From b9e3f7dc9ed95daeb83cfa45b821cacaa01aa906 Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Thu, 12 Dec 2024 18:06:44 +0100 Subject: [PATCH 01/16] net: ethtool: tsinfo: Enhance tsinfo to support several hwtstamp by net topology Either the MAC or the PHY can provide hwtstamp, so we should be able to read the tsinfo for any hwtstamp provider. Enhance 'get' command to retrieve tsinfo of hwtstamp providers within a network topology. Add support for a specific dump command to retrieve all hwtstamp providers within the network topology, with added functionality for filtered dump to target a single interface. Signed-off-by: Kory Maincent Signed-off-by: David S. Miller --- Documentation/netlink/specs/ethtool.yaml | 20 + Documentation/networking/ethtool-netlink.rst | 7 +- include/linux/ethtool.h | 4 + .../uapi/linux/ethtool_netlink_generated.h | 10 + net/ethtool/common.c | 141 ++++++- net/ethtool/common.h | 13 + net/ethtool/netlink.c | 6 +- net/ethtool/netlink.h | 5 +- net/ethtool/ts.h | 20 + net/ethtool/tsinfo.c | 358 +++++++++++++++++- 10 files changed, 563 insertions(+), 21 deletions(-) create mode 100644 net/ethtool/ts.h diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index c7634e957d9c..4082816e5f3d 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -836,6 +836,20 @@ attribute-sets: - name: tx-err type: uint + - + name: ts-hwtstamp-provider + attr-cnt-name: __ethtool-a-ts-hwtstamp-provider-cnt + attributes: + - + name: unspec + type: unused + value: 0 + - + name: index + type: u32 + - + name: qualifier + type: u32 - name: tsinfo attr-cnt-name: __ethtool-a-tsinfo-cnt @@ -867,6 +881,10 @@ attribute-sets: name: stats type: nest nested-attributes: ts-stat + - + name: hwtstamp-provider + type: nest + nested-attributes: ts-hwtstamp-provider - name: cable-result attr-cnt-name: __ethtool-a-cable-result-cnt @@ -1912,6 +1930,7 @@ operations: request: attributes: - header + - hwtstamp-provider reply: attributes: - header @@ -1920,6 +1939,7 @@ operations: - rx-filters - phc-index - stats + - hwtstamp-provider dump: *tsinfo-get-op - name: cable-test-act diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index b25926071ece..c585e2f0ddfa 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1245,9 +1245,10 @@ Gets timestamping information like ``ETHTOOL_GET_TS_INFO`` ioctl request. Request contents: - ===================================== ====== ========================== - ``ETHTOOL_A_TSINFO_HEADER`` nested request header - ===================================== ====== ========================== + ======================================== ====== ============================ + ``ETHTOOL_A_TSINFO_HEADER`` nested request header + ``ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER`` nested PTP hw clock provider + ======================================== ====== ============================ Kernel response contents: diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e217c6321ed0..f711bfd75c4d 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -711,6 +711,7 @@ struct ethtool_rxfh_param { * @cmd: command number = %ETHTOOL_GET_TS_INFO * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags * @phc_index: device index of the associated PHC, or -1 if there is none + * @phc_qualifier: qualifier of the associated PHC * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values */ @@ -718,6 +719,7 @@ struct kernel_ethtool_ts_info { u32 cmd; u32 so_timestamping; int phc_index; + enum hwtstamp_provider_qualifier phc_qualifier; enum hwtstamp_tx_types tx_types; enum hwtstamp_rx_filters rx_filters; }; @@ -749,6 +751,7 @@ struct kernel_ethtool_ts_info { * @rss_context argument to @create_rxfh_context and friends. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. + * @supported_hwtstamp_qualifiers: bitfield of supported hwtstamp qualifier. * @get_drvinfo: Report driver/device information. Modern drivers no * longer have to implement this callback. Most fields are * correctly filled in by the core using system information, or @@ -966,6 +969,7 @@ struct ethtool_ops { u32 rxfh_max_num_contexts; u32 supported_coalesce_params; u32 supported_ring_params; + u32 supported_hwtstamp_qualifiers; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index b58f352fe4f2..df289dde0f61 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -385,6 +385,15 @@ enum { ETHTOOL_A_TS_STAT_MAX = (__ETHTOOL_A_TS_STAT_CNT - 1) }; +enum { + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_UNSPEC, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER, + + __ETHTOOL_A_TS_HWTSTAMP_PROVIDER_CNT, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_MAX = (__ETHTOOL_A_TS_HWTSTAMP_PROVIDER_CNT - 1) +}; + enum { ETHTOOL_A_TSINFO_UNSPEC, ETHTOOL_A_TSINFO_HEADER, @@ -393,6 +402,7 @@ enum { ETHTOOL_A_TSINFO_RX_FILTERS, ETHTOOL_A_TSINFO_PHC_INDEX, ETHTOOL_A_TSINFO_STATS, + ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER, __ETHTOOL_A_TSINFO_CNT, ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 05ce4f8080b3..666db40bcfda 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -5,9 +5,12 @@ #include #include #include +#include #include "netlink.h" #include "common.h" +#include "../core/dev.h" + const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_SG_BIT] = "tx-scatter-gather", @@ -763,20 +766,91 @@ int ethtool_check_ops(const struct ethtool_ops *ops) return 0; } -int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) +static void ethtool_init_tsinfo(struct kernel_ethtool_ts_info *info) { - const struct ethtool_ops *ops = dev->ethtool_ops; - struct phy_device *phydev = dev->phydev; - int err = 0; - memset(info, 0, sizeof(*info)); info->cmd = ETHTOOL_GET_TS_INFO; info->phc_index = -1; +} + +int ethtool_net_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + int err; + + if (!ops->get_ts_info) + return -ENODEV; + + /* Does ptp comes from netdev */ + ethtool_init_tsinfo(info); + info->phc_qualifier = hwprov_desc->qualifier; + err = ops->get_ts_info(dev, info); + if (err) + return err; + + if (info->phc_index == hwprov_desc->index && + net_support_hwtstamp_qualifier(dev, hwprov_desc->qualifier)) + return 0; + + return -ENODEV; +} + +int +ethtool_phy_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc) +{ + int err; + + /* Only precise qualifier is supported in phydev */ + if (hwprov_desc->qualifier != HWTSTAMP_PROVIDER_QUALIFIER_PRECISE) + return -ENODEV; + + /* Look in the phy topology */ + if (dev->link_topo) { + struct phy_device_node *pdn; + unsigned long phy_index; + + xa_for_each(&dev->link_topo->phys, phy_index, pdn) { + if (!phy_has_tsinfo(pdn->phy)) + continue; + + ethtool_init_tsinfo(info); + err = phy_ts_info(pdn->phy, info); + if (err) + return err; + + if (info->phc_index == hwprov_desc->index) + return 0; + } + return -ENODEV; + } + + /* Look on the dev->phydev */ + if (phy_has_tsinfo(dev->phydev)) { + ethtool_init_tsinfo(info); + err = phy_ts_info(dev->phydev, info); + if (err) + return err; + + if (info->phc_index == hwprov_desc->index) + return 0; + } + + return -ENODEV; +} + +int ethtool_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc) +{ + int err; - if (phy_is_default_hwtstamp(phydev) && phy_has_tsinfo(phydev)) - err = phy_ts_info(phydev, info); - else if (ops->get_ts_info) - err = ops->get_ts_info(dev, info); + err = ethtool_net_get_ts_info_by_phc(dev, info, hwprov_desc); + if (err == -ENODEV) + err = ethtool_phy_get_ts_info_by_phc(dev, info, hwprov_desc); info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE; @@ -784,6 +858,55 @@ int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info return err; } +int __ethtool_get_ts_info(struct net_device *dev, + struct kernel_ethtool_ts_info *info) +{ + struct hwtstamp_provider *hwprov; + + hwprov = rtnl_dereference(dev->hwprov); + /* No provider specified, use default behavior */ + if (!hwprov) { + const struct ethtool_ops *ops = dev->ethtool_ops; + struct phy_device *phydev = dev->phydev; + int err = 0; + + ethtool_init_tsinfo(info); + if (phy_is_default_hwtstamp(phydev) && + phy_has_tsinfo(phydev)) + err = phy_ts_info(phydev, info); + else if (ops->get_ts_info) + err = ops->get_ts_info(dev, info); + + info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + + return err; + } + + return ethtool_get_ts_info_by_phc(dev, info, &hwprov->desc); +} + +bool net_support_hwtstamp_qualifier(struct net_device *dev, + enum hwtstamp_provider_qualifier qualifier) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops) + return false; + + /* Return true with precise qualifier and with NIC without + * qualifier description to not break the old behavior. + */ + if (!ops->supported_hwtstamp_qualifiers && + qualifier == HWTSTAMP_PROVIDER_QUALIFIER_PRECISE) + return true; + + if (ops->supported_hwtstamp_qualifiers & BIT(qualifier)) + return true; + + return false; +} + int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index) { struct kernel_ethtool_ts_info info = { }; diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 4a2de3ce7354..f5119204c8ff 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -21,6 +21,7 @@ struct link_mode_info { }; struct genl_info; +struct hwtstamp_provider_desc; extern const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]; @@ -49,6 +50,18 @@ int ethtool_check_max_channel(struct net_device *dev, struct genl_info *info); int ethtool_check_rss_ctx_busy(struct net_device *dev, u32 rss_context); int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info); +int ethtool_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc); +int ethtool_net_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc); +int +ethtool_phy_get_ts_info_by_phc(struct net_device *dev, + struct kernel_ethtool_ts_info *info, + struct hwtstamp_provider_desc *hwprov_desc); +bool net_support_hwtstamp_qualifier(struct net_device *dev, + enum hwtstamp_provider_qualifier qualifier); extern const struct ethtool_phy_ops *ethtool_phy_ops; extern const struct ethtool_pse_ops *ethtool_pse_ops; diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index e3f0ef6b851b..6ae1d91f36e7 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -1074,9 +1074,9 @@ static const struct genl_ops ethtool_genl_ops[] = { { .cmd = ETHTOOL_MSG_TSINFO_GET, .doit = ethnl_default_doit, - .start = ethnl_default_start, - .dumpit = ethnl_default_dumpit, - .done = ethnl_default_done, + .start = ethnl_tsinfo_start, + .dumpit = ethnl_tsinfo_dumpit, + .done = ethnl_tsinfo_done, .policy = ethnl_tsinfo_get_policy, .maxattr = ARRAY_SIZE(ethnl_tsinfo_get_policy) - 1, }, diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 203b08eb6c6f..960cda13e4fc 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -464,7 +464,7 @@ extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_STATS_SRC extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_TX + 1]; extern const struct nla_policy ethnl_eee_get_policy[ETHTOOL_A_EEE_HEADER + 1]; extern const struct nla_policy ethnl_eee_set_policy[ETHTOOL_A_EEE_TX_LPI_TIMER + 1]; -extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_HEADER + 1]; +extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1]; extern const struct nla_policy ethnl_cable_test_act_policy[ETHTOOL_A_CABLE_TEST_HEADER + 1]; extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG + 1]; extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1]; @@ -499,6 +499,9 @@ int ethnl_phy_start(struct netlink_callback *cb); int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_phy_done(struct netlink_callback *cb); +int ethnl_tsinfo_start(struct netlink_callback *cb); +int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_tsinfo_done(struct netlink_callback *cb); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/ts.h b/net/ethtool/ts.h new file mode 100644 index 000000000000..d901a879a671 --- /dev/null +++ b/net/ethtool/ts.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _NET_ETHTOOL_TS_H +#define _NET_ETHTOOL_TS_H + +#include "netlink.h" + +static const struct nla_policy +ethnl_ts_hwtst_prov_policy[ETHTOOL_A_TS_HWTSTAMP_PROVIDER_MAX + 1] = { + [ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER] = + NLA_POLICY_MAX(NLA_U32, HWTSTAMP_PROVIDER_QUALIFIER_CNT - 1) +}; + +int ts_parse_hwtst_provider(const struct nlattr *nest, + struct hwtstamp_provider_desc *hwprov_desc, + struct netlink_ext_ack *extack, + bool *mod); + +#endif /* _NET_ETHTOOL_TS_H */ diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c index 03d12d6f79ca..7e495a41aeec 100644 --- a/net/ethtool/tsinfo.c +++ b/net/ethtool/tsinfo.c @@ -1,13 +1,18 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include +#include +#include #include "netlink.h" #include "common.h" #include "bitset.h" +#include "ts.h" struct tsinfo_req_info { struct ethnl_req_info base; + struct hwtstamp_provider_desc hwprov_desc; }; struct tsinfo_reply_data { @@ -16,34 +21,96 @@ struct tsinfo_reply_data { struct ethtool_ts_stats stats; }; +#define TSINFO_REQINFO(__req_base) \ + container_of(__req_base, struct tsinfo_req_info, base) + #define TSINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct tsinfo_reply_data, base) #define ETHTOOL_TS_STAT_CNT \ (__ETHTOOL_A_TS_STAT_CNT - (ETHTOOL_A_TS_STAT_UNSPEC + 1)) -const struct nla_policy ethnl_tsinfo_get_policy[] = { +const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1] = { [ETHTOOL_A_TSINFO_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), + [ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER] = + NLA_POLICY_NESTED(ethnl_ts_hwtst_prov_policy), }; +int ts_parse_hwtst_provider(const struct nlattr *nest, + struct hwtstamp_provider_desc *hwprov_desc, + struct netlink_ext_ack *extack, + bool *mod) +{ + struct nlattr *tb[ARRAY_SIZE(ethnl_ts_hwtst_prov_policy)]; + int ret; + + ret = nla_parse_nested(tb, + ARRAY_SIZE(ethnl_ts_hwtst_prov_policy) - 1, + nest, + ethnl_ts_hwtst_prov_policy, extack); + if (ret < 0) + return ret; + + if (NL_REQ_ATTR_CHECK(extack, nest, tb, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX) || + NL_REQ_ATTR_CHECK(extack, nest, tb, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER)) + return -EINVAL; + + ethnl_update_u32(&hwprov_desc->index, + tb[ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX], + mod); + ethnl_update_u32(&hwprov_desc->qualifier, + tb[ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER], + mod); + + return 0; +} + +static int +tsinfo_parse_request(struct ethnl_req_info *req_base, struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct tsinfo_req_info *req = TSINFO_REQINFO(req_base); + bool mod = false; + + req->hwprov_desc.index = -1; + + if (!tb[ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER]) + return 0; + + return ts_parse_hwtst_provider(tb[ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER], + &req->hwprov_desc, extack, &mod); +} + static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); + struct tsinfo_req_info *req = TSINFO_REQINFO(req_base); struct net_device *dev = reply_base->dev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; + + if (req->hwprov_desc.index != -1) { + ret = ethtool_get_ts_info_by_phc(dev, &data->ts_info, + &req->hwprov_desc); + ethnl_ops_complete(dev); + return ret; + } + if (req_base->flags & ETHTOOL_FLAG_STATS) { ethtool_stats_init((u64 *)&data->stats, sizeof(data->stats) / sizeof(u64)); if (dev->ethtool_ops->get_ts_stats) dev->ethtool_ops->get_ts_stats(dev, &data->stats); } + ret = __ethtool_get_ts_info(dev, &data->ts_info); ethnl_ops_complete(dev); @@ -87,8 +154,11 @@ static int tsinfo_reply_size(const struct ethnl_req_info *req_base, return ret; len += ret; /* _TSINFO_RX_FILTERS */ } - if (ts_info->phc_index >= 0) + if (ts_info->phc_index >= 0) { len += nla_total_size(sizeof(u32)); /* _TSINFO_PHC_INDEX */ + /* _TSINFO_HWTSTAMP_PROVIDER */ + len += nla_total_size(0) + 2 * nla_total_size(sizeof(u32)); + } if (req_base->flags & ETHTOOL_FLAG_STATS) len += nla_total_size(0) + /* _TSINFO_STATS */ nla_total_size_64bit(sizeof(u64)) * ETHTOOL_TS_STAT_CNT; @@ -163,9 +233,29 @@ static int tsinfo_fill_reply(struct sk_buff *skb, if (ret < 0) return ret; } - if (ts_info->phc_index >= 0 && - nla_put_u32(skb, ETHTOOL_A_TSINFO_PHC_INDEX, ts_info->phc_index)) - return -EMSGSIZE; + if (ts_info->phc_index >= 0) { + struct nlattr *nest; + + ret = nla_put_u32(skb, ETHTOOL_A_TSINFO_PHC_INDEX, + ts_info->phc_index); + if (ret) + return -EMSGSIZE; + + nest = nla_nest_start(skb, ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX, + ts_info->phc_index) || + nla_put_u32(skb, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER, + ts_info->phc_qualifier)) { + nla_nest_cancel(skb, nest); + return -EMSGSIZE; + } + + nla_nest_end(skb, nest); + } if (req_base->flags & ETHTOOL_FLAG_STATS && tsinfo_put_stats(skb, &data->stats)) return -EMSGSIZE; @@ -173,6 +263,263 @@ static int tsinfo_fill_reply(struct sk_buff *skb, return 0; } +struct ethnl_tsinfo_dump_ctx { + struct tsinfo_req_info *req_info; + struct tsinfo_reply_data *reply_data; + unsigned long pos_ifindex; + bool netdev_dump_done; + unsigned long pos_phyindex; + enum hwtstamp_provider_qualifier pos_phcqualifier; +}; + +static void *ethnl_tsinfo_prepare_dump(struct sk_buff *skb, + struct net_device *dev, + struct tsinfo_reply_data *reply_data, + struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + void *ehdr = NULL; + + ehdr = ethnl_dump_put(skb, cb, + ETHTOOL_MSG_TSINFO_GET_REPLY); + if (!ehdr) + return ERR_PTR(-EMSGSIZE); + + reply_data = ctx->reply_data; + memset(reply_data, 0, sizeof(*reply_data)); + reply_data->base.dev = dev; + memset(&reply_data->ts_info, 0, sizeof(reply_data->ts_info)); + + return ehdr; +} + +static int ethnl_tsinfo_end_dump(struct sk_buff *skb, + struct net_device *dev, + struct tsinfo_req_info *req_info, + struct tsinfo_reply_data *reply_data, + void *ehdr) +{ + int ret; + + reply_data->ts_info.so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + + ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_TSINFO_HEADER); + if (ret < 0) + return ret; + + ret = tsinfo_fill_reply(skb, &req_info->base, &reply_data->base); + if (ret < 0) + return ret; + + reply_data->base.dev = NULL; + genlmsg_end(skb, ehdr); + + return ret; +} + +static int ethnl_tsinfo_dump_one_phydev(struct sk_buff *skb, + struct net_device *dev, + struct phy_device *phydev, + struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct tsinfo_reply_data *reply_data; + struct tsinfo_req_info *req_info; + void *ehdr = NULL; + int ret = 0; + + if (!phy_has_tsinfo(phydev)) + return -EOPNOTSUPP; + + reply_data = ctx->reply_data; + req_info = ctx->req_info; + ehdr = ethnl_tsinfo_prepare_dump(skb, dev, reply_data, cb); + if (IS_ERR(ehdr)) + return PTR_ERR(ehdr); + + ret = phy_ts_info(phydev, &reply_data->ts_info); + if (ret < 0) + goto err; + + ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data, ehdr); + if (ret < 0) + goto err; + + return ret; +err: + genlmsg_cancel(skb, ehdr); + return ret; +} + +static int ethnl_tsinfo_dump_one_netdev(struct sk_buff *skb, + struct net_device *dev, + struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct tsinfo_reply_data *reply_data; + struct tsinfo_req_info *req_info; + void *ehdr = NULL; + int ret = 0; + + if (!ops->get_ts_info) + return -EOPNOTSUPP; + + reply_data = ctx->reply_data; + req_info = ctx->req_info; + for (; ctx->pos_phcqualifier < HWTSTAMP_PROVIDER_QUALIFIER_CNT; + ctx->pos_phcqualifier++) { + if (!net_support_hwtstamp_qualifier(dev, + ctx->pos_phcqualifier)) + continue; + + ehdr = ethnl_tsinfo_prepare_dump(skb, dev, reply_data, cb); + if (IS_ERR(ehdr)) { + ret = PTR_ERR(ehdr); + goto err; + } + + reply_data->ts_info.phc_qualifier = ctx->pos_phcqualifier; + ret = ops->get_ts_info(dev, &reply_data->ts_info); + if (ret < 0) + goto err; + + ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data, + ehdr); + if (ret < 0) + goto err; + } + + return ret; + +err: + genlmsg_cancel(skb, ehdr); + return ret; +} + +static int ethnl_tsinfo_dump_one_net_topo(struct sk_buff *skb, + struct net_device *dev, + struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct phy_device_node *pdn; + int ret = 0; + + if (!ctx->netdev_dump_done) { + ret = ethnl_tsinfo_dump_one_netdev(skb, dev, cb); + if (ret < 0 && ret != -EOPNOTSUPP) + return ret; + ctx->netdev_dump_done = true; + } + + if (!dev->link_topo) { + if (phy_has_tsinfo(dev->phydev)) { + ret = ethnl_tsinfo_dump_one_phydev(skb, dev, + dev->phydev, cb); + if (ret < 0 && ret != -EOPNOTSUPP) + return ret; + } + + return 0; + } + + xa_for_each_start(&dev->link_topo->phys, ctx->pos_phyindex, pdn, + ctx->pos_phyindex) { + if (phy_has_tsinfo(pdn->phy)) { + ret = ethnl_tsinfo_dump_one_phydev(skb, dev, + pdn->phy, cb); + if (ret < 0 && ret != -EOPNOTSUPP) + return ret; + } + } + + return ret; +} + +int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + if (ctx->req_info->base.dev) { + ret = ethnl_tsinfo_dump_one_net_topo(skb, + ctx->req_info->base.dev, + cb); + } else { + for_each_netdev_dump(net, dev, ctx->pos_ifindex) { + ret = ethnl_tsinfo_dump_one_net_topo(skb, dev, cb); + if (ret < 0 && ret != -EOPNOTSUPP) + break; + ctx->pos_phyindex = 0; + ctx->netdev_dump_done = false; + ctx->pos_phcqualifier = HWTSTAMP_PROVIDER_QUALIFIER_PRECISE; + } + } + rtnl_unlock(); + + return ret; +} + +int ethnl_tsinfo_start(struct netlink_callback *cb) +{ + const struct genl_dumpit_info *info = genl_dumpit_info(cb); + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct nlattr **tb = info->info.attrs; + struct tsinfo_reply_data *reply_data; + struct tsinfo_req_info *req_info; + int ret; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + req_info = kzalloc(sizeof(*req_info), GFP_KERNEL); + if (!req_info) + return -ENOMEM; + reply_data = kzalloc(sizeof(*reply_data), GFP_KERNEL); + if (!reply_data) { + ret = -ENOMEM; + goto free_req_info; + } + + ret = ethnl_parse_header_dev_get(&req_info->base, + tb[ETHTOOL_A_TSINFO_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); + if (ret < 0) + goto free_reply_data; + + ctx->req_info = req_info; + ctx->reply_data = reply_data; + ctx->pos_ifindex = 0; + ctx->pos_phyindex = 0; + ctx->netdev_dump_done = false; + ctx->pos_phcqualifier = HWTSTAMP_PROVIDER_QUALIFIER_PRECISE; + + return 0; + +free_reply_data: + kfree(reply_data); +free_req_info: + kfree(req_info); + + return ret; +} + +int ethnl_tsinfo_done(struct netlink_callback *cb) +{ + struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; + struct tsinfo_req_info *req_info = ctx->req_info; + + ethnl_parse_header_dev_put(&req_info->base); + kfree(ctx->reply_data); + kfree(ctx->req_info); + + return 0; +} + const struct ethnl_request_ops ethnl_tsinfo_request_ops = { .request_cmd = ETHTOOL_MSG_TSINFO_GET, .reply_cmd = ETHTOOL_MSG_TSINFO_GET_REPLY, @@ -180,6 +527,7 @@ const struct ethnl_request_ops ethnl_tsinfo_request_ops = { .req_info_size = sizeof(struct tsinfo_req_info), .reply_data_size = sizeof(struct tsinfo_reply_data), + .parse_request = tsinfo_parse_request, .prepare_data = tsinfo_prepare_data, .reply_size = tsinfo_reply_size, .fill_reply = tsinfo_fill_reply, -- 2.51.0 From 6e9e2eed4f39d52edf5fd006409d211facf49f6b Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Thu, 12 Dec 2024 18:06:45 +0100 Subject: [PATCH 02/16] net: ethtool: Add support for tsconfig command to get/set hwtstamp config Introduce support for ETHTOOL_MSG_TSCONFIG_GET/SET ethtool netlink socket to read and configure hwtstamp configuration of a PHC provider. Note that simultaneous hwtstamp isn't supported; configuring a new one disables the previous setting. Signed-off-by: Kory Maincent Signed-off-by: David S. Miller --- Documentation/netlink/specs/ethtool.yaml | 56 +++ Documentation/networking/ethtool-netlink.rst | 75 +++ Documentation/networking/timestamping.rst | 38 +- .../uapi/linux/ethtool_netlink_generated.h | 16 + net/ethtool/Makefile | 2 +- net/ethtool/common.c | 27 +- net/ethtool/common.h | 2 +- net/ethtool/netlink.c | 18 + net/ethtool/netlink.h | 3 + net/ethtool/tsconfig.c | 444 ++++++++++++++++++ 10 files changed, 655 insertions(+), 26 deletions(-) create mode 100644 net/ethtool/tsconfig.c diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 4082816e5f3d..60f85fbf4156 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -1489,6 +1489,33 @@ attribute-sets: - name: downstream-sfp-name type: string + - + name: tsconfig + attr-cnt-name: __ethtool-a-tsconfig-cnt + attributes: + - + name: unspec + type: unused + value: 0 + - + name: header + type: nest + nested-attributes: header + - + name: hwtstamp-provider + type: nest + nested-attributes: ts-hwtstamp-provider + - + name: tx-types + type: nest + nested-attributes: bitset + - + name: rx-filters + type: nest + nested-attributes: bitset + - + name: hwtstamp-flags + type: u32 operations: enum-model: directional @@ -2314,3 +2341,32 @@ operations: name: phy-ntf doc: Notification for change in PHY devices. notify: phy-get + - + name: tsconfig-get + doc: Get hwtstamp config. + + attribute-set: tsconfig + + do: &tsconfig-get-op + request: + attributes: + - header + reply: + attributes: &tsconfig + - header + - hwtstamp-provider + - tx-types + - rx-filters + - hwtstamp-flags + dump: *tsconfig-get-op + - + name: tsconfig-set + doc: Set hwtstamp config. + + attribute-set: tsconfig + + do: + request: + attributes: *tsconfig + reply: + attributes: *tsconfig diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index c585e2f0ddfa..a7ba6368a4d5 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -237,6 +237,8 @@ Userspace to kernel: ``ETHTOOL_MSG_MM_SET`` set MAC merge layer parameters ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` flash transceiver module firmware ``ETHTOOL_MSG_PHY_GET`` get Ethernet PHY information + ``ETHTOOL_MSG_TSCONFIG_GET`` get hw timestamping configuration + ``ETHTOOL_MSG_TSCONFIG_SET`` set hw timestamping configuration ===================================== ================================= Kernel to userspace: @@ -286,6 +288,8 @@ Kernel to userspace: ``ETHTOOL_MSG_MODULE_FW_FLASH_NTF`` transceiver module flash updates ``ETHTOOL_MSG_PHY_GET_REPLY`` Ethernet PHY information ``ETHTOOL_MSG_PHY_NTF`` Ethernet PHY information change + ``ETHTOOL_MSG_TSCONFIG_GET_REPLY`` hw timestamping configuration + ``ETHTOOL_MSG_TSCONFIG_SET_REPLY`` new hw timestamping configuration ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -2244,6 +2248,75 @@ Kernel response contents: When ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` is PHY_UPSTREAM_PHY, the PHY's parent is another PHY. +TSCONFIG_GET +============ + +Retrieves the information about the current hardware timestamping source and +configuration. + +It is similar to the deprecated ``SIOCGHWTSTAMP`` ioctl request. + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_TSCONFIG_HEADER`` nested request header + ==================================== ====== ========================== + +Kernel response contents: + + ======================================== ====== ============================ + ``ETHTOOL_A_TSCONFIG_HEADER`` nested request header + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` nested PTP hw clock provider + ``ETHTOOL_A_TSCONFIG_TX_TYPES`` bitset hwtstamp Tx type + ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` bitset hwtstamp Rx filter + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` u32 hwtstamp flags + ======================================== ====== ============================ + +When set the ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` attribute identifies the +source of the hw timestamping provider. It is composed by +``ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX`` attribute which describe the index of +the PTP device and ``ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER`` which describe +the qualifier of the timestamp. + +When set the ``ETHTOOL_A_TSCONFIG_TX_TYPES``, ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` +and the ``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` attributes identify the Tx +type, the Rx filter and the flags configured for the current hw timestamping +provider. The attributes are propagated to the driver through the following +structure: + +.. kernel-doc:: include/linux/net_tstamp.h + :identifiers: kernel_hwtstamp_config + +TSCONFIG_SET +============ + +Set the information about the current hardware timestamping source and +configuration. + +It is similar to the deprecated ``SIOCSHWTSTAMP`` ioctl request. + +Request contents: + + ======================================== ====== ============================ + ``ETHTOOL_A_TSCONFIG_HEADER`` nested request header + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` nested PTP hw clock provider + ``ETHTOOL_A_TSCONFIG_TX_TYPES`` bitset hwtstamp Tx type + ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` bitset hwtstamp Rx filter + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` u32 hwtstamp flags + ======================================== ====== ============================ + +Kernel response contents: + + ======================================== ====== ============================ + ``ETHTOOL_A_TSCONFIG_HEADER`` nested request header + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` nested PTP hw clock provider + ``ETHTOOL_A_TSCONFIG_TX_TYPES`` bitset hwtstamp Tx type + ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` bitset hwtstamp Rx filter + ``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` u32 hwtstamp flags + ======================================== ====== ============================ + +For a description of each attribute, see ``TSCONFIG_GET``. + Request translation =================== @@ -2352,4 +2425,6 @@ are netlink only. n/a ``ETHTOOL_MSG_MM_SET`` n/a ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` n/a ``ETHTOOL_MSG_PHY_GET`` + ``SIOCGHWTSTAMP`` ``ETHTOOL_MSG_TSCONFIG_GET`` + ``SIOCSHWTSTAMP`` ``ETHTOOL_MSG_TSCONFIG_SET`` =================================== ===================================== diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index b37bfbfc7d79..61ef9da10e28 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -525,8 +525,8 @@ implicitly defined. ts[0] holds a software timestamp if set, ts[1] is again deprecated and ts[2] holds a hardware timestamp if set. -3. Hardware Timestamping configuration: SIOCSHWTSTAMP and SIOCGHWTSTAMP -======================================================================= +3. Hardware Timestamping configuration: ETHTOOL_MSG_TSCONFIG_SET/GET +==================================================================== Hardware time stamping must also be initialized for each device driver that is expected to do hardware time stamping. The parameter is defined in @@ -539,12 +539,14 @@ include/uapi/linux/net_tstamp.h as:: }; Desired behavior is passed into the kernel and to a specific device by -calling ioctl(SIOCSHWTSTAMP) with a pointer to a struct ifreq whose -ifr_data points to a struct hwtstamp_config. The tx_type and -rx_filter are hints to the driver what it is expected to do. If -the requested fine-grained filtering for incoming packets is not -supported, the driver may time stamp more than just the requested types -of packets. +calling the tsconfig netlink socket ``ETHTOOL_MSG_TSCONFIG_SET``. +The ``ETHTOOL_A_TSCONFIG_TX_TYPES``, ``ETHTOOL_A_TSCONFIG_RX_FILTERS`` and +``ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS`` netlink attributes are then used to set +the struct hwtstamp_config accordingly. + +The ``ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER`` netlink nested attribute is used +to select the source of the hardware time stamping. It is composed of an index +for the device source and a qualifier for the type of time stamping. Drivers are free to use a more permissive configuration than the requested configuration. It is expected that drivers should only implement directly the @@ -563,9 +565,16 @@ Only a processes with admin rights may change the configuration. User space is responsible to ensure that multiple processes don't interfere with each other and that the settings are reset. -Any process can read the actual configuration by passing this -structure to ioctl(SIOCGHWTSTAMP) in the same way. However, this has -not been implemented in all drivers. +Any process can read the actual configuration by requesting tsconfig netlink +socket ``ETHTOOL_MSG_TSCONFIG_GET``. + +The legacy configuration is the use of the ioctl(SIOCSHWTSTAMP) with a pointer +to a struct ifreq whose ifr_data points to a struct hwtstamp_config. +The tx_type and rx_filter are hints to the driver what it is expected to do. +If the requested fine-grained filtering for incoming packets is not +supported, the driver may time stamp more than just the requested types +of packets. ioctl(SIOCGHWTSTAMP) is used in the same way as the +ioctl(SIOCSHWTSTAMP). However, this has not been implemented in all drivers. :: @@ -610,9 +619,10 @@ not been implemented in all drivers. -------------------------------------------------------- A driver which supports hardware time stamping must support the -SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with -the actual values as described in the section on SIOCSHWTSTAMP. It -should also support SIOCGHWTSTAMP. +ndo_hwtstamp_set NDO or the legacy SIOCSHWTSTAMP ioctl and update the +supplied struct hwtstamp_config with the actual values as described in +the section on SIOCSHWTSTAMP. It should also support ndo_hwtstamp_get or +the legacy SIOCGHWTSTAMP. Time stamps for received packets must be stored in the skb. To get a pointer to the shared time stamp structure of the skb call skb_hwtstamps(). Then diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index df289dde0f61..43993a2d68e5 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -694,6 +694,18 @@ enum { ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1) }; +enum { + ETHTOOL_A_TSCONFIG_UNSPEC, + ETHTOOL_A_TSCONFIG_HEADER, + ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER, + ETHTOOL_A_TSCONFIG_TX_TYPES, + ETHTOOL_A_TSCONFIG_RX_FILTERS, + ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS, + + __ETHTOOL_A_TSCONFIG_CNT, + ETHTOOL_A_TSCONFIG_MAX = (__ETHTOOL_A_TSCONFIG_CNT - 1) +}; + enum { ETHTOOL_MSG_USER_NONE = 0, ETHTOOL_MSG_STRSET_GET = 1, @@ -741,6 +753,8 @@ enum { ETHTOOL_MSG_MM_SET, ETHTOOL_MSG_MODULE_FW_FLASH_ACT, ETHTOOL_MSG_PHY_GET, + ETHTOOL_MSG_TSCONFIG_GET, + ETHTOOL_MSG_TSCONFIG_SET, __ETHTOOL_MSG_USER_CNT, ETHTOOL_MSG_USER_MAX = (__ETHTOOL_MSG_USER_CNT - 1) @@ -794,6 +808,8 @@ enum { ETHTOOL_MSG_MODULE_FW_FLASH_NTF, ETHTOOL_MSG_PHY_GET_REPLY, ETHTOOL_MSG_PHY_NTF, + ETHTOOL_MSG_TSCONFIG_GET_REPLY, + ETHTOOL_MSG_TSCONFIG_SET_REPLY, __ETHTOOL_MSG_KERNEL_CNT, ETHTOOL_MSG_KERNEL_MAX = (__ETHTOOL_MSG_KERNEL_CNT - 1) diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 9b540644ba31..a1490c4afe6b 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -9,4 +9,4 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ module.o cmis_fw_update.o cmis_cdb.o pse-pd.o plca.o mm.o \ - phy.o + phy.o tsconfig.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 666db40bcfda..02f941f667dd 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -797,7 +797,7 @@ int ethtool_net_get_ts_info_by_phc(struct net_device *dev, return -ENODEV; } -int +struct phy_device * ethtool_phy_get_ts_info_by_phc(struct net_device *dev, struct kernel_ethtool_ts_info *info, struct hwtstamp_provider_desc *hwprov_desc) @@ -806,7 +806,7 @@ ethtool_phy_get_ts_info_by_phc(struct net_device *dev, /* Only precise qualifier is supported in phydev */ if (hwprov_desc->qualifier != HWTSTAMP_PROVIDER_QUALIFIER_PRECISE) - return -ENODEV; + return ERR_PTR(-ENODEV); /* Look in the phy topology */ if (dev->link_topo) { @@ -820,12 +820,12 @@ ethtool_phy_get_ts_info_by_phc(struct net_device *dev, ethtool_init_tsinfo(info); err = phy_ts_info(pdn->phy, info); if (err) - return err; + return ERR_PTR(err); if (info->phc_index == hwprov_desc->index) - return 0; + return pdn->phy; } - return -ENODEV; + return ERR_PTR(-ENODEV); } /* Look on the dev->phydev */ @@ -833,13 +833,13 @@ ethtool_phy_get_ts_info_by_phc(struct net_device *dev, ethtool_init_tsinfo(info); err = phy_ts_info(dev->phydev, info); if (err) - return err; + return ERR_PTR(err); if (info->phc_index == hwprov_desc->index) - return 0; + return dev->phydev; } - return -ENODEV; + return ERR_PTR(-ENODEV); } int ethtool_get_ts_info_by_phc(struct net_device *dev, @@ -849,8 +849,15 @@ int ethtool_get_ts_info_by_phc(struct net_device *dev, int err; err = ethtool_net_get_ts_info_by_phc(dev, info, hwprov_desc); - if (err == -ENODEV) - err = ethtool_phy_get_ts_info_by_phc(dev, info, hwprov_desc); + if (err == -ENODEV) { + struct phy_device *phy; + + phy = ethtool_phy_get_ts_info_by_phc(dev, info, hwprov_desc); + if (IS_ERR(phy)) + err = PTR_ERR(phy); + else + err = 0; + } info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE; diff --git a/net/ethtool/common.h b/net/ethtool/common.h index f5119204c8ff..850eadde4bfc 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -56,7 +56,7 @@ int ethtool_get_ts_info_by_phc(struct net_device *dev, int ethtool_net_get_ts_info_by_phc(struct net_device *dev, struct kernel_ethtool_ts_info *info, struct hwtstamp_provider_desc *hwprov_desc); -int +struct phy_device * ethtool_phy_get_ts_info_by_phc(struct net_device *dev, struct kernel_ethtool_ts_info *info, struct hwtstamp_provider_desc *hwprov_desc); diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 6ae1d91f36e7..849c98e637c6 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -394,6 +394,8 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, [ETHTOOL_MSG_MM_GET] = ðnl_mm_request_ops, [ETHTOOL_MSG_MM_SET] = ðnl_mm_request_ops, + [ETHTOOL_MSG_TSCONFIG_GET] = ðnl_tsconfig_request_ops, + [ETHTOOL_MSG_TSCONFIG_SET] = ðnl_tsconfig_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -1243,6 +1245,22 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_phy_get_policy, .maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_TSCONFIG_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_tsconfig_get_policy, + .maxattr = ARRAY_SIZE(ethnl_tsconfig_get_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_TSCONFIG_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_default_set_doit, + .policy = ethnl_tsconfig_set_policy, + .maxattr = ARRAY_SIZE(ethnl_tsconfig_set_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 960cda13e4fc..0a09298fff92 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -435,6 +435,7 @@ extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; extern const struct ethnl_request_ops ethnl_phy_request_ops; +extern const struct ethnl_request_ops ethnl_tsconfig_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -485,6 +486,8 @@ extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; extern const struct nla_policy ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD + 1]; extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1]; +extern const struct nla_policy ethnl_tsconfig_get_policy[ETHTOOL_A_TSCONFIG_HEADER + 1]; +extern const struct nla_policy ethnl_tsconfig_set_policy[ETHTOOL_A_TSCONFIG_MAX + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/tsconfig.c b/net/ethtool/tsconfig.c new file mode 100644 index 000000000000..9188e088fb2f --- /dev/null +++ b/net/ethtool/tsconfig.c @@ -0,0 +1,444 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +#include "netlink.h" +#include "common.h" +#include "bitset.h" +#include "../core/dev.h" +#include "ts.h" + +struct tsconfig_req_info { + struct ethnl_req_info base; +}; + +struct tsconfig_reply_data { + struct ethnl_reply_data base; + struct hwtstamp_provider_desc hwprov_desc; + struct { + u32 tx_type; + u32 rx_filter; + u32 flags; + } hwtst_config; +}; + +#define TSCONFIG_REPDATA(__reply_base) \ + container_of(__reply_base, struct tsconfig_reply_data, base) + +const struct nla_policy ethnl_tsconfig_get_policy[ETHTOOL_A_TSCONFIG_HEADER + 1] = { + [ETHTOOL_A_TSCONFIG_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int tsconfig_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + const struct genl_info *info) +{ + struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); + struct hwtstamp_provider *hwprov = NULL; + struct net_device *dev = reply_base->dev; + struct kernel_hwtstamp_config cfg = {}; + int ret; + + if (!dev->netdev_ops->ndo_hwtstamp_get) + return -EOPNOTSUPP; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + ret = dev_get_hwtstamp_phylib(dev, &cfg); + if (ret) + goto out; + + data->hwtst_config.tx_type = BIT(cfg.tx_type); + data->hwtst_config.rx_filter = BIT(cfg.rx_filter); + data->hwtst_config.flags = BIT(cfg.flags); + + data->hwprov_desc.index = -1; + hwprov = rtnl_dereference(dev->hwprov); + if (hwprov) { + data->hwprov_desc.index = hwprov->desc.index; + data->hwprov_desc.qualifier = hwprov->desc.qualifier; + } else { + struct kernel_ethtool_ts_info ts_info = {}; + + ts_info.phc_index = -1; + ret = __ethtool_get_ts_info(dev, &ts_info); + if (ret) + goto out; + + if (ts_info.phc_index == -1) + return -ENODEV; + + data->hwprov_desc.index = ts_info.phc_index; + data->hwprov_desc.qualifier = ts_info.phc_qualifier; + } + +out: + ethnl_ops_complete(dev); + return ret; +} + +static int tsconfig_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + int len = 0; + int ret; + + BUILD_BUG_ON(__HWTSTAMP_TX_CNT > 32); + BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT > 32); + + if (data->hwtst_config.flags) + /* _TSCONFIG_HWTSTAMP_FLAGS */ + len += nla_total_size(sizeof(u32)); + + if (data->hwtst_config.tx_type) { + ret = ethnl_bitset32_size(&data->hwtst_config.tx_type, + NULL, __HWTSTAMP_TX_CNT, + ts_tx_type_names, compact); + if (ret < 0) + return ret; + len += ret; /* _TSCONFIG_TX_TYPES */ + } + if (data->hwtst_config.rx_filter) { + ret = ethnl_bitset32_size(&data->hwtst_config.rx_filter, + NULL, __HWTSTAMP_FILTER_CNT, + ts_rx_filter_names, compact); + if (ret < 0) + return ret; + len += ret; /* _TSCONFIG_RX_FILTERS */ + } + + if (data->hwprov_desc.index >= 0) + /* _TSCONFIG_HWTSTAMP_PROVIDER */ + len += nla_total_size(0) + + 2 * nla_total_size(sizeof(u32)); + + return len; +} + +static int tsconfig_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + int ret; + + if (data->hwtst_config.flags) { + ret = nla_put_u32(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS, + data->hwtst_config.flags); + if (ret < 0) + return ret; + } + + if (data->hwtst_config.tx_type) { + ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_TX_TYPES, + &data->hwtst_config.tx_type, NULL, + __HWTSTAMP_TX_CNT, + ts_tx_type_names, compact); + if (ret < 0) + return ret; + } + + if (data->hwtst_config.rx_filter) { + ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_RX_FILTERS, + &data->hwtst_config.rx_filter, + NULL, __HWTSTAMP_FILTER_CNT, + ts_rx_filter_names, compact); + if (ret < 0) + return ret; + } + + if (data->hwprov_desc.index >= 0) { + struct nlattr *nest; + + nest = nla_nest_start(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX, + data->hwprov_desc.index) || + nla_put_u32(skb, + ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER, + data->hwprov_desc.qualifier)) { + nla_nest_cancel(skb, nest); + return -EMSGSIZE; + } + + nla_nest_end(skb, nest); + } + return 0; +} + +/* TSCONFIG_SET */ +const struct nla_policy ethnl_tsconfig_set_policy[ETHTOOL_A_TSCONFIG_MAX + 1] = { + [ETHTOOL_A_TSCONFIG_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER] = + NLA_POLICY_NESTED(ethnl_ts_hwtst_prov_policy), + [ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS] = { .type = NLA_U32 }, + [ETHTOOL_A_TSCONFIG_RX_FILTERS] = { .type = NLA_NESTED }, + [ETHTOOL_A_TSCONFIG_TX_TYPES] = { .type = NLA_NESTED }, +}; + +static int tsconfig_send_reply(struct net_device *dev, struct genl_info *info) +{ + struct tsconfig_reply_data *reply_data; + struct tsconfig_req_info *req_info; + struct sk_buff *rskb; + void *reply_payload; + int reply_len = 0; + int ret; + + req_info = kzalloc(sizeof(*req_info), GFP_KERNEL); + if (!req_info) + return -ENOMEM; + reply_data = kmalloc(sizeof(*reply_data), GFP_KERNEL); + if (!reply_data) { + kfree(req_info); + return -ENOMEM; + } + + ASSERT_RTNL(); + reply_data->base.dev = dev; + ret = tsconfig_prepare_data(&req_info->base, &reply_data->base, info); + if (ret < 0) + goto err_cleanup; + + ret = tsconfig_reply_size(&req_info->base, &reply_data->base); + if (ret < 0) + goto err_cleanup; + + reply_len = ret + ethnl_reply_header_size(); + rskb = ethnl_reply_init(reply_len, dev, ETHTOOL_MSG_TSCONFIG_SET_REPLY, + ETHTOOL_A_TSCONFIG_HEADER, info, &reply_payload); + if (!rskb) + goto err_cleanup; + + ret = tsconfig_fill_reply(rskb, &req_info->base, &reply_data->base); + if (ret < 0) + goto err_cleanup; + + genlmsg_end(rskb, reply_payload); + ret = genlmsg_reply(rskb, info); + +err_cleanup: + kfree(reply_data); + kfree(req_info); + return ret; +} + +static int ethnl_set_tsconfig_validate(struct ethnl_req_info *req_base, + struct genl_info *info) +{ + const struct net_device_ops *ops = req_base->dev->netdev_ops; + + if (!ops->ndo_hwtstamp_set || !ops->ndo_hwtstamp_get) + return -EOPNOTSUPP; + + return 1; +} + +static struct hwtstamp_provider * +tsconfig_set_hwprov_from_desc(struct net_device *dev, + struct genl_info *info, + struct hwtstamp_provider_desc *hwprov_desc) +{ + struct kernel_ethtool_ts_info ts_info; + struct hwtstamp_provider *hwprov; + struct nlattr **tb = info->attrs; + struct phy_device *phy = NULL; + enum hwtstamp_source source; + int ret; + + ret = ethtool_net_get_ts_info_by_phc(dev, &ts_info, hwprov_desc); + if (!ret) { + /* Found */ + source = HWTSTAMP_SOURCE_NETDEV; + } else { + phy = ethtool_phy_get_ts_info_by_phc(dev, &ts_info, hwprov_desc); + if (IS_ERR(phy)) { + if (PTR_ERR(phy) == -ENODEV) + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER], + "phc not in this net device topology"); + return ERR_CAST(phy); + } + + source = HWTSTAMP_SOURCE_PHYLIB; + } + + hwprov = kzalloc(sizeof(*hwprov), GFP_KERNEL); + if (!hwprov) + return ERR_PTR(-ENOMEM); + + hwprov->desc.index = hwprov_desc->index; + hwprov->desc.qualifier = hwprov_desc->qualifier; + hwprov->source = source; + hwprov->phydev = phy; + + return hwprov; +} + +static int ethnl_set_tsconfig(struct ethnl_req_info *req_base, + struct genl_info *info) +{ + struct kernel_hwtstamp_config hwtst_config = {0}; + bool hwprov_mod = false, config_mod = false; + struct hwtstamp_provider *hwprov = NULL; + struct net_device *dev = req_base->dev; + struct nlattr **tb = info->attrs; + int ret; + + BUILD_BUG_ON(__HWTSTAMP_TX_CNT >= 32); + BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT >= 32); + + if (!netif_device_present(dev)) + return -ENODEV; + + if (tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER]) { + struct hwtstamp_provider_desc __hwprov_desc = {.index = -1}; + struct hwtstamp_provider *__hwprov; + + __hwprov = rtnl_dereference(dev->hwprov); + if (__hwprov) { + __hwprov_desc.index = __hwprov->desc.index; + __hwprov_desc.qualifier = __hwprov->desc.qualifier; + } + + ret = ts_parse_hwtst_provider(tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER], + &__hwprov_desc, info->extack, + &hwprov_mod); + if (ret < 0) + return ret; + + if (hwprov_mod) { + hwprov = tsconfig_set_hwprov_from_desc(dev, info, + &__hwprov_desc); + if (IS_ERR(hwprov)) + return PTR_ERR(hwprov); + } + } + + /* Get current hwtstamp config if we are not changing the + * hwtstamp source. It will be zeroed in the other case. + */ + if (!hwprov_mod) { + ret = dev_get_hwtstamp_phylib(dev, &hwtst_config); + if (ret < 0 && ret != -EOPNOTSUPP) + goto err_free_hwprov; + } + + /* Get the hwtstamp config from netlink */ + if (tb[ETHTOOL_A_TSCONFIG_TX_TYPES]) { + u32 req_tx_type; + + req_tx_type = BIT(hwtst_config.tx_type); + ret = ethnl_update_bitset32(&req_tx_type, + __HWTSTAMP_TX_CNT, + tb[ETHTOOL_A_TSCONFIG_TX_TYPES], + ts_tx_type_names, info->extack, + &config_mod); + if (ret < 0) + goto err_free_hwprov; + + /* Select only one tx type at a time */ + if (ffs(req_tx_type) != fls(req_tx_type)) { + ret = -EINVAL; + goto err_free_hwprov; + } + + hwtst_config.tx_type = ffs(req_tx_type) - 1; + } + + if (tb[ETHTOOL_A_TSCONFIG_RX_FILTERS]) { + u32 req_rx_filter; + + req_rx_filter = BIT(hwtst_config.rx_filter); + ret = ethnl_update_bitset32(&req_rx_filter, + __HWTSTAMP_FILTER_CNT, + tb[ETHTOOL_A_TSCONFIG_RX_FILTERS], + ts_rx_filter_names, info->extack, + &config_mod); + if (ret < 0) + goto err_free_hwprov; + + /* Select only one rx filter at a time */ + if (ffs(req_rx_filter) != fls(req_rx_filter)) { + ret = -EINVAL; + goto err_free_hwprov; + } + + hwtst_config.rx_filter = ffs(req_rx_filter) - 1; + } + + if (tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS]) { + ethnl_update_u32(&hwtst_config.flags, + tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS], + &config_mod); + } + + ret = net_hwtstamp_validate(&hwtst_config); + if (ret) + goto err_free_hwprov; + + if (hwprov_mod) { + struct kernel_hwtstamp_config zero_config = {0}; + struct hwtstamp_provider *__hwprov; + + /* Disable current time stamping if we try to enable + * another one + */ + ret = dev_set_hwtstamp_phylib(dev, &zero_config, info->extack); + if (ret < 0) + goto err_free_hwprov; + + /* Change the selected hwtstamp source */ + __hwprov = rcu_replace_pointer_rtnl(dev->hwprov, hwprov); + if (__hwprov) + kfree_rcu(__hwprov, rcu_head); + } + + if (config_mod) { + ret = dev_set_hwtstamp_phylib(dev, &hwtst_config, + info->extack); + if (ret < 0) + return ret; + } + + if (hwprov_mod || config_mod) { + ret = tsconfig_send_reply(dev, info); + if (ret && ret != -EOPNOTSUPP) { + NL_SET_ERR_MSG(info->extack, + "error while reading the new configuration set"); + return ret; + } + } + + /* tsconfig has no notification */ + return 0; + +err_free_hwprov: + kfree(hwprov); + + return ret; +} + +const struct ethnl_request_ops ethnl_tsconfig_request_ops = { + .request_cmd = ETHTOOL_MSG_TSCONFIG_GET, + .reply_cmd = ETHTOOL_MSG_TSCONFIG_GET_REPLY, + .hdr_attr = ETHTOOL_A_TSCONFIG_HEADER, + .req_info_size = sizeof(struct tsconfig_req_info), + .reply_data_size = sizeof(struct tsconfig_reply_data), + + .prepare_data = tsconfig_prepare_data, + .reply_size = tsconfig_reply_size, + .fill_reply = tsconfig_fill_reply, + + .set_validate = ethnl_set_tsconfig_validate, + .set = ethnl_set_tsconfig, +}; -- 2.51.0 From d920270a6dbf756384b125ce39c17666a7c0c9f4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Dec 2024 20:58:15 +0000 Subject: [PATCH 03/16] rxrpc: Disable IRQ, not BH, to take the lock for ->attend_link Use spin_lock_irq(), not spin_lock_bh() to take the lock when accessing the ->attend_link() to stop a delay in the I/O thread due to an interrupt being taken in the app thread whilst that holds the lock and vice versa. Fixes: a2ea9a907260 ("rxrpc: Use irq-disabling spinlocks between app and I/O thread") Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/2870146.1734037095@warthog.procyon.org.uk Signed-off-by: Jakub Kicinski --- net/rxrpc/io_thread.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 2925c7fc82cf..64f8d77b8731 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -508,9 +508,9 @@ int rxrpc_io_thread(void *data) while ((conn = list_first_entry_or_null(&conn_attend_q, struct rxrpc_connection, attend_link))) { - spin_lock_bh(&local->lock); + spin_lock_irq(&local->lock); list_del_init(&conn->attend_link); - spin_unlock_bh(&local->lock); + spin_unlock_irq(&local->lock); rxrpc_input_conn_event(conn, NULL); rxrpc_put_connection(conn, rxrpc_conn_put_poke); } @@ -527,9 +527,9 @@ int rxrpc_io_thread(void *data) while ((call = list_first_entry_or_null(&call_attend_q, struct rxrpc_call, attend_link))) { - spin_lock_bh(&local->lock); + spin_lock_irq(&local->lock); list_del_init(&call->attend_link); - spin_unlock_bh(&local->lock); + spin_unlock_irq(&local->lock); trace_rxrpc_call_poked(call); rxrpc_input_call_event(call); rxrpc_put_call(call, rxrpc_call_put_poke); -- 2.51.0 From ae4f899894792c436d792c17d3f3e6a2affb787f Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Dec 2024 21:04:22 +0000 Subject: [PATCH 04/16] rxrpc: Fix ability to add more data to a call once MSG_MORE deasserted When userspace is adding data to an RPC call for transmission, it must pass MSG_MORE to sendmsg() if it intends to add more data in future calls to sendmsg(). Calling sendmsg() without MSG_MORE being asserted closes the transmission phase of the call (assuming sendmsg() adds all the data presented) and further attempts to add more data should be rejected. However, this is no longer the case. The change of call state that was previously the guard got bumped over to the I/O thread, which leaves a window for a repeat sendmsg() to insert more data. This previously went unnoticed, but the more recent patch that changed the structures behind the Tx queue added a warning: WARNING: CPU: 3 PID: 6639 at net/rxrpc/sendmsg.c:296 rxrpc_send_data+0x3f2/0x860 and rejected the additional data, returning error EPROTO. Fix this by adding a guard flag to the call, setting the flag when we queue the final packet and then rejecting further attempts to add data with EPROTO. Fixes: 2d689424b618 ("rxrpc: Move call state changes from sendmsg to I/O thread") Reported-by: syzbot+ff11be94dfcd7a5af8da@syzkaller.appspotmail.com Closes: https://lore.kernel.org/r/6757fb68.050a0220.2477f.005f.GAE@google.com/ Signed-off-by: David Howells Tested-by: syzbot+ff11be94dfcd7a5af8da@syzkaller.appspotmail.com cc: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/2870480.1734037462@warthog.procyon.org.uk Signed-off-by: Jakub Kicinski --- net/rxrpc/ar-internal.h | 1 + net/rxrpc/sendmsg.c | 8 ++++++++ 2 files changed, 9 insertions(+) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 0c0a3c89dba3..718193df9d2e 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -571,6 +571,7 @@ enum rxrpc_call_flag { RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ RXRPC_CALL_TX_ALL_ACKED, /* Last packet has been hard-acked */ + RXRPC_CALL_TX_NO_MORE, /* No more data to transmit (MSG_MORE deasserted) */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index c4c8b718cafa..0e8da909d4f2 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -266,6 +266,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, /* Order send_top after the queue->next pointer and txb content. */ smp_store_release(&call->send_top, seq); if (last) { + set_bit(RXRPC_CALL_TX_NO_MORE, &call->flags); rxrpc_notify_end_tx(rx, call, notify_end_tx); call->send_queue = NULL; } @@ -329,6 +330,13 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, bool more = msg->msg_flags & MSG_MORE; int ret, copied = 0; + if (test_bit(RXRPC_CALL_TX_NO_MORE, &call->flags)) { + trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send, + call->cid, call->call_id, call->rx_consumed, + 0, -EPROTO); + return -EPROTO; + } + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); ret = rxrpc_wait_to_be_connected(call, &timeo); -- 2.51.0 From 4fe205539c46ab0add34675ab037f49caa30607c Mon Sep 17 00:00:00 2001 From: Donald Hunter Date: Fri, 13 Dec 2024 11:25:50 +0000 Subject: [PATCH 05/16] netlink: specs: add phys-binding attr to rt_link spec Add the missing phys-binding attr to the mctp-attrs in the rt_link spec. This fixes commit 580db513b4a9 ("net: mctp: Expose transport binding identifier via IFLA attribute"). Note that enum mctp_phys_binding is not currently uapi, but perhaps it should be? Signed-off-by: Donald Hunter Link: https://patch.msgid.link/20241213112551.33557-1-donald.hunter@gmail.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/rt_link.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml index 9ffa13b77dcf..96465376d6fe 100644 --- a/Documentation/netlink/specs/rt_link.yaml +++ b/Documentation/netlink/specs/rt_link.yaml @@ -2086,6 +2086,9 @@ attribute-sets: - name: mctp-net type: u32 + - + name: phys-binding + type: u8 - name: stats-attrs name-prefix: ifla-stats- -- 2.51.0 From 77ec16be758ea65de641833149963bec39f311da Mon Sep 17 00:00:00 2001 From: Anna Emese Nyiri Date: Fri, 13 Dec 2024 09:44:54 +0100 Subject: [PATCH 06/16] sock: Introduce sk_set_prio_allowed helper function Simplify priority setting permissions with the 'sk_set_prio_allowed' function, centralizing the validation logic. This change is made in anticipation of a second caller in a following patch. No functional changes. Reviewed-by: Willem de Bruijn Reviewed-by: Eric Dumazet Suggested-by: Willem de Bruijn Signed-off-by: Anna Emese Nyiri Link: https://patch.msgid.link/20241213084457.45120-2-annaemesenyiri@gmail.com Signed-off-by: Jakub Kicinski --- net/core/sock.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 74729d20cd00..9016f984d44e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -454,6 +454,13 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return 0; } +static bool sk_set_prio_allowed(const struct sock *sk, int val) +{ + return ((val >= TC_PRIO_BESTEFFORT && val <= TC_PRIO_INTERACTIVE) || + sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || + sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); +} + static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { @@ -1193,9 +1200,7 @@ int sk_setsockopt(struct sock *sk, int level, int optname, /* handle options which do not require locking the socket. */ switch (optname) { case SO_PRIORITY: - if ((val >= 0 && val <= 6) || - sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || - sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + if (sk_set_prio_allowed(sk, val)) { sock_set_priority(sk, val); return 0; } -- 2.51.0 From a32f3e9d1ed146f81162702605d65447a319eb76 Mon Sep 17 00:00:00 2001 From: Anna Emese Nyiri Date: Fri, 13 Dec 2024 09:44:55 +0100 Subject: [PATCH 07/16] sock: support SO_PRIORITY cmsg The Linux socket API currently allows setting SO_PRIORITY at the socket level, applying a uniform priority to all packets sent through that socket. The exception to this is IP_TOS, when the priority value is calculated during the handling of ancillary data, as implemented in commit f02db315b8d8 ("ipv4: IP_TOS and IP_TTL can be specified as ancillary data"). However, this is a computed value, and there is currently no mechanism to set a custom priority via control messages prior to this patch. According to this patch, if SO_PRIORITY is specified as ancillary data, the packet is sent with the priority value set through sockc->priority, overriding the socket-level values set via the traditional setsockopt() method. This is analogous to the existing support for SO_MARK, as implemented in commit c6af0c227a22 ("ip: support SO_MARK cmsg"). If both cmsg SO_PRIORITY and IP_TOS are passed, then the one that takes precedence is the last one in the cmsg list. This patch has the side effect that raw_send_hdrinc now interprets cmsg IP_TOS. Reviewed-by: Willem de Bruijn Suggested-by: Ferenc Fejes Signed-off-by: Anna Emese Nyiri Link: https://patch.msgid.link/20241213084457.45120-3-annaemesenyiri@gmail.com Signed-off-by: Jakub Kicinski --- include/net/inet_sock.h | 2 +- include/net/ip.h | 2 +- include/net/sock.h | 4 +++- net/can/raw.c | 2 +- net/core/sock.c | 7 +++++++ net/ipv4/ip_output.c | 4 ++-- net/ipv4/ip_sockglue.c | 2 +- net/ipv4/raw.c | 2 +- net/ipv6/ip6_output.c | 3 ++- net/ipv6/ping.c | 1 + net/ipv6/raw.c | 3 ++- net/ipv6/udp.c | 1 + net/packet/af_packet.c | 2 +- 13 files changed, 24 insertions(+), 11 deletions(-) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 56d8bc5593d3..3ccbad881d74 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -172,7 +172,7 @@ struct inet_cork { u8 tx_flags; __u8 ttl; __s16 tos; - char priority; + u32 priority; __u16 gso_size; u32 ts_opt_id; u64 transmit_time; diff --git a/include/net/ip.h b/include/net/ip.h index 0e548c1f2a0e..9f5e33e371fc 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -81,7 +81,6 @@ struct ipcm_cookie { __u8 protocol; __u8 ttl; __s16 tos; - char priority; __u16 gso_size; }; @@ -96,6 +95,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm_init(ipcm); ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark); + ipcm->sockc.priority = READ_ONCE(inet->sk.sk_priority); ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags); ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; diff --git a/include/net/sock.h b/include/net/sock.h index 7464e9f9f47c..316a34d6c48b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1814,13 +1814,15 @@ struct sockcm_cookie { u32 mark; u32 tsflags; u32 ts_opt_id; + u32 priority; }; static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { *sockc = (struct sockcm_cookie) { - .tsflags = READ_ONCE(sk->sk_tsflags) + .tsflags = READ_ONCE(sk->sk_tsflags), + .priority = READ_ONCE(sk->sk_priority), }; } diff --git a/net/can/raw.c b/net/can/raw.c index 255c0a8f39d6..46e8ed9d64da 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -962,7 +962,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } skb->dev = dev; - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = sockc.priority; skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; diff --git a/net/core/sock.c b/net/core/sock.c index 9016f984d44e..a3d9941c1d32 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2947,6 +2947,13 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, case SCM_RIGHTS: case SCM_CREDENTIALS: break; + case SO_PRIORITY: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + if (!sk_set_prio_allowed(sk, *(u32 *)CMSG_DATA(cmsg))) + return -EPERM; + sockc->priority = *(u32 *)CMSG_DATA(cmsg); + break; default: return -EINVAL; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a59204a8d850..f45a083f2c13 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1333,7 +1333,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->mark = ipc->sockc.mark; - cork->priority = ipc->priority; + cork->priority = ipc->sockc.priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; sock_tx_timestamp(sk, &ipc->sockc, &cork->tx_flags); @@ -1470,7 +1470,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, ip_options_build(skb, opt, cork->addr, rt); } - skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); + skb->priority = cork->priority; skb->mark = cork->mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index cf377377b52d..f6a03b418dde 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -315,7 +315,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, if (val < 0 || val > 255) return -EINVAL; ipc->tos = val; - ipc->priority = rt_tos2priority(ipc->tos); + ipc->sockc.priority = rt_tos2priority(ipc->tos); break; case IP_PROTOCOL: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 0e9e01967ec9..4304a68d1db0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -358,7 +358,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IP); - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_dst_set(skb, &rt->dst); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3d672dea9f56..993106876604 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1401,6 +1401,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; cork->base.mark = ipc6->sockc.mark; + cork->base.priority = ipc6->sockc.priority; sock_tx_timestamp(sk, &ipc6->sockc, &cork->base.tx_flags); if (ipc6->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) { cork->base.flags |= IPCORK_TS_OPT_ID; @@ -1942,7 +1943,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, hdr->saddr = fl6->saddr; hdr->daddr = *final_dst; - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = cork->base.priority; skb->mark = cork->base.mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 88b3fcacd4f9..46b8adf6e7f8 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -119,6 +119,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return -EINVAL; ipcm6_init_sk(&ipc6, sk); + ipc6.sockc.priority = READ_ONCE(sk->sk_priority); ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = READ_ONCE(sk->sk_mark); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8476a3944a88..a45aba090aa4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -619,7 +619,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); @@ -780,6 +780,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init(&ipc6); ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = fl6.flowi6_mark; + ipc6.sockc.priority = READ_ONCE(sk->sk_priority); if (sin6) { if (addr_len < SIN6_LEN_RFC2133) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d766fd798ecf..7c14c449804c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1448,6 +1448,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = READ_ONCE(sk->sk_mark); + ipc6.sockc.priority = READ_ONCE(sk->sk_priority); /* destination address check */ if (sin6) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 886c0dd47b66..f8d87d622699 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3126,7 +3126,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->protocol = proto; skb->dev = dev; - skb->priority = READ_ONCE(sk->sk_priority); + skb->priority = sockc.priority; skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); -- 2.51.0 From cda7d5abe089cc8bd6d623cd6577627d8125d155 Mon Sep 17 00:00:00 2001 From: Anna Emese Nyiri Date: Fri, 13 Dec 2024 09:44:56 +0100 Subject: [PATCH 08/16] selftests: net: test SO_PRIORITY ancillary data with cmsg_sender Extend cmsg_sender.c with a new option '-Q' to send SO_PRIORITY ancillary data. cmsg_so_priority.sh script added to validate SO_PRIORITY behavior by creating VLAN device with egress QoS mapping and testing packet priorities using flower filters. Verify that packets with different priorities are correctly matched and counted by filters for multiple protocols and IP versions. Reviewed-by: Willem de Bruijn Acked-by: Willem de Bruijn Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Suggested-by: Ido Schimmel Signed-off-by: Anna Emese Nyiri Link: https://patch.msgid.link/20241213084457.45120-4-annaemesenyiri@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/cmsg_sender.c | 11 +- .../testing/selftests/net/cmsg_so_priority.sh | 151 ++++++++++++++++++ 3 files changed, 162 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/net/cmsg_so_priority.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index cb2fc601de66..f09bd96cc978 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -32,6 +32,7 @@ TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh +TEST_PROGS += cmsg_so_priority.sh TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh TEST_PROGS += netns-name.sh TEST_PROGS += nl_netdev.py diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index 876c2db02a63..bc314382e4e1 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -59,6 +59,7 @@ struct options { unsigned int proto; } sock; struct option_cmsg_u32 mark; + struct option_cmsg_u32 priority; struct { bool ena; unsigned int delay; @@ -97,6 +98,8 @@ static void __attribute__((noreturn)) cs_usage(const char *bin) "\n" "\t\t-m val Set SO_MARK with given value\n" "\t\t-M val Set SO_MARK via setsockopt\n" + "\t\t-P val Set SO_PRIORITY via setsockopt\n" + "\t\t-Q val Set SO_PRIORITY via cmsg\n" "\t\t-d val Set SO_TXTIME with given delay (usec)\n" "\t\t-t Enable time stamp reporting\n" "\t\t-f val Set don't fragment via cmsg\n" @@ -115,7 +118,7 @@ static void cs_parse_args(int argc, char *argv[]) { int o; - while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:")) != -1) { + while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:Q:")) != -1) { switch (o) { case 's': opt.silent_send = true; @@ -148,6 +151,10 @@ static void cs_parse_args(int argc, char *argv[]) opt.mark.ena = true; opt.mark.val = atoi(optarg); break; + case 'Q': + opt.priority.ena = true; + opt.priority.val = atoi(optarg); + break; case 'M': opt.sockopt.mark = atoi(optarg); break; @@ -252,6 +259,8 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, SOL_SOCKET, SO_MARK, &opt.mark); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_SOCKET, SO_PRIORITY, &opt.priority); ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag); ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, diff --git a/tools/testing/selftests/net/cmsg_so_priority.sh b/tools/testing/selftests/net/cmsg_so_priority.sh new file mode 100755 index 000000000000..ee07d8653262 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_so_priority.sh @@ -0,0 +1,151 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +readonly KSFT_SKIP=4 + +IP4=192.0.2.1/24 +TGT4=192.0.2.2 +TGT4_RAW=192.0.2.3 +IP6=2001:db8::1/64 +TGT6=2001:db8::2 +TGT6_RAW=2001:db8::3 +PORT=1234 +TOTAL_TESTS=0 +FAILED_TESTS=0 + +if ! command -v jq &> /dev/null; then + echo "SKIP cmsg_so_priroity.sh test: jq is not installed." >&2 + exit "$KSFT_SKIP" +fi + +check_result() { + ((TOTAL_TESTS++)) + if [ "$1" -ne 0 ]; then + ((FAILED_TESTS++)) + fi +} + +cleanup() +{ + cleanup_ns $NS +} + +trap cleanup EXIT + +setup_ns NS + +create_filter() { + local handle=$1 + local vlan_prio=$2 + local ip_type=$3 + local proto=$4 + local dst_ip=$5 + local ip_proto + + if [[ "$proto" == "u" ]]; then + ip_proto="udp" + elif [[ "$ip_type" == "ipv4" && "$proto" == "i" ]]; then + ip_proto="icmp" + elif [[ "$ip_type" == "ipv6" && "$proto" == "i" ]]; then + ip_proto="icmpv6" + fi + + tc -n $NS filter add dev dummy1 \ + egress pref 1 handle "$handle" proto 802.1q \ + flower vlan_prio "$vlan_prio" vlan_ethtype "$ip_type" \ + dst_ip "$dst_ip" ${ip_proto:+ip_proto $ip_proto} \ + action pass +} + +ip -n $NS link set dev lo up +ip -n $NS link add name dummy1 up type dummy + +ip -n $NS link add link dummy1 name dummy1.10 up type vlan id 10 \ + egress-qos-map 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 + +ip -n $NS address add $IP4 dev dummy1.10 +ip -n $NS address add $IP6 dev dummy1.10 nodad + +ip netns exec $NS sysctl -wq net.ipv4.ping_group_range='0 2147483647' + +ip -n $NS neigh add $TGT4 lladdr 00:11:22:33:44:55 nud permanent \ + dev dummy1.10 +ip -n $NS neigh add $TGT6 lladdr 00:11:22:33:44:55 nud permanent \ + dev dummy1.10 +ip -n $NS neigh add $TGT4_RAW lladdr 00:11:22:33:44:66 nud permanent \ + dev dummy1.10 +ip -n $NS neigh add $TGT6_RAW lladdr 00:11:22:33:44:66 nud permanent \ + dev dummy1.10 + +tc -n $NS qdisc add dev dummy1 clsact + +FILTER_COUNTER=10 + +for i in 4 6; do + for proto in u i r; do + echo "Test IPV$i, prot: $proto" + for priority in {0..7}; do + if [[ $i == 4 && $proto == "r" ]]; then + TGT=$TGT4_RAW + elif [[ $i == 6 && $proto == "r" ]]; then + TGT=$TGT6_RAW + elif [ $i == 4 ]; then + TGT=$TGT4 + else + TGT=$TGT6 + fi + + handle="${FILTER_COUNTER}${priority}" + + create_filter $handle $priority ipv$i $proto $TGT + + pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \ + | jq ".[] | select(.options.handle == ${handle}) | \ + .options.actions[0].stats.packets") + + if [[ $pkts == 0 ]]; then + check_result 0 + else + echo "prio $priority: expected 0, got $pkts" + check_result 1 + fi + + ip netns exec $NS ./cmsg_sender -$i -Q $priority \ + -p $proto $TGT $PORT + + pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \ + | jq ".[] | select(.options.handle == ${handle}) | \ + .options.actions[0].stats.packets") + if [[ $pkts == 1 ]]; then + check_result 0 + else + echo "prio $priority -Q: expected 1, got $pkts" + check_result 1 + fi + + ip netns exec $NS ./cmsg_sender -$i -P $priority \ + -p $proto $TGT $PORT + + pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \ + | jq ".[] | select(.options.handle == ${handle}) | \ + .options.actions[0].stats.packets") + if [[ $pkts == 2 ]]; then + check_result 0 + else + echo "prio $priority -P: expected 2, got $pkts" + check_result 1 + fi + done + FILTER_COUNTER=$((FILTER_COUNTER + 10)) + done +done + +if [ $FAILED_TESTS -ne 0 ]; then + echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed" + exit 1 +else + echo "OK - All $TOTAL_TESTS tests passed" + exit 0 +fi -- 2.51.0 From e45469e594b255ef8d750ed5576698743450d2ac Mon Sep 17 00:00:00 2001 From: Anna Emese Nyiri Date: Fri, 13 Dec 2024 09:44:57 +0100 Subject: [PATCH 09/16] sock: Introduce SO_RCVPRIORITY socket option Add new socket option, SO_RCVPRIORITY, to include SO_PRIORITY in the ancillary data returned by recvmsg(). This is analogous to the existing support for SO_RCVMARK, as implemented in commit 6fd1d51cfa253 ("net: SO_RCVMARK socket option for SO_MARK with recvmsg()"). Reviewed-by: Willem de Bruijn Suggested-by: Ferenc Fejes Signed-off-by: Anna Emese Nyiri Link: https://patch.msgid.link/20241213084457.45120-5-annaemesenyiri@gmail.com Signed-off-by: Jakub Kicinski --- arch/alpha/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ include/net/sock.h | 4 +++- include/uapi/asm-generic/socket.h | 2 ++ net/core/sock.c | 8 ++++++++ net/socket.c | 11 +++++++++++ tools/include/uapi/asm-generic/socket.h | 2 ++ 9 files changed, 34 insertions(+), 1 deletion(-) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 302507bf9b5d..3df5f2dd4c0f 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -148,6 +148,8 @@ #define SCM_TS_OPT_ID 81 +#define SO_RCVPRIORITY 82 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index d118d4731580..22fa8f19924a 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -159,6 +159,8 @@ #define SCM_TS_OPT_ID 81 +#define SO_RCVPRIORITY 82 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index d268d69bfcd2..aa9cd4b951fe 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -140,6 +140,8 @@ #define SCM_TS_OPT_ID 0x404C +#define SO_RCVPRIORITY 0x404D + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 113cd9f353e3..5b464a568664 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -141,6 +141,8 @@ #define SCM_TS_OPT_ID 0x005a +#define SO_RCVPRIORITY 0x005b + #if !defined(__KERNEL__) diff --git a/include/net/sock.h b/include/net/sock.h index 316a34d6c48b..d4bdd3286e03 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -953,6 +953,7 @@ enum sock_flags { SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ + SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) @@ -2660,7 +2661,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, { #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP) | \ - (1UL << SOCK_RCVMARK)) + (1UL << SOCK_RCVMARK) |\ + (1UL << SOCK_RCVPRIORITY)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index deacfd6dd197..aa5016ff3d91 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -143,6 +143,8 @@ #define SCM_TS_OPT_ID 81 +#define SO_RCVPRIORITY 82 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/net/core/sock.c b/net/core/sock.c index a3d9941c1d32..e7bcc8952248 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1519,6 +1519,10 @@ set_sndbuf: sock_valbool_flag(sk, SOCK_RCVMARK, valbool); break; + case SO_RCVPRIORITY: + sock_valbool_flag(sk, SOCK_RCVPRIORITY, valbool); + break; + case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; @@ -1947,6 +1951,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname, v.val = sock_flag(sk, SOCK_RCVMARK); break; + case SO_RCVPRIORITY: + v.val = sock_flag(sk, SOCK_RCVPRIORITY); + break; + case SO_RXQ_OVFL: v.val = sock_flag(sk, SOCK_RXQ_OVFL); break; diff --git a/net/socket.c b/net/socket.c index 9a117248f18f..16402b8be5a7 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1008,12 +1008,23 @@ static void sock_recv_mark(struct msghdr *msg, struct sock *sk, } } +static void sock_recv_priority(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + if (sock_flag(sk, SOCK_RCVPRIORITY) && skb) { + __u32 priority = skb->priority; + + put_cmsg(msg, SOL_SOCKET, SO_PRIORITY, sizeof(__u32), &priority); + } +} + void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { sock_recv_timestamp(msg, sk, skb); sock_recv_drops(msg, sk, skb); sock_recv_mark(msg, sk, skb); + sock_recv_priority(msg, sk, skb); } EXPORT_SYMBOL_GPL(__sock_recv_cmsgs); diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h index 281df9139d2b..ffff554a5230 100644 --- a/tools/include/uapi/asm-generic/socket.h +++ b/tools/include/uapi/asm-generic/socket.h @@ -126,6 +126,8 @@ #define SCM_TS_OPT_ID 78 +#define SO_RCVPRIORITY 79 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) -- 2.51.0 From b299ea0069284186b0d3d54aebe87f0d195d457a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 13 Dec 2024 20:01:41 +0100 Subject: [PATCH 10/16] r8169: adjust version numbering for RTL8126 Adjust version numbering for RTL8126, so that it doesn't overlap with new RTL8125 versions. Signed-off-by: Heiner Kallweit Reviewed-by: Simon Horman Link: https://patch.msgid.link/6a354364-20e9-48ad-a198-468264288757@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/realtek/r8169.h | 4 +- drivers/net/ethernet/realtek/r8169_main.c | 62 +++++++++---------- .../net/ethernet/realtek/r8169_phy_config.c | 4 +- 3 files changed, 35 insertions(+), 35 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h index 8904aae41aca..00d74e76c6f2 100644 --- a/drivers/net/ethernet/realtek/r8169.h +++ b/drivers/net/ethernet/realtek/r8169.h @@ -69,8 +69,8 @@ enum mac_version { RTL_GIGA_MAC_VER_61, RTL_GIGA_MAC_VER_63, RTL_GIGA_MAC_VER_64, - RTL_GIGA_MAC_VER_65, - RTL_GIGA_MAC_VER_66, + RTL_GIGA_MAC_VER_70, + RTL_GIGA_MAC_VER_71, RTL_GIGA_MAC_NONE }; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 6934bdee2a91..d153fa5598d5 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -140,8 +140,8 @@ static const struct { /* reserve 62 for CFG_METHOD_4 in the vendor driver */ [RTL_GIGA_MAC_VER_63] = {"RTL8125B", FIRMWARE_8125B_2}, [RTL_GIGA_MAC_VER_64] = {"RTL8125D", FIRMWARE_8125D_1}, - [RTL_GIGA_MAC_VER_65] = {"RTL8126A", FIRMWARE_8126A_2}, - [RTL_GIGA_MAC_VER_66] = {"RTL8126A", FIRMWARE_8126A_3}, + [RTL_GIGA_MAC_VER_70] = {"RTL8126A", FIRMWARE_8126A_2}, + [RTL_GIGA_MAC_VER_71] = {"RTL8126A", FIRMWARE_8126A_3}, }; static const struct pci_device_id rtl8169_pci_tbl[] = { @@ -1228,7 +1228,7 @@ static void rtl_writephy(struct rtl8169_private *tp, int location, int val) case RTL_GIGA_MAC_VER_31: r8168dp_2_mdio_write(tp, location, val); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: r8168g_mdio_write(tp, location, val); break; default: @@ -1243,7 +1243,7 @@ static int rtl_readphy(struct rtl8169_private *tp, int location) case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: return r8168dp_2_mdio_read(tp, location); - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: return r8168g_mdio_read(tp, location); default: return r8169_mdio_read(tp, location); @@ -1574,7 +1574,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) break; case RTL_GIGA_MAC_VER_34: case RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_71: r8169_mod_reg8_cond(tp, Config2, PME_SIGNAL, wolopts); break; default: @@ -2047,7 +2047,7 @@ static void rtl_set_eee_txidle_timer(struct rtl8169_private *tp) tp->tx_lpi_timer = timer_val; r8168_mac_ocp_write(tp, 0xe048, timer_val); break; - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: tp->tx_lpi_timer = timer_val; RTL_W16(tp, EEE_TXIDLE_TIMER_8125, timer_val); break; @@ -2255,8 +2255,8 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) enum mac_version ver; } mac_info[] = { /* 8126A family. */ - { 0x7cf, 0x64a, RTL_GIGA_MAC_VER_66 }, - { 0x7cf, 0x649, RTL_GIGA_MAC_VER_65 }, + { 0x7cf, 0x64a, RTL_GIGA_MAC_VER_71 }, + { 0x7cf, 0x649, RTL_GIGA_MAC_VER_70 }, /* 8125D family. */ { 0x7cf, 0x688, RTL_GIGA_MAC_VER_64 }, @@ -2526,7 +2526,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_61: RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST); break; - case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_71: RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST | RX_PAUSE_SLOT_ON); break; @@ -2658,7 +2658,7 @@ static void rtl_wait_txrx_fifo_empty(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_61: rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42); break; - case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_71: RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq); rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42); rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond_2, 100, 42); @@ -2901,7 +2901,7 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_38: rtl_eri_set_bits(tp, 0xd4, 0x0c00); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80); break; default: @@ -2915,7 +2915,7 @@ static void rtl_disable_exit_l1(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38: rtl_eri_clear_bits(tp, 0xd4, 0x1f00); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: r8168_mac_ocp_modify(tp, 0xc0ac, 0x1f80, 0); break; default: @@ -2941,8 +2941,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) rtl_mod_config5(tp, 0, ASPM_en); switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_65: - case RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_70: + case RTL_GIGA_MAC_VER_71: val8 = RTL_R8(tp, INT_CFG0_8125) | INT_CFG0_CLKREQEN; RTL_W8(tp, INT_CFG0_8125, val8); break; @@ -2953,7 +2953,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) switch (tp->mac_version) { case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: /* reset ephy tx/rx disable timer */ r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0); /* chip can trigger L1.2 */ @@ -2965,7 +2965,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) } else { switch (tp->mac_version) { case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0); break; default: @@ -2973,8 +2973,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) } switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_65: - case RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_70: + case RTL_GIGA_MAC_VER_71: val8 = RTL_R8(tp, INT_CFG0_8125) & ~INT_CFG0_CLKREQEN; RTL_W8(tp, INT_CFG0_8125, val8); break; @@ -3694,12 +3694,12 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp) /* disable new tx descriptor format */ r8168_mac_ocp_modify(tp, 0xeb58, 0x0001, 0x0000); - if (tp->mac_version == RTL_GIGA_MAC_VER_65 || - tp->mac_version == RTL_GIGA_MAC_VER_66) + if (tp->mac_version == RTL_GIGA_MAC_VER_70 || + tp->mac_version == RTL_GIGA_MAC_VER_71) RTL_W8(tp, 0xD8, RTL_R8(tp, 0xD8) & ~0x02); - if (tp->mac_version == RTL_GIGA_MAC_VER_65 || - tp->mac_version == RTL_GIGA_MAC_VER_66) + if (tp->mac_version == RTL_GIGA_MAC_VER_70 || + tp->mac_version == RTL_GIGA_MAC_VER_71) r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0400); else if (tp->mac_version == RTL_GIGA_MAC_VER_63) r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0200); @@ -3717,8 +3717,8 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp) r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0030); r8168_mac_ocp_modify(tp, 0xe040, 0x1000, 0x0000); r8168_mac_ocp_modify(tp, 0xea1c, 0x0003, 0x0001); - if (tp->mac_version == RTL_GIGA_MAC_VER_65 || - tp->mac_version == RTL_GIGA_MAC_VER_66) + if (tp->mac_version == RTL_GIGA_MAC_VER_70 || + tp->mac_version == RTL_GIGA_MAC_VER_71) r8168_mac_ocp_modify(tp, 0xea1c, 0x0300, 0x0000); else r8168_mac_ocp_modify(tp, 0xea1c, 0x0004, 0x0000); @@ -3837,8 +3837,8 @@ static void rtl_hw_config(struct rtl8169_private *tp) [RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2, [RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b, [RTL_GIGA_MAC_VER_64] = rtl_hw_start_8125d, - [RTL_GIGA_MAC_VER_65] = rtl_hw_start_8126a, - [RTL_GIGA_MAC_VER_66] = rtl_hw_start_8126a, + [RTL_GIGA_MAC_VER_70] = rtl_hw_start_8126a, + [RTL_GIGA_MAC_VER_71] = rtl_hw_start_8126a, }; if (hw_configs[tp->mac_version]) @@ -3859,8 +3859,8 @@ static void rtl_hw_start_8125(struct rtl8169_private *tp) RTL_W32(tp, i, 0); break; case RTL_GIGA_MAC_VER_63: - case RTL_GIGA_MAC_VER_65: - case RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_70: + case RTL_GIGA_MAC_VER_71: for (i = 0xa00; i < 0xa80; i += 4) RTL_W32(tp, i, 0); RTL_W16(tp, INT_CFG1_8125, 0x0000); @@ -4092,7 +4092,7 @@ static void rtl8169_cleanup(struct rtl8169_private *tp) RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq); rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71: rtl_enable_rxdvgate(tp); fsleep(2000); break; @@ -4249,7 +4249,7 @@ static unsigned int rtl_quirk_packet_padto(struct rtl8169_private *tp, switch (tp->mac_version) { case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: padto = max_t(unsigned int, padto, ETH_ZLEN); break; default: @@ -5267,7 +5267,7 @@ static void rtl_hw_initialize(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48: rtl_hw_init_8168g(tp); break; - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71: rtl_hw_init_8125(tp); break; default: diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index b28b30390e84..bc498ea78034 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -1162,8 +1162,8 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev, [RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config, [RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config, [RTL_GIGA_MAC_VER_64] = rtl8125d_hw_phy_config, - [RTL_GIGA_MAC_VER_65] = rtl8126a_hw_phy_config, - [RTL_GIGA_MAC_VER_66] = rtl8126a_hw_phy_config, + [RTL_GIGA_MAC_VER_70] = rtl8126a_hw_phy_config, + [RTL_GIGA_MAC_VER_71] = rtl8126a_hw_phy_config, }; if (phy_configs[ver]) -- 2.51.0 From b3593df26ab19f114d613693fa8a92ab202803d0 Mon Sep 17 00:00:00 2001 From: ChunHao Lin Date: Fri, 13 Dec 2024 20:02:58 +0100 Subject: [PATCH 11/16] r8169: add support for RTL8125D rev.b Add support for RTL8125D rev.b. Its XID is 0x689. It is basically based on the one with XID 0x688, but with different firmware file. Signed-off-by: ChunHao Lin [hkallweit1@gmail.com: rebased after adjusted version numbering] Signed-off-by: Heiner Kallweit Reviewed-by: Simon Horman Link: https://patch.msgid.link/75e5e9ec-d01f-43ac-b0f4-e7456baf18d1@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/realtek/r8169.h | 1 + drivers/net/ethernet/realtek/r8169_main.c | 6 ++++++ drivers/net/ethernet/realtek/r8169_phy_config.c | 1 + 3 files changed, 8 insertions(+) diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h index 00d74e76c6f2..e0817f2a311a 100644 --- a/drivers/net/ethernet/realtek/r8169.h +++ b/drivers/net/ethernet/realtek/r8169.h @@ -69,6 +69,7 @@ enum mac_version { RTL_GIGA_MAC_VER_61, RTL_GIGA_MAC_VER_63, RTL_GIGA_MAC_VER_64, + RTL_GIGA_MAC_VER_65, RTL_GIGA_MAC_VER_70, RTL_GIGA_MAC_VER_71, RTL_GIGA_MAC_NONE diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index d153fa5598d5..5724f650f9c6 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -57,6 +57,7 @@ #define FIRMWARE_8125A_3 "rtl_nic/rtl8125a-3.fw" #define FIRMWARE_8125B_2 "rtl_nic/rtl8125b-2.fw" #define FIRMWARE_8125D_1 "rtl_nic/rtl8125d-1.fw" +#define FIRMWARE_8125D_2 "rtl_nic/rtl8125d-2.fw" #define FIRMWARE_8126A_2 "rtl_nic/rtl8126a-2.fw" #define FIRMWARE_8126A_3 "rtl_nic/rtl8126a-3.fw" @@ -140,6 +141,7 @@ static const struct { /* reserve 62 for CFG_METHOD_4 in the vendor driver */ [RTL_GIGA_MAC_VER_63] = {"RTL8125B", FIRMWARE_8125B_2}, [RTL_GIGA_MAC_VER_64] = {"RTL8125D", FIRMWARE_8125D_1}, + [RTL_GIGA_MAC_VER_65] = {"RTL8125D", FIRMWARE_8125D_2}, [RTL_GIGA_MAC_VER_70] = {"RTL8126A", FIRMWARE_8126A_2}, [RTL_GIGA_MAC_VER_71] = {"RTL8126A", FIRMWARE_8126A_3}, }; @@ -706,6 +708,7 @@ MODULE_FIRMWARE(FIRMWARE_8107E_2); MODULE_FIRMWARE(FIRMWARE_8125A_3); MODULE_FIRMWARE(FIRMWARE_8125B_2); MODULE_FIRMWARE(FIRMWARE_8125D_1); +MODULE_FIRMWARE(FIRMWARE_8125D_2); MODULE_FIRMWARE(FIRMWARE_8126A_2); MODULE_FIRMWARE(FIRMWARE_8126A_3); @@ -2259,6 +2262,7 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) { 0x7cf, 0x649, RTL_GIGA_MAC_VER_70 }, /* 8125D family. */ + { 0x7cf, 0x689, RTL_GIGA_MAC_VER_65 }, { 0x7cf, 0x688, RTL_GIGA_MAC_VER_64 }, /* 8125B family. */ @@ -3837,6 +3841,7 @@ static void rtl_hw_config(struct rtl8169_private *tp) [RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2, [RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b, [RTL_GIGA_MAC_VER_64] = rtl_hw_start_8125d, + [RTL_GIGA_MAC_VER_65] = rtl_hw_start_8125d, [RTL_GIGA_MAC_VER_70] = rtl_hw_start_8126a, [RTL_GIGA_MAC_VER_71] = rtl_hw_start_8126a, }; @@ -3855,6 +3860,7 @@ static void rtl_hw_start_8125(struct rtl8169_private *tp) switch (tp->mac_version) { case RTL_GIGA_MAC_VER_61: case RTL_GIGA_MAC_VER_64: + case RTL_GIGA_MAC_VER_65: for (i = 0xa00; i < 0xb00; i += 4) RTL_W32(tp, i, 0); break; diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index bc498ea78034..968c8a2185a4 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -1162,6 +1162,7 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev, [RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config, [RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config, [RTL_GIGA_MAC_VER_64] = rtl8125d_hw_phy_config, + [RTL_GIGA_MAC_VER_65] = rtl8125d_hw_phy_config, [RTL_GIGA_MAC_VER_70] = rtl8126a_hw_phy_config, [RTL_GIGA_MAC_VER_71] = rtl8126a_hw_phy_config, }; -- 2.51.0 From 34c899af6c1a9d65aa85c765b2eecb1b9a88e8b8 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 13 Dec 2024 20:08:39 +0900 Subject: [PATCH 12/16] af_unix: Set error only when needed in unix_stream_connect(). We will introduce skb drop reason for AF_UNIX, then we need to set an errno and a drop reason for each path. Let's set an error only when it's needed in unix_stream_connect(). Signed-off-by: Kuniyuki Iwashima Signed-off-by: Paolo Abeni --- net/unix/af_unix.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6b1762300443..23f419f561b8 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1575,12 +1575,12 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, goto out; } - err = -ENOMEM; - /* Allocate skb for sending to listening sock */ skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL); - if (skb == NULL) + if (!skb) { + err = -ENOMEM; goto out; + } restart: /* Find listening sock. */ @@ -1600,16 +1600,17 @@ restart: goto restart; } - err = -ECONNREFUSED; - if (other->sk_state != TCP_LISTEN) - goto out_unlock; - if (other->sk_shutdown & RCV_SHUTDOWN) + if (other->sk_state != TCP_LISTEN || + other->sk_shutdown & RCV_SHUTDOWN) { + err = -ECONNREFUSED; goto out_unlock; + } if (unix_recvq_full_lockless(other)) { - err = -EAGAIN; - if (!timeo) + if (!timeo) { + err = -EAGAIN; goto out_unlock; + } timeo = unix_wait_for_peer(other, timeo); -- 2.51.0 From e26ee0a736bd949ce6fa51829fd0a2f6381391de Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 13 Dec 2024 20:08:40 +0900 Subject: [PATCH 13/16] af_unix: Clean up error paths in unix_stream_connect(). The label order is weird in unix_stream_connect(), and all NULL checks are unnecessary if reordered. Let's clean up the error paths to make it easy to set a drop reason for each path. While at it, a comment with the old style is updated. Signed-off-by: Kuniyuki Iwashima Signed-off-by: Paolo Abeni --- net/unix/af_unix.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 23f419f561b8..21e17e739f88 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1563,15 +1563,14 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); /* First of all allocate resources. - If we will make it after state is locked, - we will have to recheck all again in any case. + * If we will make it after state is locked, + * we will have to recheck all again in any case. */ /* create new sock for complete connection */ newsk = unix_create1(net, NULL, 0, sock->type); if (IS_ERR(newsk)) { err = PTR_ERR(newsk); - newsk = NULL; goto out; } @@ -1579,7 +1578,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL); if (!skb) { err = -ENOMEM; - goto out; + goto out_free_sk; } restart: @@ -1587,8 +1586,7 @@ restart: other = unix_find_other(net, sunaddr, addr_len, sk->sk_type); if (IS_ERR(other)) { err = PTR_ERR(other); - other = NULL; - goto out; + goto out_free_skb; } unix_state_lock(other); @@ -1613,11 +1611,12 @@ restart: } timeo = unix_wait_for_peer(other, timeo); + sock_put(other); err = sock_intr_errno(timeo); if (signal_pending(current)) - goto out; - sock_put(other); + goto out_free_skb; + goto restart; } @@ -1702,15 +1701,13 @@ restart: return 0; out_unlock: - if (other) - unix_state_unlock(other); - -out: + unix_state_unlock(other); + sock_put(other); +out_free_skb: kfree_skb(skb); - if (newsk) - unix_release_sock(newsk, 0); - if (other) - sock_put(other); +out_free_sk: + unix_release_sock(newsk, 0); +out: return err; } -- 2.51.0 From 6c444255b193b5b9c5a18c3784d960e10e1833a2 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 13 Dec 2024 20:08:41 +0900 Subject: [PATCH 14/16] af_unix: Set error only when needed in unix_stream_sendmsg(). We will introduce skb drop reason for AF_UNIX, then we need to set an errno and a drop reason for each path. Let's set an error only when it's needed in unix_stream_sendmsg(). Signed-off-by: Kuniyuki Iwashima Signed-off-by: Paolo Abeni --- net/unix/af_unix.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 21e17e739f88..660d8b8130ca 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2254,8 +2254,8 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, wait_for_unix_gc(scm.fp); - err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) { + err = -EOPNOTSUPP; #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (len) len--; @@ -2268,10 +2268,11 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, err = READ_ONCE(sk->sk_state) == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out_err; } else { - err = -ENOTCONN; other = unix_peer(sk); - if (!other) + if (!other) { + err = -ENOTCONN; goto out_err; + } } if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) -- 2.51.0 From d460b04bc452cf15810b79c15381fffd9d201915 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 13 Dec 2024 20:08:42 +0900 Subject: [PATCH 15/16] af_unix: Clean up error paths in unix_stream_sendmsg(). If we move send_sig() to the SEND_SHUTDOWN check before the while loop, then we can reuse the same kfree_skb() after the pipe_err_free label. Let's gather the scattered kfree_skb()s in error paths. While at it, some style issues are fixed, and the pipe_err_free label is renamed to out_pipe to match other label names. Signed-off-by: Kuniyuki Iwashima Signed-off-by: Paolo Abeni --- net/unix/af_unix.c | 39 ++++++++++++++++++++------------------- 1 file changed, 20 insertions(+), 19 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 660d8b8130ca..d30bcd50527e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2275,8 +2275,13 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, } } - if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) - goto pipe_err; + if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) { + if (!(msg->msg_flags & MSG_NOSIGNAL)) + send_sig(SIGPIPE, current, 0); + + err = -EPIPE; + goto out_err; + } while (sent < len) { size = len - sent; @@ -2305,20 +2310,18 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, /* Only send the fds in the first buffer */ err = unix_scm_to_skb(&scm, skb, !fds_sent); - if (err < 0) { - kfree_skb(skb); - goto out_err; - } + if (err < 0) + goto out_free; + fds_sent = true; if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { skb->ip_summed = CHECKSUM_UNNECESSARY; err = skb_splice_from_iter(skb, &msg->msg_iter, size, sk->sk_allocation); - if (err < 0) { - kfree_skb(skb); - goto out_err; - } + if (err < 0) + goto out_free; + size = err; refcount_add(size, &sk->sk_wmem_alloc); } else { @@ -2326,17 +2329,15 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, skb->data_len = data_len; skb->len = size; err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); - if (err) { - kfree_skb(skb); - goto out_err; - } + if (err) + goto out_free; } unix_state_lock(other); if (sock_flag(other, SOCK_DEAD) || (other->sk_shutdown & RCV_SHUTDOWN)) - goto pipe_err_free; + goto out_pipe; maybe_add_creds(skb, sock, other); scm_stat_add(other, skb); @@ -2359,13 +2360,13 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, return sent; -pipe_err_free: +out_pipe: unix_state_unlock(other); - kfree_skb(skb); -pipe_err: - if (sent == 0 && !(msg->msg_flags&MSG_NOSIGNAL)) + if (!sent && !(msg->msg_flags & MSG_NOSIGNAL)) send_sig(SIGPIPE, current, 0); err = -EPIPE; +out_free: + kfree_skb(skb); out_err: scm_destroy(&scm); return sent ? : err; -- 2.51.0 From 001a25088c35ab69bd4b2f208e47eb8acbce6353 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 13 Dec 2024 20:08:43 +0900 Subject: [PATCH 16/16] af_unix: Set error only when needed in unix_dgram_sendmsg(). We will introduce skb drop reason for AF_UNIX, then we need to set an errno and a drop reason for each path. Let's set an error only when it's needed in unix_dgram_sendmsg(). Then, we need not (re)set 0 to err. Signed-off-by: Kuniyuki Iwashima Signed-off-by: Paolo Abeni --- net/unix/af_unix.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index d30bcd50527e..07d6fba99a7c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1978,9 +1978,10 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, wait_for_unix_gc(scm.fp); - err = -EOPNOTSUPP; - if (msg->msg_flags&MSG_OOB) + if (msg->msg_flags & MSG_OOB) { + err = -EOPNOTSUPP; goto out; + } if (msg->msg_namelen) { err = unix_validate_addr(sunaddr, msg->msg_namelen); @@ -1995,10 +1996,11 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, goto out; } else { sunaddr = NULL; - err = -ENOTCONN; other = unix_peer_get(sk); - if (!other) + if (!other) { + err = -ENOTCONN; goto out; + } } if ((test_bit(SOCK_PASSCRED, &sock->flags) || @@ -2009,9 +2011,10 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, goto out; } - err = -EMSGSIZE; - if (len > READ_ONCE(sk->sk_sndbuf) - 32) + if (len > READ_ONCE(sk->sk_sndbuf) - 32) { + err = -EMSGSIZE; goto out; + } if (len > SKB_MAX_ALLOC) { data_len = min_t(size_t, @@ -2043,9 +2046,10 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, restart: if (!other) { - err = -ECONNRESET; - if (sunaddr == NULL) + if (!sunaddr) { + err = -ECONNRESET; goto out_free; + } other = unix_find_other(sock_net(sk), sunaddr, msg->msg_namelen, sk->sk_type); @@ -2065,9 +2069,11 @@ restart: sk_locked = 0; unix_state_lock(other); restart_locked: - err = -EPERM; - if (!unix_may_send(sk, other)) + + if (!unix_may_send(sk, other)) { + err = -EPERM; goto out_unlock; + } if (unlikely(sock_flag(other, SOCK_DEAD))) { /* @@ -2080,7 +2086,6 @@ restart_locked: if (!sk_locked) unix_state_lock(sk); - err = 0; if (sk->sk_type == SOCK_SEQPACKET) { /* We are here only when racing with unix_release_sock() * is clearing @other. Never change state to TCP_CLOSE @@ -2108,9 +2113,10 @@ restart_locked: goto restart; } - err = -EPIPE; - if (other->sk_shutdown & RCV_SHUTDOWN) + if (other->sk_shutdown & RCV_SHUTDOWN) { + err = -EPIPE; goto out_unlock; + } if (sk->sk_type != SOCK_SEQPACKET) { err = security_unix_may_send(sk->sk_socket, other->sk_socket); -- 2.51.0