ibmvnic: Introduce indirect subordinate Command Response Queue buffer

This patch introduces the infrastructure to send batched subordinate
Command Response Queue descriptors, which are used by the ibmvnic
driver to send TX frame and RX buffer descriptors.
Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Acked-by: Lijun Pan <ljp@linux.ibm.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/ibm/ibmvnic.c

@@ -2858,6 +2858,7 @@ static int reset_one_sub_crq_queue(struct ibmvnic_adapter *adapter,
 	memset(scrq->msgs, 0, 4 * PAGE_SIZE);
 	atomic_set(&scrq->used, 0);
 	scrq->cur = 0;
+	scrq->ind_buf.index = 0;
 
 	rc = h_reg_sub_crq(adapter->vdev->unit_address, scrq->msg_token,
 			   4 * PAGE_SIZE, &scrq->crq_num, &scrq->hw_irq);
@@ -2909,6 +2910,11 @@ static void release_sub_crq_queue(struct ibmvnic_adapter *adapter,
 		}
 	}
 
+	dma_free_coherent(dev,
+			  IBMVNIC_IND_ARR_SZ,
+			  scrq->ind_buf.indir_arr,
+			  scrq->ind_buf.indir_dma);
+
 	dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE,
 			 DMA_BIDIRECTIONAL);
 	free_pages((unsigned long)scrq->msgs, 2);
@@ -2955,6 +2961,17 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
 
 	scrq->adapter = adapter;
 	scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs);
+	scrq->ind_buf.index = 0;
+
+	scrq->ind_buf.indir_arr =
+		dma_alloc_coherent(dev,
+				   IBMVNIC_IND_ARR_SZ,
+				   &scrq->ind_buf.indir_dma,
+				   GFP_KERNEL);
+
+	if (!scrq->ind_buf.indir_arr)
+		goto indir_failed;
+
 	spin_lock_init(&scrq->lock);
 
 	netdev_dbg(adapter->netdev,
@@ -2963,6 +2980,12 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
 
 	return scrq;
 
+indir_failed:
+	do {
+		rc = plpar_hcall_norets(H_FREE_SUB_CRQ,
+					adapter->vdev->unit_address,
+					scrq->crq_num);
+	} while (rc == H_BUSY || rc == H_IS_LONG_BUSY(rc));
 reg_failed:
 	dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE,
 			 DMA_BIDIRECTIONAL);

drivers/net/ethernet/ibm/ibmvnic.h

@@ -31,6 +31,8 @@
 #define IBMVNIC_BUFFS_PER_POOL	100
 #define IBMVNIC_MAX_QUEUES	16
 #define IBMVNIC_MAX_QUEUE_SZ   4096
+#define IBMVNIC_MAX_IND_DESCS  128
+#define IBMVNIC_IND_ARR_SZ	(IBMVNIC_MAX_IND_DESCS * 32)
 
 #define IBMVNIC_TSO_BUF_SZ	65536
 #define IBMVNIC_TSO_BUFS	64
@@ -861,6 +863,12 @@ union sub_crq {
 	struct ibmvnic_rx_buff_add_desc rx_add;
 };
 
+struct ibmvnic_ind_xmit_queue {
+	union sub_crq *indir_arr;
+	dma_addr_t indir_dma;
+	int index;
+};
+
 struct ibmvnic_sub_crq_queue {
 	union sub_crq *msgs;
 	int size, cur;
@@ -873,6 +881,7 @@ struct ibmvnic_sub_crq_queue {
 	spinlock_t lock;
 	struct sk_buff *rx_skb_top;
 	struct ibmvnic_adapter *adapter;
+	struct ibmvnic_ind_xmit_queue ind_buf;
 	atomic_t used;
 	char name[32];
 	u64 handle;