Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-01-24

We've added 80 non-merge commits during the last 14 day(s) which contain
a total of 128 files changed, 4990 insertions(+), 895 deletions(-).

The main changes are:

1) Add XDP multi-buffer support and implement it for the mvneta driver,
   from Lorenzo Bianconi, Eelco Chaudron and Toke Høiland-Jørgensen.

2) Add unstable conntrack lookup helpers for BPF by using the BPF kfunc
   infra, from Kumar Kartikeya Dwivedi.

3) Extend BPF cgroup programs to export custom ret value to userspace via
   two helpers bpf_get_retval() and bpf_set_retval(), from YiFei Zhu.

4) Add support for AF_UNIX iterator batching, from Kuniyuki Iwashima.

5) Complete missing UAPI BPF helper description and change bpf_doc.py script
   to enforce consistent & complete helper documentation, from Usama Arif.

6) Deprecate libbpf's legacy BPF map definitions and streamline XDP APIs to
   follow tc-based APIs, from Andrii Nakryiko.

7) Support BPF_PROG_QUERY for BPF programs attached to sockmap, from Di Zhu.

8) Deprecate libbpf's bpf_map__def() API and replace users with proper getters
   and setters, from Christy Lee.

9) Extend libbpf's btf__add_btf() with an additional hashmap for strings to
   reduce overhead, from Kui-Feng Lee.

10) Fix bpftool and libbpf error handling related to libbpf's hashmap__new()
    utility function, from Mauricio Vásquez.

11) Add support to BTF program names in bpftool's program dump, from Raman Shukhau.

12) Fix resolve_btfids build to pick up host flags, from Connor O'Brien.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (80 commits)
  selftests, bpf: Do not yet switch to new libbpf XDP APIs
  selftests, xsk: Fix rx_full stats test
  bpf: Fix flexible_array.cocci warnings
  xdp: disable XDP_REDIRECT for xdp frags
  bpf: selftests: add CPUMAP/DEVMAP selftests for xdp frags
  bpf: selftests: introduce bpf_xdp_{load,store}_bytes selftest
  net: xdp: introduce bpf_xdp_pointer utility routine
  bpf: generalise tail call map compatibility check
  libbpf: Add SEC name for xdp frags programs
  bpf: selftests: update xdp_adjust_tail selftest to include xdp frags
  bpf: test_run: add xdp_shared_info pointer in bpf_test_finish signature
  bpf: introduce frags support to bpf_prog_test_run_xdp()
  bpf: move user_size out of bpf_test_init
  bpf: add frags support to xdp copy helpers
  bpf: add frags support to the bpf_xdp_adjust_tail() API
  bpf: introduce bpf_xdp_get_buff_len helper
  net: mvneta: enable jumbo frames if the loaded XDP program support frags
  bpf: introduce BPF_F_XDP_HAS_FRAGS flag in prog_flags loading the ebpf program
  net: mvneta: add frags support to XDP_TX
  xdp: add frags support to xdp_return_{buff/frame}
  ...
====================

Link: https://lore.kernel.org/r/20220124221235.18993-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 124 insertions, 80 deletions

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 83c8908f0cc7..309bd3e97ea0 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1884,8 +1884,8 @@ 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
@@ -2060,61 +2060,106 @@ 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_has_frags(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);
 }
 
 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_has_frags(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
@@ -2123,8 +2168,8 @@ 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);
@@ -2136,10 +2181,10 @@ 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);
@@ -2178,11 +2223,11 @@ 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++;
 	}
 
@@ -2205,7 +2250,6 @@ 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;
 
@@ -2226,7 +2270,7 @@ 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;
@@ -2237,7 +2281,7 @@ 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(pp->dev, prog, act);
@@ -2246,7 +2290,7 @@ 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;
@@ -2269,7 +2313,6 @@ 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;
@@ -2289,11 +2332,9 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 
 	/* Prefetch header */
 	prefetch(data);
+	xdp_buff_clear_frags_flag(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
@@ -2301,9 +2342,9 @@ 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;
@@ -2321,25 +2362,25 @@ 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_has_frags(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);
 		__skb_frag_set_page(frag, page);
+
+		if (!xdp_buff_has_frags(xdp)) {
+			sinfo->xdp_frags_size = *size;
+			xdp_buff_set_frags_flag(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) {
-		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;
 }
 
@@ -2348,8 +2389,11 @@ 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;
+
+	if (unlikely(xdp_buff_has_frags(xdp)))
+		num_frags = sinfo->nr_frags;
 
 	skb = build_skb(xdp->data_hard_start, PAGE_SIZE);
 	if (!skb)
@@ -2361,13 +2405,11 @@ 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);
 
-	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_has_frags(xdp)))
+		xdp_update_skb_shared_info(skb, num_frags,
+					   sinfo->xdp_frags_size,
+					   num_frags * xdp->frame_sz,
+					   xdp_buff_is_frag_pfmemalloc(xdp));
 
 	return skb;
 }
@@ -2379,7 +2421,6 @@ 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;
@@ -2388,8 +2429,6 @@ 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);
 
@@ -2431,7 +2470,7 @@ 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))
@@ -2439,7 +2478,7 @@ 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;
 		}
 
@@ -2451,7 +2490,7 @@ 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++;
@@ -2468,11 +2507,10 @@ 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();
@@ -3260,7 +3298,8 @@ 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;
 
@@ -3740,6 +3779,7 @@ 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)) {
@@ -3748,8 +3788,11 @@ 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_has_frags &&
+	    mtu > MVNETA_MAX_RX_BUF_SIZE) {
+		netdev_info(dev, "Illegal MTU %d for XDP prog without frags\n",
+			    mtu);
+
 		return -EINVAL;
 	}
 
@@ -4490,8 +4533,9 @@ 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_has_frags &&
+	    dev->mtu > MVNETA_MAX_RX_BUF_SIZE) {
+		NL_SET_ERR_MSG_MOD(extack, "prog does not support XDP frags");
 		return -EOPNOTSUPP;
 	}