[PATCH v2 net-next] xsk: Avoid starving xsk at the end of the list

[Albert Huang]

In the previous implementation, when multiple xsk sockets were
associated with a single xsk_buff_pool, a situation could arise
where the xsk_tx_list maintained data at the front for one xsk
socket while starving the xsk sockets at the back of the list.
This could result in issues such as the inability to transmit packets,
increased latency, and jitter. To address this problem, we introduced
a new variable called tx_budget_cache, which limits each xsk to transmit
a maximum of MAX_XSK_TX_BUDGET tx descriptors. This allocation ensures
equitable opportunities for subsequent xsk sockets to send tx descriptors.
The value of MAX_XSK_TX_BUDGET is temporarily set to 16.

Signed-off-by: Albert Huang <huangjie.albert@xxxxxxxxxxxxx>
---
 include/net/xdp_sock.h |  6 ++++++
 net/xdp/xsk.c          | 18 ++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 69b472604b86..f617ff54e38c 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -44,6 +44,7 @@ struct xsk_map {
 	struct xdp_sock __rcu *xsk_map[];
 };
 
+#define MAX_XSK_TX_BUDGET 16
 struct xdp_sock {
 	/* struct sock must be the first member of struct xdp_sock */
 	struct sock sk;
@@ -63,6 +64,11 @@ struct xdp_sock {
 
 	struct xsk_queue *tx ____cacheline_aligned_in_smp;
 	struct list_head tx_list;
+	/* Record the actual number of times xsk has transmitted a tx
+	 * descriptor, with a maximum limit not exceeding MAX_XSK_TX_BUDGET
+	 */
+	u32 tx_budget_cache;
+
 	/* Protects generic receive. */
 	spinlock_t rx_lock;
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index f5e96e0d6e01..087f2675333c 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -413,16 +413,25 @@ EXPORT_SYMBOL(xsk_tx_release);
 
 bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 {
+	u32 xsk_full_count = 0;
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
+again:
 	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
+		if (xs->tx_budget_cache >= MAX_XSK_TX_BUDGET) {
+			xsk_full_count++;
+			continue;
+		}
+
 		if (!xskq_cons_peek_desc(xs->tx, desc, pool)) {
 			if (xskq_has_descs(xs->tx))
 				xskq_cons_release(xs->tx);
 			continue;
 		}
 
+		xs->tx_budget_cache++;
+
 		/* This is the backpressure mechanism for the Tx path.
 		 * Reserve space in the completion queue and only proceed
 		 * if there is space in it. This avoids having to implement
@@ -436,6 +445,14 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 		return true;
 	}
 
+	if (unlikely(xsk_full_count > 0)) {
+		list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
+			xs->tx_budget_cache = 0;
+		}
+		xsk_full_count = 0;
+		goto again;
+	}
+
 out:
 	rcu_read_unlock();
 	return false;
@@ -1230,6 +1247,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	xs->zc = xs->umem->zc;
 	xs->sg = !!(xs->umem->flags & XDP_UMEM_SG_FLAG);
 	xs->queue_id = qid;
+	xs->tx_budget_cache = 0;
 	xp_add_xsk(xs->pool, xs);
 
 out_unlock:
-- 
2.20.1