1 files changed, 81 insertions, 186 deletions

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 92da8c03d960..1207196cbbed 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -71,7 +71,7 @@
 #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>
@@ -83,6 +83,8 @@
 #include <linux/uaccess.h>
 #include <linux/proc_fs.h>
 
+#include "tun_vnet.h"
+
 static void tun_default_link_ksettings(struct net_device *dev,
 				       struct ethtool_link_ksettings *cmd);
 
@@ -94,9 +96,6 @@ static void tun_default_link_ksettings(struct net_device *dev,
  * overload it to mean fasync when stored there.
  */
 #define TUN_FASYNC	IFF_ATTACH_QUEUE
-/* High bits in flags field are unused. */
-#define TUN_VNET_LE     0x80000000
-#define TUN_VNET_BE     0x40000000
 
 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
 		      IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS)
@@ -298,70 +297,6 @@ 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)
-{
-	return tun->flags & TUN_VNET_BE ? false :
-		virtio_legacy_is_little_endian();
-}
-
-static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
-{
-	int be = !!(tun->flags & TUN_VNET_BE);
-
-	if (put_user(be, argp))
-		return -EFAULT;
-
-	return 0;
-}
-
-static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
-{
-	int be;
-
-	if (get_user(be, argp))
-		return -EFAULT;
-
-	if (be)
-		tun->flags |= TUN_VNET_BE;
-	else
-		tun->flags &= ~TUN_VNET_BE;
-
-	return 0;
-}
-#else
-static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
-{
-	return virtio_legacy_is_little_endian();
-}
-
-static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
-{
-	return -EINVAL;
-}
-
-static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
-{
-	return -EINVAL;
-}
-#endif /* CONFIG_TUN_VNET_CROSS_LE */
-
-static inline bool tun_is_little_endian(struct tun_struct *tun)
-{
-	return tun->flags & TUN_VNET_LE ||
-		tun_legacy_is_little_endian(tun);
-}
-
-static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val)
-{
-	return __virtio16_to_cpu(tun_is_little_endian(tun), val);
-}
-
-static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
-{
-	return __cpu_to_virtio16(tun_is_little_endian(tun), val);
-}
-
 static inline u32 tun_hashfn(u32 rxhash)
 {
 	return rxhash & TUN_MASK_FLOW_ENTRIES;
@@ -580,7 +515,7 @@ 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);
 }
 
@@ -990,10 +925,11 @@ static int tun_net_init(struct net_device *dev)
 	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);
@@ -1129,7 +1065,7 @@ 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);
 
@@ -1359,7 +1295,7 @@ static void tun_flow_init(struct tun_struct *tun)
 
 static void tun_flow_uninit(struct tun_struct *tun)
 {
-	del_timer_sync(&tun->flow_gc_timer);
+	timer_delete_sync(&tun->flow_gc_timer);
 	tun_flow_flush(tun);
 }
 
@@ -1480,7 +1416,7 @@ 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;
@@ -1599,7 +1535,8 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile,
 
 static struct sk_buff *__tun_build_skb(struct tun_file *tfile,
 				       struct page_frag *alloc_frag, char *buf,
-				       int buflen, int len, int pad)
+				       int buflen, int len, int pad,
+				       int metasize)
 {
 	struct sk_buff *skb = build_skb(buf, buflen);
 
@@ -1608,6 +1545,8 @@ static struct sk_buff *__tun_build_skb(struct tun_file *tfile,
 
 	skb_reserve(skb, pad);
 	skb_put(skb, len);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 	skb_set_owner_w(skb, tfile->socket.sk);
 
 	get_page(alloc_frag->page);
@@ -1661,11 +1600,13 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 				     int len, int *skb_xdp)
 {
 	struct page_frag *alloc_frag = &current->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;
 	size_t copied;
 	int pad = TUN_RX_PAD;
+	int metasize = 0;
 	int err = 0;
 
 	rcu_read_lock();
@@ -1693,20 +1634,21 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	if (hdr->gso_type || !xdp_prog) {
 		*skb_xdp = 1;
 		return __tun_build_skb(tfile, alloc_frag, buf, buflen, len,
-				       pad);
+				       pad, metasize);
 	}
 
 	*skb_xdp = 0;
 
 	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;
 		u32 act;
 
 		xdp_init_buff(&xdp, buflen, &tfile->xdp_rxq);
-		xdp_prepare_buff(&xdp, buf, pad, len, false);
+		xdp_prepare_buff(&xdp, buf, pad, len, true);
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 		if (act == XDP_REDIRECT || act == XDP_TX) {
@@ -1727,13 +1669,21 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 
 		pad = xdp.data - xdp.data_hard_start;
 		len = xdp.data_end - xdp.data;
+
+		/* It is known that the xdp_buff was prepared with metadata
+		 * support, so the metasize will never be negative.
+		 */
+		metasize = xdp.data - xdp.data_meta;
 	}
+	bpf_net_ctx_clear(bpf_net_ctx);
 	rcu_read_unlock();
 	local_bh_enable();
 
-	return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad);
+	return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad,
+			       metasize);
 
 out:
+	bpf_net_ctx_clear(bpf_net_ctx);
 	rcu_read_unlock();
 	local_bh_enable();
 	return NULL;
@@ -1751,6 +1701,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	struct virtio_net_hdr gso = { 0 };
 	int good_linear;
 	int copylen;
+	int hdr_len = 0;
 	bool zerocopy = false;
 	int err;
 	u32 rxhash = 0;
@@ -1770,26 +1721,16 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	if (tun->flags & IFF_VNET_HDR) {
 		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 
-		if (len < vnet_hdr_sz)
-			return -EINVAL;
-		len -= vnet_hdr_sz;
-
-		if (!copy_from_iter_full(&gso, sizeof(gso), from))
-			return -EFAULT;
-
-		if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		    tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2 > tun16_to_cpu(tun, gso.hdr_len))
-			gso.hdr_len = cpu_to_tun16(tun, tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2);
+		hdr_len = tun_vnet_hdr_get(vnet_hdr_sz, tun->flags, from, &gso);
+		if (hdr_len < 0)
+			return hdr_len;
 
-		if (tun16_to_cpu(tun, gso.hdr_len) > len)
-			return -EINVAL;
-		iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
+		len -= vnet_hdr_sz;
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
 		align += NET_IP_ALIGN;
-		if (unlikely(len < ETH_HLEN ||
-			     (gso.hdr_len && tun16_to_cpu(tun, gso.hdr_len) < ETH_HLEN)))
+		if (unlikely(len < ETH_HLEN || (hdr_len && hdr_len < ETH_HLEN)))
 			return -EINVAL;
 	}
 
@@ -1802,9 +1743,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		 * enough room for skb expand head in case it is used.
 		 * The rest of the buffer is mapped from userspace.
 		 */
-		copylen = gso.hdr_len ? tun16_to_cpu(tun, gso.hdr_len) : GOODCOPY_LEN;
-		if (copylen > good_linear)
-			copylen = good_linear;
+		copylen = min(hdr_len ? hdr_len : GOODCOPY_LEN, good_linear);
 		linear = copylen;
 		iov_iter_advance(&i, copylen);
 		if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS)
@@ -1825,10 +1764,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	} 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);
+			linear = min(hdr_len, good_linear);
 		}
 
 		if (frags) {
@@ -1863,7 +1799,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		}
 	}
 
-	if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) {
+	if (tun_vnet_hdr_to_skb(tun->flags, skb, &gso)) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		err = -EINVAL;
 		goto free_skb;
@@ -1906,7 +1842,7 @@ 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);
@@ -2058,18 +1994,15 @@ static ssize_t tun_put_user_xdp(struct tun_struct *tun,
 {
 	int vnet_hdr_sz = 0;
 	size_t size = xdp_frame->len;
-	size_t ret;
+	ssize_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 = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso);
+		if (ret)
+			return ret;
 	}
 
 	ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz;
@@ -2092,6 +2025,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	int vlan_offset = 0;
 	int vlan_hlen = 0;
 	int vnet_hdr_sz = 0;
+	int ret;
 
 	if (skb_vlan_tag_present(skb))
 		vlan_hlen = VLAN_HLEN;
@@ -2118,31 +2052,13 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	if (vnet_hdr_sz) {
 		struct virtio_net_hdr gso;
 
-		if (iov_iter_count(iter) < vnet_hdr_sz)
-			return -EINVAL;
-
-		if (virtio_net_hdr_from_skb(skb, &gso,
-					    tun_is_little_endian(tun), true,
-					    vlan_hlen)) {
-			struct skb_shared_info *sinfo = skb_shinfo(skb);
-
-			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;
-		}
-
-		if (copy_to_iter(&gso, sizeof(gso), iter) != sizeof(gso))
-			return -EFAULT;
+		ret = tun_vnet_hdr_from_skb(tun->flags, tun->dev, skb, &gso);
+		if (ret)
+			return ret;
 
-		iov_iter_advance(iter, vnet_hdr_sz - sizeof(gso));
+		ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso);
+		if (ret)
+			return ret;
 	}
 
 	if (vlan_hlen) {
@@ -2447,10 +2363,14 @@ static int tun_xdp_one(struct tun_struct *tun,
 	struct sk_buff_head *queue;
 	u32 rxhash = 0, act;
 	int buflen = hdr->buflen;
+	int metasize = 0;
 	int ret = 0;
 	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) {
@@ -2459,7 +2379,6 @@ static int tun_xdp_one(struct tun_struct *tun,
 		}
 
 		xdp_init_buff(xdp, buflen, &tfile->xdp_rxq);
-		xdp_set_data_meta_invalid(xdp);
 
 		act = bpf_prog_run_xdp(xdp_prog, xdp);
 		ret = tun_xdp_act(tun, xdp_prog, xdp, act);
@@ -2499,7 +2418,15 @@ build:
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
 
-	if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun))) {
+	/* The externally provided xdp_buff may have no metadata support, which
+	 * is marked by xdp->data_meta being xdp->data + 1. This will lead to a
+	 * metasize of -1 and is the reason why the condition checks for > 0.
+	 */
+	metasize = xdp->data - xdp->data_meta;
+	if (metasize > 0)
+		skb_metadata_set(skb, metasize);
+
+	if (tun_vnet_hdr_to_skb(tun->flags, skb, gso)) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		kfree_skb(skb);
 		ret = -EINVAL;
@@ -2566,6 +2493,7 @@ 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;
@@ -2574,6 +2502,7 @@ 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];
@@ -2588,6 +2517,7 @@ 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();
 
@@ -3080,8 +3010,6 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	kgid_t group;
 	int ifindex;
 	int sndbuf;
-	int vnet_hdr_sz;
-	int le;
 	int ret;
 	bool do_notify = false;
 
@@ -3265,7 +3193,13 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 
 	case SIOCSIFHWADDR:
 		/* Set hw address */
-		ret = dev_set_mac_address_user(tun->dev, &ifr.ifr_hwaddr, NULL);
+		if (tun->dev->addr_len > sizeof(ifr.ifr_hwaddr)) {
+			ret = -EINVAL;
+			break;
+		}
+		ret = dev_set_mac_address_user(tun->dev,
+					       (struct sockaddr_storage *)&ifr.ifr_hwaddr,
+					       NULL);
 		break;
 
 	case TUNGETSNDBUF:
@@ -3288,50 +3222,6 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		tun_set_sndbuf(tun);
 		break;
 
-	case TUNGETVNETHDRSZ:
-		vnet_hdr_sz = tun->vnet_hdr_sz;
-		if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz)))
-			ret = -EFAULT;
-		break;
-
-	case TUNSETVNETHDRSZ:
-		if (copy_from_user(&vnet_hdr_sz, argp, sizeof(vnet_hdr_sz))) {
-			ret = -EFAULT;
-			break;
-		}
-		if (vnet_hdr_sz < (int)sizeof(struct virtio_net_hdr)) {
-			ret = -EINVAL;
-			break;
-		}
-
-		tun->vnet_hdr_sz = vnet_hdr_sz;
-		break;
-
-	case TUNGETVNETLE:
-		le = !!(tun->flags & TUN_VNET_LE);
-		if (put_user(le, (int __user *)argp))
-			ret = -EFAULT;
-		break;
-
-	case TUNSETVNETLE:
-		if (get_user(le, (int __user *)argp)) {
-			ret = -EFAULT;
-			break;
-		}
-		if (le)
-			tun->flags |= TUN_VNET_LE;
-		else
-			tun->flags &= ~TUN_VNET_LE;
-		break;
-
-	case TUNGETVNETBE:
-		ret = tun_get_vnet_be(tun, argp);
-		break;
-
-	case TUNSETVNETBE:
-		ret = tun_set_vnet_be(tun, argp);
-		break;
-
 	case TUNATTACHFILTER:
 		/* Can be set only for TAPs */
 		ret = -EINVAL;
@@ -3387,7 +3277,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		break;
 
 	default:
-		ret = -EINVAL;
+		ret = tun_vnet_ioctl(&tun->vnet_hdr_sz, &tun->flags, cmd, argp);
 		break;
 	}
 
@@ -3441,6 +3331,12 @@ 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;
 
@@ -3526,7 +3422,6 @@ 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,
@@ -3681,9 +3576,9 @@ 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;