dmaengine: idxd: assign MSIX vectors to each WQ rather than roundrobin

IOPS increased when changing MSIX vector to per WQ from roundrobin.
Allows descriptor to be completed by the submitter improves caching
locality.
Suggested-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Link: https://lore.kernel.org/r/162456717326.1130457.15258077196523268356.stgit@djiang5-desk3.ch.intel.comSigned-off-by: Vinod Koul <vkoul@kernel.org>

drivers/dma/idxd/idxd.h

@@ -153,7 +153,6 @@ struct idxd_wq {
 	enum idxd_wq_state state;
 	unsigned long flags;
 	union wqcfg *wqcfg;
-	u32 vec_ptr;		/* interrupt steering */
 	struct dsa_hw_desc **hw_descs;
 	int num_descs;
 	union {
@@ -290,7 +289,6 @@ struct idxd_desc {
 	struct list_head list;
 	int id;
 	int cpu;
-	unsigned int vector;
 	struct idxd_wq *wq;
 };
 

drivers/dma/idxd/submit.c

@@ -22,22 +22,13 @@ static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu)
 		desc->hw->pasid = idxd->pasid;
 
 	/*
-	 * Descriptor completion vectors are 1...N for MSIX. We will round
-	 * robin through the N vectors.
+	 * On host, MSIX vecotr 0 is used for misc interrupt. Therefore when we match
+	 * vector 1:1 to the WQ id, we need to add 1
 	 */
-	wq->vec_ptr = (wq->vec_ptr % idxd->num_wq_irqs) + 1;
-	if (!idxd->int_handles) {
-		desc->hw->int_handle = wq->vec_ptr;
-	} else {
-		desc->vector = wq->vec_ptr;
-		/*
-		 * int_handles are only for descriptor completion. However for device
-		 * MSIX enumeration, vec 0 is used for misc interrupts. Therefore even
-		 * though we are rotating through 1...N for descriptor interrupts, we
-		 * need to acqurie the int_handles from 0..N-1.
-		 */
-		desc->hw->int_handle = idxd->int_handles[desc->vector - 1];
-	}
+	if (!idxd->int_handles)
+		desc->hw->int_handle = wq->id + 1;
+	else
+		desc->hw->int_handle = idxd->int_handles[wq->id];
 
 	return desc;
 }
@@ -130,19 +121,8 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	 * Pending the descriptor to the lockless list for the irq_entry
 	 * that we designated the descriptor to.
 	 */
-	if (desc->hw->flags & IDXD_OP_FLAG_RCI) {
-		int vec;
-
-		/*
-		 * If the driver is on host kernel, it would be the value
-		 * assigned to interrupt handle, which is index for MSIX
-		 * vector. If it's guest then can't use the int_handle since
-		 * that is the index to IMS for the entire device. The guest
-		 * device local index will be used.
-		 */
-		vec = !idxd->int_handles ? desc->hw->int_handle : desc->vector;
-		llist_add(&desc->llnode, &idxd->irq_entries[vec].pending_llist);
-	}
+	if (desc->hw->flags & IDXD_OP_FLAG_RCI)
+		llist_add(&desc->llnode, &idxd->irq_entries[wq->id + 1].pending_llist);
 
 	return 0;
 }