1 files changed, 66 insertions, 29 deletions

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 6d40a77fccbe..13354a1e4280 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -48,6 +48,11 @@ struct xsk_queue {
 	size_t ring_vmalloc_size;
 };
 
+struct parsed_desc {
+	u32 mb;
+	u32 valid;
+};
+
 /* The structure of the shared state of the rings are a simple
  * circular buffer, as outlined in
  * Documentation/core-api/circular-buffers.rst. For the Rx and
@@ -130,18 +135,26 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 	return false;
 }
 
+static inline bool xp_unused_options_set(u32 options)
+{
+	return options & ~XDP_PKT_CONTD;
+}
+
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 					    struct xdp_desc *desc)
 {
 	u64 offset = desc->addr & (pool->chunk_size - 1);
 
+	if (!desc->len)
+		return false;
+
 	if (offset + desc->len > pool->chunk_size)
 		return false;
 
 	if (desc->addr >= pool->addrs_cnt)
 		return false;
 
-	if (desc->options)
+	if (xp_unused_options_set(desc->options))
 		return false;
 	return true;
 }
@@ -151,6 +164,9 @@ static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 {
 	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr);
 
+	if (!desc->len)
+		return false;
+
 	if (desc->len > pool->chunk_size)
 		return false;
 
@@ -158,7 +174,7 @@ static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 	    xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
 		return false;
 
-	if (desc->options)
+	if (xp_unused_options_set(desc->options))
 		return false;
 	return true;
 }
@@ -170,6 +186,11 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool,
 		xp_aligned_validate_desc(pool, desc);
 }
 
+static inline bool xskq_has_descs(struct xsk_queue *q)
+{
+	return q->cached_cons != q->cached_prod;
+}
+
 static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
 					   struct xdp_desc *d,
 					   struct xsk_buff_pool *pool)
@@ -185,17 +206,15 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 				       struct xdp_desc *desc,
 				       struct xsk_buff_pool *pool)
 {
-	while (q->cached_cons != q->cached_prod) {
+	if (q->cached_cons != q->cached_prod) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		u32 idx = q->cached_cons & q->ring_mask;
 
 		*desc = ring->desc[idx];
-		if (xskq_cons_is_valid_desc(q, desc, pool))
-			return true;
-
-		q->cached_cons++;
+		return xskq_cons_is_valid_desc(q, desc, pool);
 	}
 
+	q->queue_empty_descs++;
 	return false;
 }
 
@@ -204,30 +223,52 @@ static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
 	q->cached_cons += cnt;
 }
 
-static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
-					    u32 max)
+static inline void parse_desc(struct xsk_queue *q, struct xsk_buff_pool *pool,
+			      struct xdp_desc *desc, struct parsed_desc *parsed)
+{
+	parsed->valid = xskq_cons_is_valid_desc(q, desc, pool);
+	parsed->mb = xp_mb_desc(desc);
+}
+
+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;
+	u32 total_descs = 0, nr_frags = 0;
 
+	/* track first entry, if stumble upon *any* invalid descriptor, rewind
+	 * current packet that consists of frags and stop the processing
+	 */
 	while (cached_cons != q->cached_prod && nb_entries < max) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		u32 idx = cached_cons & q->ring_mask;
+		struct parsed_desc parsed;
 
 		descs[nb_entries] = ring->desc[idx];
-		if (unlikely(!xskq_cons_is_valid_desc(q, &descs[nb_entries], pool))) {
-			/* Skip the entry */
-			cached_cons++;
-			continue;
+		cached_cons++;
+		parse_desc(q, pool, &descs[nb_entries], &parsed);
+		if (unlikely(!parsed.valid))
+			break;
+
+		if (likely(!parsed.mb)) {
+			total_descs += (nr_frags + 1);
+			nr_frags = 0;
+		} else {
+			nr_frags++;
+			if (nr_frags == pool->netdev->xdp_zc_max_segs) {
+				nr_frags = 0;
+				break;
+			}
 		}
-
 		nb_entries++;
-		cached_cons++;
 	}
 
+	cached_cons -= nr_frags;
 	/* Release valid plus any invalid entries */
 	xskq_cons_release_n(q, cached_cons - q->cached_cons);
-	return nb_entries;
+	return total_descs;
 }
 
 /* Functions for consumers */
@@ -292,6 +333,11 @@ static inline void xskq_cons_release(struct xsk_queue *q)
 	q->cached_cons++;
 }
 
+static inline void xskq_cons_cancel_n(struct xsk_queue *q, u32 cnt)
+{
+	q->cached_cons -= cnt;
+}
+
 static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
 {
 	/* No barriers needed since data is not accessed */
@@ -319,9 +365,9 @@ static inline bool xskq_prod_is_full(struct xsk_queue *q)
 	return xskq_prod_nb_free(q, 1) ? false : true;
 }
 
-static inline void xskq_prod_cancel(struct xsk_queue *q)
+static inline void xskq_prod_cancel_n(struct xsk_queue *q, u32 cnt)
 {
-	q->cached_prod--;
+	q->cached_prod -= cnt;
 }
 
 static inline int xskq_prod_reserve(struct xsk_queue *q)
@@ -360,7 +406,7 @@ static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_de
 }
 
 static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
-					 u64 addr, u32 len)
+					 u64 addr, u32 len, u32 flags)
 {
 	struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 	u32 idx;
@@ -372,6 +418,7 @@ static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
 	idx = q->cached_prod++ & q->ring_mask;
 	ring->desc[idx].addr = addr;
 	ring->desc[idx].len = len;
+	ring->desc[idx].options = flags;
 
 	return 0;
 }
@@ -386,16 +433,6 @@ static inline void xskq_prod_submit(struct xsk_queue *q)
 	__xskq_prod_submit(q, q->cached_prod);
 }
 
-static inline void xskq_prod_submit_addr(struct xsk_queue *q, u64 addr)
-{
-	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
-	u32 idx = q->ring->producer;
-
-	ring->desc[idx++ & q->ring_mask] = addr;
-
-	__xskq_prod_submit(q, idx);
-}
-
 static inline void xskq_prod_submit_n(struct xsk_queue *q, u32 nb_entries)
 {
 	__xskq_prod_submit(q, q->ring->producer + nb_entries);