Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2018-11-07

This series contains fixes to igb, i40e and ice drivers.

Anirudh fixes an issue during rebuild of the ice driver, where we need
to set the carrier state, as well as start or stop the queues all based
on the link status.  Removed functions that were duplicating current
functionality in the VSI rebuild/replay framework.

Dave fixes a potential resource collision during the remove path, so add
a check to see if we are in the middle of a reset.  Fixed the remove
path to ensure we call netif_napi_del() to free vectors before we set
vsi->netdev to NULL.

Akeem fixes an issue when the receive or transmit pause parameter is
set, results in link loss on the interface.  Fixed the spelling of
"Enabling" in error message.

Victor fixes potential memory leak by also freeing the related VSI
contexts in the unload path.

Md Fahad fixes a flag during port VLAN insertion, which was not being
set properly.

Brett fixes a transmit timeout during stress due to the hardware tail
and software tail were incorrectly out of sync.

Miroslav Lichvar fixes the igb PHC timecounter update interval to be
sure the timecounter is updated in time.

Chinh fixes the req_speeds variable to be u16 instead of u8 so that it
can handle all the link speeds.

Jake fixes i40e to add back the missing feature flags, which was causing
IP-in-IP offloads to be reported as not supported.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -12249,6 +12249,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 			  NETIF_F_GSO_GRE		|
 			  NETIF_F_GSO_GRE_CSUM		|
 			  NETIF_F_GSO_PARTIAL		|
+			  NETIF_F_GSO_IPXIP4		|
+			  NETIF_F_GSO_IPXIP6		|
 			  NETIF_F_GSO_UDP_TUNNEL	|
 			  NETIF_F_GSO_UDP_TUNNEL_CSUM	|
 			  NETIF_F_SCTP_CRC		|
@@ -12266,13 +12268,13 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	/* record features VLANs can make use of */
 	netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
 
-	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
-		netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC;
-
 	hw_features = hw_enc_features		|
 		      NETIF_F_HW_VLAN_CTAG_TX	|
 		      NETIF_F_HW_VLAN_CTAG_RX;
 
+	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
+		hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC;
+
 	netdev->hw_features |= hw_features;
 
 	netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;

drivers/net/ethernet/intel/ice/ice.h

@@ -76,6 +76,8 @@ extern const char ice_drv_ver[];
 #define ICE_MIN_INTR_PER_VF		(ICE_MIN_QS_PER_VF + 1)
 #define ICE_DFLT_INTR_PER_VF		(ICE_DFLT_QS_PER_VF + 1)
 
+#define ICE_MAX_RESET_WAIT		20
+
 #define ICE_VSIQF_HKEY_ARRAY_SIZE	((VSIQF_HKEY_MAX_INDEX + 1) *	4)
 
 #define ICE_DFLT_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
@@ -189,7 +191,6 @@ struct ice_vsi {
 	u64 tx_linearize;
 	DECLARE_BITMAP(state, __ICE_STATE_NBITS);
 	DECLARE_BITMAP(flags, ICE_VSI_FLAG_NBITS);
-	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	unsigned int current_netdev_flags;
 	u32 tx_restart;
 	u32 tx_busy;
@@ -369,5 +370,6 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
 int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
 void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
+void ice_napi_del(struct ice_vsi *vsi);
 
 #endif /* _ICE_H_ */

drivers/net/ethernet/intel/ice/ice_common.c

@@ -811,6 +811,9 @@ void ice_deinit_hw(struct ice_hw *hw)
 	/* Attempt to disable FW logging before shutting down control queues */
 	ice_cfg_fw_log(hw, false);
 	ice_shutdown_all_ctrlq(hw);
+
+	/* Clear VSI contexts if not already cleared */
+	ice_clear_all_vsi_ctx(hw);
 }
 
 /**

drivers/net/ethernet/intel/ice/ice_ethtool.c

@@ -1517,10 +1517,15 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 	}
 
 	if (!test_bit(__ICE_DOWN, pf->state)) {
-		/* Give it a little more time to try to come back */
+		/* Give it a little more time to try to come back. If still
+		 * down, restart autoneg link or reinitialize the interface.
+		 */
 		msleep(75);
 		if (!test_bit(__ICE_DOWN, pf->state))
 			return ice_nway_reset(netdev);
+
+		ice_down(vsi);
+		ice_up(vsi);
 	}
 
 	return err;

drivers/net/ethernet/intel/ice/ice_hw_autogen.h

@@ -242,6 +242,8 @@
 #define GLNVM_ULD				0x000B6008
 #define GLNVM_ULD_CORER_DONE_M			BIT(3)
 #define GLNVM_ULD_GLOBR_DONE_M			BIT(4)
+#define GLPCI_CNF2				0x000BE004
+#define GLPCI_CNF2_CACHELINE_SIZE_M		BIT(1)
 #define PF_FUNC_RID				0x0009E880
 #define PF_FUNC_RID_FUNC_NUM_S			0
 #define PF_FUNC_RID_FUNC_NUM_M			ICE_M(0x7, 0)

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -1997,7 +1997,7 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena)
 	status = ice_update_vsi(&vsi->back->hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %d\n",
-			   ena ? "Ena" : "Dis", vsi->idx, vsi->vsi_num, status,
+			   ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status,
 			   vsi->back->hw.adminq.sq_last_status);
 		goto err_out;
 	}
@@ -2458,6 +2458,7 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	 * on this wq
 	 */
 	if (vsi->netdev && !ice_is_reset_in_progress(pf->state)) {
+		ice_napi_del(vsi);
 		unregister_netdev(vsi->netdev);
 		free_netdev(vsi->netdev);
 		vsi->netdev = NULL;

drivers/net/ethernet/intel/ice/ice_main.c

@@ -1465,7 +1465,7 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
  * ice_napi_del - Remove NAPI handler for the VSI
  * @vsi: VSI for which NAPI handler is to be removed
  */
-static void ice_napi_del(struct ice_vsi *vsi)
+void ice_napi_del(struct ice_vsi *vsi)
 {
 	int v_idx;
 
@@ -1622,7 +1622,6 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev,
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
-	int ret;
 
 	if (vid >= VLAN_N_VID) {
 		netdev_err(netdev, "VLAN id requested %d is out of range %d\n",
@@ -1635,7 +1634,8 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev,
 
 	/* Enable VLAN pruning when VLAN 0 is added */
 	if (unlikely(!vid)) {
-		ret = ice_cfg_vlan_pruning(vsi, true);
+		int ret = ice_cfg_vlan_pruning(vsi, true);
+
 		if (ret)
 			return ret;
 	}
@@ -1644,12 +1644,7 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev,
 	 * needed to continue allowing all untagged packets since VLAN prune
 	 * list is applied to all packets by the switch
 	 */
-	ret = ice_vsi_add_vlan(vsi, vid);
-
-	if (!ret)
-		set_bit(vid, vsi->active_vlans);
-
-	return ret;
+	return ice_vsi_add_vlan(vsi, vid);
 }
 
 /**
@@ -1677,8 +1672,6 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev,
 	if (status)
 		return status;
 
-	clear_bit(vid, vsi->active_vlans);
-
 	/* Disable VLAN pruning when VLAN 0 is removed */
 	if (unlikely(!vid))
 		status = ice_cfg_vlan_pruning(vsi, false);
@@ -2001,6 +1994,22 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 	return 0;
 }
 
+/**
+ * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines
+ * @pf: pointer to the PF structure
+ *
+ * There is no error returned here because the driver should be able to handle
+ * 128 Byte cache lines, so we only print a warning in case issues are seen,
+ * specifically with Tx.
+ */
+static void ice_verify_cacheline_size(struct ice_pf *pf)
+{
+	if (rd32(&pf->hw, GLPCI_CNF2) & GLPCI_CNF2_CACHELINE_SIZE_M)
+		dev_warn(&pf->pdev->dev,
+			 "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n",
+			 ICE_CACHE_LINE_BYTES);
+}
+
 /**
  * ice_probe - Device initialization routine
  * @pdev: PCI device information struct
@@ -2151,6 +2160,8 @@ static int ice_probe(struct pci_dev *pdev,
 	/* since everything is good, start the service timer */
 	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
 
+	ice_verify_cacheline_size(pf);
+
 	return 0;
 
 err_alloc_sw_unroll:
@@ -2182,6 +2193,12 @@ static void ice_remove(struct pci_dev *pdev)
 	if (!pf)
 		return;
 
+	for (i = 0; i < ICE_MAX_RESET_WAIT; i++) {
+		if (!ice_is_reset_in_progress(pf->state))
+			break;
+		msleep(100);
+	}
+
 	set_bit(__ICE_DOWN, pf->state);
 	ice_service_task_stop(pf);
 
@@ -2509,31 +2526,6 @@ static int ice_vsi_vlan_setup(struct ice_vsi *vsi)
 	return ret;
 }
 
-/**
- * ice_restore_vlan - Reinstate VLANs when vsi/netdev comes back up
- * @vsi: the VSI being brought back up
- */
-static int ice_restore_vlan(struct ice_vsi *vsi)
-{
-	int err;
-	u16 vid;
-
-	if (!vsi->netdev)
-		return -EINVAL;
-
-	err = ice_vsi_vlan_setup(vsi);
-	if (err)
-		return err;
-
-	for_each_set_bit(vid, vsi->active_vlans, VLAN_N_VID) {
-		err = ice_vlan_rx_add_vid(vsi->netdev, htons(ETH_P_8021Q), vid);
-		if (err)
-			break;
-	}
-
-	return err;
-}
-
 /**
  * ice_vsi_cfg - Setup the VSI
  * @vsi: the VSI being configured
@@ -2546,7 +2538,9 @@ static int ice_vsi_cfg(struct ice_vsi *vsi)
 
 	if (vsi->netdev) {
 		ice_set_rx_mode(vsi->netdev);
-		err = ice_restore_vlan(vsi);
+
+		err = ice_vsi_vlan_setup(vsi);
+
 		if (err)
 			return err;
 	}
@@ -3296,7 +3290,7 @@ static void ice_rebuild(struct ice_pf *pf)
 	struct device *dev = &pf->pdev->dev;
 	struct ice_hw *hw = &pf->hw;
 	enum ice_status ret;
-	int err;
+	int err, i;
 
 	if (test_bit(__ICE_DOWN, pf->state))
 		goto clear_recovery;
@@ -3370,6 +3364,22 @@ static void ice_rebuild(struct ice_pf *pf)
 	}
 
 	ice_reset_all_vfs(pf, true);
+
+	for (i = 0; i < pf->num_alloc_vsi; i++) {
+		bool link_up;
+
+		if (!pf->vsi[i] || pf->vsi[i]->type != ICE_VSI_PF)
+			continue;
+		ice_get_link_status(pf->vsi[i]->port_info, &link_up);
+		if (link_up) {
+			netif_carrier_on(pf->vsi[i]->netdev);
+			netif_tx_wake_all_queues(pf->vsi[i]->netdev);
+		} else {
+			netif_carrier_off(pf->vsi[i]->netdev);
+			netif_tx_stop_all_queues(pf->vsi[i]->netdev);
+		}
+	}
+
 	/* if we get here, reset flow is successful */
 	clear_bit(__ICE_RESET_FAILED, pf->state);
 	return;

drivers/net/ethernet/intel/ice/ice_switch.c

@@ -347,6 +347,18 @@ static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle)
 	}
 }
 
+/**
+ * ice_clear_all_vsi_ctx - clear all the VSI context entries
+ * @hw: pointer to the hw struct
+ */
+void ice_clear_all_vsi_ctx(struct ice_hw *hw)
+{
+	u16 i;
+
+	for (i = 0; i < ICE_MAX_VSI; i++)
+		ice_clear_vsi_ctx(hw, i);
+}
+
 /**
  * ice_add_vsi - add VSI context to the hardware and VSI handle list
  * @hw: pointer to the hw struct

drivers/net/ethernet/intel/ice/ice_switch.h

@@ -190,6 +190,8 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
 	       struct ice_sq_cd *cd);
 bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle);
 struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle);
+void ice_clear_all_vsi_ctx(struct ice_hw *hw);
+/* Switch config */
 enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw);
 
 /* Switch/bridge related commands */

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -1520,7 +1520,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 
 	/* update gso_segs and bytecount */
 	first->gso_segs = skb_shinfo(skb)->gso_segs;
-	first->bytecount = (first->gso_segs - 1) * off->header_len;
+	first->bytecount += (first->gso_segs - 1) * off->header_len;
 
 	cd_tso_len = skb->len - off->header_len;
 	cd_mss = skb_shinfo(skb)->gso_size;
@@ -1556,15 +1556,15 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
  * magnitude greater than our largest possible GSO size.
  *
  * This would then be implemented as:
- *     return (((size >> 12) * 85) >> 8) + 1;
+ *     return (((size >> 12) * 85) >> 8) + ICE_DESCS_FOR_SKB_DATA_PTR;
  *
  * Since multiplication and division are commutative, we can reorder
  * operations into:
- *     return ((size * 85) >> 20) + 1;
+ *     return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR;
  */
 static unsigned int ice_txd_use_count(unsigned int size)
 {
-	return ((size * 85) >> 20) + 1;
+	return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR;
 }
 
 /**
@@ -1706,7 +1706,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 	 *       + 1 desc for context descriptor,
 	 * otherwise try next time
 	 */
-	if (ice_maybe_stop_tx(tx_ring, count + 4 + 1)) {
+	if (ice_maybe_stop_tx(tx_ring, count + ICE_DESCS_PER_CACHE_LINE +
+			      ICE_DESCS_FOR_CTX_DESC)) {
 		tx_ring->tx_stats.tx_busy++;
 		return NETDEV_TX_BUSY;
 	}

drivers/net/ethernet/intel/ice/ice_txrx.h

@@ -22,8 +22,21 @@
 #define ICE_RX_BUF_WRITE	16	/* Must be power of 2 */
 #define ICE_MAX_TXQ_PER_TXQG	128
 
-/* Tx Descriptors needed, worst case */
-#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
+/* We are assuming that the cache line is always 64 Bytes here for ice.
+ * In order to make sure that is a correct assumption there is a check in probe
+ * to print a warning if the read from GLPCI_CNF2 tells us that the cache line
+ * size is 128 bytes. We do it this way because we do not want to read the
+ * GLPCI_CNF2 register or a variable containing the value on every pass through
+ * the Tx path.
+ */
+#define ICE_CACHE_LINE_BYTES		64
+#define ICE_DESCS_PER_CACHE_LINE	(ICE_CACHE_LINE_BYTES / \
+					 sizeof(struct ice_tx_desc))
+#define ICE_DESCS_FOR_CTX_DESC		1
+#define ICE_DESCS_FOR_SKB_DATA_PTR	1
+/* Tx descriptors needed, worst case */
+#define DESC_NEEDED (MAX_SKB_FRAGS + ICE_DESCS_FOR_CTX_DESC + \
+		     ICE_DESCS_PER_CACHE_LINE + ICE_DESCS_FOR_SKB_DATA_PTR)
 #define ICE_DESC_UNUSED(R)	\
 	((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
 	(R)->next_to_clean - (R)->next_to_use - 1)

drivers/net/ethernet/intel/ice/ice_type.h

@@ -92,12 +92,12 @@ struct ice_link_status {
 	u64 phy_type_low;
 	u16 max_frame_size;
 	u16 link_speed;
+	u16 req_speeds;
 	u8 lse_ena;	/* Link Status Event notification */
 	u8 link_info;
 	u8 an_info;
 	u8 ext_info;
 	u8 pacing;
-	u8 req_speeds;
 	/* Refer to #define from module_type[ICE_MODULE_TYPE_TOTAL_BYTE] of
 	 * ice_aqc_get_phy_caps structure
 	 */

drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c

@@ -348,7 +348,7 @@ static int ice_vsi_set_pvid(struct ice_vsi *vsi, u16 vid)
 	struct ice_vsi_ctx ctxt = { 0 };
 	enum ice_status status;
 
-	ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_TAGGED |
+	ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_UNTAGGED |
 			       ICE_AQ_VSI_PVLAN_INSERT_PVID |
 			       ICE_AQ_VSI_VLAN_EMOD_STR;
 	ctxt.info.pvid = cpu_to_le16(vid);
@@ -2171,7 +2171,6 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 
 			if (!ice_vsi_add_vlan(vsi, vid)) {
 				vf->num_vlan++;
-				set_bit(vid, vsi->active_vlans);
 
 				/* Enable VLAN pruning when VLAN 0 is added */
 				if (unlikely(!vid))
@@ -2190,7 +2189,6 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 			 */
 			if (!ice_vsi_kill_vlan(vsi, vid)) {
 				vf->num_vlan--;
-				clear_bit(vid, vsi->active_vlans);
 
 				/* Disable VLAN pruning when removing VLAN 0 */
 				if (unlikely(!vid))

drivers/net/ethernet/intel/igb/igb_ptp.c

@@ -53,13 +53,15 @@
  *   2^40 * 10^-9 /  60  = 18.3 minutes.
  *
  * SYSTIM is converted to real time using a timecounter. As
- * timecounter_cyc2time() allows old timestamps, the timecounter
- * needs to be updated at least once per half of the SYSTIM interval.
- * Scheduling of delayed work is not very accurate, so we aim for 8
- * minutes to be sure the actual interval is shorter than 9.16 minutes.
+ * timecounter_cyc2time() allows old timestamps, the timecounter needs
+ * to be updated at least once per half of the SYSTIM interval.
+ * Scheduling of delayed work is not very accurate, and also the NIC
+ * clock can be adjusted to run up to 6% faster and the system clock
+ * up to 10% slower, so we aim for 6 minutes to be sure the actual
+ * interval in the NIC time is shorter than 9.16 minutes.
  */
 
-#define IGB_SYSTIM_OVERFLOW_PERIOD	(HZ * 60 * 8)
+#define IGB_SYSTIM_OVERFLOW_PERIOD	(HZ * 60 * 6)
 #define IGB_PTP_TX_TIMEOUT		(HZ * 15)
 #define INCPERIOD_82576			BIT(E1000_TIMINCA_16NS_SHIFT)
 #define INCVALUE_82576_MASK		GENMASK(E1000_TIMINCA_16NS_SHIFT - 1, 0)