net/mlx5e: Support RX XDP metadata

Support RX hash and timestamp metadata kfuncs. We need to pass in the cqe
pointer to the mlx5e_skb_from* functions so it can be retrieved from the
XDP ctx to do this.

Cc: Tariq Toukan <tariqt@nvidia.com>
Cc: Saeed Mahameed <saeedm@nvidia.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Anatoly Burakov <anatoly.burakov@intel.com>
Cc: Alexander Lobakin <alexandr.lobakin@intel.com>
Cc: Magnus Karlsson <magnus.karlsson@gmail.com>
Cc: Maryam Tahhan <mtahhan@redhat.com>
Cc: xdp-hints@xdp-project.net
Cc: netdev@vger.kernel.org
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20230119221536.3349901-17-sdf@google.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -626,10 +626,11 @@ struct mlx5e_rq;
 typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*);
 typedef struct sk_buff *
 (*mlx5e_fp_skb_from_cqe_mpwrq)(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
-			       u16 cqe_bcnt, u32 head_offset, u32 page_idx);
+			       struct mlx5_cqe64 *cqe, u16 cqe_bcnt,
+			       u32 head_offset, u32 page_idx);
 typedef struct sk_buff *
 (*mlx5e_fp_skb_from_cqe)(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
-			 u32 cqe_bcnt);
+			 struct mlx5_cqe64 *cqe, u32 cqe_bcnt);
 typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq);
 typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
 typedef void (*mlx5e_fp_shampo_dealloc_hd)(struct mlx5e_rq*, u16, u16, bool);

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

@@ -73,6 +73,11 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
 void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
 void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq);
 
+static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
+{
+	return config->rx_filter == HWTSTAMP_FILTER_ALL;
+}
+
 /* TX */
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c

@@ -156,6 +156,34 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 	return true;
 }
 
+static int mlx5e_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
+{
+	const struct mlx5e_xdp_buff *_ctx = (void *)ctx;
+
+	if (unlikely(!mlx5e_rx_hw_stamp(_ctx->rq->tstamp)))
+		return -EOPNOTSUPP;
+
+	*timestamp =  mlx5e_cqe_ts_to_ns(_ctx->rq->ptp_cyc2time,
+					 _ctx->rq->clock, get_cqe_ts(_ctx->cqe));
+	return 0;
+}
+
+static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash)
+{
+	const struct mlx5e_xdp_buff *_ctx = (void *)ctx;
+
+	if (unlikely(!(_ctx->xdp.rxq->dev->features & NETIF_F_RXHASH)))
+		return -EOPNOTSUPP;
+
+	*hash = be32_to_cpu(_ctx->cqe->rss_hash_result);
+	return 0;
+}
+
+const struct xdp_metadata_ops mlx5e_xdp_metadata_ops = {
+	.xmo_rx_timestamp		= mlx5e_xdp_rx_timestamp,
+	.xmo_rx_hash			= mlx5e_xdp_rx_hash,
+};
+
 /* returns true if packet was consumed by xdp */
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct page *page,
 		      struct bpf_prog *prog, struct mlx5e_xdp_buff *mxbuf)

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h

@@ -46,6 +46,8 @@
 
 struct mlx5e_xdp_buff {
 	struct xdp_buff xdp;
+	struct mlx5_cqe64 *cqe;
+	struct mlx5e_rq *rq;
 };
 
 struct mlx5e_xsk_param;
@@ -60,6 +62,8 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
+extern const struct xdp_metadata_ops mlx5e_xdp_metadata_ops;
+
 INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 							  struct mlx5e_xmit_data *xdptxd,
 							  struct skb_shared_info *sinfo,

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c

@@ -52,25 +52,30 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	if (likely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_ALIGNED)) {
 		for (i = 0; i < batch; i++) {
+			struct mlx5e_xdp_buff *mxbuf = xsk_buff_to_mxbuf(wi->alloc_units[i].xsk);
 			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
 
 			umr_wqe->inline_mtts[i] = (struct mlx5_mtt) {
 				.ptag = cpu_to_be64(addr | MLX5_EN_WR),
 			};
+			mxbuf->rq = rq;
 		}
 	} else if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_UNALIGNED)) {
 		for (i = 0; i < batch; i++) {
+			struct mlx5e_xdp_buff *mxbuf = xsk_buff_to_mxbuf(wi->alloc_units[i].xsk);
 			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
 
 			umr_wqe->inline_ksms[i] = (struct mlx5_ksm) {
 				.key = rq->mkey_be,
 				.va = cpu_to_be64(addr),
 			};
+			mxbuf->rq = rq;
 		}
 	} else if (likely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_TRIPLE)) {
 		u32 mapping_size = 1 << (rq->mpwqe.page_shift - 2);
 
 		for (i = 0; i < batch; i++) {
+			struct mlx5e_xdp_buff *mxbuf = xsk_buff_to_mxbuf(wi->alloc_units[i].xsk);
 			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
 
 			umr_wqe->inline_ksms[i << 2] = (struct mlx5_ksm) {
@@ -89,6 +94,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 				.key = rq->mkey_be,
 				.va = cpu_to_be64(rq->wqe_overflow.addr),
 			};
+			mxbuf->rq = rq;
 		}
 	} else {
 		__be32 pad_size = cpu_to_be32((1 << rq->mpwqe.page_shift) -
@@ -96,6 +102,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		__be32 frame_size = cpu_to_be32(rq->xsk_pool->chunk_size);
 
 		for (i = 0; i < batch; i++) {
+			struct mlx5e_xdp_buff *mxbuf = xsk_buff_to_mxbuf(wi->alloc_units[i].xsk);
 			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
 
 			umr_wqe->inline_klms[i << 1] = (struct mlx5_klm) {
@@ -108,6 +115,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 				.va = cpu_to_be64(rq->wqe_overflow.addr),
 				.bcount = pad_size,
 			};
+			mxbuf->rq = rq;
 		}
 	}
 
@@ -238,6 +246,7 @@ static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, struct xdp_b
 
 struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 						    struct mlx5e_mpw_info *wi,
+						    struct mlx5_cqe64 *cqe,
 						    u16 cqe_bcnt,
 						    u32 head_offset,
 						    u32 page_idx)
@@ -258,6 +267,8 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	 */
 	WARN_ON_ONCE(head_offset);
 
+	/* mxbuf->rq is set on allocation, but cqe is per-packet so set it here */
+	mxbuf->cqe = cqe;
 	xsk_buff_set_size(&mxbuf->xdp, cqe_bcnt);
 	xsk_buff_dma_sync_for_cpu(&mxbuf->xdp, rq->xsk_pool);
 	net_prefetch(mxbuf->xdp.data);
@@ -292,6 +303,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 
 struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      struct mlx5e_wqe_frag_info *wi,
+					      struct mlx5_cqe64 *cqe,
 					      u32 cqe_bcnt)
 {
 	struct mlx5e_xdp_buff *mxbuf = xsk_buff_to_mxbuf(wi->au->xsk);
@@ -304,6 +316,8 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 	 */
 	WARN_ON_ONCE(wi->offset);
 
+	/* mxbuf->rq is set on allocation, but cqe is per-packet so set it here */
+	mxbuf->cqe = cqe;
 	xsk_buff_set_size(&mxbuf->xdp, cqe_bcnt);
 	xsk_buff_dma_sync_for_cpu(&mxbuf->xdp, rq->xsk_pool);
 	net_prefetch(mxbuf->xdp.data);

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h

@@ -13,11 +13,13 @@ int mlx5e_xsk_alloc_rx_wqes_batched(struct mlx5e_rq *rq, u16 ix, int wqe_bulk);
 int mlx5e_xsk_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk);
 struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 						    struct mlx5e_mpw_info *wi,
+						    struct mlx5_cqe64 *cqe,
 						    u16 cqe_bcnt,
 						    u32 head_offset,
 						    u32 page_idx);
 struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      struct mlx5e_wqe_frag_info *wi,
+					      struct mlx5_cqe64 *cqe,
 					      u32 cqe_bcnt);
 
 #endif /* __MLX5_EN_XSK_RX_H__ */

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -5053,6 +5053,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	SET_NETDEV_DEV(netdev, mdev->device);
 
 	netdev->netdev_ops = &mlx5e_netdev_ops;
+	netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops;
 
 	mlx5e_dcbnl_build_netdev(netdev);
 

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -62,10 +62,12 @@
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
-				u16 cqe_bcnt, u32 head_offset, u32 page_idx);
+				struct mlx5_cqe64 *cqe, u16 cqe_bcnt, u32 head_offset,
+				u32 page_idx);
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
-				   u16 cqe_bcnt, u32 head_offset, u32 page_idx);
+				   struct mlx5_cqe64 *cqe, u16 cqe_bcnt, u32 head_offset,
+				   u32 page_idx);
 static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
@@ -76,11 +78,6 @@ const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic = {
 	.handle_rx_cqe_mpwqe_shampo = mlx5e_handle_rx_cqe_mpwrq_shampo,
 };
 
-static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
-{
-	return config->rx_filter == HWTSTAMP_FILTER_ALL;
-}
-
 static inline void mlx5e_read_cqe_slot(struct mlx5_cqwq *wq,
 				       u32 cqcc, void *data)
 {
@@ -1575,16 +1572,19 @@ struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va,
 	return skb;
 }
 
-static void mlx5e_fill_mxbuf(struct mlx5e_rq *rq, void *va, u16 headroom,
+static void mlx5e_fill_mxbuf(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
-			     u32 len, struct mlx5e_xdp_buff *mxbuf)
+			     void *va, u16 headroom, u32 len,
+			     struct mlx5e_xdp_buff *mxbuf)
 {
 	xdp_init_buff(&mxbuf->xdp, rq->buff.frame0_sz, &rq->xdp_rxq);
 	xdp_prepare_buff(&mxbuf->xdp, va, headroom, len, true);
+	mxbuf->cqe = cqe;
+	mxbuf->rq = rq;
 }
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
-			  u32 cqe_bcnt)
+			  struct mlx5_cqe64 *cqe, u32 cqe_bcnt)
 {
 	union mlx5e_alloc_unit *au = wi->au;
 	u16 rx_headroom = rq->buff.headroom;
@@ -1609,7 +1609,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
 		struct mlx5e_xdp_buff mxbuf;
 
 		net_prefetchw(va); /* xdp_frame data area */
-		mlx5e_fill_mxbuf(rq, va, rx_headroom, cqe_bcnt, &mxbuf);
+		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, cqe_bcnt, &mxbuf);
 		if (mlx5e_xdp_handle(rq, au->page, prog, &mxbuf))
 			return NULL; /* page/packet was consumed by XDP */
 
@@ -1630,7 +1630,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
-			     u32 cqe_bcnt)
+			     struct mlx5_cqe64 *cqe, u32 cqe_bcnt)
 {
 	struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
 	struct mlx5e_wqe_frag_info *head_wi = wi;
@@ -1654,7 +1654,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	net_prefetchw(va); /* xdp_frame data area */
 	net_prefetch(va + rx_headroom);
 
-	mlx5e_fill_mxbuf(rq, va, rx_headroom, frag_consumed_bytes, &mxbuf);
+	mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, frag_consumed_bytes, &mxbuf);
 	sinfo = xdp_get_shared_info_from_buff(&mxbuf.xdp);
 	truesize = 0;
 
@@ -1777,7 +1777,7 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 			      mlx5e_skb_from_cqe_linear,
 			      mlx5e_skb_from_cqe_nonlinear,
 			      mlx5e_xsk_skb_from_cqe_linear,
-			      rq, wi, cqe_bcnt);
+			      rq, wi, cqe, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
@@ -1830,7 +1830,7 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
 			      mlx5e_skb_from_cqe_linear,
 			      mlx5e_skb_from_cqe_nonlinear,
-			      rq, wi, cqe_bcnt);
+			      rq, wi, cqe, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
@@ -1889,7 +1889,7 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64
 	skb = INDIRECT_CALL_2(rq->mpwqe.skb_from_cqe_mpwrq,
 			      mlx5e_skb_from_cqe_mpwrq_linear,
 			      mlx5e_skb_from_cqe_mpwrq_nonlinear,
-			      rq, wi, cqe_bcnt, head_offset, page_idx);
+			      rq, wi, cqe, cqe_bcnt, head_offset, page_idx);
 	if (!skb)
 		goto mpwrq_cqe_out;
 
@@ -1940,7 +1940,8 @@ mlx5e_fill_skb_data(struct sk_buff *skb, struct mlx5e_rq *rq,
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
-				   u16 cqe_bcnt, u32 head_offset, u32 page_idx)
+				   struct mlx5_cqe64 *cqe, u16 cqe_bcnt, u32 head_offset,
+				   u32 page_idx)
 {
 	union mlx5e_alloc_unit *au = &wi->alloc_units[page_idx];
 	u16 headlen = min_t(u16, MLX5E_RX_MAX_HEAD, cqe_bcnt);
@@ -1979,7 +1980,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
-				u16 cqe_bcnt, u32 head_offset, u32 page_idx)
+				struct mlx5_cqe64 *cqe, u16 cqe_bcnt, u32 head_offset,
+				u32 page_idx)
 {
 	union mlx5e_alloc_unit *au = &wi->alloc_units[page_idx];
 	u16 rx_headroom = rq->buff.headroom;
@@ -2010,7 +2012,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		struct mlx5e_xdp_buff mxbuf;
 
 		net_prefetchw(va); /* xdp_frame data area */
-		mlx5e_fill_mxbuf(rq, va, rx_headroom, cqe_bcnt, &mxbuf);
+		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, cqe_bcnt, &mxbuf);
 		if (mlx5e_xdp_handle(rq, au->page, prog, &mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
 				__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
@@ -2174,8 +2176,8 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 		if (likely(head_size))
 			*skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index);
 		else
-			*skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe_bcnt, data_offset,
+			*skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe, cqe_bcnt,
-								  page_idx);
+								  data_offset, page_idx);
 		if (unlikely(!*skb))
 			goto free_hd_entry;
 
@@ -2249,7 +2251,8 @@ static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cq
 			      mlx5e_skb_from_cqe_mpwrq_linear,
 			      mlx5e_skb_from_cqe_mpwrq_nonlinear,
 			      mlx5e_xsk_skb_from_cqe_mpwrq_linear,
-			      rq, wi, cqe_bcnt, head_offset, page_idx);
+			      rq, wi, cqe, cqe_bcnt, head_offset,
+			      page_idx);
 	if (!skb)
 		goto mpwrq_cqe_out;
 
@@ -2494,7 +2497,7 @@ static void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
 			      mlx5e_skb_from_cqe_linear,
 			      mlx5e_skb_from_cqe_nonlinear,
-			      rq, wi, cqe_bcnt);
+			      rq, wi, cqe, cqe_bcnt);
 	if (!skb)
 		goto wq_free_wqe;
 
@@ -2586,7 +2589,7 @@ static void mlx5e_trap_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe
 		goto free_wqe;
 	}
 
-	skb = mlx5e_skb_from_cqe_nonlinear(rq, wi, cqe_bcnt);
+	skb = mlx5e_skb_from_cqe_nonlinear(rq, wi, cqe, cqe_bcnt);
 	if (!skb)
 		goto free_wqe;