mvneta: introduce XDP multi-buffer support

index 686a666d073d..2eecb6931975 100644
@@ -535,6 +535,7 @@ struct skb_shared_info {
 	 * Warning : all fields before dataref are cleared in __alloc_skb()
 	 */
 	atomic_t	dataref;
+	unsigned int	xdp_frags_size;
 
 	/* Intermediate layers must ensure that destructor_arg
 	 * remains valid until skb destructor */

index 447f9b1578f3..4ec7bdf0d937 100644
@@ -66,6 +66,10 @@ struct xdp_txq_info {
 	struct net_device *dev;
 };
 
+enum xdp_buff_flags {
+	XDP_FLAGS_MULTI_BUFF	= BIT(0), /* non-linear xdp buff */
+};
+
 struct xdp_buff {
 	void *data;
 	void *data_end;

@@ -74,13 +78,30 @@ struct xdp_buff {
 	struct xdp_rxq_info *rxq;
 	struct xdp_txq_info *txq;
 	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
+	u32 flags; /* supported values defined in xdp_buff_flags */
 };
 
+static __always_inline bool xdp_buff_is_mb(struct xdp_buff *xdp)
+{
+	return !!(xdp->flags & XDP_FLAGS_MULTI_BUFF);
+}
+
+static __always_inline void xdp_buff_set_mb(struct xdp_buff *xdp)
+{
+	xdp->flags |= XDP_FLAGS_MULTI_BUFF;
+}
+
+static __always_inline void xdp_buff_clear_mb(struct xdp_buff *xdp)
+{
+	xdp->flags &= ~XDP_FLAGS_MULTI_BUFF;
+}
+
 static __always_inline void
 xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq)
 {
 	xdp->frame_sz = frame_sz;
 	xdp->rxq = rxq;
+	xdp->flags = 0;
 }
 
 static __always_inline void

@@ -122,8 +143,14 @@ struct xdp_frame {
 	 */
 	struct xdp_mem_info mem;
 	struct net_device *dev_rx; /* used by cpumap */
+	u32 flags; /* supported values defined in xdp_buff_flags */
 };
 
+static __always_inline bool xdp_frame_is_mb(struct xdp_frame *frame)
+{
+	return !!(frame->flags & XDP_FLAGS_MULTI_BUFF);
+}
+
 #define XDP_BULK_QUEUE_SIZE	16
 struct xdp_frame_bulk {
 	int count;

@@ -180,6 +207,7 @@ 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->flags = frame->flags;
 }
 
 static inline

@@ -206,6 +234,7 @@ 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->flags = xdp->flags;
 
 	return 0;
 }

index 67a644177880..208dc9116147 100644
@@ -2037,9 +2037,14 @@ mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 {
 	int i;
 
+	if (likely(!xdp_buff_is_mb(xdp)))
+		goto out;
+
 	for (i = 0; i < sinfo->nr_frags; i++)
 		page_pool_put_full_page(rxq->page_pool,
 					skb_frag_page(&sinfo->frags[i]), true);
+
+out:
 	page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data),
 			   sync_len, true);
 }

@@ -2241,7 +2246,6 @@ 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;

@@ -2261,11 +2265,9 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 
 	/* Prefetch header */
 	prefetch(data);
+	xdp_buff_clear_mb(xdp);
 	xdp_prepare_buff(xdp, data, pp->rx_offset_correction + MVNETA_MH_SIZE,
 			 data_len, false);
-
-	sinfo = xdp_get_shared_info_from_buff(xdp);
-	sinfo->nr_frags = 0;
 }
 
 static void

@@ -2299,6 +2301,9 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
 		skb_frag_off_set(frag, pp->rx_offset_correction);
 		skb_frag_size_set(frag, data_len);
 		__skb_frag_set_page(frag, page);
+
+		if (!xdp_buff_is_mb(xdp))
+			xdp_buff_set_mb(xdp);
 	} else {
 		page_pool_put_full_page(rxq->page_pool, page, true);
 	}

@@ -2320,8 +2325,12 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 		      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;
 	struct sk_buff *skb;
+	u8 num_frags;
+	int i;
+
+	if (unlikely(xdp_buff_is_mb(xdp)))
+		num_frags = sinfo->nr_frags;
 
 	skb = build_skb(xdp->data_hard_start, PAGE_SIZE);
 	if (!skb)

@@ -2333,6 +2342,9 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 	skb_put(skb, xdp->data_end - xdp->data);
 	skb->ip_summed = mvneta_rx_csum(pp, desc_status);
 
+	if (likely(!xdp_buff_is_mb(xdp)))
+		goto out;
+
 	for (i = 0; i < num_frags; i++) {
 		skb_frag_t *frag = &sinfo->frags[i];
 

@@ -2341,6 +2353,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 				skb_frag_size(frag), PAGE_SIZE);
 	}
 
+out:
 	return skb;
 }
 

index 208dc9116147..567358a021a9 100644
@@ -2032,9 +2032,9 @@ int mvneta_rx_refill_queue(struct mvneta_port *pp, struct mvneta_rx_queue *rxq)
 
 static void
 mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
-		    struct xdp_buff *xdp, struct skb_shared_info *sinfo,
-		    int sync_len)
+		    struct xdp_buff *xdp, int sync_len)
 {
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 	int i;
 
 	if (likely(!xdp_buff_is_mb(xdp)))

@@ -2182,7 +2182,6 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	       struct bpf_prog *prog, struct xdp_buff *xdp,
 	       u32 frame_sz, struct mvneta_stats *stats)
 {
-	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 	unsigned int len, data_len, sync;
 	u32 ret, act;
 

@@ -2203,7 +2202,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 
 		err = xdp_do_redirect(pp->dev, xdp, prog);
 		if (unlikely(err)) {
-			mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
+			mvneta_xdp_put_buff(pp, rxq, xdp, sync);
 			ret = MVNETA_XDP_DROPPED;
 		} else {
 			ret = MVNETA_XDP_REDIR;

@@ -2214,7 +2213,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	case XDP_TX:
 		ret = mvneta_xdp_xmit_back(pp, xdp);
 		if (ret != MVNETA_XDP_TX)
-			mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
+			mvneta_xdp_put_buff(pp, rxq, xdp, sync);
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);

@@ -2223,7 +2222,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		trace_xdp_exception(pp->dev, prog, act);
 		fallthrough;
 	case XDP_DROP:
-		mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
+		mvneta_xdp_put_buff(pp, rxq, xdp, sync);
 		ret = MVNETA_XDP_DROPPED;
 		stats->xdp_drop++;
 		break;

@@ -2275,9 +2274,9 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
 			    struct mvneta_rx_desc *rx_desc,
 			    struct mvneta_rx_queue *rxq,
 			    struct xdp_buff *xdp, int *size,
-			    struct skb_shared_info *xdp_sinfo,
 			    struct page *page)
 {
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 	struct net_device *dev = pp->dev;
 	enum dma_data_direction dma_dir;
 	int data_len, len;

@@ -2295,8 +2294,11 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
 				len, dma_dir);
 	rx_desc->buf_phys_addr = 0;
 
-	if (data_len > 0 && xdp_sinfo->nr_frags < MAX_SKB_FRAGS) {
-		skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags++];
+	if (!xdp_buff_is_mb(xdp))
+		sinfo->nr_frags = 0;
+
+	if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) {
+		skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags++];
 
 		skb_frag_off_set(frag, pp->rx_offset_correction);
 		skb_frag_size_set(frag, data_len);

@@ -2307,16 +2309,6 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
 	} else {
 		page_pool_put_full_page(rxq->page_pool, page, true);
 	}
-
-	/* last fragment */
-	if (len == *size) {
-		struct skb_shared_info *sinfo;
-
-		sinfo = xdp_get_shared_info_from_buff(xdp);
-		sinfo->nr_frags = xdp_sinfo->nr_frags;
-		memcpy(sinfo->frags, xdp_sinfo->frags,
-		       sinfo->nr_frags * sizeof(skb_frag_t));
-	}
 	*size -= len;
 }
 

@@ -2364,7 +2356,6 @@ 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 skb_shared_info sinfo;
 	struct mvneta_stats ps = {};
 	struct bpf_prog *xdp_prog;
 	u32 desc_status, frame_sz;

@@ -2373,8 +2364,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 	xdp_init_buff(&xdp_buf, PAGE_SIZE, &rxq->xdp_rxq);
 	xdp_buf.data_hard_start = NULL;
 
-	sinfo.nr_frags = 0;
-
 	/* Get number of received packets */
 	rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);
 

@@ -2416,7 +2405,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 			}
 
 			mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf,
-						    &size, &sinfo, page);
+						    &size, page);
 		} /* Middle or Last descriptor */
 
 		if (!(rx_status & MVNETA_RXD_LAST_DESC))

@@ -2424,7 +2413,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 			continue;
 
 		if (size) {
-			mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
+			mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1);
 			goto next;
 		}
 

@@ -2436,7 +2425,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 		if (IS_ERR(skb)) {
 			struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 
-			mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
+			mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1);
 
 			u64_stats_update_begin(&stats->syncp);
 			stats->es.skb_alloc_error++;

@@ -2453,11 +2442,10 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 		napi_gro_receive(napi, skb);
 next:
 		xdp_buf.data_hard_start = NULL;
-		sinfo.nr_frags = 0;
 	}
 
 	if (xdp_buf.data_hard_start)
-		mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
+		mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1);
 
 	if (ps.xdp_redirect)
 		xdp_do_flush_map();

index 4ec7bdf0d937..e594016eb193 100644
@@ -67,7 +67,10 @@ struct xdp_txq_info {
 };
 
 enum xdp_buff_flags {
-	XDP_FLAGS_MULTI_BUFF	= BIT(0), /* non-linear xdp buff */
+	XDP_FLAGS_MULTI_BUFF		= BIT(0), /* non-linear xdp buff */
+	XDP_FLAGS_FRAGS_PF_MEMALLOC	= BIT(1), /* xdp multi-buff paged memory
+						   * is under pressure
+						   */
 };
 
 struct xdp_buff {

@@ -96,6 +99,16 @@ static __always_inline void xdp_buff_clear_mb(struct xdp_buff *xdp)
 	xdp->flags &= ~XDP_FLAGS_MULTI_BUFF;
 }
 
+static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp)
+{
+	return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
+}
+
+static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp)
+{
+	xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC;
+}
+
 static __always_inline void
 xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq)
 {

@@ -151,6 +164,11 @@ static __always_inline bool xdp_frame_is_mb(struct xdp_frame *frame)
 	return !!(frame->flags & XDP_FLAGS_MULTI_BUFF);
 }
 
+static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame)
+{
+	return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
+}
+
 #define XDP_BULK_QUEUE_SIZE	16
 struct xdp_frame_bulk {
 	int count;

@@ -186,6 +204,19 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame)
 	frame->dev_rx = NULL;
 }
 
+static inline void
+xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags,
+			   unsigned int size, unsigned int truesize,
+			   bool pfmemalloc)
+{
+	skb_shinfo(skb)->nr_frags = nr_frags;
+
+	skb->len += size;
+	skb->data_len += size;
+	skb->truesize += truesize;
+	skb->pfmemalloc |= pfmemalloc;
+}
+
 /* Avoids inlining WARN macro in fast-path */
 void xdp_warn(const char *msg, const char *func, const int line);
 #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)

index 5ddc29f29bad..89183b2e3c07 100644
@@ -529,8 +529,14 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct sk_buff *skb,
 					   struct net_device *dev)
 {
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf);
 	unsigned int headroom, frame_size;
 	void *hard_start;
+	u8 nr_frags;
+
+	/* xdp multi-buff frame */
+	if (unlikely(xdp_frame_is_mb(xdpf)))
+		nr_frags = sinfo->nr_frags;
 
 	/* Part of headroom was reserved to xdpf */
 	headroom = sizeof(*xdpf) + xdpf->headroom;

@@ -550,6 +556,12 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 	if (xdpf->metasize)
 		skb_metadata_set(skb, xdpf->metasize);
 
+	if (unlikely(xdp_frame_is_mb(xdpf)))
+		xdp_update_skb_shared_info(skb, nr_frags,
+					   sinfo->xdp_frags_size,
+					   nr_frags * xdpf->frame_sz,
+					   xdp_frame_is_frag_pfmemalloc(xdpf));
+
 	/* Essential SKB info: protocol and skb->dev */
 	skb->protocol = eth_type_trans(skb, dev);
 

index 567358a021a9..e6977815b805 100644
@@ -2304,8 +2304,12 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
 		skb_frag_size_set(frag, data_len);
 		__skb_frag_set_page(frag, page);
 
-		if (!xdp_buff_is_mb(xdp))
+		if (!xdp_buff_is_mb(xdp)) {
+			sinfo->xdp_frags_size = *size;
 			xdp_buff_set_mb(xdp);
+		}
+		if (page_is_pfmemalloc(page))
+			xdp_buff_set_frag_pfmemalloc(xdp);
 	} else {
 		page_pool_put_full_page(rxq->page_pool, page, true);
 	}

@@ -2319,7 +2323,6 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 	struct sk_buff *skb;
 	u8 num_frags;
-	int i;
 
 	if (unlikely(xdp_buff_is_mb(xdp)))
 		num_frags = sinfo->nr_frags;

@@ -2334,18 +2337,12 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 	skb_put(skb, xdp->data_end - xdp->data);
 	skb->ip_summed = mvneta_rx_csum(pp, desc_status);
 
-	if (likely(!xdp_buff_is_mb(xdp)))
-		goto out;
-
-	for (i = 0; i < num_frags; i++) {
-		skb_frag_t *frag = &sinfo->frags[i];
-
-		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-				skb_frag_page(frag), skb_frag_off(frag),
-				skb_frag_size(frag), PAGE_SIZE);
-	}
+	if (unlikely(xdp_buff_is_mb(xdp)))
+		xdp_update_skb_shared_info(skb, num_frags,
+					   sinfo->xdp_frags_size,
+					   num_frags * xdp->frame_sz,
+					   xdp_buff_is_frag_pfmemalloc(xdp));
 
-out:
 	return skb;
 }
 

index e594016eb193..798b84d86d97 100644
@@ -306,10 +306,24 @@ 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(!xdp_frame_is_mb(xdpf)))
+		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,

84 lines not on this page · raw message

index e6977815b805..332699960b53 100644
@@ -1856,8 +1856,8 @@ 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

@@ -2051,47 +2051,87 @@ mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 
 static int
 mvneta_xdp_submit_frame(struct mvneta_port *pp, struct mvneta_tx_queue *txq,
-			struct xdp_frame *xdpf, bool dma_map)
+			struct xdp_frame *xdpf, int *nxmit_byte, 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);
+	struct device *dev = pp->dev->dev.parent;
+	struct mvneta_tx_desc *tx_desc = NULL;
+	int i, num_frames = 1;
+	struct page *page;
+
+	if (unlikely(xdp_frame_is_mb(xdpf)))
+		num_frames += sinfo->nr_frags;
 
-	if (txq->count >= txq->tx_stop_threshold)
+	if (txq->count + num_frames >= txq->size)
 		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 = NULL;
+		int len = 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;
+		if (unlikely(i)) { /* paged area */
+			frag = &sinfo->frags[i - 1];
+			len = skb_frag_size(frag);
 		}
-		buf->type = MVNETA_TYPE_XDP_NDO;
-	} else {
-		struct page *page = virt_to_page(xdpf->data);
 
-		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;
+		tx_desc = mvneta_txq_next_desc_get(txq);
+		if (dma_map) {
+			/* ndo_xdp_xmit */
+			void *data;
+
+			data = unlikely(frag) ? skb_frag_address(frag)
+					      : xdpf->data;
+			dma_addr = dma_map_single(dev, data, len,
+						  DMA_TO_DEVICE);
+			if (dma_mapping_error(dev, dma_addr)) {
+				mvneta_txq_desc_put(txq);
+				goto unmap;
+			}
+
+			buf->type = MVNETA_TYPE_XDP_NDO;
+		} else {
+			page = unlikely(frag) ? skb_frag_page(frag)
+					      : virt_to_page(xdpf->data);
+			dma_addr = page_pool_get_dma_addr(page);
+			if (unlikely(frag))
+				dma_addr += skb_frag_off(frag);
+			else
+				dma_addr += sizeof(*xdpf) + xdpf->headroom;
+			dma_sync_single_for_device(dev, dma_addr, len,
+						   DMA_BIDIRECTIONAL);
+			buf->type = MVNETA_TYPE_XDP_TX;
+		}
+		buf->xdpf = unlikely(i) ? NULL : xdpf;
+
+		tx_desc->command = unlikely(i) ? 0 : MVNETA_TXD_F_DESC;
+		tx_desc->buf_phys_addr = dma_addr;
+		tx_desc->data_size = len;
+		*nxmit_byte += 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 */
+	if (likely(tx_desc))
+		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;
+
+unmap:
+	for (i--; i >= 0; i--) {
+		mvneta_txq_desc_put(txq);
+		tx_desc = txq->descs + txq->next_desc_to_proc;
+		dma_unmap_single(dev, tx_desc->buf_phys_addr,
+				 tx_desc->data_size,
+				 DMA_TO_DEVICE);
+	}
+
+	return MVNETA_XDP_DROPPED;
 }
 
 static int

@@ -2100,8 +2140,8 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp)
 	struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 	struct mvneta_tx_queue *txq;
 	struct netdev_queue *nq;
+	int cpu, nxmit_byte = 0;
 	struct xdp_frame *xdpf;
-	int cpu;
 	u32 ret;
 
 	xdpf = xdp_convert_buff_to_frame(xdp);

@@ -2113,10 +2153,10 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp)
 	nq = netdev_get_tx_queue(pp->dev, txq->id);
 
 	__netif_tx_lock(nq, cpu);
-	ret = mvneta_xdp_submit_frame(pp, txq, xdpf, false);
+	ret = mvneta_xdp_submit_frame(pp, txq, xdpf, &nxmit_byte, false);
 	if (ret == MVNETA_XDP_TX) {
 		u64_stats_update_begin(&stats->syncp);
-		stats->es.ps.tx_bytes += xdpf->len;
+		stats->es.ps.tx_bytes += nxmit_byte;
 		stats->es.ps.tx_packets++;
 		stats->es.ps.xdp_tx++;
 		u64_stats_update_end(&stats->syncp);

@@ -2155,11 +2195,11 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame,
 
 	__netif_tx_lock(nq, cpu);
 	for (i = 0; i < num_frame; i++) {
-		ret = mvneta_xdp_submit_frame(pp, txq, frames[i], true);
+		ret = mvneta_xdp_submit_frame(pp, txq, frames[i], &nxmit_byte,
+					      true);
 		if (ret != MVNETA_XDP_TX)
 			break;
 
-		nxmit_byte += frames[i]->len;
 		nxmit++;
 	}
 

index 8bbf08fbab66..e516815e35f9 100644
@@ -875,6 +875,7 @@ struct bpf_prog_aux {
 	bool func_proto_unreliable;
 	bool sleepable;
 	bool tail_call_reachable;
+	bool xdp_mb;
 	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;

index c26871263f1f..d5d3e7d9ec49 100644
@@ -1111,6 +1111,11 @@ enum bpf_link_type {
  */
 #define BPF_F_SLEEPABLE		(1U << 4)
 
+/* If BPF_F_XDP_MB is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp multi-buffer
+ */
+#define BPF_F_XDP_MB		(1U << 5)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *

index b3ada4085f85..82626a95be99 100644
@@ -2202,7 +2202,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 				 BPF_F_ANY_ALIGNMENT |
 				 BPF_F_TEST_STATE_FREQ |
 				 BPF_F_SLEEPABLE |
-				 BPF_F_TEST_RND_HI32))
+				 BPF_F_TEST_RND_HI32 |
+				 BPF_F_XDP_MB))
 		return -EINVAL;
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&

@@ -2288,6 +2289,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 	prog->aux->dst_prog = dst_prog;
 	prog->aux->offload_requested = !!attr->prog_ifindex;
 	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
+	prog->aux->xdp_mb = attr->prog_flags & BPF_F_XDP_MB;
 
 	err = security_bpf_prog_alloc(prog->aux);
 	if (err)

index c26871263f1f..d5d3e7d9ec49 100644
@@ -1111,6 +1111,11 @@ enum bpf_link_type {
  */
 #define BPF_F_SLEEPABLE		(1U << 4)
 
+/* If BPF_F_XDP_MB is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp multi-buffer
+ */
+#define BPF_F_XDP_MB		(1U << 5)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *

index 332699960b53..98db3d03116a 100644
@@ -3750,6 +3750,7 @@ static void mvneta_percpu_disable(void *arg)
 static int mvneta_change_mtu(struct net_device *dev, int mtu)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
+	struct bpf_prog *prog = pp->xdp_prog;
 	int ret;
 
 	if (!IS_ALIGNED(MVNETA_RX_PKT_SIZE(mtu), 8)) {

@@ -3758,8 +3759,11 @@ 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);
+	if (prog && !prog->aux->xdp_mb && mtu > MVNETA_MAX_RX_BUF_SIZE) {
+		netdev_info(dev,
+			    "Illegal MTU %d for XDP prog without multi-buf\n",
+			    mtu);
+
 		return -EINVAL;
 	}
 

@@ -4428,8 +4432,9 @@ 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, "MTU too large for XDP");
+	if (prog && !prog->aux->xdp_mb && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "prog does not support XDP multi-buff");
 		return -EOPNOTSUPP;
 	}
 

index 798b84d86d97..067716d38ebc 100644
@@ -145,6 +145,20 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp)
 	return (struct skb_shared_info *)xdp_data_hard_end(xdp);
 }
 
+static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp)
+{
+	unsigned int len = xdp->data_end - xdp->data;
+	struct skb_shared_info *sinfo;
+
+	if (likely(!xdp_buff_is_mb(xdp)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_buff(xdp);
+	len += sinfo->xdp_frags_size;
+out:
+	return len;
+}
+
 struct xdp_frame {
 	void *data;
 	u16 len;

index d5d3e7d9ec49..d5921a0202f4 100644
@@ -4988,6 +4988,12 @@ union bpf_attr {
  *	Return
  *		The number of loops performed, **-EINVAL** for invalid **flags**,
  *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ *	Description
+ *		Get the total size of a given xdp buff (linear and paged area)
+ *	Return
+ *		The total size of a given xdp buffer.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

@@ -5172,6 +5178,7 @@ union bpf_attr {
 	FN(kallsyms_lookup_name),	\
 	FN(find_vma),			\
 	FN(loop),			\
+	FN(xdp_get_buff_len),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

index fe27c91e3758..122d3a6afe9d 100644
@@ -3783,6 +3783,19 @@ static const struct bpf_func_proto sk_skb_change_head_proto = {
 	.arg2_type	= ARG_ANYTHING,
 	.arg3_type	= ARG_ANYTHING,
 };
+
+BPF_CALL_1(bpf_xdp_get_buff_len, struct  xdp_buff*, xdp)
+{
+	return xdp_get_buff_len(xdp);
+}
+
+static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = {
+	.func		= bpf_xdp_get_buff_len,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
 {
 	return xdp_data_meta_unsupported(xdp) ? 0 :

@@ -7470,6 +7483,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_redirect_map_proto;
 	case BPF_FUNC_xdp_adjust_tail:
 		return &bpf_xdp_adjust_tail_proto;
+	case BPF_FUNC_xdp_get_buff_len:
+		return &bpf_xdp_get_buff_len_proto;
 	case BPF_FUNC_fib_lookup:
 		return &bpf_xdp_fib_lookup_proto;
 	case BPF_FUNC_check_mtu:

index d5d3e7d9ec49..d5921a0202f4 100644
@@ -4988,6 +4988,12 @@ union bpf_attr {
  *	Return
  *		The number of loops performed, **-EINVAL** for invalid **flags**,
  *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ *	Description
+ *		Get the total size of a given xdp buff (linear and paged area)
+ *	Return
+ *		The total size of a given xdp buffer.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

@@ -5172,6 +5178,7 @@ union bpf_attr {
 	FN(kallsyms_lookup_name),	\
 	FN(find_vma),			\
 	FN(loop),			\
+	FN(xdp_get_buff_len),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

index 98db3d03116a..5296a17236ad 100644
@@ -3270,7 +3270,8 @@ static int mvneta_create_page_pool(struct mvneta_port *pp,
 		return err;
 	}
 
-	err = xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0);
+	err = __xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0,
+				 PAGE_SIZE);
 	if (err < 0)
 		goto err_free_pp;
 

index 067716d38ebc..c45eaf58b3d4 100644
@@ -60,6 +60,7 @@ struct xdp_rxq_info {
 	u32 reg_state;
 	struct xdp_mem_info mem;
 	unsigned int napi_id;
+	u32 frag_size;
 } ____cacheline_aligned; /* perf critical, avoid false-sharing */
 
 struct xdp_txq_info {

@@ -304,6 +305,8 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
 	return xdp_frame;
 }
 
+void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+		  struct xdp_buff *xdp);
 void xdp_return_frame(struct xdp_frame *xdpf);
 void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
 void xdp_return_buff(struct xdp_buff *xdp);

@@ -340,8 +343,17 @@ static inline void xdp_release_frame(struct xdp_frame *xdpf)
 	__xdp_release_frame(xdpf->data, mem);
 }
 
-int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index, unsigned int napi_id);
+int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+		       struct net_device *dev, u32 queue_index,
+		       unsigned int napi_id, u32 frag_size);
+static inline int
+xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+		 struct net_device *dev, u32 queue_index,
+		 unsigned int napi_id)
+{
+	return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0);
+}
+
 void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq);
 void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq);
 bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq);

76 lines not on this page · raw message

index 7cfcc93116d7..bf3b3884efb3 100644
@@ -156,8 +156,9 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)
 }
 
 /* Returns 0 on success, negative on failure */
-int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index, unsigned int napi_id)
+int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+		       struct net_device *dev, u32 queue_index,
+		       unsigned int napi_id, u32 frag_size)
 {
 	if (xdp_rxq->reg_state == REG_STATE_UNUSED) {
 		WARN(1, "Driver promised not to register this");

@@ -179,11 +180,12 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
 	xdp_rxq->dev = dev;
 	xdp_rxq->queue_index = queue_index;
 	xdp_rxq->napi_id = napi_id;
+	xdp_rxq->frag_size = frag_size;
 
 	xdp_rxq->reg_state = REG_STATE_REGISTERED;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(xdp_rxq_info_reg);
+EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg);
 
 void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq)
 {

@@ -337,8 +339,8 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
  * is used for those calls sites.  Thus, allowing for faster recycling
  * of xdp_frames/pages in those cases.
  */
-static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
-			 struct xdp_buff *xdp)
+void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+		  struct xdp_buff *xdp)
 {
 	struct xdp_mem_allocator *xa;
 	struct page *page;

index 77f13de6f9f9..12f7b6ac9045 100644
@@ -1517,6 +1517,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 
 extern const struct bpf_func_proto bpf_skb_output_proto;
 extern const struct bpf_func_proto bpf_xdp_output_proto;
+extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto;
 
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)

@@ -1616,6 +1617,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sock_from_file_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_ptr_cookie_proto;
+	case BPF_FUNC_xdp_get_buff_len:
+		return &bpf_xdp_get_buff_len_trace_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?

79 lines not on this page · raw message

187 lines not on this page · raw message

index 58cf4345f5cc..3379d303f41a 100644
@@ -49,7 +49,7 @@ int BPF_PROG(trace_on_entry, struct xdp_buff *xdp)
 	void *data = (void *)(long)xdp->data;
 
 	meta.ifindex = xdp->rxq->dev->ifindex;
-	meta.pkt_len = data_end - data;
+	meta.pkt_len = bpf_xdp_get_buff_len((struct xdp_md *)xdp);
 	bpf_xdp_output(xdp, &perf_buf_map,
 		       ((__u64) meta.pkt_len << 32) |
 		       BPF_F_CURRENT_CPU,

index 46dd95755967..dbf1227f437c 100644
@@ -249,11 +249,10 @@ bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner)
 	return bpf_check_mod_kfunc_call(&prog_test_kfunc_list, kfunc_id, owner);
 }
 
-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)

@@ -581,7 +580,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (kattr->test.flags || kattr->test.cpu)
 		return -EINVAL;
 
-	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);

@@ -790,7 +790,8 @@ 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)) {
 		ret = PTR_ERR(data);
 		goto free_ctx;

@@ -876,7 +877,7 @@ 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 dbf1227f437c..9cb5d5eced9a 100644
@@ -758,16 +758,16 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr)
 {
 	u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	u32 headroom = XDP_PACKET_HEADROOM;
 	u32 size = kattr->test.data_size_in;
+	u32 headroom = XDP_PACKET_HEADROOM;
+	u32 retval, duration, max_data_sz;
 	u32 repeat = kattr->test.repeat;
 	struct netdev_rx_queue *rxqueue;
+	struct skb_shared_info *sinfo;
 	struct xdp_buff xdp = {};
-	u32 retval, duration;
+	int i, ret = -EINVAL;
 	struct xdp_md *ctx;
-	u32 max_data_sz;
 	void *data;
-	int ret = -EINVAL;
 
 	if (prog->expected_attach_type == BPF_XDP_DEVMAP ||
 	    prog->expected_attach_type == BPF_XDP_CPUMAP)

@@ -787,27 +787,60 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 		headroom -= ctx->data;
 	}
 
-	/* XDP have extra tailroom as (most) drivers use full page */
 	max_data_sz = 4096 - headroom - tailroom;
+	size = min_t(u32, size, 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)) {
 		ret = PTR_ERR(data);
 		goto free_ctx;
 	}
 
 	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
-	xdp_init_buff(&xdp, headroom + max_data_sz + tailroom,
-		      &rxqueue->xdp_rxq);
+	rxqueue->xdp_rxq.frag_size = headroom + max_data_sz + tailroom;
+	xdp_init_buff(&xdp, rxqueue->xdp_rxq.frag_size, &rxqueue->xdp_rxq);
 	xdp_prepare_buff(&xdp, data, headroom, size, true);
+	sinfo = xdp_get_shared_info_from_buff(&xdp);
 
 	ret = xdp_convert_md_to_buff(ctx, &xdp);
 	if (ret)
 		goto free_data;
 
+	if (unlikely(kattr->test.data_size_in > size)) {
+		void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
+
+		while (size < kattr->test.data_size_in) {
+			struct page *page;
+			skb_frag_t *frag;
+			int data_len;
+
+			page = alloc_page(GFP_KERNEL);
+			if (!page) {
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			frag = &sinfo->frags[sinfo->nr_frags++];
+			__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);
+
+			if (copy_from_user(page_address(page), data_in + size,
+					   data_len)) {
+				ret = -EFAULT;
+				goto out;
+			}
+			sinfo->xdp_frags_size += data_len;
+			size += data_len;
+		}
+		xdp_buff_set_mb(&xdp);
+	}
+
 	if (repeat > 1)
 		bpf_prog_change_xdp(NULL, prog);
+
 	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
 	/* We convert the xdp_buff back to an xdp_md before checking the return
 	 * code so the reference count of any held netdevice will be decremented

@@ -817,10 +850,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (ret)
 		goto out;
 
-	if (xdp.data_meta != data + headroom ||
-	    xdp.data_end != xdp.data_meta + size)
-		size = xdp.data_end - xdp.data_meta;
-
+	size = xdp.data_end - xdp.data_meta + sinfo->xdp_frags_size;
 	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval,
 			      duration);
 	if (!ret)

@@ -831,6 +861,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (repeat > 1)
 		bpf_prog_change_xdp(prog, NULL);
 free_data:
+	for (i = 0; i < sinfo->nr_frags; i++)
+		__free_page(skb_frag_page(&sinfo->frags[i]));
 	kfree(data);
 free_ctx:
 	kfree(ctx);

index 9cb5d5eced9a..e57c71085dd5 100644
@@ -130,7 +130,8 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 
 static int bpf_test_finish(const union bpf_attr *kattr,
 			   union bpf_attr __user *uattr, const void *data,
-			   u32 size, u32 retval, u32 duration)
+			   struct skb_shared_info *sinfo, u32 size,
+			   u32 retval, u32 duration)
 {
 	void __user *data_out = u64_to_user_ptr(kattr->test.data_out);
 	int err = -EFAULT;

@@ -145,8 +146,36 @@ static int bpf_test_finish(const union bpf_attr *kattr,
 		err = -ENOSPC;
 	}
 
-	if (data_out && copy_to_user(data_out, data, copy_size))
-		goto out;
+	if (data_out) {
+		int len = sinfo ? copy_size - sinfo->xdp_frags_size : copy_size;
+
+		if (copy_to_user(data_out, data, len))
+			goto out;
+
+		if (sinfo) {
+			int i, offset = len, data_len;
+
+			for (i = 0; i < sinfo->nr_frags; i++) {
+				skb_frag_t *frag = &sinfo->frags[i];
+
+				if (offset >= copy_size) {
+					err = -ENOSPC;
+					break;
+				}
+
+				data_len = min_t(int, copy_size - offset,
+						 skb_frag_size(frag));
+
+				if (copy_to_user(data_out + offset,
+						 skb_frag_address(frag),
+						 data_len))
+					goto out;
+
+				offset += data_len;
+			}
+		}
+	}
+
 	if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size)))
 		goto out;
 	if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval)))

@@ -683,7 +712,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	/* bpf program can never convert linear skb to non-linear */
 	if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
 		size = skb_headlen(skb);
-	ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
+	ret = bpf_test_finish(kattr, uattr, skb->data, NULL, size, retval,
+			      duration);
 	if (!ret)
 		ret = bpf_ctx_finish(kattr, uattr, ctx,
 				     sizeof(struct __sk_buff));

@@ -851,8 +881,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 		goto out;
 
 	size = xdp.data_end - xdp.data_meta + sinfo->xdp_frags_size;
-	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval,
-			      duration);
+	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, sinfo, size,
+			      retval, duration);
 	if (!ret)
 		ret = bpf_ctx_finish(kattr, uattr, ctx,
 				     sizeof(struct xdp_md));

@@ -944,8 +974,8 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (ret < 0)
 		goto out;
 
-	ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
-			      retval, duration);
+	ret = bpf_test_finish(kattr, uattr, &flow_keys, NULL,
+			      sizeof(flow_keys), retval, duration);
 	if (!ret)
 		ret = bpf_ctx_finish(kattr, uattr, user_ctx,
 				     sizeof(struct bpf_flow_keys));

@@ -1049,7 +1079,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
 		user_ctx->cookie = sock_gen_cookie(ctx.selected_sk);
 	}
 
-	ret = bpf_test_finish(kattr, uattr, NULL, 0, retval, duration);
+	ret = bpf_test_finish(kattr, uattr, NULL, NULL, 0, retval, duration);
 	if (!ret)
 		ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx));
 

index 3f5a17c38be5..d21e0a597b3c 100644
@@ -130,6 +130,133 @@ static void test_xdp_adjust_tail_grow2(void)
 	bpf_object__close(obj);
 }
 
+void test_xdp_adjust_mb_tail_shrink(void)
+{
+	const char *file = "./test_xdp_adjust_tail_shrink.o";
+	__u32 duration, retval, size, exp_size;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int err, prog_fd;
+	__u8 *buf;
+
+	/* For the individual test cases, the first byte in the packet
+	 * indicates which test will be run.
+	 */
+	obj = bpf_object__open(file);
+	if (libbpf_get_error(obj))
+		return;
+
+	prog = bpf_object__next_program(obj, NULL);
+	if (bpf_object__load(obj))
+		return;
+
+	prog_fd = bpf_program__fd(prog);
+
+	buf = malloc(9000);
+	if (CHECK(!buf, "malloc()", "error:%s\n", strerror(errno)))
+		goto out;
+
+	memset(buf, 0, 9000);
+
+	/* Test case removing 10 bytes from last frag, NOT freeing it */
+	exp_size = 8990; /* 9000 - 10 */
+	err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+				buf, &size, &retval, &duration);
+
+	CHECK(err || retval != XDP_TX || size != exp_size,
+	      "9k-10b", "err %d errno %d retval %d[%d] size %d[%u]\n",
+	      err, errno, retval, XDP_TX, size, exp_size);
+
+	/* Test case removing one of two pages, assuming 4K pages */
+	buf[0] = 1;
+	exp_size = 4900; /* 9000 - 4100 */
+	err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+				buf, &size, &retval, &duration);
+
+	CHECK(err || retval != XDP_TX || size != exp_size,
+	      "9k-1p", "err %d errno %d retval %d[%d] size %d[%u]\n",
+	      err, errno, retval, XDP_TX, size, exp_size);
+
+	/* Test case removing two pages resulting in a non mb xdp_buff */
+	buf[0] = 2;
+	exp_size = 800; /* 9000 - 8200 */
+	err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+				buf, &size, &retval, &duration);
+
+	CHECK(err || retval != XDP_TX || size != exp_size,
+	      "9k-2p", "err %d errno %d retval %d[%d] size %d[%u]\n",
+	      err, errno, retval, XDP_TX, size, exp_size);
+
+	free(buf);
+out:
+	bpf_object__close(obj);
+}
+
+void test_xdp_adjust_mb_tail_grow(void)
+{
+	const char *file = "./test_xdp_adjust_tail_grow.o";
+	__u32 duration, retval, size, exp_size;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int err, i, prog_fd;
+	__u8 *buf;
+
+	obj = bpf_object__open(file);
+	if (libbpf_get_error(obj))
+		return;
+
+	prog = bpf_object__next_program(obj, NULL);
+	if (bpf_object__load(obj))
+		return;
+
+	prog_fd = bpf_program__fd(prog);
+
+	buf = malloc(16384);
+	if (CHECK(!buf, "malloc()", "error:%s\n", strerror(errno)))
+		goto out;
+
+	/* Test case add 10 bytes to last frag */
+	memset(buf, 1, 16384);
+	size = 9000;
+	exp_size = size + 10;
+	err = bpf_prog_test_run(prog_fd, 1, buf, size,
+				buf, &size, &retval, &duration);
+
+	CHECK(err || retval != XDP_TX || size != exp_size,
+	      "9k+10b", "err %d retval %d[%d] size %d[%u]\n",
+	      err, retval, XDP_TX, size, exp_size);
+
+	for (i = 0; i < 9000; i++)
+		CHECK(buf[i] != 1, "9k+10b-old",
+		      "Old data not all ok, offset %i is failing [%u]!\n",
+		      i, buf[i]);
+
+	for (i = 9000; i < 9010; i++)
+		CHECK(buf[i] != 0, "9k+10b-new",
+		      "New data not all ok, offset %i is failing [%u]!\n",
+		      i, buf[i]);
+
+	for (i = 9010; i < 16384; i++)
+		CHECK(buf[i] != 1, "9k+10b-untouched",
+		      "Unused data not all ok, offset %i is failing [%u]!\n",
+		      i, buf[i]);
+
+	/* Test a too large grow */
+	memset(buf, 1, 16384);
+	size = 9001;
+	exp_size = size;
+	err = bpf_prog_test_run(prog_fd, 1, buf, size,
+				buf, &size, &retval, &duration);
+
+	CHECK(err || retval != XDP_DROP || size != exp_size,
+	      "9k+10b", "err %d retval %d[%d] size %d[%u]\n",
+	      err, retval, XDP_TX, size, exp_size);
+
+	free(buf);
+out:
+	bpf_object__close(obj);
+}
+
 void test_xdp_adjust_tail(void)
 {
 	if (test__start_subtest("xdp_adjust_tail_shrink"))

@@ -138,4 +265,8 @@ void test_xdp_adjust_tail(void)
 		test_xdp_adjust_tail_grow();
 	if (test__start_subtest("xdp_adjust_tail_grow2"))
 		test_xdp_adjust_tail_grow2();
+	if (test__start_subtest("xdp_adjust_mb_tail_shrink"))
+		test_xdp_adjust_mb_tail_shrink();
+	if (test__start_subtest("xdp_adjust_mb_tail_grow"))
+		test_xdp_adjust_mb_tail_grow();
 }

index 199c61b7d062..53b64c999450 100644
@@ -7,11 +7,10 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp)
 {
 	void *data_end = (void *)(long)xdp->data_end;
 	void *data = (void *)(long)xdp->data;
-	unsigned int data_len;
+	int data_len = bpf_xdp_get_buff_len(xdp);
 	int offset = 0;
 
 	/* Data length determine test case */
-	data_len = data_end - data;
 
 	if (data_len == 54) { /* sizeof(pkt_v4) */
 		offset = 4096; /* test too large offset */

@@ -20,7 +19,12 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp)
 	} else if (data_len == 64) {
 		offset = 128;
 	} else if (data_len == 128) {
-		offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */
+		/* Max tail grow 3520 */
+		offset = 4096 - 256 - 320 - data_len;
+	} else if (data_len == 9000) {
+		offset = 10;
+	} else if (data_len == 9001) {
+		offset = 4096;
 	} else {
 		return XDP_ABORTED; /* No matching test */
 	}

index b7448253d135..eeff48997b6e 100644
@@ -12,14 +12,38 @@
 SEC("xdp")
 int _xdp_adjust_tail_shrink(struct xdp_md *xdp)
 {
-	void *data_end = (void *)(long)xdp->data_end;
-	void *data = (void *)(long)xdp->data;
+	__u8 *data_end = (void *)(long)xdp->data_end;
+	__u8 *data = (void *)(long)xdp->data;
 	int offset = 0;
 
-	if (data_end - data == 54) /* sizeof(pkt_v4) */
+	switch (bpf_xdp_get_buff_len(xdp)) {
+	case 54:
+		/* sizeof(pkt_v4) */
 		offset = 256; /* shrink too much */
-	else
+		break;
+	case 9000:
+		/* Multi-buffer test cases */
+		if (data + 1 > data_end)
+			return XDP_DROP;
+
+		switch (data[0]) {
+		case 0:
+			offset = 10;
+			break;
+		case 1:
+			offset = 4100;
+			break;
+		case 2:
+			offset = 8200;
+			break;
+		default:
+			return XDP_DROP;
+		}
+		break;
+	default:
 		offset = 20;
+		break;
+	}
 	if (bpf_xdp_adjust_tail(xdp, 0 - offset))
 		return XDP_DROP;
 	return XDP_TX;

index d027e1d620fc..71781e4516b7 100644
@@ -271,6 +271,8 @@ enum sec_def_flags {
 	SEC_SLEEPABLE = 8,
 	/* allow non-strict prefix matching */
 	SEC_SLOPPY_PFX = 16,
+	/* BPF program support XDP multi-buff */
+	SEC_XDP_MB = 32,
 };
 
 struct bpf_sec_def {

@@ -6565,6 +6567,9 @@ static int libbpf_preload_prog(struct bpf_program *prog,
 	if (def & SEC_SLEEPABLE)
 		opts->prog_flags |= BPF_F_SLEEPABLE;
 
+	if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_MB))
+		opts->prog_flags |= BPF_F_XDP_MB;
+
 	if ((prog->type == BPF_PROG_TYPE_TRACING ||
 	     prog->type == BPF_PROG_TYPE_LSM ||
 	     prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {

@@ -8603,8 +8608,11 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("lsm.s/",		LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm),
 	SEC_DEF("iter/",		TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter),
 	SEC_DEF("syscall",		SYSCALL, 0, SEC_SLEEPABLE),
+	SEC_DEF("xdp_devmap_mb/",	XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE | SEC_XDP_MB),
 	SEC_DEF("xdp_devmap/",		XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE),
+	SEC_DEF("xdp_cpumap_mb/",	XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE | SEC_XDP_MB),
 	SEC_DEF("xdp_cpumap/",		XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE),
+	SEC_DEF("xdp_mb/",		XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX | SEC_XDP_MB),
 	SEC_DEF("xdp",			XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
 	SEC_DEF("perf_event",		PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX),
 	SEC_DEF("lwt_in",		LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX),

index e516815e35f9..394e33c45513 100644
@@ -194,6 +194,18 @@ struct bpf_map {
 	struct work_struct work;
 	struct mutex freeze_mutex;
 	u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */
+
+	/* 'Ownership' of program-containing map is claimed by the first program
+	 * that is going to use this map or by the first program which FD is
+	 * stored in the map to make sure that all callers and callees have the
+	 * same prog type, JITed flag and xdp_mb flag.
+	 */
+	struct {
+		spinlock_t lock;
+		enum bpf_prog_type type;
+		bool jited;
+		bool xdp_mb;
+	} owner;
 };
 
 static inline bool map_value_has_spin_lock(const struct bpf_map *map)

@@ -936,16 +948,6 @@ struct bpf_prog_aux {
 };
 
 struct bpf_array_aux {
-	/* 'Ownership' of prog array is claimed by the first program that
-	 * is going to use this map or by the first program which FD is
-	 * stored in the map to make sure that all callers and callees have
-	 * the same prog type and JITed flag.
-	 */
-	struct {
-		spinlock_t lock;
-		enum bpf_prog_type type;
-		bool jited;
-	} owner;
 	/* Programs with direct jumps into programs part of this array. */
 	struct list_head poke_progs;
 	struct bpf_map *map;

@@ -1120,7 +1122,14 @@ struct bpf_event_entry {
 	struct rcu_head rcu;
 };
 
-bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
+static inline bool map_type_contains_progs(struct bpf_map *map)
+{
+	return map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+	       map->map_type == BPF_MAP_TYPE_DEVMAP ||
+	       map->map_type == BPF_MAP_TYPE_CPUMAP;
+}
+
+bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp);
 int bpf_prog_calc_tag(struct bpf_prog *fp);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);

index c7a5be3bf8be..7f145aefbff8 100644
@@ -837,13 +837,12 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
 static void *prog_fd_array_get_ptr(struct bpf_map *map,
 				   struct file *map_file, int fd)
 {
-	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct bpf_prog *prog = bpf_prog_get(fd);
 
 	if (IS_ERR(prog))
 		return prog;
 
-	if (!bpf_prog_array_compatible(array, prog)) {
+	if (!bpf_prog_map_compatible(map, prog)) {
 		bpf_prog_put(prog);
 		return ERR_PTR(-EINVAL);
 	}

@@ -1071,7 +1070,6 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
 	INIT_WORK(&aux->work, prog_array_map_clear_deferred);
 	INIT_LIST_HEAD(&aux->poke_progs);
 	mutex_init(&aux->poke_mutex);
-	spin_lock_init(&aux->owner.lock);
 
 	map = array_map_alloc(attr);
 	if (IS_ERR(map)) {

index de3e5bc6781f..4a8beab6071e 100644
@@ -1829,28 +1829,30 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 }
 #endif
 
-bool bpf_prog_array_compatible(struct bpf_array *array,
-			       const struct bpf_prog *fp)
+bool bpf_prog_map_compatible(struct bpf_map *map,
+			     const struct bpf_prog *fp)
 {
 	bool ret;
 
 	if (fp->kprobe_override)
 		return false;
 
-	spin_lock(&array->aux->owner.lock);
-
-	if (!array->aux->owner.type) {
+	spin_lock(&map->owner.lock);
+	if (!map->owner.type) {
 		/* There's no owner yet where we could check for
 		 * compatibility.
 		 */
-		array->aux->owner.type  = fp->type;
-		array->aux->owner.jited = fp->jited;
+		map->owner.type  = fp->type;
+		map->owner.jited = fp->jited;
+		map->owner.xdp_mb = fp->aux->xdp_mb;
 		ret = true;
 	} else {
-		ret = array->aux->owner.type  == fp->type &&
-		      array->aux->owner.jited == fp->jited;
+		ret = map->owner.type  == fp->type &&
+		      map->owner.jited == fp->jited &&
+		      map->owner.xdp_mb == fp->aux->xdp_mb;
 	}
-	spin_unlock(&array->aux->owner.lock);
+	spin_unlock(&map->owner.lock);
+
 	return ret;
 }
 

@@ -1862,13 +1864,11 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 	mutex_lock(&aux->used_maps_mutex);
 	for (i = 0; i < aux->used_map_cnt; i++) {
 		struct bpf_map *map = aux->used_maps[i];
-		struct bpf_array *array;
 
-		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+		if (!map_type_contains_progs(map))
 			continue;
 
-		array = container_of(map, struct bpf_array, map);
-		if (!bpf_prog_array_compatible(array, fp)) {
+		if (!bpf_prog_map_compatible(map, fp)) {
 			ret = -EINVAL;
 			goto out;
 		}

index 585b2b77ccc4..7f9984e7ba1d 100644
@@ -397,7 +397,8 @@ static int cpu_map_kthread_run(void *data)
 	return 0;
 }
 
-static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
+static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu,
+				      struct bpf_map *map, int fd)
 {
 	struct bpf_prog *prog;
 

@@ -405,7 +406,8 @@ static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (prog->expected_attach_type != BPF_XDP_CPUMAP) {
+	if (prog->expected_attach_type != BPF_XDP_CPUMAP ||
+	    !bpf_prog_map_compatible(map, prog)) {
 		bpf_prog_put(prog);
 		return -EINVAL;
 	}

@@ -457,7 +459,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	rcpu->map_id = map->id;
 	rcpu->value.qsize  = value->qsize;
 
-	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd))
+	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, map, fd))
 		goto free_ptr_ring;
 
 	/* Setup kthread */

index f02d04540c0c..a35edd4a2bf1 100644
@@ -868,7 +868,8 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 					     BPF_PROG_TYPE_XDP, false);
 		if (IS_ERR(prog))
 			goto err_put_dev;
-		if (prog->expected_attach_type != BPF_XDP_DEVMAP)
+		if (prog->expected_attach_type != BPF_XDP_DEVMAP ||
+		    !bpf_prog_map_compatible(&dtab->map, prog))
 			goto err_put_prog;
 	}
 

index 82626a95be99..0c45d3e9eda3 100644
@@ -540,16 +540,15 @@ static unsigned long bpf_map_memory_footprint(const struct bpf_map *map)
 
 static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 {
-	const struct bpf_map *map = filp->private_data;
-	const struct bpf_array *array;
-	u32 type = 0, jited = 0;
-
-	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
-		array = container_of(map, struct bpf_array, map);
-		spin_lock(&array->aux->owner.lock);
-		type  = array->aux->owner.type;
-		jited = array->aux->owner.jited;
-		spin_unlock(&array->aux->owner.lock);
+	struct bpf_map *map = filp->private_data;
+	u32 type = 0, jited = 0, xdp_mb = 0;
+
+	if (map_type_contains_progs(map)) {
+		spin_lock(&map->owner.lock);
+		type  = map->owner.type;
+		jited = map->owner.jited;
+		xdp_mb = map->owner.xdp_mb;
+		spin_unlock(&map->owner.lock);
 	}
 
 	seq_printf(m,

@@ -574,6 +573,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 	if (type) {
 		seq_printf(m, "owner_prog_type:\t%u\n", type);
 		seq_printf(m, "owner_jited:\t%u\n", jited);
+		seq_printf(m, "owner_xdp_mb:\t%u\n", xdp_mb);
 	}
 }
 #endif

@@ -864,6 +864,7 @@ static int map_create(union bpf_attr *attr)
 	atomic64_set(&map->refcnt, 1);
 	atomic64_set(&map->usercnt, 1);
 	mutex_init(&map->freeze_mutex);
+	spin_lock_init(&map->owner.lock);
 
 	map->spin_lock_off = -EINVAL;
 	map->timer_off = -EINVAL;

index d5921a0202f4..94e43088971d 100644
@@ -4994,6 +4994,22 @@ union bpf_attr {
  *		Get the total size of a given xdp buff (linear and paged area)
  *	Return
  *		The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		This helper is provided as an easy way to load data from a
+ *		xdp buffer. It can be used to load *len* bytes from *offset* from
+ *		the frame associated to *xdp_md*, into the buffer pointed by
+ *		*buf*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		Store *len* bytes from buffer *buf* into the frame
+ *		associated to *xdp_md*, at *offset*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

@@ -5179,6 +5195,8 @@ union bpf_attr {
 	FN(find_vma),			\
 	FN(loop),			\
 	FN(xdp_get_buff_len),		\
+	FN(xdp_load_bytes),		\
+	FN(xdp_store_bytes),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

198 lines not on this page · raw message

index d5921a0202f4..94e43088971d 100644
@@ -4994,6 +4994,22 @@ union bpf_attr {
  *		Get the total size of a given xdp buff (linear and paged area)
  *	Return
  *		The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		This helper is provided as an easy way to load data from a
+ *		xdp buffer. It can be used to load *len* bytes from *offset* from
+ *		the frame associated to *xdp_md*, into the buffer pointed by
+ *		*buf*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		Store *len* bytes from buffer *buf* into the frame
+ *		associated to *xdp_md*, at *offset*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

@@ -5179,6 +5195,8 @@ union bpf_attr {
 	FN(find_vma),			\
 	FN(loop),			\
 	FN(xdp_get_buff_len),		\
+	FN(xdp_load_bytes),		\
+	FN(xdp_store_bytes),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

new file mode 100644
index 000000000000..4b0d04fb1041
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+void test_xdp_update_frags(void)
+{
+	const char *file = "./test_xdp_update_frags.o";
+	__u32 duration, retval, size;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int err, prog_fd;
+	__u32 *offset;
+	__u8 *buf;
+
+	obj = bpf_object__open(file);
+	if (libbpf_get_error(obj))
+		return;
+
+	prog = bpf_object__next_program(obj, NULL);
+	if (bpf_object__load(obj))
+		return;
+
+	prog_fd = bpf_program__fd(prog);
+
+	buf = malloc(128);
+	if (CHECK(!buf, "malloc()", "error:%s\n", strerror(errno)))
+		goto out;
+
+	memset(buf, 0, 128);
+	offset = (__u32 *)buf;
+	*offset = 16;
+	buf[*offset] = 0xaa;		/* marker at offset 16 (head) */
+	buf[*offset + 15] = 0xaa;	/* marker at offset 31 (head) */
+
+	err = bpf_prog_test_run(prog_fd, 1, buf, 128,
+				buf, &size, &retval, &duration);
+
+	/* test_xdp_update_frags: buf[16,31]: 0xaa -> 0xbb */
+	CHECK(err || retval != XDP_PASS || buf[16] != 0xbb || buf[31] != 0xbb,
+	      "128b", "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	free(buf);
+
+	buf = malloc(9000);
+	if (CHECK(!buf, "malloc()", "error:%s\n", strerror(errno)))
+		goto out;
+
+	memset(buf, 0, 9000);
+	offset = (__u32 *)buf;
+	*offset = 5000;
+	buf[*offset] = 0xaa;		/* marker at offset 5000 (frag0) */
+	buf[*offset + 15] = 0xaa;	/* marker at offset 5015 (frag0) */
+
+	err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+				buf, &size, &retval, &duration);
+
+	/* test_xdp_update_frags: buf[5000,5015]: 0xaa -> 0xbb */
+	CHECK(err || retval != XDP_PASS ||
+	      buf[5000] != 0xbb || buf[5015] != 0xbb,
+	      "9000b", "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	memset(buf, 0, 9000);
+	offset = (__u32 *)buf;
+	*offset = 3510;
+	buf[*offset] = 0xaa;		/* marker at offset 3510 (head) */
+	buf[*offset + 15] = 0xaa;	/* marker at offset 3525 (frag0) */
+
+	err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+				buf, &size, &retval, &duration);
+
+	/* test_xdp_update_frags: buf[3510,3525]: 0xaa -> 0xbb */
+	CHECK(err || retval != XDP_PASS ||
+	      buf[3510] != 0xbb || buf[3525] != 0xbb,
+	      "9000b", "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	memset(buf, 0, 9000);
+	offset = (__u32 *)buf;
+	*offset = 7606;
+	buf[*offset] = 0xaa;		/* marker at offset 7606 (frag0) */
+	buf[*offset + 15] = 0xaa;	/* marker at offset 7621 (frag1) */
+
+	err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+				buf, &size, &retval, &duration);
+
+	/* test_xdp_update_frags: buf[7606,7621]: 0xaa -> 0xbb */
+	CHECK(err || retval != XDP_PASS ||
+	      buf[7606] != 0xbb || buf[7621] != 0xbb,
+	      "9000b", "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	free(buf);
+out:
+	bpf_object__close(obj);
+}
+
+void test_xdp_adjust_frags(void)
+{
+	if (test__start_subtest("xdp_adjust_frags"))
+		test_xdp_update_frags();
+}

42 lines not on this page · raw message

index fd812bd43600..ee580b50a945 100644
@@ -3,11 +3,12 @@
 #include <linux/if_link.h>
 #include <test_progs.h>
 
+#include "test_xdp_with_cpumap_mb_helpers.skel.h"
 #include "test_xdp_with_cpumap_helpers.skel.h"
 
 #define IFINDEX_LO	1
 
-void serial_test_xdp_cpumap_attach(void)
+void test_xdp_with_cpumap_helpers(void)
 {
 	struct test_xdp_with_cpumap_helpers *skel;
 	struct bpf_prog_info info = {};

@@ -54,6 +55,68 @@ void serial_test_xdp_cpumap_attach(void)
 	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
 	ASSERT_NEQ(err, 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry");
 
+	/* try to attach BPF_XDP_CPUMAP multi-buff program when we have already
+	 * loaded a legacy XDP program on the map
+	 */
+	idx = 1;
+	val.qsize = 192;
+	val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm_mb);
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	ASSERT_NEQ(err, 0,
+		   "Add BPF_XDP_CPUMAP multi-buff program to cpumap entry");
+
 out_close:
 	test_xdp_with_cpumap_helpers__destroy(skel);
 }
+
+void test_xdp_with_cpumap_mb_helpers(void)
+{
+	struct test_xdp_with_cpumap_mb_helpers *skel;
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	struct bpf_cpumap_val val = {
+		.qsize = 192,
+	};
+	int err, mb_prog_fd, map_fd;
+	__u32 idx = 0;
+
+	skel = test_xdp_with_cpumap_mb_helpers__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load"))
+		return;
+
+	mb_prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm_mb);
+	map_fd = bpf_map__fd(skel->maps.cpu_map);
+	err = bpf_obj_get_info_by_fd(mb_prog_fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+		goto out_close;
+
+	val.bpf_prog.fd = mb_prog_fd;
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	ASSERT_OK(err, "Add program to cpumap entry");
+
+	err = bpf_map_lookup_elem(map_fd, &idx, &val);
+	ASSERT_OK(err, "Read cpumap entry");
+	ASSERT_EQ(info.id, val.bpf_prog.id,
+		  "Match program id to cpumap entry prog_id");
+
+	/* try to attach BPF_XDP_CPUMAP program when we have already
+	 * loaded a multi-buff XDP program on the map
+	 */
+	idx = 1;
+	val.qsize = 192;
+	val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm);
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	ASSERT_NEQ(err, 0, "Add BPF_XDP_CPUMAP program to cpumap entry");
+
+out_close:
+	test_xdp_with_cpumap_mb_helpers__destroy(skel);
+}
+
+void serial_test_xdp_cpumap_attach(void)
+{
+	if (test__start_subtest("CPUMAP with programs in entries"))
+		test_xdp_with_cpumap_helpers();
+
+	if (test__start_subtest("CPUMAP with multi-buff programs in entries"))
+		test_xdp_with_cpumap_mb_helpers();
+}

80 lines not on this page · raw message

index 532025057711..f32e4dab1751 100644
@@ -33,4 +33,10 @@ int xdp_dummy_cm(struct xdp_md *ctx)
 	return XDP_PASS;
 }
 
+SEC("xdp_cpumap_mb/mb_dummy_cm")
+int xdp_dummy_cm_mb(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
 char _license[] SEC("license") = "GPL";

new file mode 100644
index 000000000000..96eedbaef71b
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define IFINDEX_LO	1
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CPUMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_cpumap_val));
+	__uint(max_entries, 4);
+} cpu_map SEC(".maps");
+
+SEC("xdp_cpumap/dummy_cm")
+int xdp_dummy_cm(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+SEC("xdp_cpumap_mb/mb_dummy_cm")
+int xdp_dummy_cm_mb(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";

index 1e6b9c38ea6d..691f2d70dedc 100644
@@ -40,4 +40,11 @@ int xdp_dummy_dm(struct xdp_md *ctx)
 
 	return XDP_PASS;
 }
+
+SEC("xdp_devmap_mb/mp_map_prog")
+int xdp_dummy_dm_mb(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
 char _license[] SEC("license") = "GPL";

new file mode 100644
index 000000000000..05221b1fd9f2
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
+	__uint(max_entries, 4);
+} dm_ports SEC(".maps");
+
+/* valid program on DEVMAP entry via SEC name;
+ * has access to egress and ingress ifindex
+ */
+SEC("xdp_devmap/map_prog")
+int xdp_dummy_dm(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+SEC("xdp_devmap_mb/mp_map_prog")
+int xdp_dummy_dm_mb(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";

index 14860931733d..def6e9f451a7 100644
@@ -4186,6 +4186,13 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	struct bpf_map *map;
 	int err;
 
+	/* XDP_REDIRECT is not fully supported yet for xdp multi-buff since
+	 * not all XDP capable drivers can map non-linear xdp_frame in
+	 * ndo_xdp_xmit.
+	 */
+	if (unlikely(xdp_buff_is_mb(xdp) && map_type != BPF_MAP_TYPE_CPUMAP))
+		return -EOPNOTSUPP;
+
 	ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
 	ri->map_type = BPF_MAP_TYPE_UNSPEC;