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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 93 insertions, 127 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index af79211..f95ce9b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -47,8 +47,8 @@ static const char i40e_driver_string[] =
 #define DRV_KERN "-k"
 
 #define DRV_VERSION_MAJOR 2
-#define DRV_VERSION_MINOR 1
-#define DRV_VERSION_BUILD 14
+#define DRV_VERSION_MINOR 3
+#define DRV_VERSION_BUILD 2
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -1818,6 +1818,10 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 	num_tc_qps = qcount / numtc;
 	num_tc_qps = min_t(int, num_tc_qps, i40e_pf_get_max_q_per_tc(pf));
 
+	/* Do not allow use more TC queue pairs than MSI-X vectors exist */
+	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+		num_tc_qps = min_t(int, num_tc_qps, pf->num_lan_msix);
+
 	/* Setup queue offset/count for all TCs for given VSI */
 	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
 		/* See if the given TC is enabled for the given VSI */
@@ -4122,6 +4126,7 @@ static void i40e_vsi_map_rings_to_vectors(struct i40e_vsi *vsi)
 		num_ringpairs = DIV_ROUND_UP(qp_remaining, q_vectors - v_start);
 
 		q_vector->num_ringpairs = num_ringpairs;
+		q_vector->reg_idx = q_vector->v_idx + vsi->base_vector - 1;
 
 		q_vector->rx.count = 0;
 		q_vector->tx.count = 0;
@@ -4877,104 +4882,6 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
 #endif
 
 /**
- * i40e_detect_recover_hung_queue - Function to detect and recover hung_queue
- * @q_idx: TX queue number
- * @vsi: Pointer to VSI struct
- *
- * This function checks specified queue for given VSI. Detects hung condition.
- * We proactively detect hung TX queues by checking if interrupts are disabled
- * but there are pending descriptors.  If it appears hung, attempt to recover
- * by triggering a SW interrupt.
- **/
-static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
-{
-	struct i40e_ring *tx_ring = NULL;
-	struct i40e_pf	*pf;
-	u32 val, tx_pending;
-	int i;
-
-	pf = vsi->back;
-
-	/* now that we have an index, find the tx_ring struct */
-	for (i = 0; i < vsi->num_queue_pairs; i++) {
-		if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) {
-			if (q_idx == vsi->tx_rings[i]->queue_index) {
-				tx_ring = vsi->tx_rings[i];
-				break;
-			}
-		}
-	}
-
-	if (!tx_ring)
-		return;
-
-	/* Read interrupt register */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
-		val = rd32(&pf->hw,
-			   I40E_PFINT_DYN_CTLN(tx_ring->q_vector->v_idx +
-					       tx_ring->vsi->base_vector - 1));
-	else
-		val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
-
-	tx_pending = i40e_get_tx_pending(tx_ring);
-
-	/* Interrupts are disabled and TX pending is non-zero,
-	 * trigger the SW interrupt (don't wait). Worst case
-	 * there will be one extra interrupt which may result
-	 * into not cleaning any queues because queues are cleaned.
-	 */
-	if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK)))
-		i40e_force_wb(vsi, tx_ring->q_vector);
-}
-
-/**
- * i40e_detect_recover_hung - Function to detect and recover hung_queues
- * @pf:  pointer to PF struct
- *
- * LAN VSI has netdev and netdev has TX queues. This function is to check
- * each of those TX queues if they are hung, trigger recovery by issuing
- * SW interrupt.
- **/
-static void i40e_detect_recover_hung(struct i40e_pf *pf)
-{
-	struct net_device *netdev;
-	struct i40e_vsi *vsi;
-	unsigned int i;
-
-	/* Only for LAN VSI */
-	vsi = pf->vsi[pf->lan_vsi];
-
-	if (!vsi)
-		return;
-
-	/* Make sure, VSI state is not DOWN/RECOVERY_PENDING */
-	if (test_bit(__I40E_VSI_DOWN, vsi->back->state) ||
-	    test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state))
-		return;
-
-	/* Make sure type is MAIN VSI */
-	if (vsi->type != I40E_VSI_MAIN)
-		return;
-
-	netdev = vsi->netdev;
-	if (!netdev)
-		return;
-
-	/* Bail out if netif_carrier is not OK */
-	if (!netif_carrier_ok(netdev))
-		return;
-
-	/* Go thru' TX queues for netdev */
-	for (i = 0; i < netdev->num_tx_queues; i++) {
-		struct netdev_queue *q;
-
-		q = netdev_get_tx_queue(netdev, i);
-		if (q)
-			i40e_detect_recover_hung_queue(i, vsi);
-	}
-}
-
-/**
  * i40e_get_iscsi_tc_map - Return TC map for iSCSI APP
  * @pf: pointer to PF
  *
@@ -5342,6 +5249,8 @@ static void i40e_vsi_update_queue_map(struct i40e_vsi *vsi,
 static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 {
 	u8 bw_share[I40E_MAX_TRAFFIC_CLASS] = {0};
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
 	struct i40e_vsi_context ctxt;
 	int ret = 0;
 	int i;
@@ -5359,10 +5268,40 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 
 	ret = i40e_vsi_configure_bw_alloc(vsi, enabled_tc, bw_share);
 	if (ret) {
-		dev_info(&vsi->back->pdev->dev,
+		struct i40e_aqc_query_vsi_bw_config_resp bw_config = {0};
+
+		dev_info(&pf->pdev->dev,
 			 "Failed configuring TC map %d for VSI %d\n",
 			 enabled_tc, vsi->seid);
-		goto out;
+		ret = i40e_aq_query_vsi_bw_config(hw, vsi->seid,
+						  &bw_config, NULL);
+		if (ret) {
+			dev_info(&pf->pdev->dev,
+				 "Failed querying vsi bw info, err %s aq_err %s\n",
+				 i40e_stat_str(hw, ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
+			goto out;
+		}
+		if ((bw_config.tc_valid_bits & enabled_tc) != enabled_tc) {
+			u8 valid_tc = bw_config.tc_valid_bits & enabled_tc;
+
+			if (!valid_tc)
+				valid_tc = bw_config.tc_valid_bits;
+			/* Always enable TC0, no matter what */
+			valid_tc |= 1;
+			dev_info(&pf->pdev->dev,
+				 "Requested tc 0x%x, but FW reports 0x%x as valid. Attempting to use 0x%x.\n",
+				 enabled_tc, bw_config.tc_valid_bits, valid_tc);
+			enabled_tc = valid_tc;
+		}
+
+		ret = i40e_vsi_configure_bw_alloc(vsi, enabled_tc, bw_share);
+		if (ret) {
+			dev_err(&pf->pdev->dev,
+				"Unable to  configure TC map %d for VSI %d\n",
+				enabled_tc, vsi->seid);
+			goto out;
+		}
 	}
 
 	/* Update Queue Pairs Mapping for currently enabled UPs */
@@ -5402,13 +5341,12 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 	/* Update the VSI after updating the VSI queue-mapping
 	 * information
 	 */
-	ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL);
+	ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
 	if (ret) {
-		dev_info(&vsi->back->pdev->dev,
+		dev_info(&pf->pdev->dev,
 			 "Update vsi tc config failed, err %s aq_err %s\n",
-			 i40e_stat_str(&vsi->back->hw, ret),
-			 i40e_aq_str(&vsi->back->hw,
-				     vsi->back->hw.aq.asq_last_status));
+			 i40e_stat_str(hw, ret),
+			 i40e_aq_str(hw, hw->aq.asq_last_status));
 		goto out;
 	}
 	/* update the local VSI info with updated queue map */
@@ -5418,11 +5356,10 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc)
 	/* Update current VSI BW information */
 	ret = i40e_vsi_get_bw_info(vsi);
 	if (ret) {
-		dev_info(&vsi->back->pdev->dev,
+		dev_info(&pf->pdev->dev,
 			 "Failed updating vsi bw info, err %s aq_err %s\n",
-			 i40e_stat_str(&vsi->back->hw, ret),
-			 i40e_aq_str(&vsi->back->hw,
-				     vsi->back->hw.aq.asq_last_status));
+			 i40e_stat_str(hw, ret),
+			 i40e_aq_str(hw, hw->aq.asq_last_status));
 		goto out;
 	}
 
@@ -6388,8 +6325,11 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 	struct i40e_hw *hw = &pf->hw;
 	int err = 0;
 
-	/* Do not enable DCB for SW1 and SW2 images even if the FW is capable */
-	if (pf->hw_features & I40E_HW_NO_DCB_SUPPORT)
+	/* Do not enable DCB for SW1 and SW2 images even if the FW is capable
+	 * Also do not enable DCBx if FW LLDP agent is disabled
+	 */
+	if ((pf->hw_features & I40E_HW_NO_DCB_SUPPORT) ||
+	    (pf->flags & I40E_FLAG_DISABLE_FW_LLDP))
 		goto out;
 
 	/* Get the initial DCB configuration */
@@ -6416,6 +6356,9 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 			dev_dbg(&pf->pdev->dev,
 				"DCBX offload is supported for this PF.\n");
 		}
+	} else if (pf->hw.aq.asq_last_status == I40E_AQ_RC_EPERM) {
+		dev_info(&pf->pdev->dev, "FW LLDP disabled for this PF.\n");
+		pf->flags |= I40E_FLAG_DISABLE_FW_LLDP;
 	} else {
 		dev_info(&pf->pdev->dev,
 			 "Query for DCB configuration failed, err %s aq_err %s\n",
@@ -7505,11 +7448,6 @@ static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np,
 {
 	struct i40e_vsi *vsi = np->vsi;
 
-	if (!tc_can_offload(vsi->netdev))
-		return -EOPNOTSUPP;
-	if (cls_flower->common.chain_index)
-		return -EOPNOTSUPP;
-
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
 		return i40e_configure_clsflower(vsi, cls_flower);
@@ -7527,6 +7465,9 @@ static int i40e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 {
 	struct i40e_netdev_priv *np = cb_priv;
 
+	if (!tc_cls_can_offload_and_chain0(np->vsi->netdev, type_data))
+		return -EOPNOTSUPP;
+
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return i40e_setup_tc_cls_flower(np, type_data);
@@ -7744,6 +7685,9 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 	/* Reprogram the default input set for Other/IPv4 */
 	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
+
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 }
 
 /**
@@ -9077,6 +9021,17 @@ static int i40e_rebuild_channels(struct i40e_vsi *vsi)
 				 vsi->uplink_seid);
 			return ret;
 		}
+		/* Reconfigure TX queues using QTX_CTL register */
+		ret = i40e_channel_config_tx_ring(vsi->back, vsi, ch);
+		if (ret) {
+			dev_info(&vsi->back->pdev->dev,
+				 "failed to configure TX rings for channel %u\n",
+				 ch->seid);
+			return ret;
+		}
+		/* update 'next_base_queue' */
+		vsi->next_base_queue = vsi->next_base_queue +
+							ch->num_queue_pairs;
 		if (ch->max_tx_rate) {
 			u64 credits = ch->max_tx_rate;
 
@@ -9280,6 +9235,9 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 		goto end_core_reset;
 	}
 
+	/* Enable FW to write a default DCB config on link-up */
+	i40e_aq_set_dcb_parameters(hw, true, NULL);
+
 #ifdef CONFIG_I40E_DCB
 	ret = i40e_init_pf_dcb(pf);
 	if (ret) {
@@ -9697,7 +9655,7 @@ static void i40e_service_task(struct work_struct *work)
 	if (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state))
 		return;
 
-	i40e_detect_recover_hung(pf);
+	i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
 	i40e_sync_filters_subtask(pf);
 	i40e_reset_subtask(pf);
 	i40e_handle_mdd_event(pf);
@@ -10464,10 +10422,9 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
 	/* set up vector assignment tracking */
 	size = sizeof(struct i40e_lump_tracking) + (sizeof(u16) * vectors);
 	pf->irq_pile = kzalloc(size, GFP_KERNEL);
-	if (!pf->irq_pile) {
-		dev_err(&pf->pdev->dev, "error allocating irq_pile memory\n");
+	if (!pf->irq_pile)
 		return -ENOMEM;
-	}
+
 	pf->irq_pile->num_entries = vectors;
 	pf->irq_pile->search_hint = 0;
 
@@ -10785,8 +10742,13 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
 	/* Determine the RSS size of the VSI */
 	if (!vsi->rss_size) {
 		u16 qcount;
-
-		qcount = vsi->num_queue_pairs / vsi->tc_config.numtc;
+		/* If the firmware does something weird during VSI init, we
+		 * could end up with zero TCs. Check for that to avoid
+		 * divide-by-zero. It probably won't pass traffic, but it also
+		 * won't panic.
+		 */
+		qcount = vsi->num_queue_pairs /
+			 (vsi->tc_config.numtc ? vsi->tc_config.numtc : 1);
 		vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount);
 	}
 	if (!vsi->rss_size)
@@ -10974,7 +10936,7 @@ i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf)
 	ret = i40e_aq_update_nvm(&pf->hw,
 				 I40E_SR_NVM_CONTROL_WORD,
 				 0x10, sizeof(nvm_word),
-				 &nvm_word, true, NULL);
+				 &nvm_word, true, 0, NULL);
 	/* Save off last admin queue command status before releasing
 	 * the NVM
 	 */
@@ -11115,13 +11077,13 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	    pf->hw.aq.fw_maj_ver >= 6)
 		pf->hw_features |= I40E_HW_PTP_L4_CAPABLE;
 
-	if (pf->hw.func_caps.vmdq) {
+	if (pf->hw.func_caps.vmdq && num_online_cpus() != 1) {
 		pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI;
 		pf->flags |= I40E_FLAG_VMDQ_ENABLED;
 		pf->num_vmdq_qps = i40e_default_queues_per_vmdq(pf);
 	}
 
-	if (pf->hw.func_caps.iwarp) {
+	if (pf->hw.func_caps.iwarp && num_online_cpus() != 1) {
 		pf->flags |= I40E_FLAG_IWARP_ENABLED;
 		/* IWARP needs one extra vector for CQP just like MISC.*/
 		pf->num_iwarp_msix = (int)num_online_cpus() + 1;
@@ -13598,6 +13560,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, pf);
 	pci_save_state(pdev);
+
+	/* Enable FW to write default DCB config on link-up */
+	i40e_aq_set_dcb_parameters(hw, true, NULL);
+
 #ifdef CONFIG_I40E_DCB
 	err = i40e_init_pf_dcb(pf);
 	if (err) {