| // SPDX-License-Identifier: GPL-2.0-or-later |
| /* A network driver using virtio. |
| * |
| * Copyright 2007 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation |
| */ |
| //#define DEBUG |
| #include <linux/netdevice.h> |
| #include <linux/etherdevice.h> |
| #include <linux/ethtool.h> |
| #include <linux/module.h> |
| #include <linux/virtio.h> |
| #include <linux/virtio_net.h> |
| #include <linux/bpf.h> |
| #include <linux/bpf_trace.h> |
| #include <linux/scatterlist.h> |
| #include <linux/if_vlan.h> |
| #include <linux/slab.h> |
| #include <linux/cpu.h> |
| #include <linux/average.h> |
| #include <linux/filter.h> |
| #include <linux/kernel.h> |
| #include <net/route.h> |
| #include <net/xdp.h> |
| #include <net/net_failover.h> |
| |
| static int napi_weight = NAPI_POLL_WEIGHT; |
| module_param(napi_weight, int, 0444); |
| |
| static bool csum = true, gso = true, napi_tx = true; |
| module_param(csum, bool, 0444); |
| module_param(gso, bool, 0444); |
| module_param(napi_tx, bool, 0644); |
| |
| /* FIXME: MTU in config. */ |
| #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN) |
| #define GOOD_COPY_LEN 128 |
| |
| #define VIRTNET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) |
| |
| /* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */ |
| #define VIRTIO_XDP_HEADROOM 256 |
| |
| /* Separating two types of XDP xmit */ |
| #define VIRTIO_XDP_TX BIT(0) |
| #define VIRTIO_XDP_REDIR BIT(1) |
| |
| #define VIRTIO_XDP_FLAG BIT(0) |
| |
| /* 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, 0, 64) |
| |
| #define VIRTNET_DRIVER_VERSION "1.0.0" |
| |
| static const unsigned long guest_offloads[] = { |
| VIRTIO_NET_F_GUEST_TSO4, |
| VIRTIO_NET_F_GUEST_TSO6, |
| VIRTIO_NET_F_GUEST_ECN, |
| VIRTIO_NET_F_GUEST_UFO, |
| VIRTIO_NET_F_GUEST_CSUM |
| }; |
| |
| #define GUEST_OFFLOAD_GRO_HW_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \ |
| (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \ |
| (1ULL << VIRTIO_NET_F_GUEST_ECN) | \ |
| (1ULL << VIRTIO_NET_F_GUEST_UFO)) |
| |
| struct virtnet_stat_desc { |
| char desc[ETH_GSTRING_LEN]; |
| size_t offset; |
| }; |
| |
| struct virtnet_sq_stats { |
| struct u64_stats_sync syncp; |
| u64 packets; |
| u64 bytes; |
| u64 xdp_tx; |
| u64 xdp_tx_drops; |
| u64 kicks; |
| u64 tx_timeouts; |
| }; |
| |
| struct virtnet_rq_stats { |
| struct u64_stats_sync syncp; |
| u64 packets; |
| u64 bytes; |
| u64 drops; |
| u64 xdp_packets; |
| u64 xdp_tx; |
| u64 xdp_redirects; |
| u64 xdp_drops; |
| u64 kicks; |
| }; |
| |
| #define VIRTNET_SQ_STAT(m) offsetof(struct virtnet_sq_stats, m) |
| #define VIRTNET_RQ_STAT(m) offsetof(struct virtnet_rq_stats, m) |
| |
| static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = { |
| { "packets", VIRTNET_SQ_STAT(packets) }, |
| { "bytes", VIRTNET_SQ_STAT(bytes) }, |
| { "xdp_tx", VIRTNET_SQ_STAT(xdp_tx) }, |
| { "xdp_tx_drops", VIRTNET_SQ_STAT(xdp_tx_drops) }, |
| { "kicks", VIRTNET_SQ_STAT(kicks) }, |
| { "tx_timeouts", VIRTNET_SQ_STAT(tx_timeouts) }, |
| }; |
| |
| static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = { |
| { "packets", VIRTNET_RQ_STAT(packets) }, |
| { "bytes", VIRTNET_RQ_STAT(bytes) }, |
| { "drops", VIRTNET_RQ_STAT(drops) }, |
| { "xdp_packets", VIRTNET_RQ_STAT(xdp_packets) }, |
| { "xdp_tx", VIRTNET_RQ_STAT(xdp_tx) }, |
| { "xdp_redirects", VIRTNET_RQ_STAT(xdp_redirects) }, |
| { "xdp_drops", VIRTNET_RQ_STAT(xdp_drops) }, |
| { "kicks", VIRTNET_RQ_STAT(kicks) }, |
| }; |
| |
| #define VIRTNET_SQ_STATS_LEN ARRAY_SIZE(virtnet_sq_stats_desc) |
| #define VIRTNET_RQ_STATS_LEN ARRAY_SIZE(virtnet_rq_stats_desc) |
| |
| /* Internal representation of a send virtqueue */ |
| struct send_queue { |
| /* Virtqueue associated with this send _queue */ |
| struct virtqueue *vq; |
| |
| /* TX: fragments + linear part + virtio header */ |
| struct scatterlist sg[MAX_SKB_FRAGS + 2]; |
| |
| /* Name of the send queue: output.$index */ |
| char name[40]; |
| |
| struct virtnet_sq_stats stats; |
| |
| struct napi_struct napi; |
| |
| /* Record whether sq is in reset state. */ |
| bool reset; |
| }; |
| |
| /* Internal representation of a receive virtqueue */ |
| struct receive_queue { |
| /* Virtqueue associated with this receive_queue */ |
| struct virtqueue *vq; |
| |
| struct napi_struct napi; |
| |
| struct bpf_prog __rcu *xdp_prog; |
| |
| struct virtnet_rq_stats stats; |
| |
| /* Chain pages by the private ptr. */ |
| struct page *pages; |
| |
| /* Average packet length for mergeable receive buffers. */ |
| struct ewma_pkt_len mrg_avg_pkt_len; |
| |
| /* Page frag for packet buffer allocation. */ |
| struct page_frag alloc_frag; |
| |
| /* RX: fragments + linear part + virtio header */ |
| struct scatterlist sg[MAX_SKB_FRAGS + 2]; |
| |
| /* Min single buffer size for mergeable buffers case. */ |
| unsigned int min_buf_len; |
| |
| /* Name of this receive queue: input.$index */ |
| char name[40]; |
| |
| struct xdp_rxq_info xdp_rxq; |
| }; |
| |
| /* This structure can contain rss message with maximum settings for indirection table and keysize |
| * Note, that default structure that describes RSS configuration virtio_net_rss_config |
| * contains same info but can't handle table values. |
| * In any case, structure would be passed to virtio hw through sg_buf split by parts |
| * because table sizes may be differ according to the device configuration. |
| */ |
| #define VIRTIO_NET_RSS_MAX_KEY_SIZE 40 |
| #define VIRTIO_NET_RSS_MAX_TABLE_LEN 128 |
| struct virtio_net_ctrl_rss { |
| u32 hash_types; |
| u16 indirection_table_mask; |
| u16 unclassified_queue; |
| u16 indirection_table[VIRTIO_NET_RSS_MAX_TABLE_LEN]; |
| u16 max_tx_vq; |
| u8 hash_key_length; |
| u8 key[VIRTIO_NET_RSS_MAX_KEY_SIZE]; |
| }; |
| |
| /* Control VQ buffers: protected by the rtnl lock */ |
| struct control_buf { |
| struct virtio_net_ctrl_hdr hdr; |
| virtio_net_ctrl_ack status; |
| struct virtio_net_ctrl_mq mq; |
| u8 promisc; |
| u8 allmulti; |
| __virtio16 vid; |
| __virtio64 offloads; |
| struct virtio_net_ctrl_rss rss; |
| struct virtio_net_ctrl_coal_tx coal_tx; |
| struct virtio_net_ctrl_coal_rx coal_rx; |
| }; |
| |
| struct virtnet_info { |
| struct virtio_device *vdev; |
| struct virtqueue *cvq; |
| struct net_device *dev; |
| struct send_queue *sq; |
| struct receive_queue *rq; |
| unsigned int status; |
| |
| /* Max # of queue pairs supported by the device */ |
| u16 max_queue_pairs; |
| |
| /* # of queue pairs currently used by the driver */ |
| u16 curr_queue_pairs; |
| |
| /* # of XDP queue pairs currently used by the driver */ |
| u16 xdp_queue_pairs; |
| |
| /* xdp_queue_pairs may be 0, when xdp is already loaded. So add this. */ |
| bool xdp_enabled; |
| |
| /* I like... big packets and I cannot lie! */ |
| bool big_packets; |
| |
| /* number of sg entries allocated for big packets */ |
| unsigned int big_packets_num_skbfrags; |
| |
| /* Host will merge rx buffers for big packets (shake it! shake it!) */ |
| bool mergeable_rx_bufs; |
| |
| /* Host supports rss and/or hash report */ |
| bool has_rss; |
| bool has_rss_hash_report; |
| u8 rss_key_size; |
| u16 rss_indir_table_size; |
| u32 rss_hash_types_supported; |
| u32 rss_hash_types_saved; |
| |
| /* Has control virtqueue */ |
| bool has_cvq; |
| |
| /* Host can handle any s/g split between our header and packet data */ |
| bool any_header_sg; |
| |
| /* Packet virtio header size */ |
| u8 hdr_len; |
| |
| /* Work struct for delayed refilling if we run low on memory. */ |
| struct delayed_work refill; |
| |
| /* Is delayed refill enabled? */ |
| bool refill_enabled; |
| |
| /* The lock to synchronize the access to refill_enabled */ |
| spinlock_t refill_lock; |
| |
| /* Work struct for config space updates */ |
| struct work_struct config_work; |
| |
| /* Does the affinity hint is set for virtqueues? */ |
| bool affinity_hint_set; |
| |
| /* CPU hotplug instances for online & dead */ |
| struct hlist_node node; |
| struct hlist_node node_dead; |
| |
| struct control_buf *ctrl; |
| |
| /* Ethtool settings */ |
| u8 duplex; |
| u32 speed; |
| |
| /* Interrupt coalescing settings */ |
| u32 tx_usecs; |
| u32 rx_usecs; |
| u32 tx_max_packets; |
| u32 rx_max_packets; |
| |
| unsigned long guest_offloads; |
| unsigned long guest_offloads_capable; |
| |
| /* failover when STANDBY feature enabled */ |
| struct failover *failover; |
| }; |
| |
| struct padded_vnet_hdr { |
| struct virtio_net_hdr_v1_hash 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[12]; |
| }; |
| |
| static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf); |
| static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf); |
| |
| static bool is_xdp_frame(void *ptr) |
| { |
| return (unsigned long)ptr & VIRTIO_XDP_FLAG; |
| } |
| |
| static void *xdp_to_ptr(struct xdp_frame *ptr) |
| { |
| return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG); |
| } |
| |
| static struct xdp_frame *ptr_to_xdp(void *ptr) |
| { |
| return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG); |
| } |
| |
| /* Converting between virtqueue no. and kernel tx/rx queue no. |
| * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq |
| */ |
| static int vq2txq(struct virtqueue *vq) |
| { |
| return (vq->index - 1) / 2; |
| } |
| |
| static int txq2vq(int txq) |
| { |
| return txq * 2 + 1; |
| } |
| |
| static int vq2rxq(struct virtqueue *vq) |
| { |
| return vq->index / 2; |
| } |
| |
| static int rxq2vq(int rxq) |
| { |
| return rxq * 2; |
| } |
| |
| static inline struct virtio_net_hdr_mrg_rxbuf *skb_vnet_hdr(struct sk_buff *skb) |
| { |
| return (struct virtio_net_hdr_mrg_rxbuf *)skb->cb; |
| } |
| |
| /* |
| * private is used to chain pages for big packets, put the whole |
| * most recent used list in the beginning for reuse |
| */ |
| static void give_pages(struct receive_queue *rq, struct page *page) |
| { |
| struct page *end; |
| |
| /* Find end of list, sew whole thing into vi->rq.pages. */ |
| for (end = page; end->private; end = (struct page *)end->private); |
| end->private = (unsigned long)rq->pages; |
| rq->pages = page; |
| } |
| |
| static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask) |
| { |
| struct page *p = rq->pages; |
| |
| if (p) { |
| rq->pages = (struct page *)p->private; |
| /* clear private here, it is used to chain pages */ |
| p->private = 0; |
| } else |
| p = alloc_page(gfp_mask); |
| return p; |
| } |
| |
| static void enable_delayed_refill(struct virtnet_info *vi) |
| { |
| spin_lock_bh(&vi->refill_lock); |
| vi->refill_enabled = true; |
| spin_unlock_bh(&vi->refill_lock); |
| } |
| |
| static void disable_delayed_refill(struct virtnet_info *vi) |
| { |
| spin_lock_bh(&vi->refill_lock); |
| vi->refill_enabled = false; |
| spin_unlock_bh(&vi->refill_lock); |
| } |
| |
| static void virtqueue_napi_schedule(struct napi_struct *napi, |
| struct virtqueue *vq) |
| { |
| if (napi_schedule_prep(napi)) { |
| virtqueue_disable_cb(vq); |
| __napi_schedule(napi); |
| } |
| } |
| |
| static void virtqueue_napi_complete(struct napi_struct *napi, |
| struct virtqueue *vq, int processed) |
| { |
| int opaque; |
| |
| opaque = virtqueue_enable_cb_prepare(vq); |
| if (napi_complete_done(napi, processed)) { |
| if (unlikely(virtqueue_poll(vq, opaque))) |
| virtqueue_napi_schedule(napi, vq); |
| } else { |
| virtqueue_disable_cb(vq); |
| } |
| } |
| |
| static void skb_xmit_done(struct virtqueue *vq) |
| { |
| struct virtnet_info *vi = vq->vdev->priv; |
| struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi; |
| |
| /* Suppress further interrupts. */ |
| virtqueue_disable_cb(vq); |
| |
| if (napi->weight) |
| virtqueue_napi_schedule(napi, vq); |
| else |
| /* We were probably waiting for more output buffers. */ |
| netif_wake_subqueue(vi->dev, vq2txq(vq)); |
| } |
| |
| #define MRG_CTX_HEADER_SHIFT 22 |
| static void *mergeable_len_to_ctx(unsigned int truesize, |
| unsigned int headroom) |
| { |
| return (void *)(unsigned long)((headroom << MRG_CTX_HEADER_SHIFT) | truesize); |
| } |
| |
| static unsigned int mergeable_ctx_to_headroom(void *mrg_ctx) |
| { |
| return (unsigned long)mrg_ctx >> MRG_CTX_HEADER_SHIFT; |
| } |
| |
| static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx) |
| { |
| return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1); |
| } |
| |
| /* Called from bottom half context */ |
| 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, |
| bool hdr_valid, unsigned int metasize, |
| unsigned int headroom) |
| { |
| struct sk_buff *skb; |
| struct virtio_net_hdr_mrg_rxbuf *hdr; |
| unsigned int copy, hdr_len, hdr_padded_len; |
| struct page *page_to_free = NULL; |
| int tailroom, shinfo_size; |
| char *p, *hdr_p, *buf; |
| |
| p = page_address(page) + offset; |
| hdr_p = p; |
| |
| hdr_len = vi->hdr_len; |
| if (vi->mergeable_rx_bufs) |
| hdr_padded_len = hdr_len; |
| else |
| hdr_padded_len = sizeof(struct padded_vnet_hdr); |
| |
| /* If headroom is not 0, there is an offset between the beginning of the |
| * data and the allocated space, otherwise the data and the allocated |
| * space are aligned. |
| * |
| * Buffers with headroom use PAGE_SIZE as alloc size, see |
| * add_recvbuf_mergeable() + get_mergeable_buf_len() |
| */ |
| truesize = headroom ? PAGE_SIZE : truesize; |
| tailroom = truesize - headroom; |
| buf = p - headroom; |
| |
| len -= hdr_len; |
| offset += hdr_padded_len; |
| p += hdr_padded_len; |
| tailroom -= hdr_padded_len + len; |
| |
| shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); |
| |
| /* copy small packet so we can reuse these pages */ |
| if (!NET_IP_ALIGN && len > GOOD_COPY_LEN && tailroom >= shinfo_size) { |
| skb = build_skb(buf, truesize); |
| if (unlikely(!skb)) |
| return NULL; |
| |
| skb_reserve(skb, p - buf); |
| skb_put(skb, len); |
| |
| page = (struct page *)page->private; |
| if (page) |
| give_pages(rq, page); |
| goto ok; |
| } |
| |
| /* copy small packet so we can reuse these pages for small data */ |
| skb = napi_alloc_skb(&rq->napi, GOOD_COPY_LEN); |
| if (unlikely(!skb)) |
| return NULL; |
| |
| /* Copy all frame if it fits skb->head, otherwise |
| * we let virtio_net_hdr_to_skb() and GRO pull headers as needed. |
| */ |
| if (len <= skb_tailroom(skb)) |
| copy = len; |
| else |
| copy = ETH_HLEN + metasize; |
| skb_put_data(skb, p, copy); |
| |
| len -= copy; |
| offset += copy; |
| |
| if (vi->mergeable_rx_bufs) { |
| if (len) |
| skb_add_rx_frag(skb, 0, page, offset, len, truesize); |
| else |
| page_to_free = page; |
| goto ok; |
| } |
| |
| /* |
| * Verify that we can indeed put this data into a skb. |
| * This is here to handle cases when the device erroneously |
| * tries to receive more than is possible. This is usually |
| * the case of a broken device. |
| */ |
| if (unlikely(len > MAX_SKB_FRAGS * PAGE_SIZE)) { |
| net_dbg_ratelimited("%s: too much data\n", skb->dev->name); |
| dev_kfree_skb(skb); |
| return NULL; |
| } |
| BUG_ON(offset >= PAGE_SIZE); |
| while (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; |
| } |
| |
| if (page) |
| give_pages(rq, page); |
| |
| ok: |
| /* hdr_valid means no XDP, so we can copy the vnet header */ |
| if (hdr_valid) { |
| hdr = skb_vnet_hdr(skb); |
| memcpy(hdr, hdr_p, hdr_len); |
| } |
| if (page_to_free) |
| put_page(page_to_free); |
| |
| if (metasize) { |
| __skb_pull(skb, metasize); |
| skb_metadata_set(skb, metasize); |
| } |
| |
| return skb; |
| } |
| |
| static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, |
| struct send_queue *sq, |
| struct xdp_frame *xdpf) |
| { |
| struct virtio_net_hdr_mrg_rxbuf *hdr; |
| int err; |
| |
| if (unlikely(xdpf->headroom < vi->hdr_len)) |
| return -EOVERFLOW; |
| |
| /* Make room for virtqueue hdr (also change xdpf->headroom?) */ |
| xdpf->data -= vi->hdr_len; |
| /* Zero header and leave csum up to XDP layers */ |
| hdr = xdpf->data; |
| memset(hdr, 0, vi->hdr_len); |
| xdpf->len += vi->hdr_len; |
| |
| sg_init_one(sq->sg, xdpf->data, xdpf->len); |
| |
| err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf), |
| GFP_ATOMIC); |
| if (unlikely(err)) |
| return -ENOSPC; /* Caller handle free/refcnt */ |
| |
| return 0; |
| } |
| |
| /* when vi->curr_queue_pairs > nr_cpu_ids, the txq/sq is only used for xdp tx on |
| * the current cpu, so it does not need to be locked. |
| * |
| * Here we use marco instead of inline functions because we have to deal with |
| * three issues at the same time: 1. the choice of sq. 2. judge and execute the |
| * lock/unlock of txq 3. make sparse happy. It is difficult for two inline |
| * functions to perfectly solve these three problems at the same time. |
| */ |
| #define virtnet_xdp_get_sq(vi) ({ \ |
| int cpu = smp_processor_id(); \ |
| struct netdev_queue *txq; \ |
| typeof(vi) v = (vi); \ |
| unsigned int qp; \ |
| \ |
| if (v->curr_queue_pairs > nr_cpu_ids) { \ |
| qp = v->curr_queue_pairs - v->xdp_queue_pairs; \ |
| qp += cpu; \ |
| txq = netdev_get_tx_queue(v->dev, qp); \ |
| __netif_tx_acquire(txq); \ |
| } else { \ |
| qp = cpu % v->curr_queue_pairs; \ |
| txq = netdev_get_tx_queue(v->dev, qp); \ |
| __netif_tx_lock(txq, cpu); \ |
| } \ |
| v->sq + qp; \ |
| }) |
| |
| #define virtnet_xdp_put_sq(vi, q) { \ |
| struct netdev_queue *txq; \ |
| typeof(vi) v = (vi); \ |
| \ |
| txq = netdev_get_tx_queue(v->dev, (q) - v->sq); \ |
| if (v->curr_queue_pairs > nr_cpu_ids) \ |
| __netif_tx_release(txq); \ |
| else \ |
| __netif_tx_unlock(txq); \ |
| } |
| |
| static int virtnet_xdp_xmit(struct net_device *dev, |
| int n, struct xdp_frame **frames, u32 flags) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| struct receive_queue *rq = vi->rq; |
| struct bpf_prog *xdp_prog; |
| struct send_queue *sq; |
| unsigned int len; |
| int packets = 0; |
| int bytes = 0; |
| int nxmit = 0; |
| int kicks = 0; |
| void *ptr; |
| int ret; |
| int i; |
| |
| /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this |
| * indicate XDP resources have been successfully allocated. |
| */ |
| xdp_prog = rcu_access_pointer(rq->xdp_prog); |
| if (!xdp_prog) |
| return -ENXIO; |
| |
| sq = virtnet_xdp_get_sq(vi); |
| |
| if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { |
| ret = -EINVAL; |
| goto out; |
| } |
| |
| /* Free up any pending old buffers before queueing new ones. */ |
| while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { |
| if (likely(is_xdp_frame(ptr))) { |
| struct xdp_frame *frame = ptr_to_xdp(ptr); |
| |
| bytes += frame->len; |
| xdp_return_frame(frame); |
| } else { |
| struct sk_buff *skb = ptr; |
| |
| bytes += skb->len; |
| napi_consume_skb(skb, false); |
| } |
| packets++; |
| } |
| |
| for (i = 0; i < n; i++) { |
| struct xdp_frame *xdpf = frames[i]; |
| |
| if (__virtnet_xdp_xmit_one(vi, sq, xdpf)) |
| break; |
| nxmit++; |
| } |
| ret = nxmit; |
| |
| if (flags & XDP_XMIT_FLUSH) { |
| if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) |
| kicks = 1; |
| } |
| out: |
| u64_stats_update_begin(&sq->stats.syncp); |
| sq->stats.bytes += bytes; |
| sq->stats.packets += packets; |
| sq->stats.xdp_tx += n; |
| sq->stats.xdp_tx_drops += n - nxmit; |
| sq->stats.kicks += kicks; |
| u64_stats_update_end(&sq->stats.syncp); |
| |
| virtnet_xdp_put_sq(vi, sq); |
| return ret; |
| } |
| |
| static unsigned int virtnet_get_headroom(struct virtnet_info *vi) |
| { |
| return vi->xdp_enabled ? VIRTIO_XDP_HEADROOM : 0; |
| } |
| |
| /* We copy the packet for XDP in the following cases: |
| * |
| * 1) Packet is scattered across multiple rx buffers. |
| * 2) Headroom space is insufficient. |
| * |
| * This is inefficient but it's a temporary condition that |
| * we hit right after XDP is enabled and until queue is refilled |
| * with large buffers with sufficient headroom - so it should affect |
| * at most queue size packets. |
| * Afterwards, the conditions to enable |
| * XDP should preclude the underlying device from sending packets |
| * across multiple buffers (num_buf > 1), and we make sure buffers |
| * have enough headroom. |
| */ |
| static struct page *xdp_linearize_page(struct receive_queue *rq, |
| u16 *num_buf, |
| struct page *p, |
| int offset, |
| int page_off, |
| unsigned int *len) |
| { |
| int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); |
| struct page *page; |
| |
| if (page_off + *len + tailroom > PAGE_SIZE) |
| return NULL; |
| |
| page = alloc_page(GFP_ATOMIC); |
| if (!page) |
| return NULL; |
| |
| memcpy(page_address(page) + page_off, page_address(p) + offset, *len); |
| page_off += *len; |
| |
| while (--*num_buf) { |
| unsigned int buflen; |
| void *buf; |
| int off; |
| |
| buf = virtqueue_get_buf(rq->vq, &buflen); |
| if (unlikely(!buf)) |
| goto err_buf; |
| |
| p = virt_to_head_page(buf); |
| off = buf - page_address(p); |
| |
| /* guard against a misconfigured or uncooperative backend that |
| * is sending packet larger than the MTU. |
| */ |
| if ((page_off + buflen + tailroom) > PAGE_SIZE) { |
| put_page(p); |
| goto err_buf; |
| } |
| |
| memcpy(page_address(page) + page_off, |
| page_address(p) + off, buflen); |
| page_off += buflen; |
| put_page(p); |
| } |
| |
| /* Headroom does not contribute to packet length */ |
| *len = page_off - VIRTIO_XDP_HEADROOM; |
| return page; |
| err_buf: |
| __free_pages(page, 0); |
| return NULL; |
| } |
| |
| static struct sk_buff *receive_small(struct net_device *dev, |
| struct virtnet_info *vi, |
| struct receive_queue *rq, |
| void *buf, void *ctx, |
| unsigned int len, |
| unsigned int *xdp_xmit, |
| struct virtnet_rq_stats *stats) |
| { |
| struct sk_buff *skb; |
| struct bpf_prog *xdp_prog; |
| unsigned int xdp_headroom = (unsigned long)ctx; |
| unsigned int header_offset = VIRTNET_RX_PAD + xdp_headroom; |
| unsigned int headroom = vi->hdr_len + header_offset; |
| unsigned int buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + |
| SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); |
| struct page *page = virt_to_head_page(buf); |
| unsigned int delta = 0; |
| struct page *xdp_page; |
| int err; |
| unsigned int metasize = 0; |
| |
| len -= vi->hdr_len; |
| stats->bytes += len; |
| |
| if (unlikely(len > GOOD_PACKET_LEN)) { |
| pr_debug("%s: rx error: len %u exceeds max size %d\n", |
| dev->name, len, GOOD_PACKET_LEN); |
| dev->stats.rx_length_errors++; |
| goto err; |
| } |
| |
| if (likely(!vi->xdp_enabled)) { |
| xdp_prog = NULL; |
| goto skip_xdp; |
| } |
| |
| rcu_read_lock(); |
| xdp_prog = rcu_dereference(rq->xdp_prog); |
| if (xdp_prog) { |
| struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset; |
| struct xdp_frame *xdpf; |
| struct xdp_buff xdp; |
| void *orig_data; |
| u32 act; |
| |
| if (unlikely(hdr->hdr.gso_type)) |
| goto err_xdp; |
| |
| if (unlikely(xdp_headroom < virtnet_get_headroom(vi))) { |
| int offset = buf - page_address(page) + header_offset; |
| unsigned int tlen = len + vi->hdr_len; |
| u16 num_buf = 1; |
| |
| xdp_headroom = virtnet_get_headroom(vi); |
| header_offset = VIRTNET_RX_PAD + xdp_headroom; |
| headroom = vi->hdr_len + header_offset; |
| buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + |
| SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); |
| xdp_page = xdp_linearize_page(rq, &num_buf, page, |
| offset, header_offset, |
| &tlen); |
| if (!xdp_page) |
| goto err_xdp; |
| |
| buf = page_address(xdp_page); |
| put_page(page); |
| page = xdp_page; |
| } |
| |
| xdp_init_buff(&xdp, buflen, &rq->xdp_rxq); |
| xdp_prepare_buff(&xdp, buf + VIRTNET_RX_PAD + vi->hdr_len, |
| xdp_headroom, len, true); |
| orig_data = xdp.data; |
| act = bpf_prog_run_xdp(xdp_prog, &xdp); |
| stats->xdp_packets++; |
| |
| switch (act) { |
| case XDP_PASS: |
| /* Recalculate length in case bpf program changed it */ |
| delta = orig_data - xdp.data; |
| len = xdp.data_end - xdp.data; |
| metasize = xdp.data - xdp.data_meta; |
| break; |
| case XDP_TX: |
| stats->xdp_tx++; |
| xdpf = xdp_convert_buff_to_frame(&xdp); |
| if (unlikely(!xdpf)) |
| goto err_xdp; |
| err = virtnet_xdp_xmit(dev, 1, &xdpf, 0); |
| if (unlikely(!err)) { |
| xdp_return_frame_rx_napi(xdpf); |
| } else if (unlikely(err < 0)) { |
| trace_xdp_exception(vi->dev, xdp_prog, act); |
| goto err_xdp; |
| } |
| *xdp_xmit |= VIRTIO_XDP_TX; |
| rcu_read_unlock(); |
| goto xdp_xmit; |
| case XDP_REDIRECT: |
| stats->xdp_redirects++; |
| err = xdp_do_redirect(dev, &xdp, xdp_prog); |
| if (err) |
| goto err_xdp; |
| *xdp_xmit |= VIRTIO_XDP_REDIR; |
| rcu_read_unlock(); |
| goto xdp_xmit; |
| default: |
| bpf_warn_invalid_xdp_action(vi->dev, xdp_prog, act); |
| fallthrough; |
| case XDP_ABORTED: |
| trace_xdp_exception(vi->dev, xdp_prog, act); |
| goto err_xdp; |
| case XDP_DROP: |
| goto err_xdp; |
| } |
| } |
| rcu_read_unlock(); |
| |
| skip_xdp: |
| skb = build_skb(buf, buflen); |
| if (!skb) |
| goto err; |
| skb_reserve(skb, headroom - delta); |
| skb_put(skb, len); |
| if (!xdp_prog) { |
| buf += header_offset; |
| memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len); |
| } /* keep zeroed vnet hdr since XDP is loaded */ |
| |
| if (metasize) |
| skb_metadata_set(skb, metasize); |
| |
| return skb; |
| |
| err_xdp: |
| rcu_read_unlock(); |
| stats->xdp_drops++; |
| err: |
| stats->drops++; |
| put_page(page); |
| xdp_xmit: |
| return NULL; |
| } |
| |
| static struct sk_buff *receive_big(struct net_device *dev, |
| struct virtnet_info *vi, |
| struct receive_queue *rq, |
| void *buf, |
| unsigned int len, |
| struct virtnet_rq_stats *stats) |
| { |
| struct page *page = buf; |
| struct sk_buff *skb = |
| page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, true, 0, 0); |
| |
| stats->bytes += len - vi->hdr_len; |
| if (unlikely(!skb)) |
| goto err; |
| |
| return skb; |
| |
| err: |
| stats->drops++; |
| give_pages(rq, page); |
| return NULL; |
| } |
| |
| static struct sk_buff *receive_mergeable(struct net_device *dev, |
| struct virtnet_info *vi, |
| struct receive_queue *rq, |
| void *buf, |
| void *ctx, |
| unsigned int len, |
| unsigned int *xdp_xmit, |
| struct virtnet_rq_stats *stats) |
| { |
| 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); |
| struct sk_buff *head_skb, *curr_skb; |
| struct bpf_prog *xdp_prog; |
| unsigned int truesize = mergeable_ctx_to_truesize(ctx); |
| unsigned int headroom = mergeable_ctx_to_headroom(ctx); |
| unsigned int metasize = 0; |
| unsigned int frame_sz; |
| int err; |
| |
| head_skb = NULL; |
| stats->bytes += len - vi->hdr_len; |
| |
| if (unlikely(len > truesize)) { |
| pr_debug("%s: rx error: len %u exceeds truesize %lu\n", |
| dev->name, len, (unsigned long)ctx); |
| dev->stats.rx_length_errors++; |
| goto err_skb; |
| } |
| |
| if (likely(!vi->xdp_enabled)) { |
| xdp_prog = NULL; |
| goto skip_xdp; |
| } |
| |
| rcu_read_lock(); |
| xdp_prog = rcu_dereference(rq->xdp_prog); |
| if (xdp_prog) { |
| struct xdp_frame *xdpf; |
| struct page *xdp_page; |
| struct xdp_buff xdp; |
| void *data; |
| u32 act; |
| |
| /* Transient failure which in theory could occur if |
| * in-flight packets from before XDP was enabled reach |
| * the receive path after XDP is loaded. |
| */ |
| if (unlikely(hdr->hdr.gso_type)) |
| goto err_xdp; |
| |
| /* Buffers with headroom use PAGE_SIZE as alloc size, |
| * see add_recvbuf_mergeable() + get_mergeable_buf_len() |
| */ |
| frame_sz = headroom ? PAGE_SIZE : truesize; |
| |
| /* This happens when rx buffer size is underestimated |
| * or headroom is not enough because of the buffer |
| * was refilled before XDP is set. This should only |
| * happen for the first several packets, so we don't |
| * care much about its performance. |
| */ |
| if (unlikely(num_buf > 1 || |
| headroom < virtnet_get_headroom(vi))) { |
| /* linearize data for XDP */ |
| xdp_page = xdp_linearize_page(rq, &num_buf, |
| page, offset, |
| VIRTIO_XDP_HEADROOM, |
| &len); |
| frame_sz = PAGE_SIZE; |
| |
| if (!xdp_page) |
| goto err_xdp; |
| offset = VIRTIO_XDP_HEADROOM; |
| } else { |
| xdp_page = page; |
| } |
| |
| /* Allow consuming headroom but reserve enough space to push |
| * the descriptor on if we get an XDP_TX return code. |
| */ |
| data = page_address(xdp_page) + offset; |
| xdp_init_buff(&xdp, frame_sz - vi->hdr_len, &rq->xdp_rxq); |
| xdp_prepare_buff(&xdp, data - VIRTIO_XDP_HEADROOM + vi->hdr_len, |
| VIRTIO_XDP_HEADROOM, len - vi->hdr_len, true); |
| |
| act = bpf_prog_run_xdp(xdp_prog, &xdp); |
| stats->xdp_packets++; |
| |
| switch (act) { |
| case XDP_PASS: |
| metasize = xdp.data - xdp.data_meta; |
| |
| /* recalculate offset to account for any header |
| * adjustments and minus the metasize to copy the |
| * metadata in page_to_skb(). Note other cases do not |
| * build an skb and avoid using offset |
| */ |
| offset = xdp.data - page_address(xdp_page) - |
| vi->hdr_len - metasize; |
| |
| /* recalculate len if xdp.data, xdp.data_end or |
| * xdp.data_meta were adjusted |
| */ |
| len = xdp.data_end - xdp.data + vi->hdr_len + metasize; |
| |
| /* recalculate headroom if xdp.data or xdp_data_meta |
| * were adjusted, note that offset should always point |
| * to the start of the reserved bytes for virtio_net |
| * header which are followed by xdp.data, that means |
| * that offset is equal to the headroom (when buf is |
| * starting at the beginning of the page, otherwise |
| * there is a base offset inside the page) but it's used |
| * with a different starting point (buf start) than |
| * xdp.data (buf start + vnet hdr size). If xdp.data or |
| * data_meta were adjusted by the xdp prog then the |
| * headroom size has changed and so has the offset, we |
| * can use data_hard_start, which points at buf start + |
| * vnet hdr size, to calculate the new headroom and use |
| * it later to compute buf start in page_to_skb() |
| */ |
| headroom = xdp.data - xdp.data_hard_start - metasize; |
| |
| /* We can only create skb based on xdp_page. */ |
| if (unlikely(xdp_page != page)) { |
| rcu_read_unlock(); |
| put_page(page); |
| head_skb = page_to_skb(vi, rq, xdp_page, offset, |
| len, PAGE_SIZE, false, |
| metasize, |
| headroom); |
| return head_skb; |
| } |
| break; |
| case XDP_TX: |
| stats->xdp_tx++; |
| xdpf = xdp_convert_buff_to_frame(&xdp); |
| if (unlikely(!xdpf)) { |
| if (unlikely(xdp_page != page)) |
| put_page(xdp_page); |
| goto err_xdp; |
| } |
| err = virtnet_xdp_xmit(dev, 1, &xdpf, 0); |
| if (unlikely(!err)) { |
| xdp_return_frame_rx_napi(xdpf); |
| } else if (unlikely(err < 0)) { |
| trace_xdp_exception(vi->dev, xdp_prog, act); |
| if (unlikely(xdp_page != page)) |
| put_page(xdp_page); |
| goto err_xdp; |
| } |
| *xdp_xmit |= VIRTIO_XDP_TX; |
| if (unlikely(xdp_page != page)) |
| put_page(page); |
| rcu_read_unlock(); |
| goto xdp_xmit; |
| case XDP_REDIRECT: |
| stats->xdp_redirects++; |
| err = xdp_do_redirect(dev, &xdp, xdp_prog); |
| if (err) { |
| if (unlikely(xdp_page != page)) |
| put_page(xdp_page); |
| goto err_xdp; |
| } |
| *xdp_xmit |= VIRTIO_XDP_REDIR; |
| if (unlikely(xdp_page != page)) |
| put_page(page); |
| rcu_read_unlock(); |
| goto xdp_xmit; |
| default: |
| bpf_warn_invalid_xdp_action(vi->dev, xdp_prog, act); |
| fallthrough; |
| case XDP_ABORTED: |
| trace_xdp_exception(vi->dev, xdp_prog, act); |
| fallthrough; |
| case XDP_DROP: |
| if (unlikely(xdp_page != page)) |
| __free_pages(xdp_page, 0); |
| goto err_xdp; |
| } |
| } |
| rcu_read_unlock(); |
| |
| skip_xdp: |
| head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog, |
| metasize, headroom); |
| curr_skb = head_skb; |
| |
| if (unlikely(!curr_skb)) |
| goto err_skb; |
| while (--num_buf) { |
| int num_skb_frags; |
| |
| buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx); |
| if (unlikely(!buf)) { |
| 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; |
| } |
| |
| stats->bytes += len; |
| page = virt_to_head_page(buf); |
| |
| truesize = mergeable_ctx_to_truesize(ctx); |
| if (unlikely(len > truesize)) { |
| pr_debug("%s: rx error: len %u exceeds truesize %lu\n", |
| dev->name, len, (unsigned long)ctx); |
| dev->stats.rx_length_errors++; |
| goto err_skb; |
| } |
| |
| 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; |
| } |
| 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); |
| } |
| } |
| |
| ewma_pkt_len_add(&rq->mrg_avg_pkt_len, head_skb->len); |
| return head_skb; |
| |
| err_xdp: |
| rcu_read_unlock(); |
| stats->xdp_drops++; |
| err_skb: |
| put_page(page); |
| while (num_buf-- > 1) { |
| buf = virtqueue_get_buf(rq->vq, &len); |
| if (unlikely(!buf)) { |
| pr_debug("%s: rx error: %d buffers missing\n", |
| dev->name, num_buf); |
| dev->stats.rx_length_errors++; |
| break; |
| } |
| stats->bytes += len; |
| page = virt_to_head_page(buf); |
| put_page(page); |
| } |
| err_buf: |
| stats->drops++; |
| dev_kfree_skb(head_skb); |
| xdp_xmit: |
| return NULL; |
| } |
| |
| static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash, |
| struct sk_buff *skb) |
| { |
| enum pkt_hash_types rss_hash_type; |
| |
| if (!hdr_hash || !skb) |
| return; |
| |
| switch (__le16_to_cpu(hdr_hash->hash_report)) { |
| case VIRTIO_NET_HASH_REPORT_TCPv4: |
| case VIRTIO_NET_HASH_REPORT_UDPv4: |
| case VIRTIO_NET_HASH_REPORT_TCPv6: |
| case VIRTIO_NET_HASH_REPORT_UDPv6: |
| case VIRTIO_NET_HASH_REPORT_TCPv6_EX: |
| case VIRTIO_NET_HASH_REPORT_UDPv6_EX: |
| rss_hash_type = PKT_HASH_TYPE_L4; |
| break; |
| case VIRTIO_NET_HASH_REPORT_IPv4: |
| case VIRTIO_NET_HASH_REPORT_IPv6: |
| case VIRTIO_NET_HASH_REPORT_IPv6_EX: |
| rss_hash_type = PKT_HASH_TYPE_L3; |
| break; |
| case VIRTIO_NET_HASH_REPORT_NONE: |
| default: |
| rss_hash_type = PKT_HASH_TYPE_NONE; |
| } |
| skb_set_hash(skb, __le32_to_cpu(hdr_hash->hash_value), rss_hash_type); |
| } |
| |
| static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, |
| void *buf, unsigned int len, void **ctx, |
| unsigned int *xdp_xmit, |
| struct virtnet_rq_stats *stats) |
| { |
| struct net_device *dev = vi->dev; |
| struct sk_buff *skb; |
| struct virtio_net_hdr_mrg_rxbuf *hdr; |
| |
| 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) { |
| put_page(virt_to_head_page(buf)); |
| } else if (vi->big_packets) { |
| give_pages(rq, buf); |
| } else { |
| put_page(virt_to_head_page(buf)); |
| } |
| return; |
| } |
| |
| if (vi->mergeable_rx_bufs) |
| skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, |
| stats); |
| else if (vi->big_packets) |
| skb = receive_big(dev, vi, rq, buf, len, stats); |
| else |
| skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); |
| |
| if (unlikely(!skb)) |
| return; |
| |
| hdr = skb_vnet_hdr(skb); |
| if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report) |
| virtio_skb_set_hash((const struct virtio_net_hdr_v1_hash *)hdr, skb); |
| |
| if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) |
| skb->ip_summed = CHECKSUM_UNNECESSARY; |
| |
| if (virtio_net_hdr_to_skb(skb, &hdr->hdr, |
| virtio_is_little_endian(vi->vdev))) { |
| net_warn_ratelimited("%s: bad gso: type: %u, size: %u\n", |
| dev->name, hdr->hdr.gso_type, |
| hdr->hdr.gso_size); |
| goto frame_err; |
| } |
| |
| skb_record_rx_queue(skb, vq2rxq(rq->vq)); |
| skb->protocol = eth_type_trans(skb, dev); |
| pr_debug("Receiving skb proto 0x%04x len %i type %i\n", |
| ntohs(skb->protocol), skb->len, skb->pkt_type); |
| |
| napi_gro_receive(&rq->napi, skb); |
| return; |
| |
| frame_err: |
| dev->stats.rx_frame_errors++; |
| dev_kfree_skb(skb); |
| } |
| |
| /* Unlike mergeable buffers, all buffers are allocated to the |
| * same size, except for the headroom. For this reason we do |
| * not need to use mergeable_len_to_ctx here - it is enough |
| * to store the headroom as the context ignoring the truesize. |
| */ |
| static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq, |
| gfp_t gfp) |
| { |
| struct page_frag *alloc_frag = &rq->alloc_frag; |
| char *buf; |
| unsigned int xdp_headroom = virtnet_get_headroom(vi); |
| void *ctx = (void *)(unsigned long)xdp_headroom; |
| int len = vi->hdr_len + VIRTNET_RX_PAD + GOOD_PACKET_LEN + xdp_headroom; |
| int err; |
| |
| len = SKB_DATA_ALIGN(len) + |
| SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); |
| if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp))) |
| return -ENOMEM; |
| |
| buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; |
| get_page(alloc_frag->page); |
| alloc_frag->offset += len; |
| sg_init_one(rq->sg, buf + VIRTNET_RX_PAD + xdp_headroom, |
| vi->hdr_len + GOOD_PACKET_LEN); |
| err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp); |
| if (err < 0) |
| put_page(virt_to_head_page(buf)); |
| return err; |
| } |
| |
| 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, vi->big_packets_num_skbfrags + 2); |
| |
| /* page in rq->sg[vi->big_packets_num_skbfrags + 1] is list tail */ |
| for (i = vi->big_packets_num_skbfrags + 1; i > 1; --i) { |
| first = get_a_page(rq, gfp); |
| if (!first) { |
| if (list) |
| give_pages(rq, list); |
| return -ENOMEM; |
| } |
| sg_set_buf(&rq->sg[i], page_address(first), PAGE_SIZE); |
| |
| /* chain new page in list head to match sg */ |
| first->private = (unsigned long)list; |
| list = first; |
| } |
| |
| first = get_a_page(rq, gfp); |
| if (!first) { |
| give_pages(rq, list); |
| return -ENOMEM; |
| } |
| p = page_address(first); |
| |
| /* rq->sg[0], rq->sg[1] share the same page */ |
| /* 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); |
| sg_set_buf(&rq->sg[1], p + offset, PAGE_SIZE - offset); |
| |
| /* chain first in list head */ |
| first->private = (unsigned long)list; |
| err = virtqueue_add_inbuf(rq->vq, rq->sg, vi->big_packets_num_skbfrags + 2, |
| first, gfp); |
| if (err < 0) |
| give_pages(rq, first); |
| |
| return err; |
| } |
| |
| static unsigned int get_mergeable_buf_len(struct receive_queue *rq, |
| struct ewma_pkt_len *avg_pkt_len, |
| unsigned int room) |
| { |
| struct virtnet_info *vi = rq->vq->vdev->priv; |
| const size_t hdr_len = vi->hdr_len; |
| unsigned int len; |
| |
| if (room) |
| return PAGE_SIZE - room; |
| |
| len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len), |
| rq->min_buf_len, PAGE_SIZE - hdr_len); |
| |
| return ALIGN(len, L1_CACHE_BYTES); |
| } |
| |
| static int add_recvbuf_mergeable(struct virtnet_info *vi, |
| struct receive_queue *rq, gfp_t gfp) |
| { |
| struct page_frag *alloc_frag = &rq->alloc_frag; |
| unsigned int headroom = virtnet_get_headroom(vi); |
| unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; |
| unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); |
| char *buf; |
| void *ctx; |
| int err; |
| unsigned int len, hole; |
| |
| /* Extra tailroom is needed to satisfy XDP's assumption. This |
| * means rx frags coalescing won't work, but consider we've |
| * disabled GSO for XDP, it won't be a big issue. |
| */ |
| len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room); |
| if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp))) |
| return -ENOMEM; |
| |
| buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; |
| buf += headroom; /* advance address leaving hole at front of pkt */ |
| get_page(alloc_frag->page); |
| alloc_frag->offset += len + room; |
| hole = alloc_frag->size - alloc_frag->offset; |
| if (hole < len + room) { |
| /* To avoid internal fragmentation, if there is very likely not |
| * enough space for another buffer, add the remaining space to |
| * the current buffer. |
| */ |
| len += hole; |
| alloc_frag->offset += hole; |
| } |
| |
| sg_init_one(rq->sg, buf, len); |
| ctx = mergeable_len_to_ctx(len, headroom); |
| err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp); |
| if (err < 0) |
| put_page(virt_to_head_page(buf)); |
| |
| return err; |
| } |
| |
| /* |
| * Returns false if we couldn't fill entirely (OOM). |
| * |
| * Normally run in the receive path, but can also be run from ndo_open |
| * before we're receiving packets, or from refill_work which is |
| * careful to disable receiving (using napi_disable). |
| */ |
| static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq, |
| gfp_t gfp) |
| { |
| int err; |
| bool oom; |
| |
| do { |
| if (vi->mergeable_rx_bufs) |
| err = add_recvbuf_mergeable(vi, rq, gfp); |
| else if (vi->big_packets) |
| err = add_recvbuf_big(vi, rq, gfp); |
| else |
| err = add_recvbuf_small(vi, rq, gfp); |
| |
| oom = err == -ENOMEM; |
| if (err) |
| break; |
| } while (rq->vq->num_free); |
| if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) { |
| unsigned long flags; |
| |
| flags = u64_stats_update_begin_irqsave(&rq->stats.syncp); |
| rq->stats.kicks++; |
| u64_stats_update_end_irqrestore(&rq->stats.syncp, flags); |
| } |
| |
| return !oom; |
| } |
| |
| static void skb_recv_done(struct virtqueue *rvq) |
| { |
| struct virtnet_info *vi = rvq->vdev->priv; |
| struct receive_queue *rq = &vi->rq[vq2rxq(rvq)]; |
| |
| virtqueue_napi_schedule(&rq->napi, rvq); |
| } |
| |
| static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi) |
| { |
| napi_enable(napi); |
| |
| /* If all buffers were filled by other side before we napi_enabled, we |
| * won't get another interrupt, so process any outstanding packets now. |
| * Call local_bh_enable after to trigger softIRQ processing. |
| */ |
| local_bh_disable(); |
| virtqueue_napi_schedule(napi, vq); |
| local_bh_enable(); |
| } |
| |
| static void virtnet_napi_tx_enable(struct virtnet_info *vi, |
| struct virtqueue *vq, |
| struct napi_struct *napi) |
| { |
| if (!napi->weight) |
| return; |
| |
| /* Tx napi touches cachelines on the cpu handling tx interrupts. Only |
| * enable the feature if this is likely affine with the transmit path. |
| */ |
| if (!vi->affinity_hint_set) { |
| napi->weight = 0; |
| return; |
| } |
| |
| return virtnet_napi_enable(vq, napi); |
| } |
| |
| static void virtnet_napi_tx_disable(struct napi_struct *napi) |
| { |
| if (napi->weight) |
| napi_disable(napi); |
| } |
| |
| static void refill_work(struct work_struct *work) |
| { |
| struct virtnet_info *vi = |
| container_of(work, struct virtnet_info, refill.work); |
| bool still_empty; |
| int i; |
| |
| for (i = 0; i < vi->curr_queue_pairs; i++) { |
| struct receive_queue *rq = &vi->rq[i]; |
| |
| napi_disable(&rq->napi); |
| still_empty = !try_fill_recv(vi, rq, GFP_KERNEL); |
| virtnet_napi_enable(rq->vq, &rq->napi); |
| |
| /* In theory, this can happen: if we don't get any buffers in |
| * we will *never* try to fill again. |
| */ |
| if (still_empty) |
| schedule_delayed_work(&vi->refill, HZ/2); |
| } |
| } |
| |
| static int virtnet_receive(struct receive_queue *rq, int budget, |
| unsigned int *xdp_xmit) |
| { |
| struct virtnet_info *vi = rq->vq->vdev->priv; |
| struct virtnet_rq_stats stats = {}; |
| unsigned int len; |
| void *buf; |
| int i; |
| |
| if (!vi->big_packets || vi->mergeable_rx_bufs) { |
| void *ctx; |
| |
| while (stats.packets < budget && |
| (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) { |
| receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &stats); |
| stats.packets++; |
| } |
| } else { |
| while (stats.packets < budget && |
| (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) { |
| receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats); |
| stats.packets++; |
| } |
| } |
| |
| if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) { |
| if (!try_fill_recv(vi, rq, GFP_ATOMIC)) { |
| spin_lock(&vi->refill_lock); |
| if (vi->refill_enabled) |
| schedule_delayed_work(&vi->refill, 0); |
| spin_unlock(&vi->refill_lock); |
| } |
| } |
| |
| u64_stats_update_begin(&rq->stats.syncp); |
| for (i = 0; i < VIRTNET_RQ_STATS_LEN; i++) { |
| size_t offset = virtnet_rq_stats_desc[i].offset; |
| u64 *item; |
| |
| item = (u64 *)((u8 *)&rq->stats + offset); |
| *item += *(u64 *)((u8 *)&stats + offset); |
| } |
| u64_stats_update_end(&rq->stats.syncp); |
| |
| return stats.packets; |
| } |
| |
| static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) |
| { |
| unsigned int len; |
| unsigned int packets = 0; |
| unsigned int bytes = 0; |
| void *ptr; |
| |
| while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { |
| if (likely(!is_xdp_frame(ptr))) { |
| struct sk_buff *skb = ptr; |
| |
| pr_debug("Sent skb %p\n", skb); |
| |
| bytes += skb->len; |
| napi_consume_skb(skb, in_napi); |
| } else { |
| struct xdp_frame *frame = ptr_to_xdp(ptr); |
| |
| bytes += frame->len; |
| xdp_return_frame(frame); |
| } |
| packets++; |
| } |
| |
| /* Avoid overhead when no packets have been processed |
| * happens when called speculatively from start_xmit. |
| */ |
| if (!packets) |
| return; |
| |
| u64_stats_update_begin(&sq->stats.syncp); |
| sq->stats.bytes += bytes; |
| sq->stats.packets += packets; |
| u64_stats_update_end(&sq->stats.syncp); |
| } |
| |
| static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) |
| { |
| if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) |
| return false; |
| else if (q < vi->curr_queue_pairs) |
| return true; |
| else |
| return false; |
| } |
| |
| static void virtnet_poll_cleantx(struct receive_queue *rq) |
| { |
| struct virtnet_info *vi = rq->vq->vdev->priv; |
| unsigned int index = vq2rxq(rq->vq); |
| struct send_queue *sq = &vi->sq[index]; |
| struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index); |
| |
| if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index)) |
| return; |
| |
| if (__netif_tx_trylock(txq)) { |
| if (sq->reset) { |
| __netif_tx_unlock(txq); |
| return; |
| } |
| |
| do { |
| virtqueue_disable_cb(sq->vq); |
| free_old_xmit_skbs(sq, true); |
| } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq))); |
| |
| if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) |
| netif_tx_wake_queue(txq); |
| |
| __netif_tx_unlock(txq); |
| } |
| } |
| |
| static int virtnet_poll(struct napi_struct *napi, int budget) |
| { |
| struct receive_queue *rq = |
| container_of(napi, struct receive_queue, napi); |
| struct virtnet_info *vi = rq->vq->vdev->priv; |
| struct send_queue *sq; |
| unsigned int received; |
| unsigned int xdp_xmit = 0; |
| |
| virtnet_poll_cleantx(rq); |
| |
| received = virtnet_receive(rq, budget, &xdp_xmit); |
| |
| if (xdp_xmit & VIRTIO_XDP_REDIR) |
| xdp_do_flush(); |
| |
| /* Out of packets? */ |
| if (received < budget) |
| virtqueue_napi_complete(napi, rq->vq, received); |
| |
| if (xdp_xmit & VIRTIO_XDP_TX) { |
| sq = virtnet_xdp_get_sq(vi); |
| if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { |
| u64_stats_update_begin(&sq->stats.syncp); |
| sq->stats.kicks++; |
| u64_stats_update_end(&sq->stats.syncp); |
| } |
| virtnet_xdp_put_sq(vi, sq); |
| } |
| |
| return received; |
| } |
| |
| static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) |
| { |
| virtnet_napi_tx_disable(&vi->sq[qp_index].napi); |
| napi_disable(&vi->rq[qp_index].napi); |
| xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); |
| } |
| |
| static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) |
| { |
| struct net_device *dev = vi->dev; |
| int err; |
| |
| err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index, |
| vi->rq[qp_index].napi.napi_id); |
| if (err < 0) |
| return err; |
| |
| err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq, |
| MEM_TYPE_PAGE_SHARED, NULL); |
| if (err < 0) |
| goto err_xdp_reg_mem_model; |
| |
| virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); |
| virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); |
| |
| return 0; |
| |
| err_xdp_reg_mem_model: |
| xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); |
| return err; |
| } |
| |
| static int virtnet_open(struct net_device *dev) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| int i, err; |
| |
| enable_delayed_refill(vi); |
| |
| 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, &vi->rq[i], GFP_KERNEL)) |
| schedule_delayed_work(&vi->refill, 0); |
| |
| err = virtnet_enable_queue_pair(vi, i); |
| if (err < 0) |
| goto err_enable_qp; |
| } |
| |
| return 0; |
| |
| err_enable_qp: |
| disable_delayed_refill(vi); |
| cancel_delayed_work_sync(&vi->refill); |
| |
| for (i--; i >= 0; i--) |
| virtnet_disable_queue_pair(vi, i); |
| return err; |
| } |
| |
| static int virtnet_poll_tx(struct napi_struct *napi, int budget) |
| { |
| struct send_queue *sq = container_of(napi, struct send_queue, napi); |
| struct virtnet_info *vi = sq->vq->vdev->priv; |
| unsigned int index = vq2txq(sq->vq); |
| struct netdev_queue *txq; |
| int opaque; |
| bool done; |
| |
| if (unlikely(is_xdp_raw_buffer_queue(vi, index))) { |
| /* We don't need to enable cb for XDP */ |
| napi_complete_done(napi, 0); |
| return 0; |
| } |
| |
| txq = netdev_get_tx_queue(vi->dev, index); |
| __netif_tx_lock(txq, raw_smp_processor_id()); |
| virtqueue_disable_cb(sq->vq); |
| free_old_xmit_skbs(sq, true); |
| |
| if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) |
| netif_tx_wake_queue(txq); |
| |
| opaque = virtqueue_enable_cb_prepare(sq->vq); |
| |
| done = napi_complete_done(napi, 0); |
| |
| if (!done) |
| virtqueue_disable_cb(sq->vq); |
| |
| __netif_tx_unlock(txq); |
| |
| if (done) { |
| if (unlikely(virtqueue_poll(sq->vq, opaque))) { |
| if (napi_schedule_prep(napi)) { |
| __netif_tx_lock(txq, raw_smp_processor_id()); |
| virtqueue_disable_cb(sq->vq); |
| __netif_tx_unlock(txq); |
| __napi_schedule(napi); |
| } |
| } |
| } |
| |
| return 0; |
| } |
| |
| static int xmit_skb(struct send_queue *sq, struct sk_buff *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; |
| int 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 (virtio_net_hdr_from_skb(skb, &hdr->hdr, |
| virtio_is_little_endian(vi->vdev), false, |
| 0)) |
| return -EPROTO; |
| |
| if (vi->mergeable_rx_bufs) |
| hdr->num_buffers = 0; |
| |
| 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); |
| if (unlikely(num_sg < 0)) |
| return num_sg; |
| /* 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); |
| if (unlikely(num_sg < 0)) |
| return num_sg; |
| num_sg++; |
| } |
| return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC); |
| } |
| |
| static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| 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 = !netdev_xmit_more(); |
| bool use_napi = sq->napi.weight; |
| |
| /* Free up any pending old buffers before queueing new ones. */ |
| do { |
| if (use_napi) |
| virtqueue_disable_cb(sq->vq); |
| |
| free_old_xmit_skbs(sq, false); |
| |
| } while (use_napi && kick && |
| unlikely(!virtqueue_enable_cb_delayed(sq->vq))); |
| |
| /* timestamp packet in software */ |
| skb_tx_timestamp(skb); |
| |
| /* Try to transmit */ |
| err = xmit_skb(sq, skb); |
| |
| /* This should not happen! */ |
| if (unlikely(err)) { |
| dev->stats.tx_fifo_errors++; |
| if (net_ratelimit()) |
| dev_warn(&dev->dev, |
| "Unexpected TXQ (%d) queue failure: %d\n", |
| qnum, err); |
| dev->stats.tx_dropped++; |
| dev_kfree_skb_any(skb); |
| return NETDEV_TX_OK; |
| } |
| |
| /* Don't wait up for transmitted skbs to be freed. */ |
| if (!use_napi) { |
| skb_orphan(skb); |
| nf_reset_ct(skb); |
| } |
| |
| /* 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 (use_napi) { |
| if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) |
| virtqueue_napi_schedule(&sq->napi, sq->vq); |
| } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { |
| /* More just got used, free them then recheck. */ |
| free_old_xmit_skbs(sq, false); |
| if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { |
| netif_start_subqueue(dev, qnum); |
| virtqueue_disable_cb(sq->vq); |
| } |
| } |
| } |
| |
| if (kick || netif_xmit_stopped(txq)) { |
| if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { |
| u64_stats_update_begin(&sq->stats.syncp); |
| sq->stats.kicks++; |
| u64_stats_update_end(&sq->stats.syncp); |
| } |
| } |
| |
| return NETDEV_TX_OK; |
| } |
| |
| static int virtnet_rx_resize(struct virtnet_info *vi, |
| struct receive_queue *rq, u32 ring_num) |
| { |
| bool running = netif_running(vi->dev); |
| int err, qindex; |
| |
| qindex = rq - vi->rq; |
| |
| if (running) |
| napi_disable(&rq->napi); |
| |
| err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf); |
| if (err) |
| netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err); |
| |
| if (!try_fill_recv(vi, rq, GFP_KERNEL)) |
| schedule_delayed_work(&vi->refill, 0); |
| |
| if (running) |
| virtnet_napi_enable(rq->vq, &rq->napi); |
| return err; |
| } |
| |
| static int virtnet_tx_resize(struct virtnet_info *vi, |
| struct send_queue *sq, u32 ring_num) |
| { |
| bool running = netif_running(vi->dev); |
| struct netdev_queue *txq; |
| int err, qindex; |
| |
| qindex = sq - vi->sq; |
| |
| if (running) |
| virtnet_napi_tx_disable(&sq->napi); |
| |
| txq = netdev_get_tx_queue(vi->dev, qindex); |
| |
| /* 1. wait all ximt complete |
| * 2. fix the race of netif_stop_subqueue() vs netif_start_subqueue() |
| */ |
| __netif_tx_lock_bh(txq); |
| |
| /* Prevent rx poll from accessing sq. */ |
| sq->reset = true; |
| |
| /* Prevent the upper layer from trying to send packets. */ |
| netif_stop_subqueue(vi->dev, qindex); |
| |
| __netif_tx_unlock_bh(txq); |
| |
| err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf); |
| if (err) |
| netdev_err(vi->dev, "resize tx fail: tx queue index: %d err: %d\n", qindex, err); |
| |
| __netif_tx_lock_bh(txq); |
| sq->reset = false; |
| netif_tx_wake_queue(txq); |
| __netif_tx_unlock_bh(txq); |
| |
| if (running) |
| virtnet_napi_tx_enable(vi, sq->vq, &sq->napi); |
| return err; |
| } |
| |
| /* |
| * Send command via the control virtqueue and check status. Commands |
| * supported by the hypervisor, as indicated by feature bits, should |
| * never fail unless improperly formatted. |
| */ |
| static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, |
| struct scatterlist *out) |
| { |
| struct scatterlist *sgs[4], hdr, stat; |
| unsigned out_num = 0, tmp; |
| int ret; |
| |
| /* Caller should know better */ |
| BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)); |
| |
| vi->ctrl->status = ~0; |
| vi->ctrl->hdr.class = class; |
| vi->ctrl->hdr.cmd = cmd; |
| /* Add header */ |
| sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr)); |
| sgs[out_num++] = &hdr; |
| |
| if (out) |
| sgs[out_num++] = out; |
| |
| /* Add return status. */ |
| sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status)); |
| sgs[out_num] = &stat; |
| |
| BUG_ON(out_num + 1 > ARRAY_SIZE(sgs)); |
| ret = virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC); |
| if (ret < 0) { |
| dev_warn(&vi->vdev->dev, |
| "Failed to add sgs for command vq: %d\n.", ret); |
| return false; |
| } |
| |
| 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) && |
| !virtqueue_is_broken(vi->cvq)) |
| cpu_relax(); |
| |
| return vi->ctrl->status == VIRTIO_NET_OK; |
| } |
| |
| static int virtnet_set_mac_address(struct net_device *dev, void *p) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| struct virtio_device *vdev = vi->vdev; |
| int ret; |
| struct sockaddr *addr; |
| struct scatterlist sg; |
| |
| if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY)) |
| return -EOPNOTSUPP; |
| |
| addr = kmemdup(p, sizeof(*addr), GFP_KERNEL); |
| if (!addr) |
| return -ENOMEM; |
| |
| ret = eth_prepare_mac_addr_change(dev, addr); |
| if (ret) |
| goto out; |
| |
| 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)) { |
| dev_warn(&vdev->dev, |
| "Failed to set mac address by vq command.\n"); |
| ret = -EINVAL; |
| goto out; |
| } |
| } 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); |
| ret = 0; |
| |
| out: |
| kfree(addr); |
| return ret; |
| } |
| |
| static void virtnet_stats(struct net_device *dev, |
| struct rtnl_link_stats64 *tot) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| unsigned int start; |
| int i; |
| |
| for (i = 0; i < vi->max_queue_pairs; i++) { |
| u64 tpackets, tbytes, terrors, rpackets, rbytes, rdrops; |
| struct receive_queue *rq = &vi->rq[i]; |
| struct send_queue *sq = &vi->sq[i]; |
| |
| do { |
| start = u64_stats_fetch_begin_irq(&sq->stats.syncp); |
| tpackets = sq->stats.packets; |
| tbytes = sq->stats.bytes; |
| terrors = sq->stats.tx_timeouts; |
| } while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start)); |
| |
| do { |
| start = u64_stats_fetch_begin_irq(&rq->stats.syncp); |
| rpackets = rq->stats.packets; |
| rbytes = rq->stats.bytes; |
| rdrops = rq->stats.drops; |
| } while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start)); |
| |
| tot->rx_packets += rpackets; |
| tot->tx_packets += tpackets; |
| tot->rx_bytes += rbytes; |
| tot->tx_bytes += tbytes; |
| tot->rx_dropped += rdrops; |
| tot->tx_errors += terrors; |
| } |
| |
| tot->tx_dropped = dev->stats.tx_dropped; |
| tot->tx_fifo_errors = dev->stats.tx_fifo_errors; |
| tot->rx_length_errors = dev->stats.rx_length_errors; |
| tot->rx_frame_errors = dev->stats.rx_frame_errors; |
| } |
| |
| static void virtnet_ack_link_announce(struct virtnet_info *vi) |
| { |
| rtnl_lock(); |
| if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_ANNOUNCE, |
| VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL)) |
| dev_warn(&vi->dev->dev, "Failed to ack link announce.\n"); |
| rtnl_unlock(); |
| } |
| |
| static int _virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) |
| { |
| struct scatterlist sg; |
| struct net_device *dev = vi->dev; |
| |
| if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ)) |
| return 0; |
| |
| vi->ctrl->mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs); |
| sg_init_one(&sg, &vi->ctrl->mq, sizeof(vi->ctrl->mq)); |
| |
| if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, |
| 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; |
| } else { |
| vi->curr_queue_pairs = queue_pairs; |
| /* virtnet_open() will refill when device is going to up. */ |
| if (dev->flags & IFF_UP) |
| schedule_delayed_work(&vi->refill, 0); |
| } |
| |
| return 0; |
| } |
| |
| static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) |
| { |
| int err; |
| |
| rtnl_lock(); |
| err = _virtnet_set_queues(vi, queue_pairs); |
| rtnl_unlock(); |
| return err; |
| } |
| |
| static int virtnet_close(struct net_device *dev) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| int i; |
| |
| /* Make sure NAPI doesn't schedule refill work */ |
| disable_delayed_refill(vi); |
| /* Make sure refill_work doesn't re-enable napi! */ |
| cancel_delayed_work_sync(&vi->refill); |
| |
| for (i = 0; i < vi->max_queue_pairs; i++) |
| virtnet_disable_queue_pair(vi, i); |
| |
| return 0; |
| } |
| |
| static void virtnet_set_rx_mode(struct net_device *dev) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| struct scatterlist sg[2]; |
| struct virtio_net_ctrl_mac *mac_data; |
| struct netdev_hw_addr *ha; |
| int uc_count; |
| int mc_count; |
| void *buf; |
| int i; |
| |
| /* We can't dynamically set ndo_set_rx_mode, so return gracefully */ |
| if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX)) |
| return; |
| |
| vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0); |
| vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0); |
| |
| 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)) |
| dev_warn(&dev->dev, "Failed to %sable promisc mode.\n", |
| vi->ctrl->promisc ? "en" : "dis"); |
| |
| 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)) |
| dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n", |
| vi->ctrl->allmulti ? "en" : "dis"); |
| |
| uc_count = netdev_uc_count(dev); |
| mc_count = netdev_mc_count(dev); |
| /* MAC filter - use one buffer for both lists */ |
| buf = kzalloc(((uc_count + mc_count) * ETH_ALEN) + |
| (2 * sizeof(mac_data->entries)), GFP_ATOMIC); |
| mac_data = buf; |
| if (!buf) |
| return; |
| |
| sg_init_table(sg, 2); |
| |
| /* Store the unicast list and count in the front of the buffer */ |
| 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); |
| |
| sg_set_buf(&sg[0], mac_data, |
| sizeof(mac_data->entries) + (uc_count * ETH_ALEN)); |
| |
| /* multicast list and count fill the end */ |
| mac_data = (void *)&mac_data->macs[uc_count][0]; |
| |
| 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); |
| |
| sg_set_buf(&sg[1], mac_data, |
| sizeof(mac_data->entries) + (mc_count * ETH_ALEN)); |
| |
| if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, |
| VIRTIO_NET_CTRL_MAC_TABLE_SET, sg)) |
| dev_warn(&dev->dev, "Failed to set MAC filter table.\n"); |
| |
| kfree(buf); |
| } |
| |
| static int virtnet_vlan_rx_add_vid(struct net_device *dev, |
| __be16 proto, u16 vid) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| struct scatterlist sg; |
| |
| vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid); |
| sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid)); |
| |
| if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, |
| VIRTIO_NET_CTRL_VLAN_ADD, &sg)) |
| dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid); |
| return 0; |
| } |
| |
| static int virtnet_vlan_rx_kill_vid(struct net_device *dev, |
| __be16 proto, u16 vid) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| struct scatterlist sg; |
| |
| vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid); |
| sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid)); |
| |
| if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, |
| VIRTIO_NET_CTRL_VLAN_DEL, &sg)) |
| dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid); |
| return 0; |
| } |
| |
| static void virtnet_clean_affinity(struct virtnet_info *vi) |
| { |
| int i; |
| |
| if (vi->affinity_hint_set) { |
| for (i = 0; i < vi->max_queue_pairs; i++) { |
| virtqueue_set_affinity(vi->rq[i].vq, NULL); |
| virtqueue_set_affinity(vi->sq[i].vq, NULL); |
| } |
| |
| vi->affinity_hint_set = false; |
| } |
| } |
| |
| static void virtnet_set_affinity(struct virtnet_info *vi) |
| { |
| cpumask_var_t mask; |
| int stragglers; |
| int group_size; |
| int i, j, cpu; |
| int num_cpu; |
| int stride; |
| |
| if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { |
| virtnet_clean_affinity(vi); |
| return; |
| } |
| |
| num_cpu = num_online_cpus(); |
| stride = max_t(int, num_cpu / vi->curr_queue_pairs, 1); |
| stragglers = num_cpu >= vi->curr_queue_pairs ? |
| num_cpu % vi->curr_queue_pairs : |
| 0; |
| cpu = cpumask_first(cpu_online_mask); |
| |
| for (i = 0; i < vi->curr_queue_pairs; i++) { |
| group_size = stride + (i < stragglers ? 1 : 0); |
| |
| for (j = 0; j < group_size; j++) { |
| cpumask_set_cpu(cpu, mask); |
| cpu = cpumask_next_wrap(cpu, cpu_online_mask, |
| nr_cpu_ids, false); |
| } |
| virtqueue_set_affinity(vi->rq[i].vq, mask); |
| virtqueue_set_affinity(vi->sq[i].vq, mask); |
| __netif_set_xps_queue(vi->dev, cpumask_bits(mask), i, XPS_CPUS); |
| cpumask_clear(mask); |
| } |
| |
| vi->affinity_hint_set = true; |
| free_cpumask_var(mask); |
| } |
| |
| static int virtnet_cpu_online(unsigned int cpu, struct hlist_node *node) |
| { |
| struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info, |
| node); |
| virtnet_set_affinity(vi); |
| return 0; |
| } |
| |
| static int virtnet_cpu_dead(unsigned int cpu, struct hlist_node *node) |
| { |
| struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info, |
| node_dead); |
| virtnet_set_affinity(vi); |
| return 0; |
| } |
| |
| static int virtnet_cpu_down_prep(unsigned int cpu, struct hlist_node *node) |
| { |
| struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info, |
| node); |
| |
| virtnet_clean_affinity(vi); |
| return 0; |
| } |
| |
| static enum cpuhp_state virtionet_online; |
| |
| static int virtnet_cpu_notif_add(struct virtnet_info *vi) |
| { |
| int ret; |
| |
| ret = cpuhp_state_add_instance_nocalls(virtionet_online, &vi->node); |
| if (ret) |
| return ret; |
| ret = cpuhp_state_add_instance_nocalls(CPUHP_VIRT_NET_DEAD, |
| &vi->node_dead); |
| if (!ret) |
| return ret; |
| cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node); |
| return ret; |
| } |
| |
| static void virtnet_cpu_notif_remove(struct virtnet_info *vi) |
| { |
| cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node); |
| cpuhp_state_remove_instance_nocalls(CPUHP_VIRT_NET_DEAD, |
| &vi->node_dead); |
| } |
| |
| static void virtnet_get_ringparam(struct net_device *dev, |
| struct ethtool_ringparam *ring, |
| struct kernel_ethtool_ringparam *kernel_ring, |
| struct netlink_ext_ack *extack) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| |
| ring->rx_max_pending = vi->rq[0].vq->num_max; |
| ring->tx_max_pending = vi->sq[0].vq->num_max; |
| ring->rx_pending = virtqueue_get_vring_size(vi->rq[0].vq); |
| ring->tx_pending = virtqueue_get_vring_size(vi->sq[0].vq); |
| } |
| |
| static int virtnet_set_ringparam(struct net_device *dev, |
| struct ethtool_ringparam *ring, |
| struct kernel_ethtool_ringparam *kernel_ring, |
| struct netlink_ext_ack *extack) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| u32 rx_pending, tx_pending; |
| struct receive_queue *rq; |
| struct send_queue *sq; |
| int i, err; |
| |
| if (ring->rx_mini_pending || ring->rx_jumbo_pending) |
| return -EINVAL; |
| |
| rx_pending = virtqueue_get_vring_size(vi->rq[0].vq); |
| tx_pending = virtqueue_get_vring_size(vi->sq[0].vq); |
| |
| if (ring->rx_pending == rx_pending && |
| ring->tx_pending == tx_pending) |
| return 0; |
| |
| if (ring->rx_pending > vi->rq[0].vq->num_max) |
| return -EINVAL; |
| |
| if (ring->tx_pending > vi->sq[0].vq->num_max) |
| return -EINVAL; |
| |
| for (i = 0; i < vi->max_queue_pairs; i++) { |
| rq = vi->rq + i; |
| sq = vi->sq + i; |
| |
| if (ring->tx_pending != tx_pending) { |
| err = virtnet_tx_resize(vi, sq, ring->tx_pending); |
| if (err) |
| return err; |
| } |
| |
| if (ring->rx_pending != rx_pending) { |
| err = virtnet_rx_resize(vi, rq, ring->rx_pending); |
| if (err) |
| return err; |
| } |
| } |
| |
| return 0; |
| } |
| |
| static bool virtnet_commit_rss_command(struct virtnet_info *vi) |
| { |
| struct net_device *dev = vi->dev; |
| struct scatterlist sgs[4]; |
| unsigned int sg_buf_size; |
| |
| /* prepare sgs */ |
| sg_init_table(sgs, 4); |
| |
| sg_buf_size = offsetof(struct virtio_net_ctrl_rss, indirection_table); |
| sg_set_buf(&sgs[0], &vi->ctrl->rss, sg_buf_size); |
| |
| sg_buf_size = sizeof(uint16_t) * (vi->ctrl->rss.indirection_table_mask + 1); |
| sg_set_buf(&sgs[1], vi->ctrl->rss.indirection_table, sg_buf_size); |
| |
| sg_buf_size = offsetof(struct virtio_net_ctrl_rss, key) |
| - offsetof(struct virtio_net_ctrl_rss, max_tx_vq); |
| sg_set_buf(&sgs[2], &vi->ctrl->rss.max_tx_vq, sg_buf_size); |
| |
| sg_buf_size = vi->rss_key_size; |
| sg_set_buf(&sgs[3], vi->ctrl->rss.key, sg_buf_size); |
| |
| if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, |
| vi->has_rss ? VIRTIO_NET_CTRL_MQ_RSS_CONFIG |
| : VIRTIO_NET_CTRL_MQ_HASH_CONFIG, sgs)) { |
| dev_warn(&dev->dev, "VIRTIONET issue with committing RSS sgs\n"); |
| return false; |
| } |
| return true; |
| } |
| |
| static void virtnet_init_default_rss(struct virtnet_info *vi) |
| { |
| u32 indir_val = 0; |
| int i = 0; |
| |
| vi->ctrl->rss.hash_types = vi->rss_hash_types_supported; |
| vi->rss_hash_types_saved = vi->rss_hash_types_supported; |
| vi->ctrl->rss.indirection_table_mask = vi->rss_indir_table_size |
| ? vi->rss_indir_table_size - 1 : 0; |
| vi->ctrl->rss.unclassified_queue = 0; |
| |
| for (; i < vi->rss_indir_table_size; ++i) { |
| indir_val = ethtool_rxfh_indir_default(i, vi->curr_queue_pairs); |
| vi->ctrl->rss.indirection_table[i] = indir_val; |
| } |
| |
| vi->ctrl->rss.max_tx_vq = vi->has_rss ? vi->curr_queue_pairs : 0; |
| vi->ctrl->rss.hash_key_length = vi->rss_key_size; |
| |
| netdev_rss_key_fill(vi->ctrl->rss.key, vi->rss_key_size); |
| } |
| |
| static void virtnet_get_hashflow(const struct virtnet_info *vi, struct ethtool_rxnfc *info) |
| { |
| info->data = 0; |
| switch (info->flow_type) { |
| case TCP_V4_FLOW: |
| if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv4) { |
| info->data = RXH_IP_SRC | RXH_IP_DST | |
| RXH_L4_B_0_1 | RXH_L4_B_2_3; |
| } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) { |
| info->data = RXH_IP_SRC | RXH_IP_DST; |
| } |
| break; |
| case TCP_V6_FLOW: |
| if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv6) { |
| info->data = RXH_IP_SRC | RXH_IP_DST | |
| RXH_L4_B_0_1 | RXH_L4_B_2_3; |
| } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) { |
| info->data = RXH_IP_SRC | RXH_IP_DST; |
| } |
| break; |
| case UDP_V4_FLOW: |
| if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv4) { |
| info->data = RXH_IP_SRC | RXH_IP_DST | |
| RXH_L4_B_0_1 | RXH_L4_B_2_3; |
| } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) { |
| info->data = RXH_IP_SRC | RXH_IP_DST; |
| } |
| break; |
| case UDP_V6_FLOW: |
| if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv6) { |
| info->data = RXH_IP_SRC | RXH_IP_DST | |
| RXH_L4_B_0_1 | RXH_L4_B_2_3; |
| } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) { |
| info->data = RXH_IP_SRC | RXH_IP_DST; |
| } |
| break; |
| case IPV4_FLOW: |
| if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) |
| info->data = RXH_IP_SRC | RXH_IP_DST; |
| |
| break; |
| case IPV6_FLOW: |
| if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) |
| info->data = RXH_IP_SRC | RXH_IP_DST; |
| |
| break; |
| default: |
| info->data = 0; |
| break; |
| } |
| } |
| |
| static bool virtnet_set_hashflow(struct virtnet_info *vi, struct ethtool_rxnfc *info) |
| { |
| u32 new_hashtypes = vi->rss_hash_types_saved; |
| bool is_disable = info->data & RXH_DISCARD; |
| bool is_l4 = info->data == (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3); |
| |
| /* supports only 'sd', 'sdfn' and 'r' */ |
| if (!((info->data == (RXH_IP_SRC | RXH_IP_DST)) | is_l4 | is_disable)) |
| return false; |
| |
| switch (info->flow_type) { |
| case TCP_V4_FLOW: |
| new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_TCPv4); |
| if (!is_disable) |
| new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4 |
| | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv4 : 0); |
| break; |
| case UDP_V4_FLOW: |
| new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_UDPv4); |
| if (!is_disable) |
| new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4 |
| | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv4 : 0); |
| break; |
| case IPV4_FLOW: |
| new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv4; |
| if (!is_disable) |
| new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv4; |
| break; |
| case TCP_V6_FLOW: |
| new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_TCPv6); |
| if (!is_disable) |
| new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6 |
| | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv6 : 0); |
| break; |
| case UDP_V6_FLOW: |
| new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_UDPv6); |
| if (!is_disable) |
| new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6 |
| | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv6 : 0); |
| break; |
| case IPV6_FLOW: |
| new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv6; |
| if (!is_disable) |
| new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv6; |
| break; |
| default: |
| /* unsupported flow */ |
| return false; |
| } |
| |
| /* if unsupported hashtype was set */ |
| if (new_hashtypes != (new_hashtypes & vi->rss_hash_types_supported)) |
| return false; |
| |
| if (new_hashtypes != vi->rss_hash_types_saved) { |
| vi->rss_hash_types_saved = new_hashtypes; |
| vi->ctrl->rss.hash_types = vi->rss_hash_types_saved; |
| if (vi->dev->features & NETIF_F_RXHASH) |
| return virtnet_commit_rss_command(vi); |
| } |
| |
| return true; |
| } |
| |
| static void virtnet_get_drvinfo(struct net_device *dev, |
| struct ethtool_drvinfo *info) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| struct virtio_device *vdev = vi->vdev; |
| |
| strscpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); |
| strscpy(info->version, VIRTNET_DRIVER_VERSION, sizeof(info->version)); |
| strscpy(info->bus_info, virtio_bus_name(vdev), sizeof(info->bus_info)); |
| |
| } |
| |
| /* TODO: Eliminate OOO packets during switching */ |
| static int virtnet_set_channels(struct net_device *dev, |
| struct ethtool_channels *channels) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| u16 queue_pairs = channels->combined_count; |
| int err; |
| |
| /* We don't support separate rx/tx channels. |
| * We don't allow setting 'other' channels. |
| */ |
| if (channels->rx_count || channels->tx_count || channels->other_count) |
| return -EINVAL; |
| |
| if (queue_pairs > vi->max_queue_pairs || queue_pairs == 0) |
| return -EINVAL; |
| |
| /* For now we don't support modifying channels while XDP is loaded |
| * also when XDP is loaded all RX queues have XDP programs so we only |
| * need to check a single RX queue. |
| */ |
| if (vi->rq[0].xdp_prog) |
| return -EINVAL; |
| |
| cpus_read_lock(); |
| err = _virtnet_set_queues(vi, queue_pairs); |
| if (err) { |
| cpus_read_unlock(); |
| goto err; |
| } |
| virtnet_set_affinity(vi); |
| cpus_read_unlock(); |
| |
| netif_set_real_num_tx_queues(dev, queue_pairs); |
| netif_set_real_num_rx_queues(dev, queue_pairs); |
| err: |
| return err; |
| } |
| |
| static void virtnet_get_strings(struct net_device *dev, u32 stringset, u8 *data) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| unsigned int i, j; |
| u8 *p = data; |
| |
| switch (stringset) { |
| case ETH_SS_STATS: |
| for (i = 0; i < vi->curr_queue_pairs; i++) { |
| for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) |
| ethtool_sprintf(&p, "rx_queue_%u_%s", i, |
| virtnet_rq_stats_desc[j].desc); |
| } |
| |
| for (i = 0; i < vi->curr_queue_pairs; i++) { |
| for (j = 0; j < VIRTNET_SQ_STATS_LEN; j++) |
| ethtool_sprintf(&p, "tx_queue_%u_%s", i, |
| virtnet_sq_stats_desc[j].desc); |
| } |
| break; |
| } |
| } |
| |
| static int virtnet_get_sset_count(struct net_device *dev, int sset) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| |
| switch (sset) { |
| case ETH_SS_STATS: |
| return vi->curr_queue_pairs * (VIRTNET_RQ_STATS_LEN + |
| VIRTNET_SQ_STATS_LEN); |
| default: |
| return -EOPNOTSUPP; |
| } |
| } |
| |
| static void virtnet_get_ethtool_stats(struct net_device *dev, |
| struct ethtool_stats *stats, u64 *data) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| unsigned int idx = 0, start, i, j; |
| const u8 *stats_base; |
| size_t offset; |
| |
| for (i = 0; i < vi->curr_queue_pairs; i++) { |
| struct receive_queue *rq = &vi->rq[i]; |
| |
| stats_base = (u8 *)&rq->stats; |
| do { |
| start = u64_stats_fetch_begin_irq(&rq->stats.syncp); |
| for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) { |
| offset = virtnet_rq_stats_desc[j].offset; |
| data[idx + j] = *(u64 *)(stats_base + offset); |
| } |
| } while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start)); |
| idx += VIRTNET_RQ_STATS_LEN; |
| } |
| |
| for (i = 0; i < vi->curr_queue_pairs; i++) { |
| struct send_queue *sq = &vi->sq[i]; |
| |
| stats_base = (u8 *)&sq->stats; |
| do { |
| start = u64_stats_fetch_begin_irq(&sq->stats.syncp); |
| for (j = 0; j < VIRTNET_SQ_STATS_LEN; j++) { |
| offset = virtnet_sq_stats_desc[j].offset; |
| data[idx + j] = *(u64 *)(stats_base + offset); |
| } |
| } while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start)); |
| idx += VIRTNET_SQ_STATS_LEN; |
| } |
| } |
| |
| static void virtnet_get_channels(struct net_device *dev, |
| struct ethtool_channels *channels) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| |
| channels->combined_count = vi->curr_queue_pairs; |
| channels->max_combined = vi->max_queue_pairs; |
| channels->max_other = 0; |
| channels->rx_count = 0; |
| channels->tx_count = 0; |
| channels->other_count = 0; |
| } |
| |
| static int virtnet_set_link_ksettings(struct net_device *dev, |
| const struct ethtool_link_ksettings *cmd) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| |
| return ethtool_virtdev_set_link_ksettings(dev, cmd, |
| &vi->speed, &vi->duplex); |
| } |
| |
| static int virtnet_get_link_ksettings(struct net_device *dev, |
| struct ethtool_link_ksettings *cmd) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| |
| cmd->base.speed = vi->speed; |
| cmd->base.duplex = vi->duplex; |
| cmd->base.port = PORT_OTHER; |
| |
| return 0; |
| } |
| |
| static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, |
| struct ethtool_coalesce *ec) |
| { |
| struct scatterlist sgs_tx, sgs_rx; |
| |
| vi->ctrl->coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); |
| vi->ctrl->coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); |
| sg_init_one(&sgs_tx, &vi->ctrl->coal_tx, sizeof(vi->ctrl->coal_tx)); |
| |
| if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, |
| VIRTIO_NET_CTRL_NOTF_COAL_TX_SET, |
| &sgs_tx)) |
| return -EINVAL; |
| |
| /* Save parameters */ |
| vi->tx_usecs = ec->tx_coalesce_usecs; |
| vi->tx_max_packets = ec->tx_max_coalesced_frames; |
| |
| vi->ctrl->coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); |
| vi->ctrl->coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); |
| sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx)); |
| |
| if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, |
| VIRTIO_NET_CTRL_NOTF_COAL_RX_SET, |
| &sgs_rx)) |
| return -EINVAL; |
| |
| /* Save parameters */ |
| vi->rx_usecs = ec->rx_coalesce_usecs; |
| vi->rx_max_packets = ec->rx_max_coalesced_frames; |
| |
| return 0; |
| } |
| |
| static int virtnet_coal_params_supported(struct ethtool_coalesce *ec) |
| { |
| /* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL |
| * feature is negotiated. |
| */ |
| if (ec->rx_coalesce_usecs || ec->tx_coalesce_usecs) |
| return -EOPNOTSUPP; |
| |
| if (ec->tx_max_coalesced_frames > 1 || |
| ec->rx_max_coalesced_frames != 1) |
| return -EINVAL; |
| |
| return 0; |
| } |
| |
| static int virtnet_set_coalesce(struct net_device *dev, |
| struct ethtool_coalesce *ec, |
| struct kernel_ethtool_coalesce *kernel_coal, |
| struct netlink_ext_ack *extack) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| int ret, i, napi_weight; |
| bool update_napi = false; |
| |
| /* Can't change NAPI weight if the link is up */ |
| napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0; |
| if (napi_weight ^ vi->sq[0].napi.weight) { |
| if (dev->flags & IFF_UP) |
| return -EBUSY; |
| else |
| update_napi = true; |
| } |
| |
| if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) |
| ret = virtnet_send_notf_coal_cmds(vi, ec); |
| else |
| ret = virtnet_coal_params_supported(ec); |
| |
| if (ret) |
| return ret; |
| |
| if (update_napi) { |
| for (i = 0; i < vi->max_queue_pairs; i++) |
| vi->sq[i].napi.weight = napi_weight; |
| } |
| |
| return ret; |
| } |
| |
| static int virtnet_get_coalesce(struct net_device *dev, |
| struct ethtool_coalesce *ec, |
| struct kernel_ethtool_coalesce *kernel_coal, |
| struct netlink_ext_ack *extack) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| |
| if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) { |
| ec->rx_coalesce_usecs = vi->rx_usecs; |
| ec->tx_coalesce_usecs = vi->tx_usecs; |
| ec->tx_max_coalesced_frames = vi->tx_max_packets; |
| ec->rx_max_coalesced_frames = vi->rx_max_packets; |
| } else { |
| ec->rx_max_coalesced_frames = 1; |
| |
| if (vi->sq[0].napi.weight) |
| ec->tx_max_coalesced_frames = 1; |
| } |
| |
| return 0; |
| } |
| |
| static void virtnet_init_settings(struct net_device *dev) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| |
| vi->speed = SPEED_UNKNOWN; |
| vi->duplex = DUPLEX_UNKNOWN; |
| } |
| |
| static void virtnet_update_settings(struct virtnet_info *vi) |
| { |
| u32 speed; |
| u8 duplex; |
| |
| if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX)) |
| return; |
| |
| virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed); |
| |
| if (ethtool_validate_speed(speed)) |
| vi->speed = speed; |
| |
| virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex); |
| |
| if (ethtool_validate_duplex(duplex)) |
| vi->duplex = duplex; |
| } |
| |
| static u32 virtnet_get_rxfh_key_size(struct net_device *dev) |
| { |
| return ((struct virtnet_info *)netdev_priv(dev))->rss_key_size; |
| } |
| |
| static u32 virtnet_get_rxfh_indir_size(struct net_device *dev) |
| { |
| return ((struct virtnet_info *)netdev_priv(dev))->rss_indir_table_size; |
| } |
| |
| static int virtnet_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| int i; |
| |
| if (indir) { |
| for (i = 0; i < vi->rss_indir_table_size; ++i) |
| indir[i] = vi->ctrl->rss.indirection_table[i]; |
| } |
| |
| if (key) |
| memcpy(key, vi->ctrl->rss.key, vi->rss_key_size); |
| |
| if (hfunc) |
| *hfunc = ETH_RSS_HASH_TOP; |
| |
| return 0; |
| } |
| |
| static int virtnet_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| bool update = false; |
| int i; |
| |
| if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) |
| return -EOPNOTSUPP; |
| |
| if (indir) { |
| if (!vi->has_rss) |
| return -EOPNOTSUPP; |
| |
| for (i = 0; i < vi->rss_indir_table_size; ++i) |
| vi->ctrl->rss.indirection_table[i] = indir[i]; |
| update = true; |
| } |
| |
| if (key) { |
| /* If either _F_HASH_REPORT or _F_RSS are negotiated, the |
| * device provides hash calculation capabilities, that is, |
| * hash_key is configured. |
| */ |
| if (!vi->has_rss && !vi->has_rss_hash_report) |
| return -EOPNOTSUPP; |
| |
| memcpy(vi->ctrl->rss.key, key, vi->rss_key_size); |
| update = true; |
| } |
| |
| if (update) |
| virtnet_commit_rss_command(vi); |
| |
| return 0; |
| } |
| |
| static int virtnet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) |
| { |
| struct virtnet_info *vi = netdev_priv(dev); |
| int rc = 0; |
| |
| switch (info->cmd) { |
| case ETHTOOL_GRXRINGS: |
| info->data = vi->curr_queue_pairs; |
| break; |
| case ETHTOOL_GRXFH: |
|