diff options
44 files changed, 2290 insertions, 62 deletions
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 31a601cafa3f..567326491f80 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -197,6 +197,13 @@ Userspace to kernel: ``ETHTOOL_MSG_RINGS_SET`` set ring sizes ``ETHTOOL_MSG_CHANNELS_GET`` get channel counts ``ETHTOOL_MSG_CHANNELS_SET`` set channel counts + ``ETHTOOL_MSG_COALESCE_GET`` get coalescing parameters + ``ETHTOOL_MSG_COALESCE_SET`` set coalescing parameters + ``ETHTOOL_MSG_PAUSE_GET`` get pause parameters + ``ETHTOOL_MSG_PAUSE_SET`` set pause parameters + ``ETHTOOL_MSG_EEE_GET`` get EEE settings + ``ETHTOOL_MSG_EEE_SET`` set EEE settings + ``ETHTOOL_MSG_TSINFO_GET`` get timestamping info ===================================== ================================ Kernel to userspace: @@ -221,6 +228,13 @@ Kernel to userspace: ``ETHTOOL_MSG_RINGS_NTF`` ring sizes ``ETHTOOL_MSG_CHANNELS_GET_REPLY`` channel counts ``ETHTOOL_MSG_CHANNELS_NTF`` channel counts + ``ETHTOOL_MSG_COALESCE_GET_REPLY`` coalescing parameters + ``ETHTOOL_MSG_COALESCE_NTF`` coalescing parameters + ``ETHTOOL_MSG_PAUSE_GET_REPLY`` pause parameters + ``ETHTOOL_MSG_PAUSE_NTF`` pause parameters + ``ETHTOOL_MSG_EEE_GET_REPLY`` EEE settings + ``ETHTOOL_MSG_EEE_NTF`` EEE settings + ``ETHTOOL_MSG_TSINFO_GET_REPLY`` timestamping info ===================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -745,6 +759,203 @@ driver. Driver may impose additional constraints and may not suspport all attributes. +COALESCE_GET +============ + +Gets coalescing parameters like ``ETHTOOL_GCOALESCE`` ioctl request. + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_COALESCE_HEADER`` nested request header + ==================================== ====== ========================== + +Kernel response contents: + + =========================================== ====== ======================= + ``ETHTOOL_A_COALESCE_HEADER`` nested reply header + ``ETHTOOL_A_COALESCE_RX_USECS`` u32 delay (us), normal Rx + ``ETHTOOL_A_COALESCE_RX_MAX_FRAMES`` u32 max packets, normal Rx + ``ETHTOOL_A_COALESCE_RX_USECS_IRQ`` u32 delay (us), Rx in IRQ + ``ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ`` u32 max packets, Rx in IRQ + ``ETHTOOL_A_COALESCE_TX_USECS`` u32 delay (us), normal Tx + ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES`` u32 max packets, normal Tx + ``ETHTOOL_A_COALESCE_TX_USECS_IRQ`` u32 delay (us), Tx in IRQ + ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ`` u32 IRQ packets, Tx in IRQ + ``ETHTOOL_A_COALESCE_STATS_BLOCK_USECS`` u32 delay of stats update + ``ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX`` bool adaptive Rx coalesce + ``ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX`` bool adaptive Tx coalesce + ``ETHTOOL_A_COALESCE_PKT_RATE_LOW`` u32 threshold for low rate + ``ETHTOOL_A_COALESCE_RX_USECS_LOW`` u32 delay (us), low Rx + ``ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW`` u32 max packets, low Rx + ``ETHTOOL_A_COALESCE_TX_USECS_LOW`` u32 delay (us), low Tx + ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW`` u32 max packets, low Tx + ``ETHTOOL_A_COALESCE_PKT_RATE_HIGH`` u32 threshold for high rate + ``ETHTOOL_A_COALESCE_RX_USECS_HIGH`` u32 delay (us), high Rx + ``ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH`` u32 max packets, high Rx + ``ETHTOOL_A_COALESCE_TX_USECS_HIGH`` u32 delay (us), high Tx + ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH`` u32 max packets, high Tx + ``ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL`` u32 rate sampling interval + =========================================== ====== ======================= + +Attributes are only included in reply if their value is not zero or the +corresponding bit in ``ethtool_ops::supported_coalesce_params`` is set (i.e. +they are declared as supported by driver). + + +COALESCE_SET +============ + +Sets coalescing parameters like ``ETHTOOL_SCOALESCE`` ioctl request. + +Request contents: + + =========================================== ====== ======================= + ``ETHTOOL_A_COALESCE_HEADER`` nested request header + ``ETHTOOL_A_COALESCE_RX_USECS`` u32 delay (us), normal Rx + ``ETHTOOL_A_COALESCE_RX_MAX_FRAMES`` u32 max packets, normal Rx + ``ETHTOOL_A_COALESCE_RX_USECS_IRQ`` u32 delay (us), Rx in IRQ + ``ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ`` u32 max packets, Rx in IRQ + ``ETHTOOL_A_COALESCE_TX_USECS`` u32 delay (us), normal Tx + ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES`` u32 max packets, normal Tx + ``ETHTOOL_A_COALESCE_TX_USECS_IRQ`` u32 delay (us), Tx in IRQ + ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ`` u32 IRQ packets, Tx in IRQ + ``ETHTOOL_A_COALESCE_STATS_BLOCK_USECS`` u32 delay of stats update + ``ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX`` bool adaptive Rx coalesce + ``ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX`` bool adaptive Tx coalesce + ``ETHTOOL_A_COALESCE_PKT_RATE_LOW`` u32 threshold for low rate + ``ETHTOOL_A_COALESCE_RX_USECS_LOW`` u32 delay (us), low Rx + ``ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW`` u32 max packets, low Rx + ``ETHTOOL_A_COALESCE_TX_USECS_LOW`` u32 delay (us), low Tx + ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW`` u32 max packets, low Tx + ``ETHTOOL_A_COALESCE_PKT_RATE_HIGH`` u32 threshold for high rate + ``ETHTOOL_A_COALESCE_RX_USECS_HIGH`` u32 delay (us), high Rx + ``ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH`` u32 max packets, high Rx + ``ETHTOOL_A_COALESCE_TX_USECS_HIGH`` u32 delay (us), high Tx + ``ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH`` u32 max packets, high Tx + ``ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL`` u32 rate sampling interval + =========================================== ====== ======================= + +Request is rejected if it attributes declared as unsupported by driver (i.e. +such that the corresponding bit in ``ethtool_ops::supported_coalesce_params`` +is not set), regardless of their values. Driver may impose additional +constraints on coalescing parameters and their values. + + +PAUSE_GET +============ + +Gets channel counts like ``ETHTOOL_GPAUSE`` ioctl request. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_PAUSE_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_PAUSE_HEADER`` nested request header + ``ETHTOOL_A_PAUSE_AUTONEG`` bool pause autonegotiation + ``ETHTOOL_A_PAUSE_RX`` bool receive pause frames + ``ETHTOOL_A_PAUSE_TX`` bool transmit pause frames + ===================================== ====== ========================== + + +PAUSE_SET +============ + +Sets pause parameters like ``ETHTOOL_GPAUSEPARAM`` ioctl request. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_PAUSE_HEADER`` nested request header + ``ETHTOOL_A_PAUSE_AUTONEG`` bool pause autonegotiation + ``ETHTOOL_A_PAUSE_RX`` bool receive pause frames + ``ETHTOOL_A_PAUSE_TX`` bool transmit pause frames + ===================================== ====== ========================== + + +EEE_GET +======= + +Gets channel counts like ``ETHTOOL_GEEE`` ioctl request. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_EEE_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_EEE_HEADER`` nested request header + ``ETHTOOL_A_EEE_MODES_OURS`` bool supported/advertised modes + ``ETHTOOL_A_EEE_MODES_PEER`` bool peer advertised link modes + ``ETHTOOL_A_EEE_ACTIVE`` bool EEE is actively used + ``ETHTOOL_A_EEE_ENABLED`` bool EEE is enabled + ``ETHTOOL_A_EEE_TX_LPI_ENABLED`` bool Tx lpi enabled + ``ETHTOOL_A_EEE_TX_LPI_TIMER`` u32 Tx lpi timeout (in us) + ===================================== ====== ========================== + +In ``ETHTOOL_A_EEE_MODES_OURS``, mask consists of link modes for which EEE is +enabled, value of link modes for which EEE is advertised. Link modes for which +peer advertises EEE are listed in ``ETHTOOL_A_EEE_MODES_PEER`` (no mask). The +netlink interface allows reporting EEE status for all link modes but only +first 32 are provided by the ``ethtool_ops`` callback. + + +EEE_SET +======= + +Sets pause parameters like ``ETHTOOL_GEEEPARAM`` ioctl request. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_EEE_HEADER`` nested request header + ``ETHTOOL_A_EEE_MODES_OURS`` bool advertised modes + ``ETHTOOL_A_EEE_ENABLED`` bool EEE is enabled + ``ETHTOOL_A_EEE_TX_LPI_ENABLED`` bool Tx lpi enabled + ``ETHTOOL_A_EEE_TX_LPI_TIMER`` u32 Tx lpi timeout (in us) + ===================================== ====== ========================== + +``ETHTOOL_A_EEE_MODES_OURS`` is used to either list link modes to advertise +EEE for (if there is no mask) or specify changes to the list (if there is +a mask). The netlink interface allows reporting EEE status for all link modes +but only first 32 can be set at the moment as that is what the ``ethtool_ops`` +callback supports. + + +TSINFO_GET +========== + +Gets timestamping information like ``ETHTOOL_GET_TS_INFO`` ioctl request. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_TSINFO_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_TSINFO_HEADER`` nested request header + ``ETHTOOL_A_TSINFO_TIMESTAMPING`` bitset SO_TIMESTAMPING flags + ``ETHTOOL_A_TSINFO_TX_TYPES`` bitset supported Tx types + ``ETHTOOL_A_TSINFO_RX_FILTERS`` bitset supported Rx filters + ``ETHTOOL_A_TSINFO_PHC_INDEX`` u32 PTP hw clock index + ===================================== ====== ========================== + +``ETHTOOL_A_TSINFO_PHC_INDEX`` is absent if there is no associated PHC (there +is no special value for this case). The bitset attributes are omitted if they +would be empty (no bit set). + + Request translation =================== @@ -769,12 +980,12 @@ have their netlink replacement yet. ``ETHTOOL_GLINK`` ``ETHTOOL_MSG_LINKSTATE_GET`` ``ETHTOOL_GEEPROM`` n/a ``ETHTOOL_SEEPROM`` n/a - ``ETHTOOL_GCOALESCE`` n/a - ``ETHTOOL_SCOALESCE`` n/a + ``ETHTOOL_GCOALESCE`` ``ETHTOOL_MSG_COALESCE_GET`` + ``ETHTOOL_SCOALESCE`` ``ETHTOOL_MSG_COALESCE_SET`` ``ETHTOOL_GRINGPARAM`` ``ETHTOOL_MSG_RINGS_GET`` ``ETHTOOL_SRINGPARAM`` ``ETHTOOL_MSG_RINGS_SET`` - ``ETHTOOL_GPAUSEPARAM`` n/a - ``ETHTOOL_SPAUSEPARAM`` n/a + ``ETHTOOL_GPAUSEPARAM`` ``ETHTOOL_MSG_PAUSE_GET`` + ``ETHTOOL_SPAUSEPARAM`` ``ETHTOOL_MSG_PAUSE_SET`` ``ETHTOOL_GRXCSUM`` ``ETHTOOL_MSG_FEATURES_GET`` ``ETHTOOL_SRXCSUM`` ``ETHTOOL_MSG_FEATURES_SET`` ``ETHTOOL_GTXCSUM`` ``ETHTOOL_MSG_FEATURES_GET`` @@ -820,11 +1031,11 @@ have their netlink replacement yet. ``ETHTOOL_SET_DUMP`` n/a ``ETHTOOL_GET_DUMP_FLAG`` n/a ``ETHTOOL_GET_DUMP_DATA`` n/a - ``ETHTOOL_GET_TS_INFO`` n/a + ``ETHTOOL_GET_TS_INFO`` ``ETHTOOL_MSG_TSINFO_GET`` ``ETHTOOL_GMODULEINFO`` n/a ``ETHTOOL_GMODULEEEPROM`` n/a - ``ETHTOOL_GEEE`` n/a - ``ETHTOOL_SEEE`` n/a + ``ETHTOOL_GEEE`` ``ETHTOOL_MSG_EEE_GET`` + ``ETHTOOL_SEEE`` ``ETHTOOL_MSG_EEE_SET`` ``ETHTOOL_GRSSH`` n/a ``ETHTOOL_SRSSH`` n/a ``ETHTOOL_GTUNABLE`` n/a diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ea7c7906591e..2cb445a8fc9e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -74,6 +74,7 @@ struct ipv6_devconf { __u32 addr_gen_mode; __s32 disable_policy; __s32 ndisc_tclass; + __s32 rpl_seg_enabled; struct ctl_table_header *sysctl_header; }; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index a088349dd94f..e0eabe58aa8b 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -90,6 +90,9 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr); #endif +int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs, + unsigned char nsegs); + bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index dabe398bee4c..59e0d4e99f94 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -470,8 +470,9 @@ int fib_nh_init(struct net *net, struct fib_nh *fib_nh, struct fib_config *cfg, int nh_weight, struct netlink_ext_ack *extack); void fib_nh_release(struct net *net, struct fib_nh *fib_nh); -int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *fc_encap, - u16 fc_encap_type, void *cfg, gfp_t gfp_flags, +int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, + struct nlattr *fc_encap, u16 fc_encap_type, + void *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib_nh_common_release(struct fib_nh_common *nhc); diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index b5e6edf74b70..05cfd6ff6528 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -34,7 +34,7 @@ struct lwtunnel_state { }; struct lwtunnel_encap_ops { - int (*build_state)(struct nlattr *encap, + int (*build_state)(struct net *net, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack); @@ -113,7 +113,7 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack); -int lwtunnel_build_state(u16 encap_type, +int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, @@ -209,7 +209,7 @@ static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, return 0; } -static inline int lwtunnel_build_state(u16 encap_type, +static inline int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, diff --git a/include/net/rpl.h b/include/net/rpl.h new file mode 100644 index 000000000000..dceff60e8baf --- /dev/null +++ b/include/net/rpl.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * RPL implementation + * + * Author: + * (C) 2020 Alexander Aring <[email protected]> + */ + +#ifndef _NET_RPL_H +#define _NET_RPL_H + +#include <linux/rpl.h> + +#if IS_ENABLED(CONFIG_IPV6_RPL_LWTUNNEL) +extern int rpl_init(void); +extern void rpl_exit(void); +#else +static inline int rpl_init(void) +{ + return 0; +} + +static inline void rpl_exit(void) {} +#endif + +/* Worst decompression memory usage ipv6 address (16) + pad 7 */ +#define IPV6_RPL_SRH_WORST_SWAP_SIZE (sizeof(struct in6_addr) + 7) + +static inline size_t ipv6_rpl_srh_alloc_size(unsigned char n) +{ + return sizeof(struct ipv6_rpl_sr_hdr) + + ((n + 1) * sizeof(struct in6_addr)); +} + +size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, + unsigned char cmpre); + +void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr, + const struct ipv6_rpl_sr_hdr *inhdr, + const struct in6_addr *daddr, unsigned char n); + +void ipv6_rpl_srh_compress(struct ipv6_rpl_sr_hdr *outhdr, + const struct ipv6_rpl_sr_hdr *inhdr, + const struct in6_addr *daddr, unsigned char n); + +#endif /* _NET_RPL_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index d586ee5e10a1..92f737f10117 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -596,6 +596,9 @@ struct ethtool_pauseparam { * @ETH_SS_LINK_MODES: link mode names * @ETH_SS_MSG_CLASSES: debug message class names * @ETH_SS_WOL_MODES: wake-on-lan modes + * @ETH_SS_SOF_TIMESTAMPING: SOF_TIMESTAMPING_* flags + * @ETH_SS_TS_TX_TYPES: timestamping Tx types + * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters */ enum ethtool_stringset { ETH_SS_TEST = 0, @@ -610,6 +613,9 @@ enum ethtool_stringset { ETH_SS_LINK_MODES, ETH_SS_MSG_CLASSES, ETH_SS_WOL_MODES, + ETH_SS_SOF_TIMESTAMPING, + ETH_SS_TS_TX_TYPES, + ETH_SS_TS_RX_FILTERS, /* add new constants above here */ ETH_SS_COUNT diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index c7c7a1a550af..7fde76366ba4 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -32,6 +32,13 @@ enum { ETHTOOL_MSG_RINGS_SET, ETHTOOL_MSG_CHANNELS_GET, ETHTOOL_MSG_CHANNELS_SET, + ETHTOOL_MSG_COALESCE_GET, + ETHTOOL_MSG_COALESCE_SET, + ETHTOOL_MSG_PAUSE_GET, + ETHTOOL_MSG_PAUSE_SET, + ETHTOOL_MSG_EEE_GET, + ETHTOOL_MSG_EEE_SET, + ETHTOOL_MSG_TSINFO_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -60,6 +67,13 @@ enum { ETHTOOL_MSG_RINGS_NTF, ETHTOOL_MSG_CHANNELS_GET_REPLY, ETHTOOL_MSG_CHANNELS_NTF, + ETHTOOL_MSG_COALESCE_GET_REPLY, + ETHTOOL_MSG_COALESCE_NTF, + ETHTOOL_MSG_PAUSE_GET_REPLY, + ETHTOOL_MSG_PAUSE_NTF, + ETHTOOL_MSG_EEE_GET_REPLY, + ETHTOOL_MSG_EEE_NTF, + ETHTOOL_MSG_TSINFO_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -310,6 +324,85 @@ enum { ETHTOOL_A_CHANNELS_MAX = (__ETHTOOL_A_CHANNELS_CNT - 1) }; +/* COALESCE */ + +enum { + ETHTOOL_A_COALESCE_UNSPEC, + ETHTOOL_A_COALESCE_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_COALESCE_RX_USECS, /* u32 */ + ETHTOOL_A_COALESCE_RX_MAX_FRAMES, /* u32 */ + ETHTOOL_A_COALESCE_RX_USECS_IRQ, /* u32 */ + ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ, /* u32 */ + ETHTOOL_A_COALESCE_TX_USECS, /* u32 */ + ETHTOOL_A_COALESCE_TX_MAX_FRAMES, /* u32 */ + ETHTOOL_A_COALESCE_TX_USECS_IRQ, /* u32 */ + ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ, /* u32 */ + ETHTOOL_A_COALESCE_STATS_BLOCK_USECS, /* u32 */ + ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX, /* u8 */ + ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX, /* u8 */ + ETHTOOL_A_COALESCE_PKT_RATE_LOW, /* u32 */ + ETHTOOL_A_COALESCE_RX_USECS_LOW, /* u32 */ + ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW, /* u32 */ + ETHTOOL_A_COALESCE_TX_USECS_LOW, /* u32 */ + ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW, /* u32 */ + ETHTOOL_A_COALESCE_PKT_RATE_HIGH, /* u32 */ + ETHTOOL_A_COALESCE_RX_USECS_HIGH, /* u32 */ + ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH, /* u32 */ + ETHTOOL_A_COALESCE_TX_USECS_HIGH, /* u32 */ + ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, /* u32 */ + ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, /* u32 */ + + /* add new constants above here */ + __ETHTOOL_A_COALESCE_CNT, + ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1) +}; + +/* PAUSE */ + +enum { + ETHTOOL_A_PAUSE_UNSPEC, + ETHTOOL_A_PAUSE_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_PAUSE_AUTONEG, /* u8 */ + ETHTOOL_A_PAUSE_RX, /* u8 */ + ETHTOOL_A_PAUSE_TX, /* u8 */ + + /* add new constants above here */ + __ETHTOOL_A_PAUSE_CNT, + ETHTOOL_A_PAUSE_MAX = (__ETHTOOL_A_PAUSE_CNT - 1) +}; + +/* EEE */ + +enum { + ETHTOOL_A_EEE_UNSPEC, + ETHTOOL_A_EEE_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_EEE_MODES_OURS, /* bitset */ + ETHTOOL_A_EEE_MODES_PEER, /* bitset */ + ETHTOOL_A_EEE_ACTIVE, /* u8 */ + ETHTOOL_A_EEE_ENABLED, /* u8 */ + ETHTOOL_A_EEE_TX_LPI_ENABLED, /* u8 */ + ETHTOOL_A_EEE_TX_LPI_TIMER, /* u32 */ + + /* add new constants above here */ + __ETHTOOL_A_EEE_CNT, + ETHTOOL_A_EEE_MAX = (__ETHTOOL_A_EEE_CNT - 1) +}; + +/* TSINFO */ + +enum { + ETHTOOL_A_TSINFO_UNSPEC, + ETHTOOL_A_TSINFO_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_TSINFO_TIMESTAMPING, /* bitset */ + ETHTOOL_A_TSINFO_TX_TYPES, /* bitset */ + ETHTOOL_A_TSINFO_RX_FILTERS, /* bitset */ + ETHTOOL_A_TSINFO_PHC_INDEX, /* u32 */ + + /* add new constants above here */ + __ETHTOOL_A_TSINFO_CNT, + ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 9c0f4a92bcff..13e8751bf24a 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -40,6 +40,7 @@ struct in6_ifreq { #define IPV6_SRCRT_STRICT 0x01 /* Deprecated; will be removed */ #define IPV6_SRCRT_TYPE_0 0 /* Deprecated; will be removed */ #define IPV6_SRCRT_TYPE_2 2 /* IPv6 type 2 Routing Header */ +#define IPV6_SRCRT_TYPE_3 3 /* RPL Segment Routing with IPv6 */ #define IPV6_SRCRT_TYPE_4 4 /* Segment Routing with IPv6 */ /* @@ -187,6 +188,7 @@ enum { DEVCONF_DISABLE_POLICY, DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN, DEVCONF_NDISC_TCLASS, + DEVCONF_RPL_SEG_ENABLED, DEVCONF_MAX }; diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index f6035f737193..568a4303ccce 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -13,6 +13,7 @@ enum lwtunnel_encap_types { LWTUNNEL_ENCAP_SEG6, LWTUNNEL_ENCAP_BPF, LWTUNNEL_ENCAP_SEG6_LOCAL, + LWTUNNEL_ENCAP_RPL, __LWTUNNEL_ENCAP_MAX, }; diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index f96e650d0af9..7ed0b3d1c00a 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -98,6 +98,9 @@ enum hwtstamp_tx_types { * receive a time stamp via the socket error queue. */ HWTSTAMP_TX_ONESTEP_P2P, + + /* add new constants above here */ + __HWTSTAMP_TX_CNT }; /* possible values for hwtstamp_config->rx_filter */ @@ -140,6 +143,9 @@ enum hwtstamp_rx_filters { /* NTP, UDP, all versions and packet modes */ HWTSTAMP_FILTER_NTP_ALL, + + /* add new constants above here */ + __HWTSTAMP_FILTER_CNT }; /* SCM_TIMESTAMPING_PKTINFO control message */ diff --git a/include/uapi/linux/rpl.h b/include/uapi/linux/rpl.h new file mode 100644 index 000000000000..1dccb55cf8c6 --- /dev/null +++ b/include/uapi/linux/rpl.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * IPv6 RPL-SR implementation + * + * Author: + * (C) 2020 Alexander Aring <[email protected]> + */ + +#ifndef _UAPI_LINUX_RPL_H +#define _UAPI_LINUX_RPL_H + +#include <asm/byteorder.h> +#include <linux/types.h> +#include <linux/in6.h> + +/* + * RPL SR Header + */ +struct ipv6_rpl_sr_hdr { + __u8 nexthdr; + __u8 hdrlen; + __u8 type; + __u8 segments_left; +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u32 cmpre:4, + cmpri:4, + reserved:4, + pad:4, + reserved1:16; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u32 reserved:20, + pad:4, + cmpri:4, + cmpre:4; +#else +#error "Please fix <asm/byteorder.h>" +#endif + + union { + struct in6_addr addr[0]; + __u8 data[0]; + } segments; +} __attribute__((packed)); + +#define rpl_segaddr segments.addr +#define rpl_segdata segments.data + +#endif diff --git a/include/uapi/linux/rpl_iptunnel.h b/include/uapi/linux/rpl_iptunnel.h new file mode 100644 index 000000000000..f4eed1f92baa --- /dev/null +++ b/include/uapi/linux/rpl_iptunnel.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * IPv6 RPL-SR implementation + * + * Author: + * (C) 2020 Alexander Aring <[email protected]> + */ + +#ifndef _UAPI_LINUX_RPL_IPTUNNEL_H +#define _UAPI_LINUX_RPL_IPTUNNEL_H + +enum { + RPL_IPTUNNEL_UNSPEC, + RPL_IPTUNNEL_SRH, + __RPL_IPTUNNEL_MAX, +}; +#define RPL_IPTUNNEL_MAX (__RPL_IPTUNNEL_MAX - 1) + +#define RPL_IPTUNNEL_SRH_SIZE(srh) (((srh)->hdrlen + 1) << 3) + +#endif diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index dbaebbe573f0..547b587c1950 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -190,6 +190,9 @@ static int net_hwtstamp_validate(struct ifreq *ifr) case HWTSTAMP_TX_ONESTEP_P2P: tx_type_valid = 1; break; + case __HWTSTAMP_TX_CNT: + /* not a real value */ + break; } switch (rx_filter) { @@ -211,6 +214,9 @@ static int net_hwtstamp_validate(struct ifreq *ifr) case HWTSTAMP_FILTER_NTP_ALL: rx_filter_valid = 1; break; + case __HWTSTAMP_FILTER_CNT: + /* not a real value */ + break; } if (!tx_type_valid || !rx_filter_valid) diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 99a6de52b21d..7d3438215f32 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -367,7 +367,7 @@ static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = { [LWT_BPF_XMIT_HEADROOM] = { .type = NLA_U32 }, }; -static int bpf_build_state(struct nlattr *nla, +static int bpf_build_state(struct net *net, struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 2f9c0de533c7..8ec7d13d2860 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -41,6 +41,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "BPF"; case LWTUNNEL_ENCAP_SEG6_LOCAL: return "SEG6LOCAL"; + case LWTUNNEL_ENCAP_RPL: + return "RPL"; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: @@ -98,7 +100,7 @@ int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, } EXPORT_SYMBOL_GPL(lwtunnel_encap_del_ops); -int lwtunnel_build_state(u16 encap_type, +int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack) @@ -122,7 +124,7 @@ int lwtunnel_build_state(u16 encap_type, rcu_read_unlock(); if (found) { - ret = ops->build_state(encap, family, cfg, lws, extack); + ret = ops->build_state(net, encap, family, cfg, lws, extack); if (ret) module_put(ops->owner); } else { diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index b0bd3decad02..6c360c9c9370 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -6,4 +6,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ - channels.o + channels.o coalesce.o pause.o eee.o tsinfo.o diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c new file mode 100644 index 000000000000..6afd99042d67 --- /dev/null +++ b/net/ethtool/coalesce.c @@ -0,0 +1,353 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" + +struct coalesce_req_info { + struct ethnl_req_info base; +}; + +struct coalesce_reply_data { + struct ethnl_reply_data base; + struct ethtool_coalesce coalesce; + u32 supported_params; +}; + +#define COALESCE_REPDATA(__reply_base) \ + container_of(__reply_base, struct coalesce_reply_data, base) + +#define __SUPPORTED_OFFSET ETHTOOL_A_COALESCE_RX_USECS +static u32 attr_to_mask(unsigned int attr_type) +{ + return BIT(attr_type - __SUPPORTED_OFFSET); +} + +/* build time check that indices in ethtool_ops::supported_coalesce_params + * match corresponding attribute types with an offset + */ +#define __CHECK_SUPPORTED_OFFSET(x) \ + static_assert((ETHTOOL_ ## x) == \ + BIT((ETHTOOL_A_ ## x) - __SUPPORTED_OFFSET)) +__CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS); +__CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES); +__CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS_IRQ); +__CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_IRQ); +__CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS); +__CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES); +__CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_IRQ); +__CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_IRQ); +__CHECK_SUPPORTED_OFFSET(COALESCE_STATS_BLOCK_USECS); +__CHECK_SUPPORTED_OFFSET(COALESCE_USE_ADAPTIVE_RX); +__CHECK_SUPPORTED_OFFSET(COALESCE_USE_ADAPTIVE_TX); +__CHECK_SUPPORTED_OFFSET(COALESCE_PKT_RATE_LOW); +__CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS_LOW); +__CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_LOW); +__CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_LOW); +__CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_LOW); +__CHECK_SUPPORTED_OFFSET(COALESCE_PKT_RATE_HIGH); +__CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS_HIGH); +__CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_HIGH); +__CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_HIGH); +__CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_HIGH); +__CHECK_SUPPORTED_OFFSET(COALESCE_RATE_SAMPLE_INTERVAL); + +static const struct nla_policy +coalesce_get_policy[ETHTOOL_A_COALESCE_MAX + 1] = { + [ETHTOOL_A_COALESCE_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_COALESCE_RX_USECS] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_RX_USECS_IRQ] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_TX_USECS] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_TX_USECS_IRQ] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_STATS_BLOCK_USECS] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_PKT_RATE_LOW] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_RX_USECS_LOW] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_TX_USECS_LOW] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_PKT_RATE_HIGH] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_RX_USECS_HIGH] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_TX_USECS_HIGH] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_REJECT }, +}; + +static int coalesce_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + if (!dev->ethtool_ops->get_coalesce) + return -EOPNOTSUPP; + data->supported_params = dev->ethtool_ops->supported_coalesce_params; + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + ret = dev->ethtool_ops->get_coalesce(dev, &data->coalesce); + ethnl_ops_complete(dev); + + return ret; +} + +static int coalesce_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u32)) + /* _RX_USECS */ + nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES */ + nla_total_size(sizeof(u32)) + /* _RX_USECS_IRQ */ + nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_IRQ */ + nla_total_size(sizeof(u32)) + /* _TX_USECS */ + nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES */ + nla_total_size(sizeof(u32)) + /* _TX_USECS_IRQ */ + nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_IRQ */ + nla_total_size(sizeof(u32)) + /* _STATS_BLOCK_USECS */ + nla_total_size(sizeof(u8)) + /* _USE_ADAPTIVE_RX */ + nla_total_size(sizeof(u8)) + /* _USE_ADAPTIVE_TX */ + nla_total_size(sizeof(u32)) + /* _PKT_RATE_LOW */ + nla_total_size(sizeof(u32)) + /* _RX_USECS_LOW */ + nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_LOW */ + nla_total_size(sizeof(u32)) + /* _TX_USECS_LOW */ + nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_LOW */ + nla_total_size(sizeof(u32)) + /* _PKT_RATE_HIGH */ + nla_total_size(sizeof(u32)) + /* _RX_USECS_HIGH */ + nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_HIGH */ + nla_total_size(sizeof(u32)) + /* _TX_USECS_HIGH */ + nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_HIGH */ + nla_total_size(sizeof(u32)); /* _RATE_SAMPLE_INTERVAL */ +} + +static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, + u32 supported_params) +{ + if (!val && !(supported_params & attr_to_mask(attr_type))) + return false; + return nla_put_u32(skb, attr_type, val); +} + +static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val, + u32 supported_params) +{ + if (!val && !(supported_params & attr_to_mask(attr_type))) + return false; + return nla_put_u8(skb, attr_type, !!val); +} + +static int coalesce_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); + const struct ethtool_coalesce *coal = &data->coalesce; + u32 supported = data->supported_params; + + if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS, + coal->rx_coalesce_usecs, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES, + coal->rx_max_coalesced_frames, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS_IRQ, + coal->rx_coalesce_usecs_irq, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ, + coal->rx_max_coalesced_frames_irq, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS, + coal->tx_coalesce_usecs, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES, + coal->tx_max_coalesced_frames, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS_IRQ, + coal->tx_coalesce_usecs_irq, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ, + coal->tx_max_coalesced_frames_irq, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_STATS_BLOCK_USECS, + coal->stats_block_coalesce_usecs, supported) || + coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX, + coal->use_adaptive_rx_coalesce, supported) || + coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX, + coal->use_adaptive_tx_coalesce, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_PKT_RATE_LOW, + coal->pkt_rate_low, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS_LOW, + coal->rx_coalesce_usecs_low, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW, + coal->rx_max_coalesced_frames_low, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS_LOW, + coal->tx_coalesce_usecs_low, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW, + coal->tx_max_coalesced_frames_low, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_PKT_RATE_HIGH, + coal->pkt_rate_high, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS_HIGH, + coal->rx_coalesce_usecs_high, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH, + coal->rx_max_coalesced_frames_high, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS_HIGH, + coal->tx_coalesce_usecs_high, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, + coal->tx_max_coalesced_frames_high, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, + coal->rate_sample_interval, supported)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_coalesce_request_ops = { + .request_cmd = ETHTOOL_MSG_COALESCE_GET, + .reply_cmd = ETHTOOL_MSG_COALESCE_GET_REPLY, + .hdr_attr = ETHTOOL_A_COALESCE_HEADER, + .max_attr = ETHTOOL_A_COALESCE_MAX, + .req_info_size = sizeof(struct coalesce_req_info), + .reply_data_size = sizeof(struct coalesce_reply_data), + .request_policy = coalesce_get_policy, + + .prepare_data = coalesce_prepare_data, + .reply_size = coalesce_reply_size, + .fill_reply = coalesce_fill_reply, +}; + +/* COALESCE_SET */ + +static const struct nla_policy +coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1] = { + [ETHTOOL_A_COALESCE_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_COALESCE_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_COALESCE_RX_USECS] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_USECS_IRQ] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_USECS] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_USECS_IRQ] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_STATS_BLOCK_USECS] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX] = { .type = NLA_U8 }, + [ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX] = { .type = NLA_U8 }, + [ETHTOOL_A_COALESCE_PKT_RATE_LOW] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_USECS_LOW] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_USECS_LOW] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_PKT_RATE_HIGH] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_USECS_HIGH] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_USECS_HIGH] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_U32 }, +}; + +int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_COALESCE_MAX + 1]; + struct ethtool_coalesce coalesce = {}; + struct ethnl_req_info req_info = {}; + const struct ethtool_ops *ops; + struct net_device *dev; + u32 supported_params; + bool mod = false; + int ret; + u16 a; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, + ETHTOOL_A_COALESCE_MAX, coalesce_set_policy, + info->extack); + if (ret < 0) + return ret; + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_COALESCE_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + ops = dev->ethtool_ops; + ret = -EOPNOTSUPP; + if (!ops->get_coalesce || !ops->set_coalesce) + goto out_dev; + + /* make sure that only supported parameters are present */ + supported_params = ops->supported_coalesce_params; + for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++) + if (tb[a] && !(supported_params & attr_to_mask(a))) { + ret = -EINVAL; + NL_SET_ERR_MSG_ATTR(info->extack, tb[a], + "cannot modify an unsupported parameter"); + goto out_dev; + } + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + ret = ops->get_coalesce(dev, &coalesce); + if (ret < 0) + goto out_ops; + + ethnl_update_u32(&coalesce.rx_coalesce_usecs, + tb[ETHTOOL_A_COALESCE_RX_USECS], &mod); + ethnl_update_u32(&coalesce.rx_max_coalesced_frames, + tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES], &mod); + ethnl_update_u32(&coalesce.rx_coalesce_usecs_irq, + tb[ETHTOOL_A_COALESCE_RX_USECS_IRQ], &mod); + ethnl_update_u32(&coalesce.rx_max_coalesced_frames_irq, + tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ], &mod); + ethnl_update_u32(&coalesce.tx_coalesce_usecs, + tb[ETHTOOL_A_COALESCE_TX_USECS], &mod); + ethnl_update_u32(&coalesce.tx_max_coalesced_frames, + tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES], &mod); + ethnl_update_u32(&coalesce.tx_coalesce_usecs_irq, + tb[ETHTOOL_A_COALESCE_TX_USECS_IRQ], &mod); + ethnl_update_u32(&coalesce.tx_max_coalesced_frames_irq, + tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ], &mod); + ethnl_update_u32(&coalesce.stats_block_coalesce_usecs, + tb[ETHTOOL_A_COALESCE_STATS_BLOCK_USECS], &mod); + ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce, + tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod); + ethnl_update_bool32(&coalesce.use_adaptive_tx_coalesce, + tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX], &mod); + ethnl_update_u32(&coalesce.pkt_rate_low, + tb[ETHTOOL_A_COALESCE_PKT_RATE_LOW], &mod); + ethnl_update_u32(&coalesce.rx_coalesce_usecs_low, + tb[ETHTOOL_A_COALESCE_RX_USECS_LOW], &mod); + ethnl_update_u32(&coalesce.rx_max_coalesced_frames_low, + tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW], &mod); + ethnl_update_u32(&coalesce.tx_coalesce_usecs_low, + tb[ETHTOOL_A_COALESCE_TX_USECS_LOW], &mod); + ethnl_update_u32(&coalesce.tx_max_coalesced_frames_low, + tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW], &mod); + ethnl_update_u32(&coalesce.pkt_rate_high, + tb[ETHTOOL_A_COALESCE_PKT_RATE_HIGH], &mod); + ethnl_update_u32(&coalesce.rx_coalesce_usecs_high, + tb[ETHTOOL_A_COALESCE_RX_USECS_HIGH], &mod); + ethnl_update_u32(&coalesce.rx_max_coalesced_frames_high, + tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH], &mod); + ethnl_update_u32(&coalesce.tx_coalesce_usecs_high, + tb[ETHTOOL_A_COALESCE_TX_USECS_HIGH], &mod); + ethnl_update_u32(&coalesce.tx_max_coalesced_frames_high, + tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH], &mod); + ethnl_update_u32(&coalesce.rate_sample_interval, + tb[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL], &mod); + ret = 0; + if (!mod) + goto out_ops; + + ret = dev->ethtool_ops->set_coalesce(dev, &coalesce); + if (ret < 0) + goto out_ops; + ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); +out_dev: + dev_put(dev); + return ret; +} diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 51a0941fc62f..423e640e3876 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/net_tstamp.h> +#include <linux/phy.h> + #include "common.h" const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { @@ -204,6 +207,53 @@ const char wol_mode_names[][ETH_GSTRING_LEN] = { }; static_assert(ARRAY_SIZE(wol_mode_names) == WOL_MODE_COUNT); +const char sof_timestamping_names[][ETH_GSTRING_LEN] = { + [const_ilog2(SOF_TIMESTAMPING_TX_HARDWARE)] = "hardware-transmit", + [const_ilog2(SOF_TIMESTAMPING_TX_SOFTWARE)] = "software-transmit", + [const_ilog2(SOF_TIMESTAMPING_RX_HARDWARE)] = "hardware-receive", + [const_ilog2(SOF_TIMESTAMPING_RX_SOFTWARE)] = "software-receive", + [const_ilog2(SOF_TIMESTAMPING_SOFTWARE)] = "software-system-clock", + [const_ilog2(SOF_TIMESTAMPING_SYS_HARDWARE)] = "hardware-legacy-clock", + [const_ilog2(SOF_TIMESTAMPING_RAW_HARDWARE)] = "hardware-raw-clock", + [const_ilog2(SOF_TIMESTAMPING_OPT_ID)] = "option-id", + [const_ilog2(SOF_TIMESTAMPING_TX_SCHED)] = "sched-transmit", + [const_ilog2(SOF_TIMESTAMPING_TX_ACK)] = "ack-transmit", + [const_ilog2(SOF_TIMESTAMPING_OPT_CMSG)] = "option-cmsg", + [const_ilog2(SOF_TIMESTAMPING_OPT_TSONLY)] = "option-tsonly", + [const_ilog2(SOF_TIMESTAMPING_OPT_STATS)] = "option-stats", + [const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo", + [const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw", +}; +static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT); + +const char ts_tx_type_names[][ETH_GSTRING_LEN] = { + [HWTSTAMP_TX_OFF] = "off", + [HWTSTAMP_TX_ON] = "on", + [HWTSTAMP_TX_ONESTEP_SYNC] = "onestep-sync", + [HWTSTAMP_TX_ONESTEP_P2P] = "onestep-p2p", +}; +static_assert(ARRAY_SIZE(ts_tx_type_names) == __HWTSTAMP_TX_CNT); + +const char ts_rx_filter_names[][ETH_GSTRING_LEN] = { + [HWTSTAMP_FILTER_NONE] = "none", + [HWTSTAMP_FILTER_ALL] = "all", + [HWTSTAMP_FILTER_SOME] = "some", + [HWTSTAMP_FILTER_PTP_V1_L4_EVENT] = "ptpv1-l4-event", + [HWTSTAMP_FILTER_PTP_V1_L4_SYNC] = "ptpv1-l4-sync", + [HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ] = "ptpv1-l4-delay-req", + [HWTSTAMP_FILTER_PTP_V2_L4_EVENT] = "ptpv2-l4-event", + [HWTSTAMP_FILTER_PTP_V2_L4_SYNC] = "ptpv2-l4-sync", + [HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ] = "ptpv2-l4-delay-req", + [HWTSTAMP_FILTER_PTP_V2_L2_EVENT] = "ptpv2-l2-event", + [HWTSTAMP_FILTER_PTP_V2_L2_SYNC] = "ptpv2-l2-sync", + [HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ] = "ptpv2-l2-delay-req", + [HWTSTAMP_FILTER_PTP_V2_EVENT] = "ptpv2-event", + [HWTSTAMP_FILTER_PTP_V2_SYNC] = "ptpv2-sync", + [HWTSTAMP_FILTER_PTP_V2_DELAY_REQ] = "ptpv2-delay-req", + [HWTSTAMP_FILTER_NTP_ALL] = "ntp-all", +}; +static_assert(ARRAY_SIZE(ts_rx_filter_names) == __HWTSTAMP_FILTER_CNT); + /* return false if legacy contained non-0 deprecated fields * maxtxpkt/maxrxpkt. rest of ksettings always updated */ @@ -301,3 +351,23 @@ int ethtool_check_ops(const struct ethtool_ops *ops) */ return 0; } + +int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct phy_device *phydev = dev->phydev; + + memset(info, 0, sizeof(*info)); + info->cmd = ETHTOOL_GET_TS_INFO; + + if (phy_has_tsinfo(phydev)) + return phy_ts_info(phydev, info); + if (ops->get_ts_info) + return ops->get_ts_info(dev, info); + + info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info->phc_index = -1; + + return 0; +} diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 03946e16e623..a62f68ccc43a 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -12,6 +12,8 @@ #define ETHTOOL_LINK_MODE(speed, type, duplex) \ ETHTOOL_LINK_MODE_ ## speed ## base ## type ## _ ## duplex ## _BIT +#define __SOF_TIMESTAMPING_CNT (const_ilog2(SOF_TIMESTAMPING_LAST) + 1) + extern const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]; extern const char @@ -23,6 +25,9 @@ phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN]; extern const char link_mode_names[][ETH_GSTRING_LEN]; extern const char netif_msg_class_names[][ETH_GSTRING_LEN]; extern const char wol_mode_names[][ETH_GSTRING_LEN]; +extern const char sof_timestamping_names[][ETH_GSTRING_LEN]; +extern const char ts_tx_type_names[][ETH_GSTRING_LEN]; +extern const char ts_rx_filter_names[][ETH_GSTRING_LEN]; int __ethtool_get_link(struct net_device *dev); @@ -30,5 +35,6 @@ bool convert_legacy_settings_to_link_ksettings( struct ethtool_link_ksettings *link_ksettings, const struct ethtool_cmd *legacy_settings); int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max); +int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info); #endif /* _ETHTOOL_COMMON_H */ diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c new file mode 100644 index 000000000000..94aa19cff22f --- /dev/null +++ b/net/ethtool/eee.c @@ -0,0 +1,206 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +#define EEE_MODES_COUNT \ + (sizeof_field(struct ethtool_eee, supported) * BITS_PER_BYTE) + +struct eee_req_info { + struct ethnl_req_info base; +}; + +struct eee_reply_data { + struct ethnl_reply_data base; + struct ethtool_eee eee; +}; + +#define EEE_REPDATA(__reply_base) \ + container_of(__reply_base, struct eee_reply_data, base) + +static const struct nla_policy +eee_get_policy[ETHTOOL_A_EEE_MAX + 1] = { + [ETHTOOL_A_EEE_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_EEE_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_EEE_MODES_OURS] = { .type = NLA_REJECT }, + [ETHTOOL_A_EEE_MODES_PEER] = { .type = NLA_REJECT }, + [ETHTOOL_A_EEE_ACTIVE] = { .type = NLA_REJECT }, + [ETHTOOL_A_EEE_ENABLED] = { .type = NLA_REJECT }, + [ETHTOOL_A_EEE_TX_LPI_ENABLED] = { .type = NLA_REJECT }, + [ETHTOOL_A_EEE_TX_LPI_TIMER] = { .type = NLA_REJECT }, +}; + +static int eee_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct eee_reply_data *data = EEE_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + if (!dev->ethtool_ops->get_eee) + return -EOPNOTSUPP; + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + ret = dev->ethtool_ops->get_eee(dev, &data->eee); + ethnl_ops_complete(dev); + + return ret; +} + +static int eee_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct eee_reply_data *data = EEE_REPDATA(reply_base); + const struct ethtool_eee *eee = &data->eee; + int len = 0; + int ret; + + BUILD_BUG_ON(sizeof(eee->advertised) * BITS_PER_BYTE != + EEE_MODES_COUNT); + BUILD_BUG_ON(sizeof(eee->lp_advertised) * BITS_PER_BYTE != + EEE_MODES_COUNT); + + /* MODES_OURS */ + ret = ethnl_bitset32_size(&eee->advertised, &eee->supported, + EEE_MODES_COUNT, link_mode_names, compact); + if (ret < 0) + return ret; + len += ret; + /* MODES_PEERS */ + ret = ethnl_bitset32_size(&eee->lp_advertised, NULL, + EEE_MODES_COUNT, link_mode_names, compact); + if (ret < 0) + return ret; + len += ret; + + len += nla_total_size(sizeof(u8)) + /* _EEE_ACTIVE */ + nla_total_size(sizeof(u8)) + /* _EEE_ENABLED */ + nla_total_size(sizeof(u8)) + /* _EEE_TX_LPI_ENABLED */ + nla_total_size(sizeof(u32)); /* _EEE_TX_LPI_TIMER */ + + return len; +} + +static int eee_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct eee_reply_data *data = EEE_REPDATA(reply_base); + const struct ethtool_eee *eee = &data->eee; + int ret; + + ret = ethnl_put_bitset32(skb, ETHTOOL_A_EEE_MODES_OURS, + &eee->advertised, &eee->supported, + EEE_MODES_COUNT, link_mode_names, compact); + if (ret < 0) + return ret; + ret = ethnl_put_bitset32(skb, ETHTOOL_A_EEE_MODES_PEER, + &eee->lp_advertised, NULL, EEE_MODES_COUNT, + link_mode_names, compact); + if (ret < 0) + return ret; + + if (nla_put_u8(skb, ETHTOOL_A_EEE_ACTIVE, !!eee->eee_active) || + nla_put_u8(skb, ETHTOOL_A_EEE_ENABLED, !!eee->eee_enabled) || + nla_put_u8(skb, ETHTOOL_A_EEE_TX_LPI_ENABLED, + !!eee->tx_lpi_enabled) || + nla_put_u32(skb, ETHTOOL_A_EEE_TX_LPI_TIMER, eee->tx_lpi_timer)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_eee_request_ops = { + .request_cmd = ETHTOOL_MSG_EEE_GET, + .reply_cmd = ETHTOOL_MSG_EEE_GET_REPLY, + .hdr_attr = ETHTOOL_A_EEE_HEADER, + .max_attr = ETHTOOL_A_EEE_MAX, + .req_info_size = sizeof(struct eee_req_info), + .reply_data_size = sizeof(struct eee_reply_data), + .request_policy = eee_get_policy, + + .prepare_data = eee_prepare_data, + .reply_size = eee_reply_size, + .fill_reply = eee_fill_reply, +}; + +/* EEE_SET */ + +static const struct nla_policy +eee_set_policy[ETHTOOL_A_EEE_MAX + 1] = { + [ETHTOOL_A_EEE_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_EEE_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_EEE_MODES_OURS] = { .type = NLA_NESTED }, + [ETHTOOL_A_EEE_MODES_PEER] = { .type = NLA_REJECT }, + [ETHTOOL_A_EEE_ACTIVE] = { .type = NLA_REJECT }, + [ETHTOOL_A_EEE_ENABLED] = { .type = NLA_U8 }, + [ETHTOOL_A_EEE_TX_LPI_ENABLED] = { .type = NLA_U8 }, + [ETHTOOL_A_EEE_TX_LPI_TIMER] = { .type = NLA_U32 }, +}; + +int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_EEE_MAX + 1]; + struct ethtool_eee eee = {}; + struct ethnl_req_info req_info = {}; + const struct ethtool_ops *ops; + struct net_device *dev; + bool mod = false; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_EEE_MAX, + eee_set_policy, info->extack); + if (ret < 0) + return ret; + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_EEE_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + ops = dev->ethtool_ops; + ret = -EOPNOTSUPP; + if (!ops->get_eee || !ops->set_eee) + goto out_dev; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + ret = ops->get_eee(dev, &eee); + if (ret < 0) + goto out_ops; + + ret = ethnl_update_bitset32(&eee.advertised, EEE_MODES_COUNT, + tb[ETHTOOL_A_EEE_MODES_OURS], + link_mode_names, info->extack, &mod); + if (ret < 0) + goto out_ops; + ethnl_update_bool32(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod); + ethnl_update_bool32(&eee.tx_lpi_enabled, + tb[ETHTOOL_A_EEE_TX_LPI_ENABLED], &mod); + ethnl_update_bool32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER], + &mod); + ret = 0; + if (!mod) + goto out_ops; + + ret = dev->ethtool_ops->set_eee(dev, &eee); + if (ret < 0) + goto out_ops; + ethtool_notify(dev, ETHTOOL_MSG_EEE_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); +out_dev: + dev_put(dev); + return ret; +} diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 10d929abdf6a..89d0b1827aaf 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1354,6 +1354,7 @@ static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) { struct ethtool_eee edata; + int ret; if (!dev->ethtool_ops->set_eee) return -EOPNOTSUPP; @@ -1361,7 +1362,10 @@ static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; - return dev->ethtool_ops->set_eee(dev, &edata); + ret = dev->ethtool_ops->set_eee(dev, &edata); + if (!ret) + ethtool_notify(dev, ETHTOOL_MSG_EEE_NTF, NULL); + return ret; } static int ethtool_nway_reset(struct net_device *dev) @@ -1571,6 +1575,7 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) { struct ethtool_coalesce coalesce; + int ret; if (!dev->ethtool_ops->set_coalesce) return -EOPNOTSUPP; @@ -1581,7 +1586,10 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, if (!ethtool_set_coalesce_supported(dev, &coalesce)) return -EOPNOTSUPP; - return dev->ethtool_ops->set_coalesce(dev, &coalesce); + ret = dev->ethtool_ops->set_coalesce(dev, &coalesce); + if (!ret) + ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF, NULL); + return ret; } static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr) @@ -1701,6 +1709,7 @@ static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr) static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) { struct ethtool_pauseparam pauseparam; + int ret; if (!dev->ethtool_ops->set_pauseparam) return -EOPNOTSUPP; @@ -1708,7 +1717,10 @@ static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) if (copy_from_user(&pauseparam, useraddr, sizeof(pauseparam))) return -EFAULT; - return dev->ethtool_ops->set_pauseparam(dev, &pauseparam); + ret = dev->ethtool_ops->set_pauseparam(dev, &pauseparam); + if (!ret) + ethtool_notify(dev, ETHTOOL_MSG_PAUSE_NTF, NULL); + return ret; } static int ethtool_self_test(struct net_device *dev, char __user *useraddr) @@ -2128,32 +2140,17 @@ out: static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) { - int err = 0; struct ethtool_ts_info info; - const struct ethtool_ops *ops = dev->ethtool_ops; - struct phy_device *phydev = dev->phydev; - - memset(&info, 0, sizeof(info)); - info.cmd = ETHTOOL_GET_TS_INFO; - - if (phy_has_tsinfo(phydev)) { - err = phy_ts_info(phydev, &info); - } else if (ops->get_ts_info) { - err = ops->get_ts_info(dev, &info); - } else { - info.so_timestamping = - SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE; - info.phc_index = -1; - } + int err; + err = __ethtool_get_ts_info(dev, &info); if (err) return err; if (copy_to_user(useraddr, &info, sizeof(info))) - err = -EFAULT; + return -EFAULT; - return err; + return 0; } static int __ethtool_get_module_info(struct net_device *dev, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 71855bdd3b38..0c772318c023 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -227,6 +227,10 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_PRIVFLAGS_GET] = ðnl_privflags_request_ops, [ETHTOOL_MSG_RINGS_GET] = ðnl_rings_request_ops, [ETHTOOL_MSG_CHANNELS_GET] = ðnl_channels_request_ops, + [ETHTOOL_MSG_COALESCE_GET] = ðnl_coalesce_request_ops, + [ETHTOOL_MSG_PAUSE_GET] = ðnl_pause_request_ops, + [ETHTOOL_MSG_EEE_GET] = ðnl_eee_request_ops, + [ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -543,6 +547,9 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_PRIVFLAGS_NTF] = ðnl_privflags_request_ops, [ETHTOOL_MSG_RINGS_NTF] = ðnl_rings_request_ops, [ETHTOOL_MSG_CHANNELS_NTF] = ðnl_channels_request_ops, + [ETHTOOL_MSG_COALESCE_NTF] = ðnl_coalesce_request_ops, + [ETHTOOL_MSG_PAUSE_NTF] = ðnl_pause_request_ops, + [ETHTOOL_MSG_EEE_NTF] = ðnl_eee_request_ops, }; /* default notification handler */ @@ -632,6 +639,9 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_PRIVFLAGS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_RINGS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_CHANNELS_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_COALESCE_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_PAUSE_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_EEE_NTF] = ethnl_default_notify, }; void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) @@ -786,6 +796,49 @@ static const struct genl_ops ethtool_genl_ops[] = { .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_channels, }, + { + .cmd = ETHTOOL_MSG_COALESCE_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_COALESCE_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_coalesce, + }, + { + .cmd = ETHTOOL_MSG_PAUSE_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_PAUSE_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_pause, + }, + { + .cmd = ETHTOOL_MSG_EEE_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_EEE_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_eee, + }, + { + .cmd = ETHTOOL_MSG_TSINFO_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 45aad99a6021..81b8fa020bcb 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -341,6 +341,10 @@ extern const struct ethnl_request_ops ethnl_features_request_ops; extern const struct ethnl_request_ops ethnl_privflags_request_ops; extern const struct ethnl_request_ops ethnl_rings_request_ops; extern const struct ethnl_request_ops ethnl_channels_request_ops; +extern const struct ethnl_request_ops ethnl_coalesce_request_ops; +extern const struct ethnl_request_ops ethnl_pause_request_ops; +extern const struct ethnl_request_ops ethnl_eee_request_ops; +extern const struct ethnl_request_ops ethnl_tsinfo_request_ops; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); @@ -350,5 +354,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_set_privflags(struct sk_buff *skb, struct genl_info *info); int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info); int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info); #endif /* _NET_ETHTOOL_NETLINK_H */ diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c new file mode 100644 index 000000000000..7aea35d1e8a5 --- /dev/null +++ b/net/ethtool/pause.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" + +struct pause_req_info { + struct ethnl_req_info base; +}; + +struct pause_reply_data { + struct ethnl_reply_data base; + struct ethtool_pauseparam pauseparam; +}; + +#define PAUSE_REPDATA(__reply_base) \ + container_of(__reply_base, struct pause_reply_data, base) + +static const struct nla_policy +pause_get_policy[ETHTOOL_A_PAUSE_MAX + 1] = { + [ETHTOOL_A_PAUSE_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_PAUSE_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_PAUSE_AUTONEG] = { .type = NLA_REJECT }, + [ETHTOOL_A_PAUSE_RX] = { .type = NLA_REJECT }, + [ETHTOOL_A_PAUSE_TX] = { .type = NLA_REJECT }, +}; + +static int pause_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct pause_reply_data *data = PAUSE_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + if (!dev->ethtool_ops->get_pauseparam) + return -EOPNOTSUPP; + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam); + ethnl_ops_complete(dev); + + return 0; +} + +static int pause_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u8)) + /* _PAUSE_AUTONEG */ + nla_total_size(sizeof(u8)) + /* _PAUSE_RX */ + nla_total_size(sizeof(u8)); /* _PAUSE_TX */ +} + +static int pause_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct pause_reply_data *data = PAUSE_REPDATA(reply_base); + const struct ethtool_pauseparam *pauseparam = &data->pauseparam; + + if (nla_put_u8(skb, ETHTOOL_A_PAUSE_AUTONEG, !!pauseparam->autoneg) || + nla_put_u8(skb, ETHTOOL_A_PAUSE_RX, !!pauseparam->rx_pause) || + nla_put_u8(skb, ETHTOOL_A_PAUSE_TX, !!pauseparam->tx_pause)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_pause_request_ops = { + .request_cmd = ETHTOOL_MSG_PAUSE_GET, + .reply_cmd = ETHTOOL_MSG_PAUSE_GET_REPLY, + .hdr_attr = ETHTOOL_A_PAUSE_HEADER, + .max_attr = ETHTOOL_A_PAUSE_MAX, + .req_info_size = sizeof(struct pause_req_info), + .reply_data_size = sizeof(struct pause_reply_data), + .request_policy = pause_get_policy, + + .prepare_data = pause_prepare_data, + .reply_size = pause_reply_size, + .fill_reply = pause_fill_reply, +}; + +/* PAUSE_SET */ + +static const struct nla_policy +pause_set_policy[ETHTOOL_A_PAUSE_MAX + 1] = { + [ETHTOOL_A_PAUSE_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_PAUSE_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_PAUSE_AUTONEG] = { .type = NLA_U8 }, + [ETHTOOL_A_PAUSE_RX] = { .type = NLA_U8 }, + [ETHTOOL_A_PAUSE_TX] = { .type = NLA_U8 }, +}; + +int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_PAUSE_MAX + 1]; + struct ethtool_pauseparam params = {}; + struct ethnl_req_info req_info = {}; + const struct ethtool_ops *ops; + struct net_device *dev; + bool mod = false; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_PAUSE_MAX, + pause_set_policy, info->extack); + if (ret < 0) + return ret; + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_PAUSE_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + ops = dev->ethtool_ops; + ret = -EOPNOTSUPP; + if (!ops->get_pauseparam || !ops->set_pauseparam) + goto out_dev; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + ops->get_pauseparam(dev, ¶ms); + + ethnl_update_bool32(¶ms.autoneg, tb[ETHTOOL_A_PAUSE_AUTONEG], &mod); + ethnl_update_bool32(¶ms.rx_pause, tb[ETHTOOL_A_PAUSE_RX], &mod); + ethnl_update_bool32(¶ms.tx_pause, tb[ETHTOOL_A_PAUSE_TX], &mod); + ret = 0; + if (!mod) + goto out_ops; + + ret = dev->ethtool_ops->set_pauseparam(dev, ¶ms); + if (ret < 0) + goto out_ops; + ethtool_notify(dev, ETHTOOL_MSG_PAUSE_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); +out_dev: + dev_put(dev); + return ret; +} diff --git a/net/ethtool/privflags.c b/net/ethtool/privflags.c index e8f03b33db9b..77447dceb109 100644 --- a/net/ethtool/privflags.c +++ b/net/ethtool/privflags.c @@ -175,9 +175,10 @@ int ethnl_set_privflags(struct sk_buff *skb, struct genl_info *info) return ret; dev = req_info.dev; ops = dev->ethtool_ops; + ret = -EOPNOTSUPP; if (!ops->get_priv_flags || !ops->set_priv_flags || !ops->get_sset_count || !ops->get_strings) - return -EOPNOTSUPP; + goto out_dev; rtnl_lock(); ret = ethnl_ops_begin(dev); @@ -204,6 +205,7 @@ out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); +out_dev: dev_put(dev); return ret; } diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index 8e5911887b4c..95eae5c68a52 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -60,6 +60,21 @@ static const struct strset_info info_template[] = { .count = WOL_MODE_COUNT, .strings = wol_mode_names, }, + [ETH_SS_SOF_TIMESTAMPING] = { + .per_dev = false, + .count = __SOF_TIMESTAMPING_CNT, + .strings = sof_timestamping_names, + }, + [ETH_SS_TS_TX_TYPES] = { + .per_dev = false, + .count = __HWTSTAMP_TX_CNT, + .strings = ts_tx_type_names, + }, + [ETH_SS_TS_RX_FILTERS] = { + .per_dev = false, + .count = __HWTSTAMP_FILTER_CNT, + .strings = ts_rx_filter_names, + }, }; struct strset_req_info { diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c new file mode 100644 index 000000000000..7cb5b512b77c --- /dev/null +++ b/net/ethtool/tsinfo.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/net_tstamp.h> + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct tsinfo_req_info { + struct ethnl_req_info base; +}; + +struct tsinfo_reply_data { + struct ethnl_reply_data base; + struct ethtool_ts_info ts_info; +}; + +#define TSINFO_REPDATA(__reply_base) \ + container_of(__reply_base, struct tsinfo_reply_data, base) + +static const struct nla_policy +tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1] = { + [ETHTOOL_A_TSINFO_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_TSINFO_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_TSINFO_TIMESTAMPING] = { .type = NLA_REJECT }, + [ETHTOOL_A_TSINFO_TX_TYPES] = { .type = NLA_REJECT }, + [ETHTOOL_A_TSINFO_RX_FILTERS] = { .type = NLA_REJECT }, + [ETHTOOL_A_TSINFO_PHC_INDEX] = { .type = NLA_REJECT }, +}; + +static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + ret = __ethtool_get_ts_info(dev, &data->ts_info); + ethnl_ops_complete(dev); + + return ret; +} + +static int tsinfo_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct ethtool_ts_info *ts_info = &data->ts_info; + int len = 0; + int ret; + + BUILD_BUG_ON(__SOF_TIMESTAMPING_CNT > 32); + BUILD_BUG_ON(__HWTSTAMP_TX_CNT > 32); + BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT > 32); + + if (ts_info->so_timestamping) { + ret = ethnl_bitset32_size(&ts_info->so_timestamping, NULL, + __SOF_TIMESTAMPING_CNT, + sof_timestamping_names, compact); + if (ret < 0) + return ret; + len += ret; /* _TSINFO_TIMESTAMPING */ + } + if (ts_info->tx_types) { + ret = ethnl_bitset32_size(&ts_info->tx_types, NULL, + __HWTSTAMP_TX_CNT, + ts_tx_type_names, compact); + if (ret < 0) + return ret; + len += ret; /* _TSINFO_TX_TYPES */ + } + if (ts_info->rx_filters) { + ret = ethnl_bitset32_size(&ts_info->rx_filters, NULL, + __HWTSTAMP_FILTER_CNT, + ts_rx_filter_names, compact); + if (ret < 0) + return ret; + len += ret; /* _TSINFO_RX_FILTERS */ + } + if (ts_info->phc_index >= 0) + len += nla_total_size(sizeof(u32)); /* _TSINFO_PHC_INDEX */ + + return len; +} + +static int tsinfo_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct ethtool_ts_info *ts_info = &data->ts_info; + int ret; + + if (ts_info->so_timestamping) { + ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSINFO_TIMESTAMPING, + &ts_info->so_timestamping, NULL, + __SOF_TIMESTAMPING_CNT, + sof_timestamping_names, compact); + if (ret < 0) + return ret; + } + if (ts_info->tx_types) { + ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSINFO_TX_TYPES, + &ts_info->tx_types, NULL, + __HWTSTAMP_TX_CNT, + ts_tx_type_names, compact); + if (ret < 0) + return ret; + } + if (ts_info->rx_filters) { + ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSINFO_RX_FILTERS, + &ts_info->rx_filters, NULL, + __HWTSTAMP_FILTER_CNT, + ts_rx_filter_names, compact); + 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; + + return 0; +} + +const struct ethnl_request_ops ethnl_tsinfo_request_ops = { + .request_cmd = ETHTOOL_MSG_TSINFO_GET, + .reply_cmd = ETHTOOL_MSG_TSINFO_GET_REPLY, + .hdr_attr = ETHTOOL_A_TSINFO_HEADER, + .max_attr = ETHTOOL_A_TSINFO_MAX, + .req_info_size = sizeof(struct tsinfo_req_info), + .reply_data_size = sizeof(struct tsinfo_reply_data), + .request_policy = tsinfo_get_policy, + + .prepare_data = tsinfo_prepare_data, + .reply_size = tsinfo_reply_size, + .fill_reply = tsinfo_fill_reply, +}; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index c092e9a55790..818916b2a04d 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -35,7 +35,7 @@ static inline void fib_alias_accessed(struct fib_alias *fa) void fib_release_info(struct fib_info *); struct fib_info *fib_create_info(struct fib_config *cfg, struct netlink_ext_ack *extack); -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, +int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack); bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e4c62b8f57a8..6ed8c9317179 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -570,8 +570,9 @@ static int fib_detect_death(struct fib_info *fi, int order, return 1; } -int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *encap, - u16 encap_type, void *cfg, gfp_t gfp_flags, +int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, + struct nlattr *encap, u16 encap_type, + void *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { int err; @@ -589,8 +590,9 @@ int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *encap, err = -EINVAL; goto lwt_failure; } - err = lwtunnel_build_state(encap_type, encap, nhc->nhc_family, - cfg, &lwtstate, extack); + err = lwtunnel_build_state(net, encap_type, encap, + nhc->nhc_family, cfg, &lwtstate, + extack); if (err) goto lwt_failure; @@ -614,7 +616,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh, nh->fib_nh_family = AF_INET; - err = fib_nh_common_init(&nh->nh_common, cfg->fc_encap, + err = fib_nh_common_init(net, &nh->nh_common, cfg->fc_encap, cfg->fc_encap_type, cfg, GFP_KERNEL, extack); if (err) return err; @@ -814,7 +816,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, #endif /* CONFIG_IP_ROUTE_MULTIPATH */ -static int fib_encap_match(u16 encap_type, +static int fib_encap_match(struct net *net, u16 encap_type, struct nlattr *encap, const struct fib_nh *nh, const struct fib_config *cfg, @@ -826,7 +828,7 @@ static int fib_encap_match(u16 encap_type, if (encap_type == LWTUNNEL_ENCAP_NONE) return 0; - ret = lwtunnel_build_state(encap_type, encap, AF_INET, + ret = lwtunnel_build_state(net, encap_type, encap, AF_INET, cfg, &lwtstate, extack); if (!ret) { result = lwtunnel_cmp_encap(lwtstate, nh->fib_nh_lws); @@ -836,7 +838,7 @@ static int fib_encap_match(u16 encap_type, return result; } -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, +int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack) { #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -857,8 +859,8 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, struct fib_nh *nh = fib_info_nh(fi, 0); if (cfg->fc_encap) { - if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap, - nh, cfg, extack)) + if (fib_encap_match(net, cfg->fc_encap_type, + cfg->fc_encap, nh, cfg, extack)) return 1; } #ifdef CONFIG_IP_ROUTE_CLASSID diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index f4c2ac445b3f..b01b748df9dd 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1679,7 +1679,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && - fib_nh_match(cfg, fi, extack) == 0 && + fib_nh_match(net, cfg, fi, extack) == 0 && fib_metrics_match(cfg, fi)) { fa_to_delete = fa; break; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 47f8b947eef1..181b7a2a0247 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -432,7 +432,7 @@ static int ip_tun_set_opts(struct nlattr *attr, struct ip_tunnel_info *info, return ip_tun_parse_opts(attr, info, extack); } -static int ip_tun_build_state(struct nlattr *attr, +static int ip_tun_build_state(struct net *net, struct nlattr *attr, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) @@ -719,7 +719,7 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { [LWTUNNEL_IP6_OPTS] = { .type = NLA_NESTED }, }; -static int ip6_tun_build_state(struct nlattr *attr, +static int ip6_tun_build_state(struct net *net, struct nlattr *attr, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ae1344e4cec5..2ccaee98fddb 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -303,4 +303,14 @@ config IPV6_SEG6_BPF depends on IPV6_SEG6_LWTUNNEL depends on IPV6 = y +config IPV6_RPL_LWTUNNEL + bool "IPv6: RPL Source Routing Header support" + depends on IPV6 + select LWTUNNEL + ---help--- + Support for RFC6554 RPL Source Routing Header using the lightweight + tunnels mechanism. + + If unsure, say N. + endif # IPV6 diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 8ccf35514015..cf7b47bdb9b3 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -10,7 +10,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \ - udp_offload.o seg6.o fib6_notifier.o + udp_offload.o seg6.o fib6_notifier.o rpl.o ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o @@ -26,6 +26,7 @@ ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o ipv6-$(CONFIG_NETLABEL) += calipso.o ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o seg6_local.o ipv6-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o +ipv6-$(CONFIG_IPV6_RPL_LWTUNNEL) += rpl_iptunnel.o ipv6-objs += $(ipv6-y) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5b9de773ce73..a11fd4d67832 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -236,6 +236,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, + .rpl_seg_enabled = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -290,6 +291,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, + .rpl_seg_enabled = 0, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -4398,6 +4400,59 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) } #endif +/* RFC6554 has some algorithm to avoid loops in segment routing by + * checking if the segments contains any of a local interface address. + * + * Quote: + * + * To detect loops in the SRH, a router MUST determine if the SRH + * includes multiple addresses assigned to any interface on that router. + * If such addresses appear more than once and are separated by at least + * one address not assigned to that router. + */ +int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs, + unsigned char nsegs) +{ + const struct in6_addr *addr; + int i, ret = 0, found = 0; + struct inet6_ifaddr *ifp; + bool separated = false; + unsigned int hash; + bool hash_found; + + rcu_read_lock(); + for (i = 0; i < nsegs; i++) { + addr = &segs[i]; + hash = inet6_addr_hash(net, addr); + + hash_found = false; + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { + if (!net_eq(dev_net(ifp->idev->dev), net)) + continue; + + if (ipv6_addr_equal(&ifp->addr, addr)) { + hash_found = true; + break; + } + } + + if (hash_found) { + if (found > 1 && separated) { + ret = 1; + break; + } + + separated = false; + found++; + } else { + separated = true; + } + } + rcu_read_unlock(); + + return ret; +} + /* * Periodic address status verification */ @@ -5467,6 +5522,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass; + array[DEVCONF_RPL_SEG_ENABLED] = cnf->rpl_seg_enabled; } static inline size_t inet6_ifla6_size(void) @@ -6848,6 +6904,13 @@ static const struct ctl_table addrconf_sysctl[] = { .extra2 = (void *)&two_five_five, }, { + .procname = "rpl_seg_enabled", + .data = &ipv6_devconf.rpl_seg_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { /* sentinel */ } }; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d727c3b41495..345baa0a754f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -59,6 +59,7 @@ #endif #include <net/calipso.h> #include <net/seg6.h> +#include <net/rpl.h> #include <linux/uaccess.h> #include <linux/mroute6.h> @@ -1114,6 +1115,10 @@ static int __init inet6_init(void) if (err) goto seg6_fail; + err = rpl_init(); + if (err) + goto rpl_fail; + err = igmp6_late_init(); if (err) goto igmp6_late_err; @@ -1136,6 +1141,8 @@ sysctl_fail: igmp6_late_cleanup(); #endif igmp6_late_err: + rpl_exit(); +rpl_fail: seg6_exit(); seg6_fail: calipso_exit(); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index bcb9f5e62808..5a8bbcdcaf2b 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -48,6 +48,7 @@ #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif +#include <net/rpl.h> #include <linux/uaccess.h> @@ -468,6 +469,195 @@ looped_back: return -1; } +static int ipv6_rpl_srh_rcv(struct sk_buff *skb) +{ + struct ipv6_rpl_sr_hdr *hdr, *ohdr, *chdr; + struct inet6_skb_parm *opt = IP6CB(skb); + struct net *net = dev_net(skb->dev); + struct inet6_dev *idev; + struct ipv6hdr *oldhdr; + struct in6_addr addr; + unsigned char *buf; + int accept_rpl_seg; + int i, err; + u64 n = 0; + u32 r; + + idev = __in6_dev_get(skb->dev); + + accept_rpl_seg = net->ipv6.devconf_all->rpl_seg_enabled; + if (accept_rpl_seg > idev->cnf.rpl_seg_enabled) + accept_rpl_seg = idev->cnf.rpl_seg_enabled; + + if (!accept_rpl_seg) { + kfree_skb(skb); + return -1; + } + +looped_back: + hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); + + if (hdr->segments_left == 0) { + if (hdr->nexthdr == NEXTHDR_IPV6) { + int offset = (hdr->hdrlen + 1) << 3; + + skb_postpull_rcsum(skb, skb_network_header(skb), + skb_network_header_len(skb)); + + if (!pskb_pull(skb, offset)) { + kfree_skb(skb); + return -1; + } + skb_postpull_rcsum(skb, skb_transport_header(skb), + offset); + + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb->encapsulation = 0; + + __skb_tunnel_rx(skb, skb->dev, net); + + netif_rx(skb); + return -1; + } + + opt->srcrt = skb_network_header_len(skb); + opt->lastopt = opt->srcrt; + skb->transport_header += (hdr->hdrlen + 1) << 3; + opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); + + return 1; + } + + if (!pskb_may_pull(skb, sizeof(*hdr))) { + kfree_skb(skb); + return -1; + } + + n = (hdr->hdrlen << 3) - hdr->pad - (16 - hdr->cmpre); + r = do_div(n, (16 - hdr->cmpri)); + /* checks if calculation was without remainder and n fits into + * unsigned char which is segments_left field. Should not be + * higher than that. + */ + if (r || (n + 1) > 255) { + kfree_skb(skb); + return -1; + } + + if (hdr->segments_left > n + 1) { + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, + ((&hdr->segments_left) - + skb_network_header(skb))); + return -1; + } + + if (skb_cloned(skb)) { + if (pskb_expand_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE, 0, + GFP_ATOMIC)) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + return -1; + } + } else { + err = skb_cow_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE); + if (unlikely(err)) { + kfree_skb(skb); + return -1; + } + } + + hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); + + if (!pskb_may_pull(skb, ipv6_rpl_srh_size(n, hdr->cmpri, + hdr->cmpre))) { + kfree_skb(skb); + return -1; + } + + hdr->segments_left--; + i = n - hdr->segments_left; + + buf = kzalloc(ipv6_rpl_srh_alloc_size(n + 1) * 2, GFP_ATOMIC); + if (unlikely(!buf)) { + kfree_skb(skb); + return -1; + } + + ohdr = (struct ipv6_rpl_sr_hdr *)buf; + ipv6_rpl_srh_decompress(ohdr, hdr, &ipv6_hdr(skb)->daddr, n); + chdr = (struct ipv6_rpl_sr_hdr *)(buf + ((ohdr->hdrlen + 1) << 3)); + + if ((ipv6_addr_type(&ipv6_hdr(skb)->daddr) & IPV6_ADDR_MULTICAST) || + (ipv6_addr_type(&ohdr->rpl_segaddr[i]) & IPV6_ADDR_MULTICAST)) { + kfree_skb(skb); + kfree(buf); + return -1; + } + + err = ipv6_chk_rpl_srh_loop(net, ohdr->rpl_segaddr, n + 1); + if (err) { + icmpv6_send(skb, ICMPV6_PARAMPROB, 0, 0); + kfree_skb(skb); + kfree(buf); + return -1; + } + + addr = ipv6_hdr(skb)->daddr; + ipv6_hdr(skb)->daddr = ohdr->rpl_segaddr[i]; + ohdr->rpl_segaddr[i] = addr; + + ipv6_rpl_srh_compress(chdr, ohdr, &ipv6_hdr(skb)->daddr, n); + + oldhdr = ipv6_hdr(skb); + + skb_pull(skb, ((hdr->hdrlen + 1) << 3)); + skb_postpull_rcsum(skb, oldhdr, + sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); + skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + + memmove(ipv6_hdr(skb), oldhdr, sizeof(struct ipv6hdr)); + memcpy(skb_transport_header(skb), chdr, (chdr->hdrlen + 1) << 3); + + ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_postpush_rcsum(skb, ipv6_hdr(skb), + sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3)); + + kfree(buf); + + skb_dst_drop(skb); + + ip6_route_input(skb); + + if (skb_dst(skb)->error) { + dst_input(skb); + return -1; + } + + if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { + if (ipv6_hdr(skb)->hop_limit <= 1) { + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); + icmpv6_send(skb, ICMPV6_TIME_EXCEED, + ICMPV6_EXC_HOPLIMIT, 0); + kfree_skb(skb); + return -1; + } + ipv6_hdr(skb)->hop_limit--; + + skb_pull(skb, sizeof(struct ipv6hdr)); + goto looped_back; + } + + dst_input(skb); + + return -1; +} + /******************************** Routing header. ********************************/ @@ -506,9 +696,16 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) return -1; } - /* segment routing */ - if (hdr->type == IPV6_SRCRT_TYPE_4) + switch (hdr->type) { + case IPV6_SRCRT_TYPE_4: + /* segment routing */ return ipv6_srh_rcv(skb); + case IPV6_SRCRT_TYPE_3: + /* rpl segment routing */ + return ipv6_rpl_srh_rcv(skb); + default: + break; + } looped_back: if (hdr->segments_left == 0) { diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 422dcc691f71..8c1ce78956ba 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -125,7 +125,7 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_HOOK_TYPE] = { .type = NLA_U8, }, }; -static int ila_build_state(struct nlattr *nla, +static int ila_build_state(struct net *net, struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index afcde55d537c..310cbddaa533 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3471,7 +3471,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, !netif_carrier_ok(dev)) fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; - err = fib_nh_common_init(&fib6_nh->nh_common, cfg->fc_encap, + err = fib_nh_common_init(net, &fib6_nh->nh_common, cfg->fc_encap, cfg->fc_encap_type, cfg, gfp_flags, extack); if (err) goto out; diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c new file mode 100644 index 000000000000..dc4f20e23bf7 --- /dev/null +++ b/net/ipv6/rpl.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +/** + * Authors: + * (C) 2020 Alexander Aring <[email protected]> + */ + +#include <net/ipv6.h> +#include <net/rpl.h> + +#define IPV6_PFXTAIL_LEN(x) (sizeof(struct in6_addr) - (x)) + +static void ipv6_rpl_addr_decompress(struct in6_addr *dst, + const struct in6_addr *daddr, + const void *post, unsigned char pfx) +{ + memcpy(dst, daddr, pfx); + memcpy(&dst->s6_addr[pfx], post, IPV6_PFXTAIL_LEN(pfx)); +} + +static void ipv6_rpl_addr_compress(void *dst, const struct in6_addr *addr, + unsigned char pfx) +{ + memcpy(dst, &addr->s6_addr[pfx], IPV6_PFXTAIL_LEN(pfx)); +} + +static void *ipv6_rpl_segdata_pos(const struct ipv6_rpl_sr_hdr *hdr, int i) +{ + return (void *)&hdr->rpl_segdata[i * IPV6_PFXTAIL_LEN(hdr->cmpri)]; +} + +size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, + unsigned char cmpre) +{ + return (n * IPV6_PFXTAIL_LEN(cmpri)) + IPV6_PFXTAIL_LEN(cmpre); +} + +void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr, + const struct ipv6_rpl_sr_hdr *inhdr, + const struct in6_addr *daddr, unsigned char n) +{ + int i; + + outhdr->nexthdr = inhdr->nexthdr; + outhdr->hdrlen = (((n + 1) * sizeof(struct in6_addr)) >> 3); + outhdr->pad = 0; + outhdr->type = inhdr->type; + outhdr->segments_left = inhdr->segments_left; + outhdr->cmpri = 0; + outhdr->cmpre = 0; + + for (i = 0; i <= n; i++) + ipv6_rpl_addr_decompress(&outhdr->rpl_segaddr[i], daddr, + ipv6_rpl_segdata_pos(inhdr, i), + inhdr->cmpri); + + ipv6_rpl_addr_decompress(&outhdr->rpl_segaddr[n], daddr, + ipv6_rpl_segdata_pos(inhdr, n), + inhdr->cmpre); +} + +static unsigned char ipv6_rpl_srh_calc_cmpri(const struct ipv6_rpl_sr_hdr *inhdr, + const struct in6_addr *daddr, + unsigned char n) +{ + unsigned char plen; + int i; + + for (plen = 0; plen < sizeof(*daddr); plen++) { + for (i = 0; i <= n; i++) { + if (daddr->s6_addr[plen] != + inhdr->rpl_segaddr[i].s6_addr[plen]) + return plen; + } + } + + return plen; +} + +static unsigned char ipv6_rpl_srh_calc_cmpre(const struct in6_addr *daddr, + const struct in6_addr *last_segment) +{ + unsigned int plen; + + for (plen = 0; plen < sizeof(*daddr); plen++) { + if (daddr->s6_addr[plen] != last_segment->s6_addr[plen]) + break; + } + + return plen; +} + +void ipv6_rpl_srh_compress(struct ipv6_rpl_sr_hdr *outhdr, + const struct ipv6_rpl_sr_hdr *inhdr, + const struct in6_addr *daddr, unsigned char n) +{ + unsigned char cmpri, cmpre; + size_t seglen; + int i; + + cmpri = ipv6_rpl_srh_calc_cmpri(inhdr, daddr, n); + cmpre = ipv6_rpl_srh_calc_cmpre(daddr, &inhdr->rpl_segaddr[n]); + + outhdr->nexthdr = inhdr->nexthdr; + seglen = (n * IPV6_PFXTAIL_LEN(cmpri)) + IPV6_PFXTAIL_LEN(cmpre); + outhdr->hdrlen = seglen >> 3; + if (seglen & 0x7) { + outhdr->hdrlen++; + outhdr->pad = 8 - (seglen & 0x7); + } else { + outhdr->pad = 0; + } + outhdr->type = inhdr->type; + outhdr->segments_left = inhdr->segments_left; + outhdr->cmpri = cmpri; + outhdr->cmpre = cmpre; + + for (i = 0; i <= n; i++) + ipv6_rpl_addr_compress(ipv6_rpl_segdata_pos(outhdr, i), + &inhdr->rpl_segaddr[i], cmpri); + + ipv6_rpl_addr_compress(ipv6_rpl_segdata_pos(outhdr, n), + &inhdr->rpl_segaddr[n], cmpre); +} diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c new file mode 100644 index 000000000000..203037afe001 --- /dev/null +++ b/net/ipv6/rpl_iptunnel.c @@ -0,0 +1,380 @@ +// SPDX-License-Identifier: GPL-2.0-only +/** + * Authors: + * (C) 2020 Alexander Aring <[email protected]> + */ + +#include <linux/rpl_iptunnel.h> + +#include <net/dst_cache.h> +#include <net/ip6_route.h> +#include <net/lwtunnel.h> +#include <net/ipv6.h> +#include <net/rpl.h> + +struct rpl_iptunnel_encap { + struct ipv6_rpl_sr_hdr srh[0]; +}; + +struct rpl_lwt { + struct dst_cache cache; + struct rpl_iptunnel_encap tuninfo; +}; + +static inline struct rpl_lwt *rpl_lwt_lwtunnel(struct lwtunnel_state *lwt) +{ + return (struct rpl_lwt *)lwt->data; +} + +static inline struct rpl_iptunnel_encap * +rpl_encap_lwtunnel(struct lwtunnel_state *lwt) +{ + return &rpl_lwt_lwtunnel(lwt)->tuninfo; +} + +static const struct nla_policy rpl_iptunnel_policy[RPL_IPTUNNEL_MAX + 1] = { + [RPL_IPTUNNEL_SRH] = { .type = NLA_BINARY }, +}; + +static bool rpl_validate_srh(struct net *net, struct ipv6_rpl_sr_hdr *srh, + size_t seglen) +{ + int err; + + if ((srh->hdrlen << 3) != seglen) + return false; + + /* check at least one segment and seglen fit with segments_left */ + if (!srh->segments_left || + (srh->segments_left * sizeof(struct in6_addr)) != seglen) + return false; + + if (srh->cmpri || srh->cmpre) + return false; + + err = ipv6_chk_rpl_srh_loop(net, srh->rpl_segaddr, + srh->segments_left); + if (err) + return false; + + if (ipv6_addr_type(&srh->rpl_segaddr[srh->segments_left - 1]) & + IPV6_ADDR_MULTICAST) + return false; + + return true; +} + +static int rpl_build_state(struct net *net, struct nlattr *nla, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[RPL_IPTUNNEL_MAX + 1]; + struct lwtunnel_state *newts; + struct ipv6_rpl_sr_hdr *srh; + struct rpl_lwt *rlwt; + int err, srh_len; + + if (family != AF_INET6) + return -EINVAL; + + err = nla_parse_nested(tb, RPL_IPTUNNEL_MAX, nla, + rpl_iptunnel_policy, extack); + if (err < 0) + return err; + + if (!tb[RPL_IPTUNNEL_SRH]) + return -EINVAL; + + srh = nla_data(tb[RPL_IPTUNNEL_SRH]); + srh_len = nla_len(tb[RPL_IPTUNNEL_SRH]); + + if (srh_len < sizeof(*srh)) + return -EINVAL; + + /* verify that SRH is consistent */ + if (!rpl_validate_srh(net, srh, srh_len - sizeof(*srh))) + return -EINVAL; + + newts = lwtunnel_state_alloc(srh_len + sizeof(*rlwt)); + if (!newts) + return -ENOMEM; + + rlwt = rpl_lwt_lwtunnel(newts); + + err = dst_cache_init(&rlwt->cache, GFP_ATOMIC); + if (err) { + kfree(newts); + return err; + } + + memcpy(&rlwt->tuninfo.srh, srh, srh_len); + + newts->type = LWTUNNEL_ENCAP_RPL; + newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT; + newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + + *ts = newts; + + return 0; +} + +static void rpl_destroy_state(struct lwtunnel_state *lwt) +{ + dst_cache_destroy(&rpl_lwt_lwtunnel(lwt)->cache); +} + +static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, + const struct ipv6_rpl_sr_hdr *srh) +{ + struct ipv6_rpl_sr_hdr *isrh, *csrh; + const struct ipv6hdr *oldhdr; + struct ipv6hdr *hdr; + unsigned char *buf; + size_t hdrlen; + int err; + + oldhdr = ipv6_hdr(skb); + + buf = kzalloc(ipv6_rpl_srh_alloc_size(srh->segments_left - 1) * 2, + GFP_ATOMIC); + if (!buf) + return -ENOMEM; + + isrh = (struct ipv6_rpl_sr_hdr *)buf; + csrh = (struct ipv6_rpl_sr_hdr *)(buf + ((srh->hdrlen + 1) << 3)); + + memcpy(isrh, srh, sizeof(*isrh)); + memcpy(isrh->rpl_segaddr, &srh->rpl_segaddr[1], + (srh->segments_left - 1) * 16); + isrh->rpl_segaddr[srh->segments_left - 1] = oldhdr->daddr; + + ipv6_rpl_srh_compress(csrh, isrh, &srh->rpl_segaddr[0], + isrh->segments_left - 1); + + hdrlen = ((csrh->hdrlen + 1) << 3); + + err = skb_cow_head(skb, hdrlen + skb->mac_len); + if (unlikely(err)) + return err; + + skb_pull(skb, sizeof(struct ipv6hdr)); + skb_postpull_rcsum(skb, skb_network_header(skb), + sizeof(struct ipv6hdr)); + + skb_push(skb, sizeof(struct ipv6hdr) + hdrlen); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + + hdr = ipv6_hdr(skb); + memmove(hdr, oldhdr, sizeof(*hdr)); + isrh = (void *)hdr + sizeof(*hdr); + memcpy(isrh, csrh, hdrlen); + + isrh->nexthdr = hdr->nexthdr; + hdr->nexthdr = NEXTHDR_ROUTING; + hdr->daddr = srh->rpl_segaddr[0]; + + ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + + skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen); + + kfree(buf); + + return 0; +} + +static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt) +{ + struct dst_entry *dst = skb_dst(skb); + struct rpl_iptunnel_encap *tinfo; + int err = 0; + + if (skb->protocol != htons(ETH_P_IPV6)) + return -EINVAL; + + tinfo = rpl_encap_lwtunnel(dst->lwtstate); + + err = rpl_do_srh_inline(skb, rlwt, tinfo->srh); + if (err) + return err; + + return 0; +} + +static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct dst_entry *orig_dst = skb_dst(skb); + struct dst_entry *dst = NULL; + struct rpl_lwt *rlwt; + int err = -EINVAL; + + rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate); + + err = rpl_do_srh(skb, rlwt); + if (unlikely(err)) + goto drop; + + preempt_disable(); + dst = dst_cache_get(&rlwt->cache); + preempt_enable(); + + if (unlikely(!dst)) { + struct ipv6hdr *hdr = ipv6_hdr(skb); + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.daddr = hdr->daddr; + fl6.saddr = hdr->saddr; + fl6.flowlabel = ip6_flowinfo(hdr); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = hdr->nexthdr; + + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { + err = dst->error; + dst_release(dst); + goto drop; + } + + preempt_disable(); + dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr); + preempt_enable(); + } + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + if (unlikely(err)) + goto drop; + + return dst_output(net, sk, skb); + +drop: + kfree_skb(skb); + return err; +} + +static int rpl_input(struct sk_buff *skb) +{ + struct dst_entry *orig_dst = skb_dst(skb); + struct dst_entry *dst = NULL; + struct rpl_lwt *rlwt; + int err; + + rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate); + + err = rpl_do_srh(skb, rlwt); + if (unlikely(err)) { + kfree_skb(skb); + return err; + } + + preempt_disable(); + dst = dst_cache_get(&rlwt->cache); + preempt_enable(); + + skb_dst_drop(skb); + + if (!dst) { + ip6_route_input(skb); + dst = skb_dst(skb); + if (!dst->error) { + preempt_disable(); + dst_cache_set_ip6(&rlwt->cache, dst, + &ipv6_hdr(skb)->saddr); + preempt_enable(); + } + } else { + skb_dst_set(skb, dst); + } + + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + if (unlikely(err)) + return err; + + return dst_input(skb); +} + +static int nla_put_rpl_srh(struct sk_buff *skb, int attrtype, + struct rpl_iptunnel_encap *tuninfo) +{ + struct rpl_iptunnel_encap *data; + struct nlattr *nla; + int len; + + len = RPL_IPTUNNEL_SRH_SIZE(tuninfo->srh); + + nla = nla_reserve(skb, attrtype, len); + if (!nla) + return -EMSGSIZE; + + data = nla_data(nla); + memcpy(data, tuninfo->srh, len); + + return 0; +} + +static int rpl_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct rpl_iptunnel_encap *tuninfo = rpl_encap_lwtunnel(lwtstate); + + if (nla_put_rpl_srh(skb, RPL_IPTUNNEL_SRH, tuninfo)) + return -EMSGSIZE; + + return 0; +} + +static int rpl_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + struct rpl_iptunnel_encap *tuninfo = rpl_encap_lwtunnel(lwtstate); + + return nla_total_size(RPL_IPTUNNEL_SRH_SIZE(tuninfo->srh)); +} + +static int rpl_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + struct rpl_iptunnel_encap *a_hdr = rpl_encap_lwtunnel(a); + struct rpl_iptunnel_encap *b_hdr = rpl_encap_lwtunnel(b); + int len = RPL_IPTUNNEL_SRH_SIZE(a_hdr->srh); + + if (len != RPL_IPTUNNEL_SRH_SIZE(b_hdr->srh)) + return 1; + + return memcmp(a_hdr, b_hdr, len); +} + +static const struct lwtunnel_encap_ops rpl_ops = { + .build_state = rpl_build_state, + .destroy_state = rpl_destroy_state, + .output = rpl_output, + .input = rpl_input, + .fill_encap = rpl_fill_encap_info, + .get_encap_size = rpl_encap_nlsize, + .cmp_encap = rpl_encap_cmp, + .owner = THIS_MODULE, +}; + +int __init rpl_init(void) +{ + int err; + + err = lwtunnel_encap_add_ops(&rpl_ops, LWTUNNEL_ENCAP_RPL); + if (err) + goto out; + + pr_info("RPL Segment Routing with IPv6\n"); + + return 0; + +out: + return err; +} + +void rpl_exit(void) +{ + lwtunnel_encap_del_ops(&rpl_ops, LWTUNNEL_ENCAP_RPL); +} diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index ac837afb9040..c7cbfeae94f5 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -376,7 +376,7 @@ drop: return err; } -static int seg6_build_state(struct nlattr *nla, +static int seg6_build_state(struct net *net, struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 8165802d8e05..52493423f329 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -970,8 +970,9 @@ static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt) return 0; } -static int seg6_local_build_state(struct nlattr *nla, unsigned int family, - const void *cfg, struct lwtunnel_state **ts, +static int seg6_local_build_state(struct net *net, struct nlattr *nla, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts, struct netlink_ext_ack *extack) { struct nlattr *tb[SEG6_LOCAL_MAX + 1]; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 44b675016393..2def85718d94 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -162,7 +162,7 @@ drop: return -EINVAL; } -static int mpls_build_state(struct nlattr *nla, +static int mpls_build_state(struct net *net, struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) |