Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Support IPV6 RA Captive Portal Identifier, from Maciej Żenczykowski.

 2) Use bio_vec in the networking instead of custom skb_frag_t, from
    Matthew Wilcox.

 3) Make use of xmit_more in r8169 driver, from Heiner Kallweit.

 4) Add devmap_hash to xdp, from Toke Høiland-Jørgensen.

 5) Support all variants of 5750X bnxt_en chips, from Michael Chan.

 6) More RTNL avoidance work in the core and mlx5 driver, from Vlad
    Buslov.

 7) Add TCP syn cookies bpf helper, from Petar Penkov.

 8) Add 'nettest' to selftests and use it, from David Ahern.

 9) Add extack support to drop_monitor, add packet alert mode and
    support for HW drops, from Ido Schimmel.

10) Add VLAN offload to stmmac, from Jose Abreu.

11) Lots of devm_platform_ioremap_resource() conversions, from
    YueHaibing.

12) Add IONIC driver, from Shannon Nelson.

13) Several kTLS cleanups, from Jakub Kicinski.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1930 commits)
  mlxsw: spectrum_buffers: Add the ability to query the CPU port's shared buffer
  mlxsw: spectrum: Register CPU port with devlink
  mlxsw: spectrum_buffers: Prevent changing CPU port's configuration
  net: ena: fix incorrect update of intr_delay_resolution
  net: ena: fix retrieval of nonadaptive interrupt moderation intervals
  net: ena: fix update of interrupt moderation register
  net: ena: remove all old adaptive rx interrupt moderation code from ena_com
  net: ena: remove ena_restore_ethtool_params() and relevant fields
  net: ena: remove old adaptive interrupt moderation code from ena_netdev
  net: ena: remove code duplication in ena_com_update_nonadaptive_moderation_interval _*()
  net: ena: enable the interrupt_moderation in driver_supported_features
  net: ena: reimplement set/get_coalesce()
  net: ena: switch to dim algorithm for rx adaptive interrupt moderation
  net: ena: add intr_moder_rx_interval to struct ena_com_dev and use it
  net: phy: adin: implement Energy Detect Powerdown mode via phy-tunable
  ethtool: implement Energy Detect Powerdown support via phy-tunable
  xen-netfront: do not assume sk_buff_head list is empty in error handling
  s390/ctcm: Delete unnecessary checks before the macro call “dev_kfree_skb”
  net: ena: don't wake up tx queue when down
  drop_monitor: Better sanitize notified packets
  ...

3 files changed, 98 insertions, 31 deletions

diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 9d864ebeb7b3..261521d286d6 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -77,11 +77,11 @@ struct hvs_send_buf {
 					 VMBUS_PKT_TRAILER_SIZE)
 
 union hvs_service_id {
-	uuid_le	srv_id;
+	guid_t	srv_id;
 
 	struct {
 		unsigned int svm_port;
-		unsigned char b[sizeof(uuid_le) - sizeof(unsigned int)];
+		unsigned char b[sizeof(guid_t) - sizeof(unsigned int)];
 	};
 };
 
@@ -89,8 +89,8 @@ union hvs_service_id {
 struct hvsock {
 	struct vsock_sock *vsk;
 
-	uuid_le vm_srv_id;
-	uuid_le host_srv_id;
+	guid_t vm_srv_id;
+	guid_t host_srv_id;
 
 	struct vmbus_channel *chan;
 	struct vmpacket_descriptor *recv_desc;
@@ -159,21 +159,21 @@ struct hvsock {
 #define MIN_HOST_EPHEMERAL_PORT		(MAX_HOST_LISTEN_PORT + 1)
 
 /* 00000000-facb-11e6-bd58-64006a7986d3 */
-static const uuid_le srv_id_template =
-	UUID_LE(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58,
-		0x64, 0x00, 0x6a, 0x79, 0x86, 0xd3);
+static const guid_t srv_id_template =
+	GUID_INIT(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58,
+		  0x64, 0x00, 0x6a, 0x79, 0x86, 0xd3);
 
-static bool is_valid_srv_id(const uuid_le *id)
+static bool is_valid_srv_id(const guid_t *id)
 {
-	return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(uuid_le) - 4);
+	return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(guid_t) - 4);
 }
 
-static unsigned int get_port_by_srv_id(const uuid_le *svr_id)
+static unsigned int get_port_by_srv_id(const guid_t *svr_id)
 {
 	return *((unsigned int *)svr_id);
 }
 
-static void hvs_addr_init(struct sockaddr_vm *addr, const uuid_le *svr_id)
+static void hvs_addr_init(struct sockaddr_vm *addr, const guid_t *svr_id)
 {
 	unsigned int port = get_port_by_srv_id(svr_id);
 
@@ -321,7 +321,7 @@ static void hvs_close_connection(struct vmbus_channel *chan)
 
 static void hvs_open_connection(struct vmbus_channel *chan)
 {
-	uuid_le *if_instance, *if_type;
+	guid_t *if_instance, *if_type;
 	unsigned char conn_from_host;
 
 	struct sockaddr_vm addr;
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 0815d1357861..082a30936690 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -307,6 +307,7 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
 			break;
 		}
 
+		pkt->buf_len = buf_len;
 		pkt->len = buf_len;
 
 		sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr));
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 6f1a8aff65c5..5bb70c692b1e 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -26,6 +26,9 @@
 /* How long to wait for graceful shutdown of a connection */
 #define VSOCK_CLOSE_TIMEOUT (8 * HZ)
 
+/* Threshold for detecting small packets to copy */
+#define GOOD_COPY_LEN  128
+
 static const struct virtio_transport *virtio_transport_get_ops(void)
 {
 	const struct vsock_transport *t = vsock_core_get_transport();
@@ -64,6 +67,9 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
 		pkt->buf = kmalloc(len, GFP_KERNEL);
 		if (!pkt->buf)
 			goto out_pkt;
+
+		pkt->buf_len = len;
+
 		err = memcpy_from_msg(pkt->buf, info->msg, len);
 		if (err)
 			goto out;
@@ -91,8 +97,17 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
 	struct virtio_vsock_pkt *pkt = opaque;
 	struct af_vsockmon_hdr *hdr;
 	struct sk_buff *skb;
+	size_t payload_len;
+	void *payload_buf;
+
+	/* A packet could be split to fit the RX buffer, so we can retrieve
+	 * the payload length from the header and the buffer pointer taking
+	 * care of the offset in the original packet.
+	 */
+	payload_len = le32_to_cpu(pkt->hdr.len);
+	payload_buf = pkt->buf + pkt->off;
 
-	skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + pkt->len,
+	skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len,
 			GFP_ATOMIC);
 	if (!skb)
 		return NULL;
@@ -132,8 +147,8 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
 
 	skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr));
 
-	if (pkt->len) {
-		skb_put_data(skb, pkt->buf, pkt->len);
+	if (payload_len) {
+		skb_put_data(skb, payload_buf, payload_len);
 	}
 
 	return skb;
@@ -166,8 +181,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 	vvs = vsk->trans;
 
 	/* we can send less than pkt_len bytes */
-	if (pkt_len > VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE)
-		pkt_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE;
+	if (pkt_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE)
+		pkt_len = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
 
 	/* virtio_transport_get_credit might return less than pkt_len credit */
 	pkt_len = virtio_transport_get_credit(vvs, pkt_len);
@@ -204,10 +219,11 @@ static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs,
 
 void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt)
 {
-	spin_lock_bh(&vvs->tx_lock);
+	spin_lock_bh(&vvs->rx_lock);
+	vvs->last_fwd_cnt = vvs->fwd_cnt;
 	pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt);
 	pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc);
-	spin_unlock_bh(&vvs->tx_lock);
+	spin_unlock_bh(&vvs->rx_lock);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt);
 
@@ -255,6 +271,7 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 	struct virtio_vsock_sock *vvs = vsk->trans;
 	struct virtio_vsock_pkt *pkt;
 	size_t bytes, total = 0;
+	u32 free_space;
 	int err = -EFAULT;
 
 	spin_lock_bh(&vvs->rx_lock);
@@ -285,11 +302,24 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 			virtio_transport_free_pkt(pkt);
 		}
 	}
+
+	free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt);
+
 	spin_unlock_bh(&vvs->rx_lock);
 
-	/* Send a credit pkt to peer */
-	virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM,
-					    NULL);
+	/* To reduce the number of credit update messages,
+	 * don't update credits as long as lots of space is available.
+	 * Note: the limit chosen here is arbitrary. Setting the limit
+	 * too high causes extra messages. Too low causes transmitter
+	 * stalls. As stalls are in theory more expensive than extra
+	 * messages, we set the limit to a high value. TODO: experiment
+	 * with different values.
+	 */
+	if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) {
+		virtio_transport_send_credit_update(vsk,
+						    VIRTIO_VSOCK_TYPE_STREAM,
+						    NULL);
+	}
 
 	return total;
 
@@ -841,24 +871,60 @@ destroy:
 	return err;
 }
 
+static void
+virtio_transport_recv_enqueue(struct vsock_sock *vsk,
+			      struct virtio_vsock_pkt *pkt)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	bool free_pkt = false;
+
+	pkt->len = le32_to_cpu(pkt->hdr.len);
+	pkt->off = 0;
+
+	spin_lock_bh(&vvs->rx_lock);
+
+	virtio_transport_inc_rx_pkt(vvs, pkt);
+
+	/* Try to copy small packets into the buffer of last packet queued,
+	 * to avoid wasting memory queueing the entire buffer with a small
+	 * payload.
+	 */
+	if (pkt->len <= GOOD_COPY_LEN && !list_empty(&vvs->rx_queue)) {
+		struct virtio_vsock_pkt *last_pkt;
+
+		last_pkt = list_last_entry(&vvs->rx_queue,
+					   struct virtio_vsock_pkt, list);
+
+		/* If there is space in the last packet queued, we copy the
+		 * new packet in its buffer.
+		 */
+		if (pkt->len <= last_pkt->buf_len - last_pkt->len) {
+			memcpy(last_pkt->buf + last_pkt->len, pkt->buf,
+			       pkt->len);
+			last_pkt->len += pkt->len;
+			free_pkt = true;
+			goto out;
+		}
+	}
+
+	list_add_tail(&pkt->list, &vvs->rx_queue);
+
+out:
+	spin_unlock_bh(&vvs->rx_lock);
+	if (free_pkt)
+		virtio_transport_free_pkt(pkt);
+}
+
 static int
 virtio_transport_recv_connected(struct sock *sk,
 				struct virtio_vsock_pkt *pkt)
 {
 	struct vsock_sock *vsk = vsock_sk(sk);
-	struct virtio_vsock_sock *vvs = vsk->trans;
 	int err = 0;
 
 	switch (le16_to_cpu(pkt->hdr.op)) {
 	case VIRTIO_VSOCK_OP_RW:
-		pkt->len = le32_to_cpu(pkt->hdr.len);
-		pkt->off = 0;
-
-		spin_lock_bh(&vvs->rx_lock);
-		virtio_transport_inc_rx_pkt(vvs, pkt);
-		list_add_tail(&pkt->list, &vvs->rx_queue);
-		spin_unlock_bh(&vvs->rx_lock);
-
+		virtio_transport_recv_enqueue(vsk, pkt);
 		sk->sk_data_ready(sk);
 		return err;
 	case VIRTIO_VSOCK_OP_CREDIT_UPDATE: