From: Pavel Begunkov <asml.silence@gmail.com>
To: Jakub Kicinski <kuba@kernel.org>, netdev@vger.kernel.org
Cc: asml.silence@gmail.com, io-uring@vger.kernel.org,
Eric Dumazet <edumazet@google.com>,
Willem de Bruijn <willemb@google.com>,
Paolo Abeni <pabeni@redhat.com>,
andrew+netdev@lunn.ch, horms@kernel.org, davem@davemloft.net,
sdf@fomichev.me, almasrymina@google.com, dw@davidwei.uk,
michael.chan@broadcom.com, dtatulea@nvidia.com,
ap420073@gmail.com
Subject: [RFC v1 17/22] netdev: add support for setting rx-buf-len per queue
Date: Mon, 28 Jul 2025 12:04:21 +0100 [thread overview]
Message-ID: <4db7b749277d4c0723f448cb143dab66959d618c.1753694914.git.asml.silence@gmail.com> (raw)
In-Reply-To: <cover.1753694913.git.asml.silence@gmail.com>
From: Jakub Kicinski <kuba@kernel.org>
Zero-copy APIs increase the cost of buffer management. They also extend
this cost to user space applications which may be used to dealing with
much larger buffers. Allow setting rx-buf-len per queue, devices with
HW-GRO support can commonly fill buffers up to 32k (or rather 64k - 1
but that's not a power of 2..)
The implementation adds a new option to the netdev netlink, rather
than ethtool. The NIC-wide setting lives in ethtool ringparams so
one could argue that we should be extending the ethtool API.
OTOH netdev API is where we already have queue-get, and it's how
zero-copy applications bind memory providers.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
Documentation/netlink/specs/netdev.yaml | 15 ++++
include/net/netdev_queues.h | 5 ++
include/net/netlink.h | 19 +++++
include/uapi/linux/netdev.h | 2 +
net/core/netdev-genl-gen.c | 15 ++++
net/core/netdev-genl-gen.h | 1 +
net/core/netdev-genl.c | 92 +++++++++++++++++++++++++
net/core/netdev_config.c | 16 +++++
tools/include/uapi/linux/netdev.h | 2 +
9 files changed, 167 insertions(+)
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index c0ef6d0d7786..5dd1eb5909cd 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -324,6 +324,10 @@ attribute-sets:
doc: XSK information for this queue, if any.
type: nest
nested-attributes: xsk-info
+ -
+ name: rx-buf-len
+ doc: Per-queue configuration of ETHTOOL_A_RINGS_RX_BUF_LEN.
+ type: u32
-
name: qstats
doc: |
@@ -755,6 +759,17 @@ operations:
reply:
attributes:
- id
+ -
+ name: queue-set
+ doc: Set per-queue configurable options.
+ attribute-set: queue
+ do:
+ request:
+ attributes:
+ - ifindex
+ - type
+ - id
+ - rx-buf-len
kernel-family:
headers: [ "net/netdev_netlink.h"]
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index f75313fc78ba..cfd2d59861e1 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -38,6 +38,7 @@ struct netdev_config {
/* Same semantics as fields in struct netdev_config */
struct netdev_queue_config {
+ u32 rx_buf_len;
};
/* See the netdev.yaml spec for definition of each statistic */
@@ -140,6 +141,8 @@ void netdev_stat_queue_sum(struct net_device *netdev,
/**
* struct netdev_queue_mgmt_ops - netdev ops for queue management
*
+ * @supported_ring_params: ring params supported per queue (ETHTOOL_RING_USE_*).
+ *
* @ndo_queue_mem_size: Size of the struct that describes a queue's memory.
*
* @ndo_queue_cfg_defaults: (Optional) Populate queue config struct with
@@ -170,6 +173,8 @@ void netdev_stat_queue_sum(struct net_device *netdev,
* be called for an interface which is open.
*/
struct netdev_queue_mgmt_ops {
+ u32 supported_ring_params;
+
size_t ndo_queue_mem_size;
void (*ndo_queue_cfg_defaults)(struct net_device *dev,
int idx,
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 90a560dc167a..c892cae8f592 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -2186,6 +2186,25 @@ static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla)
return tmp;
}
+/**
+ * nla_update_u32() - update u32 value from NLA_U32 attribute
+ * @dst: value to update
+ * @attr: netlink attribute with new value or null
+ *
+ * Copy the u32 value from NLA_U32 netlink attribute @attr into variable
+ * pointed to by @dst; do nothing if @attr is null.
+ *
+ * Return: true if this function changed the value of @dst, otherwise false.
+ */
+static inline bool nla_update_u32(u32 *dst, const struct nlattr *attr)
+{
+ u32 old_val = *dst;
+
+ if (attr)
+ *dst = nla_get_u32(attr);
+ return *dst != old_val;
+}
+
/**
* nla_memdup - duplicate attribute memory (kmemdup)
* @src: netlink attribute to duplicate from
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 7eb9571786b8..98fa988c8db2 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -152,6 +152,7 @@ enum {
NETDEV_A_QUEUE_DMABUF,
NETDEV_A_QUEUE_IO_URING,
NETDEV_A_QUEUE_XSK,
+ NETDEV_A_QUEUE_RX_BUF_LEN,
__NETDEV_A_QUEUE_MAX,
NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
@@ -220,6 +221,7 @@ enum {
NETDEV_CMD_BIND_RX,
NETDEV_CMD_NAPI_SET,
NETDEV_CMD_BIND_TX,
+ NETDEV_CMD_QUEUE_SET,
__NETDEV_CMD_MAX,
NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 4fc44587f493..ac25584a829d 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -105,6 +105,14 @@ static const struct nla_policy netdev_bind_tx_nl_policy[NETDEV_A_DMABUF_FD + 1]
[NETDEV_A_DMABUF_FD] = { .type = NLA_U32, },
};
+/* NETDEV_CMD_QUEUE_SET - do */
+static const struct nla_policy netdev_queue_set_nl_policy[NETDEV_A_QUEUE_RX_BUF_LEN + 1] = {
+ [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+ [NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1),
+ [NETDEV_A_QUEUE_ID] = { .type = NLA_U32, },
+ [NETDEV_A_QUEUE_RX_BUF_LEN] = { .type = NLA_U32, },
+};
+
/* Ops table for netdev */
static const struct genl_split_ops netdev_nl_ops[] = {
{
@@ -203,6 +211,13 @@ static const struct genl_split_ops netdev_nl_ops[] = {
.maxattr = NETDEV_A_DMABUF_FD,
.flags = GENL_CMD_CAP_DO,
},
+ {
+ .cmd = NETDEV_CMD_QUEUE_SET,
+ .doit = netdev_nl_queue_set_doit,
+ .policy = netdev_queue_set_nl_policy,
+ .maxattr = NETDEV_A_QUEUE_RX_BUF_LEN,
+ .flags = GENL_CMD_CAP_DO,
+ },
};
static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index cf3fad74511f..b7f5e5d9fca9 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -35,6 +35,7 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info);
int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info);
int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_queue_set_doit(struct sk_buff *skb, struct genl_info *info);
enum {
NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 2afa7b2141aa..52ec8287e835 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -372,6 +372,30 @@ static int nla_put_napi_id(struct sk_buff *skb, const struct napi_struct *napi)
return 0;
}
+static int
+netdev_nl_queue_fill_cfg(struct sk_buff *rsp, struct net_device *netdev,
+ u32 q_idx, u32 q_type)
+{
+ struct netdev_queue_config *qcfg;
+
+ if (!netdev_need_ops_lock(netdev))
+ return 0;
+
+ qcfg = &netdev->cfg->qcfg[q_idx];
+ switch (q_type) {
+ case NETDEV_QUEUE_TYPE_RX:
+ if (qcfg->rx_buf_len &&
+ nla_put_u32(rsp, NETDEV_A_QUEUE_RX_BUF_LEN,
+ qcfg->rx_buf_len))
+ return -EMSGSIZE;
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
static int
netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
u32 q_idx, u32 q_type, const struct genl_info *info)
@@ -419,6 +443,9 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
break;
}
+ if (netdev_nl_queue_fill_cfg(rsp, netdev, q_idx, q_type))
+ goto nla_put_failure;
+
genlmsg_end(rsp, hdr);
return 0;
@@ -558,6 +585,71 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
return err;
}
+int netdev_nl_queue_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr * const *tb = info->attrs;
+ struct netdev_queue_config *qcfg;
+ u32 q_id, q_type, ifindex;
+ struct net_device *netdev;
+ bool mod;
+ int ret;
+
+ if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_ID) ||
+ GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_TYPE) ||
+ GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_IFINDEX))
+ return -EINVAL;
+
+ q_id = nla_get_u32(tb[NETDEV_A_QUEUE_ID]);
+ q_type = nla_get_u32(tb[NETDEV_A_QUEUE_TYPE]);
+ ifindex = nla_get_u32(tb[NETDEV_A_QUEUE_IFINDEX]);
+
+ if (q_type != NETDEV_QUEUE_TYPE_RX) {
+ /* Only Rx params exist right now */
+ NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_TYPE]);
+ return -EINVAL;
+ }
+
+ ret = 0;
+ netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
+ if (!netdev || !netif_device_present(netdev))
+ ret = -ENODEV;
+ else if (!netdev->queue_mgmt_ops)
+ ret = -EOPNOTSUPP;
+ if (ret) {
+ NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_IFINDEX]);
+ goto exit_unlock;
+ }
+
+ ret = netdev_nl_queue_validate(netdev, q_id, q_type);
+ if (ret) {
+ NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_ID]);
+ goto exit_unlock;
+ }
+
+ ret = netdev_reconfig_start(netdev);
+ if (ret)
+ goto exit_unlock;
+
+ qcfg = &netdev->cfg_pending->qcfg[q_id];
+ mod = nla_update_u32(&qcfg->rx_buf_len, tb[NETDEV_A_QUEUE_RX_BUF_LEN]);
+ if (!mod)
+ goto exit_free_cfg;
+
+ ret = netdev_rx_queue_restart(netdev, q_id, info->extack);
+ if (ret)
+ goto exit_free_cfg;
+
+ swap(netdev->cfg, netdev->cfg_pending);
+
+exit_free_cfg:
+ __netdev_free_config(netdev->cfg_pending);
+ netdev->cfg_pending = netdev->cfg;
+exit_unlock:
+ if (netdev)
+ netdev_unlock(netdev);
+ return ret;
+}
+
#define NETDEV_STAT_NOT_SET (~0ULL)
static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size)
diff --git a/net/core/netdev_config.c b/net/core/netdev_config.c
index fc700b77e4eb..ede02b77470e 100644
--- a/net/core/netdev_config.c
+++ b/net/core/netdev_config.c
@@ -67,11 +67,27 @@ int netdev_reconfig_start(struct net_device *dev)
void __netdev_queue_config(struct net_device *dev, int rxq,
struct netdev_queue_config *qcfg, bool pending)
{
+ const struct netdev_config *cfg;
+
+ cfg = pending ? dev->cfg_pending : dev->cfg;
+
memset(qcfg, 0, sizeof(*qcfg));
/* Get defaults from the driver, in case user config not set */
if (dev->queue_mgmt_ops->ndo_queue_cfg_defaults)
dev->queue_mgmt_ops->ndo_queue_cfg_defaults(dev, rxq, qcfg);
+
+ /* Set config based on device-level settings */
+ if (cfg->rx_buf_len)
+ qcfg->rx_buf_len = cfg->rx_buf_len;
+
+ /* Set config dedicated to this queue */
+ if (rxq >= 0) {
+ const struct netdev_queue_config *user_cfg = &cfg->qcfg[rxq];
+
+ if (user_cfg->rx_buf_len)
+ qcfg->rx_buf_len = user_cfg->rx_buf_len;
+ }
}
/**
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 7eb9571786b8..98fa988c8db2 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -152,6 +152,7 @@ enum {
NETDEV_A_QUEUE_DMABUF,
NETDEV_A_QUEUE_IO_URING,
NETDEV_A_QUEUE_XSK,
+ NETDEV_A_QUEUE_RX_BUF_LEN,
__NETDEV_A_QUEUE_MAX,
NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
@@ -220,6 +221,7 @@ enum {
NETDEV_CMD_BIND_RX,
NETDEV_CMD_NAPI_SET,
NETDEV_CMD_BIND_TX,
+ NETDEV_CMD_QUEUE_SET,
__NETDEV_CMD_MAX,
NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
--
2.49.0
next prev parent reply other threads:[~2025-07-28 11:03 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-28 11:04 [RFC v1 00/22] Large rx buffer support for zcrx Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 01/22] docs: ethtool: document that rx_buf_len must control payload lengths Pavel Begunkov
2025-07-28 18:11 ` Mina Almasry
2025-07-28 21:36 ` Mina Almasry
2025-08-01 23:13 ` Jakub Kicinski
2025-07-28 11:04 ` [RFC v1 02/22] net: ethtool: report max value for rx-buf-len Pavel Begunkov
2025-07-29 5:00 ` Subbaraya Sundeep
2025-07-28 11:04 ` [RFC v1 03/22] net: use zero value to restore rx_buf_len to default Pavel Begunkov
2025-07-29 5:03 ` Subbaraya Sundeep
2025-07-28 11:04 ` [RFC v1 04/22] net: clarify the meaning of netdev_config members Pavel Begunkov
2025-07-28 21:44 ` Mina Almasry
2025-08-01 23:14 ` Jakub Kicinski
2025-07-28 11:04 ` [RFC v1 05/22] net: add rx_buf_len to netdev config Pavel Begunkov
2025-07-28 21:50 ` Mina Almasry
2025-08-01 23:18 ` Jakub Kicinski
2025-07-28 11:04 ` [RFC v1 06/22] eth: bnxt: read the page size from the adapter struct Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 07/22] eth: bnxt: set page pool page order based on rx_page_size Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 08/22] eth: bnxt: support setting size of agg buffers via ethtool Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 09/22] net: move netdev_config manipulation to dedicated helpers Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 10/22] net: reduce indent of struct netdev_queue_mgmt_ops members Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 11/22] net: allocate per-queue config structs and pass them thru the queue API Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 12/22] net: pass extack to netdev_rx_queue_restart() Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 13/22] net: add queue config validation callback Pavel Begunkov
2025-07-28 22:26 ` Mina Almasry
2025-07-28 11:04 ` [RFC v1 14/22] eth: bnxt: always set the queue mgmt ops Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 15/22] eth: bnxt: store the rx buf size per queue Pavel Begunkov
2025-07-28 22:33 ` Mina Almasry
2025-08-01 23:20 ` Jakub Kicinski
2025-07-28 11:04 ` [RFC v1 16/22] eth: bnxt: adjust the fill level of agg queues with larger buffers Pavel Begunkov
2025-07-28 11:04 ` Pavel Begunkov [this message]
2025-07-28 23:10 ` [RFC v1 17/22] netdev: add support for setting rx-buf-len per queue Mina Almasry
2025-08-01 23:37 ` Jakub Kicinski
2025-07-28 11:04 ` [RFC v1 18/22] net: wipe the setting of deactived queues Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 19/22] eth: bnxt: use queue op config validate Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 20/22] eth: bnxt: support per queue configuration of rx-buf-len Pavel Begunkov
2025-07-28 11:04 ` [RFC v1 21/22] net: parametrise mp open with a queue config Pavel Begunkov
2025-08-02 0:10 ` Jakub Kicinski
2025-08-04 12:50 ` Pavel Begunkov
2025-08-05 22:43 ` Jakub Kicinski
2025-08-06 0:05 ` Jakub Kicinski
2025-08-06 16:48 ` Mina Almasry
2025-08-06 18:11 ` Jakub Kicinski
2025-08-06 18:30 ` Mina Almasry
2025-08-06 22:05 ` Jakub Kicinski
2025-07-28 11:04 ` [RFC v1 22/22] io_uring/zcrx: implement large rx buffer support Pavel Begunkov
2025-07-28 17:13 ` [RFC v1 00/22] Large rx buffer support for zcrx Stanislav Fomichev
2025-07-28 18:18 ` Pavel Begunkov
2025-07-28 20:21 ` Stanislav Fomichev
2025-07-28 21:28 ` Pavel Begunkov
2025-07-28 22:06 ` Stanislav Fomichev
2025-07-28 22:44 ` Pavel Begunkov
2025-07-29 16:33 ` Stanislav Fomichev
2025-07-30 14:16 ` Pavel Begunkov
2025-07-30 15:50 ` Stanislav Fomichev
2025-07-31 19:34 ` Mina Almasry
2025-07-31 19:57 ` Pavel Begunkov
2025-07-31 20:05 ` Mina Almasry
2025-08-01 9:48 ` Pavel Begunkov
2025-08-01 9:58 ` Pavel Begunkov
2025-07-28 23:22 ` Mina Almasry
2025-07-29 16:41 ` Stanislav Fomichev
2025-07-29 17:01 ` Mina Almasry
2025-07-28 18:54 ` Mina Almasry
2025-07-28 19:42 ` Pavel Begunkov
2025-07-28 20:23 ` Mina Almasry
2025-07-28 20:57 ` Pavel Begunkov
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=4db7b749277d4c0723f448cb143dab66959d618c.1753694914.git.asml.silence@gmail.com \
--to=asml.silence@gmail.com \
--cc=almasrymina@google.com \
--cc=andrew+netdev@lunn.ch \
--cc=ap420073@gmail.com \
--cc=davem@davemloft.net \
--cc=dtatulea@nvidia.com \
--cc=dw@davidwei.uk \
--cc=edumazet@google.com \
--cc=horms@kernel.org \
--cc=io-uring@vger.kernel.org \
--cc=kuba@kernel.org \
--cc=michael.chan@broadcom.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.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