net: ethtool: add support for configuring hds-thresh

The hds-thresh option configures the threshold value of
the header-data-split.
If a received packet size is larger than this threshold value, a packet
will be split into header and payload.
The header indicates TCP and UDP header, but it depends on driver spec.
The bnxt_en driver supports HDS(Header-Data-Split) configuration at
FW level, affecting TCP and UDP too.
So, If hds-thresh is set, it affects UDP and TCP packets.

Example:
   # ethtool -G <interface name> hds-thresh <value>

   # ethtool -G enp14s0f0np0 tcp-data-split on hds-thresh 256
   # ethtool -g enp14s0f0np0
   Ring parameters for enp14s0f0np0:
   Pre-set maximums:
   ...
   HDS thresh:  1023
   Current hardware settings:
   ...
   TCP data split:         on
   HDS thresh:  256

The default/min/max values are not defined in the ethtool so the drivers
should define themself.
The 0 value means that all TCP/UDP packets' header and payload
will be split.

Tested-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250114142852.3364986-3-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/netlink/specs/ethtool.yaml

@@ -332,6 +332,12 @@ attribute-sets:
       -
         name: tx-push-buf-len-max
         type: u32
+      -
+        name: hds-thresh
+        type: u32
+      -
+        name: hds-thresh-max
+        type: u32
 
   -
     name: mm-stat
@@ -1777,6 +1783,8 @@ operations:
             - rx-push
             - tx-push-buf-len
             - tx-push-buf-len-max
+            - hds-thresh
+            - hds-thresh-max
       dump: *ring-get-op
     -
       name: rings-set

Documentation/networking/ethtool-netlink.rst

@@ -899,6 +899,10 @@ Kernel response contents:
   ``ETHTOOL_A_RINGS_RX_PUSH``               u8      flag of RX Push mode
   ``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN``       u32     size of TX push buffer
   ``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX``   u32     max size of TX push buffer
+  ``ETHTOOL_A_RINGS_HDS_THRESH``            u32     threshold of
+                                                    header / data split
+  ``ETHTOOL_A_RINGS_HDS_THRESH_MAX``        u32     max threshold of
+                                                    header / data split
   =======================================   ======  ===========================
 
 ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with
@@ -941,10 +945,12 @@ Request contents:
   ``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_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_RX_PUSH``           u8      flag of RX Push mode
   ``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN``   u32     size of TX push buffer
+  ``ETHTOOL_A_RINGS_HDS_THRESH``        u32     threshold of header / data split
   ====================================  ======  ===========================
 
 Kernel checks that requested ring sizes do not exceed limits reported by
@@ -961,6 +967,10 @@ A bigger CQE can have more receive buffer pointers, and in turn the 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.
 
+``ETHTOOL_A_RINGS_HDS_THRESH`` specifies the threshold value of
+header / data split feature. If a received packet size is larger than this
+threshold value, header and data will be split.
+
 CHANNELS_GET
 ============
 

include/linux/ethtool.h

@@ -78,6 +78,9 @@ enum {
  * @cqe_size: Size of TX/RX completion queue event
  * @tx_push_buf_len: Size of TX push buffer
  * @tx_push_buf_max_len: Maximum allowed size of TX push buffer
+ * @hds_thresh: Packet size threshold for header data split (HDS)
+ * @hds_thresh_max: Maximum supported setting for @hds_threshold
+ *
  */
 struct kernel_ethtool_ringparam {
 	u32	rx_buf_len;
@@ -87,6 +90,8 @@ struct kernel_ethtool_ringparam {
 	u32	cqe_size;
 	u32	tx_push_buf_len;
 	u32	tx_push_buf_max_len;
+	u32	hds_thresh;
+	u32	hds_thresh_max;
 };
 
 /**
@@ -97,6 +102,7 @@ struct kernel_ethtool_ringparam {
  * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push
  * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len
  * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split
+ * @ETHTOOL_RING_USE_HDS_THRS: capture for setting header-data-split-thresh
  */
 enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_RX_BUF_LEN		= BIT(0),
@@ -105,6 +111,7 @@ enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_RX_PUSH		= BIT(3),
 	ETHTOOL_RING_USE_TX_PUSH_BUF_LEN	= BIT(4),
 	ETHTOOL_RING_USE_TCP_DATA_SPLIT		= BIT(5),
+	ETHTOOL_RING_USE_HDS_THRS		= BIT(6),
 };
 
 #define __ETH_RSS_HASH_BIT(bit)	((u32)1 << (bit))
@@ -1157,6 +1164,7 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev,
  * @rss_ctx:		XArray of custom RSS contexts
  * @rss_lock:		Protects entries in @rss_ctx.  May be taken from
  *			within RTNL.
+ * @hds_thresh:		HDS Threshold value.
  * @hds_config:		HDS value from userspace.
  * @wol_enabled:	Wake-on-LAN is enabled
  * @module_fw_flash_in_progress: Module firmware flashing is in progress.
@@ -1164,6 +1172,7 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev,
 struct ethtool_netdev_state {
 	struct xarray		rss_ctx;
 	struct mutex		rss_lock;
+	u32			hds_thresh;
 	u8			hds_config;
 	unsigned		wol_enabled:1;
 	unsigned		module_fw_flash_in_progress:1;

include/uapi/linux/ethtool_netlink_generated.h

@@ -155,6 +155,8 @@ enum {
 	ETHTOOL_A_RINGS_RX_PUSH,
 	ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN,
 	ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX,
+	ETHTOOL_A_RINGS_HDS_THRESH,
+	ETHTOOL_A_RINGS_HDS_THRESH_MAX,
 
 	__ETHTOOL_A_RINGS_CNT,
 	ETHTOOL_A_RINGS_MAX = (__ETHTOOL_A_RINGS_CNT - 1)

net/ethtool/netlink.h

@@ -456,7 +456,7 @@ extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANT
 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_TX_PUSH_BUF_LEN_MAX + 1];
+extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_HDS_THRESH_MAX + 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

@@ -61,7 +61,9 @@ static int rings_reply_size(const struct ethnl_req_info *req_base,
 	       nla_total_size(sizeof(u8))  +	/* _RINGS_TX_PUSH */
 	       nla_total_size(sizeof(u8))) +	/* _RINGS_RX_PUSH */
 	       nla_total_size(sizeof(u32)) +	/* _RINGS_TX_PUSH_BUF_LEN */
-	       nla_total_size(sizeof(u32));	/* _RINGS_TX_PUSH_BUF_LEN_MAX */
+	       nla_total_size(sizeof(u32)) +	/* _RINGS_TX_PUSH_BUF_LEN_MAX */
+	       nla_total_size(sizeof(u32)) +	/* _RINGS_HDS_THRESH */
+	       nla_total_size(sizeof(u32));	/* _RINGS_HDS_THRESH_MAX*/
 }
 
 static int rings_fill_reply(struct sk_buff *skb,
@@ -108,7 +110,12 @@ static int rings_fill_reply(struct sk_buff *skb,
 	     (nla_put_u32(skb, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX,
 			  kr->tx_push_buf_max_len) ||
 	      nla_put_u32(skb, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN,
-			  kr->tx_push_buf_len))))
+			  kr->tx_push_buf_len))) ||
+	    ((supported_ring_params & ETHTOOL_RING_USE_HDS_THRS) &&
+	     (nla_put_u32(skb, ETHTOOL_A_RINGS_HDS_THRESH,
+			  kr->hds_thresh) ||
+	      nla_put_u32(skb, ETHTOOL_A_RINGS_HDS_THRESH_MAX,
+			  kr->hds_thresh_max))))
 		return -EMSGSIZE;
 
 	return 0;
@@ -130,6 +137,7 @@ const struct nla_policy ethnl_rings_set_policy[] = {
 	[ETHTOOL_A_RINGS_TX_PUSH]		= NLA_POLICY_MAX(NLA_U8, 1),
 	[ETHTOOL_A_RINGS_RX_PUSH]		= NLA_POLICY_MAX(NLA_U8, 1),
 	[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN]	= { .type = NLA_U32 },
+	[ETHTOOL_A_RINGS_HDS_THRESH]		= { .type = NLA_U32 },
 };
 
 static int
@@ -155,6 +163,14 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info,
 		return -EOPNOTSUPP;
 	}
 
+	if (tb[ETHTOOL_A_RINGS_HDS_THRESH] &&
+	    !(ops->supported_ring_params & ETHTOOL_RING_USE_HDS_THRS)) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[ETHTOOL_A_RINGS_HDS_THRESH],
+				    "setting hds-thresh is not supported");
+		return -EOPNOTSUPP;
+	}
+
 	if (tb[ETHTOOL_A_RINGS_CQE_SIZE] &&
 	    !(ops->supported_ring_params & ETHTOOL_RING_USE_CQE_SIZE)) {
 		NL_SET_ERR_MSG_ATTR(info->extack,
@@ -223,6 +239,8 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
 			tb[ETHTOOL_A_RINGS_RX_PUSH], &mod);
 	ethnl_update_u32(&kernel_ringparam.tx_push_buf_len,
 			 tb[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN], &mod);
+	ethnl_update_u32(&kernel_ringparam.hds_thresh,
+			 tb[ETHTOOL_A_RINGS_HDS_THRESH], &mod);
 	if (!mod)
 		return 0;
 
@@ -243,6 +261,8 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
 		err_attr = tb[ETHTOOL_A_RINGS_RX_JUMBO];
 	else if (ringparam.tx_pending > ringparam.tx_max_pending)
 		err_attr = tb[ETHTOOL_A_RINGS_TX];
+	else if (kernel_ringparam.hds_thresh > kernel_ringparam.hds_thresh_max)
+		err_attr = tb[ETHTOOL_A_RINGS_HDS_THRESH];
 	else
 		err_attr = NULL;
 	if (err_attr) {
@@ -261,8 +281,10 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
 
 	ret = dev->ethtool_ops->set_ringparam(dev, &ringparam,
 					      &kernel_ringparam, info->extack);
-	if (!ret)
+	if (!ret) {
 		dev->ethtool->hds_config = kernel_ringparam.tcp_data_split;
+		dev->ethtool->hds_thresh = kernel_ringparam.hds_thresh;
+	}
 
 	return ret < 0 ? ret : 1;
 }