Merge branch 'add-ethtool-support-for-completion-queue-event-size'

Subbaraya Sundeep says:

====================
Add ethtool support for completion queue event size

After a packet is sent or received by NIC then NIC posts
a completion queue event which consists of transmission status
(like send success or error) and received status(like
pointers to packet fragments). These completion events may
also use a ring similar to rx and tx rings. This patchset
introduces cqe-size ethtool parameter to modify the size
of the completion queue event if NIC hardware has that capability.
A bigger completion queue event can have more receive buffer pointers
inturn NIC can transfer a bigger frame from wire as long as
hardware(MAC) receive frame size limit is not exceeded.

Patch 1 adds support setting/getting cqe-size via
ethtool -G and ethtool -g.

Patch 2 includes octeontx2 driver changes to use
completion queue event size set from ethtool -G.
====================

Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

Documentation/networking/ethtool-netlink.rst

···
   ``ETHTOOL_A_RINGS_TX``                u32     size of TX ring
   ``ETHTOOL_A_RINGS_RX_BUF_LEN``        u32     size of buffers on the ring
   ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT``    u8      TCP header / data split
+  ``ETHTOOL_A_RINGS_CQE_SIZE``          u32     Size of TX/RX CQE
   ====================================  ======  ===========================
 
 ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with
···
   ``ETHTOOL_A_RINGS_RX_JUMBO``          u32     size of RX jumbo ring
   ``ETHTOOL_A_RINGS_TX``                u32     size of TX ring
   ``ETHTOOL_A_RINGS_RX_BUF_LEN``        u32     size of buffers on the ring
+  ``ETHTOOL_A_RINGS_CQE_SIZE``          u32     Size of TX/RX CQE
   ====================================  ======  ===========================
 
 Kernel checks that requested ring sizes do not exceed limits reported by
 driver. Driver may impose additional constraints and may not suspport all
 attributes.
 
+
+``ETHTOOL_A_RINGS_CQE_SIZE`` specifies the completion queue event size.
+Completion queue events(CQE) are the events posted by NIC to indicate the
+completion status of a packet when the packet is sent(like send success or
+error) or received(like pointers to packet fragments). The CQE size parameter
+enables to modify the CQE size other than default size if NIC supports it.
+A bigger CQE can have more receive buffer pointers inturn NIC can transfer
+a bigger frame from wire. Based on the NIC hardware, the overall completion
+queue size can be adjusted in the driver if CQE size is modified.
 
 CHANNELS_GET
 ============

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

···
 	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);
···
 	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

···
 
 #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

···
 	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,
···
 	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;
···
 	if (rx_buf_len && (rx_buf_len < 1536 || rx_buf_len > 32768)) {
 		netdev_err(netdev,
 			   "Receive buffer range is 1536 - 32768");
+		return -EINVAL;
+	}
+
+	if (xqe_size != 128 && xqe_size != 512) {
+		netdev_err(netdev,
+			   "Completion event size must be 128 or 512");
 		return -EINVAL;
 	}
 
···
 	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)
···
 	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);
···
 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,
···
 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

···
 	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

···
 	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);

include/linux/ethtool.h

···
  * struct kernel_ethtool_ringparam - RX/TX ring configuration
  * @rx_buf_len: Current length of buffers on the rx ring.
  * @tcp_data_split: Scatter packet headers and data to separate buffers
+ * @cqe_size: Size of TX/RX completion queue event
  */
 struct kernel_ethtool_ringparam {
 	u32	rx_buf_len;
 	u8	tcp_data_split;
+	u32	cqe_size;
 };
 
 /**
  * enum ethtool_supported_ring_param - indicator caps for setting ring params
  * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len
+ * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size
  */
 enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0),
+	ETHTOOL_RING_USE_CQE_SIZE   = BIT(1),
 };
 
 #define __ETH_RSS_HASH_BIT(bit)	((u32)1 << (bit))

include/uapi/linux/ethtool_netlink.h

···
 	ETHTOOL_A_RINGS_TX,				/* u32 */
 	ETHTOOL_A_RINGS_RX_BUF_LEN,                     /* u32 */
 	ETHTOOL_A_RINGS_TCP_DATA_SPLIT,			/* u8 */
+	ETHTOOL_A_RINGS_CQE_SIZE,			/* u32 */
 
 	/* add new constants above here */
 	__ETHTOOL_A_RINGS_CNT,

net/ethtool/netlink.h

···
 extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1];
 extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1];
 extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1];
-extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_RX_BUF_LEN + 1];
+extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_CQE_SIZE + 1];
 extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1];
 extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1];
 extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1];

net/ethtool/rings.c

···
 	       nla_total_size(sizeof(u32)) +	/* _RINGS_RX_JUMBO */
 	       nla_total_size(sizeof(u32)) +	/* _RINGS_TX */
 	       nla_total_size(sizeof(u32)) +	/* _RINGS_RX_BUF_LEN */
-	       nla_total_size(sizeof(u8));	/* _RINGS_TCP_DATA_SPLIT */
+	       nla_total_size(sizeof(u8))  +	/* _RINGS_TCP_DATA_SPLIT */
+	       nla_total_size(sizeof(u32));	/* _RINGS_CQE_SIZE */
 }
 
 static int rings_fill_reply(struct sk_buff *skb,
···
 	     (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, kr->rx_buf_len))) ||
 	    (kr->tcp_data_split &&
 	     (nla_put_u8(skb, ETHTOOL_A_RINGS_TCP_DATA_SPLIT,
-			 kr->tcp_data_split))))
+			 kr->tcp_data_split))) ||
+	    (kr->cqe_size &&
+	     (nla_put_u32(skb, ETHTOOL_A_RINGS_CQE_SIZE, kr->cqe_size))))
 		return -EMSGSIZE;
 
 	return 0;
···
 	[ETHTOOL_A_RINGS_RX_JUMBO]		= { .type = NLA_U32 },
 	[ETHTOOL_A_RINGS_TX]			= { .type = NLA_U32 },
 	[ETHTOOL_A_RINGS_RX_BUF_LEN]            = NLA_POLICY_MIN(NLA_U32, 1),
+	[ETHTOOL_A_RINGS_CQE_SIZE]		= NLA_POLICY_MIN(NLA_U32, 1),
 };
 
 int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info)
···
 	ethnl_update_u32(&ringparam.tx_pending, tb[ETHTOOL_A_RINGS_TX], &mod);
 	ethnl_update_u32(&kernel_ringparam.rx_buf_len,
 			 tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod);
+	ethnl_update_u32(&kernel_ringparam.cqe_size,
+			 tb[ETHTOOL_A_RINGS_CQE_SIZE], &mod);
 	ret = 0;
 	if (!mod)
 		goto out_ops;
···
 		NL_SET_ERR_MSG_ATTR(info->extack,
 				    tb[ETHTOOL_A_RINGS_RX_BUF_LEN],
 				    "setting rx buf len not supported");
+		goto out_ops;
+	}
+
+	if (kernel_ringparam.cqe_size &&
+	    !(ops->supported_ring_params & ETHTOOL_RING_USE_CQE_SIZE)) {
+		ret = -EOPNOTSUPP;
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[ETHTOOL_A_RINGS_CQE_SIZE],
+				    "setting cqe size not supported");
 		goto out_ops;
 	}