ice: Audit hotpath structures with pahole

Currently the ice_q_vector structure and ice_ring_container structure
are taking up more space than necessary due to cache alignment holes
and unnecessary variables respectively. This is not helping the
driver's performance. The following fixes were done to improve cache
alignment, reduce wasted space, and increase performance.

1. Remove the ice_latency_range enum as it is unused.
2. Remove the latency_range variable in the ice_ring_container structure.
3. Change the size of the itr_idx in the ice_ring_container structure
   from an int to an u16. This reduced the size of ice_ring_container
   structure to 32 Bytes so it has no holes or padding.
4. Re-arrange the ice_q_vector structure using pahole to align
   members as best as possible in regards to 64 Byte cache line size.
Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

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

@@ -294,20 +294,25 @@ struct ice_vsi {
 /* struct that defines an interrupt vector */
 struct ice_q_vector {
 	struct ice_vsi *vsi;
-	cpumask_t affinity_mask;
-	struct napi_struct napi;
-	struct ice_ring_container rx;
-	struct ice_ring_container tx;
-	struct irq_affinity_notify affinity_notify;
+
 	u16 v_idx;			/* index in the vsi->q_vector array. */
-	u8 num_ring_tx;			/* total number of Tx rings in vector */
 	u8 num_ring_rx;			/* total number of Rx rings in vector */
-	char name[ICE_INT_NAME_STR_LEN];
+	u8 num_ring_tx;			/* total number of Tx rings in vector */
+	u8 itr_countdown;		/* when 0 should adjust adaptive ITR */
 	/* in usecs, need to use ice_intrl_to_usecs_reg() before writing this
 	 * value to the device
 	 */
 	u8 intrl;
-	u8 itr_countdown;	/* when 0 should adjust adaptive ITR */
+
+	struct napi_struct napi;
+
+	struct ice_ring_container rx;
+	struct ice_ring_container tx;
+
+	cpumask_t affinity_mask;
+	struct irq_affinity_notify affinity_notify;
+
+	char name[ICE_INT_NAME_STR_LEN];
 } ____cacheline_internodealigned_in_smp;
 
 enum ice_pf_flags {

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

@@ -1820,7 +1820,6 @@ ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector, u16 vector)
 		rc->target_itr = ITR_TO_REG(rc->itr_setting);
 		rc->next_update = jiffies + 1;
 		rc->current_itr = rc->target_itr;
-		rc->latency_range = ICE_LOW_LATENCY;
 		wr32(hw, GLINT_ITR(rc->itr_idx, vector),
 		     ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S);
 	}
@@ -1835,7 +1834,6 @@ ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector, u16 vector)
 		rc->target_itr = ITR_TO_REG(rc->itr_setting);
 		rc->next_update = jiffies + 1;
 		rc->current_itr = rc->target_itr;
-		rc->latency_range = ICE_LOW_LATENCY;
 		wr32(hw, GLINT_ITR(rc->itr_idx, vector),
 		     ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S);
 	}

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

@@ -1323,7 +1323,7 @@ ice_update_itr(struct ice_q_vector *q_vector, struct ice_ring_container *rc)
  * @itr_idx: interrupt throttling index
  * @itr: interrupt throttling value in usecs
  */
-static u32 ice_buildreg_itr(int itr_idx, u16 itr)
+static u32 ice_buildreg_itr(u16 itr_idx, u16 itr)
 {
 	/* The itr value is reported in microseconds, and the register value is
 	 * recorded in 2 microsecond units. For this reason we only need to

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

@@ -184,21 +184,13 @@ struct ice_ring {
 	u16 next_to_alloc;
 } ____cacheline_internodealigned_in_smp;
 
-enum ice_latency_range {
-	ICE_LOWEST_LATENCY = 0,
-	ICE_LOW_LATENCY = 1,
-	ICE_BULK_LATENCY = 2,
-	ICE_ULTRA_LATENCY = 3,
-};
-
 struct ice_ring_container {
 	/* head of linked-list of rings */
 	struct ice_ring *ring;
 	unsigned long next_update;	/* jiffies value of next queue update */
 	unsigned int total_bytes;	/* total bytes processed this int */
 	unsigned int total_pkts;	/* total packets processed this int */
-	enum ice_latency_range latency_range;
-	int itr_idx;		/* index in the interrupt vector */
+	u16 itr_idx;		/* index in the interrupt vector */
 	u16 target_itr;		/* value in usecs divided by the hw->itr_gran */
 	u16 current_itr;	/* value in usecs divided by the hw->itr_gran */
 	/* high bit set means dynamic ITR, rest is used to store user