diff options
Diffstat (limited to 'drivers/net/tun.c')
-rw-r--r-- | drivers/net/tun.c | 88 |
1 files changed, 54 insertions, 34 deletions
diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8f95a562b8d0..acf96f262488 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -54,6 +54,7 @@ #include <linux/if_tun.h> #include <linux/if_vlan.h> #include <linux/crc32.h> +#include <linux/math.h> #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> @@ -70,13 +71,14 @@ #include <linux/bpf_trace.h> #include <linux/mutex.h> #include <linux/ieee802154.h> -#include <linux/if_ltalk.h> +#include <uapi/linux/if_ltalk.h> #include <uapi/linux/if_fddi.h> #include <uapi/linux/if_hippi.h> #include <uapi/linux/if_fc.h> #include <net/ax25.h> #include <net/rose.h> #include <net/6lowpan.h> +#include <net/rps.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> @@ -523,8 +525,7 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_flow_entry *e; - u32 txq = 0; - u32 numqueues = 0; + u32 txq, numqueues; numqueues = READ_ONCE(tun->numqueues); @@ -534,8 +535,7 @@ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb) tun_flow_save_rps_rxhash(e, txq); txq = e->queue_index; } else { - /* use multiply and shift instead of expensive divide */ - txq = ((u64)txq * numqueues) >> 32; + txq = reciprocal_scale(txq, numqueues); } return txq; @@ -580,7 +580,7 @@ static inline bool tun_not_capable(struct tun_struct *tun) struct net *net = dev_net(tun->dev); return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || - (gid_valid(tun->group) && !in_egroup_p(tun->group))) && + (gid_valid(tun->group) && !in_egroup_p(tun->group))) && !ns_capable(net->user_ns, CAP_NET_ADMIN); } @@ -978,27 +978,23 @@ static int tun_net_init(struct net_device *dev) struct ifreq *ifr = tun->ifr; int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - spin_lock_init(&tun->lock); err = security_tun_dev_alloc_security(&tun->security); - if (err < 0) { - free_percpu(dev->tstats); + if (err < 0) return err; - } tun_flow_init(tun); + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - dev->features = dev->hw_features | NETIF_F_LLTX; + dev->features = dev->hw_features; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); + dev->lltx = true; tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); @@ -1009,7 +1005,6 @@ static int tun_net_init(struct net_device *dev) if (err < 0) { tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); - free_percpu(dev->tstats); return err; } return 0; @@ -1135,7 +1130,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) goto drop; } - /* NETIF_F_LLTX requires to do our own update of trans_start */ + /* dev->lltx requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); txq_trans_cond_update(queue); @@ -1345,7 +1340,6 @@ static const struct net_device_ops tap_netdev_ops = { .ndo_select_queue = tun_select_queue, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, - .ndo_get_stats64 = dev_get_tstats64, .ndo_bpf = tun_xdp, .ndo_xdp_xmit = tun_xdp_xmit, .ndo_change_carrier = tun_net_change_carrier, @@ -1487,7 +1481,7 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { - const struct iovec *iov = iter_iov(it); + const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; @@ -1668,6 +1662,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, int len, int *skb_xdp) { struct page_frag *alloc_frag = ¤t->task_frag; + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct bpf_prog *xdp_prog; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); char *buf; @@ -1707,6 +1702,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, local_bh_disable(); rcu_read_lock(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { struct xdp_buff xdp; @@ -1735,12 +1731,14 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, pad = xdp.data - xdp.data_hard_start; len = xdp.data_end - xdp.data; } + bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad); out: + bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return NULL; @@ -1913,7 +1911,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_zcopy_init(skb, msg_control); } else if (msg_control) { struct ubuf_info *uarg = msg_control; - uarg->callback(NULL, uarg, false); + uarg->ops->complete(NULL, uarg, false); } skb_reset_network_header(skb); @@ -1928,7 +1926,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { - ret = do_xdp_generic(xdp_prog, skb); + ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { rcu_read_unlock(); local_bh_enable(); @@ -2132,14 +2130,16 @@ static ssize_t tun_put_user(struct tun_struct *tun, 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", - sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), - tun16_to_cpu(tun, gso.hdr_len)); - print_hex_dump(KERN_ERR, "tun: ", - DUMP_PREFIX_NONE, - 16, 1, skb->head, - min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + + if (net_ratelimit()) { + netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), + tun16_to_cpu(tun, gso.hdr_len)); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + } WARN_ON_ONCE(1); return -EINVAL; } @@ -2318,7 +2318,6 @@ static void tun_free_netdev(struct net_device *dev) BUG_ON(!(list_empty(&tun->disabled))); - free_percpu(dev->tstats); tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); __tun_set_ebpf(tun, &tun->steering_prog, NULL); @@ -2457,6 +2456,9 @@ static int tun_xdp_one(struct tun_struct *tun, bool skb_xdp = false; struct page *page; + if (unlikely(datasize < ETH_HLEN)) + return -EINVAL; + xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { if (gso->gso_type) { @@ -2518,7 +2520,7 @@ build: skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { - ret = do_xdp_generic(xdp_prog, skb); + ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { ret = 0; goto out; @@ -2572,6 +2574,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) if (m->msg_controllen == sizeof(struct tun_msg_ctl) && ctl && ctl->type == TUN_MSG_PTR) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct tun_page tpage; int n = ctl->num; int flush = 0, queued = 0; @@ -2580,6 +2583,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) local_bh_disable(); rcu_read_lock(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); for (i = 0; i < n; i++) { xdp = &((struct xdp_buff *)ctl->ptr)[i]; @@ -2594,6 +2598,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) if (tfile->napi_enabled && queued > 0) napi_schedule(&tfile->napi); + bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); @@ -3447,6 +3452,12 @@ static int tun_chr_fasync(int fd, struct file *file, int on) struct tun_file *tfile = file->private_data; int ret; + if (on) { + ret = file_f_owner_allocate(file); + if (ret) + goto out; + } + if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0) goto out; @@ -3532,7 +3543,6 @@ static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file) static const struct file_operations tun_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read_iter = tun_chr_read_iter, .write_iter = tun_chr_write_iter, .poll = tun_chr_poll, @@ -3645,12 +3655,22 @@ static int tun_set_coalesce(struct net_device *dev, return 0; } +static void tun_get_channels(struct net_device *dev, + struct ethtool_channels *channels) +{ + struct tun_struct *tun = netdev_priv(dev); + + channels->combined_count = tun->numqueues; + channels->max_combined = tun->flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; +} + static const struct ethtool_ops tun_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES, .get_drvinfo = tun_get_drvinfo, .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, .get_link = ethtool_op_get_link, + .get_channels = tun_get_channels, .get_ts_info = ethtool_op_get_ts_info, .get_coalesce = tun_get_coalesce, .set_coalesce = tun_set_coalesce, @@ -3677,9 +3697,9 @@ static int tun_queue_resize(struct tun_struct *tun) list_for_each_entry(tfile, &tun->disabled, next) rings[i++] = &tfile->tx_ring; - ret = ptr_ring_resize_multiple(rings, n, - dev->tx_queue_len, GFP_KERNEL, - tun_ptr_free); + ret = ptr_ring_resize_multiple_bh(rings, n, + dev->tx_queue_len, GFP_KERNEL, + tun_ptr_free); kfree(rings); return ret; |