--- zzzz-none-000/linux-3.10.107/drivers/net/virtio_net.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/net/virtio_net.c 2021-02-04 17:41:59.000000000 +0000 @@ -13,8 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see . */ //#define DEBUG #include @@ -27,6 +26,8 @@ #include #include #include +#include +#include static int napi_weight = NAPI_POLL_WEIGHT; module_param(napi_weight, int, 0444); @@ -36,9 +37,19 @@ module_param(gso, bool, 0444); /* FIXME: MTU in config. */ -#define MAX_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN) +#define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN) #define GOOD_COPY_LEN 128 +/* RX packet size EWMA. The average packet size is used to determine the packet + * buffer size when refilling RX rings. As the entire RX ring may be refilled + * at once, the weight is chosen so that the EWMA will be insensitive to short- + * term, transient changes in packet size. + */ +DECLARE_EWMA(pkt_len, 1, 64) + +/* Minimum alignment for mergeable packet buffers. */ +#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256) + #define VIRTNET_DRIVER_VERSION "1.0.0" struct virtnet_stats { @@ -70,12 +81,15 @@ struct napi_struct napi; - /* Number of input buffers, and max we've ever had. */ - unsigned int num, max; - /* Chain pages by the private ptr. */ struct page *pages; + /* Average packet length for mergeable receive buffers. */ + struct ewma_pkt_len mrg_avg_pkt_len; + + /* Page frag for packet buffer allocation. */ + struct page_frag alloc_frag; + /* RX: fragments + linear part + virtio header */ struct scatterlist sg[MAX_SKB_FRAGS + 2]; @@ -106,8 +120,11 @@ /* Has control virtqueue */ bool has_cvq; - /* enable config space updates */ - bool config_enable; + /* Host can handle any s/g split between our header and packet data */ + bool any_header_sg; + + /* Packet virtio header size */ + u8 hdr_len; /* Active statistics */ struct virtnet_stats __percpu *stats; @@ -118,34 +135,27 @@ /* Work struct for config space updates */ struct work_struct config_work; - /* Lock for config space updates */ - struct mutex config_lock; - /* Does the affinity hint is set for virtqueues? */ bool affinity_hint_set; - /* Per-cpu variable to show the mapping from CPU to virtqueue */ - int __percpu *vq_index; - /* CPU hot plug notifier */ struct notifier_block nb; -}; -struct skb_vnet_hdr { - union { - struct virtio_net_hdr hdr; - struct virtio_net_hdr_mrg_rxbuf mhdr; - }; + /* Control VQ buffers: protected by the rtnl lock */ + struct virtio_net_ctrl_hdr ctrl_hdr; + virtio_net_ctrl_ack ctrl_status; + u8 ctrl_promisc; + u8 ctrl_allmulti; }; struct padded_vnet_hdr { - struct virtio_net_hdr hdr; + struct virtio_net_hdr_mrg_rxbuf hdr; /* - * virtio_net_hdr should be in a separated sg buffer because of a - * QEMU bug, and data sg buffer shares same page with this header sg. - * This padding makes next sg 16 byte aligned after virtio_net_hdr. + * hdr is in a separate sg buffer, and data sg buffer shares same page + * with this header sg. This padding makes next sg 16 byte aligned + * after the header. */ - char padding[6]; + char padding[4]; }; /* Converting between virtqueue no. and kernel tx/rx queue no. @@ -171,9 +181,9 @@ return rxq * 2; } -static inline struct skb_vnet_hdr *skb_vnet_hdr(struct sk_buff *skb) +static inline struct virtio_net_hdr_mrg_rxbuf *skb_vnet_hdr(struct sk_buff *skb) { - return (struct skb_vnet_hdr *)skb->cb; + return (struct virtio_net_hdr_mrg_rxbuf *)skb->cb; } /* @@ -214,33 +224,36 @@ netif_wake_subqueue(vi->dev, vq2txq(vq)); } -static void set_skb_frag(struct sk_buff *skb, struct page *page, - unsigned int offset, unsigned int *len) +static unsigned int mergeable_ctx_to_buf_truesize(unsigned long mrg_ctx) +{ + unsigned int truesize = mrg_ctx & (MERGEABLE_BUFFER_ALIGN - 1); + return (truesize + 1) * MERGEABLE_BUFFER_ALIGN; +} + +static void *mergeable_ctx_to_buf_address(unsigned long mrg_ctx) { - int size = min((unsigned)PAGE_SIZE - offset, *len); - int i = skb_shinfo(skb)->nr_frags; + return (void *)(mrg_ctx & -MERGEABLE_BUFFER_ALIGN); - __skb_fill_page_desc(skb, i, page, offset, size); +} - skb->data_len += size; - skb->len += size; - skb->truesize += PAGE_SIZE; - skb_shinfo(skb)->nr_frags++; - skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; - *len -= size; +static unsigned long mergeable_buf_to_ctx(void *buf, unsigned int truesize) +{ + unsigned int size = truesize / MERGEABLE_BUFFER_ALIGN; + return (unsigned long)buf | (size - 1); } /* Called from bottom half context */ -static struct sk_buff *page_to_skb(struct receive_queue *rq, - struct page *page, unsigned int len) +static struct sk_buff *page_to_skb(struct virtnet_info *vi, + struct receive_queue *rq, + struct page *page, unsigned int offset, + unsigned int len, unsigned int truesize) { - struct virtnet_info *vi = rq->vq->vdev->priv; struct sk_buff *skb; - struct skb_vnet_hdr *hdr; - unsigned int copy, hdr_len, offset; + struct virtio_net_hdr_mrg_rxbuf *hdr; + unsigned int copy, hdr_len, hdr_padded_len; char *p; - p = page_address(page); + p = page_address(page) + offset; /* copy small packet so we can reuse these pages for small data */ skb = netdev_alloc_skb_ip_align(vi->dev, GOOD_COPY_LEN); @@ -249,18 +262,17 @@ hdr = skb_vnet_hdr(skb); - if (vi->mergeable_rx_bufs) { - hdr_len = sizeof hdr->mhdr; - offset = hdr_len; - } else { - hdr_len = sizeof hdr->hdr; - offset = sizeof(struct padded_vnet_hdr); - } + hdr_len = vi->hdr_len; + if (vi->mergeable_rx_bufs) + hdr_padded_len = sizeof *hdr; + else + hdr_padded_len = sizeof(struct padded_vnet_hdr); memcpy(hdr, p, hdr_len); len -= hdr_len; - p += offset; + offset += hdr_padded_len; + p += hdr_padded_len; copy = len; if (copy > skb_tailroom(skb)) @@ -270,6 +282,14 @@ len -= copy; offset += copy; + if (vi->mergeable_rx_bufs) { + if (len) + skb_add_rx_frag(skb, 0, page, offset, len, truesize); + else + put_page(page); + return skb; + } + /* * Verify that we can indeed put this data into a skb. * This is here to handle cases when the device erroneously @@ -281,9 +301,12 @@ dev_kfree_skb(skb); return NULL; } - + BUG_ON(offset >= PAGE_SIZE); while (len) { - set_skb_frag(skb, page, offset, &len); + unsigned int frag_size = min((unsigned)PAGE_SIZE - offset, len); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset, + frag_size, truesize); + len -= frag_size; page = (struct page *)page->private; offset = 0; } @@ -294,22 +317,24 @@ return skb; } -static struct sk_buff *receive_small(void *buf, unsigned int len) +static struct sk_buff *receive_small(struct virtnet_info *vi, void *buf, unsigned int len) { struct sk_buff * skb = buf; - len -= sizeof(struct virtio_net_hdr); + len -= vi->hdr_len; skb_trim(skb, len); return skb; } static struct sk_buff *receive_big(struct net_device *dev, + struct virtnet_info *vi, struct receive_queue *rq, - void *buf) + void *buf, + unsigned int len) { struct page *page = buf; - struct sk_buff *skb = page_to_skb(rq, page, 0); + struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE); if (unlikely(!skb)) goto err; @@ -323,86 +348,122 @@ } static struct sk_buff *receive_mergeable(struct net_device *dev, + struct virtnet_info *vi, struct receive_queue *rq, - void *buf, + unsigned long ctx, unsigned int len) { - struct skb_vnet_hdr *hdr = page_address(buf); - int num_buf = hdr->mhdr.num_buffers; - struct page *page = buf; - struct sk_buff *skb = page_to_skb(rq, page, len); - int i; + void *buf = mergeable_ctx_to_buf_address(ctx); + struct virtio_net_hdr_mrg_rxbuf *hdr = buf; + u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); + struct page *page = virt_to_head_page(buf); + int offset = buf - page_address(page); + unsigned int truesize = max(len, mergeable_ctx_to_buf_truesize(ctx)); + + struct sk_buff *head_skb = page_to_skb(vi, rq, page, offset, len, + truesize); + struct sk_buff *curr_skb = head_skb; - if (unlikely(!skb)) + if (unlikely(!curr_skb)) goto err_skb; - while (--num_buf) { - i = skb_shinfo(skb)->nr_frags; - if (i >= MAX_SKB_FRAGS) { - pr_debug("%s: packet too long\n", skb->dev->name); - skb->dev->stats.rx_length_errors++; - goto err_frags; - } - page = virtqueue_get_buf(rq->vq, &len); - if (!page) { - pr_debug("%s: rx error: %d buffers %d missing\n", - dev->name, hdr->mhdr.num_buffers, num_buf); + int num_skb_frags; + + ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len); + if (unlikely(!ctx)) { + pr_debug("%s: rx error: %d buffers out of %d missing\n", + dev->name, num_buf, + virtio16_to_cpu(vi->vdev, + hdr->num_buffers)); dev->stats.rx_length_errors++; goto err_buf; } - if (len > PAGE_SIZE) - len = PAGE_SIZE; + buf = mergeable_ctx_to_buf_address(ctx); + page = virt_to_head_page(buf); - set_skb_frag(skb, page, 0, &len); - - --rq->num; + num_skb_frags = skb_shinfo(curr_skb)->nr_frags; + if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) { + struct sk_buff *nskb = alloc_skb(0, GFP_ATOMIC); + + if (unlikely(!nskb)) + goto err_skb; + if (curr_skb == head_skb) + skb_shinfo(curr_skb)->frag_list = nskb; + else + curr_skb->next = nskb; + curr_skb = nskb; + head_skb->truesize += nskb->truesize; + num_skb_frags = 0; + } + truesize = max(len, mergeable_ctx_to_buf_truesize(ctx)); + if (curr_skb != head_skb) { + head_skb->data_len += len; + head_skb->len += len; + head_skb->truesize += truesize; + } + offset = buf - page_address(page); + if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) { + put_page(page); + skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1, + len, truesize); + } else { + skb_add_rx_frag(curr_skb, num_skb_frags, page, + offset, len, truesize); + } } - return skb; + + ewma_pkt_len_add(&rq->mrg_avg_pkt_len, head_skb->len); + return head_skb; + err_skb: - give_pages(rq, page); + put_page(page); while (--num_buf) { -err_frags: - buf = virtqueue_get_buf(rq->vq, &len); - if (unlikely(!buf)) { + ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len); + if (unlikely(!ctx)) { pr_debug("%s: rx error: %d buffers missing\n", dev->name, num_buf); dev->stats.rx_length_errors++; break; } - page = buf; - give_pages(rq, page); - --rq->num; + page = virt_to_head_page(mergeable_ctx_to_buf_address(ctx)); + put_page(page); } err_buf: dev->stats.rx_dropped++; - dev_kfree_skb(skb); + dev_kfree_skb(head_skb); return NULL; } -static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) +static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, + void *buf, unsigned int len) { - struct virtnet_info *vi = rq->vq->vdev->priv; struct net_device *dev = vi->dev; struct virtnet_stats *stats = this_cpu_ptr(vi->stats); struct sk_buff *skb; - struct skb_vnet_hdr *hdr; + struct virtio_net_hdr_mrg_rxbuf *hdr; - if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) { + if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); dev->stats.rx_length_errors++; - if (vi->mergeable_rx_bufs || vi->big_packets) + if (vi->mergeable_rx_bufs) { + unsigned long ctx = (unsigned long)buf; + void *base = mergeable_ctx_to_buf_address(ctx); + put_page(virt_to_head_page(base)); + } else if (vi->big_packets) { give_pages(rq, buf); - else + } else { dev_kfree_skb(buf); + } return; } + if (vi->mergeable_rx_bufs) - skb = receive_mergeable(dev, rq, buf, len); + skb = receive_mergeable(dev, vi, rq, (unsigned long)buf, len); else if (vi->big_packets) - skb = receive_big(dev, rq, buf); + skb = receive_big(dev, vi, rq, buf, len); else - skb = receive_small(buf, len); + skb = receive_small(vi, buf, len); if (unlikely(!skb)) return; @@ -417,8 +478,8 @@ if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { pr_debug("Needs csum!\n"); if (!skb_partial_csum_set(skb, - hdr->hdr.csum_start, - hdr->hdr.csum_offset)) + virtio16_to_cpu(vi->vdev, hdr->hdr.csum_start), + virtio16_to_cpu(vi->vdev, hdr->hdr.csum_offset))) goto frame_err; } else if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -449,7 +510,8 @@ if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; - skb_shinfo(skb)->gso_size = hdr->hdr.gso_size; + skb_shinfo(skb)->gso_size = virtio16_to_cpu(vi->vdev, + hdr->hdr.gso_size); if (skb_shinfo(skb)->gso_size == 0) { net_warn_ratelimited("%s: zero gso size.\n", dev->name); goto frame_err; @@ -460,7 +522,9 @@ skb_shinfo(skb)->gso_segs = 0; } - netif_receive_skb(skb); + skb_mark_napi_id(skb, &rq->napi); + + napi_gro_receive(&rq->napi, skb); return; frame_err: @@ -468,22 +532,22 @@ dev_kfree_skb(skb); } -static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp) +static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq, + gfp_t gfp) { - struct virtnet_info *vi = rq->vq->vdev->priv; struct sk_buff *skb; - struct skb_vnet_hdr *hdr; + struct virtio_net_hdr_mrg_rxbuf *hdr; int err; - skb = __netdev_alloc_skb_ip_align(vi->dev, MAX_PACKET_LEN, gfp); + skb = __netdev_alloc_skb_ip_align(vi->dev, GOOD_PACKET_LEN, gfp); if (unlikely(!skb)) return -ENOMEM; - skb_put(skb, MAX_PACKET_LEN); + skb_put(skb, GOOD_PACKET_LEN); hdr = skb_vnet_hdr(skb); - sg_set_buf(rq->sg, &hdr->hdr, sizeof hdr->hdr); - + sg_init_table(rq->sg, 2); + sg_set_buf(rq->sg, hdr, vi->hdr_len); skb_to_sgvec(skb, rq->sg + 1, 0, skb->len); err = virtqueue_add_inbuf(rq->vq, rq->sg, 2, skb, gfp); @@ -493,12 +557,15 @@ return err; } -static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp) +static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq, + gfp_t gfp) { struct page *first, *list = NULL; char *p; int i, err, offset; + sg_init_table(rq->sg, MAX_SKB_FRAGS + 2); + /* page in rq->sg[MAX_SKB_FRAGS + 1] is list tail */ for (i = MAX_SKB_FRAGS + 1; i > 1; --i) { first = get_a_page(rq, gfp); @@ -522,8 +589,8 @@ p = page_address(first); /* rq->sg[0], rq->sg[1] share the same page */ - /* a separated rq->sg[0] for virtio_net_hdr only due to QEMU bug */ - sg_set_buf(&rq->sg[0], p, sizeof(struct virtio_net_hdr)); + /* a separated rq->sg[0] for header - required in case !any_header_sg */ + sg_set_buf(&rq->sg[0], p, vi->hdr_len); /* rq->sg[1] for data packet, from offset */ offset = sizeof(struct padded_vnet_hdr); @@ -539,20 +606,47 @@ return err; } +static unsigned int get_mergeable_buf_len(struct ewma_pkt_len *avg_pkt_len) +{ + const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); + unsigned int len; + + len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len), + GOOD_PACKET_LEN, PAGE_SIZE - hdr_len); + return ALIGN(len, MERGEABLE_BUFFER_ALIGN); +} + static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) { - struct page *page; + struct page_frag *alloc_frag = &rq->alloc_frag; + char *buf; + unsigned long ctx; int err; + unsigned int len, hole; - page = get_a_page(rq, gfp); - if (!page) + len = get_mergeable_buf_len(&rq->mrg_avg_pkt_len); + if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp))) return -ENOMEM; - sg_init_one(rq->sg, page_address(page), PAGE_SIZE); + buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; + ctx = mergeable_buf_to_ctx(buf, len); + get_page(alloc_frag->page); + alloc_frag->offset += len; + hole = alloc_frag->size - alloc_frag->offset; + if (hole < len) { + /* To avoid internal fragmentation, if there is very likely not + * enough space for another buffer, add the remaining space to + * the current buffer. This extra space is not included in + * the truesize stored in ctx. + */ + len += hole; + alloc_frag->offset += hole; + } - err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, page, gfp); + sg_init_one(rq->sg, buf, len); + err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, (void *)ctx, gfp); if (err < 0) - give_pages(rq, page); + put_page(virt_to_head_page(buf)); return err; } @@ -564,27 +658,25 @@ * before we're receiving packets, or from refill_work which is * careful to disable receiving (using napi_disable). */ -static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp) +static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq, + gfp_t gfp) { - struct virtnet_info *vi = rq->vq->vdev->priv; int err; bool oom; + gfp |= __GFP_COLD; do { if (vi->mergeable_rx_bufs) err = add_recvbuf_mergeable(rq, gfp); else if (vi->big_packets) - err = add_recvbuf_big(rq, gfp); + err = add_recvbuf_big(vi, rq, gfp); else - err = add_recvbuf_small(rq, gfp); + err = add_recvbuf_small(vi, rq, gfp); oom = err == -ENOMEM; if (err) break; - ++rq->num; } while (rq->vq->num_free); - if (unlikely(rq->num > rq->max)) - rq->max = rq->num; virtqueue_kick(rq->vq); return !oom; } @@ -628,7 +720,7 @@ struct receive_queue *rq = &vi->rq[i]; napi_disable(&rq->napi); - still_empty = !try_fill_recv(rq, GFP_KERNEL); + still_empty = !try_fill_recv(vi, rq, GFP_KERNEL); virtnet_napi_enable(rq); /* In theory, this can happen: if we don't get any buffers in @@ -639,41 +731,84 @@ } } -static int virtnet_poll(struct napi_struct *napi, int budget) +static int virtnet_receive(struct receive_queue *rq, int budget) { - struct receive_queue *rq = - container_of(napi, struct receive_queue, napi); struct virtnet_info *vi = rq->vq->vdev->priv; + unsigned int len, received = 0; void *buf; - unsigned int r, len, received = 0; -again: while (received < budget && (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) { - receive_buf(rq, buf, len); - --rq->num; + receive_buf(vi, rq, buf, len); received++; } - if (rq->num < rq->max / 2) { - if (!try_fill_recv(rq, GFP_ATOMIC)) + if (rq->vq->num_free > virtqueue_get_vring_size(rq->vq) / 2) { + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) schedule_delayed_work(&vi->refill, 0); } + return received; +} + +static int virtnet_poll(struct napi_struct *napi, int budget) +{ + struct receive_queue *rq = + container_of(napi, struct receive_queue, napi); + unsigned int r, received; + + received = virtnet_receive(rq, budget); + /* Out of packets? */ if (received < budget) { r = virtqueue_enable_cb_prepare(rq->vq); - napi_complete(napi); + napi_complete_done(napi, received); if (unlikely(virtqueue_poll(rq->vq, r)) && napi_schedule_prep(napi)) { virtqueue_disable_cb(rq->vq); __napi_schedule(napi); + } + } + + return received; +} + +#ifdef CONFIG_NET_RX_BUSY_POLL +/* must be called with local_bh_disable()d */ +static int virtnet_busy_poll(struct napi_struct *napi) +{ + struct receive_queue *rq = + container_of(napi, struct receive_queue, napi); + struct virtnet_info *vi = rq->vq->vdev->priv; + int r, received = 0, budget = 4; + + if (!(vi->status & VIRTIO_NET_S_LINK_UP)) + return LL_FLUSH_FAILED; + + if (!napi_schedule_prep(napi)) + return LL_FLUSH_BUSY; + + virtqueue_disable_cb(rq->vq); + +again: + received += virtnet_receive(rq, budget); + + r = virtqueue_enable_cb_prepare(rq->vq); + clear_bit(NAPI_STATE_SCHED, &napi->state); + if (unlikely(virtqueue_poll(rq->vq, r)) && + napi_schedule_prep(napi)) { + virtqueue_disable_cb(rq->vq); + if (received < budget) { + budget -= received; goto again; + } else { + __napi_schedule(napi); } } return received; } +#endif /* CONFIG_NET_RX_BUSY_POLL */ static int virtnet_open(struct net_device *dev) { @@ -683,7 +818,7 @@ for (i = 0; i < vi->max_queue_pairs; i++) { if (i < vi->curr_queue_pairs) /* Make sure we have some buffers: if oom use wq. */ - if (!try_fill_recv(&vi->rq[i], GFP_KERNEL)) + if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); virtnet_napi_enable(&vi->rq[i]); } @@ -712,25 +847,40 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) { - struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb); + struct virtio_net_hdr_mrg_rxbuf *hdr; const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest; struct virtnet_info *vi = sq->vq->vdev->priv; unsigned num_sg; + unsigned hdr_len = vi->hdr_len; + bool can_push; pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest); + can_push = vi->any_header_sg && + !((unsigned long)skb->data & (__alignof__(*hdr) - 1)) && + !skb_header_cloned(skb) && skb_headroom(skb) >= hdr_len; + /* Even if we can, don't push here yet as this would skew + * csum_start offset below. */ + if (can_push) + hdr = (struct virtio_net_hdr_mrg_rxbuf *)(skb->data - hdr_len); + else + hdr = skb_vnet_hdr(skb); + if (skb->ip_summed == CHECKSUM_PARTIAL) { hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - hdr->hdr.csum_start = skb_checksum_start_offset(skb); - hdr->hdr.csum_offset = skb->csum_offset; + hdr->hdr.csum_start = cpu_to_virtio16(vi->vdev, + skb_checksum_start_offset(skb)); + hdr->hdr.csum_offset = cpu_to_virtio16(vi->vdev, + skb->csum_offset); } else { hdr->hdr.flags = 0; hdr->hdr.csum_offset = hdr->hdr.csum_start = 0; } if (skb_is_gso(skb)) { - hdr->hdr.hdr_len = skb_headlen(skb); - hdr->hdr.gso_size = skb_shinfo(skb)->gso_size; + hdr->hdr.hdr_len = cpu_to_virtio16(vi->vdev, skb_headlen(skb)); + hdr->hdr.gso_size = cpu_to_virtio16(vi->vdev, + skb_shinfo(skb)->gso_size); if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) @@ -746,15 +896,19 @@ hdr->hdr.gso_size = hdr->hdr.hdr_len = 0; } - hdr->mhdr.num_buffers = 0; - - /* Encode metadata header at front. */ if (vi->mergeable_rx_bufs) - sg_set_buf(sq->sg, &hdr->mhdr, sizeof hdr->mhdr); - else - sg_set_buf(sq->sg, &hdr->hdr, sizeof hdr->hdr); + hdr->num_buffers = 0; - num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1; + sg_init_table(sq->sg, skb_shinfo(skb)->nr_frags + (can_push ? 1 : 2)); + if (can_push) { + __skb_push(skb, hdr_len); + num_sg = skb_to_sgvec(skb, sq->sg, 0, skb->len); + /* Pull header back to avoid skew in tx bytes calculations. */ + __skb_pull(skb, hdr_len); + } else { + sg_set_buf(sq->sg, hdr, hdr_len); + num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1; + } return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC); } @@ -764,10 +918,15 @@ int qnum = skb_get_queue_mapping(skb); struct send_queue *sq = &vi->sq[qnum]; int err; + struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); + bool kick = !skb->xmit_more; /* Free up any pending old buffers before queueing new ones. */ free_old_xmit_skbs(sq); + /* timestamp packet in software */ + skb_tx_timestamp(skb); + /* Try to transmit */ err = xmit_skb(sq, skb); @@ -778,17 +937,24 @@ dev_warn(&dev->dev, "Unexpected TXQ (%d) queue failure: %d\n", qnum, err); dev->stats.tx_dropped++; - kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } - virtqueue_kick(sq->vq); /* Don't wait up for transmitted skbs to be freed. */ skb_orphan(skb); nf_reset(skb); - /* Apparently nice girls don't return TX_BUSY; stop the queue - * before it gets out of hand. Naturally, this wastes entries. */ + /* If running out of space, stop queue to avoid getting packets that we + * are then unable to transmit. + * An alternative would be to force queuing layer to requeue the skb by + * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be + * returned in a normal path of operation: it means that driver is not + * maintaining the TX queue stop/start state properly, and causes + * the stack to do a non-trivial amount of useless work. + * Since most packets only take 1 or 2 ring slots, stopping the queue + * early means 16 slots are typically wasted. + */ if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { netif_stop_subqueue(dev, qnum); if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { @@ -801,54 +967,54 @@ } } + if (kick || netif_xmit_stopped(txq)) + virtqueue_kick(sq->vq); + return NETDEV_TX_OK; } /* * Send command via the control virtqueue and check status. Commands * supported by the hypervisor, as indicated by feature bits, should - * never fail unless improperly formated. + * never fail unless improperly formatted. */ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, - struct scatterlist *out, - struct scatterlist *in) + struct scatterlist *out) { struct scatterlist *sgs[4], hdr, stat; - struct virtio_net_ctrl_hdr ctrl; - virtio_net_ctrl_ack status = ~0; - unsigned out_num = 0, in_num = 0, tmp; + unsigned out_num = 0, tmp; /* Caller should know better */ BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)); - ctrl.class = class; - ctrl.cmd = cmd; + vi->ctrl_status = ~0; + vi->ctrl_hdr.class = class; + vi->ctrl_hdr.cmd = cmd; /* Add header */ - sg_init_one(&hdr, &ctrl, sizeof(ctrl)); + sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr)); sgs[out_num++] = &hdr; if (out) sgs[out_num++] = out; - if (in) - sgs[out_num + in_num++] = in; /* Add return status. */ - sg_init_one(&stat, &status, sizeof(status)); - sgs[out_num + in_num++] = &stat; + sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status)); + sgs[out_num] = &stat; - BUG_ON(out_num + in_num > ARRAY_SIZE(sgs)); - BUG_ON(virtqueue_add_sgs(vi->cvq, sgs, out_num, in_num, vi, GFP_ATOMIC) - < 0); + BUG_ON(out_num + 1 > ARRAY_SIZE(sgs)); + virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC); - virtqueue_kick(vi->cvq); + if (unlikely(!virtqueue_kick(vi->cvq))) + return vi->ctrl_status == VIRTIO_NET_OK; /* Spin for a response, the kick causes an ioport write, trapping * into the hypervisor, so the request should be handled immediately. */ - while (!virtqueue_get_buf(vi->cvq, &tmp)) + while (!virtqueue_get_buf(vi->cvq, &tmp) && + !virtqueue_is_broken(vi->cvq)) cpu_relax(); - return status == VIRTIO_NET_OK; + return vi->ctrl_status == VIRTIO_NET_OK; } static int virtnet_set_mac_address(struct net_device *dev, void *p) @@ -866,15 +1032,20 @@ if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { sg_init_one(&sg, addr->sa_data, dev->addr_len); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, - VIRTIO_NET_CTRL_MAC_ADDR_SET, - &sg, NULL)) { + VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { dev_warn(&vdev->dev, "Failed to set mac address by vq command.\n"); return -EINVAL; } - } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) { - vdev->config->set(vdev, offsetof(struct virtio_net_config, mac), - addr->sa_data, dev->addr_len); + } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && + !virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) { + unsigned int i; + + /* Naturally, this has an atomicity problem. */ + for (i = 0; i < dev->addr_len; i++) + virtio_cwrite8(vdev, + offsetof(struct virtio_net_config, mac) + + i, addr->sa_data[i]); } eth_commit_mac_addr_change(dev, p); @@ -894,16 +1065,16 @@ u64 tpackets, tbytes, rpackets, rbytes; do { - start = u64_stats_fetch_begin_bh(&stats->tx_syncp); + start = u64_stats_fetch_begin_irq(&stats->tx_syncp); tpackets = stats->tx_packets; tbytes = stats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&stats->tx_syncp, start)); + } while (u64_stats_fetch_retry_irq(&stats->tx_syncp, start)); do { - start = u64_stats_fetch_begin_bh(&stats->rx_syncp); + start = u64_stats_fetch_begin_irq(&stats->rx_syncp); rpackets = stats->rx_packets; rbytes = stats->rx_bytes; - } while (u64_stats_fetch_retry_bh(&stats->rx_syncp, start)); + } while (u64_stats_fetch_retry_irq(&stats->rx_syncp, start)); tot->rx_packets += rpackets; tot->tx_packets += tpackets; @@ -935,7 +1106,7 @@ { rtnl_lock(); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_ANNOUNCE, - VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL, NULL)) + VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL)) dev_warn(&vi->dev->dev, "Failed to ack link announce.\n"); rtnl_unlock(); } @@ -949,11 +1120,11 @@ if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ)) return 0; - s.virtqueue_pairs = queue_pairs; + s.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs); sg_init_one(&sg, &s, sizeof(s)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, - VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg, NULL)) { + VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) { dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n", queue_pairs); return -EINVAL; @@ -985,7 +1156,6 @@ { struct virtnet_info *vi = netdev_priv(dev); struct scatterlist sg[2]; - u8 promisc, allmulti; struct virtio_net_ctrl_mac *mac_data; struct netdev_hw_addr *ha; int uc_count; @@ -993,28 +1163,26 @@ void *buf; int i; - /* We can't dynamicaly set ndo_set_rx_mode, so return gracefully */ + /* We can't dynamically set ndo_set_rx_mode, so return gracefully */ if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX)) return; - promisc = ((dev->flags & IFF_PROMISC) != 0); - allmulti = ((dev->flags & IFF_ALLMULTI) != 0); + vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0); + vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0); - sg_init_one(sg, &promisc, sizeof(promisc)); + sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, - VIRTIO_NET_CTRL_RX_PROMISC, - sg, NULL)) + VIRTIO_NET_CTRL_RX_PROMISC, sg)) dev_warn(&dev->dev, "Failed to %sable promisc mode.\n", - promisc ? "en" : "dis"); + vi->ctrl_promisc ? "en" : "dis"); - sg_init_one(sg, &allmulti, sizeof(allmulti)); + sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, - VIRTIO_NET_CTRL_RX_ALLMULTI, - sg, NULL)) + VIRTIO_NET_CTRL_RX_ALLMULTI, sg)) dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n", - allmulti ? "en" : "dis"); + vi->ctrl_allmulti ? "en" : "dis"); uc_count = netdev_uc_count(dev); mc_count = netdev_mc_count(dev); @@ -1028,7 +1196,7 @@ sg_init_table(sg, 2); /* Store the unicast list and count in the front of the buffer */ - mac_data->entries = uc_count; + mac_data->entries = cpu_to_virtio32(vi->vdev, uc_count); i = 0; netdev_for_each_uc_addr(ha, dev) memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN); @@ -1039,7 +1207,7 @@ /* multicast list and count fill the end */ mac_data = (void *)&mac_data->macs[uc_count][0]; - mac_data->entries = mc_count; + mac_data->entries = cpu_to_virtio32(vi->vdev, mc_count); i = 0; netdev_for_each_mc_addr(ha, dev) memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN); @@ -1048,9 +1216,8 @@ sizeof(mac_data->entries) + (mc_count * ETH_ALEN)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, - VIRTIO_NET_CTRL_MAC_TABLE_SET, - sg, NULL)) - dev_warn(&dev->dev, "Failed to set MAC fitler table.\n"); + VIRTIO_NET_CTRL_MAC_TABLE_SET, sg)) + dev_warn(&dev->dev, "Failed to set MAC filter table.\n"); kfree(buf); } @@ -1064,7 +1231,7 @@ sg_init_one(&sg, &vid, sizeof(vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, - VIRTIO_NET_CTRL_VLAN_ADD, &sg, NULL)) + VIRTIO_NET_CTRL_VLAN_ADD, &sg)) dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid); return 0; } @@ -1078,7 +1245,7 @@ sg_init_one(&sg, &vid, sizeof(vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, - VIRTIO_NET_CTRL_VLAN_DEL, &sg, NULL)) + VIRTIO_NET_CTRL_VLAN_DEL, &sg)) dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid); return 0; } @@ -1086,7 +1253,6 @@ static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu) { int i; - int cpu; if (vi->affinity_hint_set) { for (i = 0; i < vi->max_queue_pairs; i++) { @@ -1096,16 +1262,6 @@ vi->affinity_hint_set = false; } - - i = 0; - for_each_online_cpu(cpu) { - if (cpu == hcpu) { - *per_cpu_ptr(vi->vq_index, cpu) = -1; - } else { - *per_cpu_ptr(vi->vq_index, cpu) = - ++i % vi->curr_queue_pairs; - } - } } static void virtnet_set_affinity(struct virtnet_info *vi) @@ -1127,7 +1283,7 @@ for_each_online_cpu(cpu) { virtqueue_set_affinity(vi->rq[i].vq, cpu); virtqueue_set_affinity(vi->sq[i].vq, cpu); - *per_cpu_ptr(vi->vq_index, cpu) = i; + netif_set_xps_queue(vi->dev, cpumask_of(cpu), i); i++; } @@ -1193,7 +1349,7 @@ if (channels->rx_count || channels->tx_count || channels->other_count) return -EINVAL; - if (queue_pairs > vi->max_queue_pairs) + if (queue_pairs > vi->max_queue_pairs || queue_pairs == 0) return -EINVAL; get_online_cpus(); @@ -1228,6 +1384,7 @@ .get_ringparam = virtnet_get_ringparam, .set_channels = virtnet_set_channels, .get_channels = virtnet_get_channels, + .get_ts_info = ethtool_op_get_ts_info, }; #define MIN_MTU 68 @@ -1241,28 +1398,6 @@ return 0; } -/* To avoid contending a lock hold by a vcpu who would exit to host, select the - * txq based on the processor id. - */ -static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb) -{ - int txq; - struct virtnet_info *vi = netdev_priv(dev); - - if (skb_rx_queue_recorded(skb)) { - txq = skb_get_rx_queue(skb); - } else { - txq = *__this_cpu_ptr(vi->vq_index); - if (txq == -1) - txq = 0; - } - - while (unlikely(txq >= dev->real_num_tx_queues)) - txq -= dev->real_num_tx_queues; - - return txq; -} - static const struct net_device_ops virtnet_netdev = { .ndo_open = virtnet_open, .ndo_stop = virtnet_close, @@ -1274,10 +1409,12 @@ .ndo_get_stats64 = virtnet_stats, .ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid, - .ndo_select_queue = virtnet_select_queue, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = virtnet_netpoll, #endif +#ifdef CONFIG_NET_RX_BUSY_POLL + .ndo_busy_poll = virtnet_busy_poll, +#endif }; static void virtnet_config_changed_work(struct work_struct *work) @@ -1286,14 +1423,9 @@ container_of(work, struct virtnet_info, config_work); u16 v; - mutex_lock(&vi->config_lock); - if (!vi->config_enable) - goto done; - - if (virtio_config_val(vi->vdev, VIRTIO_NET_F_STATUS, - offsetof(struct virtio_net_config, status), - &v) < 0) - goto done; + if (virtio_cread_feature(vi->vdev, VIRTIO_NET_F_STATUS, + struct virtio_net_config, status, &v) < 0) + return; if (v & VIRTIO_NET_S_ANNOUNCE) { netdev_notify_peers(vi->dev); @@ -1304,7 +1436,7 @@ v &= VIRTIO_NET_S_LINK_UP; if (vi->status == v) - goto done; + return; vi->status = v; @@ -1315,8 +1447,6 @@ netif_carrier_off(vi->dev); netif_tx_stop_all_queues(vi->dev); } -done: - mutex_unlock(&vi->config_lock); } static void virtnet_config_changed(struct virtio_device *vdev) @@ -1330,8 +1460,15 @@ { int i; - for (i = 0; i < vi->max_queue_pairs; i++) + for (i = 0; i < vi->max_queue_pairs; i++) { + napi_hash_del(&vi->rq[i].napi); netif_napi_del(&vi->rq[i].napi); + } + + /* We called napi_hash_del() before netif_napi_del(), + * we need to respect an RCU grace period before freeing vi->rq + */ + synchronize_net(); kfree(vi->rq); kfree(vi->sq); @@ -1347,6 +1484,14 @@ } } +static void free_receive_page_frags(struct virtnet_info *vi) +{ + int i; + for (i = 0; i < vi->max_queue_pairs; i++) + if (vi->rq[i].alloc_frag.page) + put_page(vi->rq[i].alloc_frag.page); +} + static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -1362,13 +1507,16 @@ struct virtqueue *vq = vi->rq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { - if (vi->mergeable_rx_bufs || vi->big_packets) + if (vi->mergeable_rx_bufs) { + unsigned long ctx = (unsigned long)buf; + void *base = mergeable_ctx_to_buf_address(ctx); + put_page(virt_to_head_page(base)); + } else if (vi->big_packets) { give_pages(&vi->rq[i], buf); - else + } else { dev_kfree_skb(buf); - --vi->rq[i].num; + } } - BUG_ON(vi->rq[i].num != 0); } } @@ -1473,8 +1621,10 @@ vi->rq[i].pages = NULL; netif_napi_add(vi->dev, &vi->rq[i].napi, virtnet_poll, napi_weight); + napi_hash_add(&vi->rq[i].napi); sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg)); + ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len); sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg)); } @@ -1511,6 +1661,67 @@ return ret; } +#ifdef CONFIG_SYSFS +static ssize_t mergeable_rx_buffer_size_show(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attribute, char *buf) +{ + struct virtnet_info *vi = netdev_priv(queue->dev); + unsigned int queue_index = get_netdev_rx_queue_index(queue); + struct ewma_pkt_len *avg; + + BUG_ON(queue_index >= vi->max_queue_pairs); + avg = &vi->rq[queue_index].mrg_avg_pkt_len; + return sprintf(buf, "%u\n", get_mergeable_buf_len(avg)); +} + +static struct rx_queue_attribute mergeable_rx_buffer_size_attribute = + __ATTR_RO(mergeable_rx_buffer_size); + +static struct attribute *virtio_net_mrg_rx_attrs[] = { + &mergeable_rx_buffer_size_attribute.attr, + NULL +}; + +static const struct attribute_group virtio_net_mrg_rx_group = { + .name = "virtio_net", + .attrs = virtio_net_mrg_rx_attrs +}; +#endif + +static bool virtnet_fail_on_feature(struct virtio_device *vdev, + unsigned int fbit, + const char *fname, const char *dname) +{ + if (!virtio_has_feature(vdev, fbit)) + return false; + + dev_err(&vdev->dev, "device advertises feature %s but not %s", + fname, dname); + + return true; +} + +#define VIRTNET_FAIL_ON(vdev, fbit, dbit) \ + virtnet_fail_on_feature(vdev, fbit, #fbit, dbit) + +static bool virtnet_validate_features(struct virtio_device *vdev) +{ + if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ) && + (VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_RX, + "VIRTIO_NET_F_CTRL_VQ") || + VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_VLAN, + "VIRTIO_NET_F_CTRL_VQ") || + VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE, + "VIRTIO_NET_F_CTRL_VQ") || + VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_MQ, "VIRTIO_NET_F_CTRL_VQ") || + VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR, + "VIRTIO_NET_F_CTRL_VQ"))) { + return false; + } + + return true; +} + static int virtnet_probe(struct virtio_device *vdev) { int i, err; @@ -1518,10 +1729,19 @@ struct virtnet_info *vi; u16 max_queue_pairs; + if (!vdev->config->get) { + dev_err(&vdev->dev, "%s failure: config access disabled\n", + __func__); + return -EINVAL; + } + + if (!virtnet_validate_features(vdev)) + return -EINVAL; + /* Find if host supports multiqueue virtio_net device */ - err = virtio_config_val(vdev, VIRTIO_NET_F_MQ, - offsetof(struct virtio_net_config, - max_virtqueue_pairs), &max_queue_pairs); + err = virtio_cread_feature(vdev, VIRTIO_NET_F_MQ, + struct virtio_net_config, + max_virtqueue_pairs, &max_queue_pairs); /* We need at least 2 queue's */ if (err || max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || @@ -1539,7 +1759,7 @@ dev->netdev_ops = &virtnet_netdev; dev->features = NETIF_F_HIGHDMA; - SET_ETHTOOL_OPS(dev, &virtnet_ethtool_ops); + dev->ethtool_ops = &virtnet_ethtool_ops; SET_NETDEV_DEV(dev, &vdev->dev); /* Do we support "hardware" checksums? */ @@ -1563,17 +1783,23 @@ if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO)) dev->hw_features |= NETIF_F_UFO; + dev->features |= NETIF_F_GSO_ROBUST; + if (gso) dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO); /* (!csum && gso) case will be fixed by register_netdev() */ } + if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM)) + dev->features |= NETIF_F_RXCSUM; dev->vlan_features = dev->features; /* Configuration may specify what MAC to use. Otherwise random. */ - if (virtio_config_val_len(vdev, VIRTIO_NET_F_MAC, - offsetof(struct virtio_net_config, mac), - dev->dev_addr, dev->addr_len) < 0) + if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) + virtio_cread_bytes(vdev, + offsetof(struct virtio_net_config, mac), + dev->dev_addr, dev->addr_len); + else eth_hw_addr_random(dev); /* Set up our device-specific information */ @@ -1586,12 +1812,13 @@ if (vi->stats == NULL) goto free; - vi->vq_index = alloc_percpu(int); - if (vi->vq_index == NULL) - goto free_stats; + for_each_possible_cpu(i) { + struct virtnet_stats *virtnet_stats; + virtnet_stats = per_cpu_ptr(vi->stats, i); + u64_stats_init(&virtnet_stats->tx_syncp); + u64_stats_init(&virtnet_stats->rx_syncp); + } - mutex_init(&vi->config_lock); - vi->config_enable = true; INIT_WORK(&vi->config_work, virtnet_config_changed_work); /* If we can receive ANY GSO packets, we must allocate large ones. */ @@ -1604,9 +1831,22 @@ if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) vi->mergeable_rx_bufs = true; + if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) || + virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) + vi->hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); + else + vi->hdr_len = sizeof(struct virtio_net_hdr); + + if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT) || + virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) + vi->any_header_sg = true; + if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) vi->has_cvq = true; + if (vi->any_header_sg) + dev->needed_headroom = vi->hdr_len; + /* Use single tx/rx queue pair as default */ vi->curr_queue_pairs = 1; vi->max_queue_pairs = max_queue_pairs; @@ -1614,10 +1854,14 @@ /* Allocate/initialize the rx/tx queues, and invoke find_vqs */ err = init_vqs(vi); if (err) - goto free_index; + goto free_stats; - netif_set_real_num_tx_queues(dev, 1); - netif_set_real_num_rx_queues(dev, 1); +#ifdef CONFIG_SYSFS + if (vi->mergeable_rx_bufs) + dev->sysfs_rx_queue_group = &virtio_net_mrg_rx_group; +#endif + netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs); + netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs); err = register_netdev(dev); if (err) { @@ -1625,12 +1869,15 @@ goto free_vqs; } + virtio_device_ready(vdev); + /* Last of all, set up some receive buffers. */ for (i = 0; i < vi->curr_queue_pairs; i++) { - try_fill_recv(&vi->rq[i], GFP_KERNEL); + try_fill_recv(vi, &vi->rq[i], GFP_KERNEL); /* If we didn't even get one input buffer, we're useless. */ - if (vi->rq[i].num == 0) { + if (vi->rq[i].vq->num_free == + virtqueue_get_vring_size(vi->rq[i].vq)) { free_unused_bufs(vi); err = -ENOMEM; goto free_recv_bufs; @@ -1660,13 +1907,14 @@ return 0; free_recv_bufs: + vi->vdev->config->reset(vdev); + free_receive_bufs(vi); unregister_netdev(dev); free_vqs: cancel_delayed_work_sync(&vi->refill); + free_receive_page_frags(vi); virtnet_del_vqs(vi); -free_index: - free_percpu(vi->vq_index); free_stats: free_percpu(vi->stats); free: @@ -1683,6 +1931,8 @@ free_receive_bufs(vi); + free_receive_page_frags(vi); + virtnet_del_vqs(vi); } @@ -1692,23 +1942,18 @@ unregister_hotcpu_notifier(&vi->nb); - /* Prevent config work handler from accessing the device. */ - mutex_lock(&vi->config_lock); - vi->config_enable = false; - mutex_unlock(&vi->config_lock); + /* Make sure no work handler is accessing the device. */ + flush_work(&vi->config_work); unregister_netdev(vi->dev); remove_vq_common(vi); - flush_work(&vi->config_work); - - free_percpu(vi->vq_index); free_percpu(vi->stats); free_netdev(vi->dev); } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static int virtnet_freeze(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; @@ -1716,24 +1961,19 @@ unregister_hotcpu_notifier(&vi->nb); - /* Prevent config work handler from accessing the device */ - mutex_lock(&vi->config_lock); - vi->config_enable = false; - mutex_unlock(&vi->config_lock); + /* Make sure no work handler is accessing the device */ + flush_work(&vi->config_work); netif_device_detach(vi->dev); cancel_delayed_work_sync(&vi->refill); - if (netif_running(vi->dev)) - for (i = 0; i < vi->max_queue_pairs; i++) { + if (netif_running(vi->dev)) { + for (i = 0; i < vi->max_queue_pairs; i++) napi_disable(&vi->rq[i].napi); - netif_napi_del(&vi->rq[i].napi); - } + } remove_vq_common(vi); - flush_work(&vi->config_work); - return 0; } @@ -1746,9 +1986,11 @@ if (err) return err; + virtio_device_ready(vdev); + if (netif_running(vi->dev)) { for (i = 0; i < vi->curr_queue_pairs; i++) - if (!try_fill_recv(&vi->rq[i], GFP_KERNEL)) + if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); for (i = 0; i < vi->max_queue_pairs; i++) @@ -1757,10 +1999,6 @@ netif_device_attach(vi->dev); - mutex_lock(&vi->config_lock); - vi->config_enable = true; - mutex_unlock(&vi->config_lock); - rtnl_lock(); virtnet_set_queues(vi, vi->curr_queue_pairs); rtnl_unlock(); @@ -1788,6 +2026,7 @@ VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, VIRTIO_NET_F_CTRL_MAC_ADDR, + VIRTIO_F_ANY_LAYOUT, }; static struct virtio_driver virtio_net_driver = { @@ -1799,7 +2038,7 @@ .probe = virtnet_probe, .remove = virtnet_remove, .config_changed = virtnet_config_changed, -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP .freeze = virtnet_freeze, .restore = virtnet_restore, #endif