From 9690ae60429020f38e4aa2540c306f27eb021bc0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Jan 2022 10:42:59 -0800 Subject: ethtool: add header/data split indication For applications running on a mix of platforms it's useful to have a clear indication whether host's NIC supports the geometry requirements of TCP zero-copy. TCP zero-copy Rx requires data to be neatly placed into memory pages. Most NICs can't do that. This patch is adding GET support only, since the NICs I work with either always have the feature enabled or enable it whenever MTU is set to jumbo. In other words I don't need SET. But adding set should be trivial. (The only note on SET is that we will likely want the setting to be "sticky" and use 0 / `unknown` to reset it back to driver default.) Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/ethtool.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/ethtool.h') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 11efc45de66a..e0853f48b75e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -70,9 +70,11 @@ 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 */ struct kernel_ethtool_ringparam { u32 rx_buf_len; + u8 tcp_data_split; }; /** -- cgit v1.2.3 From 1241e329ce2e1f5b1039fd356b75867b29721ad2 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 23 Feb 2022 00:09:12 +0530 Subject: ethtool: add support to set/get completion queue event size Add support to set completion queue event size via ethtool -G parameter and get it via ethtool -g parameter. ~ # ./ethtool -G eth0 cqe-size 512 ~ # ./ethtool -g eth0 Ring parameters for eth0: Pre-set maximums: RX: 1048576 RX Mini: n/a RX Jumbo: n/a TX: 1048576 Current hardware settings: RX: 256 RX Mini: n/a RX Jumbo: n/a TX: 4096 RX Buf Len: 2048 CQE Size: 128 Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 11 +++++++++++ include/linux/ethtool.h | 4 ++++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.h | 2 +- net/ethtool/rings.c | 19 +++++++++++++++++-- 5 files changed, 34 insertions(+), 3 deletions(-) (limited to 'include/linux/ethtool.h') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index cae28af7a476..24d9be69065d 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -861,6 +861,7 @@ Kernel response 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_TCP_DATA_SPLIT`` u8 TCP header / data split + ``ETHTOOL_A_RINGS_CQE_SIZE`` u32 Size of TX/RX CQE ==================================== ====== =========================== ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with @@ -885,6 +886,7 @@ 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_CQE_SIZE`` u32 Size of TX/RX CQE ==================================== ====== =========================== Kernel checks that requested ring sizes do not exceed limits reported by @@ -892,6 +894,15 @@ driver. Driver may impose additional constraints and may not suspport all attributes. +``ETHTOOL_A_RINGS_CQE_SIZE`` specifies the completion queue event size. +Completion queue events(CQE) are the events posted by NIC to indicate the +completion status of a packet when the packet is sent(like send success or +error) or received(like pointers to packet fragments). The CQE size parameter +enables to modify the CQE size other than default size if NIC supports it. +A bigger CQE can have more receive buffer pointers inturn 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. + CHANNELS_GET ============ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e0853f48b75e..4af58459a1e7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -71,18 +71,22 @@ 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 + * @cqe_size: Size of TX/RX completion queue event */ struct kernel_ethtool_ringparam { u32 rx_buf_len; u8 tcp_data_split; + u32 cqe_size; }; /** * 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 */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), + ETHTOOL_RING_USE_CQE_SIZE = BIT(1), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 417d4280d7b5..979850221b8d 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -337,6 +337,7 @@ enum { ETHTOOL_A_RINGS_TX, /* u32 */ ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ + ETHTOOL_A_RINGS_CQE_SIZE, /* u32 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 75856db299e9..29d01662a48b 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -363,7 +363,7 @@ 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_BUF_LEN + 1]; +extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_CQE_SIZE + 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 18a5035d3bee..9f33c9689b56 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -54,7 +54,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO */ 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(u8)) + /* _RINGS_TCP_DATA_SPLIT */ + nla_total_size(sizeof(u32)); /* _RINGS_CQE_SIZE */ } static int rings_fill_reply(struct sk_buff *skb, @@ -91,7 +92,9 @@ static int rings_fill_reply(struct sk_buff *skb, (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, kr->rx_buf_len))) || (kr->tcp_data_split && (nla_put_u8(skb, ETHTOOL_A_RINGS_TCP_DATA_SPLIT, - kr->tcp_data_split)))) + kr->tcp_data_split))) || + (kr->cqe_size && + (nla_put_u32(skb, ETHTOOL_A_RINGS_CQE_SIZE, kr->cqe_size)))) return -EMSGSIZE; return 0; @@ -119,6 +122,7 @@ const struct nla_policy ethnl_rings_set_policy[] = { [ETHTOOL_A_RINGS_RX_JUMBO] = { .type = NLA_U32 }, [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), }; int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) @@ -159,6 +163,8 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) ethnl_update_u32(&ringparam.tx_pending, tb[ETHTOOL_A_RINGS_TX], &mod); ethnl_update_u32(&kernel_ringparam.rx_buf_len, tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod); + ethnl_update_u32(&kernel_ringparam.cqe_size, + tb[ETHTOOL_A_RINGS_CQE_SIZE], &mod); ret = 0; if (!mod) goto out_ops; @@ -190,6 +196,15 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) goto out_ops; } + if (kernel_ringparam.cqe_size && + !(ops->supported_ring_params & ETHTOOL_RING_USE_CQE_SIZE)) { + ret = -EOPNOTSUPP; + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_CQE_SIZE], + "setting cqe size not supported"); + goto out_ops; + } + ret = dev->ethtool_ops->set_ringparam(dev, &ringparam, &kernel_ringparam, info->extack); if (ret < 0) -- cgit v1.2.3 From 4dc84c06a343fcb95fd5a0acb537aefa4ebdd1b0 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Tue, 12 Apr 2022 10:01:19 +0800 Subject: 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 Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 8 ++++++++ include/linux/ethtool.h | 4 ++++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.h | 2 +- net/ethtool/rings.c | 18 ++++++++++++++++-- 5 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux/ethtool.h') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 24d9be69065d..dbca3e9ec782 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -862,6 +862,7 @@ 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 @@ -871,6 +872,12 @@ 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 ========= @@ -887,6 +894,7 @@ 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 diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 4af58459a1e7..99dc7bfbcd3c 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -71,11 +71,13 @@ 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; }; @@ -83,10 +85,12 @@ 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)) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 979850221b8d..d2fb4f7be61b 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -338,6 +338,7 @@ 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, diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 29d01662a48b..7919ddb2371c 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -363,7 +363,7 @@ 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_CQE_SIZE + 1]; +extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX_PUSH + 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 9f33c9689b56..9ed60c507d97 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -55,7 +55,8 @@ 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, @@ -94,7 +95,8 @@ 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; @@ -123,6 +125,7 @@ const struct nla_policy ethnl_rings_set_policy[] = { [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) @@ -149,6 +152,15 @@ 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) @@ -165,6 +177,8 @@ 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; -- cgit v1.2.3