@@ -860,22 +860,24 @@ Request contents:
Kernel response contents:
- ==================================== ====== ===========================
- ``ETHTOOL_A_RINGS_HEADER`` nested reply header
- ``ETHTOOL_A_RINGS_RX_MAX`` u32 max size of RX ring
- ``ETHTOOL_A_RINGS_RX_MINI_MAX`` u32 max size of RX mini ring
- ``ETHTOOL_A_RINGS_RX_JUMBO_MAX`` u32 max size of RX jumbo ring
- ``ETHTOOL_A_RINGS_TX_MAX`` u32 max size of TX ring
- ``ETHTOOL_A_RINGS_RX`` u32 size of RX ring
- ``ETHTOOL_A_RINGS_RX_MINI`` u32 size of RX mini ring
- ``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_HEADER`` nested reply header
+ ``ETHTOOL_A_RINGS_RX_MAX`` u32 max size of RX ring
+ ``ETHTOOL_A_RINGS_RX_MINI_MAX`` u32 max size of RX mini ring
+ ``ETHTOOL_A_RINGS_RX_JUMBO_MAX`` u32 max size of RX jumbo ring
+ ``ETHTOOL_A_RINGS_TX_MAX`` u32 max size of TX ring
+ ``ETHTOOL_A_RINGS_RX`` u32 size of RX ring
+ ``ETHTOOL_A_RINGS_RX_MINI`` u32 size of RX mini ring
+ ``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_TX_PUSH_BUF_LEN_MAX`` u32 max size of TX push buffer
+ ======================================= ====== ===========================
``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with
page-flipping TCP zero-copy receive (``getsockopt(TCP_ZEROCOPY_RECEIVE)``).
@@ -891,6 +893,14 @@ 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).
+``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN`` specifies the maximum number of bytes of a
+transmitted packet a driver can push directly to the underlying device
+('push' mode). Pushing some of the payload bytes to the device has the
+advantages of reducing latency for small packets by avoiding DMA mapping (same
+as ``ETHTOOL_A_RINGS_TX_PUSH`` parameter) as well as allowing the underlying
+device to process packet headers ahead of fetching its payload.
+This can help the device to make fast actions based on the packet's headers.
+
RINGS_SET
=========
@@ -908,6 +918,7 @@ Request contents:
``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
==================================== ====== ===========================
Kernel checks that requested ring sizes do not exceed limits reported by
@@ -75,6 +75,8 @@ enum {
* @tx_push: The flag of tx push mode
* @rx_push: The flag of rx push mode
* @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
*/
struct kernel_ethtool_ringparam {
u32 rx_buf_len;
@@ -82,6 +84,8 @@ struct kernel_ethtool_ringparam {
u8 tx_push;
u8 rx_push;
u32 cqe_size;
+ u32 tx_push_buf_len;
+ u32 tx_push_buf_max_len;
};
/**
@@ -90,12 +94,14 @@ struct kernel_ethtool_ringparam {
* @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size
* @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push
* @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push
+ * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len
*/
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),
- ETHTOOL_RING_USE_RX_PUSH = BIT(3),
+ ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0),
+ ETHTOOL_RING_USE_CQE_SIZE = BIT(1),
+ ETHTOOL_RING_USE_TX_PUSH = BIT(2),
+ ETHTOOL_RING_USE_RX_PUSH = BIT(3),
+ ETHTOOL_RING_USE_TX_PUSH_BUF_LEN = BIT(4),
};
#define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit))
@@ -357,6 +357,8 @@ enum {
ETHTOOL_A_RINGS_CQE_SIZE, /* u32 */
ETHTOOL_A_RINGS_TX_PUSH, /* u8 */
ETHTOOL_A_RINGS_RX_PUSH, /* u8 */
+ ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN, /* u32 */
+ ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX, /* u32 */
/* add new constants above here */
__ETHTOOL_A_RINGS_CNT,
@@ -413,7 +413,7 @@ 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_RX_PUSH + 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_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];
@@ -57,7 +57,9 @@ static int rings_reply_size(const struct ethnl_req_info *req_base,
nla_total_size(sizeof(u8)) + /* _RINGS_TCP_DATA_SPLIT */
nla_total_size(sizeof(u32) + /* _RINGS_CQE_SIZE */
nla_total_size(sizeof(u8)) + /* _RINGS_TX_PUSH */
- nla_total_size(sizeof(u8))); /* _RINGS_RX_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 */
}
static int rings_fill_reply(struct sk_buff *skb,
@@ -98,7 +100,12 @@ static int rings_fill_reply(struct sk_buff *skb,
(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) ||
- nla_put_u8(skb, ETHTOOL_A_RINGS_RX_PUSH, !!kr->rx_push))
+ nla_put_u8(skb, ETHTOOL_A_RINGS_RX_PUSH, !!kr->rx_push) ||
+ (kr->tx_push_buf_len &&
+ (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))))
return -EMSGSIZE;
return 0;
@@ -117,6 +124,7 @@ const struct nla_policy ethnl_rings_set_policy[] = {
[ETHTOOL_A_RINGS_CQE_SIZE] = NLA_POLICY_MIN(NLA_U32, 1),
[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 },
};
static int
@@ -158,6 +166,14 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info,
return -EOPNOTSUPP;
}
+ if (tb[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN] &&
+ !(ops->supported_ring_params & ETHTOOL_RING_USE_TX_PUSH_BUF_LEN)) {
+ NL_SET_ERR_MSG_ATTR(info->extack,
+ tb[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN],
+ "setting tx push buf len is not supported");
+ return -EOPNOTSUPP;
+ }
+
return ops->get_ringparam && ops->set_ringparam ? 1 : -EOPNOTSUPP;
}
@@ -189,6 +205,8 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
tb[ETHTOOL_A_RINGS_TX_PUSH], &mod);
ethnl_update_u8(&kernel_ringparam.rx_push,
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);
if (!mod)
return 0;
@@ -209,6 +227,13 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
return -EINVAL;
}
+ if (kernel_ringparam.tx_push_buf_len > kernel_ringparam.tx_push_buf_max_len) {
+ NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN],
+ "Requested TX push buffer exceeds maximum");
+
+ return -EINVAL;
+ }
+
ret = dev->ethtool_ops->set_ringparam(dev, &ringparam,
&kernel_ringparam, info->extack);
return ret < 0 ? ret : 1;
This attribute, which is part of ethtool's ring param configuration allows the user to specify the maximum number of the packet's payload that can be written directly to the device. Example usage: # ethtool -G [interface] tx-push-buf-len [number of bytes] Signed-off-by: Shay Agroskin <shayagr@amazon.com> --- Documentation/networking/ethtool-netlink.rst | 43 ++++++++++++-------- include/linux/ethtool.h | 14 +++++-- include/uapi/linux/ethtool_netlink.h | 2 + net/ethtool/netlink.h | 2 +- net/ethtool/rings.c | 29 ++++++++++++- 5 files changed, 67 insertions(+), 23 deletions(-)