i40e: xsk: Move tmp desc array from driver to pool

Move desc_array from the driver to the pool. The reason behind this is
that we can then reuse this array as a temporary storage for descriptors
in all zero-copy drivers that use the batched interface. This will make
it easier to add batching to more drivers.

i40e is the only driver that has a batched Tx zero-copy
implementation, so no need to touch any other driver.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Link: https://lore.kernel.org/bpf/20220125160446.78976-6-maciej.fijalkowski@intel.com

3 files changed, 19 insertions, 13 deletions

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 28ef3f4465ae..2abd64e4d589 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -343,9 +343,9 @@ out:
 }
 EXPORT_SYMBOL(xsk_tx_peek_desc);
 
-static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, struct xdp_desc *descs,
-					u32 max_entries)
+static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, u32 max_entries)
 {
+	struct xdp_desc *descs = pool->tx_descs;
 	u32 nb_pkts = 0;
 
 	while (nb_pkts < max_entries && xsk_tx_peek_desc(pool, &descs[nb_pkts]))
@@ -355,8 +355,7 @@ static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, struct xdp_d
 	return nb_pkts;
 }
 
-u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *descs,
-				   u32 max_entries)
+u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
 {
 	struct xdp_sock *xs;
 	u32 nb_pkts;
@@ -365,7 +364,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *
 	if (!list_is_singular(&pool->xsk_tx_list)) {
 		/* Fallback to the non-batched version */
 		rcu_read_unlock();
-		return xsk_tx_peek_release_fallback(pool, descs, max_entries);
+		return xsk_tx_peek_release_fallback(pool, max_entries);
 	}
 
 	xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list);
@@ -374,7 +373,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *
 		goto out;
 	}
 
-	nb_pkts = xskq_cons_peek_desc_batch(xs->tx, descs, pool, max_entries);
+	nb_pkts = xskq_cons_peek_desc_batch(xs->tx, pool, max_entries);
 	if (!nb_pkts) {
 		xs->tx->queue_empty_descs++;
 		goto out;
@@ -386,7 +385,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *
 	 * packets. This avoids having to implement any buffering in
 	 * the Tx path.
 	 */
-	nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, descs, nb_pkts);
+	nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, pool->tx_descs, nb_pkts);
 	if (!nb_pkts)
 		goto out;
 
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index fd39bb660ebc..b34fca6ada86 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -37,6 +37,7 @@ void xp_destroy(struct xsk_buff_pool *pool)
 	if (!pool)
 		return;
 
+	kvfree(pool->tx_descs);
 	kvfree(pool->heads);
 	kvfree(pool);
 }
@@ -58,6 +59,12 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	if (!pool->heads)
 		goto out;
 
+	if (xs->tx) {
+		pool->tx_descs = kcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), GFP_KERNEL);
+		if (!pool->tx_descs)
+			goto out;
+	}
+
 	pool->chunk_mask = ~((u64)umem->chunk_size - 1);
 	pool->addrs_cnt = umem->size;
 	pool->heads_cnt = umem->chunks;
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 79be3e53ddf1..801cda5d1938 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -205,11 +205,11 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 	return false;
 }
 
-static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q,
-					    struct xdp_desc *descs,
-					    struct xsk_buff_pool *pool, u32 max)
+static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
+					    u32 max)
 {
 	u32 cached_cons = q->cached_cons, nb_entries = 0;
+	struct xdp_desc *descs = pool->tx_descs;
 
 	while (cached_cons != q->cached_prod && nb_entries < max) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
@@ -282,12 +282,12 @@ static inline bool xskq_cons_peek_desc(struct xsk_queue *q,
 	return xskq_cons_read_desc(q, desc, pool);
 }
 
-static inline u32 xskq_cons_peek_desc_batch(struct xsk_queue *q, struct xdp_desc *descs,
-					    struct xsk_buff_pool *pool, u32 max)
+static inline u32 xskq_cons_peek_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
+					    u32 max)
 {
 	u32 entries = xskq_cons_nb_entries(q, max);
 
-	return xskq_cons_read_desc_batch(q, descs, pool, entries);
+	return xskq_cons_read_desc_batch(q, pool, entries);
 }
 
 /* To improve performance in the xskq_cons_release functions, only update local state here.