From: Taehee Yoo <ap420073@gmail.com>
To: davem@davemloft.net, kuba@kernel.org, pabeni@redhat.com,
edumazet@google.com, netdev@vger.kernel.org,
almasrymina@google.com, donald.hunter@gmail.com, corbet@lwn.net,
michael.chan@broadcom.com, andrew+netdev@lunn.ch,
hawk@kernel.org, ilias.apalodimas@linaro.org, ast@kernel.org,
daniel@iogearbox.net, john.fastabend@gmail.com, dw@davidwei.uk,
sdf@fomichev.me, asml.silence@gmail.com, brett.creeley@amd.com,
linux-doc@vger.kernel.org
Cc: kory.maincent@bootlin.com, maxime.chevallier@bootlin.com,
danieller@nvidia.com, hengqi@linux.alibaba.com,
ecree.xilinx@gmail.com, przemyslaw.kitszel@intel.com,
hkallweit1@gmail.com, ahmed.zaki@intel.com,
rrameshbabu@nvidia.com, idosch@nvidia.com, jiri@resnulli.us,
bigeasy@linutronix.de, lorenzo@kernel.org, jdamato@fastly.com,
aleksander.lobakin@intel.com, kaiyuanz@google.com,
willemb@google.com, daniel.zahka@gmail.com, ap420073@gmail.com
Subject: [PATCH net-next v8 02/10] net: ethtool: add support for configuring hds-thresh
Date: Sat, 11 Jan 2025 14:45:05 +0000 [thread overview]
Message-ID: <20250111144513.1289403-3-ap420073@gmail.com> (raw)
In-Reply-To: <20250111144513.1289403-1-ap420073@gmail.com>
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>
---
v8:
- Make the handling of hds_thresh similar to hds_config.
- Update comments of hds_thresh and hds_thresh_max.
v7:
- Do not export dev_xdp_sb_prog_count().
- Remove dev_xdp_sb_prog_count().
- Use NL_SET_ERR_MSG_ATTR() instead of NL_SET_ERR_MSG().
- Change location of hds-thresh size check logic.
v6:
- Update ethtool_netlink_generated.h
- Use "HDS" instead of "HEADER_DATA_SPLIT"
- Add Test tag from Andy.
v5:
- No changes.
v4:
- Fix 80 charactor wrap.
- Rename from tcp-data-split-thresh to header-data-split-thresh
- Add description about overhead of HDS.
- Add ETHTOOL_RING_USE_HDS_THRS flag.
- Add dev_xdp_sb_prog_count() helper.
- Add Test tag from Stanislav.
v3:
- Fix documentation and ynl
- Update error messages
- Validate configuration of tcp-data-split and tcp-data-split-thresh
v2:
- Patch added.
Documentation/netlink/specs/ethtool.yaml | 8 ++++++
Documentation/networking/ethtool-netlink.rst | 10 +++++++
include/linux/ethtool.h | 9 ++++++
.../uapi/linux/ethtool_netlink_generated.h | 2 ++
net/ethtool/netlink.h | 2 +-
net/ethtool/rings.c | 28 +++++++++++++++++--
6 files changed, 55 insertions(+), 4 deletions(-)
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 60f85fbf4156..66be04013048 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/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
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index a7ba6368a4d5..ef1d1750f960 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/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
============
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 4e451084d58a..45d8f107b42e 100644
--- a/include/linux/ethtool.h
+++ b/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))
@@ -1134,6 +1141,7 @@ 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.
@@ -1141,6 +1149,7 @@ 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;
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index 43993a2d68e5..2e17ff348f89 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/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)
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 0a09298fff92..c523b763efa3 100644
--- a/net/ethtool/netlink.h
+++ b/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];
diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c
index b2a2586b241f..a381913a19f0 100644
--- a/net/ethtool/rings.c
+++ b/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;
}
--
2.34.1
next prev parent reply other threads:[~2025-01-11 14:46 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-01-11 14:45 [PATCH net-next v8 0/10] bnxt_en: implement tcp-data-split and thresh option Taehee Yoo
2025-01-11 14:45 ` [PATCH net-next v8 01/10] net: ethtool: add hds_config member in ethtool_netdev_state Taehee Yoo
2025-01-11 14:45 ` Taehee Yoo [this message]
2025-01-11 14:45 ` [PATCH net-next v8 03/10] net: devmem: add ring parameter filtering Taehee Yoo
2025-01-11 14:45 ` [PATCH net-next v8 04/10] net: ethtool: " Taehee Yoo
2025-01-11 14:45 ` [PATCH net-next v8 05/10] net: disallow setup single buffer XDP when tcp-data-split is enabled Taehee Yoo
2025-01-11 14:45 ` [PATCH net-next v8 06/10] bnxt_en: add support for rx-copybreak ethtool command Taehee Yoo
2025-01-11 14:45 ` [PATCH net-next v8 07/10] bnxt_en: add support for tcp-data-split " Taehee Yoo
2025-01-11 14:45 ` [PATCH net-next v8 08/10] bnxt_en: add support for hds-thresh " Taehee Yoo
2025-01-11 14:45 ` [PATCH net-next v8 09/10] netdevsim: add HDS feature Taehee Yoo
2025-01-11 14:45 ` [PATCH net-next v8 10/10] selftest: net-drv: hds: add test for " Taehee Yoo
2025-01-13 23:08 ` [PATCH net-next v8 0/10] bnxt_en: implement tcp-data-split and thresh option Jakub Kicinski
2025-01-14 3:20 ` Taehee Yoo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250111144513.1289403-3-ap420073@gmail.com \
--to=ap420073@gmail.com \
--cc=ahmed.zaki@intel.com \
--cc=aleksander.lobakin@intel.com \
--cc=almasrymina@google.com \
--cc=andrew+netdev@lunn.ch \
--cc=asml.silence@gmail.com \
--cc=ast@kernel.org \
--cc=bigeasy@linutronix.de \
--cc=brett.creeley@amd.com \
--cc=corbet@lwn.net \
--cc=daniel.zahka@gmail.com \
--cc=daniel@iogearbox.net \
--cc=danieller@nvidia.com \
--cc=davem@davemloft.net \
--cc=donald.hunter@gmail.com \
--cc=dw@davidwei.uk \
--cc=ecree.xilinx@gmail.com \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=hengqi@linux.alibaba.com \
--cc=hkallweit1@gmail.com \
--cc=idosch@nvidia.com \
--cc=ilias.apalodimas@linaro.org \
--cc=jdamato@fastly.com \
--cc=jiri@resnulli.us \
--cc=john.fastabend@gmail.com \
--cc=kaiyuanz@google.com \
--cc=kory.maincent@bootlin.com \
--cc=kuba@kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=lorenzo@kernel.org \
--cc=maxime.chevallier@bootlin.com \
--cc=michael.chan@broadcom.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=przemyslaw.kitszel@intel.com \
--cc=rrameshbabu@nvidia.com \
--cc=sdf@fomichev.me \
--cc=willemb@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).