// SPDX-License-Identifier: GPL-2.0-only#include <linux/etherdevice.h>#include <linux/if_tap.h>#include <linux/if_vlan.h>#include <linux/interrupt.h>#include <linux/nsproxy.h>#include <linux/compat.h>#include <linux/if_tun.h>#include <linux/module.h>#include <linux/skbuff.h>#include <linux/cache.h>#include <linux/sched/signal.h>#include <linux/types.h>#include <linux/slab.h>#include <linux/wait.h>#include <linux/cdev.h>#include <linux/idr.h>#include <linux/fs.h>#include <linux/uio.h> #include <net/gso.h>#include <net/net_namespace.h>#include <net/rtnetlink.h>#include <net/sock.h>#include <net/xdp.h>#include <linux/virtio_net.h>#include <linux/skb_array.h> #include "tun_vnet.h" #define TAP_IFFEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE) static struct proto tap_proto = { .name = "tap", .owner = THIS_MODULE, .obj_size = sizeof(struct tap_queue),}; #define TAP_NUM_DEVS (1U << MINORBITS) static LIST_HEAD(major_list); struct major_info { struct rcu_head rcu; dev_t major; struct idr minor_idr; spinlock_t minor_lock; const char *device_name; struct list_head next;}; #define GOODCOPY_LEN 128 static const struct proto_ops tap_socket_ops; #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG | NETIF_F_FRAGLIST) static struct tap_dev *tap_dev_get_rcu(const struct net_device *dev){ return rcu_dereference(dev->rx_handler_data);} /* * RCU usage: * The tap_queue and the macvlan_dev are loosely coupled, the * pointers from one to the other can only be read while rcu_read_lock * or rtnl is held. * * Both the file and the macvlan_dev hold a reference on the tap_queue * through sock_hold(&q->sk). When the macvlan_dev goes away first, * q->vlan becomes inaccessible. When the files gets closed, * tap_get_queue() fails. * * There may still be references to the struct sock inside of the * queue from outbound SKBs, but these never reference back to the * file or the dev. The data structure is freed through __sk_free * when both our references and any pending SKBs are gone. */ static int tap_enable_queue(struct tap_dev *tap, struct file *file, struct tap_queue *q){ int err = -EINVAL; ASSERT_RTNL(); if (q->enabled) goto out; err = 0; rcu_assign_pointer(tap->taps[tap->numvtaps], q); q->queue_index = tap->numvtaps; q->enabled = true; tap->numvtaps++;out: return err;} /* Requires RTNL */static int tap_set_queue(struct tap_dev *tap, struct file *file, struct tap_queue *q){ if (tap->numqueues == MAX_TAP_QUEUES) return -EBUSY; rcu_assign_pointer(q->tap, tap); rcu_assign_pointer(tap->taps[tap->numvtaps], q); sock_hold(&q->sk); q->file = file; q->queue_index = tap->numvtaps; q->enabled = true; file->private_data = q; list_add_tail(&q->next, &tap->queue_list); tap->numvtaps++; tap->numqueues++; return 0;} static int tap_disable_queue(struct tap_queue *q){ struct tap_dev *tap; struct tap_queue *nq; ASSERT_RTNL(); if (!q->enabled) return -EINVAL; tap = rtnl_dereference(q->tap); if (tap) { int index = q->queue_index; BUG_ON(index >= tap->numvtaps); nq = rtnl_dereference(tap->taps[tap->numvtaps - 1]); nq->queue_index = index; rcu_assign_pointer(tap->taps[index], nq); RCU_INIT_POINTER(tap->taps[tap->numvtaps - 1], NULL); q->enabled = false; tap->numvtaps--; } return 0;} /* * The file owning the queue got closed, give up both * the reference that the files holds as well as the * one from the macvlan_dev if that still exists. * * Using the spinlock makes sure that we don't get * to the queue again after destroying it. */static void tap_put_queue(struct tap_queue *q){ struct tap_dev *tap; rtnl_lock(); tap = rtnl_dereference(q->tap); if (tap) { if (q->enabled) BUG_ON(tap_disable_queue(q)); tap->numqueues--; RCU_INIT_POINTER(q->tap, NULL); sock_put(&q->sk); list_del_init(&q->next); } rtnl_unlock(); synchronize_rcu(); sock_put(&q->sk);} /* * Select a queue based on the rxq of the device on which this packet * arrived. If the incoming device is not mq, calculate a flow hash * to select a queue. If all fails, find the first available queue. * Cache vlan->numvtaps since it can become zero during the execution * of this function. */static struct tap_queue *tap_get_queue(struct tap_dev *tap, struct sk_buff *skb){ struct tap_queue *queue = NULL; /* Access to taps array is protected by rcu, but access to numvtaps * isn't. Below we use it to lookup a queue, but treat it as a hint * and validate that the result isn't NULL - in case we are * racing against queue removal. */ int numvtaps = READ_ONCE(tap->numvtaps); __u32 rxq; if (!numvtaps) goto out; if (numvtaps == 1) goto single; /* Check if we can use flow to select a queue */ rxq = skb_get_hash(skb); if (rxq) { queue = rcu_dereference(tap->taps[rxq % numvtaps]); goto out; } if (likely(skb_rx_queue_recorded(skb))) { rxq = skb_get_rx_queue(skb); while (unlikely(rxq >= numvtaps)) rxq -= numvtaps; queue = rcu_dereference(tap->taps[rxq]); goto out; } single: queue = rcu_dereference(tap->taps[0]);out: return queue;} /* * The net_device is going away, give up the reference * that it holds on all queues and safely set the pointer * from the queues to NULL. */void tap_del_queues(struct tap_dev *tap){ struct tap_queue *q, *tmp; ASSERT_RTNL(); list_for_each_entry_safe(q, tmp, &tap->queue_list, next) { list_del_init(&q->next); RCU_INIT_POINTER(q->tap, NULL); if (q->enabled) tap->numvtaps--; tap->numqueues--; sock_put(&q->sk); } BUG_ON(tap->numvtaps); BUG_ON(tap->numqueues); /* guarantee that any future tap_set_queue will fail */ tap->numvtaps = MAX_TAP_QUEUES;}EXPORT_SYMBOL_GPL(tap_del_queues); rx_handler_result_t tap_handle_frame(struct sk_buff **pskb){ struct sk_buff *skb = *pskb; struct net_device *dev = skb->dev; struct tap_dev *tap; struct tap_queue *q; netdev_features_t features = TAP_FEATURES; enum skb_drop_reason drop_reason; tap = tap_dev_get_rcu(dev); if (!tap) return RX_HANDLER_PASS; q = tap_get_queue(tap, skb); if (!q) return RX_HANDLER_PASS; skb_push(skb, ETH_HLEN); /* Apply the forward feature mask so that we perform segmentation * according to users wishes. This only works if VNET_HDR is * enabled. */ if (q->flags & IFF_VNET_HDR) features |= tap->tap_features; if (netif_needs_gso(skb, features)) { struct sk_buff *segs = __skb_gso_segment(skb, features, false); struct sk_buff *next; if (IS_ERR(segs)) { drop_reason = SKB_DROP_REASON_SKB_GSO_SEG; goto drop; } if (!segs) { if (ptr_ring_produce(&q->ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; goto drop; } goto wake_up; } consume_skb(skb); skb_list_walk_safe(segs, skb, next) { skb_mark_not_on_list(skb); if (ptr_ring_produce(&q->ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; kfree_skb_reason(skb, drop_reason); kfree_skb_list_reason(next, drop_reason); break; } } } else { /* If we receive a partial checksum and the tap side * doesn't support checksum offload, compute the checksum. * Note: it doesn't matter which checksum feature to * check, we either support them all or none. */ if (skb->ip_summed == CHECKSUM_PARTIAL && !(features & NETIF_F_CSUM_MASK) && skb_checksum_help(skb)) { drop_reason = SKB_DROP_REASON_SKB_CSUM; goto drop; } if (ptr_ring_produce(&q->ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; goto drop; } } wake_up: wake_up_interruptible_poll(sk_sleep(&q->sk), EPOLLIN | EPOLLRDNORM | EPOLLRDBAND); return RX_HANDLER_CONSUMED; drop: /* Count errors/drops only here, thus don't care about args. */ if (tap->count_rx_dropped) tap->count_rx_dropped(tap); kfree_skb_reason(skb, drop_reason); return RX_HANDLER_CONSUMED;}EXPORT_SYMBOL_GPL(tap_handle_frame); static struct major_info *tap_get_major(int major){ struct major_info *tap_major; list_for_each_entry_rcu(tap_major, &major_list, next) { if (tap_major->major == major) return tap_major; } return NULL;} int tap_get_minor(dev_t major, struct tap_dev *tap){ int retval = -ENOMEM; struct major_info *tap_major; rcu_read_lock(); tap_major = tap_get_major(MAJOR(major)); if (!tap_major) { retval = -EINVAL; goto unlock; } spin_lock(&tap_major->minor_lock); retval = idr_alloc(&tap_major->minor_idr, tap, 1, TAP_NUM_DEVS, GFP_ATOMIC); if (retval >= 0) { tap->minor = retval; } else if (retval == -ENOSPC) { netdev_err(tap->dev, "Too many tap devices\n"); retval = -EINVAL; } spin_unlock(&tap_major->minor_lock); unlock: rcu_read_unlock(); return retval < 0 ? retval : 0;}EXPORT_SYMBOL_GPL(tap_get_minor); void tap_free_minor(dev_t major, struct tap_dev *tap){ struct major_info *tap_major; rcu_read_lock(); tap_major = tap_get_major(MAJOR(major)); if (!tap_major) { goto unlock; } spin_lock(&tap_major->minor_lock); if (tap->minor) { idr_remove(&tap_major->minor_idr, tap->minor); tap->minor = 0; } spin_unlock(&tap_major->minor_lock); unlock: rcu_read_unlock();}EXPORT_SYMBOL_GPL(tap_free_minor); static struct tap_dev *dev_get_by_tap_file(int major, int minor){ struct net_device *dev = NULL; struct tap_dev *tap; struct major_info *tap_major; rcu_read_lock(); tap_major = tap_get_major(major); if (!tap_major) { tap = NULL; goto unlock; } spin_lock(&tap_major->minor_lock); tap = idr_find(&tap_major->minor_idr, minor); if (tap) { dev = tap->dev; dev_hold(dev); } spin_unlock(&tap_major->minor_lock); unlock: rcu_read_unlock(); return tap;} static void tap_sock_write_space(struct sock *sk){ wait_queue_head_t *wqueue; if (!sock_writeable(sk) || !test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) wake_up_interruptible_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);} static void tap_sock_destruct(struct sock *sk){ struct tap_queue *q = container_of(sk, struct tap_queue, sk); ptr_ring_cleanup(&q->ring, __skb_array_destroy_skb);} static int tap_open(struct inode *inode, struct file *file){ struct net *net = current->nsproxy->net_ns; struct tap_dev *tap; struct tap_queue *q; int err = -ENODEV; rtnl_lock(); tap = dev_get_by_tap_file(imajor(inode), iminor(inode)); if (!tap) goto err; err = -ENOMEM; q = (struct tap_queue *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tap_proto, 0); if (!q) goto err; if (ptr_ring_init(&q->ring, tap->dev->tx_queue_len, GFP_KERNEL)) { sk_free(&q->sk); goto err; } init_waitqueue_head(&q->sock.wq.wait); q->sock.type = SOCK_RAW; q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; sock_init_data_uid(&q->sock, &q->sk, current_fsuid()); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; q->vnet_hdr_sz = sizeof(struct virtio_net_hdr); /* * so far only KVM virtio_net uses tap, enable zero copy between * guest kernel and host kernel when lower device supports zerocopy * * The macvlan supports zerocopy iff the lower device supports zero * copy so we don't have to look at the lower device directly. */ if ((tap->dev->features & NETIF_F_HIGHDMA) && (tap->dev->features & NETIF_F_SG)) sock_set_flag(&q->sk, SOCK_ZEROCOPY); err = tap_set_queue(tap, file, q); if (err) { /* tap_sock_destruct() will take care of freeing ptr_ring */ goto err_put; } /* tap groks IOCB_NOWAIT just fine, mark it as such */ file->f_mode |= FMODE_NOWAIT; dev_put(tap->dev); rtnl_unlock();Lines 1–500 of 1291. Load more
// SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/gso.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <net/xdp.h> #include <linux/virtio_net.h> #include <linux/skb_array.h> #include "tun_vnet.h" #define TAP_IFFEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE) static struct proto tap_proto = { .name = "tap", .owner = THIS_MODULE, .obj_size = sizeof(struct tap_queue), }; #define TAP_NUM_DEVS (1U << MINORBITS) static LIST_HEAD(major_list); struct major_info { struct rcu_head rcu; dev_t major; struct idr minor_idr; spinlock_t minor_lock; const char *device_name; struct list_head next; }; #define GOODCOPY_LEN 128 static const struct proto_ops tap_socket_ops; #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO) #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG | NETIF_F_FRAGLIST) static struct tap_dev *tap_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->rx_handler_data); } /* * RCU usage: * The tap_queue and the macvlan_dev are loosely coupled, the * pointers from one to the other can only be read while rcu_read_lock * or rtnl is held. * * Both the file and the macvlan_dev hold a reference on the tap_queue * through sock_hold(&q->sk). When the macvlan_dev goes away first, * q->vlan becomes inaccessible. When the files gets closed, * tap_get_queue() fails. * * There may still be references to the struct sock inside of the * queue from outbound SKBs, but these never reference back to the * file or the dev. The data structure is freed through __sk_free * when both our references and any pending SKBs are gone. */ static int tap_enable_queue(struct tap_dev *tap, struct file *file, struct tap_queue *q) { int err = -EINVAL; ASSERT_RTNL(); if (q->enabled) goto out; err = 0; rcu_assign_pointer(tap->taps[tap->numvtaps], q); q->queue_index = tap->numvtaps; q->enabled = true; tap->numvtaps++; out: return err; } /* Requires RTNL */ static int tap_set_queue(struct tap_dev *tap, struct file *file, struct tap_queue *q) { if (tap->numqueues == MAX_TAP_QUEUES) return -EBUSY; rcu_assign_pointer(q->tap, tap); rcu_assign_pointer(tap->taps[tap->numvtaps], q); sock_hold(&q->sk); q->file = file; q->queue_index = tap->numvtaps; q->enabled = true; file->private_data = q; list_add_tail(&q->next, &tap->queue_list); tap->numvtaps++; tap->numqueues++; return 0; } static int tap_disable_queue(struct tap_queue *q) { struct tap_dev *tap; struct tap_queue *nq; ASSERT_RTNL(); if (!q->enabled) return -EINVAL; tap = rtnl_dereference(q->tap); if (tap) { int index = q->queue_index; BUG_ON(index >= tap->numvtaps); nq = rtnl_dereference(tap->taps[tap->numvtaps - 1]); nq->queue_index = index; rcu_assign_pointer(tap->taps[index], nq); RCU_INIT_POINTER(tap->taps[tap->numvtaps - 1], NULL); q->enabled = false; tap->numvtaps--; } return 0; } /* * The file owning the queue got closed, give up both * the reference that the files holds as well as the * one from the macvlan_dev if that still exists. * * Using the spinlock makes sure that we don't get * to the queue again after destroying it. */ static void tap_put_queue(struct tap_queue *q) { struct tap_dev *tap; rtnl_lock(); tap = rtnl_dereference(q->tap); if (tap) { if (q->enabled) BUG_ON(tap_disable_queue(q)); tap->numqueues--; RCU_INIT_POINTER(q->tap, NULL); sock_put(&q->sk); list_del_init(&q->next); } rtnl_unlock(); synchronize_rcu(); sock_put(&q->sk); } /* * Select a queue based on the rxq of the device on which this packet * arrived. If the incoming device is not mq, calculate a flow hash * to select a queue. If all fails, find the first available queue. * Cache vlan->numvtaps since it can become zero during the execution * of this function. */ static struct tap_queue *tap_get_queue(struct tap_dev *tap, struct sk_buff *skb) { struct tap_queue *queue = NULL; /* Access to taps array is protected by rcu, but access to numvtaps * isn't. Below we use it to lookup a queue, but treat it as a hint * and validate that the result isn't NULL - in case we are * racing against queue removal. */ int numvtaps = READ_ONCE(tap->numvtaps); __u32 rxq; if (!numvtaps) goto out; if (numvtaps == 1) goto single; /* Check if we can use flow to select a queue */ rxq = skb_get_hash(skb); if (rxq) { queue = rcu_dereference(tap->taps[rxq % numvtaps]); goto out; } if (likely(skb_rx_queue_recorded(skb))) { rxq = skb_get_rx_queue(skb); while (unlikely(rxq >= numvtaps)) rxq -= numvtaps; queue = rcu_dereference(tap->taps[rxq]); goto out; } single: queue = rcu_dereference(tap->taps[0]); out: return queue; } /* * The net_device is going away, give up the reference * that it holds on all queues and safely set the pointer * from the queues to NULL. */ void tap_del_queues(struct tap_dev *tap) { struct tap_queue *q, *tmp; ASSERT_RTNL(); list_for_each_entry_safe(q, tmp, &tap->queue_list, next) { list_del_init(&q->next); RCU_INIT_POINTER(q->tap, NULL); if (q->enabled) tap->numvtaps--; tap->numqueues--; sock_put(&q->sk); } BUG_ON(tap->numvtaps); BUG_ON(tap->numqueues); /* guarantee that any future tap_set_queue will fail */ tap->numvtaps = MAX_TAP_QUEUES; } EXPORT_SYMBOL_GPL(tap_del_queues); rx_handler_result_t tap_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct net_device *dev = skb->dev; struct tap_dev *tap; struct tap_queue *q; netdev_features_t features = TAP_FEATURES; enum skb_drop_reason drop_reason; tap = tap_dev_get_rcu(dev); if (!tap) return RX_HANDLER_PASS; q = tap_get_queue(tap, skb); if (!q) return RX_HANDLER_PASS; skb_push(skb, ETH_HLEN); /* Apply the forward feature mask so that we perform segmentation * according to users wishes. This only works if VNET_HDR is * enabled. */ if (q->flags & IFF_VNET_HDR) features |= tap->tap_features; if (netif_needs_gso(skb, features)) { struct sk_buff *segs = __skb_gso_segment(skb, features, false); struct sk_buff *next; if (IS_ERR(segs)) { drop_reason = SKB_DROP_REASON_SKB_GSO_SEG; goto drop; } if (!segs) { if (ptr_ring_produce(&q->ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; goto drop; } goto wake_up; } consume_skb(skb); skb_list_walk_safe(segs, skb, next) { skb_mark_not_on_list(skb); if (ptr_ring_produce(&q->ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; kfree_skb_reason(skb, drop_reason); kfree_skb_list_reason(next, drop_reason); break; } } } else { /* If we receive a partial checksum and the tap side * doesn't support checksum offload, compute the checksum. * Note: it doesn't matter which checksum feature to * check, we either support them all or none. */ if (skb->ip_summed == CHECKSUM_PARTIAL && !(features & NETIF_F_CSUM_MASK) && skb_checksum_help(skb)) { drop_reason = SKB_DROP_REASON_SKB_CSUM; goto drop; } if (ptr_ring_produce(&q->ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; goto drop; } } wake_up: wake_up_interruptible_poll(sk_sleep(&q->sk), EPOLLIN | EPOLLRDNORM | EPOLLRDBAND); return RX_HANDLER_CONSUMED; drop: /* Count errors/drops only here, thus don't care about args. */ if (tap->count_rx_dropped) tap->count_rx_dropped(tap); kfree_skb_reason(skb, drop_reason); return RX_HANDLER_CONSUMED; } EXPORT_SYMBOL_GPL(tap_handle_frame); static struct major_info *tap_get_major(int major) { struct major_info *tap_major; list_for_each_entry_rcu(tap_major, &major_list, next) { if (tap_major->major == major) return tap_major; } return NULL; } int tap_get_minor(dev_t major, struct tap_dev *tap) { int retval = -ENOMEM; struct major_info *tap_major; rcu_read_lock(); tap_major = tap_get_major(MAJOR(major)); if (!tap_major) { retval = -EINVAL; goto unlock; } spin_lock(&tap_major->minor_lock); retval = idr_alloc(&tap_major->minor_idr, tap, 1, TAP_NUM_DEVS, GFP_ATOMIC); if (retval >= 0) { tap->minor = retval; } else if (retval == -ENOSPC) { netdev_err(tap->dev, "Too many tap devices\n"); retval = -EINVAL; } spin_unlock(&tap_major->minor_lock); unlock: rcu_read_unlock(); return retval < 0 ? retval : 0; } EXPORT_SYMBOL_GPL(tap_get_minor); void tap_free_minor(dev_t major, struct tap_dev *tap) { struct major_info *tap_major; rcu_read_lock(); tap_major = tap_get_major(MAJOR(major)); if (!tap_major) { goto unlock; } spin_lock(&tap_major->minor_lock); if (tap->minor) { idr_remove(&tap_major->minor_idr, tap->minor); tap->minor = 0; } spin_unlock(&tap_major->minor_lock); unlock: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(tap_free_minor); static struct tap_dev *dev_get_by_tap_file(int major, int minor) { struct net_device *dev = NULL; struct tap_dev *tap; struct major_info *tap_major; rcu_read_lock(); tap_major = tap_get_major(major); if (!tap_major) { tap = NULL; goto unlock; } spin_lock(&tap_major->minor_lock); tap = idr_find(&tap_major->minor_idr, minor); if (tap) { dev = tap->dev; dev_hold(dev); } spin_unlock(&tap_major->minor_lock); unlock: rcu_read_unlock(); return tap; } static void tap_sock_write_space(struct sock *sk) { wait_queue_head_t *wqueue; if (!sock_writeable(sk) || !test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) wake_up_interruptible_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); } static void tap_sock_destruct(struct sock *sk) { struct tap_queue *q = container_of(sk, struct tap_queue, sk); ptr_ring_cleanup(&q->ring, __skb_array_destroy_skb); } static int tap_open(struct inode *inode, struct file *file) { struct net *net = current->nsproxy->net_ns; struct tap_dev *tap; struct tap_queue *q; int err = -ENODEV; rtnl_lock(); tap = dev_get_by_tap_file(imajor(inode), iminor(inode)); if (!tap) goto err; err = -ENOMEM; q = (struct tap_queue *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tap_proto, 0); if (!q) goto err; if (ptr_ring_init(&q->ring, tap->dev->tx_queue_len, GFP_KERNEL)) { sk_free(&q->sk); goto err; } init_waitqueue_head(&q->sock.wq.wait); q->sock.type = SOCK_RAW; q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; sock_init_data_uid(&q->sock, &q->sk, current_fsuid()); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; q->vnet_hdr_sz = sizeof(struct virtio_net_hdr); /* * so far only KVM virtio_net uses tap, enable zero copy between * guest kernel and host kernel when lower device supports zerocopy * * The macvlan supports zerocopy iff the lower device supports zero * copy so we don't have to look at the lower device directly. */ if ((tap->dev->features & NETIF_F_HIGHDMA) && (tap->dev->features & NETIF_F_SG)) sock_set_flag(&q->sk, SOCK_ZEROCOPY); err = tap_set_queue(tap, file, q); if (err) { /* tap_sock_destruct() will take care of freeing ptr_ring */ goto err_put; } /* tap groks IOCB_NOWAIT just fine, mark it as such */ file->f_mode |= FMODE_NOWAIT; dev_put(tap->dev); rtnl_unlock();