octeontx2-pf: Vary completion queue event size

Completion Queue Entry(CQE) is a descriptor written
by hardware to notify software about the send and
receive completion status. The CQE can be of size
128 or 512 bytes. A 512 bytes CQE can hold more receive
fragments pointers compared to 128 bytes CQE. This
patch enables to modify CQE size using:
<ethtool -G cqe-size N>.
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c

@@ -1048,7 +1048,7 @@ int otx2_config_nix(struct otx2_nic *pfvf)
 	struct nix_lf_alloc_rsp *rsp;
 	int err;
 
-	pfvf->qset.xqe_size = NIX_XQESZ_W16 ? 128 : 512;
+	pfvf->qset.xqe_size = pfvf->hw.xqe_size;
 
 	/* Get memory to put this msg */
 	nixlf = otx2_mbox_alloc_msg_nix_lf_alloc(&pfvf->mbox);
@@ -1061,7 +1061,7 @@ int otx2_config_nix(struct otx2_nic *pfvf)
 	nixlf->cq_cnt = pfvf->qset.cq_cnt;
 	nixlf->rss_sz = MAX_RSS_INDIR_TBL_SIZE;
 	nixlf->rss_grps = MAX_RSS_GROUPS;
-	nixlf->xqe_sz = NIX_XQESZ_W16;
+	nixlf->xqe_sz = pfvf->hw.xqe_size == 128 ? NIX_XQESZ_W16 : NIX_XQESZ_W64;
 	/* We don't know absolute NPA LF idx attached.
 	 * AF will replace 'RVU_DEFAULT_PF_FUNC' with
 	 * NPA LF attached to this RVU PF/VF.

drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h

@@ -181,6 +181,7 @@ struct otx2_hw {
 
 #define OTX2_DEFAULT_RBUF_LEN	2048
 	u16			rbuf_len;
+	u32			xqe_size;
 
 	/* NPA */
 	u32			stack_pg_ptrs;  /* No of ptrs per stack page */

drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c

@@ -372,6 +372,7 @@ static void otx2_get_ringparam(struct net_device *netdev,
 	ring->tx_max_pending = Q_COUNT(Q_SIZE_MAX);
 	ring->tx_pending = qs->sqe_cnt ? qs->sqe_cnt : Q_COUNT(Q_SIZE_4K);
 	kernel_ring->rx_buf_len = pfvf->hw.rbuf_len;
+	kernel_ring->cqe_size = pfvf->hw.xqe_size;
 }
 
 static int otx2_set_ringparam(struct net_device *netdev,
@@ -382,6 +383,7 @@ static int otx2_set_ringparam(struct net_device *netdev,
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 	u32 rx_buf_len = kernel_ring->rx_buf_len;
 	u32 old_rx_buf_len = pfvf->hw.rbuf_len;
+	u32 xqe_size = kernel_ring->cqe_size;
 	bool if_up = netif_running(netdev);
 	struct otx2_qset *qs = &pfvf->qset;
 	u32 rx_count, tx_count;
@@ -398,6 +400,12 @@ static int otx2_set_ringparam(struct net_device *netdev,
 		return -EINVAL;
 	}
 
+	if (xqe_size != 128 && xqe_size != 512) {
+		netdev_err(netdev,
+			   "Completion event size must be 128 or 512");
+		return -EINVAL;
+	}
+
 	/* Permitted lengths are 16 64 256 1K 4K 16K 64K 256K 1M  */
 	rx_count = ring->rx_pending;
 	/* On some silicon variants a skid or reserved CQEs are
@@ -416,7 +424,7 @@ static int otx2_set_ringparam(struct net_device *netdev,
 	tx_count = Q_COUNT(Q_SIZE(tx_count, 3));
 
 	if (tx_count == qs->sqe_cnt && rx_count == qs->rqe_cnt &&
-	    rx_buf_len == old_rx_buf_len)
+	    rx_buf_len == old_rx_buf_len && xqe_size == pfvf->hw.xqe_size)
 		return 0;
 
 	if (if_up)
@@ -427,6 +435,7 @@ static int otx2_set_ringparam(struct net_device *netdev,
 	qs->rqe_cnt = rx_count;
 
 	pfvf->hw.rbuf_len = rx_buf_len;
+	pfvf->hw.xqe_size = xqe_size;
 
 	if (if_up)
 		return netdev->netdev_ops->ndo_open(netdev);
@@ -1222,7 +1231,8 @@ static int otx2_set_link_ksettings(struct net_device *netdev,
 static const struct ethtool_ops otx2_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
-	.supported_ring_params  = ETHTOOL_RING_USE_RX_BUF_LEN,
+	.supported_ring_params  = ETHTOOL_RING_USE_RX_BUF_LEN |
+				  ETHTOOL_RING_USE_CQE_SIZE,
 	.get_link		= otx2_get_link,
 	.get_drvinfo		= otx2_get_drvinfo,
 	.get_strings		= otx2_get_strings,
@@ -1342,7 +1352,8 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev,
 static const struct ethtool_ops otx2vf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
-	.supported_ring_params  = ETHTOOL_RING_USE_RX_BUF_LEN,
+	.supported_ring_params  = ETHTOOL_RING_USE_RX_BUF_LEN |
+				  ETHTOOL_RING_USE_CQE_SIZE,
 	.get_link		= otx2_get_link,
 	.get_drvinfo		= otx2vf_get_drvinfo,
 	.get_strings		= otx2vf_get_strings,

drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c

@@ -2585,6 +2585,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	hw->tot_tx_queues = qcount;
 	hw->max_queues = qcount;
 	hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN;
+	/* Use CQE of 128 byte descriptor size by default */
+	hw->xqe_size = 128;
 
 	num_vec = pci_msix_vec_count(pdev);
 	hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE,

drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c

@@ -572,6 +572,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	hw->max_queues = qcount;
 	hw->tot_tx_queues = qcount;
 	hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN;
+	/* Use CQE of 128 byte descriptor size by default */
+	hw->xqe_size = 128;
 
 	hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE,
 					  GFP_KERNEL);