[v2,bpf-next,01/22] xsk: prepare 'options' in xdp_desc for multi-buffer use

Commit Message

Maciej Fijalkowski May 29, 2023, 3:50 p.m. UTC

From: Tirthendu Sarkar <[e-mail]>

Use the 'options' field in xdp_desc as a packet continuity marker. Since
'options' field was unused till now and was expected to be set to 0, the
'eop' descriptor will have it set to 0, while the non-eop descriptors
will have to set it to 1. This ensures legacy applications continue to
work without needing any change for single-buffer packets.

Add helper functions and extend xskq_prod_reserve_desc() to use the
'options' field.

Signed-off-by: Tirthendu Sarkar <[e-mail]>
---
 include/uapi/linux/if_xdp.h |  7 +++++++
 net/xdp/xsk.c               |  8 ++++----
 net/xdp/xsk_queue.h         | 12 +++++++++---
 3 files changed, 20 insertions(+), 7 deletions(-)

Patch

diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index a78a8096f4ce..434f313dc26c 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -108,4 +108,11 @@  struct xdp_desc {
 
 /* UMEM descriptor is __u64 */
 
+/* Flag indicating that the packet continues with the buffer pointed out by the
+ * next frame in the ring. The end of the packet is signalled by setting this
+ * bit to zero. For single buffer packets, every descriptor has 'options' set
+ * to 0 and this maintains backward compatibility.
+ */
+#define XDP_PKT_CONTD (1 << 0)
+
 #endif /* _LINUX_IF_XDP_H */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index cc1e7f15fa73..99f90a0d04ae 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -135,14 +135,14 @@  int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
 	return 0;
 }
 
-static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
+static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, u32 flags)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 	u64 addr;
 	int err;
 
 	addr = xp_get_handle(xskb);
-	err = xskq_prod_reserve_desc(xs->rx, addr, len);
+	err = xskq_prod_reserve_desc(xs->rx, addr, len, flags);
 	if (err) {
 		xs->rx_queue_full++;
 		return err;
@@ -189,7 +189,7 @@  static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	}
 
 	xsk_copy_xdp(xsk_xdp, xdp, len);
-	err = __xsk_rcv_zc(xs, xsk_xdp, len);
+	err = __xsk_rcv_zc(xs, xsk_xdp, len, 0);
 	if (err) {
 		xsk_buff_free(xsk_xdp);
 		return err;
@@ -259,7 +259,7 @@  static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 
 	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) {
 		len = xdp->data_end - xdp->data;
-		return __xsk_rcv_zc(xs, xdp, len);
+		return __xsk_rcv_zc(xs, xdp, len, 0);
 	}
 
 	err = __xsk_rcv(xs, xdp);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 6d40a77fccbe..ad81b19e6fdf 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -130,6 +130,11 @@  static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 	return false;
 }
 
+static inline bool xp_unused_options_set(u16 options)
+{
+	return options & ~XDP_PKT_CONTD;
+}
+
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 					    struct xdp_desc *desc)
 {
@@ -141,7 +146,7 @@  static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 	if (desc->addr >= pool->addrs_cnt)
 		return false;
 
-	if (desc->options)
+	if (xp_unused_options_set(desc->options))
 		return false;
 	return true;
 }
@@ -158,7 +163,7 @@  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;
 }
@@ -360,7 +365,7 @@  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 +377,7 @@  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;
 }