ibmvnic: Introduce batched RX buffer descriptor transmission

Utilize the H_SEND_SUB_CRQ_INDIRECT hypervisor call to send
multiple RX buffer descriptors to the device in one hypervisor
call operation. This change will reduce the number of hypervisor
calls and thus hypervisor call overhead needed to transmit
RX buffer descriptors to the device.

Signed-off-by: Thomas Falcon <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>

Author: tlfalcon

drivers/net/ethernet/ibm/ibmvnic.c

@@ -306,9 +306,11 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 	int count = pool->size - atomic_read(&pool->available);
 	u64 handle = adapter->rx_scrq[pool->index]->handle;
 	struct device *dev = &adapter->vdev->dev;
+	struct ibmvnic_ind_xmit_queue *ind_bufp;
+	struct ibmvnic_sub_crq_queue *rx_scrq;
+	union sub_crq *sub_crq;
 	int buffers_added = 0;
 	unsigned long lpar_rc;
-	union sub_crq sub_crq;
 	struct sk_buff *skb;
 	unsigned int offset;
 	dma_addr_t dma_addr;
@@ -320,6 +322,8 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 	if (!pool->active)
 		return;
 
+	rx_scrq = adapter->rx_scrq[pool->index];
+	ind_bufp = &rx_scrq->ind_buf;
 	for (i = 0; i < count; ++i) {
 		skb = alloc_skb(pool->buff_size, GFP_ATOMIC);
 		if (!skb) {
@@ -346,12 +350,13 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 		pool->rx_buff[index].pool_index = pool->index;
 		pool->rx_buff[index].size = pool->buff_size;
 
-		memset(&sub_crq, 0, sizeof(sub_crq));
-		sub_crq.rx_add.first = IBMVNIC_CRQ_CMD;
-		sub_crq.rx_add.correlator =
+		sub_crq = &ind_bufp->indir_arr[ind_bufp->index++];
+		memset(sub_crq, 0, sizeof(*sub_crq));
+		sub_crq->rx_add.first = IBMVNIC_CRQ_CMD;
+		sub_crq->rx_add.correlator =
 		    cpu_to_be64((u64)&pool->rx_buff[index]);
-		sub_crq.rx_add.ioba = cpu_to_be32(dma_addr);
-		sub_crq.rx_add.map_id = pool->long_term_buff.map_id;
+		sub_crq->rx_add.ioba = cpu_to_be32(dma_addr);
+		sub_crq->rx_add.map_id = pool->long_term_buff.map_id;
 
 		/* The length field of the sCRQ is defined to be 24 bits so the
 		 * buffer size needs to be left shifted by a byte before it is
@@ -361,29 +366,41 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 #ifdef __LITTLE_ENDIAN__
 		shift = 8;
 #endif
-		sub_crq.rx_add.len = cpu_to_be32(pool->buff_size << shift);
-
-		lpar_rc = send_subcrq(adapter, handle, &sub_crq);
-		if (lpar_rc != H_SUCCESS)
-			goto failure;
-
-		buffers_added++;
-		adapter->replenish_add_buff_success++;
+		sub_crq->rx_add.len = cpu_to_be32(pool->buff_size << shift);
 		pool->next_free = (pool->next_free + 1) % pool->size;
+		if (ind_bufp->index == IBMVNIC_MAX_IND_DESCS ||
+		    i == count - 1) {
+			lpar_rc =
+				send_subcrq_indirect(adapter, handle,
+						     (u64)ind_bufp->indir_dma,
+						     (u64)ind_bufp->index);
+			if (lpar_rc != H_SUCCESS)
+				goto failure;
+			buffers_added += ind_bufp->index;
+			adapter->replenish_add_buff_success += ind_bufp->index;
+			ind_bufp->index = 0;
+		}
 	}
 	atomic_add(buffers_added, &pool->available);
 	return;
 
 failure:
 	if (lpar_rc != H_PARAMETER && lpar_rc != H_CLOSED)
 		dev_err_ratelimited(dev, "rx: replenish packet buffer failed\n");
-	pool->free_map[pool->next_free] = index;
-	pool->rx_buff[index].skb = NULL;
-
-	dev_kfree_skb_any(skb);
-	adapter->replenish_add_buff_failure++;
-	atomic_add(buffers_added, &pool->available);
+	for (i = ind_bufp->index - 1; i >= 0; --i) {
+		struct ibmvnic_rx_buff *rx_buff;
 
+		pool->next_free = pool->next_free == 0 ?
+				  pool->size - 1 : pool->next_free - 1;
+		sub_crq = &ind_bufp->indir_arr[i];
+		rx_buff = (struct ibmvnic_rx_buff *)
+				be64_to_cpu(sub_crq->rx_add.correlator);
+		index = (int)(rx_buff - pool->rx_buff);
+		pool->free_map[pool->next_free] = index;
+		dev_kfree_skb_any(pool->rx_buff[index].skb);
+		pool->rx_buff[index].skb = NULL;
+	}
+	ind_bufp->index = 0;
 	if (lpar_rc == H_CLOSED || adapter->failover_pending) {
 		/* Disable buffer pool replenishment and report carrier off if
 		 * queue is closed or pending failover.