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

Jeff Kirsher says:

====================
100GbE Intel Wired LAN Driver Updates 2018-11-13

This series contains updates to the ice driver only.

Brett cleans up debug print messages by removing useless or duplicate
messages, and make sure we assign the hardware head pointer to head
instead of the software head pointer.  Resolved an issue when disabling
SRIOV we were trying to stop queues multiple times, so make sure we
disable SRIOV before stopping transmit and receive queues for VF.

Tony fixes a potential NULL pointer dereference during a VF reset.

Anirudh resolves an issue where we were releasing the VSI before
removing the VSI scheduler node, which was resulting in an error "Failed
to set LAN Tx queue context, error: -1".  Also fixed the guaranteed
number of VSIs available and used by discovering the device
capabilities to determine the 'guar_num_vsi' per function, rather than
always using the theoretical max number of VSIs every time.

Dave avoids a deadlock by nesting RTNL locking, so added a boolean to
determine if the RTNL lock is already held.

Lev fixes bad mask values which would break compilation.

Piotr increases the receive queue disable timeout since it can take
additional time to finish all pending queue requests.

Usha resolves an issue of VLAN priority tagged traffic not appearing on
all traffic classes, which was causing ETS bandwidth shaping to not work
as expected.

Henry fixes the reset path to cleanup the old scheduler tree before
rebuilding it.

Md Fahad removes a unnecessary check which was causing a driver load
error on platforms with more than 128 cores.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

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

@@ -52,7 +52,6 @@ extern const char ice_drv_ver[];
 #define ICE_MBXQ_LEN		64
 #define ICE_MIN_MSIX		2
 #define ICE_NO_VSI		0xffff
-#define ICE_MAX_VSI_ALLOC	130
 #define ICE_MAX_TXQS		2048
 #define ICE_MAX_RXQS		2048
 #define ICE_VSI_MAP_CONTIG	0
@@ -113,7 +112,9 @@ extern const char ice_drv_ver[];
 
 struct ice_tc_info {
 	u16 qoffset;
-	u16 qcount;
+	u16 qcount_tx;
+	u16 qcount_rx;
+	u8 netdev_tc;
 };
 
 struct ice_tc_cfg {

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

@@ -87,6 +87,7 @@ struct ice_aqc_list_caps {
 /* Device/Function buffer entry, repeated per reported capability */
 struct ice_aqc_list_caps_elem {
 	__le16 cap;
+#define ICE_AQC_CAPS_VALID_FUNCTIONS			0x0005
 #define ICE_AQC_CAPS_SRIOV				0x0012
 #define ICE_AQC_CAPS_VF					0x0013
 #define ICE_AQC_CAPS_VSI				0x0017
@@ -1065,10 +1066,10 @@ struct ice_aqc_nvm {
 #define ICE_AQC_NVM_LAST_CMD		BIT(0)
 #define ICE_AQC_NVM_PCIR_REQ		BIT(0)	/* Used by NVM Update reply */
 #define ICE_AQC_NVM_PRESERVATION_S	1
-#define ICE_AQC_NVM_PRESERVATION_M	(3 << CSR_AQ_NVM_PRESERVATION_S)
-#define ICE_AQC_NVM_NO_PRESERVATION	(0 << CSR_AQ_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_PRESERVATION_M	(3 << ICE_AQC_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_NO_PRESERVATION	(0 << ICE_AQC_NVM_PRESERVATION_S)
 #define ICE_AQC_NVM_PRESERVE_ALL	BIT(1)
-#define ICE_AQC_NVM_PRESERVE_SELECTED	(3 << CSR_AQ_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_PRESERVE_SELECTED	(3 << ICE_AQC_NVM_PRESERVATION_S)
 #define ICE_AQC_NVM_FLASH_ONLY		BIT(7)
 	__le16 module_typeid;
 	__le16 length;

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

@@ -1386,6 +1386,27 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res)
 	}
 }
 
+/**
+ * ice_get_guar_num_vsi - determine number of guar VSI for a PF
+ * @hw: pointer to the hw structure
+ *
+ * Determine the number of valid functions by going through the bitmap returned
+ * from parsing capabilities and use this to calculate the number of VSI per PF.
+ */
+static u32 ice_get_guar_num_vsi(struct ice_hw *hw)
+{
+	u8 funcs;
+
+#define ICE_CAPS_VALID_FUNCS_M	0xFF
+	funcs = hweight8(hw->dev_caps.common_cap.valid_functions &
+			 ICE_CAPS_VALID_FUNCS_M);
+
+	if (!funcs)
+		return 0;
+
+	return ICE_MAX_VSI / funcs;
+}
+
 /**
  * ice_parse_caps - parse function/device capabilities
  * @hw: pointer to the hw struct
@@ -1428,6 +1449,12 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 		u16 cap = le16_to_cpu(cap_resp->cap);
 
 		switch (cap) {
+		case ICE_AQC_CAPS_VALID_FUNCTIONS:
+			caps->valid_functions = number;
+			ice_debug(hw, ICE_DBG_INIT,
+				  "HW caps: Valid Functions = %d\n",
+				  caps->valid_functions);
+			break;
 		case ICE_AQC_CAPS_SRIOV:
 			caps->sr_iov_1_1 = (number == 1);
 			ice_debug(hw, ICE_DBG_INIT,
@@ -1457,10 +1484,10 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 					  "HW caps: Dev.VSI cnt = %d\n",
 					  dev_p->num_vsi_allocd_to_host);
 			} else if (func_p) {
-				func_p->guaranteed_num_vsi = number;
+				func_p->guar_num_vsi = ice_get_guar_num_vsi(hw);
 				ice_debug(hw, ICE_DBG_INIT,
 					  "HW caps: Func.VSI cnt = %d\n",
-					  func_p->guaranteed_num_vsi);
+					  number);
 			}
 			break;
 		case ICE_AQC_CAPS_RSS:

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

@@ -7,6 +7,9 @@
 #define _ICE_HW_AUTOGEN_H_
 
 #define QTX_COMM_DBELL(_DBQM)			(0x002C0000 + ((_DBQM) * 4))
+#define QTX_COMM_HEAD(_DBQM)			(0x000E0000 + ((_DBQM) * 4))
+#define QTX_COMM_HEAD_HEAD_S			0
+#define QTX_COMM_HEAD_HEAD_M			ICE_M(0x1FFF, 0)
 #define PF_FW_ARQBAH				0x00080180
 #define PF_FW_ARQBAL				0x00080080
 #define PF_FW_ARQH				0x00080380

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

@@ -174,15 +174,15 @@ static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena)
 {
 	int i;
 
-	for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) {
+	for (i = 0; i < ICE_Q_WAIT_MAX_RETRY; i++) {
 		u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q));
 
 		if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
 			break;
 
-		usleep_range(10, 20);
+		usleep_range(20, 40);
 	}
-	if (i >= ICE_Q_WAIT_RETRY_LIMIT)
+	if (i >= ICE_Q_WAIT_MAX_RETRY)
 		return -ETIMEDOUT;
 
 	return 0;
@@ -774,11 +774,13 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt)
  */
 static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 {
-	u16 offset = 0, qmap = 0, numq_tc;
-	u16 pow = 0, max_rss = 0, qcount;
+	u16 offset = 0, qmap = 0, tx_count = 0;
 	u16 qcount_tx = vsi->alloc_txq;
 	u16 qcount_rx = vsi->alloc_rxq;
+	u16 tx_numq_tc, rx_numq_tc;
+	u16 pow = 0, max_rss = 0;
 	bool ena_tc0 = false;
+	u8 netdev_tc = 0;
 	int i;
 
 	/* at least TC0 should be enabled by default */
@@ -794,7 +796,12 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 		vsi->tc_cfg.ena_tc |= 1;
 	}
 
-	numq_tc = qcount_rx / vsi->tc_cfg.numtc;
+	rx_numq_tc = qcount_rx / vsi->tc_cfg.numtc;
+	if (!rx_numq_tc)
+		rx_numq_tc = 1;
+	tx_numq_tc = qcount_tx / vsi->tc_cfg.numtc;
+	if (!tx_numq_tc)
+		tx_numq_tc = 1;
 
 	/* TC mapping is a function of the number of Rx queues assigned to the
 	 * VSI for each traffic class and the offset of these queues.
@@ -808,45 +815,50 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	 * Setup number and offset of Rx queues for all TCs for the VSI
 	 */
 
-	qcount = numq_tc;
+	qcount_rx = rx_numq_tc;
+
 	/* qcount will change if RSS is enabled */
 	if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) {
 		if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF) {
 			if (vsi->type == ICE_VSI_PF)
 				max_rss = ICE_MAX_LG_RSS_QS;
 			else
 				max_rss = ICE_MAX_SMALL_RSS_QS;
-			qcount = min_t(int, numq_tc, max_rss);
-			qcount = min_t(int, qcount, vsi->rss_size);
+			qcount_rx = min_t(int, rx_numq_tc, max_rss);
+			qcount_rx = min_t(int, qcount_rx, vsi->rss_size);
 		}
 	}
 
 	/* find the (rounded up) power-of-2 of qcount */
-	pow = order_base_2(qcount);
+	pow = order_base_2(qcount_rx);
 
 	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
 		if (!(vsi->tc_cfg.ena_tc & BIT(i))) {
 			/* TC is not enabled */
 			vsi->tc_cfg.tc_info[i].qoffset = 0;
-			vsi->tc_cfg.tc_info[i].qcount = 1;
+			vsi->tc_cfg.tc_info[i].qcount_rx = 1;
+			vsi->tc_cfg.tc_info[i].qcount_tx = 1;
+			vsi->tc_cfg.tc_info[i].netdev_tc = 0;
 			ctxt->info.tc_mapping[i] = 0;
 			continue;
 		}
 
 		/* TC is enabled */
 		vsi->tc_cfg.tc_info[i].qoffset = offset;
-		vsi->tc_cfg.tc_info[i].qcount = qcount;
+		vsi->tc_cfg.tc_info[i].qcount_rx = qcount_rx;
+		vsi->tc_cfg.tc_info[i].qcount_tx = tx_numq_tc;
+		vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++;
 
 		qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) &
 			ICE_AQ_VSI_TC_Q_OFFSET_M) |
 			((pow << ICE_AQ_VSI_TC_Q_NUM_S) &
 			 ICE_AQ_VSI_TC_Q_NUM_M);
-		offset += qcount;
+		offset += qcount_rx;
+		tx_count += tx_numq_tc;
 		ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
 	}
-
-	vsi->num_txq = qcount_tx;
 	vsi->num_rxq = offset;
+	vsi->num_txq = tx_count;
 
 	if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) {
 		dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n");
@@ -1611,55 +1623,62 @@ int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
 	struct ice_aqc_add_tx_qgrp *qg_buf;
 	struct ice_aqc_add_txqs_perq *txq;
 	struct ice_pf *pf = vsi->back;
+	u8 num_q_grps, q_idx = 0;
 	enum ice_status status;
 	u16 buf_len, i, pf_q;
 	int err = 0, tc = 0;
-	u8 num_q_grps;
 
 	buf_len = sizeof(struct ice_aqc_add_tx_qgrp);
 	qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL);
 	if (!qg_buf)
 		return -ENOMEM;
 
-	if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) {
-		err = -EINVAL;
-		goto err_cfg_txqs;
-	}
 	qg_buf->num_txqs = 1;
 	num_q_grps = 1;
 
-	/* set up and configure the Tx queues */
-	ice_for_each_txq(vsi, i) {
-		struct ice_tlan_ctx tlan_ctx = { 0 };
+	/* set up and configure the Tx queues for each enabled TC */
+	for (tc = 0; tc < ICE_MAX_TRAFFIC_CLASS; tc++) {
+		if (!(vsi->tc_cfg.ena_tc & BIT(tc)))
+			break;
 
-		pf_q = vsi->txq_map[i];
-		ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q);
-		/* copy context contents into the qg_buf */
-		qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
-		ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
-			    ice_tlan_ctx_info);
+		for (i = 0; i < vsi->tc_cfg.tc_info[tc].qcount_tx; i++) {
+			struct ice_tlan_ctx tlan_ctx = { 0 };
+
+			pf_q = vsi->txq_map[q_idx];
+			ice_setup_tx_ctx(vsi->tx_rings[q_idx], &tlan_ctx,
+					 pf_q);
+			/* copy context contents into the qg_buf */
+			qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
+			ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
+				    ice_tlan_ctx_info);
+
+			/* init queue specific tail reg. It is referred as
+			 * transmit comm scheduler queue doorbell.
+			 */
+			vsi->tx_rings[q_idx]->tail =
+				pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
+			status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc,
+						 num_q_grps, qg_buf, buf_len,
+						 NULL);
+			if (status) {
+				dev_err(&vsi->back->pdev->dev,
+					"Failed to set LAN Tx queue context, error: %d\n",
+					status);
+				err = -ENODEV;
+				goto err_cfg_txqs;
+			}
 
-		/* init queue specific tail reg. It is referred as transmit
-		 * comm scheduler queue doorbell.
-		 */
-		vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
-		status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc,
-					 num_q_grps, qg_buf, buf_len, NULL);
-		if (status) {
-			dev_err(&vsi->back->pdev->dev,
-				"Failed to set LAN Tx queue context, error: %d\n",
-				status);
-			err = -ENODEV;
-			goto err_cfg_txqs;
-		}
+			/* Add Tx Queue TEID into the VSI Tx ring from the
+			 * response. This will complete configuring and
+			 * enabling the queue.
+			 */
+			txq = &qg_buf->txqs[0];
+			if (pf_q == le16_to_cpu(txq->txq_id))
+				vsi->tx_rings[q_idx]->txq_teid =
+					le32_to_cpu(txq->q_teid);
 
-		/* Add Tx Queue TEID into the VSI Tx ring from the response
-		 * This will complete configuring and enabling the queue.
-		 */
-		txq = &qg_buf->txqs[0];
-		if (pf_q == le16_to_cpu(txq->txq_id))
-			vsi->tx_rings[i]->txq_teid =
-				le32_to_cpu(txq->q_teid);
+			q_idx++;
+		}
 	}
 err_cfg_txqs:
 	devm_kfree(&pf->pdev->dev, qg_buf);
@@ -1908,7 +1927,8 @@ int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 	ice_for_each_txq(vsi, i) {
 		u16 v_idx;
 
-		if (!vsi->tx_rings || !vsi->tx_rings[i]) {
+		if (!vsi->tx_rings || !vsi->tx_rings[i] ||
+		    !vsi->tx_rings[i]->q_vector) {
 			err = -EINVAL;
 			goto err_out;
 		}
@@ -2056,6 +2076,9 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	/* set RSS capabilities */
 	ice_vsi_set_rss_params(vsi);
 
+	/* set tc configuration */
+	ice_vsi_set_tc_cfg(vsi);
+
 	/* create the VSI */
 	ret = ice_vsi_init(vsi);
 	if (ret)
@@ -2119,11 +2142,9 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		goto unroll_vsi_init;
 	}
 
-	ice_vsi_set_tc_cfg(vsi);
-
 	/* configure VSI nodes based on number of queues and TC's */
 	for (i = 0; i < vsi->tc_cfg.numtc; i++)
-		max_txqs[i] = vsi->num_txq;
+		max_txqs[i] = pf->num_lan_tx;
 
 	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 			      max_txqs);
@@ -2491,6 +2512,7 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	}
 
 	ice_remove_vsi_fltr(&pf->hw, vsi->idx);
+	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	ice_vsi_delete(vsi);
 	ice_vsi_free_q_vectors(vsi);
 	ice_vsi_clear_rings(vsi);
@@ -2518,11 +2540,14 @@ int ice_vsi_release(struct ice_vsi *vsi)
 int ice_vsi_rebuild(struct ice_vsi *vsi)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	struct ice_pf *pf;
 	int ret, i;
 
 	if (!vsi)
 		return -EINVAL;
 
+	pf = vsi->back;
+	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	ice_vsi_free_q_vectors(vsi);
 	ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx);
 	ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx);
@@ -2532,6 +2557,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 	ice_vsi_free_arrays(vsi, false);
 	ice_dev_onetime_setup(&vsi->back->hw);
 	ice_vsi_set_num_qs(vsi);
+	ice_vsi_set_tc_cfg(vsi);
 
 	/* Initialize VSI struct elements and create VSI in FW */
 	ret = ice_vsi_init(vsi);
@@ -2578,11 +2604,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 		break;
 	}
 
-	ice_vsi_set_tc_cfg(vsi);
-
 	/* configure VSI nodes based on number of queues and TC's */
 	for (i = 0; i < vsi->tc_cfg.numtc; i++)
-		max_txqs[i] = vsi->num_txq;
+		max_txqs[i] = pf->num_lan_tx;
 
 	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 			      max_txqs);