From 6889fd14acfecf6ca1b8e1c27160ea3306a97453 Mon Sep 17 00:00:00 2001 From: Andriy Kokhan <43479230+akokhan@users.noreply.github.com> Date: Tue, 12 May 2020 09:23:34 +0300 Subject: [PATCH] [BFN] Fixed Barefoot platform image build. (#4565) - Updated bf_tun kernel driver; - Temporarily disabled WNC modules build; Signed-off-by: Andriy Kokhan --- .../barefoot/bfn-modules/modules/bf_tun.c | 1526 +++++++++++++---- platform/barefoot/one-image.mk | 2 +- platform/barefoot/rules.mk | 8 +- 3 files changed, 1245 insertions(+), 291 deletions(-) diff --git a/platform/barefoot/bfn-modules/modules/bf_tun.c b/platform/barefoot/bfn-modules/modules/bf_tun.c index 45913a681a..a20f5e4db5 100644 --- a/platform/barefoot/bfn-modules/modules/bf_tun.c +++ b/platform/barefoot/bfn-modules/modules/bf_tun.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include #include @@ -69,13 +70,21 @@ #include #include #include +#include #include #include #include +#include +#include +#include -#include +#include +#include -#define TUN_MINOR1 201 +#define BF_TUN_MINOR 201 + +static void tun_default_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd); /* Uncomment to enable debugging */ /* #define TUN_DEBUG 1 */ @@ -106,6 +115,9 @@ do { \ } while (0) #endif +#define TUN_HEADROOM 256 +#define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) + /* TUN device flags */ /* IFF_ATTACH_QUEUE is never stored in device flags, @@ -117,7 +129,8 @@ do { \ #define TUN_VNET_BE 0x40000000 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \ - IFF_MULTI_QUEUE) + IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS) + #define GOODCOPY_LEN 128 #define FLT_EXACT_COUNT 8 @@ -168,9 +181,14 @@ struct tun_file { u16 queue_index; unsigned int ifindex; }; + struct napi_struct napi; + bool napi_enabled; + bool napi_frags_enabled; + struct mutex napi_mutex; /* Protects access to the above napi */ struct list_head next; struct tun_struct *detached; - struct skb_array tx_array; + struct ptr_ring tx_ring; + struct xdp_rxq_info xdp_rxq; }; struct tun_flow_entry { @@ -185,6 +203,12 @@ struct tun_flow_entry { }; #define TUN_NUM_FLOW_ENTRIES 1024 +#define TUN_MASK_FLOW_ENTRIES (TUN_NUM_FLOW_ENTRIES - 1) + +struct tun_prog { + struct rcu_head rcu; + struct bpf_prog *prog; +}; /* Since the socket were moved to tun_file, to preserve the behavior of persist * device, socket filter, sndbuf and vnet header size were restore when the @@ -200,7 +224,7 @@ struct tun_struct { struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ - NETIF_F_TSO6|NETIF_F_UFO) + NETIF_F_TSO6) int align; int vnet_hdr_sz; @@ -220,9 +244,106 @@ struct tun_struct { struct list_head disabled; void *security; u32 flow_count; + u32 rx_batched; struct tun_pcpu_stats __percpu *pcpu_stats; + struct bpf_prog __rcu *xdp_prog; + struct tun_prog __rcu *steering_prog; + struct tun_prog __rcu *filter_prog; + struct ethtool_link_ksettings link_ksettings; }; +struct veth { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; +}; + +bool tun_is_xdp_frame(void *ptr) +{ + return (unsigned long)ptr & TUN_XDP_FLAG; +} +EXPORT_SYMBOL(tun_is_xdp_frame); + +void *tun_xdp_to_ptr(void *ptr) +{ + return (void *)((unsigned long)ptr | TUN_XDP_FLAG); +} +EXPORT_SYMBOL(tun_xdp_to_ptr); + +void *tun_ptr_to_xdp(void *ptr) +{ + return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG); +} +EXPORT_SYMBOL(tun_ptr_to_xdp); + +static int tun_napi_receive(struct napi_struct *napi, int budget) +{ + struct tun_file *tfile = container_of(napi, struct tun_file, napi); + struct sk_buff_head *queue = &tfile->sk.sk_write_queue; + struct sk_buff_head process_queue; + struct sk_buff *skb; + int received = 0; + + __skb_queue_head_init(&process_queue); + + spin_lock(&queue->lock); + skb_queue_splice_tail_init(queue, &process_queue); + spin_unlock(&queue->lock); + + while (received < budget && (skb = __skb_dequeue(&process_queue))) { + napi_gro_receive(napi, skb); + ++received; + } + + if (!skb_queue_empty(&process_queue)) { + spin_lock(&queue->lock); + skb_queue_splice(&process_queue, queue); + spin_unlock(&queue->lock); + } + + return received; +} + +static int tun_napi_poll(struct napi_struct *napi, int budget) +{ + unsigned int received; + + received = tun_napi_receive(napi, budget); + + if (received < budget) + napi_complete_done(napi, received); + + return received; +} + +static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, + bool napi_en, bool napi_frags) +{ + tfile->napi_enabled = napi_en; + tfile->napi_frags_enabled = napi_en && napi_frags; + if (napi_en) { + netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll, + NAPI_POLL_WEIGHT); + napi_enable(&tfile->napi); + } +} + +static void tun_napi_disable(struct tun_file *tfile) +{ + if (tfile->napi_enabled) + napi_disable(&tfile->napi); +} + +static void tun_napi_del(struct tun_file *tfile) +{ + if (tfile->napi_enabled) + netif_napi_del(&tfile->napi); +} + +static bool tun_napi_frags_enabled(const struct tun_file *tfile) +{ + return tfile->napi_frags_enabled; +} + #ifdef CONFIG_TUN_VNET_CROSS_LE static inline bool tun_legacy_is_little_endian(struct tun_struct *tun) { @@ -289,7 +410,7 @@ static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val) static inline u32 tun_hashfn(u32 rxhash) { - return rxhash & 0x3ff; + return rxhash & TUN_MASK_FLOW_ENTRIES; } static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash) @@ -364,9 +485,9 @@ static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index) spin_unlock_bh(&tun->lock); } -static void tun_flow_cleanup(unsigned long data) +static void tun_flow_cleanup(struct timer_list *t) { - struct tun_struct *tun = (struct tun_struct *)data; + struct tun_struct *tun = from_timer(tun, t, flow_gc_timer); unsigned long delay = tun->ageing_time; unsigned long next_timer = jiffies + delay; unsigned long count = 0; @@ -374,25 +495,28 @@ static void tun_flow_cleanup(unsigned long data) tun_debug(KERN_INFO, tun, "tun_flow_cleanup\n"); - spin_lock_bh(&tun->lock); + spin_lock(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { unsigned long this_timer; - count++; + this_timer = e->updated + delay; - if (time_before_eq(this_timer, jiffies)) + if (time_before_eq(this_timer, jiffies)) { tun_flow_delete(tun, e); - else if (time_before(this_timer, next_timer)) + continue; + } + count++; + if (time_before(this_timer, next_timer)) next_timer = this_timer; } } if (count) mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer)); - spin_unlock_bh(&tun->lock); + spin_unlock(&tun->lock); } static void tun_flow_update(struct tun_struct *tun, u32 rxhash, @@ -410,11 +534,6 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash, rcu_read_lock(); - /* We may get a very small possibility of OOO during switching, not - * worth to optimize.*/ - if (tun->numqueues == 1 || tfile->detached) - goto unlock; - e = tun_flow_find(head, rxhash); if (likely(e)) { /* TODO: keep queueing to old queue until it's empty? */ @@ -433,7 +552,6 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash, spin_unlock_bh(&tun->lock); } -unlock: rcu_read_unlock(); } @@ -454,18 +572,15 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) * different rxq no. here. If we could not get rxhash, then we would * hope the rxq no. may help here. */ -static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) +static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb) { - struct tun_struct *tun = netdev_priv(dev); struct tun_flow_entry *e; u32 txq = 0; u32 numqueues = 0; - rcu_read_lock(); - numqueues = ACCESS_ONCE(tun->numqueues); + numqueues = READ_ONCE(tun->numqueues); - txq = skb_get_hash(skb); + txq = __skb_get_hash_symmetric(skb); if (txq) { e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq); if (e) { @@ -480,10 +595,43 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, txq -= numqueues; } - rcu_read_unlock(); return txq; } +static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb) +{ + struct tun_prog *prog; + u32 numqueues; + u16 ret = 0; + + numqueues = READ_ONCE(tun->numqueues); + if (!numqueues) + return 0; + + prog = rcu_dereference(tun->steering_prog); + if (prog) + ret = bpf_prog_run_clear_cb(prog->prog, skb); + + return ret % numqueues; +} + +static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback) +{ + struct tun_struct *tun = netdev_priv(dev); + u16 ret; + + rcu_read_lock(); + if (rcu_dereference(tun->steering_prog)) + ret = tun_ebpf_select_queue(tun, skb); + else + ret = tun_automq_select_queue(tun, skb); + rcu_read_unlock(); + + return ret; +} + static inline bool tun_not_capable(struct tun_struct *tun) { const struct cred *cred = current_cred(); @@ -517,24 +665,31 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile) return tun; } +void tun_ptr_free(void *ptr) +{ + if (!ptr) + return; + if (tun_is_xdp_frame(ptr)) { + struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); + + xdp_return_frame(xdpf); + } else { + __skb_array_destroy_skb(ptr); + } +} +EXPORT_SYMBOL_GPL(tun_ptr_free); + static void tun_queue_purge(struct tun_file *tfile) { - struct sk_buff *skb; + void *ptr; - while ((skb = skb_array_consume(&tfile->tx_array)) != NULL) - kfree_skb(skb); + while ((ptr = ptr_ring_consume(&tfile->tx_ring)) != NULL) + tun_ptr_free(ptr); + skb_queue_purge(&tfile->sk.sk_write_queue); skb_queue_purge(&tfile->sk.sk_error_queue); } -static void tun_cleanup_tx_array(struct tun_file *tfile) -{ - if (tfile->tx_array.ring.queue) { - skb_array_cleanup(&tfile->tx_array); - memset(&tfile->tx_array, 0, sizeof(tfile->tx_array)); - } -} - static void __tun_detach(struct tun_file *tfile, bool clean) { struct tun_file *ntfile; @@ -542,6 +697,11 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun = rtnl_dereference(tfile->tun); + if (tun && clean) { + tun_napi_disable(tfile); + tun_napi_del(tfile); + } + if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); @@ -550,6 +710,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun->tfiles[tun->numqueues - 1]); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; + rcu_assign_pointer(tun->tfiles[tun->numqueues - 1], + NULL); --tun->numqueues; if (clean) { @@ -576,15 +738,24 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } - tun_cleanup_tx_array(tfile); + if (tun) + xdp_rxq_info_unreg(&tfile->xdp_rxq); + ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free); sock_put(&tfile->sk); } } static void tun_detach(struct tun_file *tfile, bool clean) { + struct tun_struct *tun; + struct net_device *dev; + rtnl_lock(); + tun = rtnl_dereference(tfile->tun); + dev = tun ? tun->dev : NULL; __tun_detach(tfile, clean); + if (dev) + netdev_state_change(dev); rtnl_unlock(); } @@ -597,6 +768,7 @@ static void tun_detach_all(struct net_device *dev) for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); BUG_ON(!tfile); + tun_napi_disable(tfile); tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); @@ -612,16 +784,17 @@ static void tun_detach_all(struct net_device *dev) synchronize_net(); for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); + tun_napi_del(tfile); /* Drop read queue */ tun_queue_purge(tfile); + xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); - tun_cleanup_tx_array(tfile); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { tun_enable_queue(tfile); tun_queue_purge(tfile); + xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); - tun_cleanup_tx_array(tfile); } BUG_ON(tun->numdisabled != 0); @@ -629,7 +802,8 @@ static void tun_detach_all(struct net_device *dev) module_put(THIS_MODULE); } -static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter) +static int tun_attach(struct tun_struct *tun, struct file *file, + bool skip_filter, bool napi, bool napi_frags) { struct tun_file *tfile = file->private_data; struct net_device *dev = tun->dev; @@ -664,33 +838,60 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte } if (!tfile->detached && - skb_array_init(&tfile->tx_array, dev->tx_queue_len, GFP_KERNEL)) { + ptr_ring_resize(&tfile->tx_ring, dev->tx_queue_len, + GFP_KERNEL, tun_ptr_free)) { err = -ENOMEM; goto out; } tfile->queue_index = tun->numqueues; tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN; - rcu_assign_pointer(tfile->tun, tun); - rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); - tun->numqueues++; - if (tfile->detached) + if (tfile->detached) { + /* Re-attach detached tfile, updating XDP queue_index */ + WARN_ON(!xdp_rxq_info_is_reg(&tfile->xdp_rxq)); + + if (tfile->xdp_rxq.queue_index != tfile->queue_index) + tfile->xdp_rxq.queue_index = tfile->queue_index; + } else { + /* Setup XDP RX-queue info, for new tfile getting attached */ + err = xdp_rxq_info_reg(&tfile->xdp_rxq, + tun->dev, tfile->queue_index); + if (err < 0) + goto out; + err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err < 0) { + xdp_rxq_info_unreg(&tfile->xdp_rxq); + goto out; + } + err = 0; + } + + if (tfile->detached) { tun_enable_queue(tfile); - else + } else { sock_hold(&tfile->sk); - - tun_set_real_num_queues(tun); + tun_napi_init(tun, tfile, napi, napi_frags); + } /* device is allowed to go away first, so no need to hold extra * refcnt. */ + /* Publish tfile->tun and tun->tfiles only after we've fully + * initialized tfile; otherwise we risk using half-initialized + * object. + */ + rcu_assign_pointer(tfile->tun, tun); + rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); + tun->numqueues++; + tun_set_real_num_queues(tun); out: return err; } -static struct tun_struct *__tun_get(struct tun_file *tfile) +static struct tun_struct *tun_get(struct tun_file *tfile) { struct tun_struct *tun; @@ -703,11 +904,6 @@ static struct tun_struct *__tun_get(struct tun_file *tfile) return tun; } -static struct tun_struct *tun_get(struct file *file) -{ - return __tun_get(file->private_data); -} - static void tun_put(struct tun_struct *tun) { dev_put(tun->dev); @@ -830,18 +1026,8 @@ static void tun_net_uninit(struct net_device *dev) /* Net device open. */ static int tun_net_open(struct net_device *dev) { - struct tun_struct *tun = netdev_priv(dev); - int i; - netif_tx_start_all_queues(dev); - for (i = 0; i < tun->numqueues; i++) { - struct tun_file *tfile; - - tfile = rtnl_dereference(tun->tfiles[i]); - tfile->socket.sk->sk_write_space(tfile->socket.sk); - } - return 0; } @@ -853,29 +1039,16 @@ static int tun_net_close(struct net_device *dev) } /* Net device start xmit */ -static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) +static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb) { - struct tun_struct *tun = netdev_priv(dev); - int txq = skb->queue_mapping; - struct tun_file *tfile; - u32 numqueues = 0; - - rcu_read_lock(); - tfile = rcu_dereference(tun->tfiles[txq]); - numqueues = ACCESS_ONCE(tun->numqueues); - - /* Drop packet if interface is not attached */ - if (txq >= numqueues) - goto drop; - #ifdef CONFIG_RPS - if (numqueues == 1 && static_key_false(&rps_needed)) { + if (tun->numqueues == 1 && static_key_false(&rps_needed)) { /* Select queue was not called for the skbuff, so we extract the * RPS hash and save it into the flow_table here. */ __u32 rxhash; - rxhash = skb_get_hash(skb); + rxhash = __skb_get_hash_symmetric(skb); if (rxhash) { struct tun_flow_entry *e; e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)], @@ -885,6 +1058,37 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) } } #endif +} + +static unsigned int run_ebpf_filter(struct tun_struct *tun, + struct sk_buff *skb, + int len) +{ + struct tun_prog *prog = rcu_dereference(tun->filter_prog); + + if (prog) + len = bpf_prog_run_clear_cb(prog->prog, skb); + + return len; +} + +/* Net device start xmit */ +static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + int txq = skb->queue_mapping; + struct tun_file *tfile; + int len = skb->len; + + rcu_read_lock(); + tfile = rcu_dereference(tun->tfiles[txq]); + + /* Drop packet if interface is not attached */ + if (!tfile) + goto drop; + + if (!rcu_dereference(tun->steering_prog)) + tun_automq_xmit(tun, skb); tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len); @@ -900,14 +1104,11 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) sk_filter(tfile->socket.sk, skb)) goto drop; - /* Limit the number of packets queued by dividing txq length with the - * number of queues. - */ - if (skb_queue_len(&tfile->socket.sk->sk_receive_queue) * numqueues - >= dev->tx_queue_len) + len = run_ebpf_filter(tun, skb, len); + if (len == 0 || pskb_trim(skb, len)) goto drop; - if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; skb_tx_timestamp(skb); @@ -919,7 +1120,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) nf_reset(skb); - if (skb_array_produce(&tfile->tx_array, skb)) + if (ptr_ring_produce(&tfile->tx_ring, skb)) goto drop; /* Notify and wake up reader process */ @@ -947,18 +1148,6 @@ static void tun_net_mclist(struct net_device *dev) */ } -#define MIN_MTU 68 -#define MAX_MTU 65535 - -static int -tun_net_change_mtu(struct net_device *dev, int new_mtu) -{ - if (new_mtu < MIN_MTU || new_mtu + dev->hard_header_len > MAX_MTU) - return -EINVAL; - dev->mtu = new_mtu; - return 0; -} - static netdev_features_t tun_net_fix_features(struct net_device *dev, netdev_features_t features) { @@ -966,23 +1155,6 @@ static netdev_features_t tun_net_fix_features(struct net_device *dev, return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void tun_poll_controller(struct net_device *dev) -{ - /* - * Tun only receives frames when: - * 1) the char device endpoint gets data from user space - * 2) the tun socket gets a sendmsg call from user space - * Since both of those are synchronous operations, we are guaranteed - * never to have pending data when we poll for it - * so there is nothing to do here but return. - * We need this though so netpoll recognizes us as an interface that - * supports polling, which enables bridge devices in virt setups to - * still use netconsole - */ - return; -} -#endif static void tun_set_headroom(struct net_device *dev, int new_hr) { @@ -994,7 +1166,7 @@ static void tun_set_headroom(struct net_device *dev, int new_hr) tun->align = new_hr; } -static struct rtnl_link_stats64 * +static void tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { u32 rx_dropped = 0, tx_dropped = 0, rx_frame_errors = 0; @@ -1028,16 +1200,66 @@ tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->rx_dropped = rx_dropped; stats->rx_frame_errors = rx_frame_errors; stats->tx_dropped = tx_dropped; - return stats; } -static int -tun_change_carrier(struct net_device *dev, bool new_carrier) { - if (new_carrier) - netif_carrier_on(dev); - else - netif_carrier_off(dev); - return 0; +static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog, + struct netlink_ext_ack *extack) +{ + struct tun_struct *tun = netdev_priv(dev); + struct bpf_prog *old_prog; + + old_prog = rtnl_dereference(tun->xdp_prog); + rcu_assign_pointer(tun->xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + + return 0; +} + +static u32 tun_xdp_query(struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + const struct bpf_prog *xdp_prog; + + xdp_prog = rtnl_dereference(tun->xdp_prog); + if (xdp_prog) + return xdp_prog->aux->id; + + return 0; +} + +static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return tun_xdp_set(dev, xdp->prog, xdp->extack); + case XDP_QUERY_PROG: + xdp->prog_id = tun_xdp_query(dev); + return 0; + default: + return -EINVAL; + } +} + +static int tun_net_change_carrier(struct net_device *dev, bool new_carrier) +{ + if (new_carrier) { + netif_carrier_on(dev); + } else { + netif_carrier_off(dev); + } + return 0; +} + +#define MIN_MTU 68 +#define MAX_MTU 65535 + +static int tun_net_change_mtu(struct net_device *dev, int new_mtu) +{ + if (new_mtu < MIN_MTU || new_mtu + dev->hard_header_len > MAX_MTU) + return -EINVAL; + dev->mtu = new_mtu; + return 0; } static const struct net_device_ops tun_netdev_ops = { @@ -1045,35 +1267,99 @@ static const struct net_device_ops tun_netdev_ops = { .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, - .ndo_change_mtu = tun_net_change_mtu, .ndo_fix_features = tun_net_fix_features, .ndo_select_queue = tun_select_queue, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = tun_poll_controller, -#endif .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, - .ndo_change_carrier = tun_change_carrier, + .ndo_change_carrier = tun_net_change_carrier, + .ndo_change_mtu = tun_net_change_mtu, }; +static void __tun_xdp_flush_tfile(struct tun_file *tfile) +{ + /* Notify and wake up reader process */ + if (tfile->flags & TUN_FASYNC) + kill_fasync(&tfile->fasync, SIGIO, POLL_IN); + tfile->socket.sk->sk_data_ready(tfile->socket.sk); +} + +static int tun_xdp_xmit(struct net_device *dev, int n, + struct xdp_frame **frames, u32 flags) +{ + struct tun_struct *tun = netdev_priv(dev); + struct tun_file *tfile; + u32 numqueues; + int drops = 0; + int cnt = n; + int i; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + rcu_read_lock(); + +resample: + numqueues = READ_ONCE(tun->numqueues); + if (!numqueues) { + rcu_read_unlock(); + return -ENXIO; /* Caller will free/return all frames */ + } + + tfile = rcu_dereference(tun->tfiles[smp_processor_id() % + numqueues]); + if (unlikely(!tfile)) + goto resample; + + spin_lock(&tfile->tx_ring.producer_lock); + for (i = 0; i < n; i++) { + struct xdp_frame *xdp = frames[i]; + /* Encode the XDP flag into lowest bit for consumer to differ + * XDP buffer from sk_buff. + */ + void *frame = tun_xdp_to_ptr(xdp); + + if (__ptr_ring_produce(&tfile->tx_ring, frame)) { + this_cpu_inc(tun->pcpu_stats->tx_dropped); + xdp_return_frame_rx_napi(xdp); + drops++; + } + } + spin_unlock(&tfile->tx_ring.producer_lock); + + if (flags & XDP_XMIT_FLUSH) + __tun_xdp_flush_tfile(tfile); + + rcu_read_unlock(); + return cnt - drops; +} + +static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) +{ + struct xdp_frame *frame = convert_to_xdp_frame(xdp); + + if (unlikely(!frame)) + return -EOVERFLOW; + + return tun_xdp_xmit(dev, 1, &frame, XDP_XMIT_FLUSH); +} + static const struct net_device_ops tap_netdev_ops = { .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, - .ndo_change_mtu = tun_net_change_mtu, .ndo_fix_features = tun_net_fix_features, .ndo_set_rx_mode = tun_net_mclist, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_select_queue = tun_select_queue, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = tun_poll_controller, -#endif .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, - .ndo_change_carrier = tun_change_carrier, + .ndo_bpf = tun_xdp, + .ndo_xdp_xmit = tun_xdp_xmit, + .ndo_change_carrier = tun_net_change_carrier, + .ndo_change_mtu = tun_net_change_mtu, }; static void tun_flow_init(struct tun_struct *tun) @@ -1084,7 +1370,7 @@ static void tun_flow_init(struct tun_struct *tun) INIT_HLIST_HEAD(&tun->flows[i]); tun->ageing_time = TUN_FLOW_EXPIRE; - setup_timer(&tun->flow_gc_timer, tun_flow_cleanup, (unsigned long)tun); + timer_setup(&tun->flow_gc_timer, tun_flow_cleanup, 0); mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + tun->ageing_time)); } @@ -1095,6 +1381,9 @@ static void tun_flow_uninit(struct tun_struct *tun) tun_flow_flush(tun); } +#define MIN_MTU 68 +#define MAX_MTU 65535 + /* Initialize net device. */ static void tun_net_init(struct net_device *dev) { @@ -1125,20 +1414,30 @@ static void tun_net_init(struct net_device *dev) break; } + + dev->min_mtu = MIN_MTU; + dev->max_mtu = MAX_MTU - dev->hard_header_len; +} + +static bool tun_sock_writeable(struct tun_struct *tun, struct tun_file *tfile) +{ + struct sock *sk = tfile->socket.sk; + + return (tun->dev->flags & IFF_UP) && sock_writeable(sk); } /* Character device part */ /* Poll */ -static unsigned int tun_chr_poll(struct file *file, poll_table *wait) +static __poll_t tun_chr_poll(struct file *file, poll_table *wait) { struct tun_file *tfile = file->private_data; - struct tun_struct *tun = __tun_get(tfile); + struct tun_struct *tun = tun_get(tfile); struct sock *sk; - unsigned int mask = 0; + __poll_t mask = 0; if (!tun) - return POLLERR; + return EPOLLERR; sk = tfile->socket.sk; @@ -1146,22 +1445,80 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait) poll_wait(file, sk_sleep(sk), wait); - if (!skb_array_empty(&tfile->tx_array)) - mask |= POLLIN | POLLRDNORM; + if (!ptr_ring_empty(&tfile->tx_ring)) + mask |= EPOLLIN | EPOLLRDNORM; - if (tun->dev->flags & IFF_UP && - (sock_writeable(sk) || - (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && - sock_writeable(sk)))) - mask |= POLLOUT | POLLWRNORM; + /* Make sure SOCKWQ_ASYNC_NOSPACE is set if not writable to + * guarantee EPOLLOUT to be raised by either here or + * tun_sock_write_space(). Then process could get notification + * after it writes to a down device and meets -EIO. + */ + if (tun_sock_writeable(tun, tfile) || + (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && + tun_sock_writeable(tun, tfile))) + mask |= EPOLLOUT | EPOLLWRNORM; if (tun->dev->reg_state != NETREG_REGISTERED) - mask = POLLERR; + mask = EPOLLERR; tun_put(tun); return mask; } +static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, + size_t len, + const struct iov_iter *it) +{ + struct sk_buff *skb; + size_t linear; + int err; + int i; + + if (it->nr_segs > MAX_SKB_FRAGS + 1) + return ERR_PTR(-ENOMEM); + + local_bh_disable(); + skb = napi_get_frags(&tfile->napi); + local_bh_enable(); + if (!skb) + return ERR_PTR(-ENOMEM); + + linear = iov_iter_single_seg_count(it); + err = __skb_grow(skb, linear); + if (err) + goto free; + + skb->len = len; + skb->data_len = len - linear; + skb->truesize += skb->data_len; + + for (i = 1; i < it->nr_segs; i++) { + struct page_frag *pfrag = ¤t->task_frag; + size_t fragsz = it->iov[i].iov_len; + + if (fragsz == 0 || fragsz > PAGE_SIZE) { + err = -EINVAL; + goto free; + } + + if (!skb_page_frag_refill(fragsz, pfrag, GFP_KERNEL)) { + err = -ENOMEM; + goto free; + } + + skb_fill_page_desc(skb, i - 1, pfrag->page, + pfrag->offset, fragsz); + page_ref_inc(pfrag->page); + pfrag->offset += fragsz; + } + + return skb; +free: + /* frees skb and all frags allocated with napi_alloc_frag() */ + napi_free_frags(&tfile->napi); + return ERR_PTR(err); +} + /* prepad is the amount to reserve at front. len is length after that. * linear is a hint as to how much to copy (usually headers). */ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile, @@ -1189,10 +1546,191 @@ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile, return skb; } +static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile, + struct sk_buff *skb, int more) +{ + struct sk_buff_head *queue = &tfile->sk.sk_write_queue; + struct sk_buff_head process_queue; + u32 rx_batched = tun->rx_batched; + bool rcv = false; + + if (!rx_batched || (!more && skb_queue_empty(queue))) { + local_bh_disable(); + skb_record_rx_queue(skb, tfile->queue_index); + netif_receive_skb(skb); + local_bh_enable(); + return; + } + + spin_lock(&queue->lock); + if (!more || skb_queue_len(queue) == rx_batched) { + __skb_queue_head_init(&process_queue); + skb_queue_splice_tail_init(queue, &process_queue); + rcv = true; + } else { + __skb_queue_tail(queue, skb); + } + spin_unlock(&queue->lock); + + if (rcv) { + struct sk_buff *nskb; + + local_bh_disable(); + while ((nskb = __skb_dequeue(&process_queue))) { + skb_record_rx_queue(nskb, tfile->queue_index); + netif_receive_skb(nskb); + } + skb_record_rx_queue(skb, tfile->queue_index); + netif_receive_skb(skb); + local_bh_enable(); + } +} + +static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, + int len, int noblock, bool zerocopy) +{ + if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) + return false; + + if (tfile->socket.sk->sk_sndbuf != INT_MAX) + return false; + + if (!noblock) + return false; + + if (zerocopy) + return false; + + if (SKB_DATA_ALIGN(len + TUN_RX_PAD) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) + return false; + + return true; +} + +static struct sk_buff *tun_build_skb(struct tun_struct *tun, + struct tun_file *tfile, + struct iov_iter *from, + struct virtio_net_hdr *hdr, + int len, int *skb_xdp) +{ + struct page_frag *alloc_frag = ¤t->task_frag; + struct sk_buff *skb; + struct bpf_prog *xdp_prog; + int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + unsigned int delta = 0; + char *buf; + size_t copied; + int err, pad = TUN_RX_PAD; + + rcu_read_lock(); + xdp_prog = rcu_dereference(tun->xdp_prog); + if (xdp_prog) + pad += TUN_HEADROOM; + buflen += SKB_DATA_ALIGN(len + pad); + rcu_read_unlock(); + + alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); + if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) + return ERR_PTR(-ENOMEM); + + buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; + copied = copy_page_from_iter(alloc_frag->page, + alloc_frag->offset + pad, + len, from); + if (copied != len) + return ERR_PTR(-EFAULT); + + /* There's a small window that XDP may be set after the check + * of xdp_prog above, this should be rare and for simplicity + * we do XDP on skb in case the headroom is not enough. + */ + if (hdr->gso_type || !xdp_prog) + *skb_xdp = 1; + else + *skb_xdp = 0; + + local_bh_disable(); + rcu_read_lock(); + xdp_prog = rcu_dereference(tun->xdp_prog); + if (xdp_prog && !*skb_xdp) { + struct xdp_buff xdp; + void *orig_data; + u32 act; + + xdp.data_hard_start = buf; + xdp.data = buf + pad; + xdp_set_data_meta_invalid(&xdp); + xdp.data_end = xdp.data + len; + xdp.rxq = &tfile->xdp_rxq; + orig_data = xdp.data; + act = bpf_prog_run_xdp(xdp_prog, &xdp); + + switch (act) { + case XDP_REDIRECT: + get_page(alloc_frag->page); + alloc_frag->offset += buflen; + err = xdp_do_redirect(tun->dev, &xdp, xdp_prog); + xdp_do_flush_map(); + if (err) + goto err_redirect; + rcu_read_unlock(); + local_bh_enable(); + return NULL; + case XDP_TX: + get_page(alloc_frag->page); + alloc_frag->offset += buflen; + if (tun_xdp_tx(tun->dev, &xdp) < 0) + goto err_redirect; + rcu_read_unlock(); + local_bh_enable(); + return NULL; + case XDP_PASS: + delta = orig_data - xdp.data; + len = xdp.data_end - xdp.data; + break; + default: + bpf_warn_invalid_xdp_action(act); + /* fall through */ + case XDP_ABORTED: + trace_xdp_exception(tun->dev, xdp_prog, act); + /* fall through */ + case XDP_DROP: + goto err_xdp; + } + } + + skb = build_skb(buf, buflen); + if (!skb) { + rcu_read_unlock(); + local_bh_enable(); + return ERR_PTR(-ENOMEM); + } + + skb_reserve(skb, pad - delta); + skb_put(skb, len); + skb_set_owner_w(skb, tfile->socket.sk); + get_page(alloc_frag->page); + alloc_frag->offset += buflen; + + rcu_read_unlock(); + local_bh_enable(); + + return skb; + +err_redirect: + put_page(alloc_frag->page); +err_xdp: + rcu_read_unlock(); + local_bh_enable(); + this_cpu_inc(tun->pcpu_stats->rx_dropped); + return NULL; +} + /* Get packet from user space buffer */ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, void *msg_control, struct iov_iter *from, - int noblock) + int noblock, bool more) { struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; struct sk_buff *skb; @@ -1204,19 +1742,16 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, int copylen; bool zerocopy = false; int err; - u32 rxhash; - ssize_t n; - - if (!(tun->dev->flags & IFF_UP)) - return -EIO; + u32 rxhash = 0; + int skb_xdp = 1; + bool frags = tun_napi_frags_enabled(tfile); if (!(tun->flags & IFF_NO_PI)) { if (len < sizeof(pi)) return -EINVAL; len -= sizeof(pi); - n = copy_from_iter(&pi, sizeof(pi), from); - if (n != sizeof(pi)) + if (!copy_from_iter_full(&pi, sizeof(pi), from)) return -EFAULT; } @@ -1227,8 +1762,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, return -EINVAL; len -= vnet_hdr_sz; - n = copy_from_iter(&gso, sizeof(gso), from); - if (n != sizeof(gso)) + if (!copy_from_iter_full(&gso, sizeof(gso), from)) return -EFAULT; if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && @@ -1265,36 +1799,75 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, zerocopy = true; } - if (!zerocopy) { - copylen = len; - if (tun16_to_cpu(tun, gso.hdr_len) > good_linear) - linear = good_linear; - else - linear = tun16_to_cpu(tun, gso.hdr_len); - } - - skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); - if (IS_ERR(skb)) { - if (PTR_ERR(skb) != -EAGAIN) + if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) { + /* For the packet that is not easy to be processed + * (e.g gso or jumbo packet), we will do it at after + * skb was created with generic XDP routine. + */ + skb = tun_build_skb(tun, tfile, from, &gso, len, &skb_xdp); + if (IS_ERR(skb)) { this_cpu_inc(tun->pcpu_stats->rx_dropped); - return PTR_ERR(skb); + return PTR_ERR(skb); + } + if (!skb) + return total_len; + } else { + if (!zerocopy) { + copylen = len; + if (tun16_to_cpu(tun, gso.hdr_len) > good_linear) + linear = good_linear; + else + linear = tun16_to_cpu(tun, gso.hdr_len); + } + + if (frags) { + mutex_lock(&tfile->napi_mutex); + skb = tun_napi_alloc_frags(tfile, copylen, from); + /* tun_napi_alloc_frags() enforces a layout for the skb. + * If zerocopy is enabled, then this layout will be + * overwritten by zerocopy_sg_from_iter(). + */ + zerocopy = false; + } else { + skb = tun_alloc_skb(tfile, align, copylen, linear, + noblock); + } + + if (IS_ERR(skb)) { + if (PTR_ERR(skb) != -EAGAIN) + this_cpu_inc(tun->pcpu_stats->rx_dropped); + if (frags) + mutex_unlock(&tfile->napi_mutex); + return PTR_ERR(skb); + } + + if (zerocopy) + err = zerocopy_sg_from_iter(skb, from); + else + err = skb_copy_datagram_from_iter(skb, 0, from, len); + + if (err) { + err = -EFAULT; +drop: + this_cpu_inc(tun->pcpu_stats->rx_dropped); + kfree_skb(skb); + if (frags) { + tfile->napi.skb = NULL; + mutex_unlock(&tfile->napi_mutex); + } + + return err; + } } - if (zerocopy) - err = zerocopy_sg_from_iter(skb, from); - else - err = skb_copy_datagram_from_iter(skb, 0, from, len); - - if (err) { - this_cpu_inc(tun->pcpu_stats->rx_dropped); - kfree_skb(skb); - return -EFAULT; - } - - err = virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun)); - if (err) { + if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) { this_cpu_inc(tun->pcpu_stats->rx_frame_errors); kfree_skb(skb); + if (frags) { + tfile->napi.skb = NULL; + mutex_unlock(&tfile->napi_mutex); + } + return -EINVAL; } @@ -1322,7 +1895,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb->dev = tun->dev; break; case IFF_TAP: - skb->protocol = eth_type_trans(skb, tun->dev); + if (!frags) + skb->protocol = eth_type_trans(skb, tun->dev); break; } @@ -1339,8 +1913,76 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_reset_network_header(skb); skb_probe_transport_header(skb, 0); - rxhash = skb_get_hash(skb); - netif_rx_ni(skb); + if (skb_xdp) { + struct bpf_prog *xdp_prog; + int ret; + + local_bh_disable(); + rcu_read_lock(); + xdp_prog = rcu_dereference(tun->xdp_prog); + if (xdp_prog) { + ret = do_xdp_generic(xdp_prog, skb); + if (ret != XDP_PASS) { + rcu_read_unlock(); + local_bh_enable(); + return total_len; + } + } + rcu_read_unlock(); + local_bh_enable(); + } + + /* Compute the costly rx hash only if needed for flow updates. + * We may get a very small possibility of OOO during switching, not + * worth to optimize. + */ + if (!rcu_access_pointer(tun->steering_prog) && tun->numqueues > 1 && + !tfile->detached) + rxhash = __skb_get_hash_symmetric(skb); + + rcu_read_lock(); + if (unlikely(!(tun->dev->flags & IFF_UP))) { + err = -EIO; + rcu_read_unlock(); + goto drop; + } + + if (frags) { + /* Exercise flow dissector code path. */ + u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb)); + + if (unlikely(headlen > skb_headlen(skb))) { + this_cpu_inc(tun->pcpu_stats->rx_dropped); + napi_free_frags(&tfile->napi); + rcu_read_unlock(); + mutex_unlock(&tfile->napi_mutex); + WARN_ON(1); + return -ENOMEM; + } + + local_bh_disable(); + napi_gro_frags(&tfile->napi); + local_bh_enable(); + mutex_unlock(&tfile->napi_mutex); + } else if (tfile->napi_enabled) { + struct sk_buff_head *queue = &tfile->sk.sk_write_queue; + int queue_len; + + spin_lock_bh(&queue->lock); + __skb_queue_tail(queue, skb); + queue_len = skb_queue_len(queue); + spin_unlock(&queue->lock); + + if (!more || queue_len > NAPI_POLL_WEIGHT) + napi_schedule(&tfile->napi); + + local_bh_enable(); + } else if (!IS_ENABLED(CONFIG_4KSTACKS)) { + tun_rx_batched(tun, tfile, skb, more); + } else { + netif_rx_ni(skb); + } + rcu_read_unlock(); stats = get_cpu_ptr(tun->pcpu_stats); u64_stats_update_begin(&stats->syncp); @@ -1349,26 +1991,63 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, u64_stats_update_end(&stats->syncp); put_cpu_ptr(stats); - tun_flow_update(tun, rxhash, tfile); + if (rxhash) + tun_flow_update(tun, rxhash, tfile); + return total_len; } static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct tun_struct *tun = tun_get(file); struct tun_file *tfile = file->private_data; + struct tun_struct *tun = tun_get(tfile); ssize_t result; if (!tun) return -EBADFD; - result = tun_get_user(tun, tfile, NULL, from, file->f_flags & O_NONBLOCK); + result = tun_get_user(tun, tfile, NULL, from, + file->f_flags & O_NONBLOCK, false); tun_put(tun); return result; } +static ssize_t tun_put_user_xdp(struct tun_struct *tun, + struct tun_file *tfile, + struct xdp_frame *xdp_frame, + struct iov_iter *iter) +{ + int vnet_hdr_sz = 0; + size_t size = xdp_frame->len; + struct tun_pcpu_stats *stats; + size_t ret; + + if (tun->flags & IFF_VNET_HDR) { + struct virtio_net_hdr gso = { 0 }; + + vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); + if (unlikely(iov_iter_count(iter) < vnet_hdr_sz)) + return -EINVAL; + if (unlikely(copy_to_iter(&gso, sizeof(gso), iter) != + sizeof(gso))) + return -EFAULT; + iov_iter_advance(iter, vnet_hdr_sz - sizeof(gso)); + } + + ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz; + + stats = get_cpu_ptr(tun->pcpu_stats); + u64_stats_update_begin(&stats->syncp); + stats->tx_packets++; + stats->tx_bytes += ret; + u64_stats_update_end(&stats->syncp); + put_cpu_ptr(tun->pcpu_stats); + + return ret; +} + /* Put packet to the user space buffer */ static ssize_t tun_put_user(struct tun_struct *tun, struct tun_file *tfile, @@ -1405,15 +2084,14 @@ static ssize_t tun_put_user(struct tun_struct *tun, } if (vnet_hdr_sz) { - struct virtio_net_hdr gso = { 0 }; /* no info leak */ - int ret; + struct virtio_net_hdr gso; if (iov_iter_count(iter) < vnet_hdr_sz) return -EINVAL; - ret = virtio_net_hdr_from_skb(skb, &gso, - tun_is_little_endian(tun), true); - if (ret) { + if (virtio_net_hdr_from_skb(skb, &gso, + tun_is_little_endian(tun), true, + vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); pr_err("unexpected GSO type: " "0x%x, gso_size %d, hdr_len %d\n", @@ -1435,10 +2113,7 @@ static ssize_t tun_put_user(struct tun_struct *tun, if (vlan_hlen) { int ret; - struct { - __be16 h_vlan_proto; - __be16 h_vlan_TCI; - } veth; + struct veth veth; veth.h_vlan_proto = skb->vlan_proto; veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); @@ -1468,15 +2143,14 @@ done: return total; } -static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock, - int *err) +static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err) { DECLARE_WAITQUEUE(wait, current); - struct sk_buff *skb = NULL; + void *ptr = NULL; int error = 0; - skb = skb_array_consume(&tfile->tx_array); - if (skb) + ptr = ptr_ring_consume(&tfile->tx_ring); + if (ptr) goto out; if (noblock) { error = -EAGAIN; @@ -1484,11 +2158,11 @@ static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock, } add_wait_queue(&tfile->wq.wait, &wait); - current->state = TASK_INTERRUPTIBLE; while (1) { - skb = skb_array_consume(&tfile->tx_array); - if (skb) + set_current_state(TASK_INTERRUPTIBLE); + ptr = ptr_ring_consume(&tfile->tx_ring); + if (ptr) break; if (signal_pending(current)) { error = -ERESTARTSYS; @@ -1502,37 +2176,49 @@ static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock, schedule(); } - current->state = TASK_RUNNING; + __set_current_state(TASK_RUNNING); remove_wait_queue(&tfile->wq.wait, &wait); out: *err = error; - return skb; + return ptr; } static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *to, - int noblock) + int noblock, void *ptr) { - struct sk_buff *skb; ssize_t ret; int err; tun_debug(KERN_INFO, tun, "tun_do_read\n"); - if (!iov_iter_count(to)) + if (!iov_iter_count(to)) { + tun_ptr_free(ptr); return 0; + } - /* Read frames from ring */ - skb = tun_ring_recv(tfile, noblock, &err); - if (!skb) - return err; + if (!ptr) { + /* Read frames from ring */ + ptr = tun_ring_recv(tfile, noblock, &err); + if (!ptr) + return err; + } - ret = tun_put_user(tun, tfile, skb, to); - if (unlikely(ret < 0)) - kfree_skb(skb); - else - consume_skb(skb); + if (tun_is_xdp_frame(ptr)) { + struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); + + ret = tun_put_user_xdp(tun, tfile, xdpf, to); + xdp_return_frame(xdpf); + } else { + struct sk_buff *skb = ptr; + + ret = tun_put_user(tun, tfile, skb, to); + if (unlikely(ret < 0)) + kfree_skb(skb); + else + consume_skb(skb); + } return ret; } @@ -1541,12 +2227,12 @@ static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; - struct tun_struct *tun = __tun_get(tfile); + struct tun_struct *tun = tun_get(tfile); ssize_t len = iov_iter_count(to), ret; if (!tun) return -EBADFD; - ret = tun_do_read(tun, tfile, to, file->f_flags & O_NONBLOCK); + ret = tun_do_read(tun, tfile, to, file->f_flags & O_NONBLOCK, NULL); ret = min_t(ssize_t, ret, len); if (ret > 0) iocb->ki_pos = ret; @@ -1554,6 +2240,39 @@ static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) return ret; } +static void tun_prog_free(struct rcu_head *rcu) +{ + struct tun_prog *prog = container_of(rcu, struct tun_prog, rcu); + + bpf_prog_destroy(prog->prog); + kfree(prog); +} + +static int __tun_set_ebpf(struct tun_struct *tun, + struct tun_prog __rcu **prog_p, + struct bpf_prog *prog) +{ + struct tun_prog *old, *new = NULL; + + if (prog) { + new = kmalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return -ENOMEM; + new->prog = prog; + } + + spin_lock_bh(&tun->lock); + old = rcu_dereference_protected(*prog_p, + lockdep_is_held(&tun->lock)); + rcu_assign_pointer(*prog_p, new); + spin_unlock_bh(&tun->lock); + + if (old) + call_rcu(&old->rcu, tun_prog_free); + + return 0; +} + static void tun_free_netdev(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); @@ -1562,7 +2281,8 @@ static void tun_free_netdev(struct net_device *dev) free_percpu(tun->pcpu_stats); tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); - free_netdev(dev); + __tun_set_ebpf(tun, &tun->steering_prog, NULL); + __tun_set_ebpf(tun, &tun->filter_prog, NULL); } static void tun_setup(struct net_device *dev) @@ -1571,9 +2291,11 @@ static void tun_setup(struct net_device *dev) tun->owner = INVALID_UID; tun->group = INVALID_GID; + tun_default_link_ksettings(dev, &tun->link_ksettings); dev->ethtool_ops = &tun_ethtool_ops; - dev->destructor = tun_free_netdev; + dev->needs_free_netdev = true; + dev->priv_destructor = tun_free_netdev; /* We prefer our own queue length */ dev->tx_queue_len = TUN_READQ_SIZE; } @@ -1581,9 +2303,66 @@ static void tun_setup(struct net_device *dev) /* Trivial set of netlink ops to allow deleting tun or tap * device with netlink. */ -static int tun_validate(struct nlattr *tb[], struct nlattr *data[]) +static int tun_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { - return -EINVAL; + NL_SET_ERR_MSG(extack, + "tun/tap creation via rtnetlink is not supported."); + return -EOPNOTSUPP; +} + +static size_t tun_get_size(const struct net_device *dev) +{ + BUILD_BUG_ON(sizeof(u32) != sizeof(uid_t)); + BUILD_BUG_ON(sizeof(u32) != sizeof(gid_t)); + + return nla_total_size(sizeof(uid_t)) + /* OWNER */ + nla_total_size(sizeof(gid_t)) + /* GROUP */ + nla_total_size(sizeof(u8)) + /* TYPE */ + nla_total_size(sizeof(u8)) + /* PI */ + nla_total_size(sizeof(u8)) + /* VNET_HDR */ + nla_total_size(sizeof(u8)) + /* PERSIST */ + nla_total_size(sizeof(u8)) + /* MULTI_QUEUE */ + nla_total_size(sizeof(u32)) + /* NUM_QUEUES */ + nla_total_size(sizeof(u32)) + /* NUM_DISABLED_QUEUES */ + 0; +} + +static int tun_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + + if (nla_put_u8(skb, IFLA_TUN_TYPE, tun->flags & TUN_TYPE_MASK)) + goto nla_put_failure; + if (uid_valid(tun->owner) && + nla_put_u32(skb, IFLA_TUN_OWNER, + from_kuid_munged(current_user_ns(), tun->owner))) + goto nla_put_failure; + if (gid_valid(tun->group) && + nla_put_u32(skb, IFLA_TUN_GROUP, + from_kgid_munged(current_user_ns(), tun->group))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_PI, !(tun->flags & IFF_NO_PI))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(tun->flags & IFF_VNET_HDR))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(tun->flags & IFF_PERSIST))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_MULTI_QUEUE, + !!(tun->flags & IFF_MULTI_QUEUE))) + goto nla_put_failure; + if (tun->flags & IFF_MULTI_QUEUE) { + if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES, tun->numqueues)) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_TUN_NUM_DISABLED_QUEUES, + tun->numdisabled)) + goto nla_put_failure; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; } static struct rtnl_link_ops tun_link_ops __read_mostly = { @@ -1591,6 +2370,8 @@ static struct rtnl_link_ops tun_link_ops __read_mostly = { .priv_size = sizeof(struct tun_struct), .setup = tun_setup, .validate = tun_validate, + .get_size = tun_get_size, + .fill_info = tun_fill_info, }; static void tun_sock_write_space(struct sock *sk) @@ -1606,8 +2387,8 @@ static void tun_sock_write_space(struct sock *sk) wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) - wake_up_interruptible_sync_poll(wqueue, POLLOUT | - POLLWRNORM | POLLWRBAND); + wake_up_interruptible_sync_poll(wqueue, EPOLLOUT | + EPOLLWRNORM | EPOLLWRBAND); tfile = container_of(sk, struct tun_file, sk); kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); @@ -1617,13 +2398,14 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { int ret; struct tun_file *tfile = container_of(sock, struct tun_file, socket); - struct tun_struct *tun = __tun_get(tfile); + struct tun_struct *tun = tun_get(tfile); if (!tun) return -EBADFD; ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter, - m->msg_flags & MSG_DONTWAIT); + m->msg_flags & MSG_DONTWAIT, + m->msg_flags & MSG_MORE); tun_put(tun); return ret; } @@ -1632,22 +2414,25 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, int flags) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); - struct tun_struct *tun = __tun_get(tfile); + struct tun_struct *tun = tun_get(tfile); + void *ptr = m->msg_control; int ret; - if (!tun) - return -EBADFD; + if (!tun) { + ret = -EBADFD; + goto out_free; + } if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { ret = -EINVAL; - goto out; + goto out_put_tun; } if (flags & MSG_ERRQUEUE) { ret = sock_recv_errqueue(sock->sk, m, total_len, SOL_PACKET, TUN_TX_TIMESTAMP); goto out; } - ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT); + ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, ptr); if (ret > (ssize_t)total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; @@ -1655,6 +2440,26 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, out: tun_put(tun); return ret; + +out_put_tun: + tun_put(tun); +out_free: + tun_ptr_free(ptr); + return ret; +} + +static int tun_ptr_peek_len(void *ptr) +{ + if (likely(ptr)) { + if (tun_is_xdp_frame(ptr)) { + struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); + + return xdpf->len; + } + return __skb_array_len_with_tag(ptr); + } else { + return 0; + } } static int tun_peek_len(struct socket *sock) @@ -1663,11 +2468,11 @@ static int tun_peek_len(struct socket *sock) struct tun_struct *tun; int ret = 0; - tun = __tun_get(tfile); + tun = tun_get(tfile); if (!tun) return 0; - ret = skb_array_peek_len(&tfile->tx_array); + ret = PTR_RING_PEEK_CALL(&tfile->tx_ring, tun_ptr_peek_len); tun_put(tun); return ret; @@ -1743,6 +2548,15 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (tfile->detached) return -EINVAL; + if ((ifr->ifr_flags & IFF_NAPI_FRAGS)) { + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!(ifr->ifr_flags & IFF_NAPI) || + (ifr->ifr_flags & TUN_TYPE_MASK) != IFF_TAP) + return -EINVAL; + } + dev = __dev_get_by_name(net, ifr->ifr_name); if (dev) { if (ifr->ifr_flags & IFF_TUN_EXCL) @@ -1764,7 +2578,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (err < 0) return err; - err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER); + err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER, + ifr->ifr_flags & IFF_NAPI, + ifr->ifr_flags & IFF_NAPI_FRAGS); if (err < 0) return err; @@ -1773,10 +2589,15 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) /* One or more queue has already been attached, no need * to initialize the device again. */ + netdev_state_change(dev); return 0; } - } - else { + + tun->flags = (tun->flags & ~TUN_FEATURES) | + (ifr->ifr_flags & TUN_FEATURES); + + netdev_state_change(dev); + } else { char *name; unsigned long flags = 0; int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? @@ -1809,11 +2630,10 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (!dev) return -ENOMEM; -#if 0 err = dev_get_valid_name(net, dev, name); if (err < 0) goto err_free_dev; -#endif + dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; dev->ifindex = tfile->ifindex; @@ -1828,6 +2648,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) tun->align = NET_SKB_PAD; tun->filter_attached = false; tun->sndbuf = tfile->socket.sk->sk_sndbuf; + tun->rx_batched = 0; + RCU_INIT_POINTER(tun->steering_prog, NULL); tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats); if (!tun->pcpu_stats) { @@ -1852,8 +2674,12 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); + tun->flags = (tun->flags & ~TUN_FEATURES) | + (ifr->ifr_flags & TUN_FEATURES); + INIT_LIST_HEAD(&tun->disabled); - err = tun_attach(tun, file, false); + err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI, + ifr->ifr_flags & IFF_NAPI_FRAGS); if (err < 0) goto err_free_flow; @@ -1866,9 +2692,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) tun_debug(KERN_INFO, tun, "tun_set_iff\n"); - tun->flags = (tun->flags & ~TUN_FEATURES) | - (ifr->ifr_flags & TUN_FEATURES); - /* Make sure persistent devices do not get stuck in * xoff state. */ @@ -1880,6 +2703,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) err_detach: tun_detach_all(dev); + /* register_netdevice() already called tun_free_netdev() */ + goto err_free_dev; + err_free_flow: tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); @@ -1923,10 +2749,7 @@ static int set_offload(struct tun_struct *tun, unsigned long arg) arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } - if (arg & TUN_F_UFO) { - features |= NETIF_F_UFO; - arg &= ~TUN_F_UFO; - } + arg &= ~TUN_F_UFO; } /* This gives the user a way to test for new features in future by @@ -1935,6 +2758,8 @@ static int set_offload(struct tun_struct *tun, unsigned long arg) return -EINVAL; tun->set_features = features; + tun->dev->wanted_features &= ~TUN_USER_FEATURES; + tun->dev->wanted_features |= features; netdev_update_features(tun->dev); return 0; @@ -2003,7 +2828,8 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr) ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; - ret = tun_attach(tun, file, false); + ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI, + tun->flags & IFF_NAPI_FRAGS); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached) @@ -2013,15 +2839,39 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr) } else ret = -EINVAL; + if (ret >= 0) + netdev_state_change(tun->dev); + unlock: rtnl_unlock(); return ret; } +static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog **prog_p, + void __user *data) +{ + struct bpf_prog *prog; + int fd; + + if (copy_from_user(&fd, data, sizeof(fd))) + return -EFAULT; + + if (fd == -1) { + prog = NULL; + } else { + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); + if (IS_ERR(prog)) + return PTR_ERR(prog); + } + + return __tun_set_ebpf(tun, prog_p, prog); +} + static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { struct tun_file *tfile = file->private_data; + struct net *net = sock_net(&tfile->sk); struct tun_struct *tun; void __user* argp = (void __user*)arg; struct ifreq ifr; @@ -2032,8 +2882,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned int ifindex; int le; int ret; + bool do_notify = false; - if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) { + if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || + (_IOC_TYPE(cmd) == SOCK_IOC_TYPE && cmd != SIOCGSKNS)) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; } else { @@ -2046,17 +2898,26 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, */ return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES, (unsigned int __user*)argp); - } else if (cmd == TUNSETQUEUE) + } else if (cmd == TUNSETQUEUE) { return tun_set_queue(file, &ifr); + } else if (cmd == SIOCGSKNS) { + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + return open_related_ns(&net->ns, get_net_ns); + } ret = 0; rtnl_lock(); - tun = __tun_get(tfile); - if (cmd == TUNSETIFF && !tun) { + tun = tun_get(tfile); + if (cmd == TUNSETIFF) { + ret = -EEXIST; + if (tun) + goto unlock; + ifr.ifr_name[IFNAMSIZ-1] = '\0'; - ret = tun_set_iff(sock_net(&tfile->sk), file, &ifr); + ret = tun_set_iff(net, file, &ifr); if (ret) goto unlock; @@ -2114,10 +2975,12 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, if (arg && !(tun->flags & IFF_PERSIST)) { tun->flags |= IFF_PERSIST; __module_get(THIS_MODULE); + do_notify = true; } if (!arg && (tun->flags & IFF_PERSIST)) { tun->flags &= ~IFF_PERSIST; module_put(THIS_MODULE); + do_notify = true; } tun_debug(KERN_INFO, tun, "persist %s\n", @@ -2132,6 +2995,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, break; } tun->owner = owner; + do_notify = true; tun_debug(KERN_INFO, tun, "owner set to %u\n", from_kuid(&init_user_ns, tun->owner)); break; @@ -2144,6 +3008,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, break; } tun->group = group; + do_notify = true; tun_debug(KERN_INFO, tun, "group set to %u\n", from_kgid(&init_user_ns, tun->group)); break; @@ -2290,11 +3155,22 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, ret = 0; break; + case TUNSETSTEERINGEBPF: + ret = tun_set_ebpf(tun, &tun->steering_prog, argp); + break; + + case TUNSETFILTEREBPF: + ret = tun_set_ebpf(tun, &tun->filter_prog, argp); + break; + default: ret = -EINVAL; break; } + if (do_notify) + netdev_state_change(tun->dev); + unlock: rtnl_unlock(); if (tun) @@ -2346,7 +3222,7 @@ static int tun_chr_fasync(int fd, struct file *file, int on) goto out; if (on) { - __f_setown(file, task_pid(current), PIDTYPE_PID, 0); + __f_setown(file, task_pid(current), PIDTYPE_TGID, 0); tfile->flags |= TUN_FASYNC; } else tfile->flags &= ~TUN_FASYNC; @@ -2366,6 +3242,12 @@ static int tun_chr_open(struct inode *inode, struct file * file) &tun_proto, 0); if (!tfile) return -ENOMEM; + if (ptr_ring_init(&tfile->tx_ring, 0, GFP_KERNEL)) { + sk_free(&tfile->sk); + return -ENOMEM; + } + + mutex_init(&tfile->napi_mutex); RCU_INIT_POINTER(tfile->tun, NULL); tfile->flags = 0; tfile->ifindex = 0; @@ -2386,8 +3268,6 @@ static int tun_chr_open(struct inode *inode, struct file * file) sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); - memset(&tfile->tx_array, 0, sizeof(tfile->tx_array)); - return 0; } @@ -2401,15 +3281,16 @@ static int tun_chr_close(struct inode *inode, struct file *file) } #ifdef CONFIG_PROC_FS -static void tun_chr_show_fdinfo(struct seq_file *m, struct file *f) +static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file) { + struct tun_file *tfile = file->private_data; struct tun_struct *tun; struct ifreq ifr; memset(&ifr, 0, sizeof(ifr)); rtnl_lock(); - tun = tun_get(f); + tun = tun_get(tfile); if (tun) tun_get_iff(current->nsproxy->net_ns, tun, &ifr); rtnl_unlock(); @@ -2440,7 +3321,7 @@ static const struct file_operations tun_fops = { }; static struct miscdevice tun_miscdev = { - .minor = TUN_MINOR1, + .minor = BF_TUN_MINOR, .name = "bf_tun", .nodename = "net/bf_tun", .fops = &tun_fops, @@ -2448,18 +3329,33 @@ static struct miscdevice tun_miscdev = { /* ethtool interface */ -static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static void tun_default_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { - cmd->supported = 0; - cmd->advertising = 0; - ethtool_cmd_speed_set(cmd, SPEED_10); - cmd->duplex = DUPLEX_FULL; - cmd->port = PORT_TP; - cmd->phy_address = 0; - cmd->transceiver = XCVR_INTERNAL; - cmd->autoneg = AUTONEG_DISABLE; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + cmd->base.speed = SPEED_10; + cmd->base.duplex = DUPLEX_FULL; + cmd->base.port = PORT_TP; + cmd->base.phy_address = 0; + cmd->base.autoneg = AUTONEG_DISABLE; +} + +static int tun_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + struct tun_struct *tun = netdev_priv(dev); + + memcpy(cmd, &tun->link_ksettings, sizeof(*cmd)); + return 0; +} + +static int tun_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) +{ + struct tun_struct *tun = netdev_priv(dev); + + memcpy(&tun->link_ksettings, cmd, sizeof(*cmd)); return 0; } @@ -2498,38 +3394,65 @@ static void tun_set_msglevel(struct net_device *dev, u32 value) #endif } +static int tun_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec) +{ + struct tun_struct *tun = netdev_priv(dev); + + ec->rx_max_coalesced_frames = tun->rx_batched; + + return 0; +} + +static int tun_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec) +{ + struct tun_struct *tun = netdev_priv(dev); + + if (ec->rx_max_coalesced_frames > NAPI_POLL_WEIGHT) + tun->rx_batched = NAPI_POLL_WEIGHT; + else + tun->rx_batched = ec->rx_max_coalesced_frames; + + return 0; +} + static const struct ethtool_ops tun_ethtool_ops = { - .get_settings = tun_get_settings, .get_drvinfo = tun_get_drvinfo, .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, .get_link = ethtool_op_get_link, .get_ts_info = ethtool_op_get_ts_info, + .get_coalesce = tun_get_coalesce, + .set_coalesce = tun_set_coalesce, + .get_link_ksettings = tun_get_link_ksettings, + .set_link_ksettings = tun_set_link_ksettings, }; static int tun_queue_resize(struct tun_struct *tun) { struct net_device *dev = tun->dev; struct tun_file *tfile; - struct skb_array **arrays; + struct ptr_ring **rings; int n = tun->numqueues + tun->numdisabled; int ret, i; - arrays = kmalloc(sizeof *arrays * n, GFP_KERNEL); - if (!arrays) + rings = kmalloc_array(n, sizeof(*rings), GFP_KERNEL); + if (!rings) return -ENOMEM; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); - arrays[i] = &tfile->tx_array; + rings[i] = &tfile->tx_ring; } list_for_each_entry(tfile, &tun->disabled, next) - arrays[i++] = &tfile->tx_array; + rings[i++] = &tfile->tx_ring; - ret = skb_array_resize_multiple(arrays, n, - dev->tx_queue_len, GFP_KERNEL); + ret = ptr_ring_resize_multiple(rings, n, + dev->tx_queue_len, GFP_KERNEL, + tun_ptr_free); - kfree(arrays); + kfree(rings); return ret; } @@ -2538,6 +3461,7 @@ static int tun_device_event(struct notifier_block *unused, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tun_struct *tun = netdev_priv(dev); + int i; if (dev->rtnl_link_ops != &tun_link_ops) return NOTIFY_DONE; @@ -2547,6 +3471,14 @@ static int tun_device_event(struct notifier_block *unused, if (tun_queue_resize(tun)) return NOTIFY_BAD; break; + case NETDEV_UP: + for (i = 0; i < tun->numqueues; i++) { + struct tun_file *tfile; + + tfile = rtnl_dereference(tun->tfiles[i]); + tfile->socket.sk->sk_write_space(tfile->socket.sk); + } + break; default: break; } @@ -2563,7 +3495,6 @@ static int __init tun_init(void) int ret = 0; pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION); - pr_info("%s\n", DRV_COPYRIGHT); ret = rtnl_link_register(&tun_link_ops); if (ret) { @@ -2573,12 +3504,20 @@ static int __init tun_init(void) ret = misc_register(&tun_miscdev); if (ret) { - pr_err("Can't register misc device %d\n", TUN_MINOR1); + pr_err("Can't register misc device %d\n", BF_TUN_MINOR); goto err_misc; } - register_netdevice_notifier(&tun_notifier_block); + ret = register_netdevice_notifier(&tun_notifier_block); + if (ret) { + pr_err("Can't register netdevice notifier\n"); + goto err_notifier; + } + return 0; + +err_notifier: + misc_deregister(&tun_miscdev); err_misc: rtnl_link_unregister(&tun_link_ops); err_linkops: @@ -2608,10 +3547,23 @@ struct socket *tun_get_socket(struct file *file) } EXPORT_SYMBOL_GPL(tun_get_socket); +struct ptr_ring *tun_get_tx_ring(struct file *file) +{ + struct tun_file *tfile; + + if (file->f_op != &tun_fops) + return ERR_PTR(-EINVAL); + tfile = file->private_data; + if (!tfile) + return ERR_PTR(-EBADFD); + return &tfile->tx_ring; +} +EXPORT_SYMBOL_GPL(tun_get_tx_ring); + module_init(tun_init); module_exit(tun_cleanup); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR(DRV_COPYRIGHT); MODULE_LICENSE("GPL"); -MODULE_ALIAS_MISCDEV(TUN_MINOR1); +MODULE_ALIAS_MISCDEV(BF_TUN_MINOR); MODULE_ALIAS("devname:net/bf_tun"); diff --git a/platform/barefoot/one-image.mk b/platform/barefoot/one-image.mk index 0147b62d00..31abd3f96c 100644 --- a/platform/barefoot/one-image.mk +++ b/platform/barefoot/one-image.mk @@ -8,7 +8,7 @@ $(SONIC_ONE_IMAGE)_INSTALLS += $(SYSTEMD_SONIC_GENERATOR) $(SONIC_ONE_IMAGE)_LAZY_INSTALLS += $(BFN_PLATFORM_MODULE) $(SONIC_ONE_IMAGE)_LAZY_INSTALLS += $(BFN_MONTARA_PLATFORM_MODULE) $(SONIC_ONE_IMAGE)_LAZY_INSTALLS += $(BFN_NEWPORT_PLATFORM_MODULE) -$(SONIC_ONE_IMAGE)_LAZY_INSTALLS += $(WNC_OSW1800_PLATFORM_MODULE) +#$(SONIC_ONE_IMAGE)_LAZY_INSTALLS += $(WNC_OSW1800_PLATFORM_MODULE) $(SONIC_ONE_IMAGE)_LAZY_INSTALLS += $(INGRASYS_S9180_32X_PLATFORM_MODULE) $(SONIC_ONE_IMAGE)_LAZY_INSTALLS += $(INGRASYS_S9280_64X_PLATFORM_MODULE) ifeq ($(INSTALL_DEBUG_TOOLS),y) diff --git a/platform/barefoot/rules.mk b/platform/barefoot/rules.mk index e9294dd813..b949392286 100644 --- a/platform/barefoot/rules.mk +++ b/platform/barefoot/rules.mk @@ -2,7 +2,7 @@ include $(PLATFORM_PATH)/platform-modules-arista.mk include $(PLATFORM_PATH)/platform-modules-bfn.mk include $(PLATFORM_PATH)/platform-modules-bfn-montara.mk include $(PLATFORM_PATH)/platform-modules-bfn-newport.mk -include $(PLATFORM_PATH)/platform-modules-wnc-osw1800.mk +#include $(PLATFORM_PATH)/platform-modules-wnc-osw1800.mk include $(PLATFORM_PATH)/platform-modules-ingrasys.mk include $(PLATFORM_PATH)/bfn-sai.mk include $(PLATFORM_PATH)/docker-syncd-bfn.mk @@ -20,11 +20,13 @@ SONIC_ALL += $(SONIC_ONE_IMAGE) $(SONIC_ONE_ABOOT) \ $(DOCKER_FPM) # Inject sai into sairedis -$(LIBSAIREDIS)_DEPENDS += $(BFN_SAI) $(WNC_OSW1800_PLATFORM) $(BFN_INGRASYS_PLATFORM) $(BFN_PLATFORM) +#$(LIBSAIREDIS)_DEPENDS += $(BFN_SAI) $(WNC_OSW1800_PLATFORM) $(BFN_INGRASYS_PLATFORM) $(BFN_PLATFORM) +$(LIBSAIREDIS)_DEPENDS += $(BFN_SAI) $(BFN_INGRASYS_PLATFORM) $(BFN_PLATFORM) ifeq ($(ENABLE_SYNCD_RPC),y) $(LIBSAIREDIS)_DEPENDS += $(LIBSAITHRIFT_DEV) endif # Runtime dependency on sai is set only for syncd -$(SYNCD)_RDEPENDS += $(BFN_SAI) $(WNC_OSW1800_PLATFORM) $(BFN_INGRASYS_PLATFORM) $(BFN_PLATFORM) +#$(SYNCD)_RDEPENDS += $(BFN_SAI) $(WNC_OSW1800_PLATFORM) $(BFN_INGRASYS_PLATFORM) $(BFN_PLATFORM) +$(SYNCD)_RDEPENDS += $(BFN_SAI) $(BFN_INGRASYS_PLATFORM) $(BFN_PLATFORM)