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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 80 insertions, 25 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 7bea09363b42..979af197f8a3 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -63,6 +63,64 @@ u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg)
 }
 
 /**
+ * ice_is_pfc_causing_hung_q
+ * @pf: pointer to PF structure
+ * @txqueue: Tx queue which is supposedly hung queue
+ *
+ * find if PFC is causing the hung queue, if yes return true else false
+ */
+bool ice_is_pfc_causing_hung_q(struct ice_pf *pf, unsigned int txqueue)
+{
+	u8 num_tcs = 0, i, tc, up_mapped_tc, up_in_tc = 0;
+	u64 ref_prio_xoff[ICE_MAX_UP];
+	struct ice_vsi *vsi;
+	u32 up2tc;
+
+	vsi = ice_get_main_vsi(pf);
+	if (!vsi)
+		return false;
+
+	ice_for_each_traffic_class(i)
+		if (vsi->tc_cfg.ena_tc & BIT(i))
+			num_tcs++;
+
+	/* first find out the TC to which the hung queue belongs to */
+	for (tc = 0; tc < num_tcs - 1; tc++)
+		if (ice_find_q_in_range(vsi->tc_cfg.tc_info[tc].qoffset,
+					vsi->tc_cfg.tc_info[tc + 1].qoffset,
+					txqueue))
+			break;
+
+	/* Build a bit map of all UPs associated to the suspect hung queue TC,
+	 * so that we check for its counter increment.
+	 */
+	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
+	for (i = 0; i < ICE_MAX_UP; i++) {
+		up_mapped_tc = (up2tc >> (i * 3)) & 0x7;
+		if (up_mapped_tc == tc)
+			up_in_tc |= BIT(i);
+	}
+
+	/* Now that we figured out that hung queue is PFC enabled, still the
+	 * Tx timeout can be legitimate. So to make sure Tx timeout is
+	 * absolutely caused by PFC storm, check if the counters are
+	 * incrementing.
+	 */
+	for (i = 0; i < ICE_MAX_UP; i++)
+		if (up_in_tc & BIT(i))
+			ref_prio_xoff[i] = pf->stats.priority_xoff_rx[i];
+
+	ice_update_dcb_stats(pf);
+
+	for (i = 0; i < ICE_MAX_UP; i++)
+		if (up_in_tc & BIT(i))
+			if (pf->stats.priority_xoff_rx[i] > ref_prio_xoff[i])
+				return true;
+
+	return false;
+}
+
+/**
  * ice_dcb_get_mode - gets the DCB mode
  * @port_info: pointer to port info structure
  * @host: if set it's HOST if not it's MANAGED
@@ -526,16 +584,21 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked)
  */
 static bool ice_dcb_tc_contig(u8 *prio_table)
 {
-	u8 max_tc = 0;
+	bool found_empty = false;
+	u8 used_tc = 0;
 	int i;
 
-	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++) {
-		u8 cur_tc = prio_table[i];
+	/* Create a bitmap of used TCs */
+	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++)
+		used_tc |= BIT(prio_table[i]);
 
-		if (cur_tc > max_tc)
-			return false;
-		else if (cur_tc == max_tc)
-			max_tc++;
+	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++) {
+		if (used_tc & BIT(i)) {
+			if (found_empty)
+				return false;
+		} else {
+			found_empty = true;
+		}
 	}
 
 	return true;
@@ -728,39 +791,31 @@ void ice_update_dcb_stats(struct ice_pf *pf)
  * ice_tx_prepare_vlan_flags_dcb - prepare VLAN tagging for DCB
  * @tx_ring: ring to send buffer on
  * @first: pointer to struct ice_tx_buf
+ *
+ * This should not be called if the outer VLAN is software offloaded as the VLAN
+ * tag will already be configured with the correct ID and priority bits
  */
-int
+void
 ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,
 			      struct ice_tx_buf *first)
 {
 	struct sk_buff *skb = first->skb;
 
 	if (!test_bit(ICE_FLAG_DCB_ENA, tx_ring->vsi->back->flags))
-		return 0;
+		return;
 
 	/* Insert 802.1p priority into VLAN header */
-	if ((first->tx_flags & (ICE_TX_FLAGS_HW_VLAN | ICE_TX_FLAGS_SW_VLAN)) ||
+	if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN) ||
 	    skb->priority != TC_PRIO_CONTROL) {
 		first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M;
 		/* Mask the lower 3 bits to set the 802.1p priority */
 		first->tx_flags |= (skb->priority & 0x7) <<
 				   ICE_TX_FLAGS_VLAN_PR_S;
-		if (first->tx_flags & ICE_TX_FLAGS_SW_VLAN) {
-			struct vlan_ethhdr *vhdr;
-			int rc;
-
-			rc = skb_cow_head(skb, 0);
-			if (rc < 0)
-				return rc;
-			vhdr = (struct vlan_ethhdr *)skb->data;
-			vhdr->h_vlan_TCI = htons(first->tx_flags >>
-						 ICE_TX_FLAGS_VLAN_S);
-		} else {
-			first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
-		}
+		/* if this is not already set it means a VLAN 0 + priority needs
+		 * to be offloaded
+		 */
+		first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
 	}
-
-	return 0;
 }
 
 /**