xsk: Add option to calculate TX checksum in SW

For XDP_COPY mode, add a UMEM option XDP_UMEM_TX_SW_CSUM
to call skb_checksum_help in transmit path. Might be useful
to debugging issues with real hardware. I also use this mode
in the selftests.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20231127190319.1190813-9-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Documentation/networking/xsk-tx-metadata.rst

@@ -50,6 +50,15 @@ packet's ``struct xdp_desc`` descriptor should set ``XDP_TX_METADATA``
 bit in the ``options`` field. Also note that in a multi-buffer packet
 only the first chunk should carry the metadata.
 
+Software TX Checksum
+====================
+
+For development and testing purposes its possible to pass
+``XDP_UMEM_TX_SW_CSUM`` flag to ``XDP_UMEM_REG`` UMEM registration call.
+In this case, when running in ``XDK_COPY`` mode, the TX checksum
+is calculated on the CPU. Do not enable this option in production because
+it will negatively affect performance.
+
 Querying Device Capabilities
 ============================
 

include/net/xsk_buff_pool.h

@@ -83,6 +83,7 @@ struct xsk_buff_pool {
 	bool uses_need_wakeup;
 	bool dma_need_sync;
 	bool unaligned;
+	bool tx_sw_csum;
 	void *addrs;
 	/* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect:
 	 * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when

include/uapi/linux/if_xdp.h

@@ -33,7 +33,13 @@
 #define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG	(1 << 0)
+
+/* Force checksum calculation in software. Can be used for testing or
+ * working around potential HW issues. This option causes performance
+ * degradation and only works in XDP_COPY mode.
+ */
+#define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;

net/xdp/xdp_umem.c

@@ -148,6 +148,11 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
 	return 0;
 }
 
+#define XDP_UMEM_FLAGS_VALID ( \
+		XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
+		XDP_UMEM_TX_SW_CSUM | \
+	0)
+
 static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 {
 	bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
@@ -167,7 +172,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 		return -EINVAL;
 	}
 
-	if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG)
+	if (mr->flags & ~XDP_UMEM_FLAGS_VALID)
 		return -EINVAL;
 
 	if (!unaligned_chunks && !is_power_of_2(chunk_size))

net/xdp/xsk.c

@@ -744,6 +744,12 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				skb->csum_start = hr + meta->request.csum_start;
 				skb->csum_offset = meta->request.csum_offset;
 				skb->ip_summed = CHECKSUM_PARTIAL;
+
+				if (unlikely(xs->pool->tx_sw_csum)) {
+					err = skb_checksum_help(skb);
+					if (err)
+						goto free_err;
+				}
 			}
 		}
 	}

net/xdp/xsk_buff_pool.c

@@ -86,6 +86,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	pool->umem = umem;
 	pool->addrs = umem->addrs;
 	pool->tx_metadata_len = umem->tx_metadata_len;
+	pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM;
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);

tools/include/uapi/linux/if_xdp.h

@@ -33,7 +33,13 @@
 #define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG	(1 << 0)
+
+/* Force checksum calculation in software. Can be used for testing or
+ * working around potential HW issues. This option causes performance
+ * degradation and only works in XDP_COPY mode.
+ */
+#define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;