mvneta: introduce XDP multi-buffer support

index 6bdb0db3e825..1abeba7ef82e 100644
@@ -522,13 +522,17 @@ struct skb_shared_info {
 	unsigned short	gso_segs;
 	struct sk_buff	*frag_list;
 	struct skb_shared_hwtstamps hwtstamps;
-	unsigned int	gso_type;
+	union {
+		unsigned int	gso_type;
+		unsigned int	xdp_frags_size;
+	};
 	u32		tskey;
 
 	/*
 	 * Warning : all fields before dataref are cleared in __alloc_skb()
 	 */
 	atomic_t	dataref;
+	unsigned int	xdp_frags_tsize;
 
 	/* Intermediate layers must ensure that destructor_arg
 	 * remains valid until skb destructor */

index ad5b02dcb6f4..ed5ea784fd45 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*/
+	u16 flags; /* supported values defined in xdp_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 */
+	u16 flags; /* supported values defined in xdp_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 5d1007e1b5c9..9f4858e35566 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 9f4858e35566..cbf614d6b993 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 ed5ea784fd45..53cccdc9528c 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 cc92ccb38432..504be3ce3ca9 100644
@@ -531,8 +531,20 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct sk_buff *skb,
 					   struct net_device *dev)
 {
+	unsigned int frag_size, frag_tsize;
 	unsigned int headroom, frame_size;
 	void *hard_start;
+	u8 nr_frags;
+
+	/* xdp multi-buff frame */
+	if (unlikely(xdp_frame_is_mb(xdpf))) {
+		struct skb_shared_info *sinfo;
+
+		sinfo = xdp_get_shared_info_from_frame(xdpf);
+		frag_tsize = sinfo->xdp_frags_tsize;
+		frag_size = sinfo->xdp_frags_size;
+		nr_frags = sinfo->nr_frags;
+	}
 
 	/* Part of headroom was reserved to xdpf */
 	headroom = sizeof(*xdpf) + xdpf->headroom;

@@ -552,6 +564,11 @@ 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,
+					   frag_size, frag_tsize,
+					   xdp_frame_is_frag_pfmemalloc(xdpf));
+
 	/* Essential SKB info: protocol and skb->dev */
 	skb->protocol = eth_type_trans(skb, dev);
 

index cbf614d6b993..b996eb49d813 100644
@@ -2304,11 +2304,19 @@ 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);
 	}
+
+	/* last fragment */
+	if (len == *size)
+		sinfo->xdp_frags_tsize = sinfo->nr_frags * PAGE_SIZE;
 	*size -= len;
 }
 

@@ -2316,13 +2324,18 @@ static struct sk_buff *
 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);
+	unsigned int size, truesize;
 	struct sk_buff *skb;
 	u8 num_frags;
-	int i;
 
-	if (unlikely(xdp_buff_is_mb(xdp)))
+	if (unlikely(xdp_buff_is_mb(xdp))) {
+		struct skb_shared_info *sinfo;
+
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		truesize = sinfo->xdp_frags_tsize;
+		size = sinfo->xdp_frags_size;
 		num_frags = sinfo->nr_frags;
+	}
 
 	skb = build_skb(xdp->data_hard_start, PAGE_SIZE);
 	if (!skb)

@@ -2334,18 +2347,10 @@ 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, size, truesize,
+					   xdp_buff_is_frag_pfmemalloc(xdp));
 
-out:
 	return skb;
 }
 

index 53cccdc9528c..d66e9877d773 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 b996eb49d813..dde1c28b0ea8 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 dde1c28b0ea8..3dbcb067346c 100644
@@ -3767,11 +3767,6 @@ 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)) {

@@ -4481,11 +4476,6 @@ 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, "MTU too large for XDP");
-		return -EOPNOTSUPP;
-	}
-
 	if (pp->bm_priv) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Hardware Buffer Management not supported on XDP");

index d66e9877d773..cdaecf8d4d61 100644
@@ -145,6 +145,13 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp)
 	return (struct skb_shared_info *)xdp_data_hard_end(xdp);
 }
 
+static inline unsigned int xdp_get_frag_tailroom(const skb_frag_t *frag)
+{
+	struct page *page = skb_frag_page(frag);
+
+	return page_size(page) - skb_frag_size(frag) - skb_frag_off(frag);
+}
+
 struct xdp_frame {
 	void *data;
 	u16 len;

@@ -290,6 +297,8 @@ 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);

71 lines not on this page · raw message

index 1346fb8b3f50..a71cdea75306 100644
@@ -339,8 +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;

@@ -373,6 +373,7 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		break;
 	}
 }
+EXPORT_SYMBOL_GPL(__xdp_return);
 
 void xdp_return_frame(struct xdp_frame *xdpf)
 {

index 2db6925e04f4..ddbf9ccc2f74 100644
@@ -4847,6 +4847,12 @@ union bpf_attr {
  * 		Get address of the traced function (for tracing and kprobe programs).
  * 	Return
  * 		Address of the traced function.
+ *
+ * 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),			\

@@ -5023,6 +5029,7 @@ union bpf_attr {
 	FN(timer_start),		\
 	FN(timer_cancel),		\
 	FN(get_func_ip),		\
+	FN(xdp_get_buff_len),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

index 1b931824161c..93ce775eaadf 100644
@@ -3784,6 +3784,27 @@ 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)
+{
+	u64 len = xdp->data_end - xdp->data;
+
+	if (unlikely(xdp_buff_is_mb(xdp))) {
+		struct skb_shared_info *sinfo;
+
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		len += sinfo->xdp_frags_size;
+	}
+	return len;
+}
+
+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 :

@@ -7501,6 +7522,8 @@ 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 2db6925e04f4..ddbf9ccc2f74 100644
@@ -4847,6 +4847,12 @@ union bpf_attr {
  * 		Get address of the traced function (for tracing and kprobe programs).
  * 	Return
  * 		Address of the traced function.
+ *
+ * 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),			\

@@ -5023,6 +5029,7 @@ union bpf_attr {
 	FN(timer_start),		\
 	FN(timer_cancel),		\
 	FN(get_func_ip),		\
+	FN(xdp_get_buff_len),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

index c5e0b6a64091..054d42b6d080 100644
@@ -1390,6 +1390,7 @@ 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)

@@ -1487,6 +1488,8 @@ 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 ?

90 lines not on this page · raw message

188 lines not on this page · raw message

index a038e827f850..902b54190377 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 335e1d8c17f8..362e020631b3 100644
@@ -245,11 +245,10 @@ bool bpf_prog_test_check_kfunc_call(u32 kfunc_id)
 	return btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id);
 }
 
-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)

@@ -570,7 +569,8 @@ 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);

@@ -781,7 +781,8 @@ 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;

@@ -865,7 +866,7 @@ 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 362e020631b3..1833b863c185 100644
@@ -749,16 +749,16 @@ 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)

@@ -778,11 +778,10 @@ 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;

@@ -792,11 +791,45 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	xdp_init_buff(&xdp, headroom + max_data_sz + tailroom,
 		      &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_tsize += PAGE_SIZE;
+			sinfo->xdp_frags_size += data_len;
+			size += data_len;
+		}
+		xdp_buff_set_mb(&xdp);
+	}
+
 	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

@@ -807,10 +840,7 @@ 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)

@@ -820,6 +850,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 out:
 	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 1833b863c185..3618cccd86b1 100644
@@ -128,7 +128,8 @@ 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;

@@ -143,8 +144,36 @@ 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)))

@@ -673,7 +702,8 @@ 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));

@@ -841,8 +871,8 @@ 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));

@@ -933,8 +963,8 @@ 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));

@@ -1038,7 +1068,7 @@ 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 d5c98f2cb12f..40f7ae798fd1 100644
@@ -130,6 +130,120 @@ 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_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.
+	 */
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	buf = malloc(9000);
+	if (CHECK(!buf, "malloc()", "error:%s\n", strerror(errno)))
+		return;
+
+	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);
+
+	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_object *obj;
+	int err, i, prog_fd;
+	__u8 *buf;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	buf = malloc(16384);
+	if (CHECK(!buf, "malloc()", "error:%s\n", strerror(errno)))
+		return;
+
+	/* 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);
+
+	bpf_object__close(obj);
+}
+
 void test_xdp_adjust_tail(void)
 {
 	if (test__start_subtest("xdp_adjust_tail_shrink"))

@@ -138,4 +252,8 @@ 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 3d66599eee2e..3d43defb0e00 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 22065a9cfb25..64177597ac29 100644
@@ -14,14 +14,38 @@ int _version SEC("version") = 1;
 SEC("xdp_adjust_tail_shrink")
 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 cdaecf8d4d61..ce4764c7cd40 100644
@@ -82,6 +82,11 @@ struct xdp_buff {
 	struct xdp_txq_info *txq;
 	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
 	u16 flags; /* supported values defined in xdp_flags */
+	/* xdp multi-buff metadata used for frags iteration */
+	struct {
+		u16 headroom;	/* frame headroom: data - data_hard_start */
+		u16 headlen;	/* first buffer length: data_end - data */
+	} mb;
 };
 
 static __always_inline bool xdp_buff_is_mb(struct xdp_buff *xdp)

@@ -127,6 +132,9 @@ xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start,
 	xdp->data = data;
 	xdp->data_end = data + data_len;
 	xdp->data_meta = meta_valid ? data : data + 1;
+	/* mb metadata for frags iteration */
+	xdp->mb.headroom = headroom;
+	xdp->mb.headlen = data_len;
 }
 
 /* Reserve memory area at end-of data area.

index ddbf9ccc2f74..c20a8b7c5c7c 100644
@@ -4853,6 +4853,37 @@ 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_adjust_data(struct xdp_buff *xdp_md, u32 offset)
+ *	Description
+ *		For XDP frames split over multiple buffers, the
+ *		*xdp_md*\ **->data** and*xdp_md *\ **->data_end** pointers
+ *		will point to the start and end of the first fragment only.
+ *		This helper can be used to access subsequent fragments by
+ *		moving the data pointers. To use, an XDP program can call
+ *		this helper with the byte offset of the packet payload that
+ *		it wants to access; the helper will move *xdp_md*\ **->data**
+ *		and *xdp_md *\ **->data_end** so they point to the requested
+ *		payload offset and to the end of the fragment containing this
+ *		byte offset, and return the byte offset of the start of the
+ *		fragment.
+ *		To move back to the beginning of the packet, simply call the
+ *		helper with an offset of '0'.
+ *		Note also that the helpers that modify the packet boundaries
+ *		(*bpf_xdp_adjust_head()*, *bpf_xdp_adjust_tail()* and
+ *		*bpf_xdp_adjust_meta()*) will fail if the pointers have been
+ *		moved; it is the responsibility of the BPF program to move them
+ *		back before using these helpers.
+ *
+ *		A call to this helper is susceptible to change the underlying
+ *		packet buffer. Therefore, at load time, all checks on pointers
+ *		previously done by the verifier are invalidated and must be
+ *		performed again, if the helper is used in combination with
+ *		direct packet access.
+ *	Return
+ *		offset between the beginning of the current fragment and
+ *		original *xdp_md*\ **->data** on success, or a negative error
+ *		in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

@@ -5030,6 +5061,7 @@ union bpf_attr {
 	FN(timer_cancel),		\
 	FN(get_func_ip),		\
 	FN(xdp_get_buff_len),		\
+	FN(xdp_adjust_data),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

index 3618cccd86b1..6efa60555258 100644
@@ -756,6 +756,8 @@ static int xdp_convert_md_to_buff(struct xdp_md *xdp_md, struct xdp_buff *xdp)
 	}
 
 	xdp->data = xdp->data_meta + xdp_md->data;
+	xdp->mb.headroom = xdp->data - xdp->data_hard_start;
+	xdp->mb.headlen = xdp->data_end - xdp->data;
 	return 0;
 
 free_dev:

@@ -870,6 +872,12 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (ret)
 		goto out;
 
+	/* data pointers need to be reset after frag iteration */
+	if (unlikely(xdp.data_hard_start + xdp.mb.headroom != xdp.data)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
 	size = xdp.data_end - xdp.data_meta + sinfo->xdp_frags_size;
 	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, sinfo, size,
 			      retval, duration);

103 lines not on this page · raw message

index ddbf9ccc2f74..c20a8b7c5c7c 100644
@@ -4853,6 +4853,37 @@ 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_adjust_data(struct xdp_buff *xdp_md, u32 offset)
+ *	Description
+ *		For XDP frames split over multiple buffers, the
+ *		*xdp_md*\ **->data** and*xdp_md *\ **->data_end** pointers
+ *		will point to the start and end of the first fragment only.
+ *		This helper can be used to access subsequent fragments by
+ *		moving the data pointers. To use, an XDP program can call
+ *		this helper with the byte offset of the packet payload that
+ *		it wants to access; the helper will move *xdp_md*\ **->data**
+ *		and *xdp_md *\ **->data_end** so they point to the requested
+ *		payload offset and to the end of the fragment containing this
+ *		byte offset, and return the byte offset of the start of the
+ *		fragment.
+ *		To move back to the beginning of the packet, simply call the
+ *		helper with an offset of '0'.
+ *		Note also that the helpers that modify the packet boundaries
+ *		(*bpf_xdp_adjust_head()*, *bpf_xdp_adjust_tail()* and
+ *		*bpf_xdp_adjust_meta()*) will fail if the pointers have been
+ *		moved; it is the responsibility of the BPF program to move them
+ *		back before using these helpers.
+ *
+ *		A call to this helper is susceptible to change the underlying
+ *		packet buffer. Therefore, at load time, all checks on pointers
+ *		previously done by the verifier are invalidated and must be
+ *		performed again, if the helper is used in combination with
+ *		direct packet access.
+ *	Return
+ *		offset between the beginning of the current fragment and
+ *		original *xdp_md*\ **->data** on success, or a negative error
+ *		in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

@@ -5030,6 +5061,7 @@ union bpf_attr {
 	FN(timer_cancel),		\
 	FN(get_func_ip),		\
 	FN(xdp_get_buff_len),		\
+	FN(xdp_adjust_data),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

new file mode 100644
index 000000000000..a3e098b72fc9
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+void test_xdp_update_frag(void)
+{
+	const char *file = "./test_xdp_update_frags.o";
+	__u32 duration, retval, size;
+	struct bpf_object *obj;
+	int err, prog_fd;
+	__u8 *buf;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	buf = malloc(128);
+	if (CHECK(!buf, "malloc()", "error:%s\n", strerror(errno)))
+		return;
+
+	memset(buf, 0, 128);
+
+	err = bpf_prog_test_run(prog_fd, 1, buf, 128,
+				buf, &size, &retval, &duration);
+	free(buf);
+
+	CHECK(err || retval != XDP_DROP,
+	      "128b", "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	buf = malloc(9000);
+	if (CHECK(!buf, "malloc()", "error:%s\n", strerror(errno)))
+		return;
+
+	memset(buf, 0, 9000);
+	buf[5000] = 0xaa; /* marker at offset 5000 (frag0) */
+
+	err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+				buf, &size, &retval, &duration);
+
+	/* test_xdp_update_frags: buf[5000]: 0xaa -> 0xbb */
+	CHECK(err || retval != XDP_PASS || buf[5000] != 0xbb,
+	      "9000b", "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	free(buf);
+
+	bpf_object__close(obj);
+}
+
+void test_xdp_adjust_data(void)
+{
+	if (test__start_subtest("xdp_adjust_data"))
+		test_xdp_update_frag();
+}

41 lines not on this page · raw message