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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 13 insertions, 40 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 120c68f78951..d6d352a6e6ea 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -960,14 +960,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 {
 	enum i40e_latency_range new_latency_range = rc->latency_range;
 	u32 new_itr = rc->itr;
-	int bytes_per_int;
+	int bytes_per_usec;
 	unsigned int usecs, estimated_usecs;
 
 	if (rc->total_packets == 0 || !rc->itr)
 		return false;
 
 	usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
-	bytes_per_int = rc->total_bytes / usecs;
+	bytes_per_usec = rc->total_bytes / usecs;
 
 	/* The calculations in this algorithm depend on interrupts actually
 	 * firing at the ITR rate. This may not happen if the packet rate is
@@ -993,18 +993,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	 */
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
-		if (bytes_per_int > 10)
+		if (bytes_per_usec > 10)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	case I40E_LOW_LATENCY:
-		if (bytes_per_int > 20)
+		if (bytes_per_usec > 20)
 			new_latency_range = I40E_BULK_LATENCY;
-		else if (bytes_per_int <= 10)
+		else if (bytes_per_usec <= 10)
 			new_latency_range = I40E_LOWEST_LATENCY;
 		break;
 	case I40E_BULK_LATENCY:
 	default:
-		if (bytes_per_int <= 20)
+		if (bytes_per_usec <= 20)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	}
@@ -2117,6 +2117,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		if (!skb) {
 			xdp.data = page_address(rx_buffer->page) +
 				   rx_buffer->page_offset;
+			xdp_set_data_meta_invalid(&xdp);
 			xdp.data_hard_start = xdp.data -
 					      i40e_rx_offset(rx_ring);
 			xdp.data_end = xdp.data + size;
@@ -2211,9 +2212,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr)
 	u32 val;
 
 	val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
-	      /* Don't clear PBA because that can cause lost interrupts that
-	       * came in while we were cleaning/polling
-	       */
+	      I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
 	      (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
 	      (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT);
 
@@ -2250,7 +2249,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 
 	/* If we don't have MSIX, then we only need to re-enable icr0 */
 	if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) {
-		i40e_irq_dynamic_enable_icr0(vsi->back, false);
+		i40e_irq_dynamic_enable_icr0(vsi->back);
 		return;
 	}
 
@@ -3176,38 +3175,12 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	/* write last descriptor with EOP bit */
 	td_cmd |= I40E_TX_DESC_CMD_EOP;
 
-	/* We can OR these values together as they both are checked against
-	 * 4 below and at this point desc_count will be used as a boolean value
-	 * after this if/else block.
+	/* We OR these values together to check both against 4 (WB_STRIDE)
+	 * below. This is safe since we don't re-use desc_count afterwards.
 	 */
 	desc_count |= ++tx_ring->packet_stride;
 
-	/* Algorithm to optimize tail and RS bit setting:
-	 * if queue is stopped
-	 *	mark RS bit
-	 *	reset packet counter
-	 * else if xmit_more is supported and is true
-	 *	advance packet counter to 4
-	 *	reset desc_count to 0
-	 *
-	 * if desc_count >= 4
-	 *	mark RS bit
-	 *	reset packet counter
-	 * if desc_count > 0
-	 *	update tail
-	 *
-	 * Note: If there are less than 4 descriptors
-	 * pending and interrupts were disabled the service task will
-	 * trigger a force WB.
-	 */
-	if (netif_xmit_stopped(txring_txq(tx_ring))) {
-		goto do_rs;
-	} else if (skb->xmit_more) {
-		/* set stride to arm on next packet and reset desc_count */
-		tx_ring->packet_stride = WB_STRIDE;
-		desc_count = 0;
-	} else if (desc_count >= WB_STRIDE) {
-do_rs:
+	if (desc_count >= WB_STRIDE) {
 		/* write last descriptor with RS bit set */
 		td_cmd |= I40E_TX_DESC_CMD_RS;
 		tx_ring->packet_stride = 0;
@@ -3228,7 +3201,7 @@ do_rs:
 	first->next_to_watch = tx_desc;
 
 	/* notify HW of packet */
-	if (desc_count) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail