[PATCH net-next v6 1/3] net: tap: track dropped skb via kfree_skb_reason()

[Dongli Zhang <dongli.zhang@oracle.com>]

The TAP can be used as vhost-net backend. E.g., the tap_handle_frame() is
the interface to forward the skb from TAP to vhost-net/virtio-net.

However, there are many "goto drop" in the TAP driver. Therefore, the
kfree_skb_reason() is involved at each "goto drop" to help userspace
ftrace/ebpf to track the reason for the loss of packets.

The below 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

Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Joe Jin <joe.jin@oracle.com>
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
---
Changed since v1:
  - revise the reason name
Changed since v2:
  - declare drop_reason as type "enum skb_drop_reason"
  - handle the drop in skb_list_walk_safe() case
Changed since v4:
  - add 'computation' to SKB_CSUM comment
  - change COPY_DATA to UCOPY_FAULT
  - add 'metadata' to DEV_HDR comment
Changed since v5:
  - rebase to net-next

 drivers/net/tap.c          | 35 +++++++++++++++++++++++++----------
 include/linux/skbuff.h     | 13 +++++++++++++
 include/trace/events/skb.h |  5 +++++
 3 files changed, 43 insertions(+), 10 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index ba2ef5437e16..c3d42062559d 100644
--- a/drivers/net/tap.c
+++ b/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;
 			}
 		}
@@ -369,10 +375,14 @@ 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:
@@ -383,7 +393,7 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
 	/* 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);
@@ -706,8 +719,10 @@ 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();
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2be263184d1e..67cfff4065b6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -412,6 +412,19 @@ 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
+					 */
+	SKB_DROP_REASON_FULL_RING,	/* ring buffer is full */
 	SKB_DROP_REASON_MAX,
 };
 
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index c0769d943f8e..240e7e7591fc 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -51,6 +51,11 @@
 	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_FULL_RING, FULL_RING)		\
 	EMe(SKB_DROP_REASON_MAX, MAX)
 
 #undef EM
-- 
2.17.1