tgupdate: merge t/DO-NOT-MERGE-mptcp-enabled-by-default into t/upstream base

Author: matttbe

MAINTAINERS

@@ -16508,6 +16508,7 @@ F:	include/linux/netdev*
 F:	include/linux/netlink.h
 F:	include/linux/netpoll.h
 F:	include/linux/rtnetlink.h
+F:	include/linux/sctp.h
 F:	include/linux/seq_file_net.h
 F:	include/linux/skbuff*
 F:	include/net/
@@ -16524,6 +16525,7 @@ F:	include/uapi/linux/netdev*
 F:	include/uapi/linux/netlink.h
 F:	include/uapi/linux/netlink_diag.h
 F:	include/uapi/linux/rtnetlink.h
+F:	include/uapi/linux/sctp.h
 F:	lib/net_utils.c
 F:	lib/random32.c
 F:	net/

drivers/net/ethernet/intel/idpf/idpf_lib.c

@@ -2159,8 +2159,13 @@ static int idpf_open(struct net_device *netdev)
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
+	err = idpf_set_real_num_queues(vport);
+	if (err)
+		goto unlock;
+
 	err = idpf_vport_open(vport);
 
+unlock:
 	idpf_vport_ctrl_unlock(netdev);
 
 	return err;

drivers/net/ethernet/intel/idpf/idpf_txrx.c

@@ -3008,8 +3008,6 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 		return -EINVAL;
 
 	rsc_segments = DIV_ROUND_UP(skb->data_len, rsc_seg_len);
-	if (unlikely(rsc_segments == 1))
-		return 0;
 
 	NAPI_GRO_CB(skb)->count = rsc_segments;
 	skb_shinfo(skb)->gso_size = rsc_seg_len;
@@ -3072,6 +3070,7 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	idpf_rx_hash(rxq, skb, rx_desc, decoded);
 
 	skb->protocol = eth_type_trans(skb, rxq->netdev);
+	skb_record_rx_queue(skb, rxq->idx);
 
 	if (le16_get_bits(rx_desc->hdrlen_flags,
 			  VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M))
@@ -3080,8 +3079,6 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	csum_bits = idpf_rx_splitq_extract_csum_bits(rx_desc);
 	idpf_rx_csum(rxq, skb, csum_bits, decoded);
 
-	skb_record_rx_queue(skb, rxq->idx);
-
 	return 0;
 }
 

drivers/net/ethernet/intel/igc/igc_main.c

@@ -1096,6 +1096,7 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 		return -ENOMEM;
 	}
 
+	buffer->type = IGC_TX_BUFFER_TYPE_SKB;
 	buffer->skb = skb;
 	buffer->protocol = 0;
 	buffer->bytecount = skb->len;
@@ -2701,8 +2702,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 }
 
 static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
-					    struct xdp_buff *xdp)
+					    struct igc_xdp_buff *ctx)
 {
+	struct xdp_buff *xdp = &ctx->xdp;
 	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
@@ -2721,27 +2723,28 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
 		__skb_pull(skb, metasize);
 	}
 
+	if (ctx->rx_ts) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV;
+		skb_hwtstamps(skb)->netdev_data = ctx->rx_ts;
+	}
+
 	return skb;
 }
 
 static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
 				union igc_adv_rx_desc *desc,
-				struct xdp_buff *xdp,
-				ktime_t timestamp)
+				struct igc_xdp_buff *ctx)
 {
 	struct igc_ring *ring = q_vector->rx.ring;
 	struct sk_buff *skb;
 
-	skb = igc_construct_skb_zc(ring, xdp);
+	skb = igc_construct_skb_zc(ring, ctx);
 	if (!skb) {
 		ring->rx_stats.alloc_failed++;
 		set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags);
 		return;
 	}
 
-	if (timestamp)
-		skb_hwtstamps(skb)->hwtstamp = timestamp;
-
 	if (igc_cleanup_headers(ring, desc, skb))
 		return;
 
@@ -2777,7 +2780,6 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		union igc_adv_rx_desc *desc;
 		struct igc_rx_buffer *bi;
 		struct igc_xdp_buff *ctx;
-		ktime_t timestamp = 0;
 		unsigned int size;
 		int res;
 
@@ -2807,6 +2809,8 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 			 */
 			bi->xdp->data_meta += IGC_TS_HDR_LEN;
 			size -= IGC_TS_HDR_LEN;
+		} else {
+			ctx->rx_ts = NULL;
 		}
 
 		bi->xdp->data_end = bi->xdp->data + size;
@@ -2815,7 +2819,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		res = __igc_xdp_run_prog(adapter, prog, bi->xdp);
 		switch (res) {
 		case IGC_XDP_PASS:
-			igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp);
+			igc_dispatch_skb_zc(q_vector, desc, ctx);
 			fallthrough;
 		case IGC_XDP_CONSUMED:
 			xsk_buff_free(bi->xdp);

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -2105,7 +2105,7 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring,
 		/* hand second half of page back to the ring */
 		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
-		if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) {
+		if (skb && IXGBE_CB(skb)->dma == rx_buffer->dma) {
 			/* the page has been released from the ring */
 			IXGBE_CB(skb)->page_released = true;
 		} else {

drivers/net/ethernet/ti/am65-cpsw-nuss.c

@@ -828,21 +828,30 @@ static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn,
 static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct am65_cpsw_tx_chn *tx_chn = data;
+	enum am65_cpsw_tx_buf_type buf_type;
 	struct cppi5_host_desc_t *desc_tx;
+	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
 	void **swdata;
 
 	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	skb = *(swdata);
-	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
+	buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
+	if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
+		skb = *(swdata);
+		dev_kfree_skb_any(skb);
+	} else {
+		xdpf = *(swdata);
+		xdp_return_frame(xdpf);
+	}
 
-	dev_kfree_skb_any(skb);
+	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
 }
 
 static struct sk_buff *am65_cpsw_build_skb(void *page_addr,
 					   struct net_device *ndev,
-					   unsigned int len)
+					   unsigned int len,
+					   unsigned int headroom)
 {
 	struct sk_buff *skb;
 
@@ -852,7 +861,7 @@ static struct sk_buff *am65_cpsw_build_skb(void *page_addr,
 	if (unlikely(!skb))
 		return NULL;
 
-	skb_reserve(skb, AM65_CPSW_HEADROOM);
+	skb_reserve(skb, headroom);
 	skb->dev = ndev;
 
 	return skb;
@@ -1169,9 +1178,11 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 	struct xdp_frame *xdpf;
 	struct bpf_prog *prog;
 	struct page *page;
+	int pkt_len;
 	u32 act;
 	int err;
 
+	pkt_len = *len;
 	prog = READ_ONCE(port->xdp_prog);
 	if (!prog)
 		return AM65_CPSW_XDP_PASS;
@@ -1189,8 +1200,10 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 		netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
 
 		xdpf = xdp_convert_buff_to_frame(xdp);
-		if (unlikely(!xdpf))
+		if (unlikely(!xdpf)) {
+			ndev->stats.tx_dropped++;
 			goto drop;
+		}
 
 		__netif_tx_lock(netif_txq, cpu);
 		err = am65_cpsw_xdp_tx_frame(ndev, tx_chn, xdpf,
@@ -1199,14 +1212,14 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 		if (err)
 			goto drop;
 
-		dev_sw_netstats_tx_add(ndev, 1, *len);
+		dev_sw_netstats_rx_add(ndev, pkt_len);
 		ret = AM65_CPSW_XDP_CONSUMED;
 		goto out;
 	case XDP_REDIRECT:
 		if (unlikely(xdp_do_redirect(ndev, xdp, prog)))
 			goto drop;
 
-		dev_sw_netstats_rx_add(ndev, *len);
+		dev_sw_netstats_rx_add(ndev, pkt_len);
 		ret = AM65_CPSW_XDP_REDIRECT;
 		goto out;
 	default:
@@ -1315,16 +1328,8 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 	dev_dbg(dev, "%s rx csum_info:%#x\n", __func__, csum_info);
 
 	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
-
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
-	skb = am65_cpsw_build_skb(page_addr, ndev,
-				  AM65_CPSW_MAX_PACKET_SIZE);
-	if (unlikely(!skb)) {
-		new_page = page;
-		goto requeue;
-	}
-
 	if (port->xdp_prog) {
 		xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq[flow->id]);
 		xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM,
@@ -1334,9 +1339,16 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 		if (*xdp_state != AM65_CPSW_XDP_PASS)
 			goto allocate;
 
-		/* Compute additional headroom to be reserved */
-		headroom = (xdp.data - xdp.data_hard_start) - skb_headroom(skb);
-		skb_reserve(skb, headroom);
+		headroom = xdp.data - xdp.data_hard_start;
+	} else {
+		headroom = AM65_CPSW_HEADROOM;
+	}
+
+	skb = am65_cpsw_build_skb(page_addr, ndev,
+				  AM65_CPSW_MAX_PACKET_SIZE, headroom);
+	if (unlikely(!skb)) {
+		new_page = page;
+		goto requeue;
 	}
 
 	ndev_priv = netdev_priv(ndev);

net/vmw_vsock/af_vsock.c

@@ -824,13 +824,19 @@ static void __vsock_release(struct sock *sk, int level)
 	 */
 	lock_sock_nested(sk, level);
 
-	sock_orphan(sk);
+	/* Indicate to vsock_remove_sock() that the socket is being released and
+	 * can be removed from the bound_table. Unlike transport reassignment
+	 * case, where the socket must remain bound despite vsock_remove_sock()
+	 * being called from the transport release() callback.
+	 */
+	sock_set_flag(sk, SOCK_DEAD);
 
 	if (vsk->transport)
 		vsk->transport->release(vsk);
 	else if (sock_type_connectible(sk->sk_type))
 		vsock_remove_sock(vsk);
 
+	sock_orphan(sk);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	skb_queue_purge(&sk->sk_receive_queue);

tools/testing/vsock/vsock_test.c

@@ -1788,6 +1788,42 @@ static void test_stream_connect_retry_server(const struct test_opts *opts)
 	close(fd);
 }
 
+static void test_stream_linger_client(const struct test_opts *opts)
+{
+	struct linger optval = {
+		.l_onoff = 1,
+		.l_linger = 1
+	};
+	int fd;
+
+	fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	if (setsockopt(fd, SOL_SOCKET, SO_LINGER, &optval, sizeof(optval))) {
+		perror("setsockopt(SO_LINGER)");
+		exit(EXIT_FAILURE);
+	}
+
+	close(fd);
+}
+
+static void test_stream_linger_server(const struct test_opts *opts)
+{
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	vsock_wait_remote_close(fd);
+	close(fd);
+}
+
 static struct test_case test_cases[] = {
 	{
 		.name = "SOCK_STREAM connection reset",
@@ -1943,6 +1979,11 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_connect_retry_client,
 		.run_server = test_stream_connect_retry_server,
 	},
+	{
+		.name = "SOCK_STREAM SO_LINGER null-ptr-deref",
+		.run_client = test_stream_linger_client,
+		.run_server = test_stream_linger_server,
+	},
 	{},
 };