xsk: introduce local_cq for each af_xdp socket

This is a prep that will be used to store the addr(s) of descriptors so
that each skb going to the end of life can publish corresponding addr(s)
in its completion queue that can be read by userspace.

Signed-off-by: Jason Xing <kernelxing@tencent.com>

Author: JasonXing

include/net/xdp_sock.h

@@ -45,6 +45,12 @@ struct xsk_map {
 	struct xdp_sock __rcu *xsk_map[];
 };
 
+struct local_cq {
+	u32 prod ____cacheline_aligned_in_smp;
+	u32 ring_mask ____cacheline_aligned_in_smp;
+	u64 desc[] ____cacheline_aligned_in_smp;
+};
+
 struct xdp_sock {
 	/* struct sock must be the first member of struct xdp_sock */
 	struct sock sk;
@@ -89,6 +95,8 @@ struct xdp_sock {
 	struct mutex mutex;
 	struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */
 	struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
+	/* Maintain addr(s) of descriptors locally */
+	struct local_cq *lcq;
 };
 
 /*

net/xdp/xsk.c

@@ -1212,6 +1212,30 @@ static void xsk_delete_from_maps(struct xdp_sock *xs)
 	}
 }
 
+/* Initialize local compeletion queue for each xsk */
+static int xsk_init_local_cq(struct xdp_sock *xs)
+{
+	struct xsk_queue *cq = xs->pool->cq;
+	size_t size;
+
+	if (!cq || !cq->nentries)
+		return -EINVAL;
+
+	size = struct_size_t(struct local_cq, desc, cq->nentries);
+	xs->lcq = vmalloc(size);
+	if (!xs->lcq)
+		return -ENOMEM;
+	xs->lcq->ring_mask = cq->nentries - 1;
+	xs->lcq->prod = 0;
+
+	return 0;
+}
+
+static void xsk_clear_local_cq(struct xdp_sock *xs)
+{
+	vfree(xs->lcq);
+}
+
 static int xsk_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
@@ -1241,6 +1265,7 @@ static int xsk_release(struct socket *sock)
 	xskq_destroy(xs->tx);
 	xskq_destroy(xs->fq_tmp);
 	xskq_destroy(xs->cq_tmp);
+	xsk_clear_local_cq(xs);
 
 	sock_orphan(sk);
 	sock->sk = NULL;
@@ -1360,9 +1385,18 @@ static int xsk_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr
 				goto out_unlock;
 			}
 
+			err = xsk_init_local_cq(xs);
+			if (err) {
+				xp_destroy(xs->pool);
+				xs->pool = NULL;
+				sockfd_put(sock);
+				goto out_unlock;
+			}
+
 			err = xp_assign_dev_shared(xs->pool, umem_xs, dev,
 						   qid);
 			if (err) {
+				xsk_clear_local_cq(xs);
 				xp_destroy(xs->pool);
 				xs->pool = NULL;
 				sockfd_put(sock);
@@ -1380,13 +1414,21 @@ static int xsk_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr
 			xp_get_pool(umem_xs->pool);
 			xs->pool = umem_xs->pool;
 
+			err = xsk_init_local_cq(xs);
+			if (err) {
+				xp_put_pool(xs->pool);
+				xs->pool = NULL;
+				sockfd_put(sock);
+				goto out_unlock;
+			}
 			/* If underlying shared umem was created without Tx
 			 * ring, allocate Tx descs array that Tx batching API
 			 * utilizes
 			 */
 			if (xs->tx && !xs->pool->tx_descs) {
 				err = xp_alloc_tx_descs(xs->pool, xs);
 				if (err) {
+					xsk_clear_local_cq(xs);
 					xp_put_pool(xs->pool);
 					xs->pool = NULL;
 					sockfd_put(sock);
@@ -1409,8 +1451,16 @@ static int xsk_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr
 			goto out_unlock;
 		}
 
+		err = xsk_init_local_cq(xs);
+		if (err) {
+			xp_destroy(xs->pool);
+			xs->pool = NULL;
+			goto out_unlock;
+		}
+
 		err = xp_assign_dev(xs->pool, dev, qid, flags);
 		if (err) {
+			xsk_clear_local_cq(xs);
 			xp_destroy(xs->pool);
 			xs->pool = NULL;
 			goto out_unlock;