Merge branch 'tun-NAPI-and-gro'

Petar Penkov says:

====================
net: Improve code coverage of syzkaller

This patch series is intended to improve code coverage of syzkaller on
the early receive path, specifically including flow dissector, GRO,
and GRO with frags parts of the networking stack. Syzkaller exercises
the stack through the TUN driver and this is therefore where changes
reside. Current coverage through netif_receive_skb() is limited as it
does not touch on any of the aforementioned code paths. Furthermore,
for full coverage, it is necessary to have more flexibility over the
linear and non-linear data of the skbs.

The following patches address this by providing the user(syzkaller)
with the ability to send via napi_gro_receive() and napi_gro_frags().
Additionally, syzkaller can specify how many fragments there are and
how much data per fragment there is. This is done by exploiting the
convenient structure of iovecs. Finally, this patch series adds
support for exercising the flow dissector during fuzzing.

The code path including napi_gro_receive() can be enabled via the
IFF_NAPI flag.  The remainder of the changes in this patch series give
the user significantly more control over packets entering the kernel.
To avoid potential security vulnerabilities, hide the ability to send
custom skbs and the flow dissector code paths behind a
capable(CAP_NET_ADMIN) check to require special user privileges.

Changes since v2 based on feedback from Willem de Bruijn and Mahesh
Bandewar:

Patch 1/ No changes.
Patch 2/ Check if the preconditions for IFF_NAPI_FRAGS (IFF_NAPI and
	 IFF_TAP) are met before opening/attaching rather than after.
	 If they are not, change the behavior from discarding the
	 flag to rejecting the command with EINVAL.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/tun.c

@@ -75,6 +75,7 @@
 #include <linux/skb_array.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
+#include <linux/mutex.h>
 
 #include <linux/uaccess.h>
 
@@ -121,7 +122,8 @@ 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
@@ -172,6 +174,8 @@ struct tun_file {
 		u16 queue_index;
 		unsigned int ifindex;
 	};
+	struct napi_struct napi;
+	struct mutex napi_mutex;	/* Protects access to the above napi */
 	struct list_head next;
 	struct tun_struct *detached;
 	struct skb_array tx_array;
@@ -229,6 +233,74 @@ struct tun_struct {
 	struct bpf_prog __rcu *xdp_prog;
 };
 
+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)
+{
+	if (napi_en) {
+		netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll,
+			       NAPI_POLL_WEIGHT);
+		napi_enable(&tfile->napi);
+		mutex_init(&tfile->napi_mutex);
+	}
+}
+
+static void tun_napi_disable(struct tun_struct *tun, struct tun_file *tfile)
+{
+	if (tun->flags & IFF_NAPI)
+		napi_disable(&tfile->napi);
+}
+
+static void tun_napi_del(struct tun_struct *tun, struct tun_file *tfile)
+{
+	if (tun->flags & IFF_NAPI)
+		netif_napi_del(&tfile->napi);
+}
+
+static bool tun_napi_frags_enabled(const struct tun_struct *tun)
+{
+	return READ_ONCE(tun->flags) & IFF_NAPI_FRAGS;
+}
+
 #ifdef CONFIG_TUN_VNET_CROSS_LE
 static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
 {
@@ -541,6 +613,11 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 
 	tun = rtnl_dereference(tfile->tun);
 
+	if (tun && clean) {
+		tun_napi_disable(tun, tfile);
+		tun_napi_del(tun, tfile);
+	}
+
 	if (tun && !tfile->detached) {
 		u16 index = tfile->queue_index;
 		BUG_ON(index >= tun->numqueues);
@@ -598,6 +675,7 @@ 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(tun, tfile);
 		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
@@ -613,6 +691,7 @@ 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(tun, tfile);
 		/* Drop read queue */
 		tun_queue_purge(tfile);
 		sock_put(&tfile->sk);
@@ -631,7 +710,8 @@ 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)
 {
 	struct tun_file *tfile = file->private_data;
 	struct net_device *dev = tun->dev;
@@ -677,10 +757,12 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
 
-	if (tfile->detached)
+	if (tfile->detached) {
 		tun_enable_queue(tfile);
-	else
+	} else {
 		sock_hold(&tfile->sk);
+		tun_napi_init(tun, tfile, napi);
+	}
 
 	tun_set_real_num_queues(tun);
 
@@ -956,13 +1038,32 @@ 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
+	 * If NAPI is not enabled, since both of those are synchronous
-	 * never to have pending data when we poll for it
+	 * operations, we are guaranteed never to have pending data when we poll
-	 * so there is nothing to do here but return.
+	 * 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
+	 * If NAPI is enabled, however, we need to schedule polling for all
+	 * queues unless we are using napi_gro_frags(), which we call in
+	 * process context and not in NAPI context.
 	 */
+	struct tun_struct *tun = netdev_priv(dev);
+
+	if (tun->flags & IFF_NAPI) {
+		struct tun_file *tfile;
+		int i;
+
+		if (tun_napi_frags_enabled(tun))
+			return;
+
+		rcu_read_lock();
+		for (i = 0; i < tun->numqueues; i++) {
+			tfile = rcu_dereference(tun->tfiles[i]);
+			napi_schedule(&tfile->napi);
+		}
+		rcu_read_unlock();
+	}
 	return;
 }
 #endif
@@ -1178,6 +1279,64 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 	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++) {
+		size_t fragsz = it->iov[i].iov_len;
+		unsigned long offset;
+		struct page *page;
+		void *data;
+
+		if (fragsz == 0 || fragsz > PAGE_SIZE) {
+			err = -EINVAL;
+			goto free;
+		}
+
+		local_bh_disable();
+		data = napi_alloc_frag(fragsz);
+		local_bh_enable();
+		if (!data) {
+			err = -ENOMEM;
+			goto free;
+		}
+
+		page = virt_to_head_page(data);
+		offset = data - page_address(page);
+		skb_fill_page_desc(skb, i - 1, page, 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,
@@ -1390,6 +1549,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	int err;
 	u32 rxhash;
 	int skb_xdp = 1;
+	bool frags = tun_napi_frags_enabled(tun);
 
 	if (!(tun->dev->flags & IFF_UP))
 		return -EIO;
@@ -1447,7 +1607,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			zerocopy = true;
 	}
 
-	if (tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) {
+	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.
@@ -1468,10 +1628,24 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 				linear = tun16_to_cpu(tun, gso.hdr_len);
 		}
 
-		skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);
+		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);
 		}
 
@@ -1483,6 +1657,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		if (err) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
 			kfree_skb(skb);
+			if (frags) {
+				tfile->napi.skb = NULL;
+				mutex_unlock(&tfile->napi_mutex);
+			}
+
 			return -EFAULT;
 		}
 	}
@@ -1490,6 +1669,11 @@ 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))) {
 		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;
 	}
 
@@ -1515,7 +1699,8 @@ 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;
 	}
 
@@ -1549,11 +1734,41 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	rxhash = __skb_get_hash_symmetric(skb);
-#ifndef CONFIG_4KSTACKS
+
-	tun_rx_batched(tun, tfile, skb, more);
+	if (frags) {
-#else
+		/* Exercise flow dissector code path. */
-	netif_rx_ni(skb);
+		u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb));
-#endif
+
+		if (headlen > skb_headlen(skb) || headlen < ETH_HLEN) {
+			this_cpu_inc(tun->pcpu_stats->rx_dropped);
+			napi_free_frags(&tfile->napi);
+			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 (tun->flags & IFF_NAPI) {
+		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);
+	}
 
 	stats = get_cpu_ptr(tun->pcpu_stats);
 	u64_stats_update_begin(&stats->syncp);
@@ -1959,6 +2174,15 @@ 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)
@@ -1980,7 +2204,8 @@ 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);
 		if (err < 0)
 			return err;
 
@@ -2066,7 +2291,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 				       NETIF_F_HW_VLAN_STAG_TX);
 
 		INIT_LIST_HEAD(&tun->disabled);
-		err = tun_attach(tun, file, false);
+		err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI);
 		if (err < 0)
 			goto err_free_flow;
 
@@ -2216,7 +2441,7 @@ 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);
 	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
 		tun = rtnl_dereference(tfile->tun);
 		if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)

include/uapi/linux/if_tun.h

@@ -60,6 +60,8 @@
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
 #define IFF_TAP		0x0002
+#define IFF_NAPI	0x0010
+#define IFF_NAPI_FRAGS	0x0020
 #define IFF_NO_PI	0x1000
 /* This flag has no real effect */
 #define IFF_ONE_QUEUE	0x2000