xsk: Add new statistics

It can be useful for the user to know the reason behind a dropped packet.
Introduce new counters which track drops on the receive path caused by:
1. rx ring being full
2. fill ring being empty

Also, on the tx path introduce a counter which tracks the number of times
we attempt pull from the tx ring when it is empty.

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200708072835.4427-2-ciara.loftus@intel.com

include/net/xdp_sock.h

@@ -69,7 +69,11 @@ struct xdp_sock {
 	spinlock_t tx_completion_lock;
 	/* Protects generic receive. */
 	spinlock_t rx_lock;
+
+	/* Statistics */
 	u64 rx_dropped;
+	u64 rx_queue_full;
+
 	struct list_head map_list;
 	/* Protects map_list */
 	spinlock_t map_list_lock;

include/uapi/linux/if_xdp.h

@@ -73,9 +73,12 @@ struct xdp_umem_reg {
 };
 
 struct xdp_statistics {
-	__u64 rx_dropped; /* Dropped for reasons other than invalid desc */
+	__u64 rx_dropped; /* Dropped for other reasons */
 	__u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
 	__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+	__u64 rx_ring_full; /* Dropped due to rx ring being full */
+	__u64 rx_fill_ring_empty_descs; /* Failed to retrieve item from fill ring */
+	__u64 tx_ring_empty_descs; /* Failed to retrieve item from tx ring */
 };
 
 struct xdp_options {

net/xdp/xsk.c

@@ -123,7 +123,7 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	addr = xp_get_handle(xskb);
 	err = xskq_prod_reserve_desc(xs->rx, addr, len);
 	if (err) {
-		xs->rx_dropped++;
+		xs->rx_queue_full++;
 		return err;
 	}
 
@@ -274,8 +274,10 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
-		if (!xskq_cons_peek_desc(xs->tx, desc, umem))
+		if (!xskq_cons_peek_desc(xs->tx, desc, umem)) {
+			xs->tx->queue_empty_descs++;
 			continue;
+		}
 
 		/* This is the backpressure mechanism for the Tx path.
 		 * Reserve space in the completion queue and only proceed
@@ -387,6 +389,8 @@ static int xsk_generic_xmit(struct sock *sk)
 		sent_frame = true;
 	}
 
+	xs->tx->queue_empty_descs++;
+
 out:
 	if (sent_frame)
 		sk->sk_write_space(sk);
@@ -812,6 +816,12 @@ static void xsk_enter_umem_offsets(struct xdp_ring_offset_v1 *ring)
 	ring->desc = offsetof(struct xdp_umem_ring, desc);
 }
 
+struct xdp_statistics_v1 {
+	__u64 rx_dropped;
+	__u64 rx_invalid_descs;
+	__u64 tx_invalid_descs;
+};
+
 static int xsk_getsockopt(struct socket *sock, int level, int optname,
 			  char __user *optval, int __user *optlen)
 {
@@ -831,19 +841,35 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname,
 	case XDP_STATISTICS:
 	{
 		struct xdp_statistics stats;
+		bool extra_stats = true;
+		size_t stats_size;
 
-		if (len < sizeof(stats))
+		if (len < sizeof(struct xdp_statistics_v1)) {
 			return -EINVAL;
+		} else if (len < sizeof(stats)) {
+			extra_stats = false;
+			stats_size = sizeof(struct xdp_statistics_v1);
+		} else {
+			stats_size = sizeof(stats);
+		}
 
 		mutex_lock(&xs->mutex);
 		stats.rx_dropped = xs->rx_dropped;
+		if (extra_stats) {
+			stats.rx_ring_full = xs->rx_queue_full;
+			stats.rx_fill_ring_empty_descs =
+				xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;
+			stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx);
+		} else {
+			stats.rx_dropped += xs->rx_queue_full;
+		}
 		stats.rx_invalid_descs = xskq_nb_invalid_descs(xs->rx);
 		stats.tx_invalid_descs = xskq_nb_invalid_descs(xs->tx);
 		mutex_unlock(&xs->mutex);
 
-		if (copy_to_user(optval, &stats, sizeof(stats)))
+		if (copy_to_user(optval, &stats, stats_size))
 			return -EFAULT;
-		if (put_user(sizeof(stats), optlen))
+		if (put_user(stats_size, optlen))
 			return -EFAULT;
 
 		return 0;

net/xdp/xsk_buff_pool.c

@@ -235,6 +235,7 @@ static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool)
 
 	for (;;) {
 		if (!xskq_cons_peek_addr_unchecked(pool->fq, &addr)) {
+			pool->fq->queue_empty_descs++;
 			xp_release(xskb);
 			return NULL;
 		}

net/xdp/xsk_queue.h

@@ -38,6 +38,7 @@ struct xsk_queue {
 	u32 cached_cons;
 	struct xdp_ring *ring;
 	u64 invalid_descs;
+	u64 queue_empty_descs;
 };
 
 /* The structure of the shared state of the rings are the same as the
@@ -354,6 +355,11 @@ static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q)
 	return q ? q->invalid_descs : 0;
 }
 
+static inline u64 xskq_nb_queue_empty_descs(struct xsk_queue *q)
+{
+	return q ? q->queue_empty_descs : 0;
+}
+
 struct xsk_queue *xskq_create(u32 nentries, bool umem_queue);
 void xskq_destroy(struct xsk_queue *q_ops);
 

tools/include/uapi/linux/if_xdp.h

@@ -73,9 +73,12 @@ struct xdp_umem_reg {
 };
 
 struct xdp_statistics {
-	__u64 rx_dropped; /* Dropped for reasons other than invalid desc */
+	__u64 rx_dropped; /* Dropped for other reasons */
 	__u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
 	__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+	__u64 rx_ring_full; /* Dropped due to rx ring being full */
+	__u64 rx_fill_ring_empty_descs; /* Failed to retrieve item from fill ring */
+	__u64 tx_ring_empty_descs; /* Failed to retrieve item from tx ring */
 };
 
 struct xdp_options {