ice: Initialize PF and setup miscellaneous interrupt

This patch continues the initialization flow as follows:

1) Allocate and initialize necessary fields (like vsi, num_alloc_vsi,
   irq_tracker, etc) in the ice_pf instance.

2) Setup the miscellaneous interrupt handler. This also known as the
   "other interrupt causes" (OIC) handler and is used to handle non
   hotpath interrupts (like control queue events, link events,
   exceptions, etc.

3) Implement a background task to process admin queue receive (ARQ)
   events received by the driver.

CC: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

10 files changed, 1025 insertions, 1 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 1a1776a2a5a1..8103e61e67f9 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -12,29 +12,113 @@
 #include <linux/compiler.h>
 #include <linux/etherdevice.h>
 #include <linux/pci.h>
+#include <linux/workqueue.h>
 #include <linux/aer.h>
+#include <linux/interrupt.h>
+#include <linux/timer.h>
 #include <linux/delay.h>
 #include <linux/bitmap.h>
+#include <linux/if_bridge.h>
 #include "ice_devids.h"
 #include "ice_type.h"
+#include "ice_txrx.h"
 #include "ice_switch.h"
 #include "ice_common.h"
 #include "ice_sched.h"
 
 #define ICE_BAR0		0
+#define ICE_INT_NAME_STR_LEN	(IFNAMSIZ + 16)
 #define ICE_AQ_LEN		64
+#define ICE_MIN_MSIX		2
+#define ICE_MAX_VSI_ALLOC	130
+#define ICE_MAX_TXQS		2048
+#define ICE_MAX_RXQS		2048
+#define ICE_RES_VALID_BIT	0x8000
+#define ICE_RES_MISC_VEC_ID	(ICE_RES_VALID_BIT - 1)
 
 #define ICE_DFLT_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
 
+struct ice_res_tracker {
+	u16 num_entries;
+	u16 search_hint;
+	u16 list[1];
+};
+
+struct ice_sw {
+	struct ice_pf *pf;
+	u16 sw_id;		/* switch ID for this switch */
+	u16 bridge_mode;	/* VEB/VEPA/Port Virtualizer */
+};
+
 enum ice_state {
 	__ICE_DOWN,
+	__ICE_PFR_REQ,			/* set by driver and peers */
+	__ICE_ADMINQ_EVENT_PENDING,
+	__ICE_SERVICE_SCHED,
 	__ICE_STATE_NBITS		/* must be last */
 };
 
+/* struct that defines a VSI, associated with a dev */
+struct ice_vsi {
+	struct net_device *netdev;
+	struct ice_port_info *port_info; /* back pointer to port_info */
+	u16 vsi_num;			 /* HW (absolute) index of this VSI */
+} ____cacheline_internodealigned_in_smp;
+
+enum ice_pf_flags {
+	ICE_FLAG_MSIX_ENA,
+	ICE_FLAG_FLTR_SYNC,
+	ICE_FLAG_RSS_ENA,
+	ICE_PF_FLAGS_NBITS		/* must be last */
+};
+
 struct ice_pf {
 	struct pci_dev *pdev;
+	struct msix_entry *msix_entries;
+	struct ice_res_tracker *irq_tracker;
+	struct ice_vsi **vsi;		/* VSIs created by the driver */
+	struct ice_sw *first_sw;	/* first switch created by firmware */
 	DECLARE_BITMAP(state, __ICE_STATE_NBITS);
+	DECLARE_BITMAP(avail_txqs, ICE_MAX_TXQS);
+	DECLARE_BITMAP(avail_rxqs, ICE_MAX_RXQS);
+	DECLARE_BITMAP(flags, ICE_PF_FLAGS_NBITS);
+	unsigned long serv_tmr_period;
+	unsigned long serv_tmr_prev;
+	struct timer_list serv_tmr;
+	struct work_struct serv_task;
+	struct mutex avail_q_mutex;	/* protects access to avail_[rx|tx]qs */
+	struct mutex sw_mutex;		/* lock for protecting VSI alloc flow */
 	u32 msg_enable;
+	u32 oicr_idx;		/* Other interrupt cause vector index */
+	u32 num_lan_msix;	/* Total MSIX vectors for base driver */
+	u32 num_avail_msix;	/* remaining MSIX vectors left unclaimed */
+	u16 num_lan_tx;		/* num lan tx queues setup */
+	u16 num_lan_rx;		/* num lan rx queues setup */
+	u16 q_left_tx;		/* remaining num tx queues left unclaimed */
+	u16 q_left_rx;		/* remaining num rx queues left unclaimed */
+	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */
+	u16 num_alloc_vsi;
+
 	struct ice_hw hw;
+	char int_name[ICE_INT_NAME_STR_LEN];
 };
+
+/**
+ * ice_irq_dynamic_ena - Enable default interrupt generation settings
+ * @hw: pointer to hw struct
+ */
+static inline void ice_irq_dynamic_ena(struct ice_hw *hw)
+{
+	u32 vector = ((struct ice_pf *)hw->back)->oicr_idx;
+	int itr = ICE_ITR_NONE;
+	u32 val;
+
+	/* clear the PBA here, as this function is meant to clean out all
+	 * previous interrupts and enable the interrupt
+	 */
+	val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
+	      (itr << GLINT_DYN_CTL_ITR_INDX_S);
+
+	wr32(hw, GLINT_DYN_CTL(vector), val);
+}
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 5061240996b1..f0837e277b2f 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -583,11 +583,13 @@ struct ice_aq_desc {
 /* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */
 #define ICE_AQ_LG_BUF	512
 
+#define ICE_AQ_FLAG_ERR_S	2
 #define ICE_AQ_FLAG_LB_S	9
 #define ICE_AQ_FLAG_RD_S	10
 #define ICE_AQ_FLAG_BUF_S	12
 #define ICE_AQ_FLAG_SI_S	13
 
+#define ICE_AQ_FLAG_ERR		BIT(ICE_AQ_FLAG_ERR_S) /* 0x4    */
 #define ICE_AQ_FLAG_LB		BIT(ICE_AQ_FLAG_LB_S)  /* 0x200  */
 #define ICE_AQ_FLAG_RD		BIT(ICE_AQ_FLAG_RD_S)  /* 0x400  */
 #define ICE_AQ_FLAG_BUF		BIT(ICE_AQ_FLAG_BUF_S) /* 0x1000 */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index ef5bab25c2f5..a4ce8a87fb0d 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -282,6 +282,12 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 	if (status)
 		return status;
 
+	/* set these values to minimum allowed */
+	hw->itr_gran_200 = ICE_ITR_GRAN_MIN_200;
+	hw->itr_gran_100 = ICE_ITR_GRAN_MIN_100;
+	hw->itr_gran_50 = ICE_ITR_GRAN_MIN_50;
+	hw->itr_gran_25 = ICE_ITR_GRAN_MIN_25;
+
 	status = ice_init_all_ctrlq(hw);
 	if (status)
 		goto err_unroll_cqinit;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index e0a7aa1dd943..dd4473e84ebb 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -17,6 +17,9 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req);
 enum ice_status ice_init_all_ctrlq(struct ice_hw *hw);
 void ice_shutdown_all_ctrlq(struct ice_hw *hw);
 enum ice_status
+ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
+		  struct ice_rq_event_info *e, u16 *pending);
+enum ice_status
 ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 		enum ice_aq_res_access_type access);
 void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res);
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index b32c0fc04bc9..5909a4407e38 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -963,3 +963,104 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode)
 	desc->opcode = cpu_to_le16(opcode);
 	desc->flags = cpu_to_le16(ICE_AQ_FLAG_SI);
 }
+
+/**
+ * ice_clean_rq_elem
+ * @hw: pointer to the hw struct
+ * @cq: pointer to the specific Control queue
+ * @e: event info from the receive descriptor, includes any buffers
+ * @pending: number of events that could be left to process
+ *
+ * This function cleans one Admin Receive Queue element and returns
+ * the contents through e.  It can also return how many events are
+ * left to process through 'pending'.
+ */
+enum ice_status
+ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
+		  struct ice_rq_event_info *e, u16 *pending)
+{
+	u16 ntc = cq->rq.next_to_clean;
+	enum ice_status ret_code = 0;
+	struct ice_aq_desc *desc;
+	struct ice_dma_mem *bi;
+	u16 desc_idx;
+	u16 datalen;
+	u16 flags;
+	u16 ntu;
+
+	/* pre-clean the event info */
+	memset(&e->desc, 0, sizeof(e->desc));
+
+	/* take the lock before we start messing with the ring */
+	mutex_lock(&cq->rq_lock);
+
+	if (!cq->rq.count) {
+		ice_debug(hw, ICE_DBG_AQ_MSG,
+			  "Control Receive queue not initialized.\n");
+		ret_code = ICE_ERR_AQ_EMPTY;
+		goto clean_rq_elem_err;
+	}
+
+	/* set next_to_use to head */
+	ntu = (u16)(rd32(hw, cq->rq.head) & cq->rq.head_mask);
+
+	if (ntu == ntc) {
+		/* nothing to do - shouldn't need to update ring's values */
+		ret_code = ICE_ERR_AQ_NO_WORK;
+		goto clean_rq_elem_out;
+	}
+
+	/* now clean the next descriptor */
+	desc = ICE_CTL_Q_DESC(cq->rq, ntc);
+	desc_idx = ntc;
+
+	flags = le16_to_cpu(desc->flags);
+	if (flags & ICE_AQ_FLAG_ERR) {
+		ret_code = ICE_ERR_AQ_ERROR;
+		cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval);
+		ice_debug(hw, ICE_DBG_AQ_MSG,
+			  "Control Receive Queue Event received with error 0x%x\n",
+			  cq->rq_last_status);
+	}
+	memcpy(&e->desc, desc, sizeof(e->desc));
+	datalen = le16_to_cpu(desc->datalen);
+	e->msg_len = min(datalen, e->buf_len);
+	if (e->msg_buf && e->msg_len)
+		memcpy(e->msg_buf, cq->rq.r.rq_bi[desc_idx].va, e->msg_len);
+
+	ice_debug(hw, ICE_DBG_AQ_MSG, "ARQ: desc and buffer:\n");
+
+	ice_debug_cq(hw, ICE_DBG_AQ_CMD, (void *)desc, e->msg_buf,
+		     cq->rq_buf_size);
+
+	/* Restore the original datalen and buffer address in the desc,
+	 * FW updates datalen to indicate the event message size
+	 */
+	bi = &cq->rq.r.rq_bi[ntc];
+	memset(desc, 0, sizeof(*desc));
+
+	desc->flags = cpu_to_le16(ICE_AQ_FLAG_BUF);
+	if (cq->rq_buf_size > ICE_AQ_LG_BUF)
+		desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB);
+	desc->datalen = cpu_to_le16(bi->size);
+	desc->params.generic.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
+	desc->params.generic.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
+
+	/* set tail = the last cleaned desc index. */
+	wr32(hw, cq->rq.tail, ntc);
+	/* ntc is updated to tail + 1 */
+	ntc++;
+	if (ntc == cq->num_rq_entries)
+		ntc = 0;
+	cq->rq.next_to_clean = ntc;
+	cq->rq.next_to_use = ntu;
+
+clean_rq_elem_out:
+	/* Set pending if needed, unlock and return */
+	if (pending)
+		*pending = (u16)((ntc > ntu ? cq->rq.count : 0) + (ntu - ntc));
+clean_rq_elem_err:
+	mutex_unlock(&cq->rq_lock);
+
+	return ret_code;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index b5306e8a5a0d..ea02b89243e2 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -67,6 +67,14 @@ struct ice_sq_cd {
 
 #define ICE_CTL_Q_DETAILS(R, i) (&(((struct ice_sq_cd *)((R).cmd_buf))[i]))
 
+/* rq event information */
+struct ice_rq_event_info {
+	struct ice_aq_desc desc;
+	u16 msg_len;
+	u16 buf_len;
+	u8 *msg_buf;
+};
+
 /* Control Queue information */
 struct ice_ctl_q_info {
 	enum ice_ctl_q qtype;
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 893d5e967e66..446a8bbef488 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -14,6 +14,12 @@
 #define PF_FW_ARQLEN			0x00080280
 #define PF_FW_ARQLEN_ARQLEN_S		0
 #define PF_FW_ARQLEN_ARQLEN_M		ICE_M(0x3FF, PF_FW_ARQLEN_ARQLEN_S)
+#define PF_FW_ARQLEN_ARQVFE_S		28
+#define PF_FW_ARQLEN_ARQVFE_M		BIT(PF_FW_ARQLEN_ARQVFE_S)
+#define PF_FW_ARQLEN_ARQOVFL_S		29
+#define PF_FW_ARQLEN_ARQOVFL_M		BIT(PF_FW_ARQLEN_ARQOVFL_S)
+#define PF_FW_ARQLEN_ARQCRIT_S		30
+#define PF_FW_ARQLEN_ARQCRIT_M		BIT(PF_FW_ARQLEN_ARQCRIT_S)
 #define PF_FW_ARQLEN_ARQENABLE_S	31
 #define PF_FW_ARQLEN_ARQENABLE_M	BIT(PF_FW_ARQLEN_ARQENABLE_S)
 #define PF_FW_ARQT			0x00080480
@@ -25,6 +31,12 @@
 #define PF_FW_ATQLEN			0x00080200
 #define PF_FW_ATQLEN_ATQLEN_S		0
 #define PF_FW_ATQLEN_ATQLEN_M		ICE_M(0x3FF, PF_FW_ATQLEN_ATQLEN_S)
+#define PF_FW_ATQLEN_ATQVFE_S		28
+#define PF_FW_ATQLEN_ATQVFE_M		BIT(PF_FW_ATQLEN_ATQVFE_S)
+#define PF_FW_ATQLEN_ATQOVFL_S		29
+#define PF_FW_ATQLEN_ATQOVFL_M		BIT(PF_FW_ATQLEN_ATQOVFL_S)
+#define PF_FW_ATQLEN_ATQCRIT_S		30
+#define PF_FW_ATQLEN_ATQCRIT_M		BIT(PF_FW_ATQLEN_ATQCRIT_S)
 #define PF_FW_ATQLEN_ATQENABLE_S	31
 #define PF_FW_ATQLEN_ATQENABLE_M	BIT(PF_FW_ATQLEN_ATQENABLE_S)
 #define PF_FW_ATQT			0x00080400
@@ -43,6 +55,57 @@
 #define PFGEN_CTRL			0x00091000
 #define PFGEN_CTRL_PFSWR_S		0
 #define PFGEN_CTRL_PFSWR_M		BIT(PFGEN_CTRL_PFSWR_S)
+#define PFHMC_ERRORDATA			0x00520500
+#define PFHMC_ERRORINFO			0x00520400
+#define GLINT_DYN_CTL(_INT)		(0x00160000 + ((_INT) * 4))
+#define GLINT_DYN_CTL_INTENA_S		0
+#define GLINT_DYN_CTL_INTENA_M		BIT(GLINT_DYN_CTL_INTENA_S)
+#define GLINT_DYN_CTL_CLEARPBA_S	1
+#define GLINT_DYN_CTL_CLEARPBA_M	BIT(GLINT_DYN_CTL_CLEARPBA_S)
+#define GLINT_DYN_CTL_ITR_INDX_S	3
+#define GLINT_DYN_CTL_SW_ITR_INDX_S	25
+#define GLINT_DYN_CTL_SW_ITR_INDX_M	ICE_M(0x3, GLINT_DYN_CTL_SW_ITR_INDX_S)
+#define GLINT_DYN_CTL_INTENA_MSK_S	31
+#define GLINT_DYN_CTL_INTENA_MSK_M	BIT(GLINT_DYN_CTL_INTENA_MSK_S)
+#define GLINT_ITR(_i, _INT)		(0x00154000 + ((_i) * 8192 + (_INT) * 4))
+#define PFINT_FW_CTL			0x0016C800
+#define PFINT_FW_CTL_MSIX_INDX_S	0
+#define PFINT_FW_CTL_MSIX_INDX_M	ICE_M(0x7FF, PFINT_FW_CTL_MSIX_INDX_S)
+#define PFINT_FW_CTL_ITR_INDX_S		11
+#define PFINT_FW_CTL_ITR_INDX_M		ICE_M(0x3, PFINT_FW_CTL_ITR_INDX_S)
+#define PFINT_FW_CTL_CAUSE_ENA_S	30
+#define PFINT_FW_CTL_CAUSE_ENA_M	BIT(PFINT_FW_CTL_CAUSE_ENA_S)
+#define PFINT_OICR			0x0016CA00
+#define PFINT_OICR_INTEVENT_S		0
+#define PFINT_OICR_INTEVENT_M		BIT(PFINT_OICR_INTEVENT_S)
+#define PFINT_OICR_HLP_RDY_S		14
+#define PFINT_OICR_HLP_RDY_M		BIT(PFINT_OICR_HLP_RDY_S)
+#define PFINT_OICR_CPM_RDY_S		15
+#define PFINT_OICR_CPM_RDY_M		BIT(PFINT_OICR_CPM_RDY_S)
+#define PFINT_OICR_ECC_ERR_S		16
+#define PFINT_OICR_ECC_ERR_M		BIT(PFINT_OICR_ECC_ERR_S)
+#define PFINT_OICR_MAL_DETECT_S		19
+#define PFINT_OICR_MAL_DETECT_M		BIT(PFINT_OICR_MAL_DETECT_S)
+#define PFINT_OICR_GRST_S		20
+#define PFINT_OICR_GRST_M		BIT(PFINT_OICR_GRST_S)
+#define PFINT_OICR_PCI_EXCEPTION_S	21
+#define PFINT_OICR_PCI_EXCEPTION_M	BIT(PFINT_OICR_PCI_EXCEPTION_S)
+#define PFINT_OICR_GPIO_S		22
+#define PFINT_OICR_GPIO_M		BIT(PFINT_OICR_GPIO_S)
+#define PFINT_OICR_STORM_DETECT_S	24
+#define PFINT_OICR_STORM_DETECT_M	BIT(PFINT_OICR_STORM_DETECT_S)
+#define PFINT_OICR_HMC_ERR_S		26
+#define PFINT_OICR_HMC_ERR_M		BIT(PFINT_OICR_HMC_ERR_S)
+#define PFINT_OICR_PE_CRITERR_S		28
+#define PFINT_OICR_PE_CRITERR_M		BIT(PFINT_OICR_PE_CRITERR_S)
+#define PFINT_OICR_CTL			0x0016CA80
+#define PFINT_OICR_CTL_MSIX_INDX_S	0
+#define PFINT_OICR_CTL_MSIX_INDX_M	ICE_M(0x7FF, PFINT_OICR_CTL_MSIX_INDX_S)
+#define PFINT_OICR_CTL_ITR_INDX_S	11
+#define PFINT_OICR_CTL_ITR_INDX_M	ICE_M(0x3, PFINT_OICR_CTL_ITR_INDX_S)
+#define PFINT_OICR_CTL_CAUSE_ENA_S	30
+#define PFINT_OICR_CTL_CAUSE_ENA_M	BIT(PFINT_OICR_CTL_CAUSE_ENA_S)
+#define PFINT_OICR_ENA			0x0016C900
 #define GLLAN_RCTL_0			0x002941F8
 #define GLNVM_FLA			0x000B6108
 #define GLNVM_FLA_LOCKED_S		6
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 953be26054ca..d93eaae5dc60 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -26,6 +26,294 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all), hw debug_mask (0x8XXXX
 MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)");
 #endif /* !CONFIG_DYNAMIC_DEBUG */
 
+static struct workqueue_struct *ice_wq;
+
+/**
+ * ice_search_res - Search the tracker for a block of resources
+ * @res: pointer to the resource
+ * @needed: size of the block needed
+ * @id: identifier to track owner
+ * Returns the base item index of the block, or -ENOMEM for error
+ */
+static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
+{
+	int start = res->search_hint;
+	int end = start;
+
+	id |= ICE_RES_VALID_BIT;
+
+	do {
+		/* skip already allocated entries */
+		if (res->list[end++] & ICE_RES_VALID_BIT) {
+			start = end;
+			if ((start + needed) > res->num_entries)
+				break;
+		}
+
+		if (end == (start + needed)) {
+			int i = start;
+
+			/* there was enough, so assign it to the requestor */
+			while (i != end)
+				res->list[i++] = id;
+
+			if (end == res->num_entries)
+				end = 0;
+
+			res->search_hint = end;
+			return start;
+		}
+	} while (1);
+
+	return -ENOMEM;
+}
+
+/**
+ * ice_get_res - get a block of resources
+ * @pf: board private structure
+ * @res: pointer to the resource
+ * @needed: size of the block needed
+ * @id: identifier to track owner
+ *
+ * Returns the base item index of the block, or -ENOMEM for error
+ * The search_hint trick and lack of advanced fit-finding only works
+ * because we're highly likely to have all the same sized requests.
+ * Linear search time and any fragmentation should be minimal.
+ */
+static int
+ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id)
+{
+	int ret;
+
+	if (!res || !pf)
+		return -EINVAL;
+
+	if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) {
+		dev_err(&pf->pdev->dev,
+			"param err: needed=%d, num_entries = %d id=0x%04x\n",
+			needed, res->num_entries, id);
+		return -EINVAL;
+	}
+
+	/* search based on search_hint */
+	ret = ice_search_res(res, needed, id);
+
+	if (ret < 0) {
+		/* previous search failed. Reset search hint and try again */
+		res->search_hint = 0;
+		ret = ice_search_res(res, needed, id);
+	}
+
+	return ret;
+}
+
+/**
+ * ice_free_res - free a block of resources
+ * @res: pointer to the resource
+ * @index: starting index previously returned by ice_get_res
+ * @id: identifier to track owner
+ * Returns number of resources freed
+ */
+static int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id)
+{
+	int count = 0;
+	int i;
+
+	if (!res || index >= res->num_entries)
+		return -EINVAL;
+
+	id |= ICE_RES_VALID_BIT;
+	for (i = index; i < res->num_entries && res->list[i] == id; i++) {
+		res->list[i] = 0;
+		count++;
+	}
+
+	return count;
+}
+
+/**
+ * __ice_clean_ctrlq - helper function to clean controlq rings
+ * @pf: ptr to struct ice_pf
+ * @q_type: specific Control queue type
+ */
+static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
+{
+	struct ice_rq_event_info event;
+	struct ice_hw *hw = &pf->hw;
+	struct ice_ctl_q_info *cq;
+	u16 pending, i = 0;
+	const char *qtype;
+	u32 oldval, val;
+
+	switch (q_type) {
+	case ICE_CTL_Q_ADMIN:
+		cq = &hw->adminq;
+		qtype = "Admin";
+		break;
+	default:
+		dev_warn(&pf->pdev->dev, "Unknown control queue type 0x%x\n",
+			 q_type);
+		return 0;
+	}
+
+	/* check for error indications - PF_xx_AxQLEN register layout for
+	 * FW/MBX/SB are identical so just use defines for PF_FW_AxQLEN.
+	 */
+	val = rd32(hw, cq->rq.len);
+	if (val & (PF_FW_ARQLEN_ARQVFE_M | PF_FW_ARQLEN_ARQOVFL_M |
+		   PF_FW_ARQLEN_ARQCRIT_M)) {
+		oldval = val;
+		if (val & PF_FW_ARQLEN_ARQVFE_M)
+			dev_dbg(&pf->pdev->dev,
+				"%s Receive Queue VF Error detected\n", qtype);
+		if (val & PF_FW_ARQLEN_ARQOVFL_M) {
+			dev_dbg(&pf->pdev->dev,
+				"%s Receive Queue Overflow Error detected\n",
+				qtype);
+		}
+		if (val & PF_FW_ARQLEN_ARQCRIT_M)
+			dev_dbg(&pf->pdev->dev,
+				"%s Receive Queue Critical Error detected\n",
+				qtype);
+		val &= ~(PF_FW_ARQLEN_ARQVFE_M | PF_FW_ARQLEN_ARQOVFL_M |
+			 PF_FW_ARQLEN_ARQCRIT_M);
+		if (oldval != val)
+			wr32(hw, cq->rq.len, val);
+	}
+
+	val = rd32(hw, cq->sq.len);
+	if (val & (PF_FW_ATQLEN_ATQVFE_M | PF_FW_ATQLEN_ATQOVFL_M |
+		   PF_FW_ATQLEN_ATQCRIT_M)) {
+		oldval = val;
+		if (val & PF_FW_ATQLEN_ATQVFE_M)
+			dev_dbg(&pf->pdev->dev,
+				"%s Send Queue VF Error detected\n", qtype);
+		if (val & PF_FW_ATQLEN_ATQOVFL_M) {
+			dev_dbg(&pf->pdev->dev,
+				"%s Send Queue Overflow Error detected\n",
+				qtype);
+		}
+		if (val & PF_FW_ATQLEN_ATQCRIT_M)
+			dev_dbg(&pf->pdev->dev,
+				"%s Send Queue Critical Error detected\n",
+				qtype);
+		val &= ~(PF_FW_ATQLEN_ATQVFE_M | PF_FW_ATQLEN_ATQOVFL_M |
+			 PF_FW_ATQLEN_ATQCRIT_M);
+		if (oldval != val)
+			wr32(hw, cq->sq.len, val);
+	}
+
+	event.buf_len = cq->rq_buf_size;
+	event.msg_buf = devm_kzalloc(&pf->pdev->dev, event.buf_len,
+				     GFP_KERNEL);
+	if (!event.msg_buf)
+		return 0;
+
+	do {
+		enum ice_status ret;
+
+		ret = ice_clean_rq_elem(hw, cq, &event, &pending);
+		if (ret == ICE_ERR_AQ_NO_WORK)
+			break;
+		if (ret) {
+			dev_err(&pf->pdev->dev,
+				"%s Receive Queue event error %d\n", qtype,
+				ret);
+			break;
+		}
+	} while (pending && (i++ < ICE_DFLT_IRQ_WORK));
+
+	devm_kfree(&pf->pdev->dev, event.msg_buf);
+
+	return pending && (i == ICE_DFLT_IRQ_WORK);
+}
+
+/**
+ * ice_clean_adminq_subtask - clean the AdminQ rings
+ * @pf: board private structure
+ */
+static void ice_clean_adminq_subtask(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+	u32 val;
+
+	if (!test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state))
+		return;
+
+	if (__ice_clean_ctrlq(pf, ICE_CTL_Q_ADMIN))
+		return;
+
+	clear_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state);
+
+	/* re-enable Admin queue interrupt causes */
+	val = rd32(hw, PFINT_FW_CTL);
+	wr32(hw, PFINT_FW_CTL, (val | PFINT_FW_CTL_CAUSE_ENA_M));
+
+	ice_flush(hw);
+}
+
+/**
+ * ice_service_task_schedule - schedule the service task to wake up
+ * @pf: board private structure
+ *
+ * If not already scheduled, this puts the task into the work queue.
+ */
+static void ice_service_task_schedule(struct ice_pf *pf)
+{
+	if (!test_bit(__ICE_DOWN, pf->state) &&
+	    !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state))
+		queue_work(ice_wq, &pf->serv_task);
+}
+
+/**
+ * ice_service_task_complete - finish up the service task
+ * @pf: board private structure
+ */
+static void ice_service_task_complete(struct ice_pf *pf)
+{
+	WARN_ON(!test_bit(__ICE_SERVICE_SCHED, pf->state));
+
+	/* force memory (pf->state) to sync before next service task */
+	smp_mb__before_atomic();
+	clear_bit(__ICE_SERVICE_SCHED, pf->state);
+}
+
+/**
+ * ice_service_timer - timer callback to schedule service task
+ * @t: pointer to timer_list
+ */
+static void ice_service_timer(struct timer_list *t)
+{
+	struct ice_pf *pf = from_timer(pf, t, serv_tmr);
+
+	mod_timer(&pf->serv_tmr, round_jiffies(pf->serv_tmr_period + jiffies));
+	ice_service_task_schedule(pf);
+}
+
+/**
+ * ice_service_task - manage and run subtasks
+ * @work: pointer to work_struct contained by the PF struct
+ */
+static void ice_service_task(struct work_struct *work)
+{
+	struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
+	unsigned long start_time = jiffies;
+
+	/* subtasks */
+	ice_clean_adminq_subtask(pf);
+
+	/* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */
+	ice_service_task_complete(pf);
+
+	/* If the tasks have taken longer than one service timer period
+	 * or there is more work to be done, reset the service timer to
+	 * schedule the service task now.
+	 */
+	if (time_after(jiffies, (start_time + pf->serv_tmr_period)) ||
+	    test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state))
+		mod_timer(&pf->serv_tmr, jiffies);
+}
+
 /**
  * ice_set_ctrlq_len - helper function to set controlq length
  * @hw: pointer to the hw instance
@@ -39,6 +327,361 @@ static void ice_set_ctrlq_len(struct ice_hw *hw)
 }
 
 /**
+ * ice_ena_misc_vector - enable the non-queue interrupts
+ * @pf: board private structure
+ */
+static void ice_ena_misc_vector(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+	u32 val;
+
+	/* clear things first */
+	wr32(hw, PFINT_OICR_ENA, 0);	/* disable all */
+	rd32(hw, PFINT_OICR);		/* read to clear */
+
+	val = (PFINT_OICR_HLP_RDY_M |
+	       PFINT_OICR_CPM_RDY_M |
+	       PFINT_OICR_ECC_ERR_M |
+	       PFINT_OICR_MAL_DETECT_M |
+	       PFINT_OICR_GRST_M |
+	       PFINT_OICR_PCI_EXCEPTION_M |
+	       PFINT_OICR_GPIO_M |
+	       PFINT_OICR_STORM_DETECT_M |
+	       PFINT_OICR_HMC_ERR_M);
+
+	wr32(hw, PFINT_OICR_ENA, val);
+
+	/* SW_ITR_IDX = 0, but don't change INTENA */
+	wr32(hw, GLINT_DYN_CTL(pf->oicr_idx),
+	     GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
+}
+
+/**
+ * ice_misc_intr - misc interrupt handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
+{
+	struct ice_pf *pf = (struct ice_pf *)data;
+	struct ice_hw *hw = &pf->hw;
+	irqreturn_t ret = IRQ_NONE;
+	u32 oicr, ena_mask;
+
+	set_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state);
+
+	oicr = rd32(hw, PFINT_OICR);
+	ena_mask = rd32(hw, PFINT_OICR_ENA);
+
+	if (!(oicr & PFINT_OICR_INTEVENT_M))
+		goto ena_intr;
+
+	if (oicr & PFINT_OICR_HMC_ERR_M) {
+		ena_mask &= ~PFINT_OICR_HMC_ERR_M;
+		dev_dbg(&pf->pdev->dev,
+			"HMC Error interrupt - info 0x%x, data 0x%x\n",
+			rd32(hw, PFHMC_ERRORINFO),
+			rd32(hw, PFHMC_ERRORDATA));
+	}
+
+	/* Report and mask off any remaining unexpected interrupts */
+	oicr &= ena_mask;
+	if (oicr) {
+		dev_dbg(&pf->pdev->dev, "unhandled interrupt oicr=0x%08x\n",
+			oicr);
+		/* If a critical error is pending there is no choice but to
+		 * reset the device.
+		 */
+		if (oicr & (PFINT_OICR_PE_CRITERR_M |
+			    PFINT_OICR_PCI_EXCEPTION_M |
+			    PFINT_OICR_ECC_ERR_M))
+			set_bit(__ICE_PFR_REQ, pf->state);
+
+		ena_mask &= ~oicr;
+	}
+	ret = IRQ_HANDLED;
+
+ena_intr:
+	/* re-enable interrupt causes that are not handled during this pass */
+	wr32(hw, PFINT_OICR_ENA, ena_mask);
+	if (!test_bit(__ICE_DOWN, pf->state)) {
+		ice_service_task_schedule(pf);
+		ice_irq_dynamic_ena(hw);
+	}
+
+	return ret;
+}
+
+/**
+ * ice_free_irq_msix_misc - Unroll misc vector setup
+ * @pf: board private structure
+ */
+static void ice_free_irq_msix_misc(struct ice_pf *pf)
+{
+	/* disable OICR interrupt */
+	wr32(&pf->hw, PFINT_OICR_ENA, 0);
+	ice_flush(&pf->hw);
+
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) {
+		synchronize_irq(pf->msix_entries[pf->oicr_idx].vector);
+		devm_free_irq(&pf->pdev->dev,
+			      pf->msix_entries[pf->oicr_idx].vector, pf);
+	}
+
+	ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID);
+}
+
+/**
+ * ice_req_irq_msix_misc - Setup the misc vector to handle non queue events
+ * @pf: board private structure
+ *
+ * This sets up the handler for MSIX 0, which is used to manage the
+ * non-queue interrupts, e.g. AdminQ and errors.  This is not used
+ * when in MSI or Legacy interrupt mode.
+ */
+static int ice_req_irq_msix_misc(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+	int oicr_idx, err = 0;
+	u8 itr_gran;
+	u32 val;
+
+	if (!pf->int_name[0])
+		snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
+			 dev_driver_string(&pf->pdev->dev),
+			 dev_name(&pf->pdev->dev));
+
+	/* reserve one vector in irq_tracker for misc interrupts */
+	oicr_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+	if (oicr_idx < 0)
+		return oicr_idx;
+
+	pf->oicr_idx = oicr_idx;
+
+	err = devm_request_irq(&pf->pdev->dev,
+			       pf->msix_entries[pf->oicr_idx].vector,
+			       ice_misc_intr, 0, pf->int_name, pf);
+	if (err) {
+		dev_err(&pf->pdev->dev,
+			"devm_request_irq for %s failed: %d\n",
+			pf->int_name, err);
+		ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+		return err;
+	}
+
+	ice_ena_misc_vector(pf);
+
+	val = (pf->oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
+	      (ICE_RX_ITR & PFINT_OICR_CTL_ITR_INDX_M) |
+	      PFINT_OICR_CTL_CAUSE_ENA_M;
+	wr32(hw, PFINT_OICR_CTL, val);
+
+	/* This enables Admin queue Interrupt causes */
+	val = (pf->oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) |
+	      (ICE_RX_ITR & PFINT_FW_CTL_ITR_INDX_M) |
+	      PFINT_FW_CTL_CAUSE_ENA_M;
+	wr32(hw, PFINT_FW_CTL, val);
+
+	itr_gran = hw->itr_gran_200;
+
+	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx),
+	     ITR_TO_REG(ICE_ITR_8K, itr_gran));
+
+	ice_flush(hw);
+	ice_irq_dynamic_ena(hw);
+
+	return 0;
+}
+
+/**
+ * ice_determine_q_usage - Calculate queue distribution
+ * @pf: board private structure
+ *
+ * Return -ENOMEM if we don't get enough queues for all ports
+ */
+static void ice_determine_q_usage(struct ice_pf *pf)
+{
+	u16 q_left_tx, q_left_rx;
+
+	q_left_tx = pf->hw.func_caps.common_cap.num_txq;
+	q_left_rx = pf->hw.func_caps.common_cap.num_rxq;
+
+	/* initial support for only 1 tx and 1 rx queue */
+	pf->num_lan_tx = 1;
+	pf->num_lan_rx = 1;
+
+	pf->q_left_tx = q_left_tx - pf->num_lan_tx;
+	pf->q_left_rx = q_left_rx - pf->num_lan_rx;
+}
+
+/**
+ * ice_deinit_pf - Unrolls initialziations done by ice_init_pf
+ * @pf: board private structure to initialize
+ */
+static void ice_deinit_pf(struct ice_pf *pf)
+{
+	if (pf->serv_tmr.function)
+		del_timer_sync(&pf->serv_tmr);
+	if (pf->serv_task.func)
+		cancel_work_sync(&pf->serv_task);
+	mutex_destroy(&pf->sw_mutex);
+	mutex_destroy(&pf->avail_q_mutex);
+}
+
+/**
+ * ice_init_pf - Initialize general software structures (struct ice_pf)
+ * @pf: board private structure to initialize
+ */
+static void ice_init_pf(struct ice_pf *pf)
+{
+	bitmap_zero(pf->flags, ICE_PF_FLAGS_NBITS);
+	set_bit(ICE_FLAG_MSIX_ENA, pf->flags);
+
+	mutex_init(&pf->sw_mutex);
+	mutex_init(&pf->avail_q_mutex);
+
+	/* Clear avail_[t|r]x_qs bitmaps (set all to avail) */
+	mutex_lock(&pf->avail_q_mutex);
+	bitmap_zero(pf->avail_txqs, ICE_MAX_TXQS);
+	bitmap_zero(pf->avail_rxqs, ICE_MAX_RXQS);
+	mutex_unlock(&pf->avail_q_mutex);
+
+	/* setup service timer and periodic service task */
+	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
+	pf->serv_tmr_period = HZ;
+	INIT_WORK(&pf->serv_task, ice_service_task);
+	clear_bit(__ICE_SERVICE_SCHED, pf->state);
+}
+
+/**
+ * ice_ena_msix_range - Request a range of MSIX vectors from the OS
+ * @pf: board private structure
+ *
+ * compute the number of MSIX vectors required (v_budget) and request from
+ * the OS. Return the number of vectors reserved or negative on failure
+ */
+static int ice_ena_msix_range(struct ice_pf *pf)
+{
+	int v_left, v_actual, v_budget = 0;
+	int needed, err, i;
+
+	v_left = pf->hw.func_caps.common_cap.num_msix_vectors;
+
+	/* reserve one vector for miscellaneous handler */
+	needed = 1;
+	v_budget += needed;
+	v_left -= needed;
+
+	/* reserve vectors for LAN traffic */
+	pf->num_lan_msix = min_t(int, num_online_cpus(), v_left);
+	v_budget += pf->num_lan_msix;
+
+	pf->msix_entries = devm_kcalloc(&pf->pdev->dev, v_budget,
+					sizeof(struct msix_entry), GFP_KERNEL);
+
+	if (!pf->msix_entries) {
+		err = -ENOMEM;
+		goto exit_err;
+	}
+
+	for (i = 0; i < v_budget; i++)
+		pf->msix_entries[i].entry = i;
+
+	/* actually reserve the vectors */
+	v_actual = pci_enable_msix_range(pf->pdev, pf->msix_entries,
+					 ICE_MIN_MSIX, v_budget);
+
+	if (v_actual < 0) {
+		dev_err(&pf->pdev->dev, "unable to reserve MSI-X vectors\n");
+		err = v_actual;
+		goto msix_err;
+	}
+
+	if (v_actual < v_budget) {
+		dev_warn(&pf->pdev->dev,
+			 "not enough vectors. requested = %d, obtained = %d\n",
+			 v_budget, v_actual);
+		if (v_actual >= (pf->num_lan_msix + 1)) {
+			pf->num_avail_msix = v_actual - (pf->num_lan_msix + 1);
+		} else if (v_actual >= 2) {
+			pf->num_lan_msix = 1;
+			pf->num_avail_msix = v_actual - 2;
+		} else {
+			pci_disable_msix(pf->pdev);
+			err = -ERANGE;
+			goto msix_err;
+		}
+	}
+
+	return v_actual;
+
+msix_err:
+	devm_kfree(&pf->pdev->dev, pf->msix_entries);
+	goto exit_err;
+
+exit_err:
+	pf->num_lan_msix = 0;
+	clear_bit(ICE_FLAG_MSIX_ENA, pf->flags);
+	return err;
+}
+
+/**
+ * ice_dis_msix - Disable MSI-X interrupt setup in OS
+ * @pf: board private structure
+ */
+static void ice_dis_msix(struct ice_pf *pf)
+{
+	pci_disable_msix(pf->pdev);
+	devm_kfree(&pf->pdev->dev, pf->msix_entries);
+	pf->msix_entries = NULL;
+	clear_bit(ICE_FLAG_MSIX_ENA, pf->flags);
+}
+
+/**
+ * ice_init_interrupt_scheme - Determine proper interrupt scheme
+ * @pf: board private structure to initialize
+ */
+static int ice_init_interrupt_scheme(struct ice_pf *pf)
+{
+	int vectors = 0;
+	ssize_t size;
+
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
+		vectors = ice_ena_msix_range(pf);
+	else
+		return -ENODEV;
+
+	if (vectors < 0)
+		return vectors;
+
+	/* set up vector assignment tracking */
+	size = sizeof(struct ice_res_tracker) + (sizeof(u16) * vectors);
+
+	pf->irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
+	if (!pf->irq_tracker) {
+		ice_dis_msix(pf);
+		return -ENOMEM;
+	}
+
+	pf->irq_tracker->num_entries = vectors;
+
+	return 0;
+}
+
+/**
+ * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme
+ * @pf: board private structure
+ */
+static void ice_clear_interrupt_scheme(struct ice_pf *pf)
+{
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
+		ice_dis_msix(pf);
+
+	devm_kfree(&pf->pdev->dev, pf->irq_tracker);
+	pf->irq_tracker = NULL;
+}
+
+/**
  * ice_probe - Device initialization routine
  * @pdev: PCI device information struct
  * @ent: entry in ice_pci_tbl
@@ -113,8 +756,70 @@ static int ice_probe(struct pci_dev *pdev,
 		 hw->fw_maj_ver, hw->fw_min_ver, hw->fw_build,
 		 hw->api_maj_ver, hw->api_min_ver);
 
+	ice_init_pf(pf);
+
+	ice_determine_q_usage(pf);
+
+	pf->num_alloc_vsi = min_t(u16, ICE_MAX_VSI_ALLOC,
+				  hw->func_caps.guaranteed_num_vsi);
+	if (!pf->num_alloc_vsi) {
+		err = -EIO;
+		goto err_init_pf_unroll;
+	}
+
+	pf->vsi = devm_kcalloc(&pdev->dev, pf->num_alloc_vsi,
+			       sizeof(struct ice_vsi *), GFP_KERNEL);
+	if (!pf->vsi) {
+		err = -ENOMEM;
+		goto err_init_pf_unroll;
+	}
+
+	err = ice_init_interrupt_scheme(pf);
+	if (err) {
+		dev_err(&pdev->dev,
+			"ice_init_interrupt_scheme failed: %d\n", err);
+		err = -EIO;
+		goto err_init_interrupt_unroll;
+	}
+
+	/* In case of MSIX we are going to setup the misc vector right here
+	 * to handle admin queue events etc. In case of legacy and MSI
+	 * the misc functionality and queue processing is combined in
+	 * the same vector and that gets setup at open.
+	 */
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
+		err = ice_req_irq_msix_misc(pf);
+		if (err) {
+			dev_err(&pdev->dev,
+				"setup of misc vector failed: %d\n", err);
+			goto err_init_interrupt_unroll;
+		}
+	}
+
+	/* create switch struct for the switch element created by FW on boot */
+	pf->first_sw = devm_kzalloc(&pdev->dev, sizeof(struct ice_sw),
+				    GFP_KERNEL);
+	if (!pf->first_sw) {
+		err = -ENOMEM;
+		goto err_msix_misc_unroll;
+	}
+
+	pf->first_sw->bridge_mode = BRIDGE_MODE_VEB;
+	pf->first_sw->pf = pf;
+
+	/* record the sw_id available for later use */
+	pf->first_sw->sw_id = hw->port_info->sw_id;
+
 	return 0;
 
+err_msix_misc_unroll:
+	ice_free_irq_msix_misc(pf);
+err_init_interrupt_unroll:
+	ice_clear_interrupt_scheme(pf);
+	devm_kfree(&pdev->dev, pf->vsi);
+err_init_pf_unroll:
+	ice_deinit_pf(pf);
+	ice_deinit_hw(hw);
 err_exit_unroll:
 	pci_disable_pcie_error_reporting(pdev);
 	return err;
@@ -133,6 +838,9 @@ static void ice_remove(struct pci_dev *pdev)
 
 	set_bit(__ICE_DOWN, pf->state);
 
+	ice_free_irq_msix_misc(pf);
+	ice_clear_interrupt_scheme(pf);
+	ice_deinit_pf(pf);
 	ice_deinit_hw(&pf->hw);
 	pci_disable_pcie_error_reporting(pdev);
 }
@@ -176,9 +884,17 @@ static int __init ice_module_init(void)
 	pr_info("%s - version %s\n", ice_driver_string, ice_drv_ver);
 	pr_info("%s\n", ice_copyright);
 
+	ice_wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, KBUILD_MODNAME);
+	if (!ice_wq) {
+		pr_err("Failed to create workqueue\n");
+		return -ENOMEM;
+	}
+
 	status = pci_register_driver(&ice_driver);
-	if (status)
+	if (status) {
 		pr_err("failed to register pci driver, err %d\n", status);
+		destroy_workqueue(ice_wq);
+	}
 
 	return status;
 }
@@ -193,6 +909,7 @@ module_init(ice_module_init);
 static void __exit ice_module_exit(void)
 {
 	pci_unregister_driver(&ice_driver);
+	destroy_workqueue(ice_wq);
 	pr_info("module unloaded\n");
 }
 module_exit(ice_module_exit);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
new file mode 100644
index 000000000000..7ceb69ea745e
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Intel Corporation. */
+
+#ifndef _ICE_TXRX_H_
+#define _ICE_TXRX_H_
+
+#define ICE_DFLT_IRQ_WORK	256
+
+/* this enum matches hardware bits and is meant to be used by DYN_CTLN
+ * registers and QINT registers or more generally anywhere in the manual
+ * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any
+ * register but instead is a special value meaning "don't update" ITR0/1/2.
+ */
+enum ice_dyn_idx_t {
+	ICE_IDX_ITR0 = 0,
+	ICE_IDX_ITR1 = 1,
+	ICE_IDX_ITR2 = 2,
+	ICE_ITR_NONE = 3	/* ITR_NONE must not be used as an index */
+};
+
+/* indices into GLINT_ITR registers */
+#define ICE_RX_ITR	ICE_IDX_ITR0
+#define ICE_ITR_DYNAMIC	0x8000  /* use top bit as a flag */
+#define ICE_ITR_8K	0x003E
+
+/* apply ITR HW granularity translation to program the HW registers */
+#define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> (itr_gran))
+
+#endif /* _ICE_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 6024c80bfa6b..2325be552a84 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -261,6 +261,17 @@ struct ice_hw {
 	u8 fw_min_ver;		/* firmware minor version */
 	u8 fw_patch;		/* firmware patch version */
 	u32 fw_build;		/* firmware build number */
+
+	/* minimum allowed value for different speeds */
+#define ICE_ITR_GRAN_MIN_200	1
+#define ICE_ITR_GRAN_MIN_100	1
+#define ICE_ITR_GRAN_MIN_50	2
+#define ICE_ITR_GRAN_MIN_25	4
+	/* ITR granularity in 1 us */
+	u8 itr_gran_200;
+	u8 itr_gran_100;
+	u8 itr_gran_50;
+	u8 itr_gran_25;
 };
 
 /* Checksum and Shadow RAM pointers */