rvq->busyloop_timeout) { /* Flush batched heads first */ - vhost_net_signal_used(rnvq); + vhost_net_signal_used(rnvq, *count); + *count = 0; /* Both tx vq and rx socket were polled here */ vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, true); @@ -1030,7 +1035,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk, /* This is a multi-buffer version of vhost_get_desc, that works if * vq has read descriptors only. - * @vq - the relevant virtqueue + * @nvq - the relevant vhost_net virtqueue * @datalen - data length we'll be reading * @iovcount - returned count of io vectors we fill * @log - vhost log @@ -1038,15 +1043,19 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk, * @quota - headcount quota, 1 for big buffer * returns number of buffer heads allocated, negative on error */ -static int get_rx_bufs(struct vhost_virtqueue *vq, +static int get_rx_bufs(struct vhost_net_virtqueue *nvq, struct vring_used_elem *heads, + u16 *nheads, int datalen, unsigned *iovcount, struct vhost_log *log, unsigned *log_num, - unsigned int quota) + unsigned int quota, + unsigned int *ndesc) { - unsigned int out, in; + struct vhost_virtqueue *vq = &nvq->vq; + bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER); + unsigned int out, in, desc_num, n = 0; int seg = 0; int headcount = 0; unsigned d; @@ -1054,16 +1063,16 @@ static int get_rx_bufs(struct vhost_virtqueue *vq, /* len is always initialized before use since we are always called with * datalen > 0. */ - u32 uninitialized_var(len); + u32 len; while (datalen > 0 && headcount < quota) { if (unlikely(seg >= UIO_MAXIOV)) { r = -ENOBUFS; goto err; } - r = vhost_get_vq_desc(vq, vq->iov + seg, - ARRAY_SIZE(vq->iov) - seg, &out, - &in, log, log_num); + r = vhost_get_vq_desc_n(vq, vq->iov + seg, + ARRAY_SIZE(vq->iov) - seg, &out, + &in, log, log_num, &desc_num); if (unlikely(r < 0)) goto err; @@ -1082,14 +1091,17 @@ static int get_rx_bufs(struct vhost_virtqueue *vq, nlogs += *log_num; log += *log_num; } - heads[headcount].id = cpu_to_vhost32(vq, d); len = iov_length(vq->iov + seg, in); - heads[headcount].len = cpu_to_vhost32(vq, len); - datalen -= len; + if (!in_order) { + heads[headcount].id = cpu_to_vhost32(vq, d); + heads[headcount].len = cpu_to_vhost32(vq, len); + } ++headcount; + datalen -= len; seg += in; + n += desc_num; } - heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen); + *iovcount = seg; if (unlikely(log)) *log_num = nlogs; @@ -1099,9 +1111,20 @@ static int get_rx_bufs(struct vhost_virtqueue *vq, r = UIO_MAXIOV + 1; goto err; } + + if (!in_order) + heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen); + else { + heads[0].len = cpu_to_vhost32(vq, len + datalen); + heads[0].id = cpu_to_vhost32(vq, d); + nheads[0] = headcount; + } + + *ndesc = n; + return headcount; err: - vhost_discard_vq_desc(vq, headcount); + vhost_discard_vq_desc(vq, headcount, n); return r; } @@ -1111,7 +1134,9 @@ static void handle_rx(struct vhost_net *net) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_virtqueue *vq = &nvq->vq; - unsigned uninitialized_var(in), log; + bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER); + unsigned int count = 0; + unsigned in, log; struct vhost_log *vq_log; struct msghdr msg = { .msg_name = NULL, @@ -1130,17 +1155,19 @@ static void handle_rx(struct vhost_net *net) size_t vhost_hlen, sock_hlen; size_t vhost_len, sock_len; bool busyloop_intr = false; + bool set_num_buffers; struct socket *sock; struct iov_iter fixup; __virtio16 num_buffers; int recv_pkts = 0; + unsigned int ndesc; mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_RX); - sock = vq->private_data; + sock = vhost_vq_get_backend(vq); if (!sock) goto out; - if (!vq_iotlb_prefetch(vq)) + if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(&net->dev, vq); @@ -1152,14 +1179,21 @@ static void handle_rx(struct vhost_net *net) vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ? vq->log : NULL; mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF); + set_num_buffers = mergeable || + vhost_has_feature(vq, VIRTIO_F_VERSION_1); - while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk, - &busyloop_intr))) { + do { + sock_len = vhost_net_rx_peek_head_len(net, sock->sk, + &busyloop_intr, &count); + if (!sock_len) + break; sock_len += sock_hlen; vhost_len = sock_len + vhost_hlen; - headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx, + headcount = get_rx_bufs(nvq, vq->heads + count, + vq->nheads + count, vhost_len, &in, vq_log, &log, - likely(mergeable) ? UIO_MAXIOV : 1); + likely(mergeable) ? UIO_MAXIOV : 1, + &ndesc); /* On error, stop handling until the next kick. */ if (unlikely(headcount < 0)) goto out; @@ -1182,14 +1216,14 @@ static void handle_rx(struct vhost_net *net) msg.msg_control = vhost_net_buf_consume(&nvq->rxq); /* On overrun, truncate and discard */ if (unlikely(headcount > UIO_MAXIOV)) { - iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1); + iov_iter_init(&msg.msg_iter, ITER_DEST, vq->iov, 1, 1); err = sock->ops->recvmsg(sock, &msg, 1, MSG_DONTWAIT | MSG_TRUNC); pr_debug("Discarded rx packet: len %zd\n", sock_len); continue; } /* We don't need to be notified again. */ - iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len); + iov_iter_init(&msg.msg_iter, ITER_DEST, vq->iov, in, vhost_len); fixup = msg.msg_iter; if (unlikely((vhost_hlen))) { /* We will supply the header ourselves @@ -1205,7 +1239,7 @@ static void handle_rx(struct vhost_net *net) if (unlikely(err != sock_len)) { pr_debug("Discarded rx packet: " " len %d, expected %zd\n", err, sock_len); - vhost_discard_vq_desc(vq, headcount); + vhost_discard_vq_desc(vq, headcount, ndesc); continue; } /* Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR */ @@ -1225,31 +1259,31 @@ static void handle_rx(struct vhost_net *net) /* TODO: Should check and handle checksum. */ num_buffers = cpu_to_vhost16(vq, headcount); - if (likely(mergeable) && + if (likely(set_num_buffers) && copy_to_iter(&num_buffers, sizeof num_buffers, &fixup) != sizeof num_buffers) { vq_err(vq, "Failed num_buffers write"); - vhost_discard_vq_desc(vq, headcount); + vhost_discard_vq_desc(vq, headcount, ndesc); goto out; } nvq->done_idx += headcount; - if (nvq->done_idx > VHOST_NET_BATCH) - vhost_net_signal_used(nvq); + count += in_order ? 1 : headcount; + if (nvq->done_idx > VHOST_NET_BATCH) { + vhost_net_signal_used(nvq, count); + count = 0; + } if (unlikely(vq_log)) vhost_log_write(vq, vq_log, log, vhost_len, vq->iov, in); total_len += vhost_len; - if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) { - vhost_poll_queue(&vq->poll); - goto out; - } - } + } while (likely(!vhost_exceeds_weight(vq, ++recv_pkts, total_len))); + if (unlikely(busyloop_intr)) vhost_poll_queue(&vq->poll); - else + else if (!sock_len) vhost_net_enable_vq(net, vq); out: - vhost_net_signal_used(nvq); + vhost_net_signal_used(nvq, count); mutex_unlock(&vq->mutex); } @@ -1337,14 +1371,18 @@ static int vhost_net_open(struct inode *inode, struct file *f) n->vqs[i].rx_ring = NULL; vhost_net_buf_init(&n->vqs[i].rxq); } - vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX); + vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, + UIO_MAXIOV + VHOST_NET_BATCH, + VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT, true, + NULL); - vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev); - vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev); + vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev, + vqs[VHOST_NET_VQ_TX]); + vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev, + vqs[VHOST_NET_VQ_RX]); f->private_data = n; - n->page_frag.page = NULL; - n->refcnt_bias = 0; + page_frag_cache_init(&n->pf_cache); return 0; } @@ -1357,9 +1395,9 @@ static struct socket *vhost_net_stop_vq(struct vhost_net *n, container_of(vq, struct vhost_net_virtqueue, vq); mutex_lock(&vq->mutex); - sock = vq->private_data; + sock = vhost_vq_get_backend(vq); vhost_net_disable_vq(n, vq); - vq->private_data = NULL; + vhost_vq_set_backend(vq, NULL); vhost_net_buf_unproduce(nvq); nvq->rx_ring = NULL; mutex_unlock(&vq->mutex); @@ -1373,16 +1411,9 @@ static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock, *rx_sock = vhost_net_stop_vq(n, &n->vqs[VHOST_NET_VQ_RX].vq); } -static void vhost_net_flush_vq(struct vhost_net *n, int index) -{ - vhost_poll_flush(n->poll + index); - vhost_poll_flush(&n->vqs[index].vq.poll); -} - static void vhost_net_flush(struct vhost_net *n) { - vhost_net_flush_vq(n, VHOST_NET_VQ_TX); - vhost_net_flush_vq(n, VHOST_NET_VQ_RX); + vhost_dev_flush(&n->dev); if (n->vqs[VHOST_NET_VQ_TX].ubufs) { mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); n->tx_flush = true; @@ -1419,18 +1450,13 @@ static int vhost_net_release(struct inode *inode, struct file *f) kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue); kfree(n->vqs[VHOST_NET_VQ_TX].xdp); kfree(n->dev.vqs); - if (n->page_frag.page) - __page_frag_cache_drain(n->page_frag.page, n->refcnt_bias); + page_frag_cache_drain(&n->pf_cache); kvfree(n); return 0; } static struct socket *get_raw_socket(int fd) { - struct { - struct sockaddr_ll sa; - char buf[MAX_ADDR_LEN]; - } uaddr; int r; struct socket *sock = sockfd_lookup(fd, &r); @@ -1443,11 +1469,7 @@ static struct socket *get_raw_socket(int fd) goto err; } - r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0); - if (r < 0) - goto err; - - if (uaddr.sa.sll_family != AF_PACKET) { + if (sock->sk->sk_family != AF_PACKET) { r = -EPFNOSUPPORT; goto err; } @@ -1457,13 +1479,9 @@ err: return ERR_PTR(r); } -static struct ptr_ring *get_tap_ptr_ring(int fd) +static struct ptr_ring *get_tap_ptr_ring(struct file *file) { struct ptr_ring *ring; - struct file *file = fget(fd); - - if (!file) - return NULL; ring = tun_get_tx_ring(file); if (!IS_ERR(ring)) goto out; @@ -1472,7 +1490,6 @@ static struct ptr_ring *get_tap_ptr_ring(int fd) goto out; ring = NULL; out: - fput(file); return ring; } @@ -1529,6 +1546,9 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) nvq = &n->vqs[index]; mutex_lock(&vq->mutex); + if (fd == -1) + vhost_clear_msg(&n->dev); + /* Verify that ring has been setup correctly. */ if (!vhost_vq_access_ok(vq)) { r = -EFAULT; @@ -1541,7 +1561,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) } /* start polling new socket */ - oldsock = vq->private_data; + oldsock = vhost_vq_get_backend(vq); if (sock != oldsock) { ubufs = vhost_net_ubuf_alloc(vq, sock && vhost_sock_zcopy(sock)); @@ -1551,7 +1571,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) } vhost_net_disable_vq(n, vq); - vq->private_data = sock; + vhost_vq_set_backend(vq, sock); vhost_net_buf_unproduce(nvq); r = vhost_vq_init_access(vq); if (r) @@ -1559,8 +1579,12 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) r = vhost_net_enable_vq(n, vq); if (r) goto err_used; - if (index == VHOST_NET_VQ_RX) - nvq->rx_ring = get_tap_ptr_ring(fd); + if (index == VHOST_NET_VQ_RX) { + if (sock) + nvq->rx_ring = get_tap_ptr_ring(sock->file); + else + nvq->rx_ring = NULL; + } oldubufs = nvq->ubufs; nvq->ubufs = ubufs; @@ -1580,7 +1604,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) } if (oldsock) { - vhost_net_flush_vq(n, index); + vhost_dev_flush(&n->dev); sockfd_put(oldsock); } @@ -1588,7 +1612,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) return 0; err_used: - vq->private_data = oldsock; + vhost_vq_set_backend(vq, oldsock); vhost_net_enable_vq(n, vq); if (ubufs) vhost_net_ubuf_put_wait_and_free(ubufs); @@ -1607,7 +1631,7 @@ static long vhost_net_reset_owner(struct vhost_net *n) struct socket *tx_sock = NULL; struct socket *rx_sock = NULL; long err; - struct vhost_umem *umem; + struct vhost_iotlb *umem; mutex_lock(&n->dev.mutex); err = vhost_dev_check_owner(&n->dev); @@ -1632,31 +1656,23 @@ done: return err; } -static int vhost_net_set_backend_features(struct vhost_net *n, u64 features) +static int vhost_net_set_features(struct vhost_net *n, const u64 *features) { + size_t vhost_hlen, sock_hlen, hdr_len; int i; - mutex_lock(&n->dev.mutex); - for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { - mutex_lock(&n->vqs[i].vq.mutex); - n->vqs[i].vq.acked_backend_features = features; - mutex_unlock(&n->vqs[i].vq.mutex); - } - mutex_unlock(&n->dev.mutex); - - return 0; -} + hdr_len = virtio_features_test_bit(features, VIRTIO_NET_F_MRG_RXBUF) || + virtio_features_test_bit(features, VIRTIO_F_VERSION_1) ? + sizeof(struct virtio_net_hdr_mrg_rxbuf) : + sizeof(struct virtio_net_hdr); -static int vhost_net_set_features(struct vhost_net *n, u64 features) -{ - size_t vhost_hlen, sock_hlen, hdr_len; - int i; + if (virtio_features_test_bit(features, + VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO) || + virtio_features_test_bit(features, + VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO)) + hdr_len = sizeof(struct virtio_net_hdr_v1_hash_tunnel); - hdr_len = (features & ((1ULL << VIRTIO_NET_F_MRG_RXBUF) | - (1ULL << VIRTIO_F_VERSION_1))) ? - sizeof(struct virtio_net_hdr_mrg_rxbuf) : - sizeof(struct virtio_net_hdr); - if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) { + if (virtio_features_test_bit(features, VHOST_NET_F_VIRTIO_NET_HDR)) { /* vhost provides vnet_hdr */ vhost_hlen = hdr_len; sock_hlen = 0; @@ -1666,18 +1682,19 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features) sock_hlen = hdr_len; } mutex_lock(&n->dev.mutex); - if ((features & (1 << VHOST_F_LOG_ALL)) && + if (virtio_features_test_bit(features, VHOST_F_LOG_ALL) && !vhost_log_access_ok(&n->dev)) goto out_unlock; - if ((features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) { - if (vhost_init_device_iotlb(&n->dev, true)) + if (virtio_features_test_bit(features, VIRTIO_F_ACCESS_PLATFORM)) { + if (vhost_init_device_iotlb(&n->dev)) goto out_unlock; } for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { mutex_lock(&n->vqs[i].vq.mutex); - n->vqs[i].vq.acked_features = features; + virtio_features_copy(n->vqs[i].vq.acked_features_array, + features); n->vqs[i].vhost_hlen = vhost_hlen; n->vqs[i].sock_hlen = sock_hlen; mutex_unlock(&n->vqs[i].vq.mutex); @@ -1714,12 +1731,14 @@ out: static long vhost_net_ioctl(struct file *f, unsigned int ioctl, unsigned long arg) { + const DEFINE_VHOST_FEATURES_ARRAY(vhost_net_features, vhost_net_bits); + u64 all_features[VIRTIO_FEATURES_U64S]; struct vhost_net *n = f->private_data; void __user *argp = (void __user *)arg; u64 __user *featurep = argp; struct vhost_vring_file backend; - u64 features; - int r; + u64 features, count, copied; + int r, i; switch (ioctl) { case VHOST_NET_SET_BACKEND: @@ -1727,16 +1746,60 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl, return -EFAULT; return vhost_net_set_backend(n, backend.index, backend.fd); case VHOST_GET_FEATURES: - features = VHOST_NET_FEATURES; + features = vhost_net_features[0]; if (copy_to_user(featurep, &features, sizeof features)) return -EFAULT; return 0; case VHOST_SET_FEATURES: if (copy_from_user(&features, featurep, sizeof features)) return -EFAULT; - if (features & ~VHOST_NET_FEATURES) + if (features & ~vhost_net_features[0]) return -EOPNOTSUPP; - return vhost_net_set_features(n, features); + + virtio_features_from_u64(all_features, features); + return vhost_net_set_features(n, all_features); + case VHOST_GET_FEATURES_ARRAY: + if (copy_from_user(&count, featurep, sizeof(count))) + return -EFAULT; + + /* Copy the net features, up to the user-provided buffer size */ + argp += sizeof(u64); + copied = min(count, (u64)VIRTIO_FEATURES_U64S); + if (copy_to_user(argp, vhost_net_features, + copied * sizeof(u64))) + return -EFAULT; + + /* Zero the trailing space provided by user-space, if any */ + if (clear_user(argp, size_mul(count - copied, sizeof(u64)))) + return -EFAULT; + return 0; + case VHOST_SET_FEATURES_ARRAY: + if (copy_from_user(&count, featurep, sizeof(count))) + return -EFAULT; + + virtio_features_zero(all_features); + argp += sizeof(u64); + copied = min(count, (u64)VIRTIO_FEATURES_U64S); + if (copy_from_user(all_features, argp, copied * sizeof(u64))) + return -EFAULT; + + /* + * Any feature specified by user-space above + * VIRTIO_FEATURES_BITS is not supported by definition. + */ + for (i = copied; i < count; ++i) { + if (copy_from_user(&features, featurep + 1 + i, + sizeof(features))) + return -EFAULT; + if (features) + return -EOPNOTSUPP; + } + + for (i = 0; i < VIRTIO_FEATURES_U64S; i++) + if (all_features[i] & ~vhost_net_features[i]) + return -EOPNOTSUPP; + + return vhost_net_set_features(n, all_features); case VHOST_GET_BACKEND_FEATURES: features = VHOST_NET_BACKEND_FEATURES; if (copy_to_user(featurep, &features, sizeof(features))) @@ -1747,7 +1810,8 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl, return -EFAULT; if (features & ~VHOST_NET_BACKEND_FEATURES) return -EOPNOTSUPP; - return vhost_net_set_backend_features(n, features); + vhost_set_backend_features(&n->dev, features); + return 0; case VHOST_RESET_OWNER: return vhost_net_reset_owner(n); case VHOST_SET_OWNER: @@ -1764,14 +1828,6 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl, } } -#ifdef CONFIG_COMPAT -static long vhost_net_compat_ioctl(struct file *f, unsigned int ioctl, - unsigned long arg) -{ - return vhost_net_ioctl(f, ioctl, (unsigned long)compat_ptr(arg)); -} -#endif - static ssize_t vhost_net_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; @@ -1807,9 +1863,7 @@ static const struct file_operations vhost_net_fops = { .write_iter = vhost_net_chr_write_iter, .poll = vhost_net_chr_poll, .unlocked_ioctl = vhost_net_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = vhost_net_compat_ioctl, -#endif + .compat_ioctl = compat_ptr_ioctl, .open = vhost_net_open, .llseek = noop_llseek, }; @@ -1820,7 +1874,7 @@ static struct miscdevice vhost_net_misc = { .fops = &vhost_net_fops, }; -static int vhost_net_init(void) +static int __init vhost_net_init(void) { if (experimental_zcopytx) vhost_net_enable_zcopy(VHOST_NET_VQ_TX); @@ -1828,7 +1882,7 @@ static int vhost_net_init(void) } module_init(vhost_net_init); -static void vhost_net_exit(void) +static void __exit vhost_net_exit(void) { misc_deregister(&vhost_net_misc); } |