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

Pull networking updates from David Miller:

 1) Add VF IPSEC offload support in ixgbe, from Shannon Nelson.

 2) Add zero-copy AF_XDP support to i40e, from Björn Töpel.

 3) All in-tree drivers are converted to {g,s}et_link_ksettings() so we
    can get rid of the {g,s}et_settings ethtool callbacks, from Michal
    Kubecek.

 4) Add software timestamping to veth driver, from Michael Walle.

 5) More work to make packet classifiers and actions lockless, from Vlad
    Buslov.

 6) Support sticky FDB entries in bridge, from Nikolay Aleksandrov.

 7) Add ipv6 version of IP_MULTICAST_ALL sockopt, from Andre Naujoks.

 8) Support batching of XDP buffers in vhost_net, from Jason Wang.

 9) Add flow dissector BPF hook, from Petar Penkov.

10) i40e vf --> generic iavf conversion, from Jesse Brandeburg.

11) Add NLA_REJECT netlink attribute policy type, to signal when users
    provide attributes in situations which don't make sense. From
    Johannes Berg.

12) Switch TCP and fair-queue scheduler over to earliest departure time
    model. From Eric Dumazet.

13) Improve guest receive performance by doing rx busy polling in tx
    path of vhost networking driver, from Tonghao Zhang.

14) Add per-cgroup local storage to bpf

15) Add reference tracking to BPF, from Joe Stringer. The verifier can
    now make sure that references taken to objects are properly released
    by the program.

16) Support in-place encryption in TLS, from Vakul Garg.

17) Add new taprio packet scheduler, from Vinicius Costa Gomes.

18) Lots of selftests additions, too numerous to mention one by one here
    but all of which are very much appreciated.

19) Support offloading of eBPF programs containing BPF to BPF calls in
    nfp driver, frm Quentin Monnet.

20) Move dpaa2_ptp driver out of staging, from Yangbo Lu.

21) Lots of u32 classifier cleanups and simplifications, from Al Viro.

22) Add new strict versions of netlink message parsers, and enable them
    for some situations. From David Ahern.

23) Evict neighbour entries on carrier down, also from David Ahern.

24) Support BPF sk_msg verdict programs with kTLS, from Daniel Borkmann
    and John Fastabend.

25) Add support for filtering route dumps, from David Ahern.

26) New igc Intel driver for 2.5G parts, from Sasha Neftin et al.

27) Allow vxlan enslavement to bridges in mlxsw driver, from Ido
    Schimmel.

28) Add queue and stack map types to eBPF, from Mauricio Vasquez B.

29) Add back byte-queue-limit support to r8169, with all the bug fixes
    in other areas of the driver it works now! From Florian Westphal and
    Heiner Kallweit.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2147 commits)
  tcp: add tcp_reset_xmit_timer() helper
  qed: Fix static checker warning
  Revert "be2net: remove desc field from be_eq_obj"
  Revert "net: simplify sock_poll_wait"
  net: socionext: Reset tx queue in ndo_stop
  net: socionext: Add dummy PHY register read in phy_write()
  net: socionext: Stop PHY before resetting netsec
  net: stmmac: Set OWN bit for jumbo frames
  arm64: dts: stratix10: Support Ethernet Jumbo frame
  tls: Add maintainers
  net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode
  octeontx2-af: Support for NIXLF's UCAST/PROMISC/ALLMULTI modes
  octeontx2-af: Support for setting MAC address
  octeontx2-af: Support for changing RSS algorithm
  octeontx2-af: NIX Rx flowkey configuration for RSS
  octeontx2-af: Install ucast and bcast pkt forwarding rules
  octeontx2-af: Add LMAC channel info to NIXLF_ALLOC response
  octeontx2-af: NPC MCAM and LDATA extract minimal configuration
  octeontx2-af: Enable packet length and csum validation
  octeontx2-af: Support for VTAG strip and capture
  ...

1 files changed, 67 insertions, 39 deletions

diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index bfe2dbea480b..a264cf2accd0 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -32,37 +32,49 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 {
 	unsigned long flags;
 
-	if (xs->dev) {
-		spin_lock_irqsave(&umem->xsk_list_lock, flags);
-		list_del_rcu(&xs->list);
-		spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
-
-		if (umem->zc)
-			synchronize_net();
-	}
+	spin_lock_irqsave(&umem->xsk_list_lock, flags);
+	list_del_rcu(&xs->list);
+	spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
 }
 
-int xdp_umem_query(struct net_device *dev, u16 queue_id)
+/* The umem is stored both in the _rx struct and the _tx struct as we do
+ * not know if the device has more tx queues than rx, or the opposite.
+ * This might also change during run time.
+ */
+static void xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
+				u16 queue_id)
 {
-	struct netdev_bpf bpf;
+	if (queue_id < dev->real_num_rx_queues)
+		dev->_rx[queue_id].umem = umem;
+	if (queue_id < dev->real_num_tx_queues)
+		dev->_tx[queue_id].umem = umem;
+}
 
-	ASSERT_RTNL();
+struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
+				       u16 queue_id)
+{
+	if (queue_id < dev->real_num_rx_queues)
+		return dev->_rx[queue_id].umem;
+	if (queue_id < dev->real_num_tx_queues)
+		return dev->_tx[queue_id].umem;
 
-	memset(&bpf, 0, sizeof(bpf));
-	bpf.command = XDP_QUERY_XSK_UMEM;
-	bpf.xsk.queue_id = queue_id;
+	return NULL;
+}
 
-	if (!dev->netdev_ops->ndo_bpf)
-		return 0;
-	return dev->netdev_ops->ndo_bpf(dev, &bpf) ?: !!bpf.xsk.umem;
+static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id)
+{
+	if (queue_id < dev->real_num_rx_queues)
+		dev->_rx[queue_id].umem = NULL;
+	if (queue_id < dev->real_num_tx_queues)
+		dev->_tx[queue_id].umem = NULL;
 }
 
 int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
-			u32 queue_id, u16 flags)
+			u16 queue_id, u16 flags)
 {
 	bool force_zc, force_copy;
 	struct netdev_bpf bpf;
-	int err;
+	int err = 0;
 
 	force_zc = flags & XDP_ZEROCOPY;
 	force_copy = flags & XDP_COPY;
@@ -70,19 +82,23 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	if (force_zc && force_copy)
 		return -EINVAL;
 
-	if (force_copy)
-		return 0;
-
-	if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit)
-		return force_zc ? -EOPNOTSUPP : 0; /* fail or fallback */
+	rtnl_lock();
+	if (xdp_get_umem_from_qid(dev, queue_id)) {
+		err = -EBUSY;
+		goto out_rtnl_unlock;
+	}
 
-	bpf.command = XDP_QUERY_XSK_UMEM;
+	xdp_reg_umem_at_qid(dev, umem, queue_id);
+	umem->dev = dev;
+	umem->queue_id = queue_id;
+	if (force_copy)
+		/* For copy-mode, we are done. */
+		goto out_rtnl_unlock;
 
-	rtnl_lock();
-	err = xdp_umem_query(dev, queue_id);
-	if (err) {
-		err = err < 0 ? -EOPNOTSUPP : -EBUSY;
-		goto err_rtnl_unlock;
+	if (!dev->netdev_ops->ndo_bpf ||
+	    !dev->netdev_ops->ndo_xsk_async_xmit) {
+		err = -EOPNOTSUPP;
+		goto err_unreg_umem;
 	}
 
 	bpf.command = XDP_SETUP_XSK_UMEM;
@@ -91,18 +107,20 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 
 	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
 	if (err)
-		goto err_rtnl_unlock;
+		goto err_unreg_umem;
 	rtnl_unlock();
 
 	dev_hold(dev);
-	umem->dev = dev;
-	umem->queue_id = queue_id;
 	umem->zc = true;
 	return 0;
 
-err_rtnl_unlock:
+err_unreg_umem:
+	xdp_clear_umem_at_qid(dev, queue_id);
+	if (!force_zc)
+		err = 0; /* fallback to copy mode */
+out_rtnl_unlock:
 	rtnl_unlock();
-	return force_zc ? err : 0; /* fail or fallback */
+	return err;
 }
 
 static void xdp_umem_clear_dev(struct xdp_umem *umem)
@@ -110,7 +128,7 @@ static void xdp_umem_clear_dev(struct xdp_umem *umem)
 	struct netdev_bpf bpf;
 	int err;
 
-	if (umem->dev) {
+	if (umem->zc) {
 		bpf.command = XDP_SETUP_XSK_UMEM;
 		bpf.xsk.umem = NULL;
 		bpf.xsk.queue_id = umem->queue_id;
@@ -121,9 +139,17 @@ static void xdp_umem_clear_dev(struct xdp_umem *umem)
 
 		if (err)
 			WARN(1, "failed to disable umem!\n");
+	}
+
+	if (umem->dev) {
+		rtnl_lock();
+		xdp_clear_umem_at_qid(umem->dev, umem->queue_id);
+		rtnl_unlock();
+	}
 
+	if (umem->zc) {
 		dev_put(umem->dev);
-		umem->dev = NULL;
+		umem->zc = false;
 	}
 }
 
@@ -167,6 +193,8 @@ static void xdp_umem_release(struct xdp_umem *umem)
 		umem->cq = NULL;
 	}
 
+	xsk_reuseq_destroy(umem);
+
 	xdp_umem_unpin_pages(umem);
 
 	task = get_pid_task(umem->pid, PIDTYPE_PID);
@@ -314,8 +342,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 
 	umem->pid = get_task_pid(current, PIDTYPE_PID);
 	umem->address = (unsigned long)addr;
-	umem->props.chunk_mask = ~((u64)chunk_size - 1);
-	umem->props.size = size;
+	umem->chunk_mask = ~((u64)chunk_size - 1);
+	umem->size = size;
 	umem->headroom = headroom;
 	umem->chunk_size_nohr = chunk_size - headroom;
 	umem->npgs = size / PAGE_SIZE;