net: ethtool: extend ringparam set/get APIs for tx_push

Currently tx push is a standard driver feature which controls use of a fast
path descriptor push. So this patch extends the ringparam APIs and data
structures to support set/get tx push by ethtool -G/g.

Signed-off-by: Jie Wang <wangjie125@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>

 Conflicts:
	net/ethtool/netlink.h

Documentation/networking/ethtool-netlink.rst

@@ -819,6 +819,7 @@ Kernel response contents:
   ``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_TX_PUSH``           u8      flag of TX Push mode
   ====================================  ======  ===========================
 
 ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with
@@ -828,6 +829,12 @@ separate buffers. The device configuration must make it possible to receive
 full memory pages of data, for example because MTU is high enough or through
 HW-GRO.
 
+``ETHTOOL_A_RINGS_TX_PUSH`` flag is used to enable descriptor fast
+path to send packets. In ordinary path, driver fills descriptors in DRAM and
+notifies NIC hardware. In fast path, driver pushes descriptors to the device
+through MMIO writes, thus reducing the latency. However, enabling this feature
+may increase the CPU cost. Drivers may enforce additional per-packet
+eligibility checks (e.g. on packet size).
 
 RINGS_SET
 =========
@@ -844,6 +851,7 @@ Request contents:
   ``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
+  ``ETHTOOL_A_RINGS_TX_PUSH``           u8      flag of TX Push mode
   ====================================  ======  ===========================
 
 Kernel checks that requested ring sizes do not exceed limits reported by

include/linux/ethtool.h

@@ -76,11 +76,13 @@ enum {
  * 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
+ * @tx_push: The flag of tx push mode
  * @cqe_size: Size of TX/RX completion queue event
  */
 struct kernel_ethtool_ringparam {
 	u32	rx_buf_len;
 	u8	tcp_data_split;
+	u8	tx_push;
 	u32	cqe_size;
 };
 
@@ -88,10 +90,12 @@ struct kernel_ethtool_ringparam {
  * 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
+ * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push
  */
 enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0),
 	ETHTOOL_RING_USE_CQE_SIZE   = BIT(1),
+	ETHTOOL_RING_USE_TX_PUSH    = BIT(2),
 };
 
 #define __ETH_RSS_HASH_BIT(bit)	((u32)1 << (bit))

include/uapi/linux/ethtool_netlink.h

@@ -317,6 +317,7 @@ enum {
 	ETHTOOL_A_RINGS_RX_BUF_LEN,                     /* u32 */
 	ETHTOOL_A_RINGS_TCP_DATA_SPLIT,			/* u8 */
 	ETHTOOL_A_RINGS_CQE_SIZE,			/* u32 */
+	ETHTOOL_A_RINGS_TX_PUSH,			/* u8 */
 
 	/* add new constants above here */
 	__ETHTOOL_A_RINGS_CNT,

net/ethtool/rings.c

@@ -64,7 +64,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base,
 	       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(u32));	/* _RINGS_CQE_SIZE */
+	       nla_total_size(sizeof(u32)  +	/* _RINGS_CQE_SIZE */
+	       nla_total_size(sizeof(u8)));	/* _RINGS_TX_PUSH */
 }
 
 static int rings_fill_reply(struct sk_buff *skb,
@@ -103,7 +104,8 @@ static int rings_fill_reply(struct sk_buff *skb,
 	     (nla_put_u8(skb, ETHTOOL_A_RINGS_TCP_DATA_SPLIT,
 			 kr->tcp_data_split))) ||
 	    (kr->cqe_size &&
-	     (nla_put_u32(skb, ETHTOOL_A_RINGS_CQE_SIZE, kr->cqe_size))))
+	     (nla_put_u32(skb, ETHTOOL_A_RINGS_CQE_SIZE, kr->cqe_size))) ||
+	    nla_put_u8(skb, ETHTOOL_A_RINGS_TX_PUSH, !!kr->tx_push))
 		return -EMSGSIZE;
 
 	return 0;
@@ -139,6 +141,7 @@ rings_set_policy[ETHTOOL_A_RINGS_MAX + 1] = {
 	[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),
+	[ETHTOOL_A_RINGS_TX_PUSH]		= NLA_POLICY_MAX(NLA_U8, 1),
 };
 
 int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info)
@@ -170,6 +173,15 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info)
 	if (!ops->get_ringparam || !ops->set_ringparam)
 		goto out_dev;
 
+	if (tb[ETHTOOL_A_RINGS_TX_PUSH] &&
+	    !(ops->supported_ring_params & ETHTOOL_RING_USE_TX_PUSH)) {
+		ret = -EOPNOTSUPP;
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[ETHTOOL_A_RINGS_TX_PUSH],
+				    "setting tx push not supported");
+		goto out_dev;
+	}
+
 	rtnl_lock();
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
@@ -186,6 +198,8 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info)
 			 tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod);
 	ethnl_update_u32(&kernel_ringparam.cqe_size,
 			 tb[ETHTOOL_A_RINGS_CQE_SIZE], &mod);
+	ethnl_update_u8(&kernel_ringparam.tx_push,
+			tb[ETHTOOL_A_RINGS_TX_PUSH], &mod);
 	ret = 0;
 	if (!mod)
 		goto out_ops;