Merge branch 'tuntap-kfree_skb_reason'

Dongli Zhang says:

====================
tun/tap: use kfree_skb_reason() to trace dropped skb

The commit c504e5c2f9 ("net: skb: introduce kfree_skb_reason()") has
introduced the kfree_skb_reason() to help track the reason.

The tun and tap are commonly used as virtio-net/vhost-net backend. This is to
use kfree_skb_reason() to trace the dropped skb for those two drivers.

Changed since v1:
- I have renamed many of the reasons since v1. I make them as generic as
  possible so that they can be re-used by core networking and drivers.

Changed since v2:
- declare drop_reason as type "enum skb_drop_reason"
- handle the drop in skb_list_walk_safe() case for tap driver, and
  kfree_skb_list_reason() is introduced

Changed since v3 (only for PATCH 4/4):
- rename to TAP_FILTER and TAP_TXFILTER
- honor reverse xmas tree style declaration for 'drop_reason' in
  tun_net_xmit()

Changed since v4:
- make kfree_skb_list() static inline
- add 'computation' to SKB_CSUM comment
- change COPY_DATA to UCOPY_FAULT
- add 'metadata' to DEV_HDR comment
- expand comment on DEV_READY
- change SKB_TRIM to NOMEM
- chnage SKB_PULL to HDR_TRUNC
Changed since v5:
- rebase to net-next

The following reasons are introduced.

- SKB_DROP_REASON_SKB_CSUM
- SKB_DROP_REASON_SKB_GSO_SEG
- SKB_DROP_REASON_SKB_UCOPY_FAULT
- SKB_DROP_REASON_DEV_HDR
- SKB_DROP_REASON_FULL_RING
- SKB_DROP_REASON_DEV_READY
- SKB_DROP_REASON_NOMEM
- SKB_DROP_REASON_HDR_TRUNC
- SKB_DROP_REASON_TAP_FILTER
- SKB_DROP_REASON_TAP_TXFILTER

This is the output for TUN device.

          <idle>-0       [029] ..s1.   450.727651: kfree_skb: skbaddr=0000000023d235cc protocol=0 location=00000000a6748854 reason: NOT_SPECIFIED
          <idle>-0       [000] b.s3.   451.165671: kfree_skb: skbaddr=000000006b5de7cc protocol=4 location=000000007c2b9eae reason: FULL_RING
          <idle>-0       [000] b.s3.   453.149650: kfree_skb: skbaddr=000000006b5de7cc protocol=4 location=000000007c2b9eae reason: FULL_RING
          <idle>-0       [000] b.s3.   455.133576: kfree_skb: skbaddr=000000006b5de7cc protocol=4 location=000000007c2b9eae reason: FULL_RING
          <idle>-0       [000] b.s3.   457.117566: kfree_skb: skbaddr=000000006b5de7cc protocol=4 location=000000007c2b9eae reason: FULL_RING

This is the output for TAP device.

          arping-7053    [006] ..s1.  1000.047753: kfree_skb: skbaddr=000000008618a587 protocol=2054 location=00000000743ad4a7 reason: FULL_RING
          <idle>-0       [022] ..s1.  1000.778514: kfree_skb: skbaddr=000000002c1e706c protocol=0 location=00000000a6748854 reason: NOT_SPECIFIED
          arping-7053    [006] ..s1.  1001.047830: kfree_skb: skbaddr=000000008618a587 protocol=2054 location=00000000743ad4a7 reason: FULL_RING
          arping-7053    [006] ..s1.  1002.047918: kfree_skb: skbaddr=000000008618a587 protocol=2054 location=00000000743ad4a7 reason: FULL_RING
          arping-7053    [006] ..s1.  1003.048017: kfree_skb: skbaddr=000000008618a587 protocol=2054 location=00000000743ad4a7 reason: FULL_RING
====================

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

drivers/net/tap.c

@@ -322,6 +322,7 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
 	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)
@@ -343,12 +344,16 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
 		struct sk_buff *segs = __skb_gso_segment(skb, features, false);
 		struct sk_buff *next;
 
-		if (IS_ERR(segs))
+		if (IS_ERR(segs)) {
+			drop_reason = SKB_DROP_REASON_SKB_GSO_SEG;
 			goto drop;
+		}
 
 		if (!segs) {
-			if (ptr_ring_produce(&q->ring, skb))
+			if (ptr_ring_produce(&q->ring, skb)) {
+				drop_reason = SKB_DROP_REASON_FULL_RING;
 				goto drop;
+			}
 			goto wake_up;
 		}
 
@@ -356,8 +361,9 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
 		skb_list_walk_safe(segs, skb, next) {
 			skb_mark_not_on_list(skb);
 			if (ptr_ring_produce(&q->ring, skb)) {
-				kfree_skb(skb);
-				kfree_skb_list(next);
+				drop_reason = SKB_DROP_REASON_FULL_RING;
+				kfree_skb_reason(skb, drop_reason);
+				kfree_skb_list_reason(next, drop_reason);
 				break;
 			}
 		}
@@ -369,11 +375,15 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
 		 */
 		if (skb->ip_summed == CHECKSUM_PARTIAL &&
 		    !(features & NETIF_F_CSUM_MASK) &&
-		    skb_checksum_help(skb))
+		    skb_checksum_help(skb)) {
+			drop_reason = SKB_DROP_REASON_SKB_CSUM;
 			goto drop;
-		if (ptr_ring_produce(&q->ring, skb))
+		}
+		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);
@@ -383,7 +393,7 @@ drop:
 	/* Count errors/drops only here, thus don't care about args. */
 	if (tap->count_rx_dropped)
 		tap->count_rx_dropped(tap);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return RX_HANDLER_CONSUMED;
 }
 EXPORT_SYMBOL_GPL(tap_handle_frame);
@@ -632,6 +642,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 	int depth;
 	bool zerocopy = false;
 	size_t linear;
+	enum skb_drop_reason drop_reason;
 
 	if (q->flags & IFF_VNET_HDR) {
 		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
@@ -696,8 +707,10 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 	else
 		err = skb_copy_datagram_from_iter(skb, 0, from, len);
 
-	if (err)
+	if (err) {
+		drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT;
 		goto err_kfree;
+	}
 
 	skb_set_network_header(skb, ETH_HLEN);
 	skb_reset_mac_header(skb);
@@ -706,9 +719,11 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 	if (vnet_hdr_len) {
 		err = virtio_net_hdr_to_skb(skb, &vnet_hdr,
 					    tap_is_little_endian(q));
-		if (err)
+		if (err) {
+			drop_reason = SKB_DROP_REASON_DEV_HDR;
 			goto err_kfree;
 		}
+	}
 
 	skb_probe_transport_header(skb);
 
@@ -738,7 +753,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 	return total_len;
 
 err_kfree:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 
 err:
 	rcu_read_lock();

drivers/net/tun.c

@@ -1058,6 +1058,7 @@ static unsigned int run_ebpf_filter(struct tun_struct *tun,
 static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct tun_struct *tun = netdev_priv(dev);
+	enum skb_drop_reason drop_reason;
 	int txq = skb->queue_mapping;
 	struct netdev_queue *queue;
 	struct tun_file *tfile;
@@ -1067,8 +1068,10 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	tfile = rcu_dereference(tun->tfiles[txq]);
 
 	/* Drop packet if interface is not attached */
-	if (!tfile)
+	if (!tfile) {
+		drop_reason = SKB_DROP_REASON_DEV_READY;
 		goto drop;
+	}
 
 	if (!rcu_dereference(tun->steering_prog))
 		tun_automq_xmit(tun, skb);
@@ -1078,19 +1081,32 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Drop if the filter does not like it.
 	 * This is a noop if the filter is disabled.
 	 * Filter can be enabled only for the TAP devices. */
-	if (!check_filter(&tun->txflt, skb))
+	if (!check_filter(&tun->txflt, skb)) {
+		drop_reason = SKB_DROP_REASON_TAP_TXFILTER;
 		goto drop;
+	}
 
 	if (tfile->socket.sk->sk_filter &&
-	    sk_filter(tfile->socket.sk, skb))
+	    sk_filter(tfile->socket.sk, skb)) {
+		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
 		goto drop;
+	}
 
 	len = run_ebpf_filter(tun, skb, len);
-	if (len == 0 || pskb_trim(skb, len))
+	if (len == 0) {
+		drop_reason = SKB_DROP_REASON_TAP_FILTER;
 		goto drop;
+	}
 
-	if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
+	if (pskb_trim(skb, len)) {
+		drop_reason = SKB_DROP_REASON_NOMEM;
 		goto drop;
+	}
+
+	if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) {
+		drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT;
+		goto drop;
+	}
 
 	skb_tx_timestamp(skb);
 
@@ -1101,8 +1117,10 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	nf_reset_ct(skb);
 
-	if (ptr_ring_produce(&tfile->tx_ring, skb))
+	if (ptr_ring_produce(&tfile->tx_ring, skb)) {
+		drop_reason = SKB_DROP_REASON_FULL_RING;
 		goto drop;
+	}
 
 	/* NETIF_F_LLTX requires to do our own update of trans_start */
 	queue = netdev_get_tx_queue(dev, txq);
@@ -1119,7 +1137,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 drop:
 	atomic_long_inc(&dev->tx_dropped);
 	skb_tx_error(skb);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	rcu_read_unlock();
 	return NET_XMIT_DROP;
 }
@@ -1717,6 +1735,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	u32 rxhash = 0;
 	int skb_xdp = 1;
 	bool frags = tun_napi_frags_enabled(tfile);
+	enum skb_drop_reason drop_reason;
 
 	if (!(tun->flags & IFF_NO_PI)) {
 		if (len < sizeof(pi))
@@ -1820,9 +1839,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 		if (err) {
 			err = -EFAULT;
+			drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT;
 drop:
 			atomic_long_inc(&tun->dev->rx_dropped);
-			kfree_skb(skb);
+			kfree_skb_reason(skb, drop_reason);
 			if (frags) {
 				tfile->napi.skb = NULL;
 				mutex_unlock(&tfile->napi_mutex);
@@ -1869,6 +1889,7 @@ drop:
 	case IFF_TAP:
 		if (frags && !pskb_may_pull(skb, ETH_HLEN)) {
 			err = -ENOMEM;
+			drop_reason = SKB_DROP_REASON_HDR_TRUNC;
 			goto drop;
 		}
 		skb->protocol = eth_type_trans(skb, tun->dev);
@@ -1922,6 +1943,7 @@ drop:
 	if (unlikely(!(tun->dev->flags & IFF_UP))) {
 		err = -EIO;
 		rcu_read_unlock();
+		drop_reason = SKB_DROP_REASON_DEV_READY;
 		goto drop;
 	}
 

include/linux/skbuff.h

@@ -412,6 +412,37 @@ enum skb_drop_reason {
 					 * this means that L3 protocol is
 					 * not supported
 					 */
+	SKB_DROP_REASON_SKB_CSUM,	/* sk_buff checksum computation
+					 * error
+					 */
+	SKB_DROP_REASON_SKB_GSO_SEG,	/* gso segmentation error */
+	SKB_DROP_REASON_SKB_UCOPY_FAULT,	/* failed to copy data from
+						 * user space, e.g., via
+						 * zerocopy_sg_from_iter()
+						 * or skb_orphan_frags_rx()
+						 */
+	SKB_DROP_REASON_DEV_HDR,	/* device driver specific
+					 * header/metadata is invalid
+					 */
+	/* the device is not ready to xmit/recv due to any of its data
+	 * structure that is not up/ready/initialized, e.g., the IFF_UP is
+	 * not set, or driver specific tun->tfiles[txq] is not initialized
+	 */
+	SKB_DROP_REASON_DEV_READY,
+	SKB_DROP_REASON_FULL_RING,	/* ring buffer is full */
+	SKB_DROP_REASON_NOMEM,		/* error due to OOM */
+	SKB_DROP_REASON_HDR_TRUNC,      /* failed to trunc/extract the header
+					 * from networking data, e.g., failed
+					 * to pull the protocol header from
+					 * frags via pskb_may_pull()
+					 */
+	SKB_DROP_REASON_TAP_FILTER,     /* dropped by (ebpf) filter directly
+					 * attached to tun/tap, e.g., via
+					 * TUNSETFILTEREBPF
+					 */
+	SKB_DROP_REASON_TAP_TXFILTER,	/* dropped by tx filter implemented
+					 * at tun/tap, e.g., check_filter()
+					 */
 	SKB_DROP_REASON_MAX,
 };
 

include/trace/events/skb.h

@@ -51,6 +51,16 @@
 	EM(SKB_DROP_REASON_XDP, XDP)				\
 	EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS)		\
 	EM(SKB_DROP_REASON_PTYPE_ABSENT, PTYPE_ABSENT)		\
+	EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM)			\
+	EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG)		\
+	EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT)	\
+	EM(SKB_DROP_REASON_DEV_HDR, DEV_HDR)			\
+	EM(SKB_DROP_REASON_DEV_READY, DEV_READY)		\
+	EM(SKB_DROP_REASON_FULL_RING, FULL_RING)		\
+	EM(SKB_DROP_REASON_NOMEM, NOMEM)			\
+	EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC)		\
+	EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER)		\
+	EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER)		\
 	EMe(SKB_DROP_REASON_MAX, MAX)
 
 #undef EM