mvneta: introduce XDP multi-buffer support

index 3814fb631d52..42f439f9fcda 100644
@@ -72,7 +72,8 @@ struct xdp_buff {
 	void *data_hard_start;
 	struct xdp_rxq_info *rxq;
 	struct xdp_txq_info *txq;
-	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
+	u32 frame_sz:31; /* frame size to deduce data_hard_end/reserved tailroom*/
+	u32 mb:1; /* xdp non-linear buffer */
 };
 
 /* Reserve memory area at end-of data area.

@@ -96,7 +97,8 @@ struct xdp_frame {
 	u16 len;
 	u16 headroom;
 	u32 metasize:8;
-	u32 frame_sz:24;
+	u32 frame_sz:23;
+	u32 mb:1; /* xdp non-linear frame */
 	/* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time,
 	 * while mem info is valid on remote CPU.
 	 */

@@ -141,6 +143,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
 	xdp->data_end = frame->data + frame->len;
 	xdp->data_meta = frame->data - frame->metasize;
 	xdp->frame_sz = frame->frame_sz;
+	xdp->mb = frame->mb;
 }
 
 static inline

@@ -167,6 +170,7 @@ int xdp_update_frame_from_buff(struct xdp_buff *xdp,
 	xdp_frame->headroom = headroom - sizeof(*xdp_frame);
 	xdp_frame->metasize = metasize;
 	xdp_frame->frame_sz = xdp->frame_sz;
+	xdp_frame->mb = xdp->mb;
 
 	return 0;
 }

index 48aba933a5a8..884f140fc3be 100644
@@ -454,6 +454,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp)
 	xdpf->headroom = 0;
 	xdpf->metasize = metasize;
 	xdpf->frame_sz = PAGE_SIZE;
+	xdpf->mb = xdp->mb;
 	xdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
 
 	xsk_buff_free(xdp);

index e8131dadc22c..339319b97853 100644
@@ -1595,6 +1595,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 	res_budget = budget;
 	xdp.rxq = &rx_ring->xdp_rxq;
 	xdp.frame_sz = ENA_PAGE_SIZE;
+	xdp.mb = 0;
 
 	do {
 		xdp_verdict = XDP_PASS;

index fcc262064766..344644b6dd4d 100644
@@ -139,6 +139,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	xdp.data_end = *data_ptr + *len;
 	xdp.rxq = &rxr->xdp_rxq;
 	xdp.frame_sz = PAGE_SIZE; /* BNXT_RX_PAGE_MODE(bp) when XDP enabled */
+	xdp.mb = 0;
 	orig_data = xdp.data;
 
 	rcu_read_lock();

index 0a94c396173b..7fdabaabab1b 100644
@@ -553,6 +553,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 	xdp.data_end = xdp.data + len;
 	xdp.rxq = &rq->xdp_rxq;
 	xdp.frame_sz = RCV_FRAG_LEN + XDP_PACKET_HEADROOM;
+	xdp.mb = 0;
 	orig_data = xdp.data;
 
 	rcu_read_lock();

index fe4caf7aad7c..8410e713162e 100644
@@ -366,6 +366,7 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv,
 
 	xdp.frame_sz = DPAA2_ETH_RX_BUF_RAW_SIZE -
 		(dpaa2_fd_get_offset(fd) - XDP_PACKET_HEADROOM);
+	xdp.mb = 0;
 
 	xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
 

index d43ce13a93c9..5df07bc98283 100644
@@ -2332,6 +2332,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, 0);
 #endif
 	xdp.rxq = &rx_ring->xdp_rxq;
+	xdp.mb = 0;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		struct i40e_rx_buffer *rx_buffer;

index eae75260fe20..d641f513b8d9 100644
@@ -1089,6 +1089,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 #if (PAGE_SIZE < 8192)
 	xdp.frame_sz = ice_rx_frame_truesize(rx_ring, 0);
 #endif
+	xdp.mb = 0;
 
 	/* start the loop to process Rx packets bounded by 'budget' */
 	while (likely(total_rx_pkts < (unsigned int)budget)) {

index a190d5c616fc..39f9d2032b9d 100644
@@ -2298,6 +2298,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 #if (PAGE_SIZE < 8192)
 	xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, 0);
 #endif
+	xdp.mb = 0;
 
 	while (likely(total_rx_packets < budget)) {
 		union ixgbe_adv_rx_desc *rx_desc;

index 82fce27f682b..1fbc740c266e 100644
@@ -1129,6 +1129,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
+	xdp.mb = 0;
 
 	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
 #if (PAGE_SIZE < 8192)

index f6616c8933ca..01661ade9009 100644
@@ -3558,6 +3558,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 			xdp.data = data + MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM;
 			xdp.data_end = xdp.data + rx_bytes;
 			xdp.frame_sz = PAGE_SIZE;
+			xdp.mb = 0;
 
 			if (bm_pool->pkt_size == MVPP2_BM_SHORT_PKT_SIZE)
 				xdp.rxq = &rxq->xdp_rxq_short;

index 99d7737e8ad6..de1ae36b068e 100644
@@ -684,6 +684,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	xdp_prog = rcu_dereference(ring->xdp_prog);
 	xdp.rxq = &ring->xdp_rxq;
 	xdp.frame_sz = priv->frag_info[0].frag_stride;
+	xdp.mb = 0;
 	doorbell_pending = 0;
 
 	/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx

index 599f5b5ebc97..82c3e755dadd 100644
@@ -1133,6 +1133,7 @@ static void mlx5e_fill_xdp_buff(struct mlx5e_rq *rq, void *va, u16 headroom,
 	xdp->data_end = xdp->data + len;
 	xdp->rxq = &rq->xdp_rxq;
 	xdp->frame_sz = rq->buff.frame0_sz;
+	xdp->mb = 0;
 }
 
 static struct sk_buff *

index b150da43adb2..69fab1010752 100644
@@ -1824,6 +1824,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 	true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz;
 	xdp.frame_sz = PAGE_SIZE - NFP_NET_RX_BUF_HEADROOM;
 	xdp.rxq = &rx_ring->xdp_rxq;
+	xdp.mb = 0;
 	tx_ring = r_vec->xdp_ring;
 
 	while (pkts_polled < budget) {

index a2494bf85007..14a54094ca08 100644
@@ -1096,6 +1096,7 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 	xdp.data_end = xdp.data + *len;
 	xdp.rxq = &rxq->xdp_rxq;
 	xdp.frame_sz = rxq->rx_buf_seg_size; /* PAGE_SIZE when XDP enabled */
+	xdp.mb = 0;
 
 	/* Queues always have a full reset currently, so for the time
 	 * being until there's atomic program replace just mark read

index aaa112877561..286feb510c21 100644
@@ -301,6 +301,7 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel,
 	xdp.data_end = xdp.data + rx_buf->len;
 	xdp.rxq = &rx_queue->xdp_rxq_info;
 	xdp.frame_sz = efx->rx_page_buf_step;
+	xdp.mb = 0;
 
 	xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
 	rcu_read_unlock();

index 806eb651cea3..0f0567083a6c 100644
@@ -947,6 +947,7 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 
 	xdp.rxq = &dring->xdp_rxq;
 	xdp.frame_sz = PAGE_SIZE;
+	xdp.mb = 0;
 
 	rcu_read_lock();
 	xdp_prog = READ_ONCE(priv->xdp_prog);

index 9fd1f77190ad..558e0abb03c1 100644
@@ -407,6 +407,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 		xdp.data_hard_start = pa;
 		xdp.rxq = &priv->xdp_rxq[ch];
 		xdp.frame_sz = PAGE_SIZE;
+		xdp.mb = 0;
 
 		port = priv->emac_port + cpsw->data.dual_emac;
 		ret = cpsw_run_xdp(priv, ch, &xdp, page, port);

index f779d2e1b5c5..7baab97e302a 100644
@@ -350,6 +350,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 		xdp.data_hard_start = pa;
 		xdp.rxq = &priv->xdp_rxq[ch];
 		xdp.frame_sz = PAGE_SIZE;
+		xdp.mb = 0;
 
 		ret = cpsw_run_xdp(priv, ch, &xdp, page, priv->emac_port);
 		if (ret != CPSW_XDP_PASS)

index 440486d9c999..a4bafc64997f 100644
@@ -50,6 +50,7 @@ u32 netvsc_run_xdp(struct net_device *ndev, struct netvsc_channel *nvchan,
 	xdp->data_end = xdp->data + len;
 	xdp->rxq = &nvchan->xdp_rxq;
 	xdp->frame_sz = PAGE_SIZE;
+	xdp->mb = 0;
 
 	memcpy(xdp->data, data, len);
 

index be69d272052f..d8380feb7626 100644
@@ -1641,6 +1641,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		xdp.data_end = xdp.data + len;
 		xdp.rxq = &tfile->xdp_rxq;
 		xdp.frame_sz = buflen;
+		xdp.mb = 0;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 		if (act == XDP_REDIRECT || act == XDP_TX) {

@@ -2388,6 +2389,7 @@ static int tun_xdp_one(struct tun_struct *tun,
 		xdp_set_data_meta_invalid(xdp);
 		xdp->rxq = &tfile->xdp_rxq;
 		xdp->frame_sz = buflen;
+		xdp->mb = 0;
 
 		act = bpf_prog_run_xdp(xdp_prog, xdp);
 		err = tun_xdp_act(tun, xdp_prog, xdp, act);

index 091e5b4ba042..e25af95a532d 100644
@@ -711,6 +711,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
 	/* SKB "head" area always have tailroom for skb_shared_info */
 	xdp.frame_sz = (void *)skb_end_pointer(skb) - xdp.data_hard_start;
 	xdp.frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	xdp.mb = 0;
 
 	orig_data = xdp.data;
 	orig_data_end = xdp.data_end;

index 7145c83c6c8c..3d39d7622840 100644
@@ -690,6 +690,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		xdp.data_meta = xdp.data;
 		xdp.rxq = &rq->xdp_rxq;
 		xdp.frame_sz = buflen;
+		xdp.mb = 0;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 		stats->xdp_packets++;

@@ -860,6 +861,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		xdp.data_meta = xdp.data;
 		xdp.rxq = &rq->xdp_rxq;
 		xdp.frame_sz = frame_sz - vi->hdr_len;
+		xdp.mb = 0;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 		stats->xdp_packets++;

index 3e9895bec15f..00440ad34ca8 100644
@@ -870,6 +870,7 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata,
 	xdp->data_end = xdp->data + len;
 	xdp->rxq = &queue->xdp_rxq;
 	xdp->frame_sz = XEN_PAGE_SIZE - XDP_PACKET_HEADROOM;
+	xdp->mb = 0;
 
 	act = bpf_prog_run_xdp(prog, xdp);
 	switch (act) {

index 9d55bf5d1a65..1e78b028518d 100644
@@ -4640,6 +4640,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	/* SKB "head" area always have tailroom for skb_shared_info */
 	xdp->frame_sz  = (void *)skb_end_pointer(skb) - xdp->data_hard_start;
 	xdp->frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	xdp->mb = 0;
 
 	orig_data_end = xdp->data_end;
 	orig_data = xdp->data;

index d095718355d3..a431e8478297 100644
@@ -2027,12 +2027,17 @@ static void
 mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		    struct xdp_buff *xdp, int sync_len, bool napi)
 {
-	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	struct skb_shared_info *sinfo;
 	int i;
 
+	if (likely(!xdp->mb))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_buff(xdp);
 	for (i = 0; i < sinfo->nr_frags; i++)
 		page_pool_put_full_page(rxq->page_pool,
 					skb_frag_page(&sinfo->frags[i]), napi);
+out:
 	page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data),
 			   sync_len, napi);
 }

@@ -2234,7 +2239,6 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 	int data_len = -MVNETA_MH_SIZE, len;
 	struct net_device *dev = pp->dev;
 	enum dma_data_direction dma_dir;
-	struct skb_shared_info *sinfo;
 
 	if (*size > MVNETA_MAX_RX_BUF_SIZE) {
 		len = MVNETA_MAX_RX_BUF_SIZE;

@@ -2259,9 +2263,6 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 	xdp->data = data + pp->rx_offset_correction + MVNETA_MH_SIZE;
 	xdp->data_end = xdp->data + data_len;
 	xdp_set_data_meta_invalid(xdp);
-
-	sinfo = xdp_get_shared_info_from_buff(xdp);
-	sinfo->nr_frags = 0;
 }
 
 static void

@@ -2272,9 +2273,9 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
 			    struct page *page)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	int data_len, len, nfrags = xdp->mb ? sinfo->nr_frags : 0;
 	struct net_device *dev = pp->dev;
 	enum dma_data_direction dma_dir;
-	int data_len, len;
 
 	if (*size > MVNETA_MAX_RX_BUF_SIZE) {
 		len = MVNETA_MAX_RX_BUF_SIZE;

@@ -2288,17 +2289,21 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
 				rx_desc->buf_phys_addr,
 				len, dma_dir);
 
-	if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) {
-		skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags];
+	if (data_len > 0 && nfrags < MAX_SKB_FRAGS) {
+		skb_frag_t *frag = &sinfo->frags[nfrags];
 
 		skb_frag_off_set(frag, pp->rx_offset_correction);
 		skb_frag_size_set(frag, data_len);
 		__skb_frag_set_page(frag, page);
-		sinfo->nr_frags++;
-
-		rx_desc->buf_phys_addr = 0;
+		nfrags++;
+	} else {
+		page_pool_put_full_page(rxq->page_pool, page, true);
 	}
+
+	rx_desc->buf_phys_addr = 0;
+	sinfo->nr_frags = nfrags;
 	*size -= len;
+	xdp->mb = 1;
 }
 
 static struct sk_buff *

@@ -2306,7 +2311,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		      struct xdp_buff *xdp, u32 desc_status)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
-	int i, num_frags = sinfo->nr_frags;
+	int i, num_frags = xdp->mb ? sinfo->nr_frags : 0;
 	struct sk_buff *skb;
 
 	skb = build_skb(xdp->data_hard_start, PAGE_SIZE);

@@ -2319,6 +2324,9 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	skb_put(skb, xdp->data_end - xdp->data);
 	mvneta_rx_csum(pp, desc_status, skb);
 
+	if (likely(!xdp->mb))
+		return skb;
+
 	for (i = 0; i < num_frags; i++) {
 		skb_frag_t *frag = &sinfo->frags[i];
 

@@ -2338,13 +2346,14 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 {
 	int rx_proc = 0, rx_todo, refill, size = 0;
 	struct net_device *dev = pp->dev;
-	struct xdp_buff xdp_buf = {
-		.frame_sz = PAGE_SIZE,
-		.rxq = &rxq->xdp_rxq,
-	};
 	struct mvneta_stats ps = {};
 	struct bpf_prog *xdp_prog;
 	u32 desc_status, frame_sz;
+	struct xdp_buff xdp_buf;
+
+	xdp_buf.data_hard_start = NULL;
+	xdp_buf.frame_sz = PAGE_SIZE;
+	xdp_buf.rxq = &rxq->xdp_rxq;
 
 	/* Get number of received packets */
 	rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);

@@ -2377,6 +2386,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 			frame_sz = size - ETH_FCS_LEN;
 			desc_status = rx_status;
 
+			xdp_buf.mb = 0;
 			mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf,
 					     &size, page);
 		} else {

index 42f439f9fcda..4d47076546ff 100644
@@ -208,10 +208,24 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem);
 static inline void xdp_release_frame(struct xdp_frame *xdpf)
 {
 	struct xdp_mem_info *mem = &xdpf->mem;
+	struct skb_shared_info *sinfo;
+	int i;
 
 	/* Curr only page_pool needs this */
-	if (mem->type == MEM_TYPE_PAGE_POOL)
-		__xdp_release_frame(xdpf->data, mem);
+	if (mem->type != MEM_TYPE_PAGE_POOL)
+		return;
+
+	if (likely(!xdpf->mb))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_frame(xdpf);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_release_frame(page_address(page), mem);
+	}
+out:
+	__xdp_release_frame(xdpf->data, mem);
 }
 
 int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,

index 884f140fc3be..6d4fd4dddb00 100644
@@ -370,18 +370,57 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct)
 
 void xdp_return_frame(struct xdp_frame *xdpf)
 {
+	struct skb_shared_info *sinfo;
+	int i;
+
+	if (likely(!xdpf->mb))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_frame(xdpf);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_return(page_address(page), &xdpf->mem, false);
+	}
+out:
 	__xdp_return(xdpf->data, &xdpf->mem, false);
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame);
 
 void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
 {
+	struct skb_shared_info *sinfo;
+	int i;
+
+	if (likely(!xdpf->mb))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_frame(xdpf);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_return(page_address(page), &xdpf->mem, true);
+	}
+out:
 	__xdp_return(xdpf->data, &xdpf->mem, true);
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
 
 void xdp_return_buff(struct xdp_buff *xdp)
 {
+	struct skb_shared_info *sinfo;
+	int i;
+
+	if (likely(!xdp->mb))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_buff(xdp);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_return(page_address(page), &xdp->rxq->mem, true);
+	}
+out:
 	__xdp_return(xdp->data, &xdp->rxq->mem, true);
 }
 

index a431e8478297..f709650974ea 100644
@@ -1852,8 +1852,8 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
 			bytes_compl += buf->skb->len;
 			pkts_compl++;
 			dev_kfree_skb_any(buf->skb);
-		} else if (buf->type == MVNETA_TYPE_XDP_TX ||
-			   buf->type == MVNETA_TYPE_XDP_NDO) {
+		} else if ((buf->type == MVNETA_TYPE_XDP_TX ||
+			    buf->type == MVNETA_TYPE_XDP_NDO) && buf->xdpf) {
 			if (napi && buf->type == MVNETA_TYPE_XDP_TX)
 				xdp_return_frame_rx_napi(buf->xdpf);
 			else

@@ -2046,43 +2046,62 @@ static int
 mvneta_xdp_submit_frame(struct mvneta_port *pp, struct mvneta_tx_queue *txq,
 			struct xdp_frame *xdpf, bool dma_map)
 {
-	struct mvneta_tx_desc *tx_desc;
-	struct mvneta_tx_buf *buf;
-	dma_addr_t dma_addr;
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf);
+	int i, num_frames = xdpf->mb ? sinfo->nr_frags + 1 : 1;
+	struct mvneta_tx_desc *tx_desc = NULL;
+	struct page *page;
 
-	if (txq->count >= txq->tx_stop_threshold)
+	if (txq->count + num_frames >= txq->tx_stop_threshold)
 		return MVNETA_XDP_DROPPED;
 
-	tx_desc = mvneta_txq_next_desc_get(txq);
+	for (i = 0; i < num_frames; i++) {
+		struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index];
+		skb_frag_t *frag = i ? &sinfo->frags[i - 1] : NULL;
+		int len = frag ? skb_frag_size(frag) : xdpf->len;
+		dma_addr_t dma_addr;
 
-	buf = &txq->buf[txq->txq_put_index];
-	if (dma_map) {
-		/* ndo_xdp_xmit */
-		dma_addr = dma_map_single(pp->dev->dev.parent, xdpf->data,
-					  xdpf->len, DMA_TO_DEVICE);
-		if (dma_mapping_error(pp->dev->dev.parent, dma_addr)) {
-			mvneta_txq_desc_put(txq);
-			return MVNETA_XDP_DROPPED;
+		tx_desc = mvneta_txq_next_desc_get(txq);
+		if (dma_map) {
+			/* ndo_xdp_xmit */
+			void *data;
+
+			data = frag ? skb_frag_address(frag) : xdpf->data;
+			dma_addr = dma_map_single(pp->dev->dev.parent, data,
+						  len, DMA_TO_DEVICE);
+			if (dma_mapping_error(pp->dev->dev.parent, dma_addr)) {
+				for (; i >= 0; i--)
+					mvneta_txq_desc_put(txq);
+				return MVNETA_XDP_DROPPED;
+			}
+			buf->type = MVNETA_TYPE_XDP_NDO;
+		} else {
+			page = frag ? skb_frag_page(frag)
+				    : virt_to_page(xdpf->data);
+			dma_addr = page_pool_get_dma_addr(page);
+			if (frag)
+				dma_addr += skb_frag_off(frag);
+			else
+				dma_addr += sizeof(*xdpf) + xdpf->headroom;
+			dma_sync_single_for_device(pp->dev->dev.parent,
+						   dma_addr, len,
+						   DMA_BIDIRECTIONAL);
+			buf->type = MVNETA_TYPE_XDP_TX;
 		}
-		buf->type = MVNETA_TYPE_XDP_NDO;
-	} else {
-		struct page *page = virt_to_page(xdpf->data);
+		buf->xdpf = i ? NULL : xdpf;
 
-		dma_addr = page_pool_get_dma_addr(page) +
-			   sizeof(*xdpf) + xdpf->headroom;
-		dma_sync_single_for_device(pp->dev->dev.parent, dma_addr,
-					   xdpf->len, DMA_BIDIRECTIONAL);
-		buf->type = MVNETA_TYPE_XDP_TX;
+		if (!i)
+			tx_desc->command = MVNETA_TXD_F_DESC;
+		tx_desc->buf_phys_addr = dma_addr;
+		tx_desc->data_size = len;
+
+		mvneta_txq_inc_put(txq);
 	}
-	buf->xdpf = xdpf;
 
-	tx_desc->command = MVNETA_TXD_FLZ_DESC;
-	tx_desc->buf_phys_addr = dma_addr;
-	tx_desc->data_size = xdpf->len;
+	/*last descriptor */
+	tx_desc->command |= MVNETA_TXD_L_DESC | MVNETA_TXD_Z_PAD;
 
-	mvneta_txq_inc_put(txq);
-	txq->pending++;
-	txq->count++;
+	txq->pending += num_frames;
+	txq->count += num_frames;
 
 	return MVNETA_XDP_TX;
 }

index a22812561064..6f97dce8cccf 100644
@@ -3586,6 +3586,18 @@ union bpf_attr {
  * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_get_frag_count(struct xdp_buff *xdp_md)
+ *	Description
+ *		Get the number of fragments for a given xdp multi-buffer.
+ *	Return
+ *		The number of fragments
+ *
+ * int bpf_xdp_get_frags_total_size(struct xdp_buff *xdp_md)
+ *	Description
+ *		Get the total size of fragments for a given xdp multi-buffer.
+ *	Return
+ *		The total size of fragments for a given xdp multi-buffer.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

@@ -3737,6 +3749,8 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(xdp_get_frag_count),		\
+	FN(xdp_get_frags_total_size),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

54 lines not on this page · raw message

index a22812561064..6f97dce8cccf 100644
@@ -3586,6 +3586,18 @@ union bpf_attr {
  * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_get_frag_count(struct xdp_buff *xdp_md)
+ *	Description
+ *		Get the number of fragments for a given xdp multi-buffer.
+ *	Return
+ *		The number of fragments
+ *
+ * int bpf_xdp_get_frags_total_size(struct xdp_buff *xdp_md)
+ *	Description
+ *		Get the total size of fragments for a given xdp multi-buffer.
+ *	Return
+ *		The total size of fragments for a given xdp multi-buffer.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

@@ -3737,6 +3749,8 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(xdp_get_frag_count),		\
+	FN(xdp_get_frags_total_size),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

68 lines not on this page · raw message

182 lines not on this page · raw message

index a66f211726e7..5608d5a902ff 100644
@@ -170,11 +170,10 @@ __diag_pop();
 
 ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO);
 
-static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
-			   u32 headroom, u32 tailroom)
+static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,
+			   u32 size, u32 headroom, u32 tailroom)
 {
 	void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
-	u32 user_size = kattr->test.data_size_in;
 	void *data;
 
 	if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)

@@ -410,7 +409,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;
 
-	data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
+	data = bpf_test_init(kattr, kattr->test.data_size_in,
+			     size, NET_SKB_PAD + NET_IP_ALIGN,
 			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
 	if (IS_ERR(data))
 		return PTR_ERR(data);

@@ -547,7 +547,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	/* XDP have extra tailroom as (most) drivers use full page */
 	max_data_sz = 4096 - headroom - tailroom;
 
-	data = bpf_test_init(kattr, max_data_sz, headroom, tailroom);
+	data = bpf_test_init(kattr, kattr->test.data_size_in,
+			     max_data_sz, headroom, tailroom);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 

@@ -610,7 +611,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (size < ETH_HLEN)
 		return -EINVAL;
 
-	data = bpf_test_init(kattr, size, 0, 0);
+	data = bpf_test_init(kattr, kattr->test.data_size_in, size, 0, 0);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 

index 5608d5a902ff..7268542b0f3c 100644
@@ -532,23 +532,22 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 {
 	u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	u32 headroom = XDP_PACKET_HEADROOM;
-	u32 size = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
 	struct netdev_rx_queue *rxqueue;
+	struct skb_shared_info *sinfo;
 	struct xdp_buff xdp = {};
+	u32 max_data_sz, size;
 	u32 retval, duration;
-	u32 max_data_sz;
 	void *data;
-	int ret;
+	int i, ret;
 
 	if (kattr->test.ctx_in || kattr->test.ctx_out)
 		return -EINVAL;
 
-	/* XDP have extra tailroom as (most) drivers use full page */
 	max_data_sz = 4096 - headroom - tailroom;
+	size = min_t(u32, kattr->test.data_size_in, max_data_sz);
 
-	data = bpf_test_init(kattr, kattr->test.data_size_in,
-			     max_data_sz, headroom, tailroom);
+	data = bpf_test_init(kattr, size, max_data_sz, headroom, tailroom);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 

@@ -558,6 +557,28 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	xdp.data_end = xdp.data + size;
 	xdp.frame_sz = headroom + max_data_sz + tailroom;
 
+	sinfo = xdp_get_shared_info_from_buff(&xdp);
+	if (unlikely(kattr->test.data_size_in > size)) {
+		for (; size < kattr->test.data_size_in; size += PAGE_SIZE) {
+			skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags];
+			struct page *page;
+			int data_len;
+
+			page = alloc_page(GFP_KERNEL);
+			if (!page) {
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			__skb_frag_set_page(frag, page);
+			data_len = min_t(int, kattr->test.data_size_in - size,
+					 PAGE_SIZE);
+			skb_frag_size_set(frag, data_len);
+			sinfo->nr_frags++;
+		}
+		xdp.mb = 1;
+	}
+
 	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
 	xdp.rxq = &rxqueue->xdp_rxq;
 	bpf_prog_change_xdp(NULL, prog);

@@ -569,7 +590,10 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
 out:
 	bpf_prog_change_xdp(prog, NULL);
+	for (i = 0; i < sinfo->nr_frags; i++)
+		__free_page(skb_frag_page(&sinfo->frags[i]));
 	kfree(data);
+
 	return ret;
 }
 

new file mode 100644
index 000000000000..8cfe7253bf2a
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <unistd.h>
+#include <linux/kernel.h>
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "test_xdp_multi_buff.skel.h"
+
+static void test_xdp_mb_check_len(void)
+{
+	int test_sizes[] = { 128, 4096, 9000 };
+	struct test_xdp_multi_buff *pkt_skel;
+	char *pkt_in = NULL, *pkt_out = NULL;
+	__u32 duration = 0, retval, size;
+	int err, pkt_fd, i;
+
+	/* Load XDP program */
+	pkt_skel = test_xdp_multi_buff__open_and_load();
+	if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp_mb skeleton failed\n"))
+		goto out;
+
+	/* Allocate resources */
+	pkt_out = malloc(test_sizes[ARRAY_SIZE(test_sizes) - 1]);
+	pkt_in = malloc(test_sizes[ARRAY_SIZE(test_sizes) - 1]);
+	if (CHECK(!pkt_in || !pkt_out, "malloc",
+		  "Failed malloc, in = %p, out %p\n", pkt_in, pkt_out))
+		goto out;
+
+	pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_check_mb_len);
+	if (pkt_fd < 0)
+		goto out;
+
+	/* Run test for specific set of packets */
+	for (i = 0; i < ARRAY_SIZE(test_sizes); i++) {
+		int frag_count;
+
+		/* Run test program */
+		err = bpf_prog_test_run(pkt_fd, 1, &pkt_in, test_sizes[i],
+					pkt_out, &size, &retval, &duration);
+
+		if (CHECK(err || retval != XDP_PASS, // || size != test_sizes[i],
+			  "test_run", "err %d errno %d retval %d size %d[%d]\n",
+			  err, errno, retval, size, test_sizes[i]))
+			goto out;
+
+		/* Verify test results */
+		frag_count = DIV_ROUND_UP(
+			test_sizes[i] - pkt_skel->data->test_result_xdp_len,
+			getpagesize());
+
+		if (CHECK(pkt_skel->data->test_result_frag_count != frag_count,
+			  "result", "frag_count = %llu != %u\n",
+			  pkt_skel->data->test_result_frag_count, frag_count))
+			goto out;
+
+		if (CHECK(pkt_skel->data->test_result_frag_len != test_sizes[i] -
+			  pkt_skel->data->test_result_xdp_len,
+			  "result", "frag_len = %llu != %llu\n",
+			  pkt_skel->data->test_result_frag_len,
+			  test_sizes[i] - pkt_skel->data->test_result_xdp_len))
+			goto out;
+	}
+out:
+	if (pkt_out)
+		free(pkt_out);
+	if (pkt_in)
+		free(pkt_in);
+
+	test_xdp_multi_buff__destroy(pkt_skel);
+}
+
+void test_xdp_mb(void)
+{
+	if (test__start_subtest("xdp_mb_check_len_frags"))
+		test_xdp_mb_check_len();
+}

new file mode 100644
index 000000000000..1a46e0925282
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <bpf/bpf_helpers.h>
+#include <stdint.h>
+
+__u64 test_result_frag_len = UINT64_MAX;
+__u64 test_result_frag_count = UINT64_MAX;
+__u64 test_result_xdp_len = UINT64_MAX;
+
+SEC("xdp_check_mb_len")
+int _xdp_check_mb_len(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+
+	test_result_xdp_len = (__u64)(data_end - data);
+	test_result_frag_len = bpf_xdp_get_frags_total_size(xdp);
+	test_result_frag_count = bpf_xdp_get_frag_count(xdp);
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";

index f709650974ea..e3352ed13ea8 100644
@@ -3743,11 +3743,6 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 		mtu = ALIGN(MVNETA_RX_PKT_SIZE(mtu), 8);
 	}
 
-	if (pp->xdp_prog && mtu > MVNETA_MAX_RX_BUF_SIZE) {
-		netdev_info(dev, "Illegal MTU value %d for XDP mode\n", mtu);
-		return -EINVAL;
-	}
-
 	dev->mtu = mtu;
 
 	if (!netif_running(dev)) {

@@ -4445,11 +4440,6 @@ static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
 	struct mvneta_port *pp = netdev_priv(dev);
 	struct bpf_prog *old_prog;
 
-	if (prog && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) {
-		NL_SET_ERR_MSG_MOD(extack, "Jumbo frames not supported on XDP");
-		return -EOPNOTSUPP;
-	}
-
 	if (pp->bm_priv) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Hardware Buffer Management not supported on XDP");

index 4d47076546ff..8d9224ef75ee 100644
@@ -134,6 +134,11 @@ void xdp_warn(const char *msg, const char *func, const int line);
 #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
 
 struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
+struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
+					   struct sk_buff *skb,
+					   struct net_device *dev);
+struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
+					 struct net_device *dev);
 
 static inline
 void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)

57 lines not on this page · raw message

67 lines not on this page · raw message